1 Commits

Author SHA1 Message Date
Mondo Diaz
832e4b27a8 Add teams migration to runtime migrations
Add teams table, team_memberships table, and team_id column to projects
in the runtime migrations. This fixes startup failures on existing databases
that don't have the teams schema from the migration file.
2026-01-28 20:25:57 +00:00
79 changed files with 4349 additions and 15137 deletions

View File

@@ -11,6 +11,13 @@ variables:
# Environment URLs (used by deploy and test jobs)
STAGE_URL: https://orchard-stage.common.global.bsf.tools
PROD_URL: https://orchard.common.global.bsf.tools
# Stage environment AWS resources (used by reset job)
STAGE_RDS_HOST: orchard-stage.cluster-cvw3jzjkozoc.us-gov-west-1.rds.amazonaws.com
STAGE_RDS_DBNAME: postgres
STAGE_SECRET_ARN: "arn:aws-us-gov:secretsmanager:us-gov-west-1:052673043337:secret:rds!cluster-a573672b-1a38-4665-a654-1b7df37b5297-IaeFQL"
STAGE_AUTH_SECRET_ARN: "arn:aws-us-gov:secretsmanager:us-gov-west-1:052673043337:secret:orchard-stage-creds-SMqvQx"
STAGE_S3_BUCKET: orchard-artifacts-stage
AWS_REGION: us-gov-west-1
# Shared pip cache directory
PIP_CACHE_DIR: "$CI_PROJECT_DIR/.pip-cache"
@@ -88,18 +95,10 @@ cve_sbom_analysis:
when: never
- when: on_success
# Disable prosper_setup for tag pipelines since no build/analysis jobs run
# (image is already built when commit was on main, and deploy uses helm directly)
prosper_setup:
rules:
- if: '$CI_COMMIT_TAG'
when: never
- when: on_success
# Override release job to wait for stage deployment and smoke tests before creating tag
# Override release job to wait for stage integration tests before creating tag
# This ensures the tag (which triggers prod deploy) is only created after stage passes
release:
needs: [smoke_test_stage, changelog]
needs: [integration_test_stage, changelog]
# Full integration test suite template (for feature/stage deployments)
# Runs the complete pytest integration test suite against the deployed environment
@@ -201,6 +200,108 @@ release:
sys.exit(0)
PYTEST_SCRIPT
# Reset stage template - runs from CI runner, uses CI variable for auth
# Calls the /api/v1/admin/factory-reset endpoint which handles DB and S3 cleanup
.reset_stage_template: &reset_stage_template
stage: deploy
image: deps.global.bsf.tools/docker/python:3.12-slim
timeout: 5m
retry: 1
before_script:
- pip install --index-url "$PIP_INDEX_URL" httpx
script:
- |
python - <<'RESET_SCRIPT'
import httpx
import sys
import os
import time
BASE_URL = os.environ.get("STAGE_URL", "")
ADMIN_USER = "admin"
ADMIN_PASS = os.environ.get("STAGE_ADMIN_PASSWORD", "")
MAX_RETRIES = 3
RETRY_DELAY = 5
if not BASE_URL:
print("ERROR: STAGE_URL not set")
sys.exit(1)
if not ADMIN_PASS:
print("ERROR: STAGE_ADMIN_PASSWORD not set")
sys.exit(1)
print(f"=== Resetting stage environment at {BASE_URL} ===")
def do_reset():
with httpx.Client(base_url=BASE_URL, timeout=120.0) as client:
print("Logging in as admin...")
login_response = client.post(
"/api/v1/auth/login",
json={"username": ADMIN_USER, "password": ADMIN_PASS},
)
if login_response.status_code != 200:
raise Exception(f"Login failed: {login_response.status_code} - {login_response.text}")
print("Login successful")
print("Calling factory reset endpoint...")
reset_response = client.post(
"/api/v1/admin/factory-reset",
headers={"X-Confirm-Reset": "yes-delete-all-data"},
)
if reset_response.status_code == 200:
result = reset_response.json()
print("Factory reset successful!")
print(f" Database tables dropped: {result['results']['database_tables_dropped']}")
print(f" S3 objects deleted: {result['results']['s3_objects_deleted']}")
print(f" Database reinitialized: {result['results']['database_reinitialized']}")
print(f" Seeded: {result['results']['seeded']}")
return True
else:
raise Exception(f"Factory reset failed: {reset_response.status_code} - {reset_response.text}")
for attempt in range(1, MAX_RETRIES + 1):
try:
print(f"Attempt {attempt}/{MAX_RETRIES}")
if do_reset():
sys.exit(0)
except Exception as e:
print(f"Attempt {attempt} failed: {e}")
if attempt < MAX_RETRIES:
print(f"Retrying in {RETRY_DELAY} seconds...")
time.sleep(RETRY_DELAY)
else:
print("All retry attempts failed")
sys.exit(1)
RESET_SCRIPT
rules:
- if: '$CI_COMMIT_BRANCH == "main"'
when: on_success
# Reset stage BEFORE integration tests (ensure known state)
reset_stage_pre:
<<: *reset_stage_template
needs: [deploy_stage]
# Integration tests for stage deployment
# Uses CI variable STAGE_ADMIN_PASSWORD (set in GitLab CI/CD settings)
integration_test_stage:
<<: *integration_test_template
needs: [reset_stage_pre]
variables:
ORCHARD_TEST_URL: $STAGE_URL
ORCHARD_TEST_PASSWORD: $STAGE_ADMIN_PASSWORD
rules:
- if: '$CI_COMMIT_BRANCH == "main"'
when: on_success
# Reset stage AFTER integration tests (clean slate for next run)
reset_stage:
<<: *reset_stage_template
needs: [integration_test_stage]
allow_failure: true # Don't fail pipeline if reset has issues
# Integration tests for feature deployment (full suite)
# Uses DEV_ADMIN_PASSWORD CI variable (same as deploy_feature)
integration_test_feature:
@@ -213,74 +314,6 @@ integration_test_feature:
- if: '$CI_COMMIT_BRANCH && $CI_COMMIT_BRANCH != "main"'
when: on_success
# Reset feature environment after integration tests
# Calls factory-reset to clean up test data created during integration tests
reset_feature:
stage: deploy
needs: [integration_test_feature]
image: deps.global.bsf.tools/docker/python:3.12-slim
timeout: 5m
before_script:
- pip install --index-url "$PIP_INDEX_URL" httpx
script:
# Debug: Check if variable is set at shell level
- echo "RESET_ADMIN_PASSWORD length at shell level:${#RESET_ADMIN_PASSWORD}"
- |
python - <<'RESET_SCRIPT'
import httpx
import os
import sys
BASE_URL = f"https://orchard-{os.environ['CI_COMMIT_REF_SLUG']}.common.global.bsf.tools"
PASSWORD_RAW = os.environ.get("RESET_ADMIN_PASSWORD")
if not PASSWORD_RAW:
print("ERROR: RESET_ADMIN_PASSWORD not set")
sys.exit(1)
# Debug: check for hidden characters
print(f"Raw password repr (first 3 chars): {repr(PASSWORD_RAW[:3])}")
print(f"Raw password repr (last 3 chars): {repr(PASSWORD_RAW[-3:])}")
print(f"Raw length: {len(PASSWORD_RAW)}")
# Strip any whitespace
PASSWORD = PASSWORD_RAW.strip()
print(f"Stripped length: {len(PASSWORD)}")
print(f"Resetting environment at {BASE_URL}")
client = httpx.Client(base_url=BASE_URL, timeout=60.0)
# Login as admin
login_resp = client.post("/api/v1/auth/login", json={
"username": "admin",
"password": PASSWORD
})
if login_resp.status_code != 200:
print(f"ERROR: Login failed: {login_resp.status_code}")
print(f"Response: {login_resp.text}")
sys.exit(1)
# Call factory reset
reset_resp = client.post(
"/api/v1/admin/factory-reset",
headers={"X-Confirm-Reset": "yes-delete-all-data"}
)
if reset_resp.status_code == 200:
print("SUCCESS: Factory reset completed")
print(reset_resp.json())
else:
print(f"ERROR: Factory reset failed: {reset_resp.status_code}")
print(reset_resp.text)
sys.exit(1)
RESET_SCRIPT
variables:
# Use same pattern as integration_test_feature - create new variable from CI variable
RESET_ADMIN_PASSWORD: $DEV_ADMIN_PASSWORD
rules:
- if: '$CI_COMMIT_BRANCH && $CI_COMMIT_BRANCH != "main"'
when: on_success
allow_failure: true # Don't fail the pipeline if reset fails
# Run Python backend unit tests
python_unit_tests:
stage: test
@@ -379,88 +412,9 @@ frontend_tests:
echo "Health check failed after 30 attempts"
exit 1
# Ephemeral test deployment in stage namespace (main branch only)
# Runs integration tests before promoting to long-running stage
deploy_test:
<<: *deploy_template
variables:
NAMESPACE: orch-stage-namespace
VALUES_FILE: helm/orchard/values-dev.yaml
BASE_URL: https://orchard-test.common.global.bsf.tools
before_script:
- kubectl config use-context esv/bsf/bsf-integration/orchard/orchard-mvp:orchard-stage
- *helm_setup
script:
- echo "Deploying ephemeral test environment"
- cd $CI_PROJECT_DIR
- |
helm upgrade --install orchard-test ./helm/orchard \
--namespace $NAMESPACE \
-f $VALUES_FILE \
--set image.tag=git.linux-amd64-$CI_COMMIT_SHA \
--set orchard.auth.adminPassword=$STAGE_ADMIN_PASSWORD \
--set ingress.hosts[0].host=orchard-test.common.global.bsf.tools \
--set ingress.tls[0].hosts[0]=orchard-test.common.global.bsf.tools \
--set ingress.tls[0].secretName=orchard-test-tls \
--set minioIngress.host=minio-test.common.global.bsf.tools \
--set minioIngress.tls.secretName=minio-test-tls \
--wait \
--atomic \
--timeout 10m
- kubectl rollout status deployment/orchard-test-server -n $NAMESPACE --timeout=10m
- *verify_deployment
environment:
name: test
url: https://orchard-test.common.global.bsf.tools
on_stop: cleanup_test
kubernetes:
agent: esv/bsf/bsf-integration/orchard/orchard-mvp:orchard-stage
rules:
- if: '$CI_COMMIT_BRANCH == "main"'
when: on_success
# Integration tests for ephemeral test deployment (main branch)
# Runs against orchard-test before promoting to long-running stage
integration_test_main:
<<: *integration_test_template
needs: [deploy_test]
variables:
ORCHARD_TEST_URL: https://orchard-test.common.global.bsf.tools
ORCHARD_TEST_PASSWORD: $STAGE_ADMIN_PASSWORD
rules:
- if: '$CI_COMMIT_BRANCH == "main"'
when: on_success
# Cleanup ephemeral test deployment after integration tests
cleanup_test:
stage: deploy
needs: [integration_test_main]
image: deps.global.bsf.tools/registry-1.docker.io/alpine/k8s:1.29.12
timeout: 5m
variables:
NAMESPACE: orch-stage-namespace
GIT_STRATEGY: none
before_script:
- kubectl config use-context esv/bsf/bsf-integration/orchard/orchard-mvp:orchard-stage
script:
- echo "Cleaning up ephemeral test deployment orchard-test"
- helm uninstall orchard-test --namespace $NAMESPACE || true
environment:
name: test
action: stop
kubernetes:
agent: esv/bsf/bsf-integration/orchard/orchard-mvp:orchard-stage
rules:
- if: '$CI_COMMIT_BRANCH == "main"'
when: on_success
allow_failure: true
# Deploy to long-running stage (main branch, after ephemeral tests pass)
# Deploy to stage (main branch)
deploy_stage:
stage: deploy
# Wait for ephemeral test to pass before promoting to long-running stage
needs: [cleanup_test]
image: deps.global.bsf.tools/registry-1.docker.io/alpine/k8s:1.29.12
<<: *deploy_template
variables:
NAMESPACE: orch-stage-namespace
VALUES_FILE: helm/orchard/values-stage.yaml
@@ -469,7 +423,7 @@ deploy_stage:
- kubectl config use-context esv/bsf/bsf-integration/orchard/orchard-mvp:orchard-stage
- *helm_setup
script:
- echo "Deploying to long-running stage environment"
- echo "Deploying to stage environment"
- cd $CI_PROJECT_DIR
- |
helm upgrade --install orchard-stage ./helm/orchard \
@@ -491,16 +445,6 @@ deploy_stage:
- if: '$CI_COMMIT_BRANCH == "main"'
when: on_success
# Smoke test for long-running stage (after promotion)
smoke_test_stage:
<<: *smoke_test_template
needs: [deploy_stage]
variables:
ORCHARD_TEST_URL: $STAGE_URL
rules:
- if: '$CI_COMMIT_BRANCH == "main"'
when: on_success
# Deploy feature branch to dev namespace
deploy_feature:
<<: *deploy_template

View File

@@ -7,136 +7,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
### Added
- Added HTTP connection pooling infrastructure for improved PyPI proxy performance
- `HttpClientManager` with configurable pool size, timeouts, and thread pool executor
- Eliminates per-request connection overhead (~100-500ms → ~5ms)
- Added Redis caching layer with category-aware TTL for hermetic builds
- `CacheService` with graceful fallback when Redis unavailable
- Immutable data (artifact metadata, dependencies) cached forever
- Mutable data (package index, versions) uses configurable TTL
- Added `ArtifactRepository` for batch database operations
- `batch_upsert_dependencies()` reduces N+1 queries to single INSERT
- `get_or_create_artifact()` uses atomic ON CONFLICT upsert
- Added infrastructure status to health endpoint (`/health`)
- Reports HTTP pool size and worker threads
- Reports Redis cache connection status
- Added new configuration settings for HTTP client, Redis, and cache TTL
- `ORCHARD_HTTP_MAX_CONNECTIONS`, `ORCHARD_HTTP_CONNECT_TIMEOUT`, etc.
- `ORCHARD_REDIS_HOST`, `ORCHARD_REDIS_PORT`, `ORCHARD_REDIS_ENABLED`
- `ORCHARD_CACHE_TTL_INDEX`, `ORCHARD_CACHE_TTL_VERSIONS`, etc.
- Added transparent PyPI proxy implementing PEP 503 Simple API (#108)
- `GET /pypi/simple/` - package index (proxied from upstream)
- `GET /pypi/simple/{package}/` - version list with rewritten download links
- `GET /pypi/simple/{package}/{filename}` - download with automatic caching
- Allows `pip install --index-url https://orchard.../pypi/simple/ <package>`
- Artifacts cached on first access through configured upstream sources
- Added `POST /api/v1/cache/resolve` endpoint to cache packages by coordinates instead of URL (#108)
### Changed
- PyPI proxy now uses shared HTTP connection pool instead of per-request clients
- PyPI proxy now caches upstream source configuration in Redis
- Dependency storage now uses batch INSERT instead of individual queries
- Increased default database pool size from 5 to 20 connections
- Increased default database max overflow from 10 to 30 connections
- Enabled Redis in Helm chart values for dev, stage, and prod environments
- Upstream sources table text is now centered under column headers (#108)
- ENV badge now appears inline with source name instead of separate column (#108)
- Test and Edit buttons now have more prominent button styling (#108)
- Reduced footer padding for cleaner layout (#108)
### Fixed
- Fixed purge_seed_data crash when deleting access permissions - was comparing UUID to VARCHAR column (#107)
### Changed
- Upstream source connectivity test no longer follows redirects, fixing "Exceeded maximum allowed redirects" error with Artifactory proxies (#107)
- Test runs automatically after saving a new or updated upstream source (#107)
- Test status now shows as colored dots (green=success, red=error) instead of text badges (#107)
- Clicking red dot shows error details in a modal (#107)
- Source name column no longer wraps text for better table layout (#107)
- Renamed "Cache Management" page to "Upstream Sources" (#107)
- Moved Delete button from table row to edit modal for cleaner table layout (#107)
### Removed
- Removed `is_public` field from upstream sources - all sources are now treated as internal/private (#107)
- Removed `allow_public_internet` (air-gap mode) setting from cache settings - not needed for enterprise proxy use case (#107)
- Removed seeding of public registry URLs (npm-public, pypi-public, maven-central, docker-hub) (#107)
- Removed "Public" badge and checkbox from upstream sources UI (#107)
- Removed "Allow Public Internet" toggle from cache settings UI (#107)
- Removed "Global Settings" section from cache management UI - auto-create system projects is always enabled (#107)
- Removed unused CacheSettings frontend types and API functions (#107)
### Added
- Added `ORCHARD_PURGE_SEED_DATA` environment variable support to stage helm values to remove seed data from long-running deployments (#107)
- Added frontend system projects visual distinction (#105)
- "Cache" badge for system projects in project list
- "System Cache" badge on project detail page
- Added `is_system` field to Project type
- Added frontend admin page for upstream sources and cache settings (#75)
- New `/admin/cache` page accessible from user menu (admin only)
- Upstream sources table with create/edit/delete/test connectivity
- Cache settings section with air-gap mode and auto-create system projects toggles
- Visual indicators for env-defined sources (locked, cannot be modified)
- Environment variable override badges when settings are overridden
- API client functions for all cache admin operations
- Added environment variable overrides for cache configuration (#74)
- `ORCHARD_CACHE_ALLOW_PUBLIC_INTERNET` - Override allow_public_internet (air-gap mode)
- `ORCHARD_CACHE_AUTO_CREATE_SYSTEM_PROJECTS` - Override auto_create_system_projects
- `ORCHARD_UPSTREAM__{NAME}__*` - Define upstream sources via env vars
- Env-defined sources appear in API with `source: "env"` marker
- Env-defined sources cannot be modified/deleted via API (400 error)
- Cache settings response includes `*_env_override` fields when overridden
- 7 unit tests for env var parsing and configuration
- Added Global Cache Settings Admin API (#73)
- `GET /api/v1/admin/cache-settings` - Retrieve current cache settings
- `PUT /api/v1/admin/cache-settings` - Update cache settings (partial updates)
- Admin-only access with audit logging
- Controls `allow_public_internet` (air-gap mode) and `auto_create_system_projects`
- 7 integration tests for settings management
- Added Upstream Sources Admin API for managing cache sources (#72)
- `GET /api/v1/admin/upstream-sources` - List sources with filtering
- `POST /api/v1/admin/upstream-sources` - Create source with auth configuration
- `GET /api/v1/admin/upstream-sources/{id}` - Get source details
- `PUT /api/v1/admin/upstream-sources/{id}` - Update source (partial updates)
- `DELETE /api/v1/admin/upstream-sources/{id}` - Delete source
- `POST /api/v1/admin/upstream-sources/{id}/test` - Test connectivity
- Admin-only access with audit logging
- Credentials never exposed (only has_password/has_headers flags)
- 13 integration tests for all CRUD operations
- Added system project restrictions and management (#71)
- System projects (`_npm`, `_pypi`, etc.) cannot be deleted (returns 403)
- System projects cannot be made private (must remain public)
- `GET /api/v1/system-projects` endpoint to list all system cache projects
- 5 integration tests for system project restrictions
- Added Cache API endpoint for fetching and storing artifacts from upstream URLs (#70)
- `POST /api/v1/cache` endpoint to cache artifacts from upstream registries
- URL parsing helpers to extract package name/version from npm, PyPI, Maven URLs
- Automatic system project creation (`_npm`, `_pypi`, `_maven`, etc.)
- URL-to-artifact provenance tracking via `cached_urls` table
- Optional user project cross-referencing for custom organization
- Cache hit returns existing artifact without re-fetching
- Air-gap mode enforcement (blocks public URLs when disabled)
- Hash verification for downloaded artifacts
- 21 unit tests for URL parsing and cache endpoint
- Added HTTP client for fetching artifacts from upstream sources (#69)
- `UpstreamClient` class in `backend/app/upstream.py` with streaming downloads
- SHA256 hash computation while streaming (doesn't load large files into memory)
- Auth support: none, basic auth, bearer token, API key (custom headers)
- URL-to-source matching by URL prefix with priority ordering
- Configuration options: timeouts, retries with exponential backoff, redirect limits, max file size
- Air-gap mode enforcement via `allow_public_internet` setting
- Response header capture for provenance tracking
- Proper error handling with custom exception types
- Connection test method for upstream source validation
- 33 unit tests for client functionality
- Added upstream artifact caching schema for hermetic builds (#68)
- `upstream_sources` table for configuring upstream registries (npm, PyPI, Maven, etc.)
- `cache_settings` table for global settings including air-gap mode
- `cached_urls` table for URL-to-artifact provenance tracking
- `is_system` column on projects for system cache projects (_npm, _pypi, etc.)
- Support for multiple auth types: none, basic auth, bearer token, API key
- Fernet encryption for credentials using `ORCHARD_CACHE_ENCRYPTION_KEY`
- Default upstream sources seeded (npm-public, pypi-public, maven-central, docker-hub) - disabled by default
- Migration `010_upstream_caching.sql`
- Added team-based multi-tenancy for organizing projects and collaboration (#88-#104)
- Teams serve as organizational containers for projects
- Users can belong to multiple teams with different roles (owner, admin, member)

View File

@@ -1,316 +0,0 @@
"""
Cache service for upstream artifact caching.
Provides URL parsing, system project management, and caching logic
for the upstream caching feature.
"""
import logging
import re
from dataclasses import dataclass
from typing import Optional
from urllib.parse import urlparse, unquote
logger = logging.getLogger(__name__)
# System project names for each source type
SYSTEM_PROJECT_NAMES = {
"npm": "_npm",
"pypi": "_pypi",
"maven": "_maven",
"docker": "_docker",
"helm": "_helm",
"nuget": "_nuget",
"deb": "_deb",
"rpm": "_rpm",
"generic": "_generic",
}
# System project descriptions
SYSTEM_PROJECT_DESCRIPTIONS = {
"npm": "System cache for npm packages",
"pypi": "System cache for PyPI packages",
"maven": "System cache for Maven packages",
"docker": "System cache for Docker images",
"helm": "System cache for Helm charts",
"nuget": "System cache for NuGet packages",
"deb": "System cache for Debian packages",
"rpm": "System cache for RPM packages",
"generic": "System cache for generic artifacts",
}
@dataclass
class ParsedUrl:
"""Parsed URL information for caching."""
package_name: str
version: Optional[str] = None
filename: Optional[str] = None
def parse_npm_url(url: str) -> Optional[ParsedUrl]:
"""
Parse npm registry URL to extract package name and version.
Formats:
- https://registry.npmjs.org/{package}/-/{package}-{version}.tgz
- https://registry.npmjs.org/@{scope}/{package}/-/{package}-{version}.tgz
Examples:
- https://registry.npmjs.org/lodash/-/lodash-4.17.21.tgz
- https://registry.npmjs.org/@types/node/-/node-18.0.0.tgz
"""
parsed = urlparse(url)
path = unquote(parsed.path)
# Pattern for scoped packages: /@scope/package/-/package-version.tgz
scoped_pattern = r"^/@([^/]+)/([^/]+)/-/\2-(.+)\.tgz$"
match = re.match(scoped_pattern, path)
if match:
scope, name, version = match.groups()
return ParsedUrl(
package_name=f"@{scope}/{name}",
version=version,
filename=f"{name}-{version}.tgz",
)
# Pattern for unscoped packages: /package/-/package-version.tgz
unscoped_pattern = r"^/([^/@]+)/-/\1-(.+)\.tgz$"
match = re.match(unscoped_pattern, path)
if match:
name, version = match.groups()
return ParsedUrl(
package_name=name,
version=version,
filename=f"{name}-{version}.tgz",
)
return None
def parse_pypi_url(url: str) -> Optional[ParsedUrl]:
"""
Parse PyPI URL to extract package name and version.
Formats:
- https://files.pythonhosted.org/packages/.../package-version.tar.gz
- https://files.pythonhosted.org/packages/.../package-version-py3-none-any.whl
- https://pypi.org/packages/.../package-version.tar.gz
Examples:
- https://files.pythonhosted.org/packages/ab/cd/requests-2.28.0.tar.gz
- https://files.pythonhosted.org/packages/ab/cd/requests-2.28.0-py3-none-any.whl
"""
parsed = urlparse(url)
path = unquote(parsed.path)
# Get the filename from the path
filename = path.split("/")[-1]
if not filename:
return None
# Handle wheel files: package-version-py3-none-any.whl
wheel_pattern = r"^([a-zA-Z0-9_-]+)-(\d+[^-]*)-.*\.whl$"
match = re.match(wheel_pattern, filename)
if match:
name, version = match.groups()
# Normalize package name (PyPI uses underscores internally)
name = name.replace("_", "-").lower()
return ParsedUrl(
package_name=name,
version=version,
filename=filename,
)
# Handle source distributions: package-version.tar.gz or package-version.zip
sdist_pattern = r"^([a-zA-Z0-9_-]+)-(\d+(?:\.\d+)*(?:[a-zA-Z0-9_.+-]*)?)(?:\.tar\.gz|\.zip|\.tar\.bz2)$"
match = re.match(sdist_pattern, filename)
if match:
name, version = match.groups()
name = name.replace("_", "-").lower()
return ParsedUrl(
package_name=name,
version=version,
filename=filename,
)
return None
def parse_maven_url(url: str) -> Optional[ParsedUrl]:
"""
Parse Maven repository URL to extract artifact info.
Format:
- https://repo1.maven.org/maven2/{group}/{artifact}/{version}/{artifact}-{version}.jar
Examples:
- https://repo1.maven.org/maven2/org/apache/commons/commons-lang3/3.12.0/commons-lang3-3.12.0.jar
- https://repo1.maven.org/maven2/com/google/guava/guava/31.1-jre/guava-31.1-jre.jar
"""
parsed = urlparse(url)
path = unquote(parsed.path)
# Find /maven2/ or similar repository path
maven2_idx = path.find("/maven2/")
if maven2_idx >= 0:
path = path[maven2_idx + 8:] # Remove /maven2/
elif path.startswith("/"):
path = path[1:]
parts = path.split("/")
if len(parts) < 4:
return None
# Last part is filename, before that is version, before that is artifact
filename = parts[-1]
version = parts[-2]
artifact = parts[-3]
group = ".".join(parts[:-3])
# Verify filename matches expected pattern
if not filename.startswith(f"{artifact}-{version}"):
return None
return ParsedUrl(
package_name=f"{group}:{artifact}",
version=version,
filename=filename,
)
def parse_docker_url(url: str) -> Optional[ParsedUrl]:
"""
Parse Docker registry URL to extract image info.
Note: Docker registries are more complex (manifests, blobs, etc.)
This handles basic blob/manifest URLs.
Examples:
- https://registry-1.docker.io/v2/library/nginx/blobs/sha256:abc123
- https://registry-1.docker.io/v2/myuser/myimage/manifests/latest
"""
parsed = urlparse(url)
path = unquote(parsed.path)
# Pattern: /v2/{namespace}/{image}/blobs/{digest} or /manifests/{tag}
pattern = r"^/v2/([^/]+(?:/[^/]+)?)/([^/]+)/(blobs|manifests)/(.+)$"
match = re.match(pattern, path)
if match:
namespace, image, artifact_type, reference = match.groups()
if namespace == "library":
package_name = image
else:
package_name = f"{namespace}/{image}"
# For manifests, the reference is the tag
version = reference if artifact_type == "manifests" else None
return ParsedUrl(
package_name=package_name,
version=version,
filename=f"{image}-{reference}" if version else reference,
)
return None
def parse_generic_url(url: str) -> ParsedUrl:
"""
Parse a generic URL to extract filename.
Attempts to extract meaningful package name and version from filename.
Examples:
- https://example.com/downloads/myapp-1.2.3.tar.gz
- https://github.com/user/repo/releases/download/v1.0/release.zip
"""
parsed = urlparse(url)
path = unquote(parsed.path)
filename = path.split("/")[-1] or "artifact"
# List of known compound and simple extensions
known_extensions = [
".tar.gz", ".tar.bz2", ".tar.xz",
".zip", ".tgz", ".gz", ".jar", ".war", ".deb", ".rpm"
]
# Strip extension from filename first
base_name = filename
matched_ext = None
for ext in known_extensions:
if filename.endswith(ext):
base_name = filename[:-len(ext)]
matched_ext = ext
break
if matched_ext is None:
# Unknown extension, return filename as package name
return ParsedUrl(
package_name=filename,
version=None,
filename=filename,
)
# Try to extract version from base_name
# Pattern: name-version or name_version
# Version starts with digit(s) and can include dots, dashes, and alphanumeric suffixes
version_pattern = r"^(.+?)[-_](v?\d+(?:\.\d+)*(?:[-_][a-zA-Z0-9]+)?)$"
match = re.match(version_pattern, base_name)
if match:
name, version = match.groups()
return ParsedUrl(
package_name=name,
version=version,
filename=filename,
)
# No version found, use base_name as package name
return ParsedUrl(
package_name=base_name,
version=None,
filename=filename,
)
def parse_url(url: str, source_type: str) -> ParsedUrl:
"""
Parse URL to extract package name and version based on source type.
Args:
url: The URL to parse.
source_type: The source type (npm, pypi, maven, docker, etc.)
Returns:
ParsedUrl with extracted information.
"""
parsed = None
if source_type == "npm":
parsed = parse_npm_url(url)
elif source_type == "pypi":
parsed = parse_pypi_url(url)
elif source_type == "maven":
parsed = parse_maven_url(url)
elif source_type == "docker":
parsed = parse_docker_url(url)
# Fall back to generic parsing if type-specific parsing fails
if parsed is None:
parsed = parse_generic_url(url)
return parsed
def get_system_project_name(source_type: str) -> str:
"""Get the system project name for a source type."""
return SYSTEM_PROJECT_NAMES.get(source_type, "_generic")
def get_system_project_description(source_type: str) -> str:
"""Get the system project description for a source type."""
return SYSTEM_PROJECT_DESCRIPTIONS.get(
source_type, "System cache for artifacts"
)

View File

@@ -1,262 +0,0 @@
"""
Redis-backed caching service with category-aware TTL and invalidation.
Provides:
- Immutable caching for artifact data (hermetic builds)
- TTL-based caching for discovery data
- Event-driven invalidation for config changes
- Graceful fallback when Redis unavailable
"""
import logging
from enum import Enum
from typing import Optional
from .config import Settings
logger = logging.getLogger(__name__)
class CacheCategory(Enum):
"""
Cache categories with different TTL and invalidation rules.
Immutable (cache forever):
- ARTIFACT_METADATA: Artifact info by SHA256
- ARTIFACT_DEPENDENCIES: Extracted deps by SHA256
- DEPENDENCY_RESOLUTION: Resolution results by input hash
Mutable (TTL + event invalidation):
- UPSTREAM_SOURCES: Upstream config, invalidate on DB change
- PACKAGE_INDEX: PyPI/npm index pages, TTL only
- PACKAGE_VERSIONS: Version listings, TTL only
"""
# Immutable - cache forever (hermetic builds)
ARTIFACT_METADATA = "artifact"
ARTIFACT_DEPENDENCIES = "deps"
DEPENDENCY_RESOLUTION = "resolve"
# Mutable - TTL + event invalidation
UPSTREAM_SOURCES = "upstream"
PACKAGE_INDEX = "index"
PACKAGE_VERSIONS = "versions"
def get_category_ttl(category: CacheCategory, settings: Settings) -> Optional[int]:
"""
Get TTL for a cache category.
Returns:
TTL in seconds, or None for no expiry (immutable).
"""
ttl_map = {
# Immutable - no TTL
CacheCategory.ARTIFACT_METADATA: None,
CacheCategory.ARTIFACT_DEPENDENCIES: None,
CacheCategory.DEPENDENCY_RESOLUTION: None,
# Mutable - configurable TTL
CacheCategory.UPSTREAM_SOURCES: settings.cache_ttl_upstream,
CacheCategory.PACKAGE_INDEX: settings.cache_ttl_index,
CacheCategory.PACKAGE_VERSIONS: settings.cache_ttl_versions,
}
return ttl_map.get(category)
class CacheService:
"""
Redis-backed caching with category-aware TTL.
Key format: orchard:{category}:{protocol}:{identifier}
Example: orchard:deps:pypi:abc123def456
When Redis is disabled or unavailable, operations gracefully
return None/no-op to allow the application to function without caching.
"""
def __init__(self, settings: Settings):
self._settings = settings
self._enabled = settings.redis_enabled
self._redis: Optional["redis.asyncio.Redis"] = None
self._started = False
async def startup(self) -> None:
"""Initialize Redis connection. Called by FastAPI lifespan."""
if self._started:
return
if not self._enabled:
logger.info("CacheService disabled (redis_enabled=False)")
self._started = True
return
try:
import redis.asyncio as redis
logger.info(
f"Connecting to Redis at {self._settings.redis_host}:"
f"{self._settings.redis_port}/{self._settings.redis_db}"
)
self._redis = redis.Redis(
host=self._settings.redis_host,
port=self._settings.redis_port,
db=self._settings.redis_db,
password=self._settings.redis_password,
decode_responses=False, # We handle bytes
)
# Test connection
await self._redis.ping()
logger.info("CacheService connected to Redis")
except ImportError:
logger.warning("redis package not installed, caching disabled")
self._enabled = False
except Exception as e:
logger.warning(f"Redis connection failed, caching disabled: {e}")
self._enabled = False
self._redis = None
self._started = True
async def shutdown(self) -> None:
"""Close Redis connection. Called by FastAPI lifespan."""
if not self._started:
return
if self._redis:
await self._redis.aclose()
self._redis = None
self._started = False
logger.info("CacheService shutdown complete")
@staticmethod
def _make_key(category: CacheCategory, protocol: str, identifier: str) -> str:
"""Build namespaced cache key."""
return f"orchard:{category.value}:{protocol}:{identifier}"
async def get(
self,
category: CacheCategory,
key: str,
protocol: str = "default",
) -> Optional[bytes]:
"""
Get cached value.
Args:
category: Cache category for TTL rules
key: Unique identifier within category
protocol: Protocol namespace (pypi, npm, etc.)
Returns:
Cached bytes or None if not found/disabled.
"""
if not self._enabled or not self._redis:
return None
try:
full_key = self._make_key(category, protocol, key)
return await self._redis.get(full_key)
except Exception as e:
logger.warning(f"Cache get failed for {key}: {e}")
return None
async def set(
self,
category: CacheCategory,
key: str,
value: bytes,
protocol: str = "default",
) -> None:
"""
Set cached value with category-appropriate TTL.
Args:
category: Cache category for TTL rules
key: Unique identifier within category
value: Bytes to cache
protocol: Protocol namespace (pypi, npm, etc.)
"""
if not self._enabled or not self._redis:
return
try:
full_key = self._make_key(category, protocol, key)
ttl = get_category_ttl(category, self._settings)
if ttl is None:
await self._redis.set(full_key, value)
else:
await self._redis.setex(full_key, ttl, value)
except Exception as e:
logger.warning(f"Cache set failed for {key}: {e}")
async def delete(
self,
category: CacheCategory,
key: str,
protocol: str = "default",
) -> None:
"""Delete a specific cache entry."""
if not self._enabled or not self._redis:
return
try:
full_key = self._make_key(category, protocol, key)
await self._redis.delete(full_key)
except Exception as e:
logger.warning(f"Cache delete failed for {key}: {e}")
async def invalidate_pattern(
self,
category: CacheCategory,
pattern: str = "*",
protocol: str = "default",
) -> int:
"""
Invalidate all entries matching pattern.
Args:
category: Cache category
pattern: Glob pattern for keys (default "*" = all in category)
protocol: Protocol namespace
Returns:
Number of keys deleted.
"""
if not self._enabled or not self._redis:
return 0
try:
full_pattern = self._make_key(category, protocol, pattern)
keys = []
async for key in self._redis.scan_iter(match=full_pattern):
keys.append(key)
if keys:
return await self._redis.delete(*keys)
return 0
except Exception as e:
logger.warning(f"Cache invalidate failed for pattern {pattern}: {e}")
return 0
async def ping(self) -> bool:
"""Check if Redis is connected and responding."""
if not self._enabled or not self._redis:
return False
try:
await self._redis.ping()
return True
except Exception:
return False
@property
def enabled(self) -> bool:
"""Check if caching is enabled."""
return self._enabled

View File

@@ -1,8 +1,5 @@
from pydantic_settings import BaseSettings
from functools import lru_cache
from typing import Optional
import os
import re
class Settings(BaseSettings):
@@ -22,8 +19,8 @@ class Settings(BaseSettings):
database_sslmode: str = "disable"
# Database connection pool settings
database_pool_size: int = 20 # Number of connections to keep open
database_max_overflow: int = 30 # Max additional connections beyond pool_size
database_pool_size: int = 5 # Number of connections to keep open
database_max_overflow: int = 10 # Max additional connections beyond pool_size
database_pool_timeout: int = 30 # Seconds to wait for a connection from pool
database_pool_recycle: int = (
1800 # Recycle connections after this many seconds (30 min)
@@ -51,26 +48,6 @@ class Settings(BaseSettings):
presigned_url_expiry: int = (
3600 # Presigned URL expiry in seconds (default: 1 hour)
)
pypi_download_mode: str = "redirect" # "redirect" (to S3) or "proxy" (stream through Orchard)
# HTTP Client pool settings
http_max_connections: int = 100 # Max connections per pool
http_max_keepalive: int = 20 # Keep-alive connections
http_connect_timeout: float = 30.0 # Connection timeout seconds
http_read_timeout: float = 60.0 # Read timeout seconds
http_worker_threads: int = 32 # Thread pool for blocking ops
# Redis cache settings
redis_host: str = "localhost"
redis_port: int = 6379
redis_db: int = 0
redis_password: Optional[str] = None
redis_enabled: bool = True # Set False to disable caching
# Cache TTL settings (seconds, 0 = no expiry)
cache_ttl_index: int = 300 # Package index pages: 5 min
cache_ttl_versions: int = 300 # Version listings: 5 min
cache_ttl_upstream: int = 3600 # Upstream source config: 1 hour
# Logging settings
log_level: str = "INFO" # DEBUG, INFO, WARNING, ERROR, CRITICAL
@@ -79,16 +56,6 @@ class Settings(BaseSettings):
# Initial admin user settings
admin_password: str = "" # Initial admin password (if empty, uses 'changeme123')
# Cache settings
cache_encryption_key: str = "" # Fernet key for encrypting upstream credentials (auto-generated if empty)
# Global cache settings override (None = use DB value, True/False = override DB)
cache_auto_create_system_projects: Optional[bool] = None # Override auto_create_system_projects
# PyPI Cache Worker settings
pypi_cache_workers: int = 5 # Number of concurrent cache workers
pypi_cache_max_depth: int = 10 # Maximum recursion depth for dependency caching
pypi_cache_max_attempts: int = 3 # Maximum retry attempts for failed cache tasks
# JWT Authentication settings (optional, for external identity providers)
jwt_enabled: bool = False # Enable JWT token validation
jwt_secret: str = "" # Secret key for HS256, or leave empty for RS256 with JWKS
@@ -113,24 +80,6 @@ class Settings(BaseSettings):
def is_production(self) -> bool:
return self.env.lower() == "production"
@property
def PORT(self) -> int:
"""Alias for server_port for compatibility."""
return self.server_port
# Uppercase aliases for PyPI cache settings (for backward compatibility)
@property
def PYPI_CACHE_WORKERS(self) -> int:
return self.pypi_cache_workers
@property
def PYPI_CACHE_MAX_DEPTH(self) -> int:
return self.pypi_cache_max_depth
@property
def PYPI_CACHE_MAX_ATTEMPTS(self) -> int:
return self.pypi_cache_max_attempts
class Config:
env_prefix = "ORCHARD_"
case_sensitive = False
@@ -139,110 +88,3 @@ class Settings(BaseSettings):
@lru_cache()
def get_settings() -> Settings:
return Settings()
class EnvUpstreamSource:
"""Represents an upstream source defined via environment variables."""
def __init__(
self,
name: str,
url: str,
source_type: str = "generic",
enabled: bool = True,
auth_type: str = "none",
username: Optional[str] = None,
password: Optional[str] = None,
priority: int = 100,
):
self.name = name
self.url = url
self.source_type = source_type
self.enabled = enabled
self.auth_type = auth_type
self.username = username
self.password = password
self.priority = priority
self.source = "env" # Mark as env-defined
def parse_upstream_sources_from_env() -> list[EnvUpstreamSource]:
"""
Parse upstream sources from environment variables.
Uses double underscore (__) as separator to allow source names with single underscores.
Pattern: ORCHARD_UPSTREAM__{NAME}__FIELD
Example:
ORCHARD_UPSTREAM__NPM_PRIVATE__URL=https://npm.corp.com
ORCHARD_UPSTREAM__NPM_PRIVATE__TYPE=npm
ORCHARD_UPSTREAM__NPM_PRIVATE__ENABLED=true
ORCHARD_UPSTREAM__NPM_PRIVATE__AUTH_TYPE=basic
ORCHARD_UPSTREAM__NPM_PRIVATE__USERNAME=reader
ORCHARD_UPSTREAM__NPM_PRIVATE__PASSWORD=secret
Returns:
List of EnvUpstreamSource objects parsed from environment variables.
"""
# Pattern: ORCHARD_UPSTREAM__{NAME}__{FIELD}
pattern = re.compile(r"^ORCHARD_UPSTREAM__([A-Z0-9_]+)__([A-Z_]+)$", re.IGNORECASE)
# Collect all env vars matching the pattern, grouped by source name
sources_data: dict[str, dict[str, str]] = {}
for key, value in os.environ.items():
match = pattern.match(key)
if match:
source_name = match.group(1).lower() # Normalize to lowercase
field = match.group(2).upper()
if source_name not in sources_data:
sources_data[source_name] = {}
sources_data[source_name][field] = value
# Build source objects from collected data
sources: list[EnvUpstreamSource] = []
for name, data in sources_data.items():
# URL is required
url = data.get("URL")
if not url:
continue # Skip sources without URL
# Parse boolean fields
def parse_bool(val: Optional[str], default: bool) -> bool:
if val is None:
return default
return val.lower() in ("true", "1", "yes", "on")
# Parse integer fields
def parse_int(val: Optional[str], default: int) -> int:
if val is None:
return default
try:
return int(val)
except ValueError:
return default
source = EnvUpstreamSource(
name=name.replace("_", "-"), # Convert underscores to hyphens for readability
url=url,
source_type=data.get("TYPE", "generic").lower(),
enabled=parse_bool(data.get("ENABLED"), True),
auth_type=data.get("AUTH_TYPE", "none").lower(),
username=data.get("USERNAME"),
password=data.get("PASSWORD"),
priority=parse_int(data.get("PRIORITY"), 100),
)
sources.append(source)
return sources
@lru_cache()
def get_env_upstream_sources() -> tuple[EnvUpstreamSource, ...]:
"""
Get cached list of upstream sources from environment variables.
Returns a tuple for hashability (required by lru_cache).
"""
return tuple(parse_upstream_sources_from_env())

View File

@@ -1,34 +1,17 @@
from sqlalchemy import create_engine, text, event
from sqlalchemy.orm import sessionmaker, Session
from sqlalchemy.pool import QueuePool
from typing import Generator, NamedTuple
from typing import Generator
from contextlib import contextmanager
import logging
import time
import hashlib
from .config import get_settings
from .models import Base
from .purge_seed_data import should_purge_seed_data, purge_seed_data
settings = get_settings()
logger = logging.getLogger(__name__)
class Migration(NamedTuple):
"""A database migration with a unique name and SQL to execute."""
name: str
sql: str
# PostgreSQL error codes that indicate "already exists" - safe to skip
SAFE_PG_ERROR_CODES = {
"42P07", # duplicate_table
"42701", # duplicate_column
"42710", # duplicate_object (index, constraint, etc.)
"42P16", # invalid_table_definition (e.g., column already exists)
}
# Build connect_args with query timeout if configured
connect_args = {}
if settings.database_query_timeout > 0:
@@ -81,562 +64,291 @@ def init_db():
# Run migrations for schema updates
_run_migrations()
# Purge seed data if requested (for transitioning to production-like environment)
if should_purge_seed_data():
db = SessionLocal()
try:
purge_seed_data(db)
finally:
db.close()
def _ensure_migrations_table(conn) -> None:
"""Create the migrations tracking table if it doesn't exist."""
conn.execute(text("""
CREATE TABLE IF NOT EXISTS _schema_migrations (
name VARCHAR(255) PRIMARY KEY,
checksum VARCHAR(64) NOT NULL,
applied_at TIMESTAMP WITH TIME ZONE DEFAULT NOW()
);
"""))
conn.commit()
def _get_applied_migrations(conn) -> dict[str, str]:
"""Get all applied migrations and their checksums."""
result = conn.execute(text(
"SELECT name, checksum FROM _schema_migrations"
))
return {row[0]: row[1] for row in result}
def _compute_checksum(sql: str) -> str:
"""Compute a checksum for migration SQL to detect changes."""
return hashlib.sha256(sql.strip().encode()).hexdigest()[:16]
def _is_safe_error(exception: Exception) -> bool:
"""Check if the error indicates the migration was already applied."""
# Check for psycopg2 errors with pgcode attribute
original = getattr(exception, "orig", None)
if original is not None:
pgcode = getattr(original, "pgcode", None)
if pgcode in SAFE_PG_ERROR_CODES:
return True
# Fallback: check error message for common "already exists" patterns
error_str = str(exception).lower()
safe_patterns = [
"already exists",
"duplicate key",
"relation .* already exists",
"column .* already exists",
]
return any(pattern in error_str for pattern in safe_patterns)
def _record_migration(conn, name: str, checksum: str) -> None:
"""Record a migration as applied."""
conn.execute(text(
"INSERT INTO _schema_migrations (name, checksum) VALUES (:name, :checksum)"
), {"name": name, "checksum": checksum})
conn.commit()
def _run_migrations():
"""Run manual migrations for schema updates with tracking and error detection."""
"""Run manual migrations for schema updates"""
migrations = [
Migration(
name="001_add_format_metadata",
sql="""
DO $$
BEGIN
IF NOT EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'artifacts' AND column_name = 'format_metadata'
) THEN
ALTER TABLE artifacts ADD COLUMN format_metadata JSONB DEFAULT '{}';
END IF;
END $$;
""",
),
Migration(
name="002_add_package_format",
sql="""
DO $$
BEGIN
IF NOT EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'packages' AND column_name = 'format'
) THEN
ALTER TABLE packages ADD COLUMN format VARCHAR(50) DEFAULT 'generic' NOT NULL;
CREATE INDEX IF NOT EXISTS idx_packages_format ON packages(format);
END IF;
END $$;
""",
),
Migration(
name="003_add_package_platform",
sql="""
DO $$
BEGIN
IF NOT EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'packages' AND column_name = 'platform'
) THEN
ALTER TABLE packages ADD COLUMN platform VARCHAR(50) DEFAULT 'any' NOT NULL;
CREATE INDEX IF NOT EXISTS idx_packages_platform ON packages(platform);
END IF;
END $$;
""",
),
Migration(
name="004_add_ref_count_index_constraint",
sql="""
DO $$
BEGIN
IF NOT EXISTS (
SELECT 1 FROM pg_indexes WHERE indexname = 'idx_artifacts_ref_count'
) THEN
CREATE INDEX idx_artifacts_ref_count ON artifacts(ref_count);
END IF;
# Add format_metadata column to artifacts table
"""
DO $$
BEGIN
IF NOT EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'artifacts' AND column_name = 'format_metadata'
) THEN
ALTER TABLE artifacts ADD COLUMN format_metadata JSONB DEFAULT '{}';
END IF;
END $$;
""",
# Add format column to packages table
"""
DO $$
BEGIN
IF NOT EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'packages' AND column_name = 'format'
) THEN
ALTER TABLE packages ADD COLUMN format VARCHAR(50) DEFAULT 'generic' NOT NULL;
CREATE INDEX IF NOT EXISTS idx_packages_format ON packages(format);
END IF;
END $$;
""",
# Add platform column to packages table
"""
DO $$
BEGIN
IF NOT EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'packages' AND column_name = 'platform'
) THEN
ALTER TABLE packages ADD COLUMN platform VARCHAR(50) DEFAULT 'any' NOT NULL;
CREATE INDEX IF NOT EXISTS idx_packages_platform ON packages(platform);
END IF;
END $$;
""",
# Add ref_count index and constraints for artifacts
"""
DO $$
BEGIN
-- Add ref_count index
IF NOT EXISTS (
SELECT 1 FROM pg_indexes WHERE indexname = 'idx_artifacts_ref_count'
) THEN
CREATE INDEX idx_artifacts_ref_count ON artifacts(ref_count);
END IF;
IF NOT EXISTS (
SELECT 1 FROM pg_constraint WHERE conname = 'check_ref_count_non_negative'
) THEN
ALTER TABLE artifacts ADD CONSTRAINT check_ref_count_non_negative CHECK (ref_count >= 0);
END IF;
END $$;
""",
),
Migration(
name="005_add_composite_indexes",
sql="""
DO $$
BEGIN
IF NOT EXISTS (
SELECT 1 FROM pg_indexes WHERE indexname = 'idx_packages_project_name'
) THEN
CREATE UNIQUE INDEX idx_packages_project_name ON packages(project_id, name);
END IF;
-- Add ref_count >= 0 constraint
IF NOT EXISTS (
SELECT 1 FROM pg_constraint WHERE conname = 'check_ref_count_non_negative'
) THEN
ALTER TABLE artifacts ADD CONSTRAINT check_ref_count_non_negative CHECK (ref_count >= 0);
END IF;
END $$;
""",
# Add composite indexes for packages and tags
"""
DO $$
BEGIN
-- Composite index for package lookup by project and name
IF NOT EXISTS (
SELECT 1 FROM pg_indexes WHERE indexname = 'idx_packages_project_name'
) THEN
CREATE UNIQUE INDEX idx_packages_project_name ON packages(project_id, name);
END IF;
-- Tag indexes removed: tags table no longer exists (removed in tag system removal)
END $$;
""",
),
Migration(
name="006_add_package_versions_indexes",
sql="""
DO $$
BEGIN
IF EXISTS (SELECT 1 FROM information_schema.tables WHERE table_name = 'package_versions') THEN
IF NOT EXISTS (SELECT 1 FROM pg_indexes WHERE indexname = 'idx_package_versions_package_id') THEN
CREATE INDEX idx_package_versions_package_id ON package_versions(package_id);
END IF;
IF NOT EXISTS (SELECT 1 FROM pg_indexes WHERE indexname = 'idx_package_versions_artifact_id') THEN
CREATE INDEX idx_package_versions_artifact_id ON package_versions(artifact_id);
END IF;
IF NOT EXISTS (SELECT 1 FROM pg_indexes WHERE indexname = 'idx_package_versions_package_version') THEN
CREATE INDEX idx_package_versions_package_version ON package_versions(package_id, version);
END IF;
END IF;
END $$;
""",
),
Migration(
name="007_create_ref_count_trigger_functions",
sql="""
CREATE OR REPLACE FUNCTION increment_artifact_ref_count()
RETURNS TRIGGER AS $$
BEGIN
UPDATE artifacts SET ref_count = ref_count + 1 WHERE id = NEW.artifact_id;
RETURN NEW;
END;
$$ LANGUAGE plpgsql;
-- Composite index for tag lookup by package and name
IF NOT EXISTS (
SELECT 1 FROM pg_indexes WHERE indexname = 'idx_tags_package_name'
) THEN
CREATE UNIQUE INDEX idx_tags_package_name ON tags(package_id, name);
END IF;
CREATE OR REPLACE FUNCTION decrement_artifact_ref_count()
RETURNS TRIGGER AS $$
BEGIN
-- Composite index for recent tags queries
IF NOT EXISTS (
SELECT 1 FROM pg_indexes WHERE indexname = 'idx_tags_package_created_at'
) THEN
CREATE INDEX idx_tags_package_created_at ON tags(package_id, created_at);
END IF;
END $$;
""",
# Add package_versions indexes and triggers (007_package_versions.sql)
"""
DO $$
BEGIN
-- Create indexes for package_versions if table exists
IF EXISTS (SELECT 1 FROM information_schema.tables WHERE table_name = 'package_versions') THEN
-- Indexes for common queries
IF NOT EXISTS (SELECT 1 FROM pg_indexes WHERE indexname = 'idx_package_versions_package_id') THEN
CREATE INDEX idx_package_versions_package_id ON package_versions(package_id);
END IF;
IF NOT EXISTS (SELECT 1 FROM pg_indexes WHERE indexname = 'idx_package_versions_artifact_id') THEN
CREATE INDEX idx_package_versions_artifact_id ON package_versions(artifact_id);
END IF;
IF NOT EXISTS (SELECT 1 FROM pg_indexes WHERE indexname = 'idx_package_versions_package_version') THEN
CREATE INDEX idx_package_versions_package_version ON package_versions(package_id, version);
END IF;
END IF;
END $$;
""",
# Create ref_count trigger functions for tags (ensures triggers exist even if initial migration wasn't run)
"""
CREATE OR REPLACE FUNCTION increment_artifact_ref_count()
RETURNS TRIGGER AS $$
BEGIN
UPDATE artifacts SET ref_count = ref_count + 1 WHERE id = NEW.artifact_id;
RETURN NEW;
END;
$$ LANGUAGE plpgsql;
""",
"""
CREATE OR REPLACE FUNCTION decrement_artifact_ref_count()
RETURNS TRIGGER AS $$
BEGIN
UPDATE artifacts SET ref_count = ref_count - 1 WHERE id = OLD.artifact_id;
RETURN OLD;
END;
$$ LANGUAGE plpgsql;
""",
"""
CREATE OR REPLACE FUNCTION update_artifact_ref_count()
RETURNS TRIGGER AS $$
BEGIN
IF OLD.artifact_id != NEW.artifact_id THEN
UPDATE artifacts SET ref_count = ref_count - 1 WHERE id = OLD.artifact_id;
RETURN OLD;
END;
$$ LANGUAGE plpgsql;
CREATE OR REPLACE FUNCTION update_artifact_ref_count()
RETURNS TRIGGER AS $$
BEGIN
IF OLD.artifact_id != NEW.artifact_id THEN
UPDATE artifacts SET ref_count = ref_count - 1 WHERE id = OLD.artifact_id;
UPDATE artifacts SET ref_count = ref_count + 1 WHERE id = NEW.artifact_id;
END IF;
RETURN NEW;
END;
$$ LANGUAGE plpgsql;
""",
),
Migration(
name="008_create_tags_ref_count_triggers",
sql="""
-- Tags table removed: triggers no longer needed (tag system removed)
DO $$ BEGIN NULL; END $$;
""",
),
Migration(
name="009_create_version_ref_count_functions",
sql="""
CREATE OR REPLACE FUNCTION increment_version_ref_count()
RETURNS TRIGGER AS $$
BEGIN
UPDATE artifacts SET ref_count = ref_count + 1 WHERE id = NEW.artifact_id;
RETURN NEW;
END;
$$ LANGUAGE plpgsql;
END IF;
RETURN NEW;
END;
$$ LANGUAGE plpgsql;
""",
# Create triggers for tags ref_count management
"""
DO $$
BEGIN
-- Drop and recreate triggers to ensure they're current
DROP TRIGGER IF EXISTS tags_ref_count_insert_trigger ON tags;
CREATE TRIGGER tags_ref_count_insert_trigger
AFTER INSERT ON tags
FOR EACH ROW
EXECUTE FUNCTION increment_artifact_ref_count();
CREATE OR REPLACE FUNCTION decrement_version_ref_count()
RETURNS TRIGGER AS $$
BEGIN
UPDATE artifacts SET ref_count = ref_count - 1 WHERE id = OLD.artifact_id;
RETURN OLD;
END;
$$ LANGUAGE plpgsql;
""",
),
Migration(
name="010_create_package_versions_triggers",
sql="""
DO $$
BEGIN
IF EXISTS (SELECT 1 FROM information_schema.tables WHERE table_name = 'package_versions') THEN
DROP TRIGGER IF EXISTS package_versions_ref_count_insert ON package_versions;
CREATE TRIGGER package_versions_ref_count_insert
AFTER INSERT ON package_versions
FOR EACH ROW
EXECUTE FUNCTION increment_version_ref_count();
DROP TRIGGER IF EXISTS tags_ref_count_delete_trigger ON tags;
CREATE TRIGGER tags_ref_count_delete_trigger
AFTER DELETE ON tags
FOR EACH ROW
EXECUTE FUNCTION decrement_artifact_ref_count();
DROP TRIGGER IF EXISTS package_versions_ref_count_delete ON package_versions;
CREATE TRIGGER package_versions_ref_count_delete
AFTER DELETE ON package_versions
FOR EACH ROW
EXECUTE FUNCTION decrement_version_ref_count();
END IF;
END $$;
""",
),
Migration(
name="011_migrate_semver_tags_to_versions",
sql=r"""
-- Migrate semver tags to versions (only if both tables exist - for existing databases)
DO $$
BEGIN
IF EXISTS (SELECT 1 FROM information_schema.tables WHERE table_name = 'package_versions')
AND EXISTS (SELECT 1 FROM information_schema.tables WHERE table_name = 'tags') THEN
INSERT INTO package_versions (id, package_id, artifact_id, version, version_source, created_by, created_at)
SELECT
gen_random_uuid(),
t.package_id,
t.artifact_id,
CASE WHEN t.name LIKE 'v%' THEN substring(t.name from 2) ELSE t.name END,
'migrated_from_tag',
t.created_by,
t.created_at
FROM tags t
WHERE t.name ~ '^v?[0-9]+\.[0-9]+(\.[0-9]+)?([-.][a-zA-Z0-9]+)?$'
ON CONFLICT (package_id, version) DO NOTHING;
END IF;
END $$;
""",
),
Migration(
name="012_create_teams_table",
sql="""
CREATE TABLE IF NOT EXISTS teams (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
name VARCHAR(255) NOT NULL,
slug VARCHAR(255) NOT NULL UNIQUE,
description TEXT,
created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
updated_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
created_by VARCHAR(255) NOT NULL,
settings JSONB DEFAULT '{}'
);
""",
),
Migration(
name="013_create_team_memberships_table",
sql="""
CREATE TABLE IF NOT EXISTS team_memberships (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
team_id UUID NOT NULL REFERENCES teams(id) ON DELETE CASCADE,
user_id UUID NOT NULL REFERENCES users(id) ON DELETE CASCADE,
role VARCHAR(50) NOT NULL DEFAULT 'member',
created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
invited_by VARCHAR(255),
CONSTRAINT team_memberships_unique UNIQUE (team_id, user_id),
CONSTRAINT team_memberships_role_check CHECK (role IN ('owner', 'admin', 'member'))
);
""",
),
Migration(
name="014_add_team_id_to_projects",
sql="""
DO $$
BEGIN
IF NOT EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'projects' AND column_name = 'team_id'
) THEN
ALTER TABLE projects ADD COLUMN team_id UUID REFERENCES teams(id) ON DELETE SET NULL;
CREATE INDEX IF NOT EXISTS idx_projects_team_id ON projects(team_id);
END IF;
END $$;
""",
),
Migration(
name="015_add_teams_indexes",
sql="""
DO $$
BEGIN
IF NOT EXISTS (SELECT 1 FROM pg_indexes WHERE indexname = 'idx_teams_slug') THEN
CREATE INDEX idx_teams_slug ON teams(slug);
END IF;
IF NOT EXISTS (SELECT 1 FROM pg_indexes WHERE indexname = 'idx_teams_created_by') THEN
CREATE INDEX idx_teams_created_by ON teams(created_by);
END IF;
IF NOT EXISTS (SELECT 1 FROM pg_indexes WHERE indexname = 'idx_team_memberships_team_id') THEN
CREATE INDEX idx_team_memberships_team_id ON team_memberships(team_id);
END IF;
IF NOT EXISTS (SELECT 1 FROM pg_indexes WHERE indexname = 'idx_team_memberships_user_id') THEN
CREATE INDEX idx_team_memberships_user_id ON team_memberships(user_id);
END IF;
END $$;
""",
),
Migration(
name="016_add_is_system_to_projects",
sql="""
DO $$
BEGIN
IF NOT EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'projects' AND column_name = 'is_system'
) THEN
ALTER TABLE projects ADD COLUMN is_system BOOLEAN NOT NULL DEFAULT FALSE;
CREATE INDEX IF NOT EXISTS idx_projects_is_system ON projects(is_system);
END IF;
END $$;
""",
),
Migration(
name="017_create_upstream_sources",
sql="""
CREATE TABLE IF NOT EXISTS upstream_sources (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
name VARCHAR(255) NOT NULL UNIQUE,
source_type VARCHAR(50) NOT NULL DEFAULT 'generic',
url VARCHAR(2048) NOT NULL,
enabled BOOLEAN NOT NULL DEFAULT FALSE,
auth_type VARCHAR(20) NOT NULL DEFAULT 'none',
username VARCHAR(255),
password_encrypted BYTEA,
headers_encrypted BYTEA,
priority INTEGER NOT NULL DEFAULT 100,
created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
updated_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
CONSTRAINT check_source_type CHECK (
source_type IN ('npm', 'pypi', 'maven', 'docker', 'helm', 'nuget', 'deb', 'rpm', 'generic')
),
CONSTRAINT check_auth_type CHECK (
auth_type IN ('none', 'basic', 'bearer', 'api_key')
),
CONSTRAINT check_priority_positive CHECK (priority > 0)
);
CREATE INDEX IF NOT EXISTS idx_upstream_sources_enabled ON upstream_sources(enabled);
CREATE INDEX IF NOT EXISTS idx_upstream_sources_source_type ON upstream_sources(source_type);
CREATE INDEX IF NOT EXISTS idx_upstream_sources_priority ON upstream_sources(priority);
""",
),
Migration(
name="018_create_cache_settings",
sql="""
CREATE TABLE IF NOT EXISTS cache_settings (
id INTEGER PRIMARY KEY DEFAULT 1,
auto_create_system_projects BOOLEAN NOT NULL DEFAULT TRUE,
created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
updated_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
CONSTRAINT check_cache_settings_singleton CHECK (id = 1)
);
INSERT INTO cache_settings (id, auto_create_system_projects)
VALUES (1, TRUE)
ON CONFLICT (id) DO NOTHING;
""",
),
Migration(
name="019_create_cached_urls",
sql="""
CREATE TABLE IF NOT EXISTS cached_urls (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
url VARCHAR(4096) NOT NULL,
url_hash VARCHAR(64) NOT NULL UNIQUE,
artifact_id VARCHAR(64) NOT NULL REFERENCES artifacts(id),
source_id UUID REFERENCES upstream_sources(id) ON DELETE SET NULL,
fetched_at TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT NOW(),
response_headers JSONB DEFAULT '{}',
created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW()
);
CREATE INDEX IF NOT EXISTS idx_cached_urls_url_hash ON cached_urls(url_hash);
CREATE INDEX IF NOT EXISTS idx_cached_urls_artifact_id ON cached_urls(artifact_id);
CREATE INDEX IF NOT EXISTS idx_cached_urls_source_id ON cached_urls(source_id);
CREATE INDEX IF NOT EXISTS idx_cached_urls_fetched_at ON cached_urls(fetched_at);
""",
),
Migration(
name="020_seed_default_upstream_sources",
sql="""
-- Originally seeded public sources, but these are no longer used.
-- Migration 023 deletes any previously seeded sources.
-- This migration is now a no-op for fresh installs.
SELECT 1;
""",
),
Migration(
name="021_remove_is_public_from_upstream_sources",
sql="""
DO $$
BEGIN
-- Drop the index if it exists
DROP INDEX IF EXISTS idx_upstream_sources_is_public;
DROP TRIGGER IF EXISTS tags_ref_count_update_trigger ON tags;
CREATE TRIGGER tags_ref_count_update_trigger
AFTER UPDATE ON tags
FOR EACH ROW
WHEN (OLD.artifact_id IS DISTINCT FROM NEW.artifact_id)
EXECUTE FUNCTION update_artifact_ref_count();
END $$;
""",
# Create ref_count trigger functions for package_versions
"""
CREATE OR REPLACE FUNCTION increment_version_ref_count()
RETURNS TRIGGER AS $$
BEGIN
UPDATE artifacts SET ref_count = ref_count + 1 WHERE id = NEW.artifact_id;
RETURN NEW;
END;
$$ LANGUAGE plpgsql;
""",
"""
CREATE OR REPLACE FUNCTION decrement_version_ref_count()
RETURNS TRIGGER AS $$
BEGIN
UPDATE artifacts SET ref_count = ref_count - 1 WHERE id = OLD.artifact_id;
RETURN OLD;
END;
$$ LANGUAGE plpgsql;
""",
# Create triggers for package_versions ref_count
"""
DO $$
BEGIN
IF EXISTS (SELECT 1 FROM information_schema.tables WHERE table_name = 'package_versions') THEN
-- Drop and recreate triggers to ensure they're current
DROP TRIGGER IF EXISTS package_versions_ref_count_insert ON package_versions;
CREATE TRIGGER package_versions_ref_count_insert
AFTER INSERT ON package_versions
FOR EACH ROW
EXECUTE FUNCTION increment_version_ref_count();
-- Drop the column if it exists
IF EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'upstream_sources' AND column_name = 'is_public'
) THEN
ALTER TABLE upstream_sources DROP COLUMN is_public;
END IF;
END $$;
""",
),
Migration(
name="022_remove_allow_public_internet_from_cache_settings",
sql="""
DO $$
BEGIN
IF EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'cache_settings' AND column_name = 'allow_public_internet'
) THEN
ALTER TABLE cache_settings DROP COLUMN allow_public_internet;
END IF;
END $$;
""",
),
Migration(
name="023_delete_seeded_public_sources",
sql="""
-- Delete the seeded public sources that were added by migration 020
DELETE FROM upstream_sources
WHERE name IN ('npm-public', 'pypi-public', 'maven-central', 'docker-hub');
""",
),
Migration(
name="024_remove_tags",
sql="""
-- Remove tag system, keeping only versions for artifact references
DO $$
BEGIN
-- Drop triggers on tags table (if they exist)
DROP TRIGGER IF EXISTS tags_ref_count_insert_trigger ON tags;
DROP TRIGGER IF EXISTS tags_ref_count_delete_trigger ON tags;
DROP TRIGGER IF EXISTS tags_ref_count_update_trigger ON tags;
DROP TRIGGER IF EXISTS tags_updated_at_trigger ON tags;
DROP TRIGGER IF EXISTS tag_changes_trigger ON tags;
-- Drop the tag change tracking function
DROP FUNCTION IF EXISTS track_tag_changes();
-- Remove tag_constraint from artifact_dependencies
IF EXISTS (
SELECT 1 FROM information_schema.table_constraints
WHERE constraint_name = 'check_constraint_type'
AND table_name = 'artifact_dependencies'
) THEN
ALTER TABLE artifact_dependencies DROP CONSTRAINT check_constraint_type;
END IF;
-- Remove the tag_constraint column if it exists
IF EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'artifact_dependencies' AND column_name = 'tag_constraint'
) THEN
ALTER TABLE artifact_dependencies DROP COLUMN tag_constraint;
END IF;
-- Make version_constraint NOT NULL
UPDATE artifact_dependencies SET version_constraint = '*' WHERE version_constraint IS NULL;
ALTER TABLE artifact_dependencies ALTER COLUMN version_constraint SET NOT NULL;
-- Drop tag_history table first (depends on tags)
DROP TABLE IF EXISTS tag_history;
-- Drop tags table
DROP TABLE IF EXISTS tags;
-- Rename uploads.tag_name to version if it exists and version doesn't
IF EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'uploads' AND column_name = 'tag_name'
) AND NOT EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'uploads' AND column_name = 'version'
) THEN
ALTER TABLE uploads RENAME COLUMN tag_name TO version;
END IF;
END $$;
""",
),
DROP TRIGGER IF EXISTS package_versions_ref_count_delete ON package_versions;
CREATE TRIGGER package_versions_ref_count_delete
AFTER DELETE ON package_versions
FOR EACH ROW
EXECUTE FUNCTION decrement_version_ref_count();
END IF;
END $$;
""",
# Migrate existing semver tags to package_versions
r"""
DO $$
BEGIN
IF EXISTS (SELECT 1 FROM information_schema.tables WHERE table_name = 'package_versions') THEN
-- Migrate tags that look like versions (v1.0.0, 1.2.3, 2.0.0-beta, etc.)
INSERT INTO package_versions (package_id, artifact_id, version, version_source, created_by, created_at)
SELECT
t.package_id,
t.artifact_id,
CASE WHEN t.name LIKE 'v%' THEN substring(t.name from 2) ELSE t.name END,
'migrated_from_tag',
t.created_by,
t.created_at
FROM tags t
WHERE t.name ~ '^v?[0-9]+\.[0-9]+(\.[0-9]+)?([-.][a-zA-Z0-9]+)?$'
ON CONFLICT (package_id, version) DO NOTHING;
END IF;
END $$;
""",
# Teams and multi-tenancy migration (009_teams.sql)
"""
CREATE TABLE IF NOT EXISTS teams (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
name VARCHAR(255) NOT NULL,
slug VARCHAR(255) NOT NULL UNIQUE,
description TEXT,
created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
updated_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
created_by VARCHAR(255) NOT NULL,
settings JSONB DEFAULT '{}'
);
""",
"""
CREATE TABLE IF NOT EXISTS team_memberships (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
team_id UUID NOT NULL REFERENCES teams(id) ON DELETE CASCADE,
user_id UUID NOT NULL REFERENCES users(id) ON DELETE CASCADE,
role VARCHAR(50) NOT NULL DEFAULT 'member',
created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
invited_by VARCHAR(255),
CONSTRAINT team_memberships_unique UNIQUE (team_id, user_id),
CONSTRAINT team_memberships_role_check CHECK (role IN ('owner', 'admin', 'member'))
);
""",
"""
DO $$
BEGIN
IF NOT EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'projects' AND column_name = 'team_id'
) THEN
ALTER TABLE projects ADD COLUMN team_id UUID REFERENCES teams(id) ON DELETE SET NULL;
CREATE INDEX IF NOT EXISTS idx_projects_team_id ON projects(team_id);
END IF;
END $$;
""",
"""
DO $$
BEGIN
IF NOT EXISTS (SELECT 1 FROM pg_indexes WHERE indexname = 'idx_teams_slug') THEN
CREATE INDEX idx_teams_slug ON teams(slug);
END IF;
IF NOT EXISTS (SELECT 1 FROM pg_indexes WHERE indexname = 'idx_teams_created_by') THEN
CREATE INDEX idx_teams_created_by ON teams(created_by);
END IF;
IF NOT EXISTS (SELECT 1 FROM pg_indexes WHERE indexname = 'idx_team_memberships_team_id') THEN
CREATE INDEX idx_team_memberships_team_id ON team_memberships(team_id);
END IF;
IF NOT EXISTS (SELECT 1 FROM pg_indexes WHERE indexname = 'idx_team_memberships_user_id') THEN
CREATE INDEX idx_team_memberships_user_id ON team_memberships(user_id);
END IF;
END $$;
""",
]
with engine.connect() as conn:
# Ensure migrations tracking table exists
_ensure_migrations_table(conn)
# Get already-applied migrations
applied = _get_applied_migrations(conn)
for migration in migrations:
checksum = _compute_checksum(migration.sql)
# Check if migration was already applied
if migration.name in applied:
stored_checksum = applied[migration.name]
if stored_checksum != checksum:
logger.warning(
f"Migration '{migration.name}' has changed since it was applied! "
f"Stored checksum: {stored_checksum}, current: {checksum}"
)
continue
# Run the migration
try:
logger.info(f"Running migration: {migration.name}")
conn.execute(text(migration.sql))
conn.execute(text(migration))
conn.commit()
_record_migration(conn, migration.name, checksum)
logger.info(f"Migration '{migration.name}' applied successfully")
except Exception as e:
conn.rollback()
if _is_safe_error(e):
# Migration was already applied (schema already exists)
logger.info(
f"Migration '{migration.name}' already applied (schema exists), recording as complete"
)
_record_migration(conn, migration.name, checksum)
else:
# Real error - fail hard
logger.error(f"Migration '{migration.name}' failed: {e}")
raise RuntimeError(
f"Migration '{migration.name}' failed with error: {e}"
) from e
logger.warning(f"Migration failed (may already be applied): {e}")
def get_db() -> Generator[Session, None, None]:

View File

@@ -1,175 +0,0 @@
"""
Database utilities for optimized artifact operations.
Provides batch operations to eliminate N+1 queries.
"""
import logging
from typing import Optional
from sqlalchemy.dialects.postgresql import insert as pg_insert
from sqlalchemy.orm import Session
from .models import Artifact, ArtifactDependency, CachedUrl
logger = logging.getLogger(__name__)
class ArtifactRepository:
"""
Optimized database operations for artifact storage.
Key optimizations:
- Atomic upserts using ON CONFLICT
- Batch inserts for dependencies
- Joined queries to avoid N+1
"""
def __init__(self, db: Session):
self.db = db
@staticmethod
def _format_dependency_values(
artifact_id: str,
dependencies: list[tuple[str, str, str]],
) -> list[dict]:
"""
Format dependencies for batch insert.
Args:
artifact_id: SHA256 of the artifact
dependencies: List of (project, package, version_constraint)
Returns:
List of dicts ready for bulk insert.
"""
return [
{
"artifact_id": artifact_id,
"dependency_project": proj,
"dependency_package": pkg,
"version_constraint": ver,
}
for proj, pkg, ver in dependencies
]
def get_or_create_artifact(
self,
sha256: str,
size: int,
filename: str,
content_type: Optional[str] = None,
created_by: str = "system",
s3_key: Optional[str] = None,
) -> tuple[Artifact, bool]:
"""
Get existing artifact or create new one atomically.
Uses INSERT ... ON CONFLICT DO UPDATE to handle races.
If artifact exists, increments ref_count.
Args:
sha256: Content hash (primary key)
size: File size in bytes
filename: Original filename
content_type: MIME type
created_by: User who created the artifact
s3_key: S3 storage key (defaults to standard path)
Returns:
(artifact, created) tuple where created is True for new artifacts.
"""
if s3_key is None:
s3_key = f"fruits/{sha256[:2]}/{sha256[2:4]}/{sha256}"
stmt = pg_insert(Artifact).values(
id=sha256,
size=size,
original_name=filename,
content_type=content_type,
ref_count=1,
created_by=created_by,
s3_key=s3_key,
).on_conflict_do_update(
index_elements=['id'],
set_={'ref_count': Artifact.ref_count + 1}
).returning(Artifact)
result = self.db.execute(stmt)
artifact = result.scalar_one()
# Check if this was an insert or update by comparing ref_count
# ref_count=1 means new, >1 means existing
created = artifact.ref_count == 1
return artifact, created
def batch_upsert_dependencies(
self,
artifact_id: str,
dependencies: list[tuple[str, str, str]],
) -> int:
"""
Insert dependencies in a single batch operation.
Uses ON CONFLICT DO NOTHING to skip duplicates.
Args:
artifact_id: SHA256 of the artifact
dependencies: List of (project, package, version_constraint)
Returns:
Number of dependencies inserted.
"""
if not dependencies:
return 0
values = self._format_dependency_values(artifact_id, dependencies)
stmt = pg_insert(ArtifactDependency).values(values)
stmt = stmt.on_conflict_do_nothing(
index_elements=['artifact_id', 'dependency_project', 'dependency_package']
)
result = self.db.execute(stmt)
return result.rowcount
def get_cached_url_with_artifact(
self,
url_hash: str,
) -> Optional[tuple[CachedUrl, Artifact]]:
"""
Get cached URL and its artifact in a single query.
Args:
url_hash: SHA256 of the URL
Returns:
(CachedUrl, Artifact) tuple or None if not found.
"""
result = (
self.db.query(CachedUrl, Artifact)
.join(Artifact, CachedUrl.artifact_id == Artifact.id)
.filter(CachedUrl.url_hash == url_hash)
.first()
)
return result
def get_artifact_dependencies(
self,
artifact_id: str,
) -> list[ArtifactDependency]:
"""
Get all dependencies for an artifact in a single query.
Args:
artifact_id: SHA256 of the artifact
Returns:
List of ArtifactDependency objects.
"""
return (
self.db.query(ArtifactDependency)
.filter(ArtifactDependency.artifact_id == artifact_id)
.all()
)

View File

@@ -10,24 +10,16 @@ Handles:
- Conflict detection
"""
import re
import yaml
from typing import List, Dict, Any, Optional, Set, Tuple
from sqlalchemy.orm import Session
from sqlalchemy import and_
# Import packaging for PEP 440 version matching
try:
from packaging.specifiers import SpecifierSet, InvalidSpecifier
from packaging.version import Version, InvalidVersion
HAS_PACKAGING = True
except ImportError:
HAS_PACKAGING = False
from .models import (
Project,
Package,
Artifact,
Tag,
ArtifactDependency,
PackageVersion,
)
@@ -41,27 +33,10 @@ from .schemas import (
ResolvedArtifact,
DependencyResolutionResponse,
DependencyConflict,
MissingDependency,
PaginationMeta,
)
def _normalize_pypi_package_name(name: str) -> str:
"""
Normalize a PyPI package name for comparison.
- Strips extras brackets (e.g., "package[extra]" -> "package")
- Replaces sequences of hyphens, underscores, and dots with a single hyphen
- Lowercases the result
This follows PEP 503 normalization rules.
"""
# Strip extras brackets like [test], [dev], etc.
base_name = re.sub(r'\[.*\]', '', name)
# Normalize separators and lowercase
return re.sub(r'[-_.]+', '-', base_name).lower()
class DependencyError(Exception):
"""Base exception for dependency errors."""
pass
@@ -152,20 +127,26 @@ def parse_ensure_file(content: bytes) -> EnsureFileContent:
project = dep.get('project')
package = dep.get('package')
version = dep.get('version')
tag = dep.get('tag')
if not project:
raise InvalidEnsureFileError(f"Dependency {i} missing 'project'")
if not package:
raise InvalidEnsureFileError(f"Dependency {i} missing 'package'")
if not version:
if not version and not tag:
raise InvalidEnsureFileError(
f"Dependency {i} must have 'version'"
f"Dependency {i} must have either 'version' or 'tag'"
)
if version and tag:
raise InvalidEnsureFileError(
f"Dependency {i} cannot have both 'version' and 'tag'"
)
dependencies.append(EnsureFileDependency(
project=project,
package=package,
version=version,
tag=tag,
))
return EnsureFileContent(dependencies=dependencies)
@@ -219,6 +200,7 @@ def store_dependencies(
dependency_project=dep.project,
dependency_package=dep.package,
version_constraint=dep.version,
tag_constraint=dep.tag,
)
db.add(artifact_dep)
created.append(artifact_dep)
@@ -284,21 +266,26 @@ def get_reverse_dependencies(
if not artifact:
continue
# Find which package this artifact belongs to via versions
version_record = db.query(PackageVersion).filter(
PackageVersion.artifact_id == dep.artifact_id,
).first()
if version_record:
pkg = db.query(Package).filter(Package.id == version_record.package_id).first()
# Find which package this artifact belongs to via tags or versions
tag = db.query(Tag).filter(Tag.artifact_id == dep.artifact_id).first()
if tag:
pkg = db.query(Package).filter(Package.id == tag.package_id).first()
if pkg:
proj = db.query(Project).filter(Project.id == pkg.project_id).first()
if proj:
# Get version if available
version_record = db.query(PackageVersion).filter(
PackageVersion.artifact_id == dep.artifact_id,
PackageVersion.package_id == pkg.id,
).first()
dependents.append(DependentInfo(
artifact_id=dep.artifact_id,
project=proj.name,
package=pkg.name,
version=version_record.version,
constraint_value=dep.version_constraint,
version=version_record.version if version_record else None,
constraint_type="version" if dep.version_constraint else "tag",
constraint_value=dep.version_constraint or dep.tag_constraint,
))
total_pages = (total + limit - 1) // limit
@@ -317,117 +304,25 @@ def get_reverse_dependencies(
)
def _is_version_constraint(version_str: str) -> bool:
"""Check if a version string contains constraint operators."""
if not version_str:
return False
# Check for common constraint operators
return any(op in version_str for op in ['>=', '<=', '!=', '~=', '>', '<', '==', '*'])
def _resolve_version_constraint(
db: Session,
package: Package,
constraint: str,
) -> Optional[Tuple[str, str, int]]:
"""
Resolve a version constraint (e.g., '>=1.9') to a specific version.
Uses PEP 440 version matching to find the best matching version.
Args:
db: Database session
package: Package to search versions in
constraint: Version constraint string (e.g., '>=1.9', '<2.0,>=1.5')
Returns:
Tuple of (artifact_id, resolved_version, size) or None if not found
"""
if not HAS_PACKAGING:
# Fallback: if packaging not available, can't do constraint matching
return None
# Handle wildcard - return latest version
if constraint == '*':
# Get the latest version by created_at
latest = db.query(PackageVersion).filter(
PackageVersion.package_id == package.id,
).order_by(PackageVersion.created_at.desc()).first()
if latest:
artifact = db.query(Artifact).filter(Artifact.id == latest.artifact_id).first()
if artifact:
return (artifact.id, latest.version, artifact.size)
return None
try:
specifier = SpecifierSet(constraint)
except InvalidSpecifier:
# Invalid constraint (e.g., ">=" without version) - treat as wildcard
# This can happen with malformed metadata from PyPI packages
latest = db.query(PackageVersion).filter(
PackageVersion.package_id == package.id,
).order_by(PackageVersion.created_at.desc()).first()
if latest:
artifact = db.query(Artifact).filter(Artifact.id == latest.artifact_id).first()
if artifact:
return (artifact.id, latest.version, artifact.size)
return None
# Get all versions for this package
all_versions = db.query(PackageVersion).filter(
PackageVersion.package_id == package.id,
).all()
if not all_versions:
return None
# Find matching versions
matching = []
for pv in all_versions:
try:
v = Version(pv.version)
if v in specifier:
matching.append((pv, v))
except InvalidVersion:
# Skip invalid versions
continue
if not matching:
return None
# Sort by version (descending) and return the latest matching
matching.sort(key=lambda x: x[1], reverse=True)
best_match = matching[0][0]
artifact = db.query(Artifact).filter(Artifact.id == best_match.artifact_id).first()
if artifact:
return (artifact.id, best_match.version, artifact.size)
return None
def _resolve_dependency_to_artifact(
db: Session,
project_name: str,
package_name: str,
version: str,
version: Optional[str],
tag: Optional[str],
) -> Optional[Tuple[str, str, int]]:
"""
Resolve a dependency constraint to an artifact ID.
Supports:
- Exact version matching (e.g., '1.2.3')
- Version constraints (e.g., '>=1.9', '<2.0,>=1.5')
- Wildcard ('*' for any version)
Args:
db: Database session
project_name: Project name
package_name: Package name
version: Version or version constraint
version: Version constraint (exact)
tag: Tag constraint
Returns:
Tuple of (artifact_id, resolved_version, size) or None if not found
Tuple of (artifact_id, resolved_version_or_tag, size) or None if not found
"""
# Get project and package
project = db.query(Project).filter(Project.name == project_name).first()
@@ -441,13 +336,8 @@ def _resolve_dependency_to_artifact(
if not package:
return None
# Check if this is a version constraint (>=, <, etc.) or exact version
if _is_version_constraint(version):
result = _resolve_version_constraint(db, package, version)
if result:
return result
else:
# Look up by exact version
if version:
# Look up by version
pkg_version = db.query(PackageVersion).filter(
PackageVersion.package_id == package.id,
PackageVersion.version == version,
@@ -459,6 +349,31 @@ def _resolve_dependency_to_artifact(
if artifact:
return (artifact.id, version, artifact.size)
# Also check if there's a tag with this exact name
tag_record = db.query(Tag).filter(
Tag.package_id == package.id,
Tag.name == version,
).first()
if tag_record:
artifact = db.query(Artifact).filter(
Artifact.id == tag_record.artifact_id
).first()
if artifact:
return (artifact.id, version, artifact.size)
if tag:
# Look up by tag
tag_record = db.query(Tag).filter(
Tag.package_id == package.id,
Tag.name == tag,
).first()
if tag_record:
artifact = db.query(Artifact).filter(
Artifact.id == tag_record.artifact_id
).first()
if artifact:
return (artifact.id, tag, artifact.size)
return None
@@ -488,16 +403,10 @@ def _detect_package_cycle(
Returns:
Cycle path if detected, None otherwise
"""
# Normalize names for comparison (handles extras like [test] and separators)
pkg_normalized = _normalize_pypi_package_name(package_name)
target_pkg_normalized = _normalize_pypi_package_name(target_package)
# Use normalized key for tracking
pkg_key = f"{project_name.lower()}/{pkg_normalized}"
pkg_key = f"{project_name}/{package_name}"
# Check if we've reached the target package (cycle detected)
# Use normalized comparison to handle extras and naming variations
if project_name.lower() == target_project.lower() and pkg_normalized == target_pkg_normalized:
if project_name == target_project and package_name == target_package:
return path + [pkg_key]
if pkg_key in visiting:
@@ -518,9 +427,9 @@ def _detect_package_cycle(
Package.name == package_name,
).first()
if package:
# Find all artifacts in this package via versions
versions = db.query(PackageVersion).filter(PackageVersion.package_id == package.id).all()
artifact_ids = {v.artifact_id for v in versions}
# Find all artifacts in this package via tags
tags = db.query(Tag).filter(Tag.package_id == package.id).all()
artifact_ids = {t.artifact_id for t in tags}
# Get dependencies from all artifacts in this package
for artifact_id in artifact_ids:
@@ -563,8 +472,8 @@ def check_circular_dependencies(
db: Database session
artifact_id: The artifact that will have these dependencies
new_dependencies: Dependencies to be added
project_name: Project name (optional, will try to look up from version if not provided)
package_name: Package name (optional, will try to look up from version if not provided)
project_name: Project name (optional, will try to look up from tag if not provided)
package_name: Package name (optional, will try to look up from tag if not provided)
Returns:
Cycle path if detected, None otherwise
@@ -573,19 +482,17 @@ def check_circular_dependencies(
if project_name and package_name:
current_path = f"{project_name}/{package_name}"
else:
# Try to look up from version
# Try to look up from tag
artifact = db.query(Artifact).filter(Artifact.id == artifact_id).first()
if not artifact:
return None
# Find package for this artifact via version
version_record = db.query(PackageVersion).filter(
PackageVersion.artifact_id == artifact_id
).first()
if not version_record:
# Find package for this artifact
tag = db.query(Tag).filter(Tag.artifact_id == artifact_id).first()
if not tag:
return None
package = db.query(Package).filter(Package.id == version_record.package_id).first()
package = db.query(Package).filter(Package.id == tag.package_id).first()
if not package:
return None
@@ -601,15 +508,12 @@ def check_circular_dependencies(
else:
return None
# Normalize the initial path for consistency with _detect_package_cycle
normalized_path = f"{target_project.lower()}/{_normalize_pypi_package_name(target_package)}"
# For each new dependency, check if it would create a cycle back to our package
for dep in new_dependencies:
# Check if this dependency (transitively) depends on us at the package level
visiting: Set[str] = set()
visited: Set[str] = set()
path: List[str] = [normalized_path]
path: List[str] = [current_path]
# Check from the dependency's package
cycle = _detect_package_cycle(
@@ -642,7 +546,7 @@ def resolve_dependencies(
db: Database session
project_name: Project name
package_name: Package name
ref: Version reference (or artifact:hash)
ref: Tag or version reference
base_url: Base URL for download URLs
Returns:
@@ -665,35 +569,22 @@ def resolve_dependencies(
if not package:
raise DependencyNotFoundError(project_name, package_name, ref)
# Handle artifact: prefix for direct artifact ID references
if ref.startswith("artifact:"):
artifact_id = ref[9:]
artifact = db.query(Artifact).filter(Artifact.id == artifact_id).first()
if not artifact:
raise DependencyNotFoundError(project_name, package_name, ref)
root_artifact_id = artifact.id
root_version = artifact_id[:12] # Use short hash as version display
root_size = artifact.size
else:
# Try to find artifact by version
resolved = _resolve_dependency_to_artifact(
db, project_name, package_name, ref
)
if not resolved:
raise DependencyNotFoundError(project_name, package_name, ref)
root_artifact_id, root_version, root_size = resolved
# Try to find artifact by tag or version
resolved = _resolve_dependency_to_artifact(
db, project_name, package_name, ref, ref
)
if not resolved:
raise DependencyNotFoundError(project_name, package_name, ref)
root_artifact_id, root_version, root_size = resolved
# Track resolved artifacts and their versions
resolved_artifacts: Dict[str, ResolvedArtifact] = {}
# Track missing dependencies (not cached on server)
missing_dependencies: List[MissingDependency] = []
# Track version requirements for conflict detection
version_requirements: Dict[str, List[Dict[str, Any]]] = {} # pkg_key -> [(version, required_by)]
# Track visiting/visited for cycle detection
visiting: Set[str] = set()
visited: Set[str] = set()
# Track the current path for cycle reporting (artifact_id -> pkg_key)
current_path: Dict[str, str] = {}
# Resolution order (topological)
resolution_order: List[str] = []
@@ -715,10 +606,8 @@ def resolve_dependencies(
# Cycle detection (at artifact level)
if artifact_id in visiting:
# Build cycle path from current_path
cycle_start = current_path.get(artifact_id, pkg_key)
cycle = [cycle_start, pkg_key]
raise CircularDependencyError(cycle)
# Build cycle path
raise CircularDependencyError([pkg_key, pkg_key])
# Conflict detection - check if we've seen this package before with a different version
if pkg_key in version_requirements:
@@ -749,7 +638,6 @@ def resolve_dependencies(
return
visiting.add(artifact_id)
current_path[artifact_id] = pkg_key
# Track version requirement
if pkg_key not in version_requirements:
@@ -766,39 +654,23 @@ def resolve_dependencies(
# Resolve each dependency first (depth-first)
for dep in deps:
# Skip self-dependencies (can happen with PyPI extras like pytest[testing])
# Use normalized comparison for PyPI naming conventions (handles extras, separators)
dep_proj_normalized = dep.dependency_project.lower()
dep_pkg_normalized = _normalize_pypi_package_name(dep.dependency_package)
curr_proj_normalized = proj_name.lower()
curr_pkg_normalized = _normalize_pypi_package_name(pkg_name)
if dep_proj_normalized == curr_proj_normalized and dep_pkg_normalized == curr_pkg_normalized:
continue
resolved_dep = _resolve_dependency_to_artifact(
db,
dep.dependency_project,
dep.dependency_package,
dep.version_constraint,
dep.tag_constraint,
)
if not resolved_dep:
# Dependency not cached on server - track as missing but continue
constraint = dep.version_constraint
missing_dependencies.append(MissingDependency(
project=dep.dependency_project,
package=dep.dependency_package,
constraint=constraint,
required_by=pkg_key,
))
continue
constraint = dep.version_constraint or dep.tag_constraint
raise DependencyNotFoundError(
dep.dependency_project,
dep.dependency_package,
constraint,
)
dep_artifact_id, dep_version, dep_size = resolved_dep
# Skip if resolved to same artifact (self-dependency at artifact level)
if dep_artifact_id == artifact_id:
continue
_resolve_recursive(
dep_artifact_id,
dep.dependency_project,
@@ -810,7 +682,6 @@ def resolve_dependencies(
)
visiting.remove(artifact_id)
del current_path[artifact_id]
visited.add(artifact_id)
# Add to resolution order (dependencies before dependents)
@@ -847,7 +718,6 @@ def resolve_dependencies(
"ref": ref,
},
resolved=resolved_list,
missing=missing_dependencies,
total_size=total_size,
artifact_count=len(resolved_list),
)

View File

@@ -1,160 +0,0 @@
"""
Encryption utilities for sensitive data storage.
Uses Fernet symmetric encryption for credentials like upstream passwords.
The encryption key is sourced from ORCHARD_CACHE_ENCRYPTION_KEY environment variable.
If not set, a random key is generated on startup (with a warning).
"""
import base64
import logging
import os
import secrets
from functools import lru_cache
from typing import Optional
from cryptography.fernet import Fernet, InvalidToken
logger = logging.getLogger(__name__)
# Module-level storage for auto-generated key (only used if env var not set)
_generated_key: Optional[bytes] = None
def _get_key_from_env() -> Optional[bytes]:
"""Get encryption key from environment variable."""
key_str = os.environ.get("ORCHARD_CACHE_ENCRYPTION_KEY", "")
if not key_str:
return None
# Support both raw base64 and url-safe base64 formats
try:
# Try to decode as-is (Fernet keys are url-safe base64)
key_bytes = key_str.encode("utf-8")
# Validate it's a valid Fernet key by trying to create a Fernet instance
Fernet(key_bytes)
return key_bytes
except Exception:
pass
# Try base64 decoding if it's a raw 32-byte key encoded as base64
try:
decoded = base64.urlsafe_b64decode(key_str)
if len(decoded) == 32:
# Re-encode as url-safe base64 for Fernet
key_bytes = base64.urlsafe_b64encode(decoded)
Fernet(key_bytes)
return key_bytes
except Exception:
pass
logger.error(
"ORCHARD_CACHE_ENCRYPTION_KEY is set but invalid. "
"Must be a valid Fernet key (32 bytes, url-safe base64 encoded). "
"Generate one with: python -c \"from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())\""
)
return None
def get_encryption_key() -> bytes:
"""
Get the Fernet encryption key.
Returns the key from ORCHARD_CACHE_ENCRYPTION_KEY if set and valid,
otherwise generates a random key (with a warning logged).
The generated key is cached for the lifetime of the process.
"""
global _generated_key
# Try to get from environment
env_key = _get_key_from_env()
if env_key:
return env_key
# Generate a new key if needed
if _generated_key is None:
_generated_key = Fernet.generate_key()
logger.warning(
"ORCHARD_CACHE_ENCRYPTION_KEY not set - using auto-generated key. "
"Encrypted credentials will be lost on restart! "
"Set ORCHARD_CACHE_ENCRYPTION_KEY for persistent encryption. "
"Generate a key with: python -c \"from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())\""
)
return _generated_key
@lru_cache(maxsize=1)
def _get_fernet() -> Fernet:
"""Get a cached Fernet instance."""
return Fernet(get_encryption_key())
def encrypt_value(plaintext: str) -> bytes:
"""
Encrypt a string value using Fernet.
Args:
plaintext: The string to encrypt
Returns:
Encrypted bytes (includes Fernet token with timestamp)
"""
if not plaintext:
raise ValueError("Cannot encrypt empty value")
fernet = _get_fernet()
return fernet.encrypt(plaintext.encode("utf-8"))
def decrypt_value(ciphertext: bytes) -> str:
"""
Decrypt a Fernet-encrypted value.
Args:
ciphertext: The encrypted bytes
Returns:
Decrypted string
Raises:
InvalidToken: If decryption fails (wrong key or corrupted data)
"""
if not ciphertext:
raise ValueError("Cannot decrypt empty value")
fernet = _get_fernet()
return fernet.decrypt(ciphertext).decode("utf-8")
def can_decrypt(ciphertext: bytes) -> bool:
"""
Check if a value can be decrypted with the current key.
Useful for checking if credentials are still valid after key rotation.
Args:
ciphertext: The encrypted bytes
Returns:
True if decryption succeeds, False otherwise
"""
if not ciphertext:
return False
try:
decrypt_value(ciphertext)
return True
except (InvalidToken, ValueError):
return False
def generate_key() -> str:
"""
Generate a new Fernet encryption key.
Returns:
A valid Fernet key as a string (url-safe base64 encoded)
"""
return Fernet.generate_key().decode("utf-8")

View File

@@ -1,179 +0,0 @@
"""
HTTP client manager with connection pooling and lifecycle management.
Provides:
- Shared connection pools for upstream requests
- Per-upstream client isolation when needed
- Thread pool for blocking I/O operations
- FastAPI lifespan integration
"""
import asyncio
import logging
from concurrent.futures import ThreadPoolExecutor
from typing import Any, Callable, Optional
import httpx
from .config import Settings
logger = logging.getLogger(__name__)
class HttpClientManager:
"""
Manages httpx.AsyncClient pools with FastAPI lifespan integration.
Features:
- Default shared pool for general requests
- Per-upstream pools for sources needing specific config/auth
- Dedicated thread pool for blocking operations
- Graceful shutdown
"""
def __init__(self, settings: Settings):
self.max_connections = settings.http_max_connections
self.max_keepalive = settings.http_max_keepalive
self.connect_timeout = settings.http_connect_timeout
self.read_timeout = settings.http_read_timeout
self.worker_threads = settings.http_worker_threads
self._default_client: Optional[httpx.AsyncClient] = None
self._upstream_clients: dict[str, httpx.AsyncClient] = {}
self._executor: Optional[ThreadPoolExecutor] = None
self._started = False
async def startup(self) -> None:
"""Initialize clients and thread pool. Called by FastAPI lifespan."""
if self._started:
return
logger.info(
f"Starting HttpClientManager: max_connections={self.max_connections}, "
f"worker_threads={self.worker_threads}"
)
# Create connection limits
limits = httpx.Limits(
max_connections=self.max_connections,
max_keepalive_connections=self.max_keepalive,
)
# Create timeout config
timeout = httpx.Timeout(
connect=self.connect_timeout,
read=self.read_timeout,
write=self.read_timeout,
pool=self.connect_timeout,
)
# Create default client
self._default_client = httpx.AsyncClient(
limits=limits,
timeout=timeout,
follow_redirects=False, # Handle redirects manually for auth
)
# Create thread pool for blocking operations
self._executor = ThreadPoolExecutor(
max_workers=self.worker_threads,
thread_name_prefix="orchard-blocking-",
)
self._started = True
logger.info("HttpClientManager started")
async def shutdown(self) -> None:
"""Close all clients and thread pool. Called by FastAPI lifespan."""
if not self._started:
return
logger.info("Shutting down HttpClientManager")
# Close default client
if self._default_client:
await self._default_client.aclose()
self._default_client = None
# Close upstream-specific clients
for name, client in self._upstream_clients.items():
logger.debug(f"Closing upstream client: {name}")
await client.aclose()
self._upstream_clients.clear()
# Shutdown thread pool
if self._executor:
self._executor.shutdown(wait=True)
self._executor = None
self._started = False
logger.info("HttpClientManager shutdown complete")
def get_client(self, upstream_name: Optional[str] = None) -> httpx.AsyncClient:
"""
Get HTTP client for making requests.
Args:
upstream_name: Optional upstream source name for dedicated pool.
If None, returns the default shared client.
Returns:
httpx.AsyncClient configured for the request.
Raises:
RuntimeError: If manager not started.
"""
if not self._started or not self._default_client:
raise RuntimeError("HttpClientManager not started. Call startup() first.")
if upstream_name and upstream_name in self._upstream_clients:
return self._upstream_clients[upstream_name]
return self._default_client
async def run_blocking(self, func: Callable[..., Any], *args: Any) -> Any:
"""
Run a blocking function in the thread pool.
Use this for:
- File I/O operations
- Archive extraction (zipfile, tarfile)
- Hash computation on large data
Args:
func: Synchronous function to execute
*args: Arguments to pass to the function
Returns:
The function's return value.
"""
if not self._executor:
raise RuntimeError("HttpClientManager not started. Call startup() first.")
loop = asyncio.get_event_loop()
return await loop.run_in_executor(self._executor, func, *args)
@property
def active_connections(self) -> int:
"""Get approximate number of active connections (for health checks)."""
if not self._default_client:
return 0
# httpx doesn't expose this directly, return pool size as approximation
return self.max_connections
@property
def pool_size(self) -> int:
"""Get configured pool size."""
return self.max_connections
@property
def executor_active(self) -> int:
"""Get number of active thread pool workers."""
if not self._executor:
return 0
return len(self._executor._threads)
@property
def executor_max(self) -> int:
"""Get max thread pool workers."""
return self.worker_threads

View File

@@ -11,12 +11,9 @@ from slowapi.errors import RateLimitExceeded
from .config import get_settings
from .database import init_db, SessionLocal
from .routes import router
from .pypi_proxy import router as pypi_router
from .seed import seed_database
from .auth import create_default_admin
from .rate_limit import limiter
from .http_client import HttpClientManager
from .cache_service import CacheService
settings = get_settings()
logging.basicConfig(level=logging.INFO)
@@ -40,17 +37,6 @@ async def lifespan(app: FastAPI):
finally:
db.close()
# Initialize infrastructure services
logger.info("Initializing infrastructure services...")
app.state.http_client = HttpClientManager(settings)
await app.state.http_client.startup()
app.state.cache = CacheService(settings)
await app.state.cache.startup()
logger.info("Infrastructure services ready")
# Seed test data in development mode
if settings.is_development:
logger.info(f"Running in {settings.env} mode - checking for seed data")
@@ -63,12 +49,7 @@ async def lifespan(app: FastAPI):
logger.info(f"Running in {settings.env} mode - skipping seed data")
yield
# Shutdown infrastructure services
logger.info("Shutting down infrastructure services...")
await app.state.http_client.shutdown()
await app.state.cache.shutdown()
logger.info("Shutdown complete")
# Shutdown: cleanup if needed
app = FastAPI(
@@ -84,7 +65,6 @@ app.add_exception_handler(RateLimitExceeded, _rate_limit_exceeded_handler)
# Include API routes
app.include_router(router)
app.include_router(pypi_router)
# Serve static files (React build) if the directory exists
static_dir = os.path.join(os.path.dirname(__file__), "..", "..", "frontend", "dist")

View File

@@ -12,7 +12,6 @@ from sqlalchemy import (
Index,
JSON,
ARRAY,
LargeBinary,
)
from sqlalchemy.dialects.postgresql import UUID
from sqlalchemy.orm import relationship, declarative_base
@@ -28,7 +27,6 @@ class Project(Base):
name = Column(String(255), unique=True, nullable=False)
description = Column(Text)
is_public = Column(Boolean, default=True)
is_system = Column(Boolean, default=False, nullable=False)
created_at = Column(DateTime(timezone=True), default=datetime.utcnow)
updated_at = Column(
DateTime(timezone=True), default=datetime.utcnow, onupdate=datetime.utcnow
@@ -48,7 +46,6 @@ class Project(Base):
Index("idx_projects_name", "name"),
Index("idx_projects_created_by", "created_by"),
Index("idx_projects_team_id", "team_id"),
Index("idx_projects_is_system", "is_system"),
)
@@ -71,6 +68,7 @@ class Package(Base):
)
project = relationship("Project", back_populates="packages")
tags = relationship("Tag", back_populates="package", cascade="all, delete-orphan")
uploads = relationship(
"Upload", back_populates="package", cascade="all, delete-orphan"
)
@@ -119,6 +117,7 @@ class Artifact(Base):
ref_count = Column(Integer, default=1)
s3_key = Column(String(1024), nullable=False)
tags = relationship("Tag", back_populates="artifact")
uploads = relationship("Upload", back_populates="artifact")
versions = relationship("PackageVersion", back_populates="artifact")
dependencies = relationship(
@@ -149,6 +148,65 @@ class Artifact(Base):
)
class Tag(Base):
__tablename__ = "tags"
id = Column(UUID(as_uuid=True), primary_key=True, default=uuid.uuid4)
package_id = Column(
UUID(as_uuid=True),
ForeignKey("packages.id", ondelete="CASCADE"),
nullable=False,
)
name = Column(String(255), nullable=False)
artifact_id = Column(String(64), ForeignKey("artifacts.id"), nullable=False)
created_at = Column(DateTime(timezone=True), default=datetime.utcnow)
updated_at = Column(
DateTime(timezone=True), default=datetime.utcnow, onupdate=datetime.utcnow
)
created_by = Column(String(255), nullable=False)
package = relationship("Package", back_populates="tags")
artifact = relationship("Artifact", back_populates="tags")
history = relationship(
"TagHistory", back_populates="tag", cascade="all, delete-orphan"
)
__table_args__ = (
Index("idx_tags_package_id", "package_id"),
Index("idx_tags_artifact_id", "artifact_id"),
Index(
"idx_tags_package_name", "package_id", "name", unique=True
), # Composite unique index
Index(
"idx_tags_package_created_at", "package_id", "created_at"
), # For recent tags queries
)
class TagHistory(Base):
__tablename__ = "tag_history"
id = Column(UUID(as_uuid=True), primary_key=True, default=uuid.uuid4)
tag_id = Column(
UUID(as_uuid=True), ForeignKey("tags.id", ondelete="CASCADE"), nullable=False
)
old_artifact_id = Column(String(64), ForeignKey("artifacts.id"))
new_artifact_id = Column(String(64), ForeignKey("artifacts.id"), nullable=False)
change_type = Column(String(20), nullable=False, default="update")
changed_at = Column(DateTime(timezone=True), default=datetime.utcnow)
changed_by = Column(String(255), nullable=False)
tag = relationship("Tag", back_populates="history")
__table_args__ = (
Index("idx_tag_history_tag_id", "tag_id"),
Index("idx_tag_history_changed_at", "changed_at"),
CheckConstraint(
"change_type IN ('create', 'update', 'delete')", name="check_change_type"
),
)
class PackageVersion(Base):
"""Immutable version record for a package-artifact relationship.
@@ -188,7 +246,7 @@ class Upload(Base):
artifact_id = Column(String(64), ForeignKey("artifacts.id"), nullable=False)
package_id = Column(UUID(as_uuid=True), ForeignKey("packages.id"), nullable=False)
original_name = Column(String(1024))
version = Column(String(255)) # Version assigned during upload
tag_name = Column(String(255)) # Tag assigned during upload
user_agent = Column(String(512)) # Client identification
duration_ms = Column(Integer) # Upload timing in milliseconds
deduplicated = Column(Boolean, default=False) # Whether artifact was deduplicated
@@ -463,8 +521,8 @@ class PackageHistory(Base):
class ArtifactDependency(Base):
"""Dependency declared by an artifact on another package.
Each artifact can declare dependencies on other packages, specifying a version.
This enables recursive dependency resolution.
Each artifact can declare dependencies on other packages, specifying either
an exact version or a tag. This enables recursive dependency resolution.
"""
__tablename__ = "artifact_dependencies"
@@ -477,13 +535,20 @@ class ArtifactDependency(Base):
)
dependency_project = Column(String(255), nullable=False)
dependency_package = Column(String(255), nullable=False)
version_constraint = Column(String(255), nullable=False)
version_constraint = Column(String(255), nullable=True)
tag_constraint = Column(String(255), nullable=True)
created_at = Column(DateTime(timezone=True), default=datetime.utcnow)
# Relationship to the artifact that declares this dependency
artifact = relationship("Artifact", back_populates="dependencies")
__table_args__ = (
# Exactly one of version_constraint or tag_constraint must be set
CheckConstraint(
"(version_constraint IS NOT NULL AND tag_constraint IS NULL) OR "
"(version_constraint IS NULL AND tag_constraint IS NOT NULL)",
name="check_constraint_type",
),
# Each artifact can only depend on a specific project/package once
Index(
"idx_artifact_dependencies_artifact_id",
@@ -572,166 +637,3 @@ class TeamMembership(Base):
name="check_team_role",
),
)
# =============================================================================
# Upstream Caching Models
# =============================================================================
# Valid source types for upstream registries
SOURCE_TYPES = ["npm", "pypi", "maven", "docker", "helm", "nuget", "deb", "rpm", "generic"]
# Valid authentication types
AUTH_TYPES = ["none", "basic", "bearer", "api_key"]
class UpstreamSource(Base):
"""Configuration for an upstream artifact registry.
Stores connection details and authentication for upstream registries
like npm, PyPI, Maven Central, or private Artifactory instances.
"""
__tablename__ = "upstream_sources"
id = Column(UUID(as_uuid=True), primary_key=True, default=uuid.uuid4)
name = Column(String(255), unique=True, nullable=False)
source_type = Column(String(50), default="generic", nullable=False)
url = Column(String(2048), nullable=False)
enabled = Column(Boolean, default=False, nullable=False)
auth_type = Column(String(20), default="none", nullable=False)
username = Column(String(255))
password_encrypted = Column(LargeBinary)
headers_encrypted = Column(LargeBinary)
priority = Column(Integer, default=100, nullable=False)
created_at = Column(DateTime(timezone=True), default=datetime.utcnow)
updated_at = Column(
DateTime(timezone=True), default=datetime.utcnow, onupdate=datetime.utcnow
)
# Relationships
cached_urls = relationship("CachedUrl", back_populates="source")
__table_args__ = (
Index("idx_upstream_sources_enabled", "enabled"),
Index("idx_upstream_sources_source_type", "source_type"),
Index("idx_upstream_sources_priority", "priority"),
CheckConstraint(
"source_type IN ('npm', 'pypi', 'maven', 'docker', 'helm', 'nuget', 'deb', 'rpm', 'generic')",
name="check_source_type",
),
CheckConstraint(
"auth_type IN ('none', 'basic', 'bearer', 'api_key')",
name="check_auth_type",
),
CheckConstraint("priority > 0", name="check_priority_positive"),
)
def set_password(self, password: str) -> None:
"""Encrypt and store a password/token."""
from .encryption import encrypt_value
if password:
self.password_encrypted = encrypt_value(password)
else:
self.password_encrypted = None
def get_password(self) -> str | None:
"""Decrypt and return the stored password/token."""
from .encryption import decrypt_value
if self.password_encrypted:
try:
return decrypt_value(self.password_encrypted)
except Exception:
return None
return None
def has_password(self) -> bool:
"""Check if a password/token is stored."""
return self.password_encrypted is not None
def set_headers(self, headers: dict) -> None:
"""Encrypt and store custom headers as JSON."""
from .encryption import encrypt_value
import json
if headers:
self.headers_encrypted = encrypt_value(json.dumps(headers))
else:
self.headers_encrypted = None
def get_headers(self) -> dict | None:
"""Decrypt and return custom headers."""
from .encryption import decrypt_value
import json
if self.headers_encrypted:
try:
return json.loads(decrypt_value(self.headers_encrypted))
except Exception:
return None
return None
class CacheSettings(Base):
"""Global cache settings (singleton table).
Controls behavior of the upstream caching system.
"""
__tablename__ = "cache_settings"
id = Column(Integer, primary_key=True, default=1)
auto_create_system_projects = Column(Boolean, default=True, nullable=False)
created_at = Column(DateTime(timezone=True), default=datetime.utcnow)
updated_at = Column(
DateTime(timezone=True), default=datetime.utcnow, onupdate=datetime.utcnow
)
__table_args__ = (
CheckConstraint("id = 1", name="check_cache_settings_singleton"),
)
class CachedUrl(Base):
"""Tracks URL to artifact mappings for provenance.
Records which URLs have been cached and maps them to their stored artifacts.
Enables "is this URL already cached?" lookups and audit trails.
"""
__tablename__ = "cached_urls"
id = Column(UUID(as_uuid=True), primary_key=True, default=uuid.uuid4)
url = Column(String(4096), nullable=False)
url_hash = Column(String(64), unique=True, nullable=False)
artifact_id = Column(
String(64), ForeignKey("artifacts.id"), nullable=False
)
source_id = Column(
UUID(as_uuid=True),
ForeignKey("upstream_sources.id", ondelete="SET NULL"),
)
fetched_at = Column(DateTime(timezone=True), default=datetime.utcnow, nullable=False)
response_headers = Column(JSON, default=dict)
created_at = Column(DateTime(timezone=True), default=datetime.utcnow)
# Relationships
artifact = relationship("Artifact")
source = relationship("UpstreamSource", back_populates="cached_urls")
__table_args__ = (
Index("idx_cached_urls_url_hash", "url_hash"),
Index("idx_cached_urls_artifact_id", "artifact_id"),
Index("idx_cached_urls_source_id", "source_id"),
Index("idx_cached_urls_fetched_at", "fetched_at"),
)
@staticmethod
def compute_url_hash(url: str) -> str:
"""Compute SHA256 hash of a URL for fast lookups."""
import hashlib
return hashlib.sha256(url.encode("utf-8")).hexdigest()

View File

@@ -1,202 +0,0 @@
"""
Purge seed/demo data from the database.
This is used when transitioning an environment from dev/test to production-like.
Triggered by setting ORCHARD_PURGE_SEED_DATA=true environment variable.
"""
import logging
import os
from sqlalchemy.orm import Session
from .models import (
Project,
Package,
Artifact,
Upload,
PackageVersion,
ArtifactDependency,
Team,
TeamMembership,
User,
AccessPermission,
)
from .storage import get_storage
logger = logging.getLogger(__name__)
# Seed data identifiers (from seed.py)
SEED_PROJECT_NAMES = [
"frontend-libs",
"backend-services",
"mobile-apps",
"internal-tools",
]
SEED_TEAM_SLUG = "demo-team"
SEED_USERNAMES = [
"alice",
"bob",
"charlie",
"diana",
"eve",
"frank",
]
def should_purge_seed_data() -> bool:
"""Check if seed data should be purged based on environment variable."""
return os.environ.get("ORCHARD_PURGE_SEED_DATA", "").lower() == "true"
def purge_seed_data(db: Session) -> dict:
"""
Purge all seed/demo data from the database.
Returns a dict with counts of deleted items.
"""
logger.warning("PURGING SEED DATA - This will delete demo projects, users, and teams")
results = {
"dependencies_deleted": 0,
"versions_deleted": 0,
"uploads_deleted": 0,
"artifacts_deleted": 0,
"packages_deleted": 0,
"projects_deleted": 0,
"permissions_deleted": 0,
"team_memberships_deleted": 0,
"users_deleted": 0,
"teams_deleted": 0,
"s3_objects_deleted": 0,
}
storage = get_storage()
# Find seed projects
seed_projects = db.query(Project).filter(Project.name.in_(SEED_PROJECT_NAMES)).all()
seed_project_ids = [p.id for p in seed_projects]
if not seed_projects:
logger.info("No seed projects found, nothing to purge")
return results
logger.info(f"Found {len(seed_projects)} seed projects to purge")
# Find packages in seed projects
seed_packages = db.query(Package).filter(Package.project_id.in_(seed_project_ids)).all()
seed_package_ids = [p.id for p in seed_packages]
# Find artifacts in seed packages (via uploads)
seed_uploads = db.query(Upload).filter(Upload.package_id.in_(seed_package_ids)).all()
seed_artifact_ids = list(set(u.artifact_id for u in seed_uploads))
# Delete in order (respecting foreign keys)
# 1. Delete artifact dependencies
if seed_artifact_ids:
count = db.query(ArtifactDependency).filter(
ArtifactDependency.artifact_id.in_(seed_artifact_ids)
).delete(synchronize_session=False)
results["dependencies_deleted"] = count
logger.info(f"Deleted {count} artifact dependencies")
# 2. Delete package versions
if seed_package_ids:
count = db.query(PackageVersion).filter(
PackageVersion.package_id.in_(seed_package_ids)
).delete(synchronize_session=False)
results["versions_deleted"] = count
logger.info(f"Deleted {count} package versions")
# 3. Delete uploads
if seed_package_ids:
count = db.query(Upload).filter(Upload.package_id.in_(seed_package_ids)).delete(
synchronize_session=False
)
results["uploads_deleted"] = count
logger.info(f"Deleted {count} uploads")
# 4. Delete S3 objects for seed artifacts
if seed_artifact_ids:
seed_artifacts = db.query(Artifact).filter(Artifact.id.in_(seed_artifact_ids)).all()
for artifact in seed_artifacts:
if artifact.s3_key:
try:
storage.client.delete_object(Bucket=storage.bucket, Key=artifact.s3_key)
results["s3_objects_deleted"] += 1
except Exception as e:
logger.warning(f"Failed to delete S3 object {artifact.s3_key}: {e}")
logger.info(f"Deleted {results['s3_objects_deleted']} S3 objects")
# 5. Delete artifacts (only those with ref_count that would be 0 after our deletions)
# Since we deleted all versions pointing to these artifacts, we can delete them
if seed_artifact_ids:
count = db.query(Artifact).filter(Artifact.id.in_(seed_artifact_ids)).delete(
synchronize_session=False
)
results["artifacts_deleted"] = count
logger.info(f"Deleted {count} artifacts")
# 6. Delete packages
if seed_package_ids:
count = db.query(Package).filter(Package.id.in_(seed_package_ids)).delete(
synchronize_session=False
)
results["packages_deleted"] = count
logger.info(f"Deleted {count} packages")
# 7. Delete access permissions for seed projects
if seed_project_ids:
count = db.query(AccessPermission).filter(
AccessPermission.project_id.in_(seed_project_ids)
).delete(synchronize_session=False)
results["permissions_deleted"] = count
logger.info(f"Deleted {count} access permissions")
# 8. Delete seed projects
count = db.query(Project).filter(Project.name.in_(SEED_PROJECT_NAMES)).delete(
synchronize_session=False
)
results["projects_deleted"] = count
logger.info(f"Deleted {count} projects")
# 9. Find and delete seed team
seed_team = db.query(Team).filter(Team.slug == SEED_TEAM_SLUG).first()
if seed_team:
# Delete team memberships first
count = db.query(TeamMembership).filter(
TeamMembership.team_id == seed_team.id
).delete(synchronize_session=False)
results["team_memberships_deleted"] = count
logger.info(f"Deleted {count} team memberships")
# Delete the team
db.delete(seed_team)
results["teams_deleted"] = 1
logger.info(f"Deleted team: {SEED_TEAM_SLUG}")
# 10. Delete seed users (but NOT admin)
seed_users = db.query(User).filter(User.username.in_(SEED_USERNAMES)).all()
for user in seed_users:
# Delete any remaining team memberships for this user
db.query(TeamMembership).filter(TeamMembership.user_id == user.id).delete(
synchronize_session=False
)
# Delete any access permissions for this user
# Note: AccessPermission.user_id is VARCHAR (username), not UUID
db.query(AccessPermission).filter(AccessPermission.user_id == user.username).delete(
synchronize_session=False
)
db.delete(user)
results["users_deleted"] += 1
if results["users_deleted"] > 0:
logger.info(f"Deleted {results['users_deleted']} seed users")
db.commit()
logger.warning("SEED DATA PURGE COMPLETE")
logger.info(f"Purge results: {results}")
return results

View File

@@ -1,968 +0,0 @@
"""
Transparent PyPI proxy implementing PEP 503 (Simple API).
Provides endpoints that allow pip to use Orchard as a PyPI index URL.
Artifacts are cached on first access through configured upstream sources.
"""
import hashlib
import json
import logging
import os
import re
import tarfile
import tempfile
import zipfile
from io import BytesIO
from typing import Optional, List, Tuple
from urllib.parse import urljoin, urlparse, quote, unquote
import httpx
from fastapi import APIRouter, Depends, HTTPException, Request, Response
from fastapi.responses import StreamingResponse, HTMLResponse, RedirectResponse
from sqlalchemy.orm import Session
from .database import get_db
from .models import UpstreamSource, CachedUrl, Artifact, Project, Package, PackageVersion
from .storage import S3Storage, get_storage
from .config import get_env_upstream_sources, get_settings
from .http_client import HttpClientManager
from .cache_service import CacheService, CacheCategory
from .db_utils import ArtifactRepository
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/pypi", tags=["pypi-proxy"])
def get_http_client(request: Request) -> HttpClientManager:
"""Get HttpClientManager from app state."""
return request.app.state.http_client
def get_cache(request: Request) -> CacheService:
"""Get CacheService from app state."""
return request.app.state.cache
# Timeout configuration for proxy requests
PROXY_CONNECT_TIMEOUT = 30.0
PROXY_READ_TIMEOUT = 60.0
def _parse_requires_dist(requires_dist: str) -> Tuple[str, Optional[str]]:
"""Parse a Requires-Dist line into (package_name, version_constraint).
Examples:
"requests (>=2.25.0)" -> ("requests", ">=2.25.0")
"typing-extensions; python_version < '3.8'" -> ("typing-extensions", None)
"numpy>=1.21.0" -> ("numpy", ">=1.21.0")
"certifi" -> ("certifi", None)
Returns:
Tuple of (normalized_package_name, version_constraint or None)
"""
# Remove any environment markers (after semicolon)
if ';' in requires_dist:
requires_dist = requires_dist.split(';')[0].strip()
# Match patterns like "package (>=1.0)" or "package>=1.0" or "package"
match = re.match(
r'^([a-zA-Z0-9][-a-zA-Z0-9._]*)\s*(?:\(([^)]+)\)|([<>=!~][^\s;]+))?',
requires_dist.strip()
)
if not match:
return None, None
package_name = match.group(1)
# Version can be in parentheses (group 2) or directly after name (group 3)
version_constraint = match.group(2) or match.group(3)
# Normalize package name (PEP 503)
normalized_name = re.sub(r'[-_.]+', '-', package_name).lower()
# Clean up version constraint
if version_constraint:
version_constraint = version_constraint.strip()
return normalized_name, version_constraint
def _extract_requires_from_metadata(metadata_content: str) -> List[Tuple[str, Optional[str]]]:
"""Extract all Requires-Dist entries from METADATA/PKG-INFO content.
Args:
metadata_content: The content of a METADATA or PKG-INFO file
Returns:
List of (package_name, version_constraint) tuples
"""
dependencies = []
for line in metadata_content.split('\n'):
if line.startswith('Requires-Dist:'):
value = line[len('Requires-Dist:'):].strip()
pkg_name, version = _parse_requires_dist(value)
if pkg_name:
dependencies.append((pkg_name, version))
return dependencies
def _extract_metadata_from_wheel(file_path: str) -> Optional[str]:
"""Extract METADATA file content from a wheel (zip) file.
Args:
file_path: Path to the wheel file
Returns:
METADATA file content as string, or None if not found
"""
try:
with zipfile.ZipFile(file_path) as zf:
for name in zf.namelist():
if name.endswith('.dist-info/METADATA'):
return zf.read(name).decode('utf-8', errors='replace')
except Exception as e:
logger.warning(f"Failed to extract metadata from wheel: {e}")
return None
def _extract_metadata_from_sdist(file_path: str) -> Optional[str]:
"""Extract PKG-INFO file content from a source distribution (.tar.gz).
Args:
file_path: Path to the tarball file
Returns:
PKG-INFO file content as string, or None if not found
"""
try:
with tarfile.open(file_path, mode='r:gz') as tf:
for member in tf.getmembers():
if member.name.endswith('/PKG-INFO') and member.name.count('/') == 1:
f = tf.extractfile(member)
if f:
return f.read().decode('utf-8', errors='replace')
except Exception as e:
logger.warning(f"Failed to extract metadata from sdist: {e}")
return None
def _extract_dependencies_from_file(file_path: str, filename: str) -> List[Tuple[str, Optional[str]]]:
"""Extract dependencies from a PyPI package file.
Supports wheel (.whl) and source distribution (.tar.gz) formats.
Args:
file_path: Path to the package file
filename: The original filename
Returns:
List of (package_name, version_constraint) tuples
"""
metadata = None
if filename.endswith('.whl'):
metadata = _extract_metadata_from_wheel(file_path)
elif filename.endswith('.tar.gz'):
metadata = _extract_metadata_from_sdist(file_path)
if metadata:
return _extract_requires_from_metadata(metadata)
return []
def _parse_upstream_error(response: httpx.Response) -> str:
"""Parse upstream error response to extract useful error details.
Handles JFrog/Artifactory policy errors and other common formats.
Returns a user-friendly error message.
"""
status = response.status_code
try:
body = response.text
except Exception:
return f"HTTP {status}"
# Try to parse as JSON (JFrog/Artifactory format)
try:
data = json.loads(body)
# JFrog Artifactory format: {"errors": [{"status": 403, "message": "..."}]}
if "errors" in data and isinstance(data["errors"], list):
messages = []
for err in data["errors"]:
if isinstance(err, dict) and "message" in err:
messages.append(err["message"])
if messages:
return "; ".join(messages)
# Alternative format: {"message": "..."}
if "message" in data:
return data["message"]
# Alternative format: {"error": "..."}
if "error" in data:
return data["error"]
except (json.JSONDecodeError, ValueError):
pass
# Check for policy-related keywords in plain text response
policy_keywords = ["policy", "blocked", "forbidden", "curation", "security"]
if any(kw in body.lower() for kw in policy_keywords):
# Truncate long responses but preserve the message
if len(body) > 500:
return body[:500] + "..."
return body
# Default: just return status code
return f"HTTP {status}"
def _extract_pypi_version(filename: str) -> Optional[str]:
"""Extract version from PyPI filename.
Handles formats like:
- cowsay-6.1-py3-none-any.whl
- cowsay-1.0.tar.gz
- some_package-1.2.3.post1-cp39-cp39-linux_x86_64.whl
"""
# Remove extension
if filename.endswith('.whl'):
# Wheel: name-version-pytag-abitag-platform.whl
parts = filename[:-4].split('-')
if len(parts) >= 2:
return parts[1]
elif filename.endswith('.tar.gz'):
# Source: name-version.tar.gz
base = filename[:-7]
# Find the last hyphen that precedes a version-like string
match = re.match(r'^(.+)-(\d+.*)$', base)
if match:
return match.group(2)
elif filename.endswith('.zip'):
# Egg/zip: name-version.zip
base = filename[:-4]
match = re.match(r'^(.+)-(\d+.*)$', base)
if match:
return match.group(2)
return None
async def _get_pypi_upstream_sources_cached(
db: Session,
cache: CacheService,
) -> list[UpstreamSource]:
"""
Get PyPI upstream sources with caching.
Sources are cached for cache_ttl_upstream seconds to avoid
repeated database queries on every request.
"""
cache_key = "sources"
# Try cache first
cached = await cache.get(CacheCategory.UPSTREAM_SOURCES, cache_key, protocol="pypi")
if cached:
source_data = json.loads(cached.decode())
# Reconstruct UpstreamSource-like objects from cached data
# We cache just the essential fields needed for requests
return [type('CachedSource', (), d)() for d in source_data]
# Query database
db_sources = (
db.query(UpstreamSource)
.filter(UpstreamSource.source_type == "pypi", UpstreamSource.enabled == True)
.order_by(UpstreamSource.priority)
.all()
)
# Combine with env sources
env_sources = [s for s in get_env_upstream_sources() if s.source_type == "pypi"]
all_sources = list(db_sources) + list(env_sources)
all_sources = sorted(all_sources, key=lambda s: s.priority)
# Cache the essential fields
if all_sources and cache.enabled:
cache_data = [
{
"name": s.name,
"url": s.url,
"priority": s.priority,
"auth_type": getattr(s, "auth_type", "none"),
"username": getattr(s, "username", None),
"password": getattr(s, "password", None),
}
for s in all_sources
]
await cache.set(
CacheCategory.UPSTREAM_SOURCES,
cache_key,
json.dumps(cache_data).encode(),
protocol="pypi",
)
return all_sources
def _get_pypi_upstream_sources(db: Session) -> list[UpstreamSource]:
"""Get all enabled upstream sources configured for PyPI."""
# Get database sources
db_sources = (
db.query(UpstreamSource)
.filter(
UpstreamSource.source_type == "pypi",
UpstreamSource.enabled == True,
)
.order_by(UpstreamSource.priority)
.all()
)
# Get env sources
env_sources = [
s for s in get_env_upstream_sources()
if s.source_type == "pypi" and s.enabled
]
# Combine and sort by priority
all_sources = list(db_sources) + list(env_sources)
return sorted(all_sources, key=lambda s: s.priority)
def _build_auth_headers(source) -> dict:
"""Build authentication headers for an upstream source."""
headers = {}
if hasattr(source, 'auth_type'):
if source.auth_type == "bearer":
password = source.get_password() if hasattr(source, 'get_password') else getattr(source, 'password', None)
if password:
headers["Authorization"] = f"Bearer {password}"
elif source.auth_type == "api_key":
custom_headers = source.get_headers() if hasattr(source, 'get_headers') else {}
if custom_headers:
headers.update(custom_headers)
return headers
def _get_basic_auth(source) -> Optional[tuple[str, str]]:
"""Get basic auth credentials if applicable."""
if hasattr(source, 'auth_type') and source.auth_type == "basic":
username = getattr(source, 'username', None)
if username:
password = source.get_password() if hasattr(source, 'get_password') else getattr(source, 'password', '')
return (username, password or '')
return None
def _get_base_url(request: Request) -> str:
"""
Get the external base URL, respecting X-Forwarded-Proto header.
When behind a reverse proxy that terminates SSL, the request.base_url
will show http:// even though the external URL is https://. This function
checks the X-Forwarded-Proto header to determine the correct scheme.
"""
base_url = str(request.base_url).rstrip('/')
# Check for X-Forwarded-Proto header (set by reverse proxies)
forwarded_proto = request.headers.get('x-forwarded-proto')
if forwarded_proto:
# Replace the scheme with the forwarded protocol
parsed = urlparse(base_url)
base_url = f"{forwarded_proto}://{parsed.netloc}{parsed.path}"
return base_url
def _rewrite_package_links(html: str, base_url: str, package_name: str, upstream_base_url: str) -> str:
"""
Rewrite download links in a PyPI simple page to go through our proxy.
Args:
html: The HTML content from upstream
base_url: Our server's base URL
package_name: The package name for the URL path
upstream_base_url: The upstream URL used to fetch this page (for resolving relative URLs)
Returns:
HTML with rewritten download links
"""
# Pattern to match href attributes in anchor tags
# PyPI simple pages have links like:
# <a href="https://files.pythonhosted.org/packages/.../file.tar.gz#sha256=...">file.tar.gz</a>
# Or relative URLs from Artifactory like:
# <a href="../../packages/packages/62/35/.../requests-0.10.0.tar.gz#sha256=...">
def replace_href(match):
original_url = match.group(1)
# Resolve relative URLs to absolute using the upstream base URL
if not original_url.startswith(('http://', 'https://')):
# Split off fragment before resolving
url_without_fragment = original_url.split('#')[0]
fragment_part = original_url[len(url_without_fragment):]
absolute_url = urljoin(upstream_base_url, url_without_fragment) + fragment_part
else:
absolute_url = original_url
# Extract the filename from the URL
parsed = urlparse(absolute_url)
path_parts = parsed.path.split('/')
filename = path_parts[-1] if path_parts else ''
# Keep the hash fragment if present
fragment = f"#{parsed.fragment}" if parsed.fragment else ""
# Encode the absolute URL (without fragment) for safe transmission
encoded_url = quote(absolute_url.split('#')[0], safe='')
# Build new URL pointing to our proxy
new_url = f"{base_url}/pypi/simple/{package_name}/{filename}?upstream={encoded_url}{fragment}"
return f'href="{new_url}"'
# Match href="..." patterns
rewritten = re.sub(r'href="([^"]+)"', replace_href, html)
return rewritten
@router.get("/simple/")
async def pypi_simple_index(
request: Request,
db: Session = Depends(get_db),
):
"""
PyPI Simple API index - lists all packages.
Proxies to the first available upstream PyPI source.
"""
sources = _get_pypi_upstream_sources(db)
if not sources:
raise HTTPException(
status_code=503,
detail="No PyPI upstream sources configured"
)
# Try each source in priority order
last_error = None
last_status = None
for source in sources:
try:
headers = {"User-Agent": "Orchard-PyPI-Proxy/1.0"}
headers.update(_build_auth_headers(source))
auth = _get_basic_auth(source)
# Use URL as-is - users should provide full path including /simple
simple_url = source.url.rstrip('/') + '/'
timeout = httpx.Timeout(PROXY_READ_TIMEOUT, connect=PROXY_CONNECT_TIMEOUT)
async with httpx.AsyncClient(timeout=timeout, follow_redirects=False) as client:
response = await client.get(
simple_url,
headers=headers,
auth=auth,
)
# Handle redirects manually to avoid loops
if response.status_code in (301, 302, 303, 307, 308):
redirect_url = response.headers.get('location')
if redirect_url:
# Follow the redirect once
response = await client.get(
redirect_url,
headers=headers,
auth=auth,
follow_redirects=False,
)
if response.status_code == 200:
# Return the index as-is (links are to package pages, not files)
# We could rewrite these too, but for now just proxy
content = response.text
# Rewrite package links to go through our proxy
base_url = _get_base_url(request)
content = re.sub(
r'href="([^"]+)/"',
lambda m: f'href="{base_url}/pypi/simple/{m.group(1)}/"',
content
)
return HTMLResponse(content=content)
# Parse upstream error for policy/blocking messages
last_error = _parse_upstream_error(response)
last_status = response.status_code
logger.warning(f"PyPI proxy: upstream returned {response.status_code}: {last_error}")
except httpx.ConnectError as e:
last_error = f"Connection failed: {e}"
last_status = 502
logger.warning(f"PyPI proxy: failed to connect to {source.url}: {e}")
except httpx.TimeoutException as e:
last_error = f"Timeout: {e}"
last_status = 504
logger.warning(f"PyPI proxy: timeout connecting to {source.url}: {e}")
except Exception as e:
last_error = str(e)
last_status = 502
logger.warning(f"PyPI proxy: error fetching from {source.url}: {e}")
# Pass through 4xx errors (like 403 policy blocks) so users understand why
status_code = last_status if last_status and 400 <= last_status < 500 else 502
raise HTTPException(
status_code=status_code,
detail=f"Upstream error: {last_error}"
)
@router.get("/simple/{package_name}/")
async def pypi_package_versions(
request: Request,
package_name: str,
db: Session = Depends(get_db),
):
"""
PyPI Simple API package page - lists all versions/files for a package.
Proxies to upstream and rewrites download links to go through our cache.
"""
sources = _get_pypi_upstream_sources(db)
if not sources:
raise HTTPException(
status_code=503,
detail="No PyPI upstream sources configured"
)
base_url = _get_base_url(request)
# Normalize package name (PEP 503)
normalized_name = re.sub(r'[-_.]+', '-', package_name).lower()
# Try each source in priority order
last_error = None
last_status = None
for source in sources:
try:
headers = {"User-Agent": "Orchard-PyPI-Proxy/1.0"}
headers.update(_build_auth_headers(source))
auth = _get_basic_auth(source)
# Use URL as-is - users should provide full path including /simple
package_url = source.url.rstrip('/') + f'/{normalized_name}/'
final_url = package_url # Track final URL after redirects
timeout = httpx.Timeout(PROXY_READ_TIMEOUT, connect=PROXY_CONNECT_TIMEOUT)
async with httpx.AsyncClient(timeout=timeout, follow_redirects=False) as client:
response = await client.get(
package_url,
headers=headers,
auth=auth,
)
# Handle redirects manually
redirect_count = 0
while response.status_code in (301, 302, 303, 307, 308) and redirect_count < 5:
redirect_url = response.headers.get('location')
if not redirect_url:
break
# Make redirect URL absolute if needed
if not redirect_url.startswith('http'):
redirect_url = urljoin(final_url, redirect_url)
final_url = redirect_url # Update final URL
response = await client.get(
redirect_url,
headers=headers,
auth=auth,
follow_redirects=False,
)
redirect_count += 1
if response.status_code == 200:
content = response.text
# Rewrite download links to go through our proxy
# Pass final_url so relative URLs can be resolved correctly
content = _rewrite_package_links(content, base_url, normalized_name, final_url)
return HTMLResponse(content=content)
if response.status_code == 404:
# Package not found in this source, try next
last_error = f"Package not found in {source.name}"
last_status = 404
continue
# Parse upstream error for policy/blocking messages
last_error = _parse_upstream_error(response)
last_status = response.status_code
logger.warning(f"PyPI proxy: upstream returned {response.status_code} for {package_name}: {last_error}")
except httpx.ConnectError as e:
last_error = f"Connection failed: {e}"
last_status = 502
logger.warning(f"PyPI proxy: failed to connect to {source.url}: {e}")
except httpx.TimeoutException as e:
last_error = f"Timeout: {e}"
last_status = 504
logger.warning(f"PyPI proxy: timeout connecting to {source.url}: {e}")
except Exception as e:
last_error = str(e)
last_status = 502
logger.warning(f"PyPI proxy: error fetching {package_name} from {source.url}: {e}")
# Pass through 4xx errors (like 403 policy blocks) so users understand why
status_code = last_status if last_status and 400 <= last_status < 500 else 404
raise HTTPException(
status_code=status_code,
detail=f"Package '{package_name}' error: {last_error}"
)
@router.get("/simple/{package_name}/{filename}")
async def pypi_download_file(
request: Request,
package_name: str,
filename: str,
upstream: Optional[str] = None,
db: Session = Depends(get_db),
storage: S3Storage = Depends(get_storage),
http_client: HttpClientManager = Depends(get_http_client),
cache: CacheService = Depends(get_cache),
):
"""
Download a package file, caching it in Orchard.
Args:
package_name: The package name
filename: The filename to download
upstream: URL-encoded upstream URL to fetch from
"""
if not upstream:
raise HTTPException(
status_code=400,
detail="Missing 'upstream' query parameter with source URL"
)
# Decode the upstream URL
upstream_url = unquote(upstream)
# Check if we already have this URL cached
url_hash = hashlib.sha256(upstream_url.encode()).hexdigest()
cached_url = db.query(CachedUrl).filter(CachedUrl.url_hash == url_hash).first()
if cached_url:
# Serve from cache
artifact = db.query(Artifact).filter(Artifact.id == cached_url.artifact_id).first()
if artifact:
logger.info(f"PyPI proxy: serving cached {filename} (artifact {artifact.id[:12]})")
settings = get_settings()
try:
if settings.pypi_download_mode == "redirect":
# Redirect to S3 presigned URL - client downloads directly from S3
presigned_url = storage.generate_presigned_url(artifact.s3_key)
return RedirectResponse(
url=presigned_url,
status_code=302,
headers={
"X-Checksum-SHA256": artifact.id,
"X-Cache": "HIT",
}
)
else:
# Proxy mode - stream from S3 through Orchard
stream, content_length, _ = storage.get_stream(artifact.s3_key)
def stream_content():
"""Generator that yields chunks from the S3 stream."""
try:
for chunk in stream.iter_chunks():
yield chunk
finally:
stream.close()
return StreamingResponse(
stream_content(),
media_type=artifact.content_type or "application/octet-stream",
headers={
"Content-Disposition": f'attachment; filename="{filename}"',
"Content-Length": str(content_length),
"X-Checksum-SHA256": artifact.id,
"X-Cache": "HIT",
}
)
except Exception as e:
logger.error(f"PyPI proxy: error serving cached artifact: {e}")
# Fall through to fetch from upstream
# Not cached - fetch from upstream
sources = _get_pypi_upstream_sources(db)
# Use the first available source for authentication headers
# Note: The upstream URL may point to files.pythonhosted.org or other CDNs,
# not the configured source URL directly, so we can't strictly validate the host
matched_source = sources[0] if sources else None
try:
headers = {"User-Agent": "Orchard-PyPI-Proxy/1.0"}
if matched_source:
headers.update(_build_auth_headers(matched_source))
auth = _get_basic_auth(matched_source) if matched_source else None
# Use shared HTTP client from pool with longer timeout for file downloads
client = http_client.get_client()
download_timeout = httpx.Timeout(connect=30.0, read=300.0, write=300.0, pool=30.0)
# Initialize extracted dependencies list
extracted_deps = []
# Fetch the file
logger.info(f"PyPI proxy: fetching {filename} from {upstream_url}")
response = await client.get(
upstream_url,
headers=headers,
auth=auth,
timeout=download_timeout,
)
# Handle redirects manually
redirect_count = 0
while response.status_code in (301, 302, 303, 307, 308) and redirect_count < 5:
redirect_url = response.headers.get('location')
if not redirect_url:
break
if not redirect_url.startswith('http'):
redirect_url = urljoin(upstream_url, redirect_url)
logger.info(f"PyPI proxy: following redirect to {redirect_url}")
# Don't send auth to different hosts
redirect_headers = {"User-Agent": "Orchard-PyPI-Proxy/1.0"}
redirect_auth = None
if urlparse(redirect_url).netloc == urlparse(upstream_url).netloc:
redirect_headers.update(headers)
redirect_auth = auth
response = await client.get(
redirect_url,
headers=redirect_headers,
auth=redirect_auth,
follow_redirects=False,
timeout=download_timeout,
)
redirect_count += 1
if response.status_code != 200:
# Parse upstream error for policy/blocking messages
error_detail = _parse_upstream_error(response)
logger.warning(f"PyPI proxy: upstream returned {response.status_code} for {filename}: {error_detail}")
raise HTTPException(
status_code=response.status_code,
detail=f"Upstream error: {error_detail}"
)
content_type = response.headers.get('content-type', 'application/octet-stream')
# Stream to temp file to avoid loading large packages into memory
# This keeps memory usage constant regardless of package size
# Using async iteration to avoid blocking the event loop
tmp_path = None
try:
with tempfile.NamedTemporaryFile(delete=False, suffix=f"_{filename}") as tmp_file:
tmp_path = tmp_file.name
async for chunk in response.aiter_bytes(chunk_size=65536): # 64KB chunks
tmp_file.write(chunk)
# Store in S3 from temp file (computes hash and deduplicates automatically)
with open(tmp_path, 'rb') as f:
result = storage.store(f)
sha256 = result.sha256
size = result.size
s3_key = result.s3_key
# Extract dependencies from the temp file before cleaning up
extracted_deps = _extract_dependencies_from_file(tmp_path, filename)
if extracted_deps:
logger.info(f"PyPI proxy: extracted {len(extracted_deps)} dependencies from {filename}")
logger.info(f"PyPI proxy: downloaded {filename}, {size} bytes, sha256={sha256[:12]}")
finally:
# Clean up temp file
if tmp_path and os.path.exists(tmp_path):
os.unlink(tmp_path)
# Check if artifact already exists
existing = db.query(Artifact).filter(Artifact.id == sha256).first()
if existing:
# Increment ref count
existing.ref_count += 1
db.flush()
else:
# Create artifact record
new_artifact = Artifact(
id=sha256,
original_name=filename,
content_type=content_type,
size=size,
ref_count=1,
created_by="pypi-proxy",
s3_key=result.s3_key,
checksum_md5=result.md5,
checksum_sha1=result.sha1,
s3_etag=result.s3_etag,
)
db.add(new_artifact)
db.flush()
# Create/get system project and package
system_project = db.query(Project).filter(Project.name == "_pypi").first()
if not system_project:
system_project = Project(
name="_pypi",
description="System project for cached PyPI packages",
is_public=True,
is_system=True,
created_by="pypi-proxy",
)
db.add(system_project)
db.flush()
elif not system_project.is_system:
# Ensure existing project is marked as system
system_project.is_system = True
db.flush()
# Normalize package name
normalized_name = re.sub(r'[-_.]+', '-', package_name).lower()
package = db.query(Package).filter(
Package.project_id == system_project.id,
Package.name == normalized_name,
).first()
if not package:
package = Package(
project_id=system_project.id,
name=normalized_name,
description=f"PyPI package: {normalized_name}",
format="pypi",
)
db.add(package)
db.flush()
# Extract and create version
# Only create version for actual package files, not .metadata files
version = _extract_pypi_version(filename)
if version and not filename.endswith('.metadata'):
# Check by version string (the unique constraint is on package_id + version)
existing_version = db.query(PackageVersion).filter(
PackageVersion.package_id == package.id,
PackageVersion.version == version,
).first()
if not existing_version:
pkg_version = PackageVersion(
package_id=package.id,
artifact_id=sha256,
version=version,
version_source="filename",
created_by="pypi-proxy",
)
db.add(pkg_version)
# Cache the URL mapping
existing_cached = db.query(CachedUrl).filter(CachedUrl.url_hash == url_hash).first()
if not existing_cached:
cached_url_record = CachedUrl(
url_hash=url_hash,
url=upstream_url,
artifact_id=sha256,
)
db.add(cached_url_record)
# Store extracted dependencies using batch operation
if extracted_deps:
# Deduplicate: keep first version constraint seen for each package name
seen_deps: dict[str, str] = {}
for dep_name, dep_version in extracted_deps:
if dep_name not in seen_deps:
seen_deps[dep_name] = dep_version if dep_version else "*"
# Convert to list of tuples for batch insert
deps_to_store = [
("_pypi", dep_name, dep_version)
for dep_name, dep_version in seen_deps.items()
]
# Batch upsert - handles duplicates with ON CONFLICT DO NOTHING
repo = ArtifactRepository(db)
inserted = repo.batch_upsert_dependencies(sha256, deps_to_store)
if inserted > 0:
logger.debug(f"Stored {inserted} dependencies for {sha256[:12]}...")
db.commit()
# Serve the file from S3
settings = get_settings()
try:
if settings.pypi_download_mode == "redirect":
# Redirect to S3 presigned URL - client downloads directly from S3
presigned_url = storage.generate_presigned_url(s3_key)
return RedirectResponse(
url=presigned_url,
status_code=302,
headers={
"X-Checksum-SHA256": sha256,
"X-Cache": "MISS",
}
)
else:
# Proxy mode - stream from S3 through Orchard
stream, content_length, _ = storage.get_stream(s3_key)
def stream_content():
"""Generator that yields chunks from the S3 stream."""
try:
for chunk in stream.iter_chunks():
yield chunk
finally:
stream.close()
return StreamingResponse(
stream_content(),
media_type=content_type,
headers={
"Content-Disposition": f'attachment; filename="{filename}"',
"Content-Length": str(size),
"X-Checksum-SHA256": sha256,
"X-Cache": "MISS",
}
)
except Exception as e:
logger.error(f"PyPI proxy: error serving from S3: {e}")
raise HTTPException(status_code=500, detail=f"Error serving file: {e}")
except httpx.ConnectError as e:
raise HTTPException(status_code=502, detail=f"Connection failed: {e}")
except httpx.TimeoutException as e:
raise HTTPException(status_code=504, detail=f"Timeout: {e}")
except HTTPException:
raise
except Exception as e:
logger.exception(f"PyPI proxy: error downloading {filename}")
raise HTTPException(status_code=500, detail=str(e))

View File

@@ -9,6 +9,7 @@ from .base import BaseRepository
from .project import ProjectRepository
from .package import PackageRepository
from .artifact import ArtifactRepository
from .tag import TagRepository
from .upload import UploadRepository
__all__ = [
@@ -16,5 +17,6 @@ __all__ = [
"ProjectRepository",
"PackageRepository",
"ArtifactRepository",
"TagRepository",
"UploadRepository",
]

View File

@@ -8,7 +8,7 @@ from sqlalchemy import func, or_
from uuid import UUID
from .base import BaseRepository
from ..models import Artifact, PackageVersion, Upload, Package, Project
from ..models import Artifact, Tag, Upload, Package, Project
class ArtifactRepository(BaseRepository[Artifact]):
@@ -77,14 +77,14 @@ class ArtifactRepository(BaseRepository[Artifact]):
.all()
)
def get_artifacts_without_versions(self, limit: int = 100) -> List[Artifact]:
"""Get artifacts that have no versions pointing to them."""
# Subquery to find artifact IDs that have versions
versioned_artifacts = self.db.query(PackageVersion.artifact_id).distinct().subquery()
def get_artifacts_without_tags(self, limit: int = 100) -> List[Artifact]:
"""Get artifacts that have no tags pointing to them."""
# Subquery to find artifact IDs that have tags
tagged_artifacts = self.db.query(Tag.artifact_id).distinct().subquery()
return (
self.db.query(Artifact)
.filter(~Artifact.id.in_(versioned_artifacts))
.filter(~Artifact.id.in_(tagged_artifacts))
.limit(limit)
.all()
)
@@ -115,34 +115,34 @@ class ArtifactRepository(BaseRepository[Artifact]):
return artifacts, total
def get_referencing_versions(self, artifact_id: str) -> List[Tuple[PackageVersion, Package, Project]]:
"""Get all versions referencing this artifact with package and project info."""
def get_referencing_tags(self, artifact_id: str) -> List[Tuple[Tag, Package, Project]]:
"""Get all tags referencing this artifact with package and project info."""
return (
self.db.query(PackageVersion, Package, Project)
.join(Package, PackageVersion.package_id == Package.id)
self.db.query(Tag, Package, Project)
.join(Package, Tag.package_id == Package.id)
.join(Project, Package.project_id == Project.id)
.filter(PackageVersion.artifact_id == artifact_id)
.filter(Tag.artifact_id == artifact_id)
.all()
)
def search(self, query_str: str, limit: int = 10) -> List[Tuple[PackageVersion, Artifact, str, str]]:
def search(self, query_str: str, limit: int = 10) -> List[Tuple[Tag, Artifact, str, str]]:
"""
Search artifacts by version or original filename.
Returns (version, artifact, package_name, project_name) tuples.
Search artifacts by tag name or original filename.
Returns (tag, artifact, package_name, project_name) tuples.
"""
search_lower = query_str.lower()
return (
self.db.query(PackageVersion, Artifact, Package.name, Project.name)
.join(Artifact, PackageVersion.artifact_id == Artifact.id)
.join(Package, PackageVersion.package_id == Package.id)
self.db.query(Tag, Artifact, Package.name, Project.name)
.join(Artifact, Tag.artifact_id == Artifact.id)
.join(Package, Tag.package_id == Package.id)
.join(Project, Package.project_id == Project.id)
.filter(
or_(
func.lower(PackageVersion.version).contains(search_lower),
func.lower(Tag.name).contains(search_lower),
func.lower(Artifact.original_name).contains(search_lower)
)
)
.order_by(PackageVersion.version)
.order_by(Tag.name)
.limit(limit)
.all()
)

View File

@@ -8,7 +8,7 @@ from sqlalchemy import func, or_, asc, desc
from uuid import UUID
from .base import BaseRepository
from ..models import Package, Project, PackageVersion, Upload, Artifact
from ..models import Package, Project, Tag, Upload, Artifact
class PackageRepository(BaseRepository[Package]):
@@ -136,10 +136,10 @@ class PackageRepository(BaseRepository[Package]):
return self.update(package, **updates)
def get_stats(self, package_id: UUID) -> dict:
"""Get package statistics (version count, artifact count, total size)."""
version_count = (
self.db.query(func.count(PackageVersion.id))
.filter(PackageVersion.package_id == package_id)
"""Get package statistics (tag count, artifact count, total size)."""
tag_count = (
self.db.query(func.count(Tag.id))
.filter(Tag.package_id == package_id)
.scalar() or 0
)
@@ -154,7 +154,7 @@ class PackageRepository(BaseRepository[Package]):
)
return {
"version_count": version_count,
"tag_count": tag_count,
"artifact_count": artifact_stats[0] if artifact_stats else 0,
"total_size": artifact_stats[1] if artifact_stats else 0,
}

View File

@@ -0,0 +1,168 @@
"""
Tag repository for data access operations.
"""
from typing import Optional, List, Tuple
from sqlalchemy.orm import Session
from sqlalchemy import func, or_, asc, desc
from uuid import UUID
from .base import BaseRepository
from ..models import Tag, TagHistory, Artifact, Package, Project
class TagRepository(BaseRepository[Tag]):
"""Repository for Tag entity operations."""
model = Tag
def get_by_name(self, package_id: UUID, name: str) -> Optional[Tag]:
"""Get tag by name within a package."""
return (
self.db.query(Tag)
.filter(Tag.package_id == package_id, Tag.name == name)
.first()
)
def get_with_artifact(self, package_id: UUID, name: str) -> Optional[Tuple[Tag, Artifact]]:
"""Get tag with its artifact."""
return (
self.db.query(Tag, Artifact)
.join(Artifact, Tag.artifact_id == Artifact.id)
.filter(Tag.package_id == package_id, Tag.name == name)
.first()
)
def exists_by_name(self, package_id: UUID, name: str) -> bool:
"""Check if tag with name exists in package."""
return self.db.query(
self.db.query(Tag)
.filter(Tag.package_id == package_id, Tag.name == name)
.exists()
).scalar()
def list_by_package(
self,
package_id: UUID,
page: int = 1,
limit: int = 20,
search: Optional[str] = None,
sort: str = "name",
order: str = "asc",
) -> Tuple[List[Tuple[Tag, Artifact]], int]:
"""
List tags in a package with artifact metadata.
Returns tuple of ((tag, artifact) tuples, total_count).
"""
query = (
self.db.query(Tag, Artifact)
.join(Artifact, Tag.artifact_id == Artifact.id)
.filter(Tag.package_id == package_id)
)
# Apply search filter (tag name or artifact original filename)
if search:
search_lower = search.lower()
query = query.filter(
or_(
func.lower(Tag.name).contains(search_lower),
func.lower(Artifact.original_name).contains(search_lower)
)
)
# Get total count
total = query.count()
# Apply sorting
sort_columns = {
"name": Tag.name,
"created_at": Tag.created_at,
}
sort_column = sort_columns.get(sort, Tag.name)
if order == "desc":
query = query.order_by(desc(sort_column))
else:
query = query.order_by(asc(sort_column))
# Apply pagination
offset = (page - 1) * limit
results = query.offset(offset).limit(limit).all()
return results, total
def create_tag(
self,
package_id: UUID,
name: str,
artifact_id: str,
created_by: str,
) -> Tag:
"""Create a new tag."""
return self.create(
package_id=package_id,
name=name,
artifact_id=artifact_id,
created_by=created_by,
)
def update_artifact(
self,
tag: Tag,
new_artifact_id: str,
changed_by: str,
record_history: bool = True,
) -> Tag:
"""
Update tag to point to a different artifact.
Optionally records change in tag history.
"""
old_artifact_id = tag.artifact_id
if record_history and old_artifact_id != new_artifact_id:
history = TagHistory(
tag_id=tag.id,
old_artifact_id=old_artifact_id,
new_artifact_id=new_artifact_id,
changed_by=changed_by,
)
self.db.add(history)
tag.artifact_id = new_artifact_id
tag.created_by = changed_by
self.db.flush()
return tag
def get_history(self, tag_id: UUID) -> List[TagHistory]:
"""Get tag change history."""
return (
self.db.query(TagHistory)
.filter(TagHistory.tag_id == tag_id)
.order_by(TagHistory.changed_at.desc())
.all()
)
def get_latest_in_package(self, package_id: UUID) -> Optional[Tag]:
"""Get the most recently created/updated tag in a package."""
return (
self.db.query(Tag)
.filter(Tag.package_id == package_id)
.order_by(Tag.created_at.desc())
.first()
)
def get_by_artifact(self, artifact_id: str) -> List[Tag]:
"""Get all tags pointing to an artifact."""
return (
self.db.query(Tag)
.filter(Tag.artifact_id == artifact_id)
.all()
)
def count_by_artifact(self, artifact_id: str) -> int:
"""Count tags pointing to an artifact."""
return (
self.db.query(func.count(Tag.id))
.filter(Tag.artifact_id == artifact_id)
.scalar() or 0
)

File diff suppressed because it is too large Load Diff

View File

@@ -33,7 +33,6 @@ class ProjectResponse(BaseModel):
name: str
description: Optional[str]
is_public: bool
is_system: bool = False
created_at: datetime
updated_at: datetime
created_by: str
@@ -114,6 +113,14 @@ class PackageUpdate(BaseModel):
platform: Optional[str] = None
class TagSummary(BaseModel):
"""Lightweight tag info for embedding in package responses"""
name: str
artifact_id: str
created_at: datetime
class PackageDetailResponse(BaseModel):
"""Package with aggregated metadata"""
@@ -126,9 +133,13 @@ class PackageDetailResponse(BaseModel):
created_at: datetime
updated_at: datetime
# Aggregated fields
tag_count: int = 0
artifact_count: int = 0
total_size: int = 0
latest_tag: Optional[str] = None
latest_upload_at: Optional[datetime] = None
# Recent tags (limit 5)
recent_tags: List[TagSummary] = []
class Config:
from_attributes = True
@@ -153,6 +164,79 @@ class ArtifactResponse(BaseModel):
from_attributes = True
# Tag schemas
class TagCreate(BaseModel):
name: str
artifact_id: str
class TagResponse(BaseModel):
id: UUID
package_id: UUID
name: str
artifact_id: str
created_at: datetime
created_by: str
version: Optional[str] = None # Version of the artifact this tag points to
class Config:
from_attributes = True
class TagDetailResponse(BaseModel):
"""Tag with embedded artifact metadata"""
id: UUID
package_id: UUID
name: str
artifact_id: str
created_at: datetime
created_by: str
version: Optional[str] = None # Version of the artifact this tag points to
# Artifact metadata
artifact_size: int
artifact_content_type: Optional[str]
artifact_original_name: Optional[str]
artifact_created_at: datetime
artifact_format_metadata: Optional[Dict[str, Any]] = None
class Config:
from_attributes = True
class TagHistoryResponse(BaseModel):
"""History entry for tag changes"""
id: UUID
tag_id: UUID
old_artifact_id: Optional[str]
new_artifact_id: str
changed_at: datetime
changed_by: str
class Config:
from_attributes = True
class TagHistoryDetailResponse(BaseModel):
"""Tag history with artifact metadata for each version"""
id: UUID
tag_id: UUID
tag_name: str
old_artifact_id: Optional[str]
new_artifact_id: str
changed_at: datetime
changed_by: str
# Artifact metadata for new artifact
artifact_size: int
artifact_original_name: Optional[str]
artifact_content_type: Optional[str]
class Config:
from_attributes = True
# Audit log schemas
class AuditLogResponse(BaseModel):
"""Audit log entry response"""
@@ -179,7 +263,7 @@ class UploadHistoryResponse(BaseModel):
package_name: str
project_name: str
original_name: Optional[str]
version: Optional[str]
tag_name: Optional[str]
uploaded_at: datetime
uploaded_by: str
source_ip: Optional[str]
@@ -210,10 +294,10 @@ class ArtifactProvenanceResponse(BaseModel):
# Usage statistics
upload_count: int
# References
packages: List[Dict[str, Any]] # List of {project_name, package_name, versions}
versions: List[
packages: List[Dict[str, Any]] # List of {project_name, package_name, tag_names}
tags: List[
Dict[str, Any]
] # List of {project_name, package_name, version, created_at}
] # List of {project_name, package_name, tag_name, created_at}
# Upload history
uploads: List[Dict[str, Any]] # List of upload events
@@ -221,8 +305,18 @@ class ArtifactProvenanceResponse(BaseModel):
from_attributes = True
class ArtifactTagInfo(BaseModel):
"""Tag info for embedding in artifact responses"""
id: UUID
name: str
package_id: UUID
package_name: str
project_name: str
class ArtifactDetailResponse(BaseModel):
"""Artifact with metadata"""
"""Artifact with list of tags/packages referencing it"""
id: str
sha256: str # Explicit SHA256 field (same as id)
@@ -236,14 +330,14 @@ class ArtifactDetailResponse(BaseModel):
created_by: str
ref_count: int
format_metadata: Optional[Dict[str, Any]] = None
versions: List[Dict[str, Any]] = [] # List of {version, package_name, project_name}
tags: List[ArtifactTagInfo] = []
class Config:
from_attributes = True
class PackageArtifactResponse(BaseModel):
"""Artifact for package artifact listing"""
"""Artifact with tags for package artifact listing"""
id: str
sha256: str # Explicit SHA256 field (same as id)
@@ -256,7 +350,7 @@ class PackageArtifactResponse(BaseModel):
created_at: datetime
created_by: str
format_metadata: Optional[Dict[str, Any]] = None
version: Optional[str] = None # Version from PackageVersion if exists
tags: List[str] = [] # Tag names pointing to this artifact
class Config:
from_attributes = True
@@ -274,9 +368,28 @@ class GlobalArtifactResponse(BaseModel):
created_by: str
format_metadata: Optional[Dict[str, Any]] = None
ref_count: int = 0
# Context from versions/packages
# Context from tags/packages
projects: List[str] = [] # List of project names containing this artifact
packages: List[str] = [] # List of "project/package" paths
tags: List[str] = [] # List of "project/package:tag" references
class Config:
from_attributes = True
class GlobalTagResponse(BaseModel):
"""Tag with project/package context for global listing"""
id: UUID
name: str
artifact_id: str
created_at: datetime
created_by: str
project_name: str
package_name: str
artifact_size: Optional[int] = None
artifact_content_type: Optional[str] = None
version: Optional[str] = None # Version of the artifact this tag points to
class Config:
from_attributes = True
@@ -289,6 +402,7 @@ class UploadResponse(BaseModel):
size: int
project: str
package: str
tag: Optional[str]
version: Optional[str] = None # Version assigned to this artifact
version_source: Optional[str] = None # How version was determined: 'explicit', 'filename', 'metadata'
checksum_md5: Optional[str] = None
@@ -315,6 +429,7 @@ class ResumableUploadInitRequest(BaseModel):
filename: str
content_type: Optional[str] = None
size: int
tag: Optional[str] = None
version: Optional[str] = None # Explicit version (auto-detected if not provided)
@field_validator("expected_hash")
@@ -349,7 +464,7 @@ class ResumableUploadPartResponse(BaseModel):
class ResumableUploadCompleteRequest(BaseModel):
"""Request to complete a resumable upload"""
pass
tag: Optional[str] = None
class ResumableUploadCompleteResponse(BaseModel):
@@ -359,6 +474,7 @@ class ResumableUploadCompleteResponse(BaseModel):
size: int
project: str
package: str
tag: Optional[str]
class ResumableUploadStatusResponse(BaseModel):
@@ -411,6 +527,7 @@ class PackageVersionResponse(BaseModel):
size: Optional[int] = None
content_type: Optional[str] = None
original_name: Optional[str] = None
tags: List[str] = [] # Tag names pointing to this artifact
class Config:
from_attributes = True
@@ -452,10 +569,11 @@ class SearchResultPackage(BaseModel):
class SearchResultArtifact(BaseModel):
"""Artifact result for global search"""
"""Artifact/tag result for global search"""
tag_id: UUID
tag_name: str
artifact_id: str
version: Optional[str]
package_id: UUID
package_name: str
project_name: str
@@ -493,8 +611,6 @@ class HealthResponse(BaseModel):
version: str = "1.0.0"
storage_healthy: Optional[bool] = None
database_healthy: Optional[bool] = None
http_pool: Optional[Dict[str, Any]] = None
cache: Optional[Dict[str, Any]] = None
# Garbage collection schemas
@@ -570,7 +686,7 @@ class ProjectStatsResponse(BaseModel):
project_id: str
project_name: str
package_count: int
version_count: int
tag_count: int
artifact_count: int
total_size_bytes: int
upload_count: int
@@ -585,7 +701,7 @@ class PackageStatsResponse(BaseModel):
package_id: str
package_name: str
project_name: str
version_count: int
tag_count: int
artifact_count: int
total_size_bytes: int
upload_count: int
@@ -602,9 +718,9 @@ class ArtifactStatsResponse(BaseModel):
size: int
ref_count: int
storage_savings: int # (ref_count - 1) * size
tags: List[Dict[str, Any]] # Tags referencing this artifact
projects: List[str] # Projects using this artifact
packages: List[str] # Packages using this artifact
versions: List[Dict[str, Any]] = [] # List of {version, package_name, project_name}
first_uploaded: Optional[datetime] = None
last_referenced: Optional[datetime] = None
@@ -813,7 +929,20 @@ class DependencyCreate(BaseModel):
"""Schema for creating a dependency"""
project: str
package: str
version: str
version: Optional[str] = None
tag: Optional[str] = None
@field_validator('version', 'tag')
@classmethod
def validate_constraint(cls, v, info):
return v
def model_post_init(self, __context):
"""Validate that exactly one of version or tag is set"""
if self.version is None and self.tag is None:
raise ValueError("Either 'version' or 'tag' must be specified")
if self.version is not None and self.tag is not None:
raise ValueError("Cannot specify both 'version' and 'tag'")
class DependencyResponse(BaseModel):
@@ -822,7 +951,8 @@ class DependencyResponse(BaseModel):
artifact_id: str
project: str
package: str
version: str
version: Optional[str] = None
tag: Optional[str] = None
created_at: datetime
class Config:
@@ -837,6 +967,7 @@ class DependencyResponse(BaseModel):
project=dep.dependency_project,
package=dep.dependency_package,
version=dep.version_constraint,
tag=dep.tag_constraint,
created_at=dep.created_at,
)
@@ -853,6 +984,7 @@ class DependentInfo(BaseModel):
project: str
package: str
version: Optional[str] = None
constraint_type: str # 'version' or 'tag'
constraint_value: str
@@ -868,7 +1000,20 @@ class EnsureFileDependency(BaseModel):
"""Dependency entry from orchard.ensure file"""
project: str
package: str
version: str
version: Optional[str] = None
tag: Optional[str] = None
@field_validator('version', 'tag')
@classmethod
def validate_constraint(cls, v, info):
return v
def model_post_init(self, __context):
"""Validate that exactly one of version or tag is set"""
if self.version is None and self.tag is None:
raise ValueError("Either 'version' or 'tag' must be specified")
if self.version is not None and self.tag is not None:
raise ValueError("Cannot specify both 'version' and 'tag'")
class EnsureFileContent(BaseModel):
@@ -882,23 +1027,15 @@ class ResolvedArtifact(BaseModel):
project: str
package: str
version: Optional[str] = None
tag: Optional[str] = None
size: int
download_url: str
class MissingDependency(BaseModel):
"""A dependency that could not be resolved (not cached on server)"""
project: str
package: str
constraint: Optional[str] = None
required_by: Optional[str] = None
class DependencyResolutionResponse(BaseModel):
"""Response from dependency resolution endpoint"""
requested: Dict[str, str] # project, package, ref
resolved: List[ResolvedArtifact]
missing: List[MissingDependency] = []
total_size: int
artifact_count: int
@@ -907,7 +1044,7 @@ class DependencyConflict(BaseModel):
"""Details about a dependency conflict"""
project: str
package: str
requirements: List[Dict[str, Any]] # version and required_by info
requirements: List[Dict[str, Any]] # version/tag and required_by info
class DependencyConflictError(BaseModel):
@@ -1059,277 +1196,3 @@ class TeamMemberResponse(BaseModel):
class Config:
from_attributes = True
# =============================================================================
# Upstream Caching Schemas
# =============================================================================
# Valid source types
SOURCE_TYPES = ["npm", "pypi", "maven", "docker", "helm", "nuget", "deb", "rpm", "generic"]
# Valid auth types
AUTH_TYPES = ["none", "basic", "bearer", "api_key"]
class UpstreamSourceCreate(BaseModel):
"""Create a new upstream source"""
name: str
source_type: str = "generic"
url: str
enabled: bool = False
auth_type: str = "none"
username: Optional[str] = None
password: Optional[str] = None # Write-only
headers: Optional[dict] = None # Write-only, custom headers
priority: int = 100
@field_validator('name')
@classmethod
def validate_name(cls, v: str) -> str:
v = v.strip()
if not v:
raise ValueError("name cannot be empty")
if len(v) > 255:
raise ValueError("name must be 255 characters or less")
return v
@field_validator('source_type')
@classmethod
def validate_source_type(cls, v: str) -> str:
if v not in SOURCE_TYPES:
raise ValueError(f"source_type must be one of: {', '.join(SOURCE_TYPES)}")
return v
@field_validator('url')
@classmethod
def validate_url(cls, v: str) -> str:
v = v.strip()
if not v:
raise ValueError("url cannot be empty")
if not (v.startswith('http://') or v.startswith('https://')):
raise ValueError("url must start with http:// or https://")
if len(v) > 2048:
raise ValueError("url must be 2048 characters or less")
return v
@field_validator('auth_type')
@classmethod
def validate_auth_type(cls, v: str) -> str:
if v not in AUTH_TYPES:
raise ValueError(f"auth_type must be one of: {', '.join(AUTH_TYPES)}")
return v
@field_validator('priority')
@classmethod
def validate_priority(cls, v: int) -> int:
if v <= 0:
raise ValueError("priority must be greater than 0")
return v
class UpstreamSourceUpdate(BaseModel):
"""Update an upstream source (partial)"""
name: Optional[str] = None
source_type: Optional[str] = None
url: Optional[str] = None
enabled: Optional[bool] = None
auth_type: Optional[str] = None
username: Optional[str] = None
password: Optional[str] = None # Write-only, None = keep existing, empty string = clear
headers: Optional[dict] = None # Write-only
priority: Optional[int] = None
@field_validator('name')
@classmethod
def validate_name(cls, v: Optional[str]) -> Optional[str]:
if v is not None:
v = v.strip()
if not v:
raise ValueError("name cannot be empty")
if len(v) > 255:
raise ValueError("name must be 255 characters or less")
return v
@field_validator('source_type')
@classmethod
def validate_source_type(cls, v: Optional[str]) -> Optional[str]:
if v is not None and v not in SOURCE_TYPES:
raise ValueError(f"source_type must be one of: {', '.join(SOURCE_TYPES)}")
return v
@field_validator('url')
@classmethod
def validate_url(cls, v: Optional[str]) -> Optional[str]:
if v is not None:
v = v.strip()
if not v:
raise ValueError("url cannot be empty")
if not (v.startswith('http://') or v.startswith('https://')):
raise ValueError("url must start with http:// or https://")
if len(v) > 2048:
raise ValueError("url must be 2048 characters or less")
return v
@field_validator('auth_type')
@classmethod
def validate_auth_type(cls, v: Optional[str]) -> Optional[str]:
if v is not None and v not in AUTH_TYPES:
raise ValueError(f"auth_type must be one of: {', '.join(AUTH_TYPES)}")
return v
@field_validator('priority')
@classmethod
def validate_priority(cls, v: Optional[int]) -> Optional[int]:
if v is not None and v <= 0:
raise ValueError("priority must be greater than 0")
return v
class UpstreamSourceResponse(BaseModel):
"""Upstream source response (credentials never included)"""
id: UUID
name: str
source_type: str
url: str
enabled: bool
auth_type: str
username: Optional[str]
has_password: bool # True if password is set
has_headers: bool # True if custom headers are set
priority: int
source: str = "database" # "database" or "env" (env = defined via environment variables)
created_at: Optional[datetime] = None # May be None for legacy/env data
updated_at: Optional[datetime] = None # May be None for legacy/env data
class Config:
from_attributes = True
class CacheSettingsResponse(BaseModel):
"""Global cache settings response"""
auto_create_system_projects: bool
auto_create_system_projects_env_override: Optional[bool] = None # Set if overridden by env var
created_at: Optional[datetime] = None # May be None for legacy data
updated_at: Optional[datetime] = None # May be None for legacy data
class Config:
from_attributes = True
class CacheSettingsUpdate(BaseModel):
"""Update cache settings (partial)"""
auto_create_system_projects: Optional[bool] = None
class CachedUrlResponse(BaseModel):
"""Cached URL response"""
id: UUID
url: str
url_hash: str
artifact_id: str
source_id: Optional[UUID]
source_name: Optional[str] = None # Populated from join
fetched_at: datetime
created_at: datetime
class Config:
from_attributes = True
class CacheRequest(BaseModel):
"""Request to cache an artifact from an upstream URL"""
url: str
source_type: str
package_name: Optional[str] = None # Auto-derived from URL if not provided
version: Optional[str] = None # Auto-derived from URL if not provided
user_project: Optional[str] = None # Cross-reference to user project
user_package: Optional[str] = None
user_version: Optional[str] = None
expected_hash: Optional[str] = None # Verify downloaded content
@field_validator('url')
@classmethod
def validate_url(cls, v: str) -> str:
v = v.strip()
if not v:
raise ValueError("url cannot be empty")
if not (v.startswith('http://') or v.startswith('https://')):
raise ValueError("url must start with http:// or https://")
if len(v) > 4096:
raise ValueError("url must be 4096 characters or less")
return v
@field_validator('source_type')
@classmethod
def validate_source_type(cls, v: str) -> str:
if v not in SOURCE_TYPES:
raise ValueError(f"source_type must be one of: {', '.join(SOURCE_TYPES)}")
return v
@field_validator('expected_hash')
@classmethod
def validate_expected_hash(cls, v: Optional[str]) -> Optional[str]:
if v is not None:
v = v.strip().lower()
# Remove sha256: prefix if present
if v.startswith('sha256:'):
v = v[7:]
# Validate hex format
if len(v) != 64 or not all(c in '0123456789abcdef' for c in v):
raise ValueError("expected_hash must be a 64-character hex string (SHA256)")
return v
class CacheResponse(BaseModel):
"""Response from caching an artifact"""
artifact_id: str
sha256: str
size: int
content_type: Optional[str]
already_cached: bool
source_url: str
source_name: Optional[str]
system_project: str
system_package: str
system_version: Optional[str]
user_reference: Optional[str] = None # e.g., "my-app/npm-deps/+/4.17.21"
class CacheResolveRequest(BaseModel):
"""Request to cache an artifact by package coordinates (no URL required).
The server will construct the appropriate URL based on source_type and
configured upstream sources.
"""
source_type: str
package: str
version: str
user_project: Optional[str] = None
user_package: Optional[str] = None
user_version: Optional[str] = None
@field_validator('source_type')
@classmethod
def validate_source_type(cls, v: str) -> str:
if v not in SOURCE_TYPES:
raise ValueError(f"source_type must be one of: {', '.join(SOURCE_TYPES)}")
return v
@field_validator('package')
@classmethod
def validate_package(cls, v: str) -> str:
v = v.strip()
if not v:
raise ValueError("package cannot be empty")
return v
@field_validator('version')
@classmethod
def validate_version(cls, v: str) -> str:
v = v.strip()
if not v:
raise ValueError("version cannot be empty")
return v

View File

@@ -5,7 +5,7 @@ import hashlib
import logging
from sqlalchemy.orm import Session
from .models import Project, Package, Artifact, Upload, PackageVersion, ArtifactDependency, Team, TeamMembership, User
from .models import Project, Package, Artifact, Tag, Upload, PackageVersion, ArtifactDependency, Team, TeamMembership, User
from .storage import get_storage
from .auth import hash_password
@@ -125,14 +125,14 @@ TEST_ARTIFACTS = [
]
# Dependencies to create (source artifact -> dependency)
# Format: (source_project, source_package, source_version, dep_project, dep_package, version_constraint)
# Format: (source_project, source_package, source_version, dep_project, dep_package, version_constraint, tag_constraint)
TEST_DEPENDENCIES = [
# ui-components v1.1.0 depends on design-tokens v1.0.0
("frontend-libs", "ui-components", "1.1.0", "frontend-libs", "design-tokens", "1.0.0"),
("frontend-libs", "ui-components", "1.1.0", "frontend-libs", "design-tokens", "1.0.0", None),
# auth-lib v1.0.0 depends on common-utils v2.0.0
("backend-services", "auth-lib", "1.0.0", "backend-services", "common-utils", "2.0.0"),
# auth-lib v1.0.0 also depends on design-tokens v1.0.0
("backend-services", "auth-lib", "1.0.0", "frontend-libs", "design-tokens", "1.0.0"),
("backend-services", "auth-lib", "1.0.0", "backend-services", "common-utils", "2.0.0", None),
# auth-lib v1.0.0 also depends on design-tokens (stable tag)
("backend-services", "auth-lib", "1.0.0", "frontend-libs", "design-tokens", None, "latest"),
]
@@ -252,8 +252,9 @@ def seed_database(db: Session) -> None:
logger.info(f"Created {len(project_map)} projects and {len(package_map)} packages (assigned to {demo_team.slug})")
# Create artifacts and versions
# Create artifacts, tags, and versions
artifact_count = 0
tag_count = 0
version_count = 0
for artifact_data in TEST_ARTIFACTS:
@@ -315,12 +316,23 @@ def seed_database(db: Session) -> None:
db.add(version)
version_count += 1
# Create tags
for tag_name in artifact_data["tags"]:
tag = Tag(
package_id=package.id,
name=tag_name,
artifact_id=sha256_hash,
created_by=team_owner_username,
)
db.add(tag)
tag_count += 1
db.flush()
# Create dependencies
dependency_count = 0
for dep_data in TEST_DEPENDENCIES:
src_project, src_package, src_version, dep_project, dep_package, version_constraint = dep_data
src_project, src_package, src_version, dep_project, dep_package, version_constraint, tag_constraint = dep_data
# Find the source artifact by looking up its version
src_pkg = package_map.get((src_project, src_package))
@@ -344,10 +356,11 @@ def seed_database(db: Session) -> None:
dependency_project=dep_project,
dependency_package=dep_package,
version_constraint=version_constraint,
tag_constraint=tag_constraint,
)
db.add(dependency)
dependency_count += 1
db.commit()
logger.info(f"Created {artifact_count} artifacts, {version_count} versions, and {dependency_count} dependencies")
logger.info(f"Created {artifact_count} artifacts, {tag_count} tags, {version_count} versions, and {dependency_count} dependencies")
logger.info("Database seeding complete")

View File

@@ -6,8 +6,9 @@ from typing import List, Optional, Tuple
from sqlalchemy.orm import Session
import logging
from ..models import Artifact, PackageVersion
from ..models import Artifact, Tag
from ..repositories.artifact import ArtifactRepository
from ..repositories.tag import TagRepository
from ..storage import S3Storage
logger = logging.getLogger(__name__)
@@ -20,8 +21,8 @@ class ArtifactCleanupService:
Reference counting rules:
- ref_count starts at 1 when artifact is first uploaded
- ref_count increments when the same artifact is uploaded again (deduplication)
- ref_count decrements when a version is deleted or updated to point elsewhere
- ref_count decrements when a package is deleted (for each version pointing to artifact)
- ref_count decrements when a tag is deleted or updated to point elsewhere
- ref_count decrements when a package is deleted (for each tag pointing to artifact)
- When ref_count reaches 0, artifact is a candidate for deletion from S3
"""
@@ -29,11 +30,12 @@ class ArtifactCleanupService:
self.db = db
self.storage = storage
self.artifact_repo = ArtifactRepository(db)
self.tag_repo = TagRepository(db)
def on_version_deleted(self, artifact_id: str) -> Artifact:
def on_tag_deleted(self, artifact_id: str) -> Artifact:
"""
Called when a version is deleted.
Decrements ref_count for the artifact the version was pointing to.
Called when a tag is deleted.
Decrements ref_count for the artifact the tag was pointing to.
"""
artifact = self.artifact_repo.get_by_sha256(artifact_id)
if artifact:
@@ -43,11 +45,11 @@ class ArtifactCleanupService:
)
return artifact
def on_version_updated(
def on_tag_updated(
self, old_artifact_id: str, new_artifact_id: str
) -> Tuple[Optional[Artifact], Optional[Artifact]]:
"""
Called when a version is updated to point to a different artifact.
Called when a tag is updated to point to a different artifact.
Decrements ref_count for old artifact, increments for new (if different).
Returns (old_artifact, new_artifact) tuple.
@@ -77,21 +79,21 @@ class ArtifactCleanupService:
def on_package_deleted(self, package_id) -> List[str]:
"""
Called when a package is deleted.
Decrements ref_count for all artifacts that had versions in the package.
Decrements ref_count for all artifacts that had tags in the package.
Returns list of artifact IDs that were affected.
"""
# Get all versions in the package before deletion
versions = self.db.query(PackageVersion).filter(PackageVersion.package_id == package_id).all()
# Get all tags in the package before deletion
tags = self.db.query(Tag).filter(Tag.package_id == package_id).all()
affected_artifacts = []
for version in versions:
artifact = self.artifact_repo.get_by_sha256(version.artifact_id)
for tag in tags:
artifact = self.artifact_repo.get_by_sha256(tag.artifact_id)
if artifact:
self.artifact_repo.decrement_ref_count(artifact)
affected_artifacts.append(version.artifact_id)
affected_artifacts.append(tag.artifact_id)
logger.info(
f"Decremented ref_count for artifact {version.artifact_id} (package delete)"
f"Decremented ref_count for artifact {tag.artifact_id} (package delete)"
)
return affected_artifacts
@@ -150,7 +152,7 @@ class ArtifactCleanupService:
def verify_ref_counts(self, fix: bool = False) -> List[dict]:
"""
Verify that ref_counts match actual version references.
Verify that ref_counts match actual tag references.
Args:
fix: If True, fix any mismatched ref_counts
@@ -160,28 +162,28 @@ class ArtifactCleanupService:
"""
from sqlalchemy import func
# Get actual version counts per artifact
version_counts = (
self.db.query(PackageVersion.artifact_id, func.count(PackageVersion.id).label("version_count"))
.group_by(PackageVersion.artifact_id)
# Get actual tag counts per artifact
tag_counts = (
self.db.query(Tag.artifact_id, func.count(Tag.id).label("tag_count"))
.group_by(Tag.artifact_id)
.all()
)
version_count_map = {artifact_id: count for artifact_id, count in version_counts}
tag_count_map = {artifact_id: count for artifact_id, count in tag_counts}
# Check all artifacts
artifacts = self.db.query(Artifact).all()
mismatches = []
for artifact in artifacts:
actual_count = version_count_map.get(artifact.id, 0)
actual_count = tag_count_map.get(artifact.id, 0)
# ref_count should be at least 1 (initial upload) + additional uploads
# But versions are the primary reference, so we check against version count
# But tags are the primary reference, so we check against tag count
if artifact.ref_count < actual_count:
mismatch = {
"artifact_id": artifact.id,
"stored_ref_count": artifact.ref_count,
"actual_version_count": actual_count,
"actual_tag_count": actual_count,
}
mismatches.append(mismatch)

View File

@@ -1,565 +0,0 @@
"""
HTTP client for fetching artifacts from upstream sources.
Provides streaming downloads with SHA256 computation, authentication support,
and automatic source matching based on URL prefixes.
"""
from __future__ import annotations
import hashlib
import logging
import tempfile
import time
from dataclasses import dataclass, field
from pathlib import Path
from typing import BinaryIO, Optional, TYPE_CHECKING
from urllib.parse import urlparse
import httpx
if TYPE_CHECKING:
from .models import CacheSettings, UpstreamSource
logger = logging.getLogger(__name__)
class UpstreamError(Exception):
"""Base exception for upstream client errors."""
pass
class UpstreamConnectionError(UpstreamError):
"""Connection to upstream failed (network error, DNS, etc.)."""
pass
class UpstreamTimeoutError(UpstreamError):
"""Request to upstream timed out."""
pass
class UpstreamHTTPError(UpstreamError):
"""Upstream returned an HTTP error response."""
def __init__(self, message: str, status_code: int, response_headers: dict = None):
super().__init__(message)
self.status_code = status_code
self.response_headers = response_headers or {}
class UpstreamSSLError(UpstreamError):
"""SSL/TLS error when connecting to upstream."""
pass
class FileSizeExceededError(UpstreamError):
"""File size exceeds the maximum allowed."""
def __init__(self, message: str, content_length: int, max_size: int):
super().__init__(message)
self.content_length = content_length
self.max_size = max_size
class SourceNotFoundError(UpstreamError):
"""No matching upstream source found for URL."""
pass
class SourceDisabledError(UpstreamError):
"""The matching upstream source is disabled."""
pass
@dataclass
class FetchResult:
"""Result of fetching an artifact from upstream."""
content: BinaryIO # File-like object with content
sha256: str # SHA256 hash of content
size: int # Size in bytes
content_type: Optional[str] # Content-Type header
response_headers: dict # All response headers for provenance
source_name: Optional[str] = None # Name of matched upstream source
temp_path: Optional[Path] = None # Path to temp file (for cleanup)
def close(self):
"""Close and clean up resources."""
if self.content:
try:
self.content.close()
except Exception:
pass
if self.temp_path and self.temp_path.exists():
try:
self.temp_path.unlink()
except Exception:
pass
@dataclass
class UpstreamClientConfig:
"""Configuration for the upstream client."""
connect_timeout: float = 30.0 # Connection timeout in seconds
read_timeout: float = 300.0 # Read timeout in seconds (5 minutes for large files)
max_retries: int = 3 # Maximum number of retry attempts
retry_backoff_base: float = 1.0 # Base delay for exponential backoff
retry_backoff_max: float = 30.0 # Maximum delay between retries
follow_redirects: bool = True # Whether to follow redirects
max_redirects: int = 5 # Maximum number of redirects to follow
max_file_size: Optional[int] = None # Maximum file size (None = unlimited)
verify_ssl: bool = True # Verify SSL certificates
user_agent: str = "Orchard-UpstreamClient/1.0"
class UpstreamClient:
"""
HTTP client for fetching artifacts from upstream sources.
Supports streaming downloads, multiple authentication methods,
automatic source matching, and air-gap mode enforcement.
"""
def __init__(
self,
sources: list[UpstreamSource] = None,
cache_settings: CacheSettings = None,
config: UpstreamClientConfig = None,
):
"""
Initialize the upstream client.
Args:
sources: List of upstream sources for URL matching and auth.
Should be sorted by priority (lowest first).
cache_settings: Global cache settings including air-gap mode.
config: Client configuration options.
"""
self.sources = sources or []
self.cache_settings = cache_settings
self.config = config or UpstreamClientConfig()
# Sort sources by priority (lower = higher priority)
self.sources = sorted(self.sources, key=lambda s: s.priority)
def _match_source(self, url: str) -> Optional[UpstreamSource]:
"""
Find the upstream source that matches the given URL.
Matches by URL prefix, returns the highest priority match.
Args:
url: The URL to match.
Returns:
The matching UpstreamSource or None if no match.
"""
for source in self.sources:
# Check if URL starts with source URL (prefix match)
if url.startswith(source.url.rstrip("/")):
return source
return None
def _build_auth_headers(self, source: UpstreamSource) -> dict:
"""
Build authentication headers for the given source.
Args:
source: The upstream source with auth configuration.
Returns:
Dictionary of headers to add to the request.
"""
headers = {}
if source.auth_type == "none":
pass
elif source.auth_type == "basic":
# httpx handles basic auth via auth parameter, but we can also
# do it manually if needed. We'll use the auth parameter instead.
pass
elif source.auth_type == "bearer":
password = source.get_password()
if password:
headers["Authorization"] = f"Bearer {password}"
elif source.auth_type == "api_key":
# API key auth uses custom headers
custom_headers = source.get_headers()
if custom_headers:
headers.update(custom_headers)
return headers
def _get_basic_auth(self, source: UpstreamSource) -> Optional[tuple[str, str]]:
"""
Get basic auth credentials if applicable.
Args:
source: The upstream source.
Returns:
Tuple of (username, password) or None.
"""
if source.auth_type == "basic" and source.username:
password = source.get_password() or ""
return (source.username, password)
return None
def _should_retry(self, error: Exception, attempt: int) -> bool:
"""
Determine if a request should be retried.
Args:
error: The exception that occurred.
attempt: Current attempt number (0-indexed).
Returns:
True if the request should be retried.
"""
if attempt >= self.config.max_retries - 1:
return False
# Retry on connection errors and timeouts
if isinstance(error, (httpx.ConnectError, httpx.ConnectTimeout)):
return True
# Retry on read timeouts
if isinstance(error, httpx.ReadTimeout):
return True
# Retry on certain HTTP errors (502, 503, 504)
if isinstance(error, httpx.HTTPStatusError):
return error.response.status_code in (502, 503, 504)
return False
def _calculate_backoff(self, attempt: int) -> float:
"""
Calculate backoff delay for retry.
Uses exponential backoff with jitter.
Args:
attempt: Current attempt number (0-indexed).
Returns:
Delay in seconds.
"""
import random
delay = self.config.retry_backoff_base * (2**attempt)
# Add jitter (±25%)
delay *= 0.75 + random.random() * 0.5
return min(delay, self.config.retry_backoff_max)
def fetch(self, url: str, expected_hash: Optional[str] = None) -> FetchResult:
"""
Fetch an artifact from the given URL.
Streams the response to a temp file while computing the SHA256 hash.
Handles authentication, retries, and error cases.
Args:
url: The URL to fetch.
expected_hash: Optional expected SHA256 hash for verification.
Returns:
FetchResult with content, hash, size, and headers.
Raises:
SourceDisabledError: If the matching source is disabled.
UpstreamConnectionError: On connection failures.
UpstreamTimeoutError: On timeout.
UpstreamHTTPError: On HTTP error responses.
UpstreamSSLError: On SSL/TLS errors.
FileSizeExceededError: If Content-Length exceeds max_file_size.
"""
start_time = time.time()
# Match URL to source
source = self._match_source(url)
# Check if source is enabled (if we have a match)
if source is not None and not source.enabled:
raise SourceDisabledError(
f"Upstream source '{source.name}' is disabled"
)
source_name = source.name if source else None
logger.info(
f"Fetching URL: {url} (source: {source_name or 'none'})"
)
# Build request parameters
headers = {"User-Agent": self.config.user_agent}
auth = None
if source:
headers.update(self._build_auth_headers(source))
auth = self._get_basic_auth(source)
timeout = httpx.Timeout(
connect=self.config.connect_timeout,
read=self.config.read_timeout,
write=30.0,
pool=10.0,
)
# Attempt fetch with retries
last_error = None
for attempt in range(self.config.max_retries):
try:
return self._do_fetch(
url=url,
headers=headers,
auth=auth,
timeout=timeout,
source_name=source_name,
start_time=start_time,
expected_hash=expected_hash,
)
except (
httpx.ConnectError,
httpx.ConnectTimeout,
httpx.ReadTimeout,
httpx.HTTPStatusError,
) as e:
last_error = e
if self._should_retry(e, attempt):
delay = self._calculate_backoff(attempt)
logger.warning(
f"Fetch failed (attempt {attempt + 1}/{self.config.max_retries}), "
f"retrying in {delay:.1f}s: {e}"
)
time.sleep(delay)
else:
break
# Convert final error to our exception types
self._raise_upstream_error(last_error, url)
def _do_fetch(
self,
url: str,
headers: dict,
auth: Optional[tuple[str, str]],
timeout: httpx.Timeout,
source_name: Optional[str],
start_time: float,
expected_hash: Optional[str] = None,
) -> FetchResult:
"""
Perform the actual fetch operation.
Args:
url: URL to fetch.
headers: Request headers.
auth: Basic auth credentials or None.
timeout: Request timeout configuration.
source_name: Name of matched source for logging.
start_time: Request start time for timing.
expected_hash: Optional expected hash for verification.
Returns:
FetchResult with content and metadata.
"""
with httpx.Client(
timeout=timeout,
follow_redirects=self.config.follow_redirects,
max_redirects=self.config.max_redirects,
verify=self.config.verify_ssl,
) as client:
with client.stream("GET", url, headers=headers, auth=auth) as response:
# Check for HTTP errors
response.raise_for_status()
# Check Content-Length against max size
content_length = response.headers.get("content-length")
if content_length:
content_length = int(content_length)
if (
self.config.max_file_size
and content_length > self.config.max_file_size
):
raise FileSizeExceededError(
f"File size {content_length} exceeds maximum {self.config.max_file_size}",
content_length,
self.config.max_file_size,
)
# Stream to temp file while computing hash
hasher = hashlib.sha256()
size = 0
# Create temp file
temp_file = tempfile.NamedTemporaryFile(
delete=False, prefix="orchard_upstream_"
)
temp_path = Path(temp_file.name)
try:
for chunk in response.iter_bytes(chunk_size=65536):
temp_file.write(chunk)
hasher.update(chunk)
size += len(chunk)
# Check size while streaming if max_file_size is set
if self.config.max_file_size and size > self.config.max_file_size:
temp_file.close()
temp_path.unlink()
raise FileSizeExceededError(
f"Downloaded size {size} exceeds maximum {self.config.max_file_size}",
size,
self.config.max_file_size,
)
temp_file.close()
sha256 = hasher.hexdigest()
# Verify hash if expected
if expected_hash and sha256 != expected_hash.lower():
temp_path.unlink()
raise UpstreamError(
f"Hash mismatch: expected {expected_hash}, got {sha256}"
)
# Capture response headers
response_headers = dict(response.headers)
# Get content type
content_type = response.headers.get("content-type")
elapsed = time.time() - start_time
logger.info(
f"Fetched {url}: {size} bytes, sha256={sha256[:12]}..., "
f"source={source_name}, time={elapsed:.2f}s"
)
# Return file handle positioned at start
content = open(temp_path, "rb")
return FetchResult(
content=content,
sha256=sha256,
size=size,
content_type=content_type,
response_headers=response_headers,
source_name=source_name,
temp_path=temp_path,
)
except Exception:
# Clean up on error
try:
temp_file.close()
except Exception:
pass
if temp_path.exists():
temp_path.unlink()
raise
def _raise_upstream_error(self, error: Exception, url: str):
"""
Convert httpx exception to appropriate UpstreamError.
Args:
error: The httpx exception.
url: The URL that was being fetched.
Raises:
Appropriate UpstreamError subclass.
"""
if error is None:
raise UpstreamError(f"Unknown error fetching {url}")
if isinstance(error, httpx.ConnectError):
raise UpstreamConnectionError(
f"Failed to connect to upstream: {error}"
) from error
if isinstance(error, (httpx.ConnectTimeout, httpx.ReadTimeout)):
raise UpstreamTimeoutError(
f"Request timed out: {error}"
) from error
if isinstance(error, httpx.HTTPStatusError):
raise UpstreamHTTPError(
f"HTTP {error.response.status_code}: {error}",
error.response.status_code,
dict(error.response.headers),
) from error
# Check for SSL errors in the error chain
if "ssl" in str(error).lower() or "certificate" in str(error).lower():
raise UpstreamSSLError(f"SSL/TLS error: {error}") from error
raise UpstreamError(f"Error fetching {url}: {error}") from error
def test_connection(self, source: UpstreamSource) -> tuple[bool, Optional[str], Optional[int]]:
"""
Test connectivity to an upstream source.
Performs a HEAD request to the source URL to verify connectivity
and authentication. Does not follow redirects - a 3xx response
is considered successful since it proves the server is reachable.
Args:
source: The upstream source to test.
Returns:
Tuple of (success, error_message, status_code).
"""
headers = {"User-Agent": self.config.user_agent}
headers.update(self._build_auth_headers(source))
auth = self._get_basic_auth(source)
timeout = httpx.Timeout(
connect=self.config.connect_timeout,
read=30.0,
write=30.0,
pool=10.0,
)
try:
with httpx.Client(
timeout=timeout,
verify=self.config.verify_ssl,
) as client:
response = client.head(
source.url,
headers=headers,
auth=auth,
follow_redirects=False,
)
# Consider 2xx and 3xx as success, also 405 (Method Not Allowed)
# since some servers don't support HEAD
if response.status_code < 400 or response.status_code == 405:
return (True, None, response.status_code)
else:
return (
False,
f"HTTP {response.status_code}",
response.status_code,
)
except httpx.ConnectError as e:
return (False, f"Connection failed: {e}", None)
except httpx.ConnectTimeout as e:
return (False, f"Connection timed out: {e}", None)
except httpx.ReadTimeout as e:
return (False, f"Read timed out: {e}", None)
except httpx.TooManyRedirects as e:
return (False, f"Too many redirects: {e}", None)
except Exception as e:
return (False, f"Error: {e}", None)

View File

@@ -11,11 +11,10 @@ python-jose[cryptography]==3.3.0
passlib[bcrypt]==1.7.4
bcrypt==4.0.1
slowapi==0.1.9
httpx>=0.25.0
redis>=5.0.0
# Test dependencies
pytest>=7.4.0
pytest-asyncio>=0.21.0
pytest-cov>=4.1.0
httpx>=0.25.0
moto[s3]>=4.2.0

View File

@@ -1 +0,0 @@
# Scripts package

View File

@@ -1,262 +0,0 @@
#!/usr/bin/env python3
"""
Backfill script to extract dependencies from cached PyPI packages.
This script scans all artifacts in the _pypi project and extracts
Requires-Dist metadata from wheel and sdist files that don't already
have dependencies recorded.
Usage:
# From within the container:
python -m scripts.backfill_pypi_dependencies
# Or with docker exec:
docker exec orchard_orchard-server_1 python -m scripts.backfill_pypi_dependencies
# Dry run (preview only):
docker exec orchard_orchard-server_1 python -m scripts.backfill_pypi_dependencies --dry-run
"""
import argparse
import logging
import re
import sys
import tarfile
import zipfile
from io import BytesIO
from typing import List, Optional, Tuple
# Add parent directory to path for imports
sys.path.insert(0, "/app")
from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
from backend.app.config import get_settings
from backend.app.models import (
Artifact,
ArtifactDependency,
Package,
Project,
Tag,
)
from backend.app.storage import get_storage
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s - %(levelname)s - %(message)s",
)
logger = logging.getLogger(__name__)
def parse_requires_dist(requires_dist: str) -> Tuple[Optional[str], Optional[str]]:
"""Parse a Requires-Dist line into (package_name, version_constraint)."""
# Remove any environment markers (after semicolon)
if ";" in requires_dist:
requires_dist = requires_dist.split(";")[0].strip()
# Match patterns like "package (>=1.0)" or "package>=1.0" or "package"
match = re.match(
r"^([a-zA-Z0-9][-a-zA-Z0-9._]*)\s*(?:\(([^)]+)\)|([<>=!~][^\s;]+))?",
requires_dist.strip(),
)
if not match:
return None, None
package_name = match.group(1)
version_constraint = match.group(2) or match.group(3)
# Normalize package name (PEP 503)
normalized_name = re.sub(r"[-_.]+", "-", package_name).lower()
if version_constraint:
version_constraint = version_constraint.strip()
return normalized_name, version_constraint
def extract_requires_from_metadata(metadata_content: str) -> List[Tuple[str, Optional[str]]]:
"""Extract all Requires-Dist entries from METADATA/PKG-INFO content."""
dependencies = []
for line in metadata_content.split("\n"):
if line.startswith("Requires-Dist:"):
value = line[len("Requires-Dist:"):].strip()
pkg_name, version = parse_requires_dist(value)
if pkg_name:
dependencies.append((pkg_name, version))
return dependencies
def extract_metadata_from_wheel(content: bytes) -> Optional[str]:
"""Extract METADATA file content from a wheel (zip) file."""
try:
with zipfile.ZipFile(BytesIO(content)) as zf:
for name in zf.namelist():
if name.endswith(".dist-info/METADATA"):
return zf.read(name).decode("utf-8", errors="replace")
except Exception as e:
logger.warning(f"Failed to extract metadata from wheel: {e}")
return None
def extract_metadata_from_sdist(content: bytes) -> Optional[str]:
"""Extract PKG-INFO file content from a source distribution (.tar.gz)."""
try:
with tarfile.open(fileobj=BytesIO(content), mode="r:gz") as tf:
for member in tf.getmembers():
if member.name.endswith("/PKG-INFO") and member.name.count("/") == 1:
f = tf.extractfile(member)
if f:
return f.read().decode("utf-8", errors="replace")
except Exception as e:
logger.warning(f"Failed to extract metadata from sdist: {e}")
return None
def extract_dependencies(content: bytes, filename: str) -> List[Tuple[str, Optional[str]]]:
"""Extract dependencies from a PyPI package file."""
metadata = None
if filename.endswith(".whl"):
metadata = extract_metadata_from_wheel(content)
elif filename.endswith(".tar.gz"):
metadata = extract_metadata_from_sdist(content)
if metadata:
return extract_requires_from_metadata(metadata)
return []
def backfill_dependencies(dry_run: bool = False):
"""Main backfill function."""
settings = get_settings()
# Create database connection
engine = create_engine(settings.database_url)
Session = sessionmaker(bind=engine)
db = Session()
# Create storage client
storage = get_storage()
try:
# Find the _pypi project
pypi_project = db.query(Project).filter(Project.name == "_pypi").first()
if not pypi_project:
logger.info("No _pypi project found. Nothing to backfill.")
return
# Get all packages in _pypi
packages = db.query(Package).filter(Package.project_id == pypi_project.id).all()
logger.info(f"Found {len(packages)} packages in _pypi project")
total_artifacts = 0
artifacts_with_deps = 0
artifacts_processed = 0
dependencies_added = 0
for package in packages:
# Get all tags (each tag points to an artifact)
tags = db.query(Tag).filter(Tag.package_id == package.id).all()
for tag in tags:
total_artifacts += 1
filename = tag.name
# Skip non-package files (like .metadata files)
if not (filename.endswith(".whl") or filename.endswith(".tar.gz")):
continue
# Check if this artifact already has dependencies
existing_deps = db.query(ArtifactDependency).filter(
ArtifactDependency.artifact_id == tag.artifact_id
).count()
if existing_deps > 0:
artifacts_with_deps += 1
continue
# Get the artifact
artifact = db.query(Artifact).filter(Artifact.id == tag.artifact_id).first()
if not artifact:
logger.warning(f"Artifact {tag.artifact_id} not found for tag {filename}")
continue
logger.info(f"Processing {package.name}/{filename}...")
if dry_run:
logger.info(f" [DRY RUN] Would extract dependencies from {filename}")
artifacts_processed += 1
continue
# Download the artifact from S3
try:
content = storage.get(artifact.s3_key)
except Exception as e:
logger.error(f" Failed to download {filename}: {e}")
continue
# Extract dependencies
deps = extract_dependencies(content, filename)
if deps:
logger.info(f" Found {len(deps)} dependencies")
for dep_name, dep_version in deps:
# Check if already exists (race condition protection)
existing = db.query(ArtifactDependency).filter(
ArtifactDependency.artifact_id == tag.artifact_id,
ArtifactDependency.dependency_project == "_pypi",
ArtifactDependency.dependency_package == dep_name,
).first()
if not existing:
dep = ArtifactDependency(
artifact_id=tag.artifact_id,
dependency_project="_pypi",
dependency_package=dep_name,
version_constraint=dep_version if dep_version else "*",
)
db.add(dep)
dependencies_added += 1
logger.info(f" + {dep_name} {dep_version or '*'}")
db.commit()
else:
logger.info(f" No dependencies found")
artifacts_processed += 1
logger.info("")
logger.info("=" * 50)
logger.info("Backfill complete!")
logger.info(f" Total artifacts: {total_artifacts}")
logger.info(f" Already had deps: {artifacts_with_deps}")
logger.info(f" Processed: {artifacts_processed}")
logger.info(f" Dependencies added: {dependencies_added}")
if dry_run:
logger.info(" (DRY RUN - no changes made)")
finally:
db.close()
def main():
parser = argparse.ArgumentParser(
description="Backfill dependencies for cached PyPI packages"
)
parser.add_argument(
"--dry-run",
action="store_true",
help="Preview what would be done without making changes",
)
args = parser.parse_args()
backfill_dependencies(dry_run=args.dry_run)
if __name__ == "__main__":
main()

View File

@@ -96,6 +96,7 @@ def upload_test_file(
package: str,
content: bytes,
filename: str = "test.bin",
tag: Optional[str] = None,
version: Optional[str] = None,
) -> dict:
"""
@@ -107,6 +108,7 @@ def upload_test_file(
package: Package name
content: File content as bytes
filename: Original filename
tag: Optional tag to assign
version: Optional version to assign
Returns:
@@ -114,6 +116,8 @@ def upload_test_file(
"""
files = {"file": (filename, io.BytesIO(content), "application/octet-stream")}
data = {}
if tag:
data["tag"] = tag
if version:
data["version"] = version

View File

@@ -25,7 +25,7 @@ class TestArtifactRetrieval:
expected_hash = compute_sha256(content)
upload_test_file(
integration_client, project_name, package_name, content, version="v1"
integration_client, project_name, package_name, content, tag="v1"
)
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
@@ -46,27 +46,27 @@ class TestArtifactRetrieval:
assert response.status_code == 404
@pytest.mark.integration
def test_artifact_includes_versions(self, integration_client, test_package):
"""Test artifact response includes versions pointing to it."""
def test_artifact_includes_tags(self, integration_client, test_package):
"""Test artifact response includes tags pointing to it."""
project_name, package_name = test_package
content = b"artifact with versions test"
content = b"artifact with tags test"
expected_hash = compute_sha256(content)
upload_test_file(
integration_client, project_name, package_name, content, version="1.0.0"
integration_client, project_name, package_name, content, tag="tagged-v1"
)
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
assert response.status_code == 200
data = response.json()
assert "versions" in data
assert len(data["versions"]) >= 1
assert "tags" in data
assert len(data["tags"]) >= 1
version = data["versions"][0]
assert "version" in version
assert "package_name" in version
assert "project_name" in version
tag = data["tags"][0]
assert "name" in tag
assert "package_name" in tag
assert "project_name" in tag
class TestArtifactStats:
@@ -82,7 +82,7 @@ class TestArtifactStats:
expected_hash = compute_sha256(content)
upload_test_file(
integration_client, project, package, content, version=f"art-{unique_test_id}"
integration_client, project, package, content, tag=f"art-{unique_test_id}"
)
response = integration_client.get(f"/api/v1/artifact/{expected_hash}/stats")
@@ -94,7 +94,7 @@ class TestArtifactStats:
assert "size" in data
assert "ref_count" in data
assert "storage_savings" in data
assert "versions" in data
assert "tags" in data
assert "projects" in data
assert "packages" in data
@@ -136,8 +136,8 @@ class TestArtifactStats:
)
# Upload same content to both projects
upload_test_file(integration_client, proj1, "pkg", content, version="v1")
upload_test_file(integration_client, proj2, "pkg", content, version="v1")
upload_test_file(integration_client, proj1, "pkg", content, tag="v1")
upload_test_file(integration_client, proj2, "pkg", content, tag="v1")
# Check artifact stats
response = integration_client.get(f"/api/v1/artifact/{expected_hash}/stats")
@@ -203,7 +203,7 @@ class TestArtifactProvenance:
assert "first_uploaded_by" in data
assert "upload_count" in data
assert "packages" in data
assert "versions" in data
assert "tags" in data
assert "uploads" in data
@pytest.mark.integration
@@ -214,17 +214,17 @@ class TestArtifactProvenance:
assert response.status_code == 404
@pytest.mark.integration
def test_artifact_history_with_version(self, integration_client, test_package):
"""Test artifact history includes version information when versioned."""
def test_artifact_history_with_tag(self, integration_client, test_package):
"""Test artifact history includes tag information when tagged."""
project_name, package_name = test_package
upload_result = upload_test_file(
integration_client,
project_name,
package_name,
b"versioned provenance test",
"versioned.txt",
version="v1.0.0",
b"tagged provenance test",
"tagged.txt",
tag="v1.0.0",
)
artifact_id = upload_result["artifact_id"]
@@ -232,12 +232,12 @@ class TestArtifactProvenance:
assert response.status_code == 200
data = response.json()
assert len(data["versions"]) >= 1
assert len(data["tags"]) >= 1
version = data["versions"][0]
assert "project_name" in version
assert "package_name" in version
assert "version" in version
tag = data["tags"][0]
assert "project_name" in tag
assert "package_name" in tag
assert "tag_name" in tag
class TestArtifactUploads:
@@ -306,24 +306,24 @@ class TestOrphanedArtifacts:
assert len(response.json()) <= 5
@pytest.mark.integration
def test_artifact_becomes_orphaned_when_version_deleted(
def test_artifact_becomes_orphaned_when_tag_deleted(
self, integration_client, test_package, unique_test_id
):
"""Test artifact appears in orphaned list after version is deleted."""
"""Test artifact appears in orphaned list after tag is deleted."""
project, package = test_package
content = f"orphan test {unique_test_id}".encode()
expected_hash = compute_sha256(content)
# Upload with version
upload_test_file(integration_client, project, package, content, version="1.0.0-temp")
# Upload with tag
upload_test_file(integration_client, project, package, content, tag="temp-tag")
# Verify not in orphaned list
response = integration_client.get("/api/v1/admin/orphaned-artifacts?limit=1000")
orphaned_ids = [a["id"] for a in response.json()]
assert expected_hash not in orphaned_ids
# Delete the version
integration_client.delete(f"/api/v1/project/{project}/{package}/versions/1.0.0-temp")
# Delete the tag
integration_client.delete(f"/api/v1/project/{project}/{package}/tags/temp-tag")
# Verify now in orphaned list
response = integration_client.get("/api/v1/admin/orphaned-artifacts?limit=1000")
@@ -356,9 +356,9 @@ class TestGarbageCollection:
content = f"dry run test {unique_test_id}".encode()
expected_hash = compute_sha256(content)
# Upload and delete version to create orphan
upload_test_file(integration_client, project, package, content, version="1.0.0-dryrun")
integration_client.delete(f"/api/v1/project/{project}/{package}/versions/1.0.0-dryrun")
# Upload and delete tag to create orphan
upload_test_file(integration_client, project, package, content, tag="dry-run")
integration_client.delete(f"/api/v1/project/{project}/{package}/tags/dry-run")
# Verify artifact exists
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
@@ -385,7 +385,7 @@ class TestGarbageCollection:
expected_hash = compute_sha256(content)
# Upload with tag (ref_count=1)
upload_test_file(integration_client, project, package, content, version="keep-this")
upload_test_file(integration_client, project, package, content, tag="keep-this")
# Verify artifact exists with ref_count=1
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
@@ -534,6 +534,50 @@ class TestGlobalArtifacts:
assert response.status_code == 400
class TestGlobalTags:
"""Tests for global tags endpoint."""
@pytest.mark.integration
def test_global_tags_returns_200(self, integration_client):
"""Test global tags endpoint returns 200."""
response = integration_client.get("/api/v1/tags")
assert response.status_code == 200
data = response.json()
assert "items" in data
assert "pagination" in data
@pytest.mark.integration
def test_global_tags_pagination(self, integration_client):
"""Test global tags endpoint respects pagination."""
response = integration_client.get("/api/v1/tags?limit=5&page=1")
assert response.status_code == 200
data = response.json()
assert len(data["items"]) <= 5
assert data["pagination"]["limit"] == 5
@pytest.mark.integration
def test_global_tags_has_project_context(self, integration_client):
"""Test global tags response includes project/package context."""
response = integration_client.get("/api/v1/tags?limit=1")
assert response.status_code == 200
data = response.json()
if len(data["items"]) > 0:
item = data["items"][0]
assert "project_name" in item
assert "package_name" in item
assert "artifact_id" in item
@pytest.mark.integration
def test_global_tags_search_with_wildcard(self, integration_client):
"""Test global tags search supports wildcards."""
response = integration_client.get("/api/v1/tags?search=v*")
assert response.status_code == 200
# Just verify it doesn't error; results may vary
class TestAuditLogs:
"""Tests for global audit logs endpoint."""

View File

@@ -63,7 +63,7 @@ class TestConcurrentUploads:
response = client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files,
data={"version": f"concurrent-{idx}"},
data={"tag": f"concurrent-{idx}"},
headers={"Authorization": f"Bearer {api_key}"},
)
if response.status_code == 200:
@@ -117,7 +117,7 @@ class TestConcurrentUploads:
response = client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files,
data={"version": f"concurrent5-{idx}"},
data={"tag": f"concurrent5-{idx}"},
headers={"Authorization": f"Bearer {api_key}"},
)
if response.status_code == 200:
@@ -171,7 +171,7 @@ class TestConcurrentUploads:
response = client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files,
data={"version": f"concurrent10-{idx}"},
data={"tag": f"concurrent10-{idx}"},
headers={"Authorization": f"Bearer {api_key}"},
)
if response.status_code == 200:
@@ -195,38 +195,19 @@ class TestConcurrentUploads:
@pytest.mark.integration
@pytest.mark.concurrent
def test_concurrent_uploads_same_file_deduplication(
self, integration_client, test_project, unique_test_id
):
"""Test concurrent uploads of same file handle deduplication correctly.
Same content uploaded to different packages should result in:
- Same artifact_id (content-addressable)
- ref_count = number of packages (one version per package)
"""
project = test_project
def test_concurrent_uploads_same_file_deduplication(self, integration_client, test_package):
"""Test concurrent uploads of same file handle deduplication correctly."""
project, package = test_package
api_key = get_api_key(integration_client)
assert api_key, "Failed to create API key"
num_concurrent = 5
package_names = []
# Create multiple packages for concurrent uploads
for i in range(num_concurrent):
pkg_name = f"dedup-pkg-{unique_test_id}-{i}"
response = integration_client.post(
f"/api/v1/project/{project}/packages",
json={"name": pkg_name, "description": f"Dedup test package {i}"},
)
assert response.status_code == 200
package_names.append(pkg_name)
content, expected_hash = generate_content_with_hash(4096, seed=999)
num_concurrent = 5
results = []
errors = []
def upload_worker(idx, package):
def upload_worker(idx):
try:
from httpx import Client
base_url = os.environ.get("ORCHARD_TEST_URL", "http://localhost:8080")
@@ -238,7 +219,7 @@ class TestConcurrentUploads:
response = client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": f"dedup-{idx}"},
headers={"Authorization": f"Bearer {api_key}"},
)
if response.status_code == 200:
@@ -249,10 +230,7 @@ class TestConcurrentUploads:
errors.append(f"Worker {idx}: {str(e)}")
with ThreadPoolExecutor(max_workers=num_concurrent) as executor:
futures = [
executor.submit(upload_worker, i, package_names[i])
for i in range(num_concurrent)
]
futures = [executor.submit(upload_worker, i) for i in range(num_concurrent)]
for future in as_completed(futures):
pass
@@ -264,7 +242,7 @@ class TestConcurrentUploads:
assert len(artifact_ids) == 1
assert expected_hash in artifact_ids
# Verify final ref_count equals number of packages
# Verify final ref_count equals number of uploads
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
assert response.status_code == 200
assert response.json()["ref_count"] == num_concurrent
@@ -309,7 +287,7 @@ class TestConcurrentUploads:
response = client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files,
data={"version": "latest"},
data={"tag": "latest"},
headers={"Authorization": f"Bearer {api_key}"},
)
if response.status_code == 200:
@@ -343,7 +321,7 @@ class TestConcurrentDownloads:
content, expected_hash = generate_content_with_hash(2048, seed=400)
# Upload first
upload_test_file(integration_client, project, package, content, version="download-test")
upload_test_file(integration_client, project, package, content, tag="download-test")
results = []
errors = []
@@ -384,7 +362,7 @@ class TestConcurrentDownloads:
project, package = test_package
content, expected_hash = generate_content_with_hash(4096, seed=500)
upload_test_file(integration_client, project, package, content, version="download5-test")
upload_test_file(integration_client, project, package, content, tag="download5-test")
num_downloads = 5
results = []
@@ -425,7 +403,7 @@ class TestConcurrentDownloads:
project, package = test_package
content, expected_hash = generate_content_with_hash(8192, seed=600)
upload_test_file(integration_client, project, package, content, version="download10-test")
upload_test_file(integration_client, project, package, content, tag="download10-test")
num_downloads = 10
results = []
@@ -472,7 +450,7 @@ class TestConcurrentDownloads:
content, expected_hash = generate_content_with_hash(1024, seed=700 + i)
upload_test_file(
integration_client, project, package, content,
version=f"multi-download-{i}"
tag=f"multi-download-{i}"
)
uploads.append((f"multi-download-{i}", content))
@@ -524,7 +502,7 @@ class TestMixedConcurrentOperations:
# Upload initial content
content1, hash1 = generate_content_with_hash(10240, seed=800) # 10KB
upload_test_file(integration_client, project, package, content1, version="initial")
upload_test_file(integration_client, project, package, content1, tag="initial")
# New content for upload during download
content2, hash2 = generate_content_with_hash(10240, seed=801)
@@ -561,7 +539,7 @@ class TestMixedConcurrentOperations:
response = client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files,
data={"version": "during-download"},
data={"tag": "during-download"},
headers={"Authorization": f"Bearer {api_key}"},
)
if response.status_code == 200:
@@ -601,7 +579,7 @@ class TestMixedConcurrentOperations:
existing_files = []
for i in range(3):
content, hash = generate_content_with_hash(2048, seed=900 + i)
upload_test_file(integration_client, project, package, content, version=f"existing-{i}")
upload_test_file(integration_client, project, package, content, tag=f"existing-{i}")
existing_files.append((f"existing-{i}", content))
# New files for uploading
@@ -641,7 +619,7 @@ class TestMixedConcurrentOperations:
response = client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files,
data={"version": f"new-{idx}"},
data={"tag": f"new-{idx}"},
headers={"Authorization": f"Bearer {api_key}"},
)
if response.status_code == 200:
@@ -711,7 +689,7 @@ class TestMixedConcurrentOperations:
upload_resp = client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files,
data={"version": f"pattern-{idx}"},
data={"tag": f"pattern-{idx}"},
headers={"Authorization": f"Bearer {api_key}"},
)
if upload_resp.status_code != 200:

View File

@@ -68,7 +68,7 @@ class TestUploadErrorHandling:
response = integration_client.post(
f"/api/v1/project/{project}/{package}/upload",
data={"version": "no-file-provided"},
data={"tag": "no-file-provided"},
)
assert response.status_code == 422
@@ -200,7 +200,7 @@ class TestTimeoutBehavior:
start_time = time.time()
result = upload_test_file(
integration_client, project, package, content, version="timeout-test"
integration_client, project, package, content, tag="timeout-test"
)
elapsed = time.time() - start_time
@@ -219,7 +219,7 @@ class TestTimeoutBehavior:
# First upload
upload_test_file(
integration_client, project, package, content, version="download-timeout-test"
integration_client, project, package, content, tag="download-timeout-test"
)
# Then download and time it

View File

@@ -41,7 +41,7 @@ class TestRoundTripVerification:
# Upload and capture returned hash
result = upload_test_file(
integration_client, project, package, content, version="roundtrip"
integration_client, project, package, content, tag="roundtrip"
)
uploaded_hash = result["artifact_id"]
@@ -84,7 +84,7 @@ class TestRoundTripVerification:
expected_hash = compute_sha256(content)
upload_test_file(
integration_client, project, package, content, version="header-check"
integration_client, project, package, content, tag="header-check"
)
response = integration_client.get(
@@ -102,7 +102,7 @@ class TestRoundTripVerification:
expected_hash = compute_sha256(content)
upload_test_file(
integration_client, project, package, content, version="etag-check"
integration_client, project, package, content, tag="etag-check"
)
response = integration_client.get(
@@ -186,7 +186,7 @@ class TestClientSideVerificationWorkflow:
content = b"Client post-download verification"
upload_test_file(
integration_client, project, package, content, version="verify-after"
integration_client, project, package, content, tag="verify-after"
)
response = integration_client.get(
@@ -215,7 +215,7 @@ class TestIntegritySizeVariants:
content, expected_hash = sized_content(SIZE_1KB, seed=100)
result = upload_test_file(
integration_client, project, package, content, version="int-1kb"
integration_client, project, package, content, tag="int-1kb"
)
assert result["artifact_id"] == expected_hash
@@ -234,7 +234,7 @@ class TestIntegritySizeVariants:
content, expected_hash = sized_content(SIZE_100KB, seed=101)
result = upload_test_file(
integration_client, project, package, content, version="int-100kb"
integration_client, project, package, content, tag="int-100kb"
)
assert result["artifact_id"] == expected_hash
@@ -253,7 +253,7 @@ class TestIntegritySizeVariants:
content, expected_hash = sized_content(SIZE_1MB, seed=102)
result = upload_test_file(
integration_client, project, package, content, version="int-1mb"
integration_client, project, package, content, tag="int-1mb"
)
assert result["artifact_id"] == expected_hash
@@ -273,7 +273,7 @@ class TestIntegritySizeVariants:
content, expected_hash = sized_content(SIZE_10MB, seed=103)
result = upload_test_file(
integration_client, project, package, content, version="int-10mb"
integration_client, project, package, content, tag="int-10mb"
)
assert result["artifact_id"] == expected_hash
@@ -323,13 +323,7 @@ class TestConsistencyCheck:
@pytest.mark.integration
def test_consistency_check_after_upload(self, integration_client, test_package):
"""Test consistency check runs successfully after a valid upload.
Note: We don't assert healthy=True because other tests (especially
corruption detection tests) may leave orphaned S3 objects behind.
This test validates the consistency check endpoint works and the
uploaded artifact is included in the check count.
"""
"""Test consistency check passes after valid upload."""
project, package = test_package
content = b"Consistency check test content"
@@ -341,10 +335,9 @@ class TestConsistencyCheck:
assert response.status_code == 200
data = response.json()
# Verify check ran - at least 1 artifact was checked
# Verify check ran and no issues
assert data["total_artifacts_checked"] >= 1
# Verify no missing S3 objects (uploaded artifact should exist)
assert data["missing_s3_objects"] == 0
assert data["healthy"] is True
@pytest.mark.integration
def test_consistency_check_limit_parameter(self, integration_client):
@@ -373,7 +366,7 @@ class TestDigestHeader:
expected_hash = compute_sha256(content)
upload_test_file(
integration_client, project, package, content, version="digest-test"
integration_client, project, package, content, tag="digest-test"
)
response = integration_client.get(
@@ -397,7 +390,7 @@ class TestDigestHeader:
expected_hash = compute_sha256(content)
upload_test_file(
integration_client, project, package, content, version="digest-b64"
integration_client, project, package, content, tag="digest-b64"
)
response = integration_client.get(
@@ -427,7 +420,7 @@ class TestVerificationModes:
content = b"Pre-verification mode test"
upload_test_file(
integration_client, project, package, content, version="pre-verify"
integration_client, project, package, content, tag="pre-verify"
)
response = integration_client.get(
@@ -447,7 +440,7 @@ class TestVerificationModes:
content = b"Stream verification mode test"
upload_test_file(
integration_client, project, package, content, version="stream-verify"
integration_client, project, package, content, tag="stream-verify"
)
response = integration_client.get(
@@ -484,7 +477,7 @@ class TestArtifactIntegrityEndpoint:
expected_size = len(content)
upload_test_file(
integration_client, project, package, content, version="content-len"
integration_client, project, package, content, tag="content-len"
)
response = integration_client.get(
@@ -520,7 +513,7 @@ class TestCorruptionDetection:
# Upload original content
result = upload_test_file(
integration_client, project, package, content, version="corrupt-test"
integration_client, project, package, content, tag="corrupt-test"
)
assert result["artifact_id"] == expected_hash
@@ -562,7 +555,7 @@ class TestCorruptionDetection:
expected_hash = compute_sha256(content)
result = upload_test_file(
integration_client, project, package, content, version="bitflip-test"
integration_client, project, package, content, tag="bitflip-test"
)
assert result["artifact_id"] == expected_hash
@@ -599,7 +592,7 @@ class TestCorruptionDetection:
expected_hash = compute_sha256(content)
result = upload_test_file(
integration_client, project, package, content, version="truncate-test"
integration_client, project, package, content, tag="truncate-test"
)
assert result["artifact_id"] == expected_hash
@@ -634,7 +627,7 @@ class TestCorruptionDetection:
expected_hash = compute_sha256(content)
result = upload_test_file(
integration_client, project, package, content, version="append-test"
integration_client, project, package, content, tag="append-test"
)
assert result["artifact_id"] == expected_hash
@@ -677,7 +670,7 @@ class TestCorruptionDetection:
expected_hash = compute_sha256(content)
result = upload_test_file(
integration_client, project, package, content, version="client-detect"
integration_client, project, package, content, tag="client-detect"
)
# Corrupt the S3 object
@@ -720,7 +713,7 @@ class TestCorruptionDetection:
expected_hash = compute_sha256(content)
result = upload_test_file(
integration_client, project, package, content, version="size-mismatch"
integration_client, project, package, content, tag="size-mismatch"
)
# Modify S3 object to have different size
@@ -754,7 +747,7 @@ class TestCorruptionDetection:
expected_hash = compute_sha256(content)
result = upload_test_file(
integration_client, project, package, content, version="missing-s3"
integration_client, project, package, content, tag="missing-s3"
)
# Delete the S3 object

View File

@@ -41,7 +41,7 @@ class TestUploadMetrics:
content = b"duration test content"
result = upload_test_file(
integration_client, project, package, content, version="duration-test"
integration_client, project, package, content, tag="duration-test"
)
assert "duration_ms" in result
@@ -55,7 +55,7 @@ class TestUploadMetrics:
content = b"throughput test content"
result = upload_test_file(
integration_client, project, package, content, version="throughput-test"
integration_client, project, package, content, tag="throughput-test"
)
assert "throughput_mbps" in result
@@ -72,7 +72,7 @@ class TestUploadMetrics:
start = time.time()
result = upload_test_file(
integration_client, project, package, content, version="duration-check"
integration_client, project, package, content, tag="duration-check"
)
actual_duration = (time.time() - start) * 1000 # ms
@@ -92,7 +92,7 @@ class TestLargeFileUploads:
content, expected_hash = sized_content(SIZE_10MB, seed=200)
result = upload_test_file(
integration_client, project, package, content, version="large-10mb"
integration_client, project, package, content, tag="large-10mb"
)
assert result["artifact_id"] == expected_hash
@@ -109,7 +109,7 @@ class TestLargeFileUploads:
content, expected_hash = sized_content(SIZE_100MB, seed=300)
result = upload_test_file(
integration_client, project, package, content, version="large-100mb"
integration_client, project, package, content, tag="large-100mb"
)
assert result["artifact_id"] == expected_hash
@@ -126,7 +126,7 @@ class TestLargeFileUploads:
content, expected_hash = sized_content(SIZE_1GB, seed=400)
result = upload_test_file(
integration_client, project, package, content, version="large-1gb"
integration_client, project, package, content, tag="large-1gb"
)
assert result["artifact_id"] == expected_hash
@@ -147,14 +147,14 @@ class TestLargeFileUploads:
# First upload
result1 = upload_test_file(
integration_client, project, package, content, version=f"dedup-{unique_test_id}-1"
integration_client, project, package, content, tag=f"dedup-{unique_test_id}-1"
)
# Note: may be True if previous test uploaded same content
first_dedupe = result1["deduplicated"]
# Second upload of same content
result2 = upload_test_file(
integration_client, project, package, content, version=f"dedup-{unique_test_id}-2"
integration_client, project, package, content, tag=f"dedup-{unique_test_id}-2"
)
assert result2["artifact_id"] == expected_hash
# Second upload MUST be deduplicated
@@ -277,7 +277,7 @@ class TestUploadSizeLimits:
content = b"X"
result = upload_test_file(
integration_client, project, package, content, version="min-size"
integration_client, project, package, content, tag="min-size"
)
assert result["size"] == 1
@@ -289,7 +289,7 @@ class TestUploadSizeLimits:
content = b"content length verification test"
result = upload_test_file(
integration_client, project, package, content, version="content-length-test"
integration_client, project, package, content, tag="content-length-test"
)
# Size in response should match actual content length
@@ -336,7 +336,7 @@ class TestUploadErrorHandling:
response = integration_client.post(
f"/api/v1/project/{project}/{package}/upload",
data={"version": "no-file"},
data={"tag": "no-file"},
)
assert response.status_code == 422
@@ -459,7 +459,7 @@ class TestUploadTimeout:
# httpx client should handle this quickly
result = upload_test_file(
integration_client, project, package, content, version="timeout-small"
integration_client, project, package, content, tag="timeout-small"
)
assert result["artifact_id"] is not None
@@ -474,7 +474,7 @@ class TestUploadTimeout:
start = time.time()
result = upload_test_file(
integration_client, project, package, content, version="timeout-check"
integration_client, project, package, content, tag="timeout-check"
)
duration = time.time() - start
@@ -525,7 +525,7 @@ class TestConcurrentUploads:
response = client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files,
data={"version": f"concurrent-diff-{idx}"},
data={"tag": f"concurrent-diff-{idx}"},
headers={"Authorization": f"Bearer {api_key}"},
)
if response.status_code == 200:

View File

@@ -175,7 +175,7 @@ class TestPackageStats:
assert "package_id" in data
assert "package_name" in data
assert "project_name" in data
assert "version_count" in data
assert "tag_count" in data
assert "artifact_count" in data
assert "total_size_bytes" in data
assert "upload_count" in data
@@ -234,11 +234,7 @@ class TestPackageCascadeDelete:
def test_ref_count_decrements_on_package_delete(
self, integration_client, unique_test_id
):
"""Test ref_count decrements when package is deleted.
Each package can only have one version per artifact (same content = same version).
This test verifies that deleting a package decrements the artifact's ref_count.
"""
"""Test ref_count decrements for all tags when package is deleted."""
project_name = f"cascade-pkg-{unique_test_id}"
package_name = f"test-pkg-{unique_test_id}"
@@ -260,17 +256,23 @@ class TestPackageCascadeDelete:
)
assert response.status_code == 200
# Upload content with version
# Upload content with multiple tags
content = f"cascade delete test {unique_test_id}".encode()
expected_hash = compute_sha256(content)
upload_test_file(
integration_client, project_name, package_name, content, version="1.0.0"
integration_client, project_name, package_name, content, tag="v1"
)
upload_test_file(
integration_client, project_name, package_name, content, tag="v2"
)
upload_test_file(
integration_client, project_name, package_name, content, tag="v3"
)
# Verify ref_count is 1
# Verify ref_count is 3
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
assert response.json()["ref_count"] == 1
assert response.json()["ref_count"] == 3
# Delete the package
delete_response = integration_client.delete(

View File

@@ -128,9 +128,7 @@ class TestProjectListingFilters:
assert response.status_code == 200
data = response.json()
# Filter out system projects (names starting with "_") as they may have
# collation-specific sort behavior and aren't part of the test data
names = [p["name"] for p in data["items"] if not p["name"].startswith("_")]
names = [p["name"] for p in data["items"]]
assert names == sorted(names)
@@ -149,7 +147,7 @@ class TestProjectStats:
assert "project_id" in data
assert "project_name" in data
assert "package_count" in data
assert "version_count" in data
assert "tag_count" in data
assert "artifact_count" in data
assert "total_size_bytes" in data
assert "upload_count" in data
@@ -229,11 +227,7 @@ class TestProjectCascadeDelete:
def test_ref_count_decrements_on_project_delete(
self, integration_client, unique_test_id
):
"""Test ref_count decrements for all versions when project is deleted.
Each package can only have one version per artifact (same content = same version).
With 2 packages, ref_count should be 2, and go to 0 when project is deleted.
"""
"""Test ref_count decrements for all tags when project is deleted."""
project_name = f"cascade-proj-{unique_test_id}"
package1_name = f"pkg1-{unique_test_id}"
package2_name = f"pkg2-{unique_test_id}"
@@ -257,20 +251,26 @@ class TestProjectCascadeDelete:
)
assert response.status_code == 200
# Upload same content to both packages
# Upload same content with tags in both packages
content = f"project cascade test {unique_test_id}".encode()
expected_hash = compute_sha256(content)
upload_test_file(
integration_client, project_name, package1_name, content, version="1.0.0"
integration_client, project_name, package1_name, content, tag="v1"
)
upload_test_file(
integration_client, project_name, package2_name, content, version="1.0.0"
integration_client, project_name, package1_name, content, tag="v2"
)
upload_test_file(
integration_client, project_name, package2_name, content, tag="latest"
)
upload_test_file(
integration_client, project_name, package2_name, content, tag="stable"
)
# Verify ref_count is 2 (1 version in each of 2 packages)
# Verify ref_count is 4 (2 tags in each of 2 packages)
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
assert response.json()["ref_count"] == 2
assert response.json()["ref_count"] == 4
# Delete the project
delete_response = integration_client.delete(f"/api/v1/projects/{project_name}")

View File

@@ -1,153 +0,0 @@
"""Integration tests for PyPI transparent proxy."""
import os
import pytest
import httpx
def get_base_url():
"""Get the base URL for the Orchard server from environment."""
return os.environ.get("ORCHARD_TEST_URL", "http://localhost:8080")
class TestPyPIProxyEndpoints:
"""Tests for PyPI proxy endpoints.
These endpoints are public (no auth required) since pip needs to use them.
"""
@pytest.mark.integration
def test_pypi_simple_index(self):
"""Test that /pypi/simple/ returns HTML response."""
with httpx.Client(base_url=get_base_url(), timeout=30.0) as client:
response = client.get("/pypi/simple/")
# Returns 200 if sources configured, 503 if not
assert response.status_code in (200, 503)
if response.status_code == 200:
assert "text/html" in response.headers.get("content-type", "")
else:
assert "No PyPI upstream sources configured" in response.json()["detail"]
@pytest.mark.integration
def test_pypi_package_endpoint(self):
"""Test that /pypi/simple/{package}/ returns appropriate response."""
with httpx.Client(base_url=get_base_url(), timeout=30.0) as client:
response = client.get("/pypi/simple/requests/")
# Returns 200 if sources configured and package found,
# 404 if package not found, 503 if no sources
assert response.status_code in (200, 404, 503)
if response.status_code == 200:
assert "text/html" in response.headers.get("content-type", "")
elif response.status_code == 404:
assert "not found" in response.json()["detail"].lower()
else: # 503
assert "No PyPI upstream sources configured" in response.json()["detail"]
@pytest.mark.integration
def test_pypi_download_missing_upstream_param(self):
"""Test that /pypi/simple/{package}/{filename} requires upstream param."""
with httpx.Client(base_url=get_base_url(), timeout=30.0) as client:
response = client.get("/pypi/simple/requests/requests-2.31.0.tar.gz")
assert response.status_code == 400
assert "upstream" in response.json()["detail"].lower()
class TestPyPILinkRewriting:
"""Tests for URL rewriting in PyPI proxy responses."""
def test_rewrite_package_links(self):
"""Test that download links are rewritten to go through proxy."""
from app.pypi_proxy import _rewrite_package_links
html = '''
<html>
<body>
<a href="https://files.pythonhosted.org/packages/ab/cd/requests-2.31.0.tar.gz#sha256=abc123">requests-2.31.0.tar.gz</a>
<a href="https://files.pythonhosted.org/packages/ef/gh/requests-2.31.0-py3-none-any.whl#sha256=def456">requests-2.31.0-py3-none-any.whl</a>
</body>
</html>
'''
# upstream_base_url is used to resolve relative URLs (not needed here since URLs are absolute)
result = _rewrite_package_links(
html,
"http://localhost:8080",
"requests",
"https://pypi.org/simple/requests/"
)
# Links should be rewritten to go through our proxy
assert "/pypi/simple/requests/requests-2.31.0.tar.gz?upstream=" in result
assert "/pypi/simple/requests/requests-2.31.0-py3-none-any.whl?upstream=" in result
# Original URLs should be encoded in upstream param
assert "files.pythonhosted.org" in result
# Hash fragments should be preserved
assert "#sha256=abc123" in result
assert "#sha256=def456" in result
def test_rewrite_relative_links(self):
"""Test that relative URLs are resolved to absolute URLs."""
from app.pypi_proxy import _rewrite_package_links
# Artifactory-style relative URLs
html = '''
<html>
<body>
<a href="../../packages/ab/cd/requests-2.31.0.tar.gz#sha256=abc123">requests-2.31.0.tar.gz</a>
</body>
</html>
'''
result = _rewrite_package_links(
html,
"https://orchard.example.com",
"requests",
"https://artifactory.example.com/api/pypi/pypi-remote/simple/requests/"
)
# The relative URL should be resolved to absolute
# ../../packages/ab/cd/... from /api/pypi/pypi-remote/simple/requests/ resolves to /api/pypi/pypi-remote/packages/ab/cd/...
assert "upstream=https%3A%2F%2Fartifactory.example.com%2Fapi%2Fpypi%2Fpypi-remote%2Fpackages" in result
# Hash fragment should be preserved
assert "#sha256=abc123" in result
class TestPyPIPackageNormalization:
"""Tests for PyPI package name normalization."""
@pytest.mark.integration
def test_package_name_normalized(self):
"""Test that package names are normalized per PEP 503.
Different capitalizations/separators should all be valid paths.
The endpoint normalizes to lowercase with hyphens before lookup.
"""
with httpx.Client(base_url=get_base_url(), timeout=30.0) as client:
# Test various name formats - all should be valid endpoint paths
for package_name in ["Requests", "some_package", "some-package"]:
response = client.get(f"/pypi/simple/{package_name}/")
# 200 = found, 404 = not found, 503 = no sources configured
assert response.status_code in (200, 404, 503), \
f"Unexpected status {response.status_code} for {package_name}"
# Verify response is appropriate for the status code
if response.status_code == 200:
assert "text/html" in response.headers.get("content-type", "")
elif response.status_code == 503:
assert "No PyPI upstream sources configured" in response.json()["detail"]
class TestPyPIProxyInfrastructure:
"""Tests for PyPI proxy infrastructure integration."""
@pytest.mark.integration
def test_health_endpoint_includes_infrastructure(self, integration_client):
"""Health endpoint should report infrastructure status."""
response = integration_client.get("/health")
assert response.status_code == 200
data = response.json()
assert data["status"] == "ok"
# Infrastructure status should be present
assert "http_pool" in data
assert "cache" in data

View File

@@ -48,7 +48,7 @@ class TestSmallFileSizes:
result = upload_test_file(
integration_client, project, package, content,
filename="1byte.bin", version="1byte"
filename="1byte.bin", tag="1byte"
)
assert result["artifact_id"] == expected_hash
assert result["size"] == SIZE_1B
@@ -70,7 +70,7 @@ class TestSmallFileSizes:
result = upload_test_file(
integration_client, project, package, content,
filename="1kb.bin", version="1kb"
filename="1kb.bin", tag="1kb"
)
assert result["artifact_id"] == expected_hash
assert result["size"] == SIZE_1KB
@@ -90,7 +90,7 @@ class TestSmallFileSizes:
result = upload_test_file(
integration_client, project, package, content,
filename="10kb.bin", version="10kb"
filename="10kb.bin", tag="10kb"
)
assert result["artifact_id"] == expected_hash
assert result["size"] == SIZE_10KB
@@ -110,7 +110,7 @@ class TestSmallFileSizes:
result = upload_test_file(
integration_client, project, package, content,
filename="100kb.bin", version="100kb"
filename="100kb.bin", tag="100kb"
)
assert result["artifact_id"] == expected_hash
assert result["size"] == SIZE_100KB
@@ -134,7 +134,7 @@ class TestMediumFileSizes:
result = upload_test_file(
integration_client, project, package, content,
filename="1mb.bin", version="1mb"
filename="1mb.bin", tag="1mb"
)
assert result["artifact_id"] == expected_hash
assert result["size"] == SIZE_1MB
@@ -155,7 +155,7 @@ class TestMediumFileSizes:
result = upload_test_file(
integration_client, project, package, content,
filename="5mb.bin", version="5mb"
filename="5mb.bin", tag="5mb"
)
assert result["artifact_id"] == expected_hash
assert result["size"] == SIZE_5MB
@@ -177,7 +177,7 @@ class TestMediumFileSizes:
result = upload_test_file(
integration_client, project, package, content,
filename="10mb.bin", version="10mb"
filename="10mb.bin", tag="10mb"
)
assert result["artifact_id"] == expected_hash
assert result["size"] == SIZE_10MB
@@ -200,7 +200,7 @@ class TestMediumFileSizes:
start_time = time.time()
result = upload_test_file(
integration_client, project, package, content,
filename="50mb.bin", version="50mb"
filename="50mb.bin", tag="50mb"
)
upload_time = time.time() - start_time
@@ -240,7 +240,7 @@ class TestLargeFileSizes:
start_time = time.time()
result = upload_test_file(
integration_client, project, package, content,
filename="100mb.bin", version="100mb"
filename="100mb.bin", tag="100mb"
)
upload_time = time.time() - start_time
@@ -271,7 +271,7 @@ class TestLargeFileSizes:
start_time = time.time()
result = upload_test_file(
integration_client, project, package, content,
filename="250mb.bin", version="250mb"
filename="250mb.bin", tag="250mb"
)
upload_time = time.time() - start_time
@@ -302,7 +302,7 @@ class TestLargeFileSizes:
start_time = time.time()
result = upload_test_file(
integration_client, project, package, content,
filename="500mb.bin", version="500mb"
filename="500mb.bin", tag="500mb"
)
upload_time = time.time() - start_time
@@ -336,7 +336,7 @@ class TestLargeFileSizes:
start_time = time.time()
result = upload_test_file(
integration_client, project, package, content,
filename="1gb.bin", version="1gb"
filename="1gb.bin", tag="1gb"
)
upload_time = time.time() - start_time
@@ -368,7 +368,7 @@ class TestChunkBoundaries:
result = upload_test_file(
integration_client, project, package, content,
filename="chunk.bin", version="chunk-exact"
filename="chunk.bin", tag="chunk-exact"
)
assert result["artifact_id"] == expected_hash
assert result["size"] == CHUNK_SIZE
@@ -389,7 +389,7 @@ class TestChunkBoundaries:
result = upload_test_file(
integration_client, project, package, content,
filename="chunk_plus.bin", version="chunk-plus"
filename="chunk_plus.bin", tag="chunk-plus"
)
assert result["artifact_id"] == expected_hash
assert result["size"] == size
@@ -410,7 +410,7 @@ class TestChunkBoundaries:
result = upload_test_file(
integration_client, project, package, content,
filename="chunk_minus.bin", version="chunk-minus"
filename="chunk_minus.bin", tag="chunk-minus"
)
assert result["artifact_id"] == expected_hash
assert result["size"] == size
@@ -431,7 +431,7 @@ class TestChunkBoundaries:
result = upload_test_file(
integration_client, project, package, content,
filename="multi_chunk.bin", version="multi-chunk"
filename="multi_chunk.bin", tag="multi-chunk"
)
assert result["artifact_id"] == expected_hash
assert result["size"] == size
@@ -457,7 +457,7 @@ class TestDataIntegrity:
result = upload_test_file(
integration_client, project, package, content,
filename="binary.bin", version="binary"
filename="binary.bin", tag="binary"
)
assert result["artifact_id"] == expected_hash
@@ -477,7 +477,7 @@ class TestDataIntegrity:
result = upload_test_file(
integration_client, project, package, content,
filename="text.txt", version="text"
filename="text.txt", tag="text"
)
assert result["artifact_id"] == expected_hash
@@ -498,7 +498,7 @@ class TestDataIntegrity:
result = upload_test_file(
integration_client, project, package, content,
filename="nulls.bin", version="nulls"
filename="nulls.bin", tag="nulls"
)
assert result["artifact_id"] == expected_hash
@@ -519,7 +519,7 @@ class TestDataIntegrity:
result = upload_test_file(
integration_client, project, package, content,
filename="文件名.txt", version="unicode-name"
filename="文件名.txt", tag="unicode-name"
)
assert result["artifact_id"] == expected_hash
assert result["original_name"] == "文件名.txt"
@@ -543,7 +543,7 @@ class TestDataIntegrity:
result = upload_test_file(
integration_client, project, package, content,
filename="data.gz", version="compressed"
filename="data.gz", tag="compressed"
)
assert result["artifact_id"] == expected_hash
@@ -568,7 +568,7 @@ class TestDataIntegrity:
result = upload_test_file(
integration_client, project, package, content,
filename=f"hash_test_{size}.bin", version=f"hash-{size}"
filename=f"hash_test_{size}.bin", tag=f"hash-{size}"
)
# Verify artifact_id matches expected hash

View File

@@ -32,7 +32,7 @@ class TestRangeRequests:
"""Test range request for first N bytes."""
project, package = test_package
content = b"0123456789" * 100 # 1000 bytes
upload_test_file(integration_client, project, package, content, version="range-test")
upload_test_file(integration_client, project, package, content, tag="range-test")
# Request first 10 bytes
response = integration_client.get(
@@ -50,7 +50,7 @@ class TestRangeRequests:
"""Test range request for bytes in the middle."""
project, package = test_package
content = b"ABCDEFGHIJKLMNOPQRSTUVWXYZ"
upload_test_file(integration_client, project, package, content, version="range-mid")
upload_test_file(integration_client, project, package, content, tag="range-mid")
# Request bytes 10-19 (KLMNOPQRST)
response = integration_client.get(
@@ -66,7 +66,7 @@ class TestRangeRequests:
"""Test range request for last N bytes (suffix range)."""
project, package = test_package
content = b"0123456789ABCDEF" # 16 bytes
upload_test_file(integration_client, project, package, content, version="range-suffix")
upload_test_file(integration_client, project, package, content, tag="range-suffix")
# Request last 4 bytes
response = integration_client.get(
@@ -82,7 +82,7 @@ class TestRangeRequests:
"""Test range request from offset to end."""
project, package = test_package
content = b"0123456789"
upload_test_file(integration_client, project, package, content, version="range-open")
upload_test_file(integration_client, project, package, content, tag="range-open")
# Request from byte 5 to end
response = integration_client.get(
@@ -100,7 +100,7 @@ class TestRangeRequests:
"""Test that range requests include Accept-Ranges header."""
project, package = test_package
content = b"test content"
upload_test_file(integration_client, project, package, content, version="accept-ranges")
upload_test_file(integration_client, project, package, content, tag="accept-ranges")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/accept-ranges",
@@ -117,7 +117,7 @@ class TestRangeRequests:
"""Test that full downloads advertise range support."""
project, package = test_package
content = b"test content"
upload_test_file(integration_client, project, package, content, version="full-accept")
upload_test_file(integration_client, project, package, content, tag="full-accept")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/full-accept",
@@ -136,7 +136,7 @@ class TestConditionalRequests:
project, package = test_package
content = b"conditional request test content"
expected_hash = compute_sha256(content)
upload_test_file(integration_client, project, package, content, version="cond-etag")
upload_test_file(integration_client, project, package, content, tag="cond-etag")
# Request with matching ETag
response = integration_client.get(
@@ -153,7 +153,7 @@ class TestConditionalRequests:
project, package = test_package
content = b"etag no quotes test"
expected_hash = compute_sha256(content)
upload_test_file(integration_client, project, package, content, version="cond-noquote")
upload_test_file(integration_client, project, package, content, tag="cond-noquote")
# Request with ETag without quotes
response = integration_client.get(
@@ -168,7 +168,7 @@ class TestConditionalRequests:
"""Test If-None-Match with non-matching ETag returns 200."""
project, package = test_package
content = b"etag mismatch test"
upload_test_file(integration_client, project, package, content, version="cond-mismatch")
upload_test_file(integration_client, project, package, content, tag="cond-mismatch")
# Request with different ETag
response = integration_client.get(
@@ -184,7 +184,7 @@ class TestConditionalRequests:
"""Test If-Modified-Since with future date returns 304."""
project, package = test_package
content = b"modified since test"
upload_test_file(integration_client, project, package, content, version="cond-modified")
upload_test_file(integration_client, project, package, content, tag="cond-modified")
# Request with future date (artifact was definitely created before this)
future_date = formatdate(time.time() + 86400, usegmt=True) # Tomorrow
@@ -202,7 +202,7 @@ class TestConditionalRequests:
"""Test If-Modified-Since with old date returns 200."""
project, package = test_package
content = b"old date test"
upload_test_file(integration_client, project, package, content, version="cond-old")
upload_test_file(integration_client, project, package, content, tag="cond-old")
# Request with old date (2020-01-01)
old_date = "Wed, 01 Jan 2020 00:00:00 GMT"
@@ -220,7 +220,7 @@ class TestConditionalRequests:
project, package = test_package
content = b"304 etag test"
expected_hash = compute_sha256(content)
upload_test_file(integration_client, project, package, content, version="304-etag")
upload_test_file(integration_client, project, package, content, tag="304-etag")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/304-etag",
@@ -236,7 +236,7 @@ class TestConditionalRequests:
project, package = test_package
content = b"304 cache test"
expected_hash = compute_sha256(content)
upload_test_file(integration_client, project, package, content, version="304-cache")
upload_test_file(integration_client, project, package, content, tag="304-cache")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/304-cache",
@@ -255,7 +255,7 @@ class TestCachingHeaders:
"""Test download response includes Cache-Control header."""
project, package = test_package
content = b"cache control test"
upload_test_file(integration_client, project, package, content, version="cache-ctl")
upload_test_file(integration_client, project, package, content, tag="cache-ctl")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/cache-ctl",
@@ -272,7 +272,7 @@ class TestCachingHeaders:
"""Test download response includes Last-Modified header."""
project, package = test_package
content = b"last modified test"
upload_test_file(integration_client, project, package, content, version="last-mod")
upload_test_file(integration_client, project, package, content, tag="last-mod")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/last-mod",
@@ -290,7 +290,7 @@ class TestCachingHeaders:
project, package = test_package
content = b"etag header test"
expected_hash = compute_sha256(content)
upload_test_file(integration_client, project, package, content, version="etag-hdr")
upload_test_file(integration_client, project, package, content, tag="etag-hdr")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/etag-hdr",
@@ -308,7 +308,7 @@ class TestDownloadResume:
"""Test resuming download from where it left off."""
project, package = test_package
content = b"ABCDEFGHIJ" * 100 # 1000 bytes
upload_test_file(integration_client, project, package, content, version="resume-test")
upload_test_file(integration_client, project, package, content, tag="resume-test")
# Simulate partial download (first 500 bytes)
response1 = integration_client.get(
@@ -340,7 +340,7 @@ class TestDownloadResume:
project, package = test_package
content = b"resume etag verification test content"
expected_hash = compute_sha256(content)
upload_test_file(integration_client, project, package, content, version="resume-etag")
upload_test_file(integration_client, project, package, content, tag="resume-etag")
# Get ETag from first request
response1 = integration_client.get(
@@ -373,7 +373,7 @@ class TestLargeFileStreaming:
project, package = test_package
content, expected_hash = sized_content(SIZE_1MB, seed=500)
upload_test_file(integration_client, project, package, content, version="stream-1mb")
upload_test_file(integration_client, project, package, content, tag="stream-1mb")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/stream-1mb",
@@ -391,7 +391,7 @@ class TestLargeFileStreaming:
project, package = test_package
content, expected_hash = sized_content(SIZE_100KB, seed=501)
upload_test_file(integration_client, project, package, content, version="stream-hdr")
upload_test_file(integration_client, project, package, content, tag="stream-hdr")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/stream-hdr",
@@ -410,7 +410,7 @@ class TestLargeFileStreaming:
project, package = test_package
content, _ = sized_content(SIZE_100KB, seed=502)
upload_test_file(integration_client, project, package, content, version="range-large")
upload_test_file(integration_client, project, package, content, tag="range-large")
# Request a slice from the middle
start = 50000
@@ -433,7 +433,7 @@ class TestDownloadModes:
"""Test proxy mode streams content through backend."""
project, package = test_package
content = b"proxy mode test content"
upload_test_file(integration_client, project, package, content, version="mode-proxy")
upload_test_file(integration_client, project, package, content, tag="mode-proxy")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/mode-proxy",
@@ -447,7 +447,7 @@ class TestDownloadModes:
"""Test presigned mode returns JSON with URL."""
project, package = test_package
content = b"presigned mode test"
upload_test_file(integration_client, project, package, content, version="mode-presign")
upload_test_file(integration_client, project, package, content, tag="mode-presign")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/mode-presign",
@@ -464,7 +464,7 @@ class TestDownloadModes:
"""Test redirect mode returns 302 to presigned URL."""
project, package = test_package
content = b"redirect mode test"
upload_test_file(integration_client, project, package, content, version="mode-redir")
upload_test_file(integration_client, project, package, content, tag="mode-redir")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/mode-redir",
@@ -484,7 +484,7 @@ class TestIntegrityDuringStreaming:
project, package = test_package
content = b"integrity check content"
expected_hash = compute_sha256(content)
upload_test_file(integration_client, project, package, content, version="integrity")
upload_test_file(integration_client, project, package, content, tag="integrity")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/integrity",
@@ -505,7 +505,7 @@ class TestIntegrityDuringStreaming:
project, package = test_package
content = b"etag integrity test"
expected_hash = compute_sha256(content)
upload_test_file(integration_client, project, package, content, version="etag-int")
upload_test_file(integration_client, project, package, content, tag="etag-int")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/etag-int",
@@ -524,7 +524,7 @@ class TestIntegrityDuringStreaming:
"""Test Digest header is present in RFC 3230 format."""
project, package = test_package
content = b"digest header test"
upload_test_file(integration_client, project, package, content, version="digest")
upload_test_file(integration_client, project, package, content, tag="digest")
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/digest",

View File

@@ -0,0 +1,403 @@
"""
Integration tests for tag API endpoints.
Tests cover:
- Tag CRUD operations
- Tag listing with pagination and search
- Tag history tracking
- ref_count behavior with tag operations
"""
import pytest
from tests.factories import compute_sha256, upload_test_file
class TestTagCRUD:
"""Tests for tag create, read, delete operations."""
@pytest.mark.integration
def test_create_tag_via_upload(self, integration_client, test_package):
"""Test creating a tag via upload endpoint."""
project_name, package_name = test_package
result = upload_test_file(
integration_client,
project_name,
package_name,
b"tag create test",
tag="v1.0.0",
)
assert result["tag"] == "v1.0.0"
assert result["artifact_id"]
@pytest.mark.integration
def test_create_tag_via_post(
self, integration_client, test_package, unique_test_id
):
"""Test creating a tag via POST /tags endpoint."""
project_name, package_name = test_package
# First upload an artifact
result = upload_test_file(
integration_client,
project_name,
package_name,
b"artifact for tag",
)
artifact_id = result["artifact_id"]
# Create tag via POST
tag_name = f"post-tag-{unique_test_id}"
response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/tags",
json={"name": tag_name, "artifact_id": artifact_id},
)
assert response.status_code == 200
data = response.json()
assert data["name"] == tag_name
assert data["artifact_id"] == artifact_id
@pytest.mark.integration
def test_get_tag(self, integration_client, test_package):
"""Test getting a tag by name."""
project_name, package_name = test_package
upload_test_file(
integration_client,
project_name,
package_name,
b"get tag test",
tag="get-tag",
)
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/tags/get-tag"
)
assert response.status_code == 200
data = response.json()
assert data["name"] == "get-tag"
assert "artifact_id" in data
assert "artifact_size" in data
assert "artifact_content_type" in data
@pytest.mark.integration
def test_list_tags(self, integration_client, test_package):
"""Test listing tags for a package."""
project_name, package_name = test_package
# Create some tags
upload_test_file(
integration_client,
project_name,
package_name,
b"list tags test",
tag="list-v1",
)
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/tags"
)
assert response.status_code == 200
data = response.json()
assert "items" in data
assert "pagination" in data
tag_names = [t["name"] for t in data["items"]]
assert "list-v1" in tag_names
@pytest.mark.integration
def test_delete_tag(self, integration_client, test_package):
"""Test deleting a tag."""
project_name, package_name = test_package
upload_test_file(
integration_client,
project_name,
package_name,
b"delete tag test",
tag="to-delete",
)
# Delete tag
response = integration_client.delete(
f"/api/v1/project/{project_name}/{package_name}/tags/to-delete"
)
assert response.status_code == 204
# Verify deleted
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/tags/to-delete"
)
assert response.status_code == 404
class TestTagListingFilters:
"""Tests for tag listing with filters and search."""
@pytest.mark.integration
def test_tags_pagination(self, integration_client, test_package):
"""Test tag listing respects pagination."""
project_name, package_name = test_package
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/tags?limit=5"
)
assert response.status_code == 200
data = response.json()
assert len(data["items"]) <= 5
assert data["pagination"]["limit"] == 5
@pytest.mark.integration
def test_tags_search(self, integration_client, test_package, unique_test_id):
"""Test tag search by name."""
project_name, package_name = test_package
tag_name = f"searchable-{unique_test_id}"
upload_test_file(
integration_client,
project_name,
package_name,
b"search test",
tag=tag_name,
)
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/tags?search=searchable"
)
assert response.status_code == 200
data = response.json()
tag_names = [t["name"] for t in data["items"]]
assert tag_name in tag_names
class TestTagHistory:
"""Tests for tag history tracking."""
@pytest.mark.integration
def test_tag_history_on_create(self, integration_client, test_package):
"""Test tag history is created when tag is created."""
project_name, package_name = test_package
upload_test_file(
integration_client,
project_name,
package_name,
b"history create test",
tag="history-create",
)
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/tags/history-create/history"
)
assert response.status_code == 200
data = response.json()
assert len(data) >= 1
@pytest.mark.integration
def test_tag_history_on_update(
self, integration_client, test_package, unique_test_id
):
"""Test tag history is created when tag is updated."""
project_name, package_name = test_package
tag_name = f"history-update-{unique_test_id}"
# Create tag with first artifact
upload_test_file(
integration_client,
project_name,
package_name,
b"first content",
tag=tag_name,
)
# Update tag with second artifact
upload_test_file(
integration_client,
project_name,
package_name,
b"second content",
tag=tag_name,
)
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/tags/{tag_name}/history"
)
assert response.status_code == 200
data = response.json()
# Should have at least 2 history entries (create + update)
assert len(data) >= 2
class TestTagRefCount:
"""Tests for ref_count behavior with tag operations."""
@pytest.mark.integration
def test_ref_count_decrements_on_tag_delete(self, integration_client, test_package):
"""Test ref_count decrements when a tag is deleted."""
project_name, package_name = test_package
content = b"ref count delete test"
expected_hash = compute_sha256(content)
# Upload with two tags
upload_test_file(
integration_client, project_name, package_name, content, tag="rc-v1"
)
upload_test_file(
integration_client, project_name, package_name, content, tag="rc-v2"
)
# Verify ref_count is 2
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
assert response.json()["ref_count"] == 2
# Delete one tag
delete_response = integration_client.delete(
f"/api/v1/project/{project_name}/{package_name}/tags/rc-v1"
)
assert delete_response.status_code == 204
# Verify ref_count is now 1
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
assert response.json()["ref_count"] == 1
@pytest.mark.integration
def test_ref_count_zero_after_all_tags_deleted(
self, integration_client, test_package
):
"""Test ref_count goes to 0 when all tags are deleted."""
project_name, package_name = test_package
content = b"orphan test content"
expected_hash = compute_sha256(content)
# Upload with one tag
upload_test_file(
integration_client, project_name, package_name, content, tag="only-tag"
)
# Delete the tag
integration_client.delete(
f"/api/v1/project/{project_name}/{package_name}/tags/only-tag"
)
# Verify ref_count is 0
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
assert response.json()["ref_count"] == 0
@pytest.mark.integration
def test_ref_count_adjusts_on_tag_update(
self, integration_client, test_package, unique_test_id
):
"""Test ref_count adjusts when a tag is updated to point to different artifact."""
project_name, package_name = test_package
# Upload two different artifacts
content1 = f"artifact one {unique_test_id}".encode()
content2 = f"artifact two {unique_test_id}".encode()
hash1 = compute_sha256(content1)
hash2 = compute_sha256(content2)
# Upload first artifact with tag "latest"
upload_test_file(
integration_client, project_name, package_name, content1, tag="latest"
)
# Verify first artifact has ref_count 1
response = integration_client.get(f"/api/v1/artifact/{hash1}")
assert response.json()["ref_count"] == 1
# Upload second artifact with different tag
upload_test_file(
integration_client, project_name, package_name, content2, tag="stable"
)
# Now update "latest" tag to point to second artifact
upload_test_file(
integration_client, project_name, package_name, content2, tag="latest"
)
# Verify first artifact ref_count decreased to 0
response = integration_client.get(f"/api/v1/artifact/{hash1}")
assert response.json()["ref_count"] == 0
# Verify second artifact ref_count increased to 2
response = integration_client.get(f"/api/v1/artifact/{hash2}")
assert response.json()["ref_count"] == 2
@pytest.mark.integration
def test_ref_count_unchanged_when_tag_same_artifact(
self, integration_client, test_package, unique_test_id
):
"""Test ref_count doesn't change when tag is 'updated' to same artifact."""
project_name, package_name = test_package
content = f"same artifact {unique_test_id}".encode()
expected_hash = compute_sha256(content)
# Upload with tag
upload_test_file(
integration_client, project_name, package_name, content, tag="same-v1"
)
# Verify ref_count is 1
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
assert response.json()["ref_count"] == 1
# Upload same content with same tag (no-op)
upload_test_file(
integration_client, project_name, package_name, content, tag="same-v1"
)
# Verify ref_count is still 1
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
assert response.json()["ref_count"] == 1
@pytest.mark.integration
def test_tag_via_post_endpoint_increments_ref_count(
self, integration_client, test_package, unique_test_id
):
"""Test creating tag via POST /tags endpoint increments ref_count."""
project_name, package_name = test_package
content = f"tag endpoint test {unique_test_id}".encode()
expected_hash = compute_sha256(content)
# Upload artifact without tag
result = upload_test_file(
integration_client, project_name, package_name, content, filename="test.bin"
)
artifact_id = result["artifact_id"]
# Verify ref_count is 0 (no tags yet)
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
assert response.json()["ref_count"] == 0
# Create tag via POST endpoint
tag_response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/tags",
json={"name": "post-v1", "artifact_id": artifact_id},
)
assert tag_response.status_code == 200
# Verify ref_count is now 1
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
assert response.json()["ref_count"] == 1
# Create another tag via POST endpoint
tag_response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/tags",
json={"name": "post-latest", "artifact_id": artifact_id},
)
assert tag_response.status_code == 200
# Verify ref_count is now 2
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
assert response.json()["ref_count"] == 2

View File

@@ -47,7 +47,7 @@ class TestUploadBasics:
expected_hash = compute_sha256(content)
result = upload_test_file(
integration_client, project_name, package_name, content, version="v1"
integration_client, project_name, package_name, content, tag="v1"
)
assert result["artifact_id"] == expected_hash
@@ -116,23 +116,31 @@ class TestUploadBasics:
assert result["created_at"] is not None
@pytest.mark.integration
def test_upload_without_version_succeeds(self, integration_client, test_package):
"""Test upload without version succeeds (no version created)."""
def test_upload_without_tag_succeeds(self, integration_client, test_package):
"""Test upload without tag succeeds (no tag created)."""
project, package = test_package
content = b"upload without version test"
content = b"upload without tag test"
expected_hash = compute_sha256(content)
files = {"file": ("no_version.bin", io.BytesIO(content), "application/octet-stream")}
files = {"file": ("no_tag.bin", io.BytesIO(content), "application/octet-stream")}
response = integration_client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files,
# No version parameter
# No tag parameter
)
assert response.status_code == 200
result = response.json()
assert result["artifact_id"] == expected_hash
# Version should be None when not specified
assert result.get("version") is None
# Verify no tag was created - list tags and check
tags_response = integration_client.get(
f"/api/v1/project/{project}/{package}/tags"
)
assert tags_response.status_code == 200
tags = tags_response.json()
# Filter for tags pointing to this artifact
artifact_tags = [t for t in tags.get("items", tags) if t.get("artifact_id") == expected_hash]
assert len(artifact_tags) == 0, "Tag should not be created when not specified"
@pytest.mark.integration
def test_upload_creates_artifact_in_database(self, integration_client, test_package):
@@ -164,29 +172,25 @@ class TestUploadBasics:
assert s3_object_exists(expected_hash), "S3 object should exist after upload"
@pytest.mark.integration
def test_upload_with_version_creates_version_record(self, integration_client, test_package):
"""Test upload with version creates version record."""
def test_upload_with_tag_creates_tag_record(self, integration_client, test_package):
"""Test upload with tag creates tag record."""
project, package = test_package
content = b"version creation test"
content = b"tag creation test"
expected_hash = compute_sha256(content)
version_name = "1.0.0"
tag_name = "my-tag-v1"
result = upload_test_file(
integration_client, project, package, content, version=version_name
upload_test_file(
integration_client, project, package, content, tag=tag_name
)
# Verify version was created
assert result.get("version") == version_name
assert result["artifact_id"] == expected_hash
# Verify version exists in versions list
versions_response = integration_client.get(
f"/api/v1/project/{project}/{package}/versions"
# Verify tag exists
tags_response = integration_client.get(
f"/api/v1/project/{project}/{package}/tags"
)
assert versions_response.status_code == 200
versions = versions_response.json()
version_names = [v["version"] for v in versions.get("items", [])]
assert version_name in version_names
assert tags_response.status_code == 200
tags = tags_response.json()
tag_names = [t["name"] for t in tags.get("items", tags)]
assert tag_name in tag_names
class TestDuplicateUploads:
@@ -203,44 +207,36 @@ class TestDuplicateUploads:
# First upload
result1 = upload_test_file(
integration_client, project, package, content, version="first"
integration_client, project, package, content, tag="first"
)
assert result1["artifact_id"] == expected_hash
# Second upload
result2 = upload_test_file(
integration_client, project, package, content, version="second"
integration_client, project, package, content, tag="second"
)
assert result2["artifact_id"] == expected_hash
assert result1["artifact_id"] == result2["artifact_id"]
@pytest.mark.integration
def test_same_file_twice_returns_existing_version(
def test_same_file_twice_increments_ref_count(
self, integration_client, test_package
):
"""Test uploading same file twice in same package returns existing version.
Same artifact can only have one version per package. Uploading the same content
with a different version name returns the existing version, not a new one.
ref_count stays at 1 because there's still only one PackageVersion reference.
"""
"""Test uploading same file twice increments ref_count to 2."""
project, package = test_package
content = b"content for ref count increment test"
# First upload
result1 = upload_test_file(
integration_client, project, package, content, version="v1"
integration_client, project, package, content, tag="v1"
)
assert result1["ref_count"] == 1
# Second upload with different version name returns existing version
# Second upload
result2 = upload_test_file(
integration_client, project, package, content, version="v2"
integration_client, project, package, content, tag="v2"
)
# Same artifact, same package = same version returned, ref_count stays 1
assert result2["ref_count"] == 1
assert result2["deduplicated"] is True
assert result1["version"] == result2["version"] # Both return "v1"
assert result2["ref_count"] == 2
@pytest.mark.integration
def test_same_file_different_packages_shares_artifact(
@@ -265,12 +261,12 @@ class TestDuplicateUploads:
)
# Upload to first package
result1 = upload_test_file(integration_client, project, pkg1, content, version="v1")
result1 = upload_test_file(integration_client, project, pkg1, content, tag="v1")
assert result1["artifact_id"] == expected_hash
assert result1["deduplicated"] is False
# Upload to second package
result2 = upload_test_file(integration_client, project, pkg2, content, version="v1")
result2 = upload_test_file(integration_client, project, pkg2, content, tag="v1")
assert result2["artifact_id"] == expected_hash
assert result2["deduplicated"] is True
@@ -290,7 +286,7 @@ class TestDuplicateUploads:
package,
content,
filename="file1.bin",
version="v1",
tag="v1",
)
assert result1["artifact_id"] == expected_hash
@@ -301,7 +297,7 @@ class TestDuplicateUploads:
package,
content,
filename="file2.bin",
version="v2",
tag="v2",
)
assert result2["artifact_id"] == expected_hash
assert result2["deduplicated"] is True
@@ -311,17 +307,17 @@ class TestDownload:
"""Tests for download functionality."""
@pytest.mark.integration
def test_download_by_version(self, integration_client, test_package):
"""Test downloading artifact by version."""
def test_download_by_tag(self, integration_client, test_package):
"""Test downloading artifact by tag name."""
project, package = test_package
original_content = b"download by version test"
original_content = b"download by tag test"
upload_test_file(
integration_client, project, package, original_content, version="1.0.0"
integration_client, project, package, original_content, tag="download-tag"
)
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/1.0.0",
f"/api/v1/project/{project}/{package}/+/download-tag",
params={"mode": "proxy"},
)
assert response.status_code == 200
@@ -344,29 +340,29 @@ class TestDownload:
assert response.content == original_content
@pytest.mark.integration
def test_download_by_version_prefix(self, integration_client, test_package):
"""Test downloading artifact using version: prefix."""
def test_download_by_tag_prefix(self, integration_client, test_package):
"""Test downloading artifact using tag: prefix."""
project, package = test_package
original_content = b"download by version prefix test"
original_content = b"download by tag prefix test"
upload_test_file(
integration_client, project, package, original_content, version="2.0.0"
integration_client, project, package, original_content, tag="prefix-tag"
)
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/version:2.0.0",
f"/api/v1/project/{project}/{package}/+/tag:prefix-tag",
params={"mode": "proxy"},
)
assert response.status_code == 200
assert response.content == original_content
@pytest.mark.integration
def test_download_nonexistent_version(self, integration_client, test_package):
"""Test downloading nonexistent version returns 404."""
def test_download_nonexistent_tag(self, integration_client, test_package):
"""Test downloading nonexistent tag returns 404."""
project, package = test_package
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/nonexistent-version"
f"/api/v1/project/{project}/{package}/+/nonexistent-tag"
)
assert response.status_code == 404
@@ -404,7 +400,7 @@ class TestDownload:
original_content = b"exact content verification test data 12345"
upload_test_file(
integration_client, project, package, original_content, version="verify"
integration_client, project, package, original_content, tag="verify"
)
response = integration_client.get(
@@ -425,7 +421,7 @@ class TestDownloadHeaders:
upload_test_file(
integration_client, project, package, content,
filename="test.txt", version="content-type-test"
filename="test.txt", tag="content-type-test"
)
response = integration_client.get(
@@ -444,7 +440,7 @@ class TestDownloadHeaders:
expected_length = len(content)
upload_test_file(
integration_client, project, package, content, version="content-length-test"
integration_client, project, package, content, tag="content-length-test"
)
response = integration_client.get(
@@ -464,7 +460,7 @@ class TestDownloadHeaders:
upload_test_file(
integration_client, project, package, content,
filename=filename, version="disposition-test"
filename=filename, tag="disposition-test"
)
response = integration_client.get(
@@ -485,7 +481,7 @@ class TestDownloadHeaders:
expected_hash = compute_sha256(content)
upload_test_file(
integration_client, project, package, content, version="checksum-headers"
integration_client, project, package, content, tag="checksum-headers"
)
response = integration_client.get(
@@ -505,7 +501,7 @@ class TestDownloadHeaders:
expected_hash = compute_sha256(content)
upload_test_file(
integration_client, project, package, content, version="etag-test"
integration_client, project, package, content, tag="etag-test"
)
response = integration_client.get(
@@ -523,31 +519,17 @@ class TestConcurrentUploads:
"""Tests for concurrent upload handling."""
@pytest.mark.integration
def test_concurrent_uploads_same_file(self, integration_client, test_project, unique_test_id):
"""Test concurrent uploads of same file to different packages handle deduplication correctly.
Same artifact can only have one version per package, so we create multiple packages
to test that concurrent uploads to different packages correctly increment ref_count.
"""
def test_concurrent_uploads_same_file(self, integration_client, test_package):
"""Test concurrent uploads of same file handle deduplication correctly."""
project, package = test_package
content = b"content for concurrent upload test"
expected_hash = compute_sha256(content)
num_concurrent = 5
# Create packages for each concurrent upload
packages = []
for i in range(num_concurrent):
pkg_name = f"concurrent-pkg-{unique_test_id}-{i}"
response = integration_client.post(
f"/api/v1/project/{test_project}/packages",
json={"name": pkg_name},
)
assert response.status_code == 200
packages.append(pkg_name)
# Create an API key for worker threads
api_key_response = integration_client.post(
"/api/v1/auth/keys",
json={"name": f"concurrent-test-key-{unique_test_id}"},
json={"name": "concurrent-test-key"},
)
assert api_key_response.status_code == 200, f"Failed to create API key: {api_key_response.text}"
api_key = api_key_response.json()["key"]
@@ -555,7 +537,7 @@ class TestConcurrentUploads:
results = []
errors = []
def upload_worker(idx):
def upload_worker(tag_suffix):
try:
from httpx import Client
@@ -563,15 +545,15 @@ class TestConcurrentUploads:
with Client(base_url=base_url, timeout=30.0) as client:
files = {
"file": (
f"concurrent-{idx}.bin",
f"concurrent-{tag_suffix}.bin",
io.BytesIO(content),
"application/octet-stream",
)
}
response = client.post(
f"/api/v1/project/{test_project}/{packages[idx]}/upload",
f"/api/v1/project/{project}/{package}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": f"concurrent-{tag_suffix}"},
headers={"Authorization": f"Bearer {api_key}"},
)
if response.status_code == 200:
@@ -594,7 +576,7 @@ class TestConcurrentUploads:
assert len(artifact_ids) == 1
assert expected_hash in artifact_ids
# Verify final ref_count equals number of packages
# Verify final ref_count
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
assert response.status_code == 200
assert response.json()["ref_count"] == num_concurrent
@@ -623,7 +605,7 @@ class TestFileSizeValidation:
content = b"X"
result = upload_test_file(
integration_client, project, package, content, version="tiny"
integration_client, project, package, content, tag="tiny"
)
assert result["artifact_id"] is not None
@@ -639,7 +621,7 @@ class TestFileSizeValidation:
expected_size = len(content)
result = upload_test_file(
integration_client, project, package, content, version="size-test"
integration_client, project, package, content, tag="size-test"
)
assert result["size"] == expected_size
@@ -667,7 +649,7 @@ class TestUploadFailureCleanup:
response = integration_client.post(
f"/api/v1/project/nonexistent-project-{unique_test_id}/nonexistent-pkg/upload",
files=files,
data={"version": "test"},
data={"tag": "test"},
)
assert response.status_code == 404
@@ -690,7 +672,7 @@ class TestUploadFailureCleanup:
response = integration_client.post(
f"/api/v1/project/{test_project}/nonexistent-package-{unique_test_id}/upload",
files=files,
data={"version": "test"},
data={"tag": "test"},
)
assert response.status_code == 404
@@ -711,7 +693,7 @@ class TestUploadFailureCleanup:
response = integration_client.post(
f"/api/v1/project/{test_project}/nonexistent-package-{unique_test_id}/upload",
files=files,
data={"version": "test"},
data={"tag": "test"},
)
assert response.status_code == 404
@@ -737,7 +719,7 @@ class TestS3StorageVerification:
# Upload same content multiple times
for tag in ["s3test1", "s3test2", "s3test3"]:
upload_test_file(integration_client, project, package, content, version=tag)
upload_test_file(integration_client, project, package, content, tag=tag)
# Verify only one S3 object exists
s3_objects = list_s3_objects_by_hash(expected_hash)
@@ -753,26 +735,16 @@ class TestS3StorageVerification:
@pytest.mark.integration
def test_artifact_table_single_row_after_duplicates(
self, integration_client, test_project, unique_test_id
self, integration_client, test_package
):
"""Test artifact table contains only one row after duplicate uploads to different packages.
Same artifact can only have one version per package, so we create multiple packages
to test deduplication across packages.
"""
"""Test artifact table contains only one row after duplicate uploads."""
project, package = test_package
content = b"content for single row test"
expected_hash = compute_sha256(content)
# Create 3 packages and upload same content to each
for i in range(3):
pkg_name = f"single-row-pkg-{unique_test_id}-{i}"
integration_client.post(
f"/api/v1/project/{test_project}/packages",
json={"name": pkg_name},
)
upload_test_file(
integration_client, test_project, pkg_name, content, version="1.0.0"
)
# Upload same content multiple times
for tag in ["v1", "v2", "v3"]:
upload_test_file(integration_client, project, package, content, tag=tag)
# Query artifact
response = integration_client.get(f"/api/v1/artifact/{expected_hash}")
@@ -811,7 +783,7 @@ class TestSecurityPathTraversal:
response = integration_client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files,
data={"version": "traversal-test"},
data={"tag": "traversal-test"},
)
assert response.status_code == 200
result = response.json()
@@ -829,16 +801,48 @@ class TestSecurityPathTraversal:
assert response.status_code in [400, 404, 422]
@pytest.mark.integration
def test_path_traversal_in_version_name(self, integration_client, test_package):
"""Test version names with path traversal are handled safely."""
def test_path_traversal_in_tag_name(self, integration_client, test_package):
"""Test tag names with path traversal are handled safely."""
project, package = test_package
content = b"version traversal test"
content = b"tag traversal test"
files = {"file": ("test.bin", io.BytesIO(content), "application/octet-stream")}
response = integration_client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files,
data={"version": "../../../etc/passwd"},
data={"tag": "../../../etc/passwd"},
)
assert response.status_code in [200, 400, 422]
@pytest.mark.integration
def test_download_path_traversal_in_ref(self, integration_client, test_package):
"""Test download ref with path traversal is rejected."""
project, package = test_package
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/../../../etc/passwd"
)
assert response.status_code in [400, 404, 422]
@pytest.mark.integration
def test_path_traversal_in_package_name(self, integration_client, test_project):
"""Test package names with path traversal sequences are rejected."""
response = integration_client.get(
f"/api/v1/project/{test_project}/packages/../../../etc/passwd"
)
assert response.status_code in [400, 404, 422]
@pytest.mark.integration
def test_path_traversal_in_tag_name(self, integration_client, test_package):
"""Test tag names with path traversal are rejected or handled safely."""
project, package = test_package
content = b"tag traversal test"
files = {"file": ("test.bin", io.BytesIO(content), "application/octet-stream")}
response = integration_client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files,
data={"tag": "../../../etc/passwd"},
)
assert response.status_code in [200, 400, 422]
@@ -863,7 +867,7 @@ class TestSecurityMalformedRequests:
response = integration_client.post(
f"/api/v1/project/{project}/{package}/upload",
data={"version": "no-file"},
data={"tag": "no-file"},
)
assert response.status_code == 422

View File

@@ -39,6 +39,31 @@ class TestVersionCreation:
assert result.get("version") == "1.0.0"
assert result.get("version_source") == "explicit"
@pytest.mark.integration
def test_upload_with_version_and_tag(self, integration_client, test_package):
"""Test upload with both version and tag creates both records."""
project, package = test_package
content = b"version and tag test"
files = {"file": ("app.tar.gz", io.BytesIO(content), "application/octet-stream")}
response = integration_client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files,
data={"version": "2.0.0", "tag": "latest"},
)
assert response.status_code == 200
result = response.json()
assert result.get("version") == "2.0.0"
# Verify tag was also created
tags_response = integration_client.get(
f"/api/v1/project/{project}/{package}/tags"
)
assert tags_response.status_code == 200
tags = tags_response.json()
tag_names = [t["name"] for t in tags.get("items", tags)]
assert "latest" in tag_names
@pytest.mark.integration
def test_duplicate_version_same_content_succeeds(self, integration_client, test_package):
"""Test uploading same version with same content succeeds (deduplication)."""
@@ -237,10 +262,11 @@ class TestDownloadByVersion:
assert response.status_code == 404
@pytest.mark.integration
def test_version_resolution_with_prefix(self, integration_client, test_package):
"""Test that version: prefix explicitly resolves to version."""
def test_version_resolution_priority(self, integration_client, test_package):
"""Test that version: prefix explicitly resolves to version, not tag."""
project, package = test_package
version_content = b"this is the version content"
tag_content = b"this is the tag content"
# Create a version 6.0.0
files1 = {"file": ("app-v.tar.gz", io.BytesIO(version_content), "application/octet-stream")}
@@ -250,6 +276,14 @@ class TestDownloadByVersion:
data={"version": "6.0.0"},
)
# Create a tag named "6.0.0" pointing to different content
files2 = {"file": ("app-t.tar.gz", io.BytesIO(tag_content), "application/octet-stream")}
integration_client.post(
f"/api/v1/project/{project}/{package}/upload",
files=files2,
data={"tag": "6.0.0"},
)
# Download with version: prefix should get version content
response = integration_client.get(
f"/api/v1/project/{project}/{package}/+/version:6.0.0",
@@ -258,6 +292,14 @@ class TestDownloadByVersion:
assert response.status_code == 200
assert response.content == version_content
# Download with tag: prefix should get tag content
response2 = integration_client.get(
f"/api/v1/project/{project}/{package}/+/tag:6.0.0",
params={"mode": "proxy"},
)
assert response2.status_code == 200
assert response2.content == tag_content
class TestVersionDeletion:
"""Tests for deleting versions."""

View File

@@ -27,9 +27,11 @@ class TestVersionCreation:
project_name,
package_name,
b"version create test",
tag="latest",
version="1.0.0",
)
assert result["tag"] == "latest"
assert result["version"] == "1.0.0"
assert result["version_source"] == "explicit"
assert result["artifact_id"]
@@ -147,6 +149,7 @@ class TestVersionCRUD:
package_name,
b"version with info",
version="1.0.0",
tag="release",
)
response = integration_client.get(
@@ -163,6 +166,8 @@ class TestVersionCRUD:
assert version_item is not None
assert "size" in version_item
assert "artifact_id" in version_item
assert "tags" in version_item
assert "release" in version_item["tags"]
@pytest.mark.integration
def test_get_version(self, integration_client, test_package):
@@ -267,9 +272,94 @@ class TestVersionDownload:
follow_redirects=False,
)
# Should resolve version
# Should resolve version first (before tag)
assert response.status_code in [200, 302, 307]
@pytest.mark.integration
def test_version_takes_precedence_over_tag(self, integration_client, test_package):
"""Test that version is checked before tag when resolving refs."""
project_name, package_name = test_package
# Upload with version "1.0"
version_result = upload_test_file(
integration_client,
project_name,
package_name,
b"version content",
version="1.0",
)
# Create a tag with the same name "1.0" pointing to different artifact
tag_result = upload_test_file(
integration_client,
project_name,
package_name,
b"tag content different",
tag="1.0",
)
# Download by "1.0" should resolve to version, not tag
# Since version:1.0 artifact was uploaded first
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/+/1.0",
follow_redirects=False,
)
assert response.status_code in [200, 302, 307]
class TestTagVersionEnrichment:
"""Tests for tag responses including version information."""
@pytest.mark.integration
def test_tag_response_includes_version(self, integration_client, test_package):
"""Test that tag responses include version of the artifact."""
project_name, package_name = test_package
# Upload with both version and tag
upload_test_file(
integration_client,
project_name,
package_name,
b"enriched tag test",
version="7.0.0",
tag="stable",
)
# Get tag and check version field
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/tags/stable"
)
assert response.status_code == 200
data = response.json()
assert data["name"] == "stable"
assert data["version"] == "7.0.0"
@pytest.mark.integration
def test_tag_list_includes_versions(self, integration_client, test_package):
"""Test that tag list responses include version for each tag."""
project_name, package_name = test_package
upload_test_file(
integration_client,
project_name,
package_name,
b"list version test",
version="8.0.0",
tag="latest",
)
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/tags"
)
assert response.status_code == 200
data = response.json()
tag_item = next((t for t in data["items"] if t["name"] == "latest"), None)
assert tag_item is not None
assert tag_item.get("version") == "8.0.0"
class TestVersionPagination:
"""Tests for version listing pagination and sorting."""

View File

@@ -39,7 +39,7 @@ class TestDependencySchema:
response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/upload",
files=files,
data={"version": f"v1.0.0-{unique_test_id}"},
data={"tag": f"v1.0.0-{unique_test_id}"},
)
assert response.status_code == 200
@@ -59,17 +59,29 @@ class TestDependencySchema:
integration_client.delete(f"/api/v1/projects/{dep_project_name}")
@pytest.mark.integration
def test_dependency_requires_version(self, integration_client):
"""Test that dependency requires version."""
def test_dependency_requires_version_or_tag(self, integration_client):
"""Test that dependency must have either version or tag, not both or neither."""
from app.schemas import DependencyCreate
# Test: missing version
with pytest.raises(ValidationError):
# Test: neither version nor tag
with pytest.raises(ValidationError) as exc_info:
DependencyCreate(project="proj", package="pkg")
assert "Either 'version' or 'tag' must be specified" in str(exc_info.value)
# Test: both version and tag
with pytest.raises(ValidationError) as exc_info:
DependencyCreate(project="proj", package="pkg", version="1.0.0", tag="stable")
assert "Cannot specify both 'version' and 'tag'" in str(exc_info.value)
# Test: valid with version
dep = DependencyCreate(project="proj", package="pkg", version="1.0.0")
assert dep.version == "1.0.0"
assert dep.tag is None
# Test: valid with tag
dep = DependencyCreate(project="proj", package="pkg", tag="stable")
assert dep.tag == "stable"
assert dep.version is None
@pytest.mark.integration
def test_dependency_unique_constraint(
@@ -114,7 +126,7 @@ class TestEnsureFileParsing:
response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/upload",
files=files,
data={"version": f"v1.0.0-{unique_test_id}"},
data={"tag": f"v1.0.0-{unique_test_id}"},
)
assert response.status_code == 200
data = response.json()
@@ -150,7 +162,7 @@ class TestEnsureFileParsing:
response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/upload",
files=files,
data={"version": f"v1.0.0-{unique_test_id}"},
data={"tag": f"v1.0.0-{unique_test_id}"},
)
assert response.status_code == 400
assert "Invalid ensure file" in response.json().get("detail", "")
@@ -176,7 +188,7 @@ class TestEnsureFileParsing:
response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/upload",
files=files,
data={"version": f"v1.0.0-{unique_test_id}"},
data={"tag": f"v1.0.0-{unique_test_id}"},
)
assert response.status_code == 400
assert "Project" in response.json().get("detail", "")
@@ -196,7 +208,7 @@ class TestEnsureFileParsing:
response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/upload",
files=files,
data={"version": f"v1.0.0-nodeps-{unique_test_id}"},
data={"tag": f"v1.0.0-nodeps-{unique_test_id}"},
)
assert response.status_code == 200
@@ -214,14 +226,13 @@ class TestEnsureFileParsing:
assert response.status_code == 200
try:
# Test with missing version field (version is now required)
ensure_content = yaml.dump({
"dependencies": [
{"project": dep_project_name, "package": "pkg"} # Missing version
{"project": dep_project_name, "package": "pkg", "version": "1.0.0", "tag": "stable"}
]
})
content = unique_content("test-missing-version", unique_test_id, "constraint")
content = unique_content("test-both", unique_test_id, "constraint")
files = {
"file": ("test.tar.gz", BytesIO(content), "application/gzip"),
"ensure": ("orchard.ensure", BytesIO(ensure_content.encode()), "application/x-yaml"),
@@ -229,10 +240,11 @@ class TestEnsureFileParsing:
response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/upload",
files=files,
data={"version": f"v1.0.0-{unique_test_id}"},
data={"tag": f"v1.0.0-{unique_test_id}"},
)
assert response.status_code == 400
assert "version" in response.json().get("detail", "").lower()
assert "both" in response.json().get("detail", "").lower() or \
"version" in response.json().get("detail", "").lower()
finally:
integration_client.delete(f"/api/v1/projects/{dep_project_name}")
@@ -259,7 +271,7 @@ class TestDependencyQueryEndpoints:
ensure_content = yaml.dump({
"dependencies": [
{"project": dep_project_name, "package": "lib-a", "version": "1.0.0"},
{"project": dep_project_name, "package": "lib-b", "version": "2.0.0"},
{"project": dep_project_name, "package": "lib-b", "tag": "stable"},
]
})
@@ -271,7 +283,7 @@ class TestDependencyQueryEndpoints:
response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/upload",
files=files,
data={"version": f"v2.0.0-{unique_test_id}"},
data={"tag": f"v2.0.0-{unique_test_id}"},
)
assert response.status_code == 200
artifact_id = response.json()["artifact_id"]
@@ -287,8 +299,10 @@ class TestDependencyQueryEndpoints:
deps = {d["package"]: d for d in data["dependencies"]}
assert "lib-a" in deps
assert deps["lib-a"]["version"] == "1.0.0"
assert deps["lib-a"]["tag"] is None
assert "lib-b" in deps
assert deps["lib-b"]["version"] == "2.0.0"
assert deps["lib-b"]["tag"] == "stable"
assert deps["lib-b"]["version"] is None
finally:
integration_client.delete(f"/api/v1/projects/{dep_project_name}")
@@ -322,7 +336,7 @@ class TestDependencyQueryEndpoints:
response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/upload",
files=files,
data={"version": tag_name},
data={"tag": tag_name},
)
assert response.status_code == 200
@@ -367,7 +381,7 @@ class TestDependencyQueryEndpoints:
response = integration_client.post(
f"/api/v1/project/{dep_project_name}/target-lib/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -386,7 +400,7 @@ class TestDependencyQueryEndpoints:
response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/upload",
files=files,
data={"version": f"v4.0.0-{unique_test_id}"},
data={"tag": f"v4.0.0-{unique_test_id}"},
)
assert response.status_code == 200
@@ -405,6 +419,7 @@ class TestDependencyQueryEndpoints:
for dep in data["dependents"]:
if dep["project"] == project_name:
found = True
assert dep["constraint_type"] == "version"
assert dep["constraint_value"] == "1.0.0"
break
assert found, "Our package should be in the dependents list"
@@ -427,7 +442,7 @@ class TestDependencyQueryEndpoints:
response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/upload",
files=files,
data={"version": f"v5.0.0-nodeps-{unique_test_id}"},
data={"tag": f"v5.0.0-nodeps-{unique_test_id}"},
)
assert response.status_code == 200
artifact_id = response.json()["artifact_id"]
@@ -467,7 +482,7 @@ class TestDependencyResolution:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_c}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -485,7 +500,7 @@ class TestDependencyResolution:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_b}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -503,7 +518,7 @@ class TestDependencyResolution:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_a}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -551,7 +566,7 @@ class TestDependencyResolution:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_d}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -569,7 +584,7 @@ class TestDependencyResolution:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_b}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -587,7 +602,7 @@ class TestDependencyResolution:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_c}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -606,7 +621,7 @@ class TestDependencyResolution:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_a}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -648,7 +663,7 @@ class TestDependencyResolution:
response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/upload",
files=files,
data={"version": f"solo-{unique_test_id}"},
data={"tag": f"solo-{unique_test_id}"},
)
assert response.status_code == 200
@@ -683,21 +698,17 @@ class TestDependencyResolution:
response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/upload",
files=files,
data={"version": f"missing-dep-{unique_test_id}"},
data={"tag": f"missing-dep-{unique_test_id}"},
)
# Should fail at upload time since package doesn't exist
# OR succeed at upload but fail at resolution
# Depending on implementation choice
if response.status_code == 200:
# Resolution should return missing dependencies
# Resolution should fail
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/+/missing-dep-{unique_test_id}/resolve"
)
# Expect 200 with missing dependencies listed
assert response.status_code == 200
data = response.json()
# The missing dependency should be in the 'missing' list
assert len(data.get("missing", [])) >= 1
assert response.status_code == 404
class TestCircularDependencyDetection:
@@ -725,7 +736,7 @@ class TestCircularDependencyDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_a}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -743,7 +754,7 @@ class TestCircularDependencyDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_b}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -761,7 +772,7 @@ class TestCircularDependencyDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_a}/upload",
files=files,
data={"version": "2.0.0"},
data={"tag": "2.0.0"},
)
# Should be rejected with 400 (circular dependency)
assert response.status_code == 400
@@ -796,7 +807,7 @@ class TestCircularDependencyDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_a}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -814,7 +825,7 @@ class TestCircularDependencyDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_b}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -832,7 +843,7 @@ class TestCircularDependencyDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_c}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -850,7 +861,7 @@ class TestCircularDependencyDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_a}/upload",
files=files,
data={"version": "2.0.0"},
data={"tag": "2.0.0"},
)
assert response.status_code == 400
data = response.json()
@@ -899,7 +910,7 @@ class TestConflictDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_common}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -909,7 +920,7 @@ class TestConflictDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_common}/upload",
files=files,
data={"version": "2.0.0"},
data={"tag": "2.0.0"},
)
assert response.status_code == 200
@@ -927,7 +938,7 @@ class TestConflictDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_lib_a}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -945,7 +956,7 @@ class TestConflictDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_lib_b}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -964,7 +975,7 @@ class TestConflictDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_app}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -1012,7 +1023,7 @@ class TestConflictDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_common}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -1031,7 +1042,7 @@ class TestConflictDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{lib_pkg}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200
@@ -1050,7 +1061,7 @@ class TestConflictDetection:
response = integration_client.post(
f"/api/v1/project/{test_project}/{pkg_app}/upload",
files=files,
data={"version": "1.0.0"},
data={"tag": "1.0.0"},
)
assert response.status_code == 200

View File

@@ -26,16 +26,16 @@ def upload_test_file(integration_client):
Factory fixture to upload a test file and return its artifact ID.
Usage:
artifact_id = upload_test_file(project, package, content, version="v1.0")
artifact_id = upload_test_file(project, package, content, tag="v1.0")
"""
def _upload(project_name: str, package_name: str, content: bytes, version: str = None):
def _upload(project_name: str, package_name: str, content: bytes, tag: str = None):
files = {
"file": ("test-file.bin", io.BytesIO(content), "application/octet-stream")
}
data = {}
if version:
data["version"] = version
if tag:
data["tag"] = tag
response = integration_client.post(
f"/api/v1/project/{project_name}/{package_name}/upload",
@@ -66,7 +66,7 @@ class TestDownloadChecksumHeaders:
# Upload file
artifact_id = upload_test_file(
project_name, package_name, content, version="sha256-header-test"
project_name, package_name, content, tag="sha256-header-test"
)
# Download with proxy mode
@@ -88,7 +88,7 @@ class TestDownloadChecksumHeaders:
content = b"Content for ETag header test"
artifact_id = upload_test_file(
project_name, package_name, content, version="etag-test"
project_name, package_name, content, tag="etag-test"
)
response = integration_client.get(
@@ -110,7 +110,7 @@ class TestDownloadChecksumHeaders:
content = b"Content for Digest header test"
sha256 = hashlib.sha256(content).hexdigest()
upload_test_file(project_name, package_name, content, version="digest-test")
upload_test_file(project_name, package_name, content, tag="digest-test")
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/+/digest-test",
@@ -137,7 +137,7 @@ class TestDownloadChecksumHeaders:
project_name, package_name = test_package
content = b"Content for X-Content-Length test"
upload_test_file(project_name, package_name, content, version="content-length-test")
upload_test_file(project_name, package_name, content, tag="content-length-test")
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/+/content-length-test",
@@ -156,7 +156,7 @@ class TestDownloadChecksumHeaders:
project_name, package_name = test_package
content = b"Content for X-Verified false test"
upload_test_file(project_name, package_name, content, version="verified-false-test")
upload_test_file(project_name, package_name, content, tag="verified-false-test")
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/+/verified-false-test",
@@ -184,7 +184,7 @@ class TestPreVerificationMode:
project_name, package_name = test_package
content = b"Content for pre-verification success test"
upload_test_file(project_name, package_name, content, version="pre-verify-success")
upload_test_file(project_name, package_name, content, tag="pre-verify-success")
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/+/pre-verify-success",
@@ -205,7 +205,7 @@ class TestPreVerificationMode:
# Use binary content to verify no corruption
content = bytes(range(256)) * 10 # 2560 bytes of all byte values
upload_test_file(project_name, package_name, content, version="pre-verify-content")
upload_test_file(project_name, package_name, content, tag="pre-verify-content")
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/+/pre-verify-content",
@@ -233,7 +233,7 @@ class TestStreamingVerificationMode:
content = b"Content for streaming verification success test"
upload_test_file(
project_name, package_name, content, version="stream-verify-success"
project_name, package_name, content, tag="stream-verify-success"
)
response = integration_client.get(
@@ -255,7 +255,7 @@ class TestStreamingVerificationMode:
# 100KB of content
content = b"x" * (100 * 1024)
upload_test_file(project_name, package_name, content, version="stream-verify-large")
upload_test_file(project_name, package_name, content, tag="stream-verify-large")
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/+/stream-verify-large",
@@ -283,7 +283,7 @@ class TestHeadRequestHeaders:
content = b"Content for HEAD SHA256 test"
artifact_id = upload_test_file(
project_name, package_name, content, version="head-sha256-test"
project_name, package_name, content, tag="head-sha256-test"
)
response = integration_client.head(
@@ -303,7 +303,7 @@ class TestHeadRequestHeaders:
content = b"Content for HEAD ETag test"
artifact_id = upload_test_file(
project_name, package_name, content, version="head-etag-test"
project_name, package_name, content, tag="head-etag-test"
)
response = integration_client.head(
@@ -322,7 +322,7 @@ class TestHeadRequestHeaders:
project_name, package_name = test_package
content = b"Content for HEAD Digest test"
upload_test_file(project_name, package_name, content, version="head-digest-test")
upload_test_file(project_name, package_name, content, tag="head-digest-test")
response = integration_client.head(
f"/api/v1/project/{project_name}/{package_name}/+/head-digest-test"
@@ -340,7 +340,7 @@ class TestHeadRequestHeaders:
project_name, package_name = test_package
content = b"Content for HEAD Content-Length test"
upload_test_file(project_name, package_name, content, version="head-length-test")
upload_test_file(project_name, package_name, content, tag="head-length-test")
response = integration_client.head(
f"/api/v1/project/{project_name}/{package_name}/+/head-length-test"
@@ -356,7 +356,7 @@ class TestHeadRequestHeaders:
project_name, package_name = test_package
content = b"Content for HEAD no-body test"
upload_test_file(project_name, package_name, content, version="head-no-body-test")
upload_test_file(project_name, package_name, content, tag="head-no-body-test")
response = integration_client.head(
f"/api/v1/project/{project_name}/{package_name}/+/head-no-body-test"
@@ -382,7 +382,7 @@ class TestRangeRequestHeaders:
project_name, package_name = test_package
content = b"Content for range request checksum header test"
upload_test_file(project_name, package_name, content, version="range-checksum-test")
upload_test_file(project_name, package_name, content, tag="range-checksum-test")
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/+/range-checksum-test",
@@ -412,7 +412,7 @@ class TestClientSideVerification:
project_name, package_name = test_package
content = b"Content for client-side verification test"
upload_test_file(project_name, package_name, content, version="client-verify-test")
upload_test_file(project_name, package_name, content, tag="client-verify-test")
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/+/client-verify-test",
@@ -438,7 +438,7 @@ class TestClientSideVerification:
project_name, package_name = test_package
content = b"Content for Digest header verification"
upload_test_file(project_name, package_name, content, version="digest-verify-test")
upload_test_file(project_name, package_name, content, tag="digest-verify-test")
response = integration_client.get(
f"/api/v1/project/{project_name}/{package_name}/+/digest-verify-test",

File diff suppressed because it is too large Load Diff

View File

@@ -1,374 +0,0 @@
"""Tests for CacheService."""
import pytest
from unittest.mock import MagicMock, AsyncMock, patch
class TestCacheCategory:
"""Tests for cache category enum."""
@pytest.mark.unit
def test_immutable_categories_have_no_ttl(self):
"""Immutable categories should return None for TTL."""
from app.cache_service import CacheCategory, get_category_ttl
from app.config import Settings
settings = Settings()
assert get_category_ttl(CacheCategory.ARTIFACT_METADATA, settings) is None
assert get_category_ttl(CacheCategory.ARTIFACT_DEPENDENCIES, settings) is None
assert get_category_ttl(CacheCategory.DEPENDENCY_RESOLUTION, settings) is None
@pytest.mark.unit
def test_mutable_categories_have_ttl(self):
"""Mutable categories should return configured TTL."""
from app.cache_service import CacheCategory, get_category_ttl
from app.config import Settings
settings = Settings(
cache_ttl_index=300,
cache_ttl_upstream=3600,
)
assert get_category_ttl(CacheCategory.PACKAGE_INDEX, settings) == 300
assert get_category_ttl(CacheCategory.UPSTREAM_SOURCES, settings) == 3600
class TestCacheService:
"""Tests for Redis cache service."""
@pytest.mark.asyncio
@pytest.mark.unit
async def test_disabled_cache_returns_none(self):
"""When Redis disabled, get() should return None."""
from app.cache_service import CacheService, CacheCategory
from app.config import Settings
settings = Settings(redis_enabled=False)
cache = CacheService(settings)
await cache.startup()
result = await cache.get(CacheCategory.PACKAGE_INDEX, "test-key")
assert result is None
await cache.shutdown()
@pytest.mark.asyncio
@pytest.mark.unit
async def test_disabled_cache_set_is_noop(self):
"""When Redis disabled, set() should be a no-op."""
from app.cache_service import CacheService, CacheCategory
from app.config import Settings
settings = Settings(redis_enabled=False)
cache = CacheService(settings)
await cache.startup()
# Should not raise
await cache.set(CacheCategory.PACKAGE_INDEX, "test-key", b"test-value")
await cache.shutdown()
@pytest.mark.asyncio
@pytest.mark.unit
async def test_cache_key_namespacing(self):
"""Cache keys should be properly namespaced."""
from app.cache_service import CacheService, CacheCategory
key = CacheService._make_key(CacheCategory.PACKAGE_INDEX, "pypi", "numpy")
assert key == "orchard:index:pypi:numpy"
@pytest.mark.asyncio
@pytest.mark.unit
async def test_ping_returns_false_when_disabled(self):
"""ping() should return False when Redis is disabled."""
from app.cache_service import CacheService
from app.config import Settings
settings = Settings(redis_enabled=False)
cache = CacheService(settings)
await cache.startup()
result = await cache.ping()
assert result is False
await cache.shutdown()
@pytest.mark.asyncio
@pytest.mark.unit
async def test_enabled_property(self):
"""enabled property should reflect Redis state."""
from app.cache_service import CacheService
from app.config import Settings
settings = Settings(redis_enabled=False)
cache = CacheService(settings)
assert cache.enabled is False
@pytest.mark.asyncio
@pytest.mark.unit
async def test_delete_is_noop_when_disabled(self):
"""delete() should be a no-op when Redis is disabled."""
from app.cache_service import CacheService, CacheCategory
from app.config import Settings
settings = Settings(redis_enabled=False)
cache = CacheService(settings)
await cache.startup()
# Should not raise
await cache.delete(CacheCategory.PACKAGE_INDEX, "test-key")
await cache.shutdown()
@pytest.mark.asyncio
@pytest.mark.unit
async def test_invalidate_pattern_returns_zero_when_disabled(self):
"""invalidate_pattern() should return 0 when Redis is disabled."""
from app.cache_service import CacheService, CacheCategory
from app.config import Settings
settings = Settings(redis_enabled=False)
cache = CacheService(settings)
await cache.startup()
result = await cache.invalidate_pattern(CacheCategory.PACKAGE_INDEX)
assert result == 0
await cache.shutdown()
@pytest.mark.asyncio
@pytest.mark.unit
async def test_startup_already_started(self):
"""startup() should be idempotent."""
from app.cache_service import CacheService
from app.config import Settings
settings = Settings(redis_enabled=False)
cache = CacheService(settings)
await cache.startup()
await cache.startup() # Should not raise
assert cache._started is True
await cache.shutdown()
@pytest.mark.asyncio
@pytest.mark.unit
async def test_shutdown_not_started(self):
"""shutdown() should handle not-started state."""
from app.cache_service import CacheService
from app.config import Settings
settings = Settings(redis_enabled=False)
cache = CacheService(settings)
# Should not raise
await cache.shutdown()
@pytest.mark.asyncio
@pytest.mark.unit
async def test_make_key_with_default_protocol(self):
"""_make_key should work with default protocol."""
from app.cache_service import CacheService, CacheCategory
key = CacheService._make_key(CacheCategory.ARTIFACT_METADATA, "default", "abc123")
assert key == "orchard:artifact:default:abc123"
class TestCacheServiceWithMockedRedis:
"""Tests for CacheService with mocked Redis client."""
@pytest.mark.asyncio
@pytest.mark.unit
async def test_get_returns_cached_value(self):
"""get() should return cached value when available."""
from app.cache_service import CacheService, CacheCategory
from app.config import Settings
settings = Settings(redis_enabled=True)
cache = CacheService(settings)
# Mock the redis client
mock_redis = AsyncMock()
mock_redis.get.return_value = b"cached-data"
cache._redis = mock_redis
cache._enabled = True
cache._started = True
result = await cache.get(CacheCategory.PACKAGE_INDEX, "test-key", "pypi")
assert result == b"cached-data"
mock_redis.get.assert_called_once_with("orchard:index:pypi:test-key")
@pytest.mark.asyncio
@pytest.mark.unit
async def test_set_with_ttl(self):
"""set() should use setex for mutable categories."""
from app.cache_service import CacheService, CacheCategory
from app.config import Settings
settings = Settings(redis_enabled=True, cache_ttl_index=300)
cache = CacheService(settings)
mock_redis = AsyncMock()
cache._redis = mock_redis
cache._enabled = True
cache._started = True
await cache.set(CacheCategory.PACKAGE_INDEX, "test-key", b"test-value", "pypi")
mock_redis.setex.assert_called_once_with(
"orchard:index:pypi:test-key", 300, b"test-value"
)
@pytest.mark.asyncio
@pytest.mark.unit
async def test_set_without_ttl(self):
"""set() should use set (no expiry) for immutable categories."""
from app.cache_service import CacheService, CacheCategory
from app.config import Settings
settings = Settings(redis_enabled=True)
cache = CacheService(settings)
mock_redis = AsyncMock()
cache._redis = mock_redis
cache._enabled = True
cache._started = True
await cache.set(
CacheCategory.ARTIFACT_METADATA, "abc123", b"metadata", "pypi"
)
mock_redis.set.assert_called_once_with(
"orchard:artifact:pypi:abc123", b"metadata"
)
@pytest.mark.asyncio
@pytest.mark.unit
async def test_delete_calls_redis_delete(self):
"""delete() should call Redis delete."""
from app.cache_service import CacheService, CacheCategory
from app.config import Settings
settings = Settings(redis_enabled=True)
cache = CacheService(settings)
mock_redis = AsyncMock()
cache._redis = mock_redis
cache._enabled = True
cache._started = True
await cache.delete(CacheCategory.PACKAGE_INDEX, "test-key", "pypi")
mock_redis.delete.assert_called_once_with("orchard:index:pypi:test-key")
@pytest.mark.asyncio
@pytest.mark.unit
async def test_invalidate_pattern_deletes_matching_keys(self):
"""invalidate_pattern() should delete all matching keys."""
from app.cache_service import CacheService, CacheCategory
from app.config import Settings
settings = Settings(redis_enabled=True)
cache = CacheService(settings)
mock_redis = AsyncMock()
# Create an async generator for scan_iter
async def mock_scan_iter(match=None):
for key in [b"orchard:index:pypi:numpy", b"orchard:index:pypi:requests"]:
yield key
mock_redis.scan_iter = mock_scan_iter
mock_redis.delete.return_value = 2
cache._redis = mock_redis
cache._enabled = True
cache._started = True
result = await cache.invalidate_pattern(CacheCategory.PACKAGE_INDEX, "*", "pypi")
assert result == 2
mock_redis.delete.assert_called_once()
@pytest.mark.asyncio
@pytest.mark.unit
async def test_ping_returns_true_when_connected(self):
"""ping() should return True when Redis responds."""
from app.cache_service import CacheService
from app.config import Settings
settings = Settings(redis_enabled=True)
cache = CacheService(settings)
mock_redis = AsyncMock()
mock_redis.ping.return_value = True
cache._redis = mock_redis
cache._enabled = True
cache._started = True
result = await cache.ping()
assert result is True
@pytest.mark.asyncio
@pytest.mark.unit
async def test_get_handles_exception(self):
"""get() should return None and log warning on exception."""
from app.cache_service import CacheService, CacheCategory
from app.config import Settings
settings = Settings(redis_enabled=True)
cache = CacheService(settings)
mock_redis = AsyncMock()
mock_redis.get.side_effect = Exception("Connection lost")
cache._redis = mock_redis
cache._enabled = True
cache._started = True
result = await cache.get(CacheCategory.PACKAGE_INDEX, "test-key")
assert result is None
@pytest.mark.asyncio
@pytest.mark.unit
async def test_set_handles_exception(self):
"""set() should log warning on exception."""
from app.cache_service import CacheService, CacheCategory
from app.config import Settings
settings = Settings(redis_enabled=True, cache_ttl_index=300)
cache = CacheService(settings)
mock_redis = AsyncMock()
mock_redis.setex.side_effect = Exception("Connection lost")
cache._redis = mock_redis
cache._enabled = True
cache._started = True
# Should not raise
await cache.set(CacheCategory.PACKAGE_INDEX, "test-key", b"value")
@pytest.mark.asyncio
@pytest.mark.unit
async def test_ping_returns_false_on_exception(self):
"""ping() should return False on exception."""
from app.cache_service import CacheService
from app.config import Settings
settings = Settings(redis_enabled=True)
cache = CacheService(settings)
mock_redis = AsyncMock()
mock_redis.ping.side_effect = Exception("Connection lost")
cache._redis = mock_redis
cache._enabled = True
cache._started = True
result = await cache.ping()
assert result is False

View File

@@ -1,167 +0,0 @@
"""Tests for database utility functions."""
import pytest
from unittest.mock import MagicMock, patch
class TestArtifactRepository:
"""Tests for ArtifactRepository."""
def test_batch_dependency_values_formatting(self):
"""batch_upsert_dependencies should format values correctly."""
from app.db_utils import ArtifactRepository
deps = [
("_pypi", "numpy", ">=1.21.0"),
("_pypi", "requests", "*"),
("myproject", "mylib", "==1.0.0"),
]
values = ArtifactRepository._format_dependency_values("abc123", deps)
assert len(values) == 3
assert values[0] == {
"artifact_id": "abc123",
"dependency_project": "_pypi",
"dependency_package": "numpy",
"version_constraint": ">=1.21.0",
}
assert values[2]["dependency_project"] == "myproject"
def test_empty_dependencies_returns_empty_list(self):
"""Empty dependency list should return empty values."""
from app.db_utils import ArtifactRepository
values = ArtifactRepository._format_dependency_values("abc123", [])
assert values == []
def test_format_dependency_values_preserves_special_characters(self):
"""Version constraints with special characters should be preserved."""
from app.db_utils import ArtifactRepository
deps = [
("_pypi", "package-name", ">=1.0.0,<2.0.0"),
("_pypi", "another_pkg", "~=1.4.2"),
]
values = ArtifactRepository._format_dependency_values("hash123", deps)
assert values[0]["version_constraint"] == ">=1.0.0,<2.0.0"
assert values[1]["version_constraint"] == "~=1.4.2"
def test_batch_upsert_dependencies_returns_zero_for_empty(self):
"""batch_upsert_dependencies should return 0 for empty list without DB call."""
from app.db_utils import ArtifactRepository
mock_db = MagicMock()
repo = ArtifactRepository(mock_db)
result = repo.batch_upsert_dependencies("abc123", [])
assert result == 0
# Verify no DB operations were performed
mock_db.execute.assert_not_called()
def test_get_or_create_artifact_builds_correct_statement(self):
"""get_or_create_artifact should use ON CONFLICT DO UPDATE."""
from app.db_utils import ArtifactRepository
from app.models import Artifact
mock_db = MagicMock()
mock_result = MagicMock()
mock_artifact = MagicMock()
mock_artifact.ref_count = 1
mock_result.scalar_one.return_value = mock_artifact
mock_db.execute.return_value = mock_result
repo = ArtifactRepository(mock_db)
artifact, created = repo.get_or_create_artifact(
sha256="abc123def456",
size=1024,
filename="test.whl",
content_type="application/zip",
)
assert mock_db.execute.called
assert created is True
assert artifact == mock_artifact
def test_get_or_create_artifact_existing_not_created(self):
"""get_or_create_artifact should return created=False for existing artifact."""
from app.db_utils import ArtifactRepository
mock_db = MagicMock()
mock_result = MagicMock()
mock_artifact = MagicMock()
mock_artifact.ref_count = 5 # Existing artifact with ref_count > 1
mock_result.scalar_one.return_value = mock_artifact
mock_db.execute.return_value = mock_result
repo = ArtifactRepository(mock_db)
artifact, created = repo.get_or_create_artifact(
sha256="abc123def456",
size=1024,
filename="test.whl",
)
assert created is False
def test_get_cached_url_with_artifact_returns_tuple(self):
"""get_cached_url_with_artifact should return (CachedUrl, Artifact) tuple."""
from app.db_utils import ArtifactRepository
mock_db = MagicMock()
mock_cached_url = MagicMock()
mock_artifact = MagicMock()
mock_db.query.return_value.join.return_value.filter.return_value.first.return_value = (
mock_cached_url,
mock_artifact,
)
repo = ArtifactRepository(mock_db)
result = repo.get_cached_url_with_artifact("url_hash_123")
assert result == (mock_cached_url, mock_artifact)
def test_get_cached_url_with_artifact_returns_none_when_not_found(self):
"""get_cached_url_with_artifact should return None when URL not cached."""
from app.db_utils import ArtifactRepository
mock_db = MagicMock()
mock_db.query.return_value.join.return_value.filter.return_value.first.return_value = None
repo = ArtifactRepository(mock_db)
result = repo.get_cached_url_with_artifact("nonexistent_hash")
assert result is None
def test_get_artifact_dependencies_returns_list(self):
"""get_artifact_dependencies should return list of dependencies."""
from app.db_utils import ArtifactRepository
mock_db = MagicMock()
mock_dep1 = MagicMock()
mock_dep2 = MagicMock()
mock_db.query.return_value.filter.return_value.all.return_value = [
mock_dep1,
mock_dep2,
]
repo = ArtifactRepository(mock_db)
result = repo.get_artifact_dependencies("artifact_hash_123")
assert len(result) == 2
assert result[0] == mock_dep1
assert result[1] == mock_dep2
def test_get_artifact_dependencies_returns_empty_list(self):
"""get_artifact_dependencies should return empty list when no dependencies."""
from app.db_utils import ArtifactRepository
mock_db = MagicMock()
mock_db.query.return_value.filter.return_value.all.return_value = []
repo = ArtifactRepository(mock_db)
result = repo.get_artifact_dependencies("artifact_without_deps")
assert result == []

View File

@@ -1,194 +0,0 @@
"""Tests for HttpClientManager."""
import pytest
from unittest.mock import MagicMock, AsyncMock, patch
class TestHttpClientManager:
"""Tests for HTTP client pool management."""
@pytest.mark.unit
def test_manager_initializes_with_settings(self):
"""Manager should initialize with config settings."""
from app.http_client import HttpClientManager
from app.config import Settings
settings = Settings(
http_max_connections=50,
http_connect_timeout=15.0,
)
manager = HttpClientManager(settings)
assert manager.max_connections == 50
assert manager.connect_timeout == 15.0
assert manager._default_client is None # Not started yet
@pytest.mark.asyncio
@pytest.mark.unit
async def test_startup_creates_client(self):
"""Startup should create the default async client."""
from app.http_client import HttpClientManager
from app.config import Settings
settings = Settings()
manager = HttpClientManager(settings)
await manager.startup()
assert manager._default_client is not None
await manager.shutdown()
@pytest.mark.asyncio
@pytest.mark.unit
async def test_shutdown_closes_client(self):
"""Shutdown should close all clients gracefully."""
from app.http_client import HttpClientManager
from app.config import Settings
settings = Settings()
manager = HttpClientManager(settings)
await manager.startup()
client = manager._default_client
await manager.shutdown()
assert manager._default_client is None
assert client.is_closed
@pytest.mark.asyncio
@pytest.mark.unit
async def test_get_client_returns_default(self):
"""get_client() should return the default client."""
from app.http_client import HttpClientManager
from app.config import Settings
settings = Settings()
manager = HttpClientManager(settings)
await manager.startup()
client = manager.get_client()
assert client is manager._default_client
await manager.shutdown()
@pytest.mark.asyncio
@pytest.mark.unit
async def test_get_client_raises_if_not_started(self):
"""get_client() should raise RuntimeError if manager not started."""
from app.http_client import HttpClientManager
from app.config import Settings
settings = Settings()
manager = HttpClientManager(settings)
with pytest.raises(RuntimeError, match="not started"):
manager.get_client()
@pytest.mark.asyncio
@pytest.mark.unit
async def test_run_blocking_executes_in_thread_pool(self):
"""run_blocking should execute sync functions in thread pool."""
from app.http_client import HttpClientManager
from app.config import Settings
import threading
settings = Settings()
manager = HttpClientManager(settings)
await manager.startup()
main_thread = threading.current_thread()
execution_thread = None
def blocking_func():
nonlocal execution_thread
execution_thread = threading.current_thread()
return "result"
result = await manager.run_blocking(blocking_func)
assert result == "result"
assert execution_thread is not main_thread
await manager.shutdown()
@pytest.mark.asyncio
@pytest.mark.unit
async def test_run_blocking_raises_if_not_started(self):
"""run_blocking should raise RuntimeError if manager not started."""
from app.http_client import HttpClientManager
from app.config import Settings
settings = Settings()
manager = HttpClientManager(settings)
with pytest.raises(RuntimeError, match="not started"):
await manager.run_blocking(lambda: None)
@pytest.mark.asyncio
@pytest.mark.unit
async def test_startup_idempotent(self):
"""Calling startup multiple times should be safe."""
from app.http_client import HttpClientManager
from app.config import Settings
settings = Settings()
manager = HttpClientManager(settings)
await manager.startup()
client1 = manager._default_client
await manager.startup() # Should not create a new client
client2 = manager._default_client
assert client1 is client2 # Same client instance
await manager.shutdown()
@pytest.mark.asyncio
@pytest.mark.unit
async def test_shutdown_idempotent(self):
"""Calling shutdown multiple times should be safe."""
from app.http_client import HttpClientManager
from app.config import Settings
settings = Settings()
manager = HttpClientManager(settings)
await manager.startup()
await manager.shutdown()
await manager.shutdown() # Should not raise
assert manager._default_client is None
@pytest.mark.asyncio
@pytest.mark.unit
async def test_properties_return_configured_values(self):
"""Properties should return configured values."""
from app.http_client import HttpClientManager
from app.config import Settings
settings = Settings(
http_max_connections=75,
http_worker_threads=16,
)
manager = HttpClientManager(settings)
await manager.startup()
assert manager.pool_size == 75
assert manager.executor_max == 16
await manager.shutdown()
@pytest.mark.asyncio
@pytest.mark.unit
async def test_active_connections_when_not_started(self):
"""active_connections should return 0 when not started."""
from app.http_client import HttpClientManager
from app.config import Settings
settings = Settings()
manager = HttpClientManager(settings)
assert manager.active_connections == 0

View File

@@ -145,6 +145,54 @@ class TestPackageModel:
assert platform_col.default.arg == "any"
class TestTagModel:
"""Tests for the Tag model."""
@pytest.mark.unit
def test_tag_requires_package_id(self):
"""Test tag requires package_id."""
from app.models import Tag
tag = Tag(
name="v1.0.0",
package_id=uuid.uuid4(),
artifact_id="f" * 64,
created_by="test-user",
)
assert tag.package_id is not None
assert tag.artifact_id == "f" * 64
class TestTagHistoryModel:
"""Tests for the TagHistory model."""
@pytest.mark.unit
def test_tag_history_default_change_type(self):
"""Test tag history change_type column has default value of 'update'."""
from app.models import TagHistory
# Check the column definition has the right default
change_type_col = TagHistory.__table__.columns["change_type"]
assert change_type_col.default is not None
assert change_type_col.default.arg == "update"
@pytest.mark.unit
def test_tag_history_allows_null_old_artifact(self):
"""Test tag history allows null old_artifact_id (for create events)."""
from app.models import TagHistory
history = TagHistory(
tag_id=uuid.uuid4(),
old_artifact_id=None,
new_artifact_id="h" * 64,
change_type="create",
changed_by="test-user",
)
assert history.old_artifact_id is None
class TestUploadModel:
"""Tests for the Upload model."""

View File

@@ -1,672 +0,0 @@
# Epic: Upstream Artifact Caching for Hermetic Builds
## Overview
Orchard will act as a permanent, content-addressable cache for upstream artifacts (npm, PyPI, Maven, Docker, etc.). Once an artifact is cached, it is stored forever by SHA256 hash - enabling reproducible builds years later regardless of whether the upstream source still exists.
## Problem Statement
Build reproducibility is critical for enterprise environments:
- Packages get deleted, yanked, or modified upstream
- Registries go down or change URLs
- Version constraints resolve differently over time
- Air-gapped environments cannot access public internet
Teams need to guarantee that a build from 5 years ago produces the exact same output today.
## Solution
Orchard becomes "the cache that never forgets":
1. **Fetch once, store forever** - When a build needs `lodash@4.17.21`, Orchard fetches it from npm, stores it by SHA256 hash, and never deletes it
2. **Content-addressable** - Same hash = same bytes, guaranteed
3. **Format-agnostic** - Orchard doesn't need to understand npm/PyPI/Maven protocols; the client provides the URL, Orchard fetches and stores
4. **Air-gap support** - Disable public internet entirely, only allow configured private upstreams
## User Workflow
```
1. Build tool resolves dependencies npm install / pip install / mvn resolve
2. Generate lockfile with URLs package-lock.json / requirements.txt
3. Cache all URLs in Orchard orchard cache --file urls.txt
4. Pin by SHA256 hash lodash = "sha256:abc123..."
5. Future builds fetch by hash Always get exact same bytes
```
## Key Features
- **Multiple upstream sources** - Configure npm, PyPI, Maven Central, private Artifactory, etc.
- **Per-source authentication** - Basic auth, bearer tokens, API keys
- **System cache projects** - `_npm`, `_pypi`, `_maven` organize cached packages by format
- **Cross-referencing** - Link cached artifacts to user projects for visibility
- **URL tracking** - Know which URLs map to which hashes, audit provenance
- **Air-gap mode** - Global kill switch for all public internet access
- **Environment variable config** - 12-factor friendly for containerized deployments
## Architecture
```
┌─────────────────────────────────────────────────────────────────┐
│ Orchard Server │
├─────────────────────────────────────────────────────────────────┤
│ POST /api/v1/cache │
│ ├── Check if URL already cached (url_hash lookup) │
│ ├── Match URL to upstream source (get auth) │
│ ├── Fetch via UpstreamClient (stream + compute SHA256) │
│ ├── Store artifact in S3 (content-addressable) │
│ ├── Create tag in system project (_npm/lodash:4.17.21) │
│ ├── Optionally create tag in user project │
│ └── Record in cached_urls table (provenance) │
├─────────────────────────────────────────────────────────────────┤
│ Tables │
│ ├── upstream_sources (npm-public, pypi-public, artifactory) │
│ ├── cache_settings (allow_public_internet, etc.) │
│ ├── cached_urls (url → artifact_id mapping) │
│ └── projects.is_system (for _npm, _pypi, etc.) │
└─────────────────────────────────────────────────────────────────┘
```
## Issues Summary
| Issue | Title | Status | Dependencies |
|-------|-------|--------|--------------|
| #68 | Schema: Upstream Sources & Cache Tracking | ✅ Complete | None |
| #69 | HTTP Client: Generic URL Fetcher | Pending | None |
| #70 | Cache API Endpoint | Pending | #68, #69 |
| #71 | System Projects (Cache Namespaces) | Pending | #68, #70 |
| #72 | Upstream Sources Admin API | Pending | #68 |
| #73 | Global Cache Settings API | Pending | #68 |
| #74 | Environment Variable Overrides | Pending | #68, #72, #73 |
| #75 | Frontend: Upstream Sources Management | Pending | #72, #73 |
| #105 | Frontend: System Projects Integration | Pending | #71 |
| #77 | CLI: Cache Command | Pending | #70 |
## Implementation Phases
**Phase 1 - Core (MVP):**
- #68 Schema ✅
- #69 HTTP Client
- #70 Cache API
- #71 System Projects
**Phase 2 - Admin:**
- #72 Upstream Sources API
- #73 Cache Settings API
- #74 Environment Variables
**Phase 3 - Frontend:**
- #75 Upstream Sources UI
- #105 System Projects UI
**Phase 4 - CLI:**
- #77 Cache Command
---
# Issue #68: Schema - Upstream Sources & Cache Tracking
**Status: ✅ Complete**
## Description
Create database schema for flexible multi-source upstream configuration and URL-to-artifact tracking. This replaces the previous singleton proxy_config design with a more flexible model supporting multiple upstream sources, air-gap mode, and provenance tracking.
## Acceptance Criteria
- [x] `upstream_sources` table:
- id (UUID, primary key)
- name (VARCHAR(255), unique, e.g., "npm-public", "artifactory-private")
- source_type (VARCHAR(50), enum: npm, pypi, maven, docker, helm, nuget, deb, rpm, generic)
- url (VARCHAR(2048), base URL of upstream)
- enabled (BOOLEAN, default false)
- is_public (BOOLEAN, true if this is a public internet source)
- auth_type (VARCHAR(20), enum: none, basic, bearer, api_key)
- username (VARCHAR(255), nullable)
- password_encrypted (BYTEA, nullable, Fernet encrypted)
- headers_encrypted (BYTEA, nullable, for custom headers like API keys)
- priority (INTEGER, default 100, lower = checked first)
- created_at, updated_at timestamps
- [x] `cache_settings` table (singleton, id always 1):
- id (INTEGER, primary key, check id = 1)
- allow_public_internet (BOOLEAN, default true, air-gap kill switch)
- auto_create_system_projects (BOOLEAN, default true)
- created_at, updated_at timestamps
- [x] `cached_urls` table:
- id (UUID, primary key)
- url (VARCHAR(4096), original URL fetched)
- url_hash (VARCHAR(64), SHA256 of URL for fast lookup, indexed)
- artifact_id (VARCHAR(64), FK to artifacts)
- source_id (UUID, FK to upstream_sources, nullable for manual imports)
- fetched_at (TIMESTAMP WITH TIME ZONE)
- response_headers (JSONB, original upstream headers for provenance)
- created_at timestamp
- [x] Add `is_system` BOOLEAN column to projects table (default false)
- [x] Migration SQL file in migrations/
- [x] Runtime migration in database.py
- [x] SQLAlchemy models for all new tables
- [x] Pydantic schemas for API input/output (passwords write-only)
- [x] Encryption helpers for password/headers fields
- [x] Seed default upstream sources (disabled by default):
- npm-public: https://registry.npmjs.org
- pypi-public: https://pypi.org/simple
- maven-central: https://repo1.maven.org/maven2
- docker-hub: https://registry-1.docker.io
- [x] Unit tests for models and schemas
## Files Modified
- `migrations/010_upstream_caching.sql`
- `backend/app/database.py` (migrations 016-020)
- `backend/app/models.py` (UpstreamSource, CacheSettings, CachedUrl, Project.is_system)
- `backend/app/schemas.py` (all caching schemas)
- `backend/app/encryption.py` (renamed env var)
- `backend/app/config.py` (renamed setting)
- `backend/tests/test_upstream_caching.py` (37 tests)
- `frontend/src/components/Layout.tsx` (footer tagline)
- `CHANGELOG.md`
---
# Issue #69: HTTP Client - Generic URL Fetcher
**Status: Pending**
## Description
Create a reusable HTTP client for fetching artifacts from upstream sources. Supports multiple auth methods, streaming for large files, and computes SHA256 while downloading.
## Acceptance Criteria
- [ ] `UpstreamClient` class in `backend/app/upstream.py`
- [ ] `fetch(url)` method that:
- Streams response body (doesn't load large files into memory)
- Computes SHA256 hash while streaming
- Returns file content, hash, size, and response headers
- [ ] Auth support based on upstream source configuration:
- None (anonymous)
- Basic auth (username/password)
- Bearer token (Authorization: Bearer {token})
- API key (custom header name/value)
- [ ] URL-to-source matching:
- Match URL to configured upstream source by URL prefix
- Apply auth from matched source
- Respect source priority for multiple matches
- [ ] Configuration options:
- Timeout (connect and read, default 30s/300s)
- Max retries (default 3)
- Follow redirects (default true, max 5)
- Max file size (reject if Content-Length exceeds limit)
- [ ] Respect `allow_public_internet` setting:
- If false, reject URLs matching `is_public=true` sources
- If false, reject URLs not matching any configured source
- [ ] Capture response headers for provenance tracking
- [ ] Proper error handling:
- Connection errors (retry with backoff)
- HTTP errors (4xx, 5xx)
- Timeout errors
- SSL/TLS errors
- [ ] Logging for debugging (URL, source matched, status, timing)
- [ ] Unit tests with mocked HTTP responses
- [ ] Integration tests against httpbin.org or similar (optional, marked)
## Technical Notes
- Use `httpx` for async HTTP support (already in requirements)
- Stream to temp file to avoid memory issues with large artifacts
- Consider checksum verification if upstream provides it (e.g., npm provides shasum)
---
# Issue #70: Cache API Endpoint
**Status: Pending**
## Description
API endpoint to cache an artifact from an upstream URL. This is the core endpoint that fetches from upstream, stores in Orchard, and creates appropriate tags.
## Acceptance Criteria
- [ ] `POST /api/v1/cache` endpoint
- [ ] Request body:
```json
{
"url": "https://registry.npmjs.org/lodash/-/lodash-4.17.21.tgz",
"source_type": "npm",
"package_name": "lodash",
"tag": "4.17.21",
"user_project": "my-app",
"user_package": "npm-deps",
"user_tag": "lodash-4.17.21",
"expected_hash": "sha256:abc123..."
}
```
- `url` (required): URL to fetch
- `source_type` (required): Determines system project (_npm, _pypi, etc.)
- `package_name` (optional): Package name in system project, derived from URL if not provided
- `tag` (optional): Tag name in system project, derived from URL if not provided
- `user_project`, `user_package`, `user_tag` (optional): Cross-reference in user's project
- `expected_hash` (optional): Verify downloaded content matches
- [ ] Response:
```json
{
"artifact_id": "abc123...",
"sha256": "abc123...",
"size": 12345,
"content_type": "application/gzip",
"already_cached": false,
"source_url": "https://registry.npmjs.org/lodash/-/lodash-4.17.21.tgz",
"source_name": "npm-public",
"system_project": "_npm",
"system_package": "lodash",
"system_tag": "4.17.21",
"user_reference": "my-app/npm-deps:lodash-4.17.21"
}
```
- [ ] Behavior:
- Check if URL already cached (by url_hash in cached_urls)
- If cached: return existing artifact, optionally create user tag
- If not cached: fetch via UpstreamClient, store artifact, create tags
- Create/get system project if needed (e.g., `_npm`)
- Create package in system project (e.g., `_npm/lodash`)
- Create tag in system project (e.g., `_npm/lodash:4.17.21`)
- If user reference provided, create tag in user's project
- Record in cached_urls table with provenance
- [ ] Error handling:
- 400: Invalid request (bad URL format, missing required fields)
- 403: Air-gap mode enabled and URL is from public source
- 404: Upstream returned 404
- 409: Hash mismatch (if expected_hash provided)
- 502: Upstream fetch failed (connection error, timeout)
- 503: Upstream source disabled
- [ ] Authentication required (any authenticated user can cache)
- [ ] Audit logging for cache operations
- [ ] Integration tests covering success and error cases
## Technical Notes
- URL parsing for package_name/tag derivation is format-specific:
- npm: `/{package}/-/{package}-{version}.tgz` → package=lodash, tag=4.17.21
- pypi: `/packages/.../requests-2.28.0.tar.gz` → package=requests, tag=2.28.0
- maven: `/{group}/{artifact}/{version}/{artifact}-{version}.jar`
- Deduplication: if same SHA256 already exists, just create new tag pointing to it
---
# Issue #71: System Projects (Cache Namespaces)
**Status: Pending**
## Description
Implement auto-created system projects for organizing cached artifacts by format type. These are special projects that provide a browsable namespace for all cached upstream packages.
## Acceptance Criteria
- [ ] System project names: `_npm`, `_pypi`, `_maven`, `_docker`, `_helm`, `_nuget`, `_deb`, `_rpm`, `_generic`
- [ ] Auto-creation:
- Created automatically on first cache request for that format
- Created by cache endpoint, not at startup
- Uses system user as creator (`created_by = "system"`)
- [ ] System project properties:
- `is_system = true`
- `is_public = true` (readable by all authenticated users)
- `description` = "System cache for {format} packages"
- [ ] Restrictions:
- Cannot be deleted (return 403 with message)
- Cannot be renamed
- Cannot change `is_public` to false
- Only admins can modify description
- [ ] Helper function: `get_or_create_system_project(source_type)` in routes.py or new cache.py module
- [ ] Update project deletion endpoint to check `is_system` flag
- [ ] Update project update endpoint to enforce restrictions
- [ ] Query helper: list all system projects for UI dropdown
- [ ] Unit tests for restrictions
- [ ] Integration tests for auto-creation and restrictions
## Technical Notes
- System projects are identified by `is_system=true`, not just naming convention
- The `_` prefix is a convention for display purposes
- Packages within system projects follow upstream naming (e.g., `_npm/lodash`, `_npm/@types/node`)
---
# Issue #72: Upstream Sources Admin API
**Status: Pending**
## Description
CRUD API endpoints for managing upstream sources configuration. Admin-only access.
## Acceptance Criteria
- [ ] `GET /api/v1/admin/upstream-sources` - List all upstream sources
- Returns array of sources with id, name, source_type, url, enabled, is_public, auth_type, priority, has_credentials, created_at, updated_at
- Supports `?enabled=true/false` filter
- Supports `?source_type=npm,pypi` filter
- Passwords/tokens never returned
- [ ] `POST /api/v1/admin/upstream-sources` - Create upstream source
- Request: name, source_type, url, enabled, is_public, auth_type, username, password, headers, priority
- Validates unique name
- Validates URL format
- Encrypts password/headers before storage
- Returns created source (without secrets)
- [ ] `GET /api/v1/admin/upstream-sources/{id}` - Get source details
- Returns source with `has_credentials` boolean, not actual credentials
- [ ] `PUT /api/v1/admin/upstream-sources/{id}` - Update source
- Partial update supported
- If password provided, re-encrypt; if omitted, keep existing
- Special value `password: null` clears credentials
- [ ] `DELETE /api/v1/admin/upstream-sources/{id}` - Delete source
- Returns 400 if source has cached_urls referencing it (optional: cascade or reassign)
- [ ] `POST /api/v1/admin/upstream-sources/{id}/test` - Test connectivity
- Attempts HEAD request to source URL
- Returns success/failure with status code and timing
- Does not cache anything
- [ ] All endpoints require admin role
- [ ] Audit logging for all mutations
- [ ] Pydantic schemas: UpstreamSourceCreate, UpstreamSourceUpdate, UpstreamSourceResponse
- [ ] Integration tests for all endpoints
## Technical Notes
- Test endpoint should respect auth configuration to verify credentials work
- Consider adding `last_used_at` and `last_error` fields for observability (future enhancement)
---
# Issue #73: Global Cache Settings API
**Status: Pending**
## Description
API endpoints for managing global cache settings including air-gap mode.
## Acceptance Criteria
- [ ] `GET /api/v1/admin/cache-settings` - Get current settings
- Returns: allow_public_internet, auto_create_system_projects, created_at, updated_at
- [ ] `PUT /api/v1/admin/cache-settings` - Update settings
- Partial update supported
- Returns updated settings
- [ ] Settings fields:
- `allow_public_internet` (boolean): When false, blocks all requests to sources marked `is_public=true`
- `auto_create_system_projects` (boolean): When false, system projects must be created manually
- [ ] Admin-only access
- [ ] Audit logging for changes (especially air-gap mode changes)
- [ ] Pydantic schemas: CacheSettingsResponse, CacheSettingsUpdate
- [ ] Initialize singleton row on first access if not exists
- [ ] Integration tests
## Technical Notes
- Air-gap mode change should be logged prominently (security-relevant)
- Consider requiring confirmation header for disabling air-gap mode (similar to factory reset)
---
# Issue #74: Environment Variable Overrides
**Status: Pending**
## Description
Allow cache and upstream configuration via environment variables for containerized deployments. Environment variables override database settings following 12-factor app principles.
## Acceptance Criteria
- [ ] Global settings overrides:
- `ORCHARD_CACHE_ALLOW_PUBLIC_INTERNET=true/false`
- `ORCHARD_CACHE_AUTO_CREATE_SYSTEM_PROJECTS=true/false`
- `ORCHARD_CACHE_ENCRYPTION_KEY` (Fernet key for credential encryption)
- [ ] Upstream source definition via env vars:
- `ORCHARD_UPSTREAM__{NAME}__URL` (double underscore as separator)
- `ORCHARD_UPSTREAM__{NAME}__TYPE` (npm, pypi, maven, etc.)
- `ORCHARD_UPSTREAM__{NAME}__ENABLED` (true/false)
- `ORCHARD_UPSTREAM__{NAME}__IS_PUBLIC` (true/false)
- `ORCHARD_UPSTREAM__{NAME}__AUTH_TYPE` (none, basic, bearer, api_key)
- `ORCHARD_UPSTREAM__{NAME}__USERNAME`
- `ORCHARD_UPSTREAM__{NAME}__PASSWORD`
- `ORCHARD_UPSTREAM__{NAME}__PRIORITY`
- Example: `ORCHARD_UPSTREAM__NPM_PRIVATE__URL=https://npm.corp.com`
- [ ] Env var sources:
- Loaded at startup
- Merged with database sources
- Env var sources have `source = "env"` marker
- Cannot be modified via API (return 400)
- Cannot be deleted via API (return 400)
- [ ] Update Settings class in config.py
- [ ] Update get/list endpoints to include env-defined sources
- [ ] Document all env vars in CLAUDE.md
- [ ] Unit tests for env var parsing
- [ ] Integration tests with env vars set
## Technical Notes
- Double underscore (`__`) separator allows source names with single underscores
- Env-defined sources should appear in API responses but marked as read-only
- Consider startup validation that warns about invalid env var combinations
---
# Issue #75: Frontend - Upstream Sources Management
**Status: Pending**
## Description
Admin UI for managing upstream sources and cache settings.
## Acceptance Criteria
- [ ] New admin page: `/admin/cache` or `/admin/upstream-sources`
- [ ] Upstream sources section:
- Table listing all sources with: name, type, URL, enabled toggle, public badge, priority, actions
- Visual distinction for env-defined sources (locked icon, no edit/delete)
- Create button opens modal/form
- Edit button for DB-defined sources
- Delete with confirmation modal
- Test connection button with status indicator
- [ ] Create/edit form fields:
- Name (text, required)
- Source type (dropdown)
- URL (text, required)
- Priority (number)
- Is public (checkbox)
- Enabled (checkbox)
- Auth type (dropdown: none, basic, bearer, api_key)
- Conditional auth fields based on type:
- Basic: username, password
- Bearer: token
- API key: header name, header value
- Password fields masked, "unchanged" placeholder on edit
- [ ] Cache settings section:
- Air-gap mode toggle with warning
- Auto-create system projects toggle
- "Air-gap mode" shows prominent warning banner when enabled
- [ ] Link from main admin navigation
- [ ] Loading and error states
- [ ] Success/error toast notifications
## Technical Notes
- Use existing admin page patterns from user management
- Air-gap toggle should require confirmation (modal with warning text)
---
# Issue #105: Frontend - System Projects Integration
**Status: Pending**
## Description
Integrate system projects into the frontend UI with appropriate visual treatment and navigation.
## Acceptance Criteria
- [ ] Home page project dropdown:
- System projects shown in separate "Cached Packages" section
- Visual distinction (icon, different background, or badge)
- Format icon for each type (npm, pypi, maven, etc.)
- [ ] Project list/grid:
- System projects can be filtered: "Show system projects" toggle
- Or separate tab: "Projects" | "Package Cache"
- [ ] System project page:
- "System Cache" badge in header
- Description explains this is auto-managed cache
- Settings/delete buttons hidden or disabled
- Shows format type prominently
- [ ] Package page within system project:
- Shows "Cached from" with source URL (linked)
- Shows "First cached" timestamp
- Shows which upstream source provided it
- [ ] Artifact page:
- If artifact came from cache, show provenance:
- Original URL
- Upstream source name
- Fetch timestamp
- [ ] Search includes system projects (with filter option)
## Technical Notes
- Use React context or query params for system project filtering
- Consider dedicated route: `/cache/npm/lodash` as alias for `/_npm/lodash`
---
# Issue #77: CLI - Cache Command
**Status: Pending**
## Description
Add a new `orchard cache` command to the existing CLI for caching artifacts from upstream URLs. This integrates with the new cache API endpoint and can optionally update `orchard.ensure` with cached artifacts.
## Acceptance Criteria
- [ ] New command: `orchard cache <url>` in `orchard/commands/cache.py`
- [ ] Basic usage:
```bash
# Cache a URL, print artifact info
orchard cache https://registry.npmjs.org/lodash/-/lodash-4.17.21.tgz
# Output:
# Caching https://registry.npmjs.org/lodash/-/lodash-4.17.21.tgz...
# Source type: npm
# Package: lodash
# Version: 4.17.21
#
# Successfully cached artifact
# Artifact ID: abc123...
# Size: 1.2 MB
# System project: _npm
# System package: lodash
# System tag: 4.17.21
```
- [ ] Options:
| Option | Description |
|--------|-------------|
| `--type, -t TYPE` | Source type: npm, pypi, maven, docker, helm, generic (auto-detected from URL if not provided) |
| `--package, -p NAME` | Package name in system project (auto-derived from URL if not provided) |
| `--tag TAG` | Tag name in system project (auto-derived from URL if not provided) |
| `--project PROJECT` | Also create tag in this user project |
| `--user-package PKG` | Package name in user project (required if --project specified) |
| `--user-tag TAG` | Tag name in user project (default: same as system tag) |
| `--expected-hash HASH` | Verify downloaded content matches this SHA256 |
| `--add` | Add to orchard.ensure after caching |
| `--add-path PATH` | Extraction path for --add (default: `<package>/`) |
| `--file, -f FILE` | Path to orchard.ensure file |
| `--verbose, -v` | Show detailed output |
- [ ] URL type auto-detection:
- `registry.npmjs.org` → npm
- `pypi.org` or `files.pythonhosted.org` → pypi
- `repo1.maven.org` or contains `/maven2/` → maven
- `registry-1.docker.io` or `docker.io` → docker
- Otherwise → generic
- [ ] Package/version extraction from URL patterns:
- npm: `/{package}/-/{package}-{version}.tgz`
- pypi: `/packages/.../requests-{version}.tar.gz`
- maven: `/{group}/{artifact}/{version}/{artifact}-{version}.jar`
- [ ] Add `cache_artifact()` function to `orchard/api.py`
- [ ] Integration with `--add` flag:
- Parse existing orchard.ensure
- Add new dependency entry pointing to cached artifact
- Use artifact_id (SHA256) for hermetic pinning
- [ ] Batch mode: `orchard cache --file urls.txt`
- One URL per line
- Lines starting with `#` are comments
- Report success/failure for each
- [ ] Exit codes:
- 0: Success (or already cached)
- 1: Fetch failed
- 2: Hash mismatch
- 3: Air-gap mode blocked request
- [ ] Error handling consistent with existing CLI patterns
- [ ] Unit tests in `test/test_cache.py`
- [ ] Update README.md with cache command documentation
## Technical Notes
- Follow existing Click patterns from other commands
- Use `get_auth_headers()` from `orchard/auth.py`
- URL parsing can use `urllib.parse`
- Consider adding URL pattern registry for extensibility
- The `--add` flag should integrate with existing ensure file parsing in `orchard/ensure.py`
## Example Workflows
```bash
# Simple: cache a single URL
orchard cache https://registry.npmjs.org/lodash/-/lodash-4.17.21.tgz
# Cache and add to orchard.ensure for current project
orchard cache https://registry.npmjs.org/lodash/-/lodash-4.17.21.tgz \
--add --add-path libs/lodash/
# Cache with explicit metadata
orchard cache https://internal.corp/files/custom-lib.tar.gz \
--type generic \
--package custom-lib \
--tag v1.0.0
# Cache and cross-reference to user project
orchard cache https://registry.npmjs.org/lodash/-/lodash-4.17.21.tgz \
--project my-app \
--user-package npm-deps \
--user-tag lodash-4.17.21
# Batch cache from file
orchard cache --file deps-urls.txt
# Verify hash while caching
orchard cache https://example.com/file.tar.gz \
--expected-hash sha256:abc123...
```
---
## Out of Scope (Future Enhancements)
- Automatic transitive dependency resolution (client's responsibility)
- Lockfile parsing (`package-lock.json`, `requirements.txt`) - stretch goal for CLI
- Cache eviction policies (we cache forever by design)
- Mirroring/sync between Orchard instances
- Format-specific metadata extraction (npm package.json parsing, etc.)
## Success Criteria
- [ ] Can cache any URL and retrieve by SHA256 hash
- [ ] Cached artifacts persist indefinitely
- [ ] Air-gap mode blocks all public internet access
- [ ] Multiple upstream sources with different auth
- [ ] System projects organize cached packages by format
- [ ] CLI can cache URLs and update orchard.ensure
- [ ] Admin UI for upstream source management

View File

@@ -1,228 +0,0 @@
# PyPI Proxy Performance & Multi-Protocol Architecture Design
**Date:** 2026-02-04
**Status:** Approved
**Branch:** fix/pypi-proxy-timeout
## Overview
Comprehensive infrastructure overhaul to address latency, throughput, and resource consumption issues in the PyPI proxy, while establishing a foundation for npm, Maven, and other package protocols.
## Goals
1. **Reduce latency** - Eliminate per-request connection overhead, cache aggressively
2. **Increase throughput** - Handle hundreds of concurrent requests without degradation
3. **Lower resource usage** - Connection pooling, efficient DB queries, proper async I/O
4. **Enable multi-protocol** - Abstract base class ready for npm/Maven/etc.
5. **Maintain hermetic builds** - Immutable artifact content and metadata, mutable discovery data
## Architecture
```
┌─────────────────────────────────────────────────────────────────────┐
│ FastAPI Application │
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
│ │ PyPI Proxy │ │ npm Proxy │ │ Maven Proxy │ │ (future) │ │
│ │ Router │ │ Router │ │ Router │ │ │ │
│ └──────┬──────┘ └──────┬──────┘ └──────┬──────┘ └─────────────┘ │
│ │ │ │ │
│ └────────────────┼────────────────┘ │
│ ▼ │
│ ┌───────────────────────┐ │
│ │ PackageProxyBase │ ← Abstract base class │
│ │ - check_cache() │ │
│ │ - fetch_upstream() │ │
│ │ - store_artifact() │ │
│ │ - serve_artifact() │ │
│ └───────────┬───────────┘ │
│ │ │
│ ┌────────────────┼────────────────┐ │
│ ▼ ▼ ▼ │
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
│ │ HttpClient │ │ CacheService│ │ ThreadPool │ │
│ │ Manager │ │ (Redis) │ │ Executor │ │
│ └─────────────┘ └─────────────┘ └─────────────┘ │
│ │ │ │ │
└─────────┼────────────────┼────────────────┼──────────────────────────┘
▼ ▼ ▼
┌──────────┐ ┌──────────┐ ┌──────────────┐
│ Upstream │ │ Redis │ │ S3/MinIO │
│ Sources │ │ │ │ │
└──────────┘ └──────────┘ └──────────────┘
```
## Components
### 1. HttpClientManager
Manages httpx.AsyncClient pools with FastAPI lifespan integration.
**Features:**
- Default pool for general requests
- Per-upstream pools for sources needing specific config/auth
- Graceful shutdown drains in-flight requests
- Dedicated thread pool for blocking operations
**Configuration:**
```bash
ORCHARD_HTTP_MAX_CONNECTIONS=100 # Default pool size
ORCHARD_HTTP_KEEPALIVE_CONNECTIONS=20 # Keep-alive connections
ORCHARD_HTTP_CONNECT_TIMEOUT=30 # Connection timeout (seconds)
ORCHARD_HTTP_READ_TIMEOUT=60 # Read timeout (seconds)
ORCHARD_HTTP_WORKER_THREADS=32 # Thread pool size
```
**File:** `backend/app/http_client.py`
### 2. CacheService (Redis Layer)
Redis-backed caching with category-aware TTL and invalidation.
**Cache Categories:**
| Category | TTL | Invalidation | Purpose |
|----------|-----|--------------|---------|
| ARTIFACT_METADATA | Forever | Never (immutable) | Artifact info by SHA256 |
| ARTIFACT_DEPENDENCIES | Forever | Never (immutable) | Extracted deps by SHA256 |
| DEPENDENCY_RESOLUTION | Forever | Manual/refresh param | Resolution results |
| UPSTREAM_SOURCES | 1 hour | On DB change | Upstream config |
| PACKAGE_INDEX | 5 min | TTL only | PyPI/npm index pages |
| PACKAGE_VERSIONS | 5 min | TTL only | Version listings |
**Key format:** `orchard:{category}:{protocol}:{identifier}`
**Configuration:**
```bash
ORCHARD_REDIS_HOST=redis
ORCHARD_REDIS_PORT=6379
ORCHARD_REDIS_DB=0
ORCHARD_CACHE_TTL_INDEX=300 # Package index: 5 minutes
ORCHARD_CACHE_TTL_VERSIONS=300 # Version listings: 5 minutes
ORCHARD_CACHE_TTL_UPSTREAM=3600 # Upstream config: 1 hour
```
**File:** `backend/app/cache_service.py`
### 3. PackageProxyBase
Abstract base class defining the cache→fetch→store→serve flow.
**Abstract methods (protocol-specific):**
- `get_protocol_name()` - Return 'pypi', 'npm', 'maven'
- `get_system_project_name()` - Return '_pypi', '_npm'
- `rewrite_index_html()` - Rewrite upstream index to Orchard URLs
- `extract_metadata()` - Extract deps from package file
- `parse_package_url()` - Parse URL into package/version/filename
**Concrete methods (shared):**
- `serve_index()` - Serve package index with caching
- `serve_artifact()` - Full cache→fetch→store→serve flow
**File:** `backend/app/proxy_base.py`
### 4. ArtifactRepository (DB Optimization)
Optimized database operations eliminating N+1 queries.
**Key methods:**
- `get_or_create_artifact()` - Atomic upsert via ON CONFLICT
- `batch_upsert_dependencies()` - Single INSERT for all deps
- `get_cached_url_with_artifact()` - Joined query for cache lookup
**Query reduction:**
| Operation | Before | After |
|-----------|--------|-------|
| Cache hit check | 2 queries | 1 query (joined) |
| Store artifact | 3-4 queries | 1 query (upsert) |
| Store 50 deps | 50+ queries | 1 query (batch) |
**Configuration:**
```bash
ORCHARD_DATABASE_POOL_SIZE=20 # Base connections (up from 5)
ORCHARD_DATABASE_MAX_OVERFLOW=30 # Burst capacity (up from 10)
ORCHARD_DATABASE_POOL_TIMEOUT=30 # Wait timeout
ORCHARD_DATABASE_POOL_PRE_PING=false # Disable in prod for performance
```
**File:** `backend/app/db_utils.py`
### 5. Dependency Resolution Caching
Cache resolution results for ensure files and API queries.
**Cache key:** Hash of (artifact_id, max_depth, include_optional)
**Invalidation:** Manual only (immutable artifact deps mean cached resolutions stay valid)
**Refresh:** `?refresh=true` parameter forces fresh resolution
**File:** Updates to `backend/app/dependencies.py`
### 6. FastAPI Integration
Lifespan-managed infrastructure with dependency injection.
**Startup:**
1. Initialize HttpClientManager (connection pools)
2. Initialize CacheService (Redis connection)
3. Load upstream source configs
**Shutdown:**
1. Drain in-flight HTTP requests
2. Close Redis connections
3. Shutdown thread pool
**Health endpoint additions:**
- Database connection status
- Redis ping
- HTTP pool active/max connections
- Thread pool active/max workers
**File:** Updates to `backend/app/main.py`
## Files Summary
**New files:**
- `backend/app/http_client.py` - HttpClientManager
- `backend/app/cache_service.py` - CacheService
- `backend/app/proxy_base.py` - PackageProxyBase
- `backend/app/db_utils.py` - ArtifactRepository
**Modified files:**
- `backend/app/config.py` - New settings
- `backend/app/main.py` - Lifespan integration
- `backend/app/pypi_proxy.py` - Refactor to use base class
- `backend/app/dependencies.py` - Resolution caching
- `backend/app/routes.py` - Health endpoint, DI
## Hermetic Build Guarantees
**Immutable (cached forever):**
- Artifact content (by SHA256)
- Extracted dependencies for a specific artifact
- Dependency resolution results
**Mutable (TTL + event invalidation):**
- Package index listings
- Version discovery
- Upstream source configuration
Once an artifact is cached with SHA256 `abc123` and dependencies extracted, that data never changes.
## Performance Expectations
| Metric | Before | After |
|--------|--------|-------|
| HTTP connection setup | Per request (~100-500ms) | Pooled (~5ms) |
| Cache hit (index page) | N/A | ~5ms (Redis) |
| Store 50 dependencies | ~500ms (50 queries) | ~10ms (1 query) |
| Dependency resolution (cached) | N/A | ~5ms |
| Concurrent request capacity | ~15 (DB pool) | ~50 (configurable) |
## Testing Requirements
- Unit tests for each new component
- Integration tests for full proxy flow
- Load tests to verify pool sizing
- Cache hit/miss verification tests

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -12,12 +12,9 @@
"test:coverage": "vitest run --coverage"
},
"dependencies": {
"@types/dagre": "^0.7.53",
"dagre": "^0.8.5",
"react": "^18.2.0",
"react-dom": "^18.2.0",
"react-router-dom": "6.28.0",
"reactflow": "^11.11.4"
"react-router-dom": "6.28.0"
},
"devDependencies": {
"@testing-library/jest-dom": "^6.4.2",
@@ -37,15 +34,6 @@
"ufo": "1.5.4",
"rollup": "4.52.4",
"caniuse-lite": "1.0.30001692",
"baseline-browser-mapping": "2.9.5",
"lodash": "4.17.21",
"electron-to-chromium": "1.5.72",
"@babel/core": "7.26.0",
"@babel/traverse": "7.26.4",
"@babel/types": "7.26.3",
"@babel/compat-data": "7.26.3",
"@babel/parser": "7.26.3",
"@babel/generator": "7.26.3",
"@babel/code-frame": "7.26.2"
"baseline-browser-mapping": "2.9.5"
}
}

View File

@@ -11,7 +11,6 @@ import ChangePasswordPage from './pages/ChangePasswordPage';
import APIKeysPage from './pages/APIKeysPage';
import AdminUsersPage from './pages/AdminUsersPage';
import AdminOIDCPage from './pages/AdminOIDCPage';
import AdminCachePage from './pages/AdminCachePage';
import ProjectSettingsPage from './pages/ProjectSettingsPage';
import TeamsPage from './pages/TeamsPage';
import TeamDashboardPage from './pages/TeamDashboardPage';
@@ -51,7 +50,6 @@ function AppRoutes() {
<Route path="/settings/api-keys" element={<APIKeysPage />} />
<Route path="/admin/users" element={<AdminUsersPage />} />
<Route path="/admin/oidc" element={<AdminOIDCPage />} />
<Route path="/admin/cache" element={<AdminCachePage />} />
<Route path="/teams" element={<TeamsPage />} />
<Route path="/teams/:slug" element={<TeamDashboardPage />} />
<Route path="/teams/:slug/settings" element={<TeamSettingsPage />} />

View File

@@ -1,11 +1,14 @@
import {
Project,
Package,
Tag,
TagDetail,
Artifact,
ArtifactDetail,
PackageArtifact,
UploadResponse,
PaginatedResponse,
ListParams,
TagListParams,
PackageListParams,
ArtifactListParams,
ProjectListParams,
@@ -39,10 +42,6 @@ import {
TeamUpdate,
TeamMemberCreate,
TeamMemberUpdate,
UpstreamSource,
UpstreamSourceCreate,
UpstreamSourceUpdate,
UpstreamSourceTestResult,
} from './types';
const API_BASE = '/api/v1';
@@ -75,13 +74,7 @@ export class ForbiddenError extends ApiError {
async function handleResponse<T>(response: Response): Promise<T> {
if (!response.ok) {
const error = await response.json().catch(() => ({ detail: 'Unknown error' }));
// Handle detail as string or object (backend may return structured errors)
let message: string;
if (typeof error.detail === 'object') {
message = JSON.stringify(error.detail);
} else {
message = error.detail || `HTTP ${response.status}`;
}
const message = error.detail || `HTTP ${response.status}`;
if (response.status === 401) {
throw new UnauthorizedError(message);
@@ -237,6 +230,32 @@ export async function createPackage(projectName: string, data: { name: string; d
return handleResponse<Package>(response);
}
// Tag API
export async function listTags(projectName: string, packageName: string, params: TagListParams = {}): Promise<PaginatedResponse<TagDetail>> {
const query = buildQueryString(params as Record<string, unknown>);
const response = await fetch(`${API_BASE}/project/${projectName}/${packageName}/tags${query}`);
return handleResponse<PaginatedResponse<TagDetail>>(response);
}
export async function listTagsSimple(projectName: string, packageName: string, params: TagListParams = {}): Promise<TagDetail[]> {
const data = await listTags(projectName, packageName, params);
return data.items;
}
export async function getTag(projectName: string, packageName: string, tagName: string): Promise<TagDetail> {
const response = await fetch(`${API_BASE}/project/${projectName}/${packageName}/tags/${tagName}`);
return handleResponse<TagDetail>(response);
}
export async function createTag(projectName: string, packageName: string, data: { name: string; artifact_id: string }): Promise<Tag> {
const response = await fetch(`${API_BASE}/project/${projectName}/${packageName}/tags`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify(data),
});
return handleResponse<Tag>(response);
}
// Artifact API
export async function getArtifact(artifactId: string): Promise<ArtifactDetail> {
const response = await fetch(`${API_BASE}/artifact/${artifactId}`);
@@ -247,10 +266,10 @@ export async function listPackageArtifacts(
projectName: string,
packageName: string,
params: ArtifactListParams = {}
): Promise<PaginatedResponse<PackageArtifact>> {
): Promise<PaginatedResponse<Artifact & { tags: string[] }>> {
const query = buildQueryString(params as Record<string, unknown>);
const response = await fetch(`${API_BASE}/project/${projectName}/${packageName}/artifacts${query}`);
return handleResponse<PaginatedResponse<PackageArtifact>>(response);
return handleResponse<PaginatedResponse<Artifact & { tags: string[] }>>(response);
}
// Upload
@@ -258,10 +277,14 @@ export async function uploadArtifact(
projectName: string,
packageName: string,
file: File,
tag?: string,
version?: string
): Promise<UploadResponse> {
const formData = new FormData();
formData.append('file', file);
if (tag) {
formData.append('tag', tag);
}
if (version) {
formData.append('version', version);
}
@@ -659,64 +682,3 @@ export async function searchUsers(query: string, limit: number = 10): Promise<Us
});
return handleResponse<UserSearchResult[]>(response);
}
// Upstream Sources Admin API
export interface UpstreamSourceListParams {
enabled?: boolean;
source_type?: string;
}
export async function listUpstreamSources(params: UpstreamSourceListParams = {}): Promise<UpstreamSource[]> {
const query = buildQueryString(params as Record<string, unknown>);
const response = await fetch(`${API_BASE}/admin/upstream-sources${query}`, {
credentials: 'include',
});
return handleResponse<UpstreamSource[]>(response);
}
export async function createUpstreamSource(data: UpstreamSourceCreate): Promise<UpstreamSource> {
const response = await fetch(`${API_BASE}/admin/upstream-sources`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify(data),
credentials: 'include',
});
return handleResponse<UpstreamSource>(response);
}
export async function getUpstreamSource(id: string): Promise<UpstreamSource> {
const response = await fetch(`${API_BASE}/admin/upstream-sources/${id}`, {
credentials: 'include',
});
return handleResponse<UpstreamSource>(response);
}
export async function updateUpstreamSource(id: string, data: UpstreamSourceUpdate): Promise<UpstreamSource> {
const response = await fetch(`${API_BASE}/admin/upstream-sources/${id}`, {
method: 'PUT',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify(data),
credentials: 'include',
});
return handleResponse<UpstreamSource>(response);
}
export async function deleteUpstreamSource(id: string): Promise<void> {
const response = await fetch(`${API_BASE}/admin/upstream-sources/${id}`, {
method: 'DELETE',
credentials: 'include',
});
if (!response.ok) {
const error = await response.json().catch(() => ({ detail: 'Unknown error' }));
throw new ApiError(error.detail || `HTTP ${response.status}`, response.status);
}
}
export async function testUpstreamSource(id: string): Promise<UpstreamSourceTestResult> {
const response = await fetch(`${API_BASE}/admin/upstream-sources/${id}/test`, {
method: 'POST',
credentials: 'include',
});
return handleResponse<UpstreamSourceTestResult>(response);
}

View File

@@ -55,10 +55,6 @@
font-size: 0.8125rem;
}
.missing-count {
color: #f59e0b;
}
.close-btn {
background: transparent;
border: none;
@@ -76,115 +72,171 @@
color: var(--text-primary);
}
.dependency-graph-toolbar {
display: flex;
align-items: center;
gap: 8px;
padding: 12px 20px;
border-bottom: 1px solid var(--border-primary);
background: var(--bg-secondary);
}
.zoom-level {
margin-left: auto;
font-size: 0.8125rem;
color: var(--text-muted);
font-family: 'JetBrains Mono', monospace;
}
.dependency-graph-container {
flex: 1;
overflow: hidden;
position: relative;
background: var(--bg-primary);
background:
linear-gradient(90deg, var(--border-primary) 1px, transparent 1px),
linear-gradient(var(--border-primary) 1px, transparent 1px);
background-size: 20px 20px;
background-position: center center;
}
/* React Flow Customization */
.react-flow__background {
background-color: var(--bg-primary) !important;
.graph-canvas {
padding: 40px;
min-width: 100%;
min-height: 100%;
transform-origin: center center;
transition: transform 0.1s ease-out;
}
.react-flow__controls {
background: var(--bg-tertiary);
border: 1px solid var(--border-primary);
border-radius: var(--radius-md);
box-shadow: 0 4px 12px rgba(0, 0, 0, 0.3);
/* Graph Nodes */
.graph-node-container {
display: flex;
flex-direction: column;
align-items: flex-start;
}
.react-flow__controls-button {
background: var(--bg-tertiary);
border: none;
border-bottom: 1px solid var(--border-primary);
color: var(--text-secondary);
width: 28px;
height: 28px;
}
.react-flow__controls-button:hover {
background: var(--bg-hover);
color: var(--text-primary);
}
.react-flow__controls-button:last-child {
border-bottom: none;
}
.react-flow__controls-button svg {
fill: currentColor;
}
.react-flow__attribution {
background: transparent !important;
}
.react-flow__attribution a {
color: var(--text-muted) !important;
font-size: 10px;
}
/* Custom Flow Nodes */
.flow-node {
.graph-node {
background: var(--bg-tertiary);
border: 2px solid var(--border-primary);
border-radius: var(--radius-md);
padding: 12px 16px;
min-width: 160px;
min-width: 200px;
cursor: pointer;
transition: all var(--transition-fast);
text-align: center;
position: relative;
}
.flow-node:hover {
.graph-node:hover {
border-color: var(--accent-primary);
box-shadow: 0 4px 12px rgba(16, 185, 129, 0.2);
}
.flow-node--root {
.graph-node--root {
background: linear-gradient(135deg, rgba(16, 185, 129, 0.15) 0%, rgba(5, 150, 105, 0.15) 100%);
border-color: var(--accent-primary);
}
.flow-node__name {
.graph-node--hovered {
transform: scale(1.02);
}
.graph-node__header {
display: flex;
align-items: center;
gap: 8px;
margin-bottom: 4px;
}
.graph-node__name {
font-weight: 600;
color: var(--accent-primary);
font-family: 'JetBrains Mono', monospace;
font-size: 0.8125rem;
margin-bottom: 4px;
word-break: break-word;
font-size: 0.875rem;
}
.flow-node__details {
.graph-node__toggle {
background: var(--bg-hover);
border: 1px solid var(--border-primary);
border-radius: 4px;
width: 20px;
height: 20px;
display: flex;
align-items: center;
justify-content: center;
gap: 8px;
font-size: 0.6875rem;
cursor: pointer;
font-size: 0.875rem;
color: var(--text-secondary);
font-weight: 600;
margin-left: auto;
}
.graph-node__toggle:hover {
background: var(--bg-tertiary);
color: var(--text-primary);
}
.graph-node__details {
display: flex;
align-items: center;
gap: 12px;
font-size: 0.75rem;
color: var(--text-muted);
}
.flow-node__version {
.graph-node__version {
font-family: 'JetBrains Mono', monospace;
color: var(--text-secondary);
}
.flow-node__size {
.graph-node__size {
color: var(--text-muted);
}
/* Flow Handles (connection points) */
.flow-handle {
width: 8px !important;
height: 8px !important;
background: var(--border-primary) !important;
border: 2px solid var(--bg-tertiary) !important;
/* Graph Children / Tree Structure */
.graph-children {
display: flex;
padding-left: 24px;
margin-top: 8px;
position: relative;
}
.flow-node:hover .flow-handle {
background: var(--accent-primary) !important;
.graph-connector {
position: absolute;
left: 12px;
top: 0;
bottom: 50%;
width: 12px;
border-left: 2px solid var(--border-primary);
border-bottom: 2px solid var(--border-primary);
border-bottom-left-radius: 8px;
}
.graph-children-list {
display: flex;
flex-direction: column;
gap: 8px;
position: relative;
}
.graph-children-list::before {
content: '';
position: absolute;
left: -12px;
top: 20px;
bottom: 20px;
border-left: 2px solid var(--border-primary);
}
.graph-children-list > .graph-node-container {
position: relative;
}
.graph-children-list > .graph-node-container::before {
content: '';
position: absolute;
left: -12px;
top: 20px;
width: 12px;
border-top: 2px solid var(--border-primary);
}
/* Loading, Error, Empty States */
@@ -227,61 +279,39 @@
line-height: 1.5;
}
/* Missing Dependencies */
.missing-dependencies {
border-top: 1px solid var(--border-primary);
padding: 16px 20px;
background: rgba(245, 158, 11, 0.05);
max-height: 200px;
overflow-y: auto;
}
.missing-dependencies h3 {
margin: 0 0 8px 0;
font-size: 0.875rem;
font-weight: 600;
color: #f59e0b;
}
.missing-hint {
margin: 0 0 12px 0;
font-size: 0.75rem;
color: var(--text-muted);
}
.missing-list {
list-style: none;
padding: 0;
margin: 0;
display: flex;
flex-wrap: wrap;
gap: 8px;
}
.missing-item {
display: inline-flex;
align-items: center;
gap: 4px;
/* Tooltip */
.graph-tooltip {
position: fixed;
bottom: 24px;
left: 50%;
transform: translateX(-50%);
background: var(--bg-tertiary);
border: 1px solid rgba(245, 158, 11, 0.3);
border-radius: var(--radius-sm);
padding: 4px 8px;
font-size: 0.75rem;
border: 1px solid var(--border-primary);
border-radius: var(--radius-md);
padding: 12px 16px;
font-size: 0.8125rem;
box-shadow: 0 8px 24px rgba(0, 0, 0, 0.4);
z-index: 1001;
}
.missing-name {
.graph-tooltip strong {
display: block;
color: var(--accent-primary);
font-family: 'JetBrains Mono', monospace;
margin-bottom: 4px;
}
.graph-tooltip div {
color: var(--text-secondary);
margin-top: 2px;
}
.missing-constraint {
.tooltip-hint {
margin-top: 8px;
padding-top: 8px;
border-top: 1px solid var(--border-primary);
color: var(--text-muted);
font-family: 'JetBrains Mono', monospace;
}
.missing-required-by {
color: var(--text-muted);
font-size: 0.6875rem;
font-size: 0.75rem;
}
/* Responsive */

View File

@@ -1,19 +1,5 @@
import { useState, useEffect, useCallback, useMemo } from 'react';
import { useState, useEffect, useCallback, useRef } from 'react';
import { useNavigate } from 'react-router-dom';
import ReactFlow, {
Node,
Edge,
Controls,
Background,
useNodesState,
useEdgesState,
MarkerType,
NodeProps,
Handle,
Position,
} from 'reactflow';
import dagre from 'dagre';
import 'reactflow/dist/style.css';
import { ResolvedArtifact, DependencyResolutionResponse, Dependency } from '../types';
import { resolveDependencies, getArtifactDependencies } from '../api';
import './DependencyGraph.css';
@@ -25,14 +11,15 @@ interface DependencyGraphProps {
onClose: () => void;
}
interface NodeData {
label: string;
interface GraphNode {
id: string;
project: string;
package: string;
version: string | null;
size: number;
isRoot: boolean;
onNavigate: (project: string, pkg: string) => void;
depth: number;
children: GraphNode[];
isRoot?: boolean;
}
function formatBytes(bytes: number): string {
@@ -43,89 +30,29 @@ function formatBytes(bytes: number): string {
return parseFloat((bytes / Math.pow(k, i)).toFixed(1)) + ' ' + sizes[i];
}
// Custom node component
function DependencyNode({ data }: NodeProps<NodeData>) {
return (
<div
className={`flow-node ${data.isRoot ? 'flow-node--root' : ''}`}
onClick={() => data.onNavigate(data.project, data.package)}
>
<Handle type="target" position={Position.Top} className="flow-handle" />
<div className="flow-node__name">{data.package}</div>
<div className="flow-node__details">
{data.version && <span className="flow-node__version">{data.version}</span>}
<span className="flow-node__size">{formatBytes(data.size)}</span>
</div>
<Handle type="source" position={Position.Bottom} className="flow-handle" />
</div>
);
}
const nodeTypes = { dependency: DependencyNode };
// Dagre layout function
function getLayoutedElements(
nodes: Node<NodeData>[],
edges: Edge[],
direction: 'TB' | 'LR' = 'TB'
) {
const dagreGraph = new dagre.graphlib.Graph();
dagreGraph.setDefaultEdgeLabel(() => ({}));
const nodeWidth = 180;
const nodeHeight = 60;
dagreGraph.setGraph({ rankdir: direction, nodesep: 50, ranksep: 80 });
nodes.forEach((node) => {
dagreGraph.setNode(node.id, { width: nodeWidth, height: nodeHeight });
});
edges.forEach((edge) => {
dagreGraph.setEdge(edge.source, edge.target);
});
dagre.layout(dagreGraph);
const layoutedNodes = nodes.map((node) => {
const nodeWithPosition = dagreGraph.node(node.id);
return {
...node,
position: {
x: nodeWithPosition.x - nodeWidth / 2,
y: nodeWithPosition.y - nodeHeight / 2,
},
};
});
return { nodes: layoutedNodes, edges };
}
function DependencyGraph({ projectName, packageName, tagName, onClose }: DependencyGraphProps) {
const navigate = useNavigate();
const containerRef = useRef<HTMLDivElement>(null);
const [loading, setLoading] = useState(true);
const [error, setError] = useState<string | null>(null);
const [resolution, setResolution] = useState<DependencyResolutionResponse | null>(null);
const [nodes, setNodes, onNodesChange] = useNodesState<NodeData>([]);
const [edges, setEdges, onEdgesChange] = useEdgesState([]);
const handleNavigate = useCallback((project: string, pkg: string) => {
navigate(`/project/${project}/${pkg}`);
onClose();
}, [navigate, onClose]);
const [graphRoot, setGraphRoot] = useState<GraphNode | null>(null);
const [hoveredNode, setHoveredNode] = useState<GraphNode | null>(null);
const [zoom, setZoom] = useState(1);
const [pan, setPan] = useState({ x: 0, y: 0 });
const [isDragging, setIsDragging] = useState(false);
const [dragStart, setDragStart] = useState({ x: 0, y: 0 });
const [collapsedNodes, setCollapsedNodes] = useState<Set<string>>(new Set());
// Build graph structure from resolution data
const buildFlowGraph = useCallback(async (
resolutionData: DependencyResolutionResponse,
onNavigate: (project: string, pkg: string) => void
) => {
const buildGraph = useCallback(async (resolutionData: DependencyResolutionResponse) => {
const artifactMap = new Map<string, ResolvedArtifact>();
resolutionData.resolved.forEach(artifact => {
artifactMap.set(artifact.artifact_id, artifact);
});
// Fetch dependencies for each artifact
// Fetch dependencies for each artifact to build the tree
const depsMap = new Map<string, Dependency[]>();
for (const artifact of resolutionData.resolved) {
@@ -137,82 +64,50 @@ function DependencyGraph({ projectName, packageName, tagName, onClose }: Depende
}
}
// Find the root artifact
// Find the root artifact (the requested one)
const rootArtifact = resolutionData.resolved.find(
a => a.project === resolutionData.requested.project &&
a.package === resolutionData.requested.package
);
if (!rootArtifact) {
return { nodes: [], edges: [] };
return null;
}
const flowNodes: Node<NodeData>[] = [];
const flowEdges: Edge[] = [];
// Build tree recursively
const visited = new Set<string>();
const nodeIdMap = new Map<string, string>(); // artifact_id -> node id
// Build nodes and edges recursively
const processNode = (artifact: ResolvedArtifact, isRoot: boolean) => {
if (visited.has(artifact.artifact_id)) {
return nodeIdMap.get(artifact.artifact_id);
}
const buildNode = (artifact: ResolvedArtifact, depth: number): GraphNode => {
const nodeId = `${artifact.project}/${artifact.package}`;
visited.add(artifact.artifact_id);
const nodeId = `node-${flowNodes.length}`;
nodeIdMap.set(artifact.artifact_id, nodeId);
flowNodes.push({
id: nodeId,
type: 'dependency',
position: { x: 0, y: 0 }, // Will be set by dagre
data: {
label: `${artifact.project}/${artifact.package}`,
project: artifact.project,
package: artifact.package,
version: artifact.version,
size: artifact.size,
isRoot,
onNavigate,
},
});
const deps = depsMap.get(artifact.artifact_id) || [];
const children: GraphNode[] = [];
for (const dep of deps) {
// Find the resolved artifact for this dependency
const childArtifact = resolutionData.resolved.find(
a => a.project === dep.project && a.package === dep.package
);
if (childArtifact) {
const childNodeId = processNode(childArtifact, false);
if (childNodeId) {
flowEdges.push({
id: `edge-${nodeId}-${childNodeId}`,
source: nodeId,
target: childNodeId,
markerEnd: {
type: MarkerType.ArrowClosed,
width: 15,
height: 15,
color: 'var(--accent-primary)',
},
style: {
stroke: 'var(--border-primary)',
strokeWidth: 2,
},
});
}
if (childArtifact && !visited.has(childArtifact.artifact_id)) {
children.push(buildNode(childArtifact, depth + 1));
}
}
return nodeId;
return {
id: nodeId,
project: artifact.project,
package: artifact.package,
version: artifact.version || artifact.tag,
size: artifact.size,
depth,
children,
isRoot: depth === 0,
};
};
processNode(rootArtifact, true);
// Apply dagre layout
return getLayoutedElements(flowNodes, flowEdges);
return buildNode(rootArtifact, 0);
}, []);
useEffect(() => {
@@ -222,21 +117,13 @@ function DependencyGraph({ projectName, packageName, tagName, onClose }: Depende
try {
const result = await resolveDependencies(projectName, packageName, tagName);
// If only the root package (no dependencies) and no missing deps, close the modal
const hasDeps = result.artifact_count > 1 || (result.missing && result.missing.length > 0);
if (!hasDeps) {
onClose();
return;
}
setResolution(result);
const { nodes: layoutedNodes, edges: layoutedEdges } = await buildFlowGraph(result, handleNavigate);
setNodes(layoutedNodes);
setEdges(layoutedEdges);
const graph = await buildGraph(result);
setGraphRoot(graph);
} catch (err) {
if (err instanceof Error) {
// Check if it's a resolution error
try {
const errorData = JSON.parse(err.message);
if (errorData.error === 'circular_dependency') {
@@ -258,9 +145,95 @@ function DependencyGraph({ projectName, packageName, tagName, onClose }: Depende
}
loadData();
}, [projectName, packageName, tagName, buildFlowGraph, handleNavigate, onClose, setNodes, setEdges]);
}, [projectName, packageName, tagName, buildGraph]);
const defaultViewport = useMemo(() => ({ x: 50, y: 50, zoom: 0.8 }), []);
const handleNodeClick = (node: GraphNode) => {
navigate(`/project/${node.project}/${node.package}`);
onClose();
};
const handleNodeToggle = (node: GraphNode, e: React.MouseEvent) => {
e.stopPropagation();
setCollapsedNodes(prev => {
const next = new Set(prev);
if (next.has(node.id)) {
next.delete(node.id);
} else {
next.add(node.id);
}
return next;
});
};
const handleWheel = (e: React.WheelEvent) => {
e.preventDefault();
const delta = e.deltaY > 0 ? -0.1 : 0.1;
setZoom(z => Math.max(0.25, Math.min(2, z + delta)));
};
const handleMouseDown = (e: React.MouseEvent) => {
if (e.target === containerRef.current || (e.target as HTMLElement).classList.contains('graph-canvas')) {
setIsDragging(true);
setDragStart({ x: e.clientX - pan.x, y: e.clientY - pan.y });
}
};
const handleMouseMove = (e: React.MouseEvent) => {
if (isDragging) {
setPan({ x: e.clientX - dragStart.x, y: e.clientY - dragStart.y });
}
};
const handleMouseUp = () => {
setIsDragging(false);
};
const resetView = () => {
setZoom(1);
setPan({ x: 0, y: 0 });
};
const renderNode = (node: GraphNode, index: number = 0): JSX.Element => {
const isCollapsed = collapsedNodes.has(node.id);
const hasChildren = node.children.length > 0;
return (
<div key={`${node.id}-${index}`} className="graph-node-container">
<div
className={`graph-node ${node.isRoot ? 'graph-node--root' : ''} ${hoveredNode?.id === node.id ? 'graph-node--hovered' : ''}`}
onClick={() => handleNodeClick(node)}
onMouseEnter={() => setHoveredNode(node)}
onMouseLeave={() => setHoveredNode(null)}
>
<div className="graph-node__header">
<span className="graph-node__name">{node.project}/{node.package}</span>
{hasChildren && (
<button
className="graph-node__toggle"
onClick={(e) => handleNodeToggle(node, e)}
title={isCollapsed ? 'Expand' : 'Collapse'}
>
{isCollapsed ? '+' : '-'}
</button>
)}
</div>
<div className="graph-node__details">
{node.version && <span className="graph-node__version">@ {node.version}</span>}
<span className="graph-node__size">{formatBytes(node.size)}</span>
</div>
</div>
{hasChildren && !isCollapsed && (
<div className="graph-children">
<div className="graph-connector"></div>
<div className="graph-children-list">
{node.children.map((child, i) => renderNode(child, i))}
</div>
</div>
)}
</div>
);
};
return (
<div className="dependency-graph-modal" onClick={onClose}>
@@ -271,11 +244,7 @@ function DependencyGraph({ projectName, packageName, tagName, onClose }: Depende
<span>{projectName}/{packageName} @ {tagName}</span>
{resolution && (
<span className="graph-stats">
{resolution.artifact_count} cached
{resolution.missing && resolution.missing.length > 0 && (
<span className="missing-count"> {resolution.missing.length} not cached</span>
)}
{formatBytes(resolution.total_size)} total
{resolution.artifact_count} packages {formatBytes(resolution.total_size)} total
</span>
)}
</div>
@@ -287,7 +256,28 @@ function DependencyGraph({ projectName, packageName, tagName, onClose }: Depende
</button>
</div>
<div className="dependency-graph-container">
<div className="dependency-graph-toolbar">
<button className="btn btn-secondary btn-small" onClick={() => setZoom(z => Math.min(2, z + 0.25))}>
Zoom In
</button>
<button className="btn btn-secondary btn-small" onClick={() => setZoom(z => Math.max(0.25, z - 0.25))}>
Zoom Out
</button>
<button className="btn btn-secondary btn-small" onClick={resetView}>
Reset View
</button>
<span className="zoom-level">{Math.round(zoom * 100)}%</span>
</div>
<div
ref={containerRef}
className="dependency-graph-container"
onWheel={handleWheel}
onMouseDown={handleMouseDown}
onMouseMove={handleMouseMove}
onMouseUp={handleMouseUp}
onMouseLeave={handleMouseUp}
>
{loading ? (
<div className="graph-loading">
<div className="spinner"></div>
@@ -302,41 +292,27 @@ function DependencyGraph({ projectName, packageName, tagName, onClose }: Depende
</svg>
<p>{error}</p>
</div>
) : nodes.length > 0 ? (
<ReactFlow
nodes={nodes}
edges={edges}
onNodesChange={onNodesChange}
onEdgesChange={onEdgesChange}
nodeTypes={nodeTypes}
defaultViewport={defaultViewport}
fitView
fitViewOptions={{ padding: 0.2 }}
minZoom={0.1}
maxZoom={2}
attributionPosition="bottom-left"
) : graphRoot ? (
<div
className="graph-canvas"
style={{
transform: `translate(${pan.x}px, ${pan.y}px) scale(${zoom})`,
cursor: isDragging ? 'grabbing' : 'grab',
}}
>
<Controls />
<Background color="var(--border-primary)" gap={20} />
</ReactFlow>
{renderNode(graphRoot)}
</div>
) : (
<div className="graph-empty">No dependencies to display</div>
)}
</div>
{resolution && resolution.missing && resolution.missing.length > 0 && (
<div className="missing-dependencies">
<h3>Not Cached ({resolution.missing.length})</h3>
<p className="missing-hint">These dependencies are referenced but not yet cached on the server.</p>
<ul className="missing-list">
{resolution.missing.map((dep, i) => (
<li key={i} className="missing-item">
<span className="missing-name">{dep.project}/{dep.package}</span>
{dep.constraint && <span className="missing-constraint">@{dep.constraint}</span>}
{dep.required_by && <span className="missing-required-by"> {dep.required_by}</span>}
</li>
))}
</ul>
{hoveredNode && (
<div className="graph-tooltip">
<strong>{hoveredNode.project}/{hoveredNode.package}</strong>
{hoveredNode.version && <div>Version: {hoveredNode.version}</div>}
<div>Size: {formatBytes(hoveredNode.size)}</div>
<div className="tooltip-hint">Click to navigate</div>
</div>
)}
</div>

View File

@@ -290,25 +290,20 @@
color: var(--error-color, #dc3545);
}
/* Progress Bar - scoped to upload component */
.drag-drop-upload .progress-bar,
.upload-queue .progress-bar {
/* Progress Bar */
.progress-bar {
height: 8px;
background: var(--border-color, #ddd);
border-radius: 4px;
overflow: hidden;
width: 100%;
max-width: 100%;
}
.drag-drop-upload .progress-bar--small,
.upload-queue .progress-bar--small {
.progress-bar--small {
height: 4px;
margin-top: 0.25rem;
}
.drag-drop-upload .progress-bar__fill,
.upload-queue .progress-bar__fill {
.progress-bar__fill {
height: 100%;
background: var(--accent-color, #007bff);
border-radius: 4px;

View File

@@ -504,4 +504,42 @@ describe('DragDropUpload', () => {
});
});
});
describe('Tag Support', () => {
it('includes tag in upload request', async () => {
let capturedFormData: FormData | null = null;
class MockXHR {
status = 200;
responseText = JSON.stringify({ artifact_id: 'abc123', size: 100 });
timeout = 0;
upload = { addEventListener: vi.fn() };
addEventListener = vi.fn((event: string, handler: () => void) => {
if (event === 'load') setTimeout(handler, 10);
});
open = vi.fn();
send = vi.fn((data: FormData) => {
capturedFormData = data;
});
}
vi.stubGlobal('XMLHttpRequest', MockXHR);
render(<DragDropUpload {...defaultProps} tag="v1.0.0" />);
const input = document.querySelector('input[type="file"]') as HTMLInputElement;
const file = createMockFile('test.txt', 100, 'text/plain');
Object.defineProperty(input, 'files', {
value: Object.assign([file], { item: (i: number) => [file][i] }),
});
fireEvent.change(input);
await vi.advanceTimersByTimeAsync(100);
await waitFor(() => {
expect(capturedFormData?.get('tag')).toBe('v1.0.0');
});
});
});
});

View File

@@ -13,6 +13,7 @@ interface StoredUploadState {
completedParts: number[];
project: string;
package: string;
tag?: string;
createdAt: number;
}
@@ -86,6 +87,7 @@ export interface DragDropUploadProps {
maxFileSize?: number; // in bytes
maxConcurrentUploads?: number;
maxRetries?: number;
tag?: string;
className?: string;
disabled?: boolean;
disabledReason?: string;
@@ -228,6 +230,7 @@ export function DragDropUpload({
maxFileSize,
maxConcurrentUploads = 3,
maxRetries = 3,
tag,
className = '',
disabled = false,
disabledReason,
@@ -365,6 +368,7 @@ export function DragDropUpload({
expected_hash: fileHash,
filename: item.file.name,
size: item.file.size,
tag: tag || undefined,
}),
}
);
@@ -388,6 +392,7 @@ export function DragDropUpload({
completedParts: [],
project: projectName,
package: packageName,
tag: tag || undefined,
createdAt: Date.now(),
});
@@ -433,6 +438,7 @@ export function DragDropUpload({
completedParts,
project: projectName,
package: packageName,
tag: tag || undefined,
createdAt: Date.now(),
});
@@ -453,7 +459,7 @@ export function DragDropUpload({
{
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({}),
body: JSON.stringify({ tag: tag || undefined }),
}
);
@@ -469,15 +475,18 @@ export function DragDropUpload({
size: completeData.size,
deduplicated: false,
};
}, [projectName, packageName, isOnline]);
}, [projectName, packageName, tag, isOnline]);
const uploadFileSimple = useCallback((item: UploadItem): Promise<UploadResult> => {
return new Promise((resolve, reject) => {
const xhr = new XMLHttpRequest();
xhrMapRef.current.set(item.id, xhr);
const formData = new FormData();
formData.append('file', item.file);
if (tag) {
formData.append('tag', tag);
}
let lastLoaded = 0;
let lastTime = Date.now();
@@ -540,13 +549,13 @@ export function DragDropUpload({
xhr.timeout = 300000;
xhr.send(formData);
setUploadQueue(prev => prev.map(u =>
u.id === item.id
setUploadQueue(prev => prev.map(u =>
u.id === item.id
? { ...u, status: 'uploading' as UploadStatus, startTime: Date.now() }
: u
));
});
}, [projectName, packageName]);
}, [projectName, packageName, tag]);
const uploadFile = useCallback((item: UploadItem): Promise<UploadResult> => {
if (item.file.size >= CHUNKED_UPLOAD_THRESHOLD) {

View File

@@ -233,7 +233,7 @@ export function GlobalSearch() {
const flatIndex = results.projects.length + results.packages.length + index;
return (
<button
key={artifact.artifact_id}
key={artifact.tag_id}
className={`global-search__result ${selectedIndex === flatIndex ? 'selected' : ''}`}
onClick={() => navigateToResult({ type: 'artifact', item: artifact })}
onMouseEnter={() => setSelectedIndex(flatIndex)}
@@ -243,7 +243,7 @@ export function GlobalSearch() {
<line x1="7" y1="7" x2="7.01" y2="7" />
</svg>
<div className="global-search__result-content">
<span className="global-search__result-name">{artifact.version}</span>
<span className="global-search__result-name">{artifact.tag_name}</span>
<span className="global-search__result-path">
{artifact.project_name} / {artifact.package_name}
</span>

View File

@@ -272,7 +272,7 @@
.footer {
background: var(--bg-secondary);
border-top: 1px solid var(--border-primary);
padding: 12px 0;
padding: 24px 0;
}
.footer-content {

View File

@@ -84,6 +84,29 @@ function Layout({ children }: LayoutProps) {
</svg>
Projects
</Link>
<Link to="/dashboard" className={location.pathname === '/dashboard' ? 'active' : ''}>
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
<rect x="3" y="3" width="7" height="7" rx="1"/>
<rect x="14" y="3" width="7" height="7" rx="1"/>
<rect x="3" y="14" width="7" height="7" rx="1"/>
<rect x="14" y="14" width="7" height="7" rx="1"/>
</svg>
Dashboard
</Link>
{user && userTeams.length > 0 && (
<Link
to={userTeams.length === 1 ? `/teams/${userTeams[0].slug}` : '/teams'}
className={location.pathname.startsWith('/teams') ? 'active' : ''}
>
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
<path d="M17 21v-2a4 4 0 0 0-4-4H5a4 4 0 0 0-4 4v2"/>
<circle cx="9" cy="7" r="4"/>
<path d="M23 21v-2a4 4 0 0 0-3-3.87"/>
<path d="M16 3.13a4 4 0 0 1 0 7.75"/>
</svg>
{userTeams.length === 1 ? 'Team' : 'Teams'}
</Link>
)}
<a href="/docs" className="nav-link-muted">
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
<path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z"/>
@@ -125,35 +148,6 @@ function Layout({ children }: LayoutProps) {
)}
</div>
<div className="user-menu-divider"></div>
<NavLink
to="/dashboard"
className="user-menu-item"
onClick={() => setShowUserMenu(false)}
>
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
<rect x="3" y="3" width="7" height="7" rx="1"/>
<rect x="14" y="3" width="7" height="7" rx="1"/>
<rect x="3" y="14" width="7" height="7" rx="1"/>
<rect x="14" y="14" width="7" height="7" rx="1"/>
</svg>
Dashboard
</NavLink>
{userTeams.length > 0 && (
<NavLink
to={userTeams.length === 1 ? `/teams/${userTeams[0].slug}` : '/teams'}
className="user-menu-item"
onClick={() => setShowUserMenu(false)}
>
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
<path d="M17 21v-2a4 4 0 0 0-4-4H5a4 4 0 0 0-4 4v2"/>
<circle cx="9" cy="7" r="4"/>
<path d="M23 21v-2a4 4 0 0 0-3-3.87"/>
<path d="M16 3.13a4 4 0 0 1 0 7.75"/>
</svg>
{userTeams.length === 1 ? 'Team' : 'Teams'}
</NavLink>
)}
<div className="user-menu-divider"></div>
<NavLink
to="/settings/api-keys"
className="user-menu-item"
@@ -189,18 +183,6 @@ function Layout({ children }: LayoutProps) {
</svg>
SSO Configuration
</NavLink>
<NavLink
to="/admin/cache"
className="user-menu-item"
onClick={() => setShowUserMenu(false)}
>
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
<path d="M21 16V8a2 2 0 0 0-1-1.73l-7-4a2 2 0 0 0-2 0l-7 4A2 2 0 0 0 3 8v8a2 2 0 0 0 1 1.73l7 4a2 2 0 0 0 2 0l7-4A2 2 0 0 0 21 16z"/>
<polyline points="3.27 6.96 12 12.01 20.73 6.96"/>
<line x1="12" y1="22.08" x2="12" y2="12"/>
</svg>
Cache Management
</NavLink>
</>
)}
<div className="user-menu-divider"></div>
@@ -247,7 +229,7 @@ function Layout({ children }: LayoutProps) {
</svg>
<span className="footer-logo">Orchard</span>
<span className="footer-separator">·</span>
<span className="footer-tagline">The cache that never forgets</span>
<span className="footer-tagline">Content-Addressable Storage</span>
</div>
<div className="footer-links">
<a href="/docs">Documentation</a>

View File

@@ -1,377 +0,0 @@
.admin-cache-page {
padding: 2rem;
max-width: 1400px;
margin: 0 auto;
}
.admin-cache-page h1 {
margin-bottom: 2rem;
color: var(--text-primary);
}
.admin-cache-page h2 {
margin-bottom: 1rem;
color: var(--text-primary);
font-size: 1.25rem;
}
/* Success/Error Messages */
.success-message {
padding: 0.75rem 1rem;
background-color: #d4edda;
border: 1px solid #c3e6cb;
border-radius: 4px;
color: #155724;
margin-bottom: 1rem;
}
.error-message {
padding: 0.75rem 1rem;
background-color: #f8d7da;
border: 1px solid #f5c6cb;
border-radius: 4px;
color: #721c24;
margin-bottom: 1rem;
}
/* Sources Section */
.sources-section {
background: var(--bg-secondary);
border: 1px solid var(--border-color);
border-radius: 8px;
padding: 1.5rem;
}
.section-header {
display: flex;
justify-content: space-between;
align-items: center;
margin-bottom: 1rem;
}
.section-header h2 {
margin: 0;
}
/* Sources Table */
.sources-table {
width: 100%;
border-collapse: collapse;
background: var(--bg-primary);
border-radius: 4px;
overflow: hidden;
}
.sources-table th,
.sources-table td {
padding: 0.75rem 1rem;
text-align: center;
border-bottom: 1px solid var(--border-color);
}
.sources-table th {
background: var(--bg-tertiary);
font-weight: 600;
color: var(--text-secondary);
font-size: 0.85rem;
text-transform: uppercase;
}
.sources-table tr:last-child td {
border-bottom: none;
}
.sources-table tr.disabled-row {
opacity: 0.6;
}
.source-name {
font-weight: 500;
color: var(--text-primary);
white-space: nowrap;
}
/* Name column should be left-aligned */
.sources-table td:first-child {
text-align: left;
}
.url-cell {
font-family: monospace;
font-size: 0.9rem;
max-width: 300px;
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
text-align: left;
}
/* Badges */
.env-badge,
.status-badge {
display: inline-block;
padding: 0.2rem 0.5rem;
border-radius: 4px;
font-size: 0.75rem;
font-weight: 500;
margin-left: 0.5rem;
}
.env-badge {
background-color: #fff3e0;
color: #e65100;
}
.status-badge.enabled {
background-color: #e8f5e9;
color: #2e7d32;
}
.status-badge.disabled {
background-color: #ffebee;
color: #c62828;
}
.coming-soon-badge {
color: #9e9e9e;
font-style: italic;
font-size: 0.85em;
}
/* Actions */
.actions-cell {
white-space: nowrap;
}
.actions-cell .btn {
margin-right: 0.5rem;
}
.actions-cell .btn:last-child {
margin-right: 0;
}
.test-cell {
text-align: center;
width: 2rem;
}
.test-dot {
font-size: 1rem;
cursor: default;
}
.test-dot.success {
color: #2e7d32;
}
.test-dot.failure {
color: #c62828;
cursor: pointer;
}
.test-dot.failure:hover {
color: #b71c1c;
}
.test-dot.testing {
color: #1976d2;
animation: pulse 1s infinite;
}
@keyframes pulse {
0%, 100% { opacity: 1; }
50% { opacity: 0.4; }
}
/* Error Modal */
.error-modal-content {
background: var(--bg-primary);
border-radius: 8px;
padding: 2rem;
width: 100%;
max-width: 500px;
}
.error-modal-content h3 {
margin-top: 0;
color: #c62828;
}
.error-modal-content .error-details {
background: var(--bg-tertiary);
padding: 1rem;
border-radius: 4px;
font-family: monospace;
font-size: 0.9rem;
word-break: break-word;
white-space: pre-wrap;
}
.error-modal-content .modal-actions {
display: flex;
justify-content: flex-end;
margin-top: 1.5rem;
}
/* Buttons */
.btn {
padding: 0.5rem 1rem;
border: 1px solid var(--border-color);
border-radius: 4px;
background: var(--bg-primary);
color: var(--text-primary);
cursor: pointer;
font-size: 0.875rem;
}
.btn:hover {
background: var(--bg-tertiary);
}
.btn:disabled {
opacity: 0.6;
cursor: not-allowed;
}
.btn-primary {
background-color: var(--color-primary);
border-color: var(--color-primary);
color: white;
}
.btn-primary:hover {
background-color: var(--color-primary-hover);
}
.btn-danger {
background-color: #dc3545;
border-color: #dc3545;
color: white;
}
.btn-danger:hover {
background-color: #c82333;
}
.btn-sm {
padding: 0.25rem 0.75rem;
font-size: 0.8rem;
}
.btn-secondary {
background-color: var(--bg-tertiary);
border-color: var(--border-color);
color: var(--text-primary);
font-weight: 500;
}
.btn-secondary:hover {
background-color: var(--bg-secondary);
border-color: var(--text-secondary);
}
.empty-message {
color: var(--text-secondary);
font-style: italic;
padding: 2rem;
text-align: center;
}
/* Modal */
.modal-overlay {
position: fixed;
top: 0;
left: 0;
right: 0;
bottom: 0;
background: rgba(0, 0, 0, 0.5);
display: flex;
align-items: center;
justify-content: center;
z-index: 1000;
}
.modal-content {
background: var(--bg-primary);
border-radius: 8px;
padding: 2rem;
width: 100%;
max-width: 600px;
max-height: 90vh;
overflow-y: auto;
}
.modal-content h2 {
margin-top: 0;
}
/* Form */
.form-group {
margin-bottom: 1rem;
}
.form-group label {
display: block;
margin-bottom: 0.5rem;
font-weight: 500;
color: var(--text-primary);
}
.form-group input,
.form-group select {
width: 100%;
padding: 0.5rem;
border: 1px solid var(--border-color);
border-radius: 4px;
background: var(--bg-primary);
color: var(--text-primary);
font-size: 1rem;
}
.form-group input:focus,
.form-group select:focus {
outline: none;
border-color: var(--color-primary);
}
.form-row {
display: flex;
gap: 1rem;
}
.form-row .form-group {
flex: 1;
}
.checkbox-group label {
display: flex;
align-items: center;
gap: 0.5rem;
cursor: pointer;
}
.checkbox-group input[type="checkbox"] {
width: auto;
}
.help-text {
display: block;
font-size: 0.8rem;
color: var(--text-secondary);
margin-top: 0.25rem;
}
.form-actions {
display: flex;
justify-content: space-between;
align-items: center;
margin-top: 1.5rem;
padding-top: 1rem;
border-top: 1px solid var(--border-color);
}
.form-actions-right {
display: flex;
gap: 0.5rem;
}

View File

@@ -1,509 +0,0 @@
import { useState, useEffect } from 'react';
import { useNavigate } from 'react-router-dom';
import { useAuth } from '../contexts/AuthContext';
import {
listUpstreamSources,
createUpstreamSource,
updateUpstreamSource,
deleteUpstreamSource,
testUpstreamSource,
} from '../api';
import { UpstreamSource, SourceType, AuthType } from '../types';
import './AdminCachePage.css';
const SOURCE_TYPES: SourceType[] = ['npm', 'pypi', 'maven', 'docker', 'helm', 'nuget', 'deb', 'rpm', 'generic'];
const SUPPORTED_SOURCE_TYPES: Set<SourceType> = new Set(['pypi', 'generic']);
const AUTH_TYPES: AuthType[] = ['none', 'basic', 'bearer', 'api_key'];
function AdminCachePage() {
const { user, loading: authLoading } = useAuth();
const navigate = useNavigate();
// Upstream sources state
const [sources, setSources] = useState<UpstreamSource[]>([]);
const [loadingSources, setLoadingSources] = useState(true);
const [sourcesError, setSourcesError] = useState<string | null>(null);
// Create/Edit form state
const [showForm, setShowForm] = useState(false);
const [editingSource, setEditingSource] = useState<UpstreamSource | null>(null);
const [formData, setFormData] = useState({
name: '',
source_type: 'generic' as SourceType,
url: '',
enabled: true,
auth_type: 'none' as AuthType,
username: '',
password: '',
priority: 100,
});
const [formError, setFormError] = useState<string | null>(null);
const [isSaving, setIsSaving] = useState(false);
// Test result state
const [testingId, setTestingId] = useState<string | null>(null);
const [testResults, setTestResults] = useState<Record<string, { success: boolean; message: string }>>({});
// Delete confirmation state
const [deletingId, setDeletingId] = useState<string | null>(null);
// Success message
const [successMessage, setSuccessMessage] = useState<string | null>(null);
// Error modal state
const [showErrorModal, setShowErrorModal] = useState(false);
const [selectedError, setSelectedError] = useState<{ sourceName: string; error: string } | null>(null);
useEffect(() => {
if (!authLoading && !user) {
navigate('/login', { state: { from: '/admin/cache' } });
}
}, [user, authLoading, navigate]);
useEffect(() => {
if (user && user.is_admin) {
loadSources();
}
}, [user]);
useEffect(() => {
if (successMessage) {
const timer = setTimeout(() => setSuccessMessage(null), 3000);
return () => clearTimeout(timer);
}
}, [successMessage]);
async function loadSources() {
setLoadingSources(true);
setSourcesError(null);
try {
const data = await listUpstreamSources();
setSources(data);
} catch (err) {
setSourcesError(err instanceof Error ? err.message : 'Failed to load sources');
} finally {
setLoadingSources(false);
}
}
function openCreateForm() {
setEditingSource(null);
setFormData({
name: '',
source_type: 'generic',
url: '',
enabled: true,
auth_type: 'none',
username: '',
password: '',
priority: 100,
});
setFormError(null);
setShowForm(true);
}
function openEditForm(source: UpstreamSource) {
setEditingSource(source);
setFormData({
name: source.name,
source_type: source.source_type,
url: source.url,
enabled: source.enabled,
auth_type: source.auth_type,
username: source.username || '',
password: '',
priority: source.priority,
});
setFormError(null);
setShowForm(true);
}
async function handleFormSubmit(e: React.FormEvent) {
e.preventDefault();
if (!formData.name.trim()) {
setFormError('Name is required');
return;
}
if (!formData.url.trim()) {
setFormError('URL is required');
return;
}
setIsSaving(true);
setFormError(null);
try {
let savedSourceId: string | null = null;
if (editingSource) {
// Update existing source
await updateUpstreamSource(editingSource.id, {
name: formData.name.trim(),
source_type: formData.source_type,
url: formData.url.trim(),
enabled: formData.enabled,
auth_type: formData.auth_type,
username: formData.username.trim() || undefined,
password: formData.password || undefined,
priority: formData.priority,
});
savedSourceId = editingSource.id;
setSuccessMessage('Source updated successfully');
} else {
// Create new source
const newSource = await createUpstreamSource({
name: formData.name.trim(),
source_type: formData.source_type,
url: formData.url.trim(),
enabled: formData.enabled,
auth_type: formData.auth_type,
username: formData.username.trim() || undefined,
password: formData.password || undefined,
priority: formData.priority,
});
savedSourceId = newSource.id;
setSuccessMessage('Source created successfully');
}
setShowForm(false);
await loadSources();
// Auto-test the source after save
if (savedSourceId) {
testSourceById(savedSourceId);
}
} catch (err) {
setFormError(err instanceof Error ? err.message : 'Failed to save source');
} finally {
setIsSaving(false);
}
}
async function handleDelete(source: UpstreamSource) {
if (!window.confirm(`Delete upstream source "${source.name}"? This cannot be undone.`)) {
return;
}
setDeletingId(source.id);
try {
await deleteUpstreamSource(source.id);
setSuccessMessage(`Source "${source.name}" deleted`);
await loadSources();
} catch (err) {
setSourcesError(err instanceof Error ? err.message : 'Failed to delete source');
} finally {
setDeletingId(null);
}
}
async function handleTest(source: UpstreamSource) {
testSourceById(source.id);
}
async function testSourceById(sourceId: string) {
setTestingId(sourceId);
setTestResults((prev) => ({ ...prev, [sourceId]: { success: true, message: 'Testing...' } }));
try {
const result = await testUpstreamSource(sourceId);
setTestResults((prev) => ({
...prev,
[sourceId]: {
success: result.success,
message: result.success
? `OK (${result.elapsed_ms}ms)`
: result.error || `HTTP ${result.status_code}`,
},
}));
} catch (err) {
setTestResults((prev) => ({
...prev,
[sourceId]: {
success: false,
message: err instanceof Error ? err.message : 'Test failed',
},
}));
} finally {
setTestingId(null);
}
}
function showError(sourceName: string, error: string) {
setSelectedError({ sourceName, error });
setShowErrorModal(true);
}
if (authLoading) {
return <div className="admin-cache-page">Loading...</div>;
}
if (!user?.is_admin) {
return (
<div className="admin-cache-page">
<div className="error-message">Access denied. Admin privileges required.</div>
</div>
);
}
return (
<div className="admin-cache-page">
<h1>Upstream Sources</h1>
{successMessage && <div className="success-message">{successMessage}</div>}
{/* Upstream Sources Section */}
<section className="sources-section">
<div className="section-header">
<button className="btn btn-primary" onClick={openCreateForm}>
Add Source
</button>
</div>
{loadingSources ? (
<p>Loading sources...</p>
) : sourcesError ? (
<div className="error-message">{sourcesError}</div>
) : sources.length === 0 ? (
<p className="empty-message">No upstream sources configured.</p>
) : (
<table className="sources-table">
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>URL</th>
<th>Priority</th>
<th>Status</th>
<th>Test</th>
<th>Actions</th>
</tr>
</thead>
<tbody>
{sources.map((source) => (
<tr key={source.id} className={source.enabled ? '' : 'disabled-row'}>
<td>
<span className="source-name">{source.name}</span>
{source.source === 'env' && (
<span className="env-badge" title="Defined via environment variable">ENV</span>
)}
</td>
<td>
{source.source_type}
{!SUPPORTED_SOURCE_TYPES.has(source.source_type) && (
<span className="coming-soon-badge"> (coming soon)</span>
)}
</td>
<td className="url-cell" title={source.url}>{source.url}</td>
<td>{source.priority}</td>
<td>
<span className={`status-badge ${source.enabled ? 'enabled' : 'disabled'}`}>
{source.enabled ? 'Enabled' : 'Disabled'}
</span>
</td>
<td className="test-cell">
{testingId === source.id ? (
<span className="test-dot testing" title="Testing..."></span>
) : testResults[source.id] ? (
testResults[source.id].success ? (
<span className="test-dot success" title={testResults[source.id].message}></span>
) : (
<span
className="test-dot failure"
title="Click to see error"
onClick={() => showError(source.name, testResults[source.id].message)}
></span>
)
) : null}
</td>
<td className="actions-cell">
<button
className="btn btn-sm btn-secondary"
onClick={() => handleTest(source)}
disabled={testingId === source.id}
>
Test
</button>
{source.source !== 'env' && (
<button className="btn btn-sm btn-secondary" onClick={() => openEditForm(source)}>
Edit
</button>
)}
</td>
</tr>
))}
</tbody>
</table>
)}
</section>
{/* Create/Edit Modal */}
{showForm && (
<div className="modal-overlay" onClick={() => setShowForm(false)}>
<div className="modal-content" onClick={(e) => e.stopPropagation()}>
<h2>{editingSource ? 'Edit Upstream Source' : 'Add Upstream Source'}</h2>
<form onSubmit={handleFormSubmit}>
{formError && <div className="error-message">{formError}</div>}
<div className="form-group">
<label htmlFor="name">Name</label>
<input
type="text"
id="name"
value={formData.name}
onChange={(e) => setFormData({ ...formData, name: e.target.value })}
placeholder="e.g., npm-private"
required
/>
</div>
<div className="form-row">
<div className="form-group">
<label htmlFor="source_type">Type</label>
<select
id="source_type"
value={formData.source_type}
onChange={(e) => setFormData({ ...formData, source_type: e.target.value as SourceType })}
>
{SOURCE_TYPES.map((type) => (
<option key={type} value={type}>
{type}{!SUPPORTED_SOURCE_TYPES.has(type) ? ' (coming soon)' : ''}
</option>
))}
</select>
</div>
<div className="form-group">
<label htmlFor="priority">Priority</label>
<input
type="number"
id="priority"
value={formData.priority}
onChange={(e) => setFormData({ ...formData, priority: parseInt(e.target.value) || 100 })}
min="1"
/>
<span className="help-text">Lower = higher priority</span>
</div>
</div>
<div className="form-group">
<label htmlFor="url">URL</label>
<input
type="url"
id="url"
value={formData.url}
onChange={(e) => setFormData({ ...formData, url: e.target.value })}
placeholder="https://registry.example.com"
required
/>
</div>
<div className="form-row">
<div className="form-group checkbox-group">
<label>
<input
type="checkbox"
checked={formData.enabled}
onChange={(e) => setFormData({ ...formData, enabled: e.target.checked })}
/>
Enabled
</label>
</div>
</div>
<div className="form-group">
<label htmlFor="auth_type">Authentication</label>
<select
id="auth_type"
value={formData.auth_type}
onChange={(e) => setFormData({ ...formData, auth_type: e.target.value as AuthType })}
>
{AUTH_TYPES.map((type) => (
<option key={type} value={type}>
{type === 'none' ? 'None' : type === 'api_key' ? 'API Key' : type.charAt(0).toUpperCase() + type.slice(1)}
</option>
))}
</select>
</div>
{formData.auth_type !== 'none' && (
<div className="form-row">
{(formData.auth_type === 'basic' || formData.auth_type === 'api_key') && (
<div className="form-group">
<label htmlFor="username">{formData.auth_type === 'api_key' ? 'Header Name' : 'Username'}</label>
<input
type="text"
id="username"
value={formData.username}
onChange={(e) => setFormData({ ...formData, username: e.target.value })}
placeholder={formData.auth_type === 'api_key' ? 'X-API-Key' : 'username'}
/>
</div>
)}
<div className="form-group">
<label htmlFor="password">
{formData.auth_type === 'bearer'
? 'Token'
: formData.auth_type === 'api_key'
? 'API Key Value'
: 'Password'}
</label>
<input
type="password"
id="password"
value={formData.password}
onChange={(e) => setFormData({ ...formData, password: e.target.value })}
placeholder={editingSource ? '(unchanged)' : ''}
/>
{editingSource && (
<span className="help-text">Leave empty to keep existing {formData.auth_type === 'bearer' ? 'token' : 'credentials'}</span>
)}
</div>
</div>
)}
<div className="form-actions">
{editingSource && (
<button
type="button"
className="btn btn-danger"
onClick={() => {
handleDelete(editingSource);
setShowForm(false);
}}
disabled={deletingId === editingSource.id}
>
{deletingId === editingSource.id ? 'Deleting...' : 'Delete'}
</button>
)}
<div className="form-actions-right">
<button type="button" className="btn" onClick={() => setShowForm(false)}>
Cancel
</button>
<button type="submit" className="btn btn-primary" disabled={isSaving}>
{isSaving ? 'Saving...' : editingSource ? 'Update' : 'Create'}
</button>
</div>
</div>
</form>
</div>
</div>
)}
{/* Error Details Modal */}
{showErrorModal && selectedError && (
<div className="modal-overlay" onClick={() => setShowErrorModal(false)}>
<div className="error-modal-content" onClick={(e) => e.stopPropagation()}>
<h3>Connection Error: {selectedError.sourceName}</h3>
<div className="error-details">{selectedError.error}</div>
<div className="modal-actions">
<button className="btn" onClick={() => setShowErrorModal(false)}>
Close
</button>
</div>
</div>
</div>
)}
</div>
);
}
export default AdminCachePage;

View File

@@ -493,16 +493,3 @@
gap: 6px;
flex-wrap: wrap;
}
/* Cell name styles */
.cell-name {
display: flex;
align-items: center;
gap: 8px;
}
/* System project badge */
.system-badge {
font-size: 0.7rem;
padding: 2px 6px;
}

View File

@@ -224,9 +224,6 @@ function Home() {
<span className="cell-name">
{!project.is_public && <LockIcon />}
{project.name}
{project.is_system && (
<Badge variant="warning" className="system-badge">Cache</Badge>
)}
</span>
),
},
@@ -249,7 +246,7 @@ function Home() {
key: 'created_by',
header: 'Owner',
className: 'cell-owner',
render: (project) => project.team_name || project.created_by,
render: (project) => project.created_by,
},
...(user
? [

View File

@@ -642,11 +642,6 @@ tr:hover .copy-btn {
padding: 20px;
}
/* Ensure file modal needs higher z-index when opened from deps modal */
.modal-overlay:has(.ensure-file-modal) {
z-index: 1100;
}
.ensure-file-modal {
background: var(--bg-secondary);
border: 1px solid var(--border-primary);
@@ -798,194 +793,4 @@ tr:hover .copy-btn {
.ensure-file-modal {
max-height: 90vh;
}
.action-menu-dropdown {
right: 0;
left: auto;
}
}
/* Header upload button */
.header-upload-btn {
margin-left: auto;
}
/* Tag/Version cell */
.tag-version-cell {
display: flex;
flex-direction: column;
gap: 4px;
}
.tag-version-cell .version-badge {
font-size: 0.75rem;
color: var(--text-muted);
}
/* Icon buttons */
.btn-icon {
display: flex;
align-items: center;
justify-content: center;
width: 32px;
height: 32px;
padding: 0;
background: transparent;
border: 1px solid transparent;
border-radius: var(--radius-sm);
color: var(--text-secondary);
cursor: pointer;
transition: all var(--transition-fast);
}
.btn-icon:hover {
background: var(--bg-hover);
color: var(--text-primary);
}
/* Action menu */
.action-buttons {
display: flex;
align-items: center;
gap: 4px;
}
.action-menu {
position: relative;
}
/* Action menu backdrop for click-outside */
.action-menu-backdrop {
position: fixed;
top: 0;
left: 0;
right: 0;
bottom: 0;
z-index: 999;
}
.action-menu-dropdown {
position: fixed;
z-index: 1000;
min-width: 180px;
padding: 4px 0;
background: var(--bg-secondary);
border: 1px solid var(--border-primary);
border-radius: var(--radius-md);
box-shadow: 0 4px 12px rgba(0, 0, 0, 0.15);
}
.action-menu-dropdown button {
display: block;
width: 100%;
padding: 8px 12px;
background: none;
border: none;
text-align: left;
font-size: 0.875rem;
color: var(--text-primary);
cursor: pointer;
transition: background var(--transition-fast);
}
.action-menu-dropdown button:hover {
background: var(--bg-hover);
}
/* Upload Modal */
.upload-modal,
.create-tag-modal {
background: var(--bg-secondary);
border-radius: var(--radius-lg);
width: 90%;
max-width: 500px;
max-height: 90vh;
overflow: hidden;
}
.modal-header {
display: flex;
align-items: center;
justify-content: space-between;
padding: 16px 20px;
border-bottom: 1px solid var(--border-primary);
}
.modal-header h3 {
margin: 0;
font-size: 1.125rem;
font-weight: 600;
}
.modal-body {
padding: 20px;
}
.modal-description {
margin-bottom: 16px;
color: var(--text-secondary);
font-size: 0.875rem;
}
.modal-actions {
display: flex;
justify-content: flex-end;
gap: 12px;
margin-top: 20px;
padding-top: 16px;
border-top: 1px solid var(--border-primary);
}
/* Dependencies Modal */
.deps-modal {
background: var(--bg-secondary);
border-radius: var(--radius-lg);
width: 90%;
max-width: 600px;
max-height: 80vh;
overflow: hidden;
display: flex;
flex-direction: column;
}
.deps-modal .modal-body {
overflow-y: auto;
flex: 1;
}
.deps-modal-controls {
display: flex;
gap: 8px;
margin-bottom: 16px;
}
/* Artifact ID Modal */
.artifact-id-modal {
background: var(--bg-secondary);
border-radius: var(--radius-lg);
width: 90%;
max-width: 500px;
}
.artifact-id-display {
display: flex;
align-items: center;
gap: 12px;
padding: 16px;
background: var(--bg-tertiary);
border-radius: var(--radius-md);
border: 1px solid var(--border-primary);
}
.artifact-id-display code {
font-family: 'JetBrains Mono', 'Fira Code', 'Consolas', monospace;
font-size: 0.8125rem;
color: var(--text-primary);
word-break: break-all;
flex: 1;
}
.artifact-id-display .copy-btn {
opacity: 1;
flex-shrink: 0;
}

File diff suppressed because it is too large Load Diff

View File

@@ -195,9 +195,6 @@ function ProjectPage() {
<Badge variant={project.is_public ? 'public' : 'private'}>
{project.is_public ? 'Public' : 'Private'}
</Badge>
{project.is_system && (
<Badge variant="warning">System Cache</Badge>
)}
{accessLevel && (
<Badge variant={accessLevel === 'admin' ? 'success' : accessLevel === 'write' ? 'info' : 'default'}>
{isOwner ? 'Owner' : accessLevel.charAt(0).toUpperCase() + accessLevel.slice(1)}
@@ -214,7 +211,7 @@ function ProjectPage() {
</div>
</div>
<div className="page-header__actions">
{canAdmin && !project.team_id && !project.is_system && (
{canAdmin && !project.team_id && (
<button
className="btn btn-secondary"
onClick={() => navigate(`/project/${projectName}/settings`)}
@@ -227,11 +224,11 @@ function ProjectPage() {
Settings
</button>
)}
{canWrite && !project.is_system ? (
{canWrite ? (
<button className="btn btn-primary" onClick={() => setShowForm(!showForm)}>
{showForm ? 'Cancel' : '+ New Package'}
</button>
) : user && !project.is_system ? (
) : user ? (
<span className="text-muted" title="You have read-only access to this project">
Read-only access
</span>
@@ -294,20 +291,18 @@ function ProjectPage() {
placeholder="Filter packages..."
className="list-controls__search"
/>
{!project?.is_system && (
<select
className="list-controls__select"
value={format}
onChange={(e) => handleFormatChange(e.target.value)}
>
<option value="">All formats</option>
{FORMAT_OPTIONS.map((f) => (
<option key={f} value={f}>
{f}
</option>
))}
</select>
)}
<select
className="list-controls__select"
value={format}
onChange={(e) => handleFormatChange(e.target.value)}
>
<option value="">All formats</option>
{FORMAT_OPTIONS.map((f) => (
<option key={f} value={f}>
{f}
</option>
))}
</select>
</div>
{hasActiveFilters && (
@@ -343,19 +338,19 @@ function ProjectPage() {
className: 'cell-description',
render: (pkg) => pkg.description || '—',
},
...(!project?.is_system ? [{
{
key: 'format',
header: 'Format',
render: (pkg: Package) => <Badge variant="default">{pkg.format}</Badge>,
}] : []),
...(!project?.is_system ? [{
key: 'version_count',
header: 'Versions',
render: (pkg: Package) => pkg.version_count ?? '—',
}] : []),
render: (pkg) => <Badge variant="default">{pkg.format}</Badge>,
},
{
key: 'tag_count',
header: 'Tags',
render: (pkg) => pkg.tag_count ?? '—',
},
{
key: 'artifact_count',
header: project?.is_system ? 'Versions' : 'Artifacts',
header: 'Artifacts',
render: (pkg) => pkg.artifact_count ?? '—',
},
{
@@ -364,12 +359,12 @@ function ProjectPage() {
render: (pkg) =>
pkg.total_size !== undefined && pkg.total_size > 0 ? formatBytes(pkg.total_size) : '—',
},
...(!project?.is_system ? [{
key: 'latest_version',
{
key: 'latest_tag',
header: 'Latest',
render: (pkg: Package) =>
pkg.latest_version ? <strong style={{ color: 'var(--accent-primary)' }}>{pkg.latest_version}</strong> : '—',
}] : []),
render: (pkg) =>
pkg.latest_tag ? <strong style={{ color: 'var(--accent-primary)' }}>{pkg.latest_tag}</strong> : '—',
},
{
key: 'created_at',
header: 'Created',

View File

@@ -6,7 +6,6 @@ export interface Project {
name: string;
description: string | null;
is_public: boolean;
is_system?: boolean; // True for system cache projects (_npm, _pypi, etc.)
created_at: string;
updated_at: string;
created_by: string;
@@ -19,6 +18,12 @@ export interface Project {
team_name?: string | null;
}
export interface TagSummary {
name: string;
artifact_id: string;
created_at: string;
}
export interface Package {
id: string;
project_id: string;
@@ -29,11 +34,12 @@ export interface Package {
created_at: string;
updated_at: string;
// Aggregated fields (from PackageDetailResponse)
tag_count?: number;
artifact_count?: number;
version_count?: number;
total_size?: number;
latest_tag?: string | null;
latest_upload_at?: string | null;
latest_version?: string | null;
recent_tags?: TagSummary[];
}
export interface Artifact {
@@ -46,19 +52,22 @@ export interface Artifact {
ref_count: number;
}
export interface PackageArtifact {
export interface Tag {
id: string;
sha256: string;
size: number;
content_type: string | null;
original_name: string | null;
checksum_md5?: string | null;
checksum_sha1?: string | null;
s3_etag?: string | null;
package_id: string;
name: string;
artifact_id: string;
created_at: string;
created_by: string;
format_metadata?: Record<string, unknown> | null;
version?: string | null; // Version from PackageVersion if exists
}
export interface TagDetail extends Tag {
artifact_size: number;
artifact_content_type: string | null;
artifact_original_name: string | null;
artifact_created_at: string;
artifact_format_metadata: Record<string, unknown> | null;
version: string | null;
}
export interface PackageVersion {
@@ -73,9 +82,20 @@ export interface PackageVersion {
size?: number;
content_type?: string | null;
original_name?: string | null;
tags?: string[];
}
export interface ArtifactDetail extends Artifact {}
export interface ArtifactTagInfo {
id: string;
name: string;
package_id: string;
package_name: string;
project_name: string;
}
export interface ArtifactDetail extends Artifact {
tags: ArtifactTagInfo[];
}
export interface PaginatedResponse<T> {
items: T[];
@@ -95,6 +115,8 @@ export interface ListParams {
order?: 'asc' | 'desc';
}
export interface TagListParams extends ListParams {}
export interface PackageListParams extends ListParams {
format?: string;
platform?: string;
@@ -119,6 +141,7 @@ export interface UploadResponse {
size: number;
project: string;
package: string;
tag: string | null;
version: string | null;
version_source: string | null;
}
@@ -141,8 +164,9 @@ export interface SearchResultPackage {
}
export interface SearchResultArtifact {
tag_id: string;
tag_name: string;
artifact_id: string;
version: string | null;
package_id: string;
package_name: string;
project_name: string;
@@ -365,7 +389,8 @@ export interface Dependency {
artifact_id: string;
project: string;
package: string;
version: string;
version: string | null;
tag: string | null;
created_at: string;
}
@@ -379,6 +404,7 @@ export interface DependentInfo {
project: string;
package: string;
version: string | null;
constraint_type: 'version' | 'tag';
constraint_value: string;
}
@@ -401,17 +427,11 @@ export interface ResolvedArtifact {
project: string;
package: string;
version: string | null;
tag: string | null;
size: number;
download_url: string;
}
export interface MissingDependency {
project: string;
package: string;
constraint: string | null;
required_by: string | null;
}
export interface DependencyResolutionResponse {
requested: {
project: string;
@@ -419,7 +439,6 @@ export interface DependencyResolutionResponse {
ref: string;
};
resolved: ResolvedArtifact[];
missing: MissingDependency[];
total_size: number;
artifact_count: number;
}
@@ -484,56 +503,3 @@ export interface TeamMemberCreate {
export interface TeamMemberUpdate {
role: TeamRole;
}
// Upstream Source types
export type SourceType = 'npm' | 'pypi' | 'maven' | 'docker' | 'helm' | 'nuget' | 'deb' | 'rpm' | 'generic';
export type AuthType = 'none' | 'basic' | 'bearer' | 'api_key';
export interface UpstreamSource {
id: string;
name: string;
source_type: SourceType;
url: string;
enabled: boolean;
auth_type: AuthType;
username: string | null;
has_password: boolean;
has_headers: boolean;
priority: number;
source: 'database' | 'env';
created_at: string | null;
updated_at: string | null;
}
export interface UpstreamSourceCreate {
name: string;
source_type: SourceType;
url: string;
enabled?: boolean;
auth_type?: AuthType;
username?: string;
password?: string;
headers?: Record<string, string>;
priority?: number;
}
export interface UpstreamSourceUpdate {
name?: string;
source_type?: SourceType;
url?: string;
enabled?: boolean;
auth_type?: AuthType;
username?: string;
password?: string;
headers?: Record<string, string> | null;
priority?: number;
}
export interface UpstreamSourceTestResult {
success: boolean;
status_code: number | null;
elapsed_ms: number;
error: string | null;
source_id: string;
source_name: string;
}

View File

@@ -128,10 +128,6 @@ spec:
value: {{ .Values.orchard.rateLimit.login | quote }}
{{- end }}
{{- end }}
{{- if .Values.orchard.purgeSeedData }}
- name: ORCHARD_PURGE_SEED_DATA
value: "true"
{{- end }}
{{- if .Values.orchard.database.poolSize }}
- name: ORCHARD_DATABASE_POOL_SIZE
value: {{ .Values.orchard.database.poolSize | quote }}
@@ -144,20 +140,6 @@ spec:
- name: ORCHARD_DATABASE_POOL_TIMEOUT
value: {{ .Values.orchard.database.poolTimeout | quote }}
{{- end }}
{{- if .Values.orchard.pypiCache }}
{{- if .Values.orchard.pypiCache.workers }}
- name: ORCHARD_PYPI_CACHE_WORKERS
value: {{ .Values.orchard.pypiCache.workers | quote }}
{{- end }}
{{- if .Values.orchard.pypiCache.maxDepth }}
- name: ORCHARD_PYPI_CACHE_MAX_DEPTH
value: {{ .Values.orchard.pypiCache.maxDepth | quote }}
{{- end }}
{{- if .Values.orchard.pypiCache.maxAttempts }}
- name: ORCHARD_PYPI_CACHE_MAX_ATTEMPTS
value: {{ .Values.orchard.pypiCache.maxAttempts | quote }}
{{- end }}
{{- end }}
{{- if .Values.orchard.auth }}
{{- if or .Values.orchard.auth.secretsManager .Values.orchard.auth.existingSecret .Values.orchard.auth.adminPassword }}
- name: ORCHARD_ADMIN_PASSWORD

View File

@@ -59,10 +59,10 @@ ingress:
resources:
limits:
cpu: 500m
memory: 1Gi
memory: 512Mi
requests:
cpu: 200m
memory: 1Gi
memory: 512Mi
livenessProbe:
httpGet:
@@ -124,12 +124,6 @@ orchard:
mode: "presigned"
presignedUrlExpiry: 3600
# PyPI Cache Worker settings (reduced workers to limit memory usage)
pypiCache:
workers: 1
maxDepth: 10
maxAttempts: 3
# Relaxed rate limits for dev/feature environments (allows integration tests to run)
rateLimit:
login: "1000/minute" # Default is 5/minute, relaxed for CI integration tests
@@ -228,7 +222,7 @@ minioIngress:
secretName: minio-tls # Overridden by CI
redis:
enabled: true
enabled: false
waitForDatabase: true

View File

@@ -57,10 +57,10 @@ ingress:
resources:
limits:
cpu: 500m
memory: 768Mi
memory: 512Mi
requests:
cpu: 500m
memory: 768Mi
memory: 512Mi
livenessProbe:
httpGet:
@@ -121,12 +121,6 @@ orchard:
mode: "presigned"
presignedUrlExpiry: 3600
# PyPI Cache Worker settings (reduced workers to limit memory usage)
pypiCache:
workers: 2
maxDepth: 10
maxAttempts: 3
# PostgreSQL subchart - disabled in prod, using RDS
postgresql:
enabled: false
@@ -140,7 +134,7 @@ minioIngress:
enabled: false
redis:
enabled: true
enabled: false
waitForDatabase: true

View File

@@ -56,10 +56,10 @@ ingress:
resources:
limits:
cpu: 500m
memory: 768Mi
memory: 512Mi
requests:
cpu: 500m
memory: 768Mi
memory: 512Mi
livenessProbe:
httpGet:
@@ -91,7 +91,6 @@ affinity: {}
# Orchard server configuration
orchard:
env: "development" # Allows seed data for testing
purgeSeedData: true # Remove public seed data (npm-public, pypi-public, etc.)
server:
host: "0.0.0.0"
port: 8080
@@ -122,12 +121,6 @@ orchard:
mode: "presigned" # presigned, redirect, or proxy
presignedUrlExpiry: 3600 # Presigned URL expiry in seconds
# PyPI Cache Worker settings (reduced workers to limit memory usage)
pypiCache:
workers: 2
maxDepth: 10
maxAttempts: 3
# Relaxed rate limits for stage (allows CI integration tests to run)
rateLimit:
login: "1000/minute" # Default is 5/minute, relaxed for CI integration tests
@@ -146,7 +139,7 @@ minioIngress:
# Redis subchart configuration (for future caching)
redis:
enabled: true
enabled: false
image:
registry: containers.global.bsf.tools
repository: bitnami/redis

View File

@@ -54,10 +54,10 @@ ingress:
resources:
limits:
cpu: 500m
memory: 768Mi
memory: 512Mi
requests:
cpu: 500m
memory: 768Mi
memory: 512Mi
livenessProbe:
httpGet:
@@ -120,12 +120,6 @@ orchard:
mode: "presigned" # presigned, redirect, or proxy
presignedUrlExpiry: 3600 # Presigned URL expiry in seconds
# PyPI Cache Worker settings
pypiCache:
workers: 2 # Number of concurrent cache workers (reduced to limit memory usage)
maxDepth: 10 # Maximum recursion depth for dependency caching
maxAttempts: 3 # Maximum retry attempts for failed cache tasks
# Authentication settings
auth:
# Option 1: Plain admin password (creates K8s secret)

View File

@@ -1,137 +0,0 @@
-- Migration 010: Upstream Artifact Caching
-- Adds support for caching artifacts from upstream registries (npm, PyPI, Maven, etc.)
-- Part of "The cache that never forgets" epic for hermetic builds
-- =============================================================================
-- upstream_sources: Configure upstream registries for artifact caching
-- =============================================================================
CREATE TABLE IF NOT EXISTS upstream_sources (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
name VARCHAR(255) NOT NULL UNIQUE,
source_type VARCHAR(50) NOT NULL DEFAULT 'generic',
url VARCHAR(2048) NOT NULL,
enabled BOOLEAN NOT NULL DEFAULT FALSE,
is_public BOOLEAN NOT NULL DEFAULT TRUE,
auth_type VARCHAR(20) NOT NULL DEFAULT 'none',
username VARCHAR(255),
password_encrypted BYTEA,
headers_encrypted BYTEA,
priority INTEGER NOT NULL DEFAULT 100,
created_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
-- Source type must be one of the supported types
CONSTRAINT check_source_type CHECK (
source_type IN ('npm', 'pypi', 'maven', 'docker', 'helm', 'nuget', 'deb', 'rpm', 'generic')
),
-- Auth type must be valid
CONSTRAINT check_auth_type CHECK (
auth_type IN ('none', 'basic', 'bearer', 'api_key')
),
-- Priority must be positive
CONSTRAINT check_priority_positive CHECK (priority > 0)
);
-- Indexes for upstream_sources
CREATE INDEX IF NOT EXISTS idx_upstream_sources_enabled ON upstream_sources(enabled);
CREATE INDEX IF NOT EXISTS idx_upstream_sources_source_type ON upstream_sources(source_type);
CREATE INDEX IF NOT EXISTS idx_upstream_sources_is_public ON upstream_sources(is_public);
CREATE INDEX IF NOT EXISTS idx_upstream_sources_priority ON upstream_sources(priority);
-- Comments for upstream_sources
COMMENT ON TABLE upstream_sources IS 'Configuration for upstream artifact registries (npm, PyPI, Maven, etc.)';
COMMENT ON COLUMN upstream_sources.name IS 'Unique human-readable name (e.g., npm-public, artifactory-private)';
COMMENT ON COLUMN upstream_sources.source_type IS 'Type of registry: npm, pypi, maven, docker, helm, nuget, deb, rpm, generic';
COMMENT ON COLUMN upstream_sources.url IS 'Base URL of the upstream registry';
COMMENT ON COLUMN upstream_sources.enabled IS 'Whether this source is active for caching';
COMMENT ON COLUMN upstream_sources.is_public IS 'True if this is a public internet source (for air-gap mode)';
COMMENT ON COLUMN upstream_sources.auth_type IS 'Authentication type: none, basic, bearer, api_key';
COMMENT ON COLUMN upstream_sources.username IS 'Username for basic auth';
COMMENT ON COLUMN upstream_sources.password_encrypted IS 'Fernet-encrypted password/token';
COMMENT ON COLUMN upstream_sources.headers_encrypted IS 'Fernet-encrypted custom headers (JSON)';
COMMENT ON COLUMN upstream_sources.priority IS 'Priority for source selection (lower = higher priority)';
-- =============================================================================
-- cache_settings: Global cache configuration (singleton table)
-- =============================================================================
CREATE TABLE IF NOT EXISTS cache_settings (
id INTEGER PRIMARY KEY DEFAULT 1,
allow_public_internet BOOLEAN NOT NULL DEFAULT TRUE,
auto_create_system_projects BOOLEAN NOT NULL DEFAULT TRUE,
created_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
-- Singleton constraint
CONSTRAINT check_cache_settings_singleton CHECK (id = 1)
);
-- Insert default row
INSERT INTO cache_settings (id, allow_public_internet, auto_create_system_projects)
VALUES (1, TRUE, TRUE)
ON CONFLICT (id) DO NOTHING;
-- Comments for cache_settings
COMMENT ON TABLE cache_settings IS 'Global cache settings (singleton table)';
COMMENT ON COLUMN cache_settings.allow_public_internet IS 'Air-gap mode: when false, blocks all public internet sources';
COMMENT ON COLUMN cache_settings.auto_create_system_projects IS 'Auto-create system projects (_npm, _pypi, etc.) on first cache';
-- =============================================================================
-- cached_urls: Track URL to artifact mappings for provenance
-- =============================================================================
CREATE TABLE IF NOT EXISTS cached_urls (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
url VARCHAR(4096) NOT NULL,
url_hash VARCHAR(64) NOT NULL,
artifact_id VARCHAR(64) NOT NULL REFERENCES artifacts(id),
source_id UUID REFERENCES upstream_sources(id) ON DELETE SET NULL,
fetched_at TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT CURRENT_TIMESTAMP,
response_headers JSONB DEFAULT '{}',
created_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
-- URL hash must be unique (same URL = same cached artifact)
CONSTRAINT unique_url_hash UNIQUE (url_hash)
);
-- Indexes for cached_urls
CREATE INDEX IF NOT EXISTS idx_cached_urls_url_hash ON cached_urls(url_hash);
CREATE INDEX IF NOT EXISTS idx_cached_urls_artifact_id ON cached_urls(artifact_id);
CREATE INDEX IF NOT EXISTS idx_cached_urls_source_id ON cached_urls(source_id);
CREATE INDEX IF NOT EXISTS idx_cached_urls_fetched_at ON cached_urls(fetched_at);
-- Comments for cached_urls
COMMENT ON TABLE cached_urls IS 'Tracks which URLs have been cached and maps to artifacts';
COMMENT ON COLUMN cached_urls.url IS 'Original URL that was fetched';
COMMENT ON COLUMN cached_urls.url_hash IS 'SHA256 hash of URL for fast lookup';
COMMENT ON COLUMN cached_urls.artifact_id IS 'The cached artifact (by SHA256 content hash)';
COMMENT ON COLUMN cached_urls.source_id IS 'Which upstream source provided this (null if manual)';
COMMENT ON COLUMN cached_urls.fetched_at IS 'When the URL was fetched from upstream';
COMMENT ON COLUMN cached_urls.response_headers IS 'Original response headers from upstream (for debugging)';
-- =============================================================================
-- Add is_system column to projects table for system cache projects
-- =============================================================================
DO $$
BEGIN
IF NOT EXISTS (
SELECT 1 FROM information_schema.columns
WHERE table_name = 'projects' AND column_name = 'is_system'
) THEN
ALTER TABLE projects ADD COLUMN is_system BOOLEAN NOT NULL DEFAULT FALSE;
CREATE INDEX IF NOT EXISTS idx_projects_is_system ON projects(is_system);
END IF;
END $$;
COMMENT ON COLUMN projects.is_system IS 'True for system cache projects (_npm, _pypi, etc.)';
-- =============================================================================
-- Seed default upstream sources (disabled by default for safety)
-- =============================================================================
INSERT INTO upstream_sources (id, name, source_type, url, enabled, is_public, auth_type, priority)
VALUES
(gen_random_uuid(), 'npm-public', 'npm', 'https://registry.npmjs.org', FALSE, TRUE, 'none', 100),
(gen_random_uuid(), 'pypi-public', 'pypi', 'https://pypi.org/simple', FALSE, TRUE, 'none', 100),
(gen_random_uuid(), 'maven-central', 'maven', 'https://repo1.maven.org/maven2', FALSE, TRUE, 'none', 100),
(gen_random_uuid(), 'docker-hub', 'docker', 'https://registry-1.docker.io', FALSE, TRUE, 'none', 100)
ON CONFLICT (name) DO NOTHING;

View File

@@ -1,55 +0,0 @@
-- Migration: 011_pypi_cache_tasks
-- Description: Add table for tracking PyPI dependency caching tasks
-- Date: 2026-02-02
-- Table for tracking PyPI cache tasks with retry support
CREATE TABLE pypi_cache_tasks (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
-- What to cache
package_name VARCHAR(255) NOT NULL,
version_constraint VARCHAR(255),
-- Origin tracking
parent_task_id UUID REFERENCES pypi_cache_tasks(id) ON DELETE SET NULL,
depth INTEGER NOT NULL DEFAULT 0,
triggered_by_artifact VARCHAR(64) REFERENCES artifacts(id) ON DELETE SET NULL,
-- Status
status VARCHAR(20) NOT NULL DEFAULT 'pending',
attempts INTEGER NOT NULL DEFAULT 0,
max_attempts INTEGER NOT NULL DEFAULT 3,
-- Results
cached_artifact_id VARCHAR(64) REFERENCES artifacts(id) ON DELETE SET NULL,
error_message TEXT,
-- Timing
created_at TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT NOW(),
started_at TIMESTAMP WITH TIME ZONE,
completed_at TIMESTAMP WITH TIME ZONE,
next_retry_at TIMESTAMP WITH TIME ZONE,
-- Constraints
CONSTRAINT check_task_status CHECK (status IN ('pending', 'in_progress', 'completed', 'failed')),
CONSTRAINT check_depth_non_negative CHECK (depth >= 0),
CONSTRAINT check_attempts_non_negative CHECK (attempts >= 0)
);
-- Index for finding tasks ready to process (pending with retry time passed)
CREATE INDEX idx_pypi_cache_tasks_status_retry ON pypi_cache_tasks(status, next_retry_at);
-- Index for deduplication check (is this package already queued?)
CREATE INDEX idx_pypi_cache_tasks_package_status ON pypi_cache_tasks(package_name, status);
-- Index for tracing dependency chains
CREATE INDEX idx_pypi_cache_tasks_parent ON pypi_cache_tasks(parent_task_id);
-- Index for finding tasks by artifact that triggered them
CREATE INDEX idx_pypi_cache_tasks_triggered_by ON pypi_cache_tasks(triggered_by_artifact);
-- Index for finding tasks by cached artifact
CREATE INDEX idx_pypi_cache_tasks_cached_artifact ON pypi_cache_tasks(cached_artifact_id);
-- Index for sorting by depth and creation time (processing order)
CREATE INDEX idx_pypi_cache_tasks_depth_created ON pypi_cache_tasks(depth, created_at);

View File

@@ -1,33 +0,0 @@
-- Migration: Remove tag system
-- Date: 2026-02-03
-- Description: Remove tags table and related objects, keeping only versions for artifact references
-- Drop triggers on tags table
DROP TRIGGER IF EXISTS tags_ref_count_insert_trigger ON tags;
DROP TRIGGER IF EXISTS tags_ref_count_delete_trigger ON tags;
DROP TRIGGER IF EXISTS tags_ref_count_update_trigger ON tags;
DROP TRIGGER IF EXISTS tags_updated_at_trigger ON tags;
DROP TRIGGER IF EXISTS tag_changes_trigger ON tags;
-- Drop the tag change tracking function
DROP FUNCTION IF EXISTS track_tag_changes();
-- Remove tag_constraint from artifact_dependencies
-- First drop the constraint that requires either version or tag
ALTER TABLE artifact_dependencies DROP CONSTRAINT IF EXISTS check_constraint_type;
-- Remove the tag_constraint column
ALTER TABLE artifact_dependencies DROP COLUMN IF EXISTS tag_constraint;
-- Make version_constraint NOT NULL (now the only option)
UPDATE artifact_dependencies SET version_constraint = '*' WHERE version_constraint IS NULL;
ALTER TABLE artifact_dependencies ALTER COLUMN version_constraint SET NOT NULL;
-- Drop tag_history table first (depends on tags)
DROP TABLE IF EXISTS tag_history;
-- Drop tags table
DROP TABLE IF EXISTS tags;
-- Rename uploads.tag_name to uploads.version (historical data field)
ALTER TABLE uploads RENAME COLUMN tag_name TO version;