mirror of
https://github.com/data-privacy-stack/presidio.git
synced 2026-09-21 05:27:53 -05:00
ci: auto-label pull requests by component and area (#2240)
* ci: auto-label pull requests by component and area Adds a path-based labeler so every pull request arrives routed to the package it changes and the analyzer subsystem it touches, instead of being triaged by hand. Uses pull_request_target for the same reason label-external.yml does: fork pull requests get a read-only token on pull_request, so the label call would fail silently. The action never checks out or runs pull request code, and both the workflow and the config are read from the base branch, so a pull request cannot alter its own label rules. sync-labels is left off so hand-applied triage labels are never removed. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0183ij1wiTEcd8wA58xY7e6C * ci: label pull requests touching docs/samples Samples are documentation but also code that has to keep working, so they need to be findable on their own rather than only under documentation. Reuses the existing `samples` label. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0183ij1wiTEcd8wA58xY7e6C * ci: correct facet documentation in labeler config The header described two facets while the file defines three, and `samples` sat under the component heading rather than type. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0183ij1wiTEcd8wA58xY7e6C * ci: name the labeler step for all three facets The workflow and step names described component and area only, while the config also applies type labels. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0183ij1wiTEcd8wA58xY7e6C --------- Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Omri Mendels
co-authored by
Claude Opus 5
Claude Opus 5
parent
5e2fcea990
commit
a7b17c75f3
@@ -0,0 +1,141 @@
|
||||
# Path-based labels applied automatically by .github/workflows/label-areas.yml
|
||||
#
|
||||
# Three facets are applied here:
|
||||
# component - which package the change lives in
|
||||
# area - which subsystem inside the analyzer it touches
|
||||
# type - what kind of change it is, where the paths make that clear
|
||||
#
|
||||
# Labels are not exclusive. A pull request that spans a package and a subsystem
|
||||
# receives both, which is intended: the component label answers "what does this
|
||||
# release affect", the area label answers "who should review it".
|
||||
#
|
||||
# Triage labels (needs-decision, good first issue, ...) are applied by hand and
|
||||
# must not be listed here, or sync-labels would eventually remove them.
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Component
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
analyzer:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- 'presidio-analyzer/**'
|
||||
- 'docs/analyzer/**'
|
||||
|
||||
anonymizer:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- 'presidio-anonymizer/**'
|
||||
- 'docs/anonymizer/**'
|
||||
|
||||
image-anonymization:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- 'presidio-image-redactor/**'
|
||||
- 'docs/image-redactor/**'
|
||||
|
||||
dicom:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- '**/dicom_*.py'
|
||||
- '**/*dicom*'
|
||||
|
||||
structured-data:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- 'presidio-structured/**'
|
||||
|
||||
cli:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- 'presidio-cli/**'
|
||||
|
||||
rest-api:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- 'presidio-*/app.py'
|
||||
- 'docs/api-docs/**'
|
||||
- 'docs/api.md'
|
||||
|
||||
deployment:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- '**/Dockerfile*'
|
||||
- 'docker-compose*.yml'
|
||||
- 'presidio/**'
|
||||
- 'scripts/**'
|
||||
|
||||
documentation:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- 'docs/**'
|
||||
- 'mkdocs.yml'
|
||||
- 'overrides/**'
|
||||
- '*.md'
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Area (analyzer subsystems)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# Pattern and predefined recognizers.
|
||||
# Review rulebook: .github/instructions/recognizers.instructions.md
|
||||
PII recognizers:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- 'presidio-analyzer/presidio_analyzer/predefined_recognizers/**'
|
||||
- 'presidio-analyzer/presidio_analyzer/conf/default_recognizers.yaml'
|
||||
- 'docs/supported_entities.md'
|
||||
|
||||
# Score boosting from surrounding words, including the lemma matching that
|
||||
# behaves differently per language.
|
||||
context-enhancement:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- 'presidio-analyzer/presidio_analyzer/context_aware_enhancers/**'
|
||||
|
||||
# The pydantic models and registry loading behind YAML configuration.
|
||||
# Review rulebook: .github/instructions/yaml-config.instructions.md
|
||||
yaml-config:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- 'presidio-analyzer/presidio_analyzer/input_validation/**'
|
||||
- 'presidio-analyzer/presidio_analyzer/recognizer_registry/**'
|
||||
- 'presidio-analyzer/presidio_analyzer/conf/**'
|
||||
|
||||
# NLP backends: spaCy, Stanza, transformers, GLiNER, LangExtract.
|
||||
nlp-engine:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- 'presidio-analyzer/presidio_analyzer/nlp_engine/**'
|
||||
- 'presidio-analyzer/presidio_analyzer/chunkers/**'
|
||||
- 'presidio-analyzer/presidio_analyzer/llm_utils/**'
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Type
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# Runnable examples and notebooks. Overlaps documentation by design: a sample
|
||||
# is documentation, but it is also code that has to keep working, so it needs
|
||||
# to be findable on its own.
|
||||
samples:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- 'docs/samples/**'
|
||||
|
||||
test:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- '**/tests/**'
|
||||
- 'e2e-tests/**'
|
||||
|
||||
ci:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- '.github/workflows/**'
|
||||
- '.github/pipelines/**'
|
||||
|
||||
dependencies:
|
||||
- changed-files:
|
||||
- any-glob-to-any-file:
|
||||
- '**/pyproject.toml'
|
||||
- '**/uv.lock'
|
||||
@@ -0,0 +1,29 @@
|
||||
name: Label pull requests by changed paths
|
||||
|
||||
on:
|
||||
pull_request_target:
|
||||
types: [opened, synchronize, reopened]
|
||||
|
||||
# pull_request_target is required so that pull requests from forks receive a
|
||||
# token with write access; a pull_request event grants read-only on forks and
|
||||
# the label call fails silently.
|
||||
#
|
||||
# The usual pull_request_target risk does not apply here: this workflow never
|
||||
# checks out or executes pull request code. It reads the changed file list
|
||||
# through the API only, and both this file and .github/labeler.yml are read
|
||||
# from the base branch, so a pull request cannot change its own label rules.
|
||||
permissions:
|
||||
contents: read
|
||||
pull-requests: write
|
||||
|
||||
jobs:
|
||||
label:
|
||||
runs-on: ubuntu-slim
|
||||
steps:
|
||||
- name: Apply component, area and type labels from changed paths
|
||||
uses: actions/labeler@b8dd2d9be0f68b860e7dae5dae7d772984eacd6d # v6.2.0
|
||||
with:
|
||||
# Add labels only. Labels applied by hand are never removed, and a
|
||||
# pull request that stops touching a path keeps the label a reviewer
|
||||
# may already have acted on.
|
||||
sync-labels: false
|
||||
Reference in New Issue
Block a user