├── .gitignore ├── neo ├── __init__.py ├── common.py ├── tests.py └── neo.py ├── .github ├── dependabot.yml └── workflows │ └── test.yaml ├── action.yml ├── README.md └── LICENSE /.gitignore: -------------------------------------------------------------------------------- 1 | __pycache__ 2 | .vscode/* 3 | -------------------------------------------------------------------------------- /neo/__init__.py: -------------------------------------------------------------------------------- 1 | from .neo import generate_matrix, set_github_actions_output, main 2 | -------------------------------------------------------------------------------- /.github/dependabot.yml: -------------------------------------------------------------------------------- 1 | version: 2 2 | updates: 3 | 4 | - package-ecosystem: "github-actions" 5 | directory: "/" 6 | schedule: 7 | interval: "daily" 8 | pull-request-branch-name: 9 | # Separate sections of the branch name with a hyphen 10 | # for example, `dependabot-npm_and_yarn-next_js-acorn-6.4.1` 11 | separator: "-" 12 | labels: 13 | - dependencies 14 | 15 | - package-ecosystem: "pip" 16 | directory: "/" 17 | schedule: 18 | interval: "daily" 19 | pull-request-branch-name: 20 | # Separate sections of the branch name with a hyphen 21 | # for example, `dependabot-npm_and_yarn-next_js-acorn-6.4.1` 22 | separator: "-" 23 | labels: 24 | - dependencies 25 | -------------------------------------------------------------------------------- /action.yml: -------------------------------------------------------------------------------- 1 | name: Neo 2 | description: Generate a matrix depending on changed files 3 | inputs: 4 | pattern: 5 | description: regex pattern with named groups to match against changed files 6 | required: true 7 | defaults: 8 | description: when set to true, if changed files don't match the pattern, recursively match all files in the repository. 9 | default: "false" 10 | required: false 11 | default-patterns: 12 | description: line separated list of UNIX-style glob patterns matched against the list of changed files. if match, switch to defaults mode. 13 | default: "" 14 | required: false 15 | ignore-deleted-files: 16 | description: whether to ignore the deleted files or not 17 | deprecationMessage: not used anymore 18 | default: "false" 19 | required: false 20 | outputs: 21 | matrix: 22 | description: the output job matrix 23 | value: ${{ steps.neo.outputs.matrix }} 24 | matrix-length: 25 | description: the length of the matrix 26 | value: ${{ steps.neo.outputs.matrix-length }} 27 | runs: 28 | using: composite 29 | steps: 30 | # required to compare the pattern on the files in the repo 31 | - if: inputs.defaults || inputs.default-patterns != '' 32 | uses: actions/checkout@v4 33 | 34 | - id: neo 35 | shell: bash 36 | env: 37 | GITHUB_TOKEN: ${{ github.token }} 38 | DEFAULT_PATTERNS: ${{ inputs.default-patterns }} 39 | run: | 40 | ${{ github.action_path }}/neo/neo.py \ 41 | --pattern "${{ inputs.pattern }}" \ 42 | --defaults=${{inputs.defaults}} >> $GITHUB_OUTPUT 43 | 44 | branding: 45 | icon: git-pull-request 46 | color: green 47 | -------------------------------------------------------------------------------- /.github/workflows/test.yaml: -------------------------------------------------------------------------------- 1 | name: Test 2 | 3 | on: 4 | pull_request: 5 | branches: 6 | - master 7 | push: 8 | branches: 9 | - master 10 | 11 | jobs: 12 | python-unit-tests: 13 | name: Unit tests 14 | runs-on: ubuntu-latest 15 | steps: 16 | - name: Checkout repository 17 | uses: actions/checkout@v4 18 | - name: Run tests 19 | env: 20 | GITHUB_TOKEN: ${{ github.token }} 21 | run: ./neo/tests.py TestChangedFiles -v 22 | 23 | python-integration-tests: 24 | name: Integration tests 25 | runs-on: ubuntu-latest 26 | steps: 27 | - name: Checkout repository 28 | uses: actions/checkout@v4 29 | - name: Run tests 30 | env: 31 | GITHUB_TOKEN: ${{ github.token }} 32 | run: ./neo/tests.py IntegrationTest -v 33 | 34 | neo: 35 | name: Test action 36 | runs-on: ubuntu-latest 37 | outputs: 38 | matrix: ${{ steps.neo.outputs.matrix }} 39 | matrix-length: ${{ steps.neo.outputs.matrix-length }} 40 | steps: 41 | - name: Checkout repository 42 | uses: actions/checkout@v4 43 | - name: Generate matrix 44 | id: neo 45 | uses: ./ 46 | env: 47 | NEO_LOG_LEVEL: DEBUG 48 | with: 49 | pattern: (?P[^/]+)/ 50 | defaults: true 51 | default-patterns: | 52 | .github/** 53 | 54 | matrix-check: 55 | name: Check matrix 56 | runs-on: ubuntu-latest 57 | needs: [ neo ] 58 | strategy: 59 | matrix: ${{ fromJson(needs.neo.outputs.matrix ) }} 60 | steps: 61 | - name: Echo Matrix Directory 62 | run: echo ${{ matrix.dir }} 63 | 64 | - name: Echo Matrix Length 65 | run: echo ${{ needs.neo.outputs.matrix-length }} 66 | -------------------------------------------------------------------------------- /neo/common.py: -------------------------------------------------------------------------------- 1 | from functools import total_ordering 2 | import os 3 | import argparse 4 | 5 | 6 | # Courtesy of http://stackoverflow.com/a/10551190 with env-var retrieval fixed 7 | class EnvDefault(argparse.Action): 8 | """An argparse action class that auto-sets missing default values from env 9 | vars. Defaults to requiring the argument.""" 10 | 11 | def __init__(self, envvar, required=True, default=None, **kwargs): 12 | if not default and envvar: 13 | if envvar in os.environ: 14 | default = os.environ[envvar] 15 | if required and default: 16 | required = False 17 | super(EnvDefault, self).__init__(default=default, required=required, **kwargs) 18 | 19 | def __call__(self, parser, namespace, values, option_string=None): 20 | setattr(namespace, self.dest, values) 21 | 22 | 23 | # functional sugar for the above 24 | def env_default(envvar): 25 | def wrapper(**kwargs): 26 | return EnvDefault(envvar, **kwargs) 27 | 28 | return wrapper 29 | 30 | 31 | def strtobool(val): 32 | # from https://github.com/python/cpython/blob/main/Lib/distutils/util.py#L308 33 | # since distutils is scheduled for removal 34 | val = val.lower() 35 | if val in ("y", "yes", "t", "true", "on", "1"): 36 | return True 37 | elif val in ("n", "no", "f", "false", "off", "0"): 38 | return False 39 | else: 40 | raise ValueError("invalid truth value %r" % (val,)) 41 | 42 | 43 | @total_ordering 44 | class hdict(dict): 45 | def __hash__(self): 46 | return hash(frozenset(self)) 47 | 48 | def __lt__(self, other): 49 | # concatenate keys and values for ordering 50 | keys = sorted(self.keys()) 51 | other_keys = sorted(other.keys()) 52 | return sorted(f"{k}-{self[k]}" for k in keys) < sorted( 53 | f"{k}-{other[k]}" for k in other_keys 54 | ) 55 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # action-changed-files 2 | 3 | ![GitHub release (latest by date)](https://img.shields.io/github/v/release/hellofresh/action-changed-files?style=for-the-badge) 4 | ![GitHub tag (latest by date)](https://img.shields.io/github/v/tag/hellofresh/action-changed-files?style=for-the-badge) 5 | ![GitHub Workflow Status](https://img.shields.io/github/actions/workflow/status/hellofresh/action-changed-files/test.yaml?label=Status&style=for-the-badge&branch=master) 6 | ![GitHub last commit](https://img.shields.io/github/last-commit/hellofresh/action-changed-files?style=for-the-badge) 7 | ![GitHub Release Date](https://img.shields.io/github/release-date/hellofresh/action-changed-files?style=for-the-badge) 8 | ![GitHub issues](https://img.shields.io/github/issues-raw/hellofresh/action-changed-files?style=for-the-badge) 9 | 10 | ![GitHub](https://img.shields.io/github/license/hellofresh/action-changed-files?style=for-the-badge) 11 | 12 | 13 | Generate a GitHub Actions job matrix based on changed files (with an extra twist). 14 | 15 | ## Problem statement 16 | 17 | Repositories are often composed of multiple modules or directories that are built & deployed differently. They can represent a part of the system, or a specific environment. Modules like this also often share some common files. 18 | 19 | The (traditional) and easiest way to guarantee that all changes are properly tested in CI is to run all jobs for every single change, but this can lead to a very long verification time. 20 | 21 | Ideally, you want to be able to trigger (and skip) jobs based on the contents (and type) of a change. 22 | 23 | [Trigger paths](https://docs.github.com/en/actions/learn-github-actions/workflow-syntax-for-github-actions#example-including-paths) and [matrix job strategy](https://docs.github.com/en/actions/learn-github-actions/workflow-syntax-for-github-actions#jobsjob_idstrategymatrix) are two great features that can help reducing verification time, but they're still not flexible enough. 24 | 25 | ## Example 26 | 27 | ### Sample repository 28 | 29 | `neo` helps with generating a job matrix based on the changed files in a pull-request, or after merging it to the target branch. 30 | 31 | Consider the following repository directory structure: 32 | 33 | ``` 34 | ├── infrastructure 35 | │ ├── live # depends on terraform-modules 36 | | |── staging # depends on terraform-modules 37 | ├── library 38 | │ ├── common 39 | │ ├── parser # depends on library/common 40 | │ ├── network # depends on library/common 41 | |── terraform-modules 42 | |── deploy.sh # used in CI to deploy infrastructure 43 | |── Makefile # used in CI to build library 44 | ``` 45 | 46 | and that we want to: 47 | 48 | * verify & deploy changes to infrastructure as code affecting the `live` and `staging` environments 49 | * build & test changes to `library/parser` and `library/network` 50 | 51 | ### Sample workflow 52 | 53 | ```yaml 54 | name: Sample workflow 55 | 56 | on: 57 | pull_request: 58 | branches: 59 | - master 60 | 61 | jobs: 62 | generate-matrix: 63 | name: Generate job matrices 64 | runs-on: ubuntu-latest 65 | # don't forget to declare outputs here! 66 | outputs: 67 | matrix-infrastructure: ${{ steps.neo-infrastructure.outputs.matrix }} 68 | matrix-library: ${{ steps.neo-library.outputs.matrix }} 69 | steps: 70 | - name: Generate matrix | Infrastructure 71 | id: neo-infrastructure 72 | uses: hellofresh/action-changed-files@v3 73 | with: 74 | pattern: infrastructure/(?P[^/]+) 75 | default-patterns: | 76 | terraform-modules 77 | deploy.sh 78 | 79 | - name: Generate matrix | Library 80 | id: neo-library 81 | uses: hellofresh/action-changed-files@v3 82 | with: 83 | pattern: library/(?P(?!common)[^/]+) 84 | default-patterns: | 85 | library/common 86 | 87 | infrastructure: 88 | needs: [ generate-matrix ] # don't forget this! 89 | strategy: 90 | matrix: ${{ fromJson(needs.generate-matrix.outputs.matrix-infrastructure) }} 91 | if: ${{ fromJson(needs.generate-matrix.outputs.matrix-infrastructure).include[0] }} # skip if the matrix is empty! 92 | steps: 93 | - name: Deploy infrastructure 94 | run: echo "Deploying ${{ matrix.environment }}" 95 | 96 | build: 97 | needs: [ generate-matrix ] 98 | strategy: 99 | matrix: ${{ fromJson(needs.generate-matrix.outputs.matrix-build) }} 100 | if: ${{ fromJson(needs.generate-matrix.outputs.matrix-build).include[0] }} 101 | steps: 102 | - name: Building library 103 | run: echo "Building ${{ matrix.lib }}" 104 | ``` 105 | 106 | Let's break down what will happen here with a few examples: 107 | 108 | 109 | 110 | 111 | 112 | 113 | 114 | 118 | 122 | 123 | 124 | 128 | 132 | 133 | 134 | 138 | 144 | 145 |
Changed filesBehaviour
115 | infrastructure/live/main.tf
116 | infrastructure/staging/main.tf
117 | 		119 | jobs.deploy[live]
120 | jobs.deploy[staging]
121 |
125 | library/parser/json.c
126 | library/network/tcp.c
127 | 		129 | jobs.build[parser]
130 | jobs.build[network]
131 |
135 | terraform-modules/aws.tf
136 | library/common/printer.c
137 | 		139 | jobs.deploy[live]
140 | jobs.deploy[staging]
141 | jobs.build[parser]
142 | jobs.build[network]
143 |
146 | 147 | ### Change statuses 148 | 149 | Each matrix entry in the output JSON will also be annotated with an additional `reason` field that can help handling corner-cases like deleting a directory. If all matches of a set of groups have the same status, the `reason` field will be set to it. 150 | 151 | Example: if you use pattern `(?Pdatabase-us|database-fr)` and all files in the `database-us` directory are deleted, the job matrix will look like: 152 | 153 | ```json 154 | [ 155 | { 156 | "module": "database-us", 157 | "reason": "deleted" 158 | }, 159 | { 160 | "module": "database-fr", 161 | "reason": "?" 162 | } 163 | ] 164 | ``` 165 | 166 | The same applies to any status, like `added` or `modified`. 167 | 168 | Note: if a pattern matching to the same set of groups were caused by multiple type of changes, the `reason` field is marked as `?`. 169 | 170 | ### Logging and debugging 171 | By default the log level for the action is `INFO` but can be overriden by setting `NEO_LOG_LEVEL` env variable 172 | example: 173 | ```yaml 174 | sample-job: 175 | name: Test action 176 | runs-on: ubuntu-latest 177 | outputs: 178 | matrix: ${{ steps.sample-step.outputs.matrix }} 179 | matrix-length: ${{ steps.sample-step.outputs.matrix-length }} 180 | steps: 181 | - name: Checkout repository 182 | uses: actions/checkout@v3 183 | - name: Generate matrix 184 | id: sample-step 185 | uses: hellofresh/action-changed-files@v3 186 | env: 187 | NEO_LOG_LEVEL: DEBUG 188 | with: 189 | pattern: (?P[^/]+)/ 190 | defaults: true 191 | default-patterns: | 192 | .github/** 193 | 194 | ``` 195 | 196 | ## Reference 197 | 198 | 199 | 200 | 201 | 202 | 203 | 204 | 205 | 206 | 207 | 208 | 209 | 212 | 213 | 214 | 215 | 216 | 217 | 220 | 221 | 222 | 223 | 224 | 225 | 228 | 229 |
Input parameter nameTypeRequiredDescription
patternstringyes 210 | Regular expression pattern with named groups. Changed files will be matched against this pattern and named groups will be extracted into the matrix. See the relevant section of the Python documentation for the syntax reference. 211 |
defaultsbooleanno 218 | if true, and no changed files match the pattern, recursively apply the pattern on all the files of the repository to generate a matrix of all possible combinations (a.k.a. run everything for changes to common files) 219 |
default-patternslist[string]no 226 | similar to the 'defaults' flag, except we match changed files on the provided UNIX-style glob pattern 227 |
230 | -------------------------------------------------------------------------------- /neo/tests.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | import neo 3 | 4 | import contextlib 5 | import io 6 | import json 7 | import os 8 | import tempfile 9 | import unittest 10 | from pathlib import Path 11 | 12 | 13 | class TestChangedFiles(unittest.TestCase): 14 | def test_no_changes(self): 15 | self.assertFalse( 16 | neo.generate_matrix( 17 | include_regex="clusters/.*", 18 | files=[ 19 | {"filename": "clusters", "status": "modified"}, 20 | {"filename": "blah", "status": "modified"}, 21 | ], 22 | ) 23 | ) 24 | 25 | def test_no_changes_with_default_pattern(self): 26 | with tempfile.TemporaryDirectory() as d: 27 | Path(os.path.join(d, "staging.txt")).touch() 28 | Path(os.path.join(d, "live.txt")).touch() 29 | self.assertEqual( 30 | neo.generate_matrix( 31 | include_regex="(?Pstaging|live)", 32 | default_patterns=["clusters/**"], 33 | default_dir=d, 34 | files=[ 35 | {"filename": "blah", "status": "modified"}, 36 | {"filename": "clusters/sample.json", "status": "modified"}, 37 | ], 38 | ), 39 | [ 40 | {'environment': 'live', 'reason': 'default'}, 41 | {'environment': 'staging', 'reason': 'default'} 42 | ], 43 | ) 44 | 45 | def test_changes_with_default_pattern(self): 46 | with tempfile.TemporaryDirectory() as d: 47 | Path(os.path.join(d, "staging.txt")).touch() 48 | Path(os.path.join(d, "live.txt")).touch() 49 | self.assertEqual( 50 | neo.generate_matrix( 51 | include_regex="(?Pstaging|live)", 52 | default_patterns=["clusters/**"], 53 | default_dir=d, 54 | files=[ 55 | {"filename": "blah", "status": "modified"}, 56 | {"filename": "clusters/sample.json", "status": "modified"}, 57 | {"filename": "staging.txt", "status": "modified"}, 58 | ], 59 | ), 60 | [ 61 | {'environment': 'live', 'reason': 'default'}, 62 | {'environment': 'staging', 'reason': 'modified'} 63 | ], 64 | ) 65 | 66 | def test_no_changes_with_defaults(self): 67 | with tempfile.TemporaryDirectory() as d: 68 | Path(os.path.join(d, "staging.txt")).touch() 69 | Path(os.path.join(d, "live.txt")).touch() 70 | self.assertCountEqual( 71 | neo.generate_matrix( 72 | include_regex="(?Pstaging|live)", 73 | defaults=True, 74 | default_dir=d, 75 | files=[ 76 | {"filename": "clusters", "status": "modified"}, 77 | {"filename": "blah", "status": "modified"}, 78 | ], 79 | ), 80 | [ 81 | {"environment": "staging", "reason": "default"}, 82 | {"environment": "live", "reason": "default"}, 83 | ], 84 | ) 85 | 86 | def test_changes_groups_level1(self): 87 | self.assertCountEqual( 88 | neo.generate_matrix( 89 | include_regex="clusters/(?P\w+)/.*", 90 | files=[ 91 | {"filename": "clusters/staging/app", "status": "modified"}, 92 | {"filename": "clusters/staging/demo", "status": "modified"}, 93 | {"filename": "clusters/live/app", "status": "modified"}, 94 | ], 95 | ), 96 | [ 97 | {"environment": "staging", "reason": "modified"}, 98 | {"environment": "live", "reason": "modified"}, 99 | ], 100 | ) 101 | 102 | def test_changes_groups_level2(self): 103 | self.assertCountEqual( 104 | neo.generate_matrix( 105 | include_regex="clusters/(?P\w+)/(?P\w+)", 106 | files=[ 107 | {"filename": "clusters/staging/app", "status": "modified"}, 108 | {"filename": "clusters/live/app", "status": "modified"}, 109 | {"filename": "clusters/staging/demo", "status": "modified"}, 110 | ], 111 | ), 112 | [ 113 | {"environment": "staging", "namespace": "app", "reason": "modified"}, 114 | {"environment": "staging", "namespace": "demo", "reason": "modified"}, 115 | {"environment": "live", "namespace": "app", "reason": "modified"}, 116 | ], 117 | ) 118 | 119 | def test_changes_no_group(self): 120 | self.assertCountEqual( 121 | neo.generate_matrix( 122 | include_regex="clusters/.*", 123 | files=[ 124 | {"filename": "clusters/staging/app", "status": "modified"}, 125 | {"filename": "clusters/live/app", "status": "modified"}, 126 | {"filename": "clusters/staging/demo", "status": "modified"}, 127 | {"filename": "my_other_file/hello", "status": "modified"}, 128 | ], 129 | ), 130 | [ 131 | {"path": "clusters/staging/app", "reason": "modified"}, 132 | {"path": "clusters/staging/demo", "reason": "modified"}, 133 | {"path": "clusters/live/app", "reason": "modified"}, 134 | ], 135 | ) 136 | 137 | def test_changes_sorted(self): 138 | self.assertListEqual( 139 | neo.generate_matrix( 140 | include_regex="clusters/.*", 141 | files=[ 142 | {"filename": "my_other_file/hello", "status": "modified"}, 143 | {"filename": "clusters/live/app", "status": "modified"}, 144 | {"filename": "clusters/staging/app", "status": "modified"}, 145 | {"filename": "clusters/staging/demo", "status": "modified"}, 146 | ], 147 | ), 148 | [ 149 | {"path": "clusters/live/app", "reason": "modified"}, 150 | {"path": "clusters/staging/app", "reason": "modified"}, 151 | {"path": "clusters/staging/demo", "reason": "modified"}, 152 | ], 153 | ) 154 | 155 | def test_all_matches_removed(self): 156 | self.assertCountEqual( 157 | neo.generate_matrix( 158 | include_regex="clusters/(?P\w+)/.*", 159 | files=[ 160 | {"filename": "clusters/staging/app", "status": "removed"}, 161 | {"filename": "clusters/staging/demo", "status": "removed"}, 162 | {"filename": "clusters/live/app", "status": "modified"}, 163 | ], 164 | ), 165 | [ 166 | {"environment": "staging", "reason": "removed"}, 167 | {"environment": "live", "reason": "modified"}, 168 | ], 169 | ) 170 | 171 | def test_one_match_removed(self): 172 | self.assertCountEqual( 173 | neo.generate_matrix( 174 | include_regex="clusters/(?P\w+)/.*", 175 | files=[ 176 | {"filename": "clusters/staging/app", "status": "removed"}, 177 | {"filename": "clusters/staging/demo", "status": "modified"}, 178 | {"filename": "clusters/live/app", "status": "modified"}, 179 | ], 180 | ), 181 | [ 182 | {"environment": "staging", "reason": "updated"}, 183 | {"environment": "live", "reason": "modified"}, 184 | ], 185 | ) 186 | 187 | def test_github_outputs(self): 188 | matrix = neo.generate_matrix( 189 | include_regex="clusters/.*", 190 | files=[ 191 | {"filename": "clusters/staging/app", "status": "modified"}, 192 | {"filename": "clusters/live/app", "status": "modified"}, 193 | {"filename": "clusters/staging/demo", "status": "modified"}, 194 | {"filename": "my_other_file/hello", "status": "modified"}, 195 | ], 196 | ) 197 | with contextlib.redirect_stdout(io.StringIO()) as f: 198 | neo.set_github_actions_output(matrix) 199 | 200 | output = f.getvalue() 201 | expected_matrix_output = json.dumps({"include": matrix}) 202 | 203 | self.assertIn(f"matrix={expected_matrix_output}", output) 204 | self.assertIn(f"matrix-length=3", output) 205 | 206 | 207 | class IntegrationTest(unittest.TestCase): 208 | empty_repo_commit_sha = "6b5794416e6750d16fb126a04eadb681349e6947" 209 | initial_import_commit_sha = "191fe221420a833dc9a43d3338c1d94ccab94ea6" 210 | 211 | def test_basic(self): 212 | matrix = neo.main( 213 | os.getenv("GITHUB_TOKEN"), 214 | "hellofresh/action-changed-files", 215 | self.empty_repo_commit_sha, 216 | self.initial_import_commit_sha, 217 | ".*", 218 | ) 219 | self.assertEqual(len(matrix), 5) 220 | 221 | def test_pagination(self): 222 | unpaginated_result = neo.main( 223 | os.getenv("GITHUB_TOKEN"), 224 | "hellofresh/action-changed-files", 225 | self.empty_repo_commit_sha, 226 | self.initial_import_commit_sha, 227 | ".*", 228 | ) 229 | paginated_result = neo.main( 230 | os.getenv("GITHUB_TOKEN"), 231 | "hellofresh/action-changed-files", 232 | self.empty_repo_commit_sha, 233 | self.initial_import_commit_sha, 234 | ".*", 235 | per_page=1, 236 | ) 237 | self.assertListEqual(unpaginated_result, paginated_result) 238 | 239 | 240 | if __name__ == "__main__": 241 | unittest.main() 242 | -------------------------------------------------------------------------------- /neo/neo.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | 3 | from collections import defaultdict 4 | import os 5 | import argparse 6 | import fnmatch 7 | import logging 8 | import requests 9 | import json 10 | import re 11 | from urllib.parse import quote_plus 12 | 13 | from common import env_default, hdict, strtobool 14 | 15 | 16 | def update_matches(files, include_regex, old_matches=defaultdict(set), ): 17 | """ 18 | The update_matches function takes a list of files and their statuses, 19 | and returns a dictionary mapping the job matrix keys to sets of statuses. 20 | For example: 21 | 22 | :param old_matches: old matches object to update 23 | :param files: Store the files that are found in the directory 24 | :param include_regex: Filter the files that are included in the job matrix 25 | :return: A dictionary of dictionaries 26 | """ 27 | matches = defaultdict(set) 28 | for (filename, status) in files: 29 | match = include_regex.match(filename) 30 | if match: 31 | if match.groupdict(): 32 | if "reason" in match.groupdict().keys(): 33 | raise ValueError("reason is a reserved name for the job matrix") 34 | key = hdict(match.groupdict()) 35 | else: 36 | key = hdict({"path": filename}) 37 | if key in list(old_matches.keys()): 38 | status = old_matches.pop(key).pop() 39 | matches[key].add(status) 40 | 41 | return matches 42 | 43 | 44 | def generate_matrix( 45 | files: list, 46 | include_regex: str, 47 | defaults: bool = False, 48 | default_patterns: list = None, 49 | default_dir: str = os.getenv("GITHUB_WORKSPACE", os.curdir), 50 | ) -> list: 51 | """ 52 | The generate_matrix function takes a list of files and returns a matrix of 53 | files that match the provided pattern. The function also takes an optional 54 | include_regex parameter which is used to filter out unwanted files. If no 55 | include_regex is provided, all changed files are included in the matrix. 56 | 57 | :param files: Pass in the list of files that were changed 58 | :param include_regex:str: Indicate that the regex should be matched against the filename, 59 | Filter the files that are included in the matrix Define the pattern that is used to filter the files 60 | :param defaults: Determine if the default patterns should be used 61 | :param default_patterns: Provide a list of default patterns that will be used to determine 62 | if the matrix should be generated Define the pattern that is used to filter the files 63 | :param default_dir: Specify the root directory of the repository or use the current directory 64 | :return: A list of dictionaries 65 | """ 66 | if default_patterns is None: 67 | default_patterns = [] 68 | include_regex = re.compile(include_regex, re.M | re.S) 69 | changed_files = [(e["filename"], e["status"]) for e in files] 70 | 71 | # check if changed files match the so-called default patterns 72 | matched_default_patterns = [ 73 | pattern 74 | for pattern in default_patterns 75 | if fnmatch.filter((c for c, _ in changed_files), pattern) 76 | ] 77 | 78 | if matched_default_patterns: 79 | logging.info("Files changed in defaults patterns: %s", matched_default_patterns) 80 | 81 | matches = update_matches(changed_files, include_regex) 82 | 83 | # if nothing changed, list all files/directories 84 | if (not matches and defaults) or matched_default_patterns: 85 | logging.info( 86 | "Listing all files/directories in repository matching the provided pattern" 87 | ) 88 | default_files = [ 89 | (os.path.relpath(os.path.join(path, f), default_dir), "default") 90 | for path, _, files in os.walk(default_dir) 91 | for f in files 92 | ] 93 | matches = update_matches( default_files, include_regex, matches) 94 | # mark matrix entries with a status if all its matches have the same status 95 | status_matrix = [] 96 | for (groups, statuses) in matches.items(): 97 | groups["reason"] = statuses.pop() if len(statuses) == 1 else "updated" 98 | status_matrix.append(groups) 99 | 100 | # convert back to a dict (hashable, serializable) 101 | return sorted(status_matrix) 102 | 103 | 104 | def main( 105 | github_token: str, 106 | github_repository: str, 107 | github_base_ref: str, 108 | github_head_ref: str, 109 | include_regex: str, 110 | defaults: bool = False, 111 | default_patterns: list = None, 112 | per_page: int = 0, 113 | ): 114 | 115 | if default_patterns is None: 116 | default_patterns = [] 117 | with requests.session() as session: 118 | session.hooks = { 119 | "response": lambda resp, *resp_args, **kwargs: resp.raise_for_status() 120 | } 121 | # see: https://docs.github.com/en/actions/security-guides/automatic-token-authentication 122 | session.headers["Authorization"] = f"token {github_token}" 123 | if per_page: 124 | session.params = {"per_page": per_page} 125 | 126 | compare_url = ( 127 | f"https://api.github.com/repos/{github_repository}" 128 | f"/compare/{quote_plus(github_base_ref)}...{quote_plus(github_head_ref)}" 129 | ) 130 | logging.info(f"GitHub API request: {compare_url}") 131 | 132 | r = session.get(compare_url) 133 | files = r.json().get("files", []) 134 | while link := r.links.get("next"): 135 | next_page_url = link["url"] 136 | logging.info(f"Loading next page: {next_page_url}") 137 | r = session.get(next_page_url) 138 | files.extend(r.json().get("files", [])) 139 | 140 | return generate_matrix(files, include_regex, defaults, default_patterns) 141 | 142 | 143 | def github_webhook_ref(dest: str, option_strings: list): 144 | """ 145 | The github_webhook_ref function is a helper function that returns an argparse.Action object 146 | that will extract the ref from either the head or base of a pull request, depending on whether 147 | the --github-head-ref option was passed to the program. If neither --github-head-ref nor 148 | --github-base-ref are passed, then this action will default to using the base ref. 149 | 150 | :param dest:str: Specify the name of the attribute to which 151 | :param option_strings:list: Determine the name of the argument 152 | :return: An action that will be used by the `github_arg_group` 153 | """ 154 | github_event_name = os.getenv("GITHUB_EVENT_NAME", None) 155 | github_event_path = os.getenv("GITHUB_EVENT_PATH", None) 156 | is_github_head_ref = "--github-head-ref" in option_strings 157 | if github_event_path: 158 | with open(github_event_path, "r") as fp: 159 | github_event = json.load(fp) 160 | if github_event_name == "pull_request": 161 | return argparse.Action( 162 | default=github_event["pull_request"]["head"]["sha"] 163 | if is_github_head_ref 164 | else github_event["pull_request"]["base"]["sha"], 165 | required=False, 166 | dest=dest, 167 | option_strings=option_strings, 168 | ) 169 | elif github_event_name == "push": 170 | return argparse.Action( 171 | default=github_event["after"] 172 | if is_github_head_ref 173 | else github_event["before"], 174 | required=False, 175 | dest=dest, 176 | option_strings=option_strings, 177 | ) 178 | else: 179 | raise NotImplementedError( 180 | f"unsupported github event {github_event_name}" 181 | ) 182 | 183 | return argparse._StoreAction( 184 | required=True, dest=dest, option_strings=option_strings 185 | ) 186 | 187 | 188 | def set_github_actions_output(generated_matrix: list) -> None: 189 | """ 190 | The set_github_actions_output function is used to generate the output for GitHub Actions. 191 | It takes in a list of dictionaries and prints out two environment variables: matrix, which contains 192 | the JSON representation of the matrix, and matrix-length, which contains an integer representing 193 | the number of rows in the matrix. 194 | 195 | :param generated_matrix:List[dict]: Pass the generated matrix to the function 196 | :return: The generated matrix in a format that can be used by the github actions workflow 197 | """ 198 | files_json = json.dumps({"include": generated_matrix}) 199 | print(f"matrix={files_json}") 200 | print(f"matrix-length={len(generated_matrix)}") 201 | 202 | 203 | if __name__ == "__main__": 204 | parser = argparse.ArgumentParser() 205 | 206 | github_arg_group = parser.add_argument_group("github environment") 207 | github_arg_group.add_argument( 208 | "--github-repository", action=env_default("GITHUB_REPOSITORY"), required=True 209 | ) 210 | github_arg_group.add_argument( 211 | "--github-token", action=env_default("GITHUB_TOKEN"), required=True 212 | ) 213 | github_arg_group.add_argument("--github-head-ref", action=github_webhook_ref) 214 | github_arg_group.add_argument("--github-base-ref", action=github_webhook_ref) 215 | 216 | user_arg_group = parser.add_argument_group("user-provided") 217 | user_arg_group.add_argument( 218 | "--pattern", 219 | dest="include_regex", 220 | help="regex pattern to match changed files against", 221 | required=True, 222 | ) 223 | user_arg_group.add_argument( 224 | "--defaults", 225 | help="if any changed files match this pattern, recursively match all files in the current directory with the " 226 | "include pattern (a.k.a. run everything)", 227 | type=strtobool, 228 | default="false", 229 | ) 230 | user_arg_group.add_argument( 231 | "--default-patterns", 232 | help="if any changed files match this pattern, apply --defaults", 233 | nargs="+", 234 | default=os.getenv("DEFAULT_PATTERNS", "").splitlines(), 235 | ) 236 | 237 | args = vars(parser.parse_args()) 238 | 239 | logging.basicConfig( 240 | level=logging.DEBUG 241 | if os.getenv("NEO_LOG_LEVEL", "INFO") == "DEBUG" 242 | else logging.INFO 243 | ) 244 | 245 | matrix = main(**args) 246 | logging.info(matrix) 247 | 248 | if os.getenv("GITHUB_ACTIONS"): 249 | set_github_actions_output(matrix) 250 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright 2020 HelloFresh SE 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------