hurdle-gate 0.3.1__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,201 @@
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 [yyyy] [name of copyright owner]
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.
@@ -0,0 +1,185 @@
1
+ Metadata-Version: 2.4
2
+ Name: hurdle-gate
3
+ Version: 0.3.1
4
+ Summary: Static-analysis gate for source↔test file existence mapping
5
+ License-Expression: Apache-2.0
6
+ Keywords: testing,test-coverage,static-analysis,ci,quality-gate
7
+ Classifier: Programming Language :: Python :: 3
8
+ Classifier: Topic :: Software Development :: Quality Assurance
9
+ Classifier: Development Status :: 4 - Beta
10
+ Requires-Python: >=3.9
11
+ Description-Content-Type: text/markdown
12
+ License-File: LICENSE
13
+ Provides-Extra: dev
14
+ Requires-Dist: pytest>=7; extra == "dev"
15
+ Dynamic: license-file
16
+
17
+ # hurdle
18
+
19
+ A source ↔ test **existence mapping** tool. A single-file executable that finds
20
+ source files added without tests (Python 3 standard library only, zero external
21
+ dependencies).
22
+
23
+ **What it does** — decides from filename/path conventions alone whether each
24
+ source file has a corresponding test, and reports the gaps (untested sources).
25
+ Text is the default output; `--json` produces a machine-readable report.
26
+
27
+ **What it does not do**
28
+ - Does not **run** tests — existence only; whether tests pass is out of scope.
29
+ - Does not measure **coverage** — this is a different (and far cheaper) signal
30
+ than line/branch coverage: "does this file have any test at all?"
31
+ - Does not judge code **quality** — a test file that exists but is thin will
32
+ not be caught.
33
+
34
+ ## Installation
35
+
36
+ ```bash
37
+ # Recommended: isolated install via pipx
38
+ pipx install .
39
+
40
+ # Development: venv + editable install (includes dev extras)
41
+ python3 -m venv .venv && source .venv/bin/activate
42
+ pip install -e .[dev]
43
+
44
+ # Environments where pip is unavailable (PEP 668 etc.): runs without installing
45
+ PYTHONPATH=src python3 -m hurdle scan .
46
+ ```
47
+
48
+ ## Quick start
49
+
50
+ ```bash
51
+ # 1) Full scan — gap report for the whole repository (use this to create a baseline)
52
+ hurdle scan ~/study/kopia --json kopia.json
53
+
54
+ # 2) diff mode — evaluate only sources new/changed vs. a base point (core of the local/CI gate)
55
+ hurdle scan . --diff origin/main
56
+
57
+ # 3) strict mode — fail (non-zero exit code) if any evaluated file has a gap
58
+ hurdle scan . --diff origin/main --strict --config .hurdle.json
59
+ ```
60
+
61
+ Reading the output: the report shows a per-file status (`matched` / `gap` /
62
+ `unmapped` — files with unknown extensions are counted only as `unmapped` and
63
+ excluded from language totals), each file's matching test and confidence
64
+ (`exact`/`heuristic`), and per-language totals. Exit codes under `--strict`:
65
+ no gaps = 0, gaps present = failure, runtime error (e.g. `--diff` outside a
66
+ git repository) = 2. CI decides pass/fail from the strict-mode exit code.
67
+
68
+ ## Verdict rules (per language)
69
+
70
+ | Language | Test-existence verdict | confidence |
71
+ |---|---|---|
72
+ | **go** | Package-level: an exact `{stem}_test.go` match wins first; otherwise covered if any `*_test.go` exists in the same package (directory) | exact |
73
+ | **py** | Probes 4 pytest-convention candidate paths — beside the file / in a `tests/` directory × `test_{stem}.py` / `{stem}_test.py` combinations — plus variant names `tests/test_{stem}_*.py` and `tests/test_*_{stem}.py` (v0.2.0). `__init__.py` counts as a package marker and non-test files under `test_dirs` (default `tests`, `test`) count as test-support — both excluded rather than gapped (config: `strict_init`, `test_dirs`) | exact |
74
+ | **ts/js** | Naming conventions: the `*.test.ts(x)` / `*.spec.ts(x)` families | exact |
75
+ | **c / shell** | File-to-file mapping is impossible in trees like lustre (centralized `lustre/tests/` + `kunit/`), so coverage is aggregated per module/directory (heuristic). Listing module→test keywords in `module_map` improves accuracy | heuristic |
76
+
77
+ ## Configuration (.hurdle.json)
78
+
79
+ Passed via `--config`. See `.hurdle.example.json` in this repository for a
80
+ minimal example and `baselines/*.hurdle.json` for real-world ones.
81
+
82
+ ```jsonc
83
+ {
84
+ "exclude": ["vendor/", "**/*_pb.go"], // kept out of the scan
85
+ "allowlist": { "cmd/legacy/main.go": "thin wrapper; covered in pkg/" },
86
+ "module_map": { "lustre/osd-zfs": ["osd", "conf-sanity"] }
87
+ }
88
+ ```
89
+
90
+ | Key | Format | Description |
91
+ |---|---|---|
92
+ | `exclude` | array of strings | Directories are excluded wholesale with a trailing `/` in the name (`vendor/`). Everything else is an fnmatch pattern matched against full paths/filenames (`**/*_pb.go`) |
93
+ | `allowlist` | relpath → reason string | Do not count this file as a gap (escape hatch). Checked **before exclude**, so a file with an explicit reason survives even broad exclude patterns. The reason stays on record in commit history |
94
+ | `module_map` | module relpath → keyword array | Feeds the C/shell heuristic. List the test-suite keywords that cover a module (e.g. `["sanity", "conf-sanity"]`) and module coverage is looked up in the centralized tests/ directory |
95
+
96
+ ## Baseline → gate workflow
97
+
98
+ The core design is a **ratchet**: existing gaps are frozen, and only new gaps
99
+ are blocked.
100
+
101
+ 1. **Capture a baseline** — run a full scan, commit the resulting JSON gap
102
+ report (covering all existing code) to the repository. This becomes a
103
+ de-facto allowlist. The actual results of doing this for the kopia/lustre/
104
+ longhorn-manager/velero repositories are in [BASELINES.md](BASELINES.md)
105
+ and `baselines/*.json`.
106
+ 2. **Classify with config** — filter generated code (`*_pb.go` etc.), vendor,
107
+ and test-support code (`internal/testutil` etc.) via `exclude`/`allowlist`
108
+ so that only files with genuinely no corresponding test remain in the
109
+ baseline.
110
+ 3. **diff + strict gate** — in CI, `--diff origin/<base> --strict` judges only
111
+ the files changed now. Legacy gaps never show up in the diff and are
112
+ ignored; only new/modified files are forced to carry tests. The gap count
113
+ decreases monotonically.
114
+
115
+ ## CI integration
116
+
117
+ Copy `ci/test-exist-gate.yml` to `.github/workflows/test-exist-gate.yml` in the
118
+ target repository and follow the 4 steps in the comment block at the top of
119
+ the file (swap the URL, commit the config, mark the check as required). The
120
+ flow: `fetch-depth: 0` checkout → install hurdle → run
121
+ `scan . --diff origin/base --strict --config .hurdle.json --json` → upload the
122
+ report artifact even on failure (`if: always()`).
123
+
124
+ ## pre-commit local hook
125
+
126
+ Copy `ci/pre-commit-hook.sh` to `.git/hooks/pre-commit`, or use this minimal
127
+ 3-line form:
128
+
129
+ ```bash
130
+ #!/bin/sh
131
+ [ -n "$(git diff --name-only --diff-filter=ACMR HEAD)" ] || exit 0
132
+ exec hurdle scan . --diff HEAD --strict
133
+ ```
134
+
135
+ ## Limitations (honestly)
136
+
137
+ - **It only checks file existence.** It never sees whether tests run, pass, or
138
+ assert anything meaningful. It is a minimal gate against "source added with
139
+ no test" — not a coverage replacement.
140
+ - **Heuristic module verdicts can over- and under-count.** The module-aggregated
141
+ C/shell verdict depends on `module_map` keywords: keywords that are too
142
+ broad over-report coverage; a missing per-module suite under-reports it.
143
+ Treat the report's confidence markers as the trust boundary.
144
+ - **The only escape hatch is the allowlist.** When a rule misjudges a file,
145
+ allowlisting it with a reason is the sole exception path — hiding it with
146
+ exclude removes it from the scan entirely and breaks gap tracking.
147
+
148
+ ## License
149
+
150
+ Apache-2.0 — see the [LICENSE](LICENSE) file for the full text.
151
+
152
+ ## Universe coverage (`hurdle universe`)
153
+
154
+ Beyond per-file test existence, hurdle can enforce coverage of a
155
+ **defined universe** — a complete set of items every one of which must be
156
+ either used, wildcard-covered, or explicitly allowlisted. The motivating
157
+ case: CDP protocol commands/events (`protocol.json` defines the complete
158
+ universe, so "missing something" is well-defined).
159
+
160
+ ```jsonc
161
+ // .hurdle.json
162
+ "universes": {
163
+ "cdp-commands": {
164
+ "items_file": "universes/cdp-commands.json", // bare array or {"items":[], "meta":{}}
165
+ "include": ["src/**/*.py"],
166
+ "literal_shape": "^[A-Z][A-Za-z0-9]*\\.[a-zA-Z][A-Za-z0-9]+$",
167
+ "wildcard_patterns": ["\\.subscribe\\(\\s*\"({domain})\\.\\*\""],
168
+ "extra_usage": ["Page.javascriptDialogOpening"],
169
+ "allowlist": {"Tracing.*": "out of scope — low-level tracing"}
170
+ }
171
+ }
172
+ ```
173
+
174
+ ```bash
175
+ hurdle universe cdp-commands . --strict --json report.json
176
+ ```
177
+
178
+ - Usage extraction collects shape-matched string literals (module
179
+ constants are picked up at their definition site) and intersects them
180
+ with the universe — universe membership itself disambiguates commands
181
+ vs events that share the `Domain.name` shape.
182
+ - Statuses: `covered` / `wildcard` (a `Domain.*` subscription) /
183
+ `allowed` (fnmatch on item names, reason recorded) / `gap`.
184
+ - `--strict` exits 1 on any gap that is not allowlisted — newly added
185
+ universe items cannot appear silently.
@@ -0,0 +1,169 @@
1
+ # hurdle
2
+
3
+ A source ↔ test **existence mapping** tool. A single-file executable that finds
4
+ source files added without tests (Python 3 standard library only, zero external
5
+ dependencies).
6
+
7
+ **What it does** — decides from filename/path conventions alone whether each
8
+ source file has a corresponding test, and reports the gaps (untested sources).
9
+ Text is the default output; `--json` produces a machine-readable report.
10
+
11
+ **What it does not do**
12
+ - Does not **run** tests — existence only; whether tests pass is out of scope.
13
+ - Does not measure **coverage** — this is a different (and far cheaper) signal
14
+ than line/branch coverage: "does this file have any test at all?"
15
+ - Does not judge code **quality** — a test file that exists but is thin will
16
+ not be caught.
17
+
18
+ ## Installation
19
+
20
+ ```bash
21
+ # Recommended: isolated install via pipx
22
+ pipx install .
23
+
24
+ # Development: venv + editable install (includes dev extras)
25
+ python3 -m venv .venv && source .venv/bin/activate
26
+ pip install -e .[dev]
27
+
28
+ # Environments where pip is unavailable (PEP 668 etc.): runs without installing
29
+ PYTHONPATH=src python3 -m hurdle scan .
30
+ ```
31
+
32
+ ## Quick start
33
+
34
+ ```bash
35
+ # 1) Full scan — gap report for the whole repository (use this to create a baseline)
36
+ hurdle scan ~/study/kopia --json kopia.json
37
+
38
+ # 2) diff mode — evaluate only sources new/changed vs. a base point (core of the local/CI gate)
39
+ hurdle scan . --diff origin/main
40
+
41
+ # 3) strict mode — fail (non-zero exit code) if any evaluated file has a gap
42
+ hurdle scan . --diff origin/main --strict --config .hurdle.json
43
+ ```
44
+
45
+ Reading the output: the report shows a per-file status (`matched` / `gap` /
46
+ `unmapped` — files with unknown extensions are counted only as `unmapped` and
47
+ excluded from language totals), each file's matching test and confidence
48
+ (`exact`/`heuristic`), and per-language totals. Exit codes under `--strict`:
49
+ no gaps = 0, gaps present = failure, runtime error (e.g. `--diff` outside a
50
+ git repository) = 2. CI decides pass/fail from the strict-mode exit code.
51
+
52
+ ## Verdict rules (per language)
53
+
54
+ | Language | Test-existence verdict | confidence |
55
+ |---|---|---|
56
+ | **go** | Package-level: an exact `{stem}_test.go` match wins first; otherwise covered if any `*_test.go` exists in the same package (directory) | exact |
57
+ | **py** | Probes 4 pytest-convention candidate paths — beside the file / in a `tests/` directory × `test_{stem}.py` / `{stem}_test.py` combinations — plus variant names `tests/test_{stem}_*.py` and `tests/test_*_{stem}.py` (v0.2.0). `__init__.py` counts as a package marker and non-test files under `test_dirs` (default `tests`, `test`) count as test-support — both excluded rather than gapped (config: `strict_init`, `test_dirs`) | exact |
58
+ | **ts/js** | Naming conventions: the `*.test.ts(x)` / `*.spec.ts(x)` families | exact |
59
+ | **c / shell** | File-to-file mapping is impossible in trees like lustre (centralized `lustre/tests/` + `kunit/`), so coverage is aggregated per module/directory (heuristic). Listing module→test keywords in `module_map` improves accuracy | heuristic |
60
+
61
+ ## Configuration (.hurdle.json)
62
+
63
+ Passed via `--config`. See `.hurdle.example.json` in this repository for a
64
+ minimal example and `baselines/*.hurdle.json` for real-world ones.
65
+
66
+ ```jsonc
67
+ {
68
+ "exclude": ["vendor/", "**/*_pb.go"], // kept out of the scan
69
+ "allowlist": { "cmd/legacy/main.go": "thin wrapper; covered in pkg/" },
70
+ "module_map": { "lustre/osd-zfs": ["osd", "conf-sanity"] }
71
+ }
72
+ ```
73
+
74
+ | Key | Format | Description |
75
+ |---|---|---|
76
+ | `exclude` | array of strings | Directories are excluded wholesale with a trailing `/` in the name (`vendor/`). Everything else is an fnmatch pattern matched against full paths/filenames (`**/*_pb.go`) |
77
+ | `allowlist` | relpath → reason string | Do not count this file as a gap (escape hatch). Checked **before exclude**, so a file with an explicit reason survives even broad exclude patterns. The reason stays on record in commit history |
78
+ | `module_map` | module relpath → keyword array | Feeds the C/shell heuristic. List the test-suite keywords that cover a module (e.g. `["sanity", "conf-sanity"]`) and module coverage is looked up in the centralized tests/ directory |
79
+
80
+ ## Baseline → gate workflow
81
+
82
+ The core design is a **ratchet**: existing gaps are frozen, and only new gaps
83
+ are blocked.
84
+
85
+ 1. **Capture a baseline** — run a full scan, commit the resulting JSON gap
86
+ report (covering all existing code) to the repository. This becomes a
87
+ de-facto allowlist. The actual results of doing this for the kopia/lustre/
88
+ longhorn-manager/velero repositories are in [BASELINES.md](BASELINES.md)
89
+ and `baselines/*.json`.
90
+ 2. **Classify with config** — filter generated code (`*_pb.go` etc.), vendor,
91
+ and test-support code (`internal/testutil` etc.) via `exclude`/`allowlist`
92
+ so that only files with genuinely no corresponding test remain in the
93
+ baseline.
94
+ 3. **diff + strict gate** — in CI, `--diff origin/<base> --strict` judges only
95
+ the files changed now. Legacy gaps never show up in the diff and are
96
+ ignored; only new/modified files are forced to carry tests. The gap count
97
+ decreases monotonically.
98
+
99
+ ## CI integration
100
+
101
+ Copy `ci/test-exist-gate.yml` to `.github/workflows/test-exist-gate.yml` in the
102
+ target repository and follow the 4 steps in the comment block at the top of
103
+ the file (swap the URL, commit the config, mark the check as required). The
104
+ flow: `fetch-depth: 0` checkout → install hurdle → run
105
+ `scan . --diff origin/base --strict --config .hurdle.json --json` → upload the
106
+ report artifact even on failure (`if: always()`).
107
+
108
+ ## pre-commit local hook
109
+
110
+ Copy `ci/pre-commit-hook.sh` to `.git/hooks/pre-commit`, or use this minimal
111
+ 3-line form:
112
+
113
+ ```bash
114
+ #!/bin/sh
115
+ [ -n "$(git diff --name-only --diff-filter=ACMR HEAD)" ] || exit 0
116
+ exec hurdle scan . --diff HEAD --strict
117
+ ```
118
+
119
+ ## Limitations (honestly)
120
+
121
+ - **It only checks file existence.** It never sees whether tests run, pass, or
122
+ assert anything meaningful. It is a minimal gate against "source added with
123
+ no test" — not a coverage replacement.
124
+ - **Heuristic module verdicts can over- and under-count.** The module-aggregated
125
+ C/shell verdict depends on `module_map` keywords: keywords that are too
126
+ broad over-report coverage; a missing per-module suite under-reports it.
127
+ Treat the report's confidence markers as the trust boundary.
128
+ - **The only escape hatch is the allowlist.** When a rule misjudges a file,
129
+ allowlisting it with a reason is the sole exception path — hiding it with
130
+ exclude removes it from the scan entirely and breaks gap tracking.
131
+
132
+ ## License
133
+
134
+ Apache-2.0 — see the [LICENSE](LICENSE) file for the full text.
135
+
136
+ ## Universe coverage (`hurdle universe`)
137
+
138
+ Beyond per-file test existence, hurdle can enforce coverage of a
139
+ **defined universe** — a complete set of items every one of which must be
140
+ either used, wildcard-covered, or explicitly allowlisted. The motivating
141
+ case: CDP protocol commands/events (`protocol.json` defines the complete
142
+ universe, so "missing something" is well-defined).
143
+
144
+ ```jsonc
145
+ // .hurdle.json
146
+ "universes": {
147
+ "cdp-commands": {
148
+ "items_file": "universes/cdp-commands.json", // bare array or {"items":[], "meta":{}}
149
+ "include": ["src/**/*.py"],
150
+ "literal_shape": "^[A-Z][A-Za-z0-9]*\\.[a-zA-Z][A-Za-z0-9]+$",
151
+ "wildcard_patterns": ["\\.subscribe\\(\\s*\"({domain})\\.\\*\""],
152
+ "extra_usage": ["Page.javascriptDialogOpening"],
153
+ "allowlist": {"Tracing.*": "out of scope — low-level tracing"}
154
+ }
155
+ }
156
+ ```
157
+
158
+ ```bash
159
+ hurdle universe cdp-commands . --strict --json report.json
160
+ ```
161
+
162
+ - Usage extraction collects shape-matched string literals (module
163
+ constants are picked up at their definition site) and intersects them
164
+ with the universe — universe membership itself disambiguates commands
165
+ vs events that share the `Domain.name` shape.
166
+ - Statuses: `covered` / `wildcard` (a `Domain.*` subscription) /
167
+ `allowed` (fnmatch on item names, reason recorded) / `gap`.
168
+ - `--strict` exits 1 on any gap that is not allowlisted — newly added
169
+ universe items cannot appear silently.
@@ -0,0 +1,32 @@
1
+ [build-system]
2
+ requires = ["setuptools>=68"]
3
+ build-backend = "setuptools.build_meta"
4
+
5
+ [project]
6
+ name = "hurdle-gate"
7
+ version = "0.3.1"
8
+ description = "Static-analysis gate for source↔test file existence mapping"
9
+ readme = "README.md"
10
+ requires-python = ">=3.9"
11
+ license = "Apache-2.0"
12
+ keywords = ["testing", "test-coverage", "static-analysis", "ci", "quality-gate"]
13
+ classifiers = [
14
+ "Programming Language :: Python :: 3",
15
+ "Topic :: Software Development :: Quality Assurance",
16
+ "Development Status :: 4 - Beta",
17
+ ]
18
+
19
+ [project.optional-dependencies]
20
+ dev = ["pytest>=7"]
21
+
22
+ [project.scripts]
23
+ hurdle = "hurdle.cli:main"
24
+
25
+ [tool.setuptools]
26
+ package-dir = {"" = "src"}
27
+ packages = ["hurdle"]
28
+
29
+ [tool.pytest.ini_options]
30
+ pythonpath = ["src"]
31
+ testpaths = ["tests"]
32
+ addopts = "--ignore=tests/fixtures --ignore=tests/fixtures02 --ignore=tests/fixtures03"
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+
@@ -0,0 +1,3 @@
1
+ """hurdle — static-analysis gate for source↔test file existence mapping."""
2
+
3
+ __version__ = "0.3.1"
@@ -0,0 +1,5 @@
1
+ import sys
2
+
3
+ from hurdle.cli import main
4
+
5
+ sys.exit(main())