crossref-matcher 1.2.2__tar.gz → 1.3.0__tar.gz

{crossref_matcher-1.2.2 → crossref_matcher-1.3.0}/MANIFEST.in

@@ -1,5 +1,6 @@
 include crossref_matcher/resources/plugins.json
 include crossref_matcher/resources/VERSION.txt
+recursive-include crossref_matcher/strategies *.txt
 recursive-include crossref_matcher/resources/data/models *.pkl *.gz *.local
 recursive-include crossref_matcher/resources/data/common_ror_endings *.txt
 recursive-include crossref_matcher/resources/data/countries *.txt

{crossref_matcher-1.2.2/crossref_matcher.egg-info → crossref_matcher-1.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: crossref-matcher
-Version: 1.2.2
+Version: 1.3.0
 Summary: Crossref's matching API
 Home-page: https://gitlab.com/crossref/marple
 Author: Crossref

{crossref_matcher-1.2.2 → crossref_matcher-1.3.0}/README.md

@@ -135,6 +135,49 @@ Strategies are located in the [strategies directory](crossref_matcher/strategies
 
 Strategies must be added to the "enabled" list in [plugins.json](crossref_matcher/resources/plugins.json) before they can be used.
 
+### Strategy versioning
+
+Each strategy directory can contain a `version.txt` file with a two-part version number (`MAJOR.MINOR`). This versioning is independent of the project's semver.
+
+```
+crossref_matcher/strategies/preprint/sbmv/
+├── strategy.py
+└── version.txt        # contains e.g. "1.2"
+```
+
+When a strategy is loaded, its version is automatically available as a class attribute:
+
+```python
+from crossref_matcher.strategies.preprint.sbmv.strategy import Sbmv
+print(Sbmv.version)  # "1.2"
+```
+
+Strategies without a `version.txt` have `version = None`.
+
+**Bumping a version:**
+
+```sh
+python scripts/bump_strategy_version.py preprint/sbmv minor   # 1.2 → 1.3
+python scripts/bump_strategy_version.py preprint/sbmv major   # 1.2 → 2.0
+```
+
+The path argument can be relative to the `strategies/` directory or an absolute path.
+
+**CI enforcement:**
+
+A CI job (`check-strategy-versions` in `.gitlab-ci.yml`) fails any merge request where a strategy's files are changed but `version.txt` is not updated. To bypass for a trivial change (e.g. a typo fix):
+
+- Pass `--force` to the check script, or
+- Set the `SKIP_BUMP_CHECK=1` environment variable on the pipeline run.
+
+**Local pre-commit hook:**
+
+To enable the check locally (as a non-blocking warning):
+
+```sh
+git config core.hooksPath .githooks
+```
+
 ### Dependencies
 
 Requirements are defined in `setup.py`. Requirements files with exact versions can be updated with `pip-compile`, which is a part of `pip-tools`. First run `pip install pip-tools`. Then:

crossref_matcher-1.3.0/crossref_matcher/resources/VERSION.txt

@@ -0,0 +1 @@
+1.3.0

{crossref_matcher-1.2.2 → crossref_matcher-1.3.0}/crossref_matcher/strategies/__init__.py

@@ -20,17 +20,25 @@ import logging
 
 logger = logging.getLogger(__name__)
 
+STRATEGIES_DIR = "crossref_matcher/strategies"
 
-def pascal_to_snake_case(s):
+
+def pascal_to_snake_case(s: str) -> str:
     return re.sub(r"(?<!^)(?=[A-Z])", "_", s).lower()
 
 
-def kebab_to_snake_case(string: str) -> str:
+def kebab_to_snake_case(string: str | None) -> str | None:
     if string is None:
         return None
     return "_".join(string.split("-"))
 
 
+def snake_to_kebab_case(string: str | None) -> str | None:
+    if string is None:
+        return None
+    return "-".join(string.split("_"))
+
+
 class NoDefaultStrategyError(ValueError):
     """Raised when no default strategy is configured for a task."""
 
@@ -57,6 +65,7 @@ class Strategy(ABC):
     id: str
     task: MatchTask
     description: str
+    version: str | None = None
 
     @classmethod
     def create_dummy_subclass(cls, module_name: str, error: str):
@@ -230,6 +239,13 @@ class Strategy(ABC):
                 raise TypeError(
                     f"Class {cls.__name__} must have a class field '{name}' of type {type.__name__}."
                 )
+        try:
+            pkg = cls.__module__.removesuffix(".strategy")
+            version_ref = resources.files(pkg) / "version.txt"
+            if version_ref.is_file():
+                cls.version = version_ref.read_text().strip()
+        except (TypeError, OSError, ModuleNotFoundError):
+            pass
 
     @classmethod
     def is_default(cls):
@@ -274,7 +290,7 @@ def list_strategies(
 
 
 def get_strategy_by_id(
-    strategy_id: str | None,
+    strategy_id: str | None = None,
     task: MatchTask | str | None = None,
     allow_disabled: bool = False,
 ) -> type[Strategy]:
@@ -298,7 +314,11 @@ def get_strategy_by_id(
             raise ValueError("Must specify at least one of [strategy_id, task]")
         return get_default_strategy(task)
     strategy_found = False
-    for id_to_check in [strategy_id, kebab_to_snake_case(strategy_id)]:
+    for id_to_check in [
+        strategy_id,
+        kebab_to_snake_case(strategy_id),
+        snake_to_kebab_case(strategy_id),
+    ]:
         strategy = [
             c
             for c in list_strategies(task=task, include_disabled=allow_disabled)
@@ -354,7 +374,7 @@ def get_strategy_by_module_name(
 
 
 def get_strategy(
-    strategy_id: str | None,
+    strategy_id: str | None = None,
     task: MatchTask | str | None = None,
     allow_disabled: bool = False,
 ) -> type[Strategy]:

crossref_matcher-1.3.0/crossref_matcher/strategies/funder/funder_name_to_ror_search/version.txt

@@ -0,0 +1 @@
+1.0

crossref_matcher-1.3.0/crossref_matcher/strategies/versioning.py

@@ -0,0 +1,77 @@
+import logging
+import subprocess
+from pathlib import PurePosixPath
+
+from crossref_matcher.strategies import STRATEGIES_DIR
+
+logger = logging.getLogger(__name__)
+
+_STRATEGIES_PATH = PurePosixPath(STRATEGIES_DIR)
+
+
+def _strategy_dir(path: str) -> str | None:
+    """Return 'task/strategy' for a path inside the strategies dir, or None."""
+    try:
+        rel = PurePosixPath(path).relative_to(_STRATEGIES_PATH)
+    except ValueError:
+        return None
+    if len(rel.parts) < 3:  # need task / strategy / filename at minimum
+        return None
+    return f"{rel.parts[0]}/{rel.parts[1]}"
+
+
+def get_changed_files(base: str | None, staged: bool) -> list[str]:
+    if staged:
+        result = subprocess.run(
+            ["git", "diff", "--cached", "--name-only"],
+            capture_output=True,
+            text=True,
+            check=True,
+        )
+    elif base:
+        result = subprocess.run(
+            ["git", "diff", "--name-only", f"{base}...HEAD"],
+            capture_output=True,
+            text=True,
+            check=True,
+        )
+    else:
+        raise ValueError("Must specify --base or --staged")
+    return result.stdout.splitlines()
+
+
+def get_changed_strategy_dirs(changed_files: list[str]) -> set[str]:
+    return {
+        _strategy_dir(f)
+        for f in changed_files
+        if PurePosixPath(f).name != "version.txt"
+        if _strategy_dir(f) is not None
+    }
+
+
+def check(base: str | None, staged: bool) -> bool:
+    changed_files = get_changed_files(base, staged)
+    changed_dirs = get_changed_strategy_dirs(changed_files)
+
+    if not changed_dirs:
+        return True
+
+    bumped_dirs = {
+        _strategy_dir(f)
+        for f in changed_files
+        if PurePosixPath(f).name == "version.txt"
+        if _strategy_dir(f) is not None
+    }
+
+    failures = sorted(changed_dirs - bumped_dirs)
+    if failures:
+        missing = "\n".join(f"  {STRATEGIES_DIR}/{d}/version.txt" for d in failures)
+        logger.error(
+            "The following strategies have changes but no version bump:\n%s\n"
+            "\nRun: python scripts/bump_strategy_version.py <strategy-path> <major|minor>"
+            "\nTo skip: rerun with --force, or set SKIP_BUMP_CHECK=1",
+            missing,
+        )
+        return False
+
+    return True

{crossref_matcher-1.2.2 → crossref_matcher-1.3.0/crossref_matcher.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: crossref-matcher
-Version: 1.2.2
+Version: 1.3.0
 Summary: Crossref's matching API
 Home-page: https://gitlab.com/crossref/marple
 Author: Crossref

{crossref_matcher-1.2.2 → crossref_matcher-1.3.0}/crossref_matcher.egg-info/SOURCES.txt

@@ -69,6 +69,7 @@ crossref_matcher/resources/data/models/reference_nn_unstructured/eval/events.out
 crossref_matcher/resources/data/models/reference_nn_unstructured/train/events.out.tfevents.1681511550.knopfler.local
 crossref_matcher/strategies/__init__.py
 crossref_matcher/strategies/common.py
+crossref_matcher/strategies/versioning.py
 crossref_matcher/strategies/affiliation/__init__.py
 crossref_matcher/strategies/affiliation/es_utils.py
 crossref_matcher/strategies/affiliation/matching.py
@@ -80,6 +81,7 @@ crossref_matcher/strategies/affiliation/single_search/strategy.py
 crossref_matcher/strategies/funder/__init__.py
 crossref_matcher/strategies/funder/funder_name_to_ror_search/__init__.py
 crossref_matcher/strategies/funder/funder_name_to_ror_search/strategy.py
+crossref_matcher/strategies/funder/funder_name_to_ror_search/version.txt
 crossref_matcher/strategies/healthcheck/__init__.py
 crossref_matcher/strategies/healthcheck/healthcheck/__init__.py
 crossref_matcher/strategies/healthcheck/healthcheck/strategy.py

crossref_matcher-1.2.2/crossref_matcher/resources/VERSION.txt

@@ -1 +0,0 @@
-1.2.2