Improve the contribs plugin

Author: RobertoPrevato

.github/workflows/build.yml

@@ -20,7 +20,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: [3.8, 3.9, "3.10"]
+        python-version: [3.8, 3.9, "3.10", "3.11"]
 
     steps:
       - uses: actions/checkout@v1
@@ -47,7 +47,7 @@ jobs:
         if: matrix.python-version == '3.10'
 
       - name: Use Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v3
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
 
@@ -97,18 +97,18 @@ jobs:
 
       - name: Install distribution dependencies
         run: pip install build
-        if: matrix.python-version == '3.10'
+        if: matrix.python-version == '3.11'
 
       - name: Create distribution package
         run: python -m build
-        if: matrix.python-version == '3.10'
+        if: matrix.python-version == '3.11'
 
       - name: Upload distribution package
         uses: actions/upload-artifact@master
         with:
           name: dist
           path: dist
-        if: matrix.python-version == '3.10'
+        if: matrix.python-version == '3.11'
 
   publish:
     runs-on: ubuntu-latest
@@ -121,19 +121,28 @@ jobs:
           name: dist
           path: dist
 
-      - name: Publish distribution 📦 to Test PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
+      - name: Use Python 3.11
+        uses: actions/setup-python@v1
         with:
-          skip_existing: true
-          user: __token__
-          password: ${{ secrets.test_pypi_password }}
-          repository_url: https://test.pypi.org/legacy/
+          python-version: '3.11'
+
+      - name: Install dependencies
+        run: |
+          pip install twine
+
+      - name: Publish distribution 📦 to Test PyPI
+        run: |
+          twine upload -r testpypi dist/*
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.test_pypi_password }}
 
       - name: Publish distribution 📦 to PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          user: __token__
-          password: ${{ secrets.pypi_password }}
+        run: |
+          twine upload -r pypi dist/*
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.pypi_password }}
 
       - name: Download CSS pack
         uses: actions/download-artifact@v2

CHANGELOG.md

@@ -5,6 +5,21 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.0.1] - 2023-04-25
+- Improves the `contribs` plugin, adding the possibility to document
+  contributors for a page also using `.txt` files close to `.md` files. This
+  can be useful in several cases:
+- - To document contributors who worked outside of Git, for example when providing
+    pictures for the page, or written content provided to someone who is
+    adding content to the MkDocs site.
+- - To document contributors following a Git history re-write
+- Improves the `contribs` plugin, adding the possibility to exclude files by
+  glob patterns (fix #33).
+- Improves the `contribs` plugin, adding the possibility to merge contributors
+  by name, for scenarios when the same person commits using different names
+  (Git reports different contributors in such cases) and it is preferred
+  displaying information aggregated as single contributor.
+
 ## [1.0.0] - 2022-12-20
 - Adds the possibility to specify a `class` for the root HTML element of `cards`.
 - Fixes a bug in the `contribs` plugin (adds a carriage return before the

Makefile

@@ -37,7 +37,7 @@ test-cov-unit:
 
 
 test-cov:
-	pytest --cov-report html --cov=neoteroi
+	pytest --cov-report html --cov=neoteroi tests
 
 
 format:

neoteroi/mkdocs/__init__.py

@@ -1 +1 @@
-__version__ = "1.0.0"
+__version__ = "1.0.1"

neoteroi/mkdocs/contribs/__init__.py

@@ -8,9 +8,10 @@
 """
 import logging
 from datetime import datetime
+from fnmatch import fnmatch
 from pathlib import Path
 from subprocess import CalledProcessError
-from typing import List, Optional
+from typing import List
 
 from mkdocs.config import config_options as c
 from mkdocs.plugins import BasePlugin
@@ -20,10 +21,35 @@
 from neoteroi.mkdocs.contribs.domain import ContributionsReader, Contributor
 from neoteroi.mkdocs.contribs.git import GitContributionsReader
 from neoteroi.mkdocs.contribs.html import ContribsViewOptions, render_contribution_stats
+from neoteroi.mkdocs.contribs.txt import TXTContributionsReader
 
 logger = logging.getLogger("MARKDOWN")
 
 
+class DefaultContributionsReader(ContributionsReader):
+    """
+    Supports both contributors obtained from Git history and from configuration files.
+    """
+
+    def __init__(self) -> None:
+        super().__init__()
+        self._git_reader = GitContributionsReader()
+        self._txt_reader = TXTContributionsReader()
+
+    def get_contributors(self, file_path: Path) -> List[Contributor]:
+        git_history_contributors = self._git_reader.get_contributors(file_path)
+        configured_contributors = self._txt_reader.get_contributors(file_path)
+        return list(
+            {
+                item.email: item
+                for item in configured_contributors + git_history_contributors
+            }.values()
+        )
+
+    def get_last_modified_date(self, file_path: Path) -> datetime:
+        return self._git_reader.get_last_modified_date(file_path)
+
+
 class ContribsPlugin(BasePlugin):
     _contribs_reader: ContributionsReader
     config_scheme = (
@@ -33,16 +59,14 @@ class ContribsPlugin(BasePlugin):
         ("contributors", c.Type(list, default=[])),
         ("show_last_modified_time", c.Type(bool, default=True)),
         ("show_contributors_title", c.Type(bool, default=False)),
+        ("exclude", c.Type(list, default=[])),
     )
 
     def __init__(self) -> None:
         super().__init__()
-        self._contribs_reader = GitContributionsReader()
-
-    def _read_contributor_merge_with(self, contributor_info) -> Optional[str]:
-        return contributor_info.get("merge_with")
+        self._contribs_reader = DefaultContributionsReader()
 
-    def _handle_merge_contributor_info(
+    def _merge_contributor_by_email(
         self,
         contributors: List[Contributor],
         contributor: Contributor,
@@ -67,6 +91,7 @@ def _handle_merge_contributor_info(
             if parent:
                 parent.count += contributor.count
                 return True
+
         return False
 
     def _get_contributors(self, page_file: File) -> List[Contributor]:
@@ -83,6 +108,7 @@ def _get_contributors(self, page_file: File) -> List[Contributor]:
             contributor_info = next(
                 (item for item in info if item.get("email") == contributor.email), None
             )
+
             if contributor_info:
                 contributor.image = contributor_info.get("image")
                 contributor.key = contributor_info.get("key")
@@ -91,8 +117,24 @@ def _get_contributors(self, page_file: File) -> List[Contributor]:
                     # ignore the contributor's information (can be useful for bots)
                     continue
 
+                if (
+                    "name" in contributor_info
+                    and contributor_info["name"] != contributor.name
+                ):
+                    parent = next(
+                        (
+                            other
+                            for other in contributors
+                            if other.name == contributor_info["name"]
+                        ),
+                        None,
+                    )
+                    if parent:
+                        parent.count += contributor.count
+                        continue
+
                 # should contributor information be merged with another object?
-                if self._handle_merge_contributor_info(
+                if self._merge_contributor_by_email(
                     contributors, contributor, contributor_info
                 ):
                     # skip this item as it was merged with another one
@@ -103,7 +145,7 @@ def _get_contributors(self, page_file: File) -> List[Contributor]:
         return results
 
     def _get_last_commit_date(self, page_file: File) -> datetime:
-        return self._contribs_reader.get_last_commit_date(
+        return self._contribs_reader.get_last_modified_date(
             Path("docs") / page_file.src_path
         )
 
@@ -127,7 +169,18 @@ def _set_contributors(self, markdown: str, page: Page) -> str:
             )
         )
 
+    def _is_ignored_page(self, page: Page) -> bool:
+        if not self.config.get("exclude"):
+            return False
+
+        return any(
+            fnmatch(page.file.src_path, ignored_pattern)
+            for ignored_pattern in self.config["exclude"]
+        )
+
     def on_page_markdown(self, markdown, *args, **kwargs):
+        if self._is_ignored_page(kwargs["page"]):
+            return markdown
         try:
             markdown = self._set_contributors(markdown, kwargs["page"])
         except (CalledProcessError, ValueError) as operation_error:

neoteroi/mkdocs/contribs/domain.py

@@ -20,5 +20,5 @@ def get_contributors(self, file_path: Path) -> List[Contributor]:
         """Obtains the list of contributors for a file with the given path."""
 
     @abstractmethod
-    def get_last_commit_date(self, file_path: Path) -> datetime:
+    def get_last_modified_date(self, file_path: Path) -> datetime:
         """Reads the last commit date of a file."""

neoteroi/mkdocs/contribs/git.py

@@ -1,3 +1,9 @@
+"""
+This module defines a ContributionsReader that obtains contributors' list for a page
+from the Git history. Note that this ContributionsReader won't work well in case of
+history rewrites or files renamed without keeping contributor's history.
+For this reason, it should be used together with a
+"""
 import re
 import subprocess
 from datetime import datetime
@@ -10,7 +16,6 @@
 
 
 class GitContributionsReader(ContributionsReader):
-
     _name_email_rx = re.compile(r"(?P<name>[^\<]+)<(?P<email>[^\>]+)>")
 
     def _decode(self, value: bytes) -> str:
@@ -57,7 +62,7 @@ def get_contributors(self, file_path: Path) -> List[Contributor]:
 
         return list(self.parse_committers(result))
 
-    def get_last_commit_date(self, file_path: Path) -> datetime:
+    def get_last_modified_date(self, file_path: Path) -> datetime:
         """Reads the last commit on a file."""
         result = self._decode(
             subprocess.check_output(

neoteroi/mkdocs/contribs/txt.py

@@ -0,0 +1,87 @@
+import os
+import re
+from datetime import datetime
+from pathlib import Path
+from typing import Iterable, List, Tuple
+
+from dateutil.parser import parse
+
+from neoteroi.mkdocs.contribs.domain import ContributionsReader, Contributor
+
+
+def _read_lines_strip_comments(file_path: Path):
+    with open(str(file_path), mode="rt", encoding="utf8") as file:
+        lines = file.readlines()
+    lines = (re.sub("#.+$", "", x).strip() for x in lines)
+    return [line for line in lines if line]
+
+
+class TXTContributionsReader(ContributionsReader):
+    """
+    A ContributionsReader that can read contributors information described in .txt
+    files.
+    """
+
+    _contrib_rx = re.compile(
+        r"(?P<name>[^\<]+)<(?P<email>[^\>]+)>\s\((?P<count>[^\>]+)\)"
+    )
+
+    _last_mod_time_rx = re.compile(
+        r"^\s*Last\smodified\stime:\s(?P<value>.+)$", re.IGNORECASE | re.MULTILINE
+    )
+
+    def _parse_value(self, value: str) -> Tuple[str, str, int]:
+        match = self._contrib_rx.search(value)
+        if match:
+            values = match.groupdict()
+            name = values["name"].strip()
+            email = values["email"].strip()
+            count = int(values["count"])
+        else:
+            name, email, count = ("", "", -1)
+        return name, email, count
+
+    def _get_txt_file_path(self, file_path: Path) -> Path:
+        path_without_extension = os.path.splitext(file_path)[0]
+        return Path(path_without_extension + ".contribs.txt")
+
+    def _get_contributors_from_txt_file(self, file_path: Path) -> Iterable[Contributor]:
+        for line in _read_lines_strip_comments(file_path):
+            name, email, count = self._parse_value(line)
+            if name and email:
+                yield Contributor(name, email, count)
+
+    def get_contributors(self, file_path: Path) -> List[Contributor]:
+        """
+        Obtains the list of contributors from a txt file with the given path.
+        The file contents should look like:
+
+        Charlie Brown <charlie.brown@peanuts.com> (3)
+
+        Having each line with such pattern:
+
+        Name <email> (Contributions Count)
+
+        and supporting comments using hashes:
+        # Example comment
+        """
+        txt_path = self._get_txt_file_path(file_path)
+
+        if not txt_path.exists():
+            return []
+
+        return list(self._get_contributors_from_txt_file(txt_path))
+
+    def get_last_modified_date(self, file_path: Path) -> datetime:
+        """Reads the last commit date of a file."""
+        txt_path = self._get_txt_file_path(file_path)
+
+        if not txt_path.exists():
+            raise FileNotFoundError()
+
+        match = self._last_mod_time_rx.search(txt_path.read_text("utf8"))
+
+        if match:
+            return parse(match.groups()[0])
+
+        return datetime.min

neoteroi/mkdocs/markdown/tables/spantable.py

@@ -24,7 +24,6 @@ def html_class(self) -> Optional[str]:
 def _iter_coords(
     x: int, y: int, colspan: int, rowspan: int
 ) -> Iterable[Tuple[int, int]]:
-
     for x_increment in range(colspan):
         for y_increment in range(rowspan):
             yield (x + x_increment, y + y_increment)

neoteroi/mkdocs/projects/__init__.py

@@ -12,7 +12,6 @@
 
 
 class ProjectsExtension(Extension):
-
     config = {
         "priority": [12, "The priority to be configured for the extension."],
     }