python-redlines 0.2.1__tar.gz → 1.0.0__tar.gz

{python_redlines-0.2.1 → python_redlines-1.0.0}/.gitignore

@@ -13,6 +13,9 @@ docxodus/**/obj/*
 packages/*/src/*/_binaries/*.tar.gz
 packages/*/src/*/_binaries/*.zip
 
+# MkDocs build output
+site/
+
 # C extensions
 *.so
 

{python_redlines-0.2.1 → python_redlines-1.0.0}/PKG-INFO

@@ -1,14 +1,16 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: python-redlines
-Version: 0.2.1
-Summary: Generate tracked-change redline .docx documents by comparing Word files.
+Version: 1.0.0
+Summary: Open-source DOCX comparison tool to generate native Word tracked changes (redlines) in Python without MS Word dependencies.
 Project-URL: Homepage, https://github.com/JSv4/Python-Redlines
+Project-URL: Documentation, https://jsv4.github.io/Python-Redlines/
+Project-URL: Demo, https://redlines.opensource.legal
 Project-URL: Issues, https://github.com/JSv4/Python-Redlines/issues
 Project-URL: Source, https://github.com/JSv4/Python-Redlines
 Author: John Scrudato IV
 License-Expression: MIT
-Keywords: diff,docx,openxml,redline,tracked-changes,word
-Classifier: Development Status :: 4 - Beta
+Keywords: compare-word-documents,diff,docx,docx-comparison,docxodus,legal-tech,openxml,python-docx-diff,redline,track-changes-api,tracked-changes,word
+Classifier: Development Status :: 5 - Production/Stable
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3.9
@@ -57,6 +59,9 @@ redline_bytes, stdout, stderr = engine.run_redline(
 )
 ```
 
+`DocxodusEngine` accepts `engine="wmlcomparer"` (default) or `engine="docxdiff"` to select the
+comparison algorithm. See the [project README](https://github.com/JSv4/Python-Redlines#choosing-an-engine).
+
 If an engine's companion package is not installed, instantiating the engine
 raises `EngineNotInstalledError` with the `pip install` command to fix it.
 

{python_redlines-0.2.1 → python_redlines-1.0.0}/README.md

@@ -28,6 +28,9 @@ redline_bytes, stdout, stderr = engine.run_redline(
 )
 ```
 
+`DocxodusEngine` accepts `engine="wmlcomparer"` (default) or `engine="docxdiff"` to select the
+comparison algorithm. See the [project README](https://github.com/JSv4/Python-Redlines#choosing-an-engine).
+
 If an engine's companion package is not installed, instantiating the engine
 raises `EngineNotInstalledError` with the `pip install` command to fix it.
 

{python_redlines-0.2.1 → python_redlines-1.0.0}/pyproject.toml

@@ -5,16 +5,29 @@ build-backend = "hatchling.build"
 [project]
 name = "python-redlines"
 dynamic = ["version"]
-description = "Generate tracked-change redline .docx documents by comparing Word files."
+description = "Open-source DOCX comparison tool to generate native Word tracked changes (redlines) in Python without MS Word dependencies."
 readme = "README.md"
 requires-python = ">=3.9"
 license = "MIT"
-keywords = ["docx", "redline", "diff", "tracked-changes", "openxml", "word"]
+keywords = [
+  "docx",
+  "redline",
+  "diff",
+  "tracked-changes",
+  "openxml",
+  "word",
+  "docx-comparison",
+  "compare-word-documents",
+  "track-changes-api",
+  "python-docx-diff",
+  "legal-tech",
+  "docxodus",
+]
 authors = [
   { name = "John Scrudato IV" },
 ]
 classifiers = [
-  "Development Status :: 4 - Beta",
+  "Development Status :: 5 - Production/Stable",
   "License :: OSI Approved :: MIT License",
   "Programming Language :: Python",
   "Programming Language :: Python :: 3.9",
@@ -31,12 +44,17 @@ dependencies = [
 # its extra, e.g. `pip install python-redlines[docxodus]`. All three packages
 # are released together from the same repository on each tagged release.
 [project.optional-dependencies]
+# Deprecated: wraps the archived Open-XML-PowerTools WmlComparer. Kept so that
+# anyone who needs that algorithm's output has somewhere to stand; `all` keeps
+# installing it so the extra does not change meaning under existing pins.
 ooxmlpowertools = ["python-redlines-ooxmlpowertools"]
 docxodus = ["python-redlines-docxodus"]
 all = ["python-redlines-ooxmlpowertools", "python-redlines-docxodus"]
 
 [project.urls]
 Homepage = "https://github.com/JSv4/Python-Redlines"
+Documentation = "https://jsv4.github.io/Python-Redlines/"
+Demo = "https://redlines.opensource.legal"
 Issues = "https://github.com/JSv4/Python-Redlines/issues"
 Source = "https://github.com/JSv4/Python-Redlines"
 

{python_redlines-0.2.1 → python_redlines-1.0.0}/src/python_redlines/__about__.py

@@ -1,4 +1,4 @@
 # SPDX-FileCopyrightText: 2024-present U.N. Owen <void@some.where>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.2.1"
+__version__ = "1.0.0"

{python_redlines-0.2.1 → python_redlines-1.0.0}/src/python_redlines/engines.py

@@ -6,6 +6,7 @@ import platform
 import subprocess
 import tarfile
 import tempfile
+import warnings
 import zipfile
 from pathlib import Path
 from typing import Optional, Tuple, Union
@@ -138,18 +139,26 @@ class BaseEngine(object):
         Runs the redline binary. The 'original' and 'modified' arguments can be either bytes or file paths
         (as ``str`` or ``pathlib.Path``). Returns the redline output as bytes.
 
-        Additional keyword arguments are passed to _build_command() for engine-specific options.
-        DocxodusEngine supports: detail_threshold, case_insensitive, detect_moves,
-        simplify_move_markup, move_similarity_threshold, move_minimum_word_count,
-        detect_format_changes, conflate_spaces, date_time.
+        A path the caller supplies is never deleted; only scratch files this
+        method creates are cleaned up.
+
+        Additional keyword arguments are passed to _build_command() for engine-specific
+        options. DocxodusEngine supports: case_insensitive, detect_moves,
+        move_similarity_threshold, move_minimum_word_count, detect_format_changes,
+        conflate_spaces, date_time. It raises ValueError for unrecognised settings and
+        for the WmlComparer-era settings removed in Docxodus v11.0.0 (engine,
+        detail_threshold, simplify_move_markup). XmlPowerToolsEngine ignores kwargs.
         """
-        temp_files = []
+        scratch_files = []
         try:
+            # mkstemp, not NamedTemporaryFile: we want a path, and NamedTemporaryFile
+            # hands back an open file object that nothing here would close (issue #30).
+            handle, target_path = tempfile.mkstemp(suffix='.docx')
+            os.close(handle)
+            scratch_files.append(target_path)
 
-            target_path = tempfile.NamedTemporaryFile(delete=False).name
-            original_path = self._write_to_temp_file(original) if isinstance(original, bytes) else original
-            modified_path = self._write_to_temp_file(modified) if isinstance(modified, bytes) else modified
-            temp_files.extend([target_path, original_path, modified_path])
+            original_path = self._as_path(original, scratch_files)
+            modified_path = self._as_path(modified, scratch_files)
 
             command = self._build_command(author_tag, original_path, modified_path, target_path, **kwargs)
 
@@ -164,14 +173,27 @@ class BaseEngine(object):
             return redline_output, stdout_output, stderr_output
 
         finally:
-            self._cleanup_temp_files(temp_files)
+            self._cleanup_temp_files(scratch_files)
+
+    def _as_path(self, document, scratch_files):
+        """Return a filesystem path for *document*, writing bytes out if needed.
+
+        Only a path this method creates is appended to *scratch_files*. A path
+        the caller passed in is the caller's own document, and registering it
+        for cleanup would delete the file they asked us to compare.
+        """
+        if isinstance(document, bytes):
+            path = self._write_to_temp_file(document)
+            scratch_files.append(path)
+            return path
+        return os.fspath(document)
 
     def _cleanup_temp_files(self, temp_files):
         for file_path in temp_files:
             try:
                 os.remove(file_path)
             except OSError as e:
-                print(f"Error deleting temp file {file_path}: {e}")
+                logger.warning("Error deleting temp file %s: %s", file_path, e)
 
     def _write_to_temp_file(self, data):
         """
@@ -188,17 +210,49 @@ class XmlPowerToolsEngine(BaseEngine):
     BINARY_BASE_NAME = 'redlines'
     EXTRA_NAME = 'ooxmlpowertools'
 
+    def __init__(self, target_path: Optional[str] = None):
+        warnings.warn(
+            "XmlPowerToolsEngine wraps the original, unmaintained Open-XML-PowerTools "
+            "WmlComparer and is deprecated; it will be removed in a future major "
+            "release. Use DocxodusEngine, which is actively maintained and runs the "
+            "DocxDiff algorithm.",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        super().__init__(target_path)
+
 
 class DocxodusEngine(BaseEngine):
     BINARY_PACKAGE = 'python_redlines_docxodus'
     BINARY_BASE_NAME = 'redline'
     EXTRA_NAME = 'docxodus'
 
+    # Settings that died with WmlComparer in Docxodus v11.0.0. They are rejected
+    # rather than dropped, because dropping them would not be a breaking change
+    # but a wrong-answer one: the v12 CLI rejects --engine as an unknown flag,
+    # and merely warns-and-ignores the other two, so a caller who passed
+    # engine='wmlcomparer' would silently receive DocxDiff output believing they
+    # had selected something else.
+    _REMOVED_KWARGS = {
+        'engine': (
+            "the comparison-engine selector was removed in Docxodus v11.0.0, which "
+            "deleted WmlComparer. DocxDiff is now the only algorithm — drop the argument"
+        ),
+        'detail_threshold': (
+            "it tuned WmlComparer's LCS granularity and went with it in Docxodus "
+            "v11.0.0. DocxDiff's granularity is structural, with no equivalent knob — "
+            "drop the argument"
+        ),
+        'simplify_move_markup': (
+            "it worked around WmlComparer's move markup and went with it in Docxodus "
+            "v11.0.0. DocxDiff renders moves natively — drop the argument"
+        ),
+    }
+
     # Boolean flags (default False — presence enables)
     _BOOL_FLAGS = [
         ('case_insensitive', '--case-insensitive'),
         ('detect_moves', '--detect-moves'),
-        ('simplify_move_markup', '--simplify-move-markup'),
     ]
 
     # Negatable flags (default True — --no- prefix disables)
@@ -209,18 +263,31 @@ class DocxodusEngine(BaseEngine):
 
     # Value flags
     _VALUE_FLAGS = [
-        ('detail_threshold', '--detail-threshold'),
         ('move_similarity_threshold', '--move-similarity-threshold'),
         ('move_minimum_word_count', '--move-minimum-word-count'),
         ('date_time', '--date-time'),
     ]
 
-    @staticmethod
-    def _validate_kwargs(kwargs):
-        if 'detail_threshold' in kwargs:
-            val = kwargs['detail_threshold']
-            if not isinstance(val, (int, float)) or val < 0.0 or val > 1.0:
-                raise ValueError(f"detail_threshold must be a float between 0.0 and 1.0, got {val!r}")
+    @classmethod
+    def _supported_kwargs(cls):
+        """Every comparison setting this engine still understands."""
+        return {name for name, _ in (*cls._BOOL_FLAGS, *cls._NEG_FLAGS, *cls._VALUE_FLAGS)}
+
+    @classmethod
+    def _validate_kwargs(cls, kwargs):
+        # Removed settings first, so they get their specific explanation rather
+        # than being lumped in with typos below.
+        for name, reason in cls._REMOVED_KWARGS.items():
+            if name in kwargs:
+                raise ValueError(f"{name} is no longer supported: {reason}.")
+
+        supported = cls._supported_kwargs()
+        unknown = sorted(set(kwargs) - supported)
+        if unknown:
+            raise ValueError(
+                f"Unknown comparison setting(s): {', '.join(unknown)}. "
+                f"Supported settings: {', '.join(sorted(supported))}."
+            )
 
         if 'move_similarity_threshold' in kwargs:
             val = kwargs['move_similarity_threshold']