V1.5.1

pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "docx-comment-parser"
-version = "1.5.0"
+version = "1.5.1"
 description = "Fast C++ library for extracting comment metadata from .docx files"
 readme = "README.md"
 requires-python = ">=3.9"

setup.py

@@ -28,6 +28,15 @@
 ROOT = os.path.dirname(os.path.abspath(__file__))
 
 
+def _read_long_description() -> str:
+    """Return README.md's contents, or an empty string if it is absent."""
+    readme = os.path.join(ROOT, "README.md")
+    if not os.path.exists(readme):
+        return ""
+    with open(readme, encoding="utf-8") as fh:
+        return fh.read()
+
+
 def _is_mingw() -> bool:
     """Return True when building with MinGW-w64 GCC under Windows."""
     if sys.platform != "win32":
@@ -126,14 +135,10 @@ def _is_mingw() -> bool:
 
 setup(
     name="docx-comment-parser",
-    version="1.3.0",
+    version="1.5.1",
     author="nick-developer",
     description="Fast C++ library for extracting comment metadata from .docx files",
-    long_description=(
-        open(os.path.join(ROOT, "README.md"), encoding="utf-8").read()
-        if os.path.exists(os.path.join(ROOT, "README.md"))
-        else ""
-    ),
+    long_description=_read_long_description(),
     long_description_content_type="text/markdown",
     ext_modules=[ext],
     # Pure-Python wrapper package (exporters, filters, CLI) lives in src/.
@@ -151,9 +156,13 @@ def _is_mingw() -> bool:
         "polars": ["polars>=1.0"],
         "cli": ["typer>=0.12", "rich>=13.0"],
         "report": ["jinja2>=3.0"],
+        # Kept in step with pyproject.toml: accelerated fuzzy matching for the
+        # diff engine, and exact token counts for chunking and compression.
+        "diff": ["rapidfuzz>=3.0"],
+        "llm": ["tiktoken>=0.7"],
         "all": [
             "pandas>=2.0", "polars>=1.0", "typer>=0.12", "rich>=13.0",
-            "jinja2>=3.0",
+            "jinja2>=3.0", "rapidfuzz>=3.0", "tiktoken>=0.7",
         ],
     },
     entry_points={

src/docx_comment_parser/__init__.py

@@ -25,6 +25,15 @@
     records = parser.to_llm_dataset(anonymize="strict")
     parser.export_jsonl("review.jsonl")
 
+and in 1.5.1 you choose how much of the document comes with each comment, fix
+the classifier's tags by hand, and spend fewer tokens doing it::
+
+    records = parser.to_llm_dataset(
+        context={"unit": "sentences", "before": 2, "after": 1},
+        overrides={4: {"priority": "blocker"}},
+        compress="balanced",
+    )
+
 Export methods are attached to the compiled ``DocxParser`` / ``BatchParser``
 classes at import time.  That is deliberate: it keeps a single parser object as
 the one thing a user needs to hold, rather than introducing a second wrapper
@@ -33,7 +42,7 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Sequence, Union
+from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Union
 
 # ─── Compiled core ───────────────────────────────────────────────────────────
 # Re-exported verbatim so `dcp.DocxParser` etc. resolve exactly as they did
@@ -60,9 +69,19 @@
     import pandas
     import polars
 
-    from .llm.dataset import LLMDataset
+    # The lazily resolved names below (see ``_LAZY``), declared here so static
+    # analysers can see every entry of ``__all__``.  Never executed at runtime.
+    from . import comparison, llm, privacy, reporting
+    from .comparison.diff_engine import DiffResult, compare_comments
+    from .llm.chunking import estimate_tokens
+    from .llm.classification import classify_comment
+    from .llm.dataset import LLMDataset, LLMRecord
+    from .llm.dataset import build_dataset as build_llm_dataset
+    from .privacy.anonymizer import Anonymizer, anonymize_comments, scan_comments
+    from .privacy.policy import AnonymizationPolicy
+    from .reporting.analytics import build_report_data
 
-__version__ = "1.5.0"
+__version__ = "1.5.1"
 
 __all__ = [
     # compiled core (unchanged public API)
@@ -309,11 +328,14 @@ def _parser_to_llm_records(
     classify: bool = True,
     anonymize: Optional[Any] = None,
     anonymizer: Optional[Any] = None,
+    **kwargs: Any,
 ) -> "LLMDataset":
     """Return this document's comments as an :class:`LLMDataset`.
 
     The object form of :meth:`to_llm_dataset`: same records, plus the
-    anonymisation report and the vault that reverses it.
+    anonymisation report and the vault that reverses it.  Also takes
+    ``context=`` (sentences, paragraphs, words), ``overrides=`` (manual tags)
+    and ``compress=`` (token reduction) — see ``llm.build_dataset``.
     """
     from .llm.dataset import build_dataset
 
@@ -326,6 +348,7 @@ def _parser_to_llm_records(
         classify=classify,
         anonymize=anonymize,
         anonymizer=anonymizer,
+        **kwargs,
     )
 
 
@@ -370,17 +393,25 @@ def _parser_to_embeddings_input(
     )
 
 
+#: build_dataset keywords that to_llm_chunks forwards, as opposed to the
+#: chunking keywords it passes to Chunk packing.
+_DATASET_OPTIONS = frozenset(
+    {
+        "chars_before", "chars_after", "include_thread", "include_context",
+        "classify", "anonymize", "anonymizer", "documents", "context",
+        "overrides", "compress",
+    }
+)
+
+
 def _parser_to_llm_chunks(
     self: DocxParser, max_tokens: int = 100_000, **kwargs: Any
 ) -> List[Any]:
     """Split this document's records into context-window-sized chunks."""
     dataset_kwargs = {
         key: kwargs.pop(key)
         for key in list(kwargs)
-        if key in {
-            "chars_before", "chars_after", "include_thread",
-            "include_context", "classify", "anonymize", "anonymizer",
-        }
+        if key in _DATASET_OPTIONS
     }
     return _parser_to_llm_records(self, **dataset_kwargs).chunks(max_tokens, **kwargs)