rc-docparser 0.2.0__tar.gz → 0.2.2__tar.gz

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/CHANGELOG.md

@@ -6,6 +6,19 @@ follows [Semantic Versioning](https://semver.org/).
 
 ## [Unreleased]
 
+## [0.2.2] - 2026-06-19
+### Changed
+- README/PyPI page now leads with the `rc-docparser` distribution name and
+  clarifies the `docparser` import name (docs-only release).
+
+## [0.2.1] - 2026-06-19
+### Changed
+- Packaging aligned with Research Commons conventions: PEP 639 SPDX
+  `license = "MIT"` (with `LICENSE` shipped via `license-files`), single-source
+  version in `src/docparser/_version.py`, `authors = ["rc-docparser contributors"]`,
+  a `Typing :: Typed` classifier, and a `Research Commons` project URL.
+- Tooling: stricter ruff rule set (added `SIM`) and a coverage report config.
+
 ## [0.2.0] - 2026-06-16
 ### Added
 - PPTX parser (extra `[pptx]`): walks slides in order; emits per-slide
@@ -36,6 +49,9 @@ follows [Semantic Versioning](https://semver.org/).
 ### Changed
 - `parse_path` and `run_all` accept the new PDF and captioning options;
   non-PDF parsers ignore PDF-only keyword arguments.
+- Published on PyPI as `rc-docparser` (the bare `docparser` name is blocked by
+  PyPI's project-name similarity guard). The Python import name is unchanged:
+  `import docparser`.
 
 ## [0.1.0] - 2026-06-12
 ### Added

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/PKG-INFO

@@ -1,39 +1,19 @@
 Metadata-Version: 2.4
 Name: rc-docparser
-Version: 0.2.0
+Version: 0.2.2
 Summary: Convert research literature (.docx, .xlsx, .pdf, .html, .pptx, .epub, .txt, .md, .csv) into structured Markdown + JSON corpora, with optional VLM image semantic captioning.
 Project-URL: Homepage, https://github.com/Research-Commons/docparser
 Project-URL: Repository, https://github.com/Research-Commons/docparser
 Project-URL: Issues, https://github.com/Research-Commons/docparser/issues
 Project-URL: Changelog, https://github.com/Research-Commons/docparser/blob/main/CHANGELOG.md
-Author-email: Research Commons <shubhankitsingh@researchcommons.ai>
-License: MIT License
-        
-        Copyright (c) 2026 Research Commons
-        
-        Permission is hereby granted, free of charge, to any person obtaining a copy
-        of this software and associated documentation files (the "Software"), to deal
-        in the Software without restriction, including without limitation the rights
-        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-        copies of the Software, and to permit persons to whom the Software is
-        furnished to do so, subject to the following conditions:
-        
-        The above copyright notice and this permission notice shall be included in all
-        copies or substantial portions of the Software.
-        
-        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-        SOFTWARE.
+Project-URL: Research Commons, https://lab.researchcommons.ai/
+Author: rc-docparser contributors
+License-Expression: MIT
 License-File: LICENSE
 Keywords: corpus,csv,docx,epub,html,literature,markdown,ocr,parser,pdf,pptx,rag,vlm,xlsx
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
-Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
@@ -41,6 +21,7 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering
 Classifier: Topic :: Text Processing :: Markup
+Classifier: Typing :: Typed
 Requires-Python: >=3.10
 Requires-Dist: lxml>=5.3.0
 Requires-Dist: openpyxl>=3.1.5
@@ -99,7 +80,9 @@ Provides-Extra: vlm
 Requires-Dist: requests>=2.32.3; extra == 'vlm'
 Description-Content-Type: text/markdown
 
-# docparser
+# rc-docparser
+
+_Published on PyPI as **`rc-docparser`**; import it as `docparser` (`import docparser`)._
 
 Convert research literature (`.docx`, `.xlsx`, `.pdf`, `.html`, `.pptx`,
 `.epub`, `.txt`, `.md`, `.csv`) into a clean, reproducible **Markdown + JSON**
@@ -121,29 +104,32 @@ via OpenRouter, OpenAI, Gemini, a local server, or a fully-local model.
 
 ## Install
 
+The package is published on PyPI as **`rc-docparser`**; the Python import name
+is `docparser` (i.e. `import docparser`).
+
 ```bash
-pip install docparser              # core: docx + xlsx + txt/md + csv/tsv
-pip install 'docparser[pdf]'       # + PyMuPDF for PDFs
-pip install 'docparser[html]'      # + trafilatura + bs4 for HTML
-pip install 'docparser[pptx]'      # + python-pptx for PowerPoint
-pip install 'docparser[epub]'      # + EbookLib + bs4 for EPUB
-pip install 'docparser[vlm]'       # + requests for API VLM captions
-pip install 'docparser[all]'       # everything above (recommended)
+pip install rc-docparser              # core: docx + xlsx + txt/md + csv/tsv
+pip install 'rc-docparser[pdf]'       # + PyMuPDF for PDFs
+pip install 'rc-docparser[html]'      # + trafilatura + bs4 for HTML
+pip install 'rc-docparser[pptx]'      # + python-pptx for PowerPoint
+pip install 'rc-docparser[epub]'      # + EbookLib + bs4 for EPUB
+pip install 'rc-docparser[vlm]'       # + requests for API VLM captions
+pip install 'rc-docparser[all]'       # everything above (recommended)
 ```
 
 Higher-fidelity / heavier features are separate opt-in extras (so the core
 install stays small and MIT):
 
 ```bash
-pip install 'docparser[tables]'       # + pdfplumber for PDF table extraction
-pip install 'docparser[ocr]'          # + rapidocr-onnxruntime for scanned PDFs
-pip install 'docparser[pymupdf4llm]'  # PyMuPDF4LLM PDF backend (AGPL/commercial)
-pip install 'docparser[docling]'      # IBM Docling PDF backend (MIT)
-pip install 'docparser[marker]'       # Datalab Marker PDF backend (GPL-3.0)
-pip install 'docparser[localvlm]'     # transformers/torch local captioning
+pip install 'rc-docparser[tables]'       # + pdfplumber for PDF table extraction
+pip install 'rc-docparser[ocr]'          # + rapidocr-onnxruntime for scanned PDFs
+pip install 'rc-docparser[pymupdf4llm]'  # PyMuPDF4LLM PDF backend (AGPL/commercial)
+pip install 'rc-docparser[docling]'      # IBM Docling PDF backend (MIT)
+pip install 'rc-docparser[marker]'       # Datalab Marker PDF backend (GPL-3.0)
+pip install 'rc-docparser[localvlm]'     # transformers/torch local captioning
 ```
 
-`docparser` requires Python 3.10+.
+`rc-docparser` requires Python 3.10+.
 
 ## Quick start (library)
 

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/README.md

@@ -1,4 +1,6 @@
-# docparser
+# rc-docparser
+
+_Published on PyPI as **`rc-docparser`**; import it as `docparser` (`import docparser`)._
 
 Convert research literature (`.docx`, `.xlsx`, `.pdf`, `.html`, `.pptx`,
 `.epub`, `.txt`, `.md`, `.csv`) into a clean, reproducible **Markdown + JSON**
@@ -20,29 +22,32 @@ via OpenRouter, OpenAI, Gemini, a local server, or a fully-local model.
 
 ## Install
 
+The package is published on PyPI as **`rc-docparser`**; the Python import name
+is `docparser` (i.e. `import docparser`).
+
 ```bash
-pip install docparser              # core: docx + xlsx + txt/md + csv/tsv
-pip install 'docparser[pdf]'       # + PyMuPDF for PDFs
-pip install 'docparser[html]'      # + trafilatura + bs4 for HTML
-pip install 'docparser[pptx]'      # + python-pptx for PowerPoint
-pip install 'docparser[epub]'      # + EbookLib + bs4 for EPUB
-pip install 'docparser[vlm]'       # + requests for API VLM captions
-pip install 'docparser[all]'       # everything above (recommended)
+pip install rc-docparser              # core: docx + xlsx + txt/md + csv/tsv
+pip install 'rc-docparser[pdf]'       # + PyMuPDF for PDFs
+pip install 'rc-docparser[html]'      # + trafilatura + bs4 for HTML
+pip install 'rc-docparser[pptx]'      # + python-pptx for PowerPoint
+pip install 'rc-docparser[epub]'      # + EbookLib + bs4 for EPUB
+pip install 'rc-docparser[vlm]'       # + requests for API VLM captions
+pip install 'rc-docparser[all]'       # everything above (recommended)
 ```
 
 Higher-fidelity / heavier features are separate opt-in extras (so the core
 install stays small and MIT):
 
 ```bash
-pip install 'docparser[tables]'       # + pdfplumber for PDF table extraction
-pip install 'docparser[ocr]'          # + rapidocr-onnxruntime for scanned PDFs
-pip install 'docparser[pymupdf4llm]'  # PyMuPDF4LLM PDF backend (AGPL/commercial)
-pip install 'docparser[docling]'      # IBM Docling PDF backend (MIT)
-pip install 'docparser[marker]'       # Datalab Marker PDF backend (GPL-3.0)
-pip install 'docparser[localvlm]'     # transformers/torch local captioning
+pip install 'rc-docparser[tables]'       # + pdfplumber for PDF table extraction
+pip install 'rc-docparser[ocr]'          # + rapidocr-onnxruntime for scanned PDFs
+pip install 'rc-docparser[pymupdf4llm]'  # PyMuPDF4LLM PDF backend (AGPL/commercial)
+pip install 'rc-docparser[docling]'      # IBM Docling PDF backend (MIT)
+pip install 'rc-docparser[marker]'       # Datalab Marker PDF backend (GPL-3.0)
+pip install 'rc-docparser[localvlm]'     # transformers/torch local captioning
 ```
 
-`docparser` requires Python 3.10+.
+`rc-docparser` requires Python 3.10+.
 
 ## Quick start (library)
 

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/pyproject.toml

@@ -7,11 +7,10 @@ name = "rc-docparser"
 dynamic = ["version"]
 description = "Convert research literature (.docx, .xlsx, .pdf, .html, .pptx, .epub, .txt, .md, .csv) into structured Markdown + JSON corpora, with optional VLM image semantic captioning."
 readme = "README.md"
-license = { file = "LICENSE" }
+license = "MIT"
+license-files = ["LICENSE"]
 requires-python = ">=3.10"
-authors = [
-    { name = "Research Commons", email = "shubhankitsingh@researchcommons.ai" },
-]
+authors = [{ name = "rc-docparser contributors" }]
 keywords = [
     "docx",
     "xlsx",
@@ -32,7 +31,6 @@ classifiers = [
     "Development Status :: 4 - Beta",
     "Intended Audience :: Developers",
     "Intended Audience :: Science/Research",
-    "License :: OSI Approved :: MIT License",
     "Operating System :: OS Independent",
     "Programming Language :: Python :: 3",
     "Programming Language :: Python :: 3.10",
@@ -40,6 +38,7 @@ classifiers = [
     "Programming Language :: Python :: 3.12",
     "Topic :: Scientific/Engineering",
     "Topic :: Text Processing :: Markup",
+    "Typing :: Typed",
 ]
 dependencies = [
     "python-docx>=1.1.2",
@@ -97,9 +96,10 @@ Homepage = "https://github.com/Research-Commons/docparser"
 Repository = "https://github.com/Research-Commons/docparser"
 Issues = "https://github.com/Research-Commons/docparser/issues"
 Changelog = "https://github.com/Research-Commons/docparser/blob/main/CHANGELOG.md"
+"Research Commons" = "https://lab.researchcommons.ai/"
 
 [tool.hatch.version]
-path = "src/docparser/__init__.py"
+path = "src/docparser/_version.py"
 
 [tool.hatch.build.targets.wheel]
 packages = ["src/docparser"]
@@ -121,7 +121,7 @@ line-length = 100
 target-version = "py310"
 
 [tool.ruff.lint]
-select = ["E", "F", "W", "I", "B", "UP", "RUF"]
+select = ["E", "F", "W", "I", "B", "UP", "SIM", "RUF"]
 ignore = ["E501"]
 
 [tool.pytest.ini_options]
@@ -135,6 +135,16 @@ markers = [
 source = ["src/docparser"]
 branch = true
 
+[tool.coverage.report]
+show_missing = true
+exclude_lines = [
+    "pragma: no cover",
+    "if TYPE_CHECKING:",
+    "@overload",
+    "raise NotImplementedError",
+    "\\.\\.\\.",
+]
+
 [tool.mypy]
 python_version = "3.10"
 files = ["src/docparser"]

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/src/docparser/__init__.py

@@ -19,8 +19,7 @@ Public API
 """
 from __future__ import annotations
 
-__version__ = "0.2.0"
-
+from ._version import __version__
 from .common import (
     WorkspaceLayout,
     bytes_sha1,

rc_docparser-0.2.2/src/docparser/_version.py

@@ -0,0 +1 @@
+__version__ = "0.2.2"

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/src/docparser/cli.py

@@ -21,10 +21,7 @@ from .orchestrator import SUPPORTED_EXTENSIONS, parse_path, run_all
 
 
 def _layout_from_args(args: argparse.Namespace) -> WorkspaceLayout:
-    if args.workspace:
-        layout = WorkspaceLayout.under(args.workspace)
-    else:
-        layout = WorkspaceLayout()
+    layout = WorkspaceLayout.under(args.workspace) if args.workspace else WorkspaceLayout()
     if getattr(args, "raw_dir", None):
         layout.raw_dir = Path(args.raw_dir)
     if getattr(args, "parsed_dir", None):

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/src/docparser/docx.py

@@ -140,9 +140,7 @@ def _is_caption(p: Paragraph) -> bool:
     if style in CAPTION_STYLE_NAMES:
         return True
     text = (p.text or "").strip()
-    if CAPTION_RE.match(text):
-        return True
-    return False
+    return bool(CAPTION_RE.match(text))
 
 
 @dataclass

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/src/docparser/epub.py

@@ -5,7 +5,7 @@ over each chapter (headings / paragraphs / lists / tables / images), and
 extracts embedded images to the asset directory. Embedded images can be
 captioned via a ``captioner`` callable.
 
-Requires the ``[epub]`` extra: ``pip install 'docparser[epub]'`` (which also
+Requires the ``[epub]`` extra: ``pip install 'rc-docparser[epub]'`` (which also
 pulls in BeautifulSoup from the ``[html]`` extra).
 """
 from __future__ import annotations
@@ -36,7 +36,7 @@ def _import_deps():
     except ImportError as exc:  # pragma: no cover - optional dep guard
         raise ImportError(
             "docparser.epub.parse_epub requires the [epub] extra. "
-            "Install with: pip install 'docparser[epub]'"
+            "Install with: pip install 'rc-docparser[epub]'"
         ) from exc
     return ebooklib, epub, BeautifulSoup
 

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/src/docparser/html.py

@@ -8,7 +8,7 @@ Two-tier strategy:
    typed blocks (heading/paragraph/list/table/image) when trafilatura returns
    nothing useful or when the caller wants the full structure.
 
-Requires the ``[html]`` extra: ``pip install 'docparser[html]'``.
+Requires the ``[html]`` extra: ``pip install 'rc-docparser[html]'``.
 """
 from __future__ import annotations
 
@@ -37,7 +37,7 @@ def _import_deps():
     except ImportError as exc:  # pragma: no cover
         raise ImportError(
             "docparser.html.parse_html requires the [html] extra. "
-            "Install with: pip install 'docparser[html]'"
+            "Install with: pip install 'rc-docparser[html]'"
         ) from exc
     return trafilatura, BeautifulSoup
 

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/src/docparser/image.py

@@ -234,7 +234,7 @@ def caption_image(
     if requests is None:  # pragma: no cover - optional dep guard
         raise ImportError(
             "docparser.image.caption_image requires the [vlm] extra. "
-            "Install with: pip install 'docparser[vlm]'"
+            "Install with: pip install 'rc-docparser[vlm]'"
         )
 
     provider_name, preset = _resolve_provider(provider)

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/src/docparser/localvlm.py

@@ -8,7 +8,7 @@ image-to-text model such as BLIP.
 It honors the same ``VLMResult`` shape and the same ``SHA1(image) x model``
 on-disk cache as the API captioner, so output is interchangeable.
 
-Requires the ``[localvlm]`` extra: ``pip install 'docparser[localvlm]'``.
+Requires the ``[localvlm]`` extra: ``pip install 'rc-docparser[localvlm]'``.
 """
 from __future__ import annotations
 
@@ -32,7 +32,7 @@ def _load_pipeline(model: str):
     except ImportError as exc:  # pragma: no cover - optional dep
         raise ImportError(
             "docparser.localvlm requires the [localvlm] extra. "
-            "Install with: pip install 'docparser[localvlm]'"
+            "Install with: pip install 'rc-docparser[localvlm]'"
         ) from exc
     return pipeline("image-to-text", model=model)
 

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/src/docparser/ocr.py

@@ -3,7 +3,7 @@
 Uses ``rapidocr-onnxruntime`` by default: a pure-pip ONNX OCR engine that needs
 no system binaries (unlike Tesseract). The engine is created once and reused.
 
-Requires the ``[ocr]`` extra: ``pip install 'docparser[ocr]'``.
+Requires the ``[ocr]`` extra: ``pip install 'rc-docparser[ocr]'``.
 """
 from __future__ import annotations
 
@@ -12,7 +12,7 @@ from functools import lru_cache
 from typing import Any
 
 _NO_OCR_MSG = (
-    "OCR requires the [ocr] extra. Install with: pip install 'docparser[ocr]'"
+    "OCR requires the [ocr] extra. Install with: pip install 'rc-docparser[ocr]'"
 )
 
 

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/src/docparser/pdf.py

@@ -12,7 +12,7 @@ heading classifier based on font sizing. On top of that it offers:
 - ``extract_tables`` use ``pdfplumber`` (the ``[tables]`` extra) to emit real
   table blocks instead of flattened text.
 
-Requires the ``[pdf]`` extra: ``pip install 'docparser[pdf]'``.
+Requires the ``[pdf]`` extra: ``pip install 'rc-docparser[pdf]'``.
 """
 from __future__ import annotations
 
@@ -104,7 +104,7 @@ def parse_pdf(
     except ImportError as exc:  # pragma: no cover
         raise ImportError(
             "docparser.pdf.parse_pdf requires the [pdf] extra. "
-            "Install with: pip install 'docparser[pdf]'"
+            "Install with: pip install 'rc-docparser[pdf]'"
         ) from exc
 
     if ocr not in {"off", "auto", "force"}:
@@ -218,7 +218,7 @@ def parse_pdf(
         except ImportError as exc:  # pragma: no cover - optional dep
             raise ImportError(
                 "extract_tables=True requires the [tables] extra. "
-                "Install with: pip install 'docparser[tables]'"
+                "Install with: pip install 'rc-docparser[tables]'"
             ) from exc
         out: list[list[list[str]]] = []
         with pdfplumber.open(str(real_source)) as pdf:

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/src/docparser/pdf_backends.py

@@ -8,9 +8,9 @@ schema via :func:`docparser.text._blocks_from_markdown`.
 
 All backends are optional extras and lazily imported:
 
-- ``pymupdf4llm`` -> ``pip install 'docparser[pymupdf4llm]'`` (note: AGPL/commercial)
-- ``docling``     -> ``pip install 'docparser[docling]'`` (MIT)
-- ``marker``      -> ``pip install 'docparser[marker]'`` (GPL-3.0)
+- ``pymupdf4llm`` -> ``pip install 'rc-docparser[pymupdf4llm]'`` (note: AGPL/commercial)
+- ``docling``     -> ``pip install 'rc-docparser[docling]'`` (MIT)
+- ``marker``      -> ``pip install 'rc-docparser[marker]'`` (GPL-3.0)
 """
 from __future__ import annotations
 
@@ -28,7 +28,7 @@ def _markdown_pymupdf4llm(path: Path) -> str:
     except ImportError as exc:  # pragma: no cover - optional dep
         raise ImportError(
             "backend='pymupdf4llm' requires the [pymupdf4llm] extra. "
-            "Install with: pip install 'docparser[pymupdf4llm]'"
+            "Install with: pip install 'rc-docparser[pymupdf4llm]'"
         ) from exc
     return pymupdf4llm.to_markdown(str(path))
 
@@ -39,7 +39,7 @@ def _markdown_docling(path: Path) -> str:
     except ImportError as exc:  # pragma: no cover - optional dep
         raise ImportError(
             "backend='docling' requires the [docling] extra. "
-            "Install with: pip install 'docparser[docling]'"
+            "Install with: pip install 'rc-docparser[docling]'"
         ) from exc
     converter = DocumentConverter()
     result = converter.convert(str(path))
@@ -55,7 +55,7 @@ def _markdown_marker(path: Path) -> str:
     except ImportError as exc:  # pragma: no cover - optional dep
         raise ImportError(
             "backend='marker' requires the [marker] extra. "
-            "Install with: pip install 'docparser[marker]'"
+            "Install with: pip install 'rc-docparser[marker]'"
         ) from exc
     config_parser = ConfigParser({"output_format": "markdown"})
     converter = PdfConverter(

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/src/docparser/pptx.py

@@ -6,7 +6,7 @@ pictures are emitted in shape order. Speaker notes are captured per slide.
 Embedded pictures are written to ``layout.assets_dir_for(source)`` and may be
 captioned via a ``captioner`` callable (same contract as the other parsers).
 
-Requires the ``[pptx]`` extra: ``pip install 'docparser[pptx]'``.
+Requires the ``[pptx]`` extra: ``pip install 'rc-docparser[pptx]'``.
 """
 from __future__ import annotations
 
@@ -33,7 +33,7 @@ def _import_pptx():
     except ImportError as exc:  # pragma: no cover - optional dep guard
         raise ImportError(
             "docparser.pptx.parse_pptx requires the [pptx] extra. "
-            "Install with: pip install 'docparser[pptx]'"
+            "Install with: pip install 'rc-docparser[pptx]'"
         ) from exc
     return Presentation, MSO_SHAPE_TYPE
 

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/src/docparser/xlsx.py

@@ -6,6 +6,7 @@ embedded images.
 """
 from __future__ import annotations
 
+import contextlib
 import datetime as _dt
 import io
 from collections.abc import Callable
@@ -66,10 +67,8 @@ def _cell_record(cell: Cell, formulas_ws: Worksheet | None) -> dict[str, Any]:
         except Exception:
             pass
     if cell.comment is not None:
-        try:
+        with contextlib.suppress(Exception):
             rec["comment"] = str(cell.comment.text)
-        except Exception:
-            pass
     return rec
 
 
@@ -84,10 +83,8 @@ def _extract_images(
             data: bytes | None = None
             if hasattr(ref, "read"):
                 data = ref.read()
-                try:
+                with contextlib.suppress(Exception):
                     ref.seek(0)
-                except Exception:
-                    pass
             elif isinstance(ref, (bytes, bytearray)):
                 data = bytes(ref)
             else:

{rc_docparser-0.2.0 → rc_docparser-0.2.2}/tests/conftest.py

@@ -1,6 +1,7 @@
 """Shared pytest fixtures: synthetic docx, xlsx, pdf, html files."""
 from __future__ import annotations
 
+import contextlib
 import io
 from pathlib import Path
 
@@ -51,10 +52,8 @@ def sample_docx(tmp_path: Path) -> Path:
     img_path.write_bytes(_png_bytes())
     doc.add_picture(str(img_path))
     cap_para = doc.add_paragraph("Figure 1: a red square example.")
-    try:
+    with contextlib.suppress(KeyError):
         cap_para.style = doc.styles["Caption"]
-    except KeyError:
-        pass
 
     doc.add_heading("Section B", level=2)
     doc.add_paragraph("Conclusion paragraph.")