docpluck 2.4.152__tar.gz → 2.4.153__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {docpluck-2.4.152 → docpluck-2.4.153}/PKG-INFO +4 -4
- {docpluck-2.4.152 → docpluck-2.4.153}/README.md +388 -388
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/__init__.py +1 -1
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/extract_structured.py +4231 -4231
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/normalize.py +121 -1
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/render.py +7473 -7339
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/flatten.py +53 -4
- {docpluck-2.4.152 → docpluck-2.4.153}/pyproject.toml +1 -1
- {docpluck-2.4.152 → docpluck-2.4.153}/.gitignore +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/LICENSE +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/__main__.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/batch.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/cli.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/extract.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/extract_columns.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/extract_docx.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/extract_docx_structured.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/extract_html.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/extract_layout.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/figures/__init__.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/glyph_evidence.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/glyph_names.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/quality.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/resources.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/sections/__init__.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/sections/_offsets.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/sections/annotators/__init__.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/sections/annotators/docx.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/sections/annotators/html.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/sections/annotators/pdf.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/sections/annotators/text.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/sections/blocks.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/sections/boundaries.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/sections/core.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/sections/taxonomy.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/sections/types.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/symbols.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/__init__.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/arm_spans.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/bbox_utils.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/camelot_extract.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/captions.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/cell_cleaning.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/cell_geometry.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/cluster.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/column_split.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/confidence.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/detect.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/docx_tables.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/notes.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/render.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/rotated.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tables/whitespace.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/telemetry.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/tempfiles.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/testing/__init__.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/testing/_root.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/testing/corpus.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/testing/corpus_manifest.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/testing/regenerate.py +0 -0
- {docpluck-2.4.152 → docpluck-2.4.153}/docpluck/version.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.5
|
|
2
2
|
Name: docpluck
|
|
3
|
-
Version: 2.4.
|
|
3
|
+
Version: 2.4.153
|
|
4
4
|
Summary: PDF, DOCX, and HTML text extraction and normalization for academic papers
|
|
5
5
|
Project-URL: Homepage, https://docpluck.app
|
|
6
6
|
Project-URL: Documentation, https://docpluck.app/api-docs
|
|
@@ -126,7 +126,7 @@ Requires Python 3.10 or newer.
|
|
|
126
126
|
pip install "docpluck[all] @ git+https://github.com/giladfeldman/docpluck.git"
|
|
127
127
|
```
|
|
128
128
|
|
|
129
|
-
To pin a release, append its tag: `...docpluck.git@v2.4.
|
|
129
|
+
To pin a release, append its tag: `...docpluck.git@v2.4.153`. The package is also on PyPI
|
|
130
130
|
(`pip install docpluck`); the GitHub tags are the release of record and PyPI can trail them,
|
|
131
131
|
so check `pip index versions docpluck` if you need a specific version from PyPI.
|
|
132
132
|
|
|
@@ -296,7 +296,7 @@ fingerprints the text buffer the offsets index into.
|
|
|
296
296
|
|
|
297
297
|
`flatten_tables_for_paper(tables)` (or `flatten_table(table)` for one) turns each body row of
|
|
298
298
|
each table into a `FlattenedRow`: its table, page, row label, header, cells, an English sentence
|
|
299
|
-
(`"Importance: t(741) = 3.93, p < .001, d = 0.29"`) and parsed `fields`. This is the input
|
|
299
|
+
(`"Importance: t(741) = 3.93, p < .001, d = 0.29"`) and parsed `fields`. A confidence interval is stated at the level the table prints (`90% CI`, `95% CrI`; a bare `CI` when none is stated), and `fields["CI_level"]` carries that level when present. This is the input
|
|
300
300
|
format for downstream statistics checkers; the CLI writes it as JSON Lines with
|
|
301
301
|
`render --tables-jsonl`. `render_flattened_inline(rows, table_id=...)` renders rows back as a
|
|
302
302
|
Markdown block.
|
|
@@ -423,7 +423,7 @@ default to off.
|
|
|
423
423
|
If you use docpluck in research, cite the version you used (from `get_version_info()`):
|
|
424
424
|
|
|
425
425
|
> Feldman, G. (2026). *docpluck: Text and statistic extraction from academic papers*
|
|
426
|
-
> (Version 2.4.
|
|
426
|
+
> (Version 2.4.153) [Computer software]. https://github.com/giladfeldman/docpluck
|
|
427
427
|
|
|
428
428
|
Machine-readable metadata is in [CITATION.cff](CITATION.cff); GitHub's "Cite this repository"
|
|
429
429
|
button reads it.
|