laygen 0.1.0__tar.gz

laygen-0.1.0/.gitignore

@@ -0,0 +1,5 @@
+__pycache__/
+*.py[cod]
+.venv/
+.pytest_cache/
+dist/

laygen-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 NEOALI CO., LTD.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

laygen-0.1.0/NOTICE

@@ -0,0 +1,7 @@
+laygen
+Copyright 2026 NEOALI CO., LTD.
+
+This product includes software developed at NEOALI CO., LTD.
+
+Licensed under the Apache License, Version 2.0. You may obtain a copy of
+the License at http://www.apache.org/licenses/LICENSE-2.0

laygen-0.1.0/PKG-INFO

@@ -0,0 +1,108 @@
+Metadata-Version: 2.5
+Name: laygen
+Version: 0.1.0
+Summary: Layout-preserving text extraction and reconstruction for office documents
+Project-URL: Homepage, https://ondevice.neoali.com/laygen
+Author-email: "NEOALI CO., LTD." <neoali.official@gmail.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+License-File: NOTICE
+Keywords: docx,hwpx,layout,localization,ooxml,pptx,translation,xlsx
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Localization
+Classifier: Topic :: Text Processing :: Markup
+Requires-Python: >=3.10
+Requires-Dist: chardet>=5.0
+Description-Content-Type: text/markdown
+
+# laygen
+
+Extract translatable text from office documents and rebuild them with the layout intact.
+
+`laygen` does not translate anything. It splits a document into its text segments, hands
+them over as JSON, and puts translated text back where it came from. Whatever does the
+translating — an agent, a script, a person — sits in between. That keeps the tool free of
+model dependencies, API keys and network access.
+
+## Formats
+
+| Extension | Segment |
+|---|---|
+| `.docx` | paragraph (body, headers, footers, notes, charts, SmartArt) |
+| `.pptx` | paragraph (slides, speaker notes, charts, SmartArt) |
+| `.xlsx` | shared string (deduplicated), inline strings, chart labels |
+| `.hwpx` | paragraph |
+| `.csv` | non-empty cell |
+| `.txt` | non-empty line |
+
+## Install
+
+```bash
+uv tool install laygen
+```
+
+The only dependency is `chardet`, for detecting text encodings. Everything else is
+standard library.
+
+## Use
+
+```bash
+# 1. Pull the text out
+laygen extract report.docx -w work/
+# 42 segments -> work/segments.json
+
+# 2. Translate work/segments.json into translated.json, keeping the keys
+
+# 3. Put it back
+laygen reconstruct -w work/ -t translated.json -o report.ko.docx
+```
+
+`work/segments.json` is a flat `{"cid0": "text", ...}` map. Your translation file uses the
+same keys. Any key you leave out keeps its source text, so a partial translation degrades
+into a partly-translated document rather than a broken one.
+
+## The workspace
+
+```
+work/
+├── original.docx    copy of the source
+├── plan.json        format, checksum and the map back to the original elements
+└── segments.json    {"cid0": "…"}  — the only file a translator needs
+```
+
+Self-contained: move the directory to another machine and reconstruction still works.
+
+## Notes and limits
+
+- **Segment ids are positional.** They are assigned in document order at extraction time.
+  Reconstruction re-reads `original.*` from the workspace, so never edit the source
+  document between the two steps — `plan.json` records a SHA-256 to help you notice.
+- **Formatting that varies inside a paragraph is lost.** A translated paragraph goes into
+  its first run and the remaining runs are emptied. Translation reorders words, so there
+  is no honest way to keep a bold span attached to the word it started on. Paragraph and
+  character styling itself is preserved.
+- **XLSX is edited through its shared string table**, not rebuilt by a spreadsheet
+  library, so charts, pivot tables, macros and formulas survive untouched. Numbers, dates
+  and formulas are skipped by construction — they are not stored as shared strings.
+  Because Excel deduplicates that table, a label repeated across fifty cells is one
+  segment, translated once and consistently.
+- **PPTX skips slide layouts and masters**, whose text is template boilerplate.
+- **HWPX drops inline markup inside a rewritten paragraph** (highlight marks, line
+  breaks). The paragraph's own text and styling survive.
+- **No PDF.** It needs layout detection and OCR, which would pull in a GPU-scale
+  dependency stack. Out of scope for this version.
+
+## Development
+
+```bash
+uv sync
+uv run pytest
+```

laygen-0.1.0/README.md

@@ -0,0 +1,83 @@
+# laygen
+
+Extract translatable text from office documents and rebuild them with the layout intact.
+
+`laygen` does not translate anything. It splits a document into its text segments, hands
+them over as JSON, and puts translated text back where it came from. Whatever does the
+translating — an agent, a script, a person — sits in between. That keeps the tool free of
+model dependencies, API keys and network access.
+
+## Formats
+
+| Extension | Segment |
+|---|---|
+| `.docx` | paragraph (body, headers, footers, notes, charts, SmartArt) |
+| `.pptx` | paragraph (slides, speaker notes, charts, SmartArt) |
+| `.xlsx` | shared string (deduplicated), inline strings, chart labels |
+| `.hwpx` | paragraph |
+| `.csv` | non-empty cell |
+| `.txt` | non-empty line |
+
+## Install
+
+```bash
+uv tool install laygen
+```
+
+The only dependency is `chardet`, for detecting text encodings. Everything else is
+standard library.
+
+## Use
+
+```bash
+# 1. Pull the text out
+laygen extract report.docx -w work/
+# 42 segments -> work/segments.json
+
+# 2. Translate work/segments.json into translated.json, keeping the keys
+
+# 3. Put it back
+laygen reconstruct -w work/ -t translated.json -o report.ko.docx
+```
+
+`work/segments.json` is a flat `{"cid0": "text", ...}` map. Your translation file uses the
+same keys. Any key you leave out keeps its source text, so a partial translation degrades
+into a partly-translated document rather than a broken one.
+
+## The workspace
+
+```
+work/
+├── original.docx    copy of the source
+├── plan.json        format, checksum and the map back to the original elements
+└── segments.json    {"cid0": "…"}  — the only file a translator needs
+```
+
+Self-contained: move the directory to another machine and reconstruction still works.
+
+## Notes and limits
+
+- **Segment ids are positional.** They are assigned in document order at extraction time.
+  Reconstruction re-reads `original.*` from the workspace, so never edit the source
+  document between the two steps — `plan.json` records a SHA-256 to help you notice.
+- **Formatting that varies inside a paragraph is lost.** A translated paragraph goes into
+  its first run and the remaining runs are emptied. Translation reorders words, so there
+  is no honest way to keep a bold span attached to the word it started on. Paragraph and
+  character styling itself is preserved.
+- **XLSX is edited through its shared string table**, not rebuilt by a spreadsheet
+  library, so charts, pivot tables, macros and formulas survive untouched. Numbers, dates
+  and formulas are skipped by construction — they are not stored as shared strings.
+  Because Excel deduplicates that table, a label repeated across fifty cells is one
+  segment, translated once and consistently.
+- **PPTX skips slide layouts and masters**, whose text is template boilerplate.
+- **HWPX drops inline markup inside a rewritten paragraph** (highlight marks, line
+  breaks). The paragraph's own text and styling survive.
+- **No PDF.** It needs layout detection and OCR, which would pull in a GPU-scale
+  dependency stack. Out of scope for this version.
+
+## Development
+
+```bash
+uv sync
+uv run pytest
+```

laygen-0.1.0/pyproject.toml

@@ -0,0 +1,46 @@
+[project]
+name = "laygen"
+version = "0.1.0"
+description = "Layout-preserving text extraction and reconstruction for office documents"
+readme = "README.md"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+license-files = ["LICENSE", "NOTICE"]
+authors = [{ name = "NEOALI CO., LTD.", email = "neoali.official@gmail.com" }]
+keywords = ["docx", "pptx", "xlsx", "hwpx", "translation", "localization", "layout", "ooxml"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Text Processing :: Markup",
+    "Topic :: Software Development :: Localization",
+]
+dependencies = [
+    "chardet>=5.0",
+]
+
+[project.urls]
+Homepage = "https://ondevice.neoali.com/laygen"
+
+[project.scripts]
+laygen = "laygen.cli:main"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/laygen"]
+
+[tool.hatch.build.targets.sdist]
+include = ["src/laygen", "tests", "README.md", "LICENSE", "NOTICE", "pyproject.toml"]
+
+[dependency-groups]
+# openpyxl is only used to author the XLSX test fixture, never at runtime.
+dev = ["pytest>=8.0", "openpyxl>=3.1.5"]

laygen-0.1.0/src/laygen/cli.py

@@ -0,0 +1,121 @@
+"""Command line interface."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+import zipfile
+from pathlib import Path
+
+from . import registry
+from .workspace import Workspace, WorkspaceError
+
+# DOCX, PPTX, XLSX and HWPX are zip containers. An OLE header instead means a legacy
+# binary format (.doc, .hwp) or a password-protected file wearing the wrong extension.
+_OLE_HEADER = b"\xd0\xcf\x11\xe0"
+
+
+def _reject_unreadable(source: Path) -> None:
+    if source.suffix.lower() in {".csv", ".txt"}:
+        return
+    if source.open("rb").read(4) == _OLE_HEADER:
+        raise SystemExit(
+            f"{source.name} is a legacy binary or password-protected file, not a "
+            f"{source.suffix} package. Unlock it or re-save it in {source.suffix} format."
+        )
+
+
+def cmd_extract(args: argparse.Namespace) -> int:
+    source = Path(args.file)
+    if not source.is_file():
+        raise SystemExit(f"No such file: {source}")
+
+    fmt = registry.resolve(source.suffix)
+    _reject_unreadable(source)
+    segments, structure = registry.extractor(fmt)(source)
+
+    workspace = Workspace(Path(args.workdir))
+    workspace.save(source, fmt, segments, structure)
+
+    print(f"{len(segments)} segments -> {workspace.path / Workspace.SEGMENTS}")
+    return 0
+
+
+def cmd_reconstruct(args: argparse.Namespace) -> int:
+    workspace = Workspace(Path(args.workdir))
+    plan = workspace.plan()
+    segments = workspace.segments()
+
+    translations = dict(segments)
+    if args.translations:
+        supplied = json.loads(Path(args.translations).read_text(encoding="utf-8"))
+        unknown = set(supplied) - set(segments)
+        if unknown:
+            raise SystemExit(
+                f"{len(unknown)} unknown segment id(s), e.g. {sorted(unknown)[:3]}"
+            )
+        # Any id the agent left out keeps its source text rather than going missing.
+        translations.update({k: v for k, v in supplied.items() if v is not None})
+        missing = len(segments) - len(supplied)
+    else:
+        missing = 0
+
+    fmt = plan["format"]
+    output = Path(args.output or f"{Path(plan['source_name']).stem}.out{registry.suffix_for(fmt)}")
+    result = registry.reconstructor(fmt)(
+        workspace.original_bytes(), plan["structure"], translations
+    )
+    output.write_bytes(result)
+
+    note = f" ({missing} untranslated kept as source)" if missing > 0 else ""
+    print(f"wrote {output}{note}")
+    return 0
+
+
+def cmd_formats(args: argparse.Namespace) -> int:
+    for suffix, fmt in sorted(registry.FORMATS.items()):
+        print(f"{suffix:<7} {fmt}")
+    return 0
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        prog="laygen",
+        description="Extract translatable text from documents and rebuild them.",
+    )
+    sub = parser.add_subparsers(dest="command", required=True)
+
+    extract = sub.add_parser("extract", help="extract text into a workspace")
+    extract.add_argument("file")
+    extract.add_argument("-w", "--workdir", required=True, help="workspace directory")
+    extract.set_defaults(func=cmd_extract)
+
+    reconstruct = sub.add_parser("reconstruct", help="rebuild the document")
+    reconstruct.add_argument("-w", "--workdir", required=True)
+    reconstruct.add_argument(
+        "-t", "--translations", help="JSON mapping segment ids to translated text"
+    )
+    reconstruct.add_argument("-o", "--output")
+    reconstruct.set_defaults(func=cmd_reconstruct)
+
+    formats = sub.add_parser("formats", help="list supported file types")
+    formats.set_defaults(func=cmd_formats)
+
+    return parser
+
+
+def main(argv: list[str] | None = None) -> int:
+    args = build_parser().parse_args(argv)
+    try:
+        return args.func(args)
+    except (WorkspaceError, registry.UnsupportedFormat) as error:
+        print(f"error: {error}", file=sys.stderr)
+        return 1
+    except zipfile.BadZipFile:
+        print("error: file is corrupt or not a valid document package", file=sys.stderr)
+        return 1
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

laygen-0.1.0/src/laygen/extractors/csv.py

@@ -0,0 +1,41 @@
+"""CSV: one segment per non-empty cell, in reading order."""
+
+from __future__ import annotations
+
+import csv as _csv
+import io
+from pathlib import Path
+from typing import Any
+
+import chardet
+
+# Sniffing a huge file is pointless; the delimiter shows up in the first rows.
+_SNIFF_BYTES = 8192
+
+
+def extract(path: Path) -> tuple[dict[str, str], dict[str, Any]]:
+    raw = Path(path).read_bytes()
+    encoding = chardet.detect(raw)["encoding"] or "utf-8"
+    text = raw.decode(encoding, errors="replace")
+
+    try:
+        delimiter = _csv.Sniffer().sniff(text[:_SNIFF_BYTES], delimiters=",;\t|").delimiter
+    except _csv.Error:
+        delimiter = ","
+
+    segments: dict[str, str] = {}
+    rows: list[list[str | None]] = []
+
+    for row in _csv.reader(io.StringIO(text, newline=""), delimiter=delimiter):
+        row_cids: list[str | None] = []
+        for cell in row:
+            if cell.strip():
+                cid = f"cid{len(segments)}"
+                segments[cid] = cell
+                row_cids.append(cid)
+            else:
+                row_cids.append(None)
+        rows.append(row_cids)
+
+    structure = {"encoding": encoding, "delimiter": delimiter, "rows": rows}
+    return segments, structure

laygen-0.1.0/src/laygen/extractors/docx.py

@@ -0,0 +1,33 @@
+"""DOCX: one segment per paragraph.
+
+Word splits a paragraph into arbitrarily many runs by formatting and spell-check
+state, so runs are concatenated verbatim - any real spacing is already inside the run
+text, carried by xml:space="preserve".
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any
+
+from .. import paragraphs, zipxml
+from ..ooxml_ns import A, DOCX_NAMESPACES, W
+
+PARTS = (
+    "word/document.xml",
+    "word/header*.xml",
+    "word/footer*.xml",
+    "word/footnotes.xml",
+    "word/endnotes.xml",
+    "word/comments.xml",
+    "word/charts/chart*.xml",
+    "word/diagrams/data*.xml",
+)
+
+# Word paragraphs, plus DrawingML paragraphs used by shapes and charts.
+KINDS = {"w": (f"{{{W}}}p", f"{{{W}}}t"), "a": (f"{{{A}}}p", f"{{{A}}}t")}
+
+
+def extract(path: Path) -> tuple[dict[str, str], dict[str, Any]]:
+    zipxml.register(DOCX_NAMESPACES)
+    return paragraphs.extract(Path(path).read_bytes(), PARTS, KINDS)