document2md 0.3.0__tar.gz

document2md-0.3.0/LICENSE

@@ -0,0 +1,201 @@
+                                 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 INGEOTEC
+
+   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.

document2md-0.3.0/PKG-INFO

@@ -0,0 +1,138 @@
+Metadata-Version: 2.4
+Name: document2md
+Version: 0.3.0
+Summary: Convert a PDF or a set of scanned page images to Markdown via OCR.
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/INGEOTEC/document2md
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests>=2.31
+Requires-Dist: mineru[pipeline]
+Provides-Extra: test
+Requires-Dist: pytest>=7.0; extra == "test"
+Dynamic: license-file
+
+# document2md
+
+[![test](https://github.com/INGEOTEC/document2md/actions/workflows/test.yml/badge.svg)](https://github.com/INGEOTEC/document2md/actions/workflows/test.yml)
+[![Documentation Status](https://readthedocs.org/projects/document2md/badge/?version=latest)](https://document2md.readthedocs.io/en/latest/)
+
+Converts a PDF, or a set of scanned page images, into Markdown — any
+document, such as an edition of Mexico's official gazette (DOF, *Diario
+Oficial de la Federación*) — optionally cropped down to a single note.
+It's a wrapper
+around [mineru](https://github.com/opendatalab/MinerU) for the OCR/layout
+analysis itself; `document2md`'s own contribution is:
+
+- Keeping mineru's `mineru-api` server warm across a batch of documents,
+  instead of paying its startup (and model-loading) cost once per document.
+- Stitching the OCR of a list of page images (several scanned pages of the
+  same note) into one continuous Markdown document.
+- Rewriting the raw HTML tables mineru falls back to (rowspan/colspan) into
+  Markdown tables, so the output is Markdown all the way through.
+- Cropping the result down to a single note, by locating its title and the
+  next note's title in the OCR'd text — useful because a scanned page
+  usually holds the tail of one note and the head of the next.
+
+It was extracted from the [LegalIA](https://github.com/INGEOTEC/LegalIA)
+monorepo at commit `e1f258c`, where every commit of its earlier history (as
+`packages/document2md`, and as `packages/dof2md` before the rename) can still
+be read.
+
+## Install
+
+```bash
+pip install document2md
+```
+
+For development, from a clone of this repository:
+
+```bash
+pip install -e ".[test]"
+```
+
+## Usage
+
+### CLI
+
+`document2md` takes exactly one input source — a local PDF or a set of local page
+images — and converts it to Markdown. It never downloads anything itself;
+get the PDF first (e.g. `dofjson.download_edicion_pdf` for a whole DOF
+edition by date and edition, see the
+[dofjson README](https://github.com/INGEOTEC/LegalIA/tree/master/packages/dofjson)),
+then convert it:
+
+```bash
+document2md --pdf edicion.pdf   # a local PDF
+
+document2md --images pagina-1.jpg pagina-2.jpg \
+    --filename out.md      # scanned pages, in order
+```
+
+`--filename` sets the output Markdown's name; with `--pdf` it defaults to
+the PDF's own name (`edicion.pdf` → `edicion.md`), but with `--images` it's
+required, since a set of images has no single name to derive one from.
+`--outdir` sets the output directory (default: `output/`).
+
+Since one edition's PDF holds every note published that day,
+`--titulo`/`--titulo-siguiente` crop the resulting Markdown down to just one
+note — its own title, and the next note's title, as they appear in the
+gazette's own index:
+
+```bash
+document2md --pdf edicion.pdf \
+    --titulo "ACUERDO por el que se..." \
+    --titulo-siguiente "DECRETO por el que se..."
+```
+
+Title matching is fuzzy (OCR text rarely matches an index title exactly), so
+a match below `--min-confidence` (default `0.6`) is treated as not found and
+the crop falls back to keeping more text rather than dropping content. Other
+flags:
+
+- `--keep-pages` — also keep the uncropped Markdown, as
+  `<outdir>/<pdf stem>.full.md`.
+- `--keep-mineru-output` — keep mineru's own raw output (layout/model JSON,
+  rendered PDFs...) in `<outdir>/<pdf stem>_mineru/` instead of discarding
+  it; useful when a conversion looks wrong and mineru's own read of the page
+  is the first thing worth inspecting.
+
+### Python: batch conversion
+
+Converting many documents in one run is where mineru's startup cost starts
+to matter. `BatchConverter` keeps a single `mineru-api` server warm across
+the whole batch instead of restarting it per document:
+
+```python
+from document2md import BatchConverter
+
+jobs = [
+    ("a.pdf", "output", "a.md"),
+    (["b-p1.jpg", "b-p2.jpg"], "output", "b.md"),
+]
+
+with BatchConverter() as convert:
+    for path_or_paths, outdir, filename in jobs:
+        convert(path_or_paths, outdir, filename)
+```
+
+Each call takes a single PDF path, or a list of image paths for a document
+spanning several scanned pages, and writes the result to `outdir/filename`.
+The same `titulo`/`titulo_siguiente`, `min_confidence`, `keep_pages` and
+`keep_mineru_output` options the CLI exposes are also its keyword
+arguments — see `BatchConverter.__call__`'s docstring for the full
+signature.
+
+`nota2md.legal_provisions` accepts an already-`__enter__`'d `BatchConverter`
+as its own `converter` parameter, so a batch of DOF legal provisions can
+share the same warm server too.
+
+## Tests
+
+```bash
+pytest -v
+```

document2md-0.3.0/README.md

@@ -0,0 +1,120 @@
+# document2md
+
+[![test](https://github.com/INGEOTEC/document2md/actions/workflows/test.yml/badge.svg)](https://github.com/INGEOTEC/document2md/actions/workflows/test.yml)
+[![Documentation Status](https://readthedocs.org/projects/document2md/badge/?version=latest)](https://document2md.readthedocs.io/en/latest/)
+
+Converts a PDF, or a set of scanned page images, into Markdown — any
+document, such as an edition of Mexico's official gazette (DOF, *Diario
+Oficial de la Federación*) — optionally cropped down to a single note.
+It's a wrapper
+around [mineru](https://github.com/opendatalab/MinerU) for the OCR/layout
+analysis itself; `document2md`'s own contribution is:
+
+- Keeping mineru's `mineru-api` server warm across a batch of documents,
+  instead of paying its startup (and model-loading) cost once per document.
+- Stitching the OCR of a list of page images (several scanned pages of the
+  same note) into one continuous Markdown document.
+- Rewriting the raw HTML tables mineru falls back to (rowspan/colspan) into
+  Markdown tables, so the output is Markdown all the way through.
+- Cropping the result down to a single note, by locating its title and the
+  next note's title in the OCR'd text — useful because a scanned page
+  usually holds the tail of one note and the head of the next.
+
+It was extracted from the [LegalIA](https://github.com/INGEOTEC/LegalIA)
+monorepo at commit `e1f258c`, where every commit of its earlier history (as
+`packages/document2md`, and as `packages/dof2md` before the rename) can still
+be read.
+
+## Install
+
+```bash
+pip install document2md
+```
+
+For development, from a clone of this repository:
+
+```bash
+pip install -e ".[test]"
+```
+
+## Usage
+
+### CLI
+
+`document2md` takes exactly one input source — a local PDF or a set of local page
+images — and converts it to Markdown. It never downloads anything itself;
+get the PDF first (e.g. `dofjson.download_edicion_pdf` for a whole DOF
+edition by date and edition, see the
+[dofjson README](https://github.com/INGEOTEC/LegalIA/tree/master/packages/dofjson)),
+then convert it:
+
+```bash
+document2md --pdf edicion.pdf   # a local PDF
+
+document2md --images pagina-1.jpg pagina-2.jpg \
+    --filename out.md      # scanned pages, in order
+```
+
+`--filename` sets the output Markdown's name; with `--pdf` it defaults to
+the PDF's own name (`edicion.pdf` → `edicion.md`), but with `--images` it's
+required, since a set of images has no single name to derive one from.
+`--outdir` sets the output directory (default: `output/`).
+
+Since one edition's PDF holds every note published that day,
+`--titulo`/`--titulo-siguiente` crop the resulting Markdown down to just one
+note — its own title, and the next note's title, as they appear in the
+gazette's own index:
+
+```bash
+document2md --pdf edicion.pdf \
+    --titulo "ACUERDO por el que se..." \
+    --titulo-siguiente "DECRETO por el que se..."
+```
+
+Title matching is fuzzy (OCR text rarely matches an index title exactly), so
+a match below `--min-confidence` (default `0.6`) is treated as not found and
+the crop falls back to keeping more text rather than dropping content. Other
+flags:
+
+- `--keep-pages` — also keep the uncropped Markdown, as
+  `<outdir>/<pdf stem>.full.md`.
+- `--keep-mineru-output` — keep mineru's own raw output (layout/model JSON,
+  rendered PDFs...) in `<outdir>/<pdf stem>_mineru/` instead of discarding
+  it; useful when a conversion looks wrong and mineru's own read of the page
+  is the first thing worth inspecting.
+
+### Python: batch conversion
+
+Converting many documents in one run is where mineru's startup cost starts
+to matter. `BatchConverter` keeps a single `mineru-api` server warm across
+the whole batch instead of restarting it per document:
+
+```python
+from document2md import BatchConverter
+
+jobs = [
+    ("a.pdf", "output", "a.md"),
+    (["b-p1.jpg", "b-p2.jpg"], "output", "b.md"),
+]
+
+with BatchConverter() as convert:
+    for path_or_paths, outdir, filename in jobs:
+        convert(path_or_paths, outdir, filename)
+```
+
+Each call takes a single PDF path, or a list of image paths for a document
+spanning several scanned pages, and writes the result to `outdir/filename`.
+The same `titulo`/`titulo_siguiente`, `min_confidence`, `keep_pages` and
+`keep_mineru_output` options the CLI exposes are also its keyword
+arguments — see `BatchConverter.__call__`'s docstring for the full
+signature.
+
+`nota2md.legal_provisions` accepts an already-`__enter__`'d `BatchConverter`
+as its own `converter` parameter, so a batch of DOF legal provisions can
+share the same warm server too.
+
+## Tests
+
+```bash
+pytest -v
+```

document2md-0.3.0/document2md/__init__.py

@@ -0,0 +1,5 @@
+from document2md.batch import BatchConverter
+
+__version__ = "0.3.0"
+
+__all__ = ["BatchConverter"]

document2md-0.3.0/document2md/batch.py

@@ -0,0 +1,108 @@
+"""Batch document-to-Markdown conversion, keeping one mineru-api server warm
+across many jobs instead of paying its startup (and model-loading) cost once
+per document:
+
+    with BatchConverter() as convert:
+        for pdf_path, outdir, filename in jobs:
+            convert(pdf_path, outdir, filename)
+
+document2md itself has no notion of what a "note" is or where a document came
+from — a job is just a PDF (a single path) or a set of scanned page images (a
+list of paths), an output directory, and an output filename. Whatever calls
+this decides what those mean (a DOF legal provision, or anything else).
+"""
+from pathlib import Path
+
+from document2md import converter as _converter
+from document2md.converter import DEFAULT_TIMEOUT_SECONDS
+from document2md.cutter import cut_markdown_by_titles
+from document2md.mineru_server import ENV_VAR as _MINERU_API_URL_ENV_VAR
+from document2md.mineru_server import MineruServer
+
+
+class BatchConverter:
+    """Context manager: `__enter__` starts a persistent `mineru-api` server
+    (skipped if a caller further up already has one running via
+    MINERU_API_URL) and returns `self`, callable once per document;
+    `__exit__` stops it. Calling it converts one document — a single PDF
+    path, or a list of image paths for a document spanning several scanned
+    pages — to Markdown, written to `outdir/filename`.
+
+    `titulo`/`titulo_siguiente`, when given, slice the OCR'd Markdown down
+    to the text between their two boundaries (see
+    document2md.cutter.cut_markdown_by_titles) — e.g. a DOF legal provision's own
+    title and the next one's, to cut a page shared with the notes before and
+    after it down to just this one. Left out (the default), the whole
+    conversion is kept as-is, on the assumption that the whole document is
+    what was asked for.
+    """
+
+    def __init__(self):
+        """Create an unstarted converter; call `__enter__` (or use as a
+        context manager) before calling it."""
+        self._server: MineruServer | None = None
+
+    def __enter__(self) -> "BatchConverter":
+        """Start a persistent `mineru-api` server, unless one is already
+        reachable via MINERU_API_URL, and return `self`."""
+        import os
+
+        if _MINERU_API_URL_ENV_VAR not in os.environ:
+            self._server = MineruServer()
+            self._server.start()
+        return self
+
+    def __exit__(self, exc_type, exc, tb) -> None:
+        """Stop the `mineru-api` server started by `__enter__`, if any."""
+        if self._server is not None:
+            self._server.stop()
+            self._server = None
+
+    def __call__(
+        self,
+        path_or_paths: str | Path | list[str | Path],
+        outdir: str | Path,
+        filename: str,
+        titulo: str | None = None,
+        titulo_siguiente: str | None = None,
+        *,
+        min_confidence: float = 0.6,
+        keep_pages: bool = False,
+        keep_mineru_output: bool = False,
+        timeout: float = DEFAULT_TIMEOUT_SECONDS,
+    ) -> Path:
+        """Convert one document — `path_or_paths` a single PDF path, or a
+        list of image paths for a document spanning several scanned pages —
+        to Markdown, written to `outdir/filename`, and return that path.
+
+        `titulo`/`titulo_siguiente`, `min_confidence` and `keep_pages` are
+        forwarded to `cutter.cut_markdown_by_titles` to crop the result down
+        to a single note; left as `None` (the default), the whole conversion
+        is kept as-is. `keep_mineru_output` and `timeout` are forwarded to
+        `converter.convert_to_markdown`/`convert_images_to_markdown`."""
+        outdir = Path(outdir)
+        outdir.mkdir(parents=True, exist_ok=True)
+        dest = outdir / filename
+
+        if isinstance(path_or_paths, (list, tuple)):
+            _converter.convert_images_to_markdown(
+                [Path(p) for p in path_or_paths], dest,
+                timeout=timeout, keep_mineru_output=keep_mineru_output,
+            )
+        else:
+            _converter.convert_to_markdown(
+                Path(path_or_paths), dest,
+                timeout=timeout, keep_mineru_output=keep_mineru_output,
+            )
+
+        if titulo is None:
+            return dest
+
+        full_markdown = dest.read_text(encoding="utf-8")
+        if keep_pages:
+            (outdir / f"{dest.stem}.full.md").write_text(full_markdown, encoding="utf-8")
+        cut = cut_markdown_by_titles(
+            full_markdown, titulo, titulo_siguiente, min_confidence=min_confidence
+        )
+        dest.write_text(cut + "\n", encoding="utf-8")
+        return dest

document2md-0.3.0/document2md/cli.py

@@ -0,0 +1,109 @@
+"""The `document2md` console script: parses command-line arguments and runs one
+`document2md.batch.BatchConverter` conversion."""
+import argparse
+import subprocess
+import sys
+from pathlib import Path
+
+from document2md.batch import BatchConverter
+from document2md.converter import DEFAULT_TIMEOUT_SECONDS
+
+
+def parse_args(argv=None):
+    """Parse the `document2md` command-line arguments (`argv`, or `sys.argv` when
+    `None`) and return the resulting `argparse.Namespace`."""
+    parser = argparse.ArgumentParser(
+        description="Convert a local PDF, or an ordered set of scanned page images, to "
+        "Markdown — any document, such as an edition of Mexico's official gazette (DOF)."
+    )
+    parser.add_argument(
+        "--pdf", default=None,
+        help="Convert this local PDF file.",
+    )
+    parser.add_argument(
+        "--images", nargs="+", default=None, metavar="PATH",
+        help="Convert this ordered list of scanned page image files (one note spanning "
+        "several pages).",
+    )
+    parser.add_argument(
+        "--filename", default=None,
+        help="Output Markdown filename. Defaults to the --pdf file's own name; required with "
+        "--images, since there's no single input name to derive one from.",
+    )
+    parser.add_argument("--outdir", default="output", help="Output directory (default: output/)")
+    parser.add_argument(
+        "--titulo", default=None,
+        help="Title of the note to keep — crops the converted Markdown down to just that note "
+        "(the whole edition's Markdown is kept by default). Combine with --titulo-siguiente.",
+    )
+    parser.add_argument(
+        "--titulo-siguiente", default=None,
+        help="Title of the note right after --titulo, marking where the kept note ends",
+    )
+    parser.add_argument(
+        "--min-confidence", type=float, default=0.6,
+        help="Minimum title-match confidence (0..1) required to apply a --titulo/--titulo-siguiente "
+        "boundary; a weaker match falls back to keeping more text rather than dropping content "
+        "(default: 0.6)",
+    )
+    parser.add_argument(
+        "--keep-pages", action="store_true",
+        help="With --titulo, also keep the uncropped Markdown as <outdir>/<pdf stem>.full.md",
+    )
+    parser.add_argument(
+        "--keep-mineru-output", action="store_true",
+        help="Keep mineru's raw output (layout/model JSON, rendered PDFs...) in "
+        "<outdir>/<pdf stem>_mineru/ instead of discarding it",
+    )
+    return parser.parse_args(argv)
+
+
+def main(argv=None):
+    """Entry point for the `document2md` console script: parse arguments, run one
+    `BatchConverter` conversion, and print where the Markdown was saved.
+    Exits with an error message (no traceback) on a missing/ambiguous input
+    source or a mineru timeout."""
+    args = parse_args(argv)
+
+    sources_given = sum(x is not None for x in (args.pdf, args.images))
+    if sources_given != 1:
+        sys.exit("Provide exactly one of: --pdf or --images.")
+
+    outdir = Path(args.outdir)
+    outdir.mkdir(parents=True, exist_ok=True)
+
+    if args.pdf is not None:
+        pdf_path = Path(args.pdf)
+        if not pdf_path.is_file():
+            sys.exit(f"--pdf file not found: {pdf_path}")
+        md_filename = args.filename or pdf_path.with_suffix(".md").name
+        path_or_paths = pdf_path
+    else:
+        if args.filename is None:
+            sys.exit("--filename is required with --images (there's no single input name to derive one from).")
+        image_paths = [Path(p) for p in args.images]
+        missing = [p for p in image_paths if not p.is_file()]
+        if missing:
+            sys.exit(f"--images file(s) not found: {', '.join(str(p) for p in missing)}")
+        md_filename = args.filename
+        path_or_paths = image_paths
+
+    print("Converting to Markdown (mineru)...")
+    try:
+        with BatchConverter() as convert:
+            md_path = convert(
+                path_or_paths, outdir, md_filename, args.titulo, args.titulo_siguiente,
+                min_confidence=args.min_confidence,
+                keep_pages=args.keep_pages,
+                keep_mineru_output=args.keep_mineru_output,
+            )
+    except subprocess.TimeoutExpired:
+        sys.exit(
+            f"Conversion timed out after {DEFAULT_TIMEOUT_SECONDS}s. "
+            "This document may be unusually large."
+        )
+    print(f"Markdown saved to: {md_path}")
+
+
+if __name__ == "__main__":
+    main()