document2md 0.3.0__py3-none-any.whl

document2md/__init__.py

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

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/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()

document2md/converter.py

@@ -0,0 +1,183 @@
+"""Shell out to mineru to OCR a PDF or a set of scanned page images into
+Markdown, then rewrite its raw HTML table fallback into Markdown tables (see
+document2md.tables).
+
+Reuses an already-running mineru-api server via MINERU_API_URL when one is
+set (see document2md.mineru_server), so a batch of documents shares one warm
+server instead of each call starting and stopping its own.
+"""
+import contextlib
+import os
+import shutil
+import subprocess
+import tempfile
+from pathlib import Path
+
+from document2md.mineru_server import ENV_VAR as MINERU_API_URL_ENV_VAR
+from document2md.mineru_server import MineruServer
+from document2md.tables import html_tables_to_markdown
+
+# Some real DOF editions run to hundreds of pages with heavy table content,
+# and mineru has been observed to stall indefinitely on a single page/table
+# in such cases rather than just running slowly. This bounds how long any
+# one conversion is allowed to run before we give up on it.
+DEFAULT_TIMEOUT_SECONDS = 3600
+
+
+def _mineru_out_dir(md_path: Path, keep_mineru_output: bool):
+    """Context manager yielding the directory mineru should write its raw
+    output (Markdown, layout/model JSON, rendered PDFs...) into.
+
+    Normally that output is only a stepping stone to the Markdown this module
+    returns, so it lives in a throwaway temp dir. When `keep_mineru_output` is
+    set, callers debugging a bad conversion need to see that raw output
+    instead of it vanishing with the temp dir, so it is written to
+    `<md stem>_mineru/` next to `md_path` and left there."""
+    if keep_mineru_output:
+        out_dir = md_path.parent / f"{md_path.stem}_mineru"
+        out_dir.mkdir(parents=True, exist_ok=True)
+        return contextlib.nullcontext(str(out_dir))
+    return tempfile.TemporaryDirectory()
+
+
+def _require_mineru() -> None:
+    """Raise RuntimeError with an actionable message if the `mineru` CLI
+    isn't on PATH, instead of letting `subprocess.run` fail opaquely."""
+    if shutil.which("mineru") is None:
+        raise RuntimeError(
+            "'mineru' is required to convert documents but isn't installed. "
+            "Install document2md's dependencies: pip install document2md"
+        )
+
+
+def _run_mineru(input_path: Path, tmp_out: str, timeout: float) -> tuple[str, Path | None]:
+    """Run mineru's pipeline backend on one input file (PDF or image) inside
+    the given temp directory. Returns the raw Markdown text and the directory
+    of any figures mineru extracted (or None if there were none).
+
+    Reuses the MINERU_API_URL server if set (see mineru_server.MineruServer),
+    so batch conversions don't reload models once per document."""
+    api_url = os.environ.get(MINERU_API_URL_ENV_VAR)
+    cmd = ["mineru", "-o", tmp_out, "-p", str(input_path), "-b", "pipeline"]
+    if api_url:
+        cmd += ["--api-url", api_url]
+    subprocess.run(cmd, check=True, timeout=timeout)
+
+    auto_dir = Path(tmp_out) / input_path.stem / "auto"
+    md_text = (auto_dir / f"{input_path.stem}.md").read_text(encoding="utf-8")
+    images_src = auto_dir / "images"
+    if images_src.is_dir() and any(images_src.iterdir()):
+        return md_text, images_src
+    return md_text, None
+
+
+def convert_to_markdown(
+    pdf_path: Path,
+    md_path: Path,
+    timeout: float = DEFAULT_TIMEOUT_SECONDS,
+    keep_mineru_output: bool = False,
+) -> None:
+    """Convert a PDF to Markdown using mineru's pipeline backend.
+
+    mineru auto-detects which parts of the document need OCR internally, so
+    this handles both born-digital and scanned DOF editions, and produces
+    much cleaner Markdown (real paragraphs, accurate headings) than plain
+    text-layer extraction — at the cost of being far slower (mineru runs
+    real layout/OCR models even on already-digital text).
+
+    Complex tables, which mineru emits as raw HTML, are rewritten to Markdown
+    tables (see tables.html_tables_to_markdown) so the output is Markdown all
+    the way through.
+
+    If MINERU_API_URL is set (see mineru_server.MineruServer), reuses that
+    already-running server instead of letting mineru spin up (and tear down)
+    its own temporary one for this single call — this is what lets a batch
+    of documents avoid reloading the models once per document.
+
+    `keep_mineru_output` writes mineru's raw output (its own Markdown, layout
+    JSON, rendered layout/model PDFs...) to `<md stem>_mineru/` next to
+    `md_path` instead of a temp dir that disappears at the end of the call —
+    useful when a conversion looks wrong and mineru's own read of the page is
+    the first thing worth inspecting.
+
+    Raises subprocess.TimeoutExpired if mineru doesn't finish within
+    `timeout` seconds — callers doing batch work should catch this and skip
+    the offending document rather than let one stuck conversion block an
+    entire run."""
+    _require_mineru()
+
+    with _mineru_out_dir(md_path, keep_mineru_output) as tmp_out:
+        md_text, images_src = _run_mineru(pdf_path, tmp_out, timeout)
+        if images_src is not None:
+            images_dirname = f"{pdf_path.stem}_images"
+            shutil.copytree(
+                images_src, md_path.parent / images_dirname, dirs_exist_ok=True
+            )
+            md_text = md_text.replace("](images/", f"]({images_dirname}/")
+
+        md_path.write_text(html_tables_to_markdown(md_text), encoding="utf-8")
+
+
+def convert_images_to_markdown(
+    image_paths: list[Path],
+    md_path: Path,
+    timeout: float = DEFAULT_TIMEOUT_SECONDS,
+    keep_mineru_output: bool = False,
+) -> None:
+    """Convert one or more scanned page images into a single Markdown document.
+
+    This is the OCR path for notes that come as scanned pages rather than
+    digital text — e.g. the JPEGs downloaded by dofjson's
+    download_nota_imagenes(). Each image is OCR'd with the same mineru
+    pipeline backend as convert_to_markdown() and the results are
+    concatenated in the order given (page order), so a note spanning several
+    pages becomes one continuous Markdown file.
+
+    Complex tables mineru emits as raw HTML are rewritten to Markdown tables
+    (see tables.html_tables_to_markdown), like convert_to_markdown().
+
+    The page images typically hold more than the note of interest (a page can
+    start or end mid-note); callers wanting only one note should slice the
+    result afterwards — see cutter.cut_markdown_by_titles(), or use
+    BatchConverter, which does the cut inline.
+
+    Figures mineru extracts from a page are copied next to the output under
+    `<md stem>_images/<image stem>/` (namespaced per page so figures from
+    different pages can't collide), and their Markdown references rewritten to
+    match. Raises subprocess.TimeoutExpired like convert_to_markdown().
+
+    `keep_mineru_output`, like in convert_to_markdown(), keeps mineru's raw
+    per-page output instead of discarding it — each page lands in its own
+    `<md stem>_mineru/<image stem>/` subdirectory, mirroring how the
+    extracted figures are namespaced per page.
+
+    A note spanning several pages OCRs each page with a separate `mineru`
+    invocation; left alone, that means reloading mineru's layout/OCR models
+    once per page. When MINERU_API_URL isn't already set (i.e. no caller is
+    already running a batch server across multiple notes) and there's more
+    than one page, this starts a MineruServer for the duration of the loop
+    so all of this note's pages share one already-warm server instead of
+    each page starting and stopping its own."""
+    _require_mineru()
+    image_paths = [Path(p) for p in image_paths]
+    if not image_paths:
+        raise ValueError("convert_images_to_markdown requires at least one image path")
+
+    images_dirname = f"{md_path.stem}_images"
+    parts = []
+    needs_server = len(image_paths) > 1 and MINERU_API_URL_ENV_VAR not in os.environ
+    server = MineruServer() if needs_server else contextlib.nullcontext()
+    with server, _mineru_out_dir(md_path, keep_mineru_output) as tmp_out:
+        for image_path in image_paths:
+            md_text, images_src = _run_mineru(image_path, tmp_out, timeout)
+            if images_src is not None:
+                page_dest = md_path.parent / images_dirname / image_path.stem
+                shutil.copytree(images_src, page_dest, dirs_exist_ok=True)
+                md_text = md_text.replace(
+                    "](images/", f"]({images_dirname}/{image_path.stem}/"
+                )
+            parts.append(md_text.strip())
+
+    md_path.write_text(
+        html_tables_to_markdown("\n\n".join(parts)) + "\n", encoding="utf-8"
+    )

document2md/cutter.py

@@ -0,0 +1,189 @@
+"""Slice the Markdown OCR'd from a note's scanned page images down to just the
+note of interest.
+
+The page images downloaded for a note (dofjson.download_nota_imagenes) hold
+whole pages: the first page usually begins with the tail of the previous note,
+and the last page often ends with the start of the next one. But the per-day
+note index gives us the title of every note in order, so we can locate two
+boundaries in the OCR'd text — where THIS note's title appears (start) and
+where the NEXT note's title appears (end) — and keep only what lies between.
+
+Matching is fuzzy on purpose: OCR text differs from the index title in case,
+accents, line breaks and the odd misread character, so titles are compared on
+an accent-folded, marker-stripped, whitespace-collapsed form, and located with
+difflib's longest-matching-block alignment rather than an exact search.
+"""
+import difflib
+import re
+import unicodedata
+
+_SKIP_CHARS = set("#*|\\>_`~[]")
+_HEADING_LINE = re.compile(r"^#{1,6}\s")
+
+
+def _normalize_with_map(text: str) -> tuple[str, list[int]]:
+    """Return an accent-folded, lowercased, marker-stripped, single-spaced copy
+    of `text`, alongside a map from each normalized-character position back to
+    its index in the original `text` (so a match can be sliced from the
+    original)."""
+    norm_chars: list[str] = []
+    idx_map: list[int] = []
+    prev_space = True
+    for i, ch in enumerate(text):
+        base = unicodedata.normalize("NFKD", ch)
+        base = "".join(c for c in base if not unicodedata.combining(c)).lower()
+        if not base or base in _SKIP_CHARS:
+            continue
+        if base.isspace():
+            if not prev_space:
+                norm_chars.append(" ")
+                idx_map.append(i)
+                prev_space = True
+            continue
+        for c in base:
+            if c in _SKIP_CHARS:
+                continue
+            norm_chars.append(c)
+            idx_map.append(i)
+        prev_space = False
+    return "".join(norm_chars), idx_map
+
+
+def _locate(
+    norm_text: str, idx_map: list[int], title: str, from_norm: int = 0
+) -> tuple[int | None, int | None, float]:
+    """Best-effort match for `title` within `norm_text[from_norm:]`. Returns
+    (normalized offset, original-text offset, 0..1 confidence), or
+    (None, None, 0.0) if nothing matches.
+
+    `from_norm` lets the caller skip past an earlier region — used to find the
+    NEXT note's title after the current one, which matters when consecutive
+    titles are near-duplicates (e.g. two deslinde avisos differing only in a
+    number) and a whole-text search would otherwise anchor on the first.
+
+    Confidence is matched characters divided by the span of haystack they are
+    spread across (floored at the title's own length): a title that appears
+    together, even split by a few OCR glitches, matches within a span close
+    to its own length. Boilerplate that merely echoes some of the title's
+    words (e.g. a shared date phrase in running prose) racks up the same
+    matched-character count but scattered over a much wider span, so it is
+    penalized instead of being scored as if it were one solid match — that
+    scattering is exactly what let such boilerplate be mistaken for a real
+    title match before."""
+    norm_title, _ = _normalize_with_map(title)
+    norm_title = norm_title.strip()
+    if not norm_title:
+        return None, None, 0.0
+
+    haystack = norm_text[from_norm:]
+    matcher = difflib.SequenceMatcher(None, haystack, norm_title, autojunk=False)
+    blocks = [b for b in matcher.get_matching_blocks() if b.size > 0]
+    if not blocks:
+        return None, None, 0.0
+    anchor = max(blocks, key=lambda b: b.size)
+
+    matched = sum(b.size for b in blocks)
+    span = max(b.a + b.size for b in blocks) - min(b.a for b in blocks)
+    confidence = matched / max(span, len(norm_title))
+    start_local = max(0, anchor.a - anchor.b)
+    start_norm = min(from_norm + start_local, len(idx_map) - 1)
+    return start_norm, idx_map[start_norm], confidence
+
+
+def locate_titles(
+    markdown: str, titulo: str, titulo_siguiente: str | None = None
+) -> dict:
+    """Locate the start (this note's title) and end (next note's title)
+    boundaries in `markdown`. Exposed mainly for inspection/testing;
+    cut_markdown_by_titles() is the usual entry point.
+
+    Returns a dict with `start`, `start_confidence`, `end`, `end_confidence`
+    (offsets are into `markdown`; `end` is None when there is no next title or
+    it wasn't found after the start)."""
+    norm_text, idx_map = _normalize_with_map(markdown)
+
+    if titulo:
+        start_norm, start, start_conf = _locate(norm_text, idx_map, titulo)
+    else:
+        start_norm, start, start_conf = None, None, 0.0
+    if start is None:
+        start_norm, start = 0, 0
+
+    end, end_conf = None, 0.0
+    if titulo_siguiente:
+        # Skip past the current note's own title before searching for the next
+        # one, so near-duplicate titles don't anchor the end back on the start.
+        norm_titulo, _ = _normalize_with_map(titulo or "")
+        from_norm = min(start_norm + len(norm_titulo.strip()), len(norm_text))
+        _, candidate, end_conf = _locate(
+            norm_text, idx_map, titulo_siguiente, from_norm=from_norm
+        )
+        if candidate is not None and candidate > start:
+            end = candidate
+
+    return {
+        "start": start,
+        "start_confidence": start_conf,
+        "end": end,
+        "end_confidence": end_conf,
+    }
+
+
+def cut_markdown_by_titles(
+    markdown: str,
+    titulo: str,
+    titulo_siguiente: str | None = None,
+    min_confidence: float = 0.6,
+) -> str:
+    """Return the slice of `markdown` that belongs to the note titled `titulo`.
+
+    `titulo` and `titulo_siguiente` are the note's own title and the next
+    note's title (in publication order) from the per-day index — the next
+    title marks where this note ends.
+
+    A boundary is only applied when its match confidence clears
+    `min_confidence`: a start below the threshold falls back to the beginning
+    of the text, and a weak/absent next-title match falls back to the end, so
+    a poor match degrades to keeping more text rather than dropping the note's
+    content."""
+    if not markdown.strip():
+        return ""
+
+    located = locate_titles(markdown, titulo, titulo_siguiente)
+
+    start = located["start"] if located["start_confidence"] >= min_confidence else 0
+    boundary_applied = (
+        located["end"] is not None and located["end_confidence"] >= min_confidence
+    )
+
+    # Snap the start to the beginning of its line, so the note's own heading
+    # marker (`## `) travels with its title instead of being clipped off.
+    start = markdown.rfind("\n", 0, start) + 1
+
+    if boundary_applied:
+        # Snap the end to the start of the next note's title line, then walk
+        # back over the blank and heading lines right before it: the DOF prints
+        # the next note's organism headers (e.g. `# SECRETARIA DE ENERGIA`)
+        # ABOVE its title, so they'd otherwise be left dangling at the tail of
+        # this note.
+        end = markdown.rfind("\n", 0, located["end"]) + 1
+        end = _trim_preceding_headings(markdown, end)
+    else:
+        end = len(markdown)
+    if end <= start:
+        end = len(markdown)
+
+    return markdown[start:end].strip()
+
+
+def _trim_preceding_headings(markdown: str, end: int) -> int:
+    """Move `end` back over any run of blank and heading (`#…`) lines that
+    immediately precede it, returning the new offset."""
+    while end > 0:
+        line_start = markdown.rfind("\n", 0, end - 1) + 1
+        line = markdown[line_start:end].strip()
+        if line == "" or _HEADING_LINE.match(line):
+            end = line_start
+        else:
+            break
+    return end

document2md/mineru_server.py

@@ -0,0 +1,103 @@
+"""Manages a persistent `mineru-api` process for batch conversions.
+
+Left to itself, the `mineru` CLI spins up (and tears down) a fresh temporary
+API server — reloading all layout/OCR models — on every single invocation.
+That's fine for converting one document, but wasteful when a batch job
+converts many documents in the same run. MineruServer starts one `mineru-api`
+process, waits for it to report healthy, and points `convert_to_markdown` at
+it via the MINERU_API_URL environment variable for the duration of the batch.
+"""
+import os
+import socket
+import subprocess
+import time
+
+import requests
+
+ENV_VAR = "MINERU_API_URL"
+
+
+def _find_free_port() -> int:
+    """Return a currently-unused TCP port on 127.0.0.1, by binding to port 0
+    and reading back the OS-assigned port."""
+    with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
+        s.bind(("127.0.0.1", 0))
+        return s.getsockname()[1]
+
+
+def _wait_until_healthy(base_url: str, timeout: float = 300.0, interval: float = 1.0) -> None:
+    """Poll `base_url`'s `/health` endpoint every `interval` seconds until it
+    answers 200, raising RuntimeError if it hasn't within `timeout` seconds —
+    mineru-api takes a while to come up because it loads its models on
+    startup."""
+    deadline = time.monotonic() + timeout
+    health_url = f"{base_url}/health"
+    while time.monotonic() < deadline:
+        try:
+            if requests.get(health_url, timeout=2).status_code == 200:
+                return
+        except requests.exceptions.RequestException:
+            pass
+        time.sleep(interval)
+    raise RuntimeError(f"mineru-api did not become healthy within {timeout}s at {health_url}")
+
+
+class MineruServer:
+    """Context manager: starts a persistent mineru-api server on __enter__,
+    exposes it to convert_to_markdown() via MINERU_API_URL, and stops it on
+    __exit__ (restoring any previous MINERU_API_URL value)."""
+
+    def __init__(self, host: str = "127.0.0.1", port: int | None = None):
+        """Create an unstarted server bound to `host`/`port` (a free port is
+        picked when `port` is `None`); call `start()` (or use as a context
+        manager) to actually launch it."""
+        self.host = host
+        self.port = port if port is not None else _find_free_port()
+        self.base_url = f"http://{self.host}:{self.port}"
+        self._process: subprocess.Popen | None = None
+        self._previous_env_value: str | None = None
+
+    def start(self) -> None:
+        """Launch `mineru-api` as a subprocess, block until it reports
+        healthy (stopping it again on failure), and point MINERU_API_URL at
+        it so `converter.py` picks it up."""
+        self._process = subprocess.Popen(
+            ["mineru-api", "--host", self.host, "--port", str(self.port)],
+            stdout=subprocess.DEVNULL,
+            stderr=subprocess.DEVNULL,
+        )
+        try:
+            _wait_until_healthy(self.base_url)
+        except Exception:
+            self.stop()
+            raise
+        self._previous_env_value = os.environ.get(ENV_VAR)
+        os.environ[ENV_VAR] = self.base_url
+
+    def stop(self) -> None:
+        """Restore MINERU_API_URL to whatever it was before `start()`, and
+        terminate the `mineru-api` subprocess (killing it if it doesn't exit
+        within 15s)."""
+        if self._previous_env_value is None:
+            os.environ.pop(ENV_VAR, None)
+        else:
+            os.environ[ENV_VAR] = self._previous_env_value
+
+        if self._process is None:
+            return
+        self._process.terminate()
+        try:
+            self._process.wait(timeout=15)
+        except subprocess.TimeoutExpired:
+            self._process.kill()
+            self._process.wait()
+        self._process = None
+
+    def __enter__(self) -> "MineruServer":
+        """Call `start()` and return `self`."""
+        self.start()
+        return self
+
+    def __exit__(self, exc_type, exc, tb) -> None:
+        """Call `stop()`."""
+        self.stop()

document2md/tables.py

@@ -0,0 +1,132 @@
+"""Turn the raw HTML tables mineru emits into Markdown tables.
+
+mineru renders simple tables as Markdown but falls back to raw HTML
+(``<table>…</table>`` with rowspan/colspan) for anything complex. This module
+rewrites those HTML tables into GitHub Markdown tables so document2md's output is
+Markdown all the way through — no leftover HTML.
+
+Implemented with the standard library's ``html.parser`` only (no BeautifulSoup)
+to keep document2md's dependencies to just ``requests`` and ``mineru``.
+"""
+import re
+from html.parser import HTMLParser
+
+_TABLE_RE = re.compile(r"<table\b[^>]*>.*?</table>", re.DOTALL | re.IGNORECASE)
+
+
+def html_tables_to_markdown(text: str) -> str:
+    """Replace every ``<table>…</table>`` block in `text` with a GitHub
+    Markdown table, leaving everything else untouched. Blank lines are ensured
+    around each converted table so it renders as a table."""
+
+    def _replace(match: "re.Match") -> str:
+        rows = _parse_rows(match.group(0))
+        rendered = _render(rows)
+        return f"\n\n{rendered}\n\n" if rendered else match.group(0)
+
+    return re.sub(r"\n{3,}", "\n\n", _TABLE_RE.sub(_replace, text))
+
+
+class _TableParser(HTMLParser):
+    """Collect a single HTML table's cells as rows of (text, attrs)."""
+
+    def __init__(self):
+        super().__init__(convert_charrefs=True)
+        self.rows: list[list[tuple[str, dict]]] = []
+        self._row: list[tuple[str, dict]] | None = None
+        self._cell: list[str] | None = None
+        self._cell_attrs: dict = {}
+
+    def handle_starttag(self, tag, attrs):
+        """Open a new row on `<tr>`, a new cell (recording its attrs, for
+        rowspan/colspan) on `<td>`/`<th>`, and turn `<br>` inside a cell into
+        a space so wrapped lines don't run together."""
+        tag = tag.lower()
+        if tag == "tr":
+            self._row = []
+        elif tag in ("td", "th"):
+            self._cell = []
+            self._cell_attrs = {k.lower(): v for k, v in attrs}
+        elif tag == "br" and self._cell is not None:
+            self._cell.append(" ")
+
+    def handle_endtag(self, tag):
+        """Close the current cell into `self._row` on `</td>`/`</th>`, and
+        the current row into `self.rows` on `</tr>`."""
+        tag = tag.lower()
+        if tag in ("td", "th") and self._cell is not None and self._row is not None:
+            self._row.append(("".join(self._cell), self._cell_attrs))
+            self._cell = None
+        elif tag == "tr" and self._row is not None:
+            self.rows.append(self._row)
+            self._row = None
+
+    def handle_data(self, data):
+        """Append text content to the currently-open cell, if any."""
+        if self._cell is not None:
+            self._cell.append(data)
+
+
+def _parse_rows(fragment: str) -> list[list[tuple[str, dict]]]:
+    """Parse a single ``<table>…</table>`` fragment into `_TableParser`'s row
+    structure."""
+    parser = _TableParser()
+    parser.feed(fragment)
+    parser.close()
+    return parser.rows
+
+
+def _span(attrs: dict, name: str) -> int:
+    """Read `attrs[name]` (`rowspan`/`colspan`) as a positive int, defaulting
+    to 1 when it is missing or not a valid integer."""
+    try:
+        return max(1, int(attrs.get(name, 1)))
+    except (TypeError, ValueError):
+        return 1
+
+
+def _clean_cell(text: str) -> str:
+    """Collapse a cell's whitespace to single spaces and escape `|` so it
+    can't be mistaken for a Markdown table column separator."""
+    return re.sub(r"\s+", " ", text).strip().replace("|", r"\|")
+
+
+def _grid(rows: list[list[tuple[str, dict]]]) -> list[list[str]]:
+    """Flatten rows into a rectangular grid honouring rowspan/colspan. A
+    spanned cell's text goes in its top-left slot; the covered slots are filled
+    with empty strings, since Markdown tables can't merge cells."""
+    filled: dict[tuple[int, int], str] = {}
+    n_cols = 0
+    for r, row in enumerate(rows):
+        c = 0
+        for text, attrs in row:
+            while (r, c) in filled:
+                c += 1
+            row_span = _span(attrs, "rowspan")
+            col_span = _span(attrs, "colspan")
+            cell = _clean_cell(text)
+            for dr in range(row_span):
+                for dc in range(col_span):
+                    filled[(r + dr, c + dc)] = cell if (dr == 0 and dc == 0) else ""
+            c += col_span
+            n_cols = max(n_cols, c)
+    return [[filled.get((r, c), "") for c in range(n_cols)] for r in range(len(rows))]
+
+
+def _render(rows: list[list[tuple[str, dict]]]) -> str:
+    """Render `_grid(rows)` as a GitHub Markdown table (first row as the
+    header), or `""` if the table has no rows/columns."""
+    grid = _grid(rows)
+    if not grid or not grid[0]:
+        return ""
+
+    n_cols = max(len(row) for row in grid)
+    grid = [row + [""] * (n_cols - len(row)) for row in grid]
+
+    lines = [
+        "| " + " | ".join(grid[0]) + " |",
+        "|" + "---|" * n_cols,
+    ]
+    for row in grid[1:]:
+        lines.append("| " + " | ".join(row) + " |")
+    return "\n".join(lines)

document2md-0.3.0.dist-info/METADATA

@@ -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.dist-info/RECORD

@@ -0,0 +1,13 @@
+document2md/__init__.py,sha256=aj7I0ERFad-qtEX6Qk88AuLuJdQIRGYwBMOrGvH-VoI,98
+document2md/batch.py,sha256=8cmHuD1VsFEz9kt42x9o0Oq64TQHZq_XaXagSjLfExw,4582
+document2md/cli.py,sha256=esehDNiKuWW4lmy76pBoOx6UVy3wKZBWA69Rn1kcNic,4454
+document2md/converter.py,sha256=Le9CRTMACQvkI3FZtlKIKQp7IdF9c6iYEADwXCMjqdE,8555
+document2md/cutter.py,sha256=ZyrP42tL3m-dQJD7aR4qKlziipgGeiGlH-Q4wPPGlUA,7778
+document2md/mineru_server.py,sha256=oOIJDeQX-hNWmDPZC7Jl2PqzrEcrp-SGf0oW6_nz1LU,3983
+document2md/tables.py,sha256=r6JxI1Jo_jqBKybaS8tn7-Ot20MMAi5PVkebBzhK8cI,5023
+document2md-0.3.0.dist-info/licenses/LICENSE,sha256=wA3K6wenbE9W-CRkfkqA9A1yrSnjX1HF7d39YPBI91Q,11338
+document2md-0.3.0.dist-info/METADATA,sha256=fh3DXuj5WZ_VMFcwbzlUD42QNSRK4EIStVQ_pN5r_9k,5204
+document2md-0.3.0.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+document2md-0.3.0.dist-info/entry_points.txt,sha256=YX6oFN0auVrrJTKynBI60PUqTVUcvolxyrJ8f2ogPXg,53
+document2md-0.3.0.dist-info/top_level.txt,sha256=AIczvx4b8KEaa7kjtp7aGbZDtr8t-kspvlXKKqNOS7w,12
+document2md-0.3.0.dist-info/RECORD,,

document2md-0.3.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.0.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

document2md-0.3.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+document2md = document2md.cli:main

document2md-0.3.0.dist-info/licenses/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.dist-info/top_level.txt

@@ -0,0 +1 @@
+document2md