feat: OCR scans with tesseract, drop docling from the default path. (#33)

pdftotext still wins on born-digital PDFs. Empty text layers go through
pdftoppm + tesseract eng+deu. Optional OCR_ENGINE=paddle. Gitea #6.

bin/tools/mailconv.py

@@ -7,7 +7,10 @@ offline against fixtures.
 from __future__ import annotations
 
 import html
+import os
 import re
+import subprocess
+import tempfile
 import zipfile
 from pathlib import Path
 
@@ -18,9 +21,10 @@ OFFICE_SUFFIXES = {".docx", ".pptx", ".xlsx", ".html", ".htm", ".epub", ".eml",
 PDF_SUFFIXES = {".pdf"}
 IMAGE_SUFFIXES = {".png", ".jpg", ".jpeg", ".gif", ".bmp", ".tiff", ".tif", ".webp"}
 ARCHIVE_SUFFIXES = {".zip"}
-# Legacy binary Office (doc/xls/ppt) — markitdown/docling skip them; we try
+# Legacy binary Office (doc/xls/ppt) — markitdown skip them; we try
 # pandoc first, else leave a stub.
 LEGACY_OFFICE_SUFFIXES = {".doc", ".xls", ".ppt"}
+TESS_LANG = "eng+deu"
 
 CONVERTIBLE_SUFFIXES = (
     TEXT_SUFFIXES | OFFICE_SUFFIXES | PDF_SUFFIXES | IMAGE_SUFFIXES | ARCHIVE_SUFFIXES | LEGACY_OFFICE_SUFFIXES
@@ -146,3 +150,82 @@ def zip_extract_safe(zip_path: Path, dest: Path) -> list[Path]:
 
 def is_convertible(suffix: str) -> bool:
     return suffix.lower() in CONVERTIBLE_SUFFIXES
+
+
+def convert_pdf(path: Path, ocr: bool = False) -> str:
+    """pdftotext -layout first; empty text layer → pdftoppm + tesseract.
+
+    `ocr` is unused for born-digital PDFs (text layer wins). Scans OCR
+    automatically. This path never execs an ONNX document converter.
+    """
+    del ocr  # scans OCR when the text layer is empty; flag is for images
+    text = pdf_fast_text(path)
+    if text and text.strip():
+        return normalize_markdown(text)
+    scanned = ocr_pdf(path)
+    if scanned and scanned.strip():
+        return normalize_markdown(scanned)
+    if text:
+        return normalize_markdown(text)
+    return "\n<!-- pdf has no text layer (ocr unavailable) -->\n"
+
+
+def pdf_fast_text(path: Path) -> str | None:
+    """pdftotext -layout; None when poppler is missing or the command fails."""
+    try:
+        proc = subprocess.run(
+            ["pdftotext", "-layout", str(path), "-"],
+            capture_output=True, timeout=60)
+    except (OSError, subprocess.TimeoutExpired):
+        return None
+    if proc.returncode != 0:
+        return None
+    return proc.stdout.decode("utf-8", errors="replace")
+
+
+def ocr_pdf(path: Path) -> str:
+    """Rasterize with pdftoppm and OCR each page (tesseract or paddle)."""
+    try:
+        with tempfile.TemporaryDirectory(prefix="2dph-ocr-") as tmp:
+            prefix = str(Path(tmp) / "page")
+            proc = subprocess.run(
+                ["pdftoppm", "-png", "-r", "200", str(path), prefix],
+                capture_output=True, timeout=120)
+            if proc.returncode != 0:
+                return ""
+            pages = sorted(Path(tmp).glob("page*.png"))
+            parts = [ocr_image(p) for p in pages]
+            return "\n\n".join(p for p in parts if p and p.strip())
+    except (OSError, subprocess.TimeoutExpired):
+        return ""
+
+
+def ocr_image(path: Path) -> str:
+    engine = os.environ.get("OCR_ENGINE", "tesseract")
+    if engine == "paddle":
+        return _ocr_paddle(path)
+    return _ocr_tesseract(path)
+
+
+def _ocr_tesseract(path: Path) -> str:
+    try:
+        proc = subprocess.run(
+            ["tesseract", str(path), "stdout", "-l", TESS_LANG, "--psm", "6"],
+            capture_output=True, timeout=120)
+    except (OSError, subprocess.TimeoutExpired):
+        return ""
+    if proc.returncode != 0:
+        return ""
+    return proc.stdout.decode("utf-8", errors="replace").strip()
+
+
+def _ocr_paddle(path: Path) -> str:
+    try:
+        proc = subprocess.run(
+            ["paddleocr", "ocr", "-i", str(path)],
+            capture_output=True, timeout=180)
+    except (OSError, subprocess.TimeoutExpired):
+        return ""
+    if proc.returncode != 0:
+        return ""
+    return proc.stdout.decode("utf-8", errors="replace").strip()

bin/tools/test_bin_layout.py

@@ -136,6 +136,33 @@ class BinLayoutTest(unittest.TestCase):
             "index_mail must point at bin/brain/index.go",
         )
 
+    def test_mail_ocr_is_tesseract_not_docling(self) -> None:
+        self._assert_shebang("bin/mail/ocr.go")
+        ocr = (ROOT / "bin" / "mail" / "ocr.go").read_text()
+        self.assertIn("internal/ocr", ocr)
+        self.assertIn("mail_ocr", ocr)
+        self.assertNotIn("github.com/otiai10/gosseract", ocr)
+        py = (ROOT / "bin" / "mail" / "import").read_text()
+        self.assertNotIn("from docling", py)
+        self.assertNotIn("import docling", py)
+        self.assertIn("convert_pdf", py)
+        conv = (ROOT / "bin" / "tools" / "mailconv.py").read_text()
+        self.assertIn("pdftotext", conv)
+        self.assertIn("pdftoppm", conv)
+        self.assertIn("tesseract", conv)
+        self.assertIn("eng+deu", conv)
+        self.assertNotIn("from docling", conv)
+        self.assertNotIn("import docling", conv)
+        self.assertNotIn("gocv", conv.lower())
+        proj = (ROOT / "pyproject.toml").read_text()
+        self.assertNotIn("docling", proj)
+        ci = (ROOT / ".github" / "workflows" / "ci.yml").read_text()
+        self.assertIn("tesseract-ocr", ci)
+        self.assertIn("./internal/ocr", ci)
+        compose = (ROOT / "compose.yaml").read_text()
+        self.assertIn("ocr-paddle", compose)
+        self.assertIn("OCR_ENGINE", compose)
+
     def test_markdown_import_is_go_not_python_exec(self) -> None:
         self._assert_shebang("bin/markdown/import.go")
         text = (ROOT / "bin" / "markdown" / "import.go").read_text()

bin/tools/test_mailconv.py

@@ -8,10 +8,13 @@ from pathlib import Path
 sys.path.insert(0, os.path.dirname(__file__))
 
 from mailconv import (  # noqa: E402
+    TESS_LANG,
     clean_email_address,
+    convert_pdf,
     html_to_markdown,
     is_convertible,
     normalize_markdown,
+    ocr_image,
     split_zip_members,
     subject_to_filename,
     zip_extract_safe,
@@ -100,6 +103,92 @@ class TestMailConv(unittest.TestCase):
         self.assertFalse(is_convertible(".exe"))
         self.assertFalse(is_convertible(".unknown"))
 
+    def test_convert_pdf_prefers_pdftotext(self):
+        import mailconv as mc
+
+        calls: list[list[str]] = []
+
+        def fake_run(cmd, **kwargs):
+            calls.append(list(cmd))
+
+            class P:
+                returncode = 0
+                stdout = b"Invoice BM25 layout"
+                stderr = b""
+
+            return P()
+
+        self._patch_run(mc, fake_run)
+        out = convert_pdf(Path(self._tmp("born.pdf")))
+        self.assertIn("BM25", out)
+        self.assertEqual(calls[0][:2], ["pdftotext", "-layout"])
+        self.assertFalse(any(c[0] == "tesseract" for c in calls))
+        self.assertFalse(any(c[0] == "pdftoppm" for c in calls))
+
+    def test_convert_pdf_empty_layer_uses_pdftoppm_tesseract(self):
+        import mailconv as mc
+
+        calls: list[list[str]] = []
+
+        def fake_run(cmd, **kwargs):
+            calls.append(list(cmd))
+
+            class P:
+                returncode = 0
+                stdout = b""
+                stderr = b""
+
+            if cmd[0] == "pdftotext":
+                P.stdout = b"  \n"
+                return P()
+            if cmd[0] == "pdftoppm":
+                prefix = Path(cmd[-1])
+                (prefix.parent / "page-1.png").write_bytes(b"fake")
+                return P()
+            if cmd[0] == "tesseract":
+                P.stdout = b"scanned HELLO"
+                return P()
+            return P()
+
+        self._patch_run(mc, fake_run)
+        out = convert_pdf(Path(self._tmp("scan.pdf")))
+        self.assertIn("HELLO", out)
+        bins = [c[0] for c in calls]
+        self.assertIn("pdftotext", bins)
+        self.assertIn("pdftoppm", bins)
+        self.assertIn("tesseract", bins)
+        tess = next(c for c in calls if c[0] == "tesseract")
+        self.assertIn(TESS_LANG, tess)
+        self.assertNotIn("docling", " ".join(bins))
+
+    def test_ocr_image_paddle_engine(self):
+        import mailconv as mc
+
+        calls: list[list[str]] = []
+
+        def fake_run(cmd, **kwargs):
+            calls.append(list(cmd))
+
+            class P:
+                returncode = 0
+                stdout = b"paddle text"
+                stderr = b""
+
+            return P()
+
+        self._patch_run(mc, fake_run)
+        os.environ["OCR_ENGINE"] = "paddle"
+        try:
+            out = ocr_image(Path(self._tmp("x.png")))
+        finally:
+            os.environ.pop("OCR_ENGINE", None)
+        self.assertEqual(out, "paddle text")
+        self.assertEqual(calls[0][:2], ["paddleocr", "ocr"])
+
+    def _patch_run(self, mod, fn) -> None:
+        self.addCleanup(setattr, mod.subprocess, "run", mod.subprocess.run)
+        mod.subprocess.run = fn
+
     def _mk_zip(self, members):
         zpath = Path(self._tmp("arc.zip"))
         with zipfile.ZipFile(zpath, "w") as zf: