Chore: Generate PDF thumbnails with pdftoppm and Pillow instead of ImageMagick

Replace the ImageMagick convert based PDF thumbnail path with pdftoppm and
Pillow. Keeps thumbnails at 500px wide for small and odd sized pages, covers
the qpdf repair and double failure paths, removes the unused run_convert
helper, hardens thumbnail encoding, deprecates PAPERLESS_CONVERT_MEMORY_LIMIT
and PAPERLESS_CONVERT_TMPDIR, and corrects the related docs and CI.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

src/documents/parsers.py

@@ -1,8 +1,8 @@
 from __future__ import annotations
 
 import logging
+import math
 import mimetypes
-import os
 import shutil
 import subprocess
 import tempfile
@@ -68,58 +68,6 @@ def get_supported_file_extensions() -> set[str]:
     return extensions
 
 
-def run_convert(
-    input_file,
-    output_file,
-    *,
-    density=None,
-    scale=None,
-    alpha=None,
-    strip=False,
-    trim=False,
-    type=None,
-    depth=None,
-    auto_orient=False,
-    use_cropbox=False,
-    extra=None,
-    logging_group=None,
-) -> None:
-    environment = os.environ.copy()
-    if settings.CONVERT_MEMORY_LIMIT:
-        # MAGICK_MEMORY_LIMIT sets the maximum amount of RAM the pixel cache can use.
-        # MAGICK_MAP_LIMIT sets the maximum amount of memory-mapped I/O allowed.
-        #
-        # For large-format documents  ImageMagick will hit the RAM limit and
-        # immediately try to "map" the remaining data. If MAGICK_MAP_LIMIT isn't
-        # also set, the process may trigger an OOM kill because the default
-        # system/policy map limit is often too restrictive for these massive bitmaps.
-        environment["MAGICK_MEMORY_LIMIT"] = settings.CONVERT_MEMORY_LIMIT
-        environment["MAGICK_MAP_LIMIT"] = settings.CONVERT_MEMORY_LIMIT
-    if settings.CONVERT_TMPDIR:
-        environment["MAGICK_TMPDIR"] = settings.CONVERT_TMPDIR
-
-    args = [settings.CONVERT_BINARY]
-    args += ["-density", str(density)] if density else []
-    args += ["-scale", str(scale)] if scale else []
-    args += ["-alpha", str(alpha)] if alpha else []
-    args += ["-strip"] if strip else []
-    args += ["-trim"] if trim else []
-    args += ["-type", str(type)] if type else []
-    args += ["-depth", str(depth)] if depth else []
-    args += ["-auto-orient"] if auto_orient else []
-    args += ["-define", "pdf:use-cropbox=true"] if use_cropbox else []
-    args += [str(input_file), str(output_file)]
-
-    logger.debug("Execute: " + " ".join(args), extra={"group": logging_group})
-
-    try:
-        run_subprocess(args, environment, logger)
-    except subprocess.CalledProcessError as e:
-        raise ParseError(f"Convert failed at {args}") from e
-    except Exception as e:  # pragma: no cover
-        raise ParseError("Unknown error running convert") from e
-
-
 def get_default_thumbnail() -> Path:
     """
     Returns the path to a generic thumbnail
@@ -127,46 +75,153 @@ def get_default_thumbnail() -> Path:
     return (Path(__file__).parent / "resources" / "document.webp").resolve()
 
 
-def make_thumbnail_from_pdf_gs_fallback(in_path, temp_dir, logging_group=None) -> Path:
-    out_path: Path = Path(temp_dir) / "convert_gs.webp"
+_THUMBNAIL_MAX_WIDTH = 500
+_THUMBNAIL_MAX_HEIGHT = 5000
+# Used only when the page geometry cannot be read
+_THUMBNAIL_FALLBACK_DPI = 150
+# Matches the density the thumbnail was previously rendered at before scaling
+_THUMBNAIL_MAX_DPI = 300
 
-    # if convert fails, fall back to extracting
-    # the first PDF page as a PNG using Ghostscript
-    logger.warning(
-        "Thumbnail generation with ImageMagick failed, falling back "
-        "to ghostscript. Check your /etc/ImageMagick-x/policy.xml!",
-        extra={"group": logging_group},
-    )
-    # Ghostscript doesn't handle WebP outputs
-    gs_out_path: Path = Path(temp_dir) / "gs_out.png"
-    cmd = [settings.GS_BINARY, "-q", "-sDEVICE=pngalpha", "-o", gs_out_path, in_path]
+
+def rasterize_pdf_page_to_png(
+    in_path: Path,
+    out_path: Path,
+    *,
+    dpi: int,
+    logging_group=None,
+) -> None:
+    """
+    Rasterizes the first page of a PDF to a PNG with pdftoppm.
+    """
+    # -singlefile drops the page number and -png appends ".png", so pass the
+    # path without its suffix
+    args = [
+        "pdftoppm",
+        "-f",
+        "1",
+        "-l",
+        "1",
+        "-r",
+        str(dpi),
+        "-png",
+        "-singlefile",
+        "-cropbox",
+        str(in_path),
+        str(out_path.with_suffix("")),
+    ]
+
+    logger.debug("Execute: " + " ".join(args), extra={"group": logging_group})
 
     try:
-        try:
-            run_subprocess(cmd, logger=logger)
-        except subprocess.CalledProcessError as e:
-            raise ParseError(f"Thumbnail (gs) failed at {cmd}") from e
-        # then run convert on the output from gs to make WebP
-        run_convert(
-            density=300,
-            scale="500x5000>",
-            alpha="remove",
-            strip=True,
-            trim=False,
-            auto_orient=True,
-            input_file=gs_out_path,
-            output_file=out_path,
-            logging_group=logging_group,
-        )
+        run_subprocess(args, logger=logger)
+    except subprocess.CalledProcessError as e:
+        raise ParseError(f"pdftoppm failed at {args}") from e
+    except Exception as e:  # pragma: no cover
+        raise ParseError("Unknown error running pdftoppm") from e
 
+
+def encode_thumbnail_webp(
+    png_path: Path,
+    out_path: Path,
+) -> None:
+    """
+    Flattens alpha onto white, shrinks to fit and saves as WebP.
+    """
+    from PIL import Image
+
+    try:
+        with Image.open(png_path) as im:
+            if im.mode in ("RGBA", "LA"):
+                flattened = Image.new("RGB", im.size, (255, 255, 255))
+                flattened.paste(im, mask=im.split()[-1])
+            else:
+                flattened = im.convert("RGB")
+
+        flattened.thumbnail((_THUMBNAIL_MAX_WIDTH, _THUMBNAIL_MAX_HEIGHT))
+        flattened.save(out_path, format="WEBP")
+    except (OSError, Image.DecompressionBombError) as e:
+        raise ParseError(f"Unable to encode thumbnail from {png_path}") from e
+
+
+def _compute_thumbnail_dpi(in_path: Path, logging_group=None) -> int:
+    """
+    Computes the DPI which renders the first page of the PDF at or just above
+    the thumbnail size in one pass, never above 300.
+    """
+    from paperless.parsers.utils import get_pdf_first_page_size_points
+
+    size = get_pdf_first_page_size_points(in_path)
+    if size is None:
+        logger.debug(
+            "Could not read PDF page size, using fallback DPI",
+            extra={"group": logging_group},
+        )
+        return _THUMBNAIL_FALLBACK_DPI
+
+    width_pts, height_pts = size
+    dpi_for_width = _THUMBNAIL_MAX_WIDTH * 72 / width_pts
+    dpi_for_height = _THUMBNAIL_MAX_HEIGHT * 72 / height_pts
+    # Round up so the render is never a few pixels short of the target; the
+    # shrink-only clamp in encode_thumbnail_webp trims the excess.
+    return max(
+        1,
+        math.ceil(min(_THUMBNAIL_MAX_DPI, dpi_for_width, dpi_for_height)),
+    )
+
+
+def _render_pdf_thumbnail(
+    in_path: Path,
+    png_path: Path,
+    out_path: Path,
+    logging_group=None,
+) -> None:
+    dpi = _compute_thumbnail_dpi(in_path, logging_group=logging_group)
+    rasterize_pdf_page_to_png(
+        in_path,
+        png_path,
+        dpi=dpi,
+        logging_group=logging_group,
+    )
+    encode_thumbnail_webp(png_path, out_path)
+
+
+def _repair_pdf_with_qpdf(in_path: Path, out_path: Path) -> None:
+    # qpdf exits 3 after a repair; --warning-exit-0 keeps that from failing
+    try:
+        shutil.copy(in_path, out_path)
+        run_subprocess(
+            ["qpdf", "--warning-exit-0", "--replace-input", str(out_path)],
+            logger=logger,
+        )
+    except (subprocess.CalledProcessError, OSError) as e:
+        raise ParseError(f"qpdf repair failed for {in_path}") from e
+
+
+def make_thumbnail_from_pdf_qpdf_fallback(
+    in_path: Path,
+    temp_dir: Path,
+    logging_group=None,
+) -> Path:
+    png_path = temp_dir / "page1_repaired.png"
+    out_path = temp_dir / "convert_qpdf.webp"
+    repaired_path = temp_dir / "repaired.pdf"
+
+    logger.warning(
+        "Thumbnail generation with pdftoppm failed, attempting qpdf repair and retry.",
+        extra={"group": logging_group},
+    )
+
+    try:
+        _repair_pdf_with_qpdf(in_path, repaired_path)
+        _render_pdf_thumbnail(repaired_path, png_path, out_path, logging_group)
         return out_path
 
     except ParseError as e:
-        logger.error(f"Unable to make thumbnail with Ghostscript: {e}")
+        logger.error(f"Unable to make thumbnail after qpdf repair: {e}")
         # The caller might expect a generated thumbnail that can be moved,
         # so we need to copy it before it gets moved.
         # https://github.com/paperless-ngx/paperless-ngx/issues/3631
-        default_thumbnail_path: Path = Path(temp_dir) / "document.webp"
+        default_thumbnail_path = temp_dir / "document.webp"
         copy_file_with_basic_stats(get_default_thumbnail(), default_thumbnail_path)
         return default_thumbnail_path
 
@@ -175,25 +230,18 @@ def make_thumbnail_from_pdf(in_path: Path, temp_dir: Path, logging_group=None) -
     """
     The thumbnail of a PDF is just a 500px wide image of the first page.
     """
+    png_path: Path = temp_dir / "page1.png"
     out_path: Path = temp_dir / "convert.webp"
 
-    # Run convert to get a decent thumbnail
     try:
-        run_convert(
-            density=300,
-            scale="500x5000>",
-            alpha="remove",
-            strip=True,
-            trim=False,
-            auto_orient=True,
-            use_cropbox=True,
-            input_file=f"{in_path}[0]",
-            output_file=str(out_path),
-            logging_group=logging_group,
-        )
+        _render_pdf_thumbnail(in_path, png_path, out_path, logging_group)
     except ParseError as e:
-        logger.error(f"Unable to make thumbnail with convert: {e}")
-        out_path = make_thumbnail_from_pdf_gs_fallback(in_path, temp_dir, logging_group)
+        logger.error(f"Unable to make thumbnail with pdftoppm: {e}")
+        out_path = make_thumbnail_from_pdf_qpdf_fallback(
+            in_path,
+            temp_dir,
+            logging_group,
+        )
 
     return out_path
 

src/documents/tests/test_parsers.py

@@ -1,11 +1,22 @@
+import subprocess
 from collections.abc import Generator
+from pathlib import Path
 
+import pikepdf
 import pytest
+from PIL import Image
 from pytest_django.fixtures import Settings
+from pytest_mock import MockerFixture
 
+from documents.parsers import ParseError
+from documents.parsers import _compute_thumbnail_dpi
+from documents.parsers import encode_thumbnail_webp
 from documents.parsers import get_default_file_extension
+from documents.parsers import get_default_thumbnail
 from documents.parsers import get_supported_file_extensions
 from documents.parsers import is_file_ext_supported
+from documents.parsers import make_thumbnail_from_pdf
+from documents.parsers import rasterize_pdf_page_to_png
 from paperless.parsers.registry import get_parser_registry
 from paperless.parsers.registry import reset_parser_registry
 from paperless.parsers.tesseract import RasterisedDocumentParser
@@ -125,3 +136,329 @@ class TestParserAvailability:
         assert is_file_ext_supported(".pdf")
         assert not is_file_ext_supported(".hsdfh")
         assert not is_file_ext_supported("")
+
+
+class TestComputeThumbnailDpi:
+    @pytest.mark.parametrize(
+        ("size", "expected"),
+        [
+            pytest.param((612.0, 792.0), 59, id="letter-width-bound"),
+            pytest.param((792.0, 612.0), 46, id="landscape-rounded-up"),
+            pytest.param((612.0, 100000.0), 4, id="tall-strip-height-bound"),
+            pytest.param((200.0, 300.0), 180, id="small-page-width-bound"),
+            pytest.param((72.0, 72.0), 300, id="tiny-page-capped-at-300"),
+            pytest.param((1000000.0, 1000000.0), 1, id="huge-page-minimum-one"),
+            pytest.param(None, 150, id="unreadable-geometry-fallback"),
+        ],
+    )
+    def test_dpi_from_page_size(
+        self,
+        mocker: MockerFixture,
+        tmp_path: Path,
+        size: tuple[float, float] | None,
+        expected: int,
+    ) -> None:
+        """
+        GIVEN:
+            - A first page of the given size, or unreadable geometry
+        WHEN:
+            - The thumbnail DPI is computed
+        THEN:
+            - The expected DPI is returned
+        """
+        mocker.patch(
+            "paperless.parsers.utils.get_pdf_first_page_size_points",
+            return_value=size,
+        )
+        assert _compute_thumbnail_dpi(tmp_path / "doc.pdf") == expected
+
+
+class TestMakeThumbnailFromPdf:
+    @pytest.fixture
+    def work_dir(self, tmp_path: Path) -> Path:
+        path = tmp_path / "work"
+        path.mkdir()
+        return path
+
+    @staticmethod
+    def _write_blank_pdf(path: Path, page_size: tuple[int, int] = (612, 792)) -> Path:
+        pdf = pikepdf.new()
+        pdf.add_blank_page(page_size=page_size)
+        pdf.save(path, object_stream_mode=pikepdf.ObjectStreamMode.disable)
+        return path
+
+    @pytest.mark.parametrize(
+        ("page_size", "expected_width"),
+        [
+            pytest.param((612, 792), 500, id="letter"),
+            pytest.param((792, 612), 500, id="landscape-letter"),
+            pytest.param((595, 842), 500, id="a4"),
+            pytest.param((200, 300), 500, id="small-page"),
+            pytest.param((72, 72), 300, id="tiny-page-capped"),
+        ],
+    )
+    def test_thumbnail_width(
+        self,
+        tmp_path: Path,
+        work_dir: Path,
+        page_size: tuple[int, int],
+        expected_width: int,
+    ) -> None:
+        """
+        GIVEN:
+            - A PDF whose first page has the given size in points
+        WHEN:
+            - A thumbnail is made from it
+        THEN:
+            - The thumbnail has the expected width
+        """
+        pdf_path = self._write_blank_pdf(tmp_path / "in.pdf", page_size)
+
+        thumb = make_thumbnail_from_pdf(pdf_path, work_dir)
+
+        assert thumb == work_dir / "convert.webp"
+        with Image.open(thumb) as im:
+            assert im.format == "WEBP"
+            assert im.width == expected_width
+
+    @classmethod
+    def _write_pdf_without_xref(cls, path: Path) -> Path:
+        """
+        Cuts off the xref and trailer, which pdftoppm cannot recover from but qpdf can.
+        """
+        cls._write_blank_pdf(path)
+        data = path.read_bytes()
+        path.write_bytes(data[: data.rindex(b"\nxref")])
+        return path
+
+    def test_qpdf_repair_produces_real_thumbnail(
+        self,
+        tmp_path: Path,
+        work_dir: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - A PDF with its xref table and trailer cut off
+        WHEN:
+            - A thumbnail is made from it
+        THEN:
+            - The thumbnail is rendered from a qpdf repaired copy
+            - The original file is unchanged
+        """
+        pdf_path = self._write_pdf_without_xref(tmp_path / "broken.pdf")
+        original_bytes = pdf_path.read_bytes()
+
+        with pytest.raises(ParseError):
+            rasterize_pdf_page_to_png(pdf_path, work_dir / "probe.png", dpi=50)
+
+        thumb = make_thumbnail_from_pdf(pdf_path, work_dir)
+
+        assert thumb == work_dir / "convert_qpdf.webp"
+        with Image.open(thumb) as im:
+            assert im.format == "WEBP"
+            assert im.width == 500
+        assert pdf_path.read_bytes() == original_bytes
+
+    @pytest.mark.parametrize(
+        "qpdf_error",
+        [
+            pytest.param(subprocess.CalledProcessError(2, "qpdf"), id="qpdf-fails"),
+            pytest.param(None, id="repaired-still-unrenderable"),
+        ],
+    )
+    def test_double_failure_uses_default_thumbnail(
+        self,
+        mocker: MockerFixture,
+        tmp_path: Path,
+        work_dir: Path,
+        qpdf_error: subprocess.CalledProcessError | None,
+    ) -> None:
+        """
+        GIVEN:
+            - A PDF that cannot be rendered, even after qpdf repair
+        WHEN:
+            - A thumbnail is made from it
+        THEN:
+            - A copy of the default thumbnail is returned
+        """
+        mocker.patch(
+            "documents.parsers.rasterize_pdf_page_to_png",
+            side_effect=ParseError("Does not compute."),
+        )
+        if qpdf_error is not None:
+            mocker.patch("documents.parsers.run_subprocess", side_effect=qpdf_error)
+        pdf_path = self._write_blank_pdf(tmp_path / "in.pdf")
+
+        thumb = make_thumbnail_from_pdf(pdf_path, work_dir)
+
+        assert thumb == work_dir / "document.webp"
+        assert thumb.read_bytes() == get_default_thumbnail().read_bytes()
+
+
+class TestRasterizePdfPageToPng:
+    @staticmethod
+    def _write_pdf(
+        path: Path,
+        *,
+        crop_box: tuple[float, float, float, float] | None = None,
+        rotate: int | None = None,
+    ) -> Path:
+        pdf = pikepdf.new()
+        pdf.add_blank_page(page_size=(144, 72))
+        pdf.add_blank_page(page_size=(300, 300))
+        page = pdf.pages[0]
+        if crop_box is not None:
+            page.obj.CropBox = pikepdf.Array(crop_box)
+        if rotate is not None:
+            page.obj.Rotate = rotate
+        pdf.save(path)
+        return path
+
+    @pytest.mark.parametrize(
+        ("crop_box", "rotate", "expected_size"),
+        [
+            pytest.param(None, None, (144, 72), id="plain"),
+            pytest.param(None, 90, (72, 144), id="rotated-90"),
+            pytest.param((0, 0, 72, 36), None, (72, 36), id="crop-box"),
+        ],
+    )
+    def test_renders_first_page_to_exact_path(
+        self,
+        tmp_path: Path,
+        crop_box: tuple[float, float, float, float] | None,
+        rotate: int | None,
+        expected_size: tuple[int, int],
+    ) -> None:
+        """
+        GIVEN:
+            - A two page PDF, first page optionally cropped or rotated
+        WHEN:
+            - The first page is rasterized at 72 DPI
+        THEN:
+            - Only out_path is written, sized to the first page's crop and rotation
+        """
+        pdf_path = self._write_pdf(
+            tmp_path / "in.pdf",
+            crop_box=crop_box,
+            rotate=rotate,
+        )
+        out_dir = tmp_path / "out"
+        out_dir.mkdir()
+        out_path = out_dir / "page1.png"
+
+        rasterize_pdf_page_to_png(pdf_path, out_path, dpi=72)
+
+        assert list(out_dir.iterdir()) == [out_path]
+        with Image.open(out_path) as im:
+            assert im.format == "PNG"
+            assert im.size == expected_size
+
+    def test_failure_raises_parse_error(self, tmp_path: Path) -> None:
+        """
+        GIVEN:
+            - A file that is not a PDF
+        WHEN:
+            - Rasterization is attempted
+        THEN:
+            - A ParseError is raised
+        """
+        bad = tmp_path / "bad.pdf"
+        bad.write_bytes(b"not a pdf")
+
+        with pytest.raises(ParseError):
+            rasterize_pdf_page_to_png(bad, tmp_path / "page1.png", dpi=72)
+
+
+class TestEncodeThumbnailWebp:
+    @pytest.mark.parametrize(
+        ("mode", "color"),
+        [
+            pytest.param("RGBA", (0, 0, 0, 0), id="rgba"),
+            pytest.param("LA", (0, 0), id="la"),
+        ],
+    )
+    def test_alpha_flattened_onto_white(
+        self,
+        tmp_path: Path,
+        mode: str,
+        color: tuple[int, ...],
+    ) -> None:
+        """
+        GIVEN:
+            - A fully transparent PNG with an alpha channel
+        WHEN:
+            - It is encoded as a thumbnail
+        THEN:
+            - The WebP output is RGB with the transparency flattened to white
+        """
+        png_path = tmp_path / "in.png"
+        Image.new(mode, (20, 10), color).save(png_path)
+        out_path = tmp_path / "out.webp"
+
+        encode_thumbnail_webp(png_path, out_path)
+
+        with Image.open(out_path) as im:
+            assert im.format == "WEBP"
+            assert im.mode == "RGB"
+            assert im.size == (20, 10)
+            red, green, blue = im.getpixel((10, 5))
+            assert min(red, green, blue) >= 250
+
+    @pytest.mark.parametrize(
+        ("in_size", "expected_size"),
+        [
+            pytest.param((1000, 2000), (500, 1000), id="too-wide-shrunk"),
+            pytest.param((100, 10000), (50, 5000), id="too-tall-shrunk"),
+            pytest.param((100, 200), (100, 200), id="small-not-enlarged"),
+        ],
+    )
+    def test_size_clamped_and_downsampled(
+        self,
+        tmp_path: Path,
+        in_size: tuple[int, int],
+        expected_size: tuple[int, int],
+    ) -> None:
+        """
+        GIVEN:
+            - A rendered image
+        WHEN:
+            - It is encoded as a thumbnail
+        THEN:
+            - It is fit within 500x5000 and never enlarged
+        """
+        png_path = tmp_path / "in.png"
+        Image.new("RGB", in_size, (255, 255, 255)).save(png_path)
+        out_path = tmp_path / "out.webp"
+
+        encode_thumbnail_webp(png_path, out_path)
+
+        with Image.open(out_path) as im:
+            assert im.size == expected_size
+
+    @pytest.mark.parametrize(
+        "error",
+        [
+            pytest.param(OSError("broken image"), id="os-error"),
+            pytest.param(Image.DecompressionBombError("too large"), id="bomb"),
+        ],
+    )
+    def test_decode_failure_raises_parse_error(
+        self,
+        tmp_path: Path,
+        mocker: MockerFixture,
+        error: Exception,
+    ) -> None:
+        """
+        GIVEN:
+            - Opening the rendered image fails
+        WHEN:
+            - It is encoded as a thumbnail
+        THEN:
+            - A ParseError is raised
+        """
+        png_path = tmp_path / "in.png"
+        Image.new("RGB", (10, 10)).save(png_path)
+        mocker.patch("PIL.Image.open", side_effect=error)
+
+        with pytest.raises(ParseError):
+            encode_thumbnail_webp(png_path, tmp_path / "out.webp")