Fix: Don't attempt to index created dates which are not representable inside the FTS index (#14390)

An interrupted rebuild left an empty index stamped as current, so the next
start reported it as up to date. Mark the rebuild as in progress and only
clear the marker once it completes.

.github/workflows/ci-backend.yml

@@ -111,7 +111,7 @@ jobs:
         timeout-minutes: 12
         uses: $/.github/actions/apt-install
         with:
-          packages: unpaper tesseract-ocr imagemagick ghostscript poppler-utils qpdf
+          packages: unpaper tesseract-ocr imagemagick ghostscript poppler-utils
       - name: Configure ImageMagick
         run: |
           sudo cp docker/rootfs/etc/ImageMagick-6/paperless-policy.xml /etc/ImageMagick-7/policy.xml

docs/configuration.md

@@ -1315,17 +1315,29 @@ valid crontab(5) expression describing when to run.
 
 #### [`PAPERLESS_CONVERT_MEMORY_LIMIT=<num>`](#PAPERLESS_CONVERT_MEMORY_LIMIT) {#PAPERLESS_CONVERT_MEMORY_LIMIT}
 
-!!! warning
+: On smaller systems, or even in the case of Very Large Documents, the
+consumer may explode, complaining about how it's "unable to extend
+pixel cache". In such cases, try setting this to a reasonably low
+value, like 32. The default is to use whatever is necessary to do
+everything without writing to disk, and units are in megabytes.
 
-    Deprecated and has no effect, since PDF thumbnails no longer use
-    ImageMagick. It will be removed in a future release.
+    For more information on how to use this value, you should search the
+    web for "MAGICK_MEMORY_LIMIT".
+
+    Defaults to 0, which disables the limit.
 
 #### [`PAPERLESS_CONVERT_TMPDIR=<path>`](#PAPERLESS_CONVERT_TMPDIR) {#PAPERLESS_CONVERT_TMPDIR}
 
-!!! warning
+: Similar to the memory limit, if you've got a small system and your
+OS mounts /tmp as tmpfs, you should set this to a path that's on a
+physical disk, like /home/your_user/tmp or something. ImageMagick
+will use this as scratch space when crunching through very large
+documents.
 
-    Deprecated and has no effect, since PDF thumbnails no longer use
-    ImageMagick. It will be removed in a future release.
+    For more information on how to use this value, you should search the
+    web for "MAGICK_TMPDIR".
+
+    Default is none, which disables the temporary directory.
 
 #### [`PAPERLESS_APPS=<string>`](#PAPERLESS_APPS) {#PAPERLESS_APPS}
 

docs/setup.md

@@ -177,12 +177,12 @@ to a positive number to enable polling and disable native filesystem notificatio
     - `pkg-config` for mysqlclient (python dependency)
     - `fonts-liberation` for generating thumbnails for plain text
       files
-    - `imagemagick` >= 6 for image alpha handling
+    - `imagemagick` >= 6 for PDF conversion
     - `gnupg` for decrypting GPG-encrypted email
     - `libpq-dev` for PostgreSQL
     - `libmagic-dev` for mime type detection
     - `mariadb-client` for MariaDB compile time
-    - `poppler-utils` for thumbnail generation and barcode detection
+    - `poppler-utils` for barcode detection
 
     Use this list for your preferred package management:
 
@@ -416,8 +416,11 @@ to a positive number to enable polling and disable native filesystem notificatio
         You may need to change the path in the files. Example:
         `ExecStart=/opt/paperless/.local/bin/celery --app paperless worker --loglevel INFO`
 
-12. Harden ImageMagick by disabling formats that Paperless-ngx does not use.
-    PDF processing is not needed and should stay disabled.
+12. Configure ImageMagick to allow processing of PDF documents and disable
+    formats that Paperless-ngx does not use. Most distributions disable PDF
+    processing by default, since PDF documents can contain malware. If you
+    don't enable it, Paperless-ngx will fall back to Ghostscript for certain
+    steps such as thumbnail generation.
 
     Configure the active ImageMagick policy file (commonly
     `/etc/ImageMagick-6/policy.xml` or `/etc/ImageMagick-7/policy.xml`) and

paperless.conf.example

@@ -50,6 +50,8 @@ PAPERLESS_SECRET_KEY=change-me
 #PAPERLESS_OCR_ROTATE_PAGES=true
 #PAPERLESS_OCR_ROTATE_PAGES_THRESHOLD=12.0
 #PAPERLESS_OCR_USER_ARGS={}
+#PAPERLESS_CONVERT_MEMORY_LIMIT=0
+#PAPERLESS_CONVERT_TMPDIR=/var/tmp/paperless
 
 # Software tweaks
 

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
@@ -68,6 +68,58 @@ 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
@@ -75,168 +127,46 @@ def get_default_thumbnail() -> Path:
     return (Path(__file__).parent / "resources" / "document.webp").resolve()
 
 
-_THUMBNAIL_MAX_WIDTH = 500
-_THUMBNAIL_MAX_HEIGHT = 5000
-# Used only when the page geometry cannot be read
-_THUMBNAIL_FALLBACK_DPI = 150
-# Applied before supersampling, so tiny pages are not enlarged
-_THUMBNAIL_MAX_DPI = 300
-# Rendering at a multiple and downsampling keeps text crisper
-_THUMBNAIL_SUPERSAMPLE = 2
-
-
-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:
-        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,
-    *,
-    supersample: int = 1,
-) -> None:
-    """
-    Flattens alpha onto white, undoes supersampling, 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")
-
-        if supersample > 1:
-            flattened = flattened.resize(
-                (
-                    max(1, round(flattened.width / supersample)),
-                    max(1, round(flattened.height / supersample)),
-                ),
-                Image.Resampling.LANCZOS,
-            )
-
-        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) -> tuple[int, int]:
-    """
-    Returns (dpi, supersample). Unknown geometry is not supersampled, since
-    the render size cannot be bounded.
-    """
-    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, 1
-
-    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 downsampled render is never a few pixels short of the
-    # target; the shrink-only clamp in encode_thumbnail_webp trims the excess.
-    dpi = max(
-        1,
-        math.ceil(min(_THUMBNAIL_MAX_DPI, dpi_for_width, dpi_for_height)),
-    )
-    # At the 1 DPI floor the page is already oversized, so do not supersample
-    return dpi, 1 if dpi == 1 else _THUMBNAIL_SUPERSAMPLE
-
-
-def _render_pdf_thumbnail(
-    in_path: Path,
-    png_path: Path,
-    out_path: Path,
-    logging_group=None,
-) -> None:
-    dpi, supersample = _compute_thumbnail_dpi(in_path, logging_group=logging_group)
-    rasterize_pdf_page_to_png(
-        in_path,
-        png_path,
-        dpi=dpi * supersample,
-        logging_group=logging_group,
-    )
-    encode_thumbnail_webp(png_path, out_path, supersample=supersample)
-
-
-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"
+def make_thumbnail_from_pdf_gs_fallback(in_path, temp_dir, logging_group=None) -> Path:
+    out_path: Path = Path(temp_dir) / "convert_gs.webp"
 
+    # if convert fails, fall back to extracting
+    # the first PDF page as a PNG using Ghostscript
     logger.warning(
-        "Thumbnail generation with pdftoppm failed, attempting qpdf repair and retry.",
+        "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]
 
     try:
-        _repair_pdf_with_qpdf(in_path, repaired_path)
-        _render_pdf_thumbnail(repaired_path, png_path, out_path, logging_group)
+        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,
+        )
+
         return out_path
 
     except ParseError as e:
-        logger.error(f"Unable to make thumbnail after qpdf repair: {e}")
+        logger.error(f"Unable to make thumbnail with Ghostscript: {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 = temp_dir / "document.webp"
+        default_thumbnail_path: Path = Path(temp_dir) / "document.webp"
         copy_file_with_basic_stats(get_default_thumbnail(), default_thumbnail_path)
         return default_thumbnail_path
 
@@ -245,18 +175,25 @@ 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:
-        _render_pdf_thumbnail(in_path, png_path, out_path, logging_group)
-    except ParseError as e:
-        logger.error(f"Unable to make thumbnail with pdftoppm: {e}")
-        out_path = make_thumbnail_from_pdf_qpdf_fallback(
-            in_path,
-            temp_dir,
-            logging_group,
+        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,
         )
+    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)
 
     return out_path
 

src/documents/search/_backend.py

@@ -7,6 +7,7 @@ import threading
 import time
 from datetime import UTC
 from datetime import datetime
+from datetime import timedelta
 from enum import StrEnum
 from itertools import islice
 from typing import TYPE_CHECKING
@@ -31,6 +32,7 @@ from documents.search._query import parse_user_query
 from documents.search._schema import _write_sentinels
 from documents.search._schema import build_schema
 from documents.search._schema import open_or_rebuild_index
+from documents.search._schema import rebuild_in_progress
 from documents.search._schema import wipe_index
 from documents.search._tokenizer import ascii_fold
 from documents.search._tokenizer import autocomplete_tokens
@@ -54,6 +56,19 @@ if TYPE_CHECKING:
 
 logger = logging.getLogger("paperless.search")
 
+# tantivy stores dates as signed 64-bit nanoseconds since the Unix epoch, which
+# covers 1677-09-21T00:12:43 to 2262-04-11T23:47:16 UTC
+_INDEX_DATE_NANOS_MIN: Final[int] = -(2**63)
+_INDEX_DATE_NANOS_MAX: Final[int] = 2**63 - 1
+_UNIX_EPOCH: Final[datetime] = datetime(1970, 1, 1, tzinfo=UTC)
+
+
+def _is_indexable_date(value: datetime) -> bool:
+    """Whether value, at whole-second precision, fits tantivy's date range."""
+    nanos = ((value - _UNIX_EPOCH) // timedelta(seconds=1)) * 1_000_000_000
+    return _INDEX_DATE_NANOS_MIN <= nanos <= _INDEX_DATE_NANOS_MAX
+
+
 _LOCK_TIMEOUT_SECONDS: Final[float] = 10.0  # per-attempt acquire timeout
 _LOCK_RETRY_ATTEMPTS: Final[int] = 4  # total attempts (1 initial + 3 retries)
 _LOCK_BACKOFF_BASE: Final[float] = 1.0  # seconds
@@ -627,7 +642,15 @@ class TantivyBackend:
             document.created.day,
             tzinfo=UTC,
         )
-        doc.add_date("created", created_date)
+        if _is_indexable_date(created_date):
+            doc.add_date("created", created_date)
+        else:
+            logger.warning(
+                "Document %s has a created date (%s) outside the range the search "
+                "index can store; it will be indexed without a created date",
+                document.pk,
+                document.created,
+            )
         doc.add_date("modified", document.modified)
         doc.add_date("added", document.added)
 
@@ -1110,39 +1133,44 @@ class TantivyBackend:
                 flushing a segment, deferring merge work; they do not avoid it.
         """
         wipe_index(self._path)
-        new_index = tantivy.Index(build_schema(), path=str(self._path))
-        _write_sentinels(self._path)
-        register_tokenizers(new_index, settings.SEARCH_LANGUAGE)
+        # The marker covers the window where the empty index is already stamped
+        # as current but not yet populated, so an interrupted rebuild is retried.
+        with rebuild_in_progress(self._path):
+            new_index = tantivy.Index(build_schema(), path=str(self._path))
+            _write_sentinels(self._path)
+            register_tokenizers(new_index, settings.SEARCH_LANGUAGE)
 
-        # Point instance at the new index so _build_tantivy_doc uses it
-        old_index, old_schema = self._raw_index, self._raw_schema
-        self._raw_index = new_index
-        self._raw_schema = new_index.schema
-        # Stream documents one-by-one (so the progress bar advances per
-        # document) while fetching viewer permissions one SQL query per chunk.
-        # The stream is Sized, so iter_wrapper can still discover the total.
-        documents_stream = _DocumentViewerStream(documents, chunk_size=1000)
-        try:
-            writer = new_index.writer(heap_size=writer_heap_bytes)
-            for document, (viewer_ids, viewer_group_ids) in iter_wrapper(
-                documents_stream,
-            ):
-                doc = self._build_tantivy_doc(
-                    document,
-                    viewer_ids=viewer_ids,
-                    viewer_group_ids=viewer_group_ids,
-                )
-                writer.add_document(doc)
-            writer.commit()
-            # Wait for background merge threads to finish so all segments are
-            # fully merged and persisted before the index is considered rebuilt.
-            writer.wait_merging_threads()
-            new_index.reload()
-        except BaseException:  # pragma: no cover
-            # Restore old index on failure so the backend remains usable
-            self._raw_index = old_index
-            self._raw_schema = old_schema
-            raise
+            # Point instance at the new index so _build_tantivy_doc uses it
+            old_index, old_schema = self._raw_index, self._raw_schema
+            self._raw_index = new_index
+            self._raw_schema = new_index.schema
+            # Stream documents one-by-one (so the progress bar advances per
+            # document) while fetching viewer permissions one SQL query per
+            # chunk. The stream is Sized, so iter_wrapper can still discover
+            # the total.
+            documents_stream = _DocumentViewerStream(documents, chunk_size=1000)
+            try:
+                writer = new_index.writer(heap_size=writer_heap_bytes)
+                for document, (viewer_ids, viewer_group_ids) in iter_wrapper(
+                    documents_stream,
+                ):
+                    doc = self._build_tantivy_doc(
+                        document,
+                        viewer_ids=viewer_ids,
+                        viewer_group_ids=viewer_group_ids,
+                    )
+                    writer.add_document(doc)
+                writer.commit()
+                # Wait for background merge threads to finish so all segments
+                # are fully merged and persisted before the index is considered
+                # rebuilt.
+                writer.wait_merging_threads()
+                new_index.reload()
+            except BaseException:  # pragma: no cover
+                # Restore old index on failure so the backend remains usable
+                self._raw_index = old_index
+                self._raw_schema = old_schema
+                raise
 
 
 def chunked(iterable, size):

src/documents/search/_schema.py

@@ -4,6 +4,7 @@ import hashlib
 import json
 import logging
 import shutil
+from contextlib import contextmanager
 from typing import TYPE_CHECKING
 from typing import Final
 from typing import NamedTuple
@@ -16,6 +17,7 @@ from whoosh_compat import FieldKind
 from documents.search._fields import PUBLIC_FIELDS
 
 if TYPE_CHECKING:
+    from collections.abc import Iterator
     from pathlib import Path
 
 logger = logging.getLogger("paperless.search")
@@ -28,6 +30,11 @@ logger = logging.getLogger("paperless.search")
 # v3 - barcodes JSON field for stored barcode contents
 SCHEMA_VERSION: Final[int] = 3
 
+# Present in the index directory from the moment a full rebuild starts until it
+# finishes. If a rebuild is interrupted it is left behind, so the half-built
+# index is not mistaken for a complete one.
+REBUILD_MARKER: Final[str] = ".rebuilding"
+
 
 class FieldDescriptor(NamedTuple):
     """One tantivy field, in declaration order.
@@ -255,9 +262,9 @@ def needs_rebuild(index_dir: Path) -> bool:
     """
     Check if the search index needs rebuilding.
 
-    Reads .index_settings.json to compare the stored schema version, search
-    language and schema fingerprint against the current configuration. Returns
-    True if the file is missing, unparsable, or any value mismatches.
+    True if a previous full rebuild never finished (the rebuild marker is still
+    present), or if the index's stamped settings no longer match the current
+    configuration. See _settings_mismatch().
 
     Args:
         index_dir: Path to the search index directory
@@ -265,6 +272,40 @@ def needs_rebuild(index_dir: Path) -> bool:
     Returns:
         True if the index needs rebuilding, False if it's up to date
     """
+    if (index_dir / REBUILD_MARKER).exists():
+        logger.warning("Previous search index rebuild did not finish - rebuilding.")
+        return True
+    return _settings_mismatch(index_dir)
+
+
+@contextmanager
+def rebuild_in_progress(index_dir: Path) -> Iterator[None]:
+    """
+    Flag the index as incomplete for the duration of a full rebuild.
+
+    The marker is cleared only if the block exits cleanly. There is deliberately
+    no try/finally: an exception must leave the marker behind so the next
+    needs_rebuild() check retries the rebuild.
+    """
+    marker = index_dir / REBUILD_MARKER
+    marker.touch()
+    yield
+    marker.unlink(missing_ok=True)
+
+
+def _settings_mismatch(index_dir: Path) -> bool:
+    """
+    Check the stamped settings against the current configuration.
+
+    Reads .index_settings.json to compare the stored schema version, search
+    language and schema fingerprint. Returns True if the file is missing,
+    unparsable, or any value mismatches.
+
+    This deliberately ignores the rebuild marker: open_or_rebuild_index() uses it
+    so that a process opening the index while another process is mid-rebuild
+    (or after one died) does not wipe the partial index out from under it.
+    Repopulating is the job of ``document_index reindex``.
+    """
     settings_file = index_dir / ".index_settings.json"
     if not settings_file.exists():
         return True
@@ -333,7 +374,7 @@ def open_or_rebuild_index(index_dir: Path | None = None) -> tantivy.Index:
         index_dir = cast("Path", settings.INDEX_DIR)
     if not index_dir.exists():
         return tantivy.Index(build_schema())
-    if needs_rebuild(index_dir):
+    if _settings_mismatch(index_dir):
         wipe_index(index_dir)
         idx = tantivy.Index(build_schema(), path=str(index_dir))
         _write_sentinels(index_dir)

src/documents/tests/search/test_backend.py

@@ -1,4 +1,6 @@
 import json
+import logging
+from datetime import date
 from pathlib import Path
 
 import pytest
@@ -16,7 +18,10 @@ from documents.search._backend import TantivyBackend
 from documents.search._backend import WriteBatch
 from documents.search._backend import get_backend
 from documents.search._backend import reset_backend
+from documents.search._schema import REBUILD_MARKER
+from documents.search._schema import needs_rebuild
 from documents.signals.handlers import add_to_index
+from paperless_testing.dirs import PaperlessDirs
 from paperless_testing.factories import CorrespondentFactory
 from paperless_testing.factories import DocumentFactory
 from paperless_testing.factories import DocumentTypeFactory
@@ -823,6 +828,53 @@ class TestRebuild:
         backend.rebuild(Document.objects.all(), iter_wrapper=wrapper)
         assert 30 in seen
 
+    def test_successful_rebuild_leaves_index_up_to_date(
+        self,
+        backend: TantivyBackend,
+        paperless_dirs: PaperlessDirs,
+    ) -> None:
+        """
+        GIVEN:
+            - A backend and one document
+        WHEN:
+            - rebuild() completes
+        THEN:
+            - needs_rebuild() is False and no rebuild marker remains
+        """
+        DocumentFactory.create()
+
+        backend.rebuild(Document.objects.all())
+
+        assert needs_rebuild(paperless_dirs.index_dir) is False
+        assert not (paperless_dirs.index_dir / REBUILD_MARKER).exists()
+
+    def test_interrupted_rebuild_is_retried(
+        self,
+        backend: TantivyBackend,
+        paperless_dirs: PaperlessDirs,
+    ) -> None:
+        """
+        GIVEN:
+            - A rebuild that dies while indexing documents (e.g. the database
+              connection is lost)
+        WHEN:
+            - needs_rebuild() is checked afterwards
+        THEN:
+            - It is True, even though the empty index was already stamped with
+              current settings, so the next start rebuilds instead of reporting
+              the index as up to date
+        """
+        DocumentFactory.create()
+
+        def die(pairs):
+            raise RuntimeError("terminating connection due to administrator command")
+            yield  # pragma: no cover
+
+        with pytest.raises(RuntimeError):
+            backend.rebuild(Document.objects.all(), iter_wrapper=die)
+
+        assert needs_rebuild(paperless_dirs.index_dir) is True
+
     def test_includes_group_granted_viewers(self, backend: TantivyBackend) -> None:
         """Rebuild must index viewer ids for group-only grants, not just direct ones.
 
@@ -854,6 +906,79 @@ class TestRebuild:
         assert ids == [doc.pk]
 
 
+class TestCreatedDateOutOfRange:
+    """The index stores dates as nanosecond i64 values (1677-09-22 to 2262-04-11).
+
+    A document whose created date falls outside that window must not abort
+    indexing: it is indexed without a created value and a warning names it.
+    """
+
+    @pytest.mark.parametrize(
+        ("created", "expected_warnings"),
+        [
+            pytest.param(date(1677, 9, 22), 0, id="first-representable-day"),
+            pytest.param(date(2262, 4, 11), 0, id="last-representable-day"),
+            pytest.param(date(1677, 9, 21), 1, id="day-before-first"),
+            pytest.param(date(2262, 4, 12), 1, id="day-after-last"),
+            pytest.param(date(16, 8, 30), 1, id="two-digit-year-read-as-year-16"),
+            pytest.param(date(9999, 12, 31), 1, id="max-python-date"),
+        ],
+    )
+    def test_add_or_update_indexes_document_and_warns_when_out_of_range(
+        self,
+        backend: TantivyBackend,
+        caplog: pytest.LogCaptureFixture,
+        created: date,
+        expected_warnings: int,
+    ) -> None:
+        """
+        GIVEN:
+            - A document with a created date at or beyond the index date limits
+        WHEN:
+            - The document is added to the index
+        THEN:
+            - The document is indexed and searchable either way
+            - A warning naming the document is logged only for out-of-range dates
+        """
+        doc = DocumentFactory(created=created, content="boundarycontent")
+
+        with caplog.at_level(logging.WARNING, logger="paperless.search"):
+            backend.add_or_update(doc)
+
+        assert backend.search_ids("boundarycontent", user=None) == [doc.pk]
+        warnings = [r for r in caplog.records if r.levelno == logging.WARNING]
+        assert len(warnings) == expected_warnings
+        if expected_warnings:
+            assert f"Document {doc.pk}" in warnings[0].getMessage()
+
+    def test_rebuild_continues_past_out_of_range_document(
+        self,
+        backend: TantivyBackend,
+        caplog: pytest.LogCaptureFixture,
+    ) -> None:
+        """
+        GIVEN:
+            - A document with an unrepresentable created date among valid ones
+        WHEN:
+            - The index is rebuilt
+        THEN:
+            - Rebuild completes and every document is searchable
+            - A warning names the offending document
+        """
+        good = DocumentFactory(created=date(2016, 8, 30), content="rebuildcontent")
+        bad = DocumentFactory(created=date(16, 8, 30), content="rebuildcontent")
+
+        with caplog.at_level(logging.WARNING, logger="paperless.search"):
+            backend.rebuild(Document.objects.all())
+
+        assert sorted(backend.search_ids("rebuildcontent", user=None)) == sorted(
+            [good.pk, bad.pk],
+        )
+        warnings = [r for r in caplog.records if r.levelno == logging.WARNING]
+        assert len(warnings) == 1
+        assert f"Document {bad.pk}" in warnings[0].getMessage()
+
+
 class TestAutocomplete:
     """Test autocomplete functionality."""
 

src/documents/tests/test_parsers.py

@@ -1,22 +1,11 @@
-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
@@ -136,374 +125,3 @@ 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, 2), id="letter-width-bound"),
-            pytest.param((792.0, 612.0), (46, 2), id="landscape-rounded-up"),
-            pytest.param((612.0, 100000.0), (4, 2), id="tall-strip-height-bound"),
-            pytest.param((200.0, 300.0), (180, 2), id="small-page-width-bound"),
-            pytest.param((72.0, 72.0), (300, 2), id="tiny-page-capped-at-300"),
-            pytest.param(
-                (1000000.0, 1000000.0),
-                (1, 1),
-                id="huge-page-minimum-one-unsupersampled",
-            ),
-            pytest.param(None, (150, 1), id="unreadable-geometry-fallback"),
-        ],
-    )
-    def test_dpi_from_page_size(
-        self,
-        mocker: MockerFixture,
-        tmp_path: Path,
-        size: tuple[float, float] | None,
-        expected: tuple[int, int],
-    ) -> None:
-        """
-        GIVEN:
-            - A first page of the given size, or unreadable geometry
-        WHEN:
-            - The thumbnail DPI is computed
-        THEN:
-            - The expected DPI and supersample factor are 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(
-        ("size", "expected_dpi", "expected_supersample"),
-        [
-            pytest.param((612.0, 792.0), 118, 2, id="known-geometry-2x"),
-            pytest.param(None, 150, 1, id="unreadable-geometry-plain-fallback"),
-        ],
-    )
-    def test_render_dpi_requested(
-        self,
-        mocker: MockerFixture,
-        tmp_path: Path,
-        work_dir: Path,
-        size: tuple[float, float] | None,
-        expected_dpi: int,
-        expected_supersample: int,
-    ) -> None:
-        """
-        GIVEN:
-            - Readable or unreadable page geometry
-        WHEN:
-            - A thumbnail is made
-        THEN:
-            - Rasterize and encode get the matching DPI and supersample factor
-        """
-        mocker.patch(
-            "paperless.parsers.utils.get_pdf_first_page_size_points",
-            return_value=size,
-        )
-        rasterize = mocker.patch("documents.parsers.rasterize_pdf_page_to_png")
-        encode = mocker.patch("documents.parsers.encode_thumbnail_webp")
-
-        make_thumbnail_from_pdf(tmp_path / "in.pdf", work_dir)
-
-        assert rasterize.call_args.kwargs["dpi"] == expected_dpi
-        assert encode.call_args.kwargs["supersample"] == expected_supersample
-
-    @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", "supersample", "expected_size"),
-        [
-            pytest.param((1000, 2000), 1, (500, 1000), id="too-wide-shrunk"),
-            pytest.param((100, 10000), 1, (50, 5000), id="too-tall-shrunk"),
-            pytest.param((100, 200), 1, (100, 200), id="small-not-enlarged"),
-            pytest.param((1000, 1400), 2, (500, 700), id="2x-halved"),
-            pytest.param((1001, 1401), 2, (500, 700), id="2x-odd-rounded"),
-            pytest.param((600, 800), 2, (300, 400), id="2x-small-not-enlarged"),
-            pytest.param((900, 1200), 2, (450, 600), id="2x-below-clamp"),
-        ],
-    )
-    def test_size_clamped_and_downsampled(
-        self,
-        tmp_path: Path,
-        in_size: tuple[int, int],
-        supersample: int,
-        expected_size: tuple[int, int],
-    ) -> None:
-        """
-        GIVEN:
-            - A rendered image and its supersample factor
-        WHEN:
-            - It is encoded as a thumbnail with that factor
-        THEN:
-            - It is downsampled, 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, supersample=supersample)
-
-        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")

src/paperless/parsers/utils.py

@@ -265,52 +265,6 @@ def get_page_count_for_pdf(
         return None
 
 
-def get_pdf_first_page_size_points(
-    path: Path,
-    log: logging.Logger | None = None,
-) -> tuple[float, float] | None:
-    """Return the first page's (width, height) in PDF points, post-rotation.
-
-    Uses the CropBox (MediaBox if absent), which must match pdftoppm's
-    ``-cropbox`` or the computed DPI targets the wrong box.
-
-    Swaps width and height for 90/270 rotation. ``page.rotation`` resolves
-    inherited and negative ``/Rotate`` values, a raw lookup does not.
-
-    Parameters
-    ----------
-    path:
-        Absolute path to the PDF file.
-    log:
-        Logger for warnings.  Falls back to the module-level logger when omitted.
-
-    Returns
-    -------
-    tuple[float, float] | None
-        ``(width_points, height_points)``, or ``None`` if the file cannot be
-        opened, has no pages, or the page box is degenerate.
-    """
-    import pikepdf
-
-    _log = log or logger
-    try:
-        with pikepdf.Pdf.open(path) as pdf:
-            if len(pdf.pages) == 0:
-                return None
-            page = pdf.pages[0]
-            llx, lly, urx, ury = (float(v) for v in page.cropbox)
-            width = abs(urx - llx)
-            height = abs(ury - lly)
-            if width <= 0 or height <= 0:
-                return None
-            if page.rotation in (90, 270):
-                width, height = height, width
-            return width, height
-    except Exception as e:
-        _log.warning("Could not determine PDF page size for %s: %s", path, e)
-        return None
-
-
 def extract_pdf_metadata(
     document_path: Path,
     log: logging.Logger | None = None,

src/paperless/settings/__init__.py

@@ -986,6 +986,8 @@ GNUPG_HOME = os.getenv("HOME", "/tmp")
 
 # Convert is part of the ImageMagick package
 CONVERT_BINARY = os.getenv("PAPERLESS_CONVERT_BINARY", "convert")
+CONVERT_TMPDIR = os.getenv("PAPERLESS_CONVERT_TMPDIR")
+CONVERT_MEMORY_LIMIT = os.getenv("PAPERLESS_CONVERT_MEMORY_LIMIT")
 
 GS_BINARY = os.getenv("PAPERLESS_GS_BINARY", "gs")
 

src/paperless/tests/parsers/test_tesseract_parser.py

@@ -15,10 +15,9 @@ from typing import TYPE_CHECKING
 
 import pytest
 from ocrmypdf import SubprocessOutputError
-from PIL import Image
 
 from documents.parsers import ParseError
-from documents.parsers import rasterize_pdf_page_to_png
+from documents.parsers import run_convert
 from paperless.models import ModeChoices
 from paperless.parsers import ParserProtocol
 from paperless.parsers.tesseract import RasterisedDocumentParser
@@ -281,71 +280,24 @@ class TestGetThumbnail:
         )
         assert thumb.is_file()
 
-    @pytest.mark.parametrize(
-        ("filename", "expected_height"),
-        [
-            pytest.param("simple-digital.pdf", 647, id="portrait-letter"),
-            pytest.param("rotated.pdf", 386, id="landscape"),
-        ],
-    )
-    def test_thumbnail_is_correct_format_and_size(
-        self,
-        tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
-        filename: str,
-        expected_height: int,
-    ) -> None:
-        """
-        GIVEN:
-            - A portrait or landscape PDF
-        WHEN:
-            - A thumbnail is generated
-        THEN:
-            - A 500px wide WebP keeping the page's aspect ratio
-        """
-        thumb = tesseract_parser.get_thumbnail(
-            tesseract_samples_dir / filename,
-            "application/pdf",
-        )
-        with Image.open(thumb) as im:
-            assert im.format == "WEBP"
-            assert im.width == 500
-            assert im.height == pytest.approx(expected_height, abs=2)
-
-    def test_thumbnail_fallback_on_pdftoppm_error(
+    def test_thumbnail_fallback_on_convert_error(
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
         tesseract_samples_dir: Path,
     ) -> None:
-        """
-        GIVEN:
-            - Rasterizing the original PDF fails
-        WHEN:
-            - A thumbnail is generated
-        THEN:
-            - The PDF is repaired with qpdf and a real thumbnail is rendered
-        """
-        original = tesseract_samples_dir / "simple-digital.pdf"
-
-        def _fail_on_original(in_path: Path, out_path: Path, **kwargs) -> None:
-            if in_path == original:
+        def _raise_on_pdf(input_file, output_file, **kwargs) -> None:
+            if ".pdf" in str(input_file):
                 raise ParseError("Does not compute.")
-            rasterize_pdf_page_to_png(in_path, out_path, **kwargs)
+            run_convert(input_file=input_file, output_file=output_file, **kwargs)
 
-        rasterize = mocker.patch(
-            "documents.parsers.rasterize_pdf_page_to_png",
-            side_effect=_fail_on_original,
+        mocker.patch("documents.parsers.run_convert", side_effect=_raise_on_pdf)
+
+        thumb = tesseract_parser.get_thumbnail(
+            tesseract_samples_dir / "simple-digital.pdf",
+            "application/pdf",
         )
-
-        thumb = tesseract_parser.get_thumbnail(original, "application/pdf")
-
-        assert rasterize.call_count == 2
         assert thumb.is_file()
-        assert thumb.name == "convert_qpdf.webp"
-        with Image.open(thumb) as im:
-            assert im.format == "WEBP"
-            assert im.width == 500
 
     def test_thumbnail_encrypted_pdf(
         self,

src/paperless/tests/test_parser_utils.py

@@ -6,10 +6,8 @@ import codecs
 from pathlib import Path
 from typing import TYPE_CHECKING
 
-import pikepdf
 import pytest
 
-from paperless.parsers.utils import get_pdf_first_page_size_points
 from paperless.parsers.utils import is_tagged_pdf
 from paperless.parsers.utils import pdf_born_digital_text
 from paperless.parsers.utils import post_process_text
@@ -72,149 +70,6 @@ class TestIsTaggedPdf:
         assert is_tagged_pdf(bad) is False
 
 
-class TestGetPdfFirstPageSizePoints:
-    @staticmethod
-    def _write_pdf(
-        path: Path,
-        *,
-        media_box: tuple[float, float, float, float] = (0, 0, 600, 800),
-        crop_box: tuple[float, float, float, float] | None = None,
-        page_rotate: int | None = None,
-        inherited_rotate: int | None = None,
-    ) -> Path:
-        pdf = pikepdf.new()
-        pdf.add_blank_page(page_size=(media_box[2], media_box[3]))
-        page = pdf.pages[0]
-        page.obj.MediaBox = pikepdf.Array(media_box)
-        if crop_box is not None:
-            page.obj.CropBox = pikepdf.Array(crop_box)
-        if page_rotate is not None:
-            page.obj.Rotate = page_rotate
-        if inherited_rotate is not None:
-            pdf.Root.Pages.Rotate = inherited_rotate
-        pdf.save(path)
-        return path
-
-    def test_letter_sample(self) -> None:
-        """
-        GIVEN:
-            - A US Letter sample PDF with no CropBox and no rotation
-        WHEN:
-            - The first page size is requested
-        THEN:
-            - The MediaBox size in points is returned
-        """
-        assert get_pdf_first_page_size_points(SAMPLES / "simple-digital.pdf") == (
-            612.0,
-            792.0,
-        )
-
-    @pytest.mark.parametrize(
-        ("rotate", "expected"),
-        [
-            pytest.param(0, (600.0, 800.0), id="rotate-0"),
-            pytest.param(90, (800.0, 600.0), id="rotate-90"),
-            pytest.param(180, (600.0, 800.0), id="rotate-180"),
-            pytest.param(270, (800.0, 600.0), id="rotate-270"),
-            pytest.param(-90, (800.0, 600.0), id="rotate-negative-90"),
-        ],
-    )
-    def test_page_rotation_swaps_dimensions(
-        self,
-        tmp_path: Path,
-        rotate: int,
-        expected: tuple[float, float],
-    ) -> None:
-        """
-        GIVEN:
-            - A portrait PDF page with /Rotate set directly on the page
-        WHEN:
-            - The first page size is requested
-        THEN:
-            - Width and height are swapped for quarter-turn rotations only
-        """
-        pdf_path = self._write_pdf(tmp_path / "rotated.pdf", page_rotate=rotate)
-        assert get_pdf_first_page_size_points(pdf_path) == expected
-
-    def test_inherited_rotation_swaps_dimensions(self, tmp_path: Path) -> None:
-        """
-        GIVEN:
-            - A page inheriting /Rotate 90 from the /Pages node
-        WHEN:
-            - The first page size is requested
-        THEN:
-            - Width and height are swapped
-        """
-        pdf_path = self._write_pdf(tmp_path / "inherited.pdf", inherited_rotate=90)
-        assert get_pdf_first_page_size_points(pdf_path) == (800.0, 600.0)
-
-    def test_crop_box_preferred_over_media_box(self, tmp_path: Path) -> None:
-        """
-        GIVEN:
-            - A PDF page with a CropBox smaller than its MediaBox
-        WHEN:
-            - The first page size is requested
-        THEN:
-            - The CropBox size is returned
-        """
-        pdf_path = self._write_pdf(
-            tmp_path / "cropped.pdf",
-            crop_box=(50, 100, 350, 500),
-        )
-        assert get_pdf_first_page_size_points(pdf_path) == (300.0, 400.0)
-
-    def test_degenerate_box_returns_none(self, tmp_path: Path) -> None:
-        """
-        GIVEN:
-            - A PDF page whose box has zero width
-        WHEN:
-            - The first page size is requested
-        THEN:
-            - None is returned
-        """
-        pdf_path = self._write_pdf(
-            tmp_path / "degenerate.pdf",
-            media_box=(0, 0, 600, 800),
-            crop_box=(100, 0, 100, 800),
-        )
-        assert get_pdf_first_page_size_points(pdf_path) is None
-
-    def test_nonexistent_path_returns_none(self) -> None:
-        """
-        GIVEN:
-            - A path that does not exist
-        WHEN:
-            - The first page size is requested
-        THEN:
-            - None is returned and nothing is raised
-        """
-        assert get_pdf_first_page_size_points(Path("/nonexistent/file.pdf")) is None
-
-    def test_corrupt_pdf_returns_none(self, tmp_path: Path) -> None:
-        """
-        GIVEN:
-            - A file that is not a PDF
-        WHEN:
-            - The first page size is requested
-        THEN:
-            - None is returned and nothing is raised
-        """
-        bad = tmp_path / "bad.pdf"
-        bad.write_bytes(b"not a pdf")
-        assert get_pdf_first_page_size_points(bad) is None
-
-    def test_encrypted_pdf_returns_none(self) -> None:
-        """
-        GIVEN:
-            - A password protected PDF
-        WHEN:
-            - The first page size is requested
-        THEN:
-            - None is returned and nothing is raised
-        """
-        assert get_pdf_first_page_size_points(SAMPLES / "encrypted.pdf") is None
-
-
 class TestPostProcessText:
     @pytest.mark.parametrize(
         ("source", "expected"),