python3Packages.ocrmypdf_16: init at 16.13.0

pkgs/development/python-modules/ocrmypdf/paths.patch

@@ -1,8 +1,8 @@
 diff --git a/src/ocrmypdf/_exec/ghostscript.py b/src/ocrmypdf/_exec/ghostscript.py
-index b48f2080..beabcf4b 100644
+index eaa48117..30201d97 100644
 --- a/src/ocrmypdf/_exec/ghostscript.py
 +++ b/src/ocrmypdf/_exec/ghostscript.py
-@@ -35,7 +35,7 @@ COLOR_CONVERSION_STRATEGIES = frozenset(
+@@ -31,7 +31,7 @@ COLOR_CONVERSION_STRATEGIES = frozenset(
      ]
  )
  # Ghostscript executable - gswin32c is not supported
@@ -12,7 +12,7 @@ index b48f2080..beabcf4b 100644
  
  log = logging.getLogger(__name__)
 diff --git a/src/ocrmypdf/_exec/jbig2enc.py b/src/ocrmypdf/_exec/jbig2enc.py
-index 736de67e..d8c24ebd 100644
+index 1c6dd5fe..b689a091 100644
 --- a/src/ocrmypdf/_exec/jbig2enc.py
 +++ b/src/ocrmypdf/_exec/jbig2enc.py
 @@ -15,7 +15,7 @@ from ocrmypdf.subprocess import get_version, run
@@ -24,7 +24,16 @@ index 736de67e..d8c24ebd 100644
      except CalledProcessError as e:
          # TeX Live for Windows provides an incompatible jbig2.EXE which may
          # be on the PATH.
-@@ -32,7 +32,7 @@ def available():
+@@ -33,7 +33,7 @@ def available():
+ 
+ def convert_group(cwd, infiles, out_prefix, threshold):
+     args = [
+-        'jbig2',
++        '@jbig2@',
+         '-b',
+         out_prefix,
+         '--symbol-mode',  # symbol mode (lossy)
+@@ -50,7 +50,7 @@ def convert_group(cwd, infiles, out_prefix, threshold):
  
  
  def convert_single(cwd, infile, outfile, threshold):
@@ -56,10 +65,10 @@ index 5b8600d0..fcad771b 100644
              '--skip-if-larger',
              '--quality',
 diff --git a/src/ocrmypdf/_exec/tesseract.py b/src/ocrmypdf/_exec/tesseract.py
-index d41a0af7..b189b0de 100644
+index 102bdab8..bfef4400 100644
 --- a/src/ocrmypdf/_exec/tesseract.py
 +++ b/src/ocrmypdf/_exec/tesseract.py
-@@ -116,7 +116,7 @@ class TesseractVersion(Version):
+@@ -95,7 +95,7 @@ class TesseractVersion(Version):
  
  
  def version() -> Version:
@@ -68,7 +77,7 @@ index d41a0af7..b189b0de 100644
  
  
  def has_thresholding() -> bool:
-@@ -134,7 +134,7 @@ def get_languages() -> set[str]:
+@@ -113,7 +113,7 @@ def get_languages() -> set[str]:
          msg += output
          return msg
  
@@ -77,7 +86,7 @@ index d41a0af7..b189b0de 100644
      try:
          proc = run(
              args_tess,
-@@ -156,7 +156,7 @@ def get_languages() -> set[str]:
+@@ -135,7 +135,7 @@ def get_languages() -> set[str]:
  
  
  def tess_base_args(langs: list[str], engine_mode: int | None) -> list[str]:

pkgs/development/python-modules/ocrmypdf_16/default.nix

@@ -0,0 +1,113 @@
+{
+  lib,
+  buildPythonPackage,
+  deprecation,
+  fetchFromGitHub,
+  fpdf2,
+  ghostscript_headless,
+  hatch-vcs,
+  hatchling,
+  hypothesis,
+  img2pdf,
+  jbig2enc,
+  packaging,
+  pdfminer-six,
+  pillow-heif,
+  pikepdf,
+  pillow,
+  pluggy,
+  pngquant,
+  pydantic,
+  pypdfium2,
+  pytest-xdist,
+  pytestCheckHook,
+  rich,
+  reportlab,
+  replaceVars,
+  tesseract,
+  uharfbuzz,
+  unpaper,
+  installShellFiles,
+}:
+
+buildPythonPackage rec {
+  pname = "ocrmypdf";
+  version = "16.13.0";
+  pyproject = true;
+
+  src = fetchFromGitHub {
+    owner = "ocrmypdf";
+    repo = "OCRmyPDF";
+    tag = "v${version}";
+    # The content of .git_archival.txt is substituted upon tarball creation,
+    # which creates indeterminism if master no longer points to the tag.
+    # See https://github.com/ocrmypdf/OCRmyPDF/issues/841
+    postFetch = ''
+      rm "$out/.git_archival.txt"
+    '';
+    hash = "sha256-xxVtncIQ72echi0VogfgqwfB8IA7JEKVUV2lmL1coeU=";
+  };
+
+  patches = [
+    ./use-pillow-heif.patch
+    (replaceVars ./paths.patch {
+      gs = lib.getExe ghostscript_headless;
+      jbig2 = lib.getExe jbig2enc;
+      pngquant = lib.getExe pngquant;
+      tesseract = lib.getExe tesseract;
+      unpaper = lib.getExe unpaper;
+    })
+  ];
+
+  build-system = [
+    hatch-vcs
+    hatchling
+  ];
+
+  nativeBuildInputs = [ installShellFiles ];
+
+  dependencies = [
+    deprecation
+    fpdf2
+    img2pdf
+    packaging
+    pdfminer-six
+    pillow-heif
+    pikepdf
+    pillow
+    pluggy
+    pydantic
+    pypdfium2
+    rich
+    uharfbuzz
+  ];
+
+  nativeCheckInputs = [
+    hypothesis
+    pytest-xdist
+    pytestCheckHook
+    reportlab
+  ];
+
+  pythonImportsCheck = [ "ocrmypdf" ];
+
+  postInstall = ''
+    installShellCompletion --cmd ocrmypdf \
+      --bash misc/completion/ocrmypdf.bash \
+      --fish misc/completion/ocrmypdf.fish
+  '';
+
+  meta = {
+    homepage = "https://github.com/ocrmypdf/OCRmyPDF";
+    description = "Adds an OCR text layer to scanned PDF files, allowing them to be searched";
+    license = with lib.licenses; [
+      mpl20
+      mit
+    ];
+    maintainers = with lib.maintainers; [
+      dotlambda
+    ];
+    changelog = "https://github.com/ocrmypdf/OCRmyPDF/blob/${src.tag}/docs/release_notes.md";
+    mainProgram = "ocrmypdf";
+  };
+}

pkgs/development/python-modules/ocrmypdf_16/paths.patch

@@ -0,0 +1,119 @@
+diff --git a/src/ocrmypdf/_exec/ghostscript.py b/src/ocrmypdf/_exec/ghostscript.py
+index eaa48117..30201d97 100644
+--- a/src/ocrmypdf/_exec/ghostscript.py
++++ b/src/ocrmypdf/_exec/ghostscript.py
+@@ -31,7 +31,7 @@ COLOR_CONVERSION_STRATEGIES = frozenset(
+     ]
+ )
+ # Ghostscript executable - gswin32c is not supported
+-GS = 'gswin64c' if os.name == 'nt' else 'gs'
++GS = '@gs@'
+ 
+ 
+ log = logging.getLogger(__name__)
+diff --git a/src/ocrmypdf/_exec/jbig2enc.py b/src/ocrmypdf/_exec/jbig2enc.py
+index 1c6dd5fe..b689a091 100644
+--- a/src/ocrmypdf/_exec/jbig2enc.py
++++ b/src/ocrmypdf/_exec/jbig2enc.py
+@@ -15,7 +15,7 @@ from ocrmypdf.subprocess import get_version, run
+ 
+ def version() -> Version:
+     try:
+-        version = get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*')
++        version = get_version('@jbig2@', regex=r'jbig2enc (\d+(\.\d+)*).*')
+     except CalledProcessError as e:
+         # TeX Live for Windows provides an incompatible jbig2.EXE which may
+         # be on the PATH.
+@@ -33,7 +33,7 @@ def available():
+ 
+ def convert_group(cwd, infiles, out_prefix, threshold):
+     args = [
+-        'jbig2',
++        '@jbig2@',
+         '-b',
+         out_prefix,
+         '--symbol-mode',  # symbol mode (lossy)
+@@ -50,7 +50,7 @@ def convert_group(cwd, infiles, out_prefix, threshold):
+ 
+ 
+ def convert_single(cwd, infile, outfile, threshold):
+-    args = ['jbig2', '--pdf', '-t', str(threshold), infile]
++    args = ['@jbig2@', '--pdf', '-t', str(threshold), infile]
+     with open(outfile, 'wb') as fstdout:
+         proc = run(args, cwd=cwd, stdout=fstdout, stderr=PIPE)
+     proc.check_returncode()
+diff --git a/src/ocrmypdf/_exec/pngquant.py b/src/ocrmypdf/_exec/pngquant.py
+index 5b8600d0..fcad771b 100644
+--- a/src/ocrmypdf/_exec/pngquant.py
++++ b/src/ocrmypdf/_exec/pngquant.py
+@@ -15,7 +15,7 @@ from ocrmypdf.subprocess import get_version, run
+ 
+ 
+ def version() -> Version:
+-    return Version(get_version('pngquant', regex=r'(\d+(\.\d+)*).*'))
++    return Version(get_version('@pngquant@', regex=r'(\d+(\.\d+)*).*'))
+ 
+ 
+ def available():
+@@ -37,7 +37,7 @@ def quantize(input_file: Path, output_file: Path, quality_min: int, quality_max:
+     """
+     with open(input_file, 'rb') as input_stream:
+         args = [
+-            'pngquant',
++            '@pngquant@',
+             '--force',
+             '--skip-if-larger',
+             '--quality',
+diff --git a/src/ocrmypdf/_exec/tesseract.py b/src/ocrmypdf/_exec/tesseract.py
+index 102bdab8..bfef4400 100644
+--- a/src/ocrmypdf/_exec/tesseract.py
++++ b/src/ocrmypdf/_exec/tesseract.py
+@@ -95,7 +95,7 @@ class TesseractVersion(Version):
+ 
+ 
+ def version() -> Version:
+-    return TesseractVersion(get_version('tesseract', regex=r'tesseract\s(.+)'))
++    return TesseractVersion(get_version('@tesseract@', regex=r'tesseract\s(.+)'))
+ 
+ 
+ def has_thresholding() -> bool:
+@@ -113,7 +113,7 @@ def get_languages() -> set[str]:
+         msg += output
+         return msg
+ 
+-    args_tess = ['tesseract', '--list-langs']
++    args_tess = ['@tesseract@', '--list-langs']
+     try:
+         proc = run(
+             args_tess,
+@@ -135,7 +135,7 @@ def get_languages() -> set[str]:
+ 
+ 
+ def tess_base_args(langs: list[str], engine_mode: int | None) -> list[str]:
+-    args = ['tesseract']
++    args = ['@tesseract@']
+     if langs:
+         args.extend(['-l', '+'.join(langs)])
+     if engine_mode is not None:
+diff --git a/src/ocrmypdf/_exec/unpaper.py b/src/ocrmypdf/_exec/unpaper.py
+index a5a92f4c..6cf56eb3 100644
+--- a/src/ocrmypdf/_exec/unpaper.py
++++ b/src/ocrmypdf/_exec/unpaper.py
+@@ -48,7 +48,7 @@ class UnpaperImageTooLargeError(Exception):
+ 
+ 
+ def version() -> Version:
+-    return Version(get_version('unpaper', regex=r'(?m).*?(\d+(\.\d+)(\.\d+)?)'))
++    return Version(get_version('@unpaper@', regex=r'(?m).*?(\d+(\.\d+)(\.\d+)?)'))
+ 
+ 
+ @contextmanager
+@@ -70,7 +70,7 @@ def _setup_unpaper_io(input_file: Path) -> Iterator[tuple[Path, Path, Path]]:
+ def run_unpaper(
+     input_file: Path, output_file: Path, *, dpi: DecFloat, mode_args: list[str]
+ ) -> None:
+-    args_unpaper = ['unpaper', '-v', '--dpi', str(round(dpi, 6))] + mode_args
++    args_unpaper = ['@unpaper@', '-v', '--dpi', str(round(dpi, 6))] + mode_args
+ 
+     with _setup_unpaper_io(input_file) as (input_png, output_pnm, tmpdir):
+         # To prevent any shenanigans from accepting arbitrary parameters in

pkgs/development/python-modules/ocrmypdf_16/use-pillow-heif.patch

@@ -0,0 +1,26 @@
+diff --git a/pyproject.toml b/pyproject.toml
+index 2caa0e75..f6fcf60a 100644
+--- a/pyproject.toml
++++ b/pyproject.toml
+@@ -16,7 +16,7 @@ dependencies = [
+   "img2pdf>=0.5",
+   "packaging>=20",
+   "pdfminer.six>=20220319",
+-  "pi-heif",                # Heif image format - maintainers: if this is removed, it will NOT break
++  "pillow-heif",                # Heif image format - maintainers: if this is removed, it will NOT break
+   "pikepdf>=10",
+   "Pillow>=10.0.1",
+   "pluggy>=1",
+diff --git a/src/ocrmypdf/_pipeline.py b/src/ocrmypdf/_pipeline.py
+index 90524d58..0be5a0f8 100644
+--- a/src/ocrmypdf/_pipeline.py
++++ b/src/ocrmypdf/_pipeline.py
+@@ -42,7 +42,7 @@ from ocrmypdf.pdfinfo import Colorspace, Encoding, PageInfo, PdfInfo
+ from ocrmypdf.pluginspec import OrientationConfidence
+ 
+ try:
+-    from pi_heif import register_heif_opener
++    from pillow_heif import register_heif_opener
+ except ImportError:
+ 
+     def register_heif_opener():

pkgs/top-level/python-packages.nix

@@ -11206,6 +11206,10 @@ self: super: with self; {
 
   ocrmypdf = callPackage ../development/python-modules/ocrmypdf { tesseract = pkgs.tesseract5; };
 
+  ocrmypdf_16 = callPackage ../development/python-modules/ocrmypdf_16 {
+    tesseract = pkgs.tesseract5;
+  };
+
   od = callPackage ../development/python-modules/od { };
 
   odc-geo = callPackage ../development/python-modules/odc-geo { };