Merge pull request #257856 from dotlambda/ocrmypdf-15.0.1

, stdenv

, fetchFromGitHub

, fetchpatch

, python3

, leptonica

, zlib

, libwebp

  };

  nativeBuildInputs = [ autoreconfHook ];

  propagatedBuildInputs = [

    leptonica

    zlib

    })

  ];

  # We don't want to install this Python 2 script

  postInstall = ''

    rm "$out/bin/pdf.py"

  '';

  # This is necessary, because the resulting library has

  # /tmp/nix-build-jbig2enc/src/.libs before /nix/store/jbig2enc/lib

  # in its rpath, which means that patchelf --shrink-rpath removes

    license = lib.licenses.asl20;

    platforms = lib.platforms.all;

    homepage = "https://github.com/agl/jbig2enc";

    mainProgram = "jbig2";

  };

}

, tqdm

, typing-extensions

, unpaper

, wheel

, installShellFiles

}:

buildPythonPackage rec {

  pname = "ocrmypdf";

  version = "14.4.0";

  version = "15.0.1";

  disabled = pythonOlder "3.8";

  disabled = pythonOlder "3.9";

  format = "pyproject";

    postFetch = ''

      rm "$out/.git_archival.txt"

    '';

    hash = "sha256-i1ZUBKR8dJXZkALUFwkzYcjtZ5Li66DfD2fupCGRQC4=";

    hash = "sha256-WTUe4ivSEU/4KMRtKhf1MDXN1segIe/wrXYVA5zJrZw=";

  };

  SETUPTOOLS_SCM_PRETEND_VERSION = version;

  patches = [

    (substituteAll {

      src = ./paths.patch;

      gs = "${lib.getBin ghostscript}/bin/gs";

      jbig2 = "${lib.getBin jbig2enc}/bin/jbig2";

      pngquant = "${lib.getBin pngquant}/bin/pngquant";

      tesseract = "${lib.getBin tesseract}/bin/tesseract";

      unpaper = "${lib.getBin unpaper}/bin/unpaper";

      gs = lib.getExe ghostscript;

      jbig2 = lib.getExe jbig2enc;

      pngquant = lib.getExe pngquant;

      tesseract = lib.getExe tesseract;

      unpaper = lib.getExe unpaper;

    })

  ];

  nativeBuildInputs = [

    setuptools

    setuptools-scm

    wheel

    installShellFiles

  ];

    pluggy

    reportlab

    rich

    tqdm

  ] ++ lib.optionals (pythonOlder "3.9") [

    importlib-resources

  ] ++ lib.optionals (pythonOlder "3.10") [

    typing-extensions

  ];

diff --git a/src/ocrmypdf/_exec/ghostscript.py b/src/ocrmypdf/_exec/ghostscript.py

index 9e21c33c..21f134b3 100644

index e28d23e9..183cd918 100644

--- a/src/ocrmypdf/_exec/ghostscript.py

+++ b/src/ocrmypdf/_exec/ghostscript.py

@@ -32,15 +32,7 @@ log = logging.getLogger(__name__)

 # Most reliable what to get the bitness of Python interpreter, according to Python docs

 _IS_64BIT = sys.maxsize > 2**32

-_GSWIN = None

-if os.name == 'nt':

-    if _IS_64BIT:

-        _GSWIN = 'gswin64c'

-    else:

-        _GSWIN = 'gswin32c'

-

-GS = _GSWIN if _GSWIN else 'gs'

-del _GSWIN

@@ -67,7 +67,7 @@ log.addFilter(DuplicateFilter(log))

 # Ghostscript executable - gswin32c is not supported

-GS = 'gswin64c' if os.name == 'nt' else 'gs'

+GS = '@gs@'

 def version():

 def version() -> Version:

diff --git a/src/ocrmypdf/_exec/jbig2enc.py b/src/ocrmypdf/_exec/jbig2enc.py

index 0f8f7392..db792b10 100644

index 28d3dd1c..477a7d6c 100644

--- a/src/ocrmypdf/_exec/jbig2enc.py

+++ b/src/ocrmypdf/_exec/jbig2enc.py

@@ -12,7 +12,7 @@ from ocrmypdf.subprocess import get_version, run

@@ -14,7 +14,7 @@ from ocrmypdf.subprocess import get_version, run

 def version():

-    return get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*')

+    return get_version('@jbig2@', regex=r'jbig2enc (\d+(\.\d+)*).*')

 def version() -> Version:

-    return Version(get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*'))

+    return Version(get_version('@jbig2@', regex=r'jbig2enc (\d+(\.\d+)*).*'))

 def available():

@@ -25,7 +25,7 @@ def available():

@@ -27,7 +27,7 @@ def available():

 def convert_group(*, cwd, infiles, out_prefix):

 def convert_group(*, cwd, infiles, out_prefix, threshold):

     args = [

-        'jbig2',

+        '@jbig2@',

         '-b',

         out_prefix,

         '-s',  # symbol mode (lossy)

@@ -44,7 +44,7 @@ def convert_group_mp(args):

         '--symbol-mode',  # symbol mode (lossy)

@@ -50,7 +50,7 @@ def convert_group_mp(args):

 def convert_single(*, cwd, infile, outfile):

-    args = ['jbig2', '-p', infile]

+    args = ['@jbig2@', '-p', infile]

 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 64e91139..ab5b9c49 100644

index 8425caec..a027f041 100644

--- a/src/ocrmypdf/_exec/pngquant.py

+++ b/src/ocrmypdf/_exec/pngquant.py

@@ -17,7 +17,7 @@ from ocrmypdf.subprocess import get_version, run

@@ -18,7 +18,7 @@ from ocrmypdf.subprocess import get_version, run

 def version():

-    return get_version('pngquant', regex=r'(\d+(\.\d+)*).*')

+    return get_version('@pngquant@', regex=r'(\d+(\.\d+)*).*')

 def version() -> Version:

-    return Version(get_version('pngquant', regex=r'(\d+(\.\d+)*).*'))

+    return Version(get_version('@pngquant@', regex=r'(\d+(\.\d+)*).*'))

 def available():

@@ -44,7 +44,7 @@ def input_as_png(input_file: Path):

@@ -45,7 +45,7 @@ def input_as_png(input_file: Path):

 def quantize(input_file: Path, output_file: Path, quality_min: int, quality_max: int):

     with input_as_png(input_file) as input_stream:

         args = [

             '--skip-if-larger',

             '--quality',

diff --git a/src/ocrmypdf/_exec/tesseract.py b/src/ocrmypdf/_exec/tesseract.py

index ad98836a..a12d3002 100644

index 4eac3470..61315d14 100644

--- a/src/ocrmypdf/_exec/tesseract.py

+++ b/src/ocrmypdf/_exec/tesseract.py

@@ -111,7 +111,7 @@ class TesseractVersion(Version):

@@ -114,7 +114,7 @@ class TesseractVersion(Version):

 def version() -> str:

-    return get_version('tesseract', regex=r'tesseract\s(.+)')

+    return get_version('@tesseract@', regex=r'tesseract\s(.+)')

 def version() -> Version:

-    return TesseractVersion(get_version('tesseract', regex=r'tesseract\s(.+)'))

+    return TesseractVersion(get_version('@tesseract@', regex=r'tesseract\s(.+)'))

 def has_user_words() -> bool:

@@ -138,7 +138,7 @@ def get_languages() -> set[str]:

 def has_thresholding() -> bool:

@@ -132,7 +132,7 @@ def get_languages() -> set[str]:

         msg += output

         return msg

     try:

         proc = run(

             args_tess,

@@ -160,7 +160,7 @@ def get_languages() -> set[str]:

@@ -154,7 +154,7 @@ def get_languages() -> set[str]:

 def tess_base_args(langs: list[str], engine_mode: int | None) -> list[str]:

         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 d7f24265..d14f85de 100644

index 2944b4f4..55a36140 100644

--- a/src/ocrmypdf/_exec/unpaper.py

+++ b/src/ocrmypdf/_exec/unpaper.py

@@ -66,7 +66,7 @@ class UnpaperImageTooLargeError(Exception):

@@ -69,7 +69,7 @@ class UnpaperImageTooLargeError(Exception):

 def version() -> str:

-    return get_version('unpaper')

+    return get_version('@unpaper@')

 def version() -> Version:

-    return Version(get_version('unpaper'))

+    return Version(get_version('@unpaper@'))

 SUPPORTED_MODES = {'1', 'L', 'RGB'}

@@ -120,7 +120,7 @@ def _setup_unpaper_io(input_file: Path) -> Iterator[tuple[Path, Path, Path]]:

@@ -123,7 +123,7 @@ 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:

    changelog = "https://github.com/kornelski/pngquant/raw/${version}/CHANGELOG";

    platforms = platforms.unix;

    license = with licenses; [ gpl3Plus hpnd bsd2 ];

    mainProgram = "pngquant";

    maintainers = [ maintainers.srapenne ];

  };

}

    description = "Post-processing tool for scanned sheets of paper";

    license = licenses.gpl2;

    platforms = platforms.all;

    mainProgram = "unpaper";

    maintainers = [ maintainers.rycee ];

  };

}