nixpkgs/pkgs/development/python-modules/pyocr/default.nix

70 lines
2.1 KiB
Nix
Raw Normal View History

{ lib, fetchFromGitHub, buildPythonPackage, pillow, six
, tesseract, cuneiform
}:
buildPythonPackage rec {
name = "pyocr-${version}";
python/pyocr: 0.4.6 -> 0.4.7 Upstream changes: * Tesseract 4.00.00alpha: * Version parsing: Ignore suffix (so '4.00.00alpha' == (4, 0, 0)) * Libtesseract: Load libtesseract.so.4 instead of libtesseract.so.3 if available * Support for Tesseract 3.05.00: * Builders: Split field 'tess_conf' into 'tess_flags' and 'tess_conf' * Libtesseract: If available, use TessBaseAPIDetectOrientationScript() instead of TessBaseAPIDetectOS * Libtesseract: * Workaround: Prevents possible segfault in image_to_string() when the target language is not available Full upstream change log can be found at: https://github.com/openpaperwork/pyocr/blob/b006123d1d002711b9/ChangeLog The tesseract.patch for supporting Tesseract version 3.05.00 has been applied upstream and we can safely drop it. We now use substituteInPlace in conjunction with a patch to insert the relevant store paths instead of sed, so it's less fragile whenever we have upstream changes in handling of these paths. I've tested this by reverting 48a941e29faa95e897f and applying a build fix patch of Cuneiform 1.1.0 from Arch Linux, because right now Cuneiform is an experimental version that can't be fixed on behalf of pyocr (the reason is that pyocr needs to get a list of languages, which doesn't work in that version anymore). In addition to that I've successfully built paperwork-backend which by now is the one package which depends on pyocr. However, I didn't do runtime tests of Paperwork. Signed-off-by: aszlig <aszlig@redmoonstudios.org> Cc: @7c6f434c
2017-09-02 05:18:38 +02:00
version = "0.4.7";
# Don't fetch from PYPI because it doesn't contain tests.
src = fetchFromGitHub {
owner = "jflesch";
repo = "pyocr";
rev = version;
python/pyocr: 0.4.6 -> 0.4.7 Upstream changes: * Tesseract 4.00.00alpha: * Version parsing: Ignore suffix (so '4.00.00alpha' == (4, 0, 0)) * Libtesseract: Load libtesseract.so.4 instead of libtesseract.so.3 if available * Support for Tesseract 3.05.00: * Builders: Split field 'tess_conf' into 'tess_flags' and 'tess_conf' * Libtesseract: If available, use TessBaseAPIDetectOrientationScript() instead of TessBaseAPIDetectOS * Libtesseract: * Workaround: Prevents possible segfault in image_to_string() when the target language is not available Full upstream change log can be found at: https://github.com/openpaperwork/pyocr/blob/b006123d1d002711b9/ChangeLog The tesseract.patch for supporting Tesseract version 3.05.00 has been applied upstream and we can safely drop it. We now use substituteInPlace in conjunction with a patch to insert the relevant store paths instead of sed, so it's less fragile whenever we have upstream changes in handling of these paths. I've tested this by reverting 48a941e29faa95e897f and applying a build fix patch of Cuneiform 1.1.0 from Arch Linux, because right now Cuneiform is an experimental version that can't be fixed on behalf of pyocr (the reason is that pyocr needs to get a list of languages, which doesn't work in that version anymore). In addition to that I've successfully built paperwork-backend which by now is the one package which depends on pyocr. However, I didn't do runtime tests of Paperwork. Signed-off-by: aszlig <aszlig@redmoonstudios.org> Cc: @7c6f434c
2017-09-02 05:18:38 +02:00
sha256 = "1iw73r8yrgjf8g00yzpz62ymqbf89cqhyhl9g430srmsrq7mn2yd";
};
python/pyocr: 0.4.6 -> 0.4.7 Upstream changes: * Tesseract 4.00.00alpha: * Version parsing: Ignore suffix (so '4.00.00alpha' == (4, 0, 0)) * Libtesseract: Load libtesseract.so.4 instead of libtesseract.so.3 if available * Support for Tesseract 3.05.00: * Builders: Split field 'tess_conf' into 'tess_flags' and 'tess_conf' * Libtesseract: If available, use TessBaseAPIDetectOrientationScript() instead of TessBaseAPIDetectOS * Libtesseract: * Workaround: Prevents possible segfault in image_to_string() when the target language is not available Full upstream change log can be found at: https://github.com/openpaperwork/pyocr/blob/b006123d1d002711b9/ChangeLog The tesseract.patch for supporting Tesseract version 3.05.00 has been applied upstream and we can safely drop it. We now use substituteInPlace in conjunction with a patch to insert the relevant store paths instead of sed, so it's less fragile whenever we have upstream changes in handling of these paths. I've tested this by reverting 48a941e29faa95e897f and applying a build fix patch of Cuneiform 1.1.0 from Arch Linux, because right now Cuneiform is an experimental version that can't be fixed on behalf of pyocr (the reason is that pyocr needs to get a list of languages, which doesn't work in that version anymore). In addition to that I've successfully built paperwork-backend which by now is the one package which depends on pyocr. However, I didn't do runtime tests of Paperwork. Signed-off-by: aszlig <aszlig@redmoonstudios.org> Cc: @7c6f434c
2017-09-02 05:18:38 +02:00
NIX_CUNEIFORM_CMD = "${cuneiform}/bin/cuneiform";
NIX_CUNEIFORM_DATA = "${cuneiform}/share/cuneiform";
NIX_LIBTESSERACT_PATH = "${tesseract}/lib/libtesseract.so";
NIX_TESSDATA_PREFIX = "${tesseract}/share/tessdata";
NIX_TESSERACT_CMD = "${tesseract}/bin/tesseract";
patches = [ ./paths.patch ];
postPatch = ''
python/pyocr: 0.4.6 -> 0.4.7 Upstream changes: * Tesseract 4.00.00alpha: * Version parsing: Ignore suffix (so '4.00.00alpha' == (4, 0, 0)) * Libtesseract: Load libtesseract.so.4 instead of libtesseract.so.3 if available * Support for Tesseract 3.05.00: * Builders: Split field 'tess_conf' into 'tess_flags' and 'tess_conf' * Libtesseract: If available, use TessBaseAPIDetectOrientationScript() instead of TessBaseAPIDetectOS * Libtesseract: * Workaround: Prevents possible segfault in image_to_string() when the target language is not available Full upstream change log can be found at: https://github.com/openpaperwork/pyocr/blob/b006123d1d002711b9/ChangeLog The tesseract.patch for supporting Tesseract version 3.05.00 has been applied upstream and we can safely drop it. We now use substituteInPlace in conjunction with a patch to insert the relevant store paths instead of sed, so it's less fragile whenever we have upstream changes in handling of these paths. I've tested this by reverting 48a941e29faa95e897f and applying a build fix patch of Cuneiform 1.1.0 from Arch Linux, because right now Cuneiform is an experimental version that can't be fixed on behalf of pyocr (the reason is that pyocr needs to get a list of languages, which doesn't work in that version anymore). In addition to that I've successfully built paperwork-backend which by now is the one package which depends on pyocr. However, I didn't do runtime tests of Paperwork. Signed-off-by: aszlig <aszlig@redmoonstudios.org> Cc: @7c6f434c
2017-09-02 05:18:38 +02:00
substituteInPlace src/pyocr/cuneiform.py \
--subst-var NIX_CUNEIFORM_CMD \
--subst-var NIX_CUNEIFORM_CMD
substituteInPlace src/pyocr/tesseract.py \
--subst-var NIX_TESSERACT_CMD
substituteInPlace src/pyocr/libtesseract/tesseract_raw.py \
--subst-var NIX_TESSDATA_PREFIX \
--subst-var NIX_LIBTESSERACT_PATH
# Disable specific tests that are probably failing because of this issue:
# https://github.com/jflesch/pyocr/issues/52
for test in $disabledTests; do
file="''${test%%:*}"
fun="''${test#*:}"
echo "$fun = unittest.skip($fun)" >> "tests/tests_$file.py"
done
'';
disabledTests = [
"cuneiform:TestTxt.test_basic"
"cuneiform:TestTxt.test_european"
"cuneiform:TestTxt.test_french"
"cuneiform:TestWordBox.test_basic"
"cuneiform:TestWordBox.test_european"
"cuneiform:TestWordBox.test_french"
"libtesseract:TestBasicDoc.test_basic"
"libtesseract:TestDigitLineBox.test_digits"
"libtesseract:TestLineBox.test_japanese"
"libtesseract:TestTxt.test_japanese"
"libtesseract:TestWordBox.test_japanese"
"tesseract:TestDigitLineBox.test_digits"
"tesseract:TestTxt.test_japanese"
];
propagatedBuildInputs = [ pillow six ];
meta = {
homepage = "https://github.com/jflesch/pyocr";
description = "A Python wrapper for Tesseract and Cuneiform";
license = lib.licenses.gpl3Plus;
};
}