Fix filename test.txt

.docker/Dockerfile

@@ -51,7 +51,7 @@ RUN . /appenv/bin/activate; \
 # Do this now to make the best use of Docker cache.
 COPY . /application
 RUN . /appenv/bin/activate; \
-  pip install -r /application/test_requirements.txt
+  pip install -r /application/requirements/test.txt
 
 # Remove the junk, including the source version of application since it was
 # already installed

.travis.yml

@@ -91,9 +91,9 @@ before_install: |
 install:
 - export PATH=$PWD/bin:$PATH
 - pip3 install pycparser  # py3.7 workaround for https://github.com/eliben/pycparser/issues/251
-- pip3 install -r requirements.txt
+- pip3 install -r requirements/main.txt
 - pip3 install --no-deps .
-- pip3 install -r test_requirements.txt
+- pip3 install -r requirements/test.txt
 
 script:
 - tesseract --version

MANIFEST.in

@@ -1,7 +1,5 @@
 # requirements
-include requirements.txt
-include test_requirements.txt
-include dev_requirements.txt
+recursive-include requirements *
 
 # git
 include .git_archival.txt
@@ -12,21 +10,20 @@ recursive-include .docker *
 
 # tests
 include .coveragerc
+recursive-include tests *.bin
 recursive-include tests *.jpg
+recursive-include tests *.jsonl
 recursive-include tests *.png
 recursive-include tests *.pdf
 recursive-include tests *.py
 recursive-include tests *.rst
 recursive-include tests *.txt
-recursive-include tests/cache *
-recursive-exclude tests/output *
-recursive-exclude tests/output_pageinfo *
 recursive-exclude tests/resources/private *
 
 # documentation
 include LICENSE
 include *.rst
-recursive-exclude .github * 
+recursive-exclude .github *
 recursive-include docs *.py
 recursive-include docs *.rst
 recursive-include docs *.svg
@@ -42,8 +39,5 @@ exclude .travis*
 
 
 # code
-recursive-include src/ocrmypdf *.py
-exclude ocrmypdf/lib/_leptonica.py
-
-
-
+exclude src/ocrmypdf/lib/_leptonica.py
+exclude scratch.py

docs/installation.rst

@@ -536,6 +536,6 @@ To install all of the development and test requirements:
     source venv/bin/activate
     cd OCRmyPDF
     pip install -e .
-    pip install -r dev_requirements.txt -r test_requirements.txt
+    pip install -r requirements/dev.txt -r requirements/test.txt
 
 To add JBIG2 encoding, see :ref:`jbig2`.

docs/release_notes.rst

@@ -14,6 +14,14 @@ Note that it is licensed under GPLv3, so scripts that ``import ocrmypdf`` and ar
    replace: `#$1 <https://github.com/jbarlow83/OCRmyPDF/issues/$1>`_
 
 
+v7.2.1
+------
+
+-   Fix compatibility with an API change in pikepdf 0.3.5.
+
+-   A kludge to support Leptonica versions older than 1.72 in the test suite was dropped. Older versions of Leptonica are likely still compatible. The only impact is that a portion of the test suite will be skipped.
+
+
 v7.2.0
 ------
 

setup.py

@@ -201,11 +201,11 @@ if 'upload' in sys.argv[1:]:
     print('Use twine to upload the package - setup.py upload is insecure')
     sys.exit(1)
 
-tests_require = open('test_requirements.txt').read().splitlines()
+tests_require = open('requirements/test.txt', encoding='utf-8').read().splitlines()
 
 
 def readme():
-    with open('README.md') as f:
+    with open('README.md', encoding='utf-8') as f:
         return f.read()
 
 setup(

src/ocrmypdf/_pipeline.py

@@ -830,7 +830,13 @@ def metadata_fixup(
         pdfmark = get_pdfmark(metadata, options)
         pdf = pikepdf.open(layers_file)
         pdf.metadata = pdf.make_indirect(pikepdf.Dictionary(pdfmark))
-        pdf.save(output_file, stream_data_mode=pikepdf.StreamDataMode.compress)
+        try:
+            pdf.save(output_file, compress_streams=True,
+                     object_stream_mode=pikepdf.ObjectStreamMode.generate)
+        except AttributeError:
+            # pikepdf <= 0.3.4
+            pdf.save(output_file,
+                     stream_data_mode=pikepdf.StreamDataMode.compress)
 
 
 def optimize_pdf(

src/ocrmypdf/leptonica.py

@@ -464,30 +464,14 @@ class Pix:
             # implementation of pixCorrelationBinary that overflows on larger
             # images.  Ubuntu 14.04/trusty has 1.70. Ubuntu PPA
             # ppa:alex-p/tesseract-ocr has leptonlib 1.75.
-            pix1_count = ffi.new('l_int32 *')
-            pix2_count = ffi.new('l_int32 *')
-            pixn_count = ffi.new('l_int32 *')
-            tab8 = Pix.make_pixel_sum_tab8()
+            raise LeptonicaError("Leptonica version is too old")
 
-            lept.pixCountPixels(pix1._pix, pix1_count, tab8)
-            lept.pixCountPixels(pix2._pix, pix2_count, tab8)
-            pixn = Pix(lept.pixAnd(ffi.NULL, pix1._pix, pix2._pix))
-            lept.pixCountPixels(pixn._pix, pixn_count, tab8)
-
-            # Python converts these int32s to larger units as needed
-            # to avoid overflow. Overflow happens easily here.
-            correlation = (
-                    (pixn_count[0] * pixn_count[0]) /
-                    (pix1_count[0] * pix2_count[0])
-                    )
-            return correlation
-        else:
-            correlation = ffi.new('float *', 0.0)
-            result = lept.pixCorrelationBinary(pix1._pix, pix2._pix,
-                                               correlation)
-            if result != 0:
-                raise LeptonicaError("Correlation failed")
-            return correlation[0]
+        correlation = ffi.new('float *', 0.0)
+        result = lept.pixCorrelationBinary(pix1._pix, pix2._pix,
+                                           correlation)
+        if result != 0:
+            raise LeptonicaError("Correlation failed")
+        return correlation[0]
 
     def generate_pdf_ci_data(self, type_, quality):
         "Convert to PDF data, with transcoding"

tests/test_rotation.py

@@ -33,6 +33,11 @@ from ocrmypdf.helpers import fspath
 # pylint: disable=no-member
 # pylint: disable=w0612
 
+pytestmark = pytest.mark.skipif(
+    leptonica.get_leptonica_version() < 'leptonica-1.72',
+    reason="Leptonica is too old, correlation doesn't work"
+)
+
 check_ocrmypdf = pytest.helpers.check_ocrmypdf
 run_ocrmypdf = pytest.helpers.run_ocrmypdf