Fixed setup.py syntax error

Better get the last one out

.travis.yml

@@ -27,6 +27,10 @@ matrix:
       language: python
       python: 3.6
       env: EXTRAS=[fitz]
+    - os: osx
+      osx_image: xcode8
+      language: generic
+      env: EXTRAS=
     - os: osx
       osx_image: xcode8
       language: generic

docs/release_notes.rst

@@ -5,6 +5,20 @@ OCRmyPDF uses `semantic versioning <http://semver.org/>`_ for its command line i
 
 The OCRmyPDF package itself does not contain a public API, although it is fairly stable and breaking changes are usually timed with a major release. A future release will clearly define the stable public API.
 
+v6.1.2
+------
+
+-   Upgrade to PyMuPDF v1.12.5 which includes a more complete fix to #239.
+
+-   Add ``defusedxml`` dependency.
+
+
+v6.1.1
+------
+
+-   Fix text being reported as found on all pages if PyMuPDF is not installed.
+
+
 v6.1.0
 ------
 

setup.cfg

@@ -12,3 +12,6 @@ ignore =
 norecursedirs = lib .pc .git output cache resources
 testpaths = tests
 addopts = -n auto
+
+[metadata]
+license_file = LICENSE

setup.py

@@ -232,26 +232,27 @@ setup(
         "Topic :: Text Processing :: Indexing",
         "Topic :: Text Processing :: Linguistic",
         ],
-    python_requires='>=3.5',
+    python_requires=' >= 3.5',
     setup_requires=[
+        'cffi >= 1.9.1',        # to build the leptonica module
+        'pytest-runner',        # to enable python setup.py test
         'setuptools_scm',       # so that version will work
-        'cffi>=1.9.1',          # to build the leptonica module
-        'pytest-runner'         # to enable python setup.py test
     ],
     use_scm_version={'version_scheme': 'post-release'},
     cffi_modules=[
         'src/ocrmypdf/lib/compile_leptonica.py:ffibuilder'
     ],
     install_requires=[
-        'ruffus==2.6.3',        # pinned - ocrmypdf implements a 2.6.3 workaround
+        'cffi >= 1.9.1',          # must be a setup and install requirement
-        'Pillow>=4.0.0',        # Pillow < 4 has BytesIO/TIFF bug w/img2pdf 0.2.3
+        'defusedxml >= 0.5.0',    # pure Python, so track HEAD closely
-        'reportlab>=3.3.0',     # oldest released version with sane image handling
+        'img2pdf >= 0.2.4',       # pure Python, so track HEAD closely
-        'PyPDF2>=1.26',         # pure Python, so track HEAD closely
+        'Pillow >= 4.0.0',        # Pillow < 4 has BytesIO/TIFF bug w/img2pdf 0.2.3
-        'img2pdf>=0.2.3',       # pure Python, so track HEAD closely
+        'PyPDF2 >= 1.26',         # pure Python, so track HEAD closely
-        'cffi>=1.9.1',          # must be a setup and install requirement
+        'reportlab >= 3.3.0',     # oldest released version with sane image handling
+        'ruffus == 2.6.3',        # pinned - ocrmypdf implements a 2.6.3 workaround
     ],
     extras_require={
-        'fitz': ['PyMuPDF == 1.12.4']     # pinned to avoid problems with 1.12.4.x
+        'fitz': ['PyMuPDF >= 1.12.5']     # for table of contents bug
     },
     tests_require=tests_require,
     entry_points={

src/ocrmypdf/lib/__init__.py

@@ -17,7 +17,12 @@
 
 """Bindings to external libraries"""
 
+import os as _os
+
 try:
     import fitz
 except ImportError:
     fitz = None
+
+if _os.environ.get('_OCRMYPDF_NO_FITZ'):
+    fitz = None

src/ocrmypdf/pdfa.py

@@ -18,7 +18,7 @@
 # Generate a PDFA_def.ps file for Ghostscript >= 9.14
 
 from string import Template
-import codecs
+from binascii import hexlify
 import pkg_resources
 import PyPDF2 as pypdf
 
@@ -93,7 +93,7 @@ def encode_text_string(s: str) -> str:
         return ''
 
     utf16_bytes = s.encode('utf-16be')
-    ascii_hex_bytes = codecs.encode(b'\xfe\xff' + utf16_bytes, 'hex')
+    ascii_hex_bytes = hexlify(b'\xfe\xff' + utf16_bytes)
     ascii_hex_str = ascii_hex_bytes.decode('ascii').lower()
     return ascii_hex_str
 

src/ocrmypdf/pdfinfo.py

@@ -205,7 +205,7 @@ def _interpret_contents(contentstream, initial_shorthand=UNIT_SQUARE):
     return ContentsInfo(
         xobject_settings=xobject_settings,
         inline_images=inline_images,
-        found_text=True)
+        found_text=found_text)
 
 
 def _get_dpi(ctm_shorthand, image_size):

src/ocrmypdf/pipeline.py

@@ -1039,12 +1039,7 @@ def merge_pages_mupdf(
 
     metadata = fitz.open(metadata_file)
     toc = metadata.getToC(simple=False)
-    def filter_toc_pages():
+    doc.setToC(toc)
-        "fitz does not escape parens properly"
-        for entry in toc:
-            entry[1] = entry[1].replace('(', '').replace(')', '')
-            yield entry
-    doc.setToC([item for item in filter_toc_pages()])
     doc.setMetadata(pymupdf_metadata)
     doc.save(output_file, garbage=4, deflate=True)