v4.0.3 release notes

Dockerfile

@@ -23,12 +23,8 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 
 RUN apt-get install -y --no-install-recommends \
   unpaper \
-  libopenjpeg-dev \
-  ghostscript \
   qpdf \
-  poppler-utils
-
-RUN apt-get install -y --no-install-recommends \
+  poppler-utils \
   tesseract-ocr \
   tesseract-ocr-deu tesseract-ocr-spa tesseract-ocr-eng tesseract-ocr-fra
 
@@ -37,6 +33,14 @@ RUN apt-get install -qy --no-install-recommends \
   libpython3-dev \
   gcc
 
+# Install Ghostscript from Debian sid to work around JPEG 2000 issue in
+# Debian stretch libgs9 or gs 9.16~dfsg-2.1
+
+COPY ./share/etc-apt-sources.list /etc/apt/sources.list
+
+RUN apt-get update && apt-get install -y ghostscript/sid
+
+
 # Enforce UTF-8
 # Borrowed from https://index.docker.io/u/crosbymichael/python/ 
 RUN dpkg-reconfigure locales && \
@@ -80,7 +84,6 @@ USER docker
 WORKDIR /home/docker
 
 ENV OCRMYPDF_TEST_OUTPUT=/tmp/test-output
-ENV OCRMYPDF_IN_DOCKER=1
 ENV OCRMYPDF_SHARP_TTF=1
 
 # Must use array form of ENTRYPOINT

RELEASE_NOTES.rst

@@ -6,6 +6,24 @@ Please always read this file before installing the package
 Download software here: https://github.com/jbarlow83/OCRmyPDF/tags
 
 
+v4.0.3:
+=======
+
+New features
+------------
+
+-  Page orientations detected are now reported in a summary comment
+
+
+Fixes
+-----
+
+-  Show stack trace if unexpect errors occur
+-  Treat "too few characters" error message from Tesseract as a reason to skip that page rather than
+   abort the file
+-  Docker: fix blank JPEG2000 issue by insisting on Ghostscript versions that have this fixed
+
+
 v4.0.2:
 =======
 

ocrmypdf/main.py

@@ -550,6 +550,12 @@ def orient_page(
         with open(output_file, 'wb') as out:
             writer.write(out)
 
+        with pdfinfo_lock:
+            pageno = int(os.path.basename(page_pdf)[0:6]) - 1
+            pageinfo = pdfinfo[pageno].copy()
+            pageinfo['rotated'] = orient_conf.angle
+            pdfinfo[pageno] = pageinfo
+
 
 @transform(
     input=orient_page,
@@ -1045,6 +1051,8 @@ def run_pipeline():
                 msg = "Error occurred while running this command:"
                 _log.error(msg + '\n' + exc_value)
                 return ExitCode.child_process_error
+            elif not options.verbose:
+                _log.error(e)
 
         return ExitCode.other_error
     except Exception as e:
@@ -1055,6 +1063,20 @@ def run_pipeline():
         _log.warning('Output file: The generated PDF/A file is INVALID')
         return ExitCode.invalid_output_pdfa
 
+    with _pdfinfo_lock:
+        _log.debug(_pdfinfo)
+        direction = {0: 'n', 90: 'e',
+                     180: 's', 270: 'w'}
+        orientations = []
+        for n, page in enumerate(_pdfinfo):
+            angle = _pdfinfo[n].get('rotated', 0)
+            if angle != 0:
+                orientations.append('{0}{1}'.format(
+                    n + 1,
+                    direction.get(angle, '')))
+        if orientations:
+            _log.info('Page orientations detected: ' + ' '.join(orientations))
+
     return ExitCode.ok
 
 

ocrmypdf/tesseract.py

@@ -98,7 +98,8 @@ def get_orientation(input_file, language: list, timeout: float, log):
         return OrientationConfidence(angle=0, confidence=0.0)
     except CalledProcessError as e:
         tesseract_log_output(log, e.output, input_file)
-        if 'Image too large' in e.output:
+        if ('Too few characters. Skipping this page' in e.output or
+                'Image too large' in e.output):
             return OrientationConfidence(0, 0)
         raise e from e
     else:

share/etc-apt-sources.list

@@ -0,0 +1,4 @@
+deb http://httpredir.debian.org/debian stretch main
+deb http://httpredir.debian.org/debian stretch-updates main
+deb http://security.debian.org stretch/updates main
+deb http://ftp.de.debian.org/debian sid main contrib non-free

tests/test_main.py

@@ -28,6 +28,11 @@ TEST_OUTPUT = os.environ.get(
     default=os.path.join(PROJECT_ROOT, 'tests', 'output', 'main'))
 
 
+def running_in_docker():
+    # Docker creates a file named /.dockerinit
+    return os.path.exists('/.dockerinit')
+
+
 def setup_module():
     with suppress(FileNotFoundError):
         shutil.rmtree(TEST_OUTPUT)
@@ -105,6 +110,8 @@ def spoof_tesseract_noop():
 
 @pytest.fixture
 def spoof_tesseract_cache():
+    if running_in_docker():
+        return os.environ.copy()
     return spoof('tesseract', "tesseract_cache.py")
 
 
@@ -408,6 +415,8 @@ def test_missing_docinfo(spoof_tesseract_noop):
     assert p.returncode == ExitCode.ok, err
 
 
+@pytest.mark.skipif(running_in_docker(),
+                    reason="writes to tests/resources")
 def test_uppercase_extension(spoof_tesseract_noop):
     shutil.copy(_infile("skew.pdf"), _infile("UPPERCASE.PDF"))
     try: