menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Bug fix: exception thrown if input PDF was missing DocumentInfo block

Browse Source
This commit is contained in:
James R. Barlow
2015-08-24 01:23:30 -07:00
parent d07db8547f
commit b376672dbc
4 changed files with 36 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ocrmypdf/main.py
+4 -2
View File
@@ -729,11 +729,13 @@ def generate_postscript_stub(
pdf = pypdf.PdfFileReader(input_file)
def from_document_info(key):
# pdf.documentInfo.get() DOES NOT work as expected
# pdf.documentInfo.get() DOES NOT behave as expected for a dict-like
# object, so call with precautions. TypeError may occur if the PDF
# is missing the optional document info section.
try:
s = pdf.documentInfo[key]
return str(s)
except KeyError:
except (KeyError, TypeError):
return ''
pdfmark = {
tests/resources/NOTE.rst
+25 -23
View File
@@ -4,29 +4,31 @@ copyright reasons.
Test files do not necessarily produce perfect (or even good) OCR
results.
+-------------------+--------------------------------------------------------------------------------+
| File | Source |
+===================+================================================================================+
| graph.pdf | Wikimedia |
+-------------------+--------------------------------------------------------------------------------+
| c02-22.pdf | Project Gutenberg: https://www.gutenberg.org/files/76/76-h/images/c02-22.jpg |
+-------------------+--------------------------------------------------------------------------------+
| LinnSequencer.jpg | Wikimedia_ |
+-------------------+--------------------------------------------------------------------------------+
| congress.jpg | http://www.baxleystamps.com/litho/meiji/courts_1871.jpg |
+-------------------+--------------------------------------------------------------------------------+
| blank.pdf | Blank page from Adobe Illustrator CC 2015 |
+-------------------+--------------------------------------------------------------------------------+
| enormous.pdf | PNG file saved to PDF using img2pdf |
+-------------------+--------------------------------------------------------------------------------+
| invalid.pdf | PDF file header followed by EOF marker; not valid |
+-------------------+--------------------------------------------------------------------------------+
| multipage.pdf | several other files concatenated |
+-------------------+--------------------------------------------------------------------------------+
| skew.pdf | skewed version of c02-22.PDF |
+-------------------+--------------------------------------------------------------------------------+
| Test_Issue_28.pdf | file with some syntax errors |
+-------------------+--------------------------------------------------------------------------------+
+---------------------+--------------------------------------------------------------------------------+
| File | Source |
+=====================+================================================================================+
| graph.pdf | Wikimedia |
+---------------------+--------------------------------------------------------------------------------+
| c02-22.pdf | Project Gutenberg: https://www.gutenberg.org/files/76/76-h/images/c02-22.jpg |
+---------------------+--------------------------------------------------------------------------------+
| LinnSequencer.jpg | Wikimedia_ |
+---------------------+--------------------------------------------------------------------------------+
| congress.jpg | http://www.baxleystamps.com/litho/meiji/courts_1871.jpg |
+---------------------+--------------------------------------------------------------------------------+
| blank.pdf | Blank page from Adobe Illustrator CC 2015 |
+---------------------+--------------------------------------------------------------------------------+
| enormous.pdf | PNG file saved to PDF using img2pdf |
+---------------------+--------------------------------------------------------------------------------+
| invalid.pdf | PDF file header followed by EOF marker; not valid |
+---------------------+--------------------------------------------------------------------------------+
| multipage.pdf | several other files concatenated |
+---------------------+--------------------------------------------------------------------------------+
| skew.pdf | skewed version of c02-22.PDF |
+---------------------+--------------------------------------------------------------------------------+
| Test_Issue_28.pdf | file with some syntax errors |
+---------------------+--------------------------------------------------------------------------------+
| missing_docinfo.pdf | file missing its DocumentInfo dictionary |
+---------------------+--------------------------------------------------------------------------------+
.. _Wikimedia: https://upload.wikimedia.org/wikipedia/en/b/b7/LinnSequencer_hardware_MIDI_sequencer_brochure_page_2_300dpi.jpg
tests/resources/missing_docinfo.pdf
BIN
View File
Binary file not shown.
tests/test_main.py
+7
View File
@@ -308,3 +308,10 @@ def test_klingon():
p, out, err = run_ocrmypdf_env(
'francais.pdf', 'francais.pdf', '-l', 'klz')
assert p.returncode == ExitCode.bad_args
def test_missing_docinfo():
p, out, err = run_ocrmypdf_env(
'missing_docinfo.pdf', 'missing_docinfo.pdf', '-l', 'eng')
assert p.returncode == ExitCode.ok, err