Skip to content

When identifying original pdf file, skip the first output lines that … #44

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
BrentNoorda wants to merge 2 commits into
base: master
Choose a base branch
from
Open

When identifying original pdf file, skip the first output lines that … #44

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b6aeb0e
When identifying original pdf file, skip the first output lines that …
BrentNoorda May 13, 2016
1e69d5c
width is being used in place of height (although this function actual…
BrentNoorda May 13, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 12 additions & 5 deletions pypdfocr/pypdfocr_gs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -124,7 +124,7 @@ def _get_dpi(self, pdf_filename):
try:
out = subprocess.check_output(cmd, shell=True)
except subprocess.CalledProcessError as e:
self._warn ("Could not execute pdfimages to calculate DPI (try installing xpdf or poppler?), so defaulting to %sdpi" % self.output_dpi)
self._warn ("Could not execute pdfimages to calculate DPI (try installing xpdf or poppler?), so defaulting to %sdpi" % self.output_dpi)
return

# Need the second line of output
Expand All @@ -137,7 +137,7 @@ def _get_dpi(self, pdf_filename):
logging.debug(results)
results = results.split()
if(results[2] != 'image'):
self._warn("Could not understand output of pdfimages, please rerun with -d option and file an issue at http://github.com/virantha/pypdfocr/issues")
self._warn("Could not understand output of pdfimages, please rerun with -d option and file an issue at http://github.com/virantha/pypdfocr/issues")
return
x_pt, y_pt, greyscale = int(results[3]), int(results[4]), results[5]=='gray'
self.greyscale = greyscale
Expand All @@ -146,7 +146,13 @@ def _get_dpi(self, pdf_filename):
cmd = 'identify -format "%%w %%x %%h %%y\n" "%s"' % pdf_filename
try:
out = subprocess.check_output(cmd, shell=True)
results = out.splitlines()[0]

# skip any lines starting with "*** Warning"
out_splitlines = out.splitlines()
while "* Warning:" in out_splitlines[0]:
out_splitlines = out_splitlines[1:]
results = out_splitlines[0]

results = results.replace("Undefined", "")
width, xdensity, height, ydensity = [float(x) for x in results.split()]
xdpi = round(x_pt/width*xdensity)
Expand All @@ -161,16 +167,17 @@ def _get_dpi(self, pdf_filename):


except Exception as e:
logging.debug(cmd)
logging.debug(str(e))
self._warn ("Could not execute identify to calculate DPI (try installing imagemagick?), so defaulting to %sdpi" % self.output_dpi)
self._warn ("Could not execute identify to calculate DPI (try installing imagemagick?), so defaulting to %sdpi" % self.output_dpi)
return



def _run_gs(self, options, output_filename, pdf_filename):
try:
cmd = '%s -q -dNOPAUSE %s -sOutputFile="%s" "%s" -c quit' % (self.binary, options, output_filename, pdf_filename)
logging.info(cmd)
logging.info(cmd)
out = subprocess.check_output(cmd, shell=True)

except subprocess.CalledProcessError as e:
Expand Down
8 changes: 4 additions & 4 deletions pypdfocr/pypdfocr_pdf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -155,7 +155,7 @@ def overlay_hocr_pages(self, dpi, hocr_filenames, orig_pdf_filename):
merger.append(PdfFileReader(file(text_pdf_filename, 'rb')))
merger.write(all_text_filename)
merger.close()
del merger
del merger


writer = PdfFileWriter()
Expand Down Expand Up @@ -191,10 +191,10 @@ def _get_merged_single_page(self, original_page, ocr_text_page):

if orig_rotation_angle != 0:
logging.info("Original Rotation: %s" % orig_rotation_angle)
self.mergeRotateAroundPointPage(original_page, ocr_text_page, orig_rotation_angle, ocr_text_page.mediaBox.getWidth()/2, ocr_text_page.mediaBox.getWidth()/2)
self.mergeRotateAroundPointPage(original_page, ocr_text_page, orig_rotation_angle, ocr_text_page.mediaBox.getWidth()/2, ocr_text_page.mediaBox.getHeight()/2)
# None of these commands worked for me:
#orig_pg.rotateCounterClockwise(orig_rotation_angle)
#orig_pg.mergeRotatedPage(text_pg,orig_rotation_angle)
#original_page.rotateCounterClockwise(orig_rotation_angle)
#original_page.mergeRotatedPage(ocr_text_page,orig_rotation_angle)
else:
original_page.mergePage(ocr_text_page)
original_page.compressContentStreams()
Expand Down