matthias/mayan-edms
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Unicode updates

Browse Source
This commit is contained in:
Roberto Rosario
2011-05-03 21:11:35 -04:00
parent 1e0d8d1f25
commit ae35e89549
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
apps/ocr/api.py
View File

@@ -64,7 +64,7 @@ def run_pdftotext(input_filename, output_filename, page_number=None):
""" """
command = [unicode(PDFTOTEXT_PATH)] command = [unicode(PDFTOTEXT_PATH)]
if page_number: if page_number:
command.extend(['-nopgbrk', '-f', unicode(page_number), '-l', unicode(page_number)]) command.extend([u'-nopgbrk', u'-f', unicode(page_number), u'-l', unicode(page_number)])
command.extend([unicode(input_filename), unicode(output_filename)]) command.extend([unicode(input_filename), unicode(output_filename)])
proc = subprocess.Popen(command, close_fds=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE) proc = subprocess.Popen(command, close_fds=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
return_code = proc.wait() return_code = proc.wait()
@@ -93,7 +93,7 @@ def do_document_ocr(document):
#PDF page had no text, run tesseract on the page #PDF page had no text, run tesseract on the page
imagefile = convert_document_for_ocr(document, page=page_index) imagefile = convert_document_for_ocr(document, page=page_index)
run_tesseract(imagefile, filepath, TESSERACT_LANGUAGE) run_tesseract(imagefile, filepath, TESSERACT_LANGUAGE)
ocr_output = os.extsep.join([filepath, 'txt']) ocr_output = os.extsep.join([filepath, u'txt'])
source = _(u'Text from OCR') source = _(u'Text from OCR')
else: else:
ocr_output = filepath ocr_output = filepath
@@ -101,7 +101,7 @@ def do_document_ocr(document):
else: else:
imagefile = convert_document_for_ocr(document, page=page_index) imagefile = convert_document_for_ocr(document, page=page_index)
run_tesseract(imagefile, filepath, TESSERACT_LANGUAGE) run_tesseract(imagefile, filepath, TESSERACT_LANGUAGE)
ocr_output = os.extsep.join([filepath, 'txt']) ocr_output = os.extsep.join([filepath, u'txt'])
source = _(u'Text from OCR') source = _(u'Text from OCR')
f = codecs.open(ocr_output, 'r', 'utf-8') f = codecs.open(ocr_output, 'r', 'utf-8')
document_page = document.documentpage_set.get(page_number=page_index + 1) document_page = document.documentpage_set.get(page_number=page_index + 1)