def processPage(page, abbyyParsed):
if page is None:
helper.log.debug('No pages for processing')
return
else:
startTime = time()
helper.log.debug('Starting Processing for scan_id: %s' %
(page['scan_id']))
if (page['abbyy_complete'] is False):
if page['scandata_index'] <= len(abbyyParsed):
result = abbyyParsed[page['scandata_index']]
if (result is not False):
page['abbyy'] = result
page['has_illustration']['abbyy'] = result[
'image_detected']
page['abbyy_complete'] = True
page['abbyy_processing_duration'] = time() - startTime
helper.log.debug('ABBYY Processing duration: %s' %
(page['abbyy_processing_duration']))
else:
page['abbyy_error'] = 'out of range %s' % (
page['scandata_index'])
#if (page['compression_complete'] is False):
#result = compression.processImage(page)
#if (result is not False):
#page.update(result)
#page['compression_complete'] = True
#page['compression_processing_duration'] = time() - startTime
#helper.log.debug('Compression Processing duration: %s' % (page['compression_processing_duration']))
if (page['contrast_complete'] is False):
result = contrast.processImage(page)
if (result is not False):
page.update(result)
page['has_illustration']['contrast'] = result['image_detected']
page['contrast_complete'] = True
page['contrast_processing_duration'] = time() - startTime
helper.log.debug('Contrast Processing duration: %s' %
(page['contrast_processing_duration']))
page['processing_lock'] = False
page['processing_lock_end'] = time()
#if (page['abbyy_complete'] is False or page['compression_complete'] is False or page['contrast_complete'] is False):
if (page['abbyy_complete'] is False
or page['contrast_complete'] is False):
page['processing_error'] = True
helper.log.debug(
'Complete: %s|%s: abbyy: %s, compression: %s, contrast: %s' %
(page['scan_id'], page['ia_page_num'], page['abbyy_complete'],
page['compression_complete'], page['contrast_complete']))
helper.log.debug('Processing duration: %s' % (time() - startTime))
def processPage(page, abbyyParsed):
if page is None:
helper.log.debug('No pages for processing')
return
else:
startTime = time()
helper.log.debug('Starting Processing for scan_id: %s' % (page['scan_id']))
if (page['abbyy_complete'] is False):
if page['scandata_index'] <= len(abbyyParsed):
result = abbyyParsed[page['scandata_index']]
if (result is not False):
page['abbyy'] = result
page['has_illustration']['abbyy'] = result['image_detected']
page['abbyy_complete'] = True
page['abbyy_processing_duration'] = time() - startTime
helper.log.debug('ABBYY Processing duration: %s' % (page['abbyy_processing_duration']))
else:
page['abbyy_error'] = 'out of range %s' % (page['scandata_index'])
#if (page['compression_complete'] is False):
#result = compression.processImage(page)
#if (result is not False):
#page.update(result)
#page['compression_complete'] = True
#page['compression_processing_duration'] = time() - startTime
#helper.log.debug('Compression Processing duration: %s' % (page['compression_processing_duration']))
if (page['contrast_complete'] is False):
result = contrast.processImage(page)
if (result is not False):
page.update(result)
page['has_illustration']['contrast'] = result['image_detected']
page['contrast_complete'] = True
page['contrast_processing_duration'] = time() - startTime
helper.log.debug('Contrast Processing duration: %s' % (page['contrast_processing_duration']))
page['processing_lock'] = False
page['processing_lock_end'] = time()
#if (page['abbyy_complete'] is False or page['compression_complete'] is False or page['contrast_complete'] is False):
if (page['abbyy_complete'] is False or page['contrast_complete'] is False):
page['processing_error'] = True
helper.log.debug('Complete: %s|%s: abbyy: %s, compression: %s, contrast: %s' %
(page['scan_id'], page['ia_page_num'], page['abbyy_complete'], page['compression_complete'], page['contrast_complete']))
helper.log.debug('Processing duration: %s' % (time() - startTime))
print len(page_data), 'pages'
import compression
import contrast
import abbyy
# Fetch ABBYY file
if (args.v):
print 'Fetching ABBYY...'
abbyy_file = urllib2.urlopen("http://archive.org/download/%(scan)s/%(file)s" % {'scan': args.scan, 'file': abbyy_filename})
abbyy_data = ET.fromstring(zlib.decompress(abbyy_file.read(), 15 + 32))
abbyy_pages = abbyy_data.findall('{http://www.abbyy.com/FineReader_xml/FineReader6-schema-v1.xml}page')
# Process each page
for page in page_data:
url = 'http://www.archive.org/download/%s/page/n%s' % (page['scan_id'], page['ia_page_num'])
img_file = StringIO(urllib2.urlopen(url).read())
image = Image.open(img_file)
print compression.processImage(img_file, image)
print contrast.processImage(image, page['scan_id'], page['ia_page_num'])
print abbyy.processABBYY(abbyy_pages[page['scandata_index']])
break
# Process metadata