def pages_from_rasterize(docid):
"""Rasterizes PDF pages, then continues with recognition."""
doc = util.is_valid_doc(docid)
print "Rasterizing pages..."
page_files = util.rasterize_pdf(doc)
if doc.num_pages != len(page_files): #Page count stage couldn't determine
doc.num_pages = len(page_files)
doc.save()
for i in range(doc.num_pages):
doc_page = DocumentPage(document=doc,
files_prefix=page_files[i][0],
stage_output_extension=page_files[i][1],
page_number=i,
start_process_date=datetime.now(),
status='w')
doc_page.save()
#Docs already guaranteed converted, move to binarization.
binarize_page.delay(doc_page)
def pages_from_rasterize(docid):
"""Rasterizes PDF pages, then continues with recognition."""
doc = util.is_valid_doc(docid)
print "Rasterizing pages..."
page_files = util.rasterize_pdf(doc)
if doc.num_pages != len(page_files): #Page count stage couldn't determine
doc.num_pages = len(page_files)
doc.save()
for i in range(doc.num_pages):
doc_page = DocumentPage(document=doc,
files_prefix=page_files[i][0],
stage_output_extension=page_files[i][1],
page_number=i,
start_process_date=datetime.now(),
status='w')
doc_page.save()
#Docs already guaranteed converted, move to binarization.
binarize_page.delay(doc_page)
def pages_from_images(docid):
doc = util.is_valid_doc(docid)
print "Constructing pages from images..."
#TODO: Consider splitting to multi-page TIFF so tesseract can learn
page_files = util.split_to_files(doc)
if doc.num_pages != len(page_files): #Page count stage couldn't determine
doc.num_pages = len(page_files)
doc.save()
# Creates DocumentPages for each file returned by
# split function, then launches conversion, etc.
# tasks for each DocumentPage.
for i in range(doc.num_pages):
doc_page = DocumentPage(document=doc,
files_prefix=page_files[i][0],
stage_output_extension=page_files[i][1],
page_number=i,
start_process_date=datetime.now(),
status='w')
doc_page.save()
convert_page.delay(doc_page)
def pages_from_images(docid):
doc = util.is_valid_doc(docid)
print "Constructing pages from images..."
#TODO: Consider splitting to multi-page TIFF so tesseract can learn
page_files = util.split_to_files(doc)
if doc.num_pages != len(page_files): #Page count stage couldn't determine
doc.num_pages = len(page_files)
doc.save()
# Creates DocumentPages for each file returned by
# split function, then launches conversion, etc.
# tasks for each DocumentPage.
for i in range(doc.num_pages):
doc_page = DocumentPage(document=doc,
files_prefix=page_files[i][0],
stage_output_extension=page_files[i][1],
page_number=i,
start_process_date=datetime.now(),
status='w')
doc_page.save()
convert_page.delay(doc_page)
