def get_ocr_language(language):
langs = get_available_languages()
if language is None:
language = get_language()
ocr_langs = get_config("ocr languages")
if ocr_langs is None:
ocr_langs = dict()
if language in langs:
lang = language
else:
if language in ocr_langs and ocr_langs[language] in langs:
lang = ocr_langs[language]
else:
try:
pc_lang = pycountry.languages.get(alpha_2=language)
lang_three_letter = pc_lang.alpha_3
if lang_three_letter in langs:
lang = lang_three_letter
else:
if 'eng' in langs:
lang = 'eng'
else:
lang = langs[0]
raise Exception(
"could not get OCR language for language " +
str(language) + "; using language " + str(lang))
except Exception as the_error:
if 'eng' in langs:
lang = 'eng'
else:
lang = langs[0]
raise Exception("could not get OCR language for language " +
str(language) + "; using language " +
str(lang) + "; error was " + str(the_error))
return lang
def ocr_page_tasks(image_file, language=None, psm=6, x=None, y=None, W=None, H=None, user_code=None, user=None, pdf=False, preserve_color=False, **kwargs):
#sys.stderr.write("ocr_page_tasks running\n")
if isinstance(image_file, set):
return []
if not isinstance(image_file, (DAFile, DAFileList, list)):
return word("(Not a DAFile, DAFileList, or list object)")
pdf_to_ppm = get_config("pdftoppm")
if pdf_to_ppm is None:
pdf_to_ppm = 'pdftoppm'
ocr_resolution = get_config("ocr dpi")
if ocr_resolution is None:
ocr_resolution = '300'
langs = get_available_languages()
if language is None:
language = get_language()
if language in langs:
lang = language
else:
ocr_langs = get_config("ocr languages")
if ocr_langs is None:
ocr_langs = {}
if language in ocr_langs and ocr_langs[language] in langs:
lang = ocr_langs[language]
else:
try:
pc_lang = pycountry.languages.get(alpha_2=language)
lang_three_letter = pc_lang.alpha_3
if lang_three_letter in langs:
lang = lang_three_letter
else:
if 'eng' in langs:
lang = 'eng'
else:
lang = langs[0]
sys.stderr.write("ocr_file: could not get OCR language for language " + str(language) + "; using language " + str(lang) + "\n")
except Exception as the_error:
if 'eng' in langs:
lang = 'eng'
else:
lang = langs[0]
sys.stderr.write("ocr_file: could not get OCR language for language " + str(language) + "; using language " + str(lang) + "; error was " + str(the_error) + "\n")
if isinstance(image_file, DAFile):
image_file = [image_file]
todo = []
for doc in image_file:
if hasattr(doc, 'extension'):
if doc.extension not in ['pdf', 'png', 'jpg', 'gif', 'docx', 'doc', 'odt', 'rtf']:
raise Exception("document with extension " + doc.extension + " is not a readable image file")
if doc.extension == 'pdf':
#doc.page_path(1, 'page')
for i in range(safe_pypdf_reader(doc.path()).getNumPages()):
todo.append(dict(doc=doc, page=i+1, lang=lang, ocr_resolution=ocr_resolution, psm=psm, x=x, y=y, W=W, H=H, pdf_to_ppm=pdf_to_ppm, user_code=user_code, user=user, pdf=pdf, preserve_color=preserve_color))
elif doc.extension in ("docx", "doc", "odt", "rtf"):
doc_conv = docassemble.base.util.pdf_concatenate(doc)
for i in range(safe_pypdf_reader(doc_conv.path()).getNumPages()):
todo.append(dict(doc=doc_conv, page=i+1, lang=lang, ocr_resolution=ocr_resolution, psm=psm, x=x, y=y, W=W, H=H, pdf_to_ppm=pdf_to_ppm, user_code=user_code, user=user, pdf=pdf, preserve_color=preserve_color))
else:
todo.append(dict(doc=doc, page=None, lang=lang, ocr_resolution=ocr_resolution, psm=psm, x=x, y=y, W=W, H=H, pdf_to_ppm=pdf_to_ppm, user_code=user_code, user=user, pdf=pdf, preserve_color=preserve_color))
#sys.stderr.write("ocr_page_tasks finished\n")
return todo
def ocr_page_tasks(image_file, language=None, psm=6, x=None, y=None, W=None, H=None, user_code=None, **kwargs):
#sys.stderr.write("ocr_page_tasks running\n")
if not (isinstance(image_file, DAFile) or isinstance(image_file, DAFileList)):
return word("(Not a DAFile or DAFileList object)")
pdf_to_ppm = get_config("pdftoppm")
if pdf_to_ppm is None:
pdf_to_ppm = 'pdftoppm'
ocr_resolution = get_config("ocr dpi")
if ocr_resolution is None:
ocr_resolution = '300'
langs = get_available_languages()
if language is None:
language = get_language()
if language in langs:
lang = language
else:
ocr_langs = get_config("ocr languages")
if ocr_langs is None:
ocr_langs = dict()
if language in ocr_langs and ocr_langs[language] in langs:
lang = ocr_langs[language]
else:
try:
pc_lang = pycountry.languages.get(alpha_2=language)
lang_three_letter = pc_lang.alpha_3
if lang_three_letter in langs:
lang = lang_three_letter
else:
if 'eng' in langs:
lang = 'eng'
else:
lang = langs[0]
sys.stderr.write("ocr_file: could not get OCR language for language " + str(language) + "; using language " + str(lang) + "\n")
except Exception as the_error:
if 'eng' in langs:
lang = 'eng'
else:
lang = langs[0]
sys.stderr.write("ocr_file: could not get OCR language for language " + str(language) + "; using language " + str(lang) + "; error was " + str(the_error) + "\n")
if isinstance(image_file, DAFile):
image_file = [image_file]
todo = list()
for doc in image_file:
if hasattr(doc, 'extension'):
if doc.extension not in ['pdf', 'png', 'jpg', 'gif']:
raise Exception("document with extension " + doc.extension + " is not a readable image file")
if doc.extension == 'pdf':
#doc.page_path(1, 'page')
for i in xrange(PdfFileReader(open(doc.path(), 'rb')).getNumPages()):
todo.append(dict(doc=doc, page=i+1, lang=lang, ocr_resolution=ocr_resolution, psm=psm, x=x, y=y, W=W, H=H, pdf_to_ppm=pdf_to_ppm, user_code=user_code))
else:
todo.append(dict(doc=doc, page=None, lang=lang, ocr_resolution=ocr_resolution, psm=psm, x=x, y=y, W=W, H=H, pdf_to_ppm=pdf_to_ppm, user_code=user_code))
#sys.stderr.write("ocr_page_tasks finished\n")
return todo
def ocr_page_tasks(image_file,
language=None,
psm=6,
x=None,
y=None,
W=None,
H=None,
user_code=None,
**kwargs):
#sys.stderr.write("ocr_page_tasks running\n")
if not (isinstance(image_file, DAFile)
or isinstance(image_file, DAFileList)):
return word("(Not a DAFile or DAFileList object)")
pdf_to_ppm = get_config("pdftoppm")
if pdf_to_ppm is None:
pdf_to_ppm = 'pdftoppm'
ocr_resolution = get_config("ocr dpi")
if ocr_resolution is None:
ocr_resolution = '300'
langs = get_available_languages()
if language is None:
language = get_language()
if language in langs:
lang = language
else:
ocr_langs = get_config("ocr languages")
if ocr_langs is None:
ocr_langs = dict()
if language in ocr_langs and ocr_langs[language] in langs:
lang = ocr_langs[language]
else:
try:
pc_lang = pycountry.languages.get(alpha_2=language)
lang_three_letter = pc_lang.alpha_3
if lang_three_letter in langs:
lang = lang_three_letter
else:
if 'eng' in langs:
lang = 'eng'
else:
lang = langs[0]
sys.stderr.write(
"ocr_file: could not get OCR language for language " +
str(language) + "; using language " + str(lang) + "\n")
except Exception as the_error:
if 'eng' in langs:
lang = 'eng'
else:
lang = langs[0]
sys.stderr.write(
"ocr_file: could not get OCR language for language " +
str(language) + "; using language " + str(lang) +
"; error was " + str(the_error) + "\n")
if isinstance(image_file, DAFile):
image_file = [image_file]
todo = list()
for doc in image_file:
if hasattr(doc, 'extension'):
if doc.extension not in ['pdf', 'png', 'jpg', 'gif']:
raise Exception("document with extension " + doc.extension +
" is not a readable image file")
if doc.extension == 'pdf':
#doc.page_path(1, 'page')
for i in range(
PdfFileReader(open(doc.path(), 'rb')).getNumPages()):
todo.append(
dict(doc=doc,
page=i + 1,
lang=lang,
ocr_resolution=ocr_resolution,
psm=psm,
x=x,
y=y,
W=W,
H=H,
pdf_to_ppm=pdf_to_ppm,
user_code=user_code))
else:
todo.append(
dict(doc=doc,
page=None,
lang=lang,
ocr_resolution=ocr_resolution,
psm=psm,
x=x,
y=y,
W=W,
H=H,
pdf_to_ppm=pdf_to_ppm,
user_code=user_code))
#sys.stderr.write("ocr_page_tasks finished\n")
return todo