def segmentation_tesseract(doc, method=u'segment_tesseract'):
"""
Performs page segmentation using tesseract's built-in algorithm and writes
a TEI XML segmentation file.
Args:
doc (unicode, unicode): The input document tuple
method (unicode): The suffix string appended to all output files.
Returns:
Two storage tuples with the first one containing the segmentation and
the second one being the file the segmentation was calculated upon.
"""
input_path = storage.get_abs_path(*doc)
output_path = splitext(storage.insert_suffix(input_path, method))[0] + '.xml'
ver = tesseract.TessVersion()
if int(ver.split('.')[0]) < 3 or int(ver.split('.')[1]) < 2:
raise NidabaTesseractException('libtesseract version is too old. Set '
'implementation to direct.')
# tesseract has a tendency to crash arbitrarily on some inputs
# necessitating execution in a separate process to ensure the worker
# doesn't just die. We use fork as the multiprocessing module thinks
# programmers are too stupid to reap their children.
logger.info('Forking before entering unstable ctypes code')
pid = os.fork()
if pid != 0:
try:
logger.info('Waiting for child to complete')
_, status = os.waitpid(pid, 0)
except OSError as e:
if e.errno not in (errno.EINTR, errno.ECHILD):
raise
return storage.get_storage_path(output_path), doc
if os.WIFSIGNALED(status):
raise NidabaTesseractException('Tesseract killed by signal: {0}'.format(os.WTERMSIG(status)))
return storage.get_storage_path(output_path), doc
api = tesseract.TessBaseAPICreate()
rc = tesseract.TessBaseAPIInit3(api, tessdata.encode('utf-8'), None)
if (rc):
tesseract.TessBaseAPIDelete(api)
raise NidabaTesseractException('Tesseract initialization failed.')
# only do segmentation and script detection
logger.debug('Setting page set mode to 2')
tesseract.TessBaseAPISetPageSegMode(api, 2)
logger.debug('Reading {} using leptonica'.format(input_path))
pix = leptonica.pixRead(input_path.encode('utf-8'))
logger.debug('Setting PIX as input image')
tesseract.TessBaseAPISetImage2(api, pix)
logger.debug('Analyzing page layout')
it = tesseract.TessBaseAPIAnalyseLayout(api)
logger.debug('Destroying PIX')
leptonica.pixDestroy(ctypes.byref(pix))
x0, y0, x1, y1 = (ctypes.c_int(), ctypes.c_int(), ctypes.c_int(),
ctypes.c_int())
w, h = Image.open(input_path).size
logger.info('Initializing TEI XML file with {}x{} {}/{}'.format(w, h, *doc))
tei = TEIFacsimile()
tei.document((w, h), os.path.join(*doc))
tei.title = os.path.basename(doc[1])
tei.add_respstmt('tesseract', 'page segmentation')
while True:
if tesseract.TessPageIteratorIsAtBeginningOf(it, RIL_TEXTLINE):
tesseract.TessPageIteratorBoundingBox(it,
RIL_TEXTLINE,
ctypes.byref(x0),
ctypes.byref(y0),
ctypes.byref(x1),
ctypes.byref(y1))
tei.add_line((x0.value, y0.value, x1.value, y1.value))
logger.debug('Segmenter found new line at {} {} {} {}'.format(x0.value,
y0.value,
x1.value,
y1.value))
if tesseract.TessPageIteratorIsAtBeginningOf(it, RIL_WORD):
tesseract.TessPageIteratorBoundingBox(it,
RIL_WORD,
ctypes.byref(x0),
ctypes.byref(y0),
ctypes.byref(x1),
ctypes.byref(y1))
tei.add_segment((x0.value, y0.value, x1.value, y1.value))
logger.debug('Segmenter found new word at {} {} {} {}'.format(x0.value,
y0.value,
x1.value,
y1.value))
tesseract.TessPageIteratorBoundingBox(it,
RIL_SYMBOL,
ctypes.byref(x0),
ctypes.byref(y0),
ctypes.byref(x1),
ctypes.byref(y1))
tei.add_graphemes([(None, (x0.value, y0.value, x1.value, y1.value))])
logger.debug('Segmenter found new symbol at {} {} {} {}'.format(x0.value,
y0.value,
x1.value,
y1.value))
if not tesseract.TessPageIteratorNext(it, RIL_SYMBOL):
logger.debug('No more elements on page')
break
logger.debug('Deleting page iterator and base API')
tesseract.TessPageIteratorDelete(it)
tesseract.TessBaseAPIEnd(api)
tesseract.TessBaseAPIDelete(api)
logger.info('Writing segmentation to {}'.format(output_path))
with open(output_path, 'w') as fp:
tei.write(fp)
logger.info('Quitting child process')
os._exit(os.EX_OK)
return storage.get_storage_path(output_path), doc
def ocr_kraken(doc, method=u'ocr_kraken', model=None):
"""
Runs kraken on an input document and writes a TEI file.
Args:
doc (unicode, unicode): The input document tuple
method (unicode): The suffix string append to all output files
model (unicode): Identifier for the font model to use
Returns:
(unicode, unicode): Storage tuple for the output file
"""
input_path = storage.get_abs_path(*doc[1])
output_path = (doc[1][0], os.path.splitext(storage.insert_suffix(doc[1][1],
method,
model))[0]
+ '.xml')
logger.debug('Searching for model {}'.format(model))
if model in nidaba_cfg['kraken_models']:
model = storage.get_abs_path(*(nidaba_cfg['kraken_models'][model]))
elif model in nidaba_cfg['ocropus_models']:
model = storage.get_abs_path(*(nidaba_cfg['ocropus_models'][model]))
else:
raise NidabaInvalidParameterException('Model not defined in '
'configuration')
img = Image.open(input_path)
logger.debug('Reading TEI segmentation from {}'.format(doc[1]))
tei = TEIFacsimile()
with storage.StorageFile(*doc[0]) as seg:
tei.read(seg)
logger.debug('Clearing out word/grapheme boxes')
# kraken is a line recognizer
tei.clear_graphemes()
tei.clear_segments()
# add and scope new responsibility statement
tei.add_respstmt('kraken', 'character recognition')
lines = tei.lines
logger.debug('Loading model {}'.format(model))
rnn = models.load_any(model)
i = 0
logger.debug('Start recognizing characters')
for rec in rpred.rpred(rnn, img, [(int(x[0]), int(x[1]), int(x[2]), int(x[3])) for x in lines]):
# scope the current line and add all graphemes recognized by kraken to
# it.
logger.debug('Scoping line {}'.format(lines[i][4]))
tei.scope_line(lines[i][4])
i += 1
splits = regex.split(u'(\s+)', rec.prediction)
line_offset = 0
for segment, whitespace in izip_longest(splits[0::2], splits[1::2]):
if len(segment):
seg_bbox = max_bbox(rec.cuts[line_offset:line_offset + len(segment)])
logger.debug('Creating new segment at {} {} {} {}'.format(*seg_bbox))
tei.add_segment(seg_bbox)
logger.debug('Adding graphemes (segment): {}'.format(rec.prediction[line_offset:line_offset+len(segment)]))
tei.add_graphemes([(x[0], x[1], int(x[2] * 100)) for x in rec[line_offset:line_offset+len(segment)]])
line_offset += len(segment)
if whitespace:
logger.debug('Adding graphemes (whitespace): {}'.format(rec.prediction[line_offset:line_offset+len(whitespace)]))
seg_bbox = max_bbox(rec.cuts[line_offset:line_offset + len(whitespace)])
tei.add_segment(seg_bbox)
tei.add_graphemes([(x[0], x[1], int(x[2] * 100)) for x in rec[line_offset:line_offset+len(whitespace)]])
line_offset += len(whitespace)
with storage.StorageFile(*output_path, mode='wb') as fp:
logger.debug('Writing TEI to {}'.format(fp.abs_path))
tei.write(fp)
return output_path
def ocr_kraken(doc, method=u'ocr_kraken', model=None):
"""
Runs kraken on an input document and writes a TEI file.
Args:
doc (unicode, unicode): The input document tuple
method (unicode): The suffix string append to all output files
model (unicode): Identifier for the font model to use
Returns:
(unicode, unicode): Storage tuple for the output file
"""
input_path = storage.get_abs_path(*doc[1])
output_path = (
doc[1][0],
os.path.splitext(storage.insert_suffix(doc[1][1], method, model))[0] +
'.xml')
logger.debug('Searching for model {}'.format(model))
if model in nidaba_cfg['kraken_models']:
model = storage.get_abs_path(*(nidaba_cfg['kraken_models'][model]))
elif model in nidaba_cfg['ocropus_models']:
model = storage.get_abs_path(*(nidaba_cfg['ocropus_models'][model]))
else:
raise NidabaInvalidParameterException('Model not defined in '
'configuration')
img = Image.open(input_path)
logger.debug('Reading TEI segmentation from {}'.format(doc[1]))
tei = TEIFacsimile()
with storage.StorageFile(*doc[0]) as seg:
tei.read(seg)
logger.debug('Clearing out word/grapheme boxes')
# kraken is a line recognizer
tei.clear_graphemes()
tei.clear_segments()
# add and scope new responsibility statement
tei.add_respstmt('kraken', 'character recognition')
lines = tei.lines
logger.debug('Loading model {}'.format(model))
rnn = models.load_any(model)
i = 0
logger.debug('Start recognizing characters')
for rec in rpred.rpred(rnn, img,
[(int(x[0]), int(x[1]), int(x[2]), int(x[3]))
for x in lines]):
# scope the current line and add all graphemes recognized by kraken to
# it.
logger.debug('Scoping line {}'.format(lines[i][4]))
tei.scope_line(lines[i][4])
i += 1
splits = regex.split(u'(\s+)', rec.prediction)
line_offset = 0
for segment, whitespace in izip_longest(splits[0::2], splits[1::2]):
if len(segment):
seg_bbox = max_bbox(rec.cuts[line_offset:line_offset +
len(segment)])
logger.debug(
'Creating new segment at {} {} {} {}'.format(*seg_bbox))
tei.add_segment(seg_bbox)
logger.debug('Adding graphemes (segment): {}'.format(
rec.prediction[line_offset:line_offset + len(segment)]))
tei.add_graphemes([
(x[0], x[1], int(x[2] * 100))
for x in rec[line_offset:line_offset + len(segment)]
])
line_offset += len(segment)
if whitespace:
logger.debug('Adding graphemes (whitespace): {}'.format(
rec.prediction[line_offset:line_offset + len(whitespace)]))
seg_bbox = max_bbox(rec.cuts[line_offset:line_offset +
len(whitespace)])
tei.add_segment(seg_bbox)
tei.add_graphemes([
(x[0], x[1], int(x[2] * 100))
for x in rec[line_offset:line_offset + len(whitespace)]
])
line_offset += len(whitespace)
with storage.StorageFile(*output_path, mode='wb') as fp:
logger.debug('Writing TEI to {}'.format(fp.abs_path))
tei.write(fp)
return output_path
def segmentation_tesseract(doc, method=u'segment_tesseract'):
"""
Performs page segmentation using tesseract's built-in algorithm and writes
a TEI XML segmentation file.
Args:
doc (unicode, unicode): The input document tuple
method (unicode): The suffix string appended to all output files.
Returns:
Two storage tuples with the first one containing the segmentation and
the second one being the file the segmentation was calculated upon.
"""
input_path = storage.get_abs_path(*doc)
output_path = splitext(storage.insert_suffix(input_path,
method))[0] + '.xml'
ver = tesseract.TessVersion()
if int(ver.split('.')[0]) < 3 or int(ver.split('.')[1]) < 2:
raise NidabaTesseractException('libtesseract version is too old. Set '
'implementation to direct.')
# tesseract has a tendency to crash arbitrarily on some inputs
# necessitating execution in a separate process to ensure the worker
# doesn't just die. We use fork as the multiprocessing module thinks
# programmers are too stupid to reap their children.
logger.info('Forking before entering unstable ctypes code')
pid = os.fork()
if pid != 0:
try:
logger.info('Waiting for child to complete')
_, status = os.waitpid(pid, 0)
except OSError as e:
if e.errno not in (errno.EINTR, errno.ECHILD):
raise
return storage.get_storage_path(output_path), doc
if os.WIFSIGNALED(status):
raise NidabaTesseractException(
'Tesseract killed by signal: {0}'.format(os.WTERMSIG(status)))
return storage.get_storage_path(output_path), doc
api = tesseract.TessBaseAPICreate()
rc = tesseract.TessBaseAPIInit3(api, tessdata.encode('utf-8'), None)
if (rc):
tesseract.TessBaseAPIDelete(api)
raise NidabaTesseractException('Tesseract initialization failed.')
# only do segmentation and script detection
logger.debug('Setting page set mode to 2')
tesseract.TessBaseAPISetPageSegMode(api, 2)
logger.debug('Reading {} using leptonica'.format(input_path))
pix = leptonica.pixRead(input_path.encode('utf-8'))
logger.debug('Setting PIX as input image')
tesseract.TessBaseAPISetImage2(api, pix)
logger.debug('Analyzing page layout')
it = tesseract.TessBaseAPIAnalyseLayout(api)
logger.debug('Destroying PIX')
leptonica.pixDestroy(ctypes.byref(pix))
x0, y0, x1, y1 = (ctypes.c_int(), ctypes.c_int(), ctypes.c_int(),
ctypes.c_int())
w, h = Image.open(input_path).size
logger.info('Initializing TEI XML file with {}x{} {}/{}'.format(
w, h, *doc))
tei = TEIFacsimile()
tei.document((w, h), os.path.join(*doc))
tei.title = os.path.basename(doc[1])
tei.add_respstmt('tesseract', 'page segmentation')
while True:
if tesseract.TessPageIteratorIsAtBeginningOf(it, RIL_TEXTLINE):
tesseract.TessPageIteratorBoundingBox(it, RIL_TEXTLINE,
ctypes.byref(x0),
ctypes.byref(y0),
ctypes.byref(x1),
ctypes.byref(y1))
tei.add_line((x0.value, y0.value, x1.value, y1.value))
logger.debug('Segmenter found new line at {} {} {} {}'.format(
x0.value, y0.value, x1.value, y1.value))
if tesseract.TessPageIteratorIsAtBeginningOf(it, RIL_WORD):
tesseract.TessPageIteratorBoundingBox(it, RIL_WORD,
ctypes.byref(x0),
ctypes.byref(y0),
ctypes.byref(x1),
ctypes.byref(y1))
tei.add_segment((x0.value, y0.value, x1.value, y1.value))
logger.debug('Segmenter found new word at {} {} {} {}'.format(
x0.value, y0.value, x1.value, y1.value))
tesseract.TessPageIteratorBoundingBox(it, RIL_SYMBOL, ctypes.byref(x0),
ctypes.byref(y0),
ctypes.byref(x1),
ctypes.byref(y1))
tei.add_graphemes([(None, (x0.value, y0.value, x1.value, y1.value))])
logger.debug('Segmenter found new symbol at {} {} {} {}'.format(
x0.value, y0.value, x1.value, y1.value))
if not tesseract.TessPageIteratorNext(it, RIL_SYMBOL):
logger.debug('No more elements on page')
break
logger.debug('Deleting page iterator and base API')
tesseract.TessPageIteratorDelete(it)
tesseract.TessBaseAPIEnd(api)
tesseract.TessBaseAPIDelete(api)
logger.info('Writing segmentation to {}'.format(output_path))
with open(output_path, 'w') as fp:
tei.write(fp)
logger.info('Quitting child process')
os._exit(os.EX_OK)
return storage.get_storage_path(output_path), doc
