def bidi_record(record):
"""
Reorders a record using the Unicode BiDi algorithm.
Models trained for RTL or mixed scripts still emit classes in LTR order
requiring reordering for proper display.
Args:
record (kraken.rpred.ocr_record)
Returns:
kraken.rpred.ocr_record
"""
storage = bd.get_empty_storage()
base_level = bd.get_base_level(record.prediction)
storage['base_level'] = base_level
storage['base_dir'] = ('L', 'R')[base_level]
bd.get_embedding_levels(record.prediction, storage)
bd.explicit_embed_and_overrides(storage)
bd.resolve_weak_types(storage)
bd.resolve_neutral_types(storage, False)
bd.resolve_implicit_levels(storage, False)
for i, j in enumerate(record):
storage['chars'][i]['record'] = j
bd.reorder_resolved_levels(storage, False)
bd.apply_mirroring(storage, False)
prediction = u''
cuts = []
confidences = []
for ch in storage['chars']:
prediction = prediction + ch['record'][0]
cuts.append(ch['record'][1])
confidences.append(ch['record'][2])
return ocr_record(prediction, cuts, confidences)
def bidi_record(record):
"""
Reorders a record using the Unicode BiDi algorithm.
Models trained for RTL or mixed scripts still emit classes in LTR order
requiring reordering for proper display.
Args:
record (kraken.rpred.ocr_record)
Returns:
kraken.rpred.ocr_record
"""
storage = bd.get_empty_storage()
base_level = bd.get_base_level(record.prediction)
storage['base_level'] = base_level
storage['base_dir'] = ('L', 'R')[base_level]
bd.get_embedding_levels(record.prediction, storage)
bd.explicit_embed_and_overrides(storage)
bd.resolve_weak_types(storage)
bd.resolve_neutral_types(storage, False)
bd.resolve_implicit_levels(storage, False)
for i, j in enumerate(record):
storage['chars'][i]['record'] = j
bd.reorder_resolved_levels(storage, False)
bd.apply_mirroring(storage, False)
prediction = u''
cuts = []
confidences = []
for ch in storage['chars']:
prediction = prediction + ch['record'][0]
cuts.append(ch['record'][1])
confidences.append(ch['record'][2])
return ocr_record(prediction, cuts, confidences)
def bidi_record(record: ocr_record, base_dir=None) -> ocr_record:
"""
Reorders a record using the Unicode BiDi algorithm.
Models trained for RTL or mixed scripts still emit classes in LTR order
requiring reordering for proper display.
Args:
record (kraken.rpred.ocr_record)
Returns:
kraken.rpred.ocr_record
"""
storage = bd.get_empty_storage()
if base_dir not in ('L', 'R'):
base_level = bd.get_base_level(record.prediction)
else:
base_level = {'L': 0, 'R': 1}[base_dir]
storage['base_level'] = base_level
storage['base_dir'] = ('L', 'R')[base_level]
bd.get_embedding_levels(record.prediction, storage)
bd.explicit_embed_and_overrides(storage)
bd.resolve_weak_types(storage)
bd.resolve_neutral_types(storage, False)
bd.resolve_implicit_levels(storage, False)
for i, j in enumerate(record):
storage['chars'][i]['record'] = j
bd.reorder_resolved_levels(storage, False)
bd.apply_mirroring(storage, False)
prediction = ''
cuts = []
confidences = []
for ch in storage['chars']:
# code point may have been mirrored
prediction = prediction + ch['ch']
cuts.append(ch['record'][1])
confidences.append(ch['record'][2])
# carry over whole line information
if record.type == 'baselines':
line = {'boundary': record.line, 'baseline': record.baseline}
else:
line = record.line
rec = ocr_record(prediction, cuts, confidences, line)
rec.tags = record.tags
rec.base_dir = base_dir
return rec
def getBiDiInfo(text, *, upper_is_rtl=False, base_dir=None, debug=False):
"""
Set `upper_is_rtl` to True to treat upper case chars as strong 'R'
for debugging (default: False).
Set `base_dir` to 'L' or 'R' to override the calculated base_level.
Set `debug` to True to display (using sys.stderr) the steps taken with the
algorithm.
Returns an info dict object and the display layout.
"""
storage = get_empty_storage()
if base_dir is None:
base_level = get_base_level(text, upper_is_rtl)
else:
base_level = PARAGRAPH_LEVELS[base_dir]
storage['base_level'] = base_level
storage['base_dir'] = ('L', 'R')[base_level]
get_embedding_levels(text, storage, upper_is_rtl, debug)
assert len(text) == len(storage["chars"])
for index, (ch, chInfo) in enumerate(zip(text, storage["chars"])):
assert ch == chInfo["ch"]
chInfo["index"] = index
explicit_embed_and_overrides(storage, debug)
resolve_weak_types(storage, debug)
resolve_neutral_types(storage, debug)
resolve_implicit_levels(storage, debug)
reorder_resolved_levels(storage, debug)
reorder_combining_marks(storage, debug)
apply_mirroring(storage, debug)
chars = storage['chars']
display = ''.join([_ch['ch'] for _ch in chars])
return storage, display
