Class BaseRecLabelEncode

openrec/preprocess/ce_label_encode.py:8–91

Convert between text-label and text-index.

class BaseRecLabelEncode(object):
    """Convert between text-label and text-index."""

    def __init__(
        self,
        max_text_length,
        character_dict_path=None,
        use_space_char=False,
        lower=False,
    ):
        self.max_text_len = max_text_length
        self.beg_str = 'sos'
        self.end_str = 'eos'
        self.lower = lower
        self.reverse = False
        if character_dict_path is None:
            logger = get_logger()
            logger.warning(
                'The character_dict_path is None, model can only recognize number and lower letters'
            )
            self.character_str = '0123456789abcdefghijklmnopqrstuvwxyz'
            dict_character = list(self.character_str)
            self.lower = True
        else:
            self.character_str = []
            with open(character_dict_path, 'rb') as fin:
                lines = fin.readlines()
                for line in lines:
                    line = line.decode('utf-8').strip('\n').strip('\r\n')
                    self.character_str.append(line)
            if use_space_char:
                self.character_str.append(' ')
            dict_character = list(self.character_str)
            if 'arabic' in character_dict_path:
                self.reverse = True
        dict_character = self.add_special_char(dict_character)
        self.dict = {}
        for i, char in enumerate(dict_character):
            self.dict[char] = i
        self.character = dict_character

    def label_reverse(self, text):
        text_re = []
        c_current = ''
        for c in text:
            if not bool(re.search('[a-zA-Z0-9 :*./%+١٢٣٤٥٦٧٨٩٠-]', c)):
                if c_current != '':
                    text_re.append(c_current)
                text_re.append(c)
                c_current = ''
            else:
                c_current += c
        if c_current != '':
            text_re.append(c_current)

        return ''.join(text_re[::-1])

    def add_special_char(self, dict_character):