fastNLP/reproduction/seqence_labelling/ner/data/utils.py

from typing import List

def iob2(tags:List[str])->List[str]:
    """
    检查数据是否是合法的IOB数据，如果是IOB1会被自动转换为IOB2。

    :param tags: 需要转换的tags
    """
    for i, tag in enumerate(tags):
        if tag == "O":
            continue
        split = tag.split("-")
        if len(split) != 2 or split[0] not in ["I", "B"]:
            raise TypeError("The encoding schema is not a valid IOB type.")
        if split[0] == "B":
            continue
        elif i == 0 or tags[i - 1] == "O":  # conversion IOB1 to IOB2
            tags[i] = "B" + tag[1:]
        elif tags[i - 1][1:] == tag[1:]:
            continue
        else:  # conversion IOB1 to IOB2
            tags[i] = "B" + tag[1:]
    return tags

def iob2bioes(tags:List[str])->List[str]:
    """
    将iob的tag转换为bmeso编码
    :param tags:
    :return:
    """
    new_tags = []
    for i, tag in enumerate(tags):
        if tag == 'O':
            new_tags.append(tag)
        else:
            split = tag.split('-')[0]
            if split == 'B':
                if i+1!=len(tags) and tags[i+1].split('-')[0] == 'I':
                    new_tags.append(tag)
                else:
                    new_tags.append(tag.replace('B-', 'S-'))
            elif split == 'I':
                if i + 1<len(tags) and tags[i+1].split('-')[0] == 'I':
                    new_tags.append(tag)
                else:
                    new_tags.append(tag.replace('I-', 'E-'))
            else:
                raise TypeError("Invalid IOB format.")
    return new_tags