preprocessing/preprocess_i2b2_2012_ner.py [17:27]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    with open(xml_path, mode='r') as f:
        lines = f.readlines()
        text, in_text = [], False
        for i, l in enumerate(lines):
            if START_CDATA in l:
                text.append(list(l[l.find(START_CDATA) + len(START_CDATA):]))
                in_text = True
            elif END_CDATA in l:
                text.append(list(l[:l.find(END_CDATA)]))
                break
            elif in_text:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



preprocessing/preprocess_i2b2_2014_ner.py [17:27]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    with open(xml_path, mode='r') as f:
        lines = f.readlines()
        text, in_text = [], False
        for i, l in enumerate(lines):
            if START_CDATA in l:
                text.append(list(l[l.find(START_CDATA) + len(START_CDATA):]))
                in_text = True
            elif END_CDATA in l:
                text.append(list(l[:l.find(END_CDATA)]))
                break
            elif in_text:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



