示例#1
0
文件: factru.py 项目: ikonnikov/corus
def load_id(id, dir, set):
    path = txt_path(id, dir, set)
    text = load_text(path)
    path = spans_path(id, dir, set)
    lines = load_lines(path)
    spans = list(parse_spans(lines))
    path = objects_path(id, dir, set)
    lines = load_lines(path)
    objects = list(parse_objects(lines, spans))
    return FactruMarkup(id, text, objects)
示例#2
0
def load_id(id, dir):
    path = txt_path(id, dir)
    text = load_text(path)
    path = ann_path(id, dir)
    lines = load_lines(path)
    spans = list(parse_spans(lines))
    return Ne5Markup(id, text, spans)
示例#3
0
文件: factru.py 项目: natasha/corus
def load_id(id, dir, set):
    path = part_path(id, dir, set, TXT)
    text = load_text(path)

    path = part_path(id, dir, set, SPANS)
    lines = load_lines(path)
    spans = list(parse_spans(lines))

    path = part_path(id, dir, set, OBJECTS)
    lines = load_lines(path)
    objects = list(parse_objects(lines, spans))

    path = part_path(id, dir, set, COREF)
    lines = load_lines(path)
    corefs = list(parse_corefs(lines, objects))

    path = part_path(id, dir, set, FACTS)
    lines = load_lines(path)
    facts = list(parse_facts(lines, corefs, spans))

    return FactruMarkup(id, text, objects, corefs, facts)
示例#4
0
def load_rudrec(path):
    lines = load_lines(path)
    items = parse_jsonl(lines)
    return parse_rudrec(items)
示例#5
0
文件: bsnlp.py 项目: natasha/corus
def load_annotated(records):
    for record in records:
        lines = load_lines(record.path)
        yield parse_annotated(record.name, lines)
示例#6
0
文件: ud.py 项目: natasha/corus
def load_ud(path):
    lines = load_lines(path)
    return parse_ud(lines)
示例#7
0
文件: gareev.py 项目: ikonnikov/corus
def load_id(id, dir):
    path = join_path(dir, '%s.txt.iob' % id)
    lines = load_lines(path)
    return parse_conll(lines)
示例#8
0
文件: russe.py 项目: natasha/corus
def load_russe(path):
    lines = load_lines(path)
    return parse_russe(lines)
示例#9
0
文件: toloka.py 项目: natasha/corus
def load_toloka_lrwc(path):
    lines = load_lines(path)
    return parse_toloka_lrwc(lines)
示例#10
0
文件: toloka.py 项目: natasha/corus
def load_ruadrect(path):
    lines = load_lines(path)
    return parse_ruadrect(lines)
示例#11
0
文件: simlex.py 项目: natasha/corus
def load_simlex(path):
    lines = load_lines(path)
    return parse_simlex(lines)
示例#12
0
def load_mokoron(path):
    for line in load_lines(path):
        if line.startswith(INSERT):
            for match in RECORD.finditer(line):
                yield MokoronRecord.from_match(match)
示例#13
0
def load_morphoru_corpora(path):
    lines = load_lines(path)
    return parse_morphoru(lines, parse_morphoru_corpora_sent)
示例#14
0
def load_morphoru_rnc(path):
    lines = load_lines(path)
    return parse_morphoru_rnc(lines)
示例#15
0
def load_morphoru_gicrya(path):
    lines = load_lines(path)
    return parse_morphoru(lines, parse_morphoru_gicrya_sent)