5651a0d052bcfd160b187828aa3d8d90652929fe,spacy/cli/ud/ud_run_test.py,,write_conllu,#Any#Any#,109

Before Change

    for i, doc in enumerate(docs):
        matches = merger(doc)
        spans = [doc[start : end + 1] for _, start, end in matches]
        offsets = [(span.start_char, span.end_char) for span in spans]
        for start_char, end_char in offsets:
            doc.merge(start_char, end_char)
        // TODO: This shuldn"t be necessary? Should be handled in merge
        for word in doc:
            if word.i == word.head.i:
                word.dep_ = "ROOT"
        file_.write("// newdoc id = {i}\n".format(i=i))

After Change

    for i, doc in enumerate(docs):
        matches = merger(doc)
        spans = [doc[start : end + 1] for _, start, end in matches]
        with doc.retokenize() as retokenizer:
            for span in spans:
                retokenizer.merge(span)
        // TODO: This shouldn"t be necessary? Should be handled in merge
        for word in doc:
            if word.i == word.head.i:
                word.dep_ = "ROOT"
        file_.write("// newdoc id = {i}\n".format(i=i))

Instances