Example #1
0
def main(in_fname):
    doc = marujirou.create_doc(in_fname)
    symbol_filter = lambda m: m.pos != '補助記号'
    for sent in doc:
        for chunk in sent:
            if chunk.dst != -1:
                print '%s\t%s' % (chunk.get_raw(symbol_filter), sent[chunk.dst].get_raw(symbol_filter))
Example #2
0
def main(in_fname):
    doc = marujirou.create_doc(in_fname)
    symbol_filter = lambda m: m.pos != "補助記号"
    for sent in doc:
        for chunk in sent:
            if chunk.dst != -1 and chunk.hasNoun() and sent[chunk.dst].hasVerb():
                print "%s\t%s" % (chunk.get_raw(symbol_filter), sent[chunk.dst].get_raw(symbol_filter))
Example #3
0
def main(in_fname):
    doc = marujirou.create_doc(in_fname)
    for sent in doc:
        nps = list()
        for chunk in sent:
            if chunk.hasNoun():
                nps.append(chunk)
        for path in get_all_path(sent, nps):
            print path
Example #4
0
def main(in_fname):
    doc = marujirou.create_doc(in_fname)
    for sent in doc:
        for chunk in sent:
            if chunk.dst != -1 and chunk.hasNoun():
                outputs = chunk.get_raw()
                while chunk.dst != -1:
                    outputs += ' -> %s' % sent[chunk.dst].get_raw()
                    chunk = sent[chunk.dst]
                print '%s' % outputs
Example #5
0
def main(in_fname):
    doc = marujirou.create_doc(in_fname)
    for sent in doc:
        for chunk in sent:
            if chunk.srcs and chunk.hasVerb():
                pred = chunk.get_first_verb().base 
                cases = sorted([sent[src].get_case().base for src in chunk.srcs if sent[src].hasCase()])
                if not cases:
                    continue
                print '%s\t%s' % (pred, ' '.join(cases)) 
Example #6
0
def main(in_fname):
    doc = marujirou.create_doc(in_fname)
    print "digraph dependency {"
    for sent_id, sent in enumerate(doc):
        for chunk_id, chunk in enumerate(sent):
            if chunk.dst != -1:
                print '%d.%d [label="%s"]' % (sent_id, chunk_id, chunk.get_raw())
                print "%d.%d -> %d.%d;" % (sent_id, chunk_id, sent_id, chunk.dst)
            elif chunk.srcs:
                print "%d.%d [label=%s]" % (sent_id, chunk_id, chunk.get_raw())
    print "}"
Example #7
0
def main(in_fname):
    doc = marujirou.create_doc(in_fname)
    for sent in doc:
        for chunk in sent:
            if chunk.srcs and chunk.hasVerb():
                pred = chunk.get_first_verb().base 
                cases_args = sorted([(sent[src].get_case().base, sent[src].get_raw()) for src in chunk.srcs if sent[src].hasCase()])
                if not cases_args:
                    continue
                cases, args = zip(*cases_args)
                print '%s\t%s\t%s' % (pred, ' '.join(cases), ' '.join(args)) 
Example #8
0
def main(in_fname):
    doc = marujirou.create_doc(in_fname)
    for sent in doc:
        for chunk in sent:
            if chunk.srcs and chunk.isSahenWoVerb():
                pred = chunk.get_sahen_wo_verb()
                cases_args = sorted([(sent[src].get_case().base, sent[src].get_raw()) for src in chunk.srcs if sent[src].hasCase()])
                if not cases_args:
                    continue
                cases, args = zip(*cases_args)
                print '%s\t%s\t%s' % (pred, ' '.join(cases), ' '.join(args)) 
Example #9
0
def main(in_fname):
    doc = marujirou.create_doc(in_fname)
    print 'digraph dependency {'
    for sent_id, sent in enumerate(doc):
        for chunk_id, chunk in enumerate(sent):
            if chunk.dst != -1:
                print '%d.%d [label="%s"]' % (sent_id, chunk_id,
                                              chunk.get_raw())
                print '%d.%d -> %d.%d;' % (sent_id, chunk_id, sent_id,
                                           chunk.dst)
            elif chunk.srcs:
                print '%d.%d [label=%s]' % (sent_id, chunk_id, chunk.get_raw())
    print '}'