def pretrained_tagger(request):
"""Exposes the command-line option to a test case."""
pretrained_tagger_path = request.config.getoption("--tagger")
if not pretrained_tagger_path:
pytest.skip("No --tagger given")
else:
return pos.Tagger(
model_file=pretrained_tagger_path,
device="cpu",
)
#!/usr/bin/env python3
import sys
import re
import rnc
import pos
sentences = []
sentences.extend(rnc.Reader().read('tmp/media1.xml'))
sentences.extend(rnc.Reader().read('tmp/media2.xml'))
sentences.extend(rnc.Reader().read('tmp/media3.xml'))
re_pos = re.compile('([\w-]+)(?:[^\w-]|$)'.format('|'.join(pos.tagset)))
tagger = pos.Tagger()
sentence_labels = []
sentence_words = []
for sentence in sentences:
labels = []
words = []
for word in sentence:
gr = word[1]['gr']
m = re_pos.match(gr)
if not m:
print(gr, file = sys.stderr)
pos = m.group(1)
if pos == 'ANUM':
pos = 'A-NUM'
label = tagger.get_label_id(pos)
if not label: