def get_prefix(config):
return config.prefix or induce_wikipedia_prefix(config.wiki)
def main():
args = parse_args()
config = load_config(args.config,
["wiki", "language_path", "wikidata", "redirections"],
defaults={
"num_names_to_load": 0,
"prefix": None,
"sample_size": 100
},
relative_to=args.relative_to)
prefix = config.prefix or induce_wikipedia_prefix(config.wiki)
collection = TypeCollection(config.wikidata, num_names_to_load=0)
collection.load_blacklist(join(SCRIPT_DIR, "blacklist.json"))
trie_index2indices = OffsetArray.load(join(config.language_path,
"trie_index2indices"),
compress=True)
trie_index2indices_counts = OffsetArray(
np.load(join(config.language_path, "trie_index2indices_counts.npy")),
trie_index2indices.offsets)
if exists(
join(config.language_path,
"trie_index2indices_transition_values.npy")):
trie_index2indices_transitions = OffsetArray(
np.load(
join(config.language_path,
"trie_index2indices_transition_values.npy")),
np.load(
join(config.language_path,
"trie_index2indices_transition_offsets.npy")),
)
else:
trie_index2indices_transitions = None
anchor_trie = marisa_trie.Trie().load(
join(config.language_path, "trie.marisa"))
wiki_trie = marisa_trie.RecordTrie('i').load(
join(config.wikidata, "wikititle2wikidata.marisa"))
redirections = load_redirections(config.redirections)
seen = 0
with open(args.out, "wt") as fout:
try:
for i, (article_name,
article) in tqdm(enumerate(iterate_articles(config.wiki))):
if i == 5409:
continue
fixed_article, article_qid = convert(
article_name,
article,
collection=collection,
anchor_trie=anchor_trie,
wiki_trie=wiki_trie,
trie_index2indices=trie_index2indices,
trie_index2indices_counts=trie_index2indices_counts,
trie_index2indices_transitions=
trie_index2indices_transitions,
redirections=redirections,
prefix=prefix)
if fixed_article is False:
continue
for paragraph in fixed_article:
for word, qids in paragraph:
if len(qids) > 0:
fout.write(word.rstrip() + "\t" +
"\t".join(qids + [article_qid]) + "\n")
else:
fout.write(word.rstrip() + "\n")
fout.write("\n")
seen += 1
if seen >= config.sample_size:
break
finally:
fout.flush()
fout.close()