Provide C API
MnO2 opened this issue · 7 comments
MnO2 commented
By providing C API so that the existing cppjieba users could switch over with minimum efforts.
-
jieba_new- #42 -
jieba_empty- #42 -
jieba_free- #42 -
jieba_add_word- ae59f5d -
jieba_suggest_freq- 2777438 -
jieba_cut- #51 -
jieba_cut_all- #58 -
jieba_cut_for_search- 64e73ef -
jieba_tag- 7667409 -
jieba_tokenize- 3015501 -
jieba_extract_tfidf -
jieba_tfidf_new- 0541850 -
jieba_tfidf_free- 0541850 -
jieba_tfidf_extract- 0541850 -
jieba_textrank_extract- #59
messense commented
messense commented
Updated issue description with planned public APIs.
messense commented
messense commented
For consistency I think we should rename jieba_extract_textrank to jieba_textrank_extract and remove jieba_extract_tfidf
MnO2 commented
the interface for tfidf and textrank should be the same. Their instances could all be reused.
217 #[test]
218 fn test_extract_tags() {
219 let jieba = Jieba::new();
220 let keyword_extractor = TextRank::new_with_jieba(&jieba);
221 let mut top_k = keyword_extractor.extract_tags(
222 "此外，公司拟对全资子公司吉林欧亚置业有限公司增资4.3亿元，增资后，吉林欧亚置业注册资本由7000万元增加到5亿元。吉林欧亚置业主要经营范围为房地产开发及百货零售等业务。目前在建吉林欧亚城市商业综合体项目。2013年，实现营业收入0万元，实现净利润-139.13万元。",
223 6,
224 vec![String::from("ns"), String::from("n"), String::from("vn"), String::from("v")],
225 );
226 assert_eq!(top_k, vec!["吉林", "欧亚", "置业", "实现", "收入", "增资"]);
227
228 top_k = keyword_extractor.extract_tags(
229 "It is nice weather in New York City. and今天纽约的天气真好啊，and京华大酒店的张尧经理吃了一只北京烤鸭。and后天纽约的天气不好，and昨天纽约的天气也不好，and北京烤鸭真好吃",
230 3,
231 vec![],
232 );
233 assert_eq!(top_k, vec!["纽约", "天气", "不好"]);
234 }