forked from mindspore-Ecosystem/mindspore
109 lines
3.9 KiB
Plaintext
109 lines
3.9 KiB
Plaintext
diff -Npur cppjieba/include/cppjieba/Jieba.hpp cppjiebap/include/cppjieba/Jieba.hpp
|
|
--- cppjieba/include/cppjieba/Jieba.hpp 2020-05-07 15:27:16.490147073 +0800
|
|
+++ cppjiebap/include/cppjieba/Jieba.hpp 2020-05-07 15:51:15.315931163 +0800
|
|
@@ -10,17 +10,14 @@ class Jieba {
|
|
public:
|
|
Jieba(const string& dict_path,
|
|
const string& model_path,
|
|
- const string& user_dict_path,
|
|
- const string& idfPath,
|
|
- const string& stopWordPath)
|
|
+ const string& user_dict_path)
|
|
: dict_trie_(dict_path, user_dict_path),
|
|
model_(model_path),
|
|
mp_seg_(&dict_trie_),
|
|
hmm_seg_(&model_),
|
|
mix_seg_(&dict_trie_, &model_),
|
|
full_seg_(&dict_trie_),
|
|
- query_seg_(&dict_trie_, &model_),
|
|
- extractor(&dict_trie_, &model_, idfPath, stopWordPath) {
|
|
+ query_seg_(&dict_trie_, &model_) {
|
|
}
|
|
~Jieba() {
|
|
}
|
|
@@ -121,8 +118,6 @@ class Jieba {
|
|
FullSegment full_seg_;
|
|
QuerySegment query_seg_;
|
|
|
|
- public:
|
|
- KeywordExtractor extractor;
|
|
}; // class Jieba
|
|
|
|
} // namespace cppjieba
|
|
diff -Npur cppjieba/test/demo.cpp cppjiebap/test/demo.cpp
|
|
--- cppjieba/test/demo.cpp 2020-05-07 15:27:16.490147073 +0800
|
|
+++ cppjiebap/test/demo.cpp 2020-05-07 15:53:21.630248552 +0800
|
|
@@ -11,9 +11,7 @@ const char* const STOP_WORD_PATH = "../d
|
|
int main(int argc, char** argv) {
|
|
cppjieba::Jieba jieba(DICT_PATH,
|
|
HMM_PATH,
|
|
- USER_DICT_PATH,
|
|
- IDF_PATH,
|
|
- STOP_WORD_PATH);
|
|
+ USER_DICT_PATH);
|
|
vector<string> words;
|
|
vector<cppjieba::Word> jiebawords;
|
|
string s;
|
|
@@ -71,10 +69,5 @@ int main(int argc, char** argv) {
|
|
cout << tagres << endl;
|
|
|
|
cout << "[demo] Keyword Extraction" << endl;
|
|
- const size_t topk = 5;
|
|
- vector<cppjieba::KeywordExtractor::Word> keywordres;
|
|
- jieba.extractor.Extract(s, keywordres, topk);
|
|
- cout << s << endl;
|
|
- cout << keywordres << endl;
|
|
return EXIT_SUCCESS;
|
|
}
|
|
diff -Npur cppjieba/test/unittest/jieba_test.cpp cppjiebap/test/unittest/jieba_test.cpp
|
|
--- cppjieba/test/unittest/jieba_test.cpp 2020-05-07 15:27:16.522146752 +0800
|
|
+++ cppjiebap/test/unittest/jieba_test.cpp 2020-05-07 15:59:11.630860061 +0800
|
|
@@ -6,9 +6,7 @@ using namespace cppjieba;
|
|
TEST(JiebaTest, Test1) {
|
|
cppjieba::Jieba jieba("../dict/jieba.dict.utf8",
|
|
"../dict/hmm_model.utf8",
|
|
- "../dict/user.dict.utf8",
|
|
- "../dict/idf.utf8",
|
|
- "../dict/stop_words.utf8");
|
|
+ "../dict/user.dict.utf8");
|
|
vector<string> words;
|
|
string result;
|
|
|
|
@@ -43,9 +41,7 @@ TEST(JiebaTest, Test1) {
|
|
TEST(JiebaTest, WordTest) {
|
|
cppjieba::Jieba jieba("../dict/jieba.dict.utf8",
|
|
"../dict/hmm_model.utf8",
|
|
- "../dict/user.dict.utf8",
|
|
- "../dict/idf.utf8",
|
|
- "../dict/stop_words.utf8");
|
|
+ "../dict/user.dict.utf8");
|
|
vector<Word> words;
|
|
string result;
|
|
|
|
@@ -85,9 +81,7 @@ TEST(JiebaTest, WordTest) {
|
|
TEST(JiebaTest, InsertUserWord) {
|
|
cppjieba::Jieba jieba("../dict/jieba.dict.utf8",
|
|
"../dict/hmm_model.utf8",
|
|
- "../dict/user.dict.utf8",
|
|
- "../dict/idf.utf8",
|
|
- "../dict/stop_words.utf8");
|
|
+ "../dict/user.dict.utf8");
|
|
vector<string> words;
|
|
string result;
|
|
|
|
@@ -120,14 +114,4 @@ TEST(JiebaTest, InsertUserWord) {
|
|
jieba.Cut("同一个世界，同一个梦想", words);
|
|
result = Join(words.begin(), words.end(), "/");
|
|
ASSERT_EQ(result, "同一个世界，同一个梦想");
|
|
-
|
|
- {
|
|
- string s("一部iPhone6");
|
|
- string res;
|
|
- vector<KeywordExtractor::Word> wordweights;
|
|
- size_t topN = 5;
|
|
- jieba.extractor.Extract(s, wordweights, topN);
|
|
- res << wordweights;
|
|
- ASSERT_EQ(res, "[{\"word\": \"iPhone6\", \"offset\": [6], \"weight\": 11.7392}, {\"word\": \"\xE4\xB8\x80\xE9\x83\xA8\", \"offset\": [0], \"weight\": 6.47592}]");
|
|
- }
|
|
}
|