mindspore/third_party/patch/cppjieba/cppjieba.patch001

diff -Npur cppjieba/deps/limonp/StringUtil.hpp cppjiebap/deps/limonp/StringUtil.hpp
--- cppjieba/deps/limonp/StringUtil.hpp	2020-03-11 09:30:52.000000000 +0800
+++ cppjiebap/deps/limonp/StringUtil.hpp	2020-12-15 16:02:38.000000000 +0800
@@ -84,12 +84,12 @@ inline bool IsSpace(unsigned c) {
 }
 
 inline std::string& LTrim(std::string &s) {
-  s.erase(s.begin(), std::find_if(s.begin(), s.end(), std::not1(std::ptr_fun<unsigned, bool>(IsSpace))));
+  s.erase(s.begin(), std::find_if(s.begin(), s.end(), std::not1(std::function<unsigned(bool)>(IsSpace))));
   return s;
 }
 
 inline std::string& RTrim(std::string &s) {
-  s.erase(std::find_if(s.rbegin(), s.rend(), std::not1(std::ptr_fun<unsigned, bool>(IsSpace))).base(), s.end());
+  s.erase(std::find_if(s.rbegin(), s.rend(), std::not1(std::function<unsigned(bool)>(IsSpace))).base(), s.end());
   return s;
 }
 
@@ -98,12 +98,12 @@ inline std::string& Trim(std::string &s)
 }
 
 inline std::string& LTrim(std::string & s, char x) {
-  s.erase(s.begin(), std::find_if(s.begin(), s.end(), std::not1(std::bind2nd(std::equal_to<char>(), x))));
+  s.erase(s.begin(), std::find_if(s.begin(), s.end(), [x](char c) -> bool { return c != x; }));
   return s;
 }
 
 inline std::string& RTrim(std::string & s, char x) {
-  s.erase(std::find_if(s.rbegin(), s.rend(), std::not1(std::bind2nd(std::equal_to<char>(), x))).base(), s.end());
+  s.erase(std::find_if(s.rbegin(), s.rend(), [x](char c) -> bool { return c != x; } ).base(), s.end());
   return s;
 }
 
diff -Npur cppjieba/include/cppjieba/Jieba.hpp cppjiebap/include/cppjieba/Jieba.hpp
--- cppjieba/include/cppjieba/Jieba.hpp	2020-03-11 09:30:52.000000000 +0800
+++ cppjiebap/include/cppjieba/Jieba.hpp	2020-12-15 16:01:46.000000000 +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	2020-03-11 09:30:52.000000000 +0800
+++ cppjiebap/test/demo.cpp	2020-12-15 16:01:46.000000000 +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	2020-03-11 09:30:52.000000000 +0800
+++ cppjiebap/test/unittest/jieba_test.cpp	2020-12-15 16:01:46.000000000 +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}]");
-  }
 }