react-native-jieba 0.4.0 → 0.4.1

package/cpp/cppjieba/deps/limonp/include/limonp/StdExtension.hpp

@@ -0,0 +1,157 @@
+#ifndef LIMONP_STD_EXTEMSION_HPP
+#define LIMONP_STD_EXTEMSION_HPP
+
+#include <map>
+
+#ifdef __APPLE__
+#include <unordered_map>
+#include <unordered_set>
+#elif(__cplusplus >= 201103L)
+#include <unordered_map>
+#include <unordered_set>
+#elif defined _MSC_VER
+#include <unordered_map>
+#include <unordered_set>
+#else
+#include <tr1/unordered_map>
+#include <tr1/unordered_set>
+namespace std {
+using std::tr1::unordered_map;
+using std::tr1::unordered_set;
+}
+
+#endif
+
+#include <set>
+#include <string>
+#include <vector>
+#include <deque>
+#include <fstream>
+#include <sstream>
+
+namespace std {
+
+template<typename T>
+ostream& operator << (ostream& os, const vector<T>& v) {
+  if(v.empty()) {
+    return os << "[]";
+  }
+  os<<"["<<v[0];
+  for(size_t i = 1; i < v.size(); i++) {
+    os<<", "<<v[i];
+  }
+  os<<"]";
+  return os;
+}
+
+template<>
+inline ostream& operator << (ostream& os, const vector<string>& v) {
+  if(v.empty()) {
+    return os << "[]";
+  }
+  os<<"[\""<<v[0];
+  for(size_t i = 1; i < v.size(); i++) {
+    os<<"\", \""<<v[i];
+  }
+  os<<"\"]";
+  return os;
+}
+
+template<typename T>
+ostream& operator << (ostream& os, const deque<T>& dq) {
+  if(dq.empty()) {
+    return os << "[]";
+  }
+  os<<"[\""<<dq[0];
+  for(size_t i = 1; i < dq.size(); i++) {
+    os<<"\", \""<<dq[i];
+  }
+  os<<"\"]";
+  return os;
+}
+
+
+template<class T1, class T2>
+ostream& operator << (ostream& os, const pair<T1, T2>& pr) {
+  os << pr.first << ":" << pr.second ;
+  return os;
+}
+
+
+template<class T>
+string& operator << (string& str, const T& obj) {
+  stringstream ss;
+  ss << obj; // call ostream& operator << (ostream& os,
+  return str = ss.str();
+}
+
+template<class T1, class T2>
+ostream& operator << (ostream& os, const map<T1, T2>& mp) {
+  if(mp.empty()) {
+    os<<"{}";
+    return os;
+  }
+  os<<'{';
+  typename map<T1, T2>::const_iterator it = mp.begin();
+  os<<*it;
+  it++;
+  while(it != mp.end()) {
+    os<<", "<<*it;
+    it++;
+  }
+  os<<'}';
+  return os;
+}
+template<class T1, class T2>
+ostream& operator << (ostream& os, const std::unordered_map<T1, T2>& mp) {
+  if(mp.empty()) {
+    return os << "{}";
+  }
+  os<<'{';
+  typename std::unordered_map<T1, T2>::const_iterator it = mp.begin();
+  os<<*it;
+  it++;
+  while(it != mp.end()) {
+    os<<", "<<*it++;
+  }
+  return os<<'}';
+}
+
+template<class T>
+ostream& operator << (ostream& os, const set<T>& st) {
+  if(st.empty()) {
+    os << "{}";
+    return os;
+  }
+  os<<'{';
+  typename set<T>::const_iterator it = st.begin();
+  os<<*it;
+  it++;
+  while(it != st.end()) {
+    os<<", "<<*it;
+    it++;
+  }
+  os<<'}';
+  return os;
+}
+
+template<class KeyType, class ContainType>
+bool IsIn(const ContainType& contain, const KeyType& key) {
+  return contain.end() != contain.find(key);
+}
+
+template<class T>
+basic_string<T> & operator << (basic_string<T> & s, ifstream & ifs) {
+  return s.assign((istreambuf_iterator<T>(ifs)), istreambuf_iterator<T>());
+}
+
+template<class T>
+ofstream & operator << (ofstream & ofs, const basic_string<T>& s) {
+  ostreambuf_iterator<T> itr (ofs);
+  copy(s.begin(), s.end(), itr);
+  return ofs;
+}
+
+} // namespace std
+
+#endif

package/cpp/cppjieba/deps/limonp/include/limonp/StringUtil.hpp

@@ -0,0 +1,386 @@
+/************************************
+ * file enc : ascii
+ * author   : wuyanyi09@gmail.com
+ ************************************/
+#ifndef LIMONP_STR_FUNCTS_H
+#define LIMONP_STR_FUNCTS_H
+#include <fstream>
+#include <iostream>
+#include <string>
+#include <vector>
+#include <algorithm>
+#include <cctype>
+#include <map>
+#include <cassert>
+#include <ctime>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdarg.h>
+#include <memory.h>
+#include <functional>
+#include <locale>
+#include <sstream>
+#include <sys/types.h>
+#include <iterator>
+#include <algorithm>
+#include "StdExtension.hpp"
+
+namespace limonp {
+using namespace std;
+inline string StringFormat(const char* fmt, ...) {
+  int size = 256;
+  std::string str;
+  va_list ap;
+  while (1) {
+    str.resize(size);
+    va_start(ap, fmt);
+    int n = vsnprintf((char *)str.c_str(), size, fmt, ap);
+    va_end(ap);
+    if (n > -1 && n < size) {
+      str.resize(n);
+      return str;
+    }
+    if (n > -1)
+      size = n + 1;
+    else
+      size *= 2;
+  }
+  return str;
+}
+
+template<class T>
+void Join(T begin, T end, string& res, const string& connector) {
+  if(begin == end) {
+    return;
+  }
+  stringstream ss;
+  ss<<*begin;
+  begin++;
+  while(begin != end) {
+    ss << connector << *begin;
+    begin ++;
+  }
+  res = ss.str();
+}
+
+template<class T>
+string Join(T begin, T end, const string& connector) {
+  string res;
+  Join(begin ,end, res, connector);
+  return res;
+}
+
+inline string& Upper(string& str) {
+  transform(str.begin(), str.end(), str.begin(), (int (*)(int))toupper);
+  return str;
+}
+
+inline string& Lower(string& str) {
+  transform(str.begin(), str.end(), str.begin(), (int (*)(int))tolower);
+  return str;
+}
+
+inline bool IsSpace(unsigned c) {
+  // when passing large int as the argument of isspace, it core dump, so here need a type cast.
+  return c > 0xff ? false : std::isspace(c & 0xff) != 0;
+}
+
+inline std::string& LTrim(std::string &s) {
+    s.erase(s.begin(), std::find_if(s.begin(), s.end(), [](unsigned char ch) {
+        return !std::isspace(ch);
+    }));
+    return s;
+}
+
+inline std::string& RTrim(std::string &s) {
+  s.erase(std::find_if(s.rbegin(), s.rend(), [](unsigned char ch) {
+      return !std::isspace(ch);
+  }).base(), s.end());
+  return s;
+}
+
+inline std::string& Trim(std::string &s) {
+  return LTrim(RTrim(s));
+}
+
+inline std::string& LTrim(std::string& s, char x) {
+    s.erase(s.begin(), std::find_if(s.begin(), s.end(),
+      [x](unsigned char c) { return !std::isspace(c) && c != x; }));
+    return s;
+}
+
+inline std::string& RTrim(std::string& s, char x) {
+    s.erase(std::find_if(s.rbegin(), s.rend(),
+        [x](unsigned char c) { return !std::isspace(c) && c != x; }).base(), s.end());
+    return s;
+}
+
+inline std::string& Trim(std::string &s, char x) {
+  return LTrim(RTrim(s, x), x);
+}
+
+inline void Split(const string& src, vector<string>& res, const string& pattern, size_t maxsplit = string::npos) {
+  res.clear();
+  size_t Start = 0;
+  size_t end = 0;
+  string sub;
+  while(Start < src.size()) {
+    end = src.find_first_of(pattern, Start);
+    if(string::npos == end || res.size() >= maxsplit) {
+      sub = src.substr(Start);
+      res.push_back(sub);
+      return;
+    }
+    sub = src.substr(Start, end - Start);
+    res.push_back(sub);
+    Start = end + 1;
+  }
+  return;
+}
+
+inline vector<string> Split(const string& src, const string& pattern, size_t maxsplit = string::npos) {
+  vector<string> res;
+  Split(src, res, pattern, maxsplit);
+  return res;
+}
+
+inline bool StartsWith(const string& str, const string& prefix) {
+  if(prefix.length() > str.length()) {
+    return false;
+  }
+  return 0 == str.compare(0, prefix.length(), prefix);
+}
+
+inline bool EndsWith(const string& str, const string& suffix) {
+  if(suffix.length() > str.length()) {
+    return false;
+  }
+  return 0 == str.compare(str.length() -  suffix.length(), suffix.length(), suffix);
+}
+
+inline bool IsInStr(const string& str, char ch) {
+  return str.find(ch) != string::npos;
+}
+
+inline uint16_t TwocharToUint16(char high, char low) {
+  return (((uint16_t(high) & 0x00ff ) << 8) | (uint16_t(low) & 0x00ff));
+}
+
+template <class Uint16Container>
+bool Utf8ToUnicode(const char * const str, size_t len, Uint16Container& vec) {
+  if(!str) {
+    return false;
+  }
+  char ch1, ch2;
+  uint16_t tmp;
+  vec.clear();
+  for(size_t i = 0; i < len;) {
+    if(!(str[i] & 0x80)) { // 0xxxxxxx
+      vec.push_back(str[i]);
+      i++;
+    } else if ((uint8_t)str[i] <= 0xdf && i + 1 < len) { // 110xxxxxx
+      ch1 = (str[i] >> 2) & 0x07;
+      ch2 = (str[i+1] & 0x3f) | ((str[i] & 0x03) << 6 );
+      tmp = (((uint16_t(ch1) & 0x00ff ) << 8) | (uint16_t(ch2) & 0x00ff));
+      vec.push_back(tmp);
+      i += 2;
+    } else if((uint8_t)str[i] <= 0xef && i + 2 < len) {
+      ch1 = ((uint8_t)str[i] << 4) | ((str[i+1] >> 2) & 0x0f );
+      ch2 = (((uint8_t)str[i+1]<<6) & 0xc0) | (str[i+2] & 0x3f);
+      tmp = (((uint16_t(ch1) & 0x00ff ) << 8) | (uint16_t(ch2) & 0x00ff));
+      vec.push_back(tmp);
+      i += 3;
+    } else {
+      return false;
+    }
+  }
+  return true;
+}
+
+template <class Uint16Container>
+bool Utf8ToUnicode(const string& str, Uint16Container& vec) {
+  return Utf8ToUnicode(str.c_str(), str.size(), vec);
+}
+
+template <class Uint32Container>
+bool Utf8ToUnicode32(const string& str, Uint32Container& vec) {
+  uint32_t tmp;
+  vec.clear();
+  for(size_t i = 0; i < str.size();) {
+    if(!(str[i] & 0x80)) { // 0xxxxxxx
+      // 7bit, total 7bit
+      tmp = (uint8_t)(str[i]) & 0x7f;
+      i++;
+    } else if ((uint8_t)str[i] <= 0xdf && i + 1 < str.size()) { // 110xxxxxx
+      // 5bit, total 5bit
+      tmp = (uint8_t)(str[i]) & 0x1f;
+
+      // 6bit, total 11bit
+      tmp <<= 6;
+      tmp |= (uint8_t)(str[i+1]) & 0x3f;
+      i += 2;
+    } else if((uint8_t)str[i] <= 0xef && i + 2 < str.size()) { // 1110xxxxxx
+      // 4bit, total 4bit
+      tmp = (uint8_t)(str[i]) & 0x0f;
+
+      // 6bit, total 10bit
+      tmp <<= 6;
+      tmp |= (uint8_t)(str[i+1]) & 0x3f;
+
+      // 6bit, total 16bit
+      tmp <<= 6;
+      tmp |= (uint8_t)(str[i+2]) & 0x3f;
+
+      i += 3;
+    } else if((uint8_t)str[i] <= 0xf7 && i + 3 < str.size()) { // 11110xxxx
+      // 3bit, total 3bit
+      tmp = (uint8_t)(str[i]) & 0x07;
+
+      // 6bit, total 9bit
+      tmp <<= 6;
+      tmp |= (uint8_t)(str[i+1]) & 0x3f;
+
+      // 6bit, total 15bit
+      tmp <<= 6;
+      tmp |= (uint8_t)(str[i+2]) & 0x3f;
+
+      // 6bit, total 21bit
+      tmp <<= 6;
+      tmp |= (uint8_t)(str[i+3]) & 0x3f;
+
+      i += 4;
+    } else {
+      return false;
+    }
+    vec.push_back(tmp);
+  }
+  return true;
+}
+
+template <class Uint32ContainerConIter>
+void Unicode32ToUtf8(Uint32ContainerConIter begin, Uint32ContainerConIter end, string& res) {
+  res.clear();
+  uint32_t ui;
+  while(begin != end) {
+    ui = *begin;
+    if(ui <= 0x7f) {
+      res += char(ui);
+    } else if(ui <= 0x7ff) {
+      res += char(((ui >> 6) & 0x1f) | 0xc0);
+      res += char((ui & 0x3f) | 0x80);
+    } else if(ui <= 0xffff) {
+      res += char(((ui >> 12) & 0x0f) | 0xe0);
+      res += char(((ui >> 6) & 0x3f) | 0x80);
+      res += char((ui & 0x3f) | 0x80);
+    } else {
+      res += char(((ui >> 18) & 0x03) | 0xf0);
+      res += char(((ui >> 12) & 0x3f) | 0x80);
+      res += char(((ui >> 6) & 0x3f) | 0x80);
+      res += char((ui & 0x3f) | 0x80);
+    }
+    begin ++;
+  }
+}
+
+template <class Uint16ContainerConIter>
+void UnicodeToUtf8(Uint16ContainerConIter begin, Uint16ContainerConIter end, string& res) {
+  res.clear();
+  uint16_t ui;
+  while(begin != end) {
+    ui = *begin;
+    if(ui <= 0x7f) {
+      res += char(ui);
+    } else if(ui <= 0x7ff) {
+      res += char(((ui>>6) & 0x1f) | 0xc0);
+      res += char((ui & 0x3f) | 0x80);
+    } else {
+      res += char(((ui >> 12) & 0x0f )| 0xe0);
+      res += char(((ui>>6) & 0x3f )| 0x80 );
+      res += char((ui & 0x3f) | 0x80);
+    }
+    begin ++;
+  }
+}
+
+
+template <class Uint16Container>
+bool GBKTrans(const char* const str, size_t len, Uint16Container& vec) {
+  vec.clear();
+  if(!str) {
+    return true;
+  }
+  size_t i = 0;
+  while(i < len) {
+    if(0 == (str[i] & 0x80)) {
+      vec.push_back(uint16_t(str[i]));
+      i++;
+    } else {
+      if(i + 1 < len) { //&& (str[i+1] & 0x80))
+        uint16_t tmp = (((uint16_t(str[i]) & 0x00ff ) << 8) | (uint16_t(str[i+1]) & 0x00ff));
+        vec.push_back(tmp);
+        i += 2;
+      } else {
+        return false;
+      }
+    }
+  }
+  return true;
+}
+
+template <class Uint16Container>
+bool GBKTrans(const string& str, Uint16Container& vec) {
+  return GBKTrans(str.c_str(), str.size(), vec);
+}
+
+template <class Uint16ContainerConIter>
+void GBKTrans(Uint16ContainerConIter begin, Uint16ContainerConIter end, string& res) {
+  res.clear();
+  //pair<char, char> pa;
+  char first, second;
+  while(begin != end) {
+    //pa = uint16ToChar2(*begin);
+    first = ((*begin)>>8) & 0x00ff;
+    second = (*begin) & 0x00ff;
+    if(first & 0x80) {
+      res += first;
+      res += second;
+    } else {
+      res += second;
+    }
+    begin++;
+  }
+}
+
+/*
+ * format example: "%Y-%m-%d %H:%M:%S"
+ */
+inline void GetTime(const string& format, string&  timeStr) {
+  time_t timeNow;
+  time(&timeNow);
+
+  struct tm tmNow;
+
+  #if defined(_WIN32) || defined(_WIN64)
+  errno_t e = localtime_s(&tmNow, &timeNow);
+  assert(e == 0);
+  #else
+  struct tm * tm_tmp = localtime_r(&timeNow, &tmNow);
+  assert(tm_tmp != nullptr);
+  #endif
+
+  timeStr.resize(64);
+  
+  size_t len = strftime((char*)timeStr.c_str(), timeStr.size(), format.c_str(), &tmNow);
+  
+  timeStr.resize(len);
+}
+
+inline string PathJoin(const string& path1, const string& path2) {
+  if(EndsWith(path1, "/")) {
+    return path1 + path2;
+  }
+  return path1 + "/" + path2;
+}
+
+}
+#endif

package/cpp/cppjieba/dict/README.md

@@ -0,0 +1,62 @@
+# CppJieba字典
+
+文件后缀名代表的是词典的编码方式。
+比如filename.utf8 是 utf8编码，filename.gbk 是 gbk编码方式。
+
+
+## 分词
+
+### jieba.dict.utf8/gbk
+
+作为最大概率法(MPSegment: Max Probability)分词所使用的词典。
+
+格式固定为:
+
+```text
+词语 词频 词性
+```
+
+- 每行必须正好三列。
+- `词频` 读取后会换算成对数权重。
+- `词性` 以字符串形式保存在词典节点中，库本身不做枚举校验。
+
+### hmm_model.utf8/gbk
+
+作为隐式马尔科夫模型(HMMSegment: Hidden Markov Model)分词所使用的词典。
+
+__对于MixSegment(混合MPSegment和HMMSegment两者)则同时使用以上两个词典__
+
+### user.dict.utf8
+
+用户词典示例。
+
+支持以下三种行格式:
+
+```text
+词语
+词语 词性
+词语 词频 词性
+```
+
+- `1` 列表示只指定词语，使用默认权重，词性为空。
+- `2` 列表示 `词语 词性`。
+- `3` 列表示 `词语 词频 词性`。
+- 可以通过 `|` 或 `;` 传入多个用户词典文件路径。
+- 不支持注释语法、额外列或带空格的词语字段。
+
+当前默认权重来自主词典统计值，默认使用中位数权重；也可以在
+`cppjieba::DictTrie` 构造时通过 `WordWeightMin`、`WordWeightMedian`、
+`WordWeightMax` 调整策略。
+
+
+## 关键词抽取
+
+### idf.utf8
+
+IDF(Inverse Document Frequency)
+在KeywordExtractor中，使用的是经典的TF-IDF算法，所以需要这么一个词典提供IDF信息。
+
+### stop_words.utf8
+
+停用词词典
+