ukui-search/libchinese-segmentation/cppjieba/limonp/StringUtil.hpp

/*
 * The MIT License (MIT)
 *
 * Copyright (C) 2013 Yanyi Wu
 * Copyright (C) 2023, KylinSoft Co., Ltd.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be
 * included in all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
 * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 * OTHER DEALINGS IN THE SOFTWARE.
 *
*/
/************************************
 * file enc : ascii
 * author   : wuyanyi09@gmail.com
 ************************************/
#ifndef LIMONP_STR_FUNCTS_H
#define LIMONP_STR_FUNCTS_H
#include <stdint.h>
#include <stdio.h>
#include <stdarg.h>
#include <memory.h>
#include <sys/types.h>
#include <fstream>
#include <iostream>
#include <string>
#include <vector>
#include <algorithm>
#include <cctype>
#include <map>
#include <functional>
#include <locale>
#include <sstream>
#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);
}

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))));
  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());
  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(), std::not1(std::bind2nd(std::equal_to<char>(), 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());
  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 char * str, size_t size, Uint32Container& vec) {
  uint32_t tmp;
  vec.clear();
  for(size_t i = 0; i < 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 < 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 < 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 < 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 Uint32Container>
bool Utf8ToUnicode32(const string& str, Uint32Container& vec) {
    return Utf8ToUnicode32(str.data(), str.size(), vec);
}

inline int UnicodeToUtf8Bytes(uint32_t ui){
    if(ui <= 0x7f) {
        return 1;
    } else if(ui <= 0x7ff) {
        return 2;
    } else if(ui <= 0xffff) {
        return 3;
    } else {
        return 4;
    }
}

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);
//   timeStr.resize(64);
//   size_t len = strftime((char*)timeStr.c_str(), timeStr.size(), format.c_str(), localtime(&timeNow));
//   timeStr.resize(len);
// }

inline string PathJoin(const string& path1, const string& path2) {
  if(EndsWith(path1, "/")) {
    return path1 + path2;
  }
  return path1 + "/" + path2;
}

}
#endif