#include "String.h"
#include "trace_worker.h"
#include <string>
#include<vector>
#include <typeinfo>

String::String(std::string &str)
:m_string(str)
{
    m_isUtf8 = IsUTF8(m_string.c_str(), m_string.size()); 
}

bool String::IsZhCh(char p)
{
    /*汉字的两个字节的最高为都为1*/
    if((p & 0x80) != 0)
    {
        return true;
    }
    
    return false;
}

bool String::IsUTF8(const void* pBuffer, long size)  
{  
    bool IsUTF8 = true;  
    unsigned char* start = (unsigned char*)pBuffer;  
    unsigned char* end = (unsigned char*)pBuffer + size;  
    while (start < end)  
    {  
        if (*start < 0x80) // (10000000): 值小于0x80的为ASCII字符  
        {  
            start++;  
        }  
        else if (*start < (0xC0)) // (11000000): 值介于0x80与0xC0之间的为无效UTF-8字符  
        {  
            IsUTF8 = false;  
            break;  
        }  
        else if (*start < (0xE0)) // (11100000): 此范围内为2字节UTF-8字符  
        {  
            if (start >= end - 1)   
                break;  
            if ((start[1] & (0xC0)) != 0x80)  
            {  
                IsUTF8 = false;  
                break;  
            }  
            start += 2;  
        }   
        else if (*start < (0xF0)) // (11110000): 此范围内为3字节UTF-8字符  
        {  
            if (start >= end - 2)   
                break;  
            if ((start[1] & (0xC0)) != 0x80 || (start[2] & (0xC0)) != 0x80)  
            {  
                IsUTF8 = false;  
                break;  
            }  
            start += 3;  
        }   
        else  
        {  
            IsUTF8 = false;  
            break;  
        }  
    }  
    return IsUTF8;  
}  


std::string String::Sub(int start, int end)
{   trace_worker();
    trace_printf("start, end  %d  %d", start, end);
    if (m_string.length() <= 0)
    {
        return "";
    }

    int len = m_string.length();

    std::string tmp = "";

    //先把str里的汉字和英文分开
    int zhChLen = m_isUtf8 ? 3 : 2;
    trace_printf("zhChLen %d", zhChLen);
    
    std::vector <std::string> dump;
    int i = 0;
    trace_printf("m_string.c_str()  %s", m_string.c_str());
    while(i < len)
    {
        if (IsZhCh(m_string.at(i)))
        {
            dump.push_back(m_string.substr(i, zhChLen));
            i = i + zhChLen;

        }
        else
        {
            dump.push_back(m_string.substr(i, 1));
            i = i + 1;
        }
    }
    trace_printf("NULL");
    if (end < 0 || end > (int)dump.size())
    {
        end = dump.size();
    }
    
    if(start < 0 || start > end)
    {   trace_printf("NULL");
        printf("start is wrong");
        return "";
    }

    trace_printf("start, end, dump.size()  %d  %d  %d", start, end, dump.size());
    for(int i=start; i<end; i++)
    {
        tmp += dump[i];
    }
    trace_printf("tmp.c_str()  %s", tmp.c_str());
    return tmp;
}

std::vector<std::string> &String::GetWords()
{   trace_worker();
    if (m_words.size() > 0)
    {
        return m_words;
    }
    int wordStartPos = -1;
    int wordEndPos = -1;
    trace_printf("m_string.c_str()  %s", m_string.c_str());
    for (unsigned int i=0; i<m_string.size(); ++i)
    {
        if (wordStartPos == -1 && m_string[i] != ' ')
        {
            wordStartPos = i;
            wordEndPos = i;
        }
        
        if (wordStartPos != -1)
        {
            if (m_string[i] != ' ')
            {
                ++wordEndPos;
            }
            else
            {
                m_words.push_back(m_string.substr(wordStartPos, wordEndPos - wordStartPos));
                wordStartPos = wordEndPos = -1;
            } 
        }
    }

    if (wordStartPos != -1 && wordStartPos < wordEndPos)
    {
        m_words.push_back(m_string.substr(wordStartPos, wordEndPos - wordStartPos));
    }
    
    for (unsigned int i=0; i<m_words.size(); ++i)
    {
        trace_printf("m_words[i].c_str()  |%s|", m_words[i].c_str());
    }
    return m_words;
}

void String::CleanRN()
{    
    int strLen = m_string.size() + 1;
    char *strBuffer = (char *)malloc(strLen);

    int dstStrLen = 0;
    for (int i=0; i<strLen; ++i)
    {
        if (m_string[i] != '\r' && m_string[i] != '\n')
        {
            strBuffer[dstStrLen++] = m_string[i];
        }
    }
    strBuffer[dstStrLen] = '\0';
    m_string = strBuffer;
    free(strBuffer);
    
    m_words.clear();
}