开源字符处理类库：CharString类 拆分自自己研发的web服务器中的类库
Posted 17岁boy想当攻城狮
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了开源字符处理类库：CharString类 拆分自自己研发的web服务器中的类库相关的知识，希望对你有一定的参考价值。
博主目前在做WEB服务器，众所周知WEB服务器最主要的是解析HTTP协议，其中最关键的是字符解析，也就是分割字符来确定每个字段所表达的意思，客户端的意愿！
此类是博主在编写WEB服务器所写出来的，专门用于处理字符串，当然也可以用在其它地方，比如用它来写一个解析json字符串的功能也是绰绰有余！
CharString类：
//未公开的库，字符进制转换
#include <Shlwapi.h>
#pragma comment(lib, "shlwapi.lib")
#include <malloc.h>
#pragma warning(disable:4996) //降低编译器安全警告，使用标准C库一些库函数
//字符类
//宏定义
#define CHARSTRING_FRONT 0x00 //前
#define CHARSTRING_AFTER 0x01 //后
class CharString {
public:
//构造
CharString() :m_str(NULL), m_size(0) {}
CharString(const char* str) {
if (m_str != NULL || str == NULL) {
Relete();
}
int strSize = strlen(str);
m_str = (char*)malloc(strSize + 1); //\\0
memset(m_str, 0, strSize + 1);
strcpy(m_str, str);
GetStrSize();
}
CharString(char* str) {
if (str == NULL){
return;
}
if (m_str != NULL) {
Relete();
}
int strSize = strlen(str);
m_str = (char*)malloc(strSize + 1); //\\0
memset(m_str, 0, strSize + 1);
strcpy(m_str, str);
GetStrSize();
}
//返回索引指定数据
char *GetNumStr(int Num) {
if (Num > GetStrSize()){
return NULL;
}
char *str = (char*)malloc(Num + 1);
strncpy(str, m_str, Num);
return str;
}
//返回索引数据
char GetNumChar(int Num) {
if (Num > GetStrSize()||Num<=0){
return NULL;
}
return m_str[Num-1];
}
//return十六进制或十进制，看字符里是什么
int StrInToHex() {
int Hex = 0;
StrToIntEx(m_str, STIF_SUPPORT_HEX, &Hex);
return Hex;
}
//重载
int StrInToHex(const char* Str) {
int Hex = 0;
StrToIntEx(Str, STIF_SUPPORT_HEX, &Hex);
return Hex;
}
//重载
int StrInToHex(char* Str) {
int Hex = 0;
StrToIntEx(Str, STIF_SUPPORT_HEX, &Hex);
return Hex;
}
//字符到数字
template <typename T>
int ReturnIntToDouble(T Type){
if (m_str == NULL){
return 0;
}
//int
if (typeid(Type) == typeid(int)) {
return atoi(m_str);
}
//double
if (typeid(Type) == typeid(double) || typeid(Type) == typeid(float)) {
return atof(m_str);
}
}
template <typename T>
int ReturnIntToDouble(char* str,T Type){
if (str == NULL){
return 0;
}
//int
if (typeid(Type) == typeid(int)) {
return atoi(str);
}
//double
if (typeid(Type) == typeid(double) || typeid(Type) == typeid(float)) {
return atof(str);
}
}
//删除指定字符后的字符
void Delete_Appoint_Str_After(char str, int Method = CHARSTRING_FRONT/*从哪开始,0前，1后*/, BOOL Retain = FALSE/*是否保留原字符*/) {
if (str == NULL) {
return;
}
if (m_str == NULL) {
return;
}
if (Method == CHARSTRING_FRONT) {
for (int i = 0;; ++i) {
if (str == m_str[i]/*指针偏移递增*/) {
char *copy_str = NULL;
int copy_num = 0; //copy num
if (Retain == TRUE) {
copy_num = i;
i = i + 2;
copy_num = copy_num + 1;
}
else {
copy_num = i;
i = i + 1;
}
copy_str = (char*)malloc(i);//\\0和原字符
memset(copy_str, 0, i);
strncpy(copy_str, m_str, copy_num);
Relete();
m_str = (char*)malloc(i);
memset(m_str, 0, i);
strcpy(m_str, copy_str);
m_strfree(copy_str);
break;
}
}
}
if (Method == CHARSTRING_AFTER) {
int i = GetStrSize();
for (;; --i) {
if (str == m_str[i]/*指针偏移递增*/) {
char *copy_str = NULL;
int copy_num = 0; //copy num
if (Retain == TRUE) {
copy_num = i;
i = i + 2;
copy_num = copy_num + 1;
}
else {
copy_num = i;
i = i + 1;
}
copy_str = (char*)malloc(i);//\\0和原字符
memset(copy_str, 0, i);
strncpy(copy_str, m_str, copy_num);
Relete();
m_str = (char*)malloc(i);
memset(m_str, 0, i);
strcpy(m_str, copy_str);
m_strfree(copy_str);
break;
}
}
}
GetStrSize();
}
//删除指定字符前的字符
void Delete_Appoint_Str_Front(char str, int Method = CHARSTRING_FRONT/*从哪开始,0前，1后*/, BOOL Retain = FALSE/*是否保留原字符*/) {
if (str == NULL) {
return;
}
if (m_str == NULL) {
return;
}
if (Method == CHARSTRING_FRONT) {
for (int i = 0;; ++i) {
if (str == m_str[i]/*指针偏移递增*/) {
char *copy_str = NULL;
int copy_num = 0; //copy num
if (Retain == TRUE) {
i = i + 2;
copy_num = copy_num + 1;
}
else {
i = i + 1;
}
copy_str = (char*)malloc(i);//\\0和原字符
memset(copy_str, 0, i);
strncpy(copy_str, m_str, i);
Relete();
m_str = (char*)malloc(i);
memset(m_str, 0, i);
strcpy(m_str, copy_str);
m_strfree(copy_str);
break;
}
}
}
if (Method == CHARSTRING_AFTER) {
int i = GetStrSize();
for (;; --i) {
if (str == m_str[i]/*指针偏移递增*/) {
char *copy_str = NULL;
int copy_num = 0; //copy num
if (Retain == TRUE) {
i = i + 2;
copy_num = copy_num + 1;
}
else {
i = i + 1;
}
copy_str = (char*)malloc(i);//\\0和原字符
memset(copy_str, 0, i);
strncpy(copy_str, m_str, i);
Relete();
m_str = (char*)malloc(i);
memset(m_str, 0, i);
strcpy(m_str, copy_str);
m_strfree(copy_str);
break;
}
}
}
GetStrSize();
}
void Relete() {
if (m_str != NULL) {
free(m_str);
m_str = NULL;
m_size = 0;
}
}
//printf
void Print_Cmd() {
if (m_str == NULL) {
return;
}
char str = 0;
for (int i = 0; m_str[i] != '\\0'; ++i) {
printf("%c", m_str[i]);
}
}
//获取字符串大小
signed long long int GetStrSize() {
if (m_str == NULL) {
return 0;
}
for (m_size = 0; m_str[m_size] != '\\0'; ++m_size) {}
return m_size;
}
//获取指定char类型字符大小
signed long long int GetCharSize(const char *str) {
signed long long int i = 0;
if (str == NULL) {
return 0;
}
for (i = 0; str[i] != '\\0'; ++i) {}
return i;
}
//压入字符
void Input(const char *str) {
if (m_str != NULL) {
Relete();
}
//Relete();
if (str == NULL) {
return;
}
signed long long int i = 0;
for (; str[i] != '\\0'; ++i) {}
m_str = (char*)malloc(i + 1);
memset(m_str, 0, i + 1);
strcpy(m_str, str);
GetStrSize();
}
//字符拼接
void Splicing(const char *str) {
if (str == NULL) {
return;
}
if (m_str != NULL) {
//保存原字符
char *copy_str = NULL;
GetStrSize();
copy_str = (char*)malloc(m_size + 1);//\\0
memset(copy_str, 0, m_size + 1);
strcpy(copy_str, m_str);
int L_Size = m_size;
Relete();
//获取字符串大小
signed long long int i = GetCharSize(str);
m_strmalloc(L_Size + i + 1); //\\0
memset(m_str, 0, L_Size + i + 1);
strcpy(m_str, copy_str);
//防止立即数copy之前将值复制一份
char *copy_str_1 = (char*)malloc(i + 1);
strcpy(copy_str_1, str);
strcat(m_str, copy_str_1);
GetStrSize();
m_strfree(copy_str_1);
m_strfree(copy_str);
}
}
//返回data
char *GetData() {
if (m_str == NULL) {
return NULL;
}
return m_str;
}
//判断指定的两个字符串是否相同
//相同返回0，不相同返回非0
int Char_Two_Identical(const char* str1, const char*str2) {
int num1 = GetCharSize(str1);
int num2 = GetCharSize(str2);
if (num1 != num2) {
return 1;
}
for (int i = 0; i <= num1; ++i) {
if (str1[i] != str2[i]) {
return 1;
}
}
return 0;
}
//字符串裁剪
int TailoringIndexToIndex(int A, int B) {
if (m_str == NULL) {
return -1;
}
if (strlen(m_str) > B) {
return -2;
}
//定位A
int size = 0;
for (int i = 0; i <= B - 1; ++i) {
if (i >= A) {
size++;
}
}
char *str1 = (char*)malloc(size + 1);
memset(str1, 0, size + 1);
int u = 0;
for (int i = 0; i <= B - 1; ++i) {
if (i >= A) {
str1[u++] = m_str[i];
}
}
//裁剪
free(m_str);
m_str = NULL;
m_str = (char*)malloc(size + 1);
memset(m_str, 0, size + 1);
strcpy(m_str, str1);
return 1;
}
//其他类型到字符
template <typename T>
void Format_Str(T Format) {
//int
if (typeid(Format) == typeid(int)) {
Relete();
m_strmalloc(sizeof(int));
sprintf(m_str, "%d", Format);
GetStrSize();
return;
}
//double
if (typeid(Format) == typeid(double)) {
Relete();
m_strmalloc(sizeof(double));
sprintf(m_str, "%lf", Format);
GetStrSize();
return;
}
//float
if (typeid(Format) == typeid(float)) {
Relete();
m_strmalloc(sizeof(float));
sprintf(m_str, "%f", Format);
GetStrSize();
return;
}
//char
if (typeid(Format) == typeid(char)) {
Relete();
m_strmalloc(sizeof(char)+1); //\\0
sprintf(m_str, "%c", Format);
GetStrSize();
return;
}
}
//获取copy的文本可以做局部变量返回
char *GetReturnStr() {
if (m_str == NULL) {
return NULL;
}
int Size = GetStrSize();
char* ReturnStr = (char*)malloc(Size);
if (ReturnStr == NULL) {
return NULL;
}
memset(ReturnStr, 0, Size);
strcpy(ReturnStr, m_str);
return ReturnStr;
}
//获取指定文本索引,穷举法稳定
int GetStrTxTIndx(const char* str){
if (m_str == NULL || str == NULL){
return -1;
}
int StrSize = strlen(str);
if (StrSize <= 0){
return -1;
}
int Str_m_str = GetStrSize();
int m_str_index = 0;/*二次循环坐标*/
int y = 0;
for (int i = 0; i <= Str_m_str -1; i++/*加一是因为i从0开始，下方循环是size+1是为了将坐标移动到下个字符*/){
y = 0;
m_str_index = i;
for (int j = 0; j <= StrSize - 1; ++j, ++m_str_index){
//printf("%d", j);
if (str[j] == m_str[m_str_index]){
y += 1;
}
if (y == StrSize){
return i+1;
}
if (str[j] != m_str[m_str_index]){
break;
}
}
}
return -1;
}
//获取指定文本索引,穷举法稳定
int GetStrTxTIndxRepeat(const char* str,int Repeat = 0/*重复次数*/){
if (m_str == NULL || str == NULL){
return -1;
}
int StrSize = strlen(str);
if (StrSize <= 0){
return -1;
}
int Str_m_str = GetStrSize();
int m_str_index = 0;/*二次循环坐标*/
int y = 0;
int Repeat_i = 0;
for (int i = 0; i <= Str_m_str - 1; i++/*加一是因为i从0开始，下方循环是size+1是为了将坐标移动到下个字符*/){
y = 0;
m_str_index = i;
for (int j = 0; j <= StrSize - 1; ++j, ++m_str_index){
//printf("%d", j);
if (str[j] == m_str[m_str_index]){
y += 1;
}
if (y == StrSize){
if (Repeat_i == Repeat){
return i + 1;
}
else{
Repeat_i++;
}
}
if (str[j] != m_str[m_str_index]){
break;
}
}
}
return -1;
}
//判断文本是否存在
BOOL JumpTxTExits(char *str){
if (GetStrTxTIndx(str) == -1){
return FALSE;
}
return TRUE;
}
//取一行文本
char* GetLineTxT(int LineIndex = 1) {
if (LineIndex == 0){
return NULL;
}
if (m_str == NULL) {
return NULL;
}
int l = 0;
char *yun = NULL;
int j = 0;
int u = 0;
for (int i = 0; i <= GetStrSize()+1/*包含\\0*/; ++i) {
if (m_str[i] == '\\n') {
++l;
if (l != LineIndex)
u = i + 1;//+1跳过\\n 这里递增1后面已经忽略0因为已经不是第一行坐标
}
if (l == LineIndex) {
//判断此行多长用于分配内存
for (j = u;; ++j) {
if (m_str[j] == '\\n' || m_str[j] == '\\0') {
int size = 0;
if (u == 0){//防止从0下标导致计算实际长度少1，因为额外的1要用来\\0
size = j + 1; //+1是因为分配内存不是从0做下标所以需要判断是否为0
}
else{
size = j;
}
yun = (char*)malloc(size + 1); //多分配额外字节,\\0
memset(yun, 0, size + 1);
break;
}
}
int in = 0;
for (int n = u; n <= j; ++n, ++in) {
yun[in] = m_str[n];
}
return yun;
}
}
}
//获取文本多少行
int GetLineNum(){
if (m_str == NULL){
return NULL;
}
int Size = 0;
for (int i = 0; i <= GetStrSize(); ++i){
if (m_str[i] == '\\n'){
++Size;
}
if (m_str[i] == '\\0'){
if (m_str[i - 1] != '\\n'){
Size++;
}
return Size;
}
}
}
//获取文本所在行
int GetTxTLineNum(char *str){
if (str == NULL || m_str == NULL){
return NULL;
}
char *str1 = NULL;
int i = 0;
int u = GetLineNum();
while (1){//查找这个文本格式在第几行里
str1 = GetLineTxT(i);
if (str1 == NULL){
return NULL;
}
if (JumpTxTExits(str1) == TRUE){
break;
}
++i;
if (i > u){
return 0;
}
}
return i;
}
//索引到字符截取
char* IndexToCharCutOut(int Index, char str){
if (Index <= 0 || str == 0 || Index > GetStrSize()){
return NULL;
}
int Is = GetStrSize();
int Size = 1;
for (int i = Index-1; i <= GetStrSize(); ++i){
if (m_str[i] == str){
char* r_str = (char*)malloc(Size+1);
memset(r_str, 0, Size + 1);
if (r_str == NULL){
return NULL;
}
int s = Index - 1;
for (int j = 0;j <= Size-1; ++j,++s){
r_str[j] = m_str[s];
}
return r_str;
}
++Size;
}
return NULL;
}
//两点字符截取
char* CharToCharCutOut(char str1, char str2){
if (str1 <= 0 || str2 == 0){
return NULL;
}
int Is = GetStrSize();
int Size = 0;
for (int i = 0; i <= GetStrSize(); ++i){
if (m_str[i] == str1){
for (int d = i; d <= GetStrSize(); ++d){//计算长度
++Size;
if (m_str[d] == str2){
break;
}
}
char* r_str = (char*)malloc(Size + 1);
memset(r_str, 0, Size + 1);
if (r_str == NULL){
return NULL;
}
int s = i;
for (int j = 0; j <= Size - 1; ++j, ++s){
r_str[j] = m_str[s];
}
return r_str;
}
}
return NULL;
}
//文本替换
int TexTSubstiTution(char *str) {
if (str == NULL || m_str == NULL) {
return NULL;
}
//获取文本索引
int i = GetStrTxTIndx(str);
if (i == 0) {
return 0;
}
//存储前面的字符
char *str_q = (char*)malloc(i + 1);
if (str_q == NULL) {
return NULL;
}
memset(str_q, 0, i + 1);
strncpy(str_q, m_str, i);
//中间字符
i = i + strlen(str) + 1;
char* str_z = (char*)malloc(i);
if (str_z == NULL) {
return NULL;
}
memset(str_z, 0, i);
sprintf(str_z, "%s%s", str_q, str);
//存储后面的字符
int h_size = 0;
for (int j = GetStrTxTIndx(str) + strlen(str) + 1; m_str[j] != '\\0'; ++j) {
++h_size;
}
char *str_h = (char*)malloc(h_size + 1);
if (str_h == NULL) {
return NULL;
}
memset(str_h, 0, h_size + 1);
int u = 0;
for (int j = GetStrTxTIndx(str) + strlen(str) + 1; m_str[j] != '\\0'; ++j, ++u) {
str_h[u] = m_str[j];
}
strcat(str_z, str_h);
free(m_str);
m_str = NULL;
m_str = (char*)malloc(strlen(str_z) + 1);
if (m_str == NULL) {
return NULL;
}
strcpy(m_str, str_h);
return 1;
}
//文本截取
int TxTCutOut(char *str) {
if (str == NULL) {
return 0;
}
//获取文本索引
int i = GetStrTxTIndx(str);
if (i == 0) {
return 0;
}
//保留前文本
char *str_q = (char*)malloc(i + 1);
if (str_q == NULL) {
return NULL;
}
memset(str_q, 0, i + 1);
strncpy(str_q, m_str, i);
//存储后面的字符
int h_size = 0;
for (int j = GetStrTxTIndx(str) + strlen(str) + 1; m_str[j] != '\\0'; ++j) {
++h_size;
}
char *str_h = (char*)malloc(h_size + 1);
if (str_h == NULL) {
return NULL;
}
memset(str_h, 0, h_size + 1);
int u = 0;
for (int j = GetStrTxTIndx(str) + strlen(str) + 1; m_str[j] != '\\0'; ++j, ++u) {
str_h[u] = m_str[j];
}
strcat(str_q, str_h);
if (m_str != NULL) {
free(m_str);
m_str = NULL;
}
m_str = (char*)malloc((GetStrSize() - strlen(str)) + 1);
strcpy(m_str, str_q);
return 1;
}
//裁剪段落如sjcy会删除sjcy字符
int CutOutChar(char *str) {
if (str == NULL || m_str == NULL) {
return 0;
}
char* Zw = (char*)malloc(strlen(str) + 1);
if (Zw == NULL) {
return NULL;
}
memset(Zw, 0, strlen(str) + 1);
//解析字符数组
for (int i = 0; i <= strlen(str) - 1; ++i) {
sprintf(Zw, "%c", str[i]);
TxTCutOut(Zw);
memset(Zw, 0, strlen(Zw) + 1);
}
return 1;
}
//索引裁剪
int CutOutIndex(int Index) {
if (Index == 0) {
return 0;
}
if (Index > GetStrSize()) {
return 0;
}
if (m_str == NULL) {
return 0;
}
m_str[Index] = '\\0';
char *s = (char*)malloc(GetStrSize());
if (s == NULL) {
return 0;
}
for (int i = 0; i <= GetStrSize() - 1; ++i) {
if (m_str[i] == '\\0') {
continue;
}
s[i] = m_str[i];
}
free(m_str);
m_str = s;
return 1;
}
//其他类型到字符，从后加入
template <typename T>
void Format_Str_After(T Format) {
if (m_str == NULL) {
return;
}
//int
if (typeid(Format) == typeid(int)) {
GetStrSize();
signed long long int i = m_size + 1; //\\0
//内容copy
char *copy_str = (char*)malloc(i);
memset(copy_str, 0, i);
strcpy(copy_str, m_str);
Relete();//释放
//重新分配内存
m_strmalloc(i + sizeof(int));
sprintf(m_str, "%s%d", copy_str, Format);
GetStrSize();
return;
}
//double
if (typeid(Format) == typeid(double)) {
GetStrSize();
signed long long int i = m_size + 1; //\\0
//内容copy
char *copy_str = (char*)malloc(i);
memset(copy_str, 0, i);
strcpy(copy_str, m_str);
Relete();//释放
//重新分配内存
m_strmalloc(i + sizeof(double));
sprintf(m_str, "%s%lf", copy_str, Format);
GetStrSize();
return;
}
//float
if (typeid(Format) == typeid(float)) {
GetStrSize();
signed long long int i = m_size + 1; //\\0
//内容copy
char *copy_str = (char*)malloc(i);
memset(copy_str, 0, i);
strcpy(copy_str, m_str);
Relete();//释放
//重新分配内存
m_strmalloc(i + sizeof(float));
sprintf(m_str, "%s%f", copy_str, Format);
GetStrSize();
return;
}
//char
if (typeid(Format) == typeid(char)) {
GetStrSize();
signed long long int i = m_size + 1; //\\0
//内容copy
char *copy_str = (char*)malloc(i);
memset(copy_str, 0, i);
strcpy(copy_str, m_str);
Relete();
//重新分配内存
m_strmalloc(i + sizeof(char));
sprintf(m_str, "%s%c", copy_str, Format);
GetStrSize();
return;
}
}
//取右边文本
char* GetRightTxT(int Length = 0){
if (Length == 0){
return 0;
}
if (m_str == NULL){
return 0;
}
char *str = (char*)malloc(Length + 1);
memset(str, 0, Length + 1);
int in = 0;
for (int i = GetStrSize()-1/*去掉\\0*/; i >= (GetStrSize() - Length); --i,++in){
str[in] = m_str[i];
}
return str;
}
//中英文浮点转换字符转换
void CharInToCharAscii(char &cstr){
switch (cstr){
case '：':
cstr = ':';
break;
case '，':
cstr = ',';
break;
default:
break;
}
}
//三点解析取文本，使用方法：例如文本是 txt:1,2,3,4\\r\\n 使用方法：AnalysisTxTtoArr(':',',','\\r',x) 每次会根据x索引返回'1''2''3'
char* ThreePoints_AnalysisTxTtoArr(char str1/*第一个char*/, char str2/*中间char*/, char str3/*结尾char*/, int Index/*索引*/){
if (m_str == NULL){
return 0;
}
if (str1 == str2 || str2 == str3){
return NULL;
}
CharInToCharAscii(str1);
CharInToCharAscii(str2);
CharInToCharAscii(str3);
int uIndex = 0;//索引
int c_size = 0;//大小从str1开始计算得到双倍字符防止小
int iis = 0; //定位上一次str2的坐标
int yuno = 0; //上一个结尾字符
for (int i = 0; i <= GetStrSize(); ++i){
if (m_str[i] == str1){
for (int j = i;j<=GetStrSize(); ++j){
if (m_str[j] == str2){
yuno = j;
++uIndex;
}
++c_size;
if (uIndex == Index){
if (Index != 1){
iis = j - 1;
}
else{
iis = i + 1;
}
char* str = (char*)malloc(c_size+1);
memset(str, 0, c_size + 1);
int y = 0;
for (int u = iis; u <= GetStrSize(); ++u, ++y){
if (m_str[u] == str2){
char *i_str = NULL;
i_str = (char*)malloc(strlen(str) + 1);
memset(i_str, 0, strlen(str) + 1);
strcpy(i_str, str);
free(str);
str = NULL;
return i_str;
}
str[y] = m_str[u];
}
}
else{
if (Index == 1){
iis = i + 1;
}
}
}
// return NULL;
}
if (m_str[i] == str3){
//先看看上一个分隔符是不是一样的
int usize = 0;
int y = 0;
if (m_str[yuno] == str2){
for (int i = yuno; i <= GetStrSize(); ++i){
++usize;
}
char *i_str = NULL;
i_str = (char*)malloc(usize + 1);
memset(i_str, 0, usize + 1);
for (int i = yuno+1; i <= GetStrSize(); ++i,++y){
if (m_str[i] == str3){
return i_str;
}
i_str[y] = m_str[i];
}
}
return NULL;
}
}
}
//三点解析取文本，获取格式大小
int ThreePoints_AnalysisGetTxTtoArrNum(char str1/*第一个char*/, char str2/*中间char*/, char str3/*结尾char*/){
if (m_str == NULL){
return 0;
}
if (str1 == str2 || str2 == str3){
return NULL;
}
CharInToCharAscii(str1);
CharInToCharAscii(str2);
CharInToCharAscii(str3);
int u = 0;
for (int i = 0; i <= GetStrSize(); ++i){
if (m_str[i] == str2){
++u;
}
if (m_str[i] == str3){
return u+1;
}
}
}
~CharString() {
Relete();
}
char *m_str;
signed long long int m_size;
//运算符重载
CharString & operator = (const char * str) {
Input(str);
return *this;
}
//运算符重载
CharString & operator = (const char str) {
Relete();
m_strmalloc(sizeof(char)+1); //\\0
sprintf(m_str, "%c", str);
return *this;
}
//+
CharString & operator + (const char *str) {
Splicing(str);
return *this;
}
//-
CharString & operator - (char *str) {
TxTCutOut(str);
return *this;
}
//[]
char & operator [] (int i) {
return m_str[i];
}
//%获取行
char * operator % (int i) {
return GetLineTxT(i);
}
//==
BOOL operator == (const char *str) {
if (0 == strcmp(m_str, str)) {
return TRUE;
}
else {
return FALSE;
}
}
//()
CharString & operator () (const char *str) {
Relete();
Input(str);
return *this;
}
CharString & operator () (char *str) {
Relete();
Input(str);
return *this;
}
private:
//内存分配
void m_strmalloc(signed long long int size) {
m_str = (char*)malloc(size);
memset(m_str, 0, size);
}
//内存释放
void m_strfree(char *str) {
free(str);
str = NULL;
}
};备注：此类可移植性高，代码不难，此类实现纯POIX C/C++实现 开发环境：vs2015，如要移植到其他开发平台请去掉#pragma warning(disable:4996) //降低编译器安全警告，使用标准C库一些库函数
以下是使用此类实现的解析一个http报文的功能（不包括权重分析）
解析HTTP结构体
//解析HTTP报文
struct Http_Format{
char Method[256]; //请求方法
char Data[1024]; // 请求数据
char Browser_Kernel[256];//请求的浏览器内核
int Browser_Kernel_Edition; //请求浏览器内核版本
char Support_File_Type[12][256];//请求方支持的文件类型
char Support_File_Type_Num = 0; //支持文件类型多少个
char Support_Encoding_Format[12][256]; //编码格式
char Support_Encoding_Format_Num = 0; //编码格式多少个
char Language[256]; //支持的语言
int Connection_Situation;//请求连接方法，0短连接，1长连接
double Http_Edition; //http连接版本
char Cookie_Data[256]; //Cookie数据
int Windows_NT_Edition;//系统版本
int Windows_NT_Bit; //系统位数
char HOST[256]; //请求的HOST
char ConnectMode[256];//连接方式
BOOL Statie = FALSE; //解析状态
};实现函数：
//解析http报文
Http_Format HttpFormat_Analysis(char* Http_Data){
struct Http_Format ht;
if (Http_Data == NULL){
return ht;
}
char sd[1024] = { 0 };
strcpy(sd, "GET /proct HTTP/1.1\\r\\nAccept：text/html,application/xhtml+html,image/jxr,*/*\\r\\nAccept-Language：zh-cn\\r\\nUser-Agent：Mozilla/5.0（Windows NT 10.0；Win64；x64）AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1\\r\\n"\\
"Accept-Encoding:gzip,deflate\\r\\nHOST：127.0.0.1:8080\\r\\nConnection：Keep Alive\\r\\n");
//获取方法数据http版本
if (1 != HttpFormatA(&ht, sd)){
ht.Statie = FALSE;
return ht;
}
//获取客户端支持的文本类型
if (1 != HttpFormat_Accept(&ht, sd)){
ht.Statie = FALSE;
return ht;
}
//获取浏览器支持的语言
if (1 != HttpFormat_Accept_Language(&ht, sd)){
ht.Statie = FALSE;
return ht;
}
//获取客户端信息
if (1 != HttpFormat_User_Agent(&ht, sd)){
ht.Statie = FALSE;
return ht;
}
//获取压缩格式
if (1 != HttpFormat_Accept_Encoding(&ht, sd)){
ht.Statie = FALSE;
return ht;
}
//获取HOST地址
if (1 != HttpFormat_HOST(&ht, sd)){
ht.Statie = FALSE;
return ht;
}
//解析TCP检测机制
if (1 != HttpFormat_Connection(&ht, sd)){
ht.Statie = FALSE;
return ht;
}
//解析Cookie
if (1 != HttpFormat_Cookie(&ht, sd)){
ht.Statie = FALSE;
return ht;
}
return ht;
}
//http报文格式打印
void HttpFormat_print(Http_Format ht){
/*打印解析的http报文*/
printf("客户端HTTP报文解析内容：\\n");
printf("方法：%s\\n数据：%s\\nHTTP版本:%0.1f\\n", ht.Method, ht.Data, ht.Http_Edition);
if (ht.Http_Edition == 1.1f){
printf("连接方式：长连接\\n");
}
else{
printf("连接方式：短连接\\n");
}
printf("支持的文本类型：");
for (int i = 0; i <= ht.Support_File_Type_Num - 1; ++i){
if (i == ht.Support_File_Type_Num - 1){
printf("%s", ht.Support_File_Type[i]);
break;
}
printf("%s,", ht.Support_File_Type[i]);
}
printf("\\n");
printf("支持的语言：%s\\n", ht.Language);
printf("系统版本：Win%dx%d\\n", ht.Windows_NT_Edition, ht.Windows_NT_Bit);
printf("浏览器内核：%s v%d\\n", ht.Browser_Kernel, ht.Browser_Kernel_Edition);
printf("压缩格式：");
for (int i = 0; i <= ht.Support_Encoding_Format_Num - 1; ++i){
if (i == ht.Support_Encoding_Format_Num - 1){
printf("%s", ht.Support_Encoding_Format[i]);
break;
}
printf("%s,", ht.Support_Encoding_Format[i]);
}
printf("\\n");
printf("HOST地址：%s\\n", ht.HOST);
printf("检测机制：%s\\n", ht.ConnectMode);
if (strlen(ht.Cookie_Data) < 1){
printf("Cookie数据：空\\n");
}
else{
printf("Cookie数据：%s\\n", ht.Cookie_Data);
}
}备注：解析函数里的参数被显示指定，如果需要接口调用请将更改参数代码
代码示例：
客户端发来的报文：
GET /proct HTTP/1.1\\r\\nAccept：text/html,application/xhtml+html,image/jxr,*/*\\r\\nAccept-Language：zh-cn\\r\\nUser-Agent：Mozilla/5.0（Windows NT 10.0；Win64；x64）AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1\\r\\n"\\
"Accept-Encoding:gzip,deflate\\r\\nHOST：127.0.0.1:8080\\r\\nConnection：Keep Alive\\r\\n
Http_Format hp = HttpFormat_Analysis("GET /proct HTTP/1.1\\r\\nAccept：text/html,application/xhtml+html,image/jxr,*/*\\r\\nAccept-Language：zh-cn\\r\\nUser-Agent：Mozilla/5.0（Windows NT 10.0；Win64；x64）AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1\\r\\n"\\
"Accept-Encoding:gzip,deflate\\r\\nHOST：127.0.0.1:8080\\r\\nConnection：Keep Alive\\r\\n");
HttpFormat_print(hp);运行结果：
以上是关于开源字符处理类库：CharString类 拆分自自己研发的web服务器中的类库的主要内容，如果未能解决你的问题，请参考以下文章
C# .NET 使用DotNetZip开源类库 处理 压缩/解压 Zip 处理乱码情况
别再重复造轮子了，推荐使用 Google Guava 开源工具类库，真心强大！