用思维导图和实例学习C++之一——字符串处理

用思维导图和实例学习C++之一——字符串处理 收藏 此文于2010-05-17被推荐到CSDN首页



原帖地址： http://blog.csdn.net/gnuhpc/archive/2010/05/17/5599102.aspx

如何被推荐？
1.本章思维导图：







Example1:
char *strcpy(char *target, const char *source) {
char *t = target;
// Copy the contents of source into target.
while(*source) *target++ = *source++;
// Null-terminate the target.
*target = '/0';
// Return pointer to the start of target.
return t;
}

Example2:
void *memmove(void *target, const void *source, size_t count)
这个函数即使是在源和目的字符串有所重叠时操作也能成功，虽然source为const，但是其指向的array也可能被修改。

2. C型字符串操作实例：

Ex1.基本操作

/*
* =====================================================================================
*
* Filename: 2-1.cpp
*
* Description: Fundamental Operations in C Type String
*
* Version: 1.0
* Created: 05/11/2010 10:43:11 AM
* Revision: none
* Compiler: gcc
*
* Author: gnuhpc (http://blog.csdn.net/gnuhpc), warmbupt@gmail.com
* Company: IBM CDL
*
* =====================================================================================
*/
#include
#include

using namespace std;

int main(int argc, char *argv[])
{
char strA[7]="UP";
char strB[5]="DOWN";
char strC[5]="LEFT";
char strD[6]="RIGHT";

/*Display */
cout << "Here are the strings: " << endl;
cout << "strA: " << strA << endl;
cout << "strB: " << strB << endl;
cout << "strC: " << strC << endl;
cout << "strD: " << strD << "/n/n";

//Display the length of strA.
cout << "Length of strA is " << strlen(strA) << endl;
cout << "Size of strA is " << sizeof(strA) << endl;
//Concatenate strB with strA
cout << "The result of Concatenate is strA::" <

//Copy strC into strB,and partially strD into strA
cout << "The result of Copy is:" < cout << "The result of partially Copy is strA:" <

//Compare strC with strB
if( !strcmp(strC,strB))
{
cout << "strC is equal to strB!"< }

if( !strncmp(strD,strA,3))
{
cout << "strD is equal to strA partially!"< }

return 0;

}

Ex2.搜索匹配相关操作

/*
* =====================================================================================
*
* Filename: 2-2.cpp
*
* Description: Search Operation in C type String
*
* Version: 1.0
* Created: 05/11/2010 11:38:15 AM
* Revision: none
* Compiler: gcc
*
* Author: gnuhpc (http://blog.csdn.net/gnuhpc), warmbupt@gmail.com
* Company: IBM CDL
*
* =====================================================================================
*/

#include
#include
using namespace std;
int main(void) {
const char *url = "HerbSchildt.com";
const char *url2 = "Apache.org";
const char *emailaddr = "Herb@HerbSchildt.com";
const char *tld[] = { ".com", ".net", ".org" };
const char *p;
// First, determine if url and url2 contain .com, .net, or .org.
for(int i=0; i < 3; i++) {
p = strstr(url, tld[i]);
if(p) cout << url << " has top-level domain " << tld[i] << endl;
p = strstr(url2, tld[i]);
if(p) cout << url2 << " has top-level domain " << tld[i] << endl;
}
// Search for a specific character.
p = strchr(emailaddr, '@');
if(p) cout << "Site name of e-mail address is: " << p+1 << endl;
// Search for any of a set of characters. In this case,
// find the first @ or period.
p = strpbrk(emailaddr, "@.");
if(p) cout << "Found " << *p << endl;

//Search for the beginning
if(strspn(url2,"Apache")==6){
cout<< "Url2 begins with the /"Apache/""<< endl;
}

//与strchr正好倒过来
if(p=strrchr(emailaddr, 'b')){
cout<< p << endl;
}
return 0;
}

Ex3.倒置一个字符串

我们用了四种方法，最后一种方法经常在面试笔试题中出现。

/*
* =====================================================================================
*
* Filename: 2-3.cpp
*
* Description: Reverse a string
*
* Version: 1.0
* Created: 05/12/2010 03:08:09 PM
* Revision: none
* Compiler: gcc
*
* Author: gnuhpc (http://blog.csdn.net/gnuhpc), warmbupt@gmail.com
* Company: IBM CDL
*
* =====================================================================================
*/
#include
#include
using namespace std;
void revstr(char *str);
void revstr_p(char *str);
void revstr_recursive(char *str, int start, int end);
char *(revstrcpy)(char *rstr, const char *orgstr);
int main() {
char str[] = "abcdefghijklmnopqrstuvwxyz";
char *des= new char[27];
cout << "Original string: " << str << endl;
revstr(str);
cout << "Reversed string: " << str << endl;
revstr_p(str);
cout << "Reversed string using pointer: " << str << endl;
revstr_recursive(str,0,strlen(str)-1);
cout << "Reversed string using recursive: " << str << endl;
cout << "Reversed string using copy method: " << revstrcpy(des,str)<< endl;
return 0;
}

void revstr(char *str) {
int i, j;
char t;
for(i = 0, j = strlen(str)-1; i < j; ++i, --j) {
t = str[i];
str[i] = str[j];
str[j] = t;
}
}

// Reverse a string in place. Use pointers rather than array indexing.
void revstr_p(char *str) {
char t;
char *inc_p = str;
char *dec_p = &str[strlen(str)-1];
while(inc_p <= dec_p) {
t = *inc_p;
*inc_p++ = *dec_p;
*dec_p-- = t;
}
}

void revstr_recursive(char *str, int start, int end) {
if(start < end)
revstr_recursive(str, start+1, end-1);
else
return;
char t = str[start];
str[start] = str[end];
str[end] = t;
}

char *(revstrcpy)(char *rstr, const char *orgstr) { //返回rstr的原始值使函数能够支持链式表达式，增加了函数的“附加值”。同样
功能的函数，如果能合理地提高的可用性，自然就更加理想。

if((rstr==NULL)||(orgstr==NULL))
throw "Invalid argument(s)";

char *dst=rstr;
dst += strlen(orgstr);
*dst-- = '/0';
while(*orgstr) *dst-- = *orgstr++;
return rstr;
}

Ex4.忽略大小写的字符串比较

/*
* =====================================================================================
*
* Filename: 2-4.cpp
*
* Description: Ignore the Letter case when compared
*
* Version: 1.0
* Created: 05/12/2010 03:44:34 PM
* Revision: none
* Compiler: gcc
*
* Author: gnuhpc (http://blog.csdn.net/gnuhpc), warmbupt@gmail.com
* Company: IBM CDL
*
* =====================================================================================
*/

#include
#include
using namespace std;
int strcmp_ign_case(const char *str1, const char *str2);
int main(void) {
char strA[]= "tesT";
char strB[] = "Test";
char strC[] = "testing";
char strD[] = "Tea";
int result;
cout << "Here are the strings: " << endl;
cout << "strA: " << strA << endl;
cout << "strB: " << strB << endl;
cout << "strC: " << strC << endl;
cout << "strD: " << strD << "/n/n";
// Compare strings ignoring case.
result = strcmp_ign_case(strA, strB);
result = strcmp_ign_case(strA, strC);
result = strcmp_ign_case(strA, strD);
result = strcmp_ign_case(strD, strA);
return 0;
}
// A simple string comparison function that ignores case differences.
int strcmp_ign_case(const char *str1, const char *str2) {
const char *str1_cp=str1;
const char *str2_cp=str2;
while(*str1_cp && *str2_cp) {
if(tolower(*str1_cp++) != tolower(*str2_cp++))
break;
}
int result=tolower(*str1_cp) - tolower(*str2_cp);
cout << str1 << " is ";
if(!result)
cout << "equal to ";
else if(result < 0)
cout << "less than ";
else
cout << "greater than ";
cout << str2 << endl;
return result;
}

Ex5.搜索替换

/*
* =====================================================================================
*
* Filename: 2-5.cpp
*
* Description: Replace the sub_str with another str
*
* Version: 1.0
* Created: 05/12/2010 04:07:02 PM
* Revision: none
* Compiler: gcc
*
* Author: gnuhpc (http://blog.csdn.net/gnuhpc), warmbupt@gmail.com
* Company: IBM CDL
*
* =====================================================================================
*/

#include
#include
#include
using namespace std;
bool search_and_replace(char *orgstr, int maxlen,
const char *oldsubstr, const char *newsubstr);
char *search_and_replace_alloc(const char *str, const char *oldsubstr,
const char *newsubstr) throw(bad_alloc);
int main(void) {
char str[80] = "alpha beta gamma alpha beta gamma";
char *ptr=NULL;
cout << "Original string: " << str << "/n/n";
cout << "First, replace all instances of alpha with epsilon./n";
// Replace all occurrences of alpha with epsilon.
while(search_and_replace(str, sizeof(str), "alpha", "epsilon"))
cout << "After a replacement: " << str << endl;
cout << "Second, replace one instances of epsilon with alpha ./n";

try {
ptr = search_and_replace_alloc(str, "epsilon", "alpha");
} catch(bad_alloc exc) {
// Take appropriate action here.
}
if(ptr) {
cout << "After a replacement: " << ptr << endl;
delete [] ptr;
}

return 0;
}
bool search_and_replace(char *orgstr, int maxlen,
const char *oldsubstr, const char *newsubstr)
{
char *pos=NULL;
if((orgstr==NULL)||(oldsubstr==NULL)||(newsubstr==NULL))
return false;
int len = strlen(orgstr) - strlen(oldsubstr) + strlen(newsubstr);
if(len > maxlen)
return false;
if(pos=strstr(orgstr,oldsubstr)){
memmove(pos+strlen(newsubstr),pos+strlen(oldsubstr),strlen(pos)-strlen(oldsubstr)+1);
strncpy(pos, newsubstr, strlen(newsubstr));
return true;
}
else{
return false;
}
}

char *search_and_replace_alloc(const char *str, const char *oldsubstr,
const char *newsubstr) throw(bad_alloc) {
const char *pos=NULL;
if((str==NULL)||(oldsubstr==NULL)||(newsubstr==NULL))
return NULL;
int size = strlen(str) + strlen(newsubstr) - strlen(oldsubstr) + 1;
char *result = new char[size];
if(pos=strstr(str,oldsubstr)){
strncpy(result, str, pos-str);
*(result+(pos-str)) = '/0';
strcat(result, newsubstr);
strcat(result, pos+strlen(oldsubstr));
cout< return result;
}
else {
delete [] result;
return NULL;
}
}

Ex6.文本统计

/*
* =====================================================================================
*
* Filename: 2-6.cpp
*
* Description: Text statistics Function
*
* Version: 1.0
* Created: 05/13/2010 02:37:34 PM
* Revision: none
* Compiler: gcc
*
* Author: gnuhpc (http://blog.csdn.net/gnuhpc), warmbupt@gmail.com
* Company: IBM CDL
*
* =====================================================================================
*/

#include
#include
using namespace std;

struct wc { //不使用class是因为这是一个纯数据的对象，虽然它包含一个默认的构造函数。
int words;
int spaces;
int punct;
int lines;
wc() {
words = punct = spaces = lines = 0;
}
};
wc wordcount(const char *str);
int main() {
const char *test = "By supplying a string class and also "
"supporting null-terminated strings,/nC++ "
"offers a rich programming environment for "
"string-intensive tasks./nIt's power programming.";
cout << "Given: " << "/n/n";
cout << test << endl;
wc wcd = wordcount(test);
cout << "/nWords: " << wcd.words << endl;
cout << "Spaces: " << wcd.spaces << endl;
cout << "Lines: " << wcd.lines << endl;
cout << "Punctuation: " << wcd.punct << endl;
return 0;
}
wc wordcount(const char *str) {
wc data;

if(*str) ++data.lines;
while(*str) {

if(isalpha(*str)) {
while(isalpha(*str) || *str == '/'') {
if(*str == '/'') ++data.punct;
++str;
}
data.words++;
}
else {
if(ispunct(*str)) ++data.punct;
else if(isspace(*str)) {
++data.spaces;
if(*str == '/n' && *(str+1)) ++data.lines;
}
++str;
}
}
return data;
}

Ex7 解析一个C型字符串

/*
* =====================================================================================
*
* Filename: 2-7.cpp
*
* Description: String Token
*
* Version: 1.0
* Created: 05/14/2010 10:01:58 AM
* Revision: none
* Compiler: gcc
*
* Author: gnuhpc (http://blog.csdn.net/gnuhpc), warmbupt@gmail.com
* Company: IBM CDL
*
* =====================================================================================
*/

#include
#include
using namespace std;

#define MAX_TOKEN_SIZE 128
const char *gettoken(const char *str);
int main() {
char delims[] = "., ?;!";
char str[] = "I like apples, pears, and grapes. Do you?";
char *tok;
cout << "Obtain the words in a sentence./n";
tok = strtok(str, delims);
while(tok) {
cout << tok << endl;
tok = strtok(NULL, delims);
}
char kvpairs[] = "count=10, name=/"Tom Jones, jr./", max=100, min=0.01";
char kvdelims[] = " =,";
cout << "/nTokenize key/Value pairs./n";
tok = strtok(kvpairs, kvdelims);
while(tok) {
cout << "Key: " << tok << " ";
if(!strcmp("name", tok)) {
tok = strtok(NULL, "/"");
}
else {
tok = strtok(NULL, kvdelims);
}
cout << "Value: " << tok << endl;
tok = strtok(NULL, kvdelims);
}

cout <<"Ori String is " << kvpairs <

//We want to token the count ,12 and the symbol add(+),but we cannot make it via strtok
char count[]="max=12+3/89; count27 = 19*(min+floor);";
char countdelims[]="=+";

const char *strtok = gettoken(count);
while(strtok) {
cout << strtok << endl;
strtok = gettoken(NULL);
}
cout << "/n/n";
return 0;
}

const char *gettoken(const char *str) {
static char token[MAX_TOKEN_SIZE+1]; //static makes the return method can be made.
static const char *ptr; //static type holds the string last time passed in
int count= 0; // holds the current character count
char *tokptr=token;
if(str) {
ptr = str;
}
while(isspace(*ptr)) ptr++;
if(isalpha(*ptr)) {
while(isalpha(*ptr) || isdigit(*ptr)) {
*tokptr++ = *ptr++;
++count;
if(count == MAX_TOKEN_SIZE) break;
}
} else if(isdigit(*ptr)) {
while(isdigit(*ptr)) {
*tokptr++ = *ptr++;
++count;
if(count == MAX_TOKEN_SIZE) break;
}
} else if(ispunct(*ptr)) {
*tokptr++ = *ptr++;
} else return NULL;
// Null terminate the token.
*tokptr = '/0';
return token;
}

3. String操作实例：

Ex8 String基本操作

/*
* =====================================================================================
*
* Filename: 2-8.cpp
*
* Description: String Basic Operation
*
* Version: 1.0
* Created: 05/14/2010 02:15:06 PM
* Revision: none
* Compiler: gcc
*
* Author: gnuhpc (http://blog.csdn.net/gnuhpc), warmbupt@gmail.com
* Company: IBM CDL
*
* =====================================================================================
*/

#include
#include
using namespace std;
int main()
{
// Create some string objects. Three are initialized
// using the string literal passed as an argument.
string str1("Alpha");
string str2("Beta");
string str3("Gamma");
string str4;
// Output a string via cout.
cout << "Here are the original strings:/n";
cout << " str1: " << str1 << endl;
cout << " str2: " << str2 << endl;
cout << " str3: " << str3 << "/n/n";
// Display the maximum string length.
cout << "The maximum string length is: " << str1.max_size()
<< "/n/n";
// Display the size of str1. You can use length() instead.这两个方法其实是一个效果，有size只是为了满足兼容STL的要求
cout << "str1 contains " << str1.size() << " characters./n";
// Display the capacity of str1.
cout << "Capacity of str1: " << str1.capacity() << "/n/n";
// Display the characters in a string one at a time
// by using the indexing operator.
for(unsigned i = 0; i < str1.size(); ++i)
&