文章目录
0. 前言
C语言中对字符和字符串的处理很是频繁,但是C语言本身是没有字符串类型的,字符串通常放在
常量字符串
中或者字符数组
中。
字符串常量
适用于那些对它不做修改的字符串函数.
1、函数介绍
1.1 求字符串长度
strlen
size_t strlen ( const char * str );
- 字符串已经 ‘\0’ 作为结束标志,
strlen
函数返回的是在字符串中'\0'
前面出现的字符个数(不包含'\0'
) - 参数指向的字符串必须要以
'\0'
结束 - 注意函数的返回值为size_t,是无符号的( 易错 )
代码实现:
#include <stdio.h>
#include <string.h>
int main()
{
const char*str1 = "abcdef";
const char*str2 = "bbb";
if(strlen(str2)-strlen(str1)>0)
{
printf("str2>str1\n");
}
else
{
printf("srt1>str2\n");
}
return 0;
}
模拟实现strlen
#include <stdio.h>
#include <string.h>
#include <assert.h>
size_t my_strlen(const char* str)
{
size_t count = 0;
assert(str);
while (*str != '\0')
{
count++;
str++;
}
return count;
}
int main()
{
char arr[] = "abcdef";
size_t n = my_strlen(arr);
printf("%u\n", n);//6
return 0;
}
1.2 长度不受限制的字符串函数
strcpy
char* strcpy(char * destination, const char * source );
- Copies the C string pointed by source into the array pointed by destination, including the terminating null character (and stopping at that point).
- 源字符串必须以
'\0'
结束 - 会将源字符串中的 ‘\0’ 拷贝到目标空间
- 目标空间必须足够大,以确保能存放源字符串
- 目标空间必须可变
代码实现:
#include <stdio.h>
#include <string.h>
int main()
{
char name[10] = "";
char arr[] = "abcdef";
strcpy(name, arr);
printf("%s\n", name);
return 0;
}
模拟实现strcpy
#include <stdio.h>
#include <string.h>
#include <assert.h>
char* my_strcpy(char* dest, const char* src)
{
assert(dest && src);
char* ret = dest;
while (*dest++ = *src++)
;
return ret;
}
int main()
{
char arr1[20] = "";
char arr2[] = "abcdef";
char* ret = my_strcpy(arr1, arr2);
printf("%s\n", ret);
return 0;
}
strcat
char * strcat ( char * destination, const char * source );
- Appends a copy of the source string to the destination string. The terminating null character in destination is overwritten by the first character of source, and a null-character is included at the end of the new string formed by the concatenation of both in destination.
- 源字符串必须以 ‘\0’ 结束
- 目标空间必须有足够的大,能容纳下源字符串的内容
- 目标空间必须可修改
代码实现:
#include <stdio.h>
#include <string.h>
int main()
{
char arr1[20] = "hello ";
char arr2[] = "world";
strcat(arr1, arr2);
printf("%s\n", arr1);
return 0;
}
模拟实现strcat
#include <stdio.h>
#include <string.h>
#include <assert.h>
char* my_strcat(char* dest, const char* src)
{
char* ret = dest;
assert(dest && src);
//1. 找到目标空间的末尾\0
while (*dest != '\0')
{
dest++;
}
//2. 拷贝字符串
while (*dest++ = *src++)
{
;
}
return ret;
}
int main()
{
char arr1[20] = "hello ";
char arr2[] = "world";
char* ret = my_strcat(arr1, arr2);
printf("%s\n", ret);
return 0;
}
strcmp
int strcmp ( const char * str1, const char * str2 );
- This function starts comparing the first character of each string. If they are equal to each other, it continues with the following pairs until the characters differ or until a terminating null-character is reached.
- 标准规定:
- 第一个字符串大于第二个字符串,则返回大于0的数字
- 第一个字符串等于第二个字符串,则返回0
- 第一个字符串小于第二个字符串,则返回小于0的数字
模拟实现
#include <stdio.h>
#include <string.h>
#include <assert.h>
int my_strcmp(const char* str1, const char* str2)
{
assert(str1 && str2);
while (*str1 == *str2)
{
if (*str1 == '\0')
return 0;//相等
str1++;
str2++;
}
return (*str1 - *str2);
}
int main()
{
char arr1[20] = "zhangsan";
char arr2[] = "zhangsanfeng";
//两个字符串比较相等,应该使用strcmp
int ret = my_strcmp(arr1, arr2);
if (ret < 0)
printf("<\n");
else if (ret == 0)
printf("==\n");
else
printf(">\n");
return 0;
}
1.3 长度受限制的字符串函数介绍
strncpy
char * strncpy ( char * destination, const char * source, size_t num );
- Copies the first num characters of source to destination. If the end of the source C string (which is signaled by a null-character) is found before num characters have been copied, destination is padded with zeros until a total of num characters have been written to it.
- 拷贝num个字符从源字符串到目标空间
- 如果源字符串的长度小于num,则拷贝完源字符串之后,在目标的后边追加0,直到num个
代码实现:
#include <stdio.h>
#include <string.h>
int main()
{
char arr1[20] = "abcdef";
char arr2[] = "bit";
//strcpy(arr1, arr2);
strncpy(arr1, arr2, 5);
printf("%s\n", arr1);
return 0;
}
strncat
char * strncat ( char * destination, const char * source, size_t num );
- Appends the first num characters of source to destination, plus a terminating null-character.
- If the length of the C string in source is less than num, only the content up to the terminating null-character is copied.
代码实现:
#include <stdio.h>
#include <string.h>
int main()
{
char arr1[20] = "hello\0xxxxxx";
char arr2[] = "bit";
strncat(arr1, arr2, 6);
printf("%s\n", arr1);
return 0;
}
strncmp
int strncmp ( const char * str1, const char * str2, size_t num );
- 比较到出现另个字符不一样或者一个字符串结束或者num个字符全部比较完。
代码实现:
#include <stdio.h>
#include <string.h>
int main()
{
char arr1[] = "abcdef";
char arr2[] = "abcq";
int ret = strncmp(arr1, arr2, 4);
printf("%d\n", ret);
if (ret == 0)
printf("==\n");
else if(ret<0)
printf("<\n");
else
printf(">\n");
return 0;
}
1.4 字符串查找
strstr
char * strstr ( const char *str1, const char * str2);
- Returns a pointer to the first occurrence of str2 in str1, or a null pointer if str2 is not part of
str1.
#include <stdio.h>
#include <string.h>
int main()
{
char email[] = "bye121345@gitee.com";
char substr[] = "gitee";
char* ret = strstr(email, substr);
if (ret == NULL)
{
printf("子串不存在\n");
}
else
{
printf("%s\n", ret);
}
return 0;
}
模拟实现strstr
#include <stdio.h>
#include <string.h>
#include <assert.h>
char* my_strstr(const char* str1, const char* str2)
{
assert(str1 && str2);
const char* s1 = str1;
const char* s2 = str2;
const char* p = str1;
while (*p)
{
s1 = p;
s2 = str2;
while (*s1 != '\0' && *s2 != '\0' && *s1 == *s2)
{
s1++;
s2++;
}
if (*s2 == '\0')
{
return (char*)p;
}
p++;
}
return NULL;
}
int main()
{
char email[] = "bye12345@gitee.com";
char substr[] = "gitee";
char* ret = my_strstr(email, substr);
if (ret == NULL)
{
printf("子串不存在\n");
}
else
{
printf("%s\n", ret);
}
return 0;
}
strtok
char * strtok ( char * str, const char * sep );
- sep参数是个字符串,定义了用作分隔符的字符集合
- 第一个参数指定一个字符串,它包含了0个或者多个由sep字符串中一个或者多个分隔符分割的标记
- strtok函数找到str中的下一个标记,并将其用 \0 结尾,返回一个指向这个标记的指针。(注:strtok函数会改变被操作的字符串,所以在使用strtok函数切分的字符串一般都是临时拷贝的内容并且可修改。)
- strtok函数的第一个参数不为 NULL ,函数将找到str中第一个标记,strtok函数将保存它在字符串中的位置
- strtok函数的第一个参数为 NULL ,函数将在同一个字符串中被保存的位置开始,查找下一个标记
- 如果字符串中不存在更多的标记,则返回 NULL 指针。
代码实现:
#include <stdio.h>
#include <string.h>
int main()
{
const char* sep = "@.";
char email[] = "bye12345@gitee.com.net";
char cp[40] = { 0 };
strcpy(cp, email);
char* ret = NULL;
for (ret = strtok(cp, sep);
ret != NULL;
ret = strtok(NULL, sep))
{
printf("%s\n", ret);
}
return 0;
}
1.5 错误信息报告
strerror
char * strerror ( int errnum );
- 返回错误码,所对应的错误信息。
代码实现:
#include <stdio.h>
#include <string.h>
#include <errno.h>
//C语言的库函数,在执行失败的时候,都会设置错误码
int main()
{
printf("%s\n", strerror(0));
printf("%s\n", strerror(1));
printf("%s\n", strerror(2));
printf("%s\n", strerror(3));
printf("%s\n", strerror(4));
printf("%s\n", strerror(5));
//errno - C语言设置的一个全局的错误码存放的变量
FILE* pf = fopen("C:\\c-language\\c\\txt.txt", "r");
if (pf == NULL)
{
printf("%s\n", strerror(errno));
return 1;
}
else
{
//
}
return 0;
}
字符分类函数
函数 | 如果他的参数符合下列条件就返回真 |
---|---|
iscntrl | 任何控制字符 |
isspace | 空白字符:空格‘ ’,换页‘\f’,换行’\n’,回车‘\r’,制表符’\t’或者垂直制表符’\v’ |
isdigit | 十进制数字 0~9 |
isxdigit | 十六进制数字,包括所有十进制数字,小写字母af,大写字母AF |
islower | 小写字母a~z |
isupper | 大写字母A~Z |
isalpha | 字母az或AZ |
isalnum | 字母或者数字,az,AZ,0~9 |
ispunct | 标点符号,任何不属于数字或者字母的图形字符(可打印) |
isgraph | 任何图形字符 |
isprint | 任何可打印字符,包括图形字符和空白字符 |
#include <stdio.h>
#include <ctype.h>
int main()
{
int a = isspace(' ');
printf("%d\n", a);
int b = isdigit('x');
printf("%d\n", b);
printf("%c\n", tolower('@'));
return 0;
}
1.6 内存操作函数
memcpy
void * memcpy ( void * destination, const void * source, size_t num );
- 函数memcpy从source的位置开始向后复制num个字节的数据到destination的内存位置
- 这个函数在遇到 ‘\0’ 的时候并不会停下来
- 如果source和destination有任何的重叠,复制的结果都是未定义的。
代码实现:
#include <stdio.h>
#include <string.h>
int main()
{
float arr3[5] = { 1.0,2.5,3.0,5.0,6.0 };
float arr4[10] = { 0.0 };
memcpy(arr4, arr3, 20);
return 0;
}
模拟实现memcpy
#include <stdio.h>
#include <string.h>
#include <assert.h>
void* my_memcpy(void* dest, const void* src, size_t num)
{
assert(dest && src);
void* ret = dest;
while (num--)
{
*(char*)dest = *(char*)src;
dest = (char*)dest + 1;
src = (char*)src + 1;
}
}
int main()
{
int arr1[] = { 1,2,3,4,5,6,7,8,9,10 };
int arr2[10] = { 0 };
my_memcpy(arr2, arr1, 28);
return 0;
}
memmove
void * memmove ( void * destination, const void * source, size_t num );
- 和memcpy的差别就是memmove函数处理的源内存块和目标内存块是可以重叠的
- 如果源空间和目标空间出现重叠,就得使用memmove函数处理。
memcmp
int memcmp ( const void * ptr1,
const void * ptr2,
size_t num );
- 比较从ptr1和ptr2指针开始的num个字节
- 返回值如下
Returns an integral value indicating the relationship between the content of the memory blocks:
(返回一个整数值,表示内存块内容之间的关系):
返回值(return value) | indicates |
---|---|
<0 | the first byte that does not match in both memory blocks has a lower value in ptr1 than in ptr2 (if evaluated as unsigned char values) |
0 | the contents of both memory blocks are equal |
<0 | the first byte that does not match in both memory blocks has a greater value in ptr1 than in ptr2 (if evaluated as unsigned char values) |
#include <stdio.h>
#include <string.h>
int main()
{
int arr1[] = { 1,2,3,4,5 };
int arr2[] = { 1,3,2 };
int ret = memcmp(arr1, arr2, 12);
printf("%d\n", ret);
return 0;
}
本博客代码仅供参考,如有错误,欢迎指正