gpt4 book ai didi

c - 如何仅使用 sscanf 从字符串中提取所有数字?

转载 作者:行者123 更新时间:2023-11-30 18:45:49 26 4
gpt4 key购买 nike

如何在 C 语言中使用 sscanf 从以下格式的字符串中提取所有数字:

“(3,2,4,5,10)”

空格可以无处不在,但当然不能在数字之间。每个位置可以有 0 个或更多空格。

字符串必须具有正确的格式,否则会出现错误。例如,“(3,2,”是一个错误。每个不是空格或格式一部分的字符都是错误

仅使用 sscanf(它不是可选的)

我的想法当然是用 sscanf 进行 while 循环,但格式是我的问题

编辑:括号内的数字数量可以不同。所以括号内可以有 0 个数字或 n 个数字。 n 是任意数字。 (a,a+1,...,a+n)。

EDIT2:当然允许使用 stdio.h 中包含的所有内容,但不允许使用扩展库

最佳答案

序言

看来数据的格式可以概括为:处处有空格;左括号后跟一系列由逗号分隔的一个或多个普通整数(无符号,无小数点),并以右括号终止。或者,() 之间可以有零个整数。

必须使用sscanf()处理数据;对于单次调用 sscanf() 没有明确的规则。与文件 I/O 替代方案(scanf()fscanf() 等)相比,使用 sscanf() 的优点之一是如有必要,您可以重试扫描。

请注意,scanf() 系列不能很好地处理“可选项目”。空格大多是微不足道的 - 除了 %c%[…] (扫描集)和 %n 之外的所有转换说明符都会跳过前导空格,格式字符串中的空白字符与输入中的零个或多个空白字符匹配。

代码

函数string_analyzer()完成这项工作;它有一个适度复杂的接口(interface),因为它本身不执行 I/O — 它分析字符串并将数字添加到传递给函数的数组结构中。它还设置一条消息,告诉调用者一些出错的信息。其他函数是支持函数(对于 struct int_array 类型)和测试工具(main() 加上 test_string_analyzer())。

#include <assert.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

struct int_array
{
char *base;
size_t maxlen;
size_t curlen;
};

static void dump_int_array(const char *tag, const struct int_array *array);
static void add_to_int_array(struct int_array *array, int data);
static void free_int_array(struct int_array *array);
static void test_string_analyzer(const char *str);

static int string_analyzer(const char *str, struct int_array *array, char **msg)
{
int offset;
int length = strlen(str);
int data;
char trailer;

if (sscanf(str, " ( %[)] %n", &trailer, &offset) == 1)
{
/* Empty list */
assert(trailer == ')');
if (offset == length)
{
*msg = "it is an empty list";
return 0;
}
else
{
*msg = "it has extra characters after an empty list";
return -1;
}
}

if (sscanf(str, " ( %d %c%n", &data, &trailer, &offset) != 2 ||
(trailer != ',' && trailer != ')'))
{
*msg = "it does not start correctly";
return -1;
}
add_to_int_array(array, data);
if (trailer == ')' && offset == length)
{
*msg = "it is valid";
return 0;
}
const char *source = str + offset;
while (sscanf(source, "%d %[,)] %n", &data, &trailer, &offset) == 2)
{
add_to_int_array(array, data);
length = strlen(source);
if (trailer == ')' && offset == length)
{
*msg = "it is valid";
return 0;
}
else if (trailer == ')')
{
*msg = "it does not end correctly";
return -1;
}
source += offset;
}
*msg = "it is incorrectly formatted";
return -1;
}

int main(void)
{
const char *samples[] =
{
/* Valid */
" (3, 2, 4,5, 10 )",
" ( 4 , 6 ) ",
"(4)",
"()",
/* random -n 15 10 99 | commalist -t -B 8 -b '"( ' -T ' )",' */
"( 65, 83, 81, 60, 61, 23, 48, 89, 67, 27, 73, 25, 92, 13, 67 )",
/* Invalid */
" (3,2, ",
"3,2",
" (3,2,1) apathy",
" () apathy",
" (3,X,1)",
" (3X,1)",
};
enum { NUM_SAMPLES = sizeof(samples) / sizeof(samples[0]) };

for (int i = 0; i < NUM_SAMPLES; i++)
test_string_analyzer(samples[i]);

return 0;
}

static void test_string_analyzer(const char *str)
{
struct int_array array = { 0, 0, 0 };
char *msg = 0;

printf("Analyzing [%s]\n", str);
int rc = string_analyzer(str, &array, &msg);
if (rc == 0)
printf("String '%s' OK: %s\n", str, msg);
else
printf("String '%s' is misformatted: %s\n", str, msg);
dump_int_array("List contents", &array);

free_int_array(&array);
}

static void dump_int_array(const char *tag, const struct int_array *array)
{
int length = printf("%s (%zu): ", tag, array->curlen);
const char *pad = "";
for (size_t i = 0; i < array->curlen; i++)
{
length += printf("%s%d", pad, array->base[i]);
pad = ", ";
if (length >= 64)
{
pad = " ";
length = 0;
putchar('\n');
}
}
if (length > 0)
putchar('\n');
}

static void add_to_int_array(struct int_array *array, int data)
{
if (array->curlen >= array->maxlen)
{
assert(array->curlen == array->maxlen);
size_t newlen = array->maxlen * 2 + 2;
void *newarr = realloc(array->base, newlen * sizeof(array->base[0]));
if (newarr == NULL)
{
}
array->base = newarr;
array->maxlen = newlen;
}
array->base[array->curlen++] = data;
}

static void free_int_array(struct int_array *array)
{
free(array->base);
array->base = 0;
array->maxlen = 0;
array->curlen = 0;
}

示例输出:

Analyzing [ (3, 2, 4,5, 10 )]
String ' (3, 2, 4,5, 10 )' OK: it is valid
List contents (5): 3, 2, 4, 5, 10
Analyzing [ ( 4 , 6 ) ]
String ' ( 4 , 6 ) ' OK: it is valid
List contents (2): 4, 6
Analyzing [(4)]
String '(4)' OK: it is valid
List contents (1): 4
Analyzing [()]
String '()' OK: it is an empty list
List contents (0):
Analyzing [( 65, 83, 81, 60, 61, 23, 48, 89, 67, 27, 73, 25, 92, 13, 67 )]
String '( 65, 83, 81, 60, 61, 23, 48, 89, 67, 27, 73, 25, 92, 13, 67 )' OK: it is valid
List contents (15): 65, 83, 81, 60, 61, 23, 48, 89, 67, 27, 73, 25
92, 13, 67
Analyzing [ (3,2, ]
String ' (3,2, ' is misformatted: it is incorrectly formatted
List contents (2): 3, 2
Analyzing [3,2]
String '3,2' is misformatted: it does not start correctly
List contents (0):
Analyzing [ (3,2,1) apathy]
String ' (3,2,1) apathy' is misformatted: it does not end correctly
List contents (3): 3, 2, 1
Analyzing [ () apathy]
String ' () apathy' is misformatted: it has extra characters after an empty list
List contents (0):
Analyzing [ (3,X,1)]
String ' (3,X,1)' is misformatted: it is incorrectly formatted
List contents (1): 3
Analyzing [ (3X,1)]
String ' (3X,1)' is misformatted: it does not start correctly
List contents (0):

关于c - 如何仅使用 sscanf 从字符串中提取所有数字?,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/53572030/

26 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com