如何检测 C 中的 CLI 特殊字符？
How do I detect CLI Special Characters in C?
Note: This is not homework. I am still a beginner.
澄清并扩展我的问题：
在命令行界面中，我们知道可以使用特殊字符表示特殊的含义，比如扩展字符
ls -l *.c
扩展命令以抓取并列出所有扩展名为“.c”的文件。
也可以使用 >、<、&、* 等其他字符及其组合。
假设我正在用 C 编写一个实用程序，它被称为 findch，查找字符的缩写，我可以在 CLI 中调用它。
所有 findch 所做的就是获取第一个参数的 first character 并尝试在后面的参数中找到它，无论它是 string 还是 file。如果找到该字符，它会报告出现的次数。如果失败，它也会报告。
Usage 1: findch [character] [filename.ext]...
Usage 2: findch a "How many times does the letter a appear in this string?"
Usage 3: findch a filename.txt
当我做类似
的事情时，问题就出现了
findch * "hello, there!"
findch ^ hello
findch & hello
当我只传递一个特殊字符时，CLI 会以这种方式解释它并扰乱我的程序。我可以实施简单的预防措施吗？或者这有点复杂和系统特定？
这是目前为止的代码。
findproto.h
/*
//C Primer Plus
//Chp 13 Programming Exercises
//Problem 13-08
*************************************************************
Written by: JargonJunkie
*************************************************************
************************************
set the preprocessor directives
************************************/
/*
SET THE SWITCHES
----------------
To avoid conflicts while editing, and recompiling, I used a
"switch mechanism" to turn the function prototypes ON and OFF.
*/
#ifndef ON
# define ON 1
#endif
#ifndef OFF
# define OFF 0
#endif
/*
maximum string length
---------------------
11 //tiny
21 //small
41 //medium
81 //large
101 //extra
---------------------
all sizes are offset by one
to include the null character
*/
#ifndef STRLEN
# define STRLEN 41
#endif
/*
Set the ERROR macro
*/
#ifndef ERROR
# define ERROR -1
#endif
/*
Since I use MinGW, there is no standard boolean header.
I have to define the bool type and create the true
and false constants. If the bool type exists, then
the bool type is not created. While my GCC is C99 compliant,
I prefer to use bool over _Bool which, IMO, looks awkward.
*/
/*
Set the boolean values for the
variables true and false...
*/
#ifndef BOOL
# define BOOL ON
# if BOOL
# define true 1
# define false 0
typedef _Bool bool;
# endif
#endif
/*
Define the file options.
------------------------
These settings are used to decide whether the given
file extension type is a "valid" one.
-----------------------------------
More extensions can be added by simply changing the EXTLEN macro
value. The strings can be found in the fcfunct.c file.
Keep in mind that the order of the values and string elements
must be the same.
*/
#ifndef FILE_OPTIONS
# define EXTLEN 9
enum file {
txt, asc, c, h, csv, html, log, xhtml, xml,
error = -1, missing = -2
};
const char * extension[EXTLEN];
#endif
/*
Prototypes make a good reference and allows the "black-box" concept
to stay in play. Once a function has been tested, and works, it
can be added to the prototype list.
*/
#ifndef PROTOTYPES
# define PROTOTYPES ON
# if PROTOTYPES == ON
void string_to_lower(char * string);
void display_help(const char * string);
enum file known_file_extension(const char * filename);
enum file string_or_file(const char * string);
bool first_arg_is_char(char * string);
unsigned int count_char_in_string(char * arg, char * string);
unsigned int count_char_in_file(char * arg, char * filename);
# endif
#endif
findfunct.c
//C Primer Plus
//Chp 13 Programming Exercises
//Problem 13-08
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include "findproto.h"
/*
Initialize EXTENSION Based Keywords
----------------------------------------------
These keywords are used to compare against input supplied by the
user. If the keyword is found to be valid, the function returns
a value accordingly; else the function returns some type of error
based value.
*/
const char * extension[EXTLEN] = {
".txt", ".asc", ".c", ".h",
".csv", ".html", ".log",
".xhtml", ".xml"
};
/*
The string_to_lower() function
---------------------------------------
Transforms the string to lower case
*/
void string_to_lower(char * string)
{
for (int index = 0; string[index]; index++)
{
if (isalpha(string[index]))
{
string[index] = tolower(string[index]);
}
}
}
/*
The display_help() Function
---------------------------------------
Prints the help menu to the standard display
*/
void display_help(const char * string)
{
putchar('\n');
printf("Usage: %s [character] [filename.ext]...\n\n", string);
printf("This program takes a character and zero or more filenames\n"
"as command-line arguments.\n\n"
"If no arguements follow the character, the program reads from\n"
"the standarad input instead. Otherwise, it opens each file in\n"
"turn and reports how many times the character appeared in each\n"
"file.\n\n"
"The filename, and the character itself, should be reported along\n"
"with the count.\n\n"
"If a file can't be opened, the program reports that fact and continues\n"
"on to the next file.\n\n");
printf("ALLOWED FILE EXTENSION TYPES\n"
".txt .asc .c .h .html\n"
".log .xhtml .dat .xml .csv\n");
}
/*
The known_file_extension() Function
---------------------------------------
IF a known file extension is found, return true on success.
ELSE return false on failure...
*/
enum file known_file_extension(const char * filename)
{
enum file value = error;
//find the last occurring period
char * file_extension_type = strrchr(filename, '.');
if (NULL == file_extension_type)
{
value = missing;
return value;
}
string_to_lower(file_extension_type);
//find the file type
for (enum file type = txt; type <= xml; type++)
{
if (0 == strcmp(file_extension_type, extension[type]))
{
value = type;
break;
}
}
return value;
}
/*
Find the first argument and make sure the string is
only one character long.
If the the string is not one character long, grab
only the first character and replace the remaining
characters with the null character.
If the function succeeds, it returns true.
If the function fails, it returns false.
*/
bool first_arg_is_char(char * string)
{
int length;
bool status = false;
length = strlen(string);
putchar('\n');
if (isalpha(string[0]))
{
if (length == 1)
{
puts("Found character literal...\n");
status = true;
}
if (length >= 2)
{
puts("Stripping string to first character...\n");
for (int i = 1; i <= length; i++)
{
string[i] = '[=11=]';
}
status = true;
puts("Successfully modified the string...\n");
}
if (status)
{
printf("Character literal: '%s'\n\n", string);
}
}
return status;
}
/*
Determine whether the given string is just a
string or a filename.
*/
enum file string_or_file(const char * string)
{
enum file type = known_file_extension(string);
switch (type)
{
case missing:
puts("The file extension seems to be missing.");
puts("Assuming string is string literal.\n");
return missing;
case error:
puts("Oops! An invalid file extension was used.");
return error;
default:
puts("Found valid file extension...");
return type;
}
}
/*
Count the number of occurrences that the given character
arugment is found in the given string.
*/
unsigned int count_char_in_string(char * arg, char * string)
{
unsigned int count = 0, index;
for (index = 0, count = 0; string[index] != '[=11=]'; index++)
{
if (arg[0] == string[index])
{
++count;
}
}
return count;
}
/*
Count the number of occurrences that the given character
arugment is found in the given file.
*/
unsigned int count_char_in_file(char * arg, char * filename)
{
FILE * source;
char ch;
unsigned int count, index;
if (NULL == (source = fopen(filename, "r")))
{
fprintf(stderr, "Oops! The file %s failed to open...", filename);
return 0;
}
for (index = 0, count = 0; EOF != (ch = fgetc(source)); index++)
{
if (arg[0] == ch)
{
++count;
}
}
return count;
}
findchar.c
//C Primer Plus
//Chp 13 Programming Exercises
//Problem 13-08
/*
*************************************************************
Written by: JargonJunkie
*************************************************************
CHP 13 Problem #8
*************************************************************
Write a program that takes as command-line arguments a character
and zero or more filenames.
If no arguements follow the character, have the program read the
standarad input. Otherwise, have it open each file in turn and
report how many times the character appears in each file.
The filename and the character itself should be reported along
with the count.
Include error-checking to see whether the number of arguments is
correct and whether the files can be opened. If a file can't be
opened, have the program report that fact and go on to the next
file.
*************************************************************
*/
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include "findproto.h"
int main(int argc, char * argv[])
{
enum file status;
unsigned number_of_chars = 0;
if (argc <= 1)
{
display_help(argv[0]);
return 1;
}
if (!first_arg_is_char(argv[1]))
{
puts("The first argument must be a character.");
return 1;
}
/*
Determine whether or not the string is a referenced
file name.
*/
for (int count = 2; count < argc; count++)
{
status = string_or_file(argv[count]);
switch (status)
{
case missing:
//assume string literal
number_of_chars = count_char_in_string(argv[1], argv[count]);
if (!number_of_chars)
{
printf("[Null Character]! The character '%s' was not found.\n", argv[1]);
}
if (number_of_chars)
{
printf("String: %s\n\n", argv[count]);
printf("The character '%s' was found %u time(s).\n", argv[1], number_of_chars);
}
break;
case error:
//something went wrong...
puts("Error! Possible invalid argument...");
break;
case txt:
case asc:
case c:
case h:
case csv:
case html:
case log:
case xhtml:
case xml:
//assume string is of FILE type
//calculate the number of occurances
//for the given letter X...
break;
default:
//something went horribly wrong...
puts("Oops! Something went HORRIBLY wrong...");
break;
}
}
return 0;
}
是的，这是特定于系统的，取决于您使用的 CLI/shell。对于像 shells 这样的大多数 unix，你可以只用单引号引用这些参数，所以 shell 不会解释那些特殊的结构，例如运行:
findch '*' "hello, there!"
findch '&' "hello, there!"
这会将 & 和 * 字符作为 argv[1] 传递给您的程序，没有单引号，也没有 shell 解释它们。
参见例如如果您使用 bash shell.
，here 了解更多信息
Note: This is not homework. I am still a beginner.
澄清并扩展我的问题：
在命令行界面中，我们知道可以使用特殊字符表示特殊的含义，比如扩展字符
ls -l *.c
扩展命令以抓取并列出所有扩展名为“.c”的文件。
也可以使用 >、<、&、* 等其他字符及其组合。
假设我正在用 C 编写一个实用程序，它被称为 findch，查找字符的缩写，我可以在 CLI 中调用它。
所有 findch 所做的就是获取第一个参数的 first character 并尝试在后面的参数中找到它，无论它是 string 还是 file。如果找到该字符，它会报告出现的次数。如果失败，它也会报告。
Usage 1:
findch [character] [filename.ext]...Usage 2:
findch a "How many times does the letter a appear in this string?"Usage 3:
findch a filename.txt
当我做类似
的事情时，问题就出现了
findch * "hello, there!"findch ^ hellofindch & hello
当我只传递一个特殊字符时，CLI 会以这种方式解释它并扰乱我的程序。我可以实施简单的预防措施吗？或者这有点复杂和系统特定？
这是目前为止的代码。
findproto.h
/*
//C Primer Plus
//Chp 13 Programming Exercises
//Problem 13-08
*************************************************************
Written by: JargonJunkie
*************************************************************
************************************
set the preprocessor directives
************************************/
/*
SET THE SWITCHES
----------------
To avoid conflicts while editing, and recompiling, I used a
"switch mechanism" to turn the function prototypes ON and OFF.
*/
#ifndef ON
# define ON 1
#endif
#ifndef OFF
# define OFF 0
#endif
/*
maximum string length
---------------------
11 //tiny
21 //small
41 //medium
81 //large
101 //extra
---------------------
all sizes are offset by one
to include the null character
*/
#ifndef STRLEN
# define STRLEN 41
#endif
/*
Set the ERROR macro
*/
#ifndef ERROR
# define ERROR -1
#endif
/*
Since I use MinGW, there is no standard boolean header.
I have to define the bool type and create the true
and false constants. If the bool type exists, then
the bool type is not created. While my GCC is C99 compliant,
I prefer to use bool over _Bool which, IMO, looks awkward.
*/
/*
Set the boolean values for the
variables true and false...
*/
#ifndef BOOL
# define BOOL ON
# if BOOL
# define true 1
# define false 0
typedef _Bool bool;
# endif
#endif
/*
Define the file options.
------------------------
These settings are used to decide whether the given
file extension type is a "valid" one.
-----------------------------------
More extensions can be added by simply changing the EXTLEN macro
value. The strings can be found in the fcfunct.c file.
Keep in mind that the order of the values and string elements
must be the same.
*/
#ifndef FILE_OPTIONS
# define EXTLEN 9
enum file {
txt, asc, c, h, csv, html, log, xhtml, xml,
error = -1, missing = -2
};
const char * extension[EXTLEN];
#endif
/*
Prototypes make a good reference and allows the "black-box" concept
to stay in play. Once a function has been tested, and works, it
can be added to the prototype list.
*/
#ifndef PROTOTYPES
# define PROTOTYPES ON
# if PROTOTYPES == ON
void string_to_lower(char * string);
void display_help(const char * string);
enum file known_file_extension(const char * filename);
enum file string_or_file(const char * string);
bool first_arg_is_char(char * string);
unsigned int count_char_in_string(char * arg, char * string);
unsigned int count_char_in_file(char * arg, char * filename);
# endif
#endif
findfunct.c
//C Primer Plus
//Chp 13 Programming Exercises
//Problem 13-08
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include "findproto.h"
/*
Initialize EXTENSION Based Keywords
----------------------------------------------
These keywords are used to compare against input supplied by the
user. If the keyword is found to be valid, the function returns
a value accordingly; else the function returns some type of error
based value.
*/
const char * extension[EXTLEN] = {
".txt", ".asc", ".c", ".h",
".csv", ".html", ".log",
".xhtml", ".xml"
};
/*
The string_to_lower() function
---------------------------------------
Transforms the string to lower case
*/
void string_to_lower(char * string)
{
for (int index = 0; string[index]; index++)
{
if (isalpha(string[index]))
{
string[index] = tolower(string[index]);
}
}
}
/*
The display_help() Function
---------------------------------------
Prints the help menu to the standard display
*/
void display_help(const char * string)
{
putchar('\n');
printf("Usage: %s [character] [filename.ext]...\n\n", string);
printf("This program takes a character and zero or more filenames\n"
"as command-line arguments.\n\n"
"If no arguements follow the character, the program reads from\n"
"the standarad input instead. Otherwise, it opens each file in\n"
"turn and reports how many times the character appeared in each\n"
"file.\n\n"
"The filename, and the character itself, should be reported along\n"
"with the count.\n\n"
"If a file can't be opened, the program reports that fact and continues\n"
"on to the next file.\n\n");
printf("ALLOWED FILE EXTENSION TYPES\n"
".txt .asc .c .h .html\n"
".log .xhtml .dat .xml .csv\n");
}
/*
The known_file_extension() Function
---------------------------------------
IF a known file extension is found, return true on success.
ELSE return false on failure...
*/
enum file known_file_extension(const char * filename)
{
enum file value = error;
//find the last occurring period
char * file_extension_type = strrchr(filename, '.');
if (NULL == file_extension_type)
{
value = missing;
return value;
}
string_to_lower(file_extension_type);
//find the file type
for (enum file type = txt; type <= xml; type++)
{
if (0 == strcmp(file_extension_type, extension[type]))
{
value = type;
break;
}
}
return value;
}
/*
Find the first argument and make sure the string is
only one character long.
If the the string is not one character long, grab
only the first character and replace the remaining
characters with the null character.
If the function succeeds, it returns true.
If the function fails, it returns false.
*/
bool first_arg_is_char(char * string)
{
int length;
bool status = false;
length = strlen(string);
putchar('\n');
if (isalpha(string[0]))
{
if (length == 1)
{
puts("Found character literal...\n");
status = true;
}
if (length >= 2)
{
puts("Stripping string to first character...\n");
for (int i = 1; i <= length; i++)
{
string[i] = '[=11=]';
}
status = true;
puts("Successfully modified the string...\n");
}
if (status)
{
printf("Character literal: '%s'\n\n", string);
}
}
return status;
}
/*
Determine whether the given string is just a
string or a filename.
*/
enum file string_or_file(const char * string)
{
enum file type = known_file_extension(string);
switch (type)
{
case missing:
puts("The file extension seems to be missing.");
puts("Assuming string is string literal.\n");
return missing;
case error:
puts("Oops! An invalid file extension was used.");
return error;
default:
puts("Found valid file extension...");
return type;
}
}
/*
Count the number of occurrences that the given character
arugment is found in the given string.
*/
unsigned int count_char_in_string(char * arg, char * string)
{
unsigned int count = 0, index;
for (index = 0, count = 0; string[index] != '[=11=]'; index++)
{
if (arg[0] == string[index])
{
++count;
}
}
return count;
}
/*
Count the number of occurrences that the given character
arugment is found in the given file.
*/
unsigned int count_char_in_file(char * arg, char * filename)
{
FILE * source;
char ch;
unsigned int count, index;
if (NULL == (source = fopen(filename, "r")))
{
fprintf(stderr, "Oops! The file %s failed to open...", filename);
return 0;
}
for (index = 0, count = 0; EOF != (ch = fgetc(source)); index++)
{
if (arg[0] == ch)
{
++count;
}
}
return count;
}
findchar.c
//C Primer Plus
//Chp 13 Programming Exercises
//Problem 13-08
/*
*************************************************************
Written by: JargonJunkie
*************************************************************
CHP 13 Problem #8
*************************************************************
Write a program that takes as command-line arguments a character
and zero or more filenames.
If no arguements follow the character, have the program read the
standarad input. Otherwise, have it open each file in turn and
report how many times the character appears in each file.
The filename and the character itself should be reported along
with the count.
Include error-checking to see whether the number of arguments is
correct and whether the files can be opened. If a file can't be
opened, have the program report that fact and go on to the next
file.
*************************************************************
*/
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include "findproto.h"
int main(int argc, char * argv[])
{
enum file status;
unsigned number_of_chars = 0;
if (argc <= 1)
{
display_help(argv[0]);
return 1;
}
if (!first_arg_is_char(argv[1]))
{
puts("The first argument must be a character.");
return 1;
}
/*
Determine whether or not the string is a referenced
file name.
*/
for (int count = 2; count < argc; count++)
{
status = string_or_file(argv[count]);
switch (status)
{
case missing:
//assume string literal
number_of_chars = count_char_in_string(argv[1], argv[count]);
if (!number_of_chars)
{
printf("[Null Character]! The character '%s' was not found.\n", argv[1]);
}
if (number_of_chars)
{
printf("String: %s\n\n", argv[count]);
printf("The character '%s' was found %u time(s).\n", argv[1], number_of_chars);
}
break;
case error:
//something went wrong...
puts("Error! Possible invalid argument...");
break;
case txt:
case asc:
case c:
case h:
case csv:
case html:
case log:
case xhtml:
case xml:
//assume string is of FILE type
//calculate the number of occurances
//for the given letter X...
break;
default:
//something went horribly wrong...
puts("Oops! Something went HORRIBLY wrong...");
break;
}
}
return 0;
}
是的，这是特定于系统的，取决于您使用的 CLI/shell。对于像 shells 这样的大多数 unix，你可以只用单引号引用这些参数，所以 shell 不会解释那些特殊的结构，例如运行:
findch '*' "hello, there!"
findch '&' "hello, there!"
这会将 & 和 * 字符作为 argv[1] 传递给您的程序，没有单引号，也没有 shell 解释它们。
参见例如如果您使用 bash shell.