Created
October 2, 2023 13:30
-
-
Save youkidearitai/0018dee27353c00aebaff3bf57c5b8c6 to your computer and use it in GitHub Desktop.
trim function for multibyte support
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #include <iostream> | |
| #include <cstring> | |
| #include <string_view> | |
| void mb_trim(size_t *strlen, char **str, const size_t | |
| trim_lengths_num, const size_t *trim_lengths, const char **trim_chars) | |
| { | |
| size_t local_strlen = *strlen; | |
| char *local_str = *str; | |
| for (;;) | |
| { | |
| for (size_t i = 0; i < trim_lengths_num; ++i) | |
| { | |
| if (local_strlen >= trim_lengths[i] && memcmp(local_str, | |
| trim_chars[i], trim_lengths[i]) == 0) | |
| { | |
| local_strlen -= trim_lengths[i]; | |
| local_str += trim_lengths[i]; | |
| goto remove_from_start_continue_2; | |
| } | |
| } | |
| break; | |
| remove_from_start_continue_2:; | |
| } | |
| for (;;) | |
| { | |
| for (size_t i = 0; i < trim_lengths_num; ++i) | |
| { | |
| if (local_strlen >= trim_lengths[i] && memcmp(((local_str | |
| + local_strlen) - trim_lengths[i]), trim_chars[i], trim_lengths[i]) == | |
| 0) | |
| { | |
| local_strlen -= trim_lengths[i]; | |
| goto remove_from_end_continue_2; | |
| } | |
| } | |
| break; | |
| remove_from_end_continue_2:; | |
| } | |
| memmove(*str, local_str, local_strlen); | |
| char *newstr = (char *)realloc(*str, local_strlen); | |
| if (newstr != nullptr) | |
| { | |
| *strlen = local_strlen; | |
| *str = newstr; | |
| } | |
| else | |
| { | |
| // some error handling | |
| } | |
| } | |
| int main() | |
| { | |
| const char *trim_chars[] = { | |
| " ", | |
| "!", | |
| // utf8 whitespace: | |
| "\xE2\x80\x80", // EN QUAD | |
| "\xE2\x80\x81", // EM QUAD | |
| "\xE2\x80\x82", // EN SPACE | |
| "\xE2\x80\x83", // EM SPACE | |
| "\xE2\x80\x84", // THREE-PER-EM SPACE | |
| "\xE2\x80\x85", // FOUR-PER-EM SPACE | |
| "\xE2\x80\x86", // SIX-PER-EM SPACE | |
| }; | |
| size_t trim_lengths[] = { | |
| strlen(trim_chars[0]), | |
| strlen(trim_chars[1]), | |
| strlen(trim_chars[2]), | |
| strlen(trim_chars[3]), | |
| strlen(trim_chars[4]), | |
| strlen(trim_chars[5]), | |
| strlen(trim_chars[6]), | |
| strlen(trim_chars[7]), | |
| strlen(trim_chars[8]), | |
| }; | |
| size_t trim_lengths_num = sizeof(trim_lengths) / sizeof(trim_lengths[0]); | |
| char *teststr = strdup(" ! \xE2\x80\x80\xE2\x80\x81\xE2\x80\x82Hello World ! \xE2\x80\x83\xE2\x80\x84\xE2\x80\x85\xE2\x80\x86 !"); | |
| // char *teststr = strdup(" ! Hello World ! ! "); | |
| size_t teststrlen = strlen(teststr); | |
| std::cout << teststrlen << ": \"" << std::string_view(teststr, | |
| teststrlen) << "\"" << std::endl; | |
| mb_trim(&teststrlen, &teststr, trim_lengths_num, trim_lengths, trim_chars); | |
| std::cout << teststrlen << ": \"" << std::string_view(teststr, | |
| teststrlen) << "\"" << std::endl; | |
| return 0; | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment