amxmodx/plugins/include/string_stocks.inc
Vincent Herbet ab854ec035 Improve UTF-8 support in some natives (bug 6475) (#407)
* Compile as static library, update AMBuildScript and link to core

* Update VS project files to include the library

* Add UTF-8 Rewind library (v1.5.1) to third_party directory

* Update ACKNOWLEDGEMENTS.txt

* Move AMXX buffer in its own function

* Move constants from string.inc to string_const.inc and update project files

* Move stocks from string.inc to string_stocks.inc and update project files

* Improve UTF-8 support in containi() and update documentation

* Improve UTF-8 support in strcmp() and update documentation

* Improve UTF-8 support in strfind() and update documentation

Worth to be noted that this native with ignorecase set was not working properly. So broken that no one reported the issue.
This adds also a safety check for "pos" parameter to not go < 0.

* Improve UTF-8 support in strncmp() and update documentation

* Improve UTF-8 support in equali() and update documentation

* Add an option to some UTF-8 Rewind functions for avoiding invalid data to be replaced

By default it replaces any invalid byte or sequence of bytes by 0xFFFD (3 bytes). It can be problematic when the input buffer is not changed (from a plugin) and that some natives need to calculate a position from the converted string. With such replacement, the position is displaced due the final string length being larger.

This compiles the library as C++, because I added some silly param with a default default value which is not supported by C.

* Improve UTF-8 support in replace_string/ex() and update documentation

* Add is_string_category() and update documentation

* Update a little testsuite plugin (and fix linux compilation)

* Add mb_strotolower/upper() and update documentation

* Add mb_ucfirst() and update documentation

* Add mb_strtotile() and update documentation

* Improve UTF-8 support in get_players() and find_player() with name/case insenstive flags set

* Fix KliPPy's complain
2017-08-05 10:32:16 +02:00

326 lines
8.1 KiB
SourcePawn

// vim: set ts=4 sw=4 tw=99 noet:
//
// AMX Mod X, based on AMX Mod by Aleksander Naszko ("OLO").
// Copyright (C) The AMX Mod X Development Team.
//
// This software is licensed under the GNU General Public License, version 3 or higher.
// Additional exceptions apply. For full license details, see LICENSE.txt or visit:
// https://alliedmods.net/amxmodx-license
//
// String Manipulation Stocks
//
#if defined _string_stocks_included
#endinput
#endif
#define _string_stocks_included
#if !defined _string_included
#include <string>
#endif
/**
* @global Unless otherwise noted, all string functions which take in a
* writable buffer and maximum length should NOT have the null terminator INCLUDED
* in the length. This means that this is valid:
* copy(string, charsmax(string), ...)
*/
/**
* Returns whether a given string contains only digits.
* This returns false for zero-length strings.
*
* @param sString Character to test.
* @return True if string contains only digit, otherwise false.
*/
stock bool:is_str_num(const sString[])
{
new i = 0;
while (sString[i] && isdigit(sString[i]))
{
++i;
}
return sString[i] == 0 && i != 0;
}
/**
* Returns an uppercase character to a lowercase character.
*
* @note Only available in 1.8.3 and above.
*
* @param chr Characer to convert.
* @return Lowercase character on success,
* no change on failure.
*/
stock char_to_upper(chr)
{
if (is_char_lower(chr))
{
return (chr & ~(1<<5));
}
return chr;
}
/**
* Returns a lowercase character to an uppercase character.
*
* @note Only available in 1.8.3 and above.
*
* @param chr Characer to convert.
* @return Uppercase character on success,
* no change on failure.
*/
stock char_to_lower(chr)
{
if (is_char_upper(chr))
{
return (chr | (1<<5));
}
return chr;
}
/**
* Backwards compatibility stock - use argbreak or argparse.
* @deprecated this function does not work properly.
*/
#pragma deprecated Use argbreak() instead
stock strbreak(const text[], Left[], leftLen, Right[], rightLen)
{
return argbreak(text, Left, leftLen, Right, rightLen);
}
/**
* Emulates strbreak() using argparse().
*
* @param text Source input string.
* @param left Buffer to store string left part.
* @param leftlen Maximum length of the string part buffer.
* @param right Buffer to store string right part.
* @param rightlen Maximum length of the string part buffer.
*
* @return -1 if no match was found; otherwise, an index into source
* marking the first index after the searched text. The
* index is always relative to the start of the input string.
*/
stock argbreak(const text[], left[], leftlen, right[], rightlen)
{
new pos = argparse(text, 0, left, leftlen);
if (pos == -1)
{
return -1;
}
new textlen = strlen(text);
while (pos < textlen && isspace(text[pos]))
{
pos++;
}
copy(right, rightlen, text[pos]);
return pos;
}
/**
* It is basically strbreak but you have a delimiter that is more than one character in length. By Suicid3.
*
* @param szInput Source input string.
* @param szLeft Buffer to store left string part.
* @param pL_Max Maximum length of the string part buffer.
* @param szRight Buffer to store right string part.
* @param pR_Max Maximum length of the string part buffer.
* @param szDelim A string which specifies a search point to break at.
*
* @noreturn
*/
stock split(const szInput[], szLeft[], pL_Max, szRight[], pR_Max, const szDelim[])
{
new iEnd = contain(szInput, szDelim);
new iStart = iEnd + strlen(szDelim);
// If delimiter isnt in Input just split the string at max lengths
if (iEnd == -1)
{
iStart = copy(szLeft, pL_Max, szInput);
copy(szRight, pR_Max, szInput[iStart]);
return;
}
// If delimter is in Input then split at input for max lengths
if (pL_Max >= iEnd)
copy(szLeft, iEnd, szInput);
else
copy(szLeft, pL_Max, szInput);
copy(szRight, pR_Max, szInput[iStart]);
}
/**
* Removes a path from szFilePath leaving the name of the file in szFile for a pMax length.
*
* @param szFilePath String to perform search and replacements on.
* @param szFile Buffer to store file name.
* @param pMax Maximum length of the string buffer.
*
* @noreturn
*/
stock remove_filepath(const szFilePath[], szFile[], pMax)
{
new len = strlen(szFilePath);
while ((--len >= 0) && (szFilePath[len] != '/') && (szFilePath[len] != '\')) { }
copy(szFile, pMax, szFilePath[len + 1]);
return;
}
/**
* Replaces a contained string iteratively.
*
* @note Consider using replace_string() instead.
*
* @note This ensures that no infinite replacements will take place by
* intelligently moving to the next string position each iteration.
*
* @param string String to perform search and replacements on.
* @param len Maximum length of the string buffer.
* @param what String to search for.
* @param with String to replace the search string with.
*
* @return Number of replacements on success, otherwise 0.
*/
stock replace_all(string[], len, const what[], const with[])
{
new pos = 0;
if ((pos = contain(string, what)) == -1)
{
return 0;
}
new total = 0;
new with_len = strlen(with);
new diff = strlen(what) - with_len;
new total_len = strlen(string);
new temp_pos = 0;
while (replace(string[pos], len - pos, what, with) != 0)
{
total++;
/* jump to position after replacement */
pos += with_len;
/* update cached length of string */
total_len -= diff;
/* will the next call be operating on the last character? */
if (pos >= total_len)
{
break;
}
/* find the next position from our offset */
temp_pos = contain(string[pos], what);
/* if it's invalid, we're done */
if (temp_pos == -1)
{
break;
}
/* otherwise, reposition and update counters */
pos += temp_pos;
}
return total;
}
/**
* Breaks a string into pieces and stores each piece into an array of buffers.
*
* @param text The string to split.
* @param split The string to use as a split delimiter.
* @param buffers An array of string buffers (2D array).
* @param maxStrings Number of string buffers (first dimension size).
* @param maxStringLength Maximum length of each string buffer.
* @param copyRemainder False (default) discard excess pieces, true to ignore
* delimiters after last piece.
* @return Number of strings retrieved.
*/
stock explode_string(const text[], const split[], buffers[][], maxStrings, maxStringLength, bool:copyRemainder = false)
{
new reloc_idx, idx, total;
if (maxStrings < 1 || !split[0])
{
return 0;
}
while ((idx = split_string(text[reloc_idx], split, buffers[total], maxStringLength)) != -1)
{
reloc_idx += idx;
if (++total == maxStrings)
{
if (copyRemainder)
{
copy(buffers[total-1], maxStringLength, text[reloc_idx-idx]);
}
return total;
}
}
copy(buffers[total++], maxStringLength, text[reloc_idx]);
return total;
}
/**
* Joins an array of strings into one string, with a "join" string inserted in
* between each given string. This function complements ExplodeString.
*
* @param strings An array of strings.
* @param numStrings Number of strings in the array.
* @param join The join string to insert between each string.
* @param buffer Output buffer to write the joined string to.
* @param maxLength Maximum length of the output buffer.
* @return Number of bytes written to the output buffer.
*/
stock implode_strings(const strings[][], numStrings, const join[], buffer[], maxLength)
{
new total, length, part_length;
new join_length = strlen(join);
for (new i=0; i<numStrings; i++)
{
length = copy(buffer[total], maxLength-total, strings[i]);
total += length;
if (length < part_length)
{
break;
}
if (i != numStrings - 1)
{
length = copy(buffer[total], maxLength-total, join);
total += length;
if (length < join_length)
{
break;
}
}
}
return total;
}