diff options
Diffstat (limited to 'strings/my_strchr.c')
| -rw-r--r-- | strings/my_strchr.c | 104 |
1 files changed, 104 insertions, 0 deletions
diff --git a/strings/my_strchr.c b/strings/my_strchr.c new file mode 100644 index 00000000..323cbd0a --- /dev/null +++ b/strings/my_strchr.c @@ -0,0 +1,104 @@ +/* Copyright (c) 2005, 2011, Oracle and/or its affiliates. + Copyright (c) 2009, 2020, MariaDB Corporation. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; version 2 of the License. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1335 USA */ + +#include "strings_def.h" +#include <m_ctype.h> + +#define NEQ(A, B) ((A) != (B)) +#define EQU(A, B) ((A) == (B)) + +/** + Macro for the body of the string scanning. + + @param CS The character set of the string + @param STR Pointer to beginning of string + @param END Pointer to one-after-end of string + @param ACC Pointer to beginning of accept (or reject) string + @param LEN Length of accept (or reject) string + @param CMP is a function-like for doing the comparison of two characters. + */ + +#define SCAN_STRING(CS, STR, END, ACC, LEN, CMP) \ + do { \ + uint mbl; \ + const char *ptr_str, *ptr_acc; \ + const char *acc_end= (ACC) + (LEN); \ + for (ptr_str= (STR) ; ptr_str < (END) ; ptr_str+= mbl) \ + { \ + mbl= my_ci_charlen_fix((CS), (const uchar *) ptr_str, \ + (const uchar *) (END)); \ + if (mbl < 2) \ + { \ + DBUG_ASSERT(mbl == 1); \ + for (ptr_acc= (ACC) ; ptr_acc < acc_end ; ++ptr_acc) \ + if (CMP(*ptr_acc, *ptr_str)) \ + goto end; \ + } \ + } \ +end: \ + return (size_t) (ptr_str - (STR)); \ + } while (0) + + +/* + my_strchr(cs, str, end, c) returns a pointer to the first place in + str where c (1-byte character) occurs, or NULL if c does not occur + in str. This function is multi-byte safe. + TODO: should be moved to CHARSET_INFO if it's going to be called + frequently. +*/ + +char *my_strchr(CHARSET_INFO *cs, const char *str, const char *end, + pchar c) +{ + while (str < end) + { + uint mbl= my_ismbchar(cs, str, end); + if (mbl < 2) + { + if (*str == c) + return((char *)str); + str++; + } + else + str+= mbl; + } + return(0); +} + +/** + Calculate the length of the initial segment of 'str' which consists + entirely of characters not in 'reject'. + + @note The reject string points to single-byte characters so it is + only possible to find the first occurrence of a single-byte + character. Multi-byte characters in 'str' are treated as not + matching any character in the reject string. + + @todo should be moved to CHARSET_INFO if it's going to be called + frequently. + + @internal The implementation builds on the assumption that 'str' is long, + while 'reject' is short. So it compares each character in string + with the characters in 'reject' in a tight loop over the characters + in 'reject'. +*/ + +size_t my_strcspn(CHARSET_INFO *cs, const char *str, const char *str_end, + const char *reject) +{ + SCAN_STRING(cs, str, str_end, reject, strlen(reject), EQU); +} |