1 /* Copyright (c) 2005, 2019, Oracle and/or its affiliates. All rights reserved.
2
3 This program is free software; you can redistribute it and/or modify
4 it under the terms of the GNU General Public License, version 2.0,
5 as published by the Free Software Foundation.
6
7 This program is also distributed with certain software (including
8 but not limited to OpenSSL) that is licensed under separate terms,
9 as designated in a particular file or component or in included license
10 documentation. The authors of MySQL hereby grant you an additional
11 permission to link the program and your derivative works with the
12 separately licensed software that they have included with MySQL.
13
14 Without limiting anything contained in the foregoing, this file,
15 which is part of C Driver for MySQL (Connector/C), is also subject to the
16 Universal FOSS Exception, version 1.0, a copy of which can be found at
17 http://oss.oracle.com/licenses/universal-foss-exception.
18
19 This program is distributed in the hope that it will be useful,
20 but WITHOUT ANY WARRANTY; without even the implied warranty of
21 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
22 GNU General Public License, version 2.0, for more details.
23
24 You should have received a copy of the GNU General Public License
25 along with this program; if not, write to the Free Software
26 Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */
27
28 #include <my_global.h>
29 #include "m_string.h"
30 #include "m_ctype.h"
31
32
33 /*
34 Return pointer to first occurrence of character in a multi-byte string
35 or NULL if the character doesn't appear in the multi-byte string or
36 invalid character in charset of multi-byte string is found.
37
38 @param cs Pointer to charset info.
39 @param str Pointer to start of multi-byte string.
40 @param end Pointer to end of multi-byte string.
41 @param c Character to find first occurrence of.
42
43 @return Pointer to first occurence of c in str or NULL.
44 */
45
my_strchr(const CHARSET_INFO * cs,const char * str,const char * end,pchar c)46 char *my_strchr(const CHARSET_INFO *cs, const char *str, const char *end,
47 pchar c)
48 {
49 while (str < end)
50 {
51 uint mbl= my_mbcharlen(cs, *(uchar *)str);
52 if (mbl == 0)
53 return NULL;
54 if (mbl == 1)
55 {
56 if (*str == c)
57 return((char *)str);
58 str++;
59 }
60 else
61 str+= mbl;
62 }
63 return(0);
64 }
65
66
67 /**
68 Calculate the length of the initial segment of 'str' which consists
69 entirely of characters not in 'reject'.
70
71 @param cs Pointer to charset info.
72 @param str Pointer to multi-byte string.
73 @param str_end Pointer to end of multi-byte string.
74 @param reject Pointer to start of single-byte reject string.
75 @param reject_length Length of single-byte reject string.
76
77 @return Length of segment of multi-byte string that doesn't contain
78 any character of the single-byte reject string or zero if an
79 invalid encoding of a character of the multi-byte string is
80 found.
81
82 @note The reject string points to single-byte characters so it is
83 only possible to find the first occurrence of a single-byte
84 character. Multi-byte characters in 'str' are treated as not
85 matching any character in the reject string.
86 This method returns zero if an invalid encoding of any character
87 in the string 'str' using charset 'cs' is found.
88
89 @todo should be moved to CHARSET_INFO if it's going to be called
90 frequently.
91
92 @internal The implementation builds on the assumption that 'str' is long,
93 while 'reject' is short. So it compares each character in string
94 with the characters in 'reject' in a tight loop over the characters
95 in 'reject'.
96 */
97
my_strcspn(const CHARSET_INFO * cs,const char * str,const char * str_end,const char * reject,int reject_length)98 size_t my_strcspn(const CHARSET_INFO *cs, const char *str,
99 const char *str_end, const char *reject,
100 int reject_length)
101 {
102 const char *ptr_str, *ptr_reject;
103 const char *reject_end= reject + reject_length;
104 uint mbl= 0;
105
106 for (ptr_str= str; ptr_str < str_end; ptr_str+= mbl)
107 {
108 mbl= my_mbcharlen(cs, *((uchar *) ptr_str));
109
110 if (mbl == 0)
111 return 0;
112
113 if (mbl == 1)
114 {
115 for (ptr_reject= reject; ptr_reject < reject_end; ++ptr_reject)
116 {
117 if (*ptr_reject == *ptr_str)
118 return (size_t) (ptr_str - str);
119 }
120 }
121 }
122 return (size_t) (ptr_str - str);
123 }
124