utf8proc
view pgsql/utf8proc_pgsql.c @ 1:61a89ecc2fb9
Version 0.2
- changed behaviour of PostgreSQL function to return NULL in case of invalid input, rather than raising an exceptional condition
- improved efficiency of PostgreSQL function (no transformation to C string is done)
- added -fpic compiler flag in Makefile
- fixed bug in the C code for the ruby library (usage of non-existent function)
- changed behaviour of PostgreSQL function to return NULL in case of invalid input, rather than raising an exceptional condition
- improved efficiency of PostgreSQL function (no transformation to C string is done)
- added -fpic compiler flag in Makefile
- fixed bug in the C code for the ruby library (usage of non-existent function)
| author | jbe |
|---|---|
| date | Tue Jun 20 12:00:00 2006 +0200 (2006-06-20) |
| parents | a0368662434c |
| children | aaad485d5335 |
line source
1 /*
2 * Copyright (c) 2006, FlexiGuided GmbH, Berlin, Germany
3 * Author: Jan Behrens <jan.behrens@flexiguided.de>
4 * All rights reserved.
5 *
6 * Redistribution and use in source and binary forms, with or without
7 * modification, are permitted provided that the following conditions are
8 * met:
9 *
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in the
14 * documentation and/or other materials provided with the distribution.
15 * 3. Neither the name of the FlexiGuided GmbH nor the names of its
16 * contributors may be used to endorse or promote products derived from
17 * this software without specific prior written permission.
18 *
19 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
22 * PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER
23 * OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
24 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
25 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
26 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
27 * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
28 * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
29 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
30 *
31 */
34 /*
35 * File name: pgsql/utf8proc_pgsql.c
36 * Version: 0.2
37 * Last changed: 2006-06-05
38 *
39 * Description:
40 * PostgreSQL extension to provide a function 'unifold', which can be used
41 * to case-fold and normalize index fields.
42 */
45 #include "../utf8proc.c"
47 #include <postgres.h>
48 #include <utils/elog.h>
49 #include <fmgr.h>
50 #include <string.h>
51 #include <unistd.h>
52 #include <utils/builtins.h>
54 #define UTF8PROC_PGSQL_OPTS ( UTF8PROC_REJECTNA | \
55 UTF8PROC_COMPOSE | UTF8PROC_IGNORE | UTF8PROC_STRIPCC | UTF8PROC_CASEFOLD)
57 PG_FUNCTION_INFO_V1(utf8proc_pgsql_unifold);
58 Datum utf8proc_pgsql_unifold(PG_FUNCTION_ARGS) {
59 text *input_string;
60 text *output_string = NULL;
61 ssize_t result;
62 input_string = PG_GETARG_TEXT_P(0);
63 do {
64 result = utf8proc_decompose(
65 VARDATA(input_string), VARSIZE(input_string) - VARHDRSZ,
66 NULL, 0, UTF8PROC_PGSQL_OPTS
67 );
68 if (result < 0) break;
69 if (result > (SIZE_MAX-1-VARHDRSZ)/sizeof(int32_t)) {
70 result = UTF8PROC_ERROR_OVERFLOW;
71 break;
72 }
73 output_string = palloc(result * sizeof(int32_t) + 1 + VARHDRSZ);
74 // reserve one extra byte for termination
75 if (!output_string) {
76 result = UTF8PROC_ERROR_NOMEM;
77 break;
78 }
79 result = utf8proc_decompose(
80 VARDATA(input_string), VARSIZE(input_string) - VARHDRSZ,
81 (int32_t *)VARDATA(output_string), result, UTF8PROC_PGSQL_OPTS);
82 if (result < 0) break;
83 result = utf8proc_reencode((int32_t *)VARDATA(output_string), result,
84 UTF8PROC_PGSQL_OPTS);
85 } while (0);
86 PG_FREE_IF_COPY(input_string, 0);
87 if (result < 0) {
88 int sqlerrcode;
89 if (output_string) pfree(output_string);
90 switch(result) {
91 case UTF8PROC_ERROR_NOMEM:
92 sqlerrcode = ERRCODE_OUT_OF_MEMORY; break;
93 case UTF8PROC_ERROR_OVERFLOW:
94 sqlerrcode = ERRCODE_PROGRAM_LIMIT_EXCEEDED; break;
95 case UTF8PROC_ERROR_INVALIDUTF8:
96 case UTF8PROC_ERROR_NOTASSIGNED:
97 PG_RETURN_NULL();
98 default:
99 sqlerrcode = ERRCODE_INTERNAL_ERROR;
100 }
101 ereport(ERROR, (
102 errcode(sqlerrcode),
103 errmsg("%s", utf8proc_errmsg(result))
104 ));
105 } else {
106 VARATT_SIZEP(output_string) = result + VARHDRSZ;
107 PG_RETURN_TEXT_P(output_string);
108 }
109 PG_RETURN_NULL(); // prohibit compiler warning
110 }