utf8proc
view pgsql/utf8proc_pgsql.c @ 5:c18366878af9
Version 1.0.2
- included a check in Integer#utf8, which raises an exception, if the given code-point is invalid because of being too high (this was missing yet)
- added support for PostgreSQL version 8.2
- included a check in Integer#utf8, which raises an exception, if the given code-point is invalid because of being too high (this was missing yet)
- added support for PostgreSQL version 8.2
| author | jbe |
|---|---|
| date | Tue Dec 26 12:00:00 2006 +0100 (2006-12-26) |
| parents | 4ee0d5f54af1 |
| children | fcfd8c836c64 |
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: 1.0
37 * Last changed: 2006-09-17
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 #ifdef PG_MODULE_MAGIC
55 PG_MODULE_MAGIC;
56 #endif
58 #define UTF8PROC_PGSQL_OPTS ( UTF8PROC_REJECTNA | UTF8PROC_COMPAT | \
59 UTF8PROC_COMPOSE | UTF8PROC_STABLE | UTF8PROC_IGNORE | UTF8PROC_STRIPCC | \
60 UTF8PROC_NLF2LF | UTF8PROC_CASEFOLD | UTF8PROC_LUMP )
62 PG_FUNCTION_INFO_V1(utf8proc_pgsql_unifold);
63 Datum utf8proc_pgsql_unifold(PG_FUNCTION_ARGS) {
64 text *input_string;
65 text *output_string = NULL;
66 ssize_t result;
67 input_string = PG_GETARG_TEXT_P(0);
68 do {
69 result = utf8proc_decompose(
70 VARDATA(input_string), VARSIZE(input_string) - VARHDRSZ,
71 NULL, 0, UTF8PROC_PGSQL_OPTS
72 );
73 if (result < 0) break;
74 if (result > (SIZE_MAX-1-VARHDRSZ)/sizeof(int32_t)) {
75 result = UTF8PROC_ERROR_OVERFLOW;
76 break;
77 }
78 output_string = palloc(result * sizeof(int32_t) + 1 + VARHDRSZ);
79 // reserve one extra byte for termination
80 if (!output_string) {
81 result = UTF8PROC_ERROR_NOMEM;
82 break;
83 }
84 result = utf8proc_decompose(
85 VARDATA(input_string), VARSIZE(input_string) - VARHDRSZ,
86 (int32_t *)VARDATA(output_string), result, UTF8PROC_PGSQL_OPTS);
87 if (result < 0) break;
88 result = utf8proc_reencode((int32_t *)VARDATA(output_string), result,
89 UTF8PROC_PGSQL_OPTS);
90 } while (0);
91 PG_FREE_IF_COPY(input_string, 0);
92 if (result < 0) {
93 int sqlerrcode;
94 if (output_string) pfree(output_string);
95 switch(result) {
96 case UTF8PROC_ERROR_NOMEM:
97 sqlerrcode = ERRCODE_OUT_OF_MEMORY; break;
98 case UTF8PROC_ERROR_OVERFLOW:
99 sqlerrcode = ERRCODE_PROGRAM_LIMIT_EXCEEDED; break;
100 case UTF8PROC_ERROR_INVALIDUTF8:
101 case UTF8PROC_ERROR_NOTASSIGNED:
102 PG_RETURN_NULL();
103 default:
104 sqlerrcode = ERRCODE_INTERNAL_ERROR;
105 }
106 ereport(ERROR, (
107 errcode(sqlerrcode),
108 errmsg("%s", utf8proc_errmsg(result))
109 ));
110 } else {
111 VARATT_SIZEP(output_string) = result + VARHDRSZ;
112 PG_RETURN_TEXT_P(output_string);
113 }
114 PG_RETURN_NULL(); // prohibit compiler warning
115 }