Line data Source code
1 : /*-------------------------------------------------------------------------
2 : *
3 : * ISO 8859 2-16 <--> UTF8
4 : *
5 : * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group
6 : * Portions Copyright (c) 1994, Regents of the University of California
7 : *
8 : * IDENTIFICATION
9 : * src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c
10 : *
11 : *-------------------------------------------------------------------------
12 : */
13 :
14 : #include "postgres.h"
15 : #include "fmgr.h"
16 : #include "mb/pg_wchar.h"
17 : #include "../../Unicode/iso8859_10_to_utf8.map"
18 : #include "../../Unicode/iso8859_13_to_utf8.map"
19 : #include "../../Unicode/iso8859_14_to_utf8.map"
20 : #include "../../Unicode/iso8859_15_to_utf8.map"
21 : #include "../../Unicode/iso8859_2_to_utf8.map"
22 : #include "../../Unicode/iso8859_3_to_utf8.map"
23 : #include "../../Unicode/iso8859_4_to_utf8.map"
24 : #include "../../Unicode/iso8859_5_to_utf8.map"
25 : #include "../../Unicode/iso8859_6_to_utf8.map"
26 : #include "../../Unicode/iso8859_7_to_utf8.map"
27 : #include "../../Unicode/iso8859_8_to_utf8.map"
28 : #include "../../Unicode/iso8859_9_to_utf8.map"
29 : #include "../../Unicode/utf8_to_iso8859_10.map"
30 : #include "../../Unicode/utf8_to_iso8859_13.map"
31 : #include "../../Unicode/utf8_to_iso8859_14.map"
32 : #include "../../Unicode/utf8_to_iso8859_15.map"
33 : #include "../../Unicode/utf8_to_iso8859_16.map"
34 : #include "../../Unicode/utf8_to_iso8859_2.map"
35 : #include "../../Unicode/utf8_to_iso8859_3.map"
36 : #include "../../Unicode/utf8_to_iso8859_4.map"
37 : #include "../../Unicode/utf8_to_iso8859_5.map"
38 : #include "../../Unicode/utf8_to_iso8859_6.map"
39 : #include "../../Unicode/utf8_to_iso8859_7.map"
40 : #include "../../Unicode/utf8_to_iso8859_8.map"
41 : #include "../../Unicode/utf8_to_iso8859_9.map"
42 : #include "../../Unicode/iso8859_16_to_utf8.map"
43 :
44 6 : PG_MODULE_MAGIC_EXT(
45 : .name = "utf8_and_iso8859",
46 : .version = PG_VERSION
47 : );
48 :
49 6 : PG_FUNCTION_INFO_V1(iso8859_to_utf8);
50 6 : PG_FUNCTION_INFO_V1(utf8_to_iso8859);
51 :
52 : /* ----------
53 : * conv_proc(
54 : * INTEGER, -- source encoding id
55 : * INTEGER, -- destination encoding id
56 : * CSTRING, -- source string (null terminated C string)
57 : * CSTRING, -- destination string (null terminated C string)
58 : * INTEGER, -- source string length
59 : * BOOL -- if true, don't throw an error if conversion fails
60 : * ) returns INTEGER;
61 : *
62 : * Returns the number of bytes successfully converted.
63 : * ----------
64 : */
65 :
66 : typedef struct
67 : {
68 : pg_enc encoding;
69 : const pg_mb_radix_tree *map1; /* to UTF8 map name */
70 : const pg_mb_radix_tree *map2; /* from UTF8 map name */
71 : } pg_conv_map;
72 :
73 : static const pg_conv_map maps[] = {
74 : {PG_LATIN2, &iso8859_2_to_unicode_tree,
75 : &iso8859_2_from_unicode_tree}, /* ISO-8859-2 Latin 2 */
76 : {PG_LATIN3, &iso8859_3_to_unicode_tree,
77 : &iso8859_3_from_unicode_tree}, /* ISO-8859-3 Latin 3 */
78 : {PG_LATIN4, &iso8859_4_to_unicode_tree,
79 : &iso8859_4_from_unicode_tree}, /* ISO-8859-4 Latin 4 */
80 : {PG_LATIN5, &iso8859_9_to_unicode_tree,
81 : &iso8859_9_from_unicode_tree}, /* ISO-8859-9 Latin 5 */
82 : {PG_LATIN6, &iso8859_10_to_unicode_tree,
83 : &iso8859_10_from_unicode_tree}, /* ISO-8859-10 Latin 6 */
84 : {PG_LATIN7, &iso8859_13_to_unicode_tree,
85 : &iso8859_13_from_unicode_tree}, /* ISO-8859-13 Latin 7 */
86 : {PG_LATIN8, &iso8859_14_to_unicode_tree,
87 : &iso8859_14_from_unicode_tree}, /* ISO-8859-14 Latin 8 */
88 : {PG_LATIN9, &iso8859_15_to_unicode_tree,
89 : &iso8859_15_from_unicode_tree}, /* ISO-8859-15 Latin 9 */
90 : {PG_LATIN10, &iso8859_16_to_unicode_tree,
91 : &iso8859_16_from_unicode_tree}, /* ISO-8859-16 Latin 10 */
92 : {PG_ISO_8859_5, &iso8859_5_to_unicode_tree,
93 : &iso8859_5_from_unicode_tree}, /* ISO-8859-5 */
94 : {PG_ISO_8859_6, &iso8859_6_to_unicode_tree,
95 : &iso8859_6_from_unicode_tree}, /* ISO-8859-6 */
96 : {PG_ISO_8859_7, &iso8859_7_to_unicode_tree,
97 : &iso8859_7_from_unicode_tree}, /* ISO-8859-7 */
98 : {PG_ISO_8859_8, &iso8859_8_to_unicode_tree,
99 : &iso8859_8_from_unicode_tree}, /* ISO-8859-8 */
100 : };
101 :
102 : Datum
103 111 : iso8859_to_utf8(PG_FUNCTION_ARGS)
104 : {
105 111 : int encoding = PG_GETARG_INT32(0);
106 111 : unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2);
107 111 : unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3);
108 111 : int len = PG_GETARG_INT32(4);
109 111 : bool noError = PG_GETARG_BOOL(5);
110 : int i;
111 :
112 111 : CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8);
113 :
114 993 : for (i = 0; i < lengthof(maps); i++)
115 : {
116 993 : if (encoding == maps[i].encoding)
117 : {
118 : int converted;
119 :
120 111 : converted = LocalToUtf(src, len, dest,
121 111 : maps[i].map1,
122 : NULL, 0,
123 : NULL,
124 : encoding,
125 : noError);
126 84 : PG_RETURN_INT32(converted);
127 : }
128 : }
129 :
130 0 : ereport(ERROR,
131 : (errcode(ERRCODE_INTERNAL_ERROR),
132 : errmsg("unexpected encoding ID %d for ISO 8859 character sets",
133 : encoding)));
134 :
135 : PG_RETURN_INT32(0);
136 : }
137 :
138 : Datum
139 471 : utf8_to_iso8859(PG_FUNCTION_ARGS)
140 : {
141 471 : int encoding = PG_GETARG_INT32(1);
142 471 : unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2);
143 471 : unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3);
144 471 : int len = PG_GETARG_INT32(4);
145 471 : bool noError = PG_GETARG_BOOL(5);
146 : int i;
147 :
148 471 : CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1);
149 :
150 1353 : for (i = 0; i < lengthof(maps); i++)
151 : {
152 1353 : if (encoding == maps[i].encoding)
153 : {
154 : int converted;
155 :
156 471 : converted = UtfToLocal(src, len, dest,
157 471 : maps[i].map2,
158 : NULL, 0,
159 : NULL,
160 : encoding,
161 : noError);
162 273 : PG_RETURN_INT32(converted);
163 : }
164 : }
165 :
166 0 : ereport(ERROR,
167 : (errcode(ERRCODE_INTERNAL_ERROR),
168 : errmsg("unexpected encoding ID %d for ISO 8859 character sets",
169 : encoding)));
170 :
171 : PG_RETURN_INT32(0);
172 : }
|
