Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to content

Commit 2c09c93

Browse files
hlinnakahlinnaka
committed
Remove code points < 0x80 from character conversion tables.
PostgreSQL treats characters with < 0x80 leading byte as plain ASCII, and they are not even passed to the conversion routines. There is no point in having them in the conversion tables. Everything in the tables were direct ASCII-ASCII mappings, except for two: * SHIFT_JIS_2004 code point 0x5C (backslash in ASCII) was mapped to Unicode YEN SIGN character. * Unicode 0x5C (backslash again) was mapped to "REVERSE SOLIDUS" in SHIFT_JIS_2004 These mappings never had any effect, so there's no functional change from removing them. Discussion: https://postgr.es/m/08e7892a-d55c-eefe-76e6-7910bc8dd1f3@iki.fi
1 parent b2cc748 commit 2c09c93

File tree

4 files changed

+0
-512
lines changed

4 files changed

+0
-512
lines changed

‎src/backend/utils/mb/Unicode/euc_jis_2004_to_utf8.map

Lines changed: 0 additions & 128 deletions
Original file line numberDiff line numberDiff line change
@@ -2,134 +2,6 @@
22
* This file was generated by UCS_to_EUC_JIS_2004.pl
33
*/
44
static const pg_local_to_utf LUmapEUC_JIS_2004[] = {
5-
{0x000000, 0x00000000}, /* U+0000 <control> */
6-
{0x000001, 0x00000001}, /* U+0001 <control> */
7-
{0x000002, 0x00000002}, /* U+0002 <control> */
8-
{0x000003, 0x00000003}, /* U+0003 <control> */
9-
{0x000004, 0x00000004}, /* U+0004 <control> */
10-
{0x000005, 0x00000005}, /* U+0005 <control> */
11-
{0x000006, 0x00000006}, /* U+0006 <control> */
12-
{0x000007, 0x00000007}, /* U+0007 <control> */
13-
{0x000008, 0x00000008}, /* U+0008 <control> */
14-
{0x000009, 0x00000009}, /* U+0009 <control> */
15-
{0x00000a, 0x0000000a}, /* U+000A <control> */
16-
{0x00000b, 0x0000000b}, /* U+000B <control> */
17-
{0x00000c, 0x0000000c}, /* U+000C <control> */
18-
{0x00000d, 0x0000000d}, /* U+000D <control> */
19-
{0x00000e, 0x0000000e}, /* U+000E <control> */
20-
{0x00000f, 0x0000000f}, /* U+000F <control> */
21-
{0x000010, 0x00000010}, /* U+0010 <control> */
22-
{0x000011, 0x00000011}, /* U+0011 <control> */
23-
{0x000012, 0x00000012}, /* U+0012 <control> */
24-
{0x000013, 0x00000013}, /* U+0013 <control> */
25-
{0x000014, 0x00000014}, /* U+0014 <control> */
26-
{0x000015, 0x00000015}, /* U+0015 <control> */
27-
{0x000016, 0x00000016}, /* U+0016 <control> */
28-
{0x000017, 0x00000017}, /* U+0017 <control> */
29-
{0x000018, 0x00000018}, /* U+0018 <control> */
30-
{0x000019, 0x00000019}, /* U+0019 <control> */
31-
{0x00001a, 0x0000001a}, /* U+001A <control> */
32-
{0x00001b, 0x0000001b}, /* U+001B <control> */
33-
{0x00001c, 0x0000001c}, /* U+001C <control> */
34-
{0x00001d, 0x0000001d}, /* U+001D <control> */
35-
{0x00001e, 0x0000001e}, /* U+001E <control> */
36-
{0x00001f, 0x0000001f}, /* U+001F <control> */
37-
{0x000020, 0x00000020}, /* U+0020 SPACE */
38-
{0x000021, 0x00000021}, /* U+0021 EXCLAMATION MARK */
39-
{0x000022, 0x00000022}, /* U+0022 QUOTATION MARK */
40-
{0x000023, 0x00000023}, /* U+0023 NUMBER SIGN */
41-
{0x000024, 0x00000024}, /* U+0024 DOLLAR SIGN */
42-
{0x000025, 0x00000025}, /* U+0025 PERCENT SIGN */
43-
{0x000026, 0x00000026}, /* U+0026 AMPERSAND */
44-
{0x000027, 0x00000027}, /* U+0027 APOSTROPHE */
45-
{0x000028, 0x00000028}, /* U+0028 LEFT PARENTHESIS */
46-
{0x000029, 0x00000029}, /* U+0029 RIGHT PARENTHESIS */
47-
{0x00002a, 0x0000002a}, /* U+002A ASTERISK */
48-
{0x00002b, 0x0000002b}, /* U+002B PLUS SIGN */
49-
{0x00002c, 0x0000002c}, /* U+002C COMMA */
50-
{0x00002d, 0x0000002d}, /* U+002D HYPHEN-MINUS */
51-
{0x00002e, 0x0000002e}, /* U+002E FULL STOP */
52-
{0x00002f, 0x0000002f}, /* U+002F SOLIDUS */
53-
{0x000030, 0x00000030}, /* U+0030 DIGIT ZERO */
54-
{0x000031, 0x00000031}, /* U+0031 DIGIT ONE */
55-
{0x000032, 0x00000032}, /* U+0032 DIGIT TWO */
56-
{0x000033, 0x00000033}, /* U+0033 DIGIT THREE */
57-
{0x000034, 0x00000034}, /* U+0034 DIGIT FOUR */
58-
{0x000035, 0x00000035}, /* U+0035 DIGIT FIVE */
59-
{0x000036, 0x00000036}, /* U+0036 DIGIT SIX */
60-
{0x000037, 0x00000037}, /* U+0037 DIGIT SEVEN */
61-
{0x000038, 0x00000038}, /* U+0038 DIGIT EIGHT */
62-
{0x000039, 0x00000039}, /* U+0039 DIGIT NINE */
63-
{0x00003a, 0x0000003a}, /* U+003A COLON */
64-
{0x00003b, 0x0000003b}, /* U+003B SEMICOLON */
65-
{0x00003c, 0x0000003c}, /* U+003C LESS-THAN SIGN */
66-
{0x00003d, 0x0000003d}, /* U+003D EQUALS SIGN */
67-
{0x00003e, 0x0000003e}, /* U+003E GREATER-THAN SIGN */
68-
{0x00003f, 0x0000003f}, /* U+003F QUESTION MARK */
69-
{0x000040, 0x00000040}, /* U+0040 COMMERCIAL AT */
70-
{0x000041, 0x00000041}, /* U+0041 LATIN CAPITAL LETTER A */
71-
{0x000042, 0x00000042}, /* U+0042 LATIN CAPITAL LETTER B */
72-
{0x000043, 0x00000043}, /* U+0043 LATIN CAPITAL LETTER C */
73-
{0x000044, 0x00000044}, /* U+0044 LATIN CAPITAL LETTER D */
74-
{0x000045, 0x00000045}, /* U+0045 LATIN CAPITAL LETTER E */
75-
{0x000046, 0x00000046}, /* U+0046 LATIN CAPITAL LETTER F */
76-
{0x000047, 0x00000047}, /* U+0047 LATIN CAPITAL LETTER G */
77-
{0x000048, 0x00000048}, /* U+0048 LATIN CAPITAL LETTER H */
78-
{0x000049, 0x00000049}, /* U+0049 LATIN CAPITAL LETTER I */
79-
{0x00004a, 0x0000004a}, /* U+004A LATIN CAPITAL LETTER J */
80-
{0x00004b, 0x0000004b}, /* U+004B LATIN CAPITAL LETTER K */
81-
{0x00004c, 0x0000004c}, /* U+004C LATIN CAPITAL LETTER L */
82-
{0x00004d, 0x0000004d}, /* U+004D LATIN CAPITAL LETTER M */
83-
{0x00004e, 0x0000004e}, /* U+004E LATIN CAPITAL LETTER N */
84-
{0x00004f, 0x0000004f}, /* U+004F LATIN CAPITAL LETTER O */
85-
{0x000050, 0x00000050}, /* U+0050 LATIN CAPITAL LETTER P */
86-
{0x000051, 0x00000051}, /* U+0051 LATIN CAPITAL LETTER Q */
87-
{0x000052, 0x00000052}, /* U+0052 LATIN CAPITAL LETTER R */
88-
{0x000053, 0x00000053}, /* U+0053 LATIN CAPITAL LETTER S */
89-
{0x000054, 0x00000054}, /* U+0054 LATIN CAPITAL LETTER T */
90-
{0x000055, 0x00000055}, /* U+0055 LATIN CAPITAL LETTER U */
91-
{0x000056, 0x00000056}, /* U+0056 LATIN CAPITAL LETTER V */
92-
{0x000057, 0x00000057}, /* U+0057 LATIN CAPITAL LETTER W */
93-
{0x000058, 0x00000058}, /* U+0058 LATIN CAPITAL LETTER X */
94-
{0x000059, 0x00000059}, /* U+0059 LATIN CAPITAL LETTER Y */
95-
{0x00005a, 0x0000005a}, /* U+005A LATIN CAPITAL LETTER Z */
96-
{0x00005b, 0x0000005b}, /* U+005B LEFT SQUARE BRACKET */
97-
{0x00005c, 0x0000005c}, /* U+005C REVERSE SOLIDUS */
98-
{0x00005d, 0x0000005d}, /* U+005D RIGHT SQUARE BRACKET */
99-
{0x00005e, 0x0000005e}, /* U+005E CIRCUMFLEX ACCENT */
100-
{0x00005f, 0x0000005f}, /* U+005F LOW LINE */
101-
{0x000060, 0x00000060}, /* U+0060 GRAVE ACCENT */
102-
{0x000061, 0x00000061}, /* U+0061 LATIN SMALL LETTER A */
103-
{0x000062, 0x00000062}, /* U+0062 LATIN SMALL LETTER B */
104-
{0x000063, 0x00000063}, /* U+0063 LATIN SMALL LETTER C */
105-
{0x000064, 0x00000064}, /* U+0064 LATIN SMALL LETTER D */
106-
{0x000065, 0x00000065}, /* U+0065 LATIN SMALL LETTER E */
107-
{0x000066, 0x00000066}, /* U+0066 LATIN SMALL LETTER F */
108-
{0x000067, 0x00000067}, /* U+0067 LATIN SMALL LETTER G */
109-
{0x000068, 0x00000068}, /* U+0068 LATIN SMALL LETTER H */
110-
{0x000069, 0x00000069}, /* U+0069 LATIN SMALL LETTER I */
111-
{0x00006a, 0x0000006a}, /* U+006A LATIN SMALL LETTER J */
112-
{0x00006b, 0x0000006b}, /* U+006B LATIN SMALL LETTER K */
113-
{0x00006c, 0x0000006c}, /* U+006C LATIN SMALL LETTER L */
114-
{0x00006d, 0x0000006d}, /* U+006D LATIN SMALL LETTER M */
115-
{0x00006e, 0x0000006e}, /* U+006E LATIN SMALL LETTER N */
116-
{0x00006f, 0x0000006f}, /* U+006F LATIN SMALL LETTER O */
117-
{0x000070, 0x00000070}, /* U+0070 LATIN SMALL LETTER P */
118-
{0x000071, 0x00000071}, /* U+0071 LATIN SMALL LETTER Q */
119-
{0x000072, 0x00000072}, /* U+0072 LATIN SMALL LETTER R */
120-
{0x000073, 0x00000073}, /* U+0073 LATIN SMALL LETTER S */
121-
{0x000074, 0x00000074}, /* U+0074 LATIN SMALL LETTER T */
122-
{0x000075, 0x00000075}, /* U+0075 LATIN SMALL LETTER U */
123-
{0x000076, 0x00000076}, /* U+0076 LATIN SMALL LETTER V */
124-
{0x000077, 0x00000077}, /* U+0077 LATIN SMALL LETTER W */
125-
{0x000078, 0x00000078}, /* U+0078 LATIN SMALL LETTER X */
126-
{0x000079, 0x00000079}, /* U+0079 LATIN SMALL LETTER Y */
127-
{0x00007a, 0x0000007a}, /* U+007A LATIN SMALL LETTER Z */
128-
{0x00007b, 0x0000007b}, /* U+007B LEFT CURLY BRACKET */
129-
{0x00007c, 0x0000007c}, /* U+007C VERTICAL LINE */
130-
{0x00007d, 0x0000007d}, /* U+007D RIGHT CURLY BRACKET */
131-
{0x00007e, 0x0000007e}, /* U+007E TILDE */
132-
{0x00007f, 0x0000007f}, /* U+007F <control> */
1335
{0x000080, 0x0000c280}, /* U+0080 <control> */
1346
{0x000081, 0x0000c281}, /* U+0081 <control> */
1357
{0x000082, 0x0000c282}, /* U+0082 <control> */

‎src/backend/utils/mb/Unicode/shift_jis_2004_to_utf8.map

Lines changed: 0 additions & 128 deletions
Original file line numberDiff line numberDiff line change
@@ -2,134 +2,6 @@
22
* This file was generated by UCS_to_SHIFTJIS_2004.pl
33
*/
44
static const pg_local_to_utf LUmapSHIFT_JIS_2004[] = {
5-
{0x0000, 0x00000000}, /* U+0000 <control> */
6-
{0x0001, 0x00000001}, /* U+0001 <control> */
7-
{0x0002, 0x00000002}, /* U+0002 <control> */
8-
{0x0003, 0x00000003}, /* U+0003 <control> */
9-
{0x0004, 0x00000004}, /* U+0004 <control> */
10-
{0x0005, 0x00000005}, /* U+0005 <control> */
11-
{0x0006, 0x00000006}, /* U+0006 <control> */
12-
{0x0007, 0x00000007}, /* U+0007 <control> */
13-
{0x0008, 0x00000008}, /* U+0008 <control> */
14-
{0x0009, 0x00000009}, /* U+0009 <control> */
15-
{0x000a, 0x0000000a}, /* U+000A <control> */
16-
{0x000b, 0x0000000b}, /* U+000B <control> */
17-
{0x000c, 0x0000000c}, /* U+000C <control> */
18-
{0x000d, 0x0000000d}, /* U+000D <control> */
19-
{0x000e, 0x0000000e}, /* U+000E <control> */
20-
{0x000f, 0x0000000f}, /* U+000F <control> */
21-
{0x0010, 0x00000010}, /* U+0010 <control> */
22-
{0x0011, 0x00000011}, /* U+0011 <control> */
23-
{0x0012, 0x00000012}, /* U+0012 <control> */
24-
{0x0013, 0x00000013}, /* U+0013 <control> */
25-
{0x0014, 0x00000014}, /* U+0014 <control> */
26-
{0x0015, 0x00000015}, /* U+0015 <control> */
27-
{0x0016, 0x00000016}, /* U+0016 <control> */
28-
{0x0017, 0x00000017}, /* U+0017 <control> */
29-
{0x0018, 0x00000018}, /* U+0018 <control> */
30-
{0x0019, 0x00000019}, /* U+0019 <control> */
31-
{0x001a, 0x0000001a}, /* U+001A <control> */
32-
{0x001b, 0x0000001b}, /* U+001B <control> */
33-
{0x001c, 0x0000001c}, /* U+001C <control> */
34-
{0x001d, 0x0000001d}, /* U+001D <control> */
35-
{0x001e, 0x0000001e}, /* U+001E <control> */
36-
{0x001f, 0x0000001f}, /* U+001F <control> */
37-
{0x0020, 0x00000020}, /* U+0020 SPACE */
38-
{0x0021, 0x00000021}, /* U+0021 EXCLAMATION MARK */
39-
{0x0022, 0x00000022}, /* U+0022 QUOTATION MARK */
40-
{0x0023, 0x00000023}, /* U+0023 NUMBER SIGN */
41-
{0x0024, 0x00000024}, /* U+0024 DOLLAR SIGN */
42-
{0x0025, 0x00000025}, /* U+0025 PERCENT SIGN */
43-
{0x0026, 0x00000026}, /* U+0026 AMPERSAND */
44-
{0x0027, 0x00000027}, /* U+0027 APOSTROPHE */
45-
{0x0028, 0x00000028}, /* U+0028 LEFT PARENTHESIS */
46-
{0x0029, 0x00000029}, /* U+0029 RIGHT PARENTHESIS */
47-
{0x002a, 0x0000002a}, /* U+002A ASTERISK */
48-
{0x002b, 0x0000002b}, /* U+002B PLUS SIGN */
49-
{0x002c, 0x0000002c}, /* U+002C COMMA */
50-
{0x002d, 0x0000002d}, /* U+002D HYPHEN-MINUS */
51-
{0x002e, 0x0000002e}, /* U+002E FULL STOP */
52-
{0x002f, 0x0000002f}, /* U+002F SOLIDUS */
53-
{0x0030, 0x00000030}, /* U+0030 DIGIT ZERO */
54-
{0x0031, 0x00000031}, /* U+0031 DIGIT ONE */
55-
{0x0032, 0x00000032}, /* U+0032 DIGIT TWO */
56-
{0x0033, 0x00000033}, /* U+0033 DIGIT THREE */
57-
{0x0034, 0x00000034}, /* U+0034 DIGIT FOUR */
58-
{0x0035, 0x00000035}, /* U+0035 DIGIT FIVE */
59-
{0x0036, 0x00000036}, /* U+0036 DIGIT SIX */
60-
{0x0037, 0x00000037}, /* U+0037 DIGIT SEVEN */
61-
{0x0038, 0x00000038}, /* U+0038 DIGIT EIGHT */
62-
{0x0039, 0x00000039}, /* U+0039 DIGIT NINE */
63-
{0x003a, 0x0000003a}, /* U+003A COLON */
64-
{0x003b, 0x0000003b}, /* U+003B SEMICOLON */
65-
{0x003c, 0x0000003c}, /* U+003C LESS-THAN SIGN */
66-
{0x003d, 0x0000003d}, /* U+003D EQUALS SIGN */
67-
{0x003e, 0x0000003e}, /* U+003E GREATER-THAN SIGN */
68-
{0x003f, 0x0000003f}, /* U+003F QUESTION MARK */
69-
{0x0040, 0x00000040}, /* U+0040 COMMERCIAL AT */
70-
{0x0041, 0x00000041}, /* U+0041 LATIN CAPITAL LETTER A */
71-
{0x0042, 0x00000042}, /* U+0042 LATIN CAPITAL LETTER B */
72-
{0x0043, 0x00000043}, /* U+0043 LATIN CAPITAL LETTER C */
73-
{0x0044, 0x00000044}, /* U+0044 LATIN CAPITAL LETTER D */
74-
{0x0045, 0x00000045}, /* U+0045 LATIN CAPITAL LETTER E */
75-
{0x0046, 0x00000046}, /* U+0046 LATIN CAPITAL LETTER F */
76-
{0x0047, 0x00000047}, /* U+0047 LATIN CAPITAL LETTER G */
77-
{0x0048, 0x00000048}, /* U+0048 LATIN CAPITAL LETTER H */
78-
{0x0049, 0x00000049}, /* U+0049 LATIN CAPITAL LETTER I */
79-
{0x004a, 0x0000004a}, /* U+004A LATIN CAPITAL LETTER J */
80-
{0x004b, 0x0000004b}, /* U+004B LATIN CAPITAL LETTER K */
81-
{0x004c, 0x0000004c}, /* U+004C LATIN CAPITAL LETTER L */
82-
{0x004d, 0x0000004d}, /* U+004D LATIN CAPITAL LETTER M */
83-
{0x004e, 0x0000004e}, /* U+004E LATIN CAPITAL LETTER N */
84-
{0x004f, 0x0000004f}, /* U+004F LATIN CAPITAL LETTER O */
85-
{0x0050, 0x00000050}, /* U+0050 LATIN CAPITAL LETTER P */
86-
{0x0051, 0x00000051}, /* U+0051 LATIN CAPITAL LETTER Q */
87-
{0x0052, 0x00000052}, /* U+0052 LATIN CAPITAL LETTER R */
88-
{0x0053, 0x00000053}, /* U+0053 LATIN CAPITAL LETTER S */
89-
{0x0054, 0x00000054}, /* U+0054 LATIN CAPITAL LETTER T */
90-
{0x0055, 0x00000055}, /* U+0055 LATIN CAPITAL LETTER U */
91-
{0x0056, 0x00000056}, /* U+0056 LATIN CAPITAL LETTER V */
92-
{0x0057, 0x00000057}, /* U+0057 LATIN CAPITAL LETTER W */
93-
{0x0058, 0x00000058}, /* U+0058 LATIN CAPITAL LETTER X */
94-
{0x0059, 0x00000059}, /* U+0059 LATIN CAPITAL LETTER Y */
95-
{0x005a, 0x0000005a}, /* U+005A LATIN CAPITAL LETTER Z */
96-
{0x005b, 0x0000005b}, /* U+005B LEFT SQUARE BRACKET */
97-
{0x005c, 0x0000c2a5}, /* U+00A5 YEN SIGN */
98-
{0x005d, 0x0000005d}, /* U+005D RIGHT SQUARE BRACKET */
99-
{0x005e, 0x0000005e}, /* U+005E CIRCUMFLEX ACCENT */
100-
{0x005f, 0x0000005f}, /* U+005F LOW LINE */
101-
{0x0060, 0x00000060}, /* U+0060 GRAVE ACCENT */
102-
{0x0061, 0x00000061}, /* U+0061 LATIN SMALL LETTER A */
103-
{0x0062, 0x00000062}, /* U+0062 LATIN SMALL LETTER B */
104-
{0x0063, 0x00000063}, /* U+0063 LATIN SMALL LETTER C */
105-
{0x0064, 0x00000064}, /* U+0064 LATIN SMALL LETTER D */
106-
{0x0065, 0x00000065}, /* U+0065 LATIN SMALL LETTER E */
107-
{0x0066, 0x00000066}, /* U+0066 LATIN SMALL LETTER F */
108-
{0x0067, 0x00000067}, /* U+0067 LATIN SMALL LETTER G */
109-
{0x0068, 0x00000068}, /* U+0068 LATIN SMALL LETTER H */
110-
{0x0069, 0x00000069}, /* U+0069 LATIN SMALL LETTER I */
111-
{0x006a, 0x0000006a}, /* U+006A LATIN SMALL LETTER J */
112-
{0x006b, 0x0000006b}, /* U+006B LATIN SMALL LETTER K */
113-
{0x006c, 0x0000006c}, /* U+006C LATIN SMALL LETTER L */
114-
{0x006d, 0x0000006d}, /* U+006D LATIN SMALL LETTER M */
115-
{0x006e, 0x0000006e}, /* U+006E LATIN SMALL LETTER N */
116-
{0x006f, 0x0000006f}, /* U+006F LATIN SMALL LETTER O */
117-
{0x0070, 0x00000070}, /* U+0070 LATIN SMALL LETTER P */
118-
{0x0071, 0x00000071}, /* U+0071 LATIN SMALL LETTER Q */
119-
{0x0072, 0x00000072}, /* U+0072 LATIN SMALL LETTER R */
120-
{0x0073, 0x00000073}, /* U+0073 LATIN SMALL LETTER S */
121-
{0x0074, 0x00000074}, /* U+0074 LATIN SMALL LETTER T */
122-
{0x0075, 0x00000075}, /* U+0075 LATIN SMALL LETTER U */
123-
{0x0076, 0x00000076}, /* U+0076 LATIN SMALL LETTER V */
124-
{0x0077, 0x00000077}, /* U+0077 LATIN SMALL LETTER W */
125-
{0x0078, 0x00000078}, /* U+0078 LATIN SMALL LETTER X */
126-
{0x0079, 0x00000079}, /* U+0079 LATIN SMALL LETTER Y */
127-
{0x007a, 0x0000007a}, /* U+007A LATIN SMALL LETTER Z */
128-
{0x007b, 0x0000007b}, /* U+007B LEFT CURLY BRACKET */
129-
{0x007c, 0x0000007c}, /* U+007C VERTICAL LINE */
130-
{0x007d, 0x0000007d}, /* U+007D RIGHT CURLY BRACKET */
131-
{0x007e, 0x00e280be}, /* U+203E OVERLINE */
132-
{0x007f, 0x0000007f}, /* U+007F <control> */
1335
{0x00a1, 0x00efbda1}, /* U+FF61 HALFWIDTH IDEOGRAPHIC FULL STOP */
1346
{0x00a2, 0x00efbda2}, /* U+FF62 HALFWIDTH LEFT CORNER BRACKET */
1357
{0x00a3, 0x00efbda3}, /* U+FF63 HALFWIDTH RIGHT CORNER BRACKET */

0 commit comments

Comments
 (0)