1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
|
/*-------------------------------------------------------------------------
*
* scansup.c
* scanner support routines used by the core lexer
*
* Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
* src/backend/parser/scansup.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include <ctype.h>
#include "mb/pg_wchar.h"
#include "parser/scansup.h"
/*
* downcase_truncate_identifier() --- do appropriate downcasing and
* truncation of an unquoted identifier. Optionally warn of truncation.
*
* Returns a palloc'd string containing the adjusted identifier.
*
* Note: in some usages the passed string is not null-terminated.
*
* Note: the API of this function is designed to allow for downcasing
* transformations that increase the string length, but we don't yet
* support that. If you want to implement it, you'll need to fix
* SplitIdentifierString() in utils/adt/varlena.c.
*/
char *
downcase_truncate_identifier(const char *ident, int len, bool warn)
{
return downcase_identifier(ident, len, warn, true);
}
/*
* a workhorse for downcase_truncate_identifier
*/
char *
downcase_identifier(const char *ident, int len, bool warn, bool truncate)
{
char *result;
int i;
bool enc_is_single_byte;
result = palloc(len + 1);
enc_is_single_byte = pg_database_encoding_max_length() == 1;
/*
* SQL99 specifies Unicode-aware case normalization, which we don't yet
* have the infrastructure for. Instead we use tolower() to provide a
* locale-aware translation. However, there are some locales where this
* is not right either (eg, Turkish may do strange things with 'i' and
* 'I'). Our current compromise is to use tolower() for characters with
* the high bit set, as long as they aren't part of a multi-byte
* character, and use an ASCII-only downcasing for 7-bit characters.
*/
for (i = 0; i < len; i++)
{
unsigned char ch = (unsigned char) ident[i];
if (ch >= 'A' && ch <= 'Z')
ch += 'a' - 'A';
else if (enc_is_single_byte && IS_HIGHBIT_SET(ch) && isupper(ch))
ch = tolower(ch);
result[i] = (char) ch;
}
result[i] = '\0';
if (i >= NAMEDATALEN && truncate)
truncate_identifier(result, i, warn);
return result;
}
/*
* truncate_identifier() --- truncate an identifier to NAMEDATALEN-1 bytes.
*
* The given string is modified in-place, if necessary. A warning is
* issued if requested.
*
* We require the caller to pass in the string length since this saves a
* strlen() call in some common usages.
*/
void
truncate_identifier(char *ident, int len, bool warn)
{
if (len >= NAMEDATALEN)
{
len = pg_mbcliplen(ident, len, NAMEDATALEN - 1);
if (warn)
ereport(NOTICE,
(errcode(ERRCODE_NAME_TOO_LONG),
errmsg("identifier \"%s\" will be truncated to \"%.*s\"",
ident, len, ident)));
ident[len] = '\0';
}
}
/*
* scanner_isspace() --- return true if flex scanner considers char whitespace
*
* This should be used instead of the potentially locale-dependent isspace()
* function when it's important to match the lexer's behavior.
*
* In principle we might need similar functions for isalnum etc, but for the
* moment only isspace seems needed.
*/
bool
scanner_isspace(char ch)
{
/* This must match scan.l's list of {space} characters */
if (ch == ' ' ||
ch == '\t' ||
ch == '\n' ||
ch == '\r' ||
ch == '\f')
return true;
return false;
}
|
