database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-11-29 23:43:17 +03:00
Code Activity

Unicode escapes in strings and identifiers

Browse Source
This commit is contained in:
Peter Eisentraut
2008-10-29 08:04:54 +00:00
parent 05bba3d176
commit 06735e3256
18 changed files with 638 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
src/backend/utils/adt/xml.c
View File

@@ -7,7 +7,7 @@
* Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* $PostgreSQL: pgsql/src/backend/utils/adt/xml.c,v 1.79 2008/10/14 17:12:33 tgl Exp $
* $PostgreSQL: pgsql/src/backend/utils/adt/xml.c,v 1.80 2008/10/29 08:04:53 petere Exp $
*
*-------------------------------------------------------------------------
*/
@@ -1497,28 +1497,7 @@ unicode_to_sqlchar(pg_wchar c)
{
static unsigned char utf8string[5]; /* need trailing zero */
if (c <= 0x7F)
{
utf8string[0] = c;
}
else if (c <= 0x7FF)
{
utf8string[0] = 0xC0 | ((c >> 6) & 0x1F);
utf8string[1] = 0x80 | (c & 0x3F);
}
else if (c <= 0xFFFF)
{
utf8string[0] = 0xE0 | ((c >> 12) & 0x0F);
utf8string[1] = 0x80 | ((c >> 6) & 0x3F);
utf8string[2] = 0x80 | (c & 0x3F);
}
else
{
utf8string[0] = 0xF0 | ((c >> 18) & 0x07);
utf8string[1] = 0x80 | ((c >> 12) & 0x3F);
utf8string[2] = 0x80 | ((c >> 6) & 0x3F);
utf8string[3] = 0x80 | (c & 0x3F);
}
unicode_to_utf8(c, utf8string);
return (char *) pg_do_encoding_conversion(utf8string,
pg_mblen((char *) utf8string),

37
src/backend/utils/mb/wchar.c
View File

@@ -1,7 +1,7 @@
/*
* conversion functions between pg_wchar and multibyte streams.
* Tatsuo Ishii
* $PostgreSQL: pgsql/src/backend/utils/mb/wchar.c,v 1.67 2008/10/27 19:37:22 tgl Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/wchar.c,v 1.68 2008/10/29 08:04:53 petere Exp $
*
*/
/* can be used in either frontend or backend */
@@ -419,6 +419,41 @@ pg_utf2wchar_with_len(const unsigned char *from, pg_wchar *to, int len)
return cnt;
}
/*
* Map a Unicode code point to UTF-8. utf8string must have 4 bytes of
* space allocated.
*/
unsigned char *
unicode_to_utf8(pg_wchar c, unsigned char *utf8string)
{
if (c <= 0x7F)
{
utf8string[0] = c;
}
else if (c <= 0x7FF)
{
utf8string[0] = 0xC0 | ((c >> 6) & 0x1F);
utf8string[1] = 0x80 | (c & 0x3F);
}
else if (c <= 0xFFFF)
{
utf8string[0] = 0xE0 | ((c >> 12) & 0x0F);
utf8string[1] = 0x80 | ((c >> 6) & 0x3F);
utf8string[2] = 0x80 | (c & 0x3F);
}
else
{
utf8string[0] = 0xF0 | ((c >> 18) & 0x07);
utf8string[1] = 0x80 | ((c >> 12) & 0x3F);
utf8string[2] = 0x80 | ((c >> 6) & 0x3F);
utf8string[3] = 0x80 | (c & 0x3F);
}
return utf8string;
}
/*
* Return the byte length of a UTF8 character pointed to by s
*