Re: UTF8MatchText - Mailing list pgsql-patches
| From | Andrew Dunstan |
|---|---|
| Subject | Re: UTF8MatchText |
| Date | |
| Msg-id | 46505986.1020005@dunslane.net Whole thread Raw |
| In response to | Re: UTF8MatchText (Andrew Dunstan <andrew@dunslane.net>) |
| Responses |
Re: UTF8MatchText
(Tom Lane <tgl@sss.pgh.pa.us>)
|
| List | pgsql-patches |
oops. patch attached this time
Andrew Dunstan wrote:
>
>
> I wrote:
>>
>>
>>>
>>> It is only when you have a pattern like '%_' when this is a problem
>>> and we could detect this and do byte by byte when it's not. Now we
>>> check (*p == '\\') || (*p == '_') in each iteration when we scan
>>> over characters for '%', and we could do it once and have different
>>> loops for the two cases.
>>>
>>> Other than this part that I think can be optimized I don't see
>>> anything wrong with the idea behind the patch. To make the '%' case
>>> fast might be an important optimization for a lot of use cases. It's
>>> not uncommon that '%' matches a bigger part of the string than the
>>> rest of the pattern.
>>>
>>
>>
>> Are you sure? The big remaining char-matching bottleneck will surely
>> be in the code that scans for a place to start matching a %. But
>> that's exactly where we can't use byte matching for cases where the
>> charset might include AB and BA as characters - the pattern might
>> contain %BA and the string AB. However, this isn't a danger for UTF8,
>> which leads me to think that we do indeed need a special case for
>> UTF8, but for a different improvement from that proposed in the
>> original patch. I'll post an updated patch shortly.
>>
>
> Here is a patch that implements this. Please analyse for possible
> breakage.
>
> cheers
>
> andrew
>
>
>
> ---------------------------(end of broadcast)---------------------------
> TIP 9: In versions below 8.0, the planner will ignore your desire to
> choose an index scan if your joining column's datatypes do not
> match
>
Index: src/backend/utils/adt/like.c
===================================================================
RCS file: /cvsroot/pgsql/src/backend/utils/adt/like.c,v
retrieving revision 1.68
diff -c -r1.68 like.c
*** src/backend/utils/adt/like.c 27 Feb 2007 23:48:08 -0000 1.68
--- src/backend/utils/adt/like.c 20 May 2007 14:16:22 -0000
***************
*** 28,48 ****
#define LIKE_ABORT (-1)
! static int MatchText(char *t, int tlen, char *p, int plen);
! static int MatchTextIC(char *t, int tlen, char *p, int plen);
! static int MatchBytea(char *t, int tlen, char *p, int plen);
! static text *do_like_escape(text *, text *);
! static int MBMatchText(char *t, int tlen, char *p, int plen);
! static int MBMatchTextIC(char *t, int tlen, char *p, int plen);
static text *MB_do_like_escape(text *, text *);
/*--------------------
* Support routine for MatchText. Compares given multibyte streams
* as wide characters. If they match, returns 1 otherwise returns 0.
*--------------------
*/
! static int
wchareq(char *p1, char *p2)
{
int p1_len;
--- 28,51 ----
#define LIKE_ABORT (-1)
! static int SB_MatchText(char *t, int tlen, char *p, int plen);
! static int SB_MatchTextIC(char *t, int tlen, char *p, int plen);
! static text *SB_do_like_escape(text *, text *);
! static int MB_MatchText(char *t, int tlen, char *p, int plen);
static text *MB_do_like_escape(text *, text *);
+ static int UTF8_MatchText(char *t, int tlen, char *p, int plen);
+
+ static int GenericMatchText(char *s, int slen, char* p, int plen);
+ static int mbtexticlike(text *str, text *pat);
+
/*--------------------
* Support routine for MatchText. Compares given multibyte streams
* as wide characters. If they match, returns 1 otherwise returns 0.
*--------------------
*/
! static inline int
wchareq(char *p1, char *p2)
{
int p1_len;
***************
*** 72,86 ****
* of getting a single character transformed to the system's wchar_t format.
* So now, we just downcase the strings using lower() and apply regular LIKE
* comparison. This should be revisited when we install better locale support.
- *
- * Note that MBMatchText and MBMatchTextIC do exactly the same thing now.
- * Is it worth refactoring to avoid duplicated code? They might become
- * different again in the future.
*/
/* Set up to compile like_match.c for multibyte characters */
#define CHAREQ(p1, p2) wchareq(p1, p2)
- #define ICHAREQ(p1, p2) wchareq(p1, p2)
#define NextChar(p, plen) \
do { int __l = pg_mblen(p); (p) +=__l; (plen) -=__l; } while (0)
#define CopyAdvChar(dst, src, srclen) \
--- 75,87 ----
* of getting a single character transformed to the system's wchar_t format.
* So now, we just downcase the strings using lower() and apply regular LIKE
* comparison. This should be revisited when we install better locale support.
*/
+ #define NextByte(p, plen) ((p)++, (plen)--)
+ #define BYTEEQ(p1, p2) (*(p1) == *(p2))
+
/* Set up to compile like_match.c for multibyte characters */
#define CHAREQ(p1, p2) wchareq(p1, p2)
#define NextChar(p, plen) \
do { int __l = pg_mblen(p); (p) +=__l; (plen) -=__l; } while (0)
#define CopyAdvChar(dst, src, srclen) \
***************
*** 89,122 ****
while (__l-- > 0) \
*(dst)++ = *(src)++; \
} while (0)
! #define MatchText MBMatchText
! #define MatchTextIC MBMatchTextIC
#define do_like_escape MB_do_like_escape
#include "like_match.c"
! #undef CHAREQ
! #undef ICHAREQ
! #undef NextChar
! #undef CopyAdvChar
! #undef MatchText
! #undef MatchTextIC
! #undef do_like_escape
/* Set up to compile like_match.c for single-byte characters */
! #define CHAREQ(p1, p2) (*(p1) == *(p2))
! #define ICHAREQ(p1, p2) (tolower((unsigned char) *(p1)) == tolower((unsigned char) *(p2)))
! #define NextChar(p, plen) ((p)++, (plen)--)
#define CopyAdvChar(dst, src, srclen) (*(dst)++ = *(src)++, (srclen)--)
#include "like_match.c"
! /* And some support for BYTEA */
! #define BYTEA_CHAREQ(p1, p2) (*(p1) == *(p2))
! #define BYTEA_NextChar(p, plen) ((p)++, (plen)--)
! #define BYTEA_CopyAdvChar(dst, src, srclen) (*(dst)++ = *(src)++, (srclen)--)
/*
* interface routines called by the function manager
--- 90,173 ----
while (__l-- > 0) \
*(dst)++ = *(src)++; \
} while (0)
+ #define BYTEEQIC(b1, b2) BYTEEQ(b1, b2)
! #define MatchText MB_MatchText
#define do_like_escape MB_do_like_escape
#include "like_match.c"
! /* Set up to compile like_match.c for UTF8 characters */
! #define CHAREQ(p1, p2) wchareq(p1, p2)
! #define NextChar(p, plen) \
! do { int __l = pg_mblen(p); (p) +=__l; (plen) -=__l; } while (0)
! #define CopyAdvChar(dst, src, srclen) \
! do { int __l = pg_mblen(src); \
! (srclen) -= __l; \
! while (__l-- > 0) \
! *(dst)++ = *(src)++; \
! } while (0)
! #define BYTEEQIC(b1, b2) BYTEEQ(b1, b2)
! #define UTF8_OPT
!
! #define MatchText UTF8_MatchText
!
! #include "like_match.c"
/* Set up to compile like_match.c for single-byte characters */
! #define CHAREQ(p1, p2) BYTEEQ(p1, p2)
! #define NextChar(p, plen) NextByte(p, plen)
#define CopyAdvChar(dst, src, srclen) (*(dst)++ = *(src)++, (srclen)--)
+ #define BYTEEQIC(b1, b2) BYTEEQ(b1, b2)
+
+ #define MatchText SB_MatchText
+ #define do_like_escape SB_do_like_escape
#include "like_match.c"
! /* set up to compile like_match.c for single byte case insensitive matching */
+ #define CHAREQ(p1, p2) (tolower((unsigned char) *(p1)) == tolower((unsigned char) *(p2)))
+ #define NextChar(p, plen) NextByte(p, plen)
+ #define CopyAdvChar(dst, src, srclen) (*(dst)++ = *(src)++, (srclen)--)
+ #define BYTEEQIC(b1, b2) CHAREQ(b1, b2)
+
+ #define MatchText SB_MatchTextIC
+
+ #include "like_match.c"
+
+ static inline int
+ GenericMatchText(char *s, int slen, char* p, int plen)
+ {
+ if (pg_database_encoding_max_length() == 1)
+ return SB_MatchText(s, slen, p, plen);
+ else if (GetDatabaseEncoding() == PG_UTF8)
+ return UTF8_MatchText(s, slen, p, plen);
+ else
+ return MB_MatchText(s, slen, p, plen);
+ }
+
+ static inline int
+ mbtexticlike(text *str, text *pat)
+ {
+ char *s,
+ *p;
+ int slen,
+ plen;
+
+ /* Force inputs to lower case to achieve case insensitivity */
+ str = DatumGetTextP(DirectFunctionCall1(lower, PointerGetDatum(str)));
+ pat = DatumGetTextP(DirectFunctionCall1(lower, PointerGetDatum(pat)));
+ s = VARDATA(str);
+ slen = (VARSIZE(str) - VARHDRSZ);
+ p = VARDATA(pat);
+ plen = (VARSIZE(pat) - VARHDRSZ);
+
+ if (GetDatabaseEncoding() == PG_UTF8)
+ return UTF8_MatchText(s, slen, p, plen);
+ else
+ return MB_MatchText(s, slen, p, plen);
+ }
/*
* interface routines called by the function manager
***************
*** 138,147 ****
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! if (pg_database_encoding_max_length() == 1)
! result = (MatchText(s, slen, p, plen) == LIKE_TRUE);
! else
! result = (MBMatchText(s, slen, p, plen) == LIKE_TRUE);
PG_RETURN_BOOL(result);
}
--- 189,195 ----
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (GenericMatchText(s, slen, p, plen) == LIKE_TRUE);
PG_RETURN_BOOL(result);
}
***************
*** 162,171 ****
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! if (pg_database_encoding_max_length() == 1)
! result = (MatchText(s, slen, p, plen) != LIKE_TRUE);
! else
! result = (MBMatchText(s, slen, p, plen) != LIKE_TRUE);
PG_RETURN_BOOL(result);
}
--- 210,216 ----
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (GenericMatchText(s, slen, p, plen) != LIKE_TRUE);
PG_RETURN_BOOL(result);
}
***************
*** 186,195 ****
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! if (pg_database_encoding_max_length() == 1)
! result = (MatchText(s, slen, p, plen) == LIKE_TRUE);
! else
! result = (MBMatchText(s, slen, p, plen) == LIKE_TRUE);
PG_RETURN_BOOL(result);
}
--- 231,237 ----
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (GenericMatchText(s, slen, p, plen) == LIKE_TRUE);
PG_RETURN_BOOL(result);
}
***************
*** 210,219 ****
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! if (pg_database_encoding_max_length() == 1)
! result = (MatchText(s, slen, p, plen) != LIKE_TRUE);
! else
! result = (MBMatchText(s, slen, p, plen) != LIKE_TRUE);
PG_RETURN_BOOL(result);
}
--- 252,258 ----
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (GenericMatchText(s, slen, p, plen) != LIKE_TRUE);
PG_RETURN_BOOL(result);
}
***************
*** 234,240 ****
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (MatchBytea(s, slen, p, plen) == LIKE_TRUE);
PG_RETURN_BOOL(result);
}
--- 273,279 ----
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (SB_MatchText(s, slen, p, plen) == LIKE_TRUE);
PG_RETURN_BOOL(result);
}
***************
*** 255,261 ****
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (MatchBytea(s, slen, p, plen) != LIKE_TRUE);
PG_RETURN_BOOL(result);
}
--- 294,300 ----
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (SB_MatchText(s, slen, p, plen) != LIKE_TRUE);
PG_RETURN_BOOL(result);
}
***************
*** 281,305 ****
slen = strlen(s);
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (MatchTextIC(s, slen, p, plen) == LIKE_TRUE);
}
else
{
- /* Force inputs to lower case to achieve case insensitivity */
text *strtext;
strtext = DatumGetTextP(DirectFunctionCall1(name_text,
NameGetDatum(str)));
! strtext = DatumGetTextP(DirectFunctionCall1(lower,
! PointerGetDatum(strtext)));
! pat = DatumGetTextP(DirectFunctionCall1(lower,
! PointerGetDatum(pat)));
!
! s = VARDATA(strtext);
! slen = (VARSIZE(strtext) - VARHDRSZ);
! p = VARDATA(pat);
! plen = (VARSIZE(pat) - VARHDRSZ);
! result = (MBMatchTextIC(s, slen, p, plen) == LIKE_TRUE);
}
PG_RETURN_BOOL(result);
--- 320,334 ----
slen = strlen(s);
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (SB_MatchTextIC(s, slen, p, plen) == LIKE_TRUE);
}
else
{
text *strtext;
strtext = DatumGetTextP(DirectFunctionCall1(name_text,
NameGetDatum(str)));
! result = (mbtexticlike(strtext, pat) == LIKE_TRUE);
}
PG_RETURN_BOOL(result);
***************
*** 322,346 ****
slen = strlen(s);
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (MatchTextIC(s, slen, p, plen) != LIKE_TRUE);
}
else
{
- /* Force inputs to lower case to achieve case insensitivity */
text *strtext;
strtext = DatumGetTextP(DirectFunctionCall1(name_text,
NameGetDatum(str)));
! strtext = DatumGetTextP(DirectFunctionCall1(lower,
! PointerGetDatum(strtext)));
! pat = DatumGetTextP(DirectFunctionCall1(lower,
! PointerGetDatum(pat)));
!
! s = VARDATA(strtext);
! slen = (VARSIZE(strtext) - VARHDRSZ);
! p = VARDATA(pat);
! plen = (VARSIZE(pat) - VARHDRSZ);
! result = (MBMatchTextIC(s, slen, p, plen) != LIKE_TRUE);
}
PG_RETURN_BOOL(result);
--- 351,365 ----
slen = strlen(s);
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (SB_MatchTextIC(s, slen, p, plen) != LIKE_TRUE);
}
else
{
text *strtext;
strtext = DatumGetTextP(DirectFunctionCall1(name_text,
NameGetDatum(str)));
! result = (mbtexticlike(strtext, pat) != LIKE_TRUE);
}
PG_RETURN_BOOL(result);
***************
*** 363,383 ****
slen = (VARSIZE(str) - VARHDRSZ);
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (MatchTextIC(s, slen, p, plen) == LIKE_TRUE);
}
else
! {
! /* Force inputs to lower case to achieve case insensitivity */
! str = DatumGetTextP(DirectFunctionCall1(lower,
! PointerGetDatum(str)));
! pat = DatumGetTextP(DirectFunctionCall1(lower,
! PointerGetDatum(pat)));
! s = VARDATA(str);
! slen = (VARSIZE(str) - VARHDRSZ);
! p = VARDATA(pat);
! plen = (VARSIZE(pat) - VARHDRSZ);
! result = (MBMatchTextIC(s, slen, p, plen) == LIKE_TRUE);
! }
PG_RETURN_BOOL(result);
}
--- 382,391 ----
slen = (VARSIZE(str) - VARHDRSZ);
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (SB_MatchTextIC(s, slen, p, plen) == LIKE_TRUE);
}
else
! result = (mbtexticlike(str, pat) == LIKE_TRUE);
PG_RETURN_BOOL(result);
}
***************
*** 399,419 ****
slen = (VARSIZE(str) - VARHDRSZ);
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (MatchTextIC(s, slen, p, plen) != LIKE_TRUE);
}
else
! {
! /* Force inputs to lower case to achieve case insensitivity */
! str = DatumGetTextP(DirectFunctionCall1(lower,
! PointerGetDatum(str)));
! pat = DatumGetTextP(DirectFunctionCall1(lower,
! PointerGetDatum(pat)));
! s = VARDATA(str);
! slen = (VARSIZE(str) - VARHDRSZ);
! p = VARDATA(pat);
! plen = (VARSIZE(pat) - VARHDRSZ);
! result = (MBMatchTextIC(s, slen, p, plen) != LIKE_TRUE);
! }
PG_RETURN_BOOL(result);
}
--- 407,416 ----
slen = (VARSIZE(str) - VARHDRSZ);
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
! result = (SB_MatchTextIC(s, slen, p, plen) != LIKE_TRUE);
}
else
! result = (mbtexticlike(str, pat) != LIKE_TRUE);
PG_RETURN_BOOL(result);
}
***************
*** 430,436 ****
text *result;
if (pg_database_encoding_max_length() == 1)
! result = do_like_escape(pat, esc);
else
result = MB_do_like_escape(pat, esc);
--- 427,433 ----
text *result;
if (pg_database_encoding_max_length() == 1)
! result = SB_do_like_escape(pat, esc);
else
result = MB_do_like_escape(pat, esc);
***************
*** 446,624 ****
{
bytea *pat = PG_GETARG_BYTEA_P(0);
bytea *esc = PG_GETARG_BYTEA_P(1);
! bytea *result;
! char *p,
! *e,
! *r;
! int plen,
! elen;
! bool afterescape;
!
! p = VARDATA(pat);
! plen = (VARSIZE(pat) - VARHDRSZ);
! e = VARDATA(esc);
! elen = (VARSIZE(esc) - VARHDRSZ);
!
! /*
! * Worst-case pattern growth is 2x --- unlikely, but it's hardly worth
! * trying to calculate the size more accurately than that.
! */
! result = (text *) palloc(plen * 2 + VARHDRSZ);
! r = VARDATA(result);
!
! if (elen == 0)
! {
! /*
! * No escape character is wanted. Double any backslashes in the
! * pattern to make them act like ordinary characters.
! */
! while (plen > 0)
! {
! if (*p == '\\')
! *r++ = '\\';
! BYTEA_CopyAdvChar(r, p, plen);
! }
! }
! else
! {
! /*
! * The specified escape must be only a single character.
! */
! BYTEA_NextChar(e, elen);
! if (elen != 0)
! ereport(ERROR,
! (errcode(ERRCODE_INVALID_ESCAPE_SEQUENCE),
! errmsg("invalid escape string"),
! errhint("Escape string must be empty or one character.")));
!
! e = VARDATA(esc);
!
! /*
! * If specified escape is '\', just copy the pattern as-is.
! */
! if (*e == '\\')
! {
! memcpy(result, pat, VARSIZE(pat));
! PG_RETURN_BYTEA_P(result);
! }
!
! /*
! * Otherwise, convert occurrences of the specified escape character to
! * '\', and double occurrences of '\' --- unless they immediately
! * follow an escape character!
! */
! afterescape = false;
! while (plen > 0)
! {
! if (BYTEA_CHAREQ(p, e) && !afterescape)
! {
! *r++ = '\\';
! BYTEA_NextChar(p, plen);
! afterescape = true;
! }
! else if (*p == '\\')
! {
! *r++ = '\\';
! if (!afterescape)
! *r++ = '\\';
! BYTEA_NextChar(p, plen);
! afterescape = false;
! }
! else
! {
! BYTEA_CopyAdvChar(r, p, plen);
! afterescape = false;
! }
! }
! }
! SET_VARSIZE(result, r - ((char *) result));
!
! PG_RETURN_BYTEA_P(result);
}
- /*
- * Same as above, but specifically for bytea (binary) datatype
- */
- static int
- MatchBytea(char *t, int tlen, char *p, int plen)
- {
- /* Fast path for match-everything pattern */
- if ((plen == 1) && (*p == '%'))
- return LIKE_TRUE;
-
- while ((tlen > 0) && (plen > 0))
- {
- if (*p == '\\')
- {
- /* Next pattern char must match literally, whatever it is */
- BYTEA_NextChar(p, plen);
- if ((plen <= 0) || !BYTEA_CHAREQ(t, p))
- return LIKE_FALSE;
- }
- else if (*p == '%')
- {
- /* %% is the same as % according to the SQL standard */
- /* Advance past all %'s */
- while ((plen > 0) && (*p == '%'))
- BYTEA_NextChar(p, plen);
- /* Trailing percent matches everything. */
- if (plen <= 0)
- return LIKE_TRUE;
-
- /*
- * Otherwise, scan for a text position at which we can match the
- * rest of the pattern.
- */
- while (tlen > 0)
- {
- /*
- * Optimization to prevent most recursion: don't recurse
- * unless first pattern char might match this text char.
- */
- if (BYTEA_CHAREQ(t, p) || (*p == '\\') || (*p == '_'))
- {
- int matched = MatchBytea(t, tlen, p, plen);
-
- if (matched != LIKE_FALSE)
- return matched; /* TRUE or ABORT */
- }
-
- BYTEA_NextChar(t, tlen);
- }
-
- /*
- * End of text with no match, so no point in trying later places
- * to start matching this pattern.
- */
- return LIKE_ABORT;
- }
- else if ((*p != '_') && !BYTEA_CHAREQ(t, p))
- {
- /*
- * Not the single-character wildcard and no explicit match? Then
- * time to quit...
- */
- return LIKE_FALSE;
- }
-
- BYTEA_NextChar(t, tlen);
- BYTEA_NextChar(p, plen);
- }
-
- if (tlen > 0)
- return LIKE_FALSE; /* end of pattern, but not of text */
-
- /* End of input string. Do we have matching pattern remaining? */
- while ((plen > 0) && (*p == '%')) /* allow multiple %'s at end of
- * pattern */
- BYTEA_NextChar(p, plen);
- if (plen <= 0)
- return LIKE_TRUE;
-
- /*
- * End of text with no match, so no point in trying later places to start
- * matching this pattern.
- */
- return LIKE_ABORT;
- } /* MatchBytea() */
--- 443,450 ----
{
bytea *pat = PG_GETARG_BYTEA_P(0);
bytea *esc = PG_GETARG_BYTEA_P(1);
! bytea *result = SB_do_like_escape((text *)pat, (text *)esc);
! PG_RETURN_BYTEA_P((bytea *)result);
}
Index: src/backend/utils/adt/like_match.c
===================================================================
RCS file: /cvsroot/pgsql/src/backend/utils/adt/like_match.c,v
retrieving revision 1.15
diff -c -r1.15 like_match.c
*** src/backend/utils/adt/like_match.c 27 Feb 2007 23:48:08 -0000 1.15
--- src/backend/utils/adt/like_match.c 20 May 2007 14:16:24 -0000
***************
*** 9,19 ****
* Before the inclusion, we need to define following macros:
*
* CHAREQ
! * ICHAREQ
* NextChar
* CopyAdvChar
* MatchText (MBMatchText)
- * MatchTextIC (MBMatchTextIC)
* do_like_escape (MB_do_like_escape)
*
* Copyright (c) 1996-2007, PostgreSQL Global Development Group
--- 9,18 ----
* Before the inclusion, we need to define following macros:
*
* CHAREQ
! * BYTEEQIC
* NextChar
* CopyAdvChar
* MatchText (MBMatchText)
* do_like_escape (MB_do_like_escape)
*
* Copyright (c) 1996-2007, PostgreSQL Global Development Group
***************
*** 70,75 ****
--- 69,82 ----
*--------------------
*/
+ #ifdef UTF8_OPT
+ #define PCT_CHAREQ(c1, c2) BYTEEQ(c1, c2)
+ #define PCT_NEXT(a, b) NextByte(a, b)
+ #else
+ #define PCT_CHAREQ(c1, c2) CHAREQ(c1, c2)
+ #define PCT_NEXT(a, b) NextChar(a, b)
+ #endif
+
static int
MatchText(char *t, int tlen, char *p, int plen)
{
***************
*** 81,89 ****
{
if (*p == '\\')
{
! /* Next pattern char must match literally, whatever it is */
! NextChar(p, plen);
! if ((plen <= 0) || !CHAREQ(t, p))
return LIKE_FALSE;
}
else if (*p == '%')
--- 88,96 ----
{
if (*p == '\\')
{
! /* Next byte must match literally, whatever it is */
! NextByte(p, plen);
! if ((plen <= 0) || !BYTEEQ(t, p))
return LIKE_FALSE;
}
else if (*p == '%')
***************
*** 91,97 ****
/* %% is the same as % according to the SQL standard */
/* Advance past all %'s */
while ((plen > 0) && (*p == '%'))
! NextChar(p, plen);
/* Trailing percent matches everything. */
if (plen <= 0)
return LIKE_TRUE;
--- 98,104 ----
/* %% is the same as % according to the SQL standard */
/* Advance past all %'s */
while ((plen > 0) && (*p == '%'))
! NextByte(p, plen);
/* Trailing percent matches everything. */
if (plen <= 0)
return LIKE_TRUE;
***************
*** 106,112 ****
* Optimization to prevent most recursion: don't recurse
* unless first pattern char might match this text char.
*/
! if (CHAREQ(t, p) || (*p == '\\') || (*p == '_'))
{
int matched = MatchText(t, tlen, p, plen);
--- 113,119 ----
* Optimization to prevent most recursion: don't recurse
* unless first pattern char might match this text char.
*/
! if (PCT_CHAREQ(t, p) || (*p == '\\') || (*p == '_'))
{
int matched = MatchText(t, tlen, p, plen);
***************
*** 114,120 ****
return matched; /* TRUE or ABORT */
}
! NextChar(t, tlen);
}
/*
--- 121,127 ----
return matched; /* TRUE or ABORT */
}
! PCT_NEXT(t, tlen);
}
/*
***************
*** 123,215 ****
*/
return LIKE_ABORT;
}
! else if ((*p != '_') && !CHAREQ(t, p))
! {
! /*
! * Not the single-character wildcard and no explicit match? Then
! * time to quit...
! */
! return LIKE_FALSE;
! }
!
! NextChar(t, tlen);
! NextChar(p, plen);
! }
!
! if (tlen > 0)
! return LIKE_FALSE; /* end of pattern, but not of text */
!
! /* End of input string. Do we have matching pattern remaining? */
! while ((plen > 0) && (*p == '%')) /* allow multiple %'s at end of
! * pattern */
! NextChar(p, plen);
! if (plen <= 0)
! return LIKE_TRUE;
!
! /*
! * End of text with no match, so no point in trying later places to start
! * matching this pattern.
! */
! return LIKE_ABORT;
! } /* MatchText() */
!
! /*
! * Same as above, but ignore case
! */
! static int
! MatchTextIC(char *t, int tlen, char *p, int plen)
! {
! /* Fast path for match-everything pattern */
! if ((plen == 1) && (*p == '%'))
! return LIKE_TRUE;
!
! while ((tlen > 0) && (plen > 0))
! {
! if (*p == '\\')
! {
! /* Next pattern char must match literally, whatever it is */
! NextChar(p, plen);
! if ((plen <= 0) || !ICHAREQ(t, p))
! return LIKE_FALSE;
! }
! else if (*p == '%')
{
! /* %% is the same as % according to the SQL standard */
! /* Advance past all %'s */
! while ((plen > 0) && (*p == '%'))
! NextChar(p, plen);
! /* Trailing percent matches everything. */
! if (plen <= 0)
! return LIKE_TRUE;
!
! /*
! * Otherwise, scan for a text position at which we can match the
! * rest of the pattern.
! */
! while (tlen > 0)
! {
! /*
! * Optimization to prevent most recursion: don't recurse
! * unless first pattern char might match this text char.
! */
! if (ICHAREQ(t, p) || (*p == '\\') || (*p == '_'))
! {
! int matched = MatchTextIC(t, tlen, p, plen);
!
! if (matched != LIKE_FALSE)
! return matched; /* TRUE or ABORT */
! }
!
! NextChar(t, tlen);
! }
!
! /*
! * End of text with no match, so no point in trying later places
! * to start matching this pattern.
! */
! return LIKE_ABORT;
}
! else if ((*p != '_') && !ICHAREQ(t, p))
{
/*
* Not the single-character wildcard and no explicit match? Then
--- 130,142 ----
*/
return LIKE_ABORT;
}
! else if (*p == '_')
{
! NextChar(t, tlen);
! NextByte(p, plen);
! continue;
}
! else if (!BYTEEQIC(t, p))
{
/*
* Not the single-character wildcard and no explicit match? Then
***************
*** 217,225 ****
*/
return LIKE_FALSE;
}
!
! NextChar(t, tlen);
! NextChar(p, plen);
}
if (tlen > 0)
--- 144,156 ----
*/
return LIKE_FALSE;
}
! /*
! * It is safe to use NextByte instead of NextChar here, even for
! * multi-byte character sets, because we are not following
! * immediately after a wildcard character.
! */
! NextByte(t, tlen);
! NextByte(p, plen);
}
if (tlen > 0)
***************
*** 228,234 ****
/* End of input string. Do we have matching pattern remaining? */
while ((plen > 0) && (*p == '%')) /* allow multiple %'s at end of
* pattern */
! NextChar(p, plen);
if (plen <= 0)
return LIKE_TRUE;
--- 159,165 ----
/* End of input string. Do we have matching pattern remaining? */
while ((plen > 0) && (*p == '%')) /* allow multiple %'s at end of
* pattern */
! NextByte(p, plen);
if (plen <= 0)
return LIKE_TRUE;
***************
*** 237,248 ****
* matching this pattern.
*/
return LIKE_ABORT;
! } /* MatchTextIC() */
/*
* like_escape() --- given a pattern and an ESCAPE string,
* convert the pattern to use Postgres' standard backslash escape convention.
*/
static text *
do_like_escape(text *pat, text *esc)
{
--- 168,181 ----
* matching this pattern.
*/
return LIKE_ABORT;
! } /* MatchText() */
/*
* like_escape() --- given a pattern and an ESCAPE string,
* convert the pattern to use Postgres' standard backslash escape convention.
*/
+ #ifdef do_like_escape
+
static text *
do_like_escape(text *pat, text *esc)
{
***************
*** 336,338 ****
--- 269,288 ----
return result;
}
+ #endif /* do_like_escape */
+
+ #undef CHAREQ
+ #undef BYTEEQIC
+ #undef PCT_CHAREQ
+ #undef PCT_NEXT
+ #undef NextChar
+ #undef CopyAdvChar
+ #undef MatchText
+
+ #ifdef do_like_escape
+ #undef do_like_escape
+ #endif
+
+ #ifdef UTF8_OPT
+ #undef UTF8_OPT
+ #endif
pgsql-patches by date: