1 files changed, 72 insertions, 330 deletions

diff --git a/src/backend/utils/adt/like.c b/src/backend/utils/adt/like.c
index 46f223b38ff..de5d7e7c859 100644
--- a/src/backend/utils/adt/like.c
+++ b/src/backend/utils/adt/like.c
@@ -11,7 +11,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	$PostgreSQL: pgsql/src/backend/utils/adt/like.c,v 1.68 2007/02/27 23:48:08 tgl Exp $
+ *	$PostgreSQL: pgsql/src/backend/utils/adt/like.c,v 1.69 2007/06/02 02:03:42 adunstan Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -28,21 +28,23 @@
 #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	SB_MatchText(char *t, int tlen, char *p, int plen);
+static text *SB_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 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	Generic_Text_IC_like(text *str, text *pat);
+
 /*--------------------
  * Support routine for MatchText. Compares given multibyte streams
  * as wide characters. If they match, returns 1 otherwise returns 0.
  *--------------------
  */
-static int
+static inline int
 wchareq(char *p1, char *p2)
 {
 	int			p1_len;
@@ -72,15 +74,12 @@ wchareq(char *p1, char *p2)
  * 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.
  */
 
+#define NextByte(p, plen)	((p)++, (plen)--)
+
 /* 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 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) \
@@ -90,33 +89,59 @@ wchareq(char *p1, char *p2)
 			 *(dst)++ = *(src)++; \
 	   } while (0)
 
-#define MatchText	MBMatchText
-#define MatchTextIC MBMatchTextIC
+#define MatchText	MB_MatchText
 #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 NextChar(p, plen) NextByte((p), (plen))
 #define CopyAdvChar(dst, src, srclen) (*(dst)++ = *(src)++, (srclen)--)
 
+#define MatchText	SB_MatchText
+#define do_like_escape	SB_do_like_escape
+
+#include "like_match.c"
+
+
+/* setup to compile like_match.c for UTF8 encoding, using fast NextChar */
+
+#define NextChar(p, plen) \
+	do { (p)++; (plen)--; } while ((plen) > 0 && (*(p) & 0xC0) == 0x80 ) 
+#define MatchText	UTF8_MatchText
+
 #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)--)
+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
+Generic_Text_IC_like(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);
 
+	return GenericMatchText(s, slen, p, plen);
+}
 
 /*
  *	interface routines called by the function manager
@@ -138,10 +163,7 @@ namelike(PG_FUNCTION_ARGS)
 	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);
+	result = (GenericMatchText(s, slen, p, plen) == LIKE_TRUE);
 
 	PG_RETURN_BOOL(result);
 }
@@ -162,10 +184,7 @@ namenlike(PG_FUNCTION_ARGS)
 	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);
+	result = (GenericMatchText(s, slen, p, plen) != LIKE_TRUE);
 
 	PG_RETURN_BOOL(result);
 }
@@ -186,10 +205,7 @@ textlike(PG_FUNCTION_ARGS)
 	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);
+	result = (GenericMatchText(s, slen, p, plen) == LIKE_TRUE);
 
 	PG_RETURN_BOOL(result);
 }
@@ -210,10 +226,7 @@ textnlike(PG_FUNCTION_ARGS)
 	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);
+	result = (GenericMatchText(s, slen, p, plen) != LIKE_TRUE);
 
 	PG_RETURN_BOOL(result);
 }
@@ -234,7 +247,7 @@ bytealike(PG_FUNCTION_ARGS)
 	p = VARDATA(pat);
 	plen = (VARSIZE(pat) - VARHDRSZ);
 
-	result = (MatchBytea(s, slen, p, plen) == LIKE_TRUE);
+	result = (SB_MatchText(s, slen, p, plen) == LIKE_TRUE);
 
 	PG_RETURN_BOOL(result);
 }
@@ -255,7 +268,7 @@ byteanlike(PG_FUNCTION_ARGS)
 	p = VARDATA(pat);
 	plen = (VARSIZE(pat) - VARHDRSZ);
 
-	result = (MatchBytea(s, slen, p, plen) != LIKE_TRUE);
+	result = (SB_MatchText(s, slen, p, plen) != LIKE_TRUE);
 
 	PG_RETURN_BOOL(result);
 }
@@ -270,37 +283,11 @@ nameiclike(PG_FUNCTION_ARGS)
 	Name		str = PG_GETARG_NAME(0);
 	text	   *pat = PG_GETARG_TEXT_P(1);
 	bool		result;
-	char	   *s,
-			   *p;
-	int			slen,
-				plen;
-
-	if (pg_database_encoding_max_length() == 1)
-	{
-		s = NameStr(*str);
-		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;
+	text	   *strtext;
 
-		strtext = DatumGetTextP(DirectFunctionCall1(name_text,
+	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);
-	}
+	result = (Generic_Text_IC_like(strtext, pat) == LIKE_TRUE);
 
 	PG_RETURN_BOOL(result);
 }
@@ -311,37 +298,11 @@ nameicnlike(PG_FUNCTION_ARGS)
 	Name		str = PG_GETARG_NAME(0);
 	text	   *pat = PG_GETARG_TEXT_P(1);
 	bool		result;
-	char	   *s,
-			   *p;
-	int			slen,
-				plen;
-
-	if (pg_database_encoding_max_length() == 1)
-	{
-		s = NameStr(*str);
-		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;
+	text	   *strtext;
 
-		strtext = DatumGetTextP(DirectFunctionCall1(name_text,
+	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);
-	}
+	result = (Generic_Text_IC_like(strtext, pat) != LIKE_TRUE);
 
 	PG_RETURN_BOOL(result);
 }
@@ -352,32 +313,8 @@ texticlike(PG_FUNCTION_ARGS)
 	text	   *str = PG_GETARG_TEXT_P(0);
 	text	   *pat = PG_GETARG_TEXT_P(1);
 	bool		result;
-	char	   *s,
-			   *p;
-	int			slen,
-				plen;
 
-	if (pg_database_encoding_max_length() == 1)
-	{
-		s = VARDATA(str);
-		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);
-	}
+	result = (Generic_Text_IC_like(str, pat) == LIKE_TRUE);
 
 	PG_RETURN_BOOL(result);
 }
@@ -388,32 +325,8 @@ texticnlike(PG_FUNCTION_ARGS)
 	text	   *str = PG_GETARG_TEXT_P(0);
 	text	   *pat = PG_GETARG_TEXT_P(1);
 	bool		result;
-	char	   *s,
-			   *p;
-	int			slen,
-				plen;
 
-	if (pg_database_encoding_max_length() == 1)
-	{
-		s = VARDATA(str);
-		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);
-	}
+	result = (Generic_Text_IC_like(str, pat) != LIKE_TRUE);
 
 	PG_RETURN_BOOL(result);
 }
@@ -430,7 +343,7 @@ like_escape(PG_FUNCTION_ARGS)
 	text	   *result;
 
 	if (pg_database_encoding_max_length() == 1)
-		result = do_like_escape(pat, esc);
+		result = SB_do_like_escape(pat, esc);
 	else
 		result = MB_do_like_escape(pat, esc);
 
@@ -446,179 +359,8 @@ like_escape_bytea(PG_FUNCTION_ARGS)
 {
 	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));
+	bytea	   *result = SB_do_like_escape((text *)pat, (text *)esc);
 
-	PG_RETURN_BYTEA_P(result);
+	PG_RETURN_BYTEA_P((bytea *)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() */