diff -cpr HEAD/src/backend/utils/adt/like.c DropMBMatchTextIC/src/backend/utils/adt/like.c *** HEAD/src/backend/utils/adt/like.c Thu Mar 1 09:40:18 2007 --- DropMBMatchTextIC/src/backend/utils/adt/like.c Mon Apr 9 11:22:26 2007 *************** static int MatchBytea(char *t, int tlen, *** 34,48 **** 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; --- 34,50 ---- static text *do_like_escape(text *, text *); static int MBMatchText(char *t, int tlen, char *p, int plen); static text *MB_do_like_escape(text *, text *); + 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; *************** wchareq(char *p1, char *p2) *** 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) \ --- 74,86 ---- * 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. */ + #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) \ *************** wchareq(char *p1, char *p2) *** 91,120 **** } 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)--) --- 91,225 ---- } while (0) #define MatchText MBMatchText #define do_like_escape MB_do_like_escape #include "like_match.c" /* Set up to compile like_match.c for single-byte characters */ ! #define CHAREQ(p1, p2) BYTEEQ(p1, p2) #define ICHAREQ(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)--) + /* + * Same as MatchText, 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 */ + NextByte(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 == '%')) + NextByte(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 + * 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 */ + NextByte(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; + } + #include "like_match.c" + static __inline__ int + GenericMatchText(char *s, int slen, char* p, int plen) + { + if (pg_database_encoding_max_length() == 1) + return MatchText(s, slen, p, plen); + else + return MBMatchText(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); + + return MBMatchText(s, slen, p, plen); + } + /* And some support for BYTEA */ ! #define BYTEA_CHAREQ(p1, p2) BYTEEQ(p1, p2) ! #define BYTEA_NextChar(p, plen) NextByte(p, plen) #define BYTEA_CopyAdvChar(dst, src, srclen) (*(dst)++ = *(src)++, (srclen)--) *************** namelike(PG_FUNCTION_ARGS) *** 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); } --- 243,249 ---- p = VARDATA(pat); plen = (VARSIZE(pat) - VARHDRSZ); ! result = (GenericMatchText(s, slen, p, plen) == LIKE_TRUE); PG_RETURN_BOOL(result); } *************** namenlike(PG_FUNCTION_ARGS) *** 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); } --- 264,270 ---- p = VARDATA(pat); plen = (VARSIZE(pat) - VARHDRSZ); ! result = (GenericMatchText(s, slen, p, plen) != LIKE_TRUE); PG_RETURN_BOOL(result); } *************** textlike(PG_FUNCTION_ARGS) *** 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); } --- 285,291 ---- p = VARDATA(pat); plen = (VARSIZE(pat) - VARHDRSZ); ! result = (GenericMatchText(s, slen, p, plen) == LIKE_TRUE); PG_RETURN_BOOL(result); } *************** textnlike(PG_FUNCTION_ARGS) *** 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); } --- 306,312 ---- p = VARDATA(pat); plen = (VARSIZE(pat) - VARHDRSZ); ! result = (GenericMatchText(s, slen, p, plen) != LIKE_TRUE); PG_RETURN_BOOL(result); } *************** nameiclike(PG_FUNCTION_ARGS) *** 285,305 **** } 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); --- 378,388 ---- } else { text *strtext; strtext = DatumGetTextP(DirectFunctionCall1(name_text, NameGetDatum(str))); ! result = (mbtexticlike(strtext, pat) == LIKE_TRUE); } PG_RETURN_BOOL(result); *************** nameicnlike(PG_FUNCTION_ARGS) *** 326,346 **** } 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); --- 409,419 ---- } else { text *strtext; strtext = DatumGetTextP(DirectFunctionCall1(name_text, NameGetDatum(str))); ! result = (mbtexticlike(strtext, pat) != LIKE_TRUE); } PG_RETURN_BOOL(result); *************** texticlike(PG_FUNCTION_ARGS) *** 366,383 **** 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); } --- 439,445 ---- result = (MatchTextIC(s, slen, p, plen) == LIKE_TRUE); } else ! result = (mbtexticlike(str, pat) == LIKE_TRUE); PG_RETURN_BOOL(result); } *************** texticnlike(PG_FUNCTION_ARGS) *** 402,419 **** 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); } --- 464,470 ---- result = (MatchTextIC(s, slen, p, plen) != LIKE_TRUE); } else ! result = (mbtexticlike(str, pat) != LIKE_TRUE); PG_RETURN_BOOL(result); } diff -cpr HEAD/src/backend/utils/adt/like_match.c DropMBMatchTextIC/src/backend/utils/adt/like_match.c *** HEAD/src/backend/utils/adt/like_match.c Thu Mar 1 09:40:18 2007 --- DropMBMatchTextIC/src/backend/utils/adt/like_match.c Mon Apr 9 11:22:26 2007 *************** *** 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 --- 9,17 ---- *************** MatchText(char *t, int tlen, char *p, in *** 82,88 **** if (*p == '\\') { /* Next pattern char must match literally, whatever it is */ ! NextChar(p, plen); if ((plen <= 0) || !CHAREQ(t, p)) return LIKE_FALSE; } --- 80,86 ---- if (*p == '\\') { /* Next pattern char must match literally, whatever it is */ ! NextByte(p, plen); if ((plen <= 0) || !CHAREQ(t, p)) return LIKE_FALSE; } *************** MatchText(char *t, int tlen, char *p, in *** 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; --- 89,95 ---- /* %% 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; *************** MatchText(char *t, int tlen, char *p, in *** 142,148 **** /* 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; --- 140,146 ---- /* 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; *************** MatchText(char *t, int tlen, char *p, in *** 154,245 **** } /* 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 - * 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; - } /* MatchTextIC() */ - - /* * like_escape() --- given a pattern and an ESCAPE string, * convert the pattern to use Postgres' standard backslash escape convention. */ --- 152,157 ---- *************** do_like_escape(text *pat, text *esc) *** 336,338 **** --- 248,256 ---- return result; } + + #undef CHAREQ + #undef NextChar + #undef CopyAdvChar + #undef MatchText + #undef do_like_escape