Replace regular expression package with Henry Spencer's latest version

(extracted from Tcl 8.4.1 release, as Henry still hasn't got round to
making it a separate library).  This solves a performance problem for
multibyte, as well as upgrading our regexp support to match recent Tcl
and nearly match recent Perl.

doc/src/sgml/release.sgml

 <!--
-$Header: /cvsroot/pgsql/doc/src/sgml/release.sgml,v 1.184 2003/02/02 23:46:38 tgl Exp $
+$Header: /cvsroot/pgsql/doc/src/sgml/release.sgml,v 1.185 2003/02/05 17:41:32 tgl Exp $
 -->
 
 <appendix id="release">
@@ -24,6 +24,7 @@ CDATA means the content is "SGML-free", so you can write without
 worries about funny characters.
 -->
 <literallayout><![CDATA[
+New regular expression package, many more regexp features (most of Perl5)
 Can now do EXPLAIN ... EXECUTE to see plan used for a prepared query
 Explicit JOINs no longer constrain query plan, unless JOIN_COLLAPSE_LIMIT = 1
 Performance of "foo IN (SELECT ...)" queries has been considerably improved

src/backend/regex/COPYRIGHT

-Copyright 1992, 1993, 1994 Henry Spencer.  All rights reserved.
-This software is not subject to any license of the American Telephone
-and Telegraph Company or of the Regents of the University of California.
-
-Permission is granted to anyone to use this software for any purpose on
-any computer system, and to alter it and redistribute it, subject
-to the following restrictions:
-
-1. The author is not responsible for the consequences of use of this
-   software, no matter how awful, even if they arise from flaws in it.
-
-2. The origin of this software must not be misrepresented, either by
-   explicit claim or by omission.  Since few users ever read sources,
-   credits must appear in the documentation.
-
-3. Altered versions must be plainly marked as such, and must not be
-   misrepresented as being the original software.  Since few users
-   ever read sources, credits must appear in the documentation.
-
-4. This notice may not be removed or altered.
-
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
-/*-
- * Copyright (c) 1994
- *	The Regents of the University of California.  All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. All advertising materials mentioning features or use of this software
- *    must display the following acknowledgement:
- *	This product includes software developed by the University of
- *	California, Berkeley and its contributors.
- * 4. Neither the name of the University nor the names of its contributors
- *    may be used to endorse or promote products derived from this software
- *    without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- *
- *	@(#)COPYRIGHT	8.1 (Berkeley) 3/16/94
- */
+This regular expression package was originally developed by Henry Spencer.
+It bears the following copyright notice:
+
+**********************************************************************
+
+Copyright (c) 1998, 1999 Henry Spencer.  All rights reserved.
+
+Development of this software was funded, in part, by Cray Research Inc.,
+UUNET Communications Services Inc., Sun Microsystems Inc., and Scriptics
+Corporation, none of whom are responsible for the results.  The author
+thanks all of them. 
+
+Redistribution and use in source and binary forms -- with or without
+modification -- are permitted for any purpose, provided that
+redistributions in source form retain this entire copyright notice and
+indicate the origin and nature of any modifications.
+
+I'd appreciate being given credit for this package in the documentation
+of software which uses it, but that is not a requirement.
+
+THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES,
+INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
+AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL
+HENRY SPENCER BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+**********************************************************************
+
+PostgreSQL adopted the code out of Tcl 8.4.1.  Portions of regc_locale.c
+and re_syntax.n were developed by Tcl developers other than Henry; these
+files bear the Tcl copyright and license notice:
+
+**********************************************************************
+
+This software is copyrighted by the Regents of the University of
+California, Sun Microsystems, Inc., Scriptics Corporation, ActiveState
+Corporation and other parties.  The following terms apply to all files
+associated with the software unless explicitly disclaimed in
+individual files.
+
+The authors hereby grant permission to use, copy, modify, distribute,
+and license this software and its documentation for any purpose, provided
+that existing copyright notices are retained in all copies and that this
+notice is included verbatim in any distributions. No written agreement,
+license, or royalty fee is required for any of the authorized uses.
+Modifications to this software may be copyrighted by their authors
+and need not follow the licensing terms described here, provided that
+the new terms are clearly indicated on the first page of each file where
+they apply.
+
+IN NO EVENT SHALL THE AUTHORS OR DISTRIBUTORS BE LIABLE TO ANY PARTY
+FOR DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES
+ARISING OUT OF THE USE OF THIS SOFTWARE, ITS DOCUMENTATION, OR ANY
+DERIVATIVES THEREOF, EVEN IF THE AUTHORS HAVE BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+
+THE AUTHORS AND DISTRIBUTORS SPECIFICALLY DISCLAIM ANY WARRANTIES,
+INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE, AND NON-INFRINGEMENT.  THIS SOFTWARE
+IS PROVIDED ON AN "AS IS" BASIS, AND THE AUTHORS AND DISTRIBUTORS HAVE
+NO OBLIGATION TO PROVIDE MAINTENANCE, SUPPORT, UPDATES, ENHANCEMENTS, OR
+MODIFICATIONS.
+
+GOVERNMENT USE: If you are acquiring this software on behalf of the
+U.S. government, the Government shall have only "Restricted Rights"
+in the software and related documentation as defined in the Federal 
+Acquisition Regulations (FARs) in Clause 52.227.19 (c) (2).  If you
+are acquiring the software on behalf of the Department of Defense, the
+software shall be classified as "Commercial Computer Software" and the
+Government shall have only "Restricted Rights" as defined in Clause
+252.227-7013 (c) (1) of DFARs.  Notwithstanding the foregoing, the
+authors grant the U.S. Government and others acting in its behalf
+permission to use and distribute the software in accordance with the
+terms specified in this license. 
+
+**********************************************************************
+
+Subsequent modifications to the code by the PostgreSQL project follow
+the same license terms as the rest of PostgreSQL.

src/backend/regex/Makefile

 #-------------------------------------------------------------------------
 #
 # Makefile--
-#    Makefile for regex
+#    Makefile for backend/regex
 #
 # IDENTIFICATION
-#    $Header: /cvsroot/pgsql/src/backend/regex/Makefile,v 1.19 2002/09/16 16:02:43 momjian Exp $
+#    $Header: /cvsroot/pgsql/src/backend/regex/Makefile,v 1.20 2003/02/05 17:41:32 tgl Exp $
 #
 #-------------------------------------------------------------------------
 
@@ -12,23 +12,17 @@ subdir = src/backend/regex
 top_builddir = ../../..
 include $(top_builddir)/src/Makefile.global
 
-override CPPFLAGS += -DPOSIX_MISTAKE 
-
 OBJS = regcomp.o regerror.o regexec.o regfree.o
-DEBUGOBJ += ../utils/mb/SUBSYS.o
 
 all: SUBSYS.o
 
 SUBSYS.o: $(OBJS)
 	$(LD) $(LDREL) $(LDOUT) SUBSYS.o $(OBJS)
 
-regexec.o: regexec.c engine.c
+# mark inclusion dependencies between .c files explicitly
+regcomp.o: regcomp.c regc_lex.c regc_color.c regc_nfa.c regc_cvec.c regc_locale.c
 
-# retest will not compile because multibyte is now enabled by default
-# and the multibyte calls require /mmgr, /adt, and other calls that
-# are complex for linkage,  bjm 2002-09-16
-#retest: retest.o SUBSYS.o $(DEBUGOBJ)
-#	$(CC) $(CFLAGS) $(LDFLAGS) $^ $(LIBS) -o $@
+regexec.o: regexec.c rege_dfa.c
 
 clean: 
-	rm -f SUBSYS.o $(OBJS) retest retest.o
+	rm -f SUBSYS.o $(OBJS)

src/backend/regex/WHATSNEW

-# @(#)WHATSNEW	8.3 (Berkeley) 3/18/94
-
-New in alpha3.4:  The complex bug alluded to below has been fixed (in a
-slightly kludgey temporary way that may hurt efficiency a bit; this is
-another "get it out the door for 4.4" release).  The tests at the end of
-the tests file have accordingly been uncommented.  The primary sign of
-the bug was that something like a?b matching ab matched b rather than ab.
-(The bug was essentially specific to this exact situation, else it would
-have shown up earlier.)
-
-New in alpha3.3:  The definition of word boundaries has been altered
-slightly, to more closely match the usual programming notion that "_"
-is an alphabetic.  Stuff used for pre-ANSI systems is now in a subdir,
-and the makefile no longer alludes to it in mysterious ways.  The
-makefile has generally been cleaned up some.  Fixes have been made
-(again!) so that the regression test will run without -DREDEBUG, at
-the cost of weaker checking.  A workaround for a bug in some folks'
-<assert.h> has been added.  And some more things have been added to
-tests, including a couple right at the end which are commented out
-because the code currently flunks them (complex bug; fix coming).
-Plus the usual minor cleanup.
-
-New in alpha3.2:  Assorted bits of cleanup and portability improvement
-(the development base is now a BSDI system using GCC instead of an ancient
-Sun system, and the newer compiler exposed some glitches).  Fix for a
-serious bug that affected REs using many [] (including REG_ICASE REs
-because of the way they are implemented), *sometimes*, depending on
-memory-allocation patterns.  The header-file prototypes no longer name
-the parameters, avoiding possible name conflicts.  The possibility that
-some clot has defined CHAR_MIN as (say) `-128' instead of `(-128)' is
-now handled gracefully.  "uchar" is no longer used as an internal type
-name (too many people have the same idea).  Still the same old lousy
-performance, alas.
-
-New in alpha3.1:  Basically nothing, this release is just a bookkeeping
-convenience.  Stay tuned.
-
-New in alpha3.0:  Performance is no better, alas, but some fixes have been
-made and some functionality has been added.  (This is basically the "get
-it out the door in time for 4.4" release.)  One bug fix:  regfree() didn't
-free the main internal structure (how embarrassing).  It is now possible
-to put NULs in either the RE or the target string, using (resp.) a new
-REG_PEND flag and the old REG_STARTEND flag.  The REG_NOSPEC flag to
-regcomp() makes all characters ordinary, so you can match a literal
-string easily (this will become more useful when performance improves!).
-There are now primitives to match beginnings and ends of words, although
-the syntax is disgusting and so is the implementation.  The REG_ATOI
-debugging interface has changed a bit.  And there has been considerable
-internal cleanup of various kinds.
-
-New in alpha2.3:  Split change list out of README, and moved flags notes
-into Makefile.  Macro-ized the name of regex(7) in regex(3), since it has
-to change for 4.4BSD.  Cleanup work in engine.c, and some new regression
-tests to catch tricky cases thereof.
-
-New in alpha2.2:  Out-of-date manpages updated.  Regerror() acquires two
-small extensions -- REG_ITOA and REG_ATOI -- which avoid debugging kludges
-in my own test program and might be useful to others for similar purposes.
-The regression test will now compile (and run) without REDEBUG.  The
-BRE \$ bug is fixed.  Most uses of "uchar" are gone; it's all chars now.
-Char/uchar parameters are now written int/unsigned, to avoid possible
-portability problems with unpromoted parameters.  Some unsigned casts have
-been introduced to minimize portability problems with shifting into sign
-bits.
-
-New in alpha2.1:  Lots of little stuff, cleanup and fixes.  The one big
-thing is that regex.h is now generated, using mkh, rather than being
-supplied in the distribution; due to circularities in dependencies,
-you have to build regex.h explicitly by "make h".  The two known bugs
-have been fixed (and the regression test now checks for them), as has a
-problem with assertions not being suppressed in the absence of REDEBUG.
-No performance work yet.
-
-New in alpha2:  Backslash-anything is an ordinary character, not an
-error (except, of course, for the handful of backslashed metacharacters
-in BREs), which should reduce script breakage.  The regression test
-checks *where* null strings are supposed to match, and has generally
-been tightened up somewhat.  Small bug fixes in parameter passing (not
-harmful, but technically errors) and some other areas.  Debugging
-invoked by defining REDEBUG rather than not defining NDEBUG.
-
-New in alpha+3:  full prototyping for internal routines, using a little
-helper program, mkh, which extracts prototypes given in stylized comments.
-More minor cleanup.  Buglet fix:  it's CHAR_BIT, not CHAR_BITS.  Simple
-pre-screening of input when a literal string is known to be part of the
-RE; this does wonders for performance.
-
-New in alpha+2:  minor bits of cleanup.  Notably, the number "32" for the
-word width isn't hardwired into regexec.c any more, the public header
-file prototypes the functions if __STDC__ is defined, and some small typos
-in the manpages have been fixed.
-
-New in alpha+1:  improvements to the manual pages, and an important
-extension, the REG_STARTEND option to regexec().

src/backend/regex/re_format.7

-.\" Copyright (c) 1992, 1993, 1994 Henry Spencer.
-.\" Copyright (c) 1992, 1993, 1994
-.\"	The Regents of the University of California.  All rights reserved.
-.\"
-.\" This code is derived from software contributed to Berkeley by
-.\" Henry Spencer.
-.\"
-.\" Redistribution and use in source and binary forms, with or without
-.\" modification, are permitted provided that the following conditions
-.\" are met:
-.\" 1. Redistributions of source code must retain the above copyright
-.\"    notice, this list of conditions and the following disclaimer.
-.\" 2. Redistributions in binary form must reproduce the above copyright
-.\"    notice, this list of conditions and the following disclaimer in the
-.\"    documentation and/or other materials provided with the distribution.
-.\" 3. All advertising materials mentioning features or use of this software
-.\"    must display the following acknowledgement:
-.\"	This product includes software developed by the University of
-.\"	California, Berkeley and its contributors.
-.\" 4. Neither the name of the University nor the names of its contributors
-.\"    may be used to endorse or promote products derived from this software
-.\"    without specific prior written permission.
-.\"
-.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
-.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-.\" ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
-.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
-.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
-.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
-.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
-.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
-.\" SUCH DAMAGE.
-.\"
-.\"	@(#)re_format.7	8.3 (Berkeley) 3/20/94
-.\"
-.TH RE_FORMAT 7 "March 20, 1994"
-.SH NAME
-re_format \- POSIX 1003.2 regular expressions
-.SH DESCRIPTION
-Regular expressions (``RE''s),
-as defined in POSIX 1003.2, come in two forms:
-modern REs (roughly those of
-.IR egrep ;
-1003.2 calls these ``extended'' REs)
-and obsolete REs (roughly those of
-.IR ed ;
-1003.2 ``basic'' REs).
-Obsolete REs mostly exist for backward compatibility in some old programs;
-they will be discussed at the end.
-1003.2 leaves some aspects of RE syntax and semantics open;
-`\(dg' marks decisions on these aspects that
-may not be fully portable to other 1003.2 implementations.
-.PP
-A (modern) RE is one\(dg or more non-empty\(dg \fIbranches\fR,
-separated by `|'.
-It matches anything that matches one of the branches.
-.PP
-A branch is one\(dg or more \fIpieces\fR, concatenated.
-It matches a match for the first, followed by a match for the second, etc.
-.PP
-A piece is an \fIatom\fR possibly followed
-by a single\(dg `*', `+', `?', or \fIbound\fR.
-An atom followed by `*' matches a sequence of 0 or more matches of the atom.
-An atom followed by `+' matches a sequence of 1 or more matches of the atom.
-An atom followed by `?' matches a sequence of 0 or 1 matches of the atom.
-.PP
-A \fIbound\fR is `{' followed by an unsigned decimal integer,
-possibly followed by `,'
-possibly followed by another unsigned decimal integer,
-always followed by `}'.
-The integers must lie between 0 and RE_DUP_MAX (255\(dg) inclusive,
-and if there are two of them, the first may not exceed the second.
-An atom followed by a bound containing one integer \fIi\fR
-and no comma matches
-a sequence of exactly \fIi\fR matches of the atom.
-An atom followed by a bound
-containing one integer \fIi\fR and a comma matches
-a sequence of \fIi\fR or more matches of the atom.
-An atom followed by a bound
-containing two integers \fIi\fR and \fIj\fR matches
-a sequence of \fIi\fR through \fIj\fR (inclusive) matches of the atom.
-.PP
-An atom is a regular expression enclosed in `()' (matching a match for the
-regular expression),
-an empty set of `()' (matching the null string)\(dg,
-a \fIbracket expression\fR (see below), `.'
-(matching any single character), `^' (matching the null string at the
-beginning of a line), `$' (matching the null string at the
-end of a line), a `\e' followed by one of the characters
-`^.[$()|*+?{\e'
-(matching that character taken as an ordinary character),
-a `\e' followed by any other character\(dg
-(matching that character taken as an ordinary character,
-as if the `\e' had not been present\(dg),
-or a single character with no other significance (matching that character).
-A `{' followed by a character other than a digit is an ordinary
-character, not the beginning of a bound\(dg.
-It is illegal to end an RE with `\e'.
-.PP
-A \fIbracket expression\fR is a list of characters enclosed in `[]'.
-It normally matches any single character from the list (but see below).
-If the list begins with `^',
-it matches any single character
-(but see below) \fInot\fR from the rest of the list.
-If two characters in the list are separated by `\-', this is shorthand
-for the full \fIrange\fR of characters between those two (inclusive) in the
-collating sequence,
-e.g. `[0-9]' in ASCII matches any decimal digit.
-It is illegal\(dg for two ranges to share an
-endpoint, e.g. `a-c-e'.
-Ranges are very collating-sequence-dependent,
-and portable programs should avoid relying on them.
-.PP
-To include a literal `]' in the list, make it the first character
-(following a possible `^').
-To include a literal `\-', make it the first or last character,
-or the second endpoint of a range.
-To use a literal `\-' as the first endpoint of a range,
-enclose it in `[.' and `.]' to make it a collating element (see below).
-With the exception of these and some combinations using `[' (see next
-paragraphs), all other special characters, including `\e', lose their
-special significance within a bracket expression.
-.PP
-Within a bracket expression, a collating element (a character,
-a multi-character sequence that collates as if it were a single character,
-or a collating-sequence name for either)
-enclosed in `[.' and `.]' stands for the
-sequence of characters of that collating element.
-The sequence is a single element of the bracket expression's list.
-A bracket expression containing a multi-character collating element 
-can thus match more than one character,
-e.g. if the collating sequence includes a `ch' collating element,
-then the RE `[[.ch.]]*c' matches the first five characters
-of `chchcc'.
-.PP
-Within a bracket expression, a collating element enclosed in `[=' and
-`=]' is an equivalence class, standing for the sequences of characters
-of all collating elements equivalent to that one, including itself.
-(If there are no other equivalent collating elements,
-the treatment is as if the enclosing delimiters were `[.' and `.]'.)
-For example, if o and \o'o^' are the members of an equivalence class,
-then `[[=o=]]', `[[=\o'o^'=]]', and `[o\o'o^']' are all synonymous.
-An equivalence class may not\(dg be an endpoint
-of a range.
-.PP
-Within a bracket expression, the name of a \fIcharacter class\fR enclosed
-in `[:' and `:]' stands for the list of all characters belonging to that
-class.
-Standard character class names are:
-.PP
-.RS
-.nf
-.ta 3c 6c 9c
-alnum	digit	punct
-alpha	graph	space
-blank	lower	upper
-cntrl	print	xdigit
-.fi
-.RE
-.PP
-These stand for the character classes defined in
-.IR ctype (3).
-A locale may provide others.
-A character class may not be used as an endpoint of a range.
-.PP
-There are two special cases\(dg of bracket expressions:
-the bracket expressions `[[:<:]]' and `[[:>:]]' match the null string at
-the beginning and end of a word respectively.
-A word is defined as a sequence of
-word characters
-which is neither preceded nor followed by
-word characters.
-A word character is an
-.I alnum
-character (as defined by
-.IR ctype (3))
-or an underscore.
-This is an extension,
-compatible with but not specified by POSIX 1003.2,
-and should be used with
-caution in software intended to be portable to other systems.
-.PP
-In the event that an RE could match more than one substring of a given
-string,
-the RE matches the one starting earliest in the string.
-If the RE could match more than one substring starting at that point,
-it matches the longest.
-Subexpressions also match the longest possible substrings, subject to
-the constraint that the whole match be as long as possible,
-with subexpressions starting earlier in the RE taking priority over
-ones starting later.
-Note that higher-level subexpressions thus take priority over
-their lower-level component subexpressions.
-.PP
-Match lengths are measured in characters, not collating elements.
-A null string is considered longer than no match at all.
-For example,
-`bb*' matches the three middle characters of `abbbc',
-`(wee|week)(knights|nights)' matches all ten characters of `weeknights',
-when `(.*).*' is matched against `abc' the parenthesized subexpression
-matches all three characters, and
-when `(a*)*' is matched against `bc' both the whole RE and the parenthesized
-subexpression match the null string.
-.PP
-If case-independent matching is specified,
-the effect is much as if all case distinctions had vanished from the
-alphabet.
-When an alphabetic that exists in multiple cases appears as an
-ordinary character outside a bracket expression, it is effectively
-transformed into a bracket expression containing both cases,
-e.g. `x' becomes `[xX]'.
-When it appears inside a bracket expression, all case counterparts
-of it are added to the bracket expression, so that (e.g.) `[x]'
-becomes `[xX]' and `[^x]' becomes `[^xX]'.
-.PP
-No particular limit is imposed on the length of REs\(dg.
-Programs intended to be portable should not employ REs longer
-than 256 bytes,
-as an implementation can refuse to accept such REs and remain
-POSIX-compliant.
-.PP
-Obsolete (``basic'') regular expressions differ in several respects.
-`|', `+', and `?' are ordinary characters and there is no equivalent
-for their functionality.
-The delimiters for bounds are `\e{' and `\e}',
-with `{' and `}' by themselves ordinary characters.
-The parentheses for nested subexpressions are `\e(' and `\e)',
-with `(' and `)' by themselves ordinary characters.
-`^' is an ordinary character except at the beginning of the
-RE or\(dg the beginning of a parenthesized subexpression,
-`$' is an ordinary character except at the end of the
-RE or\(dg the end of a parenthesized subexpression,
-and `*' is an ordinary character if it appears at the beginning of the
-RE or the beginning of a parenthesized subexpression
-(after a possible leading `^').
-Finally, there is one new type of atom, a \fIback reference\fR:
-`\e' followed by a non-zero decimal digit \fId\fR
-matches the same sequence of characters
-matched by the \fId\fRth parenthesized subexpression
-(numbering subexpressions by the positions of their opening parentheses,
-left to right),
-so that (e.g.) `\e([bc]\e)\e1' matches `bb' or `cc' but not `bc'.
-.SH SEE ALSO
-regex(3)
-.PP
-POSIX 1003.2, section 2.8 (Regular Expression Notation).
-.SH BUGS
-Having two kinds of REs is a botch.
-.PP
-The current 1003.2 spec says that `)' is an ordinary character in
-the absence of an unmatched `(';
-this was an unintentional result of a wording error,
-and change is likely.
-Avoid relying on it.
-.PP
-Back references are a dreadful botch,
-posing major problems for efficient implementations.
-They are also somewhat vaguely defined
-(does
-`a\e(\e(b\e)*\e2\e)*d' match `abbbd'?).
-Avoid using them.
-.PP
-1003.2's specification of case-independent matching is vague.
-The ``one case implies all cases'' definition given above
-is current consensus among implementors as to the right interpretation.
-.PP
-The syntax for word boundaries is incredibly ugly.

src/backend/regex/regc_color.c

+/*
+ * colorings of characters
+ * This file is #included by regcomp.c.
+ *
+ * Copyright (c) 1998, 1999 Henry Spencer.  All rights reserved.
+ * 
+ * Development of this software was funded, in part, by Cray Research Inc.,
+ * UUNET Communications Services Inc., Sun Microsystems Inc., and Scriptics
+ * Corporation, none of whom are responsible for the results.  The author
+ * thanks all of them. 
+ * 
+ * Redistribution and use in source and binary forms -- with or without
+ * modification -- are permitted for any purpose, provided that
+ * redistributions in source form retain this entire copyright notice and
+ * indicate the origin and nature of any modifications.
+ * 
+ * I'd appreciate being given credit for this package in the documentation
+ * of software which uses it, but that is not a requirement.
+ * 
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
+ * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL
+ * HENRY SPENCER BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+ * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * $Header: /cvsroot/pgsql/src/backend/regex/regc_color.c,v 1.1 2003/02/05 17:41:32 tgl Exp $
+ *
+ *
+ * Note that there are some incestuous relationships between this code and
+ * NFA arc maintenance, which perhaps ought to be cleaned up sometime.
+ */
+
+
+
+#define	CISERR()	VISERR(cm->v)
+#define	CERR(e)		VERR(cm->v, (e))
+
+
+
+/*
+ * initcm - set up new colormap
+ */
+static void
+initcm(struct vars *v,
+	   struct colormap *cm)
+{
+	int i;
+	int j;
+	union tree *t;
+	union tree *nextt;
+	struct colordesc *cd;
+
+	cm->magic = CMMAGIC;
+	cm->v = v;
+
+	cm->ncds = NINLINECDS;
+	cm->cd = cm->cdspace;
+	cm->max = 0;
+	cm->free = 0;
+
+	cd = cm->cd;			/* cm->cd[WHITE] */
+	cd->sub = NOSUB;
+	cd->arcs = NULL;
+	cd->flags = 0;
+	cd->nchrs = CHR_MAX - CHR_MIN + 1;
+
+	/* upper levels of tree */
+	for (t = &cm->tree[0], j = NBYTS-1; j > 0; t = nextt, j--) {
+		nextt = t + 1;
+		for (i = BYTTAB-1; i >= 0; i--)
+			t->tptr[i] = nextt;
+	}
+	/* bottom level is solid white */
+	t = &cm->tree[NBYTS-1];
+	for (i = BYTTAB-1; i >= 0; i--)
+		t->tcolor[i] = WHITE;
+	cd->block = t;
+}
+
+/*
+ * freecm - free dynamically-allocated things in a colormap
+ */
+static void
+freecm(struct colormap *cm)
+{
+	size_t i;
+	union tree *cb;
+
+	cm->magic = 0;
+	if (NBYTS > 1)
+		cmtreefree(cm, cm->tree, 0);
+	for (i = 1; i <= cm->max; i++)		/* skip WHITE */
+		if (!UNUSEDCOLOR(&cm->cd[i])) {
+			cb = cm->cd[i].block;
+			if (cb != NULL)
+				FREE(cb);
+		}
+	if (cm->cd != cm->cdspace)
+		FREE(cm->cd);
+}
+
+/*
+ * cmtreefree - free a non-terminal part of a colormap tree
+ */
+static void
+cmtreefree(struct colormap *cm,
+		   union tree *tree,
+		   int level)			/* level number (top == 0) of this block */
+{
+	int i;
+	union tree *t;
+	union tree *fillt = &cm->tree[level+1];
+	union tree *cb;
+
+	assert(level < NBYTS-1);	/* this level has pointers */
+	for (i = BYTTAB-1; i >= 0; i--) {
+		t = tree->tptr[i];
+		assert(t != NULL);
+		if (t != fillt) {
+			if (level < NBYTS-2) {	/* more pointer blocks below */
+				cmtreefree(cm, t, level+1);
+				FREE(t);
+			} else {		/* color block below */
+				cb = cm->cd[t->tcolor[0]].block;
+				if (t != cb)	/* not a solid block */
+					FREE(t);
+			}
+		}
+	}
+}
+
+/*
+ * setcolor - set the color of a character in a colormap
+ */
+static color			/* previous color */
+setcolor(struct colormap *cm,
+		 chr c,
+		 pcolor co)
+{
+	uchr uc = c;
+	int shift;
+	int level;
+	int b;
+	int bottom;
+	union tree *t;
+	union tree *newt;
+	union tree *fillt;
+	union tree *lastt;
+	union tree *cb;
+	color prev;
+
+	assert(cm->magic == CMMAGIC);
+	if (CISERR() || co == COLORLESS)
+		return COLORLESS;
+
+	t = cm->tree;
+	for (level = 0, shift = BYTBITS * (NBYTS - 1); shift > 0;
+						level++, shift -= BYTBITS) {
+		b = (uc >> shift) & BYTMASK;
+		lastt = t;
+		t = lastt->tptr[b];
+		assert(t != NULL);
+		fillt = &cm->tree[level+1];
+		bottom = (shift <= BYTBITS) ? 1 : 0;
+		cb = (bottom) ? cm->cd[t->tcolor[0]].block : fillt;
+		if (t == fillt || t == cb) {	/* must allocate a new block */
+			newt = (union tree *)MALLOC((bottom) ?
+				sizeof(struct colors) : sizeof(struct ptrs));
+			if (newt == NULL) {
+				CERR(REG_ESPACE);
+				return COLORLESS;
+			}
+			if (bottom)
+				memcpy(VS(newt->tcolor), VS(t->tcolor),
+							BYTTAB*sizeof(color));
+			else
+				memcpy(VS(newt->tptr), VS(t->tptr),
+						BYTTAB*sizeof(union tree *));
+			t = newt;
+			lastt->tptr[b] = t;
+		}
+	}
+
+	b = uc & BYTMASK;
+	prev = t->tcolor[b];
+	t->tcolor[b] = (color)co;
+	return prev;
+}
+
+/*
+ * maxcolor - report largest color number in use
+ */
+static color
+maxcolor(struct colormap *cm)
+{
+	if (CISERR())
+		return COLORLESS;
+
+	return (color)cm->max;
+}
+
+/*
+ * newcolor - find a new color (must be subject of setcolor at once)
+ * Beware:  may relocate the colordescs.
+ */
+static color			/* COLORLESS for error */
+newcolor(struct colormap *cm)
+{
+	struct colordesc *cd;
+	struct colordesc *new;
+	size_t n;
+
+	if (CISERR())
+		return COLORLESS;
+
+	if (cm->free != 0) {
+		assert(cm->free > 0);
+		assert((size_t)cm->free < cm->ncds);
+		cd = &cm->cd[cm->free];
+		assert(UNUSEDCOLOR(cd));
+		assert(cd->arcs == NULL);
+		cm->free = cd->sub;
+	} else if (cm->max < cm->ncds - 1) {
+		cm->max++;
+		cd = &cm->cd[cm->max];
+	} else {
+		/* oops, must allocate more */
+		n = cm->ncds * 2;
+		if (cm->cd == cm->cdspace) {
+			new = (struct colordesc *)MALLOC(n *
+						sizeof(struct colordesc));
+			if (new != NULL)
+				memcpy(VS(new), VS(cm->cdspace), cm->ncds *
+						sizeof(struct colordesc));
+		} else
+			new = (struct colordesc *)REALLOC(cm->cd,
+						n * sizeof(struct colordesc));
+		if (new == NULL) {
+			CERR(REG_ESPACE);
+			return COLORLESS;
+		}
+		cm->cd = new;
+		cm->ncds = n;
+		assert(cm->max < cm->ncds - 1);
+		cm->max++;
+		cd = &cm->cd[cm->max];
+	}
+
+	cd->nchrs = 0;
+	cd->sub = NOSUB;
+	cd->arcs = NULL;
+	cd->flags = 0;
+	cd->block = NULL;
+
+	return (color)(cd - cm->cd);
+}
+
+/*
+ * freecolor - free a color (must have no arcs or subcolor)
+ */
+static void
+freecolor(struct colormap *cm,
+		  pcolor co)
+{
+	struct colordesc *cd = &cm->cd[co];
+	color pco, nco;			/* for freelist scan */
+
+	assert(co >= 0);
+	if (co == WHITE)
+		return;
+
+	assert(cd->arcs == NULL);
+	assert(cd->sub == NOSUB);
+	assert(cd->nchrs == 0);
+	cd->flags = FREECOL;
+	if (cd->block != NULL) {
+		FREE(cd->block);
+		cd->block = NULL;	/* just paranoia */
+	}
+
+	if ((size_t)co == cm->max) {
+		while (cm->max > WHITE && UNUSEDCOLOR(&cm->cd[cm->max]))
+			cm->max--;
+		assert(cm->free >= 0);
+		while ((size_t)cm->free > cm->max)
+			cm->free = cm->cd[cm->free].sub;
+		if (cm->free > 0) {
+			assert(cm->free < cm->max);
+			pco = cm->free;
+			nco = cm->cd[pco].sub;
+			while (nco > 0)
+				if ((size_t)nco > cm->max) {
+					/* take this one out of freelist */
+					nco = cm->cd[nco].sub;
+					cm->cd[pco].sub = nco;
+				} else {
+					assert(nco < cm->max);
+					pco = nco;
+					nco = cm->cd[pco].sub;
+				}
+		}
+	} else {
+		cd->sub = cm->free;
+		cm->free = (color)(cd - cm->cd);
+	}
+}
+
+/*
+ * pseudocolor - allocate a false color, to be managed by other means
+ */
+static color
+pseudocolor(struct colormap *cm)
+{
+	color co;
+
+	co = newcolor(cm);
+	if (CISERR())
+		return COLORLESS;
+	cm->cd[co].nchrs = 1;
+	cm->cd[co].flags = PSEUDO;
+	return co;
+}
+
+/*
+ * subcolor - allocate a new subcolor (if necessary) to this chr
+ */
+static color
+subcolor(struct colormap *cm, chr c)
+{
+	color co;			/* current color of c */
+	color sco;			/* new subcolor */
+
+	co = GETCOLOR(cm, c);
+	sco = newsub(cm, co);
+	if (CISERR())
+		return COLORLESS;
+	assert(sco != COLORLESS);
+
+	if (co == sco)		/* already in an open subcolor */
+		return co;	/* rest is redundant */
+	cm->cd[co].nchrs--;
+	cm->cd[sco].nchrs++;
+	setcolor(cm, c, sco);
+	return sco;
+}
+
+/*
+ * newsub - allocate a new subcolor (if necessary) for a color
+ */
+static color
+newsub(struct colormap *cm,
+	   pcolor co)
+{
+	color sco;			/* new subcolor */
+
+	sco = cm->cd[co].sub;
+	if (sco == NOSUB) {		/* color has no open subcolor */
+		if (cm->cd[co].nchrs == 1)	/* optimization */
+			return co;
+		sco = newcolor(cm);	/* must create subcolor */
+		if (sco == COLORLESS) {
+			assert(CISERR());
+			return COLORLESS;
+		}
+		cm->cd[co].sub = sco;
+		cm->cd[sco].sub = sco;	/* open subcolor points to self */
+	}
+	assert(sco != NOSUB);
+
+	return sco;
+}
+
+/*
+ * subrange - allocate new subcolors to this range of chrs, fill in arcs
+ */
+static void
+subrange(struct vars *v,
+		 chr from,
+		 chr to,
+		 struct state *lp,
+		 struct state *rp)
+{
+	uchr uf;
+	int i;
+
+	assert(from <= to);
+
+	/* first, align "from" on a tree-block boundary */
+	uf = (uchr)from;
+	i = (int)( ((uf + BYTTAB-1) & (uchr)~BYTMASK) - uf );
+	for (; from <= to && i > 0; i--, from++)
+		newarc(v->nfa, PLAIN, subcolor(v->cm, from), lp, rp);
+	if (from > to)			/* didn't reach a boundary */
+		return;
+
+	/* deal with whole blocks */
+	for (; to - from >= BYTTAB; from += BYTTAB)
+		subblock(v, from, lp, rp);
+
+	/* clean up any remaining partial table */
+	for (; from <= to; from++)
+		newarc(v->nfa, PLAIN, subcolor(v->cm, from), lp, rp);
+}
+
+/*
+ * subblock - allocate new subcolors for one tree block of chrs, fill in arcs
+ */
+static void
+subblock(struct vars *v,
+		 chr start,				/* first of BYTTAB chrs */
+		 struct state *lp,
+		 struct state *rp)
+{
+	uchr uc = start;
+	struct colormap *cm = v->cm;
+	int shift;
+	int level;
+	int i;
+	int b;
+	union tree *t;
+	union tree *cb;
+	union tree *fillt;
+	union tree *lastt;
+	int previ;
+	int ndone;
+	color co;
+	color sco;
+
+	assert((uc % BYTTAB) == 0);
+
+	/* find its color block, making new pointer blocks as needed */
+	t = cm->tree;
+	fillt = NULL;
+	for (level = 0, shift = BYTBITS * (NBYTS - 1); shift > 0;
+						level++, shift -= BYTBITS) {
+		b = (uc >> shift) & BYTMASK;
+		lastt = t;
+		t = lastt->tptr[b];
+		assert(t != NULL);
+		fillt = &cm->tree[level+1];
+		if (t == fillt && shift > BYTBITS) {	/* need new ptr block */
+			t = (union tree *)MALLOC(sizeof(struct ptrs));
+			if (t == NULL) {
+				CERR(REG_ESPACE);
+				return;
+			}
+			memcpy(VS(t->tptr), VS(fillt->tptr),
+						BYTTAB*sizeof(union tree *));
+			lastt->tptr[b] = t;
+		}
+	}
+
+	/* special cases:  fill block or solid block */
+	co = t->tcolor[0];
+	cb = cm->cd[co].block;
+	if (t == fillt || t == cb) {
+		/* either way, we want a subcolor solid block */
+		sco = newsub(cm, co);
+		t = cm->cd[sco].block;
+		if (t == NULL) {	/* must set it up */
+			t = (union tree *)MALLOC(sizeof(struct colors));
+			if (t == NULL) {
+				CERR(REG_ESPACE);
+				return;
+			}
+			for (i = 0; i < BYTTAB; i++)
+				t->tcolor[i] = sco;
+			cm->cd[sco].block = t;
+		}
+		/* find loop must have run at least once */
+		lastt->tptr[b] = t;
+		newarc(v->nfa, PLAIN, sco, lp, rp);
+		cm->cd[co].nchrs -= BYTTAB;
+		cm->cd[sco].nchrs += BYTTAB;
+		return;
+	}
+
+	/* general case, a mixed block to be altered */
+	i = 0;
+	while (i < BYTTAB) {
+		co = t->tcolor[i];
+		sco = newsub(cm, co);
+		newarc(v->nfa, PLAIN, sco, lp, rp);
+		previ = i;
+		do {
+			t->tcolor[i++] = sco;
+		} while (i < BYTTAB && t->tcolor[i] == co);
+		ndone = i - previ;
+		cm->cd[co].nchrs -= ndone;
+		cm->cd[sco].nchrs += ndone;
+	}
+}
+
+/*
+ * okcolors - promote subcolors to full colors
+ */
+static void
+okcolors(struct nfa *nfa,
+		 struct colormap *cm)
+{
+	struct colordesc *cd;
+	struct colordesc *end = CDEND(cm);
+	struct colordesc *scd;
+	struct arc *a;
+	color co;
+	color sco;
+
+	for (cd = cm->cd, co = 0; cd < end; cd++, co++) {
+		sco = cd->sub;
+		if (UNUSEDCOLOR(cd) || sco == NOSUB) {
+			/* has no subcolor, no further action */
+		} else if (sco == co) {
+			/* is subcolor, let parent deal with it */
+		} else if (cd->nchrs == 0) {
+			/* parent empty, its arcs change color to subcolor */
+			cd->sub = NOSUB;
+			scd = &cm->cd[sco];
+			assert(scd->nchrs > 0);
+			assert(scd->sub == sco);
+			scd->sub = NOSUB;
+			while ((a = cd->arcs) != NULL) {
+				assert(a->co == co);
+				/* uncolorchain(cm, a); */
+				cd->arcs = a->colorchain;
+				a->co = sco;
+				/* colorchain(cm, a); */
+				a->colorchain = scd->arcs;
+				scd->arcs = a;
+			}
+			freecolor(cm, co);
+		} else {
+			/* parent's arcs must gain parallel subcolor arcs */
+			cd->sub = NOSUB;
+			scd = &cm->cd[sco];
+			assert(scd->nchrs > 0);
+			assert(scd->sub == sco);
+			scd->sub = NOSUB;
+			for (a = cd->arcs; a != NULL; a = a->colorchain) {
+				assert(a->co == co);
+				newarc(nfa, a->type, sco, a->from, a->to);
+			}
+		}
+	}
+}
+
+/*
+ * colorchain - add this arc to the color chain of its color
+ */
+static void
+colorchain(struct colormap *cm,
+		   struct arc *a)
+{
+	struct colordesc *cd = &cm->cd[a->co];
+
+	a->colorchain = cd->arcs;
+	cd->arcs = a;
+}
+
+/*
+ * uncolorchain - delete this arc from the color chain of its color
+ */
+static void
+uncolorchain(struct colormap *cm,
+			 struct arc *a)
+{
+	struct colordesc *cd = &cm->cd[a->co];
+	struct arc *aa;
+
+	aa = cd->arcs;
+	if (aa == a)		/* easy case */
+		cd->arcs = a->colorchain;
+	else {
+		for (; aa != NULL && aa->colorchain != a; aa = aa->colorchain)
+			continue;
+		assert(aa != NULL);
+		aa->colorchain = a->colorchain;
+	}
+	a->colorchain = NULL;	/* paranoia */
+}
+
+/*
+ * singleton - is this character in its own color?
+ */
+static int			/* predicate */
+singleton(struct colormap *cm,
+		  chr c)
+{
+	color co;			/* color of c */
+
+	co = GETCOLOR(cm, c);
+	if (cm->cd[co].nchrs == 1 && cm->cd[co].sub == NOSUB)
+		return 1;
+	return 0;
+}
+
+/*
+ * rainbow - add arcs of all full colors (but one) between specified states
+ */
+static void
+rainbow(struct nfa *nfa,
+		struct colormap *cm,
+		int type,
+		pcolor but,				/* COLORLESS if no exceptions */
+		struct state *from,
+		struct state *to)
+{
+	struct colordesc *cd;
+	struct colordesc *end = CDEND(cm);
+	color co;
+
+	for (cd = cm->cd, co = 0; cd < end && !CISERR(); cd++, co++)
+		if (!UNUSEDCOLOR(cd) && cd->sub != co && co != but &&
+							!(cd->flags&PSEUDO))
+			newarc(nfa, type, co, from, to);
+}
+
+/*
+ * colorcomplement - add arcs of complementary colors
+ *
+ * The calling sequence ought to be reconciled with cloneouts().
+ */
+static void
+colorcomplement(struct nfa *nfa,
+				struct colormap *cm,
+				int type,
+				struct state *of, /* complements of this guy's PLAIN outarcs */
+				struct state *from,
+				struct state *to)
+{
+	struct colordesc *cd;
+	struct colordesc *end = CDEND(cm);
+	color co;
+
+	assert(of != from);
+	for (cd = cm->cd, co = 0; cd < end && !CISERR(); cd++, co++)
+		if (!UNUSEDCOLOR(cd) && !(cd->flags&PSEUDO))
+			if (findarc(of, PLAIN, co) == NULL)
+				newarc(nfa, type, co, from, to);
+}
+
+
+#ifdef REG_DEBUG
+
+/*
+ * dumpcolors - debugging output
+ */
+static void
+dumpcolors(struct colormap *cm,
+		   FILE *f)
+{
+	struct colordesc *cd;
+	struct colordesc *end;
+	color co;
+	chr c;
+	char *has;
+
+	fprintf(f, "max %ld\n", (long)cm->max);
+	if (NBYTS > 1)
+		fillcheck(cm, cm->tree, 0, f);
+	end = CDEND(cm);
+	for (cd = cm->cd + 1, co = 1; cd < end; cd++, co++)	/* skip 0 */
+		if (!UNUSEDCOLOR(cd)) {
+			assert(cd->nchrs > 0);
+			has = (cd->block != NULL) ? "#" : "";
+			if (cd->flags&PSEUDO)
+				fprintf(f, "#%2ld%s(ps): ", (long)co, has);
+			else
+				fprintf(f, "#%2ld%s(%2d): ", (long)co,
+							has, cd->nchrs);
+			/* it's hard to do this more efficiently */
+			for (c = CHR_MIN; c < CHR_MAX; c++)
+				if (GETCOLOR(cm, c) == co)
+					dumpchr(c, f);
+			assert(c == CHR_MAX);
+			if (GETCOLOR(cm, c) == co)
+				dumpchr(c, f);
+			fprintf(f, "\n");
+		}
+}
+
+/*
+ * fillcheck - check proper filling of a tree
+ */
+static void
+fillcheck(struct colormap *cm,
+		  union tree *tree,
+		  int level,			/* level number (top == 0) of this block */
+		  FILE *f)
+{
+	int i;
+	union tree *t;
+	union tree *fillt = &cm->tree[level+1];
+
+	assert(level < NBYTS-1);	/* this level has pointers */
+	for (i = BYTTAB-1; i >= 0; i--) {
+		t = tree->tptr[i];
+		if (t == NULL)
+			fprintf(f, "NULL found in filled tree!\n");
+		else if (t == fillt)
+			{}
+		else if (level < NBYTS-2)	/* more pointer blocks below */
+			fillcheck(cm, t, level+1, f);
+	}
+}
+
+/*
+ * dumpchr - print a chr
+ *
+ * Kind of char-centric but works well enough for debug use.
+ */
+static void
+dumpchr(chr c,
+		FILE *f)
+{
+	if (c == '\\')
+		fprintf(f, "\\\\");
+	else if (c > ' ' && c <= '~')
+		putc((char)c, f);
+	else
+		fprintf(f, "\\u%04lx", (long)c);
+}
+
+#endif /* REG_DEBUG */

src/backend/regex/regc_cvec.c

+/*
+ * Utility functions for handling cvecs
+ * This file is #included by regcomp.c.
+ *
+ * Copyright (c) 1998, 1999 Henry Spencer.  All rights reserved.
+ * 
+ * Development of this software was funded, in part, by Cray Research Inc.,
+ * UUNET Communications Services Inc., Sun Microsystems Inc., and Scriptics
+ * Corporation, none of whom are responsible for the results.  The author
+ * thanks all of them. 
+ * 
+ * Redistribution and use in source and binary forms -- with or without
+ * modification -- are permitted for any purpose, provided that
+ * redistributions in source form retain this entire copyright notice and
+ * indicate the origin and nature of any modifications.
+ * 
+ * I'd appreciate being given credit for this package in the documentation
+ * of software which uses it, but that is not a requirement.
+ * 
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
+ * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL
+ * HENRY SPENCER BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+ * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * $Header: /cvsroot/pgsql/src/backend/regex/regc_cvec.c,v 1.1 2003/02/05 17:41:32 tgl Exp $
+ *
+ */
+
+/*
+ * newcvec - allocate a new cvec
+ */
+static struct cvec *
+newcvec(int nchrs,				/* to hold this many chrs... */
+		int nranges,			/* ... and this many ranges... */
+		int nmcces)				/* ... and this many MCCEs */
+{
+    size_t n;
+    size_t nc;
+    struct cvec *cv;
+
+    nc = (size_t)nchrs + (size_t)nmcces*(MAXMCCE+1) + (size_t)nranges*2;
+    n = sizeof(struct cvec) + (size_t)(nmcces-1)*sizeof(chr *)
+	    + nc*sizeof(chr);
+    cv = (struct cvec *)MALLOC(n);
+    if (cv == NULL) {
+	return NULL;
+    }
+    cv->chrspace = nchrs;
+    cv->chrs = (chr *)&cv->mcces[nmcces];	/* chrs just after MCCE ptrs */
+    cv->mccespace = nmcces;
+    cv->ranges = cv->chrs + nchrs + nmcces*(MAXMCCE+1);
+    cv->rangespace = nranges;
+    return clearcvec(cv);
+}
+
+/*
+ * clearcvec - clear a possibly-new cvec
+ * Returns pointer as convenience.
+ */
+static struct cvec *
+clearcvec(struct cvec *cv)
+{
+    int i;
+
+    assert(cv != NULL);
+    cv->nchrs = 0;
+    assert(cv->chrs == (chr *)&cv->mcces[cv->mccespace]);
+    cv->nmcces = 0;
+    cv->nmccechrs = 0;
+    cv->nranges = 0;
+    for (i = 0; i < cv->mccespace; i++) {
+	cv->mcces[i] = NULL;
+    }
+
+    return cv;
+}
+
+/*
+ * addchr - add a chr to a cvec
+ */
+static void
+addchr(struct cvec *cv,			/* character vector */
+	   chr c)				/* character to add */
+{
+    assert(cv->nchrs < cv->chrspace - cv->nmccechrs);
+    cv->chrs[cv->nchrs++] = (chr)c;
+}
+
+/*
+ * addrange - add a range to a cvec
+ */
+static void
+addrange(struct cvec *cv,			/* character vector */
+		 chr from,				/* first character of range */
+		 chr to)				/* last character of range */
+{
+    assert(cv->nranges < cv->rangespace);
+    cv->ranges[cv->nranges*2] = (chr)from;
+    cv->ranges[cv->nranges*2 + 1] = (chr)to;
+    cv->nranges++;
+}
+
+/*
+ * addmcce - add an MCCE to a cvec
+ */
+static void
+addmcce(struct cvec *cv,			/* character vector */
+		chr *startp,			/* beginning of text */
+		chr *endp)				/* just past end of text */
+{
+    int len;
+    int i;
+    chr *s;
+    chr *d;
+
+    if (startp == NULL && endp == NULL) {
+	return;
+    }
+    len = endp - startp;
+    assert(len > 0);
+    assert(cv->nchrs + len < cv->chrspace - cv->nmccechrs);
+    assert(cv->nmcces < cv->mccespace);
+    d = &cv->chrs[cv->chrspace - cv->nmccechrs - len - 1];
+    cv->mcces[cv->nmcces++] = d;
+    for (s = startp, i = len; i > 0; s++, i--) {
+	*d++ = *s;
+    }
+    *d++ = 0;				/* endmarker */
+    assert(d == &cv->chrs[cv->chrspace - cv->nmccechrs]);
+    cv->nmccechrs += len + 1;
+}
+
+/*
+ * haschr - does a cvec contain this chr?
+ */
+static int				/* predicate */
+haschr(struct cvec *cv,			/* character vector */
+	   chr c)				/* character to test for */
+{
+    int i;
+    chr *p;
+
+    for (p = cv->chrs, i = cv->nchrs; i > 0; p++, i--) {
+	if (*p == c) {
+	    return 1;
+	}
+    }
+    for (p = cv->ranges, i = cv->nranges; i > 0; p += 2, i--) {
+	if ((*p <= c) && (c <= *(p+1))) {
+	    return 1;
+	}
+    }
+    return 0;
+}
+
+/*
+ * getcvec - get a cvec, remembering it as v->cv
+ */
+static struct cvec *
+getcvec(struct vars *v,			/* context */
+		int nchrs,				/* to hold this many chrs... */
+		int nranges,			/* ... and this many ranges... */
+		int nmcces)				/* ... and this many MCCEs */
+{
+    if (v->cv != NULL && nchrs <= v->cv->chrspace &&
+	    nranges <= v->cv->rangespace && nmcces <= v->cv->mccespace) {
+	return clearcvec(v->cv);
+    }
+
+    if (v->cv != NULL) {
+	freecvec(v->cv);
+    }
+    v->cv = newcvec(nchrs, nranges, nmcces);
+    if (v->cv == NULL) {
+	ERR(REG_ESPACE);
+    }
+
+    return v->cv;
+}
+
+/*
+ * freecvec - free a cvec
+ */
+static void
+freecvec(struct cvec *cv)
+{
+    FREE(cv);
+}

src/backend/regex/regfree.c

-/*-
- * Copyright (c) 1992, 1993, 1994 Henry Spencer.
- * Copyright (c) 1992, 1993, 1994
- *		The Regents of the University of California.  All rights reserved.
+/*
+ * regfree - free an RE
  *
- * This code is derived from software contributed to Berkeley by
- * Henry Spencer.
+ * Copyright (c) 1998, 1999 Henry Spencer.  All rights reserved.
+ * 
+ * Development of this software was funded, in part, by Cray Research Inc.,
+ * UUNET Communications Services Inc., Sun Microsystems Inc., and Scriptics
+ * Corporation, none of whom are responsible for the results.  The author
+ * thanks all of them. 
+ * 
+ * Redistribution and use in source and binary forms -- with or without
+ * modification -- are permitted for any purpose, provided that
+ * redistributions in source form retain this entire copyright notice and
+ * indicate the origin and nature of any modifications.
+ * 
+ * I'd appreciate being given credit for this package in the documentation
+ * of software which uses it, but that is not a requirement.
+ * 
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
+ * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL
+ * HENRY SPENCER BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+ * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *	  notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *	  notice, this list of conditions and the following disclaimer in the
- *	  documentation and/or other materials provided with the distribution.
- * 3. All advertising materials mentioning features or use of this software
- *	  must display the following acknowledgement:
- *		This product includes software developed by the University of
- *		California, Berkeley and its contributors.
- * 4. Neither the name of the University nor the names of its contributors
- *	  may be used to endorse or promote products derived from this software
- *	  without specific prior written permission.
+ * $Header: /cvsroot/pgsql/src/backend/regex/regfree.c,v 1.16 2003/02/05 17:41:33 tgl Exp $
  *
- * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.	IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
  *
- *		@(#)regfree.c	8.3 (Berkeley) 3/20/94
+ * You might think that this could be incorporated into regcomp.c, and
+ * that would be a reasonable idea... except that this is a generic
+ * function (with a generic name), applicable to all compiled REs
+ * regardless of the size of their characters, whereas the stuff in
+ * regcomp.c gets compiled once per character size.
  */
 
-#include "postgres.h"
-
+#include "regex/regguts.h"
 
-#include "regex/regex.h"
-#include "regex/utils.h"
-#include "regex/regex2.h"
 
 /*
- * regfree - free everything
+ * pg_regfree - free an RE (generic function, punts to RE-specific function)
+ *
+ * Ignoring invocation with NULL is a convenience.
  */
 void
-pg_regfree(regex_t *preg)
+pg_regfree(regex_t *re)
 {
-	struct re_guts *g;
-
-	if (preg->re_magic != MAGIC1)		/* oops */
-		return;					/* nice to complain, but hard */
-
-	g = preg->re_g;
-	if (g == NULL || g->magic != MAGIC2)		/* oops again */
+	if (re == NULL)
 		return;
-	preg->re_magic = 0;			/* mark it invalid */
-	g->magic = 0;				/* mark it invalid */
-
-	if (preg->patsave != NULL)
-		free((char *) preg->patsave);
-	if (g->strip != NULL)
-		free((char *) g->strip);
-	if (g->sets != NULL)
-		free((char *) g->sets);
-	if (g->setbits != NULL)
-		free((char *) g->setbits);
-	if (g->must != NULL)
-		free(g->must);
-	free((char *) g);
+	(*((struct fns *)re->re_fns)->free)(re);
 }

src/backend/regex/retest.c

-/*
- * a simple regexp debug program
- *
- * $Header: /cvsroot/pgsql/src/backend/regex/Attic/retest.c,v 1.5 2002/06/11 15:41:37 thomas Exp $
- */
-
-#include "postgres.h"
-#include "regex/regex.h"
-
-int
-main()
-{
-	int			sts;
-	regex_t		re;
-	char		buf[1024];
-	char	   *p;
-
-	printf("type in regexp string: ");
-	if (!fgets(buf, sizeof(buf), stdin))
-		exit(0);
-	p = strchr(buf, '\n');
-	if (p)
-		*p = '\0';
-
-	sts = pg_regcomp(&re, buf, 1);
-	printf("regcomp: parses \"%s\" and returns %d\n", buf, sts);
-	for (;;)
-	{
-		printf("type in target string: ");
-		if (!fgets(buf, sizeof(buf), stdin))
-			exit(0);
-		p = strchr(buf, '\n');
-		if (p)
-			*p = '\0';
-
-		sts = pg_regexec(&re, buf, 0, 0, 0);
-		printf("regexec: returns %d\n", sts);
-	}
-}
-
-void
-elog(int lev, const char *fmt,...)
-{
-}

src/include/regex/regcustom.h

+/*
+ * Copyright (c) 1998, 1999 Henry Spencer.  All rights reserved.
+ * 
+ * Development of this software was funded, in part, by Cray Research Inc.,
+ * UUNET Communications Services Inc., Sun Microsystems Inc., and Scriptics
+ * Corporation, none of whom are responsible for the results.  The author
+ * thanks all of them. 
+ * 
+ * Redistribution and use in source and binary forms -- with or without
+ * modification -- are permitted for any purpose, provided that
+ * redistributions in source form retain this entire copyright notice and
+ * indicate the origin and nature of any modifications.
+ * 
+ * I'd appreciate being given credit for this package in the documentation
+ * of software which uses it, but that is not a requirement.
+ * 
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
+ * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL
+ * HENRY SPENCER BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+ * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * $Id: regcustom.h,v 1.1 2003/02/05 17:41:32 tgl Exp $
+ */
+
+/* headers if any */
+#include "postgres.h"
+
+#include <ctype.h>
+#include <limits.h>
+
+#include "mb/pg_wchar.h"
+
+
+/* overrides for regguts.h definitions, if any */
+#define	FUNCPTR(name, args)	(*name) args
+#define	MALLOC(n)		malloc(n)
+#define	FREE(p)			free(VS(p))
+#define	REALLOC(p,n)		realloc(VS(p),n)
+
+/* internal character type and related */
+typedef pg_wchar chr;	/* the type itself */
+typedef unsigned uchr;		/* unsigned type that will hold a chr */
+typedef int celt;		/* type to hold chr, MCCE number, or NOCELT */
+#define	NOCELT	(-1)		/* celt value which is not valid chr or MCCE */
+#define	CHR(c)	((unsigned char) (c)) /* turn char literal into chr literal */
+#define	DIGITVAL(c)	((c)-'0')	/* turn chr digit into its value */
+#define	CHRBITS	32		/* bits in a chr; must not use sizeof */
+#define	CHR_MIN	0x00000000		/* smallest and largest chr; the value */
+#define	CHR_MAX	0xfffffffe		/*  CHR_MAX-CHR_MIN+1 should fit in uchr */
+
+/* functions operating on chr */
+#define	iscalnum(x)	pg_isalnum(x)
+#define	iscalpha(x)	pg_isalpha(x)
+#define	iscdigit(x)	pg_isdigit(x)
+#define	iscspace(x)	pg_isspace(x)
+
+/* and pick up the standard header */
+#include "regex.h"