regcomp.c - decompose into smaller files

This splits a bunch of the subcomponents of the regex engine into
smaller files.

       regcomp_debug.c
       regcomp_internal.h
       regcomp_invlist.c
       regcomp_study.c
       regcomp_trie.c

The only real change besides to the build machine to achieve the split
is to also adds some new defines which can be used in embed.fnc to control
exports without having to enumerate /every/ regex engine file. For
instance all of regcomp*.c defines PERL_IN_REGCOMP_ANY, and this is used
in embed.fnc to manage exports.

MANIFEST

@@ -5513,6 +5513,11 @@ regcharclass.h			Generated by regen/regcharclass.pl
 regcomp.c			Regular expression compiler
 regcomp.h			Private declarations for above
 regcomp.sym			Data for regnodes.h
+regcomp_debug.c			Regular expression compiler debug code
+regcomp_internal.h		Internal stuff for regex compiler
+regcomp_invlist.c		Invlist logic for regular expresion engine
+regcomp_study.c			Optimizer for regular expresion compiler
+regcomp_trie.c			Trie logic for regular expresion compiler
 regen.pl			Run all scripts that (re)generate files
 regen/charset_translations.pl	Character set utilities
 regen/ebcdic.pl			Generates ebcdic_tables.h

Makefile.SH

@@ -530,17 +530,19 @@ unidatadirs = lib/unicore/To lib/unicore/lib
 
 h1 = EXTERN.h INTERN.h XSUB.h av.h $(CONFIGH) cop.h cv.h dosish.h
 h2 = embed.h form.h gv.h handy.h hv.h hv_func.h keywords.h mg.h op.h opcode.h
-h3 = pad.h patchlevel.h perl.h perlapi.h perly.h pp.h proto.h regcomp.h
+h3 = pad.h patchlevel.h perl.h perlapi.h perly.h pp.h proto.h regcomp.h regcomp_internal.h
 h4 = regexp.h scope.h sv.h unixish.h util.h iperlsys.h thread.h
 h5 = utf8.h warnings.h mydtrace.h op_reg_common.h l1_char_class_tab.h
 h6 = charclass_invlists.h
 h = $(h1) $(h2) $(h3) $(h4) $(h5) $(h6)
 
 c1 = av.c scope.c op.c peep.c doop.c doio.c dump.c gv.c hv.c mg.c reentr.c mro_core.c perl.c
-c2 = perly.c pp.c pp_hot.c pp_ctl.c pp_sys.c regcomp.c regexec.c utf8.c sv.c
+c2 = perly.c pp.c pp_hot.c pp_ctl.c pp_sys.c utf8.c sv.c
 c3 = taint.c toke.c util.c deb.c run.c builtin.c universal.c pad.c globals.c keywords.c
 c4 = perlio.c numeric.c mathoms.c locale.c pp_pack.c pp_sort.c caretx.c dquote.c time64.c
-c5 = $(mallocsrc)
+c5 = regcomp.c regcomp_debug.c regcomp_invlist.c regcomp_study.c regcomp_trie.c regexec.c
+c6 = $(mallocsrc)
+c_base  = $(c1) $(c2) $(c3) $(c4) $(c5) $(c6)
 
 !NO!SUBS!
 
@@ -552,17 +554,24 @@ main_only_objs =$main_only_objs
 
 $spitshell >>$Makefile <<'!NO!SUBS!'
 
-c = $(c1) $(c2) $(c3) $(c4) $(c5) miniperlmain.c $(mini_only_src)
+c = $(c_base) miniperlmain.c $(mini_only_src)
 
-obj1 = $(mallocobj) gv$(OBJ_EXT) toke$(OBJ_EXT) perly$(OBJ_EXT) pad$(OBJ_EXT) regcomp$(OBJ_EXT) dump$(OBJ_EXT) util$(OBJ_EXT) mg$(OBJ_EXT) reentr$(OBJ_EXT) mro_core$(OBJ_EXT) keywords$(OBJ_EXT) builtin$(OBJ_EXT)
-obj2 = hv$(OBJ_EXT) av$(OBJ_EXT) run$(OBJ_EXT) pp_hot$(OBJ_EXT) sv$(OBJ_EXT) pp$(OBJ_EXT) scope$(OBJ_EXT) pp_ctl$(OBJ_EXT) pp_sys$(OBJ_EXT) peep$(OBJ_EXT)
-obj3 = doop$(OBJ_EXT) doio$(OBJ_EXT) regexec$(OBJ_EXT) utf8$(OBJ_EXT) taint$(OBJ_EXT) deb$(OBJ_EXT) globals$(OBJ_EXT) perlio$(OBJ_EXT) numeric$(OBJ_EXT) mathoms$(OBJ_EXT) locale$(OBJ_EXT) pp_pack$(OBJ_EXT) pp_sort$(OBJ_EXT) caretx$(OBJ_EXT) dquote$(OBJ_EXT) time64$(OBJ_EXT)
+obj1  = $(mallocobj) gv$(OBJ_EXT) toke$(OBJ_EXT) perly$(OBJ_EXT) pad$(OBJ_EXT)
+obj2  = regcomp$(OBJ_EXT) regcomp_debug$(OBJ_EXT) regcomp_invlist$(OBJ_EXT) regcomp_study$(OBJ_EXT) regcomp_trie$(OBJ_EXT)
+obj3  = regexec$(OBJ_EXT) dump$(OBJ_EXT) util$(OBJ_EXT) mg$(OBJ_EXT) reentr$(OBJ_EXT) mro_core$(OBJ_EXT)
+obj4  = keywords$(OBJ_EXT) builtin$(OBJ_EXT)
+obj5  = hv$(OBJ_EXT) av$(OBJ_EXT) run$(OBJ_EXT) pp_hot$(OBJ_EXT) sv$(OBJ_EXT) pp$(OBJ_EXT)
+obj6  = scope$(OBJ_EXT) pp_ctl$(OBJ_EXT) pp_sys$(OBJ_EXT) peep$(OBJ_EXT)
+obj7  = doop$(OBJ_EXT) doio$(OBJ_EXT) utf8$(OBJ_EXT) taint$(OBJ_EXT)
+obj8  = deb$(OBJ_EXT) globals$(OBJ_EXT) perlio$(OBJ_EXT) numeric$(OBJ_EXT) mathoms$(OBJ_EXT)
+obj9  = locale$(OBJ_EXT) pp_pack$(OBJ_EXT) pp_sort$(OBJ_EXT) caretx$(OBJ_EXT) dquote$(OBJ_EXT)
+obj10 = time64$(OBJ_EXT)
 
 # split the objects into 3 exclusive sets: those used by both miniperl and
 # perl, and those used by just one or the other. Doesn't include the
 # actual perl(mini)main.o, nor any dtrace objects.
 
-common_objs    = $(obj1) $(obj2) $(obj3) $(ARCHOBJS)
+common_objs    = $(obj1) $(obj2) $(obj3) $(obj4) $(obj5) $(obj6) $(obj7) $(obj8) $(obj9) $(obj10) $(ARCHOBJS)
 
 miniperl_objs_nodt = $(mini_only_objs) $(common_objs) miniperlmain$(OBJ_EXT)
 perllib_objs_nodt  = $(main_only_objs) $(common_objs)
@@ -1722,8 +1731,8 @@ distcheck: FORCE
 
 .PHONY: ctags
 
-TAGS: $(c1) $(c2) $(c3) $(c4) $(c5) $(h)
-	etags $(c1) $(c2) $(c3) $(c4) $(c5) $(h)
+TAGS: $(c_base) $(h)
+	etags $(c_base) $(h)
 !NO!SUBS!
 
 $spitshell >>$Makefile <<!GROK!THIS!

Makefile.micro

@@ -18,7 +18,8 @@ O = uav$(_O) udeb$(_O) udoio$(_O) udoop$(_O) udquote$(_O) udump$(_O) \
 	umg$(_O) uperlmain$(_O) uop$(_O) ureentr$(_O) \
 	upad$(_O) uperl$(_O) uperlio$(_O) uperly$(_O) upp$(_O) \
 	upp_ctl$(_O) upp_hot$(_O) upp_sys$(_O) upp_pack$(_O) upp_sort$(_O) \
-	uregcomp$(_O) uregexec$(_O) urun$(_O) \
+	uregcomp$(_O) uregcomp_debug$(_O) uregcomp_invlist$(_O) \
+	uregcomp_study$(_O) uregcomp_trie$(_O) uregexec$(_O) urun$(_O) \
 	uscope$(_O) usv$(_O) utaint$(_O) utime64$(_O) utoke$(_O) \
 	unumeric$(_O) ulocale$(_O) umathoms$(_O) \
 	uuniversal$(_O) uutf8$(_O) uutil$(_O) ukeywords$(_O)
@@ -138,7 +139,19 @@ upp_pack$(_O):	$(HE) pp_pack.c
 upp_sort$(_O):	$(HE) pp_sort.c
 	$(CC) $(CCFLAGS) -o $@ $(CFLAGS) pp_sort.c
 
-uregcomp$(_O):	$(HE) regcomp.c regcomp.h regnodes.h INTERN.h
+uregcomp$(_O):	$(HE) regcomp.c regcomp_internal.h regcomp.h regnodes.h INTERN.h
+	$(CC) $(CCFLAGS) -o $@ $(CFLAGS) regcomp.c
+
+uregcomp_debug$(_O):	$(HE) regcomp_debug.c regcomp_internal.h regcomp.h regnodes.h INTERN.h
+	$(CC) $(CCFLAGS) -o $@ $(CFLAGS) regcomp.c
+
+uregcomp_invlist$(_O):	$(HE) regcomp_invlist.c regcomp_internal.h regcomp.h regnodes.h INTERN.h
+	$(CC) $(CCFLAGS) -o $@ $(CFLAGS) regcomp.c
+
+uregcomp_study$(_O):	$(HE) regcomp_study.c regcomp_internal.h regcomp.h regnodes.h INTERN.h
+	$(CC) $(CCFLAGS) -o $@ $(CFLAGS) regcomp.c
+
+uregcomp_trie$(_O):	$(HE) regcomp_trie.c regcomp_internal.h regcomp.h regnodes.h INTERN.h
 	$(CC) $(CCFLAGS) -o $@ $(CFLAGS) regcomp.c
 
 uregexec$(_O):	$(HE) regexec.c regcomp.h regnodes.h