Use dfa's new ability to handle anchors.

10 files changed, 72 insertions, 11 deletions

diff --git a/ChangeLog b/ChangeLog
index 09d2a22f..755be27b 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+2016-09-09         Norihiro Tanaka      <noritnk@kcn.ne.jp>
+
+	* awk.h (struct Regexp): Remove member has_anchor.  All uses removed.
+	* re.c (make_regexp, research): Use dfa matcher for regex with anchor.
+
 2016-09-09         Arnold D. Robbins     <arnold@skeeve.com>
 
 	* dfa.c: Sync with grep.
diff --git a/awk.h b/awk.h
index 2c401637..2353700e 100644
--- a/awk.h
+++ b/awk.h
@@ -210,7 +210,6 @@ typedef struct Regexp {
 	struct re_pattern_buffer pat;
 	struct re_registers regs;
 	struct dfa *dfareg;
-	bool has_anchor;	/* re has anchors which dfa avoids */
 	bool non_empty;		/* for use in fpat_parse_field */
 	bool has_meta;		/* re has meta chars so (probably) isn't simple string */
 	bool maybe_long;	/* re has meta chars that can match long text */
diff --git a/re.c b/re.c
index 69cc50e1..167a265d 100644
--- a/re.c
+++ b/re.c
@@ -49,7 +49,6 @@ make_regexp(const char *s, size_t len, bool ignorecase, bool dfa, bool canfatal)
 	int c, c2;
 	static bool first = true;
 	static bool no_dfa = false;
-	bool has_anchor = false;
 	reg_syntax_t dfa_syn;
 	int i;
 
@@ -160,9 +159,6 @@ make_regexp(const char *s, size_t len, bool ignorecase, bool dfa, bool canfatal)
 			} /* switch */
 		} else {
 			c = *src;
-			if (c == '^' || c == '$')
-				has_anchor = true;
-
 			*dest++ = *src++;	/* not '\\' */
 		}
 		if (gawk_mb_cur_max > 1 && is_multibyte)
@@ -228,11 +224,10 @@ make_regexp(const char *s, size_t len, bool ignorecase, bool dfa, bool canfatal)
 	if (dfa && ! no_dfa) {
 		rp->dfareg = dfaalloc();
 		dfasyntax(rp->dfareg, & localeinfo, dfa_syn,
-			  ignorecase ? DFA_CASE_FOLD : 0);
+			  (ignorecase ? DFA_CASE_FOLD : 0) | DFA_ANCHOR);
 		dfacomp(buf, len, rp->dfareg, true);
 	} else
 		rp->dfareg = NULL;
-	rp->has_anchor = has_anchor;
 
 	/* Additional flags that help with RS as regexp. */
 	for (i = 0; i < len; i++) {
@@ -287,7 +282,7 @@ research(Regexp *rp, char *str, int start,
 			ret = dfaexec(superset, str+start, str+start+len,
 							true, NULL, NULL);
 
-		if (ret && ((! need_start && ! rp->has_anchor)
+		if (ret && (! need_start
 				|| (! superset && dfaisfast(rp->dfareg))))
 			ret = dfaexec(rp->dfareg, str+start, str+start+len,
 						true, NULL, &try_backref);
@@ -298,7 +293,6 @@ research(Regexp *rp, char *str, int start,
 			|| start != 0
 			|| no_bol
 			|| need_start
-			|| rp->has_anchor
 			|| try_backref) {
 			/*
 			 * Passing NULL as last arg speeds up search for cases
diff --git a/test/ChangeLog b/test/ChangeLog
index 9ac7111e..a4d5baae 100644
--- a/test/ChangeLog
+++ b/test/ChangeLog
@@ -1,3 +1,8 @@
+2016-09-09         Norihiro Tanaka      <noritnk@kcn.ne.jp>
+
+	* Makefile.am (anchor): New test.
+	* anchor.awk, anchor.in, anchor.ok: New files.
+
 2016-08-25         Arnold D. Robbins     <arnold@skeeve.com>
 
 	* 4.1.4: Release tar ball made.
diff --git a/test/Makefile.am b/test/Makefile.am
index a0b4f525..9dbedb35 100644
--- a/test/Makefile.am
+++ b/test/Makefile.am
@@ -47,6 +47,9 @@ EXTRA_DIST = \
 	anchgsub.awk \
 	anchgsub.in \
 	anchgsub.ok \
+	anchor.awk \
+	anchor.in \
+	anchor.ok \
 	argarray.awk \
 	argarray.in \
 	argarray.ok \
@@ -1147,7 +1150,7 @@ CLEANFILES = core core.* fmtspcl.ok
 
 # try to keep these sorted. each letter starts a new line
 BASIC_TESTS = \
-	addcomma anchgsub argarray arrayind1 arrayind2 arrayparm arrayprm2 arrayprm3 \
+	addcomma anchgsub anchor argarray arrayind1 arrayind2 arrayparm arrayprm2 arrayprm3 \
 	arrayref arrymem1 arryref2 arryref3 arryref4 arryref5 arynasty \
 	arynocls aryprm1 aryprm2 aryprm3 aryprm4 aryprm5 aryprm6 aryprm7 \
 	aryprm8 aryprm9 arysubnm asgext awkpath \
diff --git a/test/Makefile.in b/test/Makefile.in
index 5731487f..f1ffc0db 100644
--- a/test/Makefile.in
+++ b/test/Makefile.in
@@ -304,6 +304,9 @@ EXTRA_DIST = \
 	anchgsub.awk \
 	anchgsub.in \
 	anchgsub.ok \
+	anchor.awk \
+	anchor.in \
+	anchor.ok \
 	argarray.awk \
 	argarray.in \
 	argarray.ok \
@@ -1403,7 +1406,7 @@ CLEANFILES = core core.* fmtspcl.ok
 
 # try to keep these sorted. each letter starts a new line
 BASIC_TESTS = \
-	addcomma anchgsub argarray arrayind1 arrayind2 arrayparm arrayprm2 arrayprm3 \
+	addcomma anchgsub anchor argarray arrayind1 arrayind2 arrayparm arrayprm2 arrayprm3 \
 	arrayref arrymem1 arryref2 arryref3 arryref4 arryref5 arynasty \
 	arynocls aryprm1 aryprm2 aryprm3 aryprm4 aryprm5 aryprm6 aryprm7 \
 	aryprm8 aryprm9 arysubnm asgext awkpath \
@@ -2800,6 +2803,11 @@ anchgsub:
 	@AWKPATH="$(srcdir)" $(AWK) -f $@.awk  < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@
 	@-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@
 
+anchor:
+	@echo $@
+	@AWKPATH="$(srcdir)" $(AWK) -f $@.awk  < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@
+	@-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@
+
 arrayind1:
 	@echo $@
 	@AWKPATH="$(srcdir)" $(AWK) -f $@.awk  < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@
diff --git a/test/Maketests b/test/Maketests
index b28a32ab..a13ed244 100644
--- a/test/Maketests
+++ b/test/Maketests
@@ -10,6 +10,11 @@ anchgsub:
 	@AWKPATH="$(srcdir)" $(AWK) -f $@.awk  < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@
 	@-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@
 
+anchor:
+	@echo $@
+	@AWKPATH="$(srcdir)" $(AWK) -f $@.awk  < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@
+	@-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@
+
 arrayind1:
 	@echo $@
 	@AWKPATH="$(srcdir)" $(AWK) -f $@.awk  < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@
diff --git a/test/anchor.awk b/test/anchor.awk
new file mode 100644
index 00000000..56f47569
--- /dev/null
+++ b/test/anchor.awk
@@ -0,0 +1,33 @@
+BEGIN { RS = "" }
+
+{
+	if (/^A/)
+		print "ok"
+	else
+		print "not ok"
+
+	if (/B$/)
+		print "not ok"
+	else
+		print "ok"
+
+	if (/^C/)
+		print "not ok"
+	else
+		print "ok"
+
+	if (/D$/)
+		print "not ok"
+	else
+		print "ok"
+
+	if (/^E/)
+		print "not ok"
+	else
+		print "ok"
+
+	if (/F$/)
+		print "ok"
+	else
+		print "not ok"
+}
diff --git a/test/anchor.in b/test/anchor.in
new file mode 100644
index 00000000..a97e9859
--- /dev/null
+++ b/test/anchor.in
@@ -0,0 +1,3 @@
+A line1 B
+C line2 D
+E line3 F
diff --git a/test/anchor.ok b/test/anchor.ok
new file mode 100644
index 00000000..7780b88b
--- /dev/null
+++ b/test/anchor.ok
@@ -0,0 +1,6 @@
+ok
+ok
+ok
+ok
+ok
+ok