Transition for non-UTF8 locales is somewhat complicated. In addtion,
optimization is only state 0 for initial state.
The patch is simplify dfaexec() and extends optimization to initial
state for all contexts, which are s < D->min_trcount.
From c3ac857ee6f7167daaa242036769f5719732ae43 Mon Sep 17 00:00:00 2001
From: Norihiro Tanaka <nori...@kcn.ne.jp>
Date: Sun, 14 Aug 2016 11:21:48 +0900
Subject: [PATCH 1/2] dfa: simplify and optimize at initial state in execution
* src/dfa.c (skip_remains_mb): Remove argument *pwc. Update calller.
(dfaexec_main): Simplify and optimize at initial state.
---
src/dfa.c | 79 +++++++++++++++++-------------------------------------------
1 files changed, 23 insertions(+), 56 deletions(-)
diff --git a/src/dfa.c b/src/dfa.c
index 30aaecf..59bb3bc 100644
--- a/src/dfa.c
+++ b/src/dfa.c
@@ -3144,16 +3144,14 @@ transit_state (struct dfa *d, state_num s, unsigned
char const **pp,
Both P and MBP must be no larger than END. */
static unsigned char const *
skip_remains_mb (struct dfa *d, unsigned char const *p,
- unsigned char const *mbp, char const *end, wint_t *wcp)
+ unsigned char const *mbp, char const *end)
{
- wint_t wc = WEOF;
+ wint_t wc;
if (never_trail[*p])
return p;
while (mbp < p)
mbp += mbs_to_wchar (&wc, (char const *) mbp,
end - (char const *) mbp, d);
- if (wcp != NULL)
- *wcp = wc;
return mbp;
}
@@ -3210,46 +3208,22 @@ dfaexec_main (struct dfa *d, char const *begin, char
*end, bool allow_nl,
for (;;)
{
- if (multibyte)
+ while ((t = trans[s]) != NULL)
{
- while ((t = trans[s]) != NULL)
+ if (s < d->min_trcount)
{
- s1 = s;
-
- if (s < d->min_trcount)
+ if (!multibyte || d->states[s].mbps.nelem == 0)
{
- if (d->min_trcount == 1)
- {
- if (d->states[s].mbps.nelem == 0)
- {
- do
- {
- while (t[*p] == 0)
- p++;
- p = mbp = skip_remains_mb (d, p, mbp, end, NULL);
- }
- while (t[*p] == 0);
- }
- else
- p = mbp = skip_remains_mb (d, p, mbp, end, NULL);
- }
- else
- {
- wint_t wc;
- mbp = skip_remains_mb (d, p, mbp, end, &wc);
-
- /* If d->min_trcount is greater than 1, maybe
- transit to another initial state after skip. */
- if (p < mbp)
- {
- /* It's CTX_LETTER or CTX_NONE. CTX_NEWLINE
- cannot happen, as we assume that a newline
- is always a single byte character. */
- s1 = s = d->initstate_notbol;
- p = mbp;
- }
- }
+ while (t[*p] == s)
+ p++;
}
+ if (multibyte)
+ p = mbp = skip_remains_mb (d, p, mbp, end);
+ }
+
+ if (multibyte)
+ {
+ s1 = s;
if (d->states[s].mbps.nelem == 0 || (*p == eol && !allow_nl)
|| (*p == '\n' && !(syntax_bits & RE_DOT_NEWLINE))
@@ -3269,22 +3243,7 @@ dfaexec_main (struct dfa *d, char const *begin, char
*end, bool allow_nl,
trans = d->trans;
}
}
- }
- else
- {
- if (s == 0)
- {
- t = trans[s];
- if (t)
- {
- while (t[*p] == 0)
- p++;
- s1 = 0;
- s = t[*p++];
- }
- }
-
- while ((t = trans[s]) != NULL)
+ else
{
s1 = t[*p++];
t = trans[s1];
@@ -3295,6 +3254,11 @@ dfaexec_main (struct dfa *d, char const *begin, char
*end, bool allow_nl,
s1 = tmp; /* swap */
break;
}
+ if (s < d->min_trcount)
+ {
+ while (t[*p] == s1)
+ p++;
+ }
s = t[*p++];
}
}
@@ -3319,6 +3283,9 @@ dfaexec_main (struct dfa *d, char const *begin, char
*end, bool allow_nl,
if (d->success[s] & sbit[*p])
goto done;
+ if (multibyte && s < d->min_trcount)
+ p = mbp = skip_remains_mb (d, p, mbp, end);
+
s1 = s;
if (!multibyte || d->states[s].mbps.nelem == 0
|| (*p == eol && !allow_nl)
--
1.7.1
