From 7e6682c62b92e15e4554ed715b946366275e9b94 Mon Sep 17 00:00:00 2001
From: Jim Meyering <meyering@fb.com>
Date: Mon, 16 Sep 2013 10:06:14 -0700
Subject: [PATCH] maint: dfa: improve comments and formatting

* src/dfa.c (add_utf8_anychar): Correct wording/alignment of a comment.
(dfaexec): Add curly braces around multi-line while statement within
a "then" block.
(ANYCHAR): Clarify comment: "." does not match an invalid UTF8 character.
(parse_bracket_exp) Improve comment.
---
 src/dfa.c | 65 ++++++++++++++++++++++++++++++++-------------------------------
 1 file changed, 33 insertions(+), 32 deletions(-)

diff --git a/src/dfa.c b/src/dfa.c
index b447a8a..45e3c40 100644
--- a/src/dfa.c
+++ b/src/dfa.c
@@ -243,7 +243,7 @@ enum
   RPAREN,                       /* RPAREN never appears in the parse tree.  */

   ANYCHAR,                      /* ANYCHAR is a terminal symbol that matches
-                                   any multibyte (or single byte) characters.
+                                   a valid multibyte (or single byte) character.
                                    It is used only if MB_CUR_MAX > 1.  */

   MBCSET,                       /* MBCSET is similar to CSET, but for
@@ -909,8 +909,7 @@ find_pred (const char *str)
 }

 /* Multibyte character handling sub-routine for lex.
-   This function  parse a bracket expression and build a struct
-   mb_char_classes.  */
+   Parse a bracket expression and build a struct mb_char_classes.  */
 static token
 parse_bracket_exp (void)
 {
@@ -1633,7 +1632,7 @@ add_utf8_anychar (void)
 {
 #if MBS_SUPPORT
   static const charclass utf8_classes[5] = {
-    {0, 0, 0, 0, ~0, ~0, 0, 0}, /* 80-bf: non-lead bytes */
+    {0, 0, 0, 0, ~0, ~0, 0, 0},		/* 80-bf: non-leading bytes */
     {~0, ~0, ~0, ~0, 0, 0, 0, 0},       /* 00-7f: 1-byte sequence */
     {0, 0, 0, 0, 0, 0, ~3, 0},          /* c2-df: 2-byte sequence */
     {0, 0, 0, 0, 0, 0, 0, 0xffff},      /* e0-ef: 3-byte sequence */
@@ -3322,37 +3321,39 @@ dfaexec (struct dfa *d, char const *begin, char *end,
   for (;;)
     {
       if (d->mb_cur_max > 1)
-        while ((t = trans[s]) != NULL)
-          {
-            if (p > buf_end)
-              break;
-            s1 = s;
-            SKIP_REMAINS_MB_IF_INITIAL_STATE (s, p);
+        {
+          while ((t = trans[s]) != NULL)
+            {
+              if (p > buf_end)
+                break;
+              s1 = s;
+              SKIP_REMAINS_MB_IF_INITIAL_STATE (s, p);

-            if (d->states[s].mbps.nelem == 0)
-              {
-                s = t[*p++];
-                continue;
-              }
+              if (d->states[s].mbps.nelem == 0)
+                {
+                  s = t[*p++];
+                  continue;
+                }

-            /* Falling back to the glibc matcher in this case gives
-               better performance (up to 25% better on [a-z], for
-               example) and enables support for collating symbols and
-               equivalence classes.  */
-            if (backref)
-              {
-                *backref = 1;
-                free (mblen_buf);
-                free (inputwcs);
-                *end = saved_end;
-                return (char *) p;
-              }
+              /* Falling back to the glibc matcher in this case gives
+                 better performance (up to 25% better on [a-z], for
+                 example) and enables support for collating symbols and
+                 equivalence classes.  */
+              if (backref)
+                {
+                  *backref = 1;
+                  free (mblen_buf);
+                  free (inputwcs);
+                  *end = saved_end;
+                  return (char *) p;
+                }

-            /* Can match with a multibyte character (and multi character
-               collating element).  Transition table might be updated.  */
-            s = transit_state (d, s, &p);
-            trans = d->trans;
-          }
+              /* Can match with a multibyte character (and multi character
+                 collating element).  Transition table might be updated.  */
+              s = transit_state (d, s, &p);
+              trans = d->trans;
+            }
+        }
       else
         {
           while ((t = trans[s]) != NULL)
--
1.8.4.299.gb3e7d24