From aa36d4df21113a36c2e368e0abb417480a6eebbd Mon Sep 17 00:00:00 2001
From: kosaki <kosaki@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>
Date: Thu, 3 Feb 2011 16:54:52 +0000
Subject: [PATCH] 	* string.c (count_utf8_lead_bytes_with_word): wrote
 function 	  comments.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@30778 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
---
 ChangeLog |  5 +++++
 string.c  | 17 +++++++++++++++++
 2 files changed, 22 insertions(+)

diff --git a/ChangeLog b/ChangeLog
index 11bb47c732..93bb47ccef 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+Fri Feb  4 01:50:13 2011  KOSAKI Motohiro  <kosaki.motohiro@gmail.com>
+
+	* string.c (count_utf8_lead_bytes_with_word): wrote function
+	  comments.
+
 Fri Feb  4 00:14:55 2011  Nobuyoshi Nakada  <nobu@ruby-lang.org>
 
 	* ext/zlib/zlib.c (gzfile_reader_get_unused): no need to dup
diff --git a/string.c b/string.c
index 6628eb0aef..96b5d9cc7f 100644
--- a/string.c
+++ b/string.c
@@ -1038,13 +1038,30 @@ rb_enc_strlen_cr(const char *p, const char *e, rb_encoding *enc, int *cr)
 
 #ifdef NONASCII_MASK
 #define is_utf8_lead_byte(c) (((c)&0xC0) != 0x80)
+
+/*
+ * UTF-8 leading bytes have either 0xxxxxxx or 11xxxxxx
+ * bit represention. (see http://en.wikipedia.org/wiki/UTF-8)
+ * Therefore, following pseudo code can detect UTF-8 leading byte.
+ *
+ * if (!(byte & 0x80))
+ *   byte |= 0x40;          // turn on bit6
+ * return ((byte>>6) & 1);  // bit6 represent it's leading byte or not.
+ *
+ * This function calculate every bytes in the argument word `s'
+ * using the above logic concurrently. and gather every bytes result.
+ */
 static inline VALUE
 count_utf8_lead_bytes_with_word(const VALUE *s)
 {
     VALUE d = *s;
+
+    /* Transform into bit0 represent UTF-8 leading or not. */
     d |= ~(d>>1);
     d >>= 6;
     d &= NONASCII_MASK >> 7;
+
+    /* Gather every bytes. */
     d += (d>>8);
     d += (d>>16);
 #if SIZEOF_VALUE == 8