merge from trunk

4 files changed, 29 insertions, 2 deletions

diff --git a/doc/lispref/ChangeLog b/doc/lispref/ChangeLog
index 3f9d23a5476..d2e86c25cc1 100644
--- a/doc/lispref/ChangeLog
+++ b/doc/lispref/ChangeLog
@@ -1,3 +1,8 @@
+2013-08-20  Eli Zaretskii  <eliz@gnu.org>
+
+        * files.texi (Information about Files): Mention file names with
+        trailing blanks on MS-Windows.  (Bug#15130)
+
 2013-08-18  Xue Fuqiao  <xfq.free@gmail.com>
 
         * positions.texi (Positions): Improve indexing.
diff --git a/doc/lispref/files.texi b/doc/lispref/files.texi
index 77b097ae90a..1f7169522cc 100644
--- a/doc/lispref/files.texi
+++ b/doc/lispref/files.texi
@@ -776,6 +776,14 @@ return information about actual files or directories, so their
 arguments must all exist as actual files or directories unless
 otherwise noted.
 
+@cindex file names, trailing whitespace
+@cindex trailing blanks in file names
+Be careful with file names that end in blanks: some filesystems
+(notably, MS-Windows) will ignore trailing whitespace in file names,
+and return information about the file after stripping those blanks
+from the name, not about the file whose name you passed to the
+functions described in this section.
+
 @menu
 * Testing Accessibility::   Is a given file readable?  Writable?
 * Kinds of Files::          Is it a directory?  A symbolic link?
diff --git a/src/ChangeLog b/src/ChangeLog
index e21d82bdc09..997459f01c2 100644
--- a/src/ChangeLog
+++ b/src/ChangeLog
@@ -1,3 +1,7 @@
+2013-08-20  Kenichi Handa  <handa@gnu.org>
+
+        * character.c (string_char): Improve commentary.
+
 2013-08-20  Paul Eggert  <eggert@cs.ucla.edu>
 
         * image.c (SIGNATURE_DIGESTSIZE): Remove.
diff --git a/src/character.c b/src/character.c
index b2caaa290af..1bde2364e37 100644
--- a/src/character.c
+++ b/src/character.c
@@ -174,11 +174,14 @@ string_char (const unsigned char *p, const unsigned char **advanced, int *len)
 
   if (*p < 0x80 || ! (*p & 0x20) || ! (*p & 0x10))
     {
+      /* 1-, 2-, and 3-byte sequences can be handled by the macro.  */
       c = STRING_CHAR_ADVANCE (p);
     }
   else if (! (*p & 0x08))
     {
-      c = ((((p)[0] & 0xF) << 18)
+      /* A 4-byte sequence of this form:
+         11110xxx 10xxxxxx 10xxxxxx 10xxxxxx  */
+      c = ((((p)[0] & 0x7) << 18)
            | (((p)[1] & 0x3F) << 12)
            | (((p)[2] & 0x3F) << 6)
            | ((p)[3] & 0x3F));
@@ -186,7 +189,14 @@ string_char (const unsigned char *p, const unsigned char **advanced, int *len)
     }
   else
     {
-      c = ((((p)[1] & 0x3F) << 18)
+      /* A 5-byte sequence of this form:
+
+         111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
+
+         Note that the top 4 `x's are always 0, so shifting p[1] can
+         never exceed the maximum valid character codepoint. */
+      c = (/* (((p)[0] & 0x3) << 24) ... always 0, so no need to shift. */
+           (((p)[1] & 0x3F) << 18)
            | (((p)[2] & 0x3F) << 12)
            | (((p)[3] & 0x3F) << 6)
            | ((p)[4] & 0x3F));