summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorKarl Williamson <public@khwilliamson.com>2013-02-07 13:43:21 -0700
committerKarl Williamson <public@khwilliamson.com>2013-02-15 14:59:33 -0700
commitf3cb6f94804ae4e7fcd6fa80bd5dc4127e37dd33 (patch)
tree63bedbb535b55f40cb3402423da7122d3613c647
parent12cf36fe17425a75fffba24e34c850767de584d0 (diff)
downloadperl-f3cb6f94804ae4e7fcd6fa80bd5dc4127e37dd33.tar.gz
utf8.h, utfebcdic.h: Add, fix comments
-rw-r--r--utf8.h6
-rw-r--r--utfebcdic.h2
2 files changed, 6 insertions, 2 deletions
diff --git a/utf8.h b/utf8.h
index 27b877ecc3..f990f37995 100644
--- a/utf8.h
+++ b/utf8.h
@@ -1,5 +1,11 @@
/* utf8.h
*
+ * This file contains definitions for use with the UTF-8 encoding. It
+ * actually also works with the variant UTF-8 encoding called UTF-EBCDIC, and
+ * hides almost all of the differences between these from the caller. In other
+ * words, someone should #include this file, and if the code is being compiled
+ * on an EBCDIC platform, things should mostly just work.
+ *
* Copyright (C) 2000, 2001, 2002, 2005, 2006, 2007, 2009,
* 2010, 2011 by Larry Wall and others
*
diff --git a/utfebcdic.h b/utfebcdic.h
index 3e46ea51cb..5705b969d4 100644
--- a/utfebcdic.h
+++ b/utfebcdic.h
@@ -541,8 +541,6 @@ END_EXTERN_C
Unicode Bit pattern 1st Byte 2nd Byte 3rd Byte 4th Byte 5th Byte 6th Byte 7th byte
U+0000..U+007F 000000000xxxxxxx 0xxxxxxx
U+0080..U+009F 00000000100xxxxx 100xxxxx
- U+00A0..U+00FF 00000000yyyxxxxx 11000yyy 101xxxxx
-
U+00A0..U+03FF 000000yyyyyxxxxx 110yyyyy 101xxxxx
U+0400..U+3FFF 00zzzzyyyyyxxxxx 1110zzzz 101yyyyy 101xxxxx
U+4000..U+3FFFF 0wwwzzzzzyyyyyxxxxx 11110www 101zzzzz 101yyyyy 101xxxxx