diff options
author | Karl Williamson <khw@cpan.org> | 2015-11-06 13:21:48 -0700 |
---|---|---|
committer | Karl Williamson <khw@cpan.org> | 2015-12-06 09:58:06 -0700 |
commit | 97d0ceda30a3e1293529cbd6e3ecb06e5ffab0cd (patch) | |
tree | 0d1ff75507d95e6e89ceb0788822162df49c1e26 /utfebcdic.h | |
parent | 796fb084743bf6c50eb8862031573a2e2b9a303e (diff) | |
download | perl-97d0ceda30a3e1293529cbd6e3ecb06e5ffab0cd.tar.gz |
utf8.h, utfebcdic.h: Comments, white-space only
Diffstat (limited to 'utfebcdic.h')
-rw-r--r-- | utfebcdic.h | 7 |
1 files changed, 6 insertions, 1 deletions
diff --git a/utfebcdic.h b/utfebcdic.h index 97c0c9d1c6..3a4fcc28af 100644 --- a/utfebcdic.h +++ b/utfebcdic.h @@ -41,7 +41,11 @@ * PL_utf2e, with its inverse being PL_e2utf. They are constructed so that * all EBCDIC invariants remain invariant, but no others do, and the first * byte of a variant will always have its upper bit set. But note that - * the upper bit of some invariants is also 1. + * the upper bit of some invariants is also 1. The table also is designed + * so that lexically comparing two UTF-EBCDIC-variant characters yields + * the Unicode code point order. (To get native code point order, one has + * to convert the latin1-range characters to their native code point + * value.) * * For example, the ordinal value of 'A' is 193 in EBCDIC, and also is 193 in * UTF-EBCDIC. Step 1) converts it to 65, Step 2 leaves it at 65, and Step 3 @@ -184,6 +188,7 @@ information, so that with 13 continuation bytes, we can handle 65 bits, just above what a 64 bit word can hold */ +/* This is a fundamental property of UTF-EBCDIC */ #define OFFUNI_IS_INVARIANT(c) (((UV)(c)) < 0xA0) /* It turns out that on EBCDIC platforms, the invariants are the characters |