diff options
| author | Kenichi Handa | 2013-08-20 17:56:03 +0300 |
|---|---|---|
| committer | Eli Zaretskii | 2013-08-20 17:56:03 +0300 |
| commit | 3f246b657225c786c460b22d774ab0b2e7488b55 (patch) | |
| tree | e2cc742e357b2d21e23a05cbb97d37a1fce1e0e9 /src | |
| parent | 9f0809d4ab26a4376ecce03909d35db80da40023 (diff) | |
| download | emacs-3f246b657225c786c460b22d774ab0b2e7488b55.tar.gz emacs-3f246b657225c786c460b22d774ab0b2e7488b55.zip | |
src/character.c (string_char): Improve commentary.
Diffstat (limited to 'src')
| -rw-r--r-- | src/ChangeLog | 4 | ||||
| -rw-r--r-- | src/character.c | 14 |
2 files changed, 16 insertions, 2 deletions
diff --git a/src/ChangeLog b/src/ChangeLog index e21d82bdc09..997459f01c2 100644 --- a/src/ChangeLog +++ b/src/ChangeLog | |||
| @@ -1,3 +1,7 @@ | |||
| 1 | 2013-08-20 Kenichi Handa <handa@gnu.org> | ||
| 2 | |||
| 3 | * character.c (string_char): Improve commentary. | ||
| 4 | |||
| 1 | 2013-08-20 Paul Eggert <eggert@cs.ucla.edu> | 5 | 2013-08-20 Paul Eggert <eggert@cs.ucla.edu> |
| 2 | 6 | ||
| 3 | * image.c (SIGNATURE_DIGESTSIZE): Remove. | 7 | * 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) | |||
| 174 | 174 | ||
| 175 | if (*p < 0x80 || ! (*p & 0x20) || ! (*p & 0x10)) | 175 | if (*p < 0x80 || ! (*p & 0x20) || ! (*p & 0x10)) |
| 176 | { | 176 | { |
| 177 | /* 1-, 2-, and 3-byte sequences can be handled by the macro. */ | ||
| 177 | c = STRING_CHAR_ADVANCE (p); | 178 | c = STRING_CHAR_ADVANCE (p); |
| 178 | } | 179 | } |
| 179 | else if (! (*p & 0x08)) | 180 | else if (! (*p & 0x08)) |
| 180 | { | 181 | { |
| 181 | c = ((((p)[0] & 0xF) << 18) | 182 | /* A 4-byte sequence of this form: |
| 183 | 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ | ||
| 184 | c = ((((p)[0] & 0x7) << 18) | ||
| 182 | | (((p)[1] & 0x3F) << 12) | 185 | | (((p)[1] & 0x3F) << 12) |
| 183 | | (((p)[2] & 0x3F) << 6) | 186 | | (((p)[2] & 0x3F) << 6) |
| 184 | | ((p)[3] & 0x3F)); | 187 | | ((p)[3] & 0x3F)); |
| @@ -186,7 +189,14 @@ string_char (const unsigned char *p, const unsigned char **advanced, int *len) | |||
| 186 | } | 189 | } |
| 187 | else | 190 | else |
| 188 | { | 191 | { |
| 189 | c = ((((p)[1] & 0x3F) << 18) | 192 | /* A 5-byte sequence of this form: |
| 193 | |||
| 194 | 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx | ||
| 195 | |||
| 196 | Note that the top 4 `x's are always 0, so shifting p[1] can | ||
| 197 | never exceed the maximum valid character codepoint. */ | ||
| 198 | c = (/* (((p)[0] & 0x3) << 24) ... always 0, so no need to shift. */ | ||
| 199 | (((p)[1] & 0x3F) << 18) | ||
| 190 | | (((p)[2] & 0x3F) << 12) | 200 | | (((p)[2] & 0x3F) << 12) |
| 191 | | (((p)[3] & 0x3F) << 6) | 201 | | (((p)[3] & 0x3F) << 6) |
| 192 | | ((p)[4] & 0x3F)); | 202 | | ((p)[4] & 0x3F)); |