diff options
author | Lennart Poettering <lennart@poettering.net> | 2015-04-14 17:31:34 -0400 |
---|---|---|
committer | Anthony G. Basile <blueness@gentoo.org> | 2015-04-14 17:31:34 -0400 |
commit | 4b725bd2d38cbad1c490d22823f73c73ef3fc9df (patch) | |
tree | e9dbfa93b5ef064af87e03005a8f27ada56e23e9 | |
parent | 119711f4e8f7dd47cb9abcdbde0023a4607e2dbf (diff) |
util: when unescaping C escape sequences support C++11 \u and
\U unicode literals
We simply recode them in utf8.
Signed-off-by: Anthony G. Basile <blueness@gentoo.org>
-rw-r--r-- | src/shared/utf8.c | 13 | ||||
-rw-r--r-- | src/shared/utf8.h | 2 |
2 files changed, 9 insertions, 6 deletions
diff --git a/src/shared/utf8.c b/src/shared/utf8.c index fec2f4df34..d59e07f3ee 100644 --- a/src/shared/utf8.c +++ b/src/shared/utf8.c @@ -50,7 +50,7 @@ #include "utf8.h" #include "util.h" -static inline bool is_unicode_valid(uint32_t ch) { +bool unichar_is_valid(uint32_t ch) { if (ch >= 0x110000) /* End of unicode space */ return false; @@ -64,7 +64,7 @@ static inline bool is_unicode_valid(uint32_t ch) { return true; } -static bool is_unicode_control(uint32_t ch) { +static bool unichar_is_control(uint32_t ch) { /* 0 to ' '-1 is the C0 range. @@ -154,7 +154,7 @@ bool utf8_is_printable_newline(const char* str, size_t length, bool newline) { val = utf8_encoded_to_unichar((const char*) p); if (val < 0 || - is_unicode_control(val) || + unichar_is_control(val) || (!newline && val == '\n')) return false; @@ -190,6 +190,7 @@ char *ascii_is_valid(const char *str) { * occupy. */ size_t utf8_encode_unichar(char *out_utf8, uint32_t g) { + if (g < (1 << 7)) { if (out_utf8) out_utf8[0] = g & 0x7f; @@ -215,9 +216,9 @@ size_t utf8_encode_unichar(char *out_utf8, uint32_t g) { out_utf8[3] = 0x80 | (g & 0x3f); } return 4; - } else { - return 0; } + + return 0; } char *utf16_to_utf8(const void *s, size_t length) { @@ -308,7 +309,7 @@ int utf8_encoded_valid_unichar(const char *str) { return -EINVAL; /* check if value has valid range */ - if (!is_unicode_valid(unichar)) + if (!unichar_is_valid(unichar)) return -EINVAL; return len; diff --git a/src/shared/utf8.h b/src/shared/utf8.h index 143b0ba08c..99a6304cf4 100644 --- a/src/shared/utf8.h +++ b/src/shared/utf8.h @@ -22,6 +22,8 @@ #include <stdbool.h> #include "macro.h" + +bool unichar_is_valid(uint32_t c); char *ascii_is_valid(const char *s) _pure_; |