diff options
author | WaLyong Cho <walyong.cho@samsung.com> | 2014-11-12 19:49:31 +0900 |
---|---|---|
committer | Lennart Poettering <lennart@poettering.net> | 2014-12-04 02:09:44 +0100 |
commit | fec8457652002fd5bff923042a7407b3810f5a7f (patch) | |
tree | 94f038e2c98fb54c228b82d32fe72c61ab47bee5 /src | |
parent | da64a1fc41e84bdb67c56693fff685b5eff2a2c7 (diff) |
utf8: intruduce utf8_escape_non_printable
Diffstat (limited to 'src')
-rw-r--r-- | src/shared/utf8.c | 39 | ||||
-rw-r--r-- | src/shared/utf8.h | 1 | ||||
-rw-r--r-- | src/test/test-utf8.c | 25 |
3 files changed, 65 insertions, 0 deletions
diff --git a/src/shared/utf8.c b/src/shared/utf8.c index 8702ceb1b2..0b6c38ebbf 100644 --- a/src/shared/utf8.c +++ b/src/shared/utf8.c @@ -212,6 +212,45 @@ char *utf8_escape_invalid(const char *str) { return p; } +char *utf8_escape_non_printable(const char *str) { + char *p, *s; + + assert(str); + + p = s = malloc(strlen(str) * 4 + 1); + if (!p) + return NULL; + + while (*str) { + int len; + + len = utf8_encoded_valid_unichar(str); + if (len > 0) { + if (utf8_is_printable(str, len)) { + s = mempcpy(s, str, len); + str += len; + } else { + if ((*str < ' ') || (*str >= 127)) { + *(s++) = '\\'; + *(s++) = 'x'; + *(s++) = hexchar((int) *str >> 4); + *(s++) = hexchar((int) *str); + } else + *(s++) = *str; + + str += 1; + } + } else { + s = mempcpy(s, UTF8_REPLACEMENT_CHARACTER, strlen(UTF8_REPLACEMENT_CHARACTER)); + str += 1; + } + } + + *s = '\0'; + + return p; +} + char *ascii_is_valid(const char *str) { const char *p; diff --git a/src/shared/utf8.h b/src/shared/utf8.h index c087995930..1fe1a350d5 100644 --- a/src/shared/utf8.h +++ b/src/shared/utf8.h @@ -30,6 +30,7 @@ const char *utf8_is_valid(const char *s) _pure_; char *ascii_is_valid(const char *s) _pure_; char *utf8_escape_invalid(const char *s); +char *utf8_escape_non_printable(const char *str); bool utf8_is_printable_newline(const char* str, size_t length, bool newline) _pure_; _pure_ static inline bool utf8_is_printable(const char* str, size_t length) { diff --git a/src/test/test-utf8.c b/src/test/test-utf8.c index b7d988f22d..6dde63cdff 100644 --- a/src/test/test-utf8.c +++ b/src/test/test-utf8.c @@ -66,12 +66,37 @@ static void test_utf8_escaping(void) { assert_se(utf8_is_valid(p3)); } +static void test_utf8_escaping_printable(void) { + _cleanup_free_ char *p1, *p2, *p3, *p4, *p5; + + p1 = utf8_escape_non_printable("goo goo goo"); + puts(p1); + assert_se(utf8_is_valid(p1)); + + p2 = utf8_escape_non_printable("\341\204\341\204"); + puts(p2); + assert_se(utf8_is_valid(p2)); + + p3 = utf8_escape_non_printable("\341\204"); + puts(p3); + assert_se(utf8_is_valid(p3)); + + p4 = utf8_escape_non_printable("ąę\n가너도루\n1234\n\341\204\341\204\n\001 \019\20\a"); + puts(p4); + assert_se(utf8_is_valid(p4)); + + p5 = utf8_escape_non_printable("\001 \019\20\a"); + puts(p5); + assert_se(utf8_is_valid(p5)); +} + int main(int argc, char *argv[]) { test_utf8_is_valid(); test_utf8_is_printable(); test_ascii_is_valid(); test_utf8_encoded_valid_unichar(); test_utf8_escaping(); + test_utf8_escaping_printable(); return 0; } |