diff options
Diffstat (limited to 'src/pulse/utf8.c')
| -rw-r--r-- | src/pulse/utf8.c | 115 |
1 files changed, 82 insertions, 33 deletions
diff --git a/src/pulse/utf8.c b/src/pulse/utf8.c index 33fa7214..fe7bcd26 100644 --- a/src/pulse/utf8.c +++ b/src/pulse/utf8.c @@ -1,4 +1,24 @@ -/* $Id$ */ +/*** + This file is part of PulseAudio. + + Copyright 2006 Lennart Poettering + Copyright 2006 Pierre Ossman <ossman@cendio.se> for Cendio AB + + PulseAudio is free software; you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License as + published by the Free Software Foundation; either version 2.1 of the + License, or (at your option) any later version. + + PulseAudio is distributed in the hope that it will be useful, but + WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with PulseAudio; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 + USA. +***/ /* This file is based on the GLIB utf8 validation functions. The * original license text follows. */ @@ -15,7 +35,7 @@ * * This library is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public @@ -28,7 +48,6 @@ #include <config.h> #endif -#include <assert.h> #include <errno.h> #include <stdlib.h> #include <inttypes.h> @@ -38,27 +57,31 @@ #include <iconv.h> #endif +#include <pulse/xmalloc.h> +#include <pulsecore/macro.h> + #include "utf8.h" -#include "xmalloc.h" #define FILTER_CHAR '_' -static inline int is_unicode_valid(uint32_t ch) { +static inline pa_bool_t is_unicode_valid(uint32_t ch) { + if (ch >= 0x110000) /* End of unicode space */ - return 0; + return FALSE; if ((ch & 0xFFFFF800) == 0xD800) /* Reserved area for UTF-16 */ - return 0; + return FALSE; if ((ch >= 0xFDD0) && (ch <= 0xFDEF)) /* Reserved */ - return 0; + return FALSE; if ((ch & 0xFFFE) == 0xFFFE) /* BOM (Byte Order Mark) */ - return 0; - return 1; + return FALSE; + + return TRUE; } -static inline int is_continuation_char(uint8_t ch) { +static inline pa_bool_t is_continuation_char(uint8_t ch) { if ((ch & 0xc0) != 0x80) /* 10xxxxxx */ - return 0; - return 1; + return FALSE; + return TRUE; } static inline void merge_continuation_char(uint32_t *u_ch, uint8_t ch) { @@ -73,6 +96,8 @@ static char* utf8_validate(const char *str, char *output) { int size; uint8_t *o; + pa_assert(str); + o = (uint8_t*) output; for (p = (const uint8_t*) str; *p; p++) { if (*p < 128) { @@ -84,21 +109,19 @@ static char* utf8_validate(const char *str, char *output) { if ((*p & 0xe0) == 0xc0) { /* 110xxxxx two-char seq. */ size = 2; min = 128; - val = *p & 0x1e; + val = (uint32_t) (*p & 0x1e); goto ONE_REMAINING; } else if ((*p & 0xf0) == 0xe0) { /* 1110xxxx three-char seq.*/ size = 3; min = (1 << 11); - val = *p & 0x0f; + val = (uint32_t) (*p & 0x0f); goto TWO_REMAINING; } else if ((*p & 0xf8) == 0xf0) { /* 11110xxx four-char seq */ size = 4; min = (1 << 16); - val = *p & 0x07; - } else { - size = 1; + val = (uint32_t) (*p & 0x07); + } else goto error; - } p++; if (!is_continuation_char(*p)) @@ -124,13 +147,10 @@ ONE_REMAINING: goto error; if (o) { - memcpy(o, last, size); - o += size - 1; + memcpy(o, last, (size_t) size); + o += size; } - if (o) - o++; - continue; error: @@ -156,15 +176,15 @@ failure: return NULL; } -const char* pa_utf8_valid (const char *str) { +char* pa_utf8_valid (const char *str) { return utf8_validate(str, NULL); } char* pa_utf8_filter (const char *str) { char *new_str; - new_str = pa_xnew(char, strlen(str) + 1); - + pa_assert(str); + new_str = pa_xmalloc(strlen(str) + 1); return utf8_validate(str, new_str); } @@ -173,22 +193,24 @@ char* pa_utf8_filter (const char *str) { static char* iconv_simple(const char *str, const char *to, const char *from) { char *new_str; size_t len, inlen; - iconv_t cd; ICONV_CONST char *inbuf; char *outbuf; size_t res, inbytes, outbytes; + pa_assert(str); + pa_assert(to); + pa_assert(from); + cd = iconv_open(to, from); if (cd == (iconv_t)-1) return NULL; inlen = len = strlen(str) + 1; new_str = pa_xmalloc(len); - assert(new_str); - while (1) { - inbuf = (ICONV_CONST char*)str; /* Brain dead prototype for iconv() */ + for (;;) { + inbuf = (ICONV_CONST char*) str; /* Brain dead prototype for iconv() */ inbytes = inlen; outbuf = new_str; outbytes = len; @@ -204,11 +226,10 @@ static char* iconv_simple(const char *str, const char *to, const char *from) { break; } - assert(inbytes != 0); + pa_assert(inbytes != 0); len += inbytes; new_str = pa_xrealloc(new_str, len); - assert(new_str); } iconv_close(cd); @@ -227,11 +248,39 @@ char* pa_locale_to_utf8 (const char *str) { #else char* pa_utf8_to_locale (const char *str) { + pa_assert(str); return NULL; } char* pa_locale_to_utf8 (const char *str) { + pa_assert(str); return NULL; } #endif + +char *pa_ascii_valid(const char *str) { + const char *p; + pa_assert(str); + + for (p = str; *p; p++) + if ((unsigned char) *p >= 128) + return NULL; + + return (char*) str; +} + +char *pa_ascii_filter(const char *str) { + char *r, *s, *d; + pa_assert(str); + + r = pa_xstrdup(str); + + for (s = r, d = r; *s; s++) + if ((unsigned char) *s < 128) + *(d++) = *s; + + *d = 0; + + return r; +} |