Package: mpg321 Version: 0.2.10.3 Severity: normal
mpg321 only works correctly in an ISO-8859-1 locale. I've done a patch to make it work in UTF-8 locales, too. You have to run aclocal, etc, because there are some new configuration thingies. diff -ru mpg321-0.2.10.1.orig/Makefile.am mpg321-0.2.10.1/Makefile.am --- mpg321-0.2.10.1.orig/Makefile.am 2001-10-13 18:28:25.000000000 +0100 +++ mpg321-0.2.10.1/Makefile.am 2005-04-29 20:31:09.000000000 +0100 @@ -11,7 +11,8 @@ getopt.h \ remote.c \ ao.c \ - options.c + options.c \ + ucs4width.c SUBDIRS = m4 EXTRA_DIST = README.remote HACKING BUGS mpg321.sgml mpg321.1 $(srcdir)/debian/* diff -ru mpg321-0.2.10.1.orig/configure.ac mpg321-0.2.10.1/configure.ac --- mpg321-0.2.10.1.orig/configure.ac 2002-03-24 05:02:28.000000000 +0000 +++ mpg321-0.2.10.1/configure.ac 2005-04-29 21:47:33.000000000 +0100 @@ -44,7 +44,7 @@ dnl Checks for header files. AC_HEADER_STDC -AC_CHECK_HEADERS(fcntl.h sys/ioctl.h sys/time.h unistd.h) +AC_CHECK_HEADERS(fcntl.h locale.h sys/ioctl.h sys/time.h unistd.h) AC_HEADER_TIME # Checks for typedefs, structures, and compiler characteristics. @@ -67,7 +67,7 @@ AC_TYPE_SOCKLEN_T -AC_CHECK_FUNCS([gethostbyname memset munmap socket strchr strdup strerror strrchr strstr gettimeofday select getenv putenv setenv unsetenv strcasecmp]) +AC_CHECK_FUNCS([gethostbyname memset munmap socket strchr strdup strerror strrchr strstr gettimeofday select getenv putenv setenv unsetenv strcasecmp setlocale]) AC_ARG_ENABLE(mpg123_symlink, [ --enable-mpg123-symlink Enable symlink of mpg123 to mpg321 [[default=yes]] ], @@ -98,5 +98,7 @@ AC_DEFINE_UNQUOTED(AUDIO_DEFAULT, "the libao default", [Define the default libao output device.]) fi +AM_LANGINFO_CODESET + AC_CONFIG_FILES([Makefile m4/Makefile]) AC_OUTPUT diff -ru mpg321-0.2.10.1.orig/mpg321.c mpg321-0.2.10.1/mpg321.c --- mpg321-0.2.10.1.orig/mpg321.c 2004-01-04 19:51:13.000000000 +0000 +++ mpg321-0.2.10.1/mpg321.c 2005-04-29 21:43:42.000000000 +0100 @@ -46,6 +46,14 @@ #include <id3tag.h> +#ifdef HAVE_LANGINFO_CODESET +#include <langinfo.h> +#endif + +#ifdef HAVE_LOCALE_H +#include <locale.h> +#endif + int shuffle_play; int stop_playing_file = 0; int quit_now = 0; @@ -56,6 +64,27 @@ int status = MPG321_STOPPED; int file_change = 0; +int utf8_mode = 0; + +void set_utf8_mode() +{ +#if defined(HAVE_SETLOCALE) && defined(HAVE_LANGINFO_CODESET) + setlocale(LC_ALL, ""); + utf8_mode = !strcmp(nl_langinfo(CODESET), "UTF-8"); +#else +#if defined(HAVE_GETENV) + char *s; + if (((s = getenv("LC_ALL")) && *s) || + ((s = getenv("LC_CTYPE")) && *s) || + ((s = getenv("LANG")) && *s)) + { + if (strstr(s, "UTF-8")) + utf8_mode = 1; + } +#endif +#endif +} + char *id3_get_tag (struct id3_tag const *tag, char const *what, unsigned int maxlen); void mpg123_boilerplate() @@ -225,6 +254,8 @@ struct mad_decoder decoder; + set_utf8_mode(); + old_dir[0] = '\0'; playbuf.pl = pl = new_playlist(); @@ -559,22 +590,20 @@ * It allocates a new string. Free it later. * NULL if no tag or error. */ -char *id3_get_tag (struct id3_tag const *tag, char const *what, unsigned int maxlen) +char *id3_get_tag (struct id3_tag const *tag, char const *what, unsigned int width) { struct id3_frame const *frame = NULL; union id3_field const *field = NULL; int nstrings; - int avail; - int j; - int tocopy; - int len; - char printable [1024]; + int j, w; char *retval = NULL; id3_ucs4_t const *ucs4 = NULL; - id3_latin1_t *latin1 = NULL; - memset (printable, '\0', 1024); - avail = 1024; + unsigned int bufmax1 = width * 3; /* Allow space for combining characters */ + unsigned int bufmax2 = bufmax1 + width; /* Allow space for padding */ + id3_ucs4_t *buffer = malloc((bufmax2 + 1) * sizeof(id3_ucs4_t)); + unsigned int bp = 0, ww; + if (strcmp (what, ID3_FRAME_COMMENT) == 0) { /*There may be sth wrong. I did not fully understand how to use @@ -584,17 +613,8 @@ if (!frame) return (NULL); ucs4 = id3_field_getfullstring (&frame->fields[3]); if (!ucs4) return (NULL); - latin1 = id3_ucs4_latin1duplicate (ucs4); - if (!latin1 || strlen(latin1) == 0) return (NULL); - len = strlen(latin1); - if (avail > len) - tocopy = len; - else - tocopy = 0; - if (!tocopy) return (NULL); - avail-=tocopy; - strncat (printable, latin1, tocopy); - free (latin1); + while (*ucs4 && bp < bufmax1) + buffer[bp++] = *ucs4++; } else @@ -609,30 +629,42 @@ if (!ucs4) return (NULL); if (strcmp (what, ID3_FRAME_GENRE) == 0) ucs4 = id3_genre_name(ucs4); - latin1 = id3_ucs4_latin1duplicate(ucs4); - if (!latin1) break; - len = strlen(latin1); - if (avail > len) - tocopy = len; - else - tocopy = 0; - if (!tocopy) break; - avail-=tocopy; - strncat (printable, latin1, tocopy); - free (latin1); + if (!ucs4) return (NULL); + while (*ucs4 && bp < bufmax1) + buffer[bp++] = *ucs4++; } } - retval = malloc (maxlen + 1); - if (!retval) return (NULL); - strncpy (retval, printable, maxlen); - retval[maxlen] = '\0'; + /* If not in UTF-8 mode, replace high characters with U+00B7 */ + if (!utf8_mode) + for (j = 0; j < bp; j++) + if (buffer[j] & ~0xff) + buffer[j] = 0xb7; - len = strlen(printable); - if (maxlen > len) + /* Replace non-printable characters and ensure required width is not exceeded */ + ww = 0; + for (j = 0; j < bp; j++) { - memset (retval + len, ' ', maxlen - len); + if ((w = ucs4width(buffer[j])) < 0) + { + buffer[j] = ' '; + w = 1; + } + if (ww + w > width) + break; + ww += w; } + bp = j; - return (retval); + /* Pad to required width with spaces */ + while (ww++ < width && bp < bufmax2) + buffer[bp++] = ' '; + buffer[bp] = 0; + + /* Convert to UTF-8 or ISO-8859-1 */ + retval = utf8_mode ? + (char *)id3_ucs4_utf8duplicate(buffer) : + (char *)id3_ucs4_latin1duplicate(buffer); + free(buffer); + return retval; } diff -ru mpg321-0.2.10.1.orig/mpg321.h mpg321-0.2.10.1/mpg321.h --- mpg321-0.2.10.1.orig/mpg321.h 2002-03-23 22:45:31.000000000 +0000 +++ mpg321-0.2.10.1/mpg321.h 2005-04-29 21:36:17.000000000 +0100 @@ -37,6 +37,7 @@ #include <limits.h> #include <ao/ao.h> #include <mad.h> +#include <id3tag.h> #define FAKEVERSION "0.59q" #define VERSIONDATE "2002/03/23" @@ -195,4 +196,7 @@ RETSIGTYPE handle_signals(int sig) ; +/* UCS-only version of wcwidth */ +int ucs4width(id3_ucs4_t ucs); + #endif /* _MPG321_H_ */ diff -ru mpg321-0.2.10.1.orig/ucs4width.c mpg321-0.2.10.1/ucs4width.c --- mpg321-0.2.10.1.orig/ucs4width.c 2005-04-29 21:59:53.000000000 +0100 +++ mpg321-0.2.10.1/ucs4width.c 2005-04-29 20:31:09.000000000 +0100 @@ -0,0 +1,119 @@ +/* + * This is an implementation of wcwidth() and wcswidth() as defined in + * "The Single UNIX Specification, Version 2, The Open Group, 1997" + * <http://www.UNIX-systems.org/online.html> + * + * Markus Kuhn -- 2000-02-08 -- public domain + */ + +/* Adapted for mpg321 by Edmund Grimley Evans. + */ + +#include "mpg321.h" +#include <id3tag.h> + +/* These functions define the column width of an ISO 10646 character + * as follows: + * + * - The null character (U+0000) has a column width of 0. + * + * - Other C0/C1 control characters and DEL will lead to a return + * value of -1. + * + * - Non-spacing and enclosing combining characters (general + * category code Mn or Me in the Unicode database) have a + * column width of 0. + * + * - Spacing characters in the East Asian Wide (W) or East Asian + * FullWidth (F) category as defined in Unicode Technical + * Report #11 have a column width of 2. + * + * - All remaining characters (including all printable + * ISO 8859-1 and WGL4 characters, Unicode control characters, + * etc.) have a column width of 1. + * + * This implementation assumes that wchar_t characters are encoded + * in ISO 10646. + */ + +int ucs4width(id3_ucs4_t ucs) +{ + /* sorted list of non-overlapping intervals of non-spacing characters */ + static const struct interval { + unsigned short first; + unsigned short last; + } combining[] = { + { 0x0300, 0x034E }, { 0x0360, 0x0362 }, { 0x0483, 0x0486 }, + { 0x0488, 0x0489 }, { 0x0591, 0x05A1 }, { 0x05A3, 0x05B9 }, + { 0x05BB, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, + { 0x05C4, 0x05C4 }, { 0x064B, 0x0655 }, { 0x0670, 0x0670 }, + { 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED }, + { 0x0711, 0x0711 }, { 0x0730, 0x074A }, { 0x07A6, 0x07B0 }, + { 0x0901, 0x0902 }, { 0x093C, 0x093C }, { 0x0941, 0x0948 }, + { 0x094D, 0x094D }, { 0x0951, 0x0954 }, { 0x0962, 0x0963 }, + { 0x0981, 0x0981 }, { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, + { 0x09CD, 0x09CD }, { 0x09E2, 0x09E3 }, { 0x0A02, 0x0A02 }, + { 0x0A3C, 0x0A3C }, { 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 }, + { 0x0A4B, 0x0A4D }, { 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 }, + { 0x0ABC, 0x0ABC }, { 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, + { 0x0ACD, 0x0ACD }, { 0x0B01, 0x0B01 }, { 0x0B3C, 0x0B3C }, + { 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 }, { 0x0B4D, 0x0B4D }, + { 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 }, { 0x0BC0, 0x0BC0 }, + { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 }, + { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 }, { 0x0CBF, 0x0CBF }, + { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD }, { 0x0D41, 0x0D43 }, + { 0x0D4D, 0x0D4D }, { 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, + { 0x0DD6, 0x0DD6 }, { 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, + { 0x0E47, 0x0E4E }, { 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, + { 0x0EBB, 0x0EBC }, { 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, + { 0x0F35, 0x0F35 }, { 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, + { 0x0F71, 0x0F7E }, { 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, + { 0x0F90, 0x0F97 }, { 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, + { 0x102D, 0x1030 }, { 0x1032, 0x1032 }, { 0x1036, 0x1037 }, + { 0x1039, 0x1039 }, { 0x1058, 0x1059 }, { 0x17B7, 0x17BD }, + { 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x18A9, 0x18A9 }, + { 0x20D0, 0x20E3 }, { 0x302A, 0x302F }, { 0x3099, 0x309A }, + { 0xFB1E, 0xFB1E }, { 0xFE20, 0xFE23 } + }; + int min = 0; + int max = sizeof(combining) / sizeof(struct interval) - 1; + int mid; + + if (ucs == 0) + return 0; + + /* test for 8-bit control characters */ + if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0)) + return -1; + + /* first quick check for Latin-1 etc. characters */ + if (ucs < combining[0].first) + return 1; + + /* binary search in table of non-spacing characters */ + while (max >= min) { + mid = (min + max) / 2; + if (combining[mid].last < ucs) + min = mid + 1; + else if (combining[mid].first > ucs) + max = mid - 1; + else if (combining[mid].first <= ucs && combining[mid].last >= ucs) + return 0; + } + + /* if we arrive here, ucs is not a combining or C0/C1 control character */ + + /* fast test for majority of non-wide scripts */ + if (ucs < 0x1100) + return 1; + + return 1 + + ((ucs >= 0x1100 && ucs <= 0x115f) || /* Hangul Jamo */ + (ucs >= 0x2e80 && ucs <= 0xa4cf && (ucs & ~0x0011) != 0x300a && + ucs != 0x303f) || /* CJK ... Yi */ + (ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */ + (ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */ + (ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */ + (ucs >= 0xff00 && ucs <= 0xff5f) || /* Fullwidth Forms */ + (ucs >= 0xffe0 && ucs <= 0xffe6)); +} -- System Information: Debian Release: 3.1 APT prefers testing APT policy: (500, 'testing') Architecture: i386 (i686) Kernel: Linux 2.4.27-2-386 Locale: LANG=en_GB.UTF-8, LC_CTYPE=en_GB.UTF-8 (charmap=UTF-8) Versions of packages mpg321 depends on: ii libao2 0.8.6-1 Cross Platform Audio Output Librar ii libc6 2.3.2.ds1-20 GNU C Library: Shared libraries an ii libid3tag0 0.15.1b-4.1 ID3 tag reading library from the M ii libmad0 0.15.1b-1.1 MPEG audio decoder library ii zlib1g 1:1.2.2-3 compression library - runtime -- no debconf information -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]