Package: libc6 Version: 2.33-8 Severity: important Dear Maintainer, Consider the following reproducer: -- >8 -- #include <stdio.h> #include <wchar.h> #include <locale.h> int main(int argc, char **) { if(argc > 1) fprintf(stderr, "loc=%s\n", setlocale(LC_ALL, "")); for(int i = 0; i <= 0xFF; ++i) { char bs[] = {i, 0}; mbstate_t ctx = {}; wchar_t wc = -1; printf("%02x: %d, ", i, mbrtowc(&wc, bs, 1, &ctx)); printf("%ld\n", wc); } } -- >8 -- Yielding the following output: -- >8 -- $ ./b | paste - - - - - - - - 00: 0, 0 01: 1, 1 02: 1, 2 03: 1, 3 04: 1, 4 05: 1, 5 06: 1, 6 07: 1, 7 08: 1, 8 09: 1, 9 0a: 1, 10 0b: 1, 11 0c: 1, 12 0d: 1, 13 0e: 1, 14 0f: 1, 15 10: 1, 16 11: 1, 17 12: 1, 18 13: 1, 19 14: 1, 20 15: 1, 21 16: 1, 22 17: 1, 23 18: 1, 24 19: 1, 25 1a: 1, 26 1b: 1, 27 1c: 1, 28 1d: 1, 29 1e: 1, 30 1f: 1, 31 20: 1, 32 21: 1, 33 22: 1, 34 23: 1, 35 24: 1, 36 25: 1, 37 26: 1, 38 27: 1, 39 28: 1, 40 29: 1, 41 2a: 1, 42 2b: 1, 43 2c: 1, 44 2d: 1, 45 2e: 1, 46 2f: 1, 47 30: 1, 48 31: 1, 49 32: 1, 50 33: 1, 51 34: 1, 52 35: 1, 53 36: 1, 54 37: 1, 55 38: 1, 56 39: 1, 57 3a: 1, 58 3b: 1, 59 3c: 1, 60 3d: 1, 61 3e: 1, 62 3f: 1, 63 40: 1, 64 41: 1, 65 42: 1, 66 43: 1, 67 44: 1, 68 45: 1, 69 46: 1, 70 47: 1, 71 48: 1, 72 49: 1, 73 4a: 1, 74 4b: 1, 75 4c: 1, 76 4d: 1, 77 4e: 1, 78 4f: 1, 79 50: 1, 80 51: 1, 81 52: 1, 82 53: 1, 83 54: 1, 84 55: 1, 85 56: 1, 86 57: 1, 87 58: 1, 88 59: 1, 89 5a: 1, 90 5b: 1, 91 5c: 1, 92 5d: 1, 93 5e: 1, 94 5f: 1, 95 60: 1, 96 61: 1, 97 62: 1, 98 63: 1, 99 64: 1, 100 65: 1, 101 66: 1, 102 67: 1, 103 68: 1, 104 69: 1, 105 6a: 1, 106 6b: 1, 107 6c: 1, 108 6d: 1, 109 6e: 1, 110 6f: 1, 111 70: 1, 112 71: 1, 113 72: 1, 114 73: 1, 115 74: 1, 116 75: 1, 117 76: 1, 118 77: 1, 119 78: 1, 120 79: 1, 121 7a: 1, 122 7b: 1, 123 7c: 1, 124 7d: 1, 125 7e: 1, 126 7f: 1, 127 80: -1, -1 81: -1, -1 82: -1, -1 83: -1, -1 84: -1, -1 85: -1, -1 86: -1, -1 87: -1, -1 88: -1, -1 89: -1, -1 8a: -1, -1 8b: -1, -1 8c: -1, -1 8d: -1, -1 8e: -1, -1 8f: -1, -1 90: -1, -1 91: -1, -1 92: -1, -1 93: -1, -1 94: -1, -1 95: -1, -1 96: -1, -1 97: -1, -1 98: -1, -1 99: -1, -1 9a: -1, -1 9b: -1, -1 9c: -1, -1 9d: -1, -1 9e: -1, -1 9f: -1, -1 a0: -1, -1 a1: -1, -1 a2: -1, -1 a3: -1, -1 a4: -1, -1 a5: -1, -1 a6: -1, -1 a7: -1, -1 a8: -1, -1 a9: -1, -1 aa: -1, -1 ab: -1, -1 ac: -1, -1 ad: -1, -1 ae: -1, -1 af: -1, -1 b0: -1, -1 b1: -1, -1 b2: -1, -1 b3: -1, -1 b4: -1, -1 b5: -1, -1 b6: -1, -1 b7: -1, -1 b8: -1, -1 b9: -1, -1 ba: -1, -1 bb: -1, -1 bc: -1, -1 bd: -1, -1 be: -1, -1 bf: -1, -1 c0: -1, -1 c1: -1, -1 c2: -1, -1 c3: -1, -1 c4: -1, -1 c5: -1, -1 c6: -1, -1 c7: -1, -1 c8: -1, -1 c9: -1, -1 ca: -1, -1 cb: -1, -1 cc: -1, -1 cd: -1, -1 ce: -1, -1 cf: -1, -1 d0: -1, -1 d1: -1, -1 d2: -1, -1 d3: -1, -1 d4: -1, -1 d5: -1, -1 d6: -1, -1 d7: -1, -1 d8: -1, -1 d9: -1, -1 da: -1, -1 db: -1, -1 dc: -1, -1 dd: -1, -1 de: -1, -1 df: -1, -1 e0: -1, -1 e1: -1, -1 e2: -1, -1 e3: -1, -1 e4: -1, -1 e5: -1, -1 e6: -1, -1 e7: -1, -1 e8: -1, -1 e9: -1, -1 ea: -1, -1 eb: -1, -1 ec: -1, -1 ed: -1, -1 ee: -1, -1 ef: -1, -1 f0: -1, -1 f1: -1, -1 f2: -1, -1 f3: -1, -1 f4: -1, -1 f5: -1, -1 f6: -1, -1 f7: -1, -1 f8: -1, -1 f9: -1, -1 fa: -1, -1 fb: -1, -1 fc: -1, -1 fd: -1, -1 fe: -1, -1 ff: -1, -1 $ LC_ALL=POSIX ./b _ | paste - - - - - - - - loc=C 00: 0, 0 01: 1, 1 02: 1, 2 03: 1, 3 04: 1, 4 05: 1, 5 06: 1, 6 07: 1, 7 08: 1, 8 09: 1, 9 0a: 1, 10 0b: 1, 11 0c: 1, 12 0d: 1, 13 0e: 1, 14 0f: 1, 15 10: 1, 16 11: 1, 17 12: 1, 18 13: 1, 19 14: 1, 20 15: 1, 21 16: 1, 22 17: 1, 23 18: 1, 24 19: 1, 25 1a: 1, 26 1b: 1, 27 1c: 1, 28 1d: 1, 29 1e: 1, 30 1f: 1, 31 20: 1, 32 21: 1, 33 22: 1, 34 23: 1, 35 24: 1, 36 25: 1, 37 26: 1, 38 27: 1, 39 28: 1, 40 29: 1, 41 2a: 1, 42 2b: 1, 43 2c: 1, 44 2d: 1, 45 2e: 1, 46 2f: 1, 47 30: 1, 48 31: 1, 49 32: 1, 50 33: 1, 51 34: 1, 52 35: 1, 53 36: 1, 54 37: 1, 55 38: 1, 56 39: 1, 57 3a: 1, 58 3b: 1, 59 3c: 1, 60 3d: 1, 61 3e: 1, 62 3f: 1, 63 40: 1, 64 41: 1, 65 42: 1, 66 43: 1, 67 44: 1, 68 45: 1, 69 46: 1, 70 47: 1, 71 48: 1, 72 49: 1, 73 4a: 1, 74 4b: 1, 75 4c: 1, 76 4d: 1, 77 4e: 1, 78 4f: 1, 79 50: 1, 80 51: 1, 81 52: 1, 82 53: 1, 83 54: 1, 84 55: 1, 85 56: 1, 86 57: 1, 87 58: 1, 88 59: 1, 89 5a: 1, 90 5b: 1, 91 5c: 1, 92 5d: 1, 93 5e: 1, 94 5f: 1, 95 60: 1, 96 61: 1, 97 62: 1, 98 63: 1, 99 64: 1, 100 65: 1, 101 66: 1, 102 67: 1, 103 68: 1, 104 69: 1, 105 6a: 1, 106 6b: 1, 107 6c: 1, 108 6d: 1, 109 6e: 1, 110 6f: 1, 111 70: 1, 112 71: 1, 113 72: 1, 114 73: 1, 115 74: 1, 116 75: 1, 117 76: 1, 118 77: 1, 119 78: 1, 120 79: 1, 121 7a: 1, 122 7b: 1, 123 7c: 1, 124 7d: 1, 125 7e: 1, 126 7f: 1, 127 80: -1, -1 81: -1, -1 82: -1, -1 83: -1, -1 84: -1, -1 85: -1, -1 86: -1, -1 87: -1, -1 88: -1, -1 89: -1, -1 8a: -1, -1 8b: -1, -1 8c: -1, -1 8d: -1, -1 8e: -1, -1 8f: -1, -1 90: -1, -1 91: -1, -1 92: -1, -1 93: -1, -1 94: -1, -1 95: -1, -1 96: -1, -1 97: -1, -1 98: -1, -1 99: -1, -1 9a: -1, -1 9b: -1, -1 9c: -1, -1 9d: -1, -1 9e: -1, -1 9f: -1, -1 a0: -1, -1 a1: -1, -1 a2: -1, -1 a3: -1, -1 a4: -1, -1 a5: -1, -1 a6: -1, -1 a7: -1, -1 a8: -1, -1 a9: -1, -1 aa: -1, -1 ab: -1, -1 ac: -1, -1 ad: -1, -1 ae: -1, -1 af: -1, -1 b0: -1, -1 b1: -1, -1 b2: -1, -1 b3: -1, -1 b4: -1, -1 b5: -1, -1 b6: -1, -1 b7: -1, -1 b8: -1, -1 b9: -1, -1 ba: -1, -1 bb: -1, -1 bc: -1, -1 bd: -1, -1 be: -1, -1 bf: -1, -1 c0: -1, -1 c1: -1, -1 c2: -1, -1 c3: -1, -1 c4: -1, -1 c5: -1, -1 c6: -1, -1 c7: -1, -1 c8: -1, -1 c9: -1, -1 ca: -1, -1 cb: -1, -1 cc: -1, -1 cd: -1, -1 ce: -1, -1 cf: -1, -1 d0: -1, -1 d1: -1, -1 d2: -1, -1 d3: -1, -1 d4: -1, -1 d5: -1, -1 d6: -1, -1 d7: -1, -1 d8: -1, -1 d9: -1, -1 da: -1, -1 db: -1, -1 dc: -1, -1 dd: -1, -1 de: -1, -1 df: -1, -1 e0: -1, -1 e1: -1, -1 e2: -1, -1 e3: -1, -1 e4: -1, -1 e5: -1, -1 e6: -1, -1 e7: -1, -1 e8: -1, -1 e9: -1, -1 ea: -1, -1 eb: -1, -1 ec: -1, -1 ed: -1, -1 ee: -1, -1 ef: -1, -1 f0: -1, -1 f1: -1, -1 f2: -1, -1 f3: -1, -1 f4: -1, -1 f5: -1, -1 f6: -1, -1 f7: -1, -1 f8: -1, -1 f9: -1, -1 fa: -1, -1 fb: -1, -1 fc: -1, -1 fd: -1, -1 fe: -1, -1 ff: -1, -1 -- >8 -- This breaks all programs that expect to process text/data portably, since in LC_ALL=C half of all bytes collapse to one character (for sort this means that they all collate equally, &c., &c.)! Consider a diff of XBD 6.2 ("Character Encoding"), Issue 7 vs Issue 7 TC2: -- >8 -- @@ -1768,9 +1664,13 @@ <h3><a name="tag_06_02"> 6.2 </a>Character Encoding</h3> -<p>The POSIX locale contains the characters in <a href="#tagtcjh_3">Portable Character Set</a> , which have the properties listed -in <a href="../basedefs/V1_chap07.html#tag_07_03_01"><i>LC_CTYPE</i></a> . In other locales, the presence, meaning, and -representation of any additional characters are locale-specific.</p> +<p>The POSIX locale shall contain 256 single-byte characters including the characters in <a href="#tagtcjh_3">Portable Character +Set</a> and <a href="#tagtcjh_4">Non-Portable Control Characters</a>, which have the properties listed in <a href= +"../basedefs/V1_chap07.html#tag_07_03_01"><i>LC_CTYPE</i></a>. It is unspecified whether characters not listed in those two tables +are classified as <b>punct</b> or <b>cntrl</b>, or neither. Other locales shall contain the characters in <a href= +"#tagtcjh_3">Portable Character Set</a> and may contain any or all of the control characters identified in <a href= +"#tagtcjh_4">Non-Portable Control Characters</a>; the presence, meaning, and representation of any additional characters are +locale-specific.</p> <p>In locales other than the POSIX locale, a character may have a state-dependent encoding. There are two types of these encodings:</p> -- >8 -- This text is widely supported with global changes later originating from bug 674: > An invalid character sequence is detected. In the POSIX locale an EILSEQ error cannot occur since all byte values are valid characters.[/CX] > In the POSIX locale each byte is a valid single-byte character, and therefore this problem is avoided. &c. This text is unchanged in Issue 8 Draft 2.1. Agonised, наб -- System Information: Debian Release: bookworm/sid APT prefers unstable APT policy: (500, 'unstable') Architecture: x32 (x86_64) Foreign Architectures: amd64, i386 Kernel: Linux 5.18.0-3-amd64 (SMP w/2 CPU threads; PREEMPT) Kernel taint flags: TAINT_PROPRIETARY_MODULE, TAINT_OOT_MODULE, TAINT_UNSIGNED_MODULE Locale: LANG=en_GB.UTF-8, LC_CTYPE=en_GB.UTF-8 (charmap=UTF-8), LANGUAGE not set Shell: /bin/sh linked to /usr/bin/dash Init: systemd (via /run/systemd/system) LSM: AppArmor: enabled Versions of packages libc6 depends on: ii libgcc-s1 12.1.0-2 Versions of packages libc6 recommends: ii libidn2-0 2.3.3-1 Versions of packages libc6 suggests: ii debconf [debconf-2.0] 1.5.79 pn glibc-doc <none> ii libc-l10n 2.33-8 ii libnss-nis 3.1-4 ii libnss-nisplus 1.3-4 ii locales 2.33-8 -- debconf information excluded
Attachment:
signature.asc
Description: PGP signature