From patchwork Sat Jan 8 00:39:07 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tom Honermann X-Patchwork-Id: 49742 Return-Path: X-Original-To: patchwork@sourceware.org Delivered-To: patchwork@sourceware.org Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id AEB32385803D for ; Sat, 8 Jan 2022 00:40:10 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org AEB32385803D DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org; s=default; t=1641602410; bh=KTYI0o0F4K/kVgOy64XjR7O8JQJR9wrh/ouo0Lcu03k=; h=To:Subject:Date:List-Id:List-Unsubscribe:List-Archive:List-Post: List-Help:List-Subscribe:From:Reply-To:From; b=nwj88LdOlYlMrdrsQkFedvY5vOVBVI0kL4n/OjKjJoQ9l+seD7v1Bwqq0LW2I0XnM N0i423ru78vw49He3RTELdGwEeJcM23J+02TsDukrUJINeT+bmXBr1SKhWX0mXFXIk mHTwSuzoXV+dmHJwt0gizKk95TOPRAyf41zMZSu0= X-Original-To: libc-alpha@sourceware.org Delivered-To: libc-alpha@sourceware.org Received: from smtp69.ord1c.emailsrvr.com (smtp69.ord1c.emailsrvr.com [108.166.43.69]) by sourceware.org (Postfix) with ESMTPS id C73793858D28 for ; Sat, 8 Jan 2022 00:39:08 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org C73793858D28 X-Auth-ID: tom@honermann.net Received: by smtp17.relay.ord1c.emailsrvr.com (Authenticated sender: tom-AT-honermann.net) with ESMTPSA id 1B4DC6010F for ; Fri, 7 Jan 2022 19:39:08 -0500 (EST) To: libc-alpha Subject: [PATCH 1/3]: C++20 P0482R6 and C2X N2653: Fix for bug 25744, mbrtowc with Big5-HKSCS Message-ID: <9de491d0-5f3f-518e-47d8-1f25123027bf@honermann.net> Date: Fri, 7 Jan 2022 19:39:07 -0500 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101 Thunderbird/78.13.0 MIME-Version: 1.0 Content-Language: en-US X-Classification-ID: c9cd65af-25f8-4e84-8b92-807952e7f8f4-1-1 X-Spam-Status: No, score=-12.0 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, DKIM_VALID_EF, GIT_PATCH_0, RCVD_IN_DNSWL_NONE, SPF_HELO_NONE, SPF_PASS, TXREP autolearn=ham autolearn_force=no version=3.4.4 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on server2.sourceware.org X-BeenThere: libc-alpha@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Libc-alpha mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-Patchwork-Original-From: Tom Honermann via Libc-alpha From: Tom Honermann Reply-To: Tom Honermann Errors-To: libc-alpha-bounces+patchwork=sourceware.org@sourceware.org Sender: "Libc-alpha" This patch for bug 25744 [1] updates the Big5-HKSCS converter to properly maintain the lowest 3 bits of the mbstate_t __count data member. This change is necessary to ensure that state is correctly preserved when the converter encounters an incomplete multibyte character. More details are available in bug 25744 [1]. The code changes are styled to match how these bits are maintained by converters such as iso-2022-jp.c, ibm930.c, and others. Running 'grep __count' in the 'iconvdata' directory suggests that a number of other converters, euc-jisx0213.c for example, also fail to preserve these bits in some cases, though it may be that negative effects are not observed for those converters. This patch does not attempt to address such issues with other converters. This fix was previously posted to this mailing list on April 7th, 2020 [2], and again on June 7th, 2021 [3], but was not followed up on. Tested on Linux x86_64. Tom. [1]: Bug 25744 "mbrtowc with Big5-HKSCS returns 2 instead of 1 when consuming the second byte of certain double byte characters" https://sourceware.org/bugzilla/show_bug.cgi?id=25744 [2]: "[PATCH] Correct the Big5-HKSCS converter to preserve low order state bits (bug 25744)" https://sourceware.org/pipermail/libc-alpha/2020-April/112595.html [3]: "[PATCH 1/3]: C++20 P0482R6 and C2X N2653: Fix for bug 25744, mbrtowc with Big5-HKSCS" https://sourceware.org/pipermail/libc-alpha/2021-June/127231.html commit 900d307f4bfc5016e1a18711e8909dbce3488d3e Author: Tom Honermann Date: Wed Jan 5 18:02:24 2022 -0500 Correct the Big5-HKSCS converter to preserve low order state bits. BZ: https://sourceware.org/bugzilla/show_bug.cgi?id=25744 diff --git a/iconvdata/big5hkscs.c b/iconvdata/big5hkscs.c index ed51412bb9..2455c9db53 100644 --- a/iconvdata/big5hkscs.c +++ b/iconvdata/big5hkscs.c @@ -17769,7 +17769,7 @@ static struct the output state to the initial state. This has to be done during the flushing. */ #define EMIT_SHIFT_TO_INIT \ - if (data->__statep->__count != 0) \ + if ((data->__statep->__count >> 3) != 0) \ { \ if (FROM_DIRECTION) \ { \ @@ -17778,7 +17778,7 @@ static struct /* Write out the last character. */ \ *((uint32_t *) outbuf) = data->__statep->__count >> 3; \ outbuf += sizeof (uint32_t); \ - data->__statep->__count = 0; \ + data->__statep->__count &= 7; \ } \ else \ /* We don't have enough room in the output buffer. */ \ @@ -17792,7 +17792,7 @@ static struct uint32_t lasttwo = data->__statep->__count >> 3; \ *outbuf++ = (lasttwo >> 8) & 0xff; \ *outbuf++ = lasttwo & 0xff; \ - data->__statep->__count = 0; \ + data->__statep->__count &= 7; \ } \ else \ /* We don't have enough room in the output buffer. */ \ @@ -17878,7 +17878,7 @@ static struct \ /* Otherwise store only the first character now, and \ put the second one into the queue. */ \ - *statep = ch2 << 3; \ + *statep = (ch2 << 3) | (*statep & 7); \ /* Tell the caller why we terminate the loop. */ \ result = __GCONV_FULL_OUTPUT; \ break; \ @@ -17895,7 +17895,7 @@ static struct } \ else \ /* Clear the queue and proceed to output the saved character. */ \ - *statep = 0; \ + *statep &= 7; \ \ put32 (outptr, ch); \ outptr += 4; \ @@ -17946,7 +17946,7 @@ static struct } \ *outptr++ = (ch >> 8) & 0xff; \ *outptr++ = ch & 0xff; \ - *statep = 0; \ + *statep &= 7; \ inptr += 4; \ continue; \ \ @@ -17959,7 +17959,7 @@ static struct } \ *outptr++ = (lasttwo >> 8) & 0xff; \ *outptr++ = lasttwo & 0xff; \ - *statep = 0; \ + *statep &= 7; \ continue; \ } \ \ @@ -17996,7 +17996,7 @@ static struct /* Check for possible combining character. */ \ if (__glibc_unlikely (ch == 0xca || ch == 0xea)) \ { \ - *statep = ((cp[0] << 8) | cp[1]) << 3; \ + *statep = (((cp[0] << 8) | cp[1]) << 3) | (*statep & 7); \ inptr += 4; \ continue; \ } \ diff --git a/iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c b/iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c index 91d7d3a552..12697ebe23 100644 --- a/iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c +++ b/iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c @@ -128,6 +128,71 @@ check_conversion (struct testdata test) printf ("error: Result of third conversion was wrong.\n"); err++; } + + /* Now perform the same test as above consuming one byte at a time. */ + mbs = test.input; + memset (&st, 0, sizeof (st)); + + /* Consume the first byte; expect an incomplete multibyte character. */ + ret = mbrtowc (&wc, mbs, 1, &st); + if (ret != -2) + { + printf ("error: First byte conversion returned %zd.\n", ret); + err++; + } + /* Advance past the first consumed byte. */ + mbs += 1; + /* Consume the second byte; expect the first wchar_t. */ + ret = mbrtowc (&wc, mbs, 1, &st); + if (ret != 1) + { + printf ("error: Second byte conversion returned %zd.\n", ret); + err++; + } + /* Advance past the second consumed byte. */ + mbs += 1; + if (wc != test.expected[0]) + { + printf ("error: Result of first wchar_t conversion was wrong.\n"); + err++; + } + /* Consume no bytes; expect the second wchar_t. */ + ret = mbrtowc (&wc, mbs, 1, &st); + if (ret != 0) + { + printf ("error: First attempt of third byte conversion returned %zd.\n", ret); + err++; + } + /* Do not advance past the third byte. */ + mbs += 0; + if (wc != test.expected[1]) + { + printf ("error: Result of second wchar_t conversion was wrong.\n"); + err++; + } + /* After the second wchar_t conversion, the converter should be in + the initial state since the two input BIG5-HKSCS bytes have been + consumed and the two wchar_t's have been output. */ + if (mbsinit (&st) == 0) + { + printf ("error: Converter not in initial state.\n"); + err++; + } + /* Consume the third byte; expect the third wchar_t. */ + ret = mbrtowc (&wc, mbs, 1, &st); + if (ret != 1) + { + printf ("error: Third byte conversion returned %zd.\n", ret); + err++; + } + /* Advance past the third consumed byte. */ + mbs += 1; + if (wc != test.expected[2]) + { + printf ("error: Result of third wchar_t conversion was wrong.\n"); + err++; + } + /* Return 0 if we saw no errors. */ return err; } From patchwork Sat Jan 8 00:39:11 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tom Honermann X-Patchwork-Id: 49743 Return-Path: X-Original-To: patchwork@sourceware.org Delivered-To: patchwork@sourceware.org Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id 9871C3857C78 for ; Sat, 8 Jan 2022 00:40:53 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 9871C3857C78 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org; s=default; t=1641602453; bh=/dNlv3vzU+ZCWqAKp6WXPZITJ7vf2LzFg1J9z/+7bG0=; h=To:Subject:Date:List-Id:List-Unsubscribe:List-Archive:List-Post: List-Help:List-Subscribe:From:Reply-To:From; b=b2rairMQzypDTs6Nd7MuEFSp2C6uGUFMEwpjAzHyQM3P2yi6s/scj4SbA0hb+Ndhe ZL4gjffxgj3xPV0NFWKUn9mJLF++6xcucDXzNXmY9wNJW4eMoN2lBtyBPUFhuDqBSA 4Tc/JQZMq9Vqi3laA1aDUGsN+Qihibb8gXVuB9BM= X-Original-To: libc-alpha@sourceware.org Delivered-To: libc-alpha@sourceware.org Received: from smtp69.ord1c.emailsrvr.com (smtp69.ord1c.emailsrvr.com [108.166.43.69]) by sourceware.org (Postfix) with ESMTPS id F1DF73858421 for ; Sat, 8 Jan 2022 00:39:12 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org F1DF73858421 X-Auth-ID: tom@honermann.net Received: by smtp1.relay.ord1c.emailsrvr.com (Authenticated sender: tom-AT-honermann.net) with ESMTPSA id 5F7F5200C3 for ; Fri, 7 Jan 2022 19:39:12 -0500 (EST) To: libc-alpha Subject: [PATCH 2/3]: C++20 P0482R6 and C2X N2653: Implement mbrtoc8, c8rtomb, char8_t Message-ID: Date: Fri, 7 Jan 2022 19:39:11 -0500 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101 Thunderbird/78.13.0 MIME-Version: 1.0 Content-Language: en-US X-Classification-ID: 11cdab8b-8a77-4e47-9009-0e29b8406365-1-1 X-Spam-Status: No, score=-12.0 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, DKIM_VALID_EF, GIT_PATCH_0, KAM_SHORT, RCVD_IN_DNSWL_NONE, SPF_HELO_NONE, SPF_PASS, TXREP autolearn=ham autolearn_force=no version=3.4.4 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on server2.sourceware.org X-BeenThere: libc-alpha@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Libc-alpha mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-Patchwork-Original-From: Tom Honermann via Libc-alpha From: Tom Honermann Reply-To: Tom Honermann Errors-To: libc-alpha-bounces+patchwork=sourceware.org@sourceware.org Sender: "Libc-alpha" This patch provides implementations for the mbrtoc8 and c8rtomb functions adopted for C++20 via WG21 P0482R6 [1] and proposed for C2X via WG14 N2653 [2]. It also provides the char8_t typedef from WG14 N2653 [2]. The mbrtoc8 and c8rtomb functions are declared in uchar.h if either of the C++20 __cpp_char8_t or _GNU_SOURCE feature test macros are defined. The char8_t typedef is declared in uchar.h if _GNU_SOURCE is defined and __cpp_char8_t is not defined (if __cpp_char8_t is defined, then char8_t is a builtin type). Tested on Linux x86_64. Tom. [1]: WG21 P0482R6 "char8_t: A type for UTF-8 characters and strings (Revision 6)" https://wg21.link/p0482r6 [2]: WG14 N2653 "char8_t: A type for UTF-8 characters and strings (Revision 1)" http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2653.htm commit 0710b1004c1eb151d739c73090c4eab81e454eb1 Author: Tom Honermann Date: Wed Jan 5 18:42:03 2022 -0500 Implement mbrtoc8(), c8rtomb(), and the char8_t typedef. This change provides implementations for the mbrtoc8 and c8rtomb functions adopted for C++20 via WG21 P0482R6 and proposed for C2X via WG14 N2653. It also provides the char8_t typedef from N2653. The mbrtoc8 and c8rtomb functions are declared in uchar.h if either of the C++20 __cpp_char8_t feature test macro or the _GNU_SOURCE macro are defined. The char8_t typedef is declared in uchar.h if _GNU_SOURCE is defined and __cpp_char8_t is not defined (if __cpp_char8_t is defined, then char8_t is a builtin type). diff --git a/NEWS b/NEWS index 4762bfcc4e..ccb22553f2 100644 --- a/NEWS +++ b/NEWS @@ -237,6 +237,14 @@ Major new features: * The audit libraries will avoid unnecessary slowdown if it is not required PLT tracking (by not implementing the la_pltenter or la_pltexit callbacks). +* The mbrtoc8 and c8rtomb functions are added for implementation of the + C++20 P0482R6 and C2X N2653 proposals. These functions perform conversions + between multibyte sequences and the UTF-8 character encoding. A char8_t + typedef is added for the C2X N2653 proposal. The functions are declared + in uchar.h if the C++20 __cpp_char8_t feature test macro or _GNU_SOURCE + macro is defined. The char8_t typedef is declared in uchar.h if _GNU_SOURCE + is defined and __cpp_char8_t is not defined. + Deprecated and removed features, and other changes affecting compatibility: * The function pthread_mutex_consistent_np has been deprecated; programs diff --git a/sysdeps/mach/hurd/i386/libc.abilist b/sysdeps/mach/hurd/i386/libc.abilist index ecf8c0992e..d1188a83a5 100644 --- a/sysdeps/mach/hurd/i386/libc.abilist +++ b/sysdeps/mach/hurd/i386/libc.abilist @@ -2287,7 +2287,9 @@ GLIBC_2.34 shm_unlink F GLIBC_2.34 timespec_getres F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F GLIBC_2.35 close_range F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 __confstr_chk F GLIBC_2.4 __fgets_chk F GLIBC_2.4 __fgets_unlocked_chk F diff --git a/sysdeps/unix/sysv/linux/aarch64/libc.abilist b/sysdeps/unix/sysv/linux/aarch64/libc.abilist index fed942ed4b..35586c023f 100644 --- a/sysdeps/unix/sysv/linux/aarch64/libc.abilist +++ b/sysdeps/unix/sysv/linux/aarch64/libc.abilist @@ -2613,4 +2613,6 @@ GLIBC_2.34 tss_delete F GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F +GLIBC_2.35 c8rtomb F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 mbrtoc8 F diff --git a/sysdeps/unix/sysv/linux/alpha/libc.abilist b/sysdeps/unix/sysv/linux/alpha/libc.abilist index 2867932704..4969c57a37 100644 --- a/sysdeps/unix/sysv/linux/alpha/libc.abilist +++ b/sysdeps/unix/sysv/linux/alpha/libc.abilist @@ -2711,6 +2711,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 _IO_fprintf F GLIBC_2.4 _IO_printf F GLIBC_2.4 _IO_sprintf F diff --git a/sysdeps/unix/sysv/linux/arc/libc.abilist b/sysdeps/unix/sysv/linux/arc/libc.abilist index 239db7bab0..fccd1f8662 100644 --- a/sysdeps/unix/sysv/linux/arc/libc.abilist +++ b/sysdeps/unix/sysv/linux/arc/libc.abilist @@ -2375,3 +2375,5 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F diff --git a/sysdeps/unix/sysv/linux/arm/be/libc.abilist b/sysdeps/unix/sysv/linux/arm/be/libc.abilist index bc79dcfe8a..1cb2d4fd66 100644 --- a/sysdeps/unix/sysv/linux/arm/be/libc.abilist +++ b/sysdeps/unix/sysv/linux/arm/be/libc.abilist @@ -493,6 +493,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 _Exit F GLIBC_2.4 _IO_2_1_stderr_ D 0xa0 GLIBC_2.4 _IO_2_1_stdin_ D 0xa0 diff --git a/sysdeps/unix/sysv/linux/arm/le/libc.abilist b/sysdeps/unix/sysv/linux/arm/le/libc.abilist index 614607fd6b..b36859f8e1 100644 --- a/sysdeps/unix/sysv/linux/arm/le/libc.abilist +++ b/sysdeps/unix/sysv/linux/arm/le/libc.abilist @@ -490,6 +490,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 _Exit F GLIBC_2.4 _IO_2_1_stderr_ D 0xa0 GLIBC_2.4 _IO_2_1_stdin_ D 0xa0 diff --git a/sysdeps/unix/sysv/linux/csky/libc.abilist b/sysdeps/unix/sysv/linux/csky/libc.abilist index 2b61543f0d..4f7828d822 100644 --- a/sysdeps/unix/sysv/linux/csky/libc.abilist +++ b/sysdeps/unix/sysv/linux/csky/libc.abilist @@ -2649,3 +2649,5 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F diff --git a/sysdeps/unix/sysv/linux/hppa/libc.abilist b/sysdeps/unix/sysv/linux/hppa/libc.abilist index 6b3cb1adb4..d59accc822 100644 --- a/sysdeps/unix/sysv/linux/hppa/libc.abilist +++ b/sysdeps/unix/sysv/linux/hppa/libc.abilist @@ -2598,6 +2598,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 __confstr_chk F GLIBC_2.4 __fgets_chk F GLIBC_2.4 __fgets_unlocked_chk F diff --git a/sysdeps/unix/sysv/linux/i386/libc.abilist b/sysdeps/unix/sysv/linux/i386/libc.abilist index 7f608c1b64..37a065f555 100644 --- a/sysdeps/unix/sysv/linux/i386/libc.abilist +++ b/sysdeps/unix/sysv/linux/i386/libc.abilist @@ -2782,6 +2782,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 __confstr_chk F GLIBC_2.4 __fgets_chk F GLIBC_2.4 __fgets_unlocked_chk F diff --git a/sysdeps/unix/sysv/linux/ia64/libc.abilist b/sysdeps/unix/sysv/linux/ia64/libc.abilist index 865deec43f..69839c86fd 100644 --- a/sysdeps/unix/sysv/linux/ia64/libc.abilist +++ b/sysdeps/unix/sysv/linux/ia64/libc.abilist @@ -2549,6 +2549,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 __confstr_chk F GLIBC_2.4 __fgets_chk F GLIBC_2.4 __fgets_unlocked_chk F diff --git a/sysdeps/unix/sysv/linux/m68k/coldfire/libc.abilist b/sysdeps/unix/sysv/linux/m68k/coldfire/libc.abilist index a172d74632..b8418d612c 100644 --- a/sysdeps/unix/sysv/linux/m68k/coldfire/libc.abilist +++ b/sysdeps/unix/sysv/linux/m68k/coldfire/libc.abilist @@ -494,6 +494,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 _Exit F GLIBC_2.4 _IO_2_1_stderr_ D 0x98 GLIBC_2.4 _IO_2_1_stdin_ D 0x98 diff --git a/sysdeps/unix/sysv/linux/m68k/m680x0/libc.abilist b/sysdeps/unix/sysv/linux/m68k/m680x0/libc.abilist index 174e9c7739..8cfbb5f235 100644 --- a/sysdeps/unix/sysv/linux/m68k/m680x0/libc.abilist +++ b/sysdeps/unix/sysv/linux/m68k/m680x0/libc.abilist @@ -2725,6 +2725,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 __confstr_chk F GLIBC_2.4 __fgets_chk F GLIBC_2.4 __fgets_unlocked_chk F diff --git a/sysdeps/unix/sysv/linux/microblaze/be/libc.abilist b/sysdeps/unix/sysv/linux/microblaze/be/libc.abilist index d042be1369..0d729329aa 100644 --- a/sysdeps/unix/sysv/linux/microblaze/be/libc.abilist +++ b/sysdeps/unix/sysv/linux/microblaze/be/libc.abilist @@ -2698,3 +2698,5 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F diff --git a/sysdeps/unix/sysv/linux/microblaze/le/libc.abilist b/sysdeps/unix/sysv/linux/microblaze/le/libc.abilist index 332da62de2..3980c6df0d 100644 --- a/sysdeps/unix/sysv/linux/microblaze/le/libc.abilist +++ b/sysdeps/unix/sysv/linux/microblaze/le/libc.abilist @@ -2695,3 +2695,5 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F diff --git a/sysdeps/unix/sysv/linux/mips/mips32/fpu/libc.abilist b/sysdeps/unix/sysv/linux/mips/mips32/fpu/libc.abilist index 2d6ec0d0e8..f8c2087559 100644 --- a/sysdeps/unix/sysv/linux/mips/mips32/fpu/libc.abilist +++ b/sysdeps/unix/sysv/linux/mips/mips32/fpu/libc.abilist @@ -2690,6 +2690,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 __confstr_chk F GLIBC_2.4 __fgets_chk F GLIBC_2.4 __fgets_unlocked_chk F diff --git a/sysdeps/unix/sysv/linux/mips/mips32/nofpu/libc.abilist b/sysdeps/unix/sysv/linux/mips/mips32/nofpu/libc.abilist index 6c5befa72b..ce87791286 100644 --- a/sysdeps/unix/sysv/linux/mips/mips32/nofpu/libc.abilist +++ b/sysdeps/unix/sysv/linux/mips/mips32/nofpu/libc.abilist @@ -2688,6 +2688,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 __confstr_chk F GLIBC_2.4 __fgets_chk F GLIBC_2.4 __fgets_unlocked_chk F diff --git a/sysdeps/unix/sysv/linux/mips/mips64/n32/libc.abilist b/sysdeps/unix/sysv/linux/mips/mips64/n32/libc.abilist index 5fb24c97e1..ee547ceb78 100644 --- a/sysdeps/unix/sysv/linux/mips/mips64/n32/libc.abilist +++ b/sysdeps/unix/sysv/linux/mips/mips64/n32/libc.abilist @@ -2696,6 +2696,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 __confstr_chk F GLIBC_2.4 __fgets_chk F GLIBC_2.4 __fgets_unlocked_chk F diff --git a/sysdeps/unix/sysv/linux/mips/mips64/n64/libc.abilist b/sysdeps/unix/sysv/linux/mips/mips64/n64/libc.abilist index f4f29fc15e..4c558a283e 100644 --- a/sysdeps/unix/sysv/linux/mips/mips64/n64/libc.abilist +++ b/sysdeps/unix/sysv/linux/mips/mips64/n64/libc.abilist @@ -2600,6 +2600,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 __confstr_chk F GLIBC_2.4 __fgets_chk F GLIBC_2.4 __fgets_unlocked_chk F diff --git a/sysdeps/unix/sysv/linux/nios2/libc.abilist b/sysdeps/unix/sysv/linux/nios2/libc.abilist index 2e7300cd05..234ab84125 100644 --- a/sysdeps/unix/sysv/linux/nios2/libc.abilist +++ b/sysdeps/unix/sysv/linux/nios2/libc.abilist @@ -2737,3 +2737,5 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F diff --git a/sysdeps/unix/sysv/linux/powerpc/powerpc32/fpu/libc.abilist b/sysdeps/unix/sysv/linux/powerpc/powerpc32/fpu/libc.abilist index 129a2f16a7..e383bac9bd 100644 --- a/sysdeps/unix/sysv/linux/powerpc/powerpc32/fpu/libc.abilist +++ b/sysdeps/unix/sysv/linux/powerpc/powerpc32/fpu/libc.abilist @@ -2752,6 +2752,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 _IO_fprintf F GLIBC_2.4 _IO_printf F GLIBC_2.4 _IO_sprintf F diff --git a/sysdeps/unix/sysv/linux/powerpc/powerpc32/nofpu/libc.abilist b/sysdeps/unix/sysv/linux/powerpc/powerpc32/nofpu/libc.abilist index 7e23226779..ddbcb3e085 100644 --- a/sysdeps/unix/sysv/linux/powerpc/powerpc32/nofpu/libc.abilist +++ b/sysdeps/unix/sysv/linux/powerpc/powerpc32/nofpu/libc.abilist @@ -2785,6 +2785,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 _IO_fprintf F GLIBC_2.4 _IO_printf F GLIBC_2.4 _IO_sprintf F diff --git a/sysdeps/unix/sysv/linux/powerpc/powerpc64/be/libc.abilist b/sysdeps/unix/sysv/linux/powerpc/powerpc64/be/libc.abilist index 6f97392b70..daaa374fa0 100644 --- a/sysdeps/unix/sysv/linux/powerpc/powerpc64/be/libc.abilist +++ b/sysdeps/unix/sysv/linux/powerpc/powerpc64/be/libc.abilist @@ -2508,6 +2508,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 _IO_fprintf F GLIBC_2.4 _IO_printf F GLIBC_2.4 _IO_sprintf F diff --git a/sysdeps/unix/sysv/linux/powerpc/powerpc64/le/libc.abilist b/sysdeps/unix/sysv/linux/powerpc/powerpc64/le/libc.abilist index 29058a041a..a24f6b4751 100644 --- a/sysdeps/unix/sysv/linux/powerpc/powerpc64/le/libc.abilist +++ b/sysdeps/unix/sysv/linux/powerpc/powerpc64/le/libc.abilist @@ -2810,3 +2810,5 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F diff --git a/sysdeps/unix/sysv/linux/riscv/rv32/libc.abilist b/sysdeps/unix/sysv/linux/riscv/rv32/libc.abilist index d2924766d2..3dc0e04f64 100644 --- a/sysdeps/unix/sysv/linux/riscv/rv32/libc.abilist +++ b/sysdeps/unix/sysv/linux/riscv/rv32/libc.abilist @@ -2377,3 +2377,5 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F diff --git a/sysdeps/unix/sysv/linux/riscv/rv64/libc.abilist b/sysdeps/unix/sysv/linux/riscv/rv64/libc.abilist index b770e05da3..af3bbfc83b 100644 --- a/sysdeps/unix/sysv/linux/riscv/rv64/libc.abilist +++ b/sysdeps/unix/sysv/linux/riscv/rv64/libc.abilist @@ -2577,3 +2577,5 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F diff --git a/sysdeps/unix/sysv/linux/s390/s390-32/libc.abilist b/sysdeps/unix/sysv/linux/s390/s390-32/libc.abilist index bed3433a2b..4025a7f913 100644 --- a/sysdeps/unix/sysv/linux/s390/s390-32/libc.abilist +++ b/sysdeps/unix/sysv/linux/s390/s390-32/libc.abilist @@ -2750,6 +2750,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 _IO_fprintf F GLIBC_2.4 _IO_printf F GLIBC_2.4 _IO_sprintf F diff --git a/sysdeps/unix/sysv/linux/s390/s390-64/libc.abilist b/sysdeps/unix/sysv/linux/s390/s390-64/libc.abilist index 4f1a143da5..55febf9508 100644 --- a/sysdeps/unix/sysv/linux/s390/s390-64/libc.abilist +++ b/sysdeps/unix/sysv/linux/s390/s390-64/libc.abilist @@ -2545,6 +2545,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 _IO_fprintf F GLIBC_2.4 _IO_printf F GLIBC_2.4 _IO_sprintf F diff --git a/sysdeps/unix/sysv/linux/sh/be/libc.abilist b/sysdeps/unix/sysv/linux/sh/be/libc.abilist index 92c8dec8ec..cc37920ee2 100644 --- a/sysdeps/unix/sysv/linux/sh/be/libc.abilist +++ b/sysdeps/unix/sysv/linux/sh/be/libc.abilist @@ -2605,6 +2605,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 __confstr_chk F GLIBC_2.4 __fgets_chk F GLIBC_2.4 __fgets_unlocked_chk F diff --git a/sysdeps/unix/sysv/linux/sh/le/libc.abilist b/sysdeps/unix/sysv/linux/sh/le/libc.abilist index 263da58cb7..298654b119 100644 --- a/sysdeps/unix/sysv/linux/sh/le/libc.abilist +++ b/sysdeps/unix/sysv/linux/sh/le/libc.abilist @@ -2602,6 +2602,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 __confstr_chk F GLIBC_2.4 __fgets_chk F GLIBC_2.4 __fgets_unlocked_chk F diff --git a/sysdeps/unix/sysv/linux/sparc/sparc32/libc.abilist b/sysdeps/unix/sysv/linux/sparc/sparc32/libc.abilist index 0171efe7db..ed214429f0 100644 --- a/sysdeps/unix/sysv/linux/sparc/sparc32/libc.abilist +++ b/sysdeps/unix/sysv/linux/sparc/sparc32/libc.abilist @@ -2745,6 +2745,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 _IO_fprintf F GLIBC_2.4 _IO_printf F GLIBC_2.4 _IO_sprintf F diff --git a/sysdeps/unix/sysv/linux/sparc/sparc64/libc.abilist b/sysdeps/unix/sysv/linux/sparc/sparc64/libc.abilist index 7f8d45f362..0dcc3674eb 100644 --- a/sysdeps/unix/sysv/linux/sparc/sparc64/libc.abilist +++ b/sysdeps/unix/sysv/linux/sparc/sparc64/libc.abilist @@ -2572,6 +2572,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 __confstr_chk F GLIBC_2.4 __fgets_chk F GLIBC_2.4 __fgets_unlocked_chk F diff --git a/sysdeps/unix/sysv/linux/x86_64/64/libc.abilist b/sysdeps/unix/sysv/linux/x86_64/64/libc.abilist index c2f1a8ecc6..ec4e0b73e4 100644 --- a/sysdeps/unix/sysv/linux/x86_64/64/libc.abilist +++ b/sysdeps/unix/sysv/linux/x86_64/64/libc.abilist @@ -2523,6 +2523,8 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F GLIBC_2.4 __confstr_chk F GLIBC_2.4 __fgets_chk F GLIBC_2.4 __fgets_unlocked_chk F diff --git a/sysdeps/unix/sysv/linux/x86_64/x32/libc.abilist b/sysdeps/unix/sysv/linux/x86_64/x32/libc.abilist index 8b43acf100..b60cd45821 100644 --- a/sysdeps/unix/sysv/linux/x86_64/x32/libc.abilist +++ b/sysdeps/unix/sysv/linux/x86_64/x32/libc.abilist @@ -2629,3 +2629,5 @@ GLIBC_2.34 tss_get F GLIBC_2.34 tss_set F GLIBC_2.35 __memcmpeq F GLIBC_2.35 _dl_find_object F +GLIBC_2.35 c8rtomb F +GLIBC_2.35 mbrtoc8 F diff --git a/wcsmbs/Makefile b/wcsmbs/Makefile index 3a3be9cd95..390d94bbb2 100644 --- a/wcsmbs/Makefile +++ b/wcsmbs/Makefile @@ -42,7 +42,7 @@ routines := wcscat wcschr wcscmp wcscpy wcscspn wcsdup wcslen wcsncat \ wcsmbsload mbsrtowcs_l \ isoc99_wscanf isoc99_vwscanf isoc99_fwscanf isoc99_vfwscanf \ isoc99_swscanf isoc99_vswscanf \ - mbrtoc16 c16rtomb mbrtoc32 c32rtomb + mbrtoc8 c8rtomb mbrtoc16 c16rtomb mbrtoc32 c32rtomb strop-tests := wcscmp wcsncmp wmemcmp wcslen wcschr wcsrchr wcscpy wcsnlen \ wcpcpy wcsncpy wcpncpy wcscat wcsncat wcschrnul wcsspn wcspbrk \ diff --git a/wcsmbs/Versions b/wcsmbs/Versions index 0b31c1b940..d578518fad 100644 --- a/wcsmbs/Versions +++ b/wcsmbs/Versions @@ -49,4 +49,7 @@ libc { wcstof32; wcstof64; wcstof32x; wcstof32_l; wcstof64_l; wcstof32x_l; } + GLIBC_2.35 { + c8rtomb; mbrtoc8; + } } diff --git a/wcsmbs/c8rtomb.c b/wcsmbs/c8rtomb.c new file mode 100644 index 0000000000..8a5ffeab23 --- /dev/null +++ b/wcsmbs/c8rtomb.c @@ -0,0 +1,132 @@ +/* UTF-8 to multibyte conversion. + Copyright (C) 2022 Free Software Foundation, Inc. + This file is part of the GNU C Library. + + The GNU C Library 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. + + The GNU C 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 + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, see + . */ + +#include +#include +#include + + +/* This is the private state used if PS is NULL. */ +static mbstate_t state; + +size_t +c8rtomb (char *s, char8_t c8, mbstate_t *ps) +{ + /* This implementation depends on the converter invoked by wcrtomb not + needing to retain state in either the top most bit of ps->__count or + in ps->__value between invocations. This implementation uses the + top most bit of ps->__count to indicate that trailing code units are + expected and uses ps->__value to store previously seen code units. */ + + wchar_t wc; + + if (ps == NULL) + ps = &state; + + if (s == NULL) + { + /* if 's' is a null pointer, behave as if u8'\0' was passed as 'c8'. If + this occurs for an incomplete code unit sequence, then an error will + be reported below. */ + c8 = u8""[0]; + } + + if (! (ps->__count & 0x80000000)) + { + /* Initial state. */ + if ((c8 >= 0x80 && c8 <= 0xC1) || c8 >= 0xF5) + { + /* An invalid lead code unit. */ + __set_errno (EILSEQ); + return -1; + } + if (c8 >= 0xC2) + { + /* A valid lead code unit. */ + ps->__count |= 0x80000000; + ps->__value.__wchb[0] = c8; + ps->__value.__wchb[3] = 1; + return 0; + } + /* A single byte (ASCII) code unit. */ + wc = c8; + } + else + { + char8_t cu1 = ps->__value.__wchb[0]; + if (ps->__value.__wchb[3] == 1) + { + /* A single lead code unit was previously seen. */ + if ((c8 < 0x80 || c8 > 0xBF) || + (cu1 == 0xE0 && c8 < 0xA0) || + (cu1 == 0xED && c8 > 0x9F) || + (cu1 == 0xF0 && c8 < 0x90) || + (cu1 == 0xF4 && c8 > 0x8F)) + { + /* An invalid second code unit. */ + __set_errno (EILSEQ); + return -1; + } + if (cu1 >= 0xE0) + { + /* A three or four code unit sequence. */ + ps->__value.__wchb[1] = c8; + ++ps->__value.__wchb[3]; + return 0; + } + wc = ((cu1 & 0x1F) << 6) + + (c8 & 0x3F); + } + else + { + char8_t cu2 = ps->__value.__wchb[1]; + /* A three or four byte code unit sequence. */ + if (c8 < 0x80 || c8 > 0xBF) + { + /* An invalid third or fourth code unit. */ + __set_errno (EILSEQ); + return -1; + } + if (ps->__value.__wchb[3] == 2 && cu1 >= 0xF0) + { + /* A four code unit sequence. */ + ps->__value.__wchb[2] = c8; + ++ps->__value.__wchb[3]; + return 0; + } + if (cu1 < 0xF0) + { + wc = ((cu1 & 0x0F) << 12) + + ((cu2 & 0x3F) << 6) + + (c8 & 0x3F); + } + else + { + char8_t cu3 = ps->__value.__wchb[2]; + wc = ((cu1 & 0x07) << 18) + + ((cu2 & 0x3F) << 12) + + ((cu3 & 0x3F) << 6) + + (c8 & 0x3F); + } + } + ps->__count &= 0x7fffffff; + ps->__value.__wch = 0; + } + + return wcrtomb (s, wc, ps); +} diff --git a/wcsmbs/mbrtoc8.c b/wcsmbs/mbrtoc8.c new file mode 100644 index 0000000000..8ca457088d --- /dev/null +++ b/wcsmbs/mbrtoc8.c @@ -0,0 +1,126 @@ +/* Multibyte to UTF-8 conversion. + Copyright (C) 2022 Free Software Foundation, Inc. + This file is part of the GNU C Library. + + The GNU C Library 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. + + The GNU C 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 + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, see + . */ + +#include +#include +#include +#include +#include +#include + +#include + +#ifndef EILSEQ +# define EILSEQ EINVAL +#endif + + +/* This is the private state used if PS is NULL. */ +static mbstate_t state; + +size_t +mbrtoc8 (char8_t *pc8, const char *s, size_t n, mbstate_t *ps) +{ + /* This implementation depends on the converter invoked by mbrtowc() not + needing to retain state in either the top most bit of ps->__count or + in ps->__value between invocations. This implementation uses the + top most bit of ps->__count to indicate that trailing code units are + yet to be written and uses ps->__value to store those code units. */ + + if (ps == NULL) + ps = &state; + + /* If state indicates that trailing code units are yet to be written, write + those first regardless of whether 's' is a null pointer. */ + if (ps->__count & 0x80000000) + { + /* ps->__value.__wchb[3] stores the index of the next code unit to + write. Code units are stored in reverse order. */ + size_t i = ps->__value.__wchb[3]; + if (pc8 != NULL) + { + *pc8 = ps->__value.__wchb[i]; + } + if (i == 0) + { + ps->__count &= 0x7fffffff; + ps->__value.__wch = 0; + } + else + --ps->__value.__wchb[3]; + return -3; + } + + if (s == NULL) + { + /* if 's' is a null pointer, behave as if a null pointer was passed for + 'pc8', an empty string was passed for 's', and 1 passed for 'n'. */ + pc8 = NULL; + s = ""; + n = 1; + } + + wchar_t wc; + size_t result; + + result = mbrtowc(&wc, s, n, ps); + if (result <= n) + { + if (wc <= 0x7F) + { + if (pc8 != NULL) + *pc8 = wc; + } + else if (wc <= 0x7FF) + { + if (pc8 != NULL) + *pc8 = 0xC0 + ((wc >> 6) & 0x1F); + ps->__value.__wchb[0] = 0x80 + (wc & 0x3F); + ps->__value.__wchb[3] = 0; + ps->__count |= 0x80000000; + } + else if (wc <= 0xFFFF) + { + if (pc8 != NULL) + *pc8 = 0xE0 + ((wc >> 12) & 0x0F); + ps->__value.__wchb[1] = 0x80 + ((wc >> 6) & 0x3F); + ps->__value.__wchb[0] = 0x80 + (wc & 0x3F); + ps->__value.__wchb[3] = 1; + ps->__count |= 0x80000000; + } + else if (wc <= 0x10FFFF) + { + if (pc8 != NULL) + *pc8 = 0xF0 + ((wc >> 18) & 0x07); + ps->__value.__wchb[2] = 0x80 + ((wc >> 12) & 0x3F); + ps->__value.__wchb[1] = 0x80 + ((wc >> 6) & 0x3F); + ps->__value.__wchb[0] = 0x80 + (wc & 0x3F); + ps->__value.__wchb[3] = 2; + ps->__count |= 0x80000000; + } + } + if (result == 0 && wc != 0) + { + /* mbrtowc() never returns -3. When a MB sequence converts to multiple + WCs, no input is consumed when writing the subsequent WCs resulting + in a result of 0 even if a null character wasn't written. */ + result = -3; + } + + return result; +} diff --git a/wcsmbs/uchar.h b/wcsmbs/uchar.h index 6020f66cf6..2f15c6f74d 100644 --- a/wcsmbs/uchar.h +++ b/wcsmbs/uchar.h @@ -31,6 +31,13 @@ #include #include +/* Declare the char8_t typedef in _GNU_SOURCE mode, but only if the C++ + __cpp_char8_t feature test macro is not defined. */ +#if defined __USE_GNU && !defined __cpp_char8_t +/* Define the 8-bit character type. */ +typedef unsigned char char8_t; +#endif + #ifndef __USE_ISOCXX11 /* Define the 16-bit and 32-bit character types. */ typedef __uint_least16_t char16_t; @@ -40,6 +47,20 @@ typedef __uint_least32_t char32_t; __BEGIN_DECLS +/* Declare mbrtoc8() and c8rtomb() in _GNU_SOURCE mode or if the C++ + __cpp_char8_t feature test macro is defined. */ +#if defined __USE_GNU || defined __cpp_char8_t +/* Write char8_t representation of multibyte character pointed + to by S to PC8. */ +extern size_t mbrtoc8 (char8_t *__restrict __pc8, + const char *__restrict __s, size_t __n, + mbstate_t *__restrict __p) __THROW; + +/* Write multibyte representation of char8_t C8 to S. */ +extern size_t c8rtomb (char *__restrict __s, char8_t __c8, + mbstate_t *__restrict __ps) __THROW; +#endif + /* Write char16_t representation of multibyte character pointed to by S to PC16. */ extern size_t mbrtoc16 (char16_t *__restrict __pc16, From patchwork Sat Jan 8 00:39:16 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tom Honermann X-Patchwork-Id: 49744 Return-Path: X-Original-To: patchwork@sourceware.org Delivered-To: patchwork@sourceware.org Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id 529AD385780D for ; Sat, 8 Jan 2022 00:41:45 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 529AD385780D DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org; s=default; t=1641602505; bh=uYknCqJztbOhdYxLnqMLOwoAGbDTajTPcCz39r1/XDk=; h=To:Subject:Date:List-Id:List-Unsubscribe:List-Archive:List-Post: List-Help:List-Subscribe:From:Reply-To:From; b=ENcQDjy2qtpHkjw308C+g8eKJemOVQHHFKXVzhs13CQ/Tf6aDnN77pCe2lqhkkc3E o954+VcuPz5YJCn88vouyVsREgdCtH9HCCVW0YvbPKpSO8lDYPUVfHnaKswSD+knvx 4+j83uZp1o8ja7YR984fJBjZ2flZ5LDU26wqarlw= X-Original-To: libc-alpha@sourceware.org Delivered-To: libc-alpha@sourceware.org Received: from smtp124.ord1c.emailsrvr.com (smtp124.ord1c.emailsrvr.com [108.166.43.124]) by sourceware.org (Postfix) with ESMTPS id B09043858036 for ; Sat, 8 Jan 2022 00:39:17 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org B09043858036 X-Auth-ID: tom@honermann.net Received: by smtp16.relay.ord1c.emailsrvr.com (Authenticated sender: tom-AT-honermann.net) with ESMTPSA id E9696C0142 for ; Fri, 7 Jan 2022 19:39:16 -0500 (EST) To: libc-alpha Subject: [PATCH 3/3]: C++20 P0482R6 and C2X N2653: Tests for mbrtoc8, c8rtomb, char8_t Message-ID: <9aedd6cd-ebfa-e47c-3789-42d8af43299f@honermann.net> Date: Fri, 7 Jan 2022 19:39:16 -0500 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101 Thunderbird/78.13.0 MIME-Version: 1.0 Content-Language: en-US X-Classification-ID: 9a58daca-218e-4e69-9844-16f6a590ff46-1-1 X-Spam-Status: No, score=-12.1 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, DKIM_VALID_EF, GIT_PATCH_0, KAM_SHORT, RCVD_IN_DNSWL_NONE, RCVD_IN_MSPIKE_H4, RCVD_IN_MSPIKE_WL, SPF_HELO_NONE, SPF_PASS, TXREP autolearn=ham autolearn_force=no version=3.4.4 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on server2.sourceware.org X-BeenThere: libc-alpha@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Libc-alpha mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-Patchwork-Original-From: Tom Honermann via Libc-alpha From: Tom Honermann Reply-To: Tom Honermann Errors-To: libc-alpha-bounces+patchwork=sourceware.org@sourceware.org Sender: "Libc-alpha" This patch adds tests for the mbrtoc8 and c8rtomb functions adopted for C++20 via WG21 P0482R6 [1] and proposed for C2X via WG14 N2653 [2], and for the char8_t typedef from WG14 N2653 [2]. The tests for mbrtoc8 and c8rtomb specifically exercise conversion from/to Big5-HKSCS because of special cases that arise with that encoding. Big5-HKSCS defines some double byte sequences that convert to more than one Unicode code point. In order to test this, the locale dependencies for running tests under wcsmbs is expanded to include zh_HK.BIG5-HKSCS. Tested on Linux x86_64. Tom. [1]: WG21 P0482R6 "char8_t: A type for UTF-8 characters and strings (Revision 6)" https://wg21.link/p0482r6 [2]: WG14 N2653 "char8_t: A type for UTF-8 characters and strings (Revision 1)" http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2653.htm commit e424b0647d5c5abf5f3efcb29bb41e33d89cb8ca Author: Tom Honermann Date: Thu Jan 6 15:46:37 2022 -0500 Tests for mbrtoc8(), c8rtomb(), and the char8_t typedef. This change adds tests for the mbrtoc8 and c8rtomb functions adopted for C++20 via WG21 P0482R6 and proposed for C2X via WG14 N2653, and for the char8_t typedef from WG14 N2653. The tests for mbrtoc8 and c8rtomb specifically exercise conversion to and from Big5-HKSCS because of special cases that arise with that encoding. Big5-HKSCS defines some double byte sequences that convert to more than one Unicode code point. In order to test this, the locale dependencies for running tests under wcsmbs is expanded to include zh_HK.BIG5-HKSCS. diff --git a/wcsmbs/Makefile b/wcsmbs/Makefile index 390d94bbb2..72e936b781 100644 --- a/wcsmbs/Makefile +++ b/wcsmbs/Makefile @@ -52,6 +52,7 @@ tests := tst-wcstof wcsmbs-tst1 tst-wcsnlen tst-btowc tst-mbrtowc \ tst-c16c32-1 wcsatcliff tst-wcstol-locale tst-wcstod-nan-locale \ tst-wcstod-round test-char-types tst-fgetwc-after-eof \ tst-wcstod-nan-sign tst-c16-surrogate tst-c32-state \ + test-char8-type test-mbrtoc8 test-c8rtomb \ $(addprefix test-,$(strop-tests)) tst-mbstowcs \ tst-wprintf-binary @@ -59,7 +60,7 @@ include ../Rules ifeq ($(run-built-tests),yes) LOCALES := de_DE.ISO-8859-1 de_DE.UTF-8 en_US.ANSI_X3.4-1968 hr_HR.ISO-8859-2 \ - ja_JP.EUC-JP zh_TW.EUC-TW tr_TR.UTF-8 tr_TR.ISO-8859-9 + ja_JP.EUC-JP zh_TW.EUC-TW tr_TR.UTF-8 tr_TR.ISO-8859-9 zh_HK.BIG5-HKSCS include ../gen-locales.mk $(objpfx)tst-btowc.out: $(gen-locales) diff --git a/wcsmbs/test-c8rtomb.c b/wcsmbs/test-c8rtomb.c new file mode 100644 index 0000000000..14564fa00a --- /dev/null +++ b/wcsmbs/test-c8rtomb.c @@ -0,0 +1,519 @@ +/* Test c8rtomb. + Copyright (C) 2022 Free Software Foundation, Inc. + This file is part of the GNU C Library. + + The GNU C Library 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. + + The GNU C 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 + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, see + . */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static int +test_truncated_code_unit_sequence (void) +{ + const char8_t *u8s; + char buf[MB_LEN_MAX]; + mbstate_t s; + + /* Missing trailing code unit for a two code byte unit sequence. */ + u8s = (const char8_t*) u8"\xC2"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) -1); /* No trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Missing first trailing code unit for a three byte code unit sequence. */ + u8s = (const char8_t*) u8"\xE0"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) -1); /* No trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Missing second trailing code unit for a three byte code unit sequence. */ + u8s = (const char8_t*) u8"\xE0\xA0"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) -1); /* No trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Missing first trailing code unit for a four byte code unit sequence. */ + u8s = (const char8_t*) u8"\xF0"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) -1); /* No trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Missing second trailing code unit for a four byte code unit sequence. */ + u8s = (const char8_t*) u8"\xF0\x90"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) -1); /* No trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Missing third trailing code unit for a four byte code unit sequence. */ + u8s = (const char8_t*) u8"\xF0\x90\x80"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) 0); /* 3rd byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[3], &s), (size_t) -1); /* No trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + return 0; +} + +static int +test_invalid_trailing_code_unit_sequence (void) +{ + const char8_t *u8s; + char buf[MB_LEN_MAX]; + mbstate_t s; + + /* Invalid trailing code unit for a two code byte unit sequence. */ + u8s = (const char8_t*) u8"\xC2\xC0"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) -1); /* Invalid trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Invalid first trailing code unit for a three byte code unit sequence. */ + u8s = (const char8_t*) u8"\xE0\xC0"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) -1); /* Invalid trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Invalid second trailing code unit for a three byte code unit sequence. */ + u8s = (const char8_t*) u8"\xE0\xA0\xC0"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) -1); /* Invalid trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Invalid first trailing code unit for a four byte code unit sequence. */ + u8s = (const char8_t*) u8"\xF0\xC0"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) -1); /* Invalid trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Invalid second trailing code unit for a four byte code unit sequence. */ + u8s = (const char8_t*) u8"\xF0\x90\xC0"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) -1); /* Invalid trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Invalid third trailing code unit for a four byte code unit sequence. */ + u8s = (const char8_t*) u8"\xF0\x90\x80\xC0"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) 0); /* 3rd byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[3], &s), (size_t) -1); /* Invalid trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + return 0; +} + +static int +test_lone_trailing_code_units (void) +{ + const char8_t *u8s; + char buf[MB_LEN_MAX]; + mbstate_t s; + + /* Lone trailing code unit. */ + u8s = (const char8_t*) u8"\x80"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) -1); /* Lone trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + return 0; +} + +static int +test_overlong_encoding (void) +{ + const char8_t *u8s; + char buf[MB_LEN_MAX]; + mbstate_t s; + + /* Two byte overlong encoding. */ + u8s = (const char8_t*) u8"\xC0\x80"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) -1); /* Invalid lead code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Two byte overlong encoding. */ + u8s = (const char8_t*) u8"\xC1\x80"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) -1); /* Invalid lead code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Three byte overlong encoding. */ + u8s = (const char8_t*) u8"\xE0\x9F\xBF"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* First byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) -1); /* Invalid trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Four byte overlong encoding. */ + u8s = (const char8_t*) u8"\xF0\x8F\xBF\xBF"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* First byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) -1); /* Invalid trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + return 0; +} + +static int +test_surrogate_range (void) +{ + const char8_t *u8s; + char buf[MB_LEN_MAX]; + mbstate_t s; + + /* Would encode U+D800. */ + u8s = (const char8_t*) u8"\xED\xA0\x80"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* First byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) -1); /* Invalid trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Would encode U+DFFF. */ + u8s = (const char8_t*) u8"\xED\xBF\xBF"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* First byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) -1); /* Invalid trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + return 0; +} + +static int +test_out_of_range_encoding (void) +{ + const char8_t *u8s; + char buf[MB_LEN_MAX]; + mbstate_t s; + + /* Would encode U+00110000. */ + u8s = (const char8_t*) u8"\xF4\x90\x80\x80"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* First byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) -1); /* Invalid trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + /* Would encode U+00140000. */ + u8s = (const char8_t*) u8"\xF5\x90\x80\x80"; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + errno = 0; + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) -1); /* Invalid lead code unit */ + TEST_COMPARE (errno, EILSEQ); + + return 0; +} + +static int +test_null_output_buffer (void) +{ + char buf[MB_LEN_MAX]; + mbstate_t s; + + /* Null character with an initial state. */ + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (NULL, u8"X"[0], &s), (size_t) 1); /* null byte processed */ + TEST_VERIFY (mbsinit (&s)); /* Assert the state is now an initial state. */ + + /* Null buffer with a state corresponding to an incompletely read code + unit sequence. In this case, an error occurs since insufficient + information is available to complete the already started code unit + sequence and return to the initial state. */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8"\xC2"[0], &s), (size_t) 0); /* 1st byte processed */ + errno = 0; + TEST_COMPARE (c8rtomb (NULL, u8"\x80"[0], &s), (size_t) -1); /* No trailing code unit */ + TEST_COMPARE (errno, EILSEQ); + + return 0; +} + +static int +test_utf8 (void) +{ + const char8_t *u8s; + char buf[MB_LEN_MAX]; + mbstate_t s; + + TEST_VERIFY_EXIT (setlocale (LC_ALL, "de_DE.UTF-8") != NULL); + + /* Null character. */ + u8s = (const char8_t*) u8"\x00"; /* U+0000 => 0x00 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 1); /* 1st byte processed */ + TEST_COMPARE (buf[0], (char) 0x00); + TEST_VERIFY (mbsinit (&s)); + + /* First non-null character in the code point range that maps to a single + code unit. */ + u8s = (const char8_t*) u8"\x01"; /* U+0001 => 0x01 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 1); /* 1st byte processed */ + TEST_COMPARE (buf[0], (char) 0x01); + TEST_VERIFY (mbsinit (&s)); + + /* Last character in the code point range that maps to a single code unit. */ + u8s = (const char8_t*) u8"\x7F"; /* U+007F => 0x7F */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 1); /* 1st byte processed */ + TEST_COMPARE (buf[0], (char) 0x7F); + TEST_VERIFY (mbsinit (&s)); + + /* First character in the code point range that maps to two code units. */ + u8s = (const char8_t*) u8"\xC2\x80"; /* U+0080 => 0xC2 0x80 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 2); /* 2nd byte processed */ + TEST_COMPARE (buf[0], (char) 0xC2); + TEST_COMPARE (buf[1], (char) 0x80); + TEST_VERIFY (mbsinit (&s)); + + /* Last character in the code point range that maps to two code units. */ + u8s = (const char8_t*) u8"\u07FF"; /* U+07FF => 0xDF 0xBF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 2); /* 2nd byte processed */ + TEST_COMPARE (buf[0], (char) 0xDF); + TEST_COMPARE (buf[1], (char) 0xBF); + TEST_VERIFY (mbsinit (&s)); + + /* First character in the code point range that maps to three code units. */ + u8s = (const char8_t*) u8"\u0800"; /* U+0800 => 0xE0 0xA0 0x80 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) 3); /* 3rd byte processed */ + TEST_COMPARE (buf[0], (char) 0xE0); + TEST_COMPARE (buf[1], (char) 0xA0); + TEST_COMPARE (buf[2], (char) 0x80); + TEST_VERIFY (mbsinit (&s)); + + /* Last character in the code point range that maps to three code units + before the surrogate code point range. */ + u8s = (const char8_t*) u8"\uD7FF"; /* U+D7FF => 0xED 0x9F 0xBF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) 3); /* 3rd byte processed */ + TEST_COMPARE (buf[0], (char) 0xED); + TEST_COMPARE (buf[1], (char) 0x9F); + TEST_COMPARE (buf[2], (char) 0xBF); + TEST_VERIFY (mbsinit (&s)); + + /* First character in the code point range that maps to three code units + after the surrogate code point range. */ + u8s = (const char8_t*) u8"\uE000"; /* U+E000 => 0xEE 0x80 0x80 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) 3); /* 3rd byte processed */ + TEST_COMPARE (buf[0], (char) 0xEE); + TEST_COMPARE (buf[1], (char) 0x80); + TEST_COMPARE (buf[2], (char) 0x80); + TEST_VERIFY (mbsinit (&s)); + + /* Not a BOM. */ + u8s = (const char8_t*) u8"\uFEFF"; /* U+FEFF => 0xEF 0xBB 0xBF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) 3); /* 3rd byte processed */ + TEST_COMPARE (buf[0], (char) 0xEF); + TEST_COMPARE (buf[1], (char) 0xBB); + TEST_COMPARE (buf[2], (char) 0xBF); + TEST_VERIFY (mbsinit (&s)); + + /* Replacement character. */ + u8s = (const char8_t*) u8"\uFFFD"; /* U+FFFD => 0xEF 0xBF 0xBD */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) 3); /* 3rd byte processed */ + TEST_COMPARE (buf[0], (char) 0xEF); + TEST_COMPARE (buf[1], (char) 0xBF); + TEST_COMPARE (buf[2], (char) 0xBD); + TEST_VERIFY (mbsinit (&s)); + + /* Last character in the code point range that maps to three code units. */ + u8s = (const char8_t*) u8"\uFFFF"; /* U+FFFF => 0xEF 0xBF 0xBF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) 3); /* 3rd byte processed */ + TEST_COMPARE (buf[0], (char) 0xEF); + TEST_COMPARE (buf[1], (char) 0xBF); + TEST_COMPARE (buf[2], (char) 0xBF); + TEST_VERIFY (mbsinit (&s)); + + /* First character in the code point range that maps to four code units. */ + u8s = (const char8_t*) u8"\U00010000"; /* U+10000 => 0xF0 0x90 0x80 0x80 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) 0); /* 3rd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[3], &s), (size_t) 4); /* 4th byte processed */ + TEST_COMPARE (buf[0], (char) 0xF0); + TEST_COMPARE (buf[1], (char) 0x90); + TEST_COMPARE (buf[2], (char) 0x80); + TEST_COMPARE (buf[3], (char) 0x80); + TEST_VERIFY (mbsinit (&s)); + + /* Last character in the code point range that maps to four code units. */ + u8s = (const char8_t*) u8"\U0010FFFF"; /* U+10FFFF => 0xF4 0x8F 0xBF 0xBF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) 0); /* 3rd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[3], &s), (size_t) 4); /* 4th byte processed */ + TEST_COMPARE (buf[0], (char) 0xF4); + TEST_COMPARE (buf[1], (char) 0x8F); + TEST_COMPARE (buf[2], (char) 0xBF); + TEST_COMPARE (buf[3], (char) 0xBF); + TEST_VERIFY (mbsinit (&s)); + + return 0; +} + +static int +test_big5_hkscs (void) +{ + const char8_t *u8s; + char buf[MB_LEN_MAX]; + mbstate_t s; + + TEST_VERIFY_EXIT (setlocale (LC_ALL, "zh_HK.BIG5-HKSCS") != NULL); + + /* A pair of two byte UTF-8 code unit sequences that map a Unicode code + point and combining character to a single double byte character. */ + u8s = (const char8_t*) u8"\u00CA\u0304"; /* U+00CA U+0304 => 0x88 0x62 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) 0); /* 3rd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[3], &s), (size_t) 2); /* 4th byte processed */ + TEST_COMPARE (buf[0], (char) 0x88); + TEST_COMPARE (buf[1], (char) 0x62); + TEST_VERIFY (mbsinit (&s)); + + /* Another pair of two byte UTF-8 code unit sequences that map a Unicode code + point and combining character to a single double byte character. */ + u8s = (const char8_t*) u8"\u00EA\u030C"; /* U+00EA U+030C => 0x88 0xA5 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (c8rtomb (buf, u8s[0], &s), (size_t) 0); /* 1st byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[1], &s), (size_t) 0); /* 2nd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[2], &s), (size_t) 0); /* 3rd byte processed */ + TEST_COMPARE (c8rtomb (buf, u8s[3], &s), (size_t) 2); /* 4th byte processed */ + TEST_COMPARE (buf[0], (char) 0x88); + TEST_COMPARE (buf[1], (char) 0xA5); + TEST_VERIFY (mbsinit (&s)); + + return 0; +} + +static int +do_test (void) +{ + test_truncated_code_unit_sequence (); + test_invalid_trailing_code_unit_sequence (); + test_lone_trailing_code_units (); + test_overlong_encoding (); + test_surrogate_range (); + test_out_of_range_encoding (); + test_null_output_buffer (); + test_utf8 (); + test_big5_hkscs (); + return 0; +} + +#include diff --git a/wcsmbs/test-char8-type.c b/wcsmbs/test-char8-type.c new file mode 100644 index 0000000000..642c7044ed --- /dev/null +++ b/wcsmbs/test-char8-type.c @@ -0,0 +1,31 @@ +/* Test the char8_t typedef. + Copyright (C) 2022 Free Software Foundation, Inc. + This file is part of the GNU C Library. + + The GNU C Library 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. + + The GNU C 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 + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, see + . */ + +#include + +/* Verify that the char8_t type is recognized. */ +char8_t c8; + +static int +do_test (void) +{ + /* This is a compilation test. */ + return 0; +} + +#include diff --git a/wcsmbs/test-mbrtoc8.c b/wcsmbs/test-mbrtoc8.c new file mode 100644 index 0000000000..c5061635ac --- /dev/null +++ b/wcsmbs/test-mbrtoc8.c @@ -0,0 +1,462 @@ +/* Test mbrtoc8. + Copyright (C) 2022 Free Software Foundation, Inc. + This file is part of the GNU C Library. + + The GNU C Library 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. + + The GNU C 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 + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, see + . */ + +#include +#include +#include +#include +#include +#include +#include + +static int +test_utf8 (void) +{ + const char *mbs; + char8_t buf[1]; + mbstate_t s; + + TEST_VERIFY_EXIT (setlocale (LC_ALL, "de_DE.UTF-8") != NULL); + + /* No inputs. */ + mbs = ""; + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, 0, &s), (size_t) -2); /* no input */ + TEST_VERIFY (mbsinit (&s)); + + /* Null character. */ + mbs = "\x00"; /* 0x00 => U+0000 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 0); /* null byte written */ + mbs += 1; + TEST_COMPARE (buf[0], 0x00); + TEST_VERIFY (mbsinit (&s)); + + /* First non-null character in the code point range that maps to a single + code unit. */ + mbs = "\x01"; /* 0x01 => U+0001 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 1); /* 1st byte processed */ + mbs += 1; + TEST_COMPARE (buf[0], 0x01); + TEST_VERIFY (mbsinit (&s)); + + /* Last character in the code point range that maps to a single code unit. */ + mbs = "\x7F"; /* 0x7F => U+007F */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 1); /* 1st byte processed */ + mbs += 1; + TEST_COMPARE (buf[0], 0x7F); + TEST_VERIFY (mbsinit (&s)); + + /* First character in the code point range that maps to two code units. */ + mbs = "\xC2\x80"; /* 0xC2 0x80 => U+0080 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 2); /* 1st byte written */ + mbs += 2; + TEST_COMPARE (buf[0], 0xC2); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0x80); + TEST_VERIFY (mbsinit (&s)); + + /* Same as last test, but one code unit at a time. */ + mbs = "\xC2\x80"; /* 0xC2 0x80 => U+0080 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) 1); /* 1st byte written */ + mbs += 1; + TEST_COMPARE (buf[0], 0xC2); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0x80); + TEST_VERIFY (mbsinit (&s)); + + /* Last character in the code point range that maps to two code units. */ + mbs = "\xDF\xBF"; /* 0xDF 0xBF => U+07FF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 2); /* 1st byte written */ + mbs += 2; + TEST_COMPARE (buf[0], 0xDF); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0xBF); + TEST_VERIFY (mbsinit (&s)); + + /* Same as last test, but one code unit at a time. */ + mbs = "\xDF\xBF"; /* 0xDF 0xBF => U+07FF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) 1); /* 1st byte written */ + mbs += 1; + TEST_COMPARE (buf[0], 0xDF); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0xBF); + TEST_VERIFY (mbsinit (&s)); + + /* First character in the code point range that maps to three code units. */ + mbs = u8"\xE0\xA0\x80"; /* 0xE0 0xA0 0x80 => U+0800 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 3); /* 1st byte written */ + mbs += 3; + TEST_COMPARE (buf[0], 0xE0); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0xA0); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0x80); + TEST_VERIFY (mbsinit (&s)); + + /* Same as last test, but one code unit at a time. */ + mbs = u8"\xE0\xA0\x80"; /* 0xE0 0xA0 0x80 => U+0800 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) 1); /* 1st byte written */ + mbs += 1; + TEST_COMPARE (buf[0], 0xE0); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0xA0); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0x80); + TEST_VERIFY (mbsinit (&s)); + + /* Last character in the code point range that maps to three code units + before the surrogate code point range. */ + mbs = "\xED\x9F\xBF"; /* 0xED 0x9F 0xBF => U+D7FF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 3); /* 1st byte written */ + mbs += 3; + TEST_COMPARE (buf[0], 0xED); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0x9F); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0xBF); + TEST_VERIFY (mbsinit (&s)); + + /* Same as last test, but one code unit at a time. */ + mbs = "\xED\x9F\xBF"; /* 0xED 0x9F 0xBF => U+D7FF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) 1); /* 1st byte written */ + mbs += 1; + TEST_COMPARE (buf[0], 0xED); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0x9F); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0xBF); + TEST_VERIFY (mbsinit (&s)); + + /* First character in the code point range that maps to three code units + after the surrogate code point range. */ + mbs = "\xEE\x80\x80"; /* 0xEE 0x80 0x80 => U+E000 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 3); /* 1st byte written */ + mbs += 3; + TEST_COMPARE (buf[0], 0xEE); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0x80); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0x80); + TEST_VERIFY (mbsinit (&s)); + + /* Same as last test, but one code unit at a time. */ + mbs = "\xEE\x80\x80"; /* 0xEE 0x80 0x80 => U+E000 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) 1); /* 1st byte written */ + mbs += 1; + TEST_COMPARE (buf[0], 0xEE); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0x80); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0x80); + TEST_VERIFY (mbsinit (&s)); + + /* Not a BOM. */ + mbs = "\xEF\xBB\xBF"; /* 0xEF 0xBB 0xBF => U+FEFF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 3); /* 1st byte written */ + mbs += 3; + TEST_COMPARE (buf[0], 0xEF); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0xBB); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0xBF); + TEST_VERIFY (mbsinit (&s)); + + /* Same as last test, but one code unit at a time. */ + mbs = "\xEF\xBB\xBF"; /* 0xEF 0xBB 0xBF => U+FEFF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) 1); /* 1st byte written */ + mbs += 1; + TEST_COMPARE (buf[0], 0xEF); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0xBB); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0xBF); + TEST_VERIFY (mbsinit (&s)); + + /* Replacement character. */ + mbs = "\xEF\xBF\xBD"; /* 0xEF 0xBF 0xBD => U+FFFD */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 3); /* 1st byte written */ + mbs += 3; + TEST_COMPARE (buf[0], 0xEF); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0xBF); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0xBD); + TEST_VERIFY (mbsinit (&s)); + + /* Same as last test, but one code unit at a time. */ + mbs = "\xEF\xBF\xBD"; /* 0xEF 0xBF 0xBD => U+FFFD */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) 1); /* 1st byte written */ + mbs += 1; + TEST_COMPARE (buf[0], 0xEF); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0xBF); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0xBD); + TEST_VERIFY (mbsinit (&s)); + + /* Last character in the code point range that maps to three code units. */ + mbs = "\xEF\xBF\xBF"; /* 0xEF 0xBF 0xBF => U+FFFF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 3); /* 1st byte processed */ + mbs += 3; + TEST_COMPARE (buf[0], 0xEF); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 2nd byte processed */ + TEST_COMPARE (buf[0], 0xBF); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 3rd byte processed */ + TEST_COMPARE (buf[0], 0xBF); + TEST_VERIFY (mbsinit (&s)); + + /* Same as last test, but one code unit at a time. */ + mbs = "\xEF\xBF\xBF"; /* 0xEF 0xBF 0xBF => U+FFFF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) 1); /* 1st byte written */ + mbs += 1; + TEST_COMPARE (buf[0], 0xEF); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0xBF); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0xBF); + TEST_VERIFY (mbsinit (&s)); + + /* First character in the code point range that maps to four code units. */ + mbs = "\xF0\x90\x80\x80"; /* 0xF0 0x90 0x80 0x80 => U+10000 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 4); /* 1st byte written */ + mbs += 4; + TEST_COMPARE (buf[0], 0xF0); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0x90); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0x80); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 4th byte written */ + TEST_COMPARE (buf[0], 0x80); + TEST_VERIFY (mbsinit (&s)); + + /* Same as last test, but one code unit at a time. */ + mbs = "\xF0\x90\x80\x80"; /* 0xF0 0x90 0x80 0x80 => U+10000 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) 1); /* 1st byte written */ + mbs += 1; + TEST_COMPARE (buf[0], 0xF0); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0x90); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0x80); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 4th byte written */ + TEST_COMPARE (buf[0], 0x80); + TEST_VERIFY (mbsinit (&s)); + + /* Last character in the code point range that maps to four code units. */ + mbs = "\xF4\x8F\xBF\xBF"; /* 0xF4 0x8F 0xBF 0xBF => U+10FFFF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 4); /* 1st byte written */ + mbs += 4; + TEST_COMPARE (buf[0], 0xF4); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0x8F); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0xBF); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 4th byte written */ + TEST_COMPARE (buf[0], 0xBF); + TEST_VERIFY (mbsinit (&s)); + + /* Same as last test, but one code unit at a time. */ + mbs = "\xF4\x8F\xBF\xBF"; /* 0xF4 0x8F 0xBF 0xBF => U+10FFFF */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) 1); /* 1st byte written */ + mbs += 1; + TEST_COMPARE (buf[0], 0xF4); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0x8F); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0xBF); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 4th byte written */ + TEST_COMPARE (buf[0], 0xBF); + TEST_VERIFY (mbsinit (&s)); + + return 0; +} + +static int +test_big5_hkscs (void) +{ + const char *mbs; + char8_t buf[1]; + mbstate_t s; + + TEST_VERIFY_EXIT (setlocale (LC_ALL, "zh_HK.BIG5-HKSCS") != NULL); + + /* A double byte character that maps to a pair of two byte UTF-8 code unit + sequences. */ + mbs = "\x88\x62"; /* 0x88 0x62 => U+00CA U+0304 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 2); /* 1st byte written */ + mbs += 2; + TEST_COMPARE (buf[0], 0xC3); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0x8A); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0xCC); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 4th byte written */ + TEST_COMPARE (buf[0], 0x84); + TEST_VERIFY (mbsinit (&s)); + + /* Same as last test, but one code unit at a time. */ + mbs = "\x88\x62"; /* 0x88 0x62 => U+00CA U+0304 */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) 1); /* 1st byte written */ + mbs += 1; + TEST_COMPARE (buf[0], 0xC3); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0x8A); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0xCC); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 4th byte written */ + TEST_COMPARE (buf[0], 0x84); + TEST_VERIFY (mbsinit (&s)); + + /* Another double byte character that maps to a pair of two byte UTF-8 code + unit sequences. */ + mbs = "\x88\xA5"; /* 0x88 0xA5 => U+00EA U+030C */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) 2); /* 1st byte written */ + mbs += 2; + TEST_COMPARE (buf[0], 0xC3); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0xAA); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0xCC); + TEST_COMPARE (mbrtoc8 (buf, mbs, strlen(mbs)+1, &s), (size_t) -3); /* 4th byte written */ + TEST_COMPARE (buf[0], 0x8C); + TEST_VERIFY (mbsinit (&s)); + + /* Same as last test, but one code unit at a time. */ + mbs = "\x88\xA5"; /* 0x88 0xA5 => U+00EA U+030C */ + memset (buf, 0, sizeof (buf)); + memset (&s, 0, sizeof (s)); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -2); /* incomplete */ + mbs += 1; + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) 1); /* 1st byte written */ + mbs += 1; + TEST_COMPARE (buf[0], 0xC3); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 2nd byte written */ + TEST_COMPARE (buf[0], 0xAA); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 3rd byte written */ + TEST_COMPARE (buf[0], 0xCC); + TEST_COMPARE (mbrtoc8 (buf, mbs, 1, &s), (size_t) -3); /* 4th byte written */ + TEST_COMPARE (buf[0], 0x8C); + TEST_VERIFY (mbsinit (&s)); + + return 0; +} + +static int +do_test (void) +{ + test_utf8 (); + test_big5_hkscs (); + return 0; +} + +#include