From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by sourceware.org (Postfix) with ESMTPS id 88A4E3858D35 for ; Mon, 28 Aug 2023 14:00:54 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 88A4E3858D35 Authentication-Results: sourceware.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=redhat.com DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1693231254; h=from:from:reply-to:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type:in-reply-to:in-reply-to: references:references; bh=B4hEDdeBKIwLZfhp2z62aJFf7kGKtrKxrZBAhqlND8g=; b=TTcP6VkxF3gJFfjrheH3sY0xXqBko0XzJHZXB7LH8MLImofO8Mr4VSuxDgYAZRjKRusGUF oQ/uKfBPY4jxexFqu/zxZL85j8H1AAQ1IqEK7BdK+KWsrn1MoGTTI0IiXGv5u+DQZ47E5R atPLjWppSj7j6M7VwzMtjGE620DCYUk= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-612-lhjSLRD8N0WpDFT5zmm_Sg-1; Mon, 28 Aug 2023 10:00:50 -0400 X-MC-Unique: lhjSLRD8N0WpDFT5zmm_Sg-1 Received: from smtp.corp.redhat.com (int-mx01.intmail.prod.int.rdu2.redhat.com [10.11.54.1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 57B0385CBF8 for ; Mon, 28 Aug 2023 14:00:50 +0000 (UTC) Received: from tucnak.zalov.cz (unknown [10.45.224.16]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 1E11540C2063; Mon, 28 Aug 2023 14:00:50 +0000 (UTC) Received: from tucnak.zalov.cz (localhost [127.0.0.1]) by tucnak.zalov.cz (8.17.1/8.17.1) with ESMTPS id 37SE0mBh1504098 (version=TLSv1.3 cipher=TLS_AES_256_GCM_SHA384 bits=256 verify=NOT); Mon, 28 Aug 2023 16:00:48 +0200 Received: (from jakub@localhost) by tucnak.zalov.cz (8.17.1/8.17.1/Submit) id 37SE0mSN1504097; Mon, 28 Aug 2023 16:00:48 +0200 Date: Mon, 28 Aug 2023 16:00:48 +0200 From: Jakub Jelinek To: Jason Merrill Cc: gcc-patches@gcc.gnu.org Subject: [PATCH] libcpp, v2: Small incremental patch for P1854R4 [PR110341] Message-ID: Reply-To: Jakub Jelinek References: MIME-Version: 1.0 In-Reply-To: X-Scanned-By: MIMEDefang 3.1 on 10.11.54.1 X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-Type: text/plain; charset=us-ascii Content-Disposition: inline X-Spam-Status: No, score=-0.9 required=5.0 tests=BAYES_00,DKIMWL_WL_HIGH,DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,RCVD_IN_DNSWL_NONE,RCVD_IN_MSPIKE_H4,RCVD_IN_MSPIKE_WL,SCC_10_SHORT_WORD_LINES,SCC_20_SHORT_WORD_LINES,SCC_5_SHORT_WORD_LINES,SPF_HELO_NONE,SPF_NONE,TXREP autolearn=no autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org List-Id: Hi! Sorry, testing revealed an unused uchar *outbuf; declaration breaking the build, here is the same patch with that one line removed, bootstrapped/regtested on x86_64-linux and i686-linux (on top of the earlier POR110341 patch). On Sat, Aug 26, 2023 at 01:11:06PM +0200, Jakub Jelinek via Gcc-patches wrote: > The following incremental patch to the PR110341 posted patch uses > a special conversion callback instead of conversion from host charset > (UTF-8/UTF-EBCDIC) to UTF-32, and also ignores all diagnostics from the > second cpp_interpret_string which should just count chars. The UTF-EBCDIC > is untested, but simple enough that it should just work. 2023-08-28 Jakub Jelinek PR c++/110341 * charset.cc (one_count_chars, convert_count_chars): New functions. (narrow_str_to_charconst): Call cpp_interpret_string with type rather than CPP_STRING32, temporarily override for that call pfile->cb.diagnostic to noop_diagnostic_cb and pfile->narrow_cset_desc.func to convert_count_chars and just compare str.len against str2.len. --- libcpp/charset.cc.jj 2023-08-25 17:14:14.098733396 +0200 +++ libcpp/charset.cc 2023-08-28 12:57:44.858858994 +0200 @@ -446,6 +446,73 @@ one_utf16_to_utf8 (iconv_t bigend, const return 0; } + +/* Special routine which just counts number of characters in the + string, what exactly is stored into the output doesn't matter + as long as it is one uchar per character. */ + +static inline int +one_count_chars (iconv_t, const uchar **inbufp, size_t *inbytesleftp, + uchar **outbufp, size_t *outbytesleftp) +{ + cppchar_t s = 0; + int rval; + + /* Check for space first, since we know exactly how much we need. */ + if (*outbytesleftp < 1) + return E2BIG; + +#if HOST_CHARSET == HOST_CHARSET_ASCII + rval = one_utf8_to_cppchar (inbufp, inbytesleftp, &s); + if (rval) + return rval; +#else + if (*inbytesleftp < 1) + return EINVAL; + static const uchar utf_ebcdic_map[256] = { + /* See table 4 in http://unicode.org/reports/tr16/tr16-7.2.html */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 1, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 1, 1, 1, 1, 1, + 1, 9, 9, 9, 9, 9, 9, 9, 9, 9, 1, 1, 1, 1, 1, 1, + 1, 1, 9, 9, 9, 9, 9, 9, 9, 9, 9, 1, 1, 1, 1, 1, + 9, 9, 9, 9, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, + 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, + 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, + 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 1, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 1, 3, 3, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 3, 3, 3, 3, 3, 3, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 3, 3, 4, 4, 4, 4, + 1, 4, 1, 1, 1, 1, 1, 1, 1, 1, 4, 4, 4, 5, 5, 5, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 5, 6, 6, 7, 7, 0 + }; + rval = utf_ebcdic_map[**inbufp]; + if (rval == 9) + return EILSEQ; + if (rval == 0) + rval = 1; + if (rval >= 2) + { + if (*inbytesleftp < rval) + return EINVAL; + for (int i = 1; i < rval; ++i) + if (utf_ebcdic_map[(*inbufp)[i]] != 9) + return EILSEQ; + } + *inbytesleftp -= rval; + *inbufp += rval; +#endif + + **outbufp = ' '; + + *outbufp += 1; + *outbytesleftp -= 1; + return 0; +} + + /* Helper routine for the next few functions. The 'const' on one_conversion means that we promise not to modify what function is pointed to, which lets the inliner see through it. */ @@ -529,6 +596,15 @@ convert_utf32_utf8 (iconv_t cd, const uc return conversion_loop (one_utf32_to_utf8, cd, from, flen, to); } +/* Magic conversion which just counts characters from input, so + only to->len is significant. */ +static bool +convert_count_chars (iconv_t cd, const uchar *from, + size_t flen, struct _cpp_strbuf *to) +{ + return conversion_loop (one_count_chars, cd, from, flen, to); +} + /* Identity conversion, used when we have no alternative. */ static bool convert_no_conversion (iconv_t cd ATTRIBUTE_UNUSED, @@ -2623,15 +2699,22 @@ narrow_str_to_charconst (cpp_reader *pfi ill-formed. We need to count the number of c-chars and compare that to str.len. */ cpp_string str2 = { 0, 0 }; - if (cpp_interpret_string (pfile, &token->val.str, 1, &str2, - CPP_STRING32)) + bool (*saved_diagnostic_handler) (cpp_reader *, enum cpp_diagnostic_level, + enum cpp_warning_reason, rich_location *, + const char *, va_list *) + ATTRIBUTE_FPTR_PRINTF(5,0); + saved_diagnostic_handler = pfile->cb.diagnostic; + pfile->cb.diagnostic = noop_diagnostic_cb; + convert_f save_func = pfile->narrow_cset_desc.func; + pfile->narrow_cset_desc.func = convert_count_chars; + bool ret = cpp_interpret_string (pfile, &token->val.str, 1, &str2, type); + pfile->narrow_cset_desc.func = save_func; + pfile->cb.diagnostic = saved_diagnostic_handler; + if (ret) { - size_t width32 = converter_for_type (pfile, CPP_STRING32).width; - size_t nbwc = width32 / width; - size_t len = str2.len / nbwc; if (str2.text != token->val.str.text) free ((void *)str2.text); - if (str.len > len) + if (str.len > str2.len) { diagnosed = cpp_error (pfile, CPP_DL_PEDWARN, Jakub