From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wr1-x436.google.com (mail-wr1-x436.google.com [IPv6:2a00:1450:4864:20::436]) by sourceware.org (Postfix) with ESMTPS id E86DA3857704 for ; Tue, 30 Jan 2024 12:11:54 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org E86DA3857704 Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=embecosm.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=embecosm.com ARC-Filter: OpenARC Filter v1.0.0 sourceware.org E86DA3857704 Authentication-Results: server2.sourceware.org; arc=none smtp.remote-ip=2a00:1450:4864:20::436 ARC-Seal: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1706616764; cv=none; b=ZsaZ/z5ioeF5wbJvOph0Q4Vk/1H2Q2N9n5bjbRIi6ANWaBCbEgrsTV7jsmyeI2q4yCTPjaYYtQFfuGLobS2fa+UyAxqF+nCrQE0Gsd+GPyqSo+fxZ/Drj6Z4MPGKzurkVjt+zt6L0CEiZuaO1K/3z555Vg8Odq4jwhGCP8SsURM= ARC-Message-Signature: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1706616764; c=relaxed/simple; bh=ZN0rvn8in8ZMbV5vZetI+gc+H51uej32P4tuU6SOCIo=; h=DKIM-Signature:From:To:Subject:Date:Message-ID:MIME-Version; b=PxqAwz2e0uWHObruIZCBj+rwlfq7dxEh7wgeEDIj0kRz6WK8mWBc5SsL5MwCTqiiH8NGPZl914QJht6T8dUd/JMcXHY8zsVqQyKvXYPrUpfTj3z2tCkpbnyle6LAV+c2ej97NXlfA1P+H2xflaQ2W3E8Qb6maamIwUTUICj4LhI= ARC-Authentication-Results: i=1; server2.sourceware.org Received: by mail-wr1-x436.google.com with SMTP id ffacd0b85a97d-33af4a0beb3so1012926f8f.2 for ; Tue, 30 Jan 2024 04:11:54 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=embecosm.com; s=google; t=1706616713; x=1707221513; darn=gcc.gnu.org; h=content-transfer-encoding:mime-version:reply-to:references :in-reply-to:message-id:date:subject:cc:to:from:from:to:cc:subject :date:message-id:reply-to; bh=ImOjUA18ADzQV3sCjjzF2siEn4ZR/3JrQmRxSl8A3jA=; b=VJqSEiYh/m0Z0k8HhBpgMiIw8fS32RBq/5VXYZPw4sJlbAVRWrq1TEx2S8sx5Z9jp3 +7iAVXPMmTRQYpXaZecYdB4N1aLWlP+THkU0yJbt2ZqATQ74qfUNMCFvlRAvfhHxhK4h vWQh9Ox6Wr8KoX0I1hGU8r+XzguRUythpyTcnEpFUJXMu73NFJaQ3vPkW513LylVt2o0 fg97z4VBBfhGoRoDsuMBK7SXfV2hMNkShemn5pHsS0AlBZVrRRS9s+iabgLhu8U1Ig1T anC+cr/mBKmMnL4BKH01rgBu+5gRsExsEEz6ew/lngkKf+OASIuu9gm/PWmcERQHBHkt iMCQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1706616713; x=1707221513; h=content-transfer-encoding:mime-version:reply-to:references :in-reply-to:message-id:date:subject:cc:to:from:x-gm-message-state :from:to:cc:subject:date:message-id:reply-to; bh=ImOjUA18ADzQV3sCjjzF2siEn4ZR/3JrQmRxSl8A3jA=; b=ocbhy4jemEsqeGItUGetaSh/qcwA9wrnSsZA7ONJPzq3Wm654O4YEPsViFHuNhQSAz SY8Iu37kHEqeQNstKmsmsRPu3Z1EbNP9Q/payCQ2dHXaKRnMNcn2V9UWkLe/WVJMUN9I m0KgtSyduAXprI9tRUx43FlD+wv2wVkGIRnQ83xNNdn614pZYvc0Ez4PN7h06H5pzwkn 4T6ZG5moNyd3Rc++NyC9zd99UAJj1ri4434J9aCqzNEKbBQDhICcmqyhPhlR5dIGNW58 4liNWPVrXAlx44cDRgb5FWgUVWwN6Hns/FMFuDXa6fRfgCjGD2vskqKXGPdDlfpOtIAO KEVQ== X-Gm-Message-State: AOJu0YzXk6IIBuJ7lUpVcXKu/q6Bl+v8WAUWM7a2KGLvE5IrQ3CTt/wG A4bmUCOfiIyKhJ55w2mpeWL/Lp34dOOdlaBLkVgDNgFhUResv6IxbKbXB0EIlaosVTXyy5aXO8y k9g== X-Google-Smtp-Source: AGHT+IFAFp7a6cPlE+p/I6AR5DySMYELf1pNh6JlOgmNppDdDr1QEkX6D2eVIXXpP8rIgBwckDH+xg== X-Received: by 2002:a05:6000:1542:b0:33a:ed2c:fea0 with SMTP id 2-20020a056000154200b0033aed2cfea0mr4326901wry.1.1706616712904; Tue, 30 Jan 2024 04:11:52 -0800 (PST) Received: from platypus.localdomain ([62.23.166.218]) by smtp.gmail.com with ESMTPSA id f9-20020a056000036900b00339307d9d31sm10569894wrf.112.2024.01.30.04.11.52 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 30 Jan 2024 04:11:52 -0800 (PST) From: arthur.cohen@embecosm.com To: gcc-patches@gcc.gnu.org Cc: gcc-rust@gcc.gnu.org, Nirmal Patel Subject: [COMMITTED 088/101] gccrs: Handle newlines during string parsing while lexing Date: Tue, 30 Jan 2024 13:07:44 +0100 Message-ID: <20240130121026.807464-91-arthur.cohen@embecosm.com> X-Mailer: git-send-email 2.42.1 In-Reply-To: <20240130121026.807464-2-arthur.cohen@embecosm.com> References: <20240130121026.807464-2-arthur.cohen@embecosm.com> Reply-To: arthur.cohen@embecosm.com MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Spam-Status: No, score=-14.2 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,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org List-Id: From: Nirmal Patel If newline strings are encountered while lexing, the lexer now handles newline characters by incrementing current line number. This provides correct line number when displaying errors. If the lexer encounters end of file before string end, then it will use the start of the string as the location to an report error. gcc/rust/ChangeLog: * lex/rust-lex.cc (Lexer::parse_byte_string): Handle newline while parsing byte strings (Lexer::parse_string): Handle newline while parsing strings Signed-off-by: Nirmal Patel --- gcc/rust/lex/rust-lex.cc | 40 ++++++++++++++----- gcc/testsuite/rust/compile/issue-2187.rs | 11 +++++ .../rust/execute/torture/issue-2187.rs | 23 +++++++++++ 3 files changed, 63 insertions(+), 11 deletions(-) create mode 100644 gcc/testsuite/rust/compile/issue-2187.rs create mode 100644 gcc/testsuite/rust/execute/torture/issue-2187.rs diff --git a/gcc/rust/lex/rust-lex.cc b/gcc/rust/lex/rust-lex.cc index 5bff2d9125c..6fc336d97e0 100644 --- a/gcc/rust/lex/rust-lex.cc +++ b/gcc/rust/lex/rust-lex.cc @@ -1766,13 +1766,15 @@ Lexer::parse_byte_string (location_t loc) std::string str; str.reserve (16); // some sensible default - int length = 1; current_char = peek_input (); + const location_t string_begin_locus = get_current_location (); + while (current_char != '"' && !current_char.is_eof ()) { if (current_char == '\\') { + int length = 1; auto escape_length_pair = parse_escape ('"'); char output_char = std::get<0> (escape_length_pair); @@ -1784,18 +1786,25 @@ Lexer::parse_byte_string (location_t loc) if (output_char != 0 || !std::get<2> (escape_length_pair)) str += output_char; + current_column += length; + continue; } - length++; + current_column++; + if (current_char.value == '\n') + { + current_line++; + current_column = 1; + // tell line_table that new line starts + start_line (current_line, max_column_hint); + } str += current_char; skip_input (); current_char = peek_input (); } - current_column += length; - if (current_char == '"') { current_column++; @@ -1805,7 +1814,7 @@ Lexer::parse_byte_string (location_t loc) } else if (current_char.is_eof ()) { - rust_error_at (get_current_location (), "unended byte string literal"); + rust_error_at (string_begin_locus, "unended byte string literal"); return Token::make (END_OF_FILE, get_current_location ()); } else @@ -1996,14 +2005,17 @@ Lexer::parse_string (location_t loc) std::string str; str.reserve (16); // some sensible default - int length = 1; current_char = peek_input (); + const location_t string_begin_locus = get_current_location (); + // FIXME: This fails if the input ends. How do we check for EOF? while (current_char.value != '"' && !current_char.is_eof ()) { if (current_char.value == '\\') { + int length = 1; + // parse escape auto utf8_escape_pair = parse_utf8_escape (); current_char = std::get<0> (utf8_escape_pair); @@ -2016,21 +2028,28 @@ Lexer::parse_string (location_t loc) if (current_char != Codepoint (0) || !std::get<2> (utf8_escape_pair)) str += current_char.as_string (); + current_column += length; + // FIXME: should remove this but can't. // `parse_utf8_escape` does not update `current_char` correctly. current_char = peek_input (); continue; } - length++; + current_column++; + if (current_char.value == '\n') + { + current_line++; + current_column = 1; + // tell line_table that new line starts + start_line (current_line, max_column_hint); + } str += current_char; skip_input (); current_char = peek_input (); } - current_column += length; - if (current_char.value == '"') { current_column++; @@ -2040,7 +2059,7 @@ Lexer::parse_string (location_t loc) } else if (current_char.is_eof ()) { - rust_error_at (get_current_location (), "unended string literal"); + rust_error_at (string_begin_locus, "unended string literal"); return Token::make (END_OF_FILE, get_current_location ()); } else @@ -2049,7 +2068,6 @@ Lexer::parse_string (location_t loc) } str.shrink_to_fit (); - loc += length - 1; return Token::make_string (loc, std::move (str)); } diff --git a/gcc/testsuite/rust/compile/issue-2187.rs b/gcc/testsuite/rust/compile/issue-2187.rs new file mode 100644 index 00000000000..deef417a668 --- /dev/null +++ b/gcc/testsuite/rust/compile/issue-2187.rs @@ -0,0 +1,11 @@ +const A: &'static u8 = b" +"; +const B: &'static str = b" +"; +const C: &'static u8 = " +"; +const D: &'static str = " +"; +ERROR_TIME +// { dg-error "unrecognised token" "" { target *-*-* } .-1 } +// { dg-error "failed to parse item in crate" "" { target *-*-* } .-2 } diff --git a/gcc/testsuite/rust/execute/torture/issue-2187.rs b/gcc/testsuite/rust/execute/torture/issue-2187.rs new file mode 100644 index 00000000000..b5312575041 --- /dev/null +++ b/gcc/testsuite/rust/execute/torture/issue-2187.rs @@ -0,0 +1,23 @@ +/* { dg-output "L1\n\L2\nL3\nL4" } */ +extern "C" { + fn printf(s: *const i8, ...); +} + +fn main() -> i32 { + let A = b"L1 +L2\0"; + let B = "L3 +L4\0"; + + unsafe { + let a = "%s\n\0"; + let b = a as *const str; + let c = b as *const i8; + + printf(c, A); + printf(c, B); + } + + 0 +} + -- 2.42.1