From 0b7b8162cab67d58915d4561a52d70e7208233c1 Mon Sep 17 00:00:00 2001 From: chriseth Date: Thu, 6 Sep 2018 11:05:35 +0200 Subject: This fixes several bugs with regards to line breaks and comments: - any unicode line break (line feed, vertical tab, form feed, carriage return, NEL, LS and PS) is considered to terminate a single-line comment. The line break itself is considered to be the next token after the comment, leading to a parser error if it is not an ascii character (i.e. for NEL, LS and PS). - unterminated multiline comments are considered illegal tokens - '/** /' is considered an unterminated multiline comment (previously, whitespace was allowed before the last '/' --- test/libsolidity/SolidityScanner.cpp | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'test') diff --git a/test/libsolidity/SolidityScanner.cpp b/test/libsolidity/SolidityScanner.cpp index f2e756bb..6b7f559a 100644 --- a/test/libsolidity/SolidityScanner.cpp +++ b/test/libsolidity/SolidityScanner.cpp @@ -500,6 +500,14 @@ BOOST_AUTO_TEST_CASE(invalid_hex_literal_nonhex_string) BOOST_CHECK_EQUAL(scanner.next(), Token::Illegal); } +BOOST_AUTO_TEST_CASE(invalid_multiline_comment_close) +{ + // This used to parse as "comment", "identifier" + Scanner scanner(CharStream("/** / x")); + BOOST_CHECK_EQUAL(scanner.currentToken(), Token::Illegal); + BOOST_CHECK_EQUAL(scanner.next(), Token::EOS); +} + BOOST_AUTO_TEST_SUITE_END() -- cgit From 6a40048aa43abdd17fa6e8b74e4c32127f6c1840 Mon Sep 17 00:00:00 2001 From: chriseth Date: Thu, 6 Sep 2018 16:42:39 +0200 Subject: Tests. --- test/libsolidity/SolidityScanner.cpp | 98 ++++++++++++++++++++++++++++++++++++ 1 file changed, 98 insertions(+) (limited to 'test') diff --git a/test/libsolidity/SolidityScanner.cpp b/test/libsolidity/SolidityScanner.cpp index 6b7f559a..3a210f94 100644 --- a/test/libsolidity/SolidityScanner.cpp +++ b/test/libsolidity/SolidityScanner.cpp @@ -23,6 +23,8 @@ #include #include +using namespace std; + namespace dev { namespace solidity @@ -508,6 +510,102 @@ BOOST_AUTO_TEST_CASE(invalid_multiline_comment_close) BOOST_CHECK_EQUAL(scanner.next(), Token::EOS); } +BOOST_AUTO_TEST_CASE(multiline_doc_comment_at_eos) +{ + // This used to parse as "whitespace" + Scanner scanner(CharStream("/**")); + BOOST_CHECK_EQUAL(scanner.currentToken(), Token::Illegal); + BOOST_CHECK_EQUAL(scanner.next(), Token::EOS); +} + +BOOST_AUTO_TEST_CASE(multiline_comment_at_eos) +{ + Scanner scanner(CharStream("/*")); + BOOST_CHECK_EQUAL(scanner.currentToken(), Token::Illegal); + BOOST_CHECK_EQUAL(scanner.next(), Token::EOS); +} + +BOOST_AUTO_TEST_CASE(regular_line_break_in_single_line_comment) +{ + for (auto const& nl: {"\r", "\n"}) + { + Scanner scanner(CharStream("// abc " + string(nl) + " def ")); + BOOST_CHECK_EQUAL(scanner.currentCommentLiteral(), ""); + BOOST_CHECK_EQUAL(scanner.currentToken(), Token::Identifier); + BOOST_CHECK_EQUAL(scanner.currentLiteral(), "def"); + BOOST_CHECK_EQUAL(scanner.next(), Token::EOS); + } +} + +BOOST_AUTO_TEST_CASE(irregular_line_breaks_in_single_line_comment) +{ + for (auto const& nl: {"\v", "\f", "\xE2\x80\xA8", "\xE2\x80\xA9"}) + { + Scanner scanner(CharStream("// abc " + string(nl) + " def ")); + BOOST_CHECK_EQUAL(scanner.currentCommentLiteral(), ""); + BOOST_CHECK_EQUAL(scanner.currentToken(), Token::Illegal); + for (size_t i = 0; i < string(nl).size() - 1; i++) + BOOST_CHECK_EQUAL(scanner.next(), Token::Illegal); + BOOST_CHECK_EQUAL(scanner.next(), Token::Identifier); + BOOST_CHECK_EQUAL(scanner.currentLiteral(), "def"); + BOOST_CHECK_EQUAL(scanner.next(), Token::EOS); + } +} + +BOOST_AUTO_TEST_CASE(regular_line_breaks_in_single_line_doc_comment) +{ + for (auto const& nl: {"\r", "\n"}) + { + Scanner scanner(CharStream("/// abc " + string(nl) + " def ")); + BOOST_CHECK_EQUAL(scanner.currentCommentLiteral(), "abc "); + BOOST_CHECK_EQUAL(scanner.currentToken(), Token::Identifier); + BOOST_CHECK_EQUAL(scanner.currentLiteral(), "def"); + BOOST_CHECK_EQUAL(scanner.next(), Token::EOS); + } +} + +BOOST_AUTO_TEST_CASE(irregular_line_breaks_in_single_line_doc_comment) +{ + for (auto const& nl: {"\v", "\f", "\xE2\x80\xA8", "\xE2\x80\xA9"}) + { + Scanner scanner(CharStream("/// abc " + string(nl) + " def ")); + BOOST_CHECK_EQUAL(scanner.currentCommentLiteral(), "abc "); + BOOST_CHECK_EQUAL(scanner.currentToken(), Token::Illegal); + for (size_t i = 0; i < string(nl).size() - 1; i++) + BOOST_CHECK_EQUAL(scanner.next(), Token::Illegal); + BOOST_CHECK_EQUAL(scanner.next(), Token::Identifier); + BOOST_CHECK_EQUAL(scanner.currentLiteral(), "def"); + BOOST_CHECK_EQUAL(scanner.next(), Token::EOS); + } +} + +BOOST_AUTO_TEST_CASE(regular_line_breaks_in_strings) +{ + for (auto const& nl: {"\n", "\r"}) + { + Scanner scanner(CharStream("\"abc " + string(nl) + " def\"")); + BOOST_CHECK_EQUAL(scanner.currentToken(), Token::Illegal); + BOOST_CHECK_EQUAL(scanner.next(), Token::Identifier); + BOOST_CHECK_EQUAL(scanner.currentLiteral(), "def"); + BOOST_CHECK_EQUAL(scanner.next(), Token::Illegal); + BOOST_CHECK_EQUAL(scanner.next(), Token::EOS); + } +} + +BOOST_AUTO_TEST_CASE(irregular_line_breaks_in_strings) +{ + for (auto const& nl: {"\v", "\f", "\xE2\x80\xA8", "\xE2\x80\xA9"}) + { + Scanner scanner(CharStream("\"abc " + string(nl) + " def\"")); + BOOST_CHECK_EQUAL(scanner.currentToken(), Token::Illegal); + for (size_t i = 0; i < string(nl).size(); i++) + BOOST_CHECK_EQUAL(scanner.next(), Token::Illegal); + BOOST_CHECK_EQUAL(scanner.next(), Token::Identifier); + BOOST_CHECK_EQUAL(scanner.currentLiteral(), "def"); + BOOST_CHECK_EQUAL(scanner.next(), Token::Illegal); + BOOST_CHECK_EQUAL(scanner.next(), Token::EOS); + } +} BOOST_AUTO_TEST_SUITE_END() -- cgit