From 7314af7d04d3fd4f29fff1f0da648944183bd0d0 Mon Sep 17 00:00:00 2001 From: Ryan Harrison Date: Thu, 27 Jul 2017 14:24:02 -0400 Subject: Rewrite FMLexer to use nullptr for errors This CL rewrites how FMLexer returns errors, instead of having a flag that gets flipped and needs to be checked, it now returns nullptr for NextToken() when an error occurs. The Lexer's behaviour has also been changed to only return nullptr once an error has occurred, instead of advancing the lexing on further calls. FMParse now checks the returned value from the lexer instead of testing the error flag on the parser object. For any operation that might cause the error state of the parser to change, i.e. consuming a token, an error check has been added. In the event this check fails the related function returns nullptr. This will cause the parse to short circuit and exit. BUG=pdfium:814 Change-Id: I669012c4732c18d13009be7cd7bf1ae682950904 Reviewed-on: https://pdfium-review.googlesource.com/8950 Commit-Queue: Ryan Harrison Reviewed-by: (OOO Jul 28 - Aug 8) dsinclair Reviewed-by: Tom Sepez --- xfa/fxfa/fm2js/cxfa_fmlexer.cpp | 136 +++++++++++++++++++++------------------- 1 file changed, 71 insertions(+), 65 deletions(-) (limited to 'xfa/fxfa/fm2js/cxfa_fmlexer.cpp') diff --git a/xfa/fxfa/fm2js/cxfa_fmlexer.cpp b/xfa/fxfa/fm2js/cxfa_fmlexer.cpp index 5ae8a6f40b..d217587e66 100644 --- a/xfa/fxfa/fm2js/cxfa_fmlexer.cpp +++ b/xfa/fxfa/fm2js/cxfa_fmlexer.cpp @@ -156,12 +156,15 @@ CXFA_FMLexer::CXFA_FMLexer(const CFX_WideStringC& wsFormCalc) CXFA_FMLexer::~CXFA_FMLexer() {} -CXFA_FMToken* CXFA_FMLexer::NextToken() { +std::unique_ptr CXFA_FMLexer::NextToken() { + if (m_lexer_error) + return nullptr; + m_token = pdfium::MakeUnique(m_current_line); while (m_cursor <= m_end && *m_cursor) { if (!IsFormCalcCharacter(*m_cursor)) { - m_lexer_error = true; - return m_token.get(); + RaiseError(); + return nullptr; } switch (*m_cursor) { @@ -180,7 +183,7 @@ CXFA_FMToken* CXFA_FMLexer::NextToken() { case '"': { m_token->m_type = TOKstring; AdvanceForString(); - return m_token.get(); + return std::move(m_token); } case '0': case '1': @@ -194,119 +197,119 @@ CXFA_FMToken* CXFA_FMLexer::NextToken() { case '9': { m_token->m_type = TOKnumber; AdvanceForNumber(); - return m_token.get(); + return std::move(m_token); } case '=': ++m_cursor; if (m_cursor > m_end) { m_token->m_type = TOKassign; - return m_token.get(); + return std::move(m_token); } - if (IsFormCalcCharacter(*m_cursor)) { - if (*m_cursor == '=') { - m_token->m_type = TOKeq; - ++m_cursor; - } else { - m_token->m_type = TOKassign; - } + if (!IsFormCalcCharacter(*m_cursor)) { + RaiseError(); + return nullptr; + } + if (*m_cursor == '=') { + m_token->m_type = TOKeq; + ++m_cursor; } else { - m_lexer_error = true; + m_token->m_type = TOKassign; } - return m_token.get(); + return std::move(m_token); case '<': ++m_cursor; if (m_cursor > m_end) { m_token->m_type = TOKlt; - return m_token.get(); + return std::move(m_token); } - if (IsFormCalcCharacter(*m_cursor)) { - if (*m_cursor == '=') { - m_token->m_type = TOKle; - ++m_cursor; - } else if (*m_cursor == '>') { - m_token->m_type = TOKne; - ++m_cursor; - } else { - m_token->m_type = TOKlt; - } + if (!IsFormCalcCharacter(*m_cursor)) { + RaiseError(); + return nullptr; + } + if (*m_cursor == '=') { + m_token->m_type = TOKle; + ++m_cursor; + } else if (*m_cursor == '>') { + m_token->m_type = TOKne; + ++m_cursor; } else { - m_lexer_error = true; + m_token->m_type = TOKlt; } - return m_token.get(); + return std::move(m_token); case '>': ++m_cursor; if (m_cursor > m_end) { m_token->m_type = TOKgt; - return m_token.get(); + return std::move(m_token); } - if (IsFormCalcCharacter(*m_cursor)) { - if (*m_cursor == '=') { - m_token->m_type = TOKge; - ++m_cursor; - } else { - m_token->m_type = TOKgt; - } + if (!IsFormCalcCharacter(*m_cursor)) { + RaiseError(); + return nullptr; + } + if (*m_cursor == '=') { + m_token->m_type = TOKge; + ++m_cursor; } else { - m_lexer_error = true; + m_token->m_type = TOKgt; } - return m_token.get(); + return std::move(m_token); case ',': m_token->m_type = TOKcomma; ++m_cursor; - return m_token.get(); + return std::move(m_token); case '(': m_token->m_type = TOKlparen; ++m_cursor; - return m_token.get(); + return std::move(m_token); case ')': m_token->m_type = TOKrparen; ++m_cursor; - return m_token.get(); + return std::move(m_token); case '[': m_token->m_type = TOKlbracket; ++m_cursor; - return m_token.get(); + return std::move(m_token); case ']': m_token->m_type = TOKrbracket; ++m_cursor; - return m_token.get(); + return std::move(m_token); case '&': ++m_cursor; m_token->m_type = TOKand; - return m_token.get(); + return std::move(m_token); case '|': ++m_cursor; m_token->m_type = TOKor; - return m_token.get(); + return std::move(m_token); case '+': ++m_cursor; m_token->m_type = TOKplus; - return m_token.get(); + return std::move(m_token); case '-': ++m_cursor; m_token->m_type = TOKminus; - return m_token.get(); + return std::move(m_token); case '*': ++m_cursor; m_token->m_type = TOKmul; - return m_token.get(); + return std::move(m_token); case '/': { ++m_cursor; if (m_cursor > m_end) { m_token->m_type = TOKdiv; - return m_token.get(); + return std::move(m_token); } if (!IsFormCalcCharacter(*m_cursor)) { - m_lexer_error = true; - return m_token.get(); + RaiseError(); + return nullptr; } if (*m_cursor != '/') { m_token->m_type = TOKdiv; - return m_token.get(); + return std::move(m_token); } AdvanceForComment(); break; @@ -315,12 +318,12 @@ CXFA_FMToken* CXFA_FMLexer::NextToken() { ++m_cursor; if (m_cursor > m_end) { m_token->m_type = TOKdot; - return m_token.get(); + return std::move(m_token); } if (!IsFormCalcCharacter(*m_cursor)) { - m_lexer_error = true; - return m_token.get(); + RaiseError(); + return nullptr; } if (*m_cursor == '.') { @@ -339,7 +342,7 @@ CXFA_FMToken* CXFA_FMLexer::NextToken() { } else { m_token->m_type = TOKdot; } - return m_token.get(); + return std::move(m_token); case 0x09: case 0x0B: case 0x0C: @@ -348,11 +351,11 @@ CXFA_FMToken* CXFA_FMLexer::NextToken() { break; default: { if (!IsInitialIdentifierCharacter(*m_cursor)) { - m_lexer_error = true; - return m_token.get(); + RaiseError(); + return nullptr; } AdvanceForIdentifier(); - return m_token.get(); + return std::move(m_token); } } } @@ -360,7 +363,7 @@ CXFA_FMToken* CXFA_FMLexer::NextToken() { // If there isn't currently a token type then mark it EOF. if (m_token->m_type == TOKreserver) m_token->m_type = TOKeof; - return m_token.get(); + return std::move(m_token); } void CXFA_FMLexer::AdvanceForNumber() { @@ -369,7 +372,7 @@ void CXFA_FMLexer::AdvanceForNumber() { if (m_cursor) wcstod(const_cast(m_cursor), &end); if (end && FXSYS_iswalpha(*end)) { - m_lexer_error = true; + RaiseError(); return; } @@ -406,8 +409,7 @@ void CXFA_FMLexer::AdvanceForString() { } // Didn't find the end of the string. - m_token->m_string = CFX_WideStringC(start, (m_cursor - start)); - m_lexer_error = true; + RaiseError(); } void CXFA_FMLexer::AdvanceForIdentifier() { @@ -415,8 +417,7 @@ void CXFA_FMLexer::AdvanceForIdentifier() { ++m_cursor; while (m_cursor <= m_end && *m_cursor) { if (!IsFormCalcCharacter(*m_cursor)) { - m_token->m_string = CFX_WideStringC(start, (m_cursor - start)); - m_lexer_error = true; + RaiseError(); return; } @@ -432,6 +433,11 @@ void CXFA_FMLexer::AdvanceForIdentifier() { void CXFA_FMLexer::AdvanceForComment() { m_cursor++; while (m_cursor <= m_end && *m_cursor) { + if (!IsFormCalcCharacter(*m_cursor)) { + RaiseError(); + return; + } + if (*m_cursor == L'\r') { ++m_cursor; return; -- cgit v1.2.3