X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=utils%2FFileCheck%2FFileCheck.cpp;h=37c7874aa20a4238ed13948eeaadbb0697963786;hb=8d4021c83142bfaf65b234b625ea2897a1e06e03;hp=cd76d44043086016320ea674070c65da099df4bd;hpb=7112c86fc208145334aaa04812c794ce6feef416;p=oota-llvm.git diff --git a/utils/FileCheck/FileCheck.cpp b/utils/FileCheck/FileCheck.cpp index cd76d440430..37c7874aa20 100644 --- a/utils/FileCheck/FileCheck.cpp +++ b/utils/FileCheck/FileCheck.cpp @@ -16,16 +16,22 @@ // //===----------------------------------------------------------------------===// +#include "llvm/ADT/OwningPtr.h" +#include "llvm/ADT/SmallString.h" +#include "llvm/ADT/StringExtras.h" +#include "llvm/ADT/StringMap.h" #include "llvm/Support/CommandLine.h" #include "llvm/Support/MemoryBuffer.h" #include "llvm/Support/PrettyStackTrace.h" #include "llvm/Support/Regex.h" +#include "llvm/Support/Signals.h" #include "llvm/Support/SourceMgr.h" #include "llvm/Support/raw_ostream.h" -#include "llvm/System/Signals.h" -#include "llvm/ADT/SmallString.h" -#include "llvm/ADT/StringMap.h" +#include "llvm/Support/system_error.h" #include +#include +#include +#include using namespace llvm; static cl::opt @@ -50,6 +56,16 @@ NoCanonicalizeWhiteSpace("strict-whitespace", class Pattern { SMLoc PatternLoc; + /// MatchEOF - When set, this pattern only matches the end of file. This is + /// used for trailing CHECK-NOTs. + bool MatchEOF; + + /// MatchNot + bool MatchNot; + + /// MatchDag + bool MatchDag; + /// FixedStr - If non-empty, this pattern is a fixed string match with the /// specified fixed string. StringRef FixedStr; @@ -57,23 +73,33 @@ class Pattern { /// RegEx - If non-empty, this is a regex pattern. std::string RegExStr; + /// \brief Contains the number of line this pattern is in. + unsigned LineNumber; + /// VariableUses - Entries in this vector map to uses of a variable in the /// pattern, e.g. "foo[[bar]]baz". In this case, the RegExStr will contain /// "foobaz" and we'll get an entry in this vector that tells us to insert the /// value of bar at offset 3. std::vector > VariableUses; - /// VariableDefs - Entries in this vector map to definitions of a variable in - /// the pattern, e.g. "foo[[bar:.*]]baz". In this case, the RegExStr will - /// contain "foo(.*)baz" and VariableDefs will contain the pair "bar",1. The - /// index indicates what parenthesized value captures the variable value. - std::vector > VariableDefs; + /// VariableDefs - Maps definitions of variables to their parenthesized + /// capture numbers. + /// E.g. for the pattern "foo[[bar:.*]]baz", VariableDefs will map "bar" to 1. + std::map VariableDefs; public: - Pattern() { } + Pattern(bool matchEOF = false) + : MatchEOF(matchEOF), MatchNot(false), MatchDag(false) { } + + /// getLoc - Return the location in source code. + SMLoc getLoc() const { return PatternLoc; } - bool ParsePattern(StringRef PatternStr, SourceMgr &SM); + /// ParsePattern - Parse the given string into the Pattern. SM provides the + /// SourceMgr used for error reports, and LineNumber is the line number in + /// the input file from which the pattern string was read. + /// Returns true in case of an error, false otherwise. + bool ParsePattern(StringRef PatternStr, SourceMgr &SM, unsigned LineNumber); /// Match - Match the pattern string against the input buffer Buffer. This /// returns the position that is matched or npos if there is no match. If @@ -89,19 +115,42 @@ public: void PrintFailureInfo(const SourceMgr &SM, StringRef Buffer, const StringMap &VariableTable) const; + bool hasVariable() const { return !(VariableUses.empty() && + VariableDefs.empty()); } + + void setMatchNot(bool Not) { MatchNot = Not; } + bool getMatchNot() const { return MatchNot; } + + void setMatchDag(bool Dag) { MatchDag = Dag; } + bool getMatchDag() const { return MatchDag; } + private: static void AddFixedStringToRegEx(StringRef FixedStr, std::string &TheStr); - bool AddRegExToRegEx(StringRef RegExStr, unsigned &CurParen, SourceMgr &SM); + bool AddRegExToRegEx(StringRef RS, unsigned &CurParen, SourceMgr &SM); + void AddBackrefToRegEx(unsigned BackrefNum); /// ComputeMatchDistance - Compute an arbitrary estimate for the quality of /// matching this pattern at the start of \arg Buffer; a distance of zero /// should correspond to a perfect match. unsigned ComputeMatchDistance(StringRef Buffer, const StringMap &VariableTable) const; + + /// \brief Evaluates expression and stores the result to \p Value. + /// \return true on success. false when the expression has invalid syntax. + bool EvaluateExpression(StringRef Expr, std::string &Value) const; + + /// \brief Finds the closing sequence of a regex variable usage or + /// definition. Str has to point in the beginning of the definition + /// (right after the opening sequence). + /// \return offset of the closing sequence within Str, or npos if it was not + /// found. + size_t FindRegexVarEnd(StringRef Str); }; -bool Pattern::ParsePattern(StringRef PatternStr, SourceMgr &SM) { +bool Pattern::ParsePattern(StringRef PatternStr, SourceMgr &SM, + unsigned LineNumber) { + this->LineNumber = LineNumber; PatternLoc = SMLoc::getFromPointer(PatternStr.data()); // Ignore trailing whitespace. @@ -111,8 +160,9 @@ bool Pattern::ParsePattern(StringRef PatternStr, SourceMgr &SM) { // Check that there is something on the line. if (PatternStr.empty()) { - SM.PrintMessage(PatternLoc, "found empty check string with prefix '" + - CheckPrefix+":'", "error"); + SM.PrintMessage(PatternLoc, SourceMgr::DK_Error, + "found empty check string with prefix '" + + CheckPrefix+":'"); return true; } @@ -125,26 +175,34 @@ bool Pattern::ParsePattern(StringRef PatternStr, SourceMgr &SM) { } // Paren value #0 is for the fully matched string. Any new parenthesized - // values add from their. + // values add from there. unsigned CurParen = 1; // Otherwise, there is at least one regex piece. Build up the regex pattern // by escaping scary characters in fixed strings, building up one big regex. while (!PatternStr.empty()) { // RegEx matches. - if (PatternStr.size() >= 2 && - PatternStr[0] == '{' && PatternStr[1] == '{') { - - // Otherwise, this is the start of a regex match. Scan for the }}. + if (PatternStr.startswith("{{")) { + // This is the start of a regex match. Scan for the }}. size_t End = PatternStr.find("}}"); if (End == StringRef::npos) { SM.PrintMessage(SMLoc::getFromPointer(PatternStr.data()), - "found start of regex string with no end '}}'", "error"); + SourceMgr::DK_Error, + "found start of regex string with no end '}}'"); return true; } + // Enclose {{}} patterns in parens just like [[]] even though we're not + // capturing the result for any purpose. This is required in case the + // expression contains an alternation like: CHECK: abc{{x|z}}def. We + // want this to turn into: "abc(x|z)def" not "abcx|zdef". + RegExStr += '('; + ++CurParen; + if (AddRegExToRegEx(PatternStr.substr(2, End-2), CurParen, SM)) return true; + RegExStr += ')'; + PatternStr = PatternStr.substr(End+2); continue; } @@ -154,55 +212,82 @@ bool Pattern::ParsePattern(StringRef PatternStr, SourceMgr &SM) { // second form is [[foo]] which is a reference to foo. The variable name // itself must be of the form "[a-zA-Z_][0-9a-zA-Z_]*", otherwise we reject // it. This is to catch some common errors. - if (PatternStr.size() >= 2 && - PatternStr[0] == '[' && PatternStr[1] == '[') { - // Verify that it is terminated properly. - size_t End = PatternStr.find("]]"); + if (PatternStr.startswith("[[")) { + // Find the closing bracket pair ending the match. End is going to be an + // offset relative to the beginning of the match string. + size_t End = FindRegexVarEnd(PatternStr.substr(2)); + if (End == StringRef::npos) { SM.PrintMessage(SMLoc::getFromPointer(PatternStr.data()), - "invalid named regex reference, no ]] found", "error"); + SourceMgr::DK_Error, + "invalid named regex reference, no ]] found"); return true; } - StringRef MatchStr = PatternStr.substr(2, End-2); - PatternStr = PatternStr.substr(End+2); + StringRef MatchStr = PatternStr.substr(2, End); + PatternStr = PatternStr.substr(End+4); // Get the regex name (e.g. "foo"). size_t NameEnd = MatchStr.find(':'); StringRef Name = MatchStr.substr(0, NameEnd); if (Name.empty()) { - SM.PrintMessage(SMLoc::getFromPointer(Name.data()), - "invalid name in named regex: empty name", "error"); + SM.PrintMessage(SMLoc::getFromPointer(Name.data()), SourceMgr::DK_Error, + "invalid name in named regex: empty name"); return true; } - // Verify that the name is well formed. - for (unsigned i = 0, e = Name.size(); i != e; ++i) - if (Name[i] != '_' && - (Name[i] < 'a' || Name[i] > 'z') && - (Name[i] < 'A' || Name[i] > 'Z') && - (Name[i] < '0' || Name[i] > '9')) { + // Verify that the name/expression is well formed. FileCheck currently + // supports @LINE, @LINE+number, @LINE-number expressions. The check here + // is relaxed, more strict check is performed in \c EvaluateExpression. + bool IsExpression = false; + for (unsigned i = 0, e = Name.size(); i != e; ++i) { + if (i == 0 && Name[i] == '@') { + if (NameEnd != StringRef::npos) { + SM.PrintMessage(SMLoc::getFromPointer(Name.data()), + SourceMgr::DK_Error, + "invalid name in named regex definition"); + return true; + } + IsExpression = true; + continue; + } + if (Name[i] != '_' && !isalnum(Name[i]) && + (!IsExpression || (Name[i] != '+' && Name[i] != '-'))) { SM.PrintMessage(SMLoc::getFromPointer(Name.data()+i), - "invalid name in named regex", "error"); + SourceMgr::DK_Error, "invalid name in named regex"); return true; } + } // Name can't start with a digit. - if (isdigit(Name[0])) { - SM.PrintMessage(SMLoc::getFromPointer(Name.data()), - "invalid name in named regex", "error"); + if (isdigit(static_cast(Name[0]))) { + SM.PrintMessage(SMLoc::getFromPointer(Name.data()), SourceMgr::DK_Error, + "invalid name in named regex"); return true; } // Handle [[foo]]. if (NameEnd == StringRef::npos) { - VariableUses.push_back(std::make_pair(Name, RegExStr.size())); + // Handle variables that were defined earlier on the same line by + // emitting a backreference. + if (VariableDefs.find(Name) != VariableDefs.end()) { + unsigned VarParenNum = VariableDefs[Name]; + if (VarParenNum < 1 || VarParenNum > 9) { + SM.PrintMessage(SMLoc::getFromPointer(Name.data()), + SourceMgr::DK_Error, + "Can't back-reference more than 9 variables"); + return true; + } + AddBackrefToRegEx(VarParenNum); + } else { + VariableUses.push_back(std::make_pair(Name, RegExStr.size())); + } continue; } // Handle [[foo:.*]]. - VariableDefs.push_back(std::make_pair(Name, CurParen)); + VariableDefs[Name] = CurParen; RegExStr += '('; ++CurParen; @@ -218,7 +303,6 @@ bool Pattern::ParsePattern(StringRef PatternStr, SourceMgr &SM) { FixedMatchEnd = std::min(FixedMatchEnd, PatternStr.find("[[")); AddFixedStringToRegEx(PatternStr.substr(0, FixedMatchEnd), RegExStr); PatternStr = PatternStr.substr(FixedMatchEnd); - continue; } return false; @@ -251,26 +335,57 @@ void Pattern::AddFixedStringToRegEx(StringRef FixedStr, std::string &TheStr) { } } -bool Pattern::AddRegExToRegEx(StringRef RegexStr, unsigned &CurParen, +bool Pattern::AddRegExToRegEx(StringRef RS, unsigned &CurParen, SourceMgr &SM) { - Regex R(RegexStr); + Regex R(RS); std::string Error; if (!R.isValid(Error)) { - SM.PrintMessage(SMLoc::getFromPointer(RegexStr.data()), - "invalid regex: " + Error, "error"); + SM.PrintMessage(SMLoc::getFromPointer(RS.data()), SourceMgr::DK_Error, + "invalid regex: " + Error); return true; } - RegExStr += RegexStr.str(); + RegExStr += RS.str(); CurParen += R.getNumMatches(); return false; } +void Pattern::AddBackrefToRegEx(unsigned BackrefNum) { + assert(BackrefNum >= 1 && BackrefNum <= 9 && "Invalid backref number"); + std::string Backref = std::string("\\") + + std::string(1, '0' + BackrefNum); + RegExStr += Backref; +} + +bool Pattern::EvaluateExpression(StringRef Expr, std::string &Value) const { + // The only supported expression is @LINE([\+-]\d+)? + if (!Expr.startswith("@LINE")) + return false; + Expr = Expr.substr(StringRef("@LINE").size()); + int Offset = 0; + if (!Expr.empty()) { + if (Expr[0] == '+') + Expr = Expr.substr(1); + else if (Expr[0] != '-') + return false; + if (Expr.getAsInteger(10, Offset)) + return false; + } + Value = llvm::itostr(LineNumber + Offset); + return true; +} + /// Match - Match the pattern string against the input buffer Buffer. This /// returns the position that is matched or npos if there is no match. If /// there is a match, the size of the matched string is returned in MatchLen. size_t Pattern::Match(StringRef Buffer, size_t &MatchLen, StringMap &VariableTable) const { + // If this is the EOF pattern, match it immediately. + if (MatchEOF) { + MatchLen = 0; + return Buffer.size(); + } + // If this is a fixed string pattern, just match it now. if (!FixedStr.empty()) { MatchLen = FixedStr.size(); @@ -288,15 +403,21 @@ size_t Pattern::Match(StringRef Buffer, size_t &MatchLen, unsigned InsertOffset = 0; for (unsigned i = 0, e = VariableUses.size(); i != e; ++i) { - StringMap::iterator it = - VariableTable.find(VariableUses[i].first); - // If the variable is undefined, return an error. - if (it == VariableTable.end()) - return StringRef::npos; - - // Look up the value and escape it so that we can plop it into the regex. std::string Value; - AddFixedStringToRegEx(it->second, Value); + + if (VariableUses[i].first[0] == '@') { + if (!EvaluateExpression(VariableUses[i].first, Value)) + return StringRef::npos; + } else { + StringMap::iterator it = + VariableTable.find(VariableUses[i].first); + // If the variable is undefined, return an error. + if (it == VariableTable.end()) + return StringRef::npos; + + // Look up the value and escape it so that we can plop it into the regex. + AddFixedStringToRegEx(it->second, Value); + } // Plop it into the regex at the adjusted offset. TmpStr.insert(TmpStr.begin()+VariableUses[i].second+InsertOffset, @@ -318,10 +439,11 @@ size_t Pattern::Match(StringRef Buffer, size_t &MatchLen, StringRef FullMatch = MatchInfo[0]; // If this defines any variables, remember their values. - for (unsigned i = 0, e = VariableDefs.size(); i != e; ++i) { - assert(VariableDefs[i].second < MatchInfo.size() && - "Internal paren error"); - VariableTable[VariableDefs[i].first] = MatchInfo[VariableDefs[i].second]; + for (std::map::const_iterator I = VariableDefs.begin(), + E = VariableDefs.end(); + I != E; ++I) { + assert(I->second < MatchInfo.size() && "Internal paren error"); + VariableTable[I->first] = MatchInfo[I->second]; } MatchLen = FullMatch.size(); @@ -352,23 +474,35 @@ void Pattern::PrintFailureInfo(const SourceMgr &SM, StringRef Buffer, // variable values. if (!VariableUses.empty()) { for (unsigned i = 0, e = VariableUses.size(); i != e; ++i) { - StringRef Var = VariableUses[i].first; - StringMap::const_iterator it = VariableTable.find(Var); SmallString<256> Msg; raw_svector_ostream OS(Msg); - - // Check for undefined variable references. - if (it == VariableTable.end()) { - OS << "uses undefined variable \""; - OS.write_escaped(Var) << "\"";; + StringRef Var = VariableUses[i].first; + if (Var[0] == '@') { + std::string Value; + if (EvaluateExpression(Var, Value)) { + OS << "with expression \""; + OS.write_escaped(Var) << "\" equal to \""; + OS.write_escaped(Value) << "\""; + } else { + OS << "uses incorrect expression \""; + OS.write_escaped(Var) << "\""; + } } else { - OS << "with variable \""; - OS.write_escaped(Var) << "\" equal to \""; - OS.write_escaped(it->second) << "\""; + StringMap::const_iterator it = VariableTable.find(Var); + + // Check for undefined variable references. + if (it == VariableTable.end()) { + OS << "uses undefined variable \""; + OS.write_escaped(Var) << "\""; + } else { + OS << "with variable \""; + OS.write_escaped(Var) << "\" equal to \""; + OS.write_escaped(it->second) << "\""; + } } - SM.PrintMessage(SMLoc::getFromPointer(Buffer.data()), OS.str(), "note", - /*ShowLine=*/false); + SM.PrintMessage(SMLoc::getFromPointer(Buffer.data()), SourceMgr::DK_Note, + OS.str()); } } @@ -406,13 +540,47 @@ void Pattern::PrintFailureInfo(const SourceMgr &SM, StringRef Buffer, // line. if (Best && Best != StringRef::npos && BestQuality < 50) { SM.PrintMessage(SMLoc::getFromPointer(Buffer.data() + Best), - "possible intended match here", "note"); + SourceMgr::DK_Note, "possible intended match here"); // FIXME: If we wanted to be really friendly we would show why the match // failed, as it can be hard to spot simple one character differences. } } +size_t Pattern::FindRegexVarEnd(StringRef Str) { + // Offset keeps track of the current offset within the input Str + size_t Offset = 0; + // [...] Nesting depth + size_t BracketDepth = 0; + + while (!Str.empty()) { + if (Str.startswith("]]") && BracketDepth == 0) + return Offset; + if (Str[0] == '\\') { + // Backslash escapes the next char within regexes, so skip them both. + Str = Str.substr(2); + Offset += 2; + } else { + switch (Str[0]) { + default: + break; + case '[': + BracketDepth++; + break; + case ']': + assert(BracketDepth > 0 && "Invalid regex"); + BracketDepth--; + break; + } + Str = Str.substr(1); + Offset++; + } + } + + return StringRef::npos; +} + + //===----------------------------------------------------------------------===// // Check Strings. //===----------------------------------------------------------------------===// @@ -429,25 +597,56 @@ struct CheckString { /// to a CHECK: directive. bool IsCheckNext; - /// NotStrings - These are all of the strings that are disallowed from + /// IsCheckLabel - This is true if this is a CHECK-LABEL: directive (as + /// opposed to a CHECK: directive. + bool IsCheckLabel; + + /// DagNotStrings - These are all of the strings that are disallowed from /// occurring between this match string and the previous one (or start of /// file). - std::vector > NotStrings; + std::vector DagNotStrings; + + CheckString(const Pattern &P, SMLoc L, bool isCheckNext, bool isCheckLabel) + : Pat(P), Loc(L), IsCheckNext(isCheckNext), IsCheckLabel(isCheckLabel) {} + + /// Check - Match check string and its "not strings" and/or "dag strings". + size_t Check(const SourceMgr &SM, StringRef Buffer, bool IsLabel, + size_t &MatchLen, StringMap &VariableTable) const; - CheckString(const Pattern &P, SMLoc L, bool isCheckNext) - : Pat(P), Loc(L), IsCheckNext(isCheckNext) {} + /// CheckNext - Verify there is a single line in the given buffer. + bool CheckNext(const SourceMgr &SM, StringRef Buffer) const; + + /// CheckNot - Verify there's no "not strings" in the given buffer. + bool CheckNot(const SourceMgr &SM, StringRef Buffer, + const std::vector &NotStrings, + StringMap &VariableTable) const; + + /// CheckDag - Match "dag strings" and their mixed "not strings". + size_t CheckDag(const SourceMgr &SM, StringRef Buffer, + std::vector &NotStrings, + StringMap &VariableTable) const; }; -/// CanonicalizeInputFile - Remove duplicate horizontal space from the specified -/// memory buffer, free it, and return a new one. -static MemoryBuffer *CanonicalizeInputFile(MemoryBuffer *MB) { +/// Canonicalize whitespaces in the input file. Line endings are replaced +/// with UNIX-style '\n'. +/// +/// \param PreserveHorizontal Don't squash consecutive horizontal whitespace +/// characters to a single space. +static MemoryBuffer *CanonicalizeInputFile(MemoryBuffer *MB, + bool PreserveHorizontal) { SmallString<128> NewFile; NewFile.reserve(MB->getBufferSize()); for (const char *Ptr = MB->getBufferStart(), *End = MB->getBufferEnd(); Ptr != End; ++Ptr) { - // If C is not a horizontal whitespace, skip it. - if (*Ptr != ' ' && *Ptr != '\t') { + // Eliminate trailing dosish \r. + if (Ptr <= End - 2 && Ptr[0] == '\r' && Ptr[1] == '\n') { + continue; + } + + // If current char is not a horizontal whitespace or if horizontal + // whitespace canonicalization is disabled, dump it to output as is. + if (PreserveHorizontal || (*Ptr != ' ' && *Ptr != '\t')) { NewFile.push_back(*Ptr); continue; } @@ -470,55 +669,80 @@ static MemoryBuffer *CanonicalizeInputFile(MemoryBuffer *MB) { /// ReadCheckFile - Read the check file, which specifies the sequence of /// expected strings. The strings are added to the CheckStrings vector. +/// Returns true in case of an error, false otherwise. static bool ReadCheckFile(SourceMgr &SM, std::vector &CheckStrings) { - // Open the check file, and tell SourceMgr about it. - std::string ErrorStr; - MemoryBuffer *F = - MemoryBuffer::getFileOrSTDIN(CheckFilename.c_str(), &ErrorStr); - if (F == 0) { + OwningPtr File; + if (error_code ec = + MemoryBuffer::getFileOrSTDIN(CheckFilename, File)) { errs() << "Could not open check file '" << CheckFilename << "': " - << ErrorStr << '\n'; + << ec.message() << '\n'; return true; } // If we want to canonicalize whitespace, strip excess whitespace from the - // buffer containing the CHECK lines. - if (!NoCanonicalizeWhiteSpace) - F = CanonicalizeInputFile(F); + // buffer containing the CHECK lines. Remove DOS style line endings. + MemoryBuffer *F = + CanonicalizeInputFile(File.take(), NoCanonicalizeWhiteSpace); SM.AddNewSourceBuffer(F, SMLoc()); // Find all instances of CheckPrefix followed by : in the file. StringRef Buffer = F->getBuffer(); + std::vector DagNotMatches; - std::vector > NotMatches; + // LineNumber keeps track of the line on which CheckPrefix instances are + // found. + unsigned LineNumber = 1; while (1) { // See if Prefix occurs in the memory buffer. - Buffer = Buffer.substr(Buffer.find(CheckPrefix)); - + size_t PrefixLoc = Buffer.find(CheckPrefix); // If we didn't find a match, we're done. - if (Buffer.empty()) + if (PrefixLoc == StringRef::npos) break; - const char *CheckPrefixStart = Buffer.data(); + LineNumber += Buffer.substr(0, PrefixLoc).count('\n'); + + // Keep the charcter before our prefix so we can validate that we have + // found our prefix, and account for cases when PrefixLoc is 0. + Buffer = Buffer.substr(std::min(PrefixLoc-1, PrefixLoc)); + + const char *CheckPrefixStart = Buffer.data() + (PrefixLoc == 0 ? 0 : 1); // When we find a check prefix, keep track of whether we find CHECK: or // CHECK-NEXT: - bool IsCheckNext = false, IsCheckNot = false; + bool IsCheckNext = false, IsCheckNot = false, IsCheckDag = false, + IsCheckLabel = false; + + // Make sure we have actually found our prefix, and not a word containing + // our prefix. + if (PrefixLoc != 0 && (isalnum(Buffer[0]) || + Buffer[0] == '-' || + Buffer[0] == '_')) { + Buffer = Buffer.substr(CheckPrefix.size()); + continue; + } // Verify that the : is present after the prefix. if (Buffer[CheckPrefix.size()] == ':') { Buffer = Buffer.substr(CheckPrefix.size()+1); } else if (Buffer.size() > CheckPrefix.size()+6 && memcmp(Buffer.data()+CheckPrefix.size(), "-NEXT:", 6) == 0) { - Buffer = Buffer.substr(CheckPrefix.size()+7); + Buffer = Buffer.substr(CheckPrefix.size()+6); IsCheckNext = true; } else if (Buffer.size() > CheckPrefix.size()+5 && memcmp(Buffer.data()+CheckPrefix.size(), "-NOT:", 5) == 0) { - Buffer = Buffer.substr(CheckPrefix.size()+6); + Buffer = Buffer.substr(CheckPrefix.size()+5); IsCheckNot = true; + } else if (Buffer.size() > CheckPrefix.size()+5 && + memcmp(Buffer.data()+CheckPrefix.size(), "-DAG:", 5) == 0) { + Buffer = Buffer.substr(CheckPrefix.size()+5); + IsCheckDag = true; + } else if (Buffer.size() > CheckPrefix.size()+7 && + memcmp(Buffer.data()+CheckPrefix.size(), "-LABEL:", 7) == 0) { + Buffer = Buffer.substr(CheckPrefix.size()+7); + IsCheckLabel = true; } else { Buffer = Buffer.substr(1); continue; @@ -536,33 +760,53 @@ static bool ReadCheckFile(SourceMgr &SM, // Parse the pattern. Pattern P; - if (P.ParsePattern(Buffer.substr(0, EOL), SM)) + if (P.ParsePattern(Buffer.substr(0, EOL), SM, LineNumber)) return true; - Buffer = Buffer.substr(EOL); + // Verify that CHECK-LABEL lines do not define or use variables + if (IsCheckLabel && P.hasVariable()) { + SM.PrintMessage(SMLoc::getFromPointer(CheckPrefixStart), + SourceMgr::DK_Error, + "found '"+CheckPrefix+"-LABEL:' with variable definition" + " or use"); + return true; + } + P.setMatchNot(IsCheckNot); + P.setMatchDag(IsCheckDag); + + Buffer = Buffer.substr(EOL); // Verify that CHECK-NEXT lines have at least one CHECK line before them. if (IsCheckNext && CheckStrings.empty()) { SM.PrintMessage(SMLoc::getFromPointer(CheckPrefixStart), + SourceMgr::DK_Error, "found '"+CheckPrefix+"-NEXT:' without previous '"+ - CheckPrefix+ ": line", "error"); + CheckPrefix+ ": line"); return true; } - // Handle CHECK-NOT. - if (IsCheckNot) { - NotMatches.push_back(std::make_pair(SMLoc::getFromPointer(Buffer.data()), - P)); + // Handle CHECK-DAG/-NOT. + if (IsCheckDag || IsCheckNot) { + DagNotMatches.push_back(P); continue; } - // Okay, add the string we captured to the output vector and move on. CheckStrings.push_back(CheckString(P, PatternLoc, - IsCheckNext)); - std::swap(NotMatches, CheckStrings.back().NotStrings); + IsCheckNext, + IsCheckLabel)); + std::swap(DagNotMatches, CheckStrings.back().DagNotStrings); + } + + // Add an EOF pattern for any trailing CHECK-DAG/-NOTs. + if (!DagNotMatches.empty()) { + CheckStrings.push_back(CheckString(Pattern(true), + SMLoc::getFromPointer(Buffer.data()), + false, + false)); + std::swap(DagNotMatches, CheckStrings.back().DagNotStrings); } if (CheckStrings.empty()) { @@ -571,31 +815,31 @@ static bool ReadCheckFile(SourceMgr &SM, return true; } - if (!NotMatches.empty()) { - errs() << "error: '" << CheckPrefix - << "-NOT:' not supported after last check line.\n"; - return true; - } - return false; } -static void PrintCheckFailed(const SourceMgr &SM, const CheckString &CheckStr, - StringRef Buffer, +static void PrintCheckFailed(const SourceMgr &SM, const SMLoc &Loc, + const Pattern &Pat, StringRef Buffer, StringMap &VariableTable) { // Otherwise, we have an error, emit an error message. - SM.PrintMessage(CheckStr.Loc, "expected string not found in input", - "error"); + SM.PrintMessage(Loc, SourceMgr::DK_Error, + "expected string not found in input"); // Print the "scanning from here" line. If the current position is at the // end of a line, advance to the start of the next line. Buffer = Buffer.substr(Buffer.find_first_not_of(" \t\n\r")); - SM.PrintMessage(SMLoc::getFromPointer(Buffer.data()), "scanning from here", - "note"); + SM.PrintMessage(SMLoc::getFromPointer(Buffer.data()), SourceMgr::DK_Note, + "scanning from here"); // Allow the pattern to print additional information if desired. - CheckStr.Pat.PrintFailureInfo(SM, Buffer, VariableTable); + Pat.PrintFailureInfo(SM, Buffer, VariableTable); +} + +static void PrintCheckFailed(const SourceMgr &SM, const CheckString &CheckStr, + StringRef Buffer, + StringMap &VariableTable) { + PrintCheckFailed(SM, CheckStr.Loc, CheckStr.Pat, Buffer, VariableTable); } /// CountNumNewlinesBetween - Count the number of newlines in the specified @@ -618,11 +862,199 @@ static unsigned CountNumNewlinesBetween(StringRef Range) { } } +size_t CheckString::Check(const SourceMgr &SM, StringRef Buffer, + bool IsLabel, size_t &MatchLen, + StringMap &VariableTable) const { + size_t LastPos = 0; + std::vector NotStrings; + + if (!IsLabel) { + // Match "dag strings" (with mixed "not strings" if any). + LastPos = CheckDag(SM, Buffer, NotStrings, VariableTable); + if (LastPos == StringRef::npos) + return StringRef::npos; + } + + // Match itself from the last position after matching CHECK-DAG. + StringRef MatchBuffer = Buffer.substr(LastPos); + size_t MatchPos = Pat.Match(MatchBuffer, MatchLen, VariableTable); + if (MatchPos == StringRef::npos) { + PrintCheckFailed(SM, *this, MatchBuffer, VariableTable); + return StringRef::npos; + } + MatchPos += LastPos; + + if (!IsLabel) { + StringRef SkippedRegion = Buffer.substr(LastPos, MatchPos); + + // If this check is a "CHECK-NEXT", verify that the previous match was on + // the previous line (i.e. that there is one newline between them). + if (CheckNext(SM, SkippedRegion)) + return StringRef::npos; + + // If this match had "not strings", verify that they don't exist in the + // skipped region. + if (CheckNot(SM, SkippedRegion, NotStrings, VariableTable)) + return StringRef::npos; + } + + return MatchPos; +} + +bool CheckString::CheckNext(const SourceMgr &SM, StringRef Buffer) const { + if (!IsCheckNext) + return false; + + // Count the number of newlines between the previous match and this one. + assert(Buffer.data() != + SM.getMemoryBuffer( + SM.FindBufferContainingLoc( + SMLoc::getFromPointer(Buffer.data())))->getBufferStart() && + "CHECK-NEXT can't be the first check in a file"); + + unsigned NumNewLines = CountNumNewlinesBetween(Buffer); + + if (NumNewLines == 0) { + SM.PrintMessage(Loc, SourceMgr::DK_Error, CheckPrefix+ + "-NEXT: is on the same line as previous match"); + SM.PrintMessage(SMLoc::getFromPointer(Buffer.end()), + SourceMgr::DK_Note, "'next' match was here"); + SM.PrintMessage(SMLoc::getFromPointer(Buffer.data()), SourceMgr::DK_Note, + "previous match ended here"); + return true; + } + + if (NumNewLines != 1) { + SM.PrintMessage(Loc, SourceMgr::DK_Error, CheckPrefix+ + "-NEXT: is not on the line after the previous match"); + SM.PrintMessage(SMLoc::getFromPointer(Buffer.end()), + SourceMgr::DK_Note, "'next' match was here"); + SM.PrintMessage(SMLoc::getFromPointer(Buffer.data()), SourceMgr::DK_Note, + "previous match ended here"); + return true; + } + + return false; +} + +bool CheckString::CheckNot(const SourceMgr &SM, StringRef Buffer, + const std::vector &NotStrings, + StringMap &VariableTable) const { + for (unsigned ChunkNo = 0, e = NotStrings.size(); + ChunkNo != e; ++ChunkNo) { + const Pattern *Pat = NotStrings[ChunkNo]; + assert(Pat->getMatchNot() && "Expect CHECK-NOT!"); + + size_t MatchLen = 0; + size_t Pos = Pat->Match(Buffer, MatchLen, VariableTable); + + if (Pos == StringRef::npos) continue; + + SM.PrintMessage(SMLoc::getFromPointer(Buffer.data()+Pos), + SourceMgr::DK_Error, + CheckPrefix+"-NOT: string occurred!"); + SM.PrintMessage(Pat->getLoc(), SourceMgr::DK_Note, + CheckPrefix+"-NOT: pattern specified here"); + return true; + } + + return false; +} + +size_t CheckString::CheckDag(const SourceMgr &SM, StringRef Buffer, + std::vector &NotStrings, + StringMap &VariableTable) const { + if (DagNotStrings.empty()) + return 0; + + size_t LastPos = 0; + size_t StartPos = LastPos; + + for (unsigned ChunkNo = 0, e = DagNotStrings.size(); + ChunkNo != e; ++ChunkNo) { + const Pattern &Pat = DagNotStrings[ChunkNo]; + + assert((Pat.getMatchDag() ^ Pat.getMatchNot()) && + "Invalid CHECK-DAG or CHECK-NOT!"); + + if (Pat.getMatchNot()) { + NotStrings.push_back(&Pat); + continue; + } + + assert(Pat.getMatchDag() && "Expect CHECK-DAG!"); + + size_t MatchLen = 0, MatchPos; + + // CHECK-DAG always matches from the start. + StringRef MatchBuffer = Buffer.substr(StartPos); + MatchPos = Pat.Match(MatchBuffer, MatchLen, VariableTable); + // With a group of CHECK-DAGs, a single mismatching means the match on + // that group of CHECK-DAGs fails immediately. + if (MatchPos == StringRef::npos) { + PrintCheckFailed(SM, Pat.getLoc(), Pat, MatchBuffer, VariableTable); + return StringRef::npos; + } + // Re-calc it as the offset relative to the start of the original string. + MatchPos += StartPos; + + if (!NotStrings.empty()) { + if (MatchPos < LastPos) { + // Reordered? + SM.PrintMessage(SMLoc::getFromPointer(Buffer.data() + MatchPos), + SourceMgr::DK_Error, + CheckPrefix+"-DAG: found a match of CHECK-DAG" + " reordering across a CHECK-NOT"); + SM.PrintMessage(SMLoc::getFromPointer(Buffer.data() + LastPos), + SourceMgr::DK_Note, + CheckPrefix+"-DAG: the farthest match of CHECK-DAG" + " is found here"); + SM.PrintMessage(NotStrings[0]->getLoc(), SourceMgr::DK_Note, + CheckPrefix+"-NOT: the crossed pattern specified" + " here"); + SM.PrintMessage(Pat.getLoc(), SourceMgr::DK_Note, + CheckPrefix+"-DAG: the reordered pattern specified" + " here"); + return StringRef::npos; + } + // All subsequent CHECK-DAGs should be matched from the farthest + // position of all precedent CHECK-DAGs (including this one.) + StartPos = LastPos; + // If there's CHECK-NOTs between two CHECK-DAGs or from CHECK to + // CHECK-DAG, verify that there's no 'not' strings occurred in that + // region. + StringRef SkippedRegion = Buffer.substr(LastPos, MatchPos); + if (CheckNot(SM, SkippedRegion, NotStrings, VariableTable)) + return StringRef::npos; + // Clear "not strings". + NotStrings.clear(); + } + + // Update the last position with CHECK-DAG matches. + LastPos = std::max(MatchPos + MatchLen, LastPos); + } + + return LastPos; +} + +bool ValidateCheckPrefix() { + // The check prefix must contain only alphanumeric, hyphens and underscores. + Regex prefixValidator("^[a-zA-Z0-9_-]*$"); + return prefixValidator.match(CheckPrefix); +} + int main(int argc, char **argv) { sys::PrintStackTraceOnErrorSignal(); PrettyStackTraceProgram X(argc, argv); cl::ParseCommandLineOptions(argc, argv); + if (!ValidateCheckPrefix()) { + errs() << "Supplied check-prefix is invalid! Prefixes must start with a " + "letter and contain only alphanumeric characters, hyphens and " + "underscores\n"; + return 2; + } + SourceMgr SM; // Read the expected strings from the check file. @@ -631,18 +1063,23 @@ int main(int argc, char **argv) { return 2; // Open the file to check and add it to SourceMgr. - std::string ErrorStr; - MemoryBuffer *F = - MemoryBuffer::getFileOrSTDIN(InputFilename.c_str(), &ErrorStr); - if (F == 0) { + OwningPtr File; + if (error_code ec = + MemoryBuffer::getFileOrSTDIN(InputFilename, File)) { errs() << "Could not open input file '" << InputFilename << "': " - << ErrorStr << '\n'; - return true; + << ec.message() << '\n'; + return 2; + } + + if (File->getBufferSize() == 0) { + errs() << "FileCheck error: '" << InputFilename << "' is empty.\n"; + return 2; } // Remove duplicate spaces in the input file if requested. - if (!NoCanonicalizeWhiteSpace) - F = CanonicalizeInputFile(F); + // Remove DOS style line endings. + MemoryBuffer *F = + CanonicalizeInputFile(File.take(), NoCanonicalizeWhiteSpace); SM.AddNewSourceBuffer(F, SMLoc()); @@ -653,80 +1090,56 @@ int main(int argc, char **argv) { // file. StringRef Buffer = F->getBuffer(); - const char *LastMatch = Buffer.data(); + bool hasError = false; - for (unsigned StrNo = 0, e = CheckStrings.size(); StrNo != e; ++StrNo) { - const CheckString &CheckStr = CheckStrings[StrNo]; + unsigned i = 0, j = 0, e = CheckStrings.size(); - StringRef SearchFrom = Buffer; + while (true) { + StringRef CheckRegion; + if (j == e) { + CheckRegion = Buffer; + } else { + const CheckString &CheckLabelStr = CheckStrings[j]; + if (!CheckLabelStr.IsCheckLabel) { + ++j; + continue; + } - // Find StrNo in the file. - size_t MatchLen = 0; - Buffer = Buffer.substr(CheckStr.Pat.Match(Buffer, MatchLen, VariableTable)); + // Scan to next CHECK-LABEL match, ignoring CHECK-NOT and CHECK-DAG + size_t MatchLabelLen = 0; + size_t MatchLabelPos = CheckLabelStr.Check(SM, Buffer, true, + MatchLabelLen, VariableTable); + if (MatchLabelPos == StringRef::npos) { + hasError = true; + break; + } - // If we didn't find a match, reject the input. - if (Buffer.empty()) { - PrintCheckFailed(SM, CheckStr, SearchFrom, VariableTable); - return 1; + CheckRegion = Buffer.substr(0, MatchLabelPos + MatchLabelLen); + Buffer = Buffer.substr(MatchLabelPos + MatchLabelLen); + ++j; } - StringRef SkippedRegion(LastMatch, Buffer.data()-LastMatch); + for ( ; i != j; ++i) { + const CheckString &CheckStr = CheckStrings[i]; - // If this check is a "CHECK-NEXT", verify that the previous match was on - // the previous line (i.e. that there is one newline between them). - if (CheckStr.IsCheckNext) { - // Count the number of newlines between the previous match and this one. - assert(LastMatch != F->getBufferStart() && - "CHECK-NEXT can't be the first check in a file"); - - unsigned NumNewLines = CountNumNewlinesBetween(SkippedRegion); - if (NumNewLines == 0) { - SM.PrintMessage(CheckStr.Loc, - CheckPrefix+"-NEXT: is on the same line as previous match", - "error"); - SM.PrintMessage(SMLoc::getFromPointer(Buffer.data()), - "'next' match was here", "note"); - SM.PrintMessage(SMLoc::getFromPointer(LastMatch), - "previous match was here", "note"); - return 1; - } + // Check each string within the scanned region, including a second check + // of any final CHECK-LABEL (to verify CHECK-NOT and CHECK-DAG) + size_t MatchLen = 0; + size_t MatchPos = CheckStr.Check(SM, CheckRegion, false, MatchLen, + VariableTable); - if (NumNewLines != 1) { - SM.PrintMessage(CheckStr.Loc, - CheckPrefix+ - "-NEXT: is not on the line after the previous match", - "error"); - SM.PrintMessage(SMLoc::getFromPointer(Buffer.data()), - "'next' match was here", "note"); - SM.PrintMessage(SMLoc::getFromPointer(LastMatch), - "previous match was here", "note"); - return 1; + if (MatchPos == StringRef::npos) { + hasError = true; + i = j; + break; } - } - // If this match had "not strings", verify that they don't exist in the - // skipped region. - for (unsigned ChunkNo = 0, e = CheckStr.NotStrings.size(); - ChunkNo != e; ++ChunkNo) { - size_t MatchLen = 0; - size_t Pos = CheckStr.NotStrings[ChunkNo].second.Match(SkippedRegion, - MatchLen, - VariableTable); - if (Pos == StringRef::npos) continue; - - SM.PrintMessage(SMLoc::getFromPointer(LastMatch+Pos), - CheckPrefix+"-NOT: string occurred!", "error"); - SM.PrintMessage(CheckStr.NotStrings[ChunkNo].first, - CheckPrefix+"-NOT: pattern specified here", "note"); - return 1; + CheckRegion = CheckRegion.substr(MatchPos + MatchLen); } - - // Otherwise, everything is good. Step over the matched text and remember - // the position after the match as the end of the last match. - Buffer = Buffer.substr(MatchLen); - LastMatch = Buffer.data(); + if (j == e) + break; } - return 0; + return hasError ? 1 : 0; }