diff options
Diffstat (limited to 'utils/FileCheck/FileCheck.cpp')
| -rw-r--r-- | utils/FileCheck/FileCheck.cpp | 691 |
1 files changed, 556 insertions, 135 deletions
diff --git a/utils/FileCheck/FileCheck.cpp b/utils/FileCheck/FileCheck.cpp index cd7bb5a44fb99..f2510d7dfd708 100644 --- a/utils/FileCheck/FileCheck.cpp +++ b/utils/FileCheck/FileCheck.cpp @@ -20,6 +20,7 @@ #include "llvm/ADT/SmallString.h" #include "llvm/ADT/StringExtras.h" #include "llvm/ADT/StringMap.h" +#include "llvm/ADT/StringSet.h" #include "llvm/Support/CommandLine.h" #include "llvm/Support/MemoryBuffer.h" #include "llvm/Support/PrettyStackTrace.h" @@ -29,6 +30,7 @@ #include "llvm/Support/raw_ostream.h" #include "llvm/Support/system_error.h" #include <algorithm> +#include <cctype> #include <map> #include <string> #include <vector> @@ -41,24 +43,39 @@ static cl::opt<std::string> InputFilename("input-file", cl::desc("File to check (defaults to stdin)"), cl::init("-"), cl::value_desc("filename")); -static cl::opt<std::string> -CheckPrefix("check-prefix", cl::init("CHECK"), - cl::desc("Prefix to use from check file (defaults to 'CHECK')")); +static cl::list<std::string> +CheckPrefixes("check-prefix", + cl::desc("Prefix to use from check file (defaults to 'CHECK')")); static cl::opt<bool> NoCanonicalizeWhiteSpace("strict-whitespace", cl::desc("Do not treat all horizontal whitespace as equivalent")); +typedef cl::list<std::string>::const_iterator prefix_iterator; + //===----------------------------------------------------------------------===// // Pattern Handling Code. //===----------------------------------------------------------------------===// +namespace Check { + enum CheckType { + CheckNone = 0, + CheckPlain, + CheckNext, + CheckNot, + CheckDAG, + CheckLabel, + + /// MatchEOF - When set, this pattern only matches the end of file. This is + /// used for trailing CHECK-NOTs. + CheckEOF + }; +} + class Pattern { SMLoc PatternLoc; - /// MatchEOF - When set, this pattern only matches the end of file. This is - /// used for trailing CHECK-NOTs. - bool MatchEOF; + Check::CheckType CheckTy; /// FixedStr - If non-empty, this pattern is a fixed string match with the /// specified fixed string. @@ -83,16 +100,21 @@ class Pattern { public: - Pattern(bool matchEOF = false) : MatchEOF(matchEOF) { } + Pattern(Check::CheckType Ty) + : CheckTy(Ty) { } /// getLoc - Return the location in source code. SMLoc getLoc() const { return PatternLoc; } - /// 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); + /// ParsePattern - Parse the given string into the Pattern. Prefix provides + /// which prefix is being matched, 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, + StringRef Prefix, + 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 @@ -108,6 +130,11 @@ public: void PrintFailureInfo(const SourceMgr &SM, StringRef Buffer, const StringMap<StringRef> &VariableTable) const; + bool hasVariable() const { return !(VariableUses.empty() && + VariableDefs.empty()); } + + Check::CheckType getCheckTy() const { return CheckTy; } + private: static void AddFixedStringToRegEx(StringRef FixedStr, std::string &TheStr); bool AddRegExToRegEx(StringRef RS, unsigned &CurParen, SourceMgr &SM); @@ -132,7 +159,9 @@ private: }; -bool Pattern::ParsePattern(StringRef PatternStr, SourceMgr &SM, +bool Pattern::ParsePattern(StringRef PatternStr, + StringRef Prefix, + SourceMgr &SM, unsigned LineNumber) { this->LineNumber = LineNumber; PatternLoc = SMLoc::getFromPointer(PatternStr.data()); @@ -146,7 +175,7 @@ bool Pattern::ParsePattern(StringRef PatternStr, SourceMgr &SM, if (PatternStr.empty()) { SM.PrintMessage(PatternLoc, SourceMgr::DK_Error, "found empty check string with prefix '" + - CheckPrefix+":'"); + Prefix + ":'"); return true; } @@ -365,7 +394,7 @@ bool Pattern::EvaluateExpression(StringRef Expr, std::string &Value) const { size_t Pattern::Match(StringRef Buffer, size_t &MatchLen, StringMap<StringRef> &VariableTable) const { // If this is the EOF pattern, match it immediately. - if (MatchEOF) { + if (CheckTy == Check::CheckEOF) { MatchLen = 0; return Buffer.size(); } @@ -574,20 +603,44 @@ struct CheckString { /// Pat - The pattern to match. Pattern Pat; + /// Prefix - Which prefix name this check matched. + StringRef Prefix; + /// Loc - The location in the match file that the check string was specified. SMLoc Loc; - /// IsCheckNext - This is true if this is a CHECK-NEXT: directive (as opposed - /// to a CHECK: directive. - bool IsCheckNext; + /// CheckTy - Specify what kind of check this is. e.g. CHECK-NEXT: directive, + /// as opposed to a CHECK: directive. + Check::CheckType CheckTy; - /// NotStrings - These are all of the strings that are disallowed from + /// 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<Pattern> NotStrings; + std::vector<Pattern> DagNotStrings; + + + CheckString(const Pattern &P, + StringRef S, + SMLoc L, + Check::CheckType Ty) + : Pat(P), Prefix(S), Loc(L), CheckTy(Ty) {} + + /// Check - Match check string and its "not strings" and/or "dag strings". + size_t Check(const SourceMgr &SM, StringRef Buffer, bool IsLabelScanMode, + size_t &MatchLen, StringMap<StringRef> &VariableTable) const; + + /// CheckNext - Verify there is a single line in the given buffer. + bool CheckNext(const SourceMgr &SM, StringRef Buffer) const; - CheckString(const Pattern &P, SMLoc L, bool isCheckNext) - : Pat(P), Loc(L), IsCheckNext(isCheckNext) {} + /// CheckNot - Verify there's no "not strings" in the given buffer. + bool CheckNot(const SourceMgr &SM, StringRef Buffer, + const std::vector<const Pattern *> &NotStrings, + StringMap<StringRef> &VariableTable) const; + + /// CheckDag - Match "dag strings" and their mixed "not strings". + size_t CheckDag(const SourceMgr &SM, StringRef Buffer, + std::vector<const Pattern *> &NotStrings, + StringMap<StringRef> &VariableTable) const; }; /// Canonicalize whitespaces in the input file. Line endings are replaced @@ -629,6 +682,161 @@ static MemoryBuffer *CanonicalizeInputFile(MemoryBuffer *MB, return MB2; } +static bool IsPartOfWord(char c) { + return (isalnum(c) || c == '-' || c == '_'); +} + +// Get the size of the prefix extension. +static size_t CheckTypeSize(Check::CheckType Ty) { + switch (Ty) { + case Check::CheckNone: + return 0; + + case Check::CheckPlain: + return sizeof(":") - 1; + + case Check::CheckNext: + return sizeof("-NEXT:") - 1; + + case Check::CheckNot: + return sizeof("-NOT:") - 1; + + case Check::CheckDAG: + return sizeof("-DAG:") - 1; + + case Check::CheckLabel: + return sizeof("-LABEL:") - 1; + + case Check::CheckEOF: + llvm_unreachable("Should not be using EOF size"); + } + + llvm_unreachable("Bad check type"); +} + +static Check::CheckType FindCheckType(StringRef Buffer, StringRef Prefix) { + char NextChar = Buffer[Prefix.size()]; + + // Verify that the : is present after the prefix. + if (NextChar == ':') + return Check::CheckPlain; + + if (NextChar != '-') + return Check::CheckNone; + + StringRef Rest = Buffer.drop_front(Prefix.size() + 1); + if (Rest.startswith("NEXT:")) + return Check::CheckNext; + + if (Rest.startswith("NOT:")) + return Check::CheckNot; + + if (Rest.startswith("DAG:")) + return Check::CheckDAG; + + if (Rest.startswith("LABEL:")) + return Check::CheckLabel; + + return Check::CheckNone; +} + +// From the given position, find the next character after the word. +static size_t SkipWord(StringRef Str, size_t Loc) { + while (Loc < Str.size() && IsPartOfWord(Str[Loc])) + ++Loc; + return Loc; +} + +// Try to find the first match in buffer for any prefix. If a valid match is +// found, return that prefix and set its type and location. If there are almost +// matches (e.g. the actual prefix string is found, but is not an actual check +// string), but no valid match, return an empty string and set the position to +// resume searching from. If no partial matches are found, return an empty +// string and the location will be StringRef::npos. If one prefix is a substring +// of another, the maximal match should be found. e.g. if "A" and "AA" are +// prefixes then AA-CHECK: should match the second one. +static StringRef FindFirstCandidateMatch(StringRef &Buffer, + Check::CheckType &CheckTy, + size_t &CheckLoc) { + StringRef FirstPrefix; + size_t FirstLoc = StringRef::npos; + size_t SearchLoc = StringRef::npos; + Check::CheckType FirstTy = Check::CheckNone; + + CheckTy = Check::CheckNone; + CheckLoc = StringRef::npos; + + for (prefix_iterator I = CheckPrefixes.begin(), E = CheckPrefixes.end(); + I != E; ++I) { + StringRef Prefix(*I); + size_t PrefixLoc = Buffer.find(Prefix); + + if (PrefixLoc == StringRef::npos) + continue; + + // Track where we are searching for invalid prefixes that look almost right. + // We need to only advance to the first partial match on the next attempt + // since a partial match could be a substring of a later, valid prefix. + // Need to skip to the end of the word, otherwise we could end up + // matching a prefix in a substring later. + if (PrefixLoc < SearchLoc) + SearchLoc = SkipWord(Buffer, PrefixLoc); + + // We only want to find the first match to avoid skipping some. + if (PrefixLoc > FirstLoc) + continue; + // If one matching check-prefix is a prefix of another, choose the + // longer one. + if (PrefixLoc == FirstLoc && Prefix.size() < FirstPrefix.size()) + continue; + + StringRef Rest = Buffer.drop_front(PrefixLoc); + // Make sure we have actually found the prefix, and not a word containing + // it. This should also prevent matching the wrong prefix when one is a + // substring of another. + if (PrefixLoc != 0 && IsPartOfWord(Buffer[PrefixLoc - 1])) + continue; + + FirstLoc = PrefixLoc; + FirstTy = FindCheckType(Rest, Prefix); + FirstPrefix = Prefix; + } + + // If the first prefix is invalid, we should continue the search after it. + if (FirstTy == Check::CheckNone) { + CheckLoc = SearchLoc; + return ""; + } + + CheckTy = FirstTy; + CheckLoc = FirstLoc; + return FirstPrefix; +} + +static StringRef FindFirstMatchingPrefix(StringRef &Buffer, + unsigned &LineNumber, + Check::CheckType &CheckTy, + size_t &CheckLoc) { + while (!Buffer.empty()) { + StringRef Prefix = FindFirstCandidateMatch(Buffer, CheckTy, CheckLoc); + // If we found a real match, we are done. + if (!Prefix.empty()) { + LineNumber += Buffer.substr(0, CheckLoc).count('\n'); + return Prefix; + } + + // We didn't find any almost matches either, we are also done. + if (CheckLoc == StringRef::npos) + return StringRef(); + + LineNumber += Buffer.substr(0, CheckLoc + 1).count('\n'); + + // Advance to the last possible match we found and try again. + Buffer = Buffer.drop_front(CheckLoc + 1); + } + + return StringRef(); +} /// ReadCheckFile - Read the check file, which specifies the sequence of /// expected strings. The strings are added to the CheckStrings vector. @@ -637,7 +845,7 @@ static bool ReadCheckFile(SourceMgr &SM, std::vector<CheckString> &CheckStrings) { OwningPtr<MemoryBuffer> File; if (error_code ec = - MemoryBuffer::getFileOrSTDIN(CheckFilename.c_str(), File)) { + MemoryBuffer::getFileOrSTDIN(CheckFilename, File)) { errs() << "Could not open check file '" << CheckFilename << "': " << ec.message() << '\n'; return true; @@ -652,47 +860,34 @@ static bool ReadCheckFile(SourceMgr &SM, // Find all instances of CheckPrefix followed by : in the file. StringRef Buffer = F->getBuffer(); - std::vector<Pattern> NotMatches; + std::vector<Pattern> DagNotMatches; // 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. - size_t PrefixLoc = Buffer.find(CheckPrefix); - // If we didn't find a match, we're done. - if (PrefixLoc == StringRef::npos) + Check::CheckType CheckTy; + size_t PrefixLoc; + + // See if a prefix occurs in the memory buffer. + StringRef UsedPrefix = FindFirstMatchingPrefix(Buffer, + LineNumber, + CheckTy, + PrefixLoc); + if (UsedPrefix.empty()) break; - LineNumber += Buffer.substr(0, PrefixLoc).count('\n'); - - Buffer = Buffer.substr(PrefixLoc); - - const char *CheckPrefixStart = Buffer.data(); + Buffer = Buffer.drop_front(PrefixLoc); - // When we find a check prefix, keep track of whether we find CHECK: or - // CHECK-NEXT: - bool IsCheckNext = false, IsCheckNot = false; + // Location to use for error messages. + const char *UsedPrefixStart = Buffer.data() + (PrefixLoc == 0 ? 0 : 1); - // 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()+6); - IsCheckNext = true; - } else if (Buffer.size() > CheckPrefix.size()+5 && - memcmp(Buffer.data()+CheckPrefix.size(), "-NOT:", 5) == 0) { - Buffer = Buffer.substr(CheckPrefix.size()+5); - IsCheckNot = true; - } else { - Buffer = Buffer.substr(1); - continue; - } + // PrefixLoc is to the start of the prefix. Skip to the end. + Buffer = Buffer.drop_front(UsedPrefix.size() + CheckTypeSize(CheckTy)); - // Okay, we found the prefix, yay. Remember the rest of the line, but - // ignore leading and trailing whitespace. + // Okay, we found the prefix, yay. Remember the rest of the line, but ignore + // leading and trailing whitespace. Buffer = Buffer.substr(Buffer.find_first_not_of(" \t")); // Scan ahead to the end of line. @@ -702,56 +897,76 @@ static bool ReadCheckFile(SourceMgr &SM, SMLoc PatternLoc = SMLoc::getFromPointer(Buffer.data()); // Parse the pattern. - Pattern P; - if (P.ParsePattern(Buffer.substr(0, EOL), SM, LineNumber)) + Pattern P(CheckTy); + if (P.ParsePattern(Buffer.substr(0, EOL), UsedPrefix, SM, LineNumber)) + return true; + + // Verify that CHECK-LABEL lines do not define or use variables + if ((CheckTy == Check::CheckLabel) && P.hasVariable()) { + SM.PrintMessage(SMLoc::getFromPointer(UsedPrefixStart), + SourceMgr::DK_Error, + "found '" + UsedPrefix + "-LABEL:'" + " with variable definition or use"); return true; + } 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), + if ((CheckTy == Check::CheckNext) && CheckStrings.empty()) { + SM.PrintMessage(SMLoc::getFromPointer(UsedPrefixStart), SourceMgr::DK_Error, - "found '"+CheckPrefix+"-NEXT:' without previous '"+ - CheckPrefix+ ": line"); + "found '" + UsedPrefix + "-NEXT:' without previous '" + + UsedPrefix + ": line"); return true; } - // Handle CHECK-NOT. - if (IsCheckNot) { - NotMatches.push_back(P); + // Handle CHECK-DAG/-NOT. + if (CheckTy == Check::CheckDAG || CheckTy == Check::CheckNot) { + DagNotMatches.push_back(P); continue; } // Okay, add the string we captured to the output vector and move on. CheckStrings.push_back(CheckString(P, + UsedPrefix, PatternLoc, - IsCheckNext)); - std::swap(NotMatches, CheckStrings.back().NotStrings); + CheckTy)); + std::swap(DagNotMatches, CheckStrings.back().DagNotStrings); } - // Add an EOF pattern for any trailing CHECK-NOTs. - if (!NotMatches.empty()) { - CheckStrings.push_back(CheckString(Pattern(true), + // Add an EOF pattern for any trailing CHECK-DAG/-NOTs, and use the first + // prefix as a filler for the error message. + if (!DagNotMatches.empty()) { + CheckStrings.push_back(CheckString(Pattern(Check::CheckEOF), + CheckPrefixes[0], SMLoc::getFromPointer(Buffer.data()), - false)); - std::swap(NotMatches, CheckStrings.back().NotStrings); + Check::CheckEOF)); + std::swap(DagNotMatches, CheckStrings.back().DagNotStrings); } if (CheckStrings.empty()) { - errs() << "error: no check strings found with prefix '" << CheckPrefix - << ":'\n"; + errs() << "error: no check strings found with prefix" + << (CheckPrefixes.size() > 1 ? "es " : " "); + for (size_t I = 0, N = CheckPrefixes.size(); I != N; ++I) { + StringRef Prefix(CheckPrefixes[I]); + errs() << '\'' << Prefix << ":'"; + if (I != N - 1) + errs() << ", "; + } + + errs() << '\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<StringRef> &VariableTable) { // Otherwise, we have an error, emit an error message. - SM.PrintMessage(CheckStr.Loc, SourceMgr::DK_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 @@ -762,7 +977,13 @@ static void PrintCheckFailed(const SourceMgr &SM, const CheckString &CheckStr, "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<StringRef> &VariableTable) { + PrintCheckFailed(SM, CheckStr.Loc, CheckStr.Pat, Buffer, VariableTable); } /// CountNumNewlinesBetween - Count the number of newlines in the specified @@ -785,11 +1006,232 @@ static unsigned CountNumNewlinesBetween(StringRef Range) { } } +size_t CheckString::Check(const SourceMgr &SM, StringRef Buffer, + bool IsLabelScanMode, size_t &MatchLen, + StringMap<StringRef> &VariableTable) const { + size_t LastPos = 0; + std::vector<const Pattern *> NotStrings; + + // IsLabelScanMode is true when we are scanning forward to find CHECK-LABEL + // bounds; we have not processed variable definitions within the bounded block + // yet so cannot handle any final CHECK-DAG yet; this is handled when going + // over the block again (including the last CHECK-LABEL) in normal mode. + if (!IsLabelScanMode) { + // 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; + + // Similar to the above, in "label-scan mode" we can't yet handle CHECK-NEXT + // or CHECK-NOT + if (!IsLabelScanMode) { + 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 (CheckTy != Check::CheckNext) + 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, Prefix + + "-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, Prefix + + "-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<const Pattern *> &NotStrings, + StringMap<StringRef> &VariableTable) const { + for (unsigned ChunkNo = 0, e = NotStrings.size(); + ChunkNo != e; ++ChunkNo) { + const Pattern *Pat = NotStrings[ChunkNo]; + assert((Pat->getCheckTy() == Check::CheckNot) && "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, + Prefix + "-NOT: string occurred!"); + SM.PrintMessage(Pat->getLoc(), SourceMgr::DK_Note, + Prefix + "-NOT: pattern specified here"); + return true; + } + + return false; +} + +size_t CheckString::CheckDag(const SourceMgr &SM, StringRef Buffer, + std::vector<const Pattern *> &NotStrings, + StringMap<StringRef> &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.getCheckTy() == Check::CheckDAG || + Pat.getCheckTy() == Check::CheckNot) && + "Invalid CHECK-DAG or CHECK-NOT!"); + + if (Pat.getCheckTy() == Check::CheckNot) { + NotStrings.push_back(&Pat); + continue; + } + + assert((Pat.getCheckTy() == Check::CheckDAG) && "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, + Prefix + "-DAG: found a match of CHECK-DAG" + " reordering across a CHECK-NOT"); + SM.PrintMessage(SMLoc::getFromPointer(Buffer.data() + LastPos), + SourceMgr::DK_Note, + Prefix + "-DAG: the farthest match of CHECK-DAG" + " is found here"); + SM.PrintMessage(NotStrings[0]->getLoc(), SourceMgr::DK_Note, + Prefix + "-NOT: the crossed pattern specified" + " here"); + SM.PrintMessage(Pat.getLoc(), SourceMgr::DK_Note, + Prefix + "-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; +} + +// A check prefix must contain only alphanumeric, hyphens and underscores. +static bool ValidateCheckPrefix(StringRef CheckPrefix) { + Regex Validator("^[a-zA-Z0-9_-]*$"); + return Validator.match(CheckPrefix); +} + +static bool ValidateCheckPrefixes() { + StringSet<> PrefixSet; + + for (prefix_iterator I = CheckPrefixes.begin(), E = CheckPrefixes.end(); + I != E; ++I) { + StringRef Prefix(*I); + + if (!PrefixSet.insert(Prefix)) + return false; + + if (!ValidateCheckPrefix(Prefix)) + return false; + } + + return true; +} + +// I don't think there's a way to specify an initial value for cl::list, +// so if nothing was specified, add the default +static void AddCheckPrefixIfNeeded() { + if (CheckPrefixes.empty()) + CheckPrefixes.push_back("CHECK"); +} + int main(int argc, char **argv) { sys::PrintStackTraceOnErrorSignal(); PrettyStackTraceProgram X(argc, argv); cl::ParseCommandLineOptions(argc, argv); + if (!ValidateCheckPrefixes()) { + errs() << "Supplied check-prefix is invalid! Prefixes must be unique and " + "start with a letter and contain only alphanumeric characters, " + "hyphens and underscores\n"; + return 2; + } + + AddCheckPrefixIfNeeded(); + SourceMgr SM; // Read the expected strings from the check file. @@ -800,7 +1242,7 @@ int main(int argc, char **argv) { // Open the file to check and add it to SourceMgr. OwningPtr<MemoryBuffer> File; if (error_code ec = - MemoryBuffer::getFileOrSTDIN(InputFilename.c_str(), File)) { + MemoryBuffer::getFileOrSTDIN(InputFilename, File)) { errs() << "Could not open input file '" << InputFilename << "': " << ec.message() << '\n'; return 2; @@ -825,77 +1267,56 @@ 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.CheckTy != Check::CheckLabel) { + ++j; + continue; + } - // Find StrNo in the file. - size_t MatchLen = 0; - size_t MatchPos = CheckStr.Pat.Match(Buffer, MatchLen, VariableTable); - Buffer = Buffer.substr(MatchPos); + // 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 (MatchPos == StringRef::npos) { - 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, SourceMgr::DK_Error, - CheckPrefix+"-NEXT: is on the same line as previous match"); - SM.PrintMessage(SMLoc::getFromPointer(Buffer.data()), - SourceMgr::DK_Note, "'next' match was here"); - SM.PrintMessage(SMLoc::getFromPointer(LastMatch), SourceMgr::DK_Note, - "previous match was here"); - 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, SourceMgr::DK_Error, CheckPrefix+ - "-NEXT: is not on the line after the previous match"); - SM.PrintMessage(SMLoc::getFromPointer(Buffer.data()), - SourceMgr::DK_Note, "'next' match was here"); - SM.PrintMessage(SMLoc::getFromPointer(LastMatch), SourceMgr::DK_Note, - "previous match was here"); - 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].Match(SkippedRegion, MatchLen, - VariableTable); - if (Pos == StringRef::npos) continue; - - SM.PrintMessage(SMLoc::getFromPointer(LastMatch+Pos), SourceMgr::DK_Error, - CheckPrefix+"-NOT: string occurred!"); - SM.PrintMessage(CheckStr.NotStrings[ChunkNo].getLoc(), SourceMgr::DK_Note, - CheckPrefix+"-NOT: pattern specified here"); - 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; } |