#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 <algorithm>
using namespace llvm;
static cl::opt<std::string>
// Pattern Handling Code.
//===----------------------------------------------------------------------===//
-class PatternChunk {
- StringRef Str;
- bool isRegEx;
-public:
- PatternChunk(StringRef S, bool isRE) : Str(S), isRegEx(isRE) {}
-
- size_t Match(StringRef Buffer, size_t &MatchLen) const {
- if (!isRegEx) {
- // Fixed string match.
- MatchLen = Str.size();
- return Buffer.find(Str);
- }
-
- // Regex match.
- SmallVector<StringRef, 4> MatchInfo;
- if (!Regex(Str, Regex::Sub|Regex::Newline).match(Buffer, &MatchInfo))
- return StringRef::npos;
-
- // Successful regex match.
- assert(!MatchInfo.empty() && "Didn't get any match");
- StringRef FullMatch = MatchInfo[0];
-
- MatchLen = FullMatch.size();
- return FullMatch.data()-Buffer.data();
- }
-};
-
class Pattern {
- /// Chunks - The pattern chunks to match. If the bool is false, it is a fixed
- /// string match, if it is true, it is a regex match.
- SmallVector<PatternChunk, 4> Chunks;
+ SMLoc PatternLoc;
+
+ /// FixedStr - If non-empty, this pattern is a fixed string match with the
+ /// specified fixed string.
+ StringRef FixedStr;
+
+ /// RegEx - If non-empty, this is a regex pattern.
+ std::string RegExStr;
+
+ /// 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<std::pair<StringRef, unsigned> > 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<std::pair<StringRef, unsigned> > VariableDefs;
+
public:
Pattern() { }
/// 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 Match(StringRef Buffer, size_t &MatchLen) const;
+ ///
+ /// The VariableTable StringMap provides the current values of filecheck
+ /// variables and is updated if this match defines new values.
+ size_t Match(StringRef Buffer, size_t &MatchLen,
+ StringMap<StringRef> &VariableTable) const;
+
+ /// PrintFailureInfo - Print additional information about a failure to match
+ /// involving this pattern.
+ void PrintFailureInfo(const SourceMgr &SM, StringRef Buffer,
+ const StringMap<StringRef> &VariableTable) const;
+
+private:
+ static void AddFixedStringToRegEx(StringRef FixedStr, std::string &TheStr);
+ bool AddRegExToRegEx(StringRef RegExStr, unsigned &CurParen, SourceMgr &SM);
+
+ /// 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<StringRef> &VariableTable) const;
};
+
bool Pattern::ParsePattern(StringRef PatternStr, SourceMgr &SM) {
+ PatternLoc = SMLoc::getFromPointer(PatternStr.data());
+
// Ignore trailing whitespace.
while (!PatternStr.empty() &&
(PatternStr.back() == ' ' || PatternStr.back() == '\t'))
// Check that there is something on the line.
if (PatternStr.empty()) {
- SM.PrintMessage(SMLoc::getFromPointer(PatternStr.data()),
- "found empty check string with prefix '"+CheckPrefix+":'",
- "error");
+ SM.PrintMessage(PatternLoc, "found empty check string with prefix '" +
+ CheckPrefix+":'", "error");
return true;
}
- // Scan the pattern to break it into regex and non-regex pieces.
+ // Check to see if this is a fixed string, or if it has regex pieces.
+ if (PatternStr.size() < 2 ||
+ (PatternStr.find("{{") == StringRef::npos &&
+ PatternStr.find("[[") == StringRef::npos)) {
+ FixedStr = PatternStr;
+ return false;
+ }
+
+ // Paren value #0 is for the fully matched string. Any new parenthesized
+ // values add from their.
+ 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()) {
- // Handle fixed string matches.
- if (PatternStr.size() < 2 ||
- PatternStr[0] != '{' || PatternStr[1] != '{') {
- // Find the end, which is the start of the next regex.
- size_t FixedMatchEnd = PatternStr.find("{{");
+ // RegEx matches.
+ if (PatternStr.size() >= 2 &&
+ PatternStr[0] == '{' && PatternStr[1] == '{') {
+
+ // Otherwise, 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");
+ return true;
+ }
- Chunks.push_back(PatternChunk(PatternStr.substr(0, FixedMatchEnd),false));
- PatternStr = PatternStr.substr(FixedMatchEnd);
+ if (AddRegExToRegEx(PatternStr.substr(2, End-2), CurParen, SM))
+ return true;
+ PatternStr = PatternStr.substr(End+2);
continue;
}
- // Otherwise, 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");
- return true;
+ // Named RegEx matches. These are of two forms: [[foo:.*]] which matches .*
+ // (or some other regex) and assigns it to the FileCheck variable 'foo'. The
+ // 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 (End == StringRef::npos) {
+ SM.PrintMessage(SMLoc::getFromPointer(PatternStr.data()),
+ "invalid named regex reference, no ]] found", "error");
+ return true;
+ }
+
+ StringRef MatchStr = PatternStr.substr(2, End-2);
+ PatternStr = PatternStr.substr(End+2);
+
+ // 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");
+ 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')) {
+ SM.PrintMessage(SMLoc::getFromPointer(Name.data()+i),
+ "invalid name in named regex", "error");
+ 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");
+ return true;
+ }
+
+ // Handle [[foo]].
+ if (NameEnd == StringRef::npos) {
+ VariableUses.push_back(std::make_pair(Name, RegExStr.size()));
+ continue;
+ }
+
+ // Handle [[foo:.*]].
+ VariableDefs.push_back(std::make_pair(Name, CurParen));
+ RegExStr += '(';
+ ++CurParen;
+
+ if (AddRegExToRegEx(MatchStr.substr(NameEnd+1), CurParen, SM))
+ return true;
+
+ RegExStr += ')';
}
- Regex R(PatternStr.substr(2, End-2));
- std::string Error;
- if (!R.isValid(Error)) {
- SM.PrintMessage(SMLoc::getFromPointer(PatternStr.data()+2),
- "invalid regex: " + Error, "error");
- return true;
+ // Handle fixed string matches.
+ // Find the end, which is the start of the next regex.
+ size_t FixedMatchEnd = PatternStr.find("{{");
+ FixedMatchEnd = std::min(FixedMatchEnd, PatternStr.find("[["));
+ AddFixedStringToRegEx(PatternStr.substr(0, FixedMatchEnd), RegExStr);
+ PatternStr = PatternStr.substr(FixedMatchEnd);
+ continue;
+ }
+
+ return false;
+}
+
+void Pattern::AddFixedStringToRegEx(StringRef FixedStr, std::string &TheStr) {
+ // Add the characters from FixedStr to the regex, escaping as needed. This
+ // avoids "leaning toothpicks" in common patterns.
+ for (unsigned i = 0, e = FixedStr.size(); i != e; ++i) {
+ switch (FixedStr[i]) {
+ // These are the special characters matched in "p_ere_exp".
+ case '(':
+ case ')':
+ case '^':
+ case '$':
+ case '|':
+ case '*':
+ case '+':
+ case '?':
+ case '.':
+ case '[':
+ case '\\':
+ case '{':
+ TheStr += '\\';
+ // FALL THROUGH.
+ default:
+ TheStr += FixedStr[i];
+ break;
}
-
- Chunks.push_back(PatternChunk(PatternStr.substr(2, End-2), true));
- PatternStr = PatternStr.substr(End+2);
}
+}
+bool Pattern::AddRegExToRegEx(StringRef RegexStr, unsigned &CurParen,
+ SourceMgr &SM) {
+ Regex R(RegexStr);
+ std::string Error;
+ if (!R.isValid(Error)) {
+ SM.PrintMessage(SMLoc::getFromPointer(RegexStr.data()),
+ "invalid regex: " + Error, "error");
+ return true;
+ }
+
+ RegExStr += RegexStr.str();
+ CurParen += R.getNumMatches();
return false;
}
/// 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) const {
- size_t FirstMatch = StringRef::npos;
- MatchLen = 0;
+size_t Pattern::Match(StringRef Buffer, size_t &MatchLen,
+ StringMap<StringRef> &VariableTable) const {
+ // If this is a fixed string pattern, just match it now.
+ if (!FixedStr.empty()) {
+ MatchLen = FixedStr.size();
+ return Buffer.find(FixedStr);
+ }
+
+ // Regex match.
- while (!Buffer.empty()) {
- StringRef MatchAttempt = Buffer;
+ // If there are variable uses, we need to create a temporary string with the
+ // actual value.
+ StringRef RegExToMatch = RegExStr;
+ std::string TmpStr;
+ if (!VariableUses.empty()) {
+ TmpStr = RegExStr;
- unsigned ChunkNo = 0, e = Chunks.size();
- for (; ChunkNo != e; ++ChunkNo) {
- size_t ThisMatch, ThisLength = StringRef::npos;
- ThisMatch = Chunks[ChunkNo].Match(MatchAttempt, ThisLength);
-
- // Otherwise, what we do depends on if this is the first match or not. If
- // this is the first match, it doesn't match to match at the start of
- // MatchAttempt.
- if (ChunkNo == 0) {
- // If the first match fails then this pattern will never match in
- // Buffer.
- if (ThisMatch == StringRef::npos)
- return ThisMatch;
-
- FirstMatch = ThisMatch;
- MatchAttempt = MatchAttempt.substr(FirstMatch);
- ThisMatch = 0;
- }
-
- // If this chunk didn't match, then the entire pattern didn't match from
- // FirstMatch, try later in the buffer.
- if (ThisMatch == StringRef::npos)
- break;
-
- // Ok, if the match didn't match at the beginning of MatchAttempt, then we
- // have something like "ABC{{DEF}} and something was in-between. Reject
- // the match.
- if (ThisMatch != 0)
- break;
+ unsigned InsertOffset = 0;
+ for (unsigned i = 0, e = VariableUses.size(); i != e; ++i) {
+ StringMap<StringRef>::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);
- // Otherwise, match the string and move to the next chunk.
- MatchLen += ThisLength;
- MatchAttempt = MatchAttempt.substr(ThisLength);
+ // Plop it into the regex at the adjusted offset.
+ TmpStr.insert(TmpStr.begin()+VariableUses[i].second+InsertOffset,
+ Value.begin(), Value.end());
+ InsertOffset += Value.size();
}
-
- // If the whole thing matched, we win.
- if (ChunkNo == e)
- return FirstMatch;
- // Otherwise, try matching again after FirstMatch to see if this pattern
- // matches later in the buffer.
- Buffer = Buffer.substr(FirstMatch+1);
+ // Match the newly constructed regex.
+ RegExToMatch = TmpStr;
+ }
+
+
+ SmallVector<StringRef, 4> MatchInfo;
+ if (!Regex(RegExToMatch, Regex::Newline).match(Buffer, &MatchInfo))
+ return StringRef::npos;
+
+ // Successful regex match.
+ assert(!MatchInfo.empty() && "Didn't get any match");
+ 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];
}
- // If we ran out of stuff to scan, then we didn't match.
- return StringRef::npos;
+ MatchLen = FullMatch.size();
+ return FullMatch.data()-Buffer.data();
}
+unsigned Pattern::ComputeMatchDistance(StringRef Buffer,
+ const StringMap<StringRef> &VariableTable) const {
+ // Just compute the number of matching characters. For regular expressions, we
+ // just compare against the regex itself and hope for the best.
+ //
+ // FIXME: One easy improvement here is have the regex lib generate a single
+ // example regular expression which matches, and use that as the example
+ // string.
+ StringRef ExampleString(FixedStr);
+ if (ExampleString.empty())
+ ExampleString = RegExStr;
+
+ unsigned Distance = 0;
+ for (unsigned i = 0, e = ExampleString.size(); i != e; ++i)
+ if (Buffer.substr(i, 1) != ExampleString.substr(i, 1))
+ ++Distance;
+
+ return Distance;
+}
+
+void Pattern::PrintFailureInfo(const SourceMgr &SM, StringRef Buffer,
+ const StringMap<StringRef> &VariableTable) const{
+ // If this was a regular expression using variables, print the current
+ // variable values.
+ if (!VariableUses.empty()) {
+ for (unsigned i = 0, e = VariableUses.size(); i != e; ++i) {
+ StringRef Var = VariableUses[i].first;
+ StringMap<StringRef>::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) << "\"";;
+ } 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);
+ }
+ }
+
+ // Attempt to find the closest/best fuzzy match. Usually an error happens
+ // because some string in the output didn't exactly match. In these cases, we
+ // would like to show the user a best guess at what "should have" matched, to
+ // save them having to actually check the input manually.
+ size_t NumLinesForward = 0;
+ size_t Best = StringRef::npos;
+ double BestQuality = 0;
+
+ // Use an arbitrary 4k limit on how far we will search.
+ for (size_t i = 0, e = std::min(4096, int(Buffer.size())); i != e; ++i) {
+ if (Buffer[i] == '\n')
+ ++NumLinesForward;
+
+ // Compute the "quality" of this match as an arbitrary combination of the
+ // match distance and the number of lines skipped to get to this match.
+ unsigned Distance = ComputeMatchDistance(Buffer.substr(i), VariableTable);
+ double Quality = Distance + (NumLinesForward / 100.);
+
+ if (Quality < BestQuality || Best == StringRef::npos) {
+ Best = i;
+ BestQuality = Quality;
+ }
+ }
+
+ if (Best != StringRef::npos && BestQuality < 50) {
+ // Print the "possible intended match here" line if we found something
+ // reasonable.
+ SM.PrintMessage(SMLoc::getFromPointer(Buffer.data() + Best),
+ "possible intended match here", "note");
+
+ // 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.
+ }
+}
//===----------------------------------------------------------------------===//
// Check Strings.
}
static void PrintCheckFailed(const SourceMgr &SM, const CheckString &CheckStr,
- StringRef Buffer) {
+ StringRef Buffer,
+ StringMap<StringRef> &VariableTable) {
// Otherwise, we have an error, emit an error message.
SM.PrintMessage(CheckStr.Loc, "expected string not found in input",
"error");
SM.PrintMessage(SMLoc::getFromPointer(Buffer.data()), "scanning from here",
"note");
+
+ // Allow the pattern to print additional information if desired.
+ CheckStr.Pat.PrintFailureInfo(SM, Buffer, VariableTable);
}
/// CountNumNewlinesBetween - Count the number of newlines in the specified
SM.AddNewSourceBuffer(F, SMLoc());
+ /// VariableTable - This holds all the current filecheck variables.
+ StringMap<StringRef> VariableTable;
+
// Check that we have all of the expected strings, in order, in the input
// file.
StringRef Buffer = F->getBuffer();
// Find StrNo in the file.
size_t MatchLen = 0;
- Buffer = Buffer.substr(CheckStr.Pat.Match(Buffer, MatchLen));
+ Buffer = Buffer.substr(CheckStr.Pat.Match(Buffer, MatchLen, VariableTable));
// If we didn't find a match, reject the input.
if (Buffer.empty()) {
- PrintCheckFailed(SM, CheckStr, SearchFrom);
+ PrintCheckFailed(SM, CheckStr, SearchFrom, VariableTable);
return 1;
}
// 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) {
+ 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);
+ size_t Pos = CheckStr.NotStrings[ChunkNo].second.Match(SkippedRegion,
+ MatchLen,
+ VariableTable);
if (Pos == StringRef::npos) continue;
SM.PrintMessage(SMLoc::getFromPointer(LastMatch+Pos),