remove support for "NoSub" from regex. It seems like a minor optimization

and makes the API more annoying.  Add a Regex::getNumMatches() method.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@82877 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Support/Regex.h

@@ -22,47 +22,42 @@ namespace llvm {
   class Regex {
   public:
     enum {
-      /// Compile with support for subgroup matches, this is just to make
+      NoFlags=0,
-      /// constructs like Regex("...", 0) more readable as Regex("...", Sub).
-      Sub=0,
       /// Compile for matching that ignores upper/lower case distinctions.
       IgnoreCase=1,
-      /// Compile for matching that need only report success or failure,
-      /// not what was matched.
-      NoSub=2,
       /// Compile for newline-sensitive matching. With this flag '[^' bracket
       /// expressions and '.' never match newline. A ^ anchor matches the 
       /// null string after any newline in the string in addition to its normal 
       /// function, and the $ anchor matches the null string before any 
       /// newline in the string in addition to its normal function.
-      Newline=4
+      Newline=2
     };
 
     /// Compiles the given POSIX Extended Regular Expression \arg Regex.
     /// This implementation supports regexes and matching strings with embedded
     /// NUL characters.
-    Regex(const StringRef &Regex, unsigned Flags=NoSub);
+    Regex(const StringRef &Regex, unsigned Flags = NoFlags);
     ~Regex();
 
     /// isValid - returns the error encountered during regex compilation, or
     /// matching, if any.
     bool isValid(std::string &Error);
 
+    /// getNumMatches - In a valid regex, return the number of parenthesized
+    /// matches it contains.  The number filled in by match will include this
+    /// many entries plus one for the whole regex (as element 0).
+    unsigned getNumMatches() const;
+    
     /// matches - Match the regex against a given \arg String.
     ///
     /// \param Matches - If given, on a succesful match this will be filled in
     /// with references to the matched group expressions (inside \arg String),
     /// the first group is always the entire pattern.
-    /// By default the regex is compiled with NoSub, which disables support for
-    /// Matches.
-    /// For this feature to be enabled you must construct the regex using
-    /// Regex("...", Regex::Sub) constructor.
     ///
     /// This returns true on a successful match.
     bool match(const StringRef &String, SmallVectorImpl<StringRef> *Matches=0);
   private:
     struct llvm_regex *preg;
     int error;
-    bool sub;
   };
 }

lib/Support/Regex.cpp

@@ -25,41 +25,36 @@ Regex::Regex(const StringRef &regex, unsigned Flags) {
   preg->re_endp = regex.end();
   if (Flags & IgnoreCase) 
     flags |= REG_ICASE;
-  if (Flags & NoSub) {
-    flags |= REG_NOSUB;
-    sub = false;
-  } else {
-    sub = true;
-  }
   if (Flags & Newline)
     flags |= REG_NEWLINE;
   error = llvm_regcomp(preg, regex.data(), flags|REG_EXTENDED|REG_PEND);
 }
 
-bool Regex::isValid(std::string &Error) {
-  if (!error)
-    return true;
-
-  size_t len = llvm_regerror(error, preg, NULL, 0);
-  
-  Error.resize(len);
-  llvm_regerror(error, preg, &Error[0], len);
-  return false;
-}
-
 Regex::~Regex() {
   llvm_regfree(preg);
   delete preg;
 }
 
+bool Regex::isValid(std::string &Error) {
+  if (!error)
+    return true;
+  
+  size_t len = llvm_regerror(error, preg, NULL, 0);
+  
+  Error.resize(len);
+  llvm_regerror(error, preg, &Error[0], len);
+  return false;
+}
+
+/// getNumMatches - In a valid regex, return the number of parenthesized
+/// matches it contains.
+unsigned Regex::getNumMatches() const {
+  return preg->re_nsub;
+}
+
 bool Regex::match(const StringRef &String, SmallVectorImpl<StringRef> *Matches){
   unsigned nmatch = Matches ? preg->re_nsub+1 : 0;
 
-  if (Matches) {
-    assert(sub && "Substring matching requested but pattern compiled without");
-    Matches->clear();
-  }
-
   // pmatch needs to have at least one element.
   SmallVector<llvm_regmatch_t, 8> pm;
   pm.resize(nmatch > 0 ? nmatch : 1);
@@ -79,6 +74,8 @@ bool Regex::match(const StringRef &String, SmallVectorImpl<StringRef> *Matches){
   // There was a match.
 
   if (Matches) { // match position requested
+    Matches->clear();
+    
     for (unsigned i = 0; i != nmatch; ++i) {
       if (pm[i].rm_so == -1) {
         // this group didn't match

unittests/Support/RegexTest.cpp

@@ -25,12 +25,12 @@ TEST_F(RegexTest, Basics) {
   EXPECT_FALSE(r1.match("9a"));
 
   SmallVector<StringRef, 1> Matches;
-  Regex r2("[0-9]+", Regex::Sub);
+  Regex r2("[0-9]+");
   EXPECT_TRUE(r2.match("aa216b", &Matches));
   EXPECT_EQ(1u, Matches.size());
   EXPECT_EQ("216", Matches[0].str());
 
-  Regex r3("[0-9]+([a-f])?:([0-9]+)", Regex::Sub);
+  Regex r3("[0-9]+([a-f])?:([0-9]+)");
   EXPECT_TRUE(r3.match("9a:513b", &Matches));
   EXPECT_EQ(3u, Matches.size());
   EXPECT_EQ("9a:513", Matches[0].str());
@@ -43,7 +43,7 @@ TEST_F(RegexTest, Basics) {
   EXPECT_EQ("", Matches[1].str());
   EXPECT_EQ("513", Matches[2].str());
 
-  Regex r4("a[^b]+b", Regex::Sub);
+  Regex r4("a[^b]+b");
   std::string String="axxb";
   String[2] = '\0';
   EXPECT_FALSE(r4.match("abb"));
@@ -55,7 +55,7 @@ TEST_F(RegexTest, Basics) {
   std::string NulPattern="X[0-9]+X([a-f])?:([0-9]+)";
   String="YX99a:513b";
   NulPattern[7] = '\0';
-  Regex r5(NulPattern, Regex::Sub);
+  Regex r5(NulPattern);
   EXPECT_FALSE(r5.match(String));
   EXPECT_FALSE(r5.match("X9"));
   String[3]='\0';

utils/FileCheck/FileCheck.cpp

@@ -168,7 +168,7 @@ size_t Pattern::Match(StringRef Buffer, size_t &MatchLen) const {
   
   // Regex match.
   SmallVector<StringRef, 4> MatchInfo;
-  if (!Regex(RegExStr, Regex::Sub|Regex::Newline).match(Buffer, &MatchInfo))
+  if (!Regex(RegExStr, Regex::Newline).match(Buffer, &MatchInfo))
     return StringRef::npos;
   
   // Successful regex match.