X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FSupport%2FStringRef.cpp;h=e73c6e38e2f41146209b290d88326fce25a22d9e;hb=11c2defa9157bd589cb322218c718c4492ed5746;hp=0e09122e766395d8df60150618c2b73ab00d16b1;hpb=326990f1eb7ff005adabe46a1f982eff8835813e;p=oota-llvm.git

diff --git a/lib/Support/StringRef.cpp b/lib/Support/StringRef.cpp
index 0e09122e766..e73c6e38e2f 100644
--- a/lib/Support/StringRef.cpp
+++ b/lib/Support/StringRef.cpp
@@ -25,6 +25,12 @@ static char ascii_tolower(char x) {
   return x;
 }
 
+static char ascii_toupper(char x) {
+  if (x >= 'a' && x <= 'z')
+    return x - 'a' + 'A';
+  return x;
+}
+
 static bool ascii_isdigit(char x) {
   return x >= '0' && x <= '9';
 }
@@ -46,12 +52,12 @@ int StringRef::compare_lower(StringRef RHS) const {
 /// compare_numeric - Compare strings, handle embedded numbers.
 int StringRef::compare_numeric(StringRef RHS) const {
   for (size_t I = 0, E = min(Length, RHS.Length); I != E; ++I) {
-    if (Data[I] == RHS.Data[I])
-      continue;
+    // Check for sequences of digits.
     if (ascii_isdigit(Data[I]) && ascii_isdigit(RHS.Data[I])) {
-      // The longer sequence of numbers is larger. This doesn't really handle
-      // prefixed zeros well.
-      for (size_t J = I+1; J != E+1; ++J) {
+      // The longer sequence of numbers is considered larger.
+      // This doesn't really handle prefixed zeros well.
+      size_t J;
+      for (J = I + 1; J != E + 1; ++J) {
         bool ld = J < Length && ascii_isdigit(Data[J]);
         bool rd = J < RHS.Length && ascii_isdigit(RHS.Data[J]);
         if (ld != rd)
@@ -59,8 +65,15 @@ int StringRef::compare_numeric(StringRef RHS) const {
         if (!rd)
           break;
       }
+      // The two number sequences have the same length (J-I), just memcmp them.
+      if (int Res = compareMemory(Data + I, RHS.Data + I, J - I))
+        return Res < 0 ? -1 : 1;
+      // Identical number sequences, continue search after the numbers.
+      I = J - 1;
+      continue;
     }
-    return (unsigned char)Data[I] < (unsigned char)RHS.Data[I] ? -1 : 1;
+    if (Data[I] != RHS.Data[I])
+      return (unsigned char)Data[I] < (unsigned char)RHS.Data[I] ? -1 : 1;
   }
   if (Length == RHS.Length)
     return 0;
@@ -124,6 +137,26 @@ unsigned StringRef::edit_distance(llvm::StringRef Other,
   return Result;
 }
 
+//===----------------------------------------------------------------------===//
+// String Operations
+//===----------------------------------------------------------------------===//
+
+std::string StringRef::lower() const {
+  std::string Result(size(), char());
+  for (size_type i = 0, e = size(); i != e; ++i) {
+    Result[i] = ascii_tolower(Data[i]);
+  }
+  return Result;
+}
+
+std::string StringRef::upper() const {
+  std::string Result(size(), char());
+  for (size_type i = 0, e = size(); i != e; ++i) {
+    Result[i] = ascii_toupper(Data[i]);
+  }
+  return Result;
+}
+
 //===----------------------------------------------------------------------===//
 // String Searching
 //===----------------------------------------------------------------------===//
@@ -131,21 +164,47 @@ unsigned StringRef::edit_distance(llvm::StringRef Other,
 
 /// find - Search for the first string \arg Str in the string.
 ///
-/// \return - The index of the first occurence of \arg Str, or npos if not
+/// \return - The index of the first occurrence of \arg Str, or npos if not
 /// found.
 size_t StringRef::find(StringRef Str, size_t From) const {
   size_t N = Str.size();
   if (N > Length)
     return npos;
-  for (size_t e = Length - N + 1, i = min(From, e); i != e; ++i)
-    if (substr(i, N).equals(Str))
-      return i;
+
+  // For short haystacks or unsupported needles fall back to the naive algorithm
+  if (Length < 16 || N > 255 || N == 0) {
+    for (size_t e = Length - N + 1, i = min(From, e); i != e; ++i)
+      if (substr(i, N).equals(Str))
+        return i;
+    return npos;
+  }
+
+  if (From >= Length)
+    return npos;
+
+  // Build the bad char heuristic table, with uint8_t to reduce cache thrashing.
+  uint8_t BadCharSkip[256];
+  std::memset(BadCharSkip, N, 256);
+  for (unsigned i = 0; i != N-1; ++i)
+    BadCharSkip[(uint8_t)Str[i]] = N-1-i;
+
+  unsigned Len = Length-From, Pos = From;
+  while (Len >= N) {
+    if (substr(Pos, N).equals(Str)) // See if this is the correct substring.
+      return Pos;
+
+    // Otherwise skip the appropriate number of bytes.
+    uint8_t Skip = BadCharSkip[(uint8_t)(*this)[Pos+N-1]];
+    Len -= Skip;
+    Pos += Skip;
+  }
+
   return npos;
 }
 
 /// rfind - Search for the last string \arg Str in the string.
 ///
-/// \return - The index of the last occurence of \arg Str, or npos if not
+/// \return - The index of the last occurrence of \arg Str, or npos if not
 /// found.
 size_t StringRef::rfind(StringRef Str) const {
   size_t N = Str.size();
@@ -200,6 +259,21 @@ StringRef::size_type StringRef::find_first_not_of(StringRef Chars,
   return npos;
 }
 
+/// find_last_of - Find the last character in the string that is in \arg C,
+/// or npos if not found.
+///
+/// Note: O(size() + Chars.size())
+StringRef::size_type StringRef::find_last_of(StringRef Chars,
+                                             size_t From) const {
+  std::bitset<1 << CHAR_BIT> CharBits;
+  for (size_type i = 0; i != Chars.size(); ++i)
+    CharBits.set((unsigned char)Chars[i]);
+
+  for (size_type i = min(From, Length) - 1, e = -1; i != e; --i)
+    if (CharBits.test((unsigned char)Data[i]))
+      return i;
+  return npos;
+}
 
 //===----------------------------------------------------------------------===//
 // Helpful Algorithms
@@ -356,7 +430,7 @@ bool StringRef::getAsInteger(unsigned Radix, APInt &Result) const {
   if (BitWidth < Result.getBitWidth())
     BitWidth = Result.getBitWidth(); // don't shrink the result
   else
-    Result.zext(BitWidth);
+    Result = Result.zext(BitWidth);
 
   APInt RadixAP, CharAP; // unused unless !IsPowerOf2Radix
   if (!IsPowerOf2Radix) {