[ADT] Fix a confusing interface spec and some annoying peculiarities

[oota-llvm.git] / include / llvm / ADT / StringRef.h

diff --git a/include/llvm/ADT/StringRef.h b/include/llvm/ADT/StringRef.h
index 778fa10a32c252e7e5bd22bad634ce1dddb804c7..34caeee801a2f477975492907df7867c42ea0527 100644 (file)
--- a/include/llvm/ADT/StringRef.h
+++ b/include/llvm/ADT/StringRef.h
@@ -91,6 +91,13 @@ namespace llvm {
 
     iterator end() const { return Data + Length; }
 
+    const unsigned char *bytes_begin() const {
+      return reinterpret_cast<const unsigned char *>(begin());
+    }
+    const unsigned char *bytes_end() const {
+      return reinterpret_cast<const unsigned char *>(end());
+    }
+
     /// @}
     /// @name String Operations
     /// @{
@@ -231,9 +238,12 @@ namespace llvm {
     /// \returns The index of the first occurrence of \p C, or npos if not
     /// found.
     size_t find(char C, size_t From = 0) const {
-      for (size_t i = std::min(From, Length), e = Length; i != e; ++i)
-        if (Data[i] == C)
-          return i;
+      size_t FindBegin = std::min(From, Length);
+      if (FindBegin < Length) { // Avoid calling memchr with nullptr.
+        // Just forward to memchr, which is faster than a hand-rolled loop.
+        if (const void *P = ::memchr(Data + FindBegin, C, Length - FindBegin))
+          return static_cast<const char *>(P) - Data;
+      }
       return npos;
     }
 
@@ -464,7 +474,7 @@ namespace llvm {
     /// Split into substrings around the occurrences of a separator string.
     ///
     /// Each substring is stored in \p A. If \p MaxSplit is >= 0, at most
-    /// \p MaxSplit splits are done and consequently <= \p MaxSplit
+    /// \p MaxSplit splits are done and consequently <= \p MaxSplit + 1
     /// elements are added to A.
     /// If \p KeepEmpty is false, empty strings are not added to \p A. They
     /// still count when considering \p MaxSplit
@@ -479,6 +489,23 @@ namespace llvm {
                StringRef Separator, int MaxSplit = -1,
                bool KeepEmpty = true) const;
 
+    /// Split into substrings around the occurrences of a separator character.
+    ///
+    /// Each substring is stored in \p A. If \p MaxSplit is >= 0, at most
+    /// \p MaxSplit splits are done and consequently <= \p MaxSplit + 1
+    /// elements are added to A.
+    /// If \p KeepEmpty is false, empty strings are not added to \p A. They
+    /// still count when considering \p MaxSplit
+    /// An useful invariant is that
+    /// Separator.join(A) == *this if MaxSplit == -1 and KeepEmpty == true
+    ///
+    /// \param A - Where to put the substrings.
+    /// \param Separator - The string to split on.
+    /// \param MaxSplit - The maximum number of times the string is split.
+    /// \param KeepEmpty - True if empty substring should be added.
+    void split(SmallVectorImpl<StringRef> &A, char Separator, int MaxSplit = -1,
+               bool KeepEmpty = true) const;
+
     /// Split into two substrings around the last occurrence of a separator
     /// character.
     ///