From 250eb005d91e80b05a61345394bae9e9528151ac Mon Sep 17 00:00:00 2001 From: Benjamin Kramer Date: Mon, 23 Aug 2010 18:16:08 +0000 Subject: Avoid O(n*m) complexity in StringRef::find_first(_not)_of(StringRef). - Cache used characters in a bitset to reduce memory overhead to just 32 bytes. - On my core2 this code is faster except when the checked string was very short (smaller than the list of delimiters). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@111817 91177308-0d34-0410-b5e6-96231b3b80d8 --- lib/Support/StringRef.cpp | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'lib/Support/StringRef.cpp') diff --git a/lib/Support/StringRef.cpp b/lib/Support/StringRef.cpp index ca0f518a88..40b732c62d 100644 --- a/lib/Support/StringRef.cpp +++ b/lib/Support/StringRef.cpp @@ -9,6 +9,7 @@ #include "llvm/ADT/StringRef.h" #include "llvm/ADT/APInt.h" +#include using namespace llvm; @@ -153,11 +154,15 @@ size_t StringRef::rfind(StringRef Str) const { /// find_first_of - Find the first character in the string that is in \arg /// Chars, or npos if not found. /// -/// Note: O(size() * Chars.size()) +/// Note: O(size() + Chars.size()) StringRef::size_type StringRef::find_first_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), e = Length; i != e; ++i) - if (Chars.find(Data[i]) != npos) + if (CharBits.test((unsigned char)Data[i])) return i; return npos; } @@ -174,11 +179,15 @@ StringRef::size_type StringRef::find_first_not_of(char C, size_t From) const { /// find_first_not_of - Find the first character in the string that is not /// in the string \arg Chars, or npos if not found. /// -/// Note: O(size() * Chars.size()) +/// Note: O(size() + Chars.size()) StringRef::size_type StringRef::find_first_not_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), e = Length; i != e; ++i) - if (Chars.find(Data[i]) == npos) + if (!CharBits.test((unsigned char)Data[i])) return i; return npos; } -- cgit v1.2.3-18-g5258