Distinguish "a," from "a". The first one splits into "a" + "" and the second one...

[oota-llvm.git] / lib / Support / StringExtras.cpp

diff --git a/lib/Support/StringExtras.cpp b/lib/Support/StringExtras.cpp
index 8ce371535b6da1fdb1bd3704fdf236ee358f225c..1b233ab200ae703b79b273d59d37cdf2c3509a21 100644 (file)
--- a/lib/Support/StringExtras.cpp
+++ b/lib/Support/StringExtras.cpp
@@ -2,8 +2,8 @@
 //
 //                     The LLVM Compiler Infrastructure
 //
-// This file was developed by the LLVM research group and is distributed under
-// the University of Illinois Open Source License. See LICENSE.TXT for details.
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 //
@@ -12,6 +12,8 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/ADT/StringExtras.h"
+#include "llvm/ADT/SmallVector.h"
+#include <cstring>
 using namespace llvm;
 
 /// getToken - This function extracts one token from source, ignoring any
@@ -21,7 +23,7 @@ using namespace llvm;
 /// The Source source string is updated in place to remove the returned string
 /// and any delimiter prefix from it.
 std::string llvm::getToken(std::string &Source, const char *Delimiters) {
-  unsigned NumDelimiters = std::strlen(Delimiters);
+  size_t NumDelimiters = std::strlen(Delimiters);
 
   // Figure out where the token starts.
   std::string::size_type Start =
@@ -42,52 +44,37 @@ std::string llvm::getToken(std::string &Source, const char *Delimiters) {
   return Result;
 }
 
-
-/// UnescapeString - Modify the argument string, turning two character sequences
-/// like '\\' 'n' into '\n'.  This handles: \e \a \b \f \n \r \t \v \' \\ and
-/// \num (where num is a 1-3 byte octal value).
-void llvm::UnescapeString(std::string &Str) {
-  for (unsigned i = 0; i != Str.size(); ++i) {
-    if (Str[i] == '\\' && i != Str.size()-1) {
-      switch (Str[i+1]) {
-      default: continue;  // Don't execute the code after the switch.
-      case 'a': Str[i] = '\a'; break;
-      case 'b': Str[i] = '\b'; break;
-      case 'e': Str[i] = 27; break;
-      case 'f': Str[i] = '\f'; break;
-      case 'n': Str[i] = '\n'; break;
-      case 'r': Str[i] = '\r'; break;
-      case 't': Str[i] = '\t'; break;
-      case 'v': Str[i] = '\v'; break;
-      case '\'': Str[i] = '\''; break;
-      case '\\': Str[i] = '\\'; break;
-      }
-      // Nuke the second character.
-      Str.erase(Str.begin()+i+1);
-    }
+/// SplitString - Split up the specified string according to the specified
+/// delimiters, appending the result fragments to the output list.
+void llvm::SplitString(const std::string &Source, 
+                       std::vector<std::string> &OutFragments,
+                       const char *Delimiters) {
+  std::string S = Source;
+  
+  std::string S2 = getToken(S, Delimiters);
+  while (!S2.empty()) {
+    OutFragments.push_back(S2);
+    S2 = getToken(S, Delimiters);
   }
 }
 
-/// EscapeString - Modify the argument string, turning '\\' and anything that
-/// doesn't satisfy std::isprint into an escape sequence.
-void llvm::EscapeString(std::string &Str) {
-  for (unsigned i = 0; i != Str.size(); ++i) {
-    if (Str[i] == '\\') {
-      ++i;
-      Str.insert(Str.begin()+i, '\\');
-    } else if (Str[i] == '\t') {
-      Str[i++] = '\\';
-      Str.insert(Str.begin()+i, 't');
-    } else if (Str[i] == '\n') {
-      Str[i++] = '\\';
-      Str.insert(Str.begin()+i, 'n');
-    } else if (!std::isprint(Str[i])) {
-      // Always expand to a 3-digit octal escape.
-      unsigned Char = Str[i];
-      Str[i++] = '\\';
-      Str.insert(Str.begin()+i++, '0'+((Char/64) & 7));
-      Str.insert(Str.begin()+i++, '0'+((Char/8)  & 7));
-      Str.insert(Str.begin()+i  , '0'+( Char     & 7));
-    }
+void llvm::StringRef::split(SmallVectorImpl<StringRef> &A,
+                            StringRef Separators, int MaxSplit,
+                            bool KeepEmpty) const {
+  StringRef rest = *this;
+
+  // rest.data() is used to distinguish cases like "a," that splits into
+  // "a" + "" and "a" that splits into "a" + 0.
+  for (int splits = 0;
+       rest.data() != NULL && (MaxSplit < 0 || splits < MaxSplit);
+       ++splits) {
+    std::pair<llvm::StringRef, llvm::StringRef> p = rest.split(Separators);
+
+    if (p.first.size() != 0 || KeepEmpty)
+      A.push_back(p.first);
+    rest = p.second;
   }
+  // If we have a tail left, add it.
+  if (rest.data() != NULL && (rest.size() != 0 || KeepEmpty))
+    A.push_back(rest);
 }