Use the testcase from PR2791.

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

diff --git a/lib/Support/StringExtras.cpp b/lib/Support/StringExtras.cpp
index 011ce280f05080f4154f7b8d9381ea27fb15c2ff..1618086e602ea0b424488f5b2f89f98ff2d3bd73 100644 (file)
--- a/lib/Support/StringExtras.cpp
+++ b/lib/Support/StringExtras.cpp
@@ -1,17 +1,18 @@
 //===-- StringExtras.cpp - Implement the StringExtras header --------------===//
-// 
+//
 //                     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.
+//
 //===----------------------------------------------------------------------===//
 //
 // This file implements the StringExtras.h header
 //
 //===----------------------------------------------------------------------===//
 
-#include "Support/StringExtras.h"
+#include "llvm/ADT/StringExtras.h"
+#include <cstring>
 using namespace llvm;
 
 /// getToken - This function extracts one token from source, ignoring any
@@ -21,7 +22,7 @@ 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 =
@@ -35,9 +36,79 @@ std::string llvm::getToken(std::string &Source, const char *Delimiters) {
 
   // Create the return token.
   std::string Result = std::string(Source.begin()+Start, Source.begin()+End);
-  
+
   // Erase the token that we read in.
   Source.erase(Source.begin(), Source.begin()+End);
-  
+
   return Result;
 }
+
+/// 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);
+  }
+}
+
+
+
+/// UnescapeString - Modify the argument string, turning two character sequences
+/// @verbatim
+/// 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).
+/// @endverbatim
+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;
+      case '\\': Str[i] = '\\'; break;
+      }
+      // Nuke the second character.
+      Str.erase(Str.begin()+i+1);
+    }
+  }
+}
+
+/// 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] == '"') {
+      Str.insert(Str.begin()+i++, '\\');
+    } 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));
+    }
+  }
+}