Add an override to StringRef::getAsInteger which parses into an APInt.

It gets its own implementation totally divorced from the (presumably
performance-sensitive) routines which parse into a uint64_t.

Add APInt::operator|=(uint64_t), which is situationally much better than
using a full APInt.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97381 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/ADT/APInt.h

@@ -150,7 +150,17 @@ class APInt {
     return isSingleWord() ? VAL : pVal[whichWord(bitPosition)];
   }
 
+  /// Converts a string into a number.  The string must be non-empty
+  /// and well-formed as a number of the given base. The bit-width
+  /// must be sufficient to hold the result.
+  ///
   /// This is used by the constructors that take string arguments.
+  ///
+  /// StringRef::getAsInteger is superficially similar but (1) does
+  /// not assume that the string is well-formed and (2) grows the
+  /// result to hold the input.
+  ///
+  /// @param radix 2, 8, 10, or 16
   /// @brief Convert a char array into an APInt
   void fromString(unsigned numBits, const StringRef &str, uint8_t radix);
 
@@ -571,6 +581,21 @@ public:
   /// @brief Bitwise OR assignment operator.
   APInt& operator|=(const APInt& RHS);
 
+  /// Performs a bitwise OR operation on this APInt and RHS. RHS is
+  /// logically zero-extended or truncated to match the bit-width of
+  /// the LHS.
+  /// 
+  /// @brief Bitwise OR assignment operator.
+  APInt& operator|=(uint64_t RHS) {
+    if (isSingleWord()) {
+      VAL |= RHS;
+      clearUnusedBits();
+    } else {
+      pVal[0] |= RHS;
+    }
+    return *this;
+  }
+
   /// Performs a bitwise XOR operation on this APInt and RHS. The result is
   /// assigned to *this.
   /// @returns *this after XORing with RHS.

include/llvm/ADT/StringRef.h

@@ -18,6 +18,7 @@
 namespace llvm {
   template<typename T>
   class SmallVectorImpl;
+  class APInt;
 
   /// StringRef - Represent a constant reference to a string, i.e. a character
   /// array and a length, which need not be null terminated.
@@ -273,6 +274,19 @@ namespace llvm {
 
     // TODO: Provide overloads for int/unsigned that check for overflow.
 
+    /// getAsInteger - Parse the current string as an integer of the
+    /// specified radix, or of an autosensed radix if the radix given
+    /// is 0.  The current value in Result is discarded, and the
+    /// storage is changed to be wide enough to store the parsed
+    /// integer.
+    ///
+    /// Returns true if the string does not solely consist of a valid
+    /// non-empty number in the appropriate base.
+    ///
+    /// APInt::fromString is superficially similar but assumes the
+    /// string is well-formed in the given radix.
+    bool getAsInteger(unsigned Radix, APInt &Result) const;
+
     /// @}
     /// @name Substring Operations
     /// @{

lib/Support/StringRef.cpp

@@ -8,6 +8,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/ADT/StringRef.h"
+#include "llvm/ADT/APInt.h"
 
 using namespace llvm;
 
@@ -172,23 +173,28 @@ size_t StringRef::count(StringRef Str) const {
   return Count;
 }
 
+static unsigned GetAutoSenseRadix(StringRef &Str) {
+  if (Str.startswith("0x")) {
+    Str = Str.substr(2);
+    return 16;
+  } else if (Str.startswith("0b")) {
+    Str = Str.substr(2);
+    return 2;
+  } else if (Str.startswith("0")) {
+    return 8;
+  } else {
+    return 10;
+  }
+}
+
+
 /// GetAsUnsignedInteger - Workhorse method that converts a integer character
 /// sequence of radix up to 36 to an unsigned long long value.
 static bool GetAsUnsignedInteger(StringRef Str, unsigned Radix,
                                  unsigned long long &Result) {
   // Autosense radix if not specified.
-  if (Radix == 0) {
+  if (Radix == 0)
-    if (Str.startswith("0x")) {
+    Radix = GetAutoSenseRadix(Str);
-      Str = Str.substr(2);
-      Radix = 16;
-    } else if (Str.startswith("0b")) {
-      Str = Str.substr(2);
-      Radix = 2;
-    } else if (Str.startswith("0"))
-      Radix = 8;
-    else
-      Radix = 10;
-  }
   
   // Empty strings (after the radix autosense) are invalid.
   if (Str.empty()) return true;
@@ -272,3 +278,78 @@ bool StringRef::getAsInteger(unsigned Radix, unsigned &Result) const {
   Result = Val;
   return false;
 }  
+
+bool StringRef::getAsInteger(unsigned Radix, APInt &Result) const {
+  StringRef Str = *this;
+
+  // Autosense radix if not specified.
+  if (Radix == 0)
+    Radix = GetAutoSenseRadix(Str);
+
+  assert(Radix > 1 && Radix <= 36);
+  
+  // Empty strings (after the radix autosense) are invalid.
+  if (Str.empty()) return true;
+
+  // Skip leading zeroes.  This can be a significant improvement if
+  // it means we don't need > 64 bits.
+  while (!Str.empty() && Str.front() == '0')
+    Str = Str.substr(1);
+
+  // If it was nothing but zeroes....
+  if (Str.empty()) {
+    Result = APInt(64, 0);
+    return false;
+  }
+
+  // (Over-)estimate the required number of bits.
+  unsigned Log2Radix = 0;
+  while ((1U << Log2Radix) < Radix) Log2Radix++;
+  bool IsPowerOf2Radix = ((1U << Log2Radix) == Radix);
+
+  unsigned BitWidth = Log2Radix * Str.size();
+  if (BitWidth < Result.getBitWidth())
+    BitWidth = Result.getBitWidth(); // don't shrink the result
+  else
+    Result.zext(BitWidth);
+
+  APInt RadixAP, CharAP; // unused unless !IsPowerOf2Radix
+  if (!IsPowerOf2Radix) {
+    // These must have the same bit-width as Result.
+    RadixAP = APInt(BitWidth, Radix);
+    CharAP = APInt(BitWidth, 0);
+  }
+
+  // Parse all the bytes of the string given this radix.
+  Result = 0;
+  while (!Str.empty()) {
+    unsigned CharVal;
+    if (Str[0] >= '0' && Str[0] <= '9')
+      CharVal = Str[0]-'0';
+    else if (Str[0] >= 'a' && Str[0] <= 'z')
+      CharVal = Str[0]-'a'+10;
+    else if (Str[0] >= 'A' && Str[0] <= 'Z')
+      CharVal = Str[0]-'A'+10;
+    else
+      return true;
+    
+    // If the parsed value is larger than the integer radix, the string is
+    // invalid.
+    if (CharVal >= Radix)
+      return true;
+    
+    // Add in this character.
+    if (IsPowerOf2Radix) {
+      Result <<= Log2Radix;
+      Result |= CharVal;
+    } else {
+      Result *= RadixAP;
+      CharAP = CharVal;
+      Result += CharAP;
+    }
+
+    Str = Str.substr(1);
+  }
+  
+  return false;
+}