[llvm] [llvm] Improve implementation of StringRef::find_last_of and cie (PR #71865)

via llvm-commits llvm-commits at lists.llvm.org
Wed Nov 15 06:05:37 PST 2023


github-actions[bot] wrote:

<!--LLVM CODE FORMAT COMMENT: {clang-format}-->


:warning: C/C++ code formatter, clang-format found issues in your code. :warning:

<details>
<summary>
You can test this locally with the following command:
</summary>

``````````bash
git-clang-format --diff 2060bfcdc7eb704647c64bf925cdceb94c1f535f 5ebe6d8729ea7b9fa69f2c1ff39c8ddd76997503 -- llvm/lib/Support/StringRef.cpp
``````````

</details>

<details>
<summary>
View the diff from clang-format here.
</summary>

``````````diff
diff --git a/llvm/lib/Support/StringRef.cpp b/llvm/lib/Support/StringRef.cpp
index c9923cdfdb..b6c60c77d8 100644
--- a/llvm/lib/Support/StringRef.cpp
+++ b/llvm/lib/Support/StringRef.cpp
@@ -305,358 +305,360 @@ StringRef::size_type StringRef::find_last_of(StringRef Chars,
     return vectorized_find_last_of_specialized(Data, Sz, Chars[0], Chars[1]);
 #endif
 
-  std::bitset<1 << CHAR_BIT> CharBits;
-  for (char C : Chars)
-    CharBits.set((unsigned char)C);
+    std::bitset<1 << CHAR_BIT> CharBits;
+    for (char C : Chars)
+      CharBits.set((unsigned char)C);
 
-  for (size_type i = Sz - 1, e = -1; i != e; --i)
-    if (CharBits.test((unsigned char)Data[i]))
-      return i;
-  return npos;
-}
+    for (size_type i = Sz - 1, e = -1; i != e; --i)
+      if (CharBits.test((unsigned char)Data[i]))
+        return i;
+    return npos;
+  }
 
-/// find_last_not_of - Find the last character in the string that is not
-/// \arg C, or npos if not found.
-StringRef::size_type StringRef::find_last_not_of(char C, size_t From) const {
-  for (size_type i = std::min(From, Length) - 1, e = -1; i != e; --i)
-    if (Data[i] != C)
-      return i;
-  return npos;
-}
+  /// find_last_not_of - Find the last character in the string that is not
+  /// \arg C, or npos if not found.
+  StringRef::size_type StringRef::find_last_not_of(char C, size_t From) const {
+    for (size_type i = std::min(From, Length) - 1, e = -1; i != e; --i)
+      if (Data[i] != C)
+        return i;
+    return npos;
+  }
 
-/// find_last_not_of - Find the last character in the string that is not in
-/// \arg Chars, or npos if not found.
-///
-/// Note: O(size() + Chars.size())
-StringRef::size_type StringRef::find_last_not_of(StringRef Chars,
-                                                 size_t From) const {
-  std::bitset<1 << CHAR_BIT> CharBits;
-  for (char C : Chars)
-    CharBits.set((unsigned char)C);
+  /// find_last_not_of - Find the last character in the string that is not in
+  /// \arg Chars, or npos if not found.
+  ///
+  /// Note: O(size() + Chars.size())
+  StringRef::size_type StringRef::find_last_not_of(StringRef Chars, size_t From)
+      const {
+    std::bitset<1 << CHAR_BIT> CharBits;
+    for (char C : Chars)
+      CharBits.set((unsigned char)C);
+
+    for (size_type i = std::min(From, Length) - 1, e = -1; i != e; --i)
+      if (!CharBits.test((unsigned char)Data[i]))
+        return i;
+    return npos;
+  }
 
-  for (size_type i = std::min(From, Length) - 1, e = -1; i != e; --i)
-    if (!CharBits.test((unsigned char)Data[i]))
-      return i;
-  return npos;
-}
+  void StringRef::split(SmallVectorImpl<StringRef> & A, StringRef Separator,
+                        int MaxSplit, bool KeepEmpty) const {
+    StringRef S = *this;
+
+    // Count down from MaxSplit. When MaxSplit is -1, this will just split
+    // "forever". This doesn't support splitting more than 2^31 times
+    // intentionally; if we ever want that we can make MaxSplit a 64-bit integer
+    // but that seems unlikely to be useful.
+    while (MaxSplit-- != 0) {
+      size_t Idx = S.find(Separator);
+      if (Idx == npos)
+        break;
+
+      // Push this split.
+      if (KeepEmpty || Idx > 0)
+        A.push_back(S.slice(0, Idx));
+
+      // Jump forward.
+      S = S.slice(Idx + Separator.size(), npos);
+    }
 
-void StringRef::split(SmallVectorImpl<StringRef> &A,
-                      StringRef Separator, int MaxSplit,
-                      bool KeepEmpty) const {
-  StringRef S = *this;
-
-  // Count down from MaxSplit. When MaxSplit is -1, this will just split
-  // "forever". This doesn't support splitting more than 2^31 times
-  // intentionally; if we ever want that we can make MaxSplit a 64-bit integer
-  // but that seems unlikely to be useful.
-  while (MaxSplit-- != 0) {
-    size_t Idx = S.find(Separator);
-    if (Idx == npos)
-      break;
-
-    // Push this split.
-    if (KeepEmpty || Idx > 0)
-      A.push_back(S.slice(0, Idx));
-
-    // Jump forward.
-    S = S.slice(Idx + Separator.size(), npos);
+    // Push the tail.
+    if (KeepEmpty || !S.empty())
+      A.push_back(S);
   }
 
-  // Push the tail.
-  if (KeepEmpty || !S.empty())
-    A.push_back(S);
-}
+  void StringRef::split(SmallVectorImpl<StringRef> & A, char Separator,
+                        int MaxSplit, bool KeepEmpty) const {
+    StringRef S = *this;
+
+    // Count down from MaxSplit. When MaxSplit is -1, this will just split
+    // "forever". This doesn't support splitting more than 2^31 times
+    // intentionally; if we ever want that we can make MaxSplit a 64-bit integer
+    // but that seems unlikely to be useful.
+    while (MaxSplit-- != 0) {
+      size_t Idx = S.find(Separator);
+      if (Idx == npos)
+        break;
+
+      // Push this split.
+      if (KeepEmpty || Idx > 0)
+        A.push_back(S.slice(0, Idx));
+
+      // Jump forward.
+      S = S.slice(Idx + 1, npos);
+    }
 
-void StringRef::split(SmallVectorImpl<StringRef> &A, char Separator,
-                      int MaxSplit, bool KeepEmpty) const {
-  StringRef S = *this;
-
-  // Count down from MaxSplit. When MaxSplit is -1, this will just split
-  // "forever". This doesn't support splitting more than 2^31 times
-  // intentionally; if we ever want that we can make MaxSplit a 64-bit integer
-  // but that seems unlikely to be useful.
-  while (MaxSplit-- != 0) {
-    size_t Idx = S.find(Separator);
-    if (Idx == npos)
-      break;
-
-    // Push this split.
-    if (KeepEmpty || Idx > 0)
-      A.push_back(S.slice(0, Idx));
-
-    // Jump forward.
-    S = S.slice(Idx + 1, npos);
+    // Push the tail.
+    if (KeepEmpty || !S.empty())
+      A.push_back(S);
   }
 
-  // Push the tail.
-  if (KeepEmpty || !S.empty())
-    A.push_back(S);
-}
+  //===----------------------------------------------------------------------===//
+  // Helpful Algorithms
+  //===----------------------------------------------------------------------===//
+
+  /// count - Return the number of non-overlapped occurrences of \arg Str in
+  /// the string.
+  size_t StringRef::count(StringRef Str) const {
+    size_t Count = 0;
+    size_t Pos = 0;
+    size_t N = Str.size();
+    // TODO: For an empty `Str` we return 0 for legacy reasons. Consider
+    // changing
+    //       this to `Length + 1` which is more in-line with the function
+    //       description.
+    if (!N)
+      return 0;
+    while ((Pos = find(Str, Pos)) != npos) {
+      ++Count;
+      Pos += N;
+    }
+    return Count;
+  }
 
-//===----------------------------------------------------------------------===//
-// Helpful Algorithms
-//===----------------------------------------------------------------------===//
+  static unsigned GetAutoSenseRadix(StringRef & Str) {
+    if (Str.empty())
+      return 10;
 
-/// count - Return the number of non-overlapped occurrences of \arg Str in
-/// the string.
-size_t StringRef::count(StringRef Str) const {
-  size_t Count = 0;
-  size_t Pos = 0;
-  size_t N = Str.size();
-  // TODO: For an empty `Str` we return 0 for legacy reasons. Consider changing
-  //       this to `Length + 1` which is more in-line with the function
-  //       description.
-  if (!N)
-    return 0;
-  while ((Pos = find(Str, Pos)) != npos) {
-    ++Count;
-    Pos += N;
-  }
-  return Count;
-}
+    if (Str.starts_with("0x") || Str.starts_with("0X")) {
+      Str = Str.substr(2);
+      return 16;
+    }
 
-static unsigned GetAutoSenseRadix(StringRef &Str) {
-  if (Str.empty())
-    return 10;
+    if (Str.starts_with("0b") || Str.starts_with("0B")) {
+      Str = Str.substr(2);
+      return 2;
+    }
 
-  if (Str.starts_with("0x") || Str.starts_with("0X")) {
-    Str = Str.substr(2);
-    return 16;
-  }
+    if (Str.starts_with("0o")) {
+      Str = Str.substr(2);
+      return 8;
+    }
 
-  if (Str.starts_with("0b") || Str.starts_with("0B")) {
-    Str = Str.substr(2);
-    return 2;
-  }
+    if (Str[0] == '0' && Str.size() > 1 && isDigit(Str[1])) {
+      Str = Str.substr(1);
+      return 8;
+    }
 
-  if (Str.starts_with("0o")) {
-    Str = Str.substr(2);
-    return 8;
+    return 10;
   }
 
-  if (Str[0] == '0' && Str.size() > 1 && isDigit(Str[1])) {
-    Str = Str.substr(1);
-    return 8;
+  bool llvm::consumeUnsignedInteger(StringRef & Str, unsigned Radix,
+                                    unsigned long long &Result) {
+    // Autosense radix if not specified.
+    if (Radix == 0)
+      Radix = GetAutoSenseRadix(Str);
+
+    // Empty strings (after the radix autosense) are invalid.
+    if (Str.empty())
+      return true;
+
+    // Parse all the bytes of the string given this radix.  Watch for overflow.
+    StringRef Str2 = Str;
+    Result = 0;
+    while (!Str2.empty()) {
+      unsigned CharVal;
+      if (Str2[0] >= '0' && Str2[0] <= '9')
+        CharVal = Str2[0] - '0';
+      else if (Str2[0] >= 'a' && Str2[0] <= 'z')
+        CharVal = Str2[0] - 'a' + 10;
+      else if (Str2[0] >= 'A' && Str2[0] <= 'Z')
+        CharVal = Str2[0] - 'A' + 10;
+      else
+        break;
+
+      // If the parsed value is larger than the integer radix, we cannot
+      // consume any more characters.
+      if (CharVal >= Radix)
+        break;
+
+      // Add in this character.
+      unsigned long long PrevResult = Result;
+      Result = Result * Radix + CharVal;
+
+      // Check for overflow by shifting back and seeing if bits were lost.
+      if (Result / Radix < PrevResult)
+        return true;
+
+      Str2 = Str2.substr(1);
+    }
+
+    // We consider the operation a failure if no characters were consumed
+    // successfully.
+    if (Str.size() == Str2.size())
+      return true;
+
+    Str = Str2;
+    return false;
   }
 
-  return 10;
-}
+  bool llvm::consumeSignedInteger(StringRef & Str, unsigned Radix,
+                                  long long &Result) {
+    unsigned long long ULLVal;
+
+    // Handle positive strings first.
+    if (Str.empty() || Str.front() != '-') {
+      if (consumeUnsignedInteger(Str, Radix, ULLVal) ||
+          // Check for value so large it overflows a signed value.
+          (long long)ULLVal < 0)
+        return true;
+      Result = ULLVal;
+      return false;
+    }
 
-bool llvm::consumeUnsignedInteger(StringRef &Str, unsigned Radix,
-                                  unsigned long long &Result) {
-  // Autosense radix if not specified.
-  if (Radix == 0)
-    Radix = GetAutoSenseRadix(Str);
-
-  // Empty strings (after the radix autosense) are invalid.
-  if (Str.empty()) return true;
-
-  // Parse all the bytes of the string given this radix.  Watch for overflow.
-  StringRef Str2 = Str;
-  Result = 0;
-  while (!Str2.empty()) {
-    unsigned CharVal;
-    if (Str2[0] >= '0' && Str2[0] <= '9')
-      CharVal = Str2[0] - '0';
-    else if (Str2[0] >= 'a' && Str2[0] <= 'z')
-      CharVal = Str2[0] - 'a' + 10;
-    else if (Str2[0] >= 'A' && Str2[0] <= 'Z')
-      CharVal = Str2[0] - 'A' + 10;
-    else
-      break;
-
-    // If the parsed value is larger than the integer radix, we cannot
-    // consume any more characters.
-    if (CharVal >= Radix)
-      break;
-
-    // Add in this character.
-    unsigned long long PrevResult = Result;
-    Result = Result * Radix + CharVal;
-
-    // Check for overflow by shifting back and seeing if bits were lost.
-    if (Result / Radix < PrevResult)
+    // Get the positive part of the value.
+    StringRef Str2 = Str.drop_front(1);
+    if (consumeUnsignedInteger(Str2, Radix, ULLVal) ||
+        // Reject values so large they'd overflow as negative signed, but allow
+        // "-0".  This negates the unsigned so that the negative isn't undefined
+        // on signed overflow.
+        (long long)-ULLVal > 0)
       return true;
 
-    Str2 = Str2.substr(1);
+    Str = Str2;
+    Result = -ULLVal;
+    return false;
   }
 
-  // We consider the operation a failure if no characters were consumed
-  // successfully.
-  if (Str.size() == Str2.size())
-    return true;
+  /// GetAsUnsignedInteger - Workhorse method that converts a integer character
+  /// sequence of radix up to 36 to an unsigned long long value.
+  bool llvm::getAsUnsignedInteger(StringRef Str, unsigned Radix,
+                                  unsigned long long &Result) {
+    if (consumeUnsignedInteger(Str, Radix, Result))
+      return true;
 
-  Str = Str2;
-  return false;
-}
+    // For getAsUnsignedInteger, we require the whole string to be consumed or
+    // else we consider it a failure.
+    return !Str.empty();
+  }
 
-bool llvm::consumeSignedInteger(StringRef &Str, unsigned Radix,
+  bool llvm::getAsSignedInteger(StringRef Str, unsigned Radix,
                                 long long &Result) {
-  unsigned long long ULLVal;
-
-  // Handle positive strings first.
-  if (Str.empty() || Str.front() != '-') {
-    if (consumeUnsignedInteger(Str, Radix, ULLVal) ||
-        // Check for value so large it overflows a signed value.
-        (long long)ULLVal < 0)
+    if (consumeSignedInteger(Str, Radix, Result))
       return true;
-    Result = ULLVal;
-    return false;
+
+    // For getAsSignedInteger, we require the whole string to be consumed or
+    // else we consider it a failure.
+    return !Str.empty();
   }
 
-  // Get the positive part of the value.
-  StringRef Str2 = Str.drop_front(1);
-  if (consumeUnsignedInteger(Str2, Radix, ULLVal) ||
-      // Reject values so large they'd overflow as negative signed, but allow
-      // "-0".  This negates the unsigned so that the negative isn't undefined
-      // on signed overflow.
-      (long long)-ULLVal > 0)
-    return true;
-
-  Str = Str2;
-  Result = -ULLVal;
-  return false;
-}
+  bool StringRef::consumeInteger(unsigned Radix, APInt &Result) {
+    StringRef Str = *this;
 
-/// GetAsUnsignedInteger - Workhorse method that converts a integer character
-/// sequence of radix up to 36 to an unsigned long long value.
-bool llvm::getAsUnsignedInteger(StringRef Str, unsigned Radix,
-                                unsigned long long &Result) {
-  if (consumeUnsignedInteger(Str, Radix, Result))
-    return true;
+    // Autosense radix if not specified.
+    if (Radix == 0)
+      Radix = GetAutoSenseRadix(Str);
 
-  // For getAsUnsignedInteger, we require the whole string to be consumed or
-  // else we consider it a failure.
-  return !Str.empty();
-}
+    assert(Radix > 1 && Radix <= 36);
 
-bool llvm::getAsSignedInteger(StringRef Str, unsigned Radix,
-                              long long &Result) {
-  if (consumeSignedInteger(Str, Radix, Result))
-    return true;
+    // Empty strings (after the radix autosense) are invalid.
+    if (Str.empty())
+      return true;
 
-  // For getAsSignedInteger, we require the whole string to be consumed or else
-  // we consider it a failure.
-  return !Str.empty();
-}
+    // 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);
 
-bool StringRef::consumeInteger(unsigned Radix, APInt &Result) {
-  StringRef Str = *this;
+    // If it was nothing but zeroes....
+    if (Str.empty()) {
+      Result = APInt(64, 0);
+      *this = Str;
+      return false;
+    }
 
-  // Autosense radix if not specified.
-  if (Radix == 0)
-    Radix = GetAutoSenseRadix(Str);
+    // (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 if (BitWidth > Result.getBitWidth())
+      Result = 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);
+    }
 
-  assert(Radix > 1 && Radix <= 36);
+    // 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
+        break;
+
+      // If the parsed value is larger than the integer radix, the string is
+      // invalid.
+      if (CharVal >= Radix)
+        break;
+
+      // Add in this character.
+      if (IsPowerOf2Radix) {
+        Result <<= Log2Radix;
+        Result |= CharVal;
+      } else {
+        Result *= RadixAP;
+        CharAP = CharVal;
+        Result += CharAP;
+      }
 
-  // Empty strings (after the radix autosense) are invalid.
-  if (Str.empty()) return true;
+      Str = Str.substr(1);
+    }
 
-  // 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);
+    // We consider the operation a failure if no characters were consumed
+    // successfully.
+    if (size() == Str.size())
+      return true;
 
-  // If it was nothing but zeroes....
-  if (Str.empty()) {
-    Result = APInt(64, 0);
     *this = Str;
     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 if (BitWidth > Result.getBitWidth())
-    Result = 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
-      break;
-
-    // If the parsed value is larger than the integer radix, the string is
-    // invalid.
-    if (CharVal >= Radix)
-      break;
-
-    // Add in this character.
-    if (IsPowerOf2Radix) {
-      Result <<= Log2Radix;
-      Result |= CharVal;
-    } else {
-      Result *= RadixAP;
-      CharAP = CharVal;
-      Result += CharAP;
-    }
+  bool StringRef::getAsInteger(unsigned Radix, APInt &Result) const {
+    StringRef Str = *this;
+    if (Str.consumeInteger(Radix, Result))
+      return true;
 
-    Str = Str.substr(1);
+    // For getAsInteger, we require the whole string to be consumed or else we
+    // consider it a failure.
+    return !Str.empty();
   }
 
-  // We consider the operation a failure if no characters were consumed
-  // successfully.
-  if (size() == Str.size())
-    return true;
-
-  *this = Str;
-  return false;
-}
-
-bool StringRef::getAsInteger(unsigned Radix, APInt &Result) const {
-  StringRef Str = *this;
-  if (Str.consumeInteger(Radix, Result))
-    return true;
-
-  // For getAsInteger, we require the whole string to be consumed or else we
-  // consider it a failure.
-  return !Str.empty();
-}
+  bool StringRef::getAsDouble(double &Result, bool AllowInexact) const {
+    APFloat F(0.0);
+    auto StatusOrErr = F.convertFromString(*this, APFloat::rmNearestTiesToEven);
+    if (errorToBool(StatusOrErr.takeError()))
+      return true;
 
-bool StringRef::getAsDouble(double &Result, bool AllowInexact) const {
-  APFloat F(0.0);
-  auto StatusOrErr = F.convertFromString(*this, APFloat::rmNearestTiesToEven);
-  if (errorToBool(StatusOrErr.takeError()))
-    return true;
+    APFloat::opStatus Status = *StatusOrErr;
+    if (Status != APFloat::opOK) {
+      if (!AllowInexact || !(Status & APFloat::opInexact))
+        return true;
+    }
 
-  APFloat::opStatus Status = *StatusOrErr;
-  if (Status != APFloat::opOK) {
-    if (!AllowInexact || !(Status & APFloat::opInexact))
-      return true;
+    Result = F.convertToDouble();
+    return false;
   }
 
-  Result = F.convertToDouble();
-  return false;
-}
-
-// Implementation of StringRef hashing.
-hash_code llvm::hash_value(StringRef S) {
-  return hash_combine_range(S.begin(), S.end());
-}
+  // Implementation of StringRef hashing.
+  hash_code llvm::hash_value(StringRef S) {
+    return hash_combine_range(S.begin(), S.end());
+  }
 
-unsigned DenseMapInfo<StringRef, void>::getHashValue(StringRef Val) {
-  assert(Val.data() != getEmptyKey().data() &&
-         "Cannot hash the empty key!");
-  assert(Val.data() != getTombstoneKey().data() &&
-         "Cannot hash the tombstone key!");
-  return (unsigned)(hash_value(Val));
-}
+  unsigned DenseMapInfo<StringRef, void>::getHashValue(StringRef Val) {
+    assert(Val.data() != getEmptyKey().data() && "Cannot hash the empty key!");
+    assert(Val.data() != getTombstoneKey().data() &&
+           "Cannot hash the tombstone key!");
+    return (unsigned)(hash_value(Val));
+  }

``````````

</details>


https://github.com/llvm/llvm-project/pull/71865


More information about the llvm-commits mailing list