[wpiutil] Rewrite StringExtras for std::string_view (#3394)

Remove unused functions and add StringRef-like convenience functions.
Minimize header dependencies.

wpiutil/src/main/native/cpp/StringExtras.cpp

@@ -0,0 +1,252 @@
+// Copyright (c) FIRST and other WPILib contributors.
+// Open Source Software; you can modify and/or share it under the terms of
+// the WPILib BSD license file in the root directory of this project.
+
+//===-- StringExtras.cpp - Implement the StringExtras header --------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// 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 "wpi/StringExtras.h"
+
+#include <algorithm>
+#include <cstdlib>
+#include <string_view>
+
+#include "wpi/SmallString.h"
+#include "wpi/SmallVector.h"
+#include "wpi/StringRef.h"
+
+// strncasecmp() is not available on non-POSIX systems, so define an
+// alternative function here.
+static int ascii_strncasecmp(const char* lhs, const char* rhs,
+                             size_t length) noexcept {
+  for (size_t i = 0; i < length; ++i) {
+    unsigned char lhc = wpi::toLower(lhs[i]);
+    unsigned char rhc = wpi::toLower(rhs[i]);
+    if (lhc != rhc) {
+      return lhc < rhc ? -1 : 1;
+    }
+  }
+  return 0;
+}
+
+int wpi::compare_lower(std::string_view lhs, std::string_view rhs) noexcept {
+  if (int Res = ascii_strncasecmp(lhs.data(), rhs.data(),
+                                  (std::min)(lhs.size(), rhs.size()))) {
+    return Res;
+  }
+  if (lhs.size() == rhs.size()) {
+    return 0;
+  }
+  return lhs.size() < rhs.size() ? -1 : 1;
+}
+
+std::string_view::size_type wpi::find_lower(
+    std::string_view str, char ch, std::string_view::size_type from) noexcept {
+  char lch = toLower(ch);
+  auto s = drop_front(str, from);
+  while (!s.empty()) {
+    if (toLower(s.front()) == lch) {
+      return str.size() - s.size();
+    }
+    s.remove_prefix(1);
+  }
+  return std::string_view::npos;
+}
+
+std::string_view::size_type wpi::find_lower(
+    std::string_view str, std::string_view other,
+    std::string_view::size_type from) noexcept {
+  auto s = str.substr(from);
+  while (s.size() >= other.size()) {
+    if (starts_with_lower(s, other)) {
+      return from;
+    }
+    s.remove_prefix(1);
+    ++from;
+  }
+  return std::string_view::npos;
+}
+
+std::string_view::size_type wpi::rfind_lower(
+    std::string_view str, char ch, std::string_view::size_type from) noexcept {
+  from = (std::min)(from, str.size());
+  auto data = str.data();
+  std::string_view::size_type i = from;
+  while (i != 0) {
+    --i;
+    if (toLower(data[i]) == toLower(ch)) {
+      return i;
+    }
+  }
+  return std::string_view::npos;
+}
+
+std::string_view::size_type wpi::rfind_lower(std::string_view str,
+                                             std::string_view other) noexcept {
+  std::string_view::size_type n = other.size();
+  if (n > str.size()) {
+    return std::string_view::npos;
+  }
+  for (size_t i = str.size() - n + 1, e = 0; i != e;) {
+    --i;
+    if (equals_lower(str.substr(i, n), other)) {
+      return i;
+    }
+  }
+  return std::string_view::npos;
+}
+
+bool wpi::starts_with_lower(std::string_view str,
+                            std::string_view prefix) noexcept {
+  return str.size() >= prefix.size() &&
+         ascii_strncasecmp(str.data(), prefix.data(), prefix.size()) == 0;
+}
+
+bool wpi::ends_with_lower(std::string_view str,
+                          std::string_view suffix) noexcept {
+  return str.size() >= suffix.size() &&
+         ascii_strncasecmp(str.data() + str.size() - suffix.size(),
+                           suffix.data(), suffix.size()) == 0;
+}
+
+void wpi::split(std::string_view str, SmallVectorImpl<std::string_view>& arr,
+                std::string_view separator, int maxSplit,
+                bool keepEmpty) noexcept {
+  std::string_view s = str;
+
+  // 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) {
+    auto idx = s.find(separator);
+    if (idx == std::string_view::npos) {
+      break;
+    }
+
+    // Push this split.
+    if (keepEmpty || idx > 0) {
+      arr.push_back(slice(s, 0, idx));
+    }
+
+    // Jump forward.
+    s = slice(s, idx + separator.size(), std::string_view::npos);
+  }
+
+  // Push the tail.
+  if (keepEmpty || !s.empty()) {
+    arr.push_back(s);
+  }
+}
+
+void wpi::split(std::string_view str, SmallVectorImpl<std::string_view>& arr,
+                char separator, int maxSplit, bool keepEmpty) noexcept {
+  std::string_view s = str;
+
+  // 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 == std::string_view::npos) {
+      break;
+    }
+
+    // Push this split.
+    if (keepEmpty || idx > 0) {
+      arr.push_back(slice(s, 0, idx));
+    }
+
+    // Jump forward.
+    s = slice(s, idx + 1, std::string_view::npos);
+  }
+
+  // Push the tail.
+  if (keepEmpty || !s.empty()) {
+    arr.push_back(s);
+  }
+}
+
+bool wpi::detail::GetAsUnsignedInteger(
+    std::string_view str, unsigned radix,
+    unsigned long long& result) noexcept {  // NOLINT(runtime/int)
+  return wpi::getAsUnsignedInteger(str, radix, result);
+}
+
+bool wpi::detail::GetAsSignedInteger(
+    std::string_view str, unsigned radix,
+    long long& result) noexcept {  // NOLINT(runtime/int)
+  return wpi::getAsSignedInteger(str, radix, result);
+}
+
+bool wpi::detail::ConsumeUnsignedInteger(
+    std::string_view& str, unsigned radix,
+    unsigned long long& result) noexcept {  // NOLINT(runtime/int)
+  wpi::StringRef sref = str;
+  bool rv = wpi::consumeUnsignedInteger(sref, radix, result);
+  str = sref;
+  return rv;
+}
+
+bool wpi::detail::ConsumeSignedInteger(
+    std::string_view& str, unsigned radix,
+    long long& result) noexcept {  // NOLINT(runtime/int)
+  wpi::StringRef sref = str;
+  bool rv = wpi::consumeSignedInteger(sref, radix, result);
+  str = sref;
+  return rv;
+}
+
+template <>
+std::optional<float> wpi::parse_float<float>(std::string_view str) noexcept {
+  if (str.empty()) {
+    return std::nullopt;
+  }
+  wpi::SmallString<32> storage{str};
+  char* end;
+  float val = std::strtof(storage.c_str(), &end);
+  if (*end != '\0') {
+    return std::nullopt;
+  }
+  return val;
+}
+
+template <>
+std::optional<double> wpi::parse_float<double>(std::string_view str) noexcept {
+  if (str.empty()) {
+    return std::nullopt;
+  }
+  wpi::SmallString<32> storage{str};
+  char* end;
+  double val = std::strtod(storage.c_str(), &end);
+  if (*end != '\0') {
+    return std::nullopt;
+  }
+  return val;
+}
+
+template <>
+std::optional<long double> wpi::parse_float<long double>(
+    std::string_view str) noexcept {
+  if (str.empty()) {
+    return std::nullopt;
+  }
+  wpi::SmallString<32> storage{str};
+  char* end;
+  long double val = std::strtold(storage.c_str(), &end);
+  if (*end != '\0') {
+    return std::nullopt;
+  }
+  return val;
+}

wpiutil/src/main/native/cpp/llvm/StringExtras.cpp

@@ -1,91 +0,0 @@
-//===-- StringExtras.cpp - Implement the StringExtras header --------------===//
-//
-//                     The LLVM Compiler Infrastructure
-//
-// 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 "wpi/StringExtras.h"
-#include "wpi/SmallVector.h"
-#include "wpi/raw_ostream.h"
-using namespace wpi;
-
-/// StrInStrNoCase - Portable version of strcasestr.  Locates the first
-/// occurrence of string 's1' in string 's2', ignoring case.  Returns
-/// the offset of s2 in s1 or npos if s2 cannot be found.
-StringRef::size_type wpi::StrInStrNoCase(StringRef s1, StringRef s2) {
-  size_t N = s2.size(), M = s1.size();
-  if (N > M)
-    return StringRef::npos;
-  for (size_t i = 0, e = M - N + 1; i != e; ++i)
-    if (s1.substr(i, N).equals_lower(s2))
-      return i;
-  return StringRef::npos;
-}
-
-/// getToken - This function extracts one token from source, ignoring any
-/// leading characters that appear in the Delimiters string, and ending the
-/// token at any of the characters that appear in the Delimiters string.  If
-/// there are no tokens in the source string, an empty string is returned.
-/// The function returns a pair containing the extracted token and the
-/// remaining tail string.
-std::pair<StringRef, StringRef> wpi::getToken(StringRef Source,
-                                               StringRef Delimiters) {
-  // Figure out where the token starts.
-  StringRef::size_type Start = Source.find_first_not_of(Delimiters);
-
-  // Find the next occurrence of the delimiter.
-  StringRef::size_type End = Source.find_first_of(Delimiters, Start);
-
-  return std::make_pair(Source.slice(Start, End), Source.substr(End));
-}
-
-/// SplitString - Split up the specified string according to the specified
-/// delimiters, appending the result fragments to the output list.
-void wpi::SplitString(StringRef Source,
-                       SmallVectorImpl<StringRef> &OutFragments,
-                       StringRef Delimiters) {
-  std::pair<StringRef, StringRef> S = getToken(Source, Delimiters);
-  while (!S.first.empty()) {
-    OutFragments.push_back(S.first);
-    S = getToken(S.second, Delimiters);
-  }
-}
-
-void wpi::printEscapedString(StringRef Name, raw_ostream &Out) {
-  for (unsigned i = 0, e = Name.size(); i != e; ++i) {
-    unsigned char C = Name[i];
-    if (isPrint(C) && C != '\\' && C != '"')
-      Out << C;
-    else
-      Out << '\\' << hexdigit(C >> 4) << hexdigit(C & 0x0F);
-  }
-}
-
-void wpi::printHTMLEscaped(StringRef String, raw_ostream &Out) {
-  for (char C : String) {
-    if (C == '&')
-      Out << "&amp;";
-    else if (C == '<')
-      Out << "&lt;";
-    else if (C == '>')
-      Out << "&gt;";
-    else if (C == '\"')
-      Out << "&quot;";
-    else if (C == '\'')
-      Out << "&apos;";
-    else
-      Out << C;
-  }
-}
-
-void wpi::printLowerCase(StringRef String, raw_ostream &Out) {
-  for (const char C : String)
-    Out << toLower(C);
-}

wpiutil/src/main/native/cpp/llvm/StringMap.cpp

@@ -19,6 +19,21 @@
 
 using namespace wpi;
 
+/// HashString - Hash function for strings.
+///
+/// This is the Bernstein hash function.
+//
+// FIXME: Investigate whether a modified bernstein hash function performs
+// better: http://eternallyconfuzzled.com/tuts/algorithms/jsw_tut_hashing.aspx
+//   X*33+c -> X*33^c
+static inline unsigned HashString(std::string_view str,
+                                  unsigned result = 0) noexcept {
+  for (std::string_view::size_type i = 0, e = str.size(); i != e; ++i) {
+    result = result * 33 + static_cast<unsigned char>(str[i]);
+  }
+  return result;
+}
+
 /// Returns the number of buckets to allocate to ensure that the DenseMap can
 /// accommodate \p NumEntries without need to grow().
 static unsigned getMinBucketToReserveForEntries(unsigned NumEntries) {