Clean up rewrite_to_chrome_style naming logic.

tools/clang/rewrite_to_chrome_style/Renamer.cpp

+// Copyright 2016 The Chromium Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
+
+#include "Renamer.h"
+
+#include <assert.h>
+
+#include "clang/Basic/CharInfo.h"
+#include "llvm/ADT/SmallVector.h"
+
+namespace {
+
+enum class Case {
+  NEITHER,
+  LOWER,
+  UPPER,
+};
+
+using WordList = llvm::SmallVector<llvm::StringRef, 6>;
+
+Case DetermineCase(char c) {
+  if (clang::isUppercase(c))
+    return Case::UPPER;
+  if (clang::isLowercase(c))
+    return Case::LOWER;
+  return Case::NEITHER;
+}
+
+// True if the input only contains letters of one case.
+bool CanSplitWithUnderscores(llvm::StringRef input) {
+  Case expected_case = Case::NEITHER;
+  for (size_t i = 0; i < input.size(); ++i) {
+    Case current_case = DetermineCase(input[i]);
+    if (expected_case == Case::NEITHER) {
+      expected_case = current_case;
+      continue;
+    }
+    if (current_case == Case::NEITHER)
+      continue;
+    if (expected_case != current_case)
+      return false;
+  }
+  return true;
+}
+
+WordList SplitWithUnderscores(llvm::StringRef input) {
+  WordList output;
+  input.split(output, "_", -1, false /*KeepEmpty*/);
+  return output;
+}
+
+// Most identifiers in Blink use CamelCase, but some (incorrectly) mix in
+// underscores. In that case, split into words, using uppercase letters and
+// underscores signal the start of the next word, while trying to handle
+// acronyms.
+WordList SplitWithHeuristics(llvm::StringRef input) {
+  WordList output;
+  for (size_t i = 0; i < input.size();) {
+    size_t start = i;
+    size_t end = input.size();
+    Case previous_case = DetermineCase(input[start]);
+    bool in_acronym = false;
+
+    // Find the next "meaningful" uppercase letter or underscore.
+    for (++i; i < input.size(); ++i) {
+      // Underscore case: assume underscores always separate two words.
+      if (input[i] == '_') {
+        end = i;
+        ++i;  // Skip the underscore.
+        break;
+      }
+
+      Case current_case = DetermineCase(input[i]);
+      // Non-acronym case: the next uppercase letter is the beginning of the
+      // next word.
+      if (previous_case != Case::UPPER && current_case == Case::UPPER) {
+        end = i;
+        break;
+      }
+      // End of ACRONYM case:
+      if (in_acronym && previous_case == Case::UPPER &&
+          current_case == Case::LOWER) {
+        --i;  // Already iterated into the next word, so backtrack.
+        end = i;
+        break;
+      }
+      // Seeing a non-uppercase letter after an uppercase letter means this is
+      // probably part of an acronym.
+      if (previous_case == Case::UPPER && current_case != Case::LOWER) {
+        in_acronym = true;
+        // Intentionally fallthrough, so casing state is updated.
+      }
+
+      previous_case = current_case;
+    }
+    // TODO(dcheng): Special acronym handling here.
+    output.emplace_back(input.substr(start, end - start));
+  }
+  return output;
+}
+
+WordList SplitIdentifier(llvm::StringRef input) {
+  assert(input.size() > 0);
+
+  if (CanSplitWithUnderscores(input))
+    return SplitWithUnderscores(input);
+
+  return SplitWithHeuristics(input);
+}
+
+}  // namespace
+
+std::string IdentifierToCamelCase(llvm::StringRef input) {
+  WordList words = SplitIdentifier(input);
+  std::string output;
+  for (const auto& word : words) {
+    output += clang::toUppercase(word[0]);
+    for (size_t i = 1; i < word.size(); ++i)
+      output += clang::toLowercase(word[i]);
+  }
+  return output;
+}
+
+std::string IdentifierToUnderscoreCase(llvm::StringRef input) {
+  WordList words = SplitIdentifier(input);
+  std::string output;
+  for (const auto& word : words) {
+    if (!output.empty())
+      output += '_';
+    for (size_t i = 0; i < word.size(); ++i)
+      output += clang::toLowercase(word[i]);
+  }
+  return output;
+}
+
+std::string identifierToShoutyCase(llvm::StringRef input) {
+  WordList words = SplitIdentifier(input);
+  std::string output;
+  for (const auto& word : words) {
+    if (!output.empty())
+      output += '_';
+    for (size_t i = 0; i < word.size(); ++i)
+      output += clang::toUppercase(word[i]);
+  }
+  return output;
+}