[clang][NFC] Make various uses of Regex const

Thomas Preud'homme · Thomas Preud'homme · commit b81cc6032902 · 2019-11-19T16:15:21.000Z
The const-correctness of match() was fixed in rL372764, which allows uses of Regex objects to be const in cases they couldn't be before. This patch tightens up the const-ness of Regex in various such cases. Reviewers: thopre Reviewed By: thopre Subscribers: cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D68155
diff --git a/clang/include/clang/Tooling/Inclusions/HeaderIncludes.h b/clang/include/clang/Tooling/Inclusions/HeaderIncludes.h
@@ -42,8 +42,7 @@ class IncludeCategoryManager {
   std::string FileName;
   // This refers to a substring in FileName.
   StringRef FileStem;
-  // Regex is not thread-safe.
-  mutable SmallVector<llvm::Regex, 4> CategoryRegexs;
+  SmallVector<llvm::Regex, 4> CategoryRegexs;
 };
 
 /// Generates replacements for inserting or deleting #include directives in a
diff --git a/clang/lib/Format/BreakableToken.cpp b/clang/lib/Format/BreakableToken.cpp
@@ -88,11 +88,11 @@ getCommentSplit(StringRef Text, unsigned ContentStartColumn,
 
   StringRef::size_type SpaceOffset = Text.find_last_of(Blanks, MaxSplitBytes);
 
-  static auto *const kNumberedListRegexp = new llvm::Regex("^[1-9][0-9]?\\.");
+  static const auto kNumberedListRegexp = llvm::Regex("^[1-9][0-9]?\\.");
   while (SpaceOffset != StringRef::npos) {
     // Do not split before a number followed by a dot: this would be interpreted
     // as a numbered list, which would prevent re-flowing in subsequent passes.
-    if (kNumberedListRegexp->match(Text.substr(SpaceOffset).ltrim(Blanks)))
+    if (kNumberedListRegexp.match(Text.substr(SpaceOffset).ltrim(Blanks)))
       SpaceOffset = Text.find_last_of(Blanks, SpaceOffset);
     // In JavaScript, some @tags can be followed by {, and machinery that parses
     // these comments will fail to understand the comment if followed by a line
@@ -245,7 +245,7 @@ BreakableStringLiteral::BreakableStringLiteral(
 
 BreakableToken::Split BreakableStringLiteral::getSplit(
     unsigned LineIndex, unsigned TailOffset, unsigned ColumnLimit,
-    unsigned ContentStartColumn, llvm::Regex &CommentPragmasRegex) const {
+    unsigned ContentStartColumn, const llvm::Regex &CommentPragmasRegex) const {
   return getStringSplit(Line.substr(TailOffset), ContentStartColumn,
                         ColumnLimit - Postfix.size(), Style.TabWidth, Encoding);
 }
@@ -271,7 +271,7 @@ unsigned BreakableComment::getLineCount() const { return Lines.size(); }
 BreakableToken::Split
 BreakableComment::getSplit(unsigned LineIndex, unsigned TailOffset,
                            unsigned ColumnLimit, unsigned ContentStartColumn,
-                           llvm::Regex &CommentPragmasRegex) const {
+                           const llvm::Regex &CommentPragmasRegex) const {
   // Don't break lines matching the comment pragmas regex.
   if (CommentPragmasRegex.match(Content[LineIndex]))
     return Split(StringRef::npos, 0);
@@ -316,9 +316,9 @@ static bool mayReflowContent(StringRef Content) {
   // Numbered lists may also start with a number followed by '.'
   // To avoid issues if a line starts with a number which is actually the end
   // of a previous line, we only consider numbers with up to 2 digits.
-  static auto *const kNumberedListRegexp = new llvm::Regex("^[1-9][0-9]?\\. ");
+  static const auto kNumberedListRegexp = llvm::Regex("^[1-9][0-9]?\\. ");
   hasSpecialMeaningPrefix =
-      hasSpecialMeaningPrefix || kNumberedListRegexp->match(Content);
+      hasSpecialMeaningPrefix || kNumberedListRegexp.match(Content);
 
   // Simple heuristic for what to reflow: content should contain at least two
   // characters and either the first or second character must be
@@ -458,7 +458,7 @@ BreakableBlockComment::BreakableBlockComment(
 
 BreakableToken::Split BreakableBlockComment::getSplit(
     unsigned LineIndex, unsigned TailOffset, unsigned ColumnLimit,
-    unsigned ContentStartColumn, llvm::Regex &CommentPragmasRegex) const {
+    unsigned ContentStartColumn, const llvm::Regex &CommentPragmasRegex) const {
   // Don't break lines matching the comment pragmas regex.
   if (CommentPragmasRegex.match(Content[LineIndex]))
     return Split(StringRef::npos, 0);
@@ -597,9 +597,8 @@ void BreakableBlockComment::insertBreak(unsigned LineIndex, unsigned TailOffset,
           PrefixWithTrailingIndent.size());
 }
 
-BreakableToken::Split
-BreakableBlockComment::getReflowSplit(unsigned LineIndex,
-                                      llvm::Regex &CommentPragmasRegex) const {
+BreakableToken::Split BreakableBlockComment::getReflowSplit(
+    unsigned LineIndex, const llvm::Regex &CommentPragmasRegex) const {
   if (!mayReflow(LineIndex, CommentPragmasRegex))
     return Split(StringRef::npos, 0);
 
@@ -706,8 +705,8 @@ BreakableBlockComment::getSplitAfterLastLine(unsigned TailOffset) const {
   return Split(StringRef::npos, 0);
 }
 
-bool BreakableBlockComment::mayReflow(unsigned LineIndex,
-                                      llvm::Regex &CommentPragmasRegex) const {
+bool BreakableBlockComment::mayReflow(
+    unsigned LineIndex, const llvm::Regex &CommentPragmasRegex) const {
   // Content[LineIndex] may exclude the indent after the '*' decoration. In that
   // case, we compute the start of the comment pragma manually.
   StringRef IndentContent = Content[LineIndex];
@@ -845,7 +844,7 @@ void BreakableLineCommentSection::insertBreak(
 }
 
 BreakableComment::Split BreakableLineCommentSection::getReflowSplit(
-    unsigned LineIndex, llvm::Regex &CommentPragmasRegex) const {
+    unsigned LineIndex, const llvm::Regex &CommentPragmasRegex) const {
   if (!mayReflow(LineIndex, CommentPragmasRegex))
     return Split(StringRef::npos, 0);
 
@@ -955,7 +954,7 @@ void BreakableLineCommentSection::updateNextToken(LineState &State) const {
 }
 
 bool BreakableLineCommentSection::mayReflow(
-    unsigned LineIndex, llvm::Regex &CommentPragmasRegex) const {
+    unsigned LineIndex, const llvm::Regex &CommentPragmasRegex) const {
   // Line comments have the indent as part of the prefix, so we need to
   // recompute the start of the line.
   StringRef IndentContent = Content[LineIndex];
diff --git a/clang/lib/Format/BreakableToken.h b/clang/lib/Format/BreakableToken.h
@@ -155,7 +155,7 @@ class BreakableToken {
   /// file.
   virtual Split getSplit(unsigned LineIndex, unsigned TailOffset,
                          unsigned ColumnLimit, unsigned ContentStartColumn,
-                         llvm::Regex &CommentPragmasRegex) const = 0;
+                         const llvm::Regex &CommentPragmasRegex) const = 0;
 
   /// Emits the previously retrieved \p Split via \p Whitespaces.
   virtual void insertBreak(unsigned LineIndex, unsigned TailOffset, Split Split,
@@ -190,7 +190,7 @@ class BreakableToken {
   /// If the split is not contained within one token, for example when reflowing
   /// line comments, returns (0, <length>).
   virtual Split getReflowSplit(unsigned LineIndex,
-                               llvm::Regex &CommentPragmasRegex) const {
+                               const llvm::Regex &CommentPragmasRegex) const {
     return Split(StringRef::npos, 0);
   }
 
@@ -255,7 +255,7 @@ class BreakableStringLiteral : public BreakableToken {
 
   Split getSplit(unsigned LineIndex, unsigned TailOffset, unsigned ColumnLimit,
                  unsigned ContentStartColumn,
-                 llvm::Regex &CommentPragmasRegex) const override;
+                 const llvm::Regex &CommentPragmasRegex) const override;
   void insertBreak(unsigned LineIndex, unsigned TailOffset, Split Split,
                    unsigned ContentIndent,
                    WhitespaceManager &Whitespaces) const override;
@@ -298,7 +298,7 @@ class BreakableComment : public BreakableToken {
   unsigned getLineCount() const override;
   Split getSplit(unsigned LineIndex, unsigned TailOffset, unsigned ColumnLimit,
                  unsigned ContentStartColumn,
-                 llvm::Regex &CommentPragmasRegex) const override;
+                 const llvm::Regex &CommentPragmasRegex) const override;
   void compressWhitespace(unsigned LineIndex, unsigned TailOffset, Split Split,
                           WhitespaceManager &Whitespaces) const override;
 
@@ -309,7 +309,7 @@ class BreakableComment : public BreakableToken {
   // Checks if the content of line LineIndex may be reflown with the previous
   // line.
   virtual bool mayReflow(unsigned LineIndex,
-                         llvm::Regex &CommentPragmasRegex) const = 0;
+                         const llvm::Regex &CommentPragmasRegex) const = 0;
 
   // Contains the original text of the lines of the block comment.
   //
@@ -363,7 +363,7 @@ class BreakableBlockComment : public BreakableComment {
 
   Split getSplit(unsigned LineIndex, unsigned TailOffset, unsigned ColumnLimit,
                  unsigned ContentStartColumn,
-                 llvm::Regex &CommentPragmasRegex) const override;
+                 const llvm::Regex &CommentPragmasRegex) const override;
   unsigned getRangeLength(unsigned LineIndex, unsigned Offset,
                           StringRef::size_type Length,
                           unsigned StartColumn) const override;
@@ -375,7 +375,7 @@ class BreakableBlockComment : public BreakableComment {
                    unsigned ContentIndent,
                    WhitespaceManager &Whitespaces) const override;
   Split getReflowSplit(unsigned LineIndex,
-                       llvm::Regex &CommentPragmasRegex) const override;
+                       const llvm::Regex &CommentPragmasRegex) const override;
   void reflow(unsigned LineIndex,
               WhitespaceManager &Whitespaces) const override;
   bool introducesBreakBeforeToken() const override;
@@ -384,7 +384,7 @@ class BreakableBlockComment : public BreakableComment {
   Split getSplitAfterLastLine(unsigned TailOffset) const override;
 
   bool mayReflow(unsigned LineIndex,
-                 llvm::Regex &CommentPragmasRegex) const override;
+                 const llvm::Regex &CommentPragmasRegex) const override;
 
   // Contains Javadoc annotations that require additional indent when continued
   // on multiple lines.
@@ -448,14 +448,14 @@ class BreakableLineCommentSection : public BreakableComment {
                    unsigned ContentIndent,
                    WhitespaceManager &Whitespaces) const override;
   Split getReflowSplit(unsigned LineIndex,
-                       llvm::Regex &CommentPragmasRegex) const override;
+                       const llvm::Regex &CommentPragmasRegex) const override;
   void reflow(unsigned LineIndex,
               WhitespaceManager &Whitespaces) const override;
   void adaptStartOfLine(unsigned LineIndex,
                         WhitespaceManager &Whitespaces) const override;
   void updateNextToken(LineState &State) const override;
   bool mayReflow(unsigned LineIndex,
-                 llvm::Regex &CommentPragmasRegex) const override;
+                 const llvm::Regex &CommentPragmasRegex) const override;
 
 private:
   // OriginalPrefix[i] contains the original prefix of line i, including
diff --git a/clang/lib/Format/NamespaceEndCommentsFixer.cpp b/clang/lib/Format/NamespaceEndCommentsFixer.cpp
@@ -92,24 +92,24 @@ bool validEndComment(const FormatToken *RBraceTok, StringRef NamespaceName,
 
   // Matches a valid namespace end comment.
   // Valid namespace end comments don't need to be edited.
-  static llvm::Regex *const NamespaceCommentPattern =
-      new llvm::Regex("^/[/*] *(end (of )?)? *(anonymous|unnamed)? *"
-                      "namespace( +([a-zA-Z0-9:_]+))?\\.? *(\\*/)?$",
-                      llvm::Regex::IgnoreCase);
-  static llvm::Regex *const NamespaceMacroCommentPattern =
-      new llvm::Regex("^/[/*] *(end (of )?)? *(anonymous|unnamed)? *"
-                      "([a-zA-Z0-9_]+)\\(([a-zA-Z0-9:_]*)\\)\\.? *(\\*/)?$",
-                      llvm::Regex::IgnoreCase);
+  static const llvm::Regex NamespaceCommentPattern =
+      llvm::Regex("^/[/*] *(end (of )?)? *(anonymous|unnamed)? *"
+                  "namespace( +([a-zA-Z0-9:_]+))?\\.? *(\\*/)?$",
+                  llvm::Regex::IgnoreCase);
+  static const llvm::Regex NamespaceMacroCommentPattern =
+      llvm::Regex("^/[/*] *(end (of )?)? *(anonymous|unnamed)? *"
+                  "([a-zA-Z0-9_]+)\\(([a-zA-Z0-9:_]*)\\)\\.? *(\\*/)?$",
+                  llvm::Regex::IgnoreCase);
 
   SmallVector<StringRef, 8> Groups;
   if (NamespaceTok->is(TT_NamespaceMacro) &&
-      NamespaceMacroCommentPattern->match(Comment->TokenText, &Groups)) {
+      NamespaceMacroCommentPattern.match(Comment->TokenText, &Groups)) {
     StringRef NamespaceTokenText = Groups.size() > 4 ? Groups[4] : "";
     // The name of the macro must be used.
     if (NamespaceTokenText != NamespaceTok->TokenText)
       return false;
   } else if (NamespaceTok->isNot(tok::kw_namespace) ||
-             !NamespaceCommentPattern->match(Comment->TokenText, &Groups)) {
+             !NamespaceCommentPattern.match(Comment->TokenText, &Groups)) {
     // Comment does not match regex.
     return false;
   }
diff --git a/clang/lib/Format/UnwrappedLineParser.cpp b/clang/lib/Format/UnwrappedLineParser.cpp
@@ -2498,9 +2498,10 @@ bool UnwrappedLineParser::isOnNewLine(const FormatToken &FormatTok) {
 
 // Checks if \p FormatTok is a line comment that continues the line comment
 // section on \p Line.
-static bool continuesLineCommentSection(const FormatToken &FormatTok,
-                                        const UnwrappedLine &Line,
-                                        llvm::Regex &CommentPragmasRegex) {
+static bool
+continuesLineCommentSection(const FormatToken &FormatTok,
+                            const UnwrappedLine &Line,
+                            const llvm::Regex &CommentPragmasRegex) {
   if (Line.Tokens.empty())
     return false;
 
diff --git a/clang/tools/clang-refactor/TestSupport.cpp b/clang/tools/clang-refactor/TestSupport.cpp
@@ -303,9 +303,10 @@ findTestSelectionRanges(StringRef Filename) {
 
   // See the doc comment for this function for the explanation of this
   // syntax.
-  static Regex RangeRegex("range[[:blank:]]*([[:alpha:]_]*)?[[:blank:]]*=[[:"
-                          "blank:]]*(\\+[[:digit:]]+)?[[:blank:]]*(->[[:blank:]"
-                          "]*[\\+\\:[:digit:]]+)?");
+  static const Regex RangeRegex(
+      "range[[:blank:]]*([[:alpha:]_]*)?[[:blank:]]*=[[:"
+      "blank:]]*(\\+[[:digit:]]+)?[[:blank:]]*(->[[:blank:]"
+      "]*[\\+\\:[:digit:]]+)?");
 
   std::map<std::string, SmallVector<TestSelectionRange, 8>> GroupedRanges;
 
@@ -352,7 +353,7 @@ findTestSelectionRanges(StringRef Filename) {
     unsigned EndOffset;
 
     if (!Matches[3].empty()) {
-      static Regex EndLocRegex(
+      static const Regex EndLocRegex(
           "->[[:blank:]]*(\\+[[:digit:]]+):([[:digit:]]+)");
       SmallVector<StringRef, 4> EndLocMatches;
       if (!EndLocRegex.match(Matches[3], &EndLocMatches)) {
