clang-format: do not reflow bullet lists

Summary:
This patch prevents reflowing bullet lists in block comments.

It handles all lists supported by doxygen and markdown, e.g. bullet
lists starting with '-', '*', '+', as well as numbered lists starting
with -# or a number followed by a dot.

Reviewers: krasimir

Reviewed By: krasimir

Subscribers: djasper, klimek, cfe-commits

Differential Revision: https://reviews.llvm.org/D33285

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@303556 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Format/BreakableToken.cpp

@@ -78,6 +78,14 @@ static BreakableToken::Split getCommentSplit(StringRef Text,
   }
 
   StringRef::size_type SpaceOffset = Text.find_last_of(Blanks, MaxSplitBytes);
+
+  // 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.
+  static llvm::Regex kNumberedListRegexp = llvm::Regex("^[1-9][0-9]?\\.");
+  if (SpaceOffset != StringRef::npos &&
+      kNumberedListRegexp.match(Text.substr(SpaceOffset).ltrim(Blanks)))
+    SpaceOffset = Text.find_last_of(Blanks, SpaceOffset);
+
   if (SpaceOffset == StringRef::npos ||
       // Don't break at leading whitespace.
       Text.find_last_not_of(Blanks, SpaceOffset) == StringRef::npos) {
@@ -299,8 +307,9 @@ const FormatToken &BreakableComment::tokenAt(unsigned LineIndex) const {
 static bool mayReflowContent(StringRef Content) {
   Content = Content.trim(Blanks);
   // Lines starting with '@' commonly have special meaning.
-  static const SmallVector<StringRef, 4> kSpecialMeaningPrefixes = {
-      "@", "TODO", "FIXME", "XXX"};
+  // Lines starting with '-', '-#', '+' or '*' are bulleted/numbered lists.
+  static const SmallVector<StringRef, 8> kSpecialMeaningPrefixes = {
+      "@", "TODO", "FIXME", "XXX", "-# ", "- ", "+ ", "* " };
   bool hasSpecialMeaningPrefix = false;
   for (StringRef Prefix : kSpecialMeaningPrefixes) {
     if (Content.startswith(Prefix)) {
@@ -308,6 +317,14 @@ static bool mayReflowContent(StringRef Content) {
       break;
     }
   }
+
+  // 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 llvm::Regex kNumberedListRegexp = llvm::Regex("^[1-9][0-9]?\\. ");
+  hasSpecialMeaningPrefix = 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
   // non-punctuation.

unittests/Format/FormatTestComments.cpp

@@ -1577,7 +1577,7 @@ TEST_F(FormatTestComments, ReflowsComments) {
                    " *\n"
                    " * long */",
                    getLLVMStyleWithColumns(20)));
-  
+
   // Don't reflow lines having content that is a single character.
   EXPECT_EQ("// long long long\n"
             "// long\n"
@@ -1602,7 +1602,7 @@ TEST_F(FormatTestComments, ReflowsComments) {
             format("// long long long long\n"
                    "// @param arg",
                    getLLVMStyleWithColumns(20)));
-  
+
   // Don't reflow lines starting with 'TODO'.
   EXPECT_EQ("// long long long\n"
             "// long\n"
@@ -1671,6 +1671,69 @@ TEST_F(FormatTestComments, ReflowsComments) {
                    "//  long",
                    getLLVMStyleWithColumns(20)));
 
+  // Don't reflow separate bullets in list
+  EXPECT_EQ("// - long long long\n"
+            "// long\n"
+            "// - long",
+            format("// - long long long long\n"
+                   "// - long",
+                   getLLVMStyleWithColumns(20)));
+  EXPECT_EQ("// * long long long\n"
+            "// long\n"
+            "// * long",
+            format("// * long long long long\n"
+                   "// * long",
+                   getLLVMStyleWithColumns(20)));
+  EXPECT_EQ("// + long long long\n"
+            "// long\n"
+            "// + long",
+            format("// + long long long long\n"
+                   "// + long",
+                   getLLVMStyleWithColumns(20)));
+  EXPECT_EQ("// 1. long long long\n"
+            "// long\n"
+            "// 2. long",
+            format("// 1. long long long long\n"
+                   "// 2. long",
+                   getLLVMStyleWithColumns(20)));
+  EXPECT_EQ("// -# long long long\n"
+            "// long\n"
+            "// -# long",
+            format("// -# long long long long\n"
+                   "// -# long",
+                   getLLVMStyleWithColumns(20)));
+
+  EXPECT_EQ("// - long long long\n"
+            "// long long long\n"
+            "// - long",
+            format("// - long long long long\n"
+                   "// long long\n"
+                   "// - long",
+                   getLLVMStyleWithColumns(20)));
+  EXPECT_EQ("// - long long long\n"
+            "// long long long\n"
+            "// long\n"
+            "// - long",
+            format("// - long long long long\n"
+                   "// long long long\n"
+                   "// - long",
+                   getLLVMStyleWithColumns(20)));
+
+  // Large number (>2 digits) are not list items
+  EXPECT_EQ("// long long long\n"
+            "// long 1024. long.",
+            format("// long long long long\n"
+                   "// 1024. long.",
+                   getLLVMStyleWithColumns(20)));
+
+  // Do not break before number, to avoid introducing a non-reflowable doxygen
+  // list item.
+  EXPECT_EQ("// long long\n"
+            "// long 10. long.",
+            format("// long long long 10.\n"
+                   "// long.",
+                   getLLVMStyleWithColumns(20)));
+
   // Don't break or reflow after implicit string literals.
   verifyFormat("#include <t> // l l l\n"
                "             // l",