[PATCH] D37136: [clang-format] Do not format likely xml

[Krasimir Georgiev via Phabricator via cfe-commits]

krasimir created this revision.
Herald added a subscriber: klimek.

This patch detects the leading '<' in likely xml files and stops formatting in
that case. A recent use of a Qt xml file with a .ts extension triggered this:
http://doc.qt.io/qt-4.8/linguist-ts-file-format.html


https://reviews.llvm.org/D37136

Files:
  lib/Format/Format.cpp
  unittests/Format/FormatTest.cpp
  unittests/Format/SortIncludesTest.cpp


Index: unittests/Format/SortIncludesTest.cpp
===================================================================
--- unittests/Format/SortIncludesTest.cpp
+++ unittests/Format/SortIncludesTest.cpp
@@ -398,6 +398,17 @@
   EXPECT_EQ(26u, Ranges[0].getLength());
 }
 
+TEST_F(SortIncludesTest, DoNotSortLikelyXml) {
+  EXPECT_EQ("<!--;\n"
+            "#include <b>\n"
+            "#include <a>\n"
+            "-->",
+            sort("<!--;\n"
+                 "#include <b>\n"
+                 "#include <a>\n"
+                 "-->"));
+}
+
 } // end namespace
 } // end namespace format
 } // end namespace clang
Index: unittests/Format/FormatTest.cpp
===================================================================
--- unittests/Format/FormatTest.cpp
+++ unittests/Format/FormatTest.cpp
@@ -11217,6 +11217,13 @@
   EXPECT_EQ("auto c = u8'a';", format("auto c = u8'a';"));
 }
 
+TEST_F(FormatTest, DoNotFormatLikelyXml) {
+  EXPECT_EQ("<!-- ;> -->",
+            format("<!-- ;> -->", getGoogleStyle()));
+  EXPECT_EQ(" <!-- >; -->",
+            format(" <!-- >; -->", getGoogleStyle()));
+}
+
 } // end namespace
 } // end namespace format
 } // end namespace clang
Index: lib/Format/Format.cpp
===================================================================
--- lib/Format/Format.cpp
+++ lib/Format/Format.cpp
@@ -1539,14 +1539,19 @@
   return Code.size() > 188 && Code[0] == 0x47 && Code[188] == 0x47;
 }
 
+bool likelyXml(StringRef Code) {
+  return Code.ltrim().startswith("<");
+}
+
 tooling::Replacements sortIncludes(const FormatStyle &Style, StringRef Code,
                                    ArrayRef<tooling::Range> Ranges,
                                    StringRef FileName, unsigned *Cursor) {
   tooling::Replacements Replaces;
   if (!Style.SortIncludes)
     return Replaces;
-  if (Style.Language == FormatStyle::LanguageKind::LK_JavaScript &&
-      isMpegTS(Code))
+  if (likelyXml(Code) ||
+      (Style.Language == FormatStyle::LanguageKind::LK_JavaScript &&
+       isMpegTS(Code)))
     return Replaces;
   if (Style.Language == FormatStyle::LanguageKind::LK_JavaScript)
     return sortJavaScriptImports(Style, Code, Ranges, FileName);
@@ -1894,7 +1899,8 @@
   FormatStyle Expanded = expandPresets(Style);
   if (Expanded.DisableFormat)
     return tooling::Replacements();
-  if (Expanded.Language == FormatStyle::LK_JavaScript && isMpegTS(Code))
+  if (likelyXml(Code) ||
+      (Expanded.Language == FormatStyle::LK_JavaScript && isMpegTS(Code)))
     return tooling::Replacements();
 
   typedef std::function<tooling::Replacements(const Environment &)>



Index: unittests/Format/SortIncludesTest.cpp
===================================================================
--- unittests/Format/SortIncludesTest.cpp
+++ unittests/Format/SortIncludesTest.cpp
@@ -398,6 +398,17 @@
   EXPECT_EQ(26u, Ranges[0].getLength());
 }
 
+TEST_F(SortIncludesTest, DoNotSortLikelyXml) {
+  EXPECT_EQ("<!--;\n"
+            "#include <b>\n"
+            "#include <a>\n"
+            "-->",
+            sort("<!--;\n"
+                 "#include <b>\n"
+                 "#include <a>\n"
+                 "-->"));
+}
+
 } // end namespace
 } // end namespace format
 } // end namespace clang
Index: unittests/Format/FormatTest.cpp
===================================================================
--- unittests/Format/FormatTest.cpp
+++ unittests/Format/FormatTest.cpp
@@ -11217,6 +11217,13 @@
   EXPECT_EQ("auto c = u8'a';", format("auto c = u8'a';"));
 }
 
+TEST_F(FormatTest, DoNotFormatLikelyXml) {
+  EXPECT_EQ("<!-- ;> -->",
+            format("<!-- ;> -->", getGoogleStyle()));
+  EXPECT_EQ(" <!-- >; -->",
+            format(" <!-- >; -->", getGoogleStyle()));
+}
+
 } // end namespace
 } // end namespace format
 } // end namespace clang
Index: lib/Format/Format.cpp
===================================================================
--- lib/Format/Format.cpp
+++ lib/Format/Format.cpp
@@ -1539,14 +1539,19 @@
   return Code.size() > 188 && Code[0] == 0x47 && Code[188] == 0x47;
 }
 
+bool likelyXml(StringRef Code) {
+  return Code.ltrim().startswith("<");
+}
+
 tooling::Replacements sortIncludes(const FormatStyle &Style, StringRef Code,
                                    ArrayRef<tooling::Range> Ranges,
                                    StringRef FileName, unsigned *Cursor) {
   tooling::Replacements Replaces;
   if (!Style.SortIncludes)
     return Replaces;
-  if (Style.Language == FormatStyle::LanguageKind::LK_JavaScript &&
-      isMpegTS(Code))
+  if (likelyXml(Code) ||
+      (Style.Language == FormatStyle::LanguageKind::LK_JavaScript &&
+       isMpegTS(Code)))
     return Replaces;
   if (Style.Language == FormatStyle::LanguageKind::LK_JavaScript)
     return sortJavaScriptImports(Style, Code, Ranges, FileName);
@@ -1894,7 +1899,8 @@
   FormatStyle Expanded = expandPresets(Style);
   if (Expanded.DisableFormat)
     return tooling::Replacements();
-  if (Expanded.Language == FormatStyle::LK_JavaScript && isMpegTS(Code))
+  if (likelyXml(Code) ||
+      (Expanded.Language == FormatStyle::LK_JavaScript && isMpegTS(Code)))
     return tooling::Replacements();
 
   typedef std::function<tooling::Replacements(const Environment &)>

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits