clang-format: [JS] do not format MPEG transport streams.

[mprobst]

Summary

The MPEG transport stream file format also uses ".ts" as its file extension.
This change detects its specific framing format (0x47 every 189 bytes) and
simply ignores MPEG TS files.

[djasper]

unittests/Format/FormatTestJS.cpp

1040

nit: Should be MpegTS.

[mprobst]

• Move MPEG check into Format.cpp.

[mprobst]

PTAL, moved the check down a bit.

[• alexeagle]

confused, wasn't this committed last year? is this an extra check?

[mprobst]

In D29186#657828, @alexeagle wrote:

confused, wasn't this committed last year? is this an extra check?

I think I fixed this in tslint, but not in clang-format. At least I cannot find a trace of it (but yeah, I thought I had fixed it, too).

lib/Format/Format.cpp

if (Pos == StringRef::npos || Pos + 1 == Code.size())
       break;
     SearchFrom = Pos + 1;
   }
   if (!IncludesInBlock.empty())
     sortCppIncludes(Style, IncludesInBlock, Ranges, FileName, Replaces, Cursor);
   return Replaces;
 }
 
+bool isMpegTS(StringRef Code) {
+  // MPEG transport streams use the ".ts" file extension. clang-format should
+  // not attempt to format those. MPEG TS' frame format starts with 0x47 every
+  // 189 bytes - detect that and return.
+  return Code.size() > 188 && Code[0] == 0x47 && Code[188] == 0x47;
+}
+
 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))
+    return Replaces;
   if (Style.Language == FormatStyle::LanguageKind::LK_JavaScript)
     return sortJavaScriptImports(Style, Code, Ranges, FileName);
   sortCppIncludes(Style, Code, Ranges, FileName, Replaces, Cursor);
   return Replaces;
 }
 
 template <typename T>
 static llvm::Expected<tooling::Replacements>

 }
 
 tooling::Replacements reformat(const FormatStyle &Style, StringRef Code,
                                ArrayRef<tooling::Range> Ranges,
                                StringRef FileName, bool *IncompleteFormat) {
   FormatStyle Expanded = expandPresets(Style);
   if (Expanded.DisableFormat)
     return tooling::Replacements();
-
+  if (Expanded.Language == FormatStyle::LK_JavaScript && isMpegTS(Code))
+    return tooling::Replacements();
   auto Env = Environment::CreateVirtualEnvironment(Code, FileName, Ranges);
 
   if (Style.Language == FormatStyle::LK_JavaScript &&
       Style.JavaScriptQuotes != FormatStyle::JSQS_Leave) {
     JavaScriptRequoter Requoter(*Env, Expanded);
     tooling::Replacements Requotes = Requoter.process();
     if (!Requotes.empty()) {
       auto NewCode = applyAllReplacements(Code, Requotes);

tools/clang-format/ClangFormat.cpp

static bool format(StringRef FileName) {
   StringRef AssumedFileName = (FileName == "-") ? AssumeFileName : FileName;
 
   llvm::Expected<FormatStyle> FormatStyle =
       getStyle(Style, AssumedFileName, FallbackStyle, Code->getBuffer());
   if (!FormatStyle) {
     llvm::errs() << llvm::toString(FormatStyle.takeError()) << "\n";
     return true;
   }
+
   if (SortIncludes.getNumOccurrences() != 0)
     FormatStyle->SortIncludes = SortIncludes;
   unsigned CursorPosition = Cursor;
   Replacements Replaces = sortIncludes(*FormatStyle, Code->getBuffer(), Ranges,
                                        AssumedFileName, &CursorPosition);
   auto ChangedCode = tooling::applyAllReplacements(Code->getBuffer(), Replaces);
   if (!ChangedCode) {
     llvm::errs() << llvm::toString(ChangedCode.takeError()) << "\n";

unittests/Format/FormatTestJS.cpp

TEST_F(FormatTestJS, RegexLiteralLength) {
   verifyFormat("var regex = /\\xaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/;",
                getGoogleJSStyleWithColumns(50));
 }
 
 TEST_F(FormatTestJS, RegexLiteralExamples) {
   verifyFormat("var regex = search.match(/(?:\?|&)times=([^?&]+)/i);");
 }
 
+TEST_F(FormatTestJS, IgnoresMpegTS) {
+  std::string MpegTS(200, ' ');
+  MpegTS.replace(0, strlen("nearlyLooks  +   like +   ts + code;  "),
+                 "nearlyLooks  +   like +   ts + code;  ");
+  MpegTS[0] = 0x47;
+  MpegTS[188] = 0x47;
+  verifyFormat(MpegTS, MpegTS);
+}
+
 TEST_F(FormatTestJS, TypeAnnotations) {
   verifyFormat("var x: string;");
   verifyFormat("var x: {a: string; b: number;} = {};");
   verifyFormat("function x(): string {\n  return 'x';\n}");
   verifyFormat("function x(): {x: string} {\n  return {x: 'x'};\n}");
   verifyFormat("function x(y: string): string {\n  return 'x';\n}");
   verifyFormat("for (var y: string in x) {\n  x();\n}");
   verifyFormat("for (var y: string of x) {\n  x();\n}");