[llvm-profdata] Add check for text profile formats and improve error reporting

Summary:
This change addresses two possible instances of user error / confusion when
merging sampled profile data.

Previously any input that didn't match the raw or processed instrumented format
would automatically be interpreted as instrumented profile text format data.
No error would be reported during the merge.

Example:
If foo-sampled.profdata and bar-sampled.profdata are binary sampled profiles:

Old behavior:
$ llvm-profdata merge foo-sampled.profdata bar-sampled.profdata -output foobar-sampled.profdata
$ llvm-profdata show -sample foobar-sampled.profdata
error: foobar-sampled.profdata:1: Expected 'mangled_name:NUM:NUM', found  lprofi

This change adds basic checks for valid input data when assuming text input.
It also makes error messages related to file format validity more specific about
the assumbed profile data type.

New behavior:
$ llvm-profdata merge foo-sampled.profdata bar-sampled.profdata -o foobar-sampled.profdata
error: foo.profdata: Unrecognized instrumentation profile encoding format
Perhaps you forgot to use the -sample option?

Reviewers: bogner, davidxl, dnovillo

Subscribers: davidxl, llvm-commits

Differential Revision: http://reviews.llvm.org/D14558

llvm-svn: 252916

1 files changed, 12 insertions, 1 deletions

diff --git a/llvm/lib/ProfileData/InstrProfReader.cpp b/llvm/lib/ProfileData/InstrProfReader.cpp
index bf10b44..6f20124 100644
--- a/llvm/lib/ProfileData/InstrProfReader.cpp
+++ b/llvm/lib/ProfileData/InstrProfReader.cpp
@@ -54,8 +54,10 @@ InstrProfReader::create(std::unique_ptr<MemoryBuffer> Buffer) {
     Result.reset(new RawInstrProfReader64(std::move(Buffer)));
   else if (RawInstrProfReader32::hasFormat(*Buffer))
     Result.reset(new RawInstrProfReader32(std::move(Buffer)));
-  else
+  else if (TextInstrProfReader::hasFormat(*Buffer))
     Result.reset(new TextInstrProfReader(std::move(Buffer)));
+  else
+    return instrprof_error::unrecognized_format;
 
   // Initialize the reader and return the result.
   if (std::error_code EC = initializeReader(*Result))
@@ -97,6 +99,15 @@ void InstrProfIterator::Increment() {
     *this = InstrProfIterator();
 }
 
+bool TextInstrProfReader::hasFormat(const MemoryBuffer &Buffer) {
+  // Verify that this really looks like plain ASCII text by checking a
+  // 'reasonable' number of characters (up to profile magic size).
+  size_t count = std::min(Buffer.getBufferSize(), sizeof(uint64_t));
+  StringRef buffer = Buffer.getBufferStart();
+  return count == 0 || std::all_of(buffer.begin(), buffer.begin() + count,
+    [](char c) { return ::isprint(c) || ::isspace(c); });
+}
+
 std::error_code TextInstrProfReader::readNextRecord(InstrProfRecord &Record) {
   // Skip empty lines and comments.
   while (!Line.is_at_end() && (Line->empty() || Line->startswith("#")))