Stopgap for unicode chars in filename strings

Such filenames still can't be matched against, but at least we won't throw an
exception when it happens.

Fixes #279, relevant to #278

cpp/ycm/CandidateRepository.cpp

@@ -21,6 +21,8 @@
 #include "Utils.h"
 
 #include <boost/thread/locks.hpp>
+#include <boost/algorithm/string.hpp>
+#include <locale>
 
 #ifdef USE_CLANG_COMPLETER
 #  include "ClangCompleter/CompletionData.h"
@@ -28,6 +30,9 @@
 
 namespace YouCompleteMe {
 
+using boost::all;
+using boost::is_print;
+
 boost::mutex CandidateRepository::singleton_mutex_;
 CandidateRepository *CandidateRepository::instance_ = NULL;
 
@@ -58,12 +63,18 @@ std::vector< const Candidate * > CandidateRepository::GetCandidatesForStrings(
     boost::lock_guard< boost::mutex > locker( holder_mutex_ );
 
     foreach ( const std::string & candidate_text, strings ) {
-      const Candidate *&candidate = GetValueElseInsert( candidate_holder_,
-                                                        candidate_text,
-                                                        NULL );
+      const std::string &validated_candidate_text =
+        all( candidate_text, is_print( std::locale::classic() ) ) ?
+        candidate_text :
+        empty_;
+
+      const Candidate *&candidate = GetValueElseInsert(
+          candidate_holder_,
+          validated_candidate_text,
+          NULL );
 
       if ( !candidate )
-        candidate = new Candidate( candidate_text );
+        candidate = new Candidate( validated_candidate_text );
 
       candidates.push_back( candidate );
     }

cpp/ycm/CandidateRepository.h

@@ -56,6 +56,8 @@ private:
   static boost::mutex singleton_mutex_;
   static CandidateRepository *instance_;
 
+  const std::string empty_;
+
   // This data structure owns all the Candidate pointers
   CandidateHolder candidate_holder_;
 };

cpp/ycm/tests/CandidateRepository_test.cpp

@@ -0,0 +1,52 @@
+// Copyright (C) 2011, 2012  Strahinja Val Markovic  <val@markovic.io>
+//
+// This file is part of YouCompleteMe.
+//
+// YouCompleteMe is free software: you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// YouCompleteMe is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with YouCompleteMe.  If not, see <http://www.gnu.org/licenses/>.
+
+#include <gtest/gtest.h>
+#include "CandidateRepository.h"
+#include "Candidate.h"
+#include "Result.h"
+
+namespace YouCompleteMe {
+
+TEST( CandidateRepositoryTest, EmptyCandidatesForUnicode ) {
+  std::vector< std::string > inputs;
+  inputs.push_back( "fooδιακριτικός" );
+  inputs.push_back( "fooδιακός" );
+
+  CandidateRepository& repo = CandidateRepository::Instance();
+  std::vector< const Candidate* > candidates =
+    repo.GetCandidatesForStrings( inputs );
+
+  EXPECT_EQ( "", candidates[ 0 ]->Text() );
+  EXPECT_EQ( "", candidates[ 1 ]->Text() );
+}
+
+
+TEST( CandidateRepositoryTest, EmptyCandidatesForNonPrintable ) {
+  std::vector< std::string > inputs;
+  inputs.push_back( "\x01\x05\x0a\x15" );
+
+  CandidateRepository& repo = CandidateRepository::Instance();
+  std::vector< const Candidate* > candidates =
+    repo.GetCandidatesForStrings( inputs );
+
+  EXPECT_EQ( "", candidates[ 0 ]->Text() );
+}
+
+
+} // namespace YouCompleteMe
+