Update llvm version for C tokenizer (#14)

* update print statement

* update llvm version

Author: bmcutler

compare_hashes/compare_hashes.cpp

@@ -207,17 +207,20 @@ int main(int argc, char* argv[]) {
   std::map<Submission,std::map<int,std::map<Submission, std::vector<Sequence> > > > suspicious;
 
   int my_counter = 0;
-
+  int my_percent = 0;
+  
   // ---------------------------------------------------------------------------
   // walk over the structure containing all of the hashes identifying
   // common to many/all, provided code, suspicious matches, and unique code
   for (hashed_sequences::iterator itr = hash_counts.begin(); itr != hash_counts.end(); itr++) {
     int count = itr->second.size();
 
     my_counter++;
-
-    std::cout << "hash walk " << hash_counts.size() << " " << my_counter << std::endl;
-
+    int percent = (int) (100 * (my_counter / float(hash_counts.size())));
+    if (percent > my_percent) {
+      std::cout << "hash walk " << percent << "% complete" << std::endl;
+      my_percent = percent;
+    }
     if (count > threshold) {
       // common to many/all
       for (std::map<std::string,std::vector<Sequence> >::iterator itr2 = itr->second.begin(); itr2 != itr->second.end(); itr2++) {

tokenizer/c/c_tokenizer.py

@@ -14,7 +14,10 @@
 # copy the concatenated file to the temporary file location
 shutil.copy(sys.argv[1],tmp_cpp_file_name)
 
-clang.cindex.Config.set_library_file("/usr/lib/llvm-3.8/lib/libclang-3.8.so.1")
+if (os.path.isfile("/usr/lib/llvm-6.0/lib/libclang.so.1")):
+        clang.cindex.Config.set_library_file("/usr/lib/llvm-6.0/lib/libclang.so.1")
+elif (os.path.isfile("/usr/lib/llvm-3.8/lib/libclang-3.8.so.1")):
+        clang.cindex.Config.set_library_file("/usr/lib/llvm-3.8/lib/libclang-3.8.so.1")
 idx = clang.cindex.Index.create()
 
 # parse the input file