modified CMakeLists to generate vocabulary.h

src/CMakeLists.txt

@@ -1,14 +1,17 @@
 
 configure_file (./include/version.h.cmake version.h @ONLY)
 include_directories(./include ${CMAKE_CURRENT_BINARY_DIR})
-
+include_directories(${CMAKE_BINARY_DIR})
 set(commonsrc FlowAware.cpp Symbolic.cpp utils.cpp)
 set(libsrc libIR2Vec.cpp ${commonsrc})
 set(binsrc CollectIR.cpp IR2Vec.cpp)
 
-file(GLOB RESOURCE_FILES ../vocabulary/seedEmbeddingVocab.txt)
-
 option(LLVM_IR2VEC "where to enable IR2Vec as subproject for LLVM" OFF)
+execute_process(
+    COMMAND bash generate_vocabulary.sh -o ${CMAKE_BINARY_DIR}/vocabulary.h
+    WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
+    COMMAND echo "Vocabulary file generated."
+)
 
 if(NOT LLVM_IR2VEC)
 
@@ -37,7 +40,6 @@ if(NOT LLVM_IR2VEC)
       VERSION ${PROJECT_VERSION}
       SOVERSION 1
       PUBLIC_HEADER "./include/IR2Vec.h"
-      RESOURCE ${RESOURCE_FILES}
       OUTPUT_NAME ${IR2VEC_LIB}
       LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/lib
       ARCHIVE_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/lib

generate_vocabulary.sh → src/generate_vocabulary.sh

@@ -1,8 +1,30 @@
 #!/bin/bash
 
+# Parse arguments
+while [[ $# -gt 0 ]]; do
+	key="$1"
+
+	case $key in
+	-o | --output)
+		output_file="$2"
+		shift # past argument
+		shift # past value
+		;;
+	*) # unknown option
+		echo "Unknown option: $1"
+		exit 1
+		;;
+	esac
+done
+
+# Check if the output file path is provided
+if [ -z "$output_file" ]; then
+	echo "Error: Output file path not provided."
+	exit 1
+fi
+
 # Define paths
-vocab_file="vocabulary/seedEmbeddingVocab.txt"
-output_file="src/include/vocabulary.h" # Output file path adjusted
+vocab_file="../vocabulary/seedEmbeddingVocab.txt"
 
 # Check if the vocabulary file exists
 if [ ! -f "$vocab_file" ]; then

src/utils.cpp

@@ -6,6 +6,7 @@
 //
 #include "utils.h"
 #include "IR2Vec.h"
+#include "vocabulary.h"
 #include <fstream>
 #include <string>
 
@@ -40,26 +41,8 @@ std::unique_ptr<Module> IR2Vec::getLLVMIR() {
 }
 
 void IR2Vec::collectDataFromVocab(std::map<std::string, Vector> &opcMap) {
-  IR2VEC_DEBUG(errs() << "Reading from " + vocab + "\n");
-  std::ifstream i(vocab);
-  std::string delimiter = ":";
-  for (std::string line; getline(i, line);) {
-    std::string token = line.substr(0, line.find(delimiter));
-    Vector rep;
-    std::string vec = line.substr(line.find(delimiter) + 1, line.length());
-    std::string val = vec.substr(vec.find("[") + 1, vec.find(", ") - 1);
-    rep.push_back(stod(val));
-    int pos = vec.find(", ");
-    vec = vec.substr(pos + 1);
-    for (int i = 1; i < DIM - 1; i++) {
-      val = vec.substr(1, vec.find(", ") - 1);
-      rep.push_back(stod(val));
-      pos = vec.find(", ");
-      vec = vec.substr(pos + 1);
-    }
-    val = vec.substr(1, vec.find("]") - 1);
-    rep.push_back(stod(val));
-    opcMap[token] = rep;
+  for (const auto &entry : vocabulary) {
+    opcMap[entry.first] = entry.second;
   }
 }