Remove generateTriplets.py to move to next PR

Author: svkeerthy

llvm/docs/CommandGuide/llvm-ir2vec.rst

@@ -55,9 +55,9 @@ Triplet Generation Mode
 
 In triplet mode, :program:`llvm-ir2vec` analyzes LLVM IR and extracts numeric
 triplets consisting of opcode IDs, type IDs, and operand IDs. These triplets 
-are generated in train2id format. The tool outputs numeric IDs directly using 
-the ir2vec::Vocabulary mapping infrastructure, eliminating the need for 
-string-to-ID preprocessing.
+are generated in the standard format used for knowledge graph embedding training. 
+The tool outputs numeric IDs directly using the ir2vec::Vocabulary mapping 
+infrastructure, eliminating the need for string-to-ID preprocessing.
 
 Usage:
 
@@ -69,9 +69,9 @@ Entity Mapping Generation Mode
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 In entity mode, :program:`llvm-ir2vec` generates the entity mappings supported by
-IR2Vec in entity2id format. This mode outputs all supported entities (opcodes, 
-types, and operands) with their corresponding numeric IDs, and is not specific for 
-an LLVM IR file.
+IR2Vec in the standard format used for knowledge graph embedding training. This
+mode outputs all supported entities (opcodes, types, and operands) with their
+corresponding numeric IDs, and is not specific for an LLVM IR file.
 
 Usage:
 

llvm/test/tools/llvm-ir2vec/error-handling.ll

@@ -0,0 +1,22 @@
+; Test error handling and input validation for llvm-ir2vec tool
+
+; RUN: not llvm-ir2vec --mode=embeddings %s 2>&1 | FileCheck %s -check-prefix=CHECK-NO-VOCAB
+
+; RUN: not llvm-ir2vec --mode=embeddings --function=nonexistent --ir2vec-vocab-path=%ir2vec_test_vocab_dir/dummy_3D_nonzero_opc_vocab.json %s 2>&1 | FileCheck %s -check-prefix=CHECK-FUNC-NOT-FOUND
+
+; RUN: llvm-ir2vec --mode=triplets --ir2vec-vocab-path=%ir2vec_test_vocab_dir/dummy_3D_nonzero_opc_vocab.json --level=inst %s 2>&1 | FileCheck %s -check-prefix=CHECK-UNUSED-LEVEL
+; RUN: llvm-ir2vec --mode=entities --level=inst %s 2>&1 | FileCheck %s -check-prefix=CHECK-UNUSED-LEVEL
+
+; RUN: llvm-ir2vec --mode=triplets --ir2vec-vocab-path=%ir2vec_test_vocab_dir/dummy_3D_nonzero_opc_vocab.json --function=dummy %s 2>&1 | FileCheck %s -check-prefix=CHECK-UNUSED-FUNC
+; RUN: llvm-ir2vec --mode=entities --function=dummy %s 2>&1 | FileCheck %s -check-prefix=CHECK-UNUSED-FUNC
+
+; Simple test function for valid IR
+define i32 @test_func(i32 %a) {
+entry:
+  ret i32 %a
+}
+
+; CHECK-NO-VOCAB: error: IR2Vec vocabulary file path not specified; You may need to set it using --ir2vec-vocab-path
+; CHECK-FUNC-NOT-FOUND: Error: Function 'nonexistent' not found
+; CHECK-UNUSED-LEVEL: Warning: --level option is ignored
+; CHECK-UNUSED-FUNC: Warning: --function option is ignored

llvm/tools/llvm-ir2vec/llvm-ir2vec.cpp

@@ -128,6 +128,7 @@ class IR2VecTool {
     // option
     MAM.registerPass([&] { return PassInstrumentationAnalysis(); });
     MAM.registerPass([&] { return IR2VecVocabAnalysis(); });
+    // This will throw an error if vocab is not found or invalid
     Vocab = &MAM.getResult<IR2VecVocabAnalysis>(M);
     return Vocab->isValid();
   }
@@ -293,11 +294,9 @@ Error processModule(Module &M, raw_ostream &OS) {
   if (Mode == EmbeddingMode) {
     // Initialize vocabulary for embedding generation
     // Note: Requires --ir2vec-vocab-path option to be set
-    if (!Tool.initializeVocabulary())
-      return createStringError(
-          errc::invalid_argument,
-          "Failed to initialize IR2Vec vocabulary. "
-          "Make sure to specify --ir2vec-vocab-path for embedding mode.");
+    auto VocabStatus = Tool.initializeVocabulary();
+    assert(VocabStatus && "Failed to initialize IR2Vec vocabulary");
+    (void)VocabStatus;
 
     if (!FunctionName.empty()) {
       // Process single function
@@ -335,12 +334,6 @@ int main(int argc, char **argv) {
       "See https://llvm.org/docs/CommandGuide/llvm-ir2vec.html for more "
       "information.\n");
 
-  // Validate input file requirement
-  if (InputFilename.empty() && Mode != EntityMode) {
-    errs() << "Error: Input file (.bc/.ll) or stdin (-) is required\n";
-    return 1;
-  }
-
   // Validate command line options
   if (Mode != EmbeddingMode) {
     if (Level.getNumOccurrences() > 0)