[llvm] [Runtimes] Merge 'compile_commands.json' files from runtimes build (PR #116303)

[Joseph Huber via llvm-commits]

https://github.com/jhuber6 created https://github.com/llvm/llvm-project/pull/116303

Summary:
When building a project in a runtime mode, the compilation database is a
separate CMake invocation. So its `compile_commands.json` file will be
placed elsewhere in the `runtimes/runtime-bins` directory. This is
somewhat annoying for ongoing development when a runtimes build is
necessary. This patch adds some CMake magic to merge the two files.


>From 11aab09d95b0e752995762ec233ea21907a55a03 Mon Sep 17 00:00:00 2001
From: Joseph Huber <huberjn at outlook.com>
Date: Thu, 14 Nov 2024 18:34:53 -0600
Subject: [PATCH] [Runtimes] Merge 'compile_commands.json' files from runtimes
 build

Summary:
When building a project in a runtime mode, the compilation database is a
separate CMake invocation. So its `compile_commands.json` file will be
placed elsewhere in the `runtimes/runtime-bins` directory. This is
somewhat annoying for ongoing development when a runtimes build is
necessary. This patch adds some CMake magic to merge the two files.
---
 llvm/utils/merge-json.py | 42 ++++++++++++++++++++++++++++++++++++++++
 runtimes/CMakeLists.txt  | 15 ++++++++++++++
 2 files changed, 57 insertions(+)
 create mode 100644 llvm/utils/merge-json.py

diff --git a/llvm/utils/merge-json.py b/llvm/utils/merge-json.py
new file mode 100644
index 00000000000000..85136f3a120895
--- /dev/null
+++ b/llvm/utils/merge-json.py
@@ -0,0 +1,42 @@
+#!/usr/bin/env python
+"""A command line utility to merge two JSON files.
+
+This is a python program that merges two JSON files into a single one. The 
+intended use for this is to combine generated 'compile_commands.json' files
+created by CMake when performing an LLVM runtime build.
+"""
+
+import argparse
+import json
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument(
+        "-o", type=str,
+        help="The output file to write JSON data to",
+        default=None, nargs="?",
+    )
+    parser.add_argument(
+        "json_files", type=str, nargs='+', help="Input JSON files to merge"
+    )
+    args = parser.parse_args()
+
+    merged_data = []
+    
+    for json_file in args.json_files:
+        try:
+            with open(json_file, 'r') as f:
+                data = json.load(f)
+                merged_data.extend(data)
+        except (IOError, json.JSONDecodeError):
+            continue
+
+    # Deduplicate by converting each entry to a tuple of sorted key-value pairs
+    unique_data = list({json.dumps(entry, sort_keys=True) for entry in merged_data})
+    unique_data = [json.loads(entry) for entry in unique_data]
+
+    with open(args.o, 'w') as f:
+        json.dump(unique_data, f, indent=2)
+
+if __name__ == "__main__":
+    main()
diff --git a/runtimes/CMakeLists.txt b/runtimes/CMakeLists.txt
index 832a7d0c193592..f9c1704d864515 100644
--- a/runtimes/CMakeLists.txt
+++ b/runtimes/CMakeLists.txt
@@ -313,3 +313,18 @@ if(SUB_COMPONENTS)
       ${LLVM_BINARY_DIR}/runtimes/Components.cmake)
   endif()
 endif()
+
+# If the user requested 'compile_commands.json' we merge the generated JSON from
+# the created directories.
+if(CMAKE_EXPORT_COMPILE_COMMANDS)
+  file(TO_NATIVE_PATH "${LLVM_MAIN_SRC_DIR}/utils/merge-json.py" MERGE_JSON_PATH)
+  add_custom_command(OUTPUT ${LLVM_BINARY_DIR}/compile_commands.json
+                     COMMAND ${CMAKE_COMMAND} -E touch ${LLVM_BINARY_DIR}/compile_commands.json
+                     COMMAND ${CMAKE_COMMAND} -E touch ${CMAKE_BINARY_DIR}/compile_commands.json
+                     COMMAND ${Python3_EXECUTABLE} ${MERGE_JSON_PATH}
+                             ${LLVM_BINARY_DIR}/compile_commands.json   
+                             ${CMAKE_BINARY_DIR}/compile_commands.json
+                             -o ${LLVM_BINARY_DIR}/compile_commands.json   
+                     DEPENDS ${CMAKE_BINARY_DIR}/compile_commands.json)
+  add_custom_target(merge_runtime_commands ALL DEPENDS ${LLVM_BINARY_DIR}/compile_commands.json)
+endif()