diff options
Diffstat (limited to 'scripts/clang-tools/gen_compile_commands.py')
| -rwxr-xr-x | scripts/clang-tools/gen_compile_commands.py | 188 |
1 files changed, 146 insertions, 42 deletions
diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py index 1d1bde1fd45e..6f4afa92a466 100755 --- a/scripts/clang-tools/gen_compile_commands.py +++ b/scripts/clang-tools/gen_compile_commands.py @@ -19,8 +19,14 @@ _DEFAULT_OUTPUT = 'compile_commands.json' _DEFAULT_LOG_LEVEL = 'WARNING' _FILENAME_PATTERN = r'^\..*\.cmd$' -_LINE_PATTERN = r'^cmd_[^ ]*\.o := (.* )([^ ]*\.c) *(;|$)' +_LINE_PATTERN = r'^(saved)?cmd_[^ ]*\.o := (?P<command_prefix>.* )(?P<file_path>[^ ]*\.[cS]) *(;|$)' _VALID_LOG_LEVELS = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'] + +# Pre-compiled regexes for better performance +_INCLUDE_PATTERN = re.compile(r'^\s*#\s*include\s*[<"]([^>"]*)[>"]') +_C_INCLUDE_PATTERN = re.compile(r'^\s*#\s*include\s*"([^"]*\.c)"\s*$') +_FILENAME_MATCHER = re.compile(_FILENAME_PATTERN) + # The tools/ directory adopts a different build system, and produces .cmd # files in a different format. Do not support it. _EXCLUDE_DIRS = ['.git', 'Documentation', 'include', 'tools'] @@ -64,7 +70,7 @@ def parse_arguments(): args = parser.parse_args() return (args.log_level, - os.path.abspath(args.directory), + os.path.realpath(args.directory), args.output, args.ar, args.paths if len(args.paths) > 0 else [args.directory]) @@ -82,7 +88,6 @@ def cmdfiles_in_dir(directory): The path to a .cmd file. """ - filename_matcher = re.compile(_FILENAME_PATTERN) exclude_dirs = [ os.path.join(directory, d) for d in _EXCLUDE_DIRS ] for dirpath, dirnames, filenames in os.walk(directory, topdown=True): @@ -92,7 +97,7 @@ def cmdfiles_in_dir(directory): continue for filename in filenames: - if filename_matcher.match(filename): + if _FILENAME_MATCHER.match(filename): yield os.path.join(dirpath, filename) @@ -109,20 +114,6 @@ def to_cmdfile(path): return os.path.join(dir, '.' + base + '.cmd') -def cmdfiles_for_o(obj): - """Generate the iterator of .cmd files associated with the object - - Yield the .cmd file used to build the given object - - Args: - obj: The object path - - Yields: - The path to .cmd file - """ - yield to_cmdfile(obj) - - def cmdfiles_for_a(archive, ar): """Generate the iterator of .cmd files associated with the archive. @@ -152,19 +143,98 @@ def cmdfiles_for_modorder(modorder): """ with open(modorder) as f: for line in f: - ko = line.rstrip() - base, ext = os.path.splitext(ko) - if ext != '.ko': - sys.exit('{}: module path must end with .ko'.format(ko)) + obj = line.rstrip() + base, ext = os.path.splitext(obj) + if ext != '.o': + sys.exit('{}: module path must end with .o'.format(obj)) mod = base + '.mod' - # The first line of *.mod lists the objects that compose the module. + # Read from *.mod, to get a list of objects that compose the module. with open(mod) as m: - for obj in m.readline().split(): - yield to_cmdfile(obj) + for mod_line in m: + yield to_cmdfile(mod_line.rstrip()) + + +def extract_includes_from_file(source_file, root_directory): + """Extract #include statements from a C file. + + Args: + source_file: Path to the source .c file to analyze + root_directory: Root directory for resolving relative paths + + Returns: + List of header files that should be included (without quotes/brackets) + """ + includes = [] + if not os.path.exists(source_file): + return includes + + try: + with open(source_file, 'r') as f: + for line in f: + line = line.strip() + # Look for #include statements. + # Match both #include "header.h" and #include <header.h>. + match = _INCLUDE_PATTERN.match(line) + if match: + header = match.group(1) + # Skip including other .c files to avoid circular includes. + if not header.endswith('.c'): + # For relative includes (quoted), resolve path relative to source file. + if '"' in line: + src_dir = os.path.dirname(source_file) + header_path = os.path.join(src_dir, header) + if os.path.exists(header_path): + rel_header = os.path.relpath(header_path, root_directory) + includes.append(rel_header) + else: + includes.append(header) + else: + # System include like <linux/sched.h>. + includes.append(header) + except IOError: + pass + + return includes + + +def find_included_c_files(source_file, root_directory): + """Find .c files that are included by the given source file. + + Args: + source_file: Path to the source .c file + root_directory: Root directory for resolving relative paths + + Yields: + Full paths to included .c files + """ + if not os.path.exists(source_file): + return + + try: + with open(source_file, 'r') as f: + for line in f: + line = line.strip() + # Look for #include "*.c" patterns. + match = _C_INCLUDE_PATTERN.match(line) + if match: + included_file = match.group(1) + # Handle relative paths. + if not os.path.isabs(included_file): + src_dir = os.path.dirname(source_file) + included_file = os.path.join(src_dir, included_file) + + # Normalize the path. + included_file = os.path.normpath(included_file) + + # Check if the file exists. + if os.path.exists(included_file): + yield included_file + except IOError: + pass def process_line(root_directory, command_prefix, file_path): - """Extracts information from a .cmd line and creates an entry from it. + """Extracts information from a .cmd line and creates entries from it. Args: root_directory: The directory that was searched for .cmd files. Usually @@ -174,27 +244,64 @@ def process_line(root_directory, command_prefix, file_path): Usually relative to root_directory, but sometimes absolute. Returns: - An entry to append to compile_commands. + A list of entries to append to compile_commands (may include multiple + entries if the source file includes other .c files). Raises: ValueError: Could not find the extracted file based on file_path and root_directory or file_directory. """ # The .cmd files are intended to be included directly by Make, so they - # escape the pound sign '#', either as '\#' or '$(pound)' (depending on the - # kernel version). The compile_commands.json file is not interepreted - # by Make, so this code replaces the escaped version with '#'. - prefix = command_prefix.replace('\#', '#').replace('$(pound)', '#') + # escape the pound sign '#' as '$(pound)'. The compile_commands.json file + # is not interepreted by Make, so this code replaces the escaped version + # with '#'. + prefix = command_prefix.replace('$(pound)', '#') - # Use os.path.abspath() to normalize the path resolving '.' and '..' . - abs_path = os.path.abspath(os.path.join(root_directory, file_path)) + # Return the canonical path, eliminating any symbolic links encountered in the path. + abs_path = os.path.realpath(os.path.join(root_directory, file_path)) if not os.path.exists(abs_path): raise ValueError('File %s not found' % abs_path) - return { + + entries = [] + + # Create entry for the main source file. + main_entry = { 'directory': root_directory, 'file': abs_path, 'command': prefix + file_path, } + entries.append(main_entry) + + # Find and create entries for included .c files. + for included_c_file in find_included_c_files(abs_path, root_directory): + # For included .c files, create a compilation command that: + # 1. Uses the same compilation flags as the parent file + # 2. But compiles the included file directly (not the parent) + # 3. Includes necessary headers from the parent file for proper macro resolution + + # Convert absolute path to relative for the command. + rel_path = os.path.relpath(included_c_file, root_directory) + + # Extract includes from the parent file to provide proper compilation context. + extra_includes = '' + try: + parent_includes = extract_includes_from_file(abs_path, root_directory) + if parent_includes: + extra_includes = ' ' + ' '.join('-include ' + inc for inc in parent_includes) + except IOError: + pass + + included_entry = { + 'directory': root_directory, + 'file': included_c_file, + # Use the same compilation prefix but target the included file directly. + # Add extra headers for proper macro resolution. + 'command': prefix + extra_includes + ' ' + rel_path, + } + entries.append(included_entry) + logging.debug('Added entry for included file: %s', included_c_file) + + return entries def main(): @@ -211,13 +318,10 @@ def main(): for path in paths: # If 'path' is a directory, handle all .cmd files under it. # Otherwise, handle .cmd files associated with the file. - # Most of built-in objects are linked via archives (built-in.a or lib.a) - # but some objects are linked to vmlinux directly. + # built-in objects are linked via vmlinux.a # Modules are listed in modules.order. if os.path.isdir(path): cmdfiles = cmdfiles_in_dir(path) - elif path.endswith('.o'): - cmdfiles = cmdfiles_for_o(path) elif path.endswith('.a'): cmdfiles = cmdfiles_for_a(path, ar) elif path.endswith('modules.order'): @@ -230,15 +334,15 @@ def main(): result = line_matcher.match(f.readline()) if result: try: - entry = process_line(directory, result.group(1), - result.group(2)) - compile_commands.append(entry) + entries = process_line(directory, result.group('command_prefix'), + result.group('file_path')) + compile_commands.extend(entries) except ValueError as err: logging.info('Could not add line from %s: %s', cmdfile, err) with open(output, 'wt') as f: - json.dump(compile_commands, f, indent=2, sort_keys=True) + json.dump(sorted(compile_commands, key=lambda x: x["file"]), f, indent=2, sort_keys=True) if __name__ == '__main__': |