Created
September 14, 2024 14:05
-
-
Save allista/58a4c32152858339cda38e31251ea24c to your computer and use it in GitHub Desktop.
Simple python script to generate kewords.txt for arduino library from its sources
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env python3 | |
| import os | |
| import re | |
| import argparse | |
| class Keywords: | |
| def __init__(self): | |
| self.functions = set() | |
| self.classes = set() | |
| self.constants = set() | |
| def update(self, other): | |
| self.functions.update(other.functions) | |
| self.classes.update(other.classes) | |
| self.constants.update(other.constants) | |
| def prune(self): | |
| self.functions -= self.classes | |
| def _write_set(self, f, keywords_set, keyword_type): | |
| for keyword in sorted(keywords_set): | |
| f.write(f'{keyword}\t{keyword_type}\n') | |
| f.write('\n') | |
| def write(self, output_path): | |
| with open(output_path, 'w', encoding='utf-8') as f: | |
| if self.classes: | |
| f.write('### CLASSES/STRUCTS ###\n') | |
| self._write_set(f, self.classes, 'KEYWORD1') | |
| if self.functions: | |
| f.write('### FUNCTIONS ###\n') | |
| self._write_set(f, self.functions, 'KEYWORD2') | |
| if self.functions: | |
| f.write('### CONSTANTS ###\n') | |
| self._write_set(f, self.constants, 'LITERAL1') | |
| def __len__(self): | |
| return len(self.functions)+len(self.classes)+len(self.constants) | |
| # Regular expressions to capture function, class, and constant definitions | |
| function_pattern = re.compile(r'^([a-zA-Z_][a-zA-Z0-9_]+\s*(\*+)?\s*)(?P<name>[a-zA-Z_][a-zA-Z0-9_]+)\s*\([^)]*\)') | |
| class_pattern = re.compile(r'^(class|struct)\s+(?P<name>[a-zA-Z_][a-zA-Z0-9_]*)') | |
| constant_pattern = re.compile(r'^(#define|((static\s+)?const\s+\w+))\s+(?P<name>[a-zA-Z_][a-zA-Z0-9_]*)') | |
| # Regular expression to match header guards like #ifndef MyLibrary_h | |
| header_guard_pattern = re.compile(r'^#ifndef\s+([a-zA-Z_][a-zA-Z0-9_]*_h)') | |
| def extract_keywords_from_file(file_path): | |
| keywords = Keywords() | |
| with open(file_path, 'r', encoding='utf-8') as f: | |
| # Track the current header guard to skip its corresponding #define | |
| current_header_guard = None | |
| for line in f: | |
| # Remove comments from lines | |
| line = re.sub(r'//.*', '', line) | |
| line = re.sub(r'/\*.*?\*/', '', line) | |
| # Detect header guard and store the guard name | |
| header_guard_match = header_guard_pattern.match(line) | |
| if header_guard_match: | |
| current_header_guard = header_guard_match.group(1) # Store the guard symbol | |
| continue | |
| # Skip the matching #define that corresponds to the header guard | |
| if current_header_guard and re.match(rf'#define\s+{current_header_guard}', line): | |
| current_header_guard = None # Reset after skipping the matching #define | |
| continue | |
| # Check for function, class, and constant definitions | |
| function_matches = [match.group('name') for match in function_pattern.finditer(line)] | |
| class_matches = [match.group('name') for match in class_pattern.finditer(line)] | |
| constant_matches = [match.group('name') for match in constant_pattern.finditer(line)] | |
| if function_matches: | |
| keywords.functions.update(function_matches) | |
| if class_matches: | |
| keywords.classes.update(class_matches) | |
| if constant_matches: | |
| keywords.constants.update(constant_matches) | |
| return keywords | |
| def scan_library_for_keywords(library_path): | |
| keywords = Keywords() | |
| for root, dirs, files in os.walk(library_path): | |
| for file in files: | |
| if file.endswith('.h'): | |
| file_path = os.path.join(root, file) | |
| keywords.update(extract_keywords_from_file(file_path)) | |
| return keywords | |
| def main(): | |
| # Set up argument parser | |
| parser = argparse.ArgumentParser(description='Generate keywords.txt for Arduino libraries.') | |
| # Add arguments for input and output paths | |
| parser.add_argument('source_path', type=str, help='Path to the Arduino library source files') | |
| parser.add_argument('output_path', type=str, help='Output path for keywords.txt') | |
| # Parse the arguments | |
| args = parser.parse_args() | |
| # Get keywords from source path | |
| keywords = scan_library_for_keywords(args.source_path) | |
| keywords.prune() | |
| # Write the keywords.txt to the output path | |
| keywords.write(args.output_path) | |
| print(f'{args.output_path} has been generated with {len(keywords)} keyword(s).') | |
| if __name__ == '__main__': | |
| main() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment