import re import json import re class CourseOutlineParser: def __init__(self, file_path): self.file_path = file_path self.content = self._read_markdown() def _read_markdown(self): with open(self.file_path, 'r', encoding='utf-8') as f: return f.read() def parse_content(self): result = {} # Main Heading main_heading_match = re.search(r'^#\s*\**(.*?)\**\s*$', self.content, re.MULTILINE) if main_heading_match: result['main_heading'] = main_heading_match.group(1).strip() # Find all stage titles and their content stage_pattern = r'##\s*\**(Stage \d+:?.*?)\**\s*\n' matches = list(re.finditer(stage_pattern, self.content)) stages = [] for idx, match in enumerate(matches): stage_title = match.group(1).strip() # Get content between this match and next one (or end of file) start = match.end() end = matches[idx + 1].start() if idx + 1 < len(matches) else len(self.content) stage_content = self.content[start:end] focus = self._extract_section(stage_content, 'Focus') outcome = self._extract_section(stage_content, 'Outcome') duration = self._extract_section(stage_content, 'Duration') topics = self._extract_topics(stage_content) stages.append({ 'stage_title': stage_title, 'focus': focus, 'outcome': outcome, 'duration': duration, 'topics_covered': topics }) result['stages'] = stages return result def _extract_section(self, content, section_name): pattern = rf'###\s*\**{section_name}\**\s*(.*?)\s*(?=\n###|\Z)' match = re.search(pattern, content, re.DOTALL) return match.group(1).strip() if match else None def _extract_topics(self, content): pattern = r'###\s*\**Topics Covered\**\s*(.*?)(?=\n###|\Z)' match = re.search(pattern, content, re.DOTALL) if match: topics_block = match.group(1).strip() topics = re.findall(r'-\s+(.*)', topics_block) return [t.strip() for t in topics] return [] # class CourseOutlineParser: # """ # Parses a markdown-formatted course outline file and extracts structured stage-wise metadata. # """ # def __init__(self, file_path): # self.file_path = file_path # self.content = self._read_markdown() # def _read_markdown(self): # """Reads the markdown file content.""" # with open(self.file_path, 'r', encoding='utf-8') as f: # return f.read() # def parse_content(self): # """Parses the markdown content and extracts the course structure.""" # result = {} # # Extract main heading (with or without **) # main_heading_match = re.search(r'^#\s*\**(.*?)\**\s*$', self.content, re.MULTILINE) # if main_heading_match: # result['main_heading'] = main_heading_match.group(1).strip() # # Split stages (with or without **) # stage_blocks = re.split(r'##\s*\**(Stage \d+ - .*?)\**\s*$', self.content, flags=re.MULTILINE) # stages = [] # for i in range(1, len(stage_blocks), 2): # stage_title = stage_blocks[i].strip() # stage_content = stage_blocks[i+1] # focus = self._extract_section(stage_content, 'Focus') # outcome = self._extract_section(stage_content, 'Outcome') # duration = self._extract_section(stage_content, 'Duration') # topics = self._extract_topics(stage_content) # stages.append({ # 'stage_title': stage_title, # 'focus': focus, # 'outcome': outcome, # 'duration': duration, # 'topics_covered': topics # }) # result['stages'] = stages # return result # def _extract_section(self, content, section_name): # """Extracts a section like Focus, Outcome, etc.""" # pattern = rf'###\s*\**{section_name}\**\s*(.*?)\s*(?=(###|$))' # match = re.search(pattern, content, re.DOTALL) # return match.group(1).strip() if match else None # def _extract_topics(self, content): # """Extracts bullet-point topics under 'Topics Covered'.""" # pattern = r'###\s*\**Topics Covered\**\s*(.*?)(?=(###|$))' # match = re.search(pattern, content, re.DOTALL) # if match: # topics_block = match.group(1).strip() # topics = re.findall(r'-\s+(.*)', topics_block) # return [t.strip() for t in topics] # return [] # def parse_content(self): # """Parses the markdown content and extracts the course structure.""" # result = {} # # Extract main heading # # main_heading_match = re.search(r'#\s*\*\*(.*?)\*\*', self.content) # main_heading_match = re.search(r'^#\s*(?:\*\*)?(.*?)(?:\*\*)?\s*$', self.content, re.MULTILINE) # print(f"The main heading match is : {main_heading_match}") # if main_heading_match: # result['main_heading'] = main_heading_match.group(1).strip() # # Split stages # # stage_blocks = re.split(r'##\s*\*\*(Stage \d+.*?)\*\*', self.content) # stage_blocks = re.split(r'##\s*(?:\*\*)?(Stage \d+.*?)(?:\*\*)?', self.content) # # The first element is before stages, ignore it # stages = [] # for i in range(1, len(stage_blocks), 2): # stage_title = stage_blocks[i].strip() # stage_content = stage_blocks[i+1] # # Extract Focus # focus = self._extract_section(stage_content, 'Focus') # # Extract Outcome # outcome = self._extract_section(stage_content, 'Outcome') # # Extract Duration # duration = self._extract_section(stage_content, 'Duration') # # Extract Topics Covered # topics = self._extract_topics(stage_content) # # Add to stages list # stages.append({ # 'stage_title': stage_title, # 'focus': focus, # 'outcome': outcome, # 'duration': duration, # 'topics_covered': topics # }) # result['stages'] = stages # return result # def _extract_section(self, text, section_name): # """Extracts a specific section (e.g., Focus, Outcome) from stage content.""" # pattern = fr'###\s*{section_name}\s*(.*?)\n###' # match = re.search(pattern, text, re.DOTALL) # return match.group(1).strip() if match else None # def _extract_topics(self, text): # """Extracts topics covered as a list.""" # topics_match = re.search(r'###\s*Topics Covered\s*(.*?)($|\n##)', text, re.DOTALL) # if topics_match: # topics_raw = topics_match.group(1).strip() # return [line.strip('- ').strip() for line in topics_raw.split('\n') if line.strip()] # return [] def export_to_json(self, output_path, parsed_data): """Exports the parsed result to a JSON file.""" with open(output_path, 'w', encoding='utf-8') as f: json.dump(parsed_data, f, indent=4)