| import re | |
| from pymongo import MongoClient | |
| from src.utils.markdown_processing.CustomMarkdownAnalyzer.MarkdownAnalyzer import MarkdownAnalyzer | |
| from src.utils.markdown_processing.CustomMarkdownAnalyzer.event_texts import TEXTS | |
| def get_dates(text): | |
| pattern = r"\b(\d{2}\.\d{2}\.\d{4})\b" | |
| return re.findall(pattern, text) | |
| def get_date_ranges(text): | |
| pattern = r"\b(\d{2}\.\d{2}\.\d{4})\b\s*(?:\-|bis|bis\s*zum)\s*\b(\d{2}\.\d{2}\.\d{4})\b" | |
| return re.findall(pattern, text) | |
| # for text in TEXTS: | |
| # analyzer = MarkdownAnalyzer(text) | |
| # result = analyzer.identify_all() | |
| # result = sorted(result, key=lambda el: el.line) | |
| # for element in result: | |
| # if get_date_ranges(element.text): | |
| # print(f"Found Date Range in {element.text}\n") | |
| # elif get_dates(element.text): | |
| # print(f"Found Date in {element.text}\n") | |
| for text in TEXTS: | |
| analyzer = MarkdownAnalyzer(text) | |
| segments = analyzer.segmentation() | |
| text_dates = [] | |
| for segment in segments: | |
| segment_dates = [] | |
| for element in segment: | |
| date_ranges = get_date_ranges(element.text) | |
| if date_ranges: | |
| segment_dates.extend(date_ranges) | |
| # print(f"Found Date Range in {element.text}\n") | |
| else: | |
| dates = get_dates(element.text) | |
| if dates: | |
| segment_dates.extend(dates) | |
| # print(f"Found Date in {element.text}\n") | |
| text_dates.append(segment_dates) | |
| print(text) | |
| print(text_dates) | |
| print("*"*100) | |
| # uri = f"mongodb+srv://event_data_extraction_application:[email protected]/?retryWrites=true&w=majority&appName=Cluster0" | |
| # client = MongoClient(uri) | |
| # db = client.event_data | |
| # | |
| # event_urls = db.event_urls | |
| # | |
| # for event in event_urls.find({"data": {"$ne": None}}, {"data": 1, "_id": 0}): | |
| # analyzer = MarkdownAnalyzer(event["data"]) | |
| # result = analyzer.identify_all() | |
| # result = sorted(result, key=lambda el: el.line) | |
| # for element in result: | |
| # if has_date(element.text): | |
| # | |
| # print(f"Found Date in {element.text}\n") | |