diff --git a/website/meta/universe.json b/website/meta/universe.json index b7842bddc..467f6d11d 100644 --- a/website/meta/universe.json +++ b/website/meta/universe.json @@ -3,7 +3,7 @@ { "id": "TeNs", "title": "Temporal Expressions Normalization spaCy", - "thumb": "https://github-production-user-asset-6210df.s3.amazonaws.com/40547052/433595900-fae3c9d9-7181-4d8b-8b49-e6dc4fca930b.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAVCODYLSA53PQK4ZA%2F20250414%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20250414T235545Z&X-Amz-Expires=300&X-Amz-Signature=e21d3c06300ceb15fa1dadd7cb60081cc9f1b35e5a7bfd07f6e8b90dd7fad9d0&X-Amz-SignedHeaders=host", + "thumb": "https://raw.githubusercontent.com/iliedorobat/timespan-normalization-spacy/refs/heads/main/icon.png", "url": "https://pypi.org/project/temporal-normalization-spacy/", "slogan": "A temporal expression normalization plugin for Romanian using rule-based methods and DBpedia mappings.", "description": "**[Temporal Expressions Normalization spaCy (TeNs)](https://github.com/iliedorobat/timespan-normalization-spacy)** is a powerful pipeline component for spaCy that seamlessly identifies and parses date entities in text. It leverages the **[Temporal Expressions Normalization Framework]( https://github.com/iliedorobat/timespan-normalization)** to recognize a wide variety of date formats using an extensive set of regular expressions (RegEx), ensuring robust and adaptable date extraction across diverse textual sources.\n\nUnlike conventional solutions that primarily focus on well-structured date formats, TeNs excels in handling real-world text by **identifying** not only standard date representations but also **abbreviated, informal, or even misspelled temporal expressions.** This makes it particularly effective for processing noisy or unstructured data, such as historical records, user-generated content, and scanned documents with OCR inaccuracies.", @@ -34,21 +34,25 @@ "", "# Display information about the identified and normalized dates in the text.", "for entity in doc.ents:", - " edges = entity._.time_series.edges", + " time_series = entity._.time_series", "", - " print('Start Edge:')", - " print(edges.start.serialize('\\t'))", - " print()", + " if isinstance(time_series, list):", + " for ts in time_series:", + " edges = ts.edges", "", - " print('End Edge:')", - " print(edges.end.serialize('\\t'))", - " print()", + " print('Start Edge:')", + " print(edges.start.serialize('\\t'))", + " print()", "", - " print('Periods:')", - " for period in entity._.time_series.periods:", - " print(period.serialize('\\t'))", - " print()", - " print('---------------------')" + " print('End Edge:')", + " print(edges.end.serialize('\\t'))", + " print()", + "", + " print('Periods:')", + " for period in ts.periods:", + " print(period.serialize('\\t'))", + " print()", + " print('---------------------')" ], "code_language": "python", "author": "Ilie Cristian Dorobat",