From 885f51b83d45477309d60905bb00408964d647e2 Mon Sep 17 00:00:00 2001 From: Simon Moisy Date: Sat, 22 Mar 2025 04:46:48 +0800 Subject: [PATCH] cleanup --- article_analyzer.py | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/article_analyzer.py b/article_analyzer.py index ea75917..b6409a0 100644 --- a/article_analyzer.py +++ b/article_analyzer.py @@ -74,5 +74,12 @@ class ArticleAnalyzer: def classify_article_finbert(self, article_html): article_md = self.convert_to_markdown(article_html) - result = self.classifier(article_md) - return result \ No newline at end of file + chunk_size = 512 + chunks = [article_md[i:i + chunk_size] for i in range(0, len(article_md), chunk_size)] + + results = [] + for chunk in chunks: + result = self.classifier(chunk) + results.append(result) + + return results \ No newline at end of file