Update curated.py

curated.py

@@ -599,8 +599,8 @@ filtering_process = Div(
     Section(
         H3("FreeLaw"),
         H4("Download and Extraction"),
-        P("The dataset was downloaded from:" A("https://storage.courtlistener.com/bulk-data/", href="https://storage.courtlistener.com/bulk-data/"),". There are 19 CSV files which contain overlapping content. CSV files can contain content in multiple columns requiring a holistic extraction approach. Text was extracted from the following using html2text function.", 
-          D_code("""
+        P("The dataset was downloaded from:" A("https://storage.courtlistener.com/bulk-data/", href="https://storage.courtlistener.com/bulk-data/"),". There are 19 CSV files which contain overlapping content. CSV files can contain content in multiple columns requiring a holistic extraction approach. Text was extracted from the following using html2text function. The block below shows how each text type was extracted."), 
+        D_code("""
         ("html", html2text),
         ("html_lawbox", html2text),
         ("html_columbia", html2text),
@@ -608,7 +608,8 @@ filtering_process = Div(
         ("html_with_citations", html2text),
         ("xml_harvard", html2text),
         plain_text
-        """, language ="SQL")," All content was downloaded leading to high number of documents filtered during local deduplication. Following The Pile, priorty was given to plain_text first, followed by the columns in the table in reverse order."),
+        """, language ="SQL"),
+        P("All content was downloaded leading to high number of documents filtered during local deduplication. Following The Pile, priorty was given to plain_text first, followed by the columns in the table in reverse order."),
         H4("Filtering"),
         Ol(
             Li("Language Filter: English"),