Update curated.py

curated.py

@@ -679,8 +679,21 @@ filtering_process = Div(
         P("Papers from the PhilPapers database, a comprehensive index and bibliography of philosophy research maintained by the Center for Digital Philosophy at the University of Western Ontario."),
         P(B("Download and Extraction: "), "Original PDF files download from", A("https://philarchive.org/oai.pl", href="https://philarchive.org/oai.pl"), ". All available PDF's were downloaded. Each PDF was converted to text using java", D_code("-jar ../philpapers_resources/src/pdfbox-app-2.0.21.jar ExtractText {f0} {FOUT.name}", language="java"), ". After converting to text formatting, a language was detected and added using the langdetect (citation needed) library."),
         H4("Filtering"),
-        Ol(
-            Li("Many filters were used to clean the phil papers like double whitespaces, new lines etc. All filter details are here: https://github.com/thoppe/The-Pile-PhilPapers/blob/master/pdf_filter.py"),
+        Ul(
+            Li(P(B("Hyphenation Removal"), D_code("end-of", language="python"), " becomes ", D_code("end of", language="python"))),
+            Li(P(B("Newline Filtering"), "")),
+            Li(P(B("Header/Footer Filtering"), "")),
+            Li(P(B("Double Whitespace Filtering"), "")),
+            Li(P(B("Mean Line Length Check"), "")),
+            Li(P(B("CID Percentage Filter "), "")),
+            Li(P(B("Letterness Filter"), "")),
+            Li(P(B("Removing Leading/Trailing Numbers"), "")),
+            Li(P(B("Fixing Unicode Issues"), "")),
+            Li(P(B("Combining Diacritics Correction"), "")),
+            Li(P(B("Unigram Log Probability"), "")),
+            Li(""),
+            
+            
         ),
         table_div_phil,
         Details(