Spaces:
Runtime error
Runtime error
victormiller
commited on
Commit
•
8acb3f0
1
Parent(s):
dc1c900
Update curated.py
Browse files- curated.py +2 -2
curated.py
CHANGED
@@ -678,11 +678,11 @@ filtering_process = Div(
|
|
678 |
H3("Phil Papers"),
|
679 |
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."),
|
680 |
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."),
|
681 |
-
H4("Filtering"),
|
682 |
Ul(
|
683 |
Li(P(B("Hyphenation Removal:"), D_code("end-of", language="python"), " becomes ", D_code("end of", language="python"))),
|
684 |
Li(P(B("Newline Filtering:"), D_code("This is/na sentence.", language="python"), " becomes ", D_code("This is a sentence.", language="python"))),
|
685 |
-
Li(P(B("Header/Footer Filtering:"), D_code("(c) 2023 Company Name.", language="python"), " is removed ",))
|
686 |
Li(P(B("Double Whitespace Filtering:"), D_code("This is a test.", language="python"), " becomes ", D_code("This is a test.", language="python"))),
|
687 |
Li(P(B("Mean Line Length Check: "), "removes paragraphs with an average line length of < 2.0")),
|
688 |
Li(P(B("CID Percentage Filter: "), "removes LaTex heavy paragraphs that contain over 10% “CID” font artifacts.")),
|
|
|
678 |
H3("Phil Papers"),
|
679 |
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."),
|
680 |
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."),
|
681 |
+
H4("Filtering"),
|
682 |
Ul(
|
683 |
Li(P(B("Hyphenation Removal:"), D_code("end-of", language="python"), " becomes ", D_code("end of", language="python"))),
|
684 |
Li(P(B("Newline Filtering:"), D_code("This is/na sentence.", language="python"), " becomes ", D_code("This is a sentence.", language="python"))),
|
685 |
+
Li(P(B("Header/Footer Filtering:"), D_code("(c) 2023 Company Name.", language="python"), " is removed ",)),
|
686 |
Li(P(B("Double Whitespace Filtering:"), D_code("This is a test.", language="python"), " becomes ", D_code("This is a test.", language="python"))),
|
687 |
Li(P(B("Mean Line Length Check: "), "removes paragraphs with an average line length of < 2.0")),
|
688 |
Li(P(B("CID Percentage Filter: "), "removes LaTex heavy paragraphs that contain over 10% “CID” font artifacts.")),
|