eellak · Mar 23, 2025
diff --git a/‎pipeline/src/glossapi.egg-info/PKG-INFO
+3-4 b/‎pipeline/src/glossapi.egg-info/PKG-INFO
+3-4
diff --git a/‎pipeline/src/glossapi.egg-info/SOURCES.txt
-1 b/‎pipeline/src/glossapi.egg-info/SOURCES.txt
-1
diff --git a/‎scraping/download_and_extract_scripts/copy_paste_pdf.py
-67 b/‎scraping/download_and_extract_scripts/copy_paste_pdf.py
-67
diff --git a/‎scraping/download_and_extract_scripts/create_metadata_json.py
-36 b/‎scraping/download_and_extract_scripts/create_metadata_json.py
-36
diff --git a/‎scraping/download_and_extract_scripts/downloader10.py
-264 b/‎scraping/download_and_extract_scripts/downloader10.py
-264
diff --git a/‎scraping/download_and_extract_scripts/extractor4.py
-99 b/‎scraping/download_and_extract_scripts/extractor4.py
-99
diff --git a/‎scraping/download_and_extract_scripts/site_specific_scrapers/gr-land-studies.py
-79 b/‎scraping/download_and_extract_scripts/site_specific_scrapers/gr-land-studies.py
-79
diff --git a/‎scraping/download_and_extract_scripts/site_specific_scrapers/gr-lang-anthology.py
-89 b/‎scraping/download_and_extract_scripts/site_specific_scrapers/gr-lang-anthology.py
-89
diff --git a/‎scraping/download_and_extract_scripts/site_specific_scrapers/gr-lang-perilhpsh.py
-65 b/‎scraping/download_and_extract_scripts/site_specific_scrapers/gr-lang-perilhpsh.py
-65
diff --git a/‎scraping/download_and_extract_scripts/site_specific_scrapers/lawspot2.py
-59 b/‎scraping/download_and_extract_scripts/site_specific_scrapers/lawspot2.py
-59
diff --git a/‎scraping/paragraphs_final.csv
-806 b/‎scraping/paragraphs_final.csv
-806
@@ -1,4 +1,4 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: glossapi
 Version: 0.0.7
 Summary: A library for processing academic texts in Greek and other languages
@@ -11,7 +11,6 @@ Classifier: Operating System :: OS Independent
 Classifier: Development Status :: 3 - Alpha
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
-License-File: LICENSE.md
 Requires-Dist: pandas
 Requires-Dist: numpy
 Requires-Dist: scikit-learn
@@ -64,8 +63,8 @@ corpus = Corpus(
     }
 )
 
-# Step 1: Filter documents (quality control)
-corpus.filter()
+# Step 1: Extract documents (quality control)
+corpus.extract()
 
 # Step 2: Extract sections from filtered documents
 corpus.section()
 
@@ -1,4 +1,3 @@
-LICENSE.md
 MANIFEST.in
 README.md
 pyproject.toml
Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,3 @@`
`1`		`-LICENSE.md`
`2`	`1`	`MANIFEST.in`
`3`	`2`	`README.md`
`4`	`3`	`pyproject.toml`