chore(codebase): import fixes, restructuring

src/parsers/csv_parser.py

@@ -1,23 +1,27 @@
 import csv
+from pathlib import Path
 
 from charset_normalizer import detect
 
+from src.core.models import Book, SemapDocument
 
-def csv_to_list(path: str) -> list[str]:
-    """
-    Extracts the data from a csv file and returns it as a pandas dataframe
-    """
+
+def csv_to_list(path: str) -> SemapDocument:
+    """Extract the data from a csv file and return it as a minimal SemapDocument."""
     encoding = detect(open(path, "rb").read())["encoding"]
-    with open(path, newline="", encoding=encoding) as csvfile:
+    with Path(path).open(newline="", encoding=encoding) as csvfile:
         # if decoder fails to map, assign ""
         reader = csv.reader(csvfile, delimiter=";", quotechar="|")
         ret = []
         for row in reader:
             ret.append(row[0].replace('"', ""))
-        return ret
+
+        books = [Book(signature=row) for row in ret]
+
+        return SemapDocument(books=books)
 
 
 if __name__ == "__main__":
-    text = csv_to_list("C:/Users/aky547/Desktop/semap/71.csv")
+    text = csv_to_list("C:/Users/aky547/Desktop/semap/sap71.csv")
     # remove linebreaks
-    # #print(text)
+    print(text)