src/logic/wordparser.py

@@ -9,7 +9,7 @@ from bs4 import BeautifulSoup
 from docx import Document
 
 from src import LOG_DIR
-from src.backend import Semester
+from src.backend.semester import Semester
 from src.logic.openai import name_tester, run_shortener, semester_converter
 
 log = loguru.logger
@@ -18,7 +18,6 @@ log.add(sys.stdout, level="INFO")
 log.add(f"{LOG_DIR}/application.log", rotation="1 MB", retention="10 days")
 
 
-
 letters = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
 
 
@@ -111,6 +110,7 @@ class SemapDocument:
         else:
             self.title_suggestions = []
         pass
+
     @property
     def renameSemester(self) -> None:
         if ", Dauer" in self.semester:
@@ -141,8 +141,8 @@ def word_docx_to_csv(path: str) -> list[pd.DataFrame]:
 
                 text = text.replace("\n", "")
                 row_data.append(text)
-                if text == "Ihr Fach:":
-                    row_data.append(get_fach(path))
+                # if text == "Ihr Fach:":
+                #     row_data.append(get_fach(path))
             data.append(row_data)
         df = pd.DataFrame(data)
         df.columns = df.iloc[0]
@@ -265,7 +265,7 @@ def elsa_word_to_csv(path: str):
     return tuple_to_dict(data, doctype), doctype
 
 
-def word_to_semap(word_path: str) -> SemapDocument:
+def word_to_semap(word_path: str, ai: bool = True) -> SemapDocument:
     log.info("Parsing Word Document {}", word_path)
     semap = SemapDocument()
     df = word_docx_to_csv(word_path)
@@ -286,8 +286,9 @@ def word_to_semap(word_path: str) -> SemapDocument:
     appdata = {keys[i]: keys[i + 1] for i in range(0, len(keys), 2)}
     semap.title = appdata["Veranstaltung:"]
     semap.semester = appdata["Semester:"]
-    semap.renameSemester
-    semap.nameSetter
+    if ai:
+        semap.renameSemester
+        semap.nameSetter
 
     books = df[2]
     booklist = []
@@ -309,7 +310,5 @@ def word_to_semap(word_path: str) -> SemapDocument:
 
 
 if __name__ == "__main__":
-    else_df = elsa_word_to_csv(
-        "C:/Users/aky547/Desktop/ELSA_Bestellung Scann Der Westen und der Rest.docx"
-    )
+    else_df = word_to_semap("C:/Users/aky547/Desktop/semap/db/temp/tmpzsz_hgdr.docx")
     print(else_df)