add logger

src/logic/wordparser.py

@@ -1,6 +1,22 @@
 import pandas as pd
 from docx import Document
 from dataclasses import dataclass
+import sys
+from loguru import logger as log
+
+logger = log
+logger.remove()
+logger.add("logs/wordparser.log", rotation="1 week", enqueue=True)
+log.add(
+    f"logs/application.log",
+    rotation="1 day",
+    compression="zip",
+    enqueue=True,
+)
+
+# logger.add(sys.stderr, format="{time} {level} {message}", level="INFO")
+logger.add(sys.stdout)
+
 
 letters = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
 
@@ -85,10 +101,6 @@ class SemapDocument:
 def word_docx_to_csv(path: str) -> list[pd.DataFrame]:
     doc = Document(path)
     tables = doc.tables
-    print("Tables: ", len(tables))
-
-    # print content of all tables
-
     m_data = []
     for table in tables:
         data = []
@@ -205,13 +217,13 @@ def elsa_word_to_csv(path):
 
 
 def word_to_semap(word_path: str) -> SemapDocument:
+    logger.info("Parsing Word Document {}", word_path)
     semap = SemapDocument()
     df = word_docx_to_csv(word_path)
     apparatdata = df[0]
     apparatdata = apparatdata.to_dict()
     keys = list(apparatdata.keys())
     appdata = {keys[i]: keys[i + 1] for i in range(0, len(keys), 2)}
-    print(appdata.keys())
     semap.phoneNumber = appdata["Telefon:"]
     semap.subject = appdata["Ihr Fach:"]
     semap.mail = appdata["Mailadresse:"]
@@ -236,7 +248,7 @@ def word_to_semap(word_path: str) -> SemapDocument:
             continue
         else:
             booklist.append(book)
-
+    logger.info("Found {} books", len(booklist))
     semap.books = booklist
 
     return semap
@@ -246,4 +258,3 @@ if __name__ == "__main__":
     else_df = word_to_semap(
         "C:/Users/aky547/Desktop/SA 80 titelmeldung_SoSe2025 Burth.docx"
     )
-    print(else_df)