From b1d523f574817f792a0c0099146afb0319e676a7 Mon Sep 17 00:00:00 2001
From: WorldTeacher <coding_contact@pm.me>
Date: Mon, 26 May 2025 13:22:47 +0200
Subject: [PATCH] update wordparser

---
 src/logic/wordparser.py | 39 +++++++++++++++++++++++++++++++++------
 1 file changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/logic/wordparser.py b/src/logic/wordparser.py
index c0ad35a..77391a1 100644
--- a/src/logic/wordparser.py
+++ b/src/logic/wordparser.py
@@ -3,13 +3,14 @@ from docx import Document
 from dataclasses import dataclass
 from src.backend import Semester
 from typing import Union, Any
+from src.logic.openai import name_tester, run_shortener, semester_converter
 
 import loguru
 import sys
 
 log = loguru.logger
 log.remove()
-log.add(sys.stdout)
+log.add(sys.stdout, level="INFO")
 log.add("logs/application.log", rotation="1 MB", retention="10 days")
 
 
@@ -75,12 +76,37 @@ class SemapDocument:
     phoneNumber: int = None
     mail: str = None
     title: str = None
+    title_suggestions: list[str] = None
     semester: Union[str, Semester] = None
     books: list[Book] = None
     eternal: bool = False
     personName: str = None
     personTitle: str = None
+    title_length = 0
+    title_max_length = 0
 
+    def __post_init__(self):
+        self.title_suggestions = []
+
+    @property
+    def nameSetter(self):
+        data = name_tester(self.personTitle)
+        name = f"{data['last_name']}, {data['first_name']}"
+        if data["title"] is not None:
+            title = data["title"]
+            self.personTitle = title
+        self.personName = name
+        self.title_length = len(self.title) + 3 + len(self.personName.split(",")[0])
+        if self.title_length > 40:
+            log.warning("Title is too long")
+            name_len = len(self.personName.split(",")[0])
+            self.title_max_length = 38 - name_len
+            suggestions = run_shortener(self.title, self.title_max_length)
+            for suggestion in suggestions:
+                self.title_suggestions.append(suggestion["shortened_string"])
+        else:
+            self.title_suggestions = []
+        pass
     @property
     def renameSemester(self) -> None:
         if ", Dauer" in self.semester:
@@ -88,8 +114,8 @@ class SemapDocument:
             self.eternal = True
             self.semester = Semester().from_string(self.semester)
         else:
-            logger.warning("Semester {} is not valid", self.semester)
-            self.semester = None
+            log.warning("Semester {} is not valid", self.semester)
+            self.semester = Semester().from_string(semester_converter(self.semester))
 
     @property
     def signatures(self) -> list[str]:
@@ -105,7 +131,7 @@ def word_docx_to_csv(path: str) -> list[pd.DataFrame]:
     for table in tables:
         data = []
         for row in table.rows:
-            row_data = []
+            row_data: list[Any] = []
             for cell in row.cells:
                 text = cell.text
                 text = text.replace("\n", "")
@@ -117,7 +143,6 @@ def word_docx_to_csv(path: str) -> list[pd.DataFrame]:
 
         m_data.append(df)
 
-    # for df[0, 1]: merge i and i+1 as key, value
 
     return m_data
 
@@ -220,6 +245,7 @@ def word_to_semap(word_path: str) -> SemapDocument:
     log.info("Parsing Word Document {}", word_path)
     semap = SemapDocument()
     df = word_docx_to_csv(word_path)
+    print(df)
     apparatdata = df[0]
     apparatdata = apparatdata.to_dict()
 
@@ -238,6 +264,8 @@ def word_to_semap(word_path: str) -> SemapDocument:
     semap.title = appdata["Veranstaltung:"]
     semap.semester = appdata["Semester:"]
     semap.renameSemester
+    semap.nameSetter
+
     books = df[2]
     booklist = []
     for i in range(len(books)):
@@ -254,7 +282,6 @@ def word_to_semap(word_path: str) -> SemapDocument:
             booklist.append(book)
     log.info("Found {} books", len(booklist))
     semap.books = booklist
-
     return semap