update logging, update docuprint add new ui for generating documents

src/logic/webrequest.py

@@ -4,10 +4,11 @@ from bs4 import BeautifulSoup
 
 # import sleep_and_retry decorator to retry requests
 from ratelimit import limits, sleep_and_retry
-from typing import Union, Any
+from typing import Union, Any, Literal, Optional
 from src.logic.dataclass import BookData
 
 from src.transformers import ARRAYData, BibTeXData, COinSData, RDSData, RISData
+from src.transformers.transformers import RDS_AVAIL_DATA, RDS_GENERIC_DATA
 import sys
 from loguru import logger as log
 
@@ -105,6 +106,7 @@ class WebRequest:
     def get_data(self) -> Union[list[str], None]:
         links = self.get_book_links(self.ppn)
         logger.debug(f"Links: {links}")
+        return_data: list[str] = []
         for link in links:
             result: str = self.search(link)  # type:ignore
             # in result search for class col-xs-12 rds-dl RDS_LOCATION
@@ -116,9 +118,9 @@ class WebRequest:
                     item_location = location.find(
                         "div", class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel"
                     ).text.strip()
+                    logger.debug(f"Item location: {item_location}")
                     if self.use_any:
                         pre_tag = soup.find_all("pre")
-                        return_data: list[str] = []
                         if pre_tag:
                             for tag in pre_tag:
                                 data = tag.text.strip()
@@ -142,9 +144,9 @@ class WebRequest:
                         logger.error(
                             f"Signature {self.signature} not found in {item_location}"
                         )
-                        return_data = []
+                        # return_data = []
 
-                        return return_data
+        return return_data
 
     def get_data_elsa(self):
         links = self.get_book_links(self.ppn)
@@ -225,7 +227,15 @@ class BibTextTransformer:
                     self.data = line
         return self
 
-    def return_data(self, option: Any = None) -> Union[BookData, None]:
+    def return_data(
+        self, option: Any = None
+    ) -> Union[
+        Optional[BookData],
+        Optional[RDS_GENERIC_DATA],
+        Optional[RDS_AVAIL_DATA],
+        None,
+        dict[str, Union[RDS_AVAIL_DATA, RDS_GENERIC_DATA]],
+    ]:
         """Return Data to caller.
 
         Args:

src/logic/wordparser.py

@@ -3,6 +3,8 @@ from docx import Document
 from dataclasses import dataclass
 import sys
 from loguru import logger as log
+from src.backend import Semester
+from typing import Union, Any
 
 logger = log
 logger.remove()
@@ -51,8 +53,9 @@ class Book:
             ]
         )
 
-    def from_dict(self, data: dict):
+    def from_dict(self, data: dict[str, Any]):
         for key, value in data.items():
+            value = value.strip()
             if value == "\u2002\u2002\u2002\u2002\u2002":
                 value = ""
 
@@ -78,18 +81,21 @@ class SemapDocument:
     phoneNumber: int = None
     mail: str = None
     title: str = None
-    semester: str = None
+    semester: Union[str, Semester] = None
     books: list[Book] = None
+    eternal: bool = False
+    personName: str = None
+    personTitle: str = None
 
     @property
     def renameSemester(self) -> None:
-        if self.semester is not None:
-            if "sommersemester" in self.semester.lower():
-                year = self.semester.split(" ")[-1]
-                self.semester = f"SoSe {year}"
-            elif "wintersemester" in self.semester.lower():
-                year = self.semester.split(" ")[-1]
-                self.semester = f"WiSe {year}"
+        if ", Dauer" in self.semester:
+            self.semester = self.semester.split(",")[0]
+            self.eternal = True
+            self.semester = Semester().from_string(self.semester)
+        else:
+            logger.warning("Semester {} is not valid", self.semester)
+            self.semester = None
 
     @property
     def signatures(self) -> list[str]:
@@ -181,7 +187,7 @@ def tuple_to_dict(tlist: tuple, type: str) -> dict:
     return ret
 
 
-def elsa_word_to_csv(path):
+def elsa_word_to_csv(path: str):
     doc = Document(path)
     # # print all lines in doc
     doctype = [para.text for para in doc.paragraphs if para.text != ""][-1]
@@ -192,18 +198,18 @@ def elsa_word_to_csv(path):
     }
     tables = doc.tables
 
-    m_data = []
+    m_data: list[pd.DataFrame] = []
     for table in tables:
-        data = []
+        data: list[list[str]] = []
         for row in table.rows:
-            row_data = []
+            row_data: list[str] = []
             for cell in row.cells:
                 text = cell.text
                 text = text.replace("\n", "")
                 text = text.replace("\u2002", "")
                 row_data.append(text)
             data.append(row_data)
-            df = pd.DataFrame(data)
+        df = pd.DataFrame(data)
         df.columns = df.iloc[0]
         df = df.iloc[1:]
         m_data.append(df)
@@ -222,11 +228,15 @@ def word_to_semap(word_path: str) -> 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)}
     semap.phoneNumber = appdata["Telefon:"]
     semap.subject = appdata["Ihr Fach:"]
     semap.mail = appdata["Mailadresse:"]
+    semap.personName = ",".join(appdata["Ihr Name und Titel:"].split(",")[:-1])
+    semap.personTitle = ",".join(appdata["Ihr Name und Titel:"].split(",")[-1:]).strip()
     apparatdata = df[1]
     apparatdata = apparatdata.to_dict()
     keys = list(apparatdata.keys())
@@ -255,6 +265,7 @@ def word_to_semap(word_path: str) -> SemapDocument:
 
 
 if __name__ == "__main__":
-    else_df = word_to_semap(
-        "C:/Users/aky547/Desktop/SA 80 titelmeldung_SoSe2025 Burth.docx"
+    else_df = elsa_word_to_csv(
+        "C:/Users/aky547/Desktop/ELSA_Bestellung Scann Der Westen und der Rest.docx"
     )
+    print(else_df)