From 9b8e0621fe89ef8f0a730d9095ea2730a0eb9413 Mon Sep 17 00:00:00 2001
From: WorldTeacher <41587052+WorldTeacher@users.noreply.github.com>
Date: Wed, 26 Jun 2024 16:34:26 +0200
Subject: [PATCH] add valid letters to detect paragraphs

---
 src/logic/wordparser.py | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/src/logic/wordparser.py b/src/logic/wordparser.py
index 6f3131c..99fba0c 100644
--- a/src/logic/wordparser.py
+++ b/src/logic/wordparser.py
@@ -1,6 +1,6 @@
 import pandas as pd
 from docx import Document
-
+letters = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
 
 def word_docx_to_csv(path) -> pd.DataFrame:
     doc = Document(path)
@@ -28,6 +28,8 @@ def word_docx_to_csv(path) -> pd.DataFrame:
 
 def elsa_word_to_csv(path) -> list[tuple]:
     doc = Document(path)
+    # print all lines in doc
+    doctype = [para.text for para in doc.paragraphs if para.text != ""][-1]
     tables = doc.tables
 
     m_data = []
@@ -53,4 +55,11 @@ def elsa_word_to_csv(path) -> list[tuple]:
         if row != ("", "", "", "", "", "", "", "", "")
     ]
 
-    return data
+    return data, doctype
+
+
+if __name__ == "__main__":
+    else_df = elsa_word_to_csv(
+        "c:/Users/aky547/Desktop/semap/formularsemhrsg2023_Bestellung Sahrai_Hurrelmann et al.Referenzwerk Prävention.docx"
+    )
+    print(else_df)
\ No newline at end of file