rework elsa file parser, add function to add dicts

src/logic/wordparser.py

@@ -1,5 +1,6 @@
 import pandas as pd
 from docx import Document
+import re
 letters = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
 
 def word_docx_to_csv(path) -> pd.DataFrame:
@@ -24,12 +25,72 @@ def word_docx_to_csv(path) -> pd.DataFrame:
 
     df = m_data[2]
     return df
+def makeDict():
+    return {
+        "work_author": None,
+        "section_author": None,
+        "year": None,
+        "edition": None,
+        "work_title": None,
+        "chapter_title": None,
+        "location": None,
+        "publisher": None,
+        "signature": None,
+        "issue": None,
+        "pages": None,
+        "isbn": None,
+        "type": None,
+    }
 
+def tuple_to_dict(tlist: tuple, type: str) -> dict:
+    ret = []
+    for line in tlist:
+        data = makeDict()
+        if type == "Monographie":
+            data["type"] = type
+            data["work_author"] = line[0]
+            data["year"] = line[1]
+            data["edition"] = line[2]
+            data["work_title"] = line[3]
+            data["location"] = line[4]
+            data["publisher"] = line[5]
+            data["signature"] = line[6]
+            data["pages"] = line[7]
+        elif type == "Herausgeberwerke":
+            data["type"] = type
+            data["section_author"] = line[0]
+            data["year"] = line[1]
+            data["edition"] = line[2]
+            data["chapter_title"] = line[3]
+            data["work_author"] = line[4]
+            data["work_title"] = line[5]
+            data["location"] = line[6]
+            data["publisher"] = line[7]
+            data["signature"] = line[9]
+            data["pages"] = line[8]
+        elif type == "Zeitschriftenaufsätze":
+            data["type"] = type
+            data["section_author"] = line[0]
+            data["year"] = line[1]
+            data["issue"] = line[2]
+            data["chapter_title"] = line[3]
+            data["work_title"] = line[4]
+            data["location"] = line[5]
+            data["publisher"] = line[6]
+            data["signature"] = line[8]
+            data["pages"] = line[7]
+        ret.append(data)
+    return ret
 
-def elsa_word_to_csv(path) -> list[tuple]:
+def elsa_word_to_csv(path):
     doc = Document(path)
     # print all lines in doc
     doctype = [para.text for para in doc.paragraphs if para.text != ""][-1]
+    tuples = {
+        "Monographie": ("", "", "", "", "", "", "", "", ""),
+        "Herausgeberwerke": ("", "", "", "", "", "", "", "", "", "", ""),
+        "Zeitschriftenaufsätze": ("", "", "", "", "", "", "", "", "", ""),
+    }
     tables = doc.tables
 
     m_data = []
@@ -50,16 +111,12 @@ def elsa_word_to_csv(path) -> list[tuple]:
     df = m_data[0]
     # split df to rows
     data = [
-        row
+        row for row in df.itertuples(index=False, name=None) if row != tuples[doctype]
-        for row in df.itertuples(index=False, name=None)
-        if row != ("", "", "", "", "", "", "", "", "")
     ]
-
+    print(data)
-    return data, doctype
+    return tuple_to_dict(data, doctype), doctype
 
 
 if __name__ == "__main__":
-    else_df = elsa_word_to_csv(
+    else_df = elsa_word_to_csv("c:/Users/aky547/Desktop/hrsgw_test.docx")
-        "c:/Users/aky547/Desktop/semap/formularsemhrsg2023_Bestellung Sahrai_Hurrelmann et al.Referenzwerk Prävention.docx"
-    )
     print(else_df)