add elsa word parser

src/logic/wordparser.py

@@ -24,3 +24,33 @@ def word_docx_to_csv(path) -> pd.DataFrame:
 
     df = m_data[2]
     return df
+
+
+def elsa_word_to_csv(path) -> list[tuple]:
+    doc = Document(path)
+    tables = doc.tables
+
+    m_data = []
+    for table in tables:
+        data = []
+        for row in table.rows:
+            row_data = []
+            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.columns = df.iloc[0]
+        df = df.iloc[1:]
+        m_data.append(df)
+    df = m_data[0]
+    # split df to rows
+    data = [
+        row
+        for row in df.itertuples(index=False, name=None)
+        if row != ("", "", "", "", "", "", "", "", "")
+    ]
+
+    return data