Update app.py

app.py

@@ -4,6 +4,7 @@ import pandas as pd
 from io import StringIO
 import folium
 from streamlit_folium import st_folium
+import unicodedata
 
 # -------------------------------
 # Authority Lists as XML Strings
@@ -449,8 +450,52 @@ with tabs[1]:
 # -------------------------------
 # Diplomatic Edition Tab
 # -------------------------------
-import streamlit as st
-import xml.etree.ElementTree as ET
+
+# Function to remove diacritics from text
+def remove_diacritics(text):
+    """
+    Removes diacritics from the input text.
+    """
+    normalized_text = unicodedata.normalize('NFD', text)
+    return ''.join(
+        char for char in normalized_text
+        if unicodedata.category(char) != 'Mn'
+    )
+
+# Function to process the Text element
+def render_diplomatic(text_elem):
+    """
+    Transforms the XML Text element into uppercase Greek text without diacritics and spaces,
+    with line breaks at <lb> tags.
+    """
+    lines = []
+    current_line = []
+
+    for elem in text_elem.iter():
+        if elem.tag == 'lb':
+            # Finalize the current line
+            line_text = ''.join(current_line).strip()
+            if line_text:
+                # Remove diacritics and spaces, then convert to uppercase
+                line_text = remove_diacritics(line_text).replace(' ', '').upper()
+                lines.append(line_text)
+            current_line = []
+        elif elem.text:
+            # Append text, handling any nested tags
+            current_line.append(elem.text)
+        if elem.tail:
+            # Append tail text after a nested tag
+            current_line.append(elem.tail)
+
+    # Add the last line if exists
+    if current_line:
+        line_text = ''.join(current_line).strip()
+        if line_text:
+            line_text = remove_diacritics(line_text).replace(' ', '').upper()
+            lines.append(line_text)
+
+    # Join all lines with newline characters
+    return '\n'.join(lines)
 
 # Assuming 'tabs' and 'df' are already defined in your Streamlit app
 with tabs[2]:
@@ -467,42 +512,13 @@ with tabs[2]:
     inscription_elem = root.find(f".//inscription[@n='{selected_inscription_num}']")
     text_element = inscription_elem.find("Text") if inscription_elem is not None else None
 
-    def render_diplomatic(text_elem):
-        """
-        Transforms the XML Text element into uppercase Greek text with line breaks at <lb> tags.
-        """
-        lines = []
-        current_line = []
-
-        for elem in text_elem.iter():
-            if elem.tag == 'lb':
-                # When encountering an <lb> tag, finalize the current line
-                line_text = ''.join(current_line).strip().upper()
-                if line_text:
-                    lines.append(line_text)
-                current_line = []
-            elif elem.text:
-                # Append text, handling any nested tags
-                current_line.append(elem.text)
-            if elem.tail:
-                # Append tail text after a nested tag
-                current_line.append(elem.tail)
-
-        # Add the last line if exists
-        if current_line:
-            line_text = ''.join(current_line).strip().upper()
-            if line_text:
-                lines.append(line_text)
-
-        # Join all lines with newline characters
-        return '\n'.join(lines)
-
     if text_element is not None:
         diplomatic_text = render_diplomatic(text_element)
         st.code(diplomatic_text, language="plaintext")
     else:
         st.warning("No text found for the selected inscription.")
 
+
 # -------------------------------
 # Editor Edition Tab
 # -------------------------------