update

data_structure/add_id.py

@@ -0,0 +1,49 @@
+import json
+import uuid
+import re
+
+# Load the original JSON file
+with open("structure.json", "r", encoding="utf-8") as file:
+    data = json.load(file)
+
+# Create the new structure
+new_structure = {"byId": {}, "allIds": []}
+
+
+# Function to fix punctuation in titles
+def fix_title_punctuation(title):
+    # Fix spaces around semicolons (ensure there's a space after each semicolon and no space before)
+    fixed_title = re.sub(r"\s*;\s*", "; ", title)
+
+    # Fix spaces around hyphens (ensure there's a space after but not before)
+    fixed_title = re.sub(r"(\w)-\s+", r"\1- ", fixed_title)
+
+    return fixed_title
+
+
+# Process each item in the original array
+for i, item in enumerate(data):
+    # Generate a new UUID
+    new_id = str(uuid.uuid4())
+
+    # Store the original item with the new ID
+    new_item = item.copy()
+    new_item["id"] = new_id
+    new_item["index"] = i
+    new_item["isFirst"] = i == 0
+    new_item["isLast"] = i == len(data) - 1
+    new_item["files"] = [f.replace("pdf", "html") for f in new_item["files"]]
+
+    # Fix the title punctuation
+    if "title" in new_item:
+        new_item["title"] = fix_title_punctuation(new_item["title"])
+
+    # Add to the new structure
+    new_structure["byId"][new_id] = new_item
+    new_structure["allIds"].append(new_id)
+
+# Save the new structure to topics.json
+with open("topics.json", "w", encoding="utf-8") as file:
+    json.dump(new_structure, file, ensure_ascii=False, indent=4)
+
+print("topics.json created successfully with fixed punctuation")