Remove unsupported characters from Azure Search section id (Azure-Sam…

…ples#39)
dusan2-gh · Mar 22, 2023 · e201432 · e201432
1 parent ffc416c
commit e201432
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/scripts/prepdocs.py b/scripts/prepdocs.py
@@ -134,7 +134,7 @@ def find_page(offset):
 def create_sections(filename, pages):
     for i, (section, pagenum) in enumerate(split_text(pages)):
         yield {
-            "id": f"{filename}-{i}".replace(".", "_").replace(" ", "_"),
+            "id": re.sub("[^0-9a-zA-Z_-]","_",f"{filename}-{i}"),
             "content": section,
             "category": args.category,
             "sourcepage": blob_name_from_file_page(filename, pagenum),