ignore numbers in braces in indexing

CHANGELOG.md

@@ -1,5 +1,10 @@
 # Changelog
 
+- 2024/03/29
+
+  - ignore numbers in braces in `make4ht-indexing` library.
+    https://tex.stackexchange.com/q/714247/2891
+
 - 2024/02/22
 
   - version `0.4` released

make4ht-indexing.lua

@@ -99,7 +99,9 @@ local fix_idx_pages = function(content, idxobj)
       -- there is a problem when index term itself contains numbers, like Bible verses (1:2),
       -- because they will be detected as page numbers too. I cannot find a good solution 
       -- that wouldn't break something else.
-      return start .. rest:gsub("(%d+)", function(page)
+      -- There can be also commands with numbers in braces. These numbers in braces will be ignored, 
+      -- as they may be not page numbers
+      return start .. rest:gsub("(%{?%d+%}?)", function(page)
         local entry = entries[tonumber(page)]
         if entry then
           -- construct link to the index entry

make4ht-odtfilter.lua

@@ -0,0 +1,33 @@
+local mkutils = require "mkutils"
+local zip = require "zip"
+
+
+-- use function to change contents of the ODT file
+local function update_odt(odtfilename, file_path, fn)
+  -- get name of the odt file
+  local odtname = mkutils.remove_extension(odtfilename) .. ".odt"
+  -- open and read contents of the requested file inside ODT file
+  local odtfile = zip.open(odtname)
+  local local_file = odtfile:open(file_path)
+  local content = local_file:read("*all")
+  local_file:close()
+  odtfile:close()
+  -- update the content using user function
+  content = fn(content)
+  -- write the updated file
+  local local_file_file  = io.open(file_path,"w")
+  local_file_file:write(content)
+  local_file_file:close()
+  os.execute("zip " .. odtname .. " " .. file_path)
+  os.remove(file_path)
+end
+
+Make:match("tmp$", function(name, par)
+  update_odt(name, "content.xml", function(content)
+    return content:gsub("%&%#x([A-Fa-f0-9]+);", function(entity)
+      -- convert hexadecimal entity to Unicode
+      print(entity,utfchar(tonumber(entity, 16)))
+      return utfchar(tonumber(entity, 16))
+    end)
+  end)
+end)