fix(treesitter): correctly handle query quantifiers (#24738)

Query patterns can contain quantifiers (e.g. (foo)+ @bar), so a single
capture can map to multiple nodes. The iter_matches API can not handle
this situation because the match table incorrectly maps capture indices
to a single node instead of to an array of nodes.

The match table should be updated to map capture indices to an array of
nodes. However, this is a massively breaking change, so must be done
with a proper deprecation period.

`iter_matches`, `add_predicate` and `add_directive` must opt-in to the
correct behavior for backward compatibility. This is done with a new
"all" option. This option will become the default and removed after the
0.10 release.

Co-authored-by: Christian Clason <c.clason@uni-graz.at>
Co-authored-by: MDeiml <matthias@deiml.net>
Co-authored-by: Gregory Anders <greg@gpanders.com>

1 files changed, 18 insertions, 10 deletions

diff --git a/runtime/lua/vim/treesitter/languagetree.lua b/runtime/lua/vim/treesitter/languagetree.lua
index 971c4449e8..79566f5eeb 100644
--- a/runtime/lua/vim/treesitter/languagetree.lua
+++ b/runtime/lua/vim/treesitter/languagetree.lua
@@ -784,7 +784,7 @@ end
 ---@private
 --- Extract injections according to:
 --- https://tree-sitter.github.io/tree-sitter/syntax-highlighting#language-injection
----@param match table<integer,TSNode>
+---@param match table<integer,TSNode[]>
 ---@param metadata TSMetadata
 ---@return string?, boolean, Range6[]
 function LanguageTree:_get_injection(match, metadata)
@@ -796,14 +796,16 @@ function LanguageTree:_get_injection(match, metadata)
     or (injection_lang and resolve_lang(injection_lang))
   local include_children = metadata['injection.include-children'] ~= nil
 
-  for id, node in pairs(match) do
-    local name = self._injection_query.captures[id]
-    -- Lang should override any other language tag
-    if name == 'injection.language' then
-      local text = vim.treesitter.get_node_text(node, self._source, { metadata = metadata[id] })
-      lang = resolve_lang(text)
-    elseif name == 'injection.content' then
-      ranges = get_node_ranges(node, self._source, metadata[id], include_children)
+  for id, nodes in pairs(match) do
+    for _, node in ipairs(nodes) do
+      local name = self._injection_query.captures[id]
+      -- Lang should override any other language tag
+      if name == 'injection.language' then
+        local text = vim.treesitter.get_node_text(node, self._source, { metadata = metadata[id] })
+        lang = resolve_lang(text)
+      elseif name == 'injection.content' then
+        ranges = get_node_ranges(node, self._source, metadata[id], include_children)
+      end
     end
   end
 
@@ -844,7 +846,13 @@ function LanguageTree:_get_injections()
     local start_line, _, end_line, _ = root_node:range()
 
     for pattern, match, metadata in
-      self._injection_query:iter_matches(root_node, self._source, start_line, end_line + 1)
+      self._injection_query:iter_matches(
+        root_node,
+        self._source,
+        start_line,
+        end_line + 1,
+        { all = true }
+      )
     do
       local lang, combined, ranges = self:_get_injection(match, metadata)
       if lang then