perf(treesitter): smarter languagetree invalidation

Problem:
  Treesitter injections are slow because all injected trees are invalidated on every change.

Solution:
    Implement smarter invalidation to avoid reparsing injected regions.

    - In on_bytes, try and update self._regions as best we can. This PR just offsets any regions after the change.
    - Add valid flags for each region in self._regions.
    - Call on_bytes recursively for all children.
       - We still need to run the query every time for the top level tree. I don't know how to avoid this. However, if the new injection ranges don't change, then we re-use the old trees and avoid reparsing children.

This should result in roughly a 2-3x reduction in tree parsing when the comment injections are enabled.

1 files changed, 35 insertions, 0 deletions

diff --git a/test/functional/treesitter/parser_spec.lua b/test/functional/treesitter/parser_spec.lua
index 2430021617..fdd6403859 100644
--- a/test/functional/treesitter/parser_spec.lua
+++ b/test/functional/treesitter/parser_spec.lua
@@ -639,6 +639,17 @@ int x = INT_MAX;
           {1, 26, 1, 65}, -- READ_STRING(x, y) (char_u *)read_string((x), (size_t)(y))
           {2, 29, 2, 68}  -- READ_STRING_OK(x, y) (char_u *)read_string((x), (size_t)(y))
         }, get_ranges())
+
+        helpers.feed('ggo<esc>')
+        eq(5, exec_lua("return #parser:children().c:trees()"))
+        eq({
+          {0, 0, 8, 0},   -- root tree
+          {4, 14, 4, 17}, -- VALUE 123
+          {5, 15, 5, 18}, -- VALUE1 123
+          {6, 15, 6, 18}, -- VALUE2 123
+          {2, 26, 2, 65}, -- READ_STRING(x, y) (char_u *)read_string((x), (size_t)(y))
+          {3, 29, 3, 68}  -- READ_STRING_OK(x, y) (char_u *)read_string((x), (size_t)(y))
+        }, get_ranges())
       end)
     end)
 
@@ -660,6 +671,18 @@ int x = INT_MAX;
           {1, 26, 2, 68}  -- READ_STRING(x, y) (char_u *)read_string((x), (size_t)(y))
                           -- READ_STRING_OK(x, y) (char_u *)read_string((x), (size_t)(y))
         }, get_ranges())
+
+        helpers.feed('ggo<esc>')
+        eq("table", exec_lua("return type(parser:children().c)"))
+        eq(2, exec_lua("return #parser:children().c:trees()"))
+        eq({
+          {0, 0, 8, 0},   -- root tree
+          {4, 14, 6, 18}, -- VALUE 123
+                          -- VALUE1 123
+                          -- VALUE2 123
+          {2, 26, 3, 68}  -- READ_STRING(x, y) (char_u *)read_string((x), (size_t)(y))
+                          -- READ_STRING_OK(x, y) (char_u *)read_string((x), (size_t)(y))
+        }, get_ranges())
       end)
     end)
 
@@ -688,6 +711,18 @@ int x = INT_MAX;
           {1, 26, 2, 68}  -- READ_STRING(x, y) (char_u *)read_string((x), (size_t)(y))
                           -- READ_STRING_OK(x, y) (char_u *)read_string((x), (size_t)(y))
         }, get_ranges())
+
+        helpers.feed('ggo<esc>')
+        eq("table", exec_lua("return type(parser:children().c)"))
+        eq(2, exec_lua("return #parser:children().c:trees()"))
+        eq({
+          {0, 0, 8, 0},   -- root tree
+          {4, 14, 6, 18}, -- VALUE 123
+                          -- VALUE1 123
+                          -- VALUE2 123
+          {2, 26, 3, 68}  -- READ_STRING(x, y) (char_u *)read_string((x), (size_t)(y))
+                          -- READ_STRING_OK(x, y) (char_u *)read_string((x), (size_t)(y))
+        }, get_ranges())
       end)
 
       it("should not inject bad languages", function()