fix: improve error recovery

grammar.js

@@ -64,6 +64,8 @@ module.exports = grammar({
 
     $._bl,
     $.comment,
+
+    $._err_rec,
   ],
 
   extras: $ => [$.comment],

src/grammar.json

@@ -6950,6 +6950,10 @@
     {
       "type": "SYMBOL",
       "name": "comment"
+    },
+    {
+      "type": "SYMBOL",
+      "name": "_err_rec"
     }
   ],
   "inline": [

src/scanner.c

@@ -60,6 +60,8 @@ typedef enum {
 
     BL,
     COMMENT,
+
+    ERR_REC,
 } TokenType;
 
 // clang-format on
@@ -1355,7 +1357,7 @@ static bool scan(Scanner *scanner, TSLexer *lexer, const bool *valid_symbols) {
         return false;
     }
 
-    return false;
+    return !valid_symbols[ERR_REC];
 }
 
 void *tree_sitter_yaml_external_scanner_create() {

src/tree_sitter/parser.h

@@ -86,6 +86,11 @@ typedef union {
   } entry;
 } TSParseActionEntry;
 
+typedef struct {
+  int32_t start;
+  int32_t end;
+} TSCharacterRange;
+
 struct TSLanguage {
   uint32_t version;
   uint32_t symbol_count;
@@ -125,6 +130,24 @@ struct TSLanguage {
   const TSStateId *primary_state_ids;
 };
 
+static inline bool set_contains(TSCharacterRange *ranges, uint32_t len, int32_t lookahead) {
+  uint32_t index = 0;
+  uint32_t size = len - index;
+  while (size > 1) {
+    uint32_t half_size = size / 2;
+    uint32_t mid_index = index + half_size;
+    TSCharacterRange *range = &ranges[mid_index];
+    if (lookahead >= range->start && lookahead <= range->end) {
+      return true;
+    } else if (lookahead > range->end) {
+      index = mid_index;
+    }
+    size -= half_size;
+  }
+  TSCharacterRange *range = &ranges[index];
+  return (lookahead >= range->start && lookahead <= range->end);
+}
+
 /*
  *  Lexer Macros
  */
@@ -138,9 +161,8 @@ struct TSLanguage {
 #define START_LEXER()           \
   bool result = false;          \
   bool skip = false;            \
-  UNUSED                        \
+  UNUSED bool eof = false;      \
-  bool eof = false;             \
+  UNUSED int32_t lookahead;     \
-  int32_t lookahead;            \
   goto start;                   \
   next_state:                   \
   lexer->advance(lexer, skip);  \
@@ -154,6 +176,17 @@ struct TSLanguage {
     goto next_state;         \
   }
 
+#define ADVANCE_MAP(...)                                              \
+  {                                                                   \
+    static const uint16_t map[] = { __VA_ARGS__ };                    \
+    for (uint32_t i = 0; i < sizeof(map) / sizeof(map[0]); i += 2) {  \
+      if (map[i] == lookahead) {                                      \
+        state = map[i + 1];                                           \
+        goto next_state;                                              \
+      }                                                               \
+    }                                                                 \
+  }
+
 #define SKIP(state_value) \
   {                       \
     skip = true;          \
@@ -203,14 +236,15 @@ struct TSLanguage {
     }                                 \
   }}
 
-#define REDUCE(symbol_val, child_count_val, ...) \
+#define REDUCE(symbol_name, children, precedence, prod_id) \
   {{                                                       \
     .reduce = {                                            \
       .type = TSParseActionTypeReduce,                     \
-      .symbol = symbol_val,                      \
+      .symbol = symbol_name,                               \
-      .child_count = child_count_val,            \
+      .child_count = children,                             \
-      __VA_ARGS__                                \
+      .dynamic_precedence = precedence,                    \
-    },                                           \
+      .production_id = prod_id                             \
+    }                                                      \
   }}
 
 #define RECOVER()                    \