feat: universal AST preprocessor with nvim-treesitter queries

- Replace old per-language query files with unified tag-preprocessor
- Universal preprocessor uses nvim-treesitter highlights.scm for 10 langs
- Resolves ; inherits: directives (ecma, jsx) for JS/TS
- ts-kotlin bundled query for Kotlin compatibility
- Strips unsupported #set! 3-arg predicates for jsx
- archive old community queries

bex/queries/community/kotlin_tags.scm

@@ -1,43 +0,0 @@
-; Classes
-(class_declaration
-  (type_identifier) @name) @definition.class
-
-; Objects
-(object_declaration
-  (type_identifier) @name) @definition.class
-
-; Functions (top-level and member)
-(function_declaration
-  (simple_identifier) @name) @definition.function
-
-; Properties
-(property_declaration
-  (variable_declaration
-    (simple_identifier) @name)) @definition.constant
-
-; Enum entries
-(enum_entry
-  (simple_identifier) @name) @definition.constant
-
-; Type aliases
-(type_alias
-  (type_identifier) @name) @definition.type
-
-; Companion objects (only named ones)
-(companion_object
-  (type_identifier) @name) @definition.class
-
-; Function calls
-(call_expression
-  (simple_identifier) @name) @reference.call
-
-; Method calls via navigation
-(call_expression
-  (navigation_expression
-    (navigation_suffix
-      (simple_identifier) @name))) @reference.call
-
-; Constructor invocations (class references)
-(constructor_invocation
-  (user_type
-    (type_identifier) @name)) @reference.class

bex/queries/community/typescript_highlights.scm

@@ -1,35 +0,0 @@
-; Types
-
-(type_identifier) @type
-(predefined_type) @type.builtin
-
-((identifier) @type
- (#match? @type "^[A-Z]"))
-
-(type_arguments
-  "<" @punctuation.bracket
-  ">" @punctuation.bracket)
-
-; Variables
-
-(required_parameter (identifier) @variable.parameter)
-(optional_parameter (identifier) @variable.parameter)
-
-; Keywords
-
-[ "abstract"
-  "declare"
-  "enum"
-  "export"
-  "implements"
-  "interface"
-  "keyof"
-  "namespace"
-  "private"
-  "protected"
-  "public"
-  "type"
-  "readonly"
-  "override"
-  "satisfies"
-] @keyword

bex/queries/community/typescript_tags.scm

@@ -1,23 +0,0 @@
-(function_signature
-  name: (identifier) @name) @definition.function
-
-(method_signature
-  name: (property_identifier) @name) @definition.method
-
-(abstract_method_signature
-  name: (property_identifier) @name) @definition.method
-
-(abstract_class_declaration
-  name: (type_identifier) @name) @definition.class
-
-(module
-  name: (identifier) @name) @definition.module
-
-(interface_declaration
-  name: (type_identifier) @name) @definition.interface
-
-(type_annotation
-  (type_identifier) @name) @reference.type
-
-(new_expression
-  constructor: (identifier) @name) @reference.class

bex/queries/universal.scm

@@ -1,132 +0,0 @@
-; UNIVERSAL DERVISH QUERY
-;
-; One query to extract behavioral tokens from any TreeSitter-supported language.
-; TreeSitter silently ignores non-existent node types at query time,
-; so we can reference nodes from all languages safely.
-;
-; Captures:
-;   @qualified-call — obj.method() → "obj.method"
-;   @simple-call   — bare method() → "method"
-;   @annotation    — @Annotation   → "@Annotation"
-;   @constructor   — new Type() / Type()  → "Type"
-
-;; === JAVA ===
-
-; obj.method()
-(method_invocation
-  object: (identifier) @object
-  name: (identifier) @method) @qualified-call
-
-; method() (no explicit object)
-(method_invocation
-  name: (identifier) @method
-  !object) @simple-call
-
-; @Annotation
-(annotation
-  name: (identifier) @name) @annotation
-
-; @Annotation (no args)
-(marker_annotation
-  name: (identifier) @name) @annotation
-
-; new Type()
-(object_creation_expression
-  type: (type_identifier) @name) @constructor
-
-;; === KOTLIN ===
-
-; obj.method()
-(navigation_expression
-  (identifier) @object
-  (identifier) @method) @qualified-call
-
-; method() bare call (Kotlin top-level function)
-(call_expression
-  function: (identifier) @method) @simple-call
-
-; @Annotation (simple)
-(annotation
-  (user_type) @name) @annotation
-
-; @Annotation(args)
-(annotation
-  (constructor_invocation
-    (user_type) @name)) @annotation
-
-;; === PYTHON ===
-
-; obj.method()
-(call
-  function: (attribute
-    object: (identifier) @object
-    attribute: (identifier) @method)) @qualified-call
-
-; method() bare call
-(call
-  function: (identifier) @method) @simple-call
-
-; @decorator
-(decorator
-  (identifier) @name) @annotation
-
-; @decorator(args)
-(decorator
-  (attribute
-    attribute: (identifier) @name)) @annotation
-
-;; === GO ===
-
-; obj.method()
-(call_expression
-  function: (selector_expression
-    operand: (identifier) @object
-    field: (field_identifier) @method)) @qualified-call
-
-; method() bare call
-(call_expression
-  function: (identifier) @method) @simple-call
-
-;; === RUST ===
-
-; obj::method()
-(call_expression
-  function: (scoped_identifier
-    path: (identifier) @object
-    name: (identifier) @method)) @qualified-call
-
-; obj.method()
-(call_expression
-  function: (field_expression
-    value: (identifier) @object
-    field: (field_identifier) @method)) @qualified-call
-
-; method() bare call
-(call_expression
-  function: (identifier) @method) @simple-call
-
-;; === TYPE-SCRIPT / JAVASCRIPT ===
-
-; obj.method()
-(call_expression
-  function: (member_expression
-    object: (identifier) @object
-    property: (property_identifier) @method)) @qualified-call
-
-; method() bare call
-(call_expression
-  function: (identifier) @method) @simple-call
-
-; new Type()
-(new_expression
-  constructor: (identifier) @name) @constructor
-
-;; === C / C++ ===
-
-(call_expression
-  function: (field_expression
-    argument: (identifier) @object
-    field: (field_identifier) @method)) @qualified-call
-
-(call_expression
-  function: (identifier) @method) @simple-call

bex/tag-preprocessor/code.py

@@ -0,0 +1,188 @@
+"""Universal tree-sitter tag preprocessor.
+
+Usage:
+    python -m bex.tag-preprocessor.code <file>
+
+Emits an ordered sequence of behavioral tokens using community highlights.scm
+queries from nvim-treesitter. One code path for all languages.
+"""
+
+import importlib
+import os
+import re
+import sys
+from pathlib import Path
+
+from tree_sitter import Language, Parser, Query, QueryCursor
+
+QUERIES_DIR = Path(__file__).parent / "queries"
+
+# (query_name, module_name, func_name)
+EXTENSION_MAP = {
+    ".py": ("python", "tree_sitter_python", "language"),
+    ".js": ("javascript", "tree_sitter_javascript", "language"),
+    ".mjs": ("javascript", "tree_sitter_javascript", "language"),
+    ".cjs": ("javascript", "tree_sitter_javascript", "language"),
+    ".ts": ("typescript", "tree_sitter_typescript", "language_typescript"),
+    ".tsx": ("typescript", "tree_sitter_typescript", "language_tsx"),
+    ".rb": ("ruby", "tree_sitter_ruby", "language"),
+    ".go": ("go", "tree_sitter_go", "language"),
+    ".rs": ("rust", "tree_sitter_rust", "language"),
+    ".java": ("java", "tree_sitter_java", "language"),
+    ".kt": ("kotlin", "tree_sitter_kotlin", "language"),
+    ".kts": ("kotlin", "tree_sitter_kotlin", "language"),
+    ".c": ("c", "tree_sitter_c", "language"),
+    ".h": ("c", "tree_sitter_c", "language"),
+    ".cpp": ("cpp", "tree_sitter_cpp", "language"),
+    ".cc": ("cpp", "tree_sitter_cpp", "language"),
+    ".cxx": ("cpp", "tree_sitter_cpp", "language"),
+    ".hpp": ("cpp", "tree_sitter_cpp", "language"),
+}
+
+BEHAVIORAL_PREFIXES = (
+    "definition.",
+    "reference.",
+    "keyword.",
+    "function",
+    "attribute",
+    "constructor",
+    "label",
+    "type.definition",
+    "module",
+)
+
+_grammar_cache = {}
+_query_cache = {}
+
+
+def _load_grammar(ext):
+    entry = EXTENSION_MAP.get(ext)
+    if entry is None:
+        raise ValueError(f"Unsupported extension: {ext}")
+    query_name, module_name, func_name = entry
+
+    cache_key = f"{module_name}.{func_name}"
+    if cache_key in _grammar_cache:
+        return _grammar_cache[cache_key], query_name
+
+    mod = importlib.import_module(module_name)
+    lang = Language(getattr(mod, func_name)())
+    _grammar_cache[cache_key] = lang
+    return lang, query_name
+
+
+INHERIT_RE = re.compile(r"^;\s*inherits:\s*(.+)$", re.MULTILINE)
+
+
+def _resolve_inherits(src, query_name, seen=None):
+    if seen is None:
+        seen = set()
+    if query_name in seen:
+        return ""
+    seen.add(query_name)
+
+    qpath = QUERIES_DIR / f"{query_name}.scm"
+    if not qpath.exists():
+        return ""
+
+    content = qpath.read_text()
+    m = INHERIT_RE.search(content)
+    if m:
+        parents = m.group(1)
+        parent_parts = []
+        for parent in parents.split(","):
+            parent = parent.strip().strip("()")
+            if parent:
+                parent_parts.append(_resolve_inherits(parent, parent, seen))
+        parent_src = "\n".join(p for p in parent_parts if p)
+        body = INHERIT_RE.sub("", content)
+        return parent_src + "\n" + body if parent_src else body
+    return content
+
+
+def _load_query(query_name):
+    if query_name in _query_cache:
+        return _query_cache[query_name]
+
+    src = _resolve_inherits(query_name, query_name)
+    if not src:
+        raise FileNotFoundError(f"Query file not found: {query_name}")
+
+    _query_cache[query_name] = src
+    return src
+
+
+def preprocess(file_path: str, code: str):
+    ext = os.path.splitext(file_path)[1].lower()
+    lang, query_name = _load_grammar(ext)
+    query_src = _load_query(query_name)
+
+    parser = Parser(lang)
+    tree = parser.parse(code.encode())
+
+    try:
+        query = Query(lang, query_src)
+    except Exception as e:
+        print(f"Query error for {query_name}: {e}", file=sys.stderr)
+        return
+
+    cursor = QueryCursor(query)
+    captures = cursor.captures(tree.root_node)
+
+    items = []
+    for capname, nodes in captures.items():
+        if not capname.startswith(BEHAVIORAL_PREFIXES):
+            continue
+        for node in nodes:
+            items.append((node.start_byte, capname, node, code[node.start_byte:node.end_byte].strip()))
+
+    items.sort(key=lambda x: x[0])
+
+    return [(capname, text, code[:start].count("\n") + 1) for start, capname, _, text in items]
+
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: python -m bex.tag-preprocessor.code <file>", file=sys.stderr)
+        sys.exit(1)
+
+    file_path = sys.argv[1]
+
+    if not os.path.exists(file_path):
+        print(f"File not found: {file_path}", file=sys.stderr)
+        sys.exit(1)
+
+    try:
+        with open(file_path) as f:
+            code = f.read()
+    except Exception as e:
+        print(f"Error reading {file_path}: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    try:
+        seq = preprocess(file_path, code)
+    except ValueError as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+    except FileNotFoundError as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+    except Exception as e:
+        print(f"Error preprocessing {file_path}: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    if not seq:
+        print("(no behavioral tokens)")
+        return
+
+    print(f"{'CAPTURE':35s} {'TEXT':50s} LINE")
+    print("-" * 88)
+    for capname, text, line in seq:
+        print(f"{capname:35s} '{text[:48]:48s}' L{line}")
+
+    print(f"\nSequence ({len(seq)} tokens):")
+    print(" -> ".join(c for c, _, _ in seq))
+
+
+if __name__ == "__main__":
+    main()

bex/tag-preprocessor/nvim-reference/c.scm

@@ -0,0 +1,341 @@
+; Lower priority to prefer @variable.parameter when identifier appears in parameter_declaration.
+((identifier) @variable
+  (#set! priority 95))
+
+(preproc_def
+  (preproc_arg) @variable)
+
+[
+  "default"
+  "goto"
+  "asm"
+  "__asm__"
+] @keyword
+
+[
+  "enum"
+  "struct"
+  "union"
+  "typedef"
+] @keyword.type
+
+[
+  "sizeof"
+  "offsetof"
+] @keyword.operator
+
+(alignof_expression
+  .
+  _ @keyword.operator)
+
+"return" @keyword.return
+
+[
+  "while"
+  "for"
+  "do"
+  "continue"
+  "break"
+] @keyword.repeat
+
+[
+  "if"
+  "else"
+  "case"
+  "switch"
+] @keyword.conditional
+
+[
+  "#if"
+  "#ifdef"
+  "#ifndef"
+  "#else"
+  "#elif"
+  "#endif"
+  "#elifdef"
+  "#elifndef"
+  (preproc_directive)
+] @keyword.directive
+
+"#define" @keyword.directive.define
+
+"#include" @keyword.import
+
+[
+  ";"
+  ":"
+  ","
+  "."
+  "::"
+] @punctuation.delimiter
+
+"..." @punctuation.special
+
+[
+  "("
+  ")"
+  "["
+  "]"
+  "{"
+  "}"
+] @punctuation.bracket
+
+[
+  "="
+  "-"
+  "*"
+  "/"
+  "+"
+  "%"
+  "~"
+  "|"
+  "&"
+  "^"
+  "<<"
+  ">>"
+  "->"
+  "<"
+  "<="
+  ">="
+  ">"
+  "=="
+  "!="
+  "!"
+  "&&"
+  "||"
+  "-="
+  "+="
+  "*="
+  "/="
+  "%="
+  "|="
+  "&="
+  "^="
+  ">>="
+  "<<="
+  "--"
+  "++"
+] @operator
+
+; Make sure the comma operator is given a highlight group after the comma
+; punctuator so the operator is highlighted properly.
+(comma_expression
+  "," @operator)
+
+[
+  (true)
+  (false)
+] @boolean
+
+(conditional_expression
+  [
+    "?"
+    ":"
+  ] @keyword.conditional.ternary)
+
+(string_literal) @string
+
+(system_lib_string) @string
+
+(escape_sequence) @string.escape
+
+(null) @constant.builtin
+
+(number_literal) @number
+
+(char_literal) @character
+
+(preproc_defined) @function.macro
+
+((field_expression
+  (field_identifier) @property) @_parent
+  (#not-has-parent? @_parent template_method function_declarator call_expression))
+
+(field_designator) @property
+
+((field_identifier) @property
+  (#has-ancestor? @property field_declaration)
+  (#not-has-ancestor? @property function_declarator))
+
+(statement_identifier) @label
+
+(declaration
+  type: (type_identifier) @_type
+  declarator: (identifier) @label
+  (#eq? @_type "__label__"))
+
+[
+  (type_identifier)
+  (type_descriptor)
+] @type
+
+(storage_class_specifier) @keyword.modifier
+
+[
+  (type_qualifier)
+  (gnu_asm_qualifier)
+  "__extension__"
+] @keyword.modifier
+
+(linkage_specification
+  "extern" @keyword.modifier)
+
+(type_definition
+  declarator: (type_identifier) @type.definition)
+
+(primitive_type) @type.builtin
+
+(sized_type_specifier
+  _ @type.builtin
+  type: _?)
+
+((identifier) @constant
+  (#lua-match? @constant "^[A-Z][A-Z0-9_]+$"))
+
+(preproc_def
+  (preproc_arg) @constant
+  (#lua-match? @constant "^[A-Z][A-Z0-9_]+$"))
+
+(enumerator
+  name: (identifier) @constant)
+
+(case_statement
+  value: (identifier) @constant)
+
+((identifier) @constant.builtin
+  ; format-ignore
+  (#any-of? @constant.builtin
+    "stderr" "stdin" "stdout"
+    "__FILE__" "__LINE__" "__DATE__" "__TIME__"
+    "__STDC__" "__STDC_VERSION__" "__STDC_HOSTED__"
+    "__cplusplus" "__OBJC__" "__ASSEMBLER__"
+    "__BASE_FILE__" "__FILE_NAME__" "__INCLUDE_LEVEL__"
+    "__TIMESTAMP__" "__clang__" "__clang_major__"
+    "__clang_minor__" "__clang_patchlevel__"
+    "__clang_version__" "__clang_literal_encoding__"
+    "__clang_wide_literal_encoding__"
+    "__FUNCTION__" "__func__" "__PRETTY_FUNCTION__"
+    "__VA_ARGS__" "__VA_OPT__"))
+
+(preproc_def
+  (preproc_arg) @constant.builtin
+  ; format-ignore
+  (#any-of? @constant.builtin
+    "stderr" "stdin" "stdout"
+    "__FILE__" "__LINE__" "__DATE__" "__TIME__"
+    "__STDC__" "__STDC_VERSION__" "__STDC_HOSTED__"
+    "__cplusplus" "__OBJC__" "__ASSEMBLER__"
+    "__BASE_FILE__" "__FILE_NAME__" "__INCLUDE_LEVEL__"
+    "__TIMESTAMP__" "__clang__" "__clang_major__"
+    "__clang_minor__" "__clang_patchlevel__"
+    "__clang_version__" "__clang_literal_encoding__"
+    "__clang_wide_literal_encoding__"
+    "__FUNCTION__" "__func__" "__PRETTY_FUNCTION__"
+    "__VA_ARGS__" "__VA_OPT__"))
+
+(attribute_specifier
+  (argument_list
+    (identifier) @variable.builtin))
+
+(attribute_specifier
+  (argument_list
+    (call_expression
+      function: (identifier) @variable.builtin)))
+
+((call_expression
+  function: (identifier) @function.builtin)
+  (#lua-match? @function.builtin "^__builtin_"))
+
+((call_expression
+  function: (identifier) @function.builtin)
+  (#has-ancestor? @function.builtin attribute_specifier))
+
+; Preproc def / undef
+(preproc_def
+  name: (_) @constant.macro)
+
+(preproc_call
+  directive: (preproc_directive) @_u
+  argument: (_) @constant.macro
+  (#eq? @_u "#undef"))
+
+(preproc_ifdef
+  name: (identifier) @constant.macro)
+
+(preproc_elifdef
+  name: (identifier) @constant.macro)
+
+(preproc_defined
+  (identifier) @constant.macro)
+
+(call_expression
+  function: (identifier) @function.call)
+
+(call_expression
+  function: (field_expression
+    field: (field_identifier) @function.call))
+
+(function_declarator
+  declarator: (identifier) @function)
+
+(function_declarator
+  declarator: (parenthesized_declarator
+    (pointer_declarator
+      declarator: (field_identifier) @function)))
+
+(preproc_function_def
+  name: (identifier) @function.macro)
+
+(comment) @comment @spell
+
+((comment) @comment.documentation
+  (#lua-match? @comment.documentation "^/[*][*][^*].*[*]/$"))
+
+; Parameters
+(parameter_declaration
+  declarator: (identifier) @variable.parameter)
+
+(parameter_declaration
+  declarator: (array_declarator) @variable.parameter)
+
+(parameter_declaration
+  declarator: (pointer_declarator) @variable.parameter)
+
+; K&R functions
+; To enable support for K&R functions,
+; add the following lines to your own query config and uncomment them.
+; They are commented out as they'll conflict with C++
+; Note that you'll need to have `; extends` at the top of your query file.
+;
+; (parameter_list (identifier) @variable.parameter)
+;
+; (function_definition
+;   declarator: _
+;   (declaration
+;     declarator: (identifier) @variable.parameter))
+;
+; (function_definition
+;   declarator: _
+;   (declaration
+;     declarator: (array_declarator) @variable.parameter))
+;
+; (function_definition
+;   declarator: _
+;   (declaration
+;     declarator: (pointer_declarator) @variable.parameter))
+(preproc_params
+  (identifier) @variable.parameter)
+
+[
+  "__attribute__"
+  "__declspec"
+  "__based"
+  "__cdecl"
+  "__clrcall"
+  "__stdcall"
+  "__fastcall"
+  "__thiscall"
+  "__vectorcall"
+  (ms_pointer_modifier)
+  (attribute_declaration)
+] @attribute

bex/tag-preprocessor/nvim-reference/cpp.scm

@@ -0,0 +1,268 @@
+; inherits: c
+
+((identifier) @variable.member
+  (#lua-match? @variable.member "^m_.*$"))
+
+(parameter_declaration
+  declarator: (reference_declarator) @variable.parameter)
+
+; function(Foo ...foo)
+(variadic_parameter_declaration
+  declarator: (variadic_declarator
+    (_) @variable.parameter))
+
+; int foo = 0
+(optional_parameter_declaration
+  declarator: (_) @variable.parameter)
+
+;(field_expression) @variable.parameter ;; How to highlight this?
+((field_expression
+  (field_identifier) @function.method) @_parent
+  (#has-parent? @_parent template_method function_declarator))
+
+(field_declaration
+  (field_identifier) @variable.member)
+
+(field_initializer
+  (field_identifier) @property)
+
+(function_declarator
+  declarator: (field_identifier) @function.method)
+
+(concept_definition
+  name: (identifier) @type.definition)
+
+(alias_declaration
+  name: (type_identifier) @type.definition)
+
+(auto) @type.builtin
+
+(namespace_identifier) @module
+
+((namespace_identifier) @type
+  (#lua-match? @type "^[%u]"))
+
+(case_statement
+  value: (qualified_identifier
+    (identifier) @constant))
+
+(using_declaration
+  .
+  "using"
+  .
+  "namespace"
+  .
+  [
+    (qualified_identifier)
+    (identifier)
+  ] @module)
+
+(destructor_name
+  (identifier) @function.method)
+
+; functions
+(function_declarator
+  (qualified_identifier
+    (identifier) @function))
+
+(function_declarator
+  (qualified_identifier
+    (qualified_identifier
+      (identifier) @function)))
+
+(function_declarator
+  (qualified_identifier
+    (qualified_identifier
+      (qualified_identifier
+        (identifier) @function))))
+
+((qualified_identifier
+  (qualified_identifier
+    (qualified_identifier
+      (qualified_identifier
+        (identifier) @function)))) @_parent
+  (#has-ancestor? @_parent function_declarator))
+
+(function_declarator
+  (template_function
+    (identifier) @function))
+
+(operator_name) @function
+
+"operator" @function
+
+"static_assert" @function.builtin
+
+(call_expression
+  (qualified_identifier
+    (identifier) @function.call))
+
+(call_expression
+  (qualified_identifier
+    (qualified_identifier
+      (identifier) @function.call)))
+
+(call_expression
+  (qualified_identifier
+    (qualified_identifier
+      (qualified_identifier
+        (identifier) @function.call))))
+
+((qualified_identifier
+  (qualified_identifier
+    (qualified_identifier
+      (qualified_identifier
+        (identifier) @function.call)))) @_parent
+  (#has-ancestor? @_parent call_expression))
+
+(call_expression
+  (template_function
+    (identifier) @function.call))
+
+(call_expression
+  (qualified_identifier
+    (template_function
+      (identifier) @function.call)))
+
+(call_expression
+  (qualified_identifier
+    (qualified_identifier
+      (template_function
+        (identifier) @function.call))))
+
+(call_expression
+  (qualified_identifier
+    (qualified_identifier
+      (qualified_identifier
+        (template_function
+          (identifier) @function.call)))))
+
+((qualified_identifier
+  (qualified_identifier
+    (qualified_identifier
+      (qualified_identifier
+        (template_function
+          (identifier) @function.call))))) @_parent
+  (#has-ancestor? @_parent call_expression))
+
+; methods
+(function_declarator
+  (template_method
+    (field_identifier) @function.method))
+
+(call_expression
+  (field_expression
+    (field_identifier) @function.method.call))
+
+; constructors
+((function_declarator
+  (qualified_identifier
+    (identifier) @constructor))
+  (#lua-match? @constructor "^%u"))
+
+((call_expression
+  function: (identifier) @constructor)
+  (#lua-match? @constructor "^%u"))
+
+((call_expression
+  function: (qualified_identifier
+    name: (identifier) @constructor))
+  (#lua-match? @constructor "^%u"))
+
+((call_expression
+  function: (field_expression
+    field: (field_identifier) @constructor))
+  (#lua-match? @constructor "^%u"))
+
+; constructing a type in an initializer list: Constructor ():  **SuperType (1)**
+((field_initializer
+  (field_identifier) @constructor
+  (argument_list))
+  (#lua-match? @constructor "^%u"))
+
+; Constants
+(this) @variable.builtin
+
+(null
+  "nullptr" @constant.builtin)
+
+(true) @boolean
+
+(false) @boolean
+
+; Literals
+(raw_string_literal) @string
+
+; Keywords
+[
+  "try"
+  "catch"
+  "noexcept"
+  "throw"
+] @keyword.exception
+
+[
+  "decltype"
+  "explicit"
+  "friend"
+  "override"
+  "using"
+  "requires"
+  "constexpr"
+] @keyword
+
+[
+  "class"
+  "namespace"
+  "template"
+  "typename"
+  "concept"
+] @keyword.type
+
+[
+  "co_await"
+  "co_yield"
+  "co_return"
+] @keyword.coroutine
+
+[
+  "public"
+  "private"
+  "protected"
+  "final"
+  "virtual"
+] @keyword.modifier
+
+[
+  "new"
+  "delete"
+  "xor"
+  "bitand"
+  "bitor"
+  "compl"
+  "not"
+  "xor_eq"
+  "and_eq"
+  "or_eq"
+  "not_eq"
+  "and"
+  "or"
+] @keyword.operator
+
+"<=>" @operator
+
+"::" @punctuation.delimiter
+
+(template_argument_list
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(template_parameter_list
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(literal_suffix) @operator

bex/tag-preprocessor/nvim-reference/go.scm

@@ -0,0 +1,254 @@
+; Forked from tree-sitter-go
+; Copyright (c) 2014 Max Brunsfeld (The MIT License)
+;
+; Identifiers
+(type_identifier) @type
+
+(type_spec
+  name: (type_identifier) @type.definition)
+
+(field_identifier) @property
+
+(identifier) @variable
+
+(package_identifier) @module
+
+(parameter_declaration
+  (identifier) @variable.parameter)
+
+(variadic_parameter_declaration
+  (identifier) @variable.parameter)
+
+(label_name) @label
+
+(const_spec
+  name: (identifier) @constant)
+
+; Function calls
+(call_expression
+  function: (identifier) @function.call)
+
+(call_expression
+  function: (selector_expression
+    field: (field_identifier) @function.method.call))
+
+; Function definitions
+(function_declaration
+  name: (identifier) @function)
+
+(method_declaration
+  name: (field_identifier) @function.method)
+
+(method_elem
+  name: (field_identifier) @function.method)
+
+; Constructors
+((call_expression
+  (identifier) @constructor)
+  (#lua-match? @constructor "^[nN]ew.+$"))
+
+((call_expression
+  (identifier) @constructor)
+  (#lua-match? @constructor "^[mM]ake.+$"))
+
+; Operators
+[
+  "--"
+  "-"
+  "-="
+  ":="
+  "!"
+  "!="
+  "..."
+  "*"
+  "*"
+  "*="
+  "/"
+  "/="
+  "&"
+  "&&"
+  "&="
+  "&^"
+  "&^="
+  "%"
+  "%="
+  "^"
+  "^="
+  "+"
+  "++"
+  "+="
+  "<-"
+  "<"
+  "<<"
+  "<<="
+  "<="
+  "="
+  "=="
+  ">"
+  ">="
+  ">>"
+  ">>="
+  "|"
+  "|="
+  "||"
+  "~"
+] @operator
+
+; Keywords
+[
+  "break"
+  "const"
+  "continue"
+  "default"
+  "defer"
+  "goto"
+  "range"
+  "select"
+  "var"
+  "fallthrough"
+] @keyword
+
+[
+  "type"
+  "struct"
+  "interface"
+] @keyword.type
+
+"func" @keyword.function
+
+"return" @keyword.return
+
+"go" @keyword.coroutine
+
+"for" @keyword.repeat
+
+[
+  "import"
+  "package"
+] @keyword.import
+
+[
+  "else"
+  "case"
+  "switch"
+  "if"
+] @keyword.conditional
+
+; Builtin types
+[
+  "chan"
+  "map"
+] @type.builtin
+
+((type_identifier) @type.builtin
+  (#any-of? @type.builtin
+    "any" "bool" "byte" "comparable" "complex128" "complex64" "error" "float32" "float64" "int"
+    "int16" "int32" "int64" "int8" "rune" "string" "uint" "uint16" "uint32" "uint64" "uint8"
+    "uintptr"))
+
+; Builtin functions
+((identifier) @function.builtin
+  (#any-of? @function.builtin
+    "append" "cap" "clear" "close" "complex" "copy" "delete" "imag" "len" "make" "max" "min" "new"
+    "panic" "print" "println" "real" "recover"))
+
+; Delimiters
+"." @punctuation.delimiter
+
+"," @punctuation.delimiter
+
+":" @punctuation.delimiter
+
+";" @punctuation.delimiter
+
+"(" @punctuation.bracket
+
+")" @punctuation.bracket
+
+"{" @punctuation.bracket
+
+"}" @punctuation.bracket
+
+"[" @punctuation.bracket
+
+"]" @punctuation.bracket
+
+; Literals
+(interpreted_string_literal) @string
+
+(raw_string_literal) @string
+
+(rune_literal) @string
+
+(escape_sequence) @string.escape
+
+(int_literal) @number
+
+(float_literal) @number.float
+
+(imaginary_literal) @number
+
+[
+  (true)
+  (false)
+] @boolean
+
+[
+  (nil)
+  (iota)
+] @constant.builtin
+
+(keyed_element
+  .
+  (literal_element
+    (identifier) @variable.member))
+
+(field_declaration
+  name: (field_identifier) @variable.member)
+
+; Comments
+(comment) @comment @spell
+
+; Doc Comments
+(source_file
+  .
+  (comment)+ @comment.documentation)
+
+(source_file
+  (comment)+ @comment.documentation
+  .
+  (const_declaration))
+
+(source_file
+  (comment)+ @comment.documentation
+  .
+  (function_declaration))
+
+(source_file
+  (comment)+ @comment.documentation
+  .
+  (type_declaration))
+
+(source_file
+  (comment)+ @comment.documentation
+  .
+  (var_declaration))
+
+; Spell
+((interpreted_string_literal) @spell
+  (#not-has-parent? @spell import_spec))
+
+; Regex
+(call_expression
+  (selector_expression) @_function
+  (#any-of? @_function
+    "regexp.Match" "regexp.MatchReader" "regexp.MatchString" "regexp.Compile" "regexp.CompilePOSIX"
+    "regexp.MustCompile" "regexp.MustCompilePOSIX")
+  (argument_list
+    .
+    [
+      (raw_string_literal
+        (raw_string_literal_content) @string.regexp)
+      (interpreted_string_literal
+        (interpreted_string_literal_content) @string.regexp)
+    ]))

bex/tag-preprocessor/nvim-reference/java.scm

@@ -0,0 +1,330 @@
+; CREDITS @maxbrunsfeld (maxbrunsfeld@gmail.com)
+; Variables
+(identifier) @variable
+
+(underscore_pattern) @character.special
+
+; Methods
+(method_declaration
+  name: (identifier) @function.method)
+
+(method_invocation
+  name: (identifier) @function.method.call)
+
+(super) @function.builtin
+
+; Parameters
+(formal_parameter
+  name: (identifier) @variable.parameter)
+
+(spread_parameter
+  (variable_declarator
+    name: (identifier) @variable.parameter)) ; int... foo
+
+; Lambda parameter
+(inferred_parameters
+  (identifier) @variable.parameter) ; (x,y) -> ...
+
+(lambda_expression
+  parameters: (identifier) @variable.parameter) ; x -> ...
+
+; Operators
+[
+  "+"
+  ":"
+  "++"
+  "-"
+  "--"
+  "&"
+  "&&"
+  "|"
+  "||"
+  "!"
+  "!="
+  "=="
+  "*"
+  "/"
+  "%"
+  "<"
+  "<="
+  ">"
+  ">="
+  "="
+  "-="
+  "+="
+  "*="
+  "/="
+  "%="
+  "->"
+  "^"
+  "^="
+  "&="
+  "|="
+  "~"
+  ">>"
+  ">>>"
+  "<<"
+  "::"
+] @operator
+
+; Types
+(interface_declaration
+  name: (identifier) @type)
+
+(annotation_type_declaration
+  name: (identifier) @type)
+
+(class_declaration
+  name: (identifier) @type)
+
+(record_declaration
+  name: (identifier) @type)
+
+(enum_declaration
+  name: (identifier) @type)
+
+(constructor_declaration
+  name: (identifier) @type)
+
+(compact_constructor_declaration
+  name: (identifier) @type)
+
+(type_identifier) @type
+
+((type_identifier) @type.builtin
+  (#eq? @type.builtin "var"))
+
+((method_invocation
+  object: (identifier) @type)
+  (#lua-match? @type "^[A-Z]"))
+
+((method_reference
+  .
+  (identifier) @type)
+  (#lua-match? @type "^[A-Z]"))
+
+((field_access
+  object: (identifier) @type)
+  (#lua-match? @type "^[A-Z]"))
+
+(scoped_identifier
+  (identifier) @type
+  (#lua-match? @type "^[A-Z]"))
+
+; Fields
+(field_declaration
+  declarator: (variable_declarator
+    name: (identifier) @variable.member))
+
+(field_access
+  field: (identifier) @variable.member)
+
+[
+  (boolean_type)
+  (integral_type)
+  (floating_point_type)
+  (void_type)
+] @type.builtin
+
+; Variables
+((identifier) @constant
+  (#lua-match? @constant "^[A-Z_][A-Z%d_]+$"))
+
+(this) @variable.builtin
+
+; Annotations
+(annotation
+  "@" @attribute
+  name: (identifier) @attribute)
+
+(marker_annotation
+  "@" @attribute
+  name: (identifier) @attribute)
+
+; Literals
+(string_literal) @string
+
+(escape_sequence) @string.escape
+
+(character_literal) @character
+
+[
+  (hex_integer_literal)
+  (decimal_integer_literal)
+  (octal_integer_literal)
+  (binary_integer_literal)
+] @number
+
+[
+  (decimal_floating_point_literal)
+  (hex_floating_point_literal)
+] @number.float
+
+[
+  (true)
+  (false)
+] @boolean
+
+(null_literal) @constant.builtin
+
+; Keywords
+[
+  "assert"
+  "default"
+  "extends"
+  "implements"
+  "instanceof"
+  "@interface"
+  "permits"
+  "to"
+  "with"
+] @keyword
+
+[
+  "record"
+  "class"
+  "enum"
+  "interface"
+] @keyword.type
+
+(synchronized_statement
+  "synchronized" @keyword)
+
+[
+  "abstract"
+  "final"
+  "native"
+  "non-sealed"
+  "open"
+  "private"
+  "protected"
+  "public"
+  "sealed"
+  "static"
+  "strictfp"
+  "transitive"
+] @keyword.modifier
+
+(modifiers
+  "synchronized" @keyword.modifier)
+
+[
+  "transient"
+  "volatile"
+] @keyword.modifier
+
+[
+  "return"
+  "yield"
+] @keyword.return
+
+"new" @keyword.operator
+
+; Conditionals
+[
+  "if"
+  "else"
+  "switch"
+  "case"
+  "when"
+] @keyword.conditional
+
+(ternary_expression
+  [
+    "?"
+    ":"
+  ] @keyword.conditional.ternary)
+
+; Loops
+[
+  "for"
+  "while"
+  "do"
+  "continue"
+  "break"
+] @keyword.repeat
+
+; Includes
+[
+  "exports"
+  "import"
+  "module"
+  "opens"
+  "package"
+  "provides"
+  "requires"
+  "uses"
+] @keyword.import
+
+(import_declaration
+  (asterisk
+    "*" @character.special))
+
+; Punctuation
+[
+  ";"
+  "."
+  "..."
+  ","
+] @punctuation.delimiter
+
+[
+  "{"
+  "}"
+] @punctuation.bracket
+
+[
+  "["
+  "]"
+] @punctuation.bracket
+
+[
+  "("
+  ")"
+] @punctuation.bracket
+
+(type_arguments
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(type_parameters
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(string_interpolation
+  [
+    "\\{"
+    "}"
+  ] @punctuation.special)
+
+; Exceptions
+[
+  "throw"
+  "throws"
+  "finally"
+  "try"
+  "catch"
+] @keyword.exception
+
+; Labels
+(labeled_statement
+  (identifier) @label)
+
+; Comments
+[
+  (line_comment)
+  (block_comment)
+] @comment @spell
+
+((block_comment) @comment.documentation
+  (#lua-match? @comment.documentation "^/[*][*][^*].*[*]/$"))
+
+((line_comment) @comment.documentation
+  (#lua-match? @comment.documentation "^///[^/]"))
+
+((line_comment) @comment.documentation
+  (#lua-match? @comment.documentation "^///$"))

bex/tag-preprocessor/nvim-reference/javascript.scm

@@ -0,0 +1,56 @@
+; inherits: ecma,jsx
+
+; Parameters
+(formal_parameters
+  (identifier) @variable.parameter)
+
+(formal_parameters
+  (rest_pattern
+    (identifier) @variable.parameter))
+
+; ({ a }) => null
+(formal_parameters
+  (object_pattern
+    (shorthand_property_identifier_pattern) @variable.parameter))
+
+; ({ a = b }) => null
+(formal_parameters
+  (object_pattern
+    (object_assignment_pattern
+      (shorthand_property_identifier_pattern) @variable.parameter)))
+
+; ({ a: b }) => null
+(formal_parameters
+  (object_pattern
+    (pair_pattern
+      value: (identifier) @variable.parameter)))
+
+; ([ a ]) => null
+(formal_parameters
+  (array_pattern
+    (identifier) @variable.parameter))
+
+; ({ a } = { a }) => null
+(formal_parameters
+  (assignment_pattern
+    (object_pattern
+      (shorthand_property_identifier_pattern) @variable.parameter)))
+
+; ({ a = b } = { a }) => null
+(formal_parameters
+  (assignment_pattern
+    (object_pattern
+      (object_assignment_pattern
+        (shorthand_property_identifier_pattern) @variable.parameter))))
+
+; a => null
+(arrow_function
+  parameter: (identifier) @variable.parameter)
+
+; optional parameters
+(formal_parameters
+  (assignment_pattern
+    left: (identifier) @variable.parameter))
+
+; punctuation
+(optional_chain) @punctuation.delimiter

bex/tag-preprocessor/nvim-reference/kotlin.scm

@@ -0,0 +1,398 @@
+; Identifiers
+(simple_identifier) @variable
+
+; `it` keyword inside lambdas
+; FIXME: This will highlight the keyword outside of lambdas since tree-sitter
+;        does not allow us to check for arbitrary nestation
+((simple_identifier) @variable.builtin
+  (#eq? @variable.builtin "it"))
+
+; `field` keyword inside property getter/setter
+; FIXME: This will highlight the keyword outside of getters and setters
+;        since tree-sitter does not allow us to check for arbitrary nestation
+((simple_identifier) @variable.builtin
+  (#eq? @variable.builtin "field"))
+
+[
+  "this"
+  "super"
+  "this@"
+  "super@"
+] @variable.builtin
+
+; NOTE: for consistency with "super@"
+(super_expression
+  "@" @variable.builtin)
+
+(class_parameter
+  (simple_identifier) @variable.member)
+
+; NOTE: temporary fix for treesitter bug that causes delay in file opening
+;(class_body
+;  (property_declaration
+;    (variable_declaration
+;      (simple_identifier) @variable.member)))
+; id_1.id_2.id_3: `id_2` and `id_3` are assumed as object properties
+(_
+  (navigation_suffix
+    (simple_identifier) @variable.member))
+
+; SCREAMING CASE identifiers are assumed to be constants
+((simple_identifier) @constant
+  (#lua-match? @constant "^[A-Z][A-Z0-9_]*$"))
+
+(_
+  (navigation_suffix
+    (simple_identifier) @constant
+    (#lua-match? @constant "^[A-Z][A-Z0-9_]*$")))
+
+(enum_entry
+  (simple_identifier) @constant)
+
+(type_identifier) @type
+
+; '?' operator, replacement for Java @Nullable
+(nullable_type) @punctuation.special
+
+(type_alias
+  (type_identifier) @type.definition)
+
+((type_identifier) @type.builtin
+  (#any-of? @type.builtin
+    "Byte" "Short" "Int" "Long" "UByte" "UShort" "UInt" "ULong" "Float" "Double" "Boolean" "Char"
+    "String" "Array" "ByteArray" "ShortArray" "IntArray" "LongArray" "UByteArray" "UShortArray"
+    "UIntArray" "ULongArray" "FloatArray" "DoubleArray" "BooleanArray" "CharArray" "Map" "Set"
+    "List" "EmptyMap" "EmptySet" "EmptyList" "MutableMap" "MutableSet" "MutableList"))
+
+(package_header
+  "package" @keyword
+  .
+  (identifier
+    (simple_identifier) @module))
+
+(import_header
+  "import" @keyword.import)
+
+(wildcard_import) @character.special
+
+; The last `simple_identifier` in a `import_header` will always either be a function
+; or a type. Classes can appear anywhere in the import path, unlike functions
+(import_header
+  (identifier
+    (simple_identifier) @type @_import)
+  (import_alias
+    (type_identifier) @type.definition)?
+  (#lua-match? @_import "^[A-Z]"))
+
+(import_header
+  (identifier
+    (simple_identifier) @function @_import .)
+  (import_alias
+    (type_identifier) @function)?
+  (#lua-match? @_import "^[a-z]"))
+
+(label) @label
+
+; Function definitions
+(function_declaration
+  (simple_identifier) @function)
+
+(getter
+  "get" @function.builtin)
+
+(setter
+  "set" @function.builtin)
+
+(primary_constructor) @constructor
+
+(secondary_constructor
+  "constructor" @constructor)
+
+(constructor_invocation
+  (user_type
+    (type_identifier) @constructor))
+
+(anonymous_initializer
+  "init" @constructor)
+
+(parameter
+  (simple_identifier) @variable.parameter)
+
+(parameter_with_optional_type
+  (simple_identifier) @variable.parameter)
+
+; lambda parameters
+(lambda_literal
+  (lambda_parameters
+    (variable_declaration
+      (simple_identifier) @variable.parameter)))
+
+; Function calls
+; function()
+(call_expression
+  .
+  (simple_identifier) @function.call)
+
+; ::function
+(callable_reference
+  .
+  (simple_identifier) @function.call)
+
+; object.function() or object.property.function()
+(call_expression
+  (navigation_expression
+    (navigation_suffix
+      (simple_identifier) @function.call) .))
+
+(call_expression
+  .
+  (simple_identifier) @function.builtin
+  (#any-of? @function.builtin
+    "arrayOf" "arrayOfNulls" "byteArrayOf" "shortArrayOf" "intArrayOf" "longArrayOf" "ubyteArrayOf"
+    "ushortArrayOf" "uintArrayOf" "ulongArrayOf" "floatArrayOf" "doubleArrayOf" "booleanArrayOf"
+    "charArrayOf" "emptyArray" "mapOf" "setOf" "listOf" "emptyMap" "emptySet" "emptyList"
+    "mutableMapOf" "mutableSetOf" "mutableListOf" "print" "println" "error" "TODO" "run"
+    "runCatching" "repeat" "lazy" "lazyOf" "enumValues" "enumValueOf" "assert" "check"
+    "checkNotNull" "require" "requireNotNull" "with" "suspend" "synchronized"))
+
+; Literals
+[
+  (line_comment)
+  (multiline_comment)
+] @comment @spell
+
+((multiline_comment) @comment.documentation
+  (#lua-match? @comment.documentation "^/[*][*][^*].*[*]/$"))
+
+(shebang_line) @keyword.directive
+
+(real_literal) @number.float
+
+[
+  (integer_literal)
+  (long_literal)
+  (hex_literal)
+  (bin_literal)
+  (unsigned_literal)
+] @number
+
+[
+  (null_literal)
+  ; should be highlighted the same as booleans
+  (boolean_literal)
+] @boolean
+
+(character_literal) @character
+
+(string_literal) @string
+
+; NOTE: Escapes not allowed in multi-line strings
+(character_literal
+  (character_escape_seq) @string.escape)
+
+; There are 3 ways to define a regex
+;    - "[abc]?".toRegex()
+(call_expression
+  (navigation_expression
+    (string_literal) @string.regexp
+    (navigation_suffix
+      ((simple_identifier) @_function
+        (#eq? @_function "toRegex")))))
+
+;    - Regex("[abc]?")
+(call_expression
+  ((simple_identifier) @_function
+    (#eq? @_function "Regex"))
+  (call_suffix
+    (value_arguments
+      (value_argument
+        (string_literal) @string.regexp))))
+
+;    - Regex.fromLiteral("[abc]?")
+(call_expression
+  (navigation_expression
+    ((simple_identifier) @_class
+      (#eq? @_class "Regex"))
+    (navigation_suffix
+      ((simple_identifier) @_function
+        (#eq? @_function "fromLiteral"))))
+  (call_suffix
+    (value_arguments
+      (value_argument
+        (string_literal) @string.regexp))))
+
+; Keywords
+(type_alias
+  "typealias" @keyword)
+
+(companion_object
+  "companion" @keyword)
+
+[
+  (class_modifier)
+  (member_modifier)
+  (function_modifier)
+  (property_modifier)
+  (platform_modifier)
+  (variance_modifier)
+  (parameter_modifier)
+  (visibility_modifier)
+  (reification_modifier)
+  (inheritance_modifier)
+] @keyword.modifier
+
+[
+  "val"
+  "var"
+  ;	"typeof" ; NOTE: It is reserved for future use
+] @keyword
+
+[
+  "enum"
+  "class"
+  "object"
+  "interface"
+] @keyword.type
+
+[
+  "return"
+  "return@"
+] @keyword.return
+
+"suspend" @keyword.coroutine
+
+"fun" @keyword.function
+
+[
+  "if"
+  "else"
+  "when"
+] @keyword.conditional
+
+[
+  "for"
+  "do"
+  "while"
+  "continue"
+  "continue@"
+  "break"
+  "break@"
+] @keyword.repeat
+
+[
+  "try"
+  "catch"
+  "throw"
+  "finally"
+] @keyword.exception
+
+(annotation
+  "@" @attribute
+  (use_site_target)? @attribute)
+
+(annotation
+  (user_type
+    (type_identifier) @attribute))
+
+(annotation
+  (constructor_invocation
+    (user_type
+      (type_identifier) @attribute)))
+
+(file_annotation
+  "@" @attribute
+  "file" @attribute
+  ":" @attribute)
+
+(file_annotation
+  (user_type
+    (type_identifier) @attribute))
+
+(file_annotation
+  (constructor_invocation
+    (user_type
+      (type_identifier) @attribute)))
+
+; Operators & Punctuation
+[
+  "!"
+  "!="
+  "!=="
+  "="
+  "=="
+  "==="
+  ">"
+  ">="
+  "<"
+  "<="
+  "||"
+  "&&"
+  "+"
+  "++"
+  "+="
+  "-"
+  "--"
+  "-="
+  "*"
+  "*="
+  "/"
+  "/="
+  "%"
+  "%="
+  "?."
+  "?:"
+  "!!"
+  "is"
+  "!is"
+  "in"
+  "!in"
+  "as"
+  "as?"
+  ".."
+  "->"
+] @operator
+
+[
+  "("
+  ")"
+  "["
+  "]"
+  "{"
+  "}"
+] @punctuation.bracket
+
+[
+  "."
+  ","
+  ";"
+  ":"
+  "::"
+] @punctuation.delimiter
+
+(super_expression
+  [
+    "<"
+    ">"
+  ] @punctuation.delimiter)
+
+(type_arguments
+  [
+    "<"
+    ">"
+  ] @punctuation.delimiter)
+
+(type_parameters
+  [
+    "<"
+    ">"
+  ] @punctuation.delimiter)
+
+; NOTE: `interpolated_identifier`s can be highlighted in any way
+(string_literal
+  "$" @punctuation.special
+  (interpolated_identifier) @none @variable)
+
+(string_literal
+  "${" @punctuation.special
+  (interpolated_expression) @none
+  "}" @punctuation.special)

bex/tag-preprocessor/nvim-reference/python.scm

@@ -0,0 +1,443 @@
+; From tree-sitter-python licensed under MIT License
+; Copyright (c) 2016 Max Brunsfeld
+; Variables
+(identifier) @variable
+
+; Reset highlighting in f-string interpolations
+(interpolation) @none
+
+; Identifier naming conventions
+((identifier) @type
+  (#lua-match? @type "^[A-Z].*[a-z]"))
+
+((identifier) @constant
+  (#lua-match? @constant "^[A-Z][A-Z_0-9]*$"))
+
+((identifier) @constant.builtin
+  (#lua-match? @constant.builtin "^__[a-zA-Z0-9_]*__$"))
+
+((identifier) @constant.builtin
+  (#any-of? @constant.builtin
+    ; https://docs.python.org/3/library/constants.html
+    "NotImplemented" "Ellipsis" "quit" "exit" "copyright" "credits" "license"))
+
+"_" @character.special ; match wildcard
+
+((assignment
+  left: (identifier) @type.definition
+  (type
+    (identifier) @_annotation))
+  (#eq? @_annotation "TypeAlias"))
+
+((assignment
+  left: (identifier) @type.definition
+  right: (call
+    function: (identifier) @_func))
+  (#any-of? @_func "TypeVar" "NewType"))
+
+; Function definitions
+(function_definition
+  name: (identifier) @function)
+
+(type
+  (identifier) @type)
+
+(type
+  (subscript
+    (identifier) @type)) ; type subscript: Tuple[int]
+
+((call
+  function: (identifier) @_isinstance
+  arguments: (argument_list
+    (_)
+    (identifier) @type))
+  (#eq? @_isinstance "isinstance"))
+
+; Literals
+(none) @constant.builtin
+
+[
+  (true)
+  (false)
+] @boolean
+
+(integer) @number
+
+(float) @number.float
+
+(comment) @comment @spell
+
+((module
+  .
+  (comment) @keyword.directive @nospell)
+  (#lua-match? @keyword.directive "^#!/"))
+
+(string) @string
+
+[
+  (escape_sequence)
+  (escape_interpolation)
+] @string.escape
+
+; doc-strings
+(expression_statement
+  (string
+    (string_content) @spell) @string.documentation)
+
+; Tokens
+[
+  "-"
+  "-="
+  ":="
+  "!="
+  "*"
+  "**"
+  "**="
+  "*="
+  "/"
+  "//"
+  "//="
+  "/="
+  "&"
+  "&="
+  "%"
+  "%="
+  "^"
+  "^="
+  "+"
+  "+="
+  "<"
+  "<<"
+  "<<="
+  "<="
+  "<>"
+  "="
+  "=="
+  ">"
+  ">="
+  ">>"
+  ">>="
+  "@"
+  "@="
+  "|"
+  "|="
+  "~"
+  "->"
+] @operator
+
+; Keywords
+[
+  "and"
+  "in"
+  "is"
+  "not"
+  "or"
+  "is not"
+  "not in"
+  "del"
+] @keyword.operator
+
+[
+  "def"
+  "lambda"
+] @keyword.function
+
+[
+  "assert"
+  "exec"
+  "global"
+  "nonlocal"
+  "pass"
+  "print"
+  "with"
+  "as"
+] @keyword
+
+[
+  "type"
+  "class"
+] @keyword.type
+
+[
+  "async"
+  "await"
+] @keyword.coroutine
+
+[
+  "return"
+  "yield"
+] @keyword.return
+
+(yield
+  "from" @keyword.return)
+
+(future_import_statement
+  "from" @keyword.import
+  "__future__" @module.builtin)
+
+(import_from_statement
+  "from" @keyword.import)
+
+"import" @keyword.import
+
+(aliased_import
+  "as" @keyword.import)
+
+(wildcard_import
+  "*" @character.special)
+
+(import_statement
+  name: (dotted_name
+    (identifier) @module))
+
+(import_statement
+  name: (aliased_import
+    name: (dotted_name
+      (identifier) @module)
+    alias: (identifier) @module))
+
+(import_from_statement
+  module_name: (dotted_name
+    (identifier) @module))
+
+(import_from_statement
+  module_name: (relative_import
+    (dotted_name
+      (identifier) @module)))
+
+[
+  "if"
+  "elif"
+  "else"
+  "match"
+  "case"
+] @keyword.conditional
+
+[
+  "for"
+  "while"
+  "break"
+  "continue"
+] @keyword.repeat
+
+[
+  "try"
+  "except"
+  "except*"
+  "raise"
+  "finally"
+] @keyword.exception
+
+(raise_statement
+  "from" @keyword.exception)
+
+(try_statement
+  (else_clause
+    "else" @keyword.exception))
+
+[
+  "("
+  ")"
+  "["
+  "]"
+  "{"
+  "}"
+] @punctuation.bracket
+
+(interpolation
+  "{" @punctuation.special
+  "}" @punctuation.special)
+
+(type_conversion) @function.macro
+
+[
+  ","
+  "."
+  ":"
+  ";"
+  (ellipsis)
+] @punctuation.delimiter
+
+((identifier) @type.builtin
+  (#any-of? @type.builtin
+    ; https://docs.python.org/3/library/exceptions.html
+    "BaseException" "Exception" "ArithmeticError" "BufferError" "LookupError" "AssertionError"
+    "AttributeError" "EOFError" "FloatingPointError" "GeneratorExit" "ImportError"
+    "ModuleNotFoundError" "IndexError" "KeyError" "KeyboardInterrupt" "MemoryError" "NameError"
+    "NotImplementedError" "OSError" "OverflowError" "RecursionError" "ReferenceError" "RuntimeError"
+    "StopIteration" "StopAsyncIteration" "SyntaxError" "IndentationError" "TabError" "SystemError"
+    "SystemExit" "TypeError" "UnboundLocalError" "UnicodeError" "UnicodeEncodeError"
+    "UnicodeDecodeError" "UnicodeTranslateError" "ValueError" "ZeroDivisionError" "EnvironmentError"
+    "IOError" "WindowsError" "BlockingIOError" "ChildProcessError" "ConnectionError"
+    "BrokenPipeError" "ConnectionAbortedError" "ConnectionRefusedError" "ConnectionResetError"
+    "FileExistsError" "FileNotFoundError" "InterruptedError" "IsADirectoryError"
+    "NotADirectoryError" "PermissionError" "ProcessLookupError" "TimeoutError" "Warning"
+    "UserWarning" "DeprecationWarning" "PendingDeprecationWarning" "SyntaxWarning" "RuntimeWarning"
+    "FutureWarning" "ImportWarning" "UnicodeWarning" "BytesWarning" "ResourceWarning"
+    ; https://docs.python.org/3/library/stdtypes.html
+    "bool" "int" "float" "complex" "list" "tuple" "range" "str" "bytes" "bytearray" "memoryview"
+    "set" "frozenset" "dict" "type" "object"))
+
+; Normal parameters
+(parameters
+  (identifier) @variable.parameter)
+
+; Lambda parameters
+(lambda_parameters
+  (identifier) @variable.parameter)
+
+(lambda_parameters
+  (tuple_pattern
+    (identifier) @variable.parameter))
+
+; Default parameters
+(keyword_argument
+  name: (identifier) @variable.parameter)
+
+; Naming parameters on call-site
+(default_parameter
+  name: (identifier) @variable.parameter)
+
+(typed_parameter
+  (identifier) @variable.parameter)
+
+(typed_default_parameter
+  name: (identifier) @variable.parameter)
+
+; Variadic parameters *args, **kwargs
+(parameters
+  (list_splat_pattern ; *args
+    (identifier) @variable.parameter))
+
+(parameters
+  (dictionary_splat_pattern ; **kwargs
+    (identifier) @variable.parameter))
+
+; Typed variadic parameters
+(parameters
+  (typed_parameter
+    (list_splat_pattern ; *args: type
+      (identifier) @variable.parameter)))
+
+(parameters
+  (typed_parameter
+    (dictionary_splat_pattern ; *kwargs: type
+      (identifier) @variable.parameter)))
+
+; Lambda parameters
+(lambda_parameters
+  (list_splat_pattern
+    (identifier) @variable.parameter))
+
+(lambda_parameters
+  (dictionary_splat_pattern
+    (identifier) @variable.parameter))
+
+((identifier) @variable.builtin
+  (#eq? @variable.builtin "self"))
+
+((identifier) @variable.builtin
+  (#eq? @variable.builtin "cls"))
+
+; After @type.builtin bacause builtins (such as `type`) are valid as attribute name
+((attribute
+  attribute: (identifier) @variable.member)
+  (#lua-match? @variable.member "^[%l_].*$"))
+
+; Class definitions
+(class_definition
+  name: (identifier) @type)
+
+(class_definition
+  body: (block
+    (function_definition
+      name: (identifier) @function.method)))
+
+(class_definition
+  superclasses: (argument_list
+    (identifier) @type))
+
+((class_definition
+  body: (block
+    (expression_statement
+      (assignment
+        left: (identifier) @variable.member))))
+  (#lua-match? @variable.member "^[%l_].*$"))
+
+((class_definition
+  body: (block
+    (expression_statement
+      (assignment
+        left: (_
+          (identifier) @variable.member)))))
+  (#lua-match? @variable.member "^[%l_].*$"))
+
+((class_definition
+  (block
+    (function_definition
+      name: (identifier) @constructor)))
+  (#any-of? @constructor "__new__" "__init__"))
+
+; Function calls
+(call
+  function: (identifier) @function.call)
+
+(call
+  function: (attribute
+    attribute: (identifier) @function.method.call))
+
+((call
+  function: (identifier) @constructor)
+  (#lua-match? @constructor "^%u"))
+
+((call
+  function: (attribute
+    attribute: (identifier) @constructor))
+  (#lua-match? @constructor "^%u"))
+
+; Builtin functions
+((call
+  function: (identifier) @function.builtin)
+  (#any-of? @function.builtin
+    "abs" "all" "any" "ascii" "bin" "bool" "breakpoint" "bytearray" "bytes" "callable" "chr"
+    "classmethod" "compile" "complex" "delattr" "dict" "dir" "divmod" "enumerate" "eval" "exec"
+    "filter" "float" "format" "frozenset" "getattr" "globals" "hasattr" "hash" "help" "hex" "id"
+    "input" "int" "isinstance" "issubclass" "iter" "len" "list" "locals" "map" "max" "memoryview"
+    "min" "next" "object" "oct" "open" "ord" "pow" "print" "property" "range" "repr" "reversed"
+    "round" "set" "setattr" "slice" "sorted" "staticmethod" "str" "sum" "super" "tuple" "type"
+    "vars" "zip" "__import__"))
+
+; Regex from the `re` module
+(call
+  function: (attribute
+    object: (identifier) @_re)
+  arguments: (argument_list
+    .
+    (string
+      (string_content) @string.regexp))
+  (#eq? @_re "re"))
+
+; Decorators
+((decorator
+  "@" @attribute)
+  (#set! priority 101))
+
+(decorator
+  (identifier) @attribute)
+
+(decorator
+  (attribute
+    attribute: (identifier) @attribute))
+
+(decorator
+  (call
+    (identifier) @attribute))
+
+(decorator
+  (call
+    (attribute
+      attribute: (identifier) @attribute)))
+
+((decorator
+  (identifier) @attribute.builtin)
+  (#any-of? @attribute.builtin "classmethod" "property" "staticmethod"))

bex/tag-preprocessor/nvim-reference/ruby.scm

@@ -0,0 +1,309 @@
+; Variables
+[
+  (identifier)
+  (global_variable)
+] @variable
+
+; Keywords
+[
+  "alias"
+  "begin"
+  "do"
+  "end"
+  "ensure"
+  "module"
+  "rescue"
+  "then"
+] @keyword
+
+"class" @keyword.type
+
+[
+  "return"
+  "yield"
+] @keyword.return
+
+[
+  "and"
+  "or"
+  "in"
+  "not"
+] @keyword.operator
+
+[
+  "def"
+  "undef"
+] @keyword.function
+
+(method
+  "end" @keyword.function)
+
+[
+  "case"
+  "else"
+  "elsif"
+  "if"
+  "unless"
+  "when"
+  "then"
+] @keyword.conditional
+
+(if
+  "end" @keyword.conditional)
+
+[
+  "for"
+  "until"
+  "while"
+  "break"
+  "redo"
+  "retry"
+  "next"
+] @keyword.repeat
+
+(constant) @constant
+
+((identifier) @keyword.modifier
+  (#any-of? @keyword.modifier "private" "protected" "public"))
+
+[
+  "rescue"
+  "ensure"
+] @keyword.exception
+
+; Function calls
+"defined?" @function
+
+(call
+  receiver: (constant)? @type
+  method: [
+    (identifier)
+    (constant)
+  ] @function.call)
+
+(program
+  (call
+    (identifier) @keyword.import)
+  (#any-of? @keyword.import "require" "require_relative" "load"))
+
+; Function definitions
+(alias
+  (identifier) @function)
+
+(setter
+  (identifier) @function)
+
+(method
+  name: [
+    (identifier) @function
+    (constant) @type
+  ])
+
+(singleton_method
+  name: [
+    (identifier) @function
+    (constant) @type
+  ])
+
+(class
+  name: (constant) @type)
+
+(module
+  name: (constant) @type)
+
+(superclass
+  (constant) @type)
+
+; Identifiers
+[
+  (class_variable)
+  (instance_variable)
+] @variable.member
+
+((identifier) @constant.builtin
+  (#any-of? @constant.builtin
+    "__callee__" "__dir__" "__id__" "__method__" "__send__" "__ENCODING__" "__FILE__" "__LINE__"))
+
+((identifier) @function.builtin
+  (#any-of? @function.builtin "attr_reader" "attr_writer" "attr_accessor" "module_function"))
+
+((call
+  !receiver
+  method: (identifier) @function.builtin)
+  (#any-of? @function.builtin "include" "extend" "prepend" "refine" "using"))
+
+((identifier) @keyword.exception
+  (#any-of? @keyword.exception "raise" "fail" "catch" "throw"))
+
+((constant) @type
+  (#not-lua-match? @type "^[A-Z0-9_]+$"))
+
+[
+  (self)
+  (super)
+] @variable.builtin
+
+(method_parameters
+  (identifier) @variable.parameter)
+
+(lambda_parameters
+  (identifier) @variable.parameter)
+
+(block_parameters
+  (identifier) @variable.parameter)
+
+(splat_parameter
+  (identifier) @variable.parameter)
+
+(hash_splat_parameter
+  (identifier) @variable.parameter)
+
+(optional_parameter
+  (identifier) @variable.parameter)
+
+(destructured_parameter
+  (identifier) @variable.parameter)
+
+(block_parameter
+  (identifier) @variable.parameter)
+
+(keyword_parameter
+  (identifier) @variable.parameter)
+
+; TODO: Re-enable this once it is supported
+; ((identifier) @function
+;  (#is-not? local))
+; Literals
+[
+  (string_content)
+  (heredoc_content)
+  "\""
+  "`"
+] @string
+
+[
+  (heredoc_beginning)
+  (heredoc_end)
+] @label
+
+[
+  (bare_symbol)
+  (simple_symbol)
+  (delimited_symbol)
+  (hash_key_symbol)
+] @string.special.symbol
+
+(regex
+  (string_content) @string.regexp)
+
+(escape_sequence) @string.escape
+
+(integer) @number
+
+(float) @number.float
+
+[
+  (true)
+  (false)
+] @boolean
+
+(nil) @constant.builtin
+
+(comment) @comment @spell
+
+((program
+  .
+  (comment) @keyword.directive @nospell)
+  (#lua-match? @keyword.directive "^#!/"))
+
+(program
+  (comment)+ @comment.documentation
+  (class))
+
+(module
+  (comment)+ @comment.documentation
+  (body_statement
+    (class)))
+
+(class
+  (comment)+ @comment.documentation
+  (body_statement
+    (method)))
+
+(body_statement
+  (comment)+ @comment.documentation
+  (method))
+
+; Operators
+[
+  "!"
+  "="
+  "=="
+  "==="
+  "<=>"
+  "=>"
+  "->"
+  ">>"
+  "<<"
+  ">"
+  "<"
+  ">="
+  "<="
+  "**"
+  "*"
+  "/"
+  "%"
+  "+"
+  "-"
+  "&"
+  "|"
+  "^"
+  "&&"
+  "||"
+  "||="
+  "&&="
+  "!="
+  "%="
+  "+="
+  "-="
+  "*="
+  "/="
+  "=~"
+  "!~"
+  "?"
+  ":"
+  ".."
+  "..."
+] @operator
+
+[
+  ","
+  ";"
+  "."
+  "&."
+  "::"
+] @punctuation.delimiter
+
+(regex
+  "/" @punctuation.bracket)
+
+(pair
+  ":" @punctuation.delimiter)
+
+[
+  "("
+  ")"
+  "["
+  "]"
+  "{"
+  "}"
+  "%w("
+  "%i("
+] @punctuation.bracket
+
+(block_parameters
+  "|" @punctuation.bracket)
+
+(interpolation
+  "#{" @punctuation.special
+  "}" @punctuation.special)

bex/tag-preprocessor/nvim-reference/rust.scm

@@ -0,0 +1,531 @@
+; Forked from https://github.com/tree-sitter/tree-sitter-rust
+; Copyright (c) 2017 Maxim Sokolov
+; Licensed under the MIT license.
+; Identifier conventions
+(shebang) @keyword.directive
+
+(identifier) @variable
+
+((identifier) @type
+  (#lua-match? @type "^[A-Z]"))
+
+(const_item
+  name: (identifier) @constant)
+
+; Assume all-caps names are constants
+((identifier) @constant
+  (#lua-match? @constant "^[A-Z][A-Z%d_]*$"))
+
+; Other identifiers
+(type_identifier) @type
+
+(primitive_type) @type.builtin
+
+(field_identifier) @variable.member
+
+(shorthand_field_identifier) @variable.member
+
+(shorthand_field_initializer
+  (identifier) @variable.member)
+
+(mod_item
+  name: (identifier) @module)
+
+(self) @variable.builtin
+
+"_" @character.special
+
+(label
+  [
+    "'"
+    (identifier)
+  ] @label)
+
+; Function definitions
+(function_item
+  (identifier) @function)
+
+(function_signature_item
+  (identifier) @function)
+
+(parameter
+  [
+    (identifier)
+    "_"
+  ] @variable.parameter)
+
+(parameter
+  (ref_pattern
+    [
+      (mut_pattern
+        (identifier) @variable.parameter)
+      (identifier) @variable.parameter
+    ]))
+
+(closure_parameters
+  (_) @variable.parameter)
+
+; Function calls
+(call_expression
+  function: (identifier) @function.call)
+
+(call_expression
+  function: (scoped_identifier
+    (identifier) @function.call .))
+
+(call_expression
+  function: (field_expression
+    field: (field_identifier) @function.call))
+
+(generic_function
+  function: (identifier) @function.call)
+
+(generic_function
+  function: (scoped_identifier
+    name: (identifier) @function.call))
+
+(generic_function
+  function: (field_expression
+    field: (field_identifier) @function.call))
+
+; Assume other uppercase names are enum constructors
+((field_identifier) @constant
+  (#lua-match? @constant "^[A-Z]"))
+
+(enum_variant
+  name: (identifier) @constant)
+
+; Assume that uppercase names in paths are types
+(scoped_identifier
+  path: (identifier) @module)
+
+(scoped_identifier
+  (scoped_identifier
+    name: (identifier) @module))
+
+(scoped_type_identifier
+  path: (identifier) @module)
+
+(scoped_type_identifier
+  path: (identifier) @type
+  (#lua-match? @type "^[A-Z]"))
+
+(scoped_type_identifier
+  (scoped_identifier
+    name: (identifier) @module))
+
+((scoped_identifier
+  path: (identifier) @type)
+  (#lua-match? @type "^[A-Z]"))
+
+((scoped_identifier
+  name: (identifier) @type)
+  (#lua-match? @type "^[A-Z]"))
+
+((scoped_identifier
+  name: (identifier) @constant)
+  (#lua-match? @constant "^[A-Z][A-Z%d_]*$"))
+
+((scoped_identifier
+  path: (identifier) @type
+  name: (identifier) @constant)
+  (#lua-match? @type "^[A-Z]")
+  (#lua-match? @constant "^[A-Z]"))
+
+((scoped_type_identifier
+  path: (identifier) @type
+  name: (type_identifier) @constant)
+  (#lua-match? @type "^[A-Z]")
+  (#lua-match? @constant "^[A-Z]"))
+
+[
+  (crate)
+  (super)
+] @module
+
+(scoped_use_list
+  path: (identifier) @module)
+
+(scoped_use_list
+  path: (scoped_identifier
+    (identifier) @module))
+
+(use_list
+  (scoped_identifier
+    (identifier) @module
+    .
+    (_)))
+
+(use_list
+  (identifier) @type
+  (#lua-match? @type "^[A-Z]"))
+
+(use_as_clause
+  alias: (identifier) @type
+  (#lua-match? @type "^[A-Z]"))
+
+; Correct enum constructors
+(call_expression
+  function: (scoped_identifier
+    "::"
+    name: (identifier) @constant)
+  (#lua-match? @constant "^[A-Z]"))
+
+; Assume uppercase names in a match arm are constants.
+((match_arm
+  pattern: (match_pattern
+    (identifier) @constant))
+  (#lua-match? @constant "^[A-Z]"))
+
+((match_arm
+  pattern: (match_pattern
+    (scoped_identifier
+      name: (identifier) @constant)))
+  (#lua-match? @constant "^[A-Z]"))
+
+((identifier) @constant.builtin
+  (#any-of? @constant.builtin "Some" "None" "Ok" "Err"))
+
+; Macro definitions
+"$" @function.macro
+
+(metavariable) @function.macro
+
+(macro_definition
+  "macro_rules!" @function.macro)
+
+; Attribute macros
+(attribute_item
+  (attribute
+    (identifier) @function.macro))
+
+(inner_attribute_item
+  (attribute
+    (identifier) @function.macro))
+
+(attribute
+  (scoped_identifier
+    (identifier) @function.macro .))
+
+; Derive macros (assume all arguments are types)
+; (attribute
+;   (identifier) @_name
+;   arguments: (attribute (attribute (identifier) @type))
+;   (#eq? @_name "derive"))
+; Function-like macros
+(macro_invocation
+  macro: (identifier) @function.macro)
+
+(macro_invocation
+  macro: (scoped_identifier
+    (identifier) @function.macro .))
+
+; Literals
+(boolean_literal) @boolean
+
+(integer_literal) @number
+
+(float_literal) @number.float
+
+[
+  (raw_string_literal)
+  (string_literal)
+] @string
+
+(escape_sequence) @string.escape
+
+(char_literal) @character
+
+; Keywords
+[
+  "use"
+  "mod"
+] @keyword.import
+
+(use_as_clause
+  "as" @keyword.import)
+
+[
+  "default"
+  "impl"
+  "let"
+  "move"
+  "unsafe"
+  "where"
+] @keyword
+
+[
+  "enum"
+  "struct"
+  "union"
+  "trait"
+  "type"
+] @keyword.type
+
+[
+  "async"
+  "await"
+  "gen"
+] @keyword.coroutine
+
+"try" @keyword.exception
+
+[
+  "ref"
+  "pub"
+  "raw"
+  (mutable_specifier)
+  "const"
+  "static"
+  "dyn"
+  "extern"
+] @keyword.modifier
+
+(lifetime
+  "'" @keyword.modifier)
+
+(lifetime
+  (identifier) @attribute)
+
+(lifetime
+  (identifier) @attribute.builtin
+  (#any-of? @attribute.builtin "static" "_"))
+
+"fn" @keyword.function
+
+[
+  "return"
+  "yield"
+] @keyword.return
+
+(type_cast_expression
+  "as" @keyword.operator)
+
+(qualified_type
+  "as" @keyword.operator)
+
+(use_list
+  (self) @module)
+
+(scoped_use_list
+  (self) @module)
+
+(scoped_identifier
+  [
+    (crate)
+    (super)
+    (self)
+  ] @module)
+
+(visibility_modifier
+  [
+    (crate)
+    (super)
+    (self)
+  ] @module)
+
+[
+  "if"
+  "else"
+  "match"
+] @keyword.conditional
+
+[
+  "break"
+  "continue"
+  "in"
+  "loop"
+  "while"
+] @keyword.repeat
+
+"for" @keyword
+
+(for_expression
+  "for" @keyword.repeat)
+
+; Operators
+[
+  "!"
+  "!="
+  "%"
+  "%="
+  "&"
+  "&&"
+  "&="
+  "*"
+  "*="
+  "+"
+  "+="
+  "-"
+  "-="
+  ".."
+  "..="
+  "..."
+  "/"
+  "/="
+  "<"
+  "<<"
+  "<<="
+  "<="
+  "="
+  "=="
+  ">"
+  ">="
+  ">>"
+  ">>="
+  "?"
+  "@"
+  "^"
+  "^="
+  "|"
+  "|="
+  "||"
+] @operator
+
+(use_wildcard
+  "*" @character.special)
+
+(remaining_field_pattern
+  ".." @character.special)
+
+(range_pattern
+  [
+    ".."
+    "..="
+    "..."
+  ] @character.special)
+
+; Punctuation
+[
+  "("
+  ")"
+  "["
+  "]"
+  "{"
+  "}"
+] @punctuation.bracket
+
+(closure_parameters
+  "|" @punctuation.bracket)
+
+(type_arguments
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(type_parameters
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(bracketed_type
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(for_lifetimes
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+[
+  ","
+  "."
+  ":"
+  "::"
+  ";"
+  "->"
+  "=>"
+] @punctuation.delimiter
+
+(attribute_item
+  "#" @punctuation.special)
+
+(inner_attribute_item
+  [
+    "!"
+    "#"
+  ] @punctuation.special)
+
+(macro_invocation
+  "!" @function.macro)
+
+(never_type
+  "!" @type.builtin)
+
+(macro_invocation
+  macro: (identifier) @_identifier @keyword.exception
+  "!" @keyword.exception
+  (#eq? @_identifier "panic"))
+
+(macro_invocation
+  macro: (identifier) @_identifier @keyword.exception
+  "!" @keyword.exception
+  (#contains? @_identifier "assert"))
+
+(macro_invocation
+  macro: (identifier) @_identifier @keyword.debug
+  "!" @keyword.debug
+  (#eq? @_identifier "dbg"))
+
+; Comments
+[
+  (line_comment)
+  (block_comment)
+  (outer_doc_comment_marker)
+  (inner_doc_comment_marker)
+] @comment @spell
+
+(line_comment
+  (doc_comment)) @comment.documentation
+
+(block_comment
+  (doc_comment)) @comment.documentation
+
+(call_expression
+  function: (scoped_identifier
+    path: (identifier) @_regex
+    (#any-of? @_regex "Regex" "ByteRegexBuilder")
+    name: (identifier) @_new
+    (#eq? @_new "new"))
+  arguments: (arguments
+    (raw_string_literal
+      (string_content) @string.regexp)))
+
+(call_expression
+  function: (scoped_identifier
+    path: (scoped_identifier
+      (identifier) @_regex
+      (#any-of? @_regex "Regex" "ByteRegexBuilder") .)
+    name: (identifier) @_new
+    (#eq? @_new "new"))
+  arguments: (arguments
+    (raw_string_literal
+      (string_content) @string.regexp)))
+
+(call_expression
+  function: (scoped_identifier
+    path: (identifier) @_regex
+    (#any-of? @_regex "RegexSet" "RegexSetBuilder")
+    name: (identifier) @_new
+    (#eq? @_new "new"))
+  arguments: (arguments
+    (array_expression
+      (raw_string_literal
+        (string_content) @string.regexp))))
+
+(call_expression
+  function: (scoped_identifier
+    path: (scoped_identifier
+      (identifier) @_regex
+      (#any-of? @_regex "RegexSet" "RegexSetBuilder") .)
+    name: (identifier) @_new
+    (#eq? @_new "new"))
+  arguments: (arguments
+    (array_expression
+      (raw_string_literal
+        (string_content) @string.regexp))))

bex/tag-preprocessor/nvim-reference/typescript.scm

@@ -0,0 +1,208 @@
+; inherits: ecma
+
+"require" @keyword.import
+
+(import_require_clause
+  source: (string) @string.special.url)
+
+[
+  "declare"
+  "implements"
+  "type"
+  "override"
+  "module"
+  "asserts"
+  "infer"
+  "is"
+  "using"
+] @keyword
+
+[
+  "namespace"
+  "interface"
+  "enum"
+] @keyword.type
+
+[
+  "keyof"
+  "satisfies"
+] @keyword.operator
+
+(as_expression
+  "as" @keyword.operator)
+
+(mapped_type_clause
+  "as" @keyword.operator)
+
+[
+  "abstract"
+  "private"
+  "protected"
+  "public"
+  "readonly"
+] @keyword.modifier
+
+; types
+(type_identifier) @type
+
+(predefined_type) @type.builtin
+
+(import_statement
+  "type"
+  (import_clause
+    (named_imports
+      (import_specifier
+        name: (identifier) @type))))
+
+(template_literal_type) @string
+
+(non_null_expression
+  "!" @operator)
+
+; punctuation
+(type_arguments
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(type_parameters
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(object_type
+  [
+    "{|"
+    "|}"
+  ] @punctuation.bracket)
+
+(union_type
+  "|" @punctuation.delimiter)
+
+(intersection_type
+  "&" @punctuation.delimiter)
+
+(type_annotation
+  ":" @punctuation.delimiter)
+
+(type_predicate_annotation
+  ":" @punctuation.delimiter)
+
+(index_signature
+  ":" @punctuation.delimiter)
+
+(omitting_type_annotation
+  "-?:" @punctuation.delimiter)
+
+(adding_type_annotation
+  "+?:" @punctuation.delimiter)
+
+(opting_type_annotation
+  "?:" @punctuation.delimiter)
+
+"?." @punctuation.delimiter
+
+(abstract_method_signature
+  "?" @punctuation.special)
+
+(method_signature
+  "?" @punctuation.special)
+
+(method_definition
+  "?" @punctuation.special)
+
+(property_signature
+  "?" @punctuation.special)
+
+(optional_parameter
+  "?" @punctuation.special)
+
+(optional_type
+  "?" @punctuation.special)
+
+(public_field_definition
+  [
+    "?"
+    "!"
+  ] @punctuation.special)
+
+(flow_maybe_type
+  "?" @punctuation.special)
+
+(template_type
+  [
+    "${"
+    "}"
+  ] @punctuation.special)
+
+(conditional_type
+  [
+    "?"
+    ":"
+  ] @keyword.conditional.ternary)
+
+; Parameters
+(required_parameter
+  pattern: (identifier) @variable.parameter)
+
+(optional_parameter
+  pattern: (identifier) @variable.parameter)
+
+(required_parameter
+  (rest_pattern
+    (identifier) @variable.parameter))
+
+; ({ a }) => null
+(required_parameter
+  (object_pattern
+    (shorthand_property_identifier_pattern) @variable.parameter))
+
+; ({ a = b }) => null
+(required_parameter
+  (object_pattern
+    (object_assignment_pattern
+      (shorthand_property_identifier_pattern) @variable.parameter)))
+
+; ({ a: b }) => null
+(required_parameter
+  (object_pattern
+    (pair_pattern
+      value: (identifier) @variable.parameter)))
+
+; ([ a ]) => null
+(required_parameter
+  (array_pattern
+    (identifier) @variable.parameter))
+
+; a => null
+(arrow_function
+  parameter: (identifier) @variable.parameter)
+
+; global declaration
+(ambient_declaration
+  "global" @module)
+
+; function signatures
+(ambient_declaration
+  (function_signature
+    name: (identifier) @function))
+
+; method signatures
+(method_signature
+  name: (_) @function.method)
+
+(abstract_method_signature
+  name: (property_identifier) @function.method)
+
+; property signatures
+(property_signature
+  name: (property_identifier) @function.method
+  type: (type_annotation
+    [
+      (union_type
+        (parenthesized_type
+          (function_type)))
+      (function_type)
+    ]))

bex/tag-preprocessor/queries/c.scm

@@ -0,0 +1,341 @@
+; Lower priority to prefer @variable.parameter when identifier appears in parameter_declaration.
+((identifier) @variable
+  (#set! priority 95))
+
+(preproc_def
+  (preproc_arg) @variable)
+
+[
+  "default"
+  "goto"
+  "asm"
+  "__asm__"
+] @keyword
+
+[
+  "enum"
+  "struct"
+  "union"
+  "typedef"
+] @keyword.type
+
+[
+  "sizeof"
+  "offsetof"
+] @keyword.operator
+
+(alignof_expression
+  .
+  _ @keyword.operator)
+
+"return" @keyword.return
+
+[
+  "while"
+  "for"
+  "do"
+  "continue"
+  "break"
+] @keyword.repeat
+
+[
+  "if"
+  "else"
+  "case"
+  "switch"
+] @keyword.conditional
+
+[
+  "#if"
+  "#ifdef"
+  "#ifndef"
+  "#else"
+  "#elif"
+  "#endif"
+  "#elifdef"
+  "#elifndef"
+  (preproc_directive)
+] @keyword.directive
+
+"#define" @keyword.directive.define
+
+"#include" @keyword.import
+
+[
+  ";"
+  ":"
+  ","
+  "."
+  "::"
+] @punctuation.delimiter
+
+"..." @punctuation.special
+
+[
+  "("
+  ")"
+  "["
+  "]"
+  "{"
+  "}"
+] @punctuation.bracket
+
+[
+  "="
+  "-"
+  "*"
+  "/"
+  "+"
+  "%"
+  "~"
+  "|"
+  "&"
+  "^"
+  "<<"
+  ">>"
+  "->"
+  "<"
+  "<="
+  ">="
+  ">"
+  "=="
+  "!="
+  "!"
+  "&&"
+  "||"
+  "-="
+  "+="
+  "*="
+  "/="
+  "%="
+  "|="
+  "&="
+  "^="
+  ">>="
+  "<<="
+  "--"
+  "++"
+] @operator
+
+; Make sure the comma operator is given a highlight group after the comma
+; punctuator so the operator is highlighted properly.
+(comma_expression
+  "," @operator)
+
+[
+  (true)
+  (false)
+] @boolean
+
+(conditional_expression
+  [
+    "?"
+    ":"
+  ] @keyword.conditional.ternary)
+
+(string_literal) @string
+
+(system_lib_string) @string
+
+(escape_sequence) @string.escape
+
+(null) @constant.builtin
+
+(number_literal) @number
+
+(char_literal) @character
+
+(preproc_defined) @function.macro
+
+((field_expression
+  (field_identifier) @property) @_parent
+  (#not-has-parent? @_parent function_declarator call_expression))
+
+(field_designator) @property
+
+((field_identifier) @property
+  (#has-ancestor? @property field_declaration)
+  (#not-has-ancestor? @property function_declarator))
+
+(statement_identifier) @label
+
+(declaration
+  type: (type_identifier) @_type
+  declarator: (identifier) @label
+  (#eq? @_type "__label__"))
+
+[
+  (type_identifier)
+  (type_descriptor)
+] @type
+
+(storage_class_specifier) @keyword.modifier
+
+[
+  (type_qualifier)
+  (gnu_asm_qualifier)
+  "__extension__"
+] @keyword.modifier
+
+(linkage_specification
+  "extern" @keyword.modifier)
+
+(type_definition
+  declarator: (type_identifier) @type.definition)
+
+(primitive_type) @type.builtin
+
+(sized_type_specifier
+  _ @type.builtin
+  type: _?)
+
+((identifier) @constant
+  (#lua-match? @constant "^[A-Z][A-Z0-9_]+$"))
+
+(preproc_def
+  (preproc_arg) @constant
+  (#lua-match? @constant "^[A-Z][A-Z0-9_]+$"))
+
+(enumerator
+  name: (identifier) @constant)
+
+(case_statement
+  value: (identifier) @constant)
+
+((identifier) @constant.builtin
+  ; format-ignore
+  (#any-of? @constant.builtin
+    "stderr" "stdin" "stdout"
+    "__FILE__" "__LINE__" "__DATE__" "__TIME__"
+    "__STDC__" "__STDC_VERSION__" "__STDC_HOSTED__"
+    "__cplusplus" "__OBJC__" "__ASSEMBLER__"
+    "__BASE_FILE__" "__FILE_NAME__" "__INCLUDE_LEVEL__"
+    "__TIMESTAMP__" "__clang__" "__clang_major__"
+    "__clang_minor__" "__clang_patchlevel__"
+    "__clang_version__" "__clang_literal_encoding__"
+    "__clang_wide_literal_encoding__"
+    "__FUNCTION__" "__func__" "__PRETTY_FUNCTION__"
+    "__VA_ARGS__" "__VA_OPT__"))
+
+(preproc_def
+  (preproc_arg) @constant.builtin
+  ; format-ignore
+  (#any-of? @constant.builtin
+    "stderr" "stdin" "stdout"
+    "__FILE__" "__LINE__" "__DATE__" "__TIME__"
+    "__STDC__" "__STDC_VERSION__" "__STDC_HOSTED__"
+    "__cplusplus" "__OBJC__" "__ASSEMBLER__"
+    "__BASE_FILE__" "__FILE_NAME__" "__INCLUDE_LEVEL__"
+    "__TIMESTAMP__" "__clang__" "__clang_major__"
+    "__clang_minor__" "__clang_patchlevel__"
+    "__clang_version__" "__clang_literal_encoding__"
+    "__clang_wide_literal_encoding__"
+    "__FUNCTION__" "__func__" "__PRETTY_FUNCTION__"
+    "__VA_ARGS__" "__VA_OPT__"))
+
+(attribute_specifier
+  (argument_list
+    (identifier) @variable.builtin))
+
+(attribute_specifier
+  (argument_list
+    (call_expression
+      function: (identifier) @variable.builtin)))
+
+((call_expression
+  function: (identifier) @function.builtin)
+  (#lua-match? @function.builtin "^__builtin_"))
+
+((call_expression
+  function: (identifier) @function.builtin)
+  (#has-ancestor? @function.builtin attribute_specifier))
+
+; Preproc def / undef
+(preproc_def
+  name: (_) @constant.macro)
+
+(preproc_call
+  directive: (preproc_directive) @_u
+  argument: (_) @constant.macro
+  (#eq? @_u "#undef"))
+
+(preproc_ifdef
+  name: (identifier) @constant.macro)
+
+(preproc_elifdef
+  name: (identifier) @constant.macro)
+
+(preproc_defined
+  (identifier) @constant.macro)
+
+(call_expression
+  function: (identifier) @function.call)
+
+(call_expression
+  function: (field_expression
+    field: (field_identifier) @function.call))
+
+(function_declarator
+  declarator: (identifier) @function)
+
+(function_declarator
+  declarator: (parenthesized_declarator
+    (pointer_declarator
+      declarator: (field_identifier) @function)))
+
+(preproc_function_def
+  name: (identifier) @function.macro)
+
+(comment) @comment @spell
+
+((comment) @comment.documentation
+  (#lua-match? @comment.documentation "^/[*][*][^*].*[*]/$"))
+
+; Parameters
+(parameter_declaration
+  declarator: (identifier) @variable.parameter)
+
+(parameter_declaration
+  declarator: (array_declarator) @variable.parameter)
+
+(parameter_declaration
+  declarator: (pointer_declarator) @variable.parameter)
+
+; K&R functions
+; To enable support for K&R functions,
+; add the following lines to your own query config and uncomment them.
+; They are commented out as they'll conflict with C++
+; Note that you'll need to have `; extends` at the top of your query file.
+;
+; (parameter_list (identifier) @variable.parameter)
+;
+; (function_definition
+;   declarator: _
+;   (declaration
+;     declarator: (identifier) @variable.parameter))
+;
+; (function_definition
+;   declarator: _
+;   (declaration
+;     declarator: (array_declarator) @variable.parameter))
+;
+; (function_definition
+;   declarator: _
+;   (declaration
+;     declarator: (pointer_declarator) @variable.parameter))
+(preproc_params
+  (identifier) @variable.parameter)
+
+[
+  "__attribute__"
+  "__declspec"
+  "__based"
+  "__cdecl"
+  "__clrcall"
+  "__stdcall"
+  "__fastcall"
+  "__thiscall"
+  "__vectorcall"
+  (ms_pointer_modifier)
+  (attribute_declaration)
+] @attribute

bex/tag-preprocessor/queries/cpp.scm

@@ -0,0 +1,273 @@
+; inherits: c
+
+((identifier) @variable.member
+  (#lua-match? @variable.member "^m_.*$"))
+
+(parameter_declaration
+  declarator: (reference_declarator) @variable.parameter)
+
+; function(Foo ...foo)
+(variadic_parameter_declaration
+  declarator: (variadic_declarator
+    (_) @variable.parameter))
+
+; int foo = 0
+(optional_parameter_declaration
+  declarator: (_) @variable.parameter)
+
+;(field_expression) @variable.parameter ;; How to highlight this?
+((field_expression
+  (field_identifier) @function.method) @_parent
+  (#has-parent? @_parent template_method function_declarator))
+
+(field_declaration
+  (field_identifier) @variable.member)
+
+(field_initializer
+  (field_identifier) @property)
+
+(function_declarator
+  declarator: (field_identifier) @function.method)
+
+(concept_definition
+  name: (identifier) @type.definition)
+
+(alias_declaration
+  name: (type_identifier) @type.definition)
+
+(auto) @type.builtin
+
+(namespace_identifier) @module
+
+((namespace_identifier) @type
+  (#lua-match? @type "^[%u]"))
+
+(case_statement
+  value: (qualified_identifier
+    (identifier) @constant))
+
+(using_declaration
+  .
+  "using"
+  .
+  "namespace"
+  .
+  [
+    (qualified_identifier)
+    (identifier)
+  ] @module)
+
+(destructor_name
+  (identifier) @function.method)
+
+; functions
+(function_declarator
+  (qualified_identifier
+    (identifier) @function))
+
+(function_declarator
+  (qualified_identifier
+    (qualified_identifier
+      (identifier) @function)))
+
+(function_declarator
+  (qualified_identifier
+    (qualified_identifier
+      (qualified_identifier
+        (identifier) @function))))
+
+((qualified_identifier
+  (qualified_identifier
+    (qualified_identifier
+      (qualified_identifier
+        (identifier) @function)))) @_parent
+  (#has-ancestor? @_parent function_declarator))
+
+(function_declarator
+  (template_function
+    (identifier) @function))
+
+(operator_name) @function
+
+"operator" @function
+
+"static_assert" @function.builtin
+
+(call_expression
+  (qualified_identifier
+    (identifier) @function.call))
+
+(call_expression
+  (qualified_identifier
+    (qualified_identifier
+      (identifier) @function.call)))
+
+(call_expression
+  (qualified_identifier
+    (qualified_identifier
+      (qualified_identifier
+        (identifier) @function.call))))
+
+((qualified_identifier
+  (qualified_identifier
+    (qualified_identifier
+      (qualified_identifier
+        (identifier) @function.call)))) @_parent
+  (#has-ancestor? @_parent call_expression))
+
+(call_expression
+  (template_function
+    (identifier) @function.call))
+
+(call_expression
+  (qualified_identifier
+    (template_function
+      (identifier) @function.call)))
+
+(call_expression
+  (qualified_identifier
+    (qualified_identifier
+      (template_function
+        (identifier) @function.call))))
+
+(call_expression
+  (qualified_identifier
+    (qualified_identifier
+      (qualified_identifier
+        (template_function
+          (identifier) @function.call)))))
+
+((qualified_identifier
+  (qualified_identifier
+    (qualified_identifier
+      (qualified_identifier
+        (template_function
+          (identifier) @function.call))))) @_parent
+  (#has-ancestor? @_parent call_expression))
+
+; methods
+(function_declarator
+  (template_method
+    (field_identifier) @function.method))
+
+(call_expression
+  (field_expression
+    (field_identifier) @function.method.call))
+
+(call_expression
+  (field_expression
+    (template_method
+      (field_identifier) @function.method.call)))
+
+; constructors
+((function_declarator
+  (qualified_identifier
+    (identifier) @constructor))
+  (#lua-match? @constructor "^%u"))
+
+((call_expression
+  function: (identifier) @constructor)
+  (#lua-match? @constructor "^%u"))
+
+((call_expression
+  function: (qualified_identifier
+    name: (identifier) @constructor))
+  (#lua-match? @constructor "^%u"))
+
+((call_expression
+  function: (field_expression
+    field: (field_identifier) @constructor))
+  (#lua-match? @constructor "^%u"))
+
+; constructing a type in an initializer list: Constructor ():  **SuperType (1)**
+((field_initializer
+  (field_identifier) @constructor
+  (argument_list))
+  (#lua-match? @constructor "^%u"))
+
+; Constants
+(this) @variable.builtin
+
+(null
+  "nullptr" @constant.builtin)
+
+(true) @boolean
+
+(false) @boolean
+
+; Literals
+(raw_string_literal) @string
+
+; Keywords
+[
+  "try"
+  "catch"
+  "noexcept"
+  "throw"
+] @keyword.exception
+
+[
+  "decltype"
+  "explicit"
+  "friend"
+  "override"
+  "using"
+  "requires"
+  "constexpr"
+] @keyword
+
+[
+  "class"
+  "namespace"
+  "template"
+  "typename"
+  "concept"
+] @keyword.type
+
+[
+  "co_await"
+  "co_yield"
+  "co_return"
+] @keyword.coroutine
+
+[
+  "public"
+  "private"
+  "protected"
+  "final"
+  "virtual"
+] @keyword.modifier
+
+[
+  "new"
+  "delete"
+  "xor"
+  "bitand"
+  "bitor"
+  "compl"
+  "not"
+  "xor_eq"
+  "and_eq"
+  "or_eq"
+  "not_eq"
+  "and"
+  "or"
+] @keyword.operator
+
+"<=>" @operator
+
+"::" @punctuation.delimiter
+
+(template_argument_list
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(template_parameter_list
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(literal_suffix) @operator

bex/tag-preprocessor/queries/ecma.scm

@@ -0,0 +1,392 @@
+; Types
+; Javascript
+; Variables
+;-----------
+(identifier) @variable
+
+; Properties
+;-----------
+(property_identifier) @variable.member
+
+(shorthand_property_identifier) @variable.member
+
+(private_property_identifier) @variable.member
+
+(object_pattern
+  (shorthand_property_identifier_pattern) @variable)
+
+(object_pattern
+  (object_assignment_pattern
+    (shorthand_property_identifier_pattern) @variable))
+
+; Special identifiers
+;--------------------
+((identifier) @type
+  (#lua-match? @type "^[A-Z]"))
+
+((identifier) @constant
+  (#lua-match? @constant "^_*[A-Z][A-Z%d_]*$"))
+
+((shorthand_property_identifier) @constant
+  (#lua-match? @constant "^_*[A-Z][A-Z%d_]*$"))
+
+((identifier) @variable.builtin
+  (#any-of? @variable.builtin "arguments" "module" "console" "window" "document"))
+
+((identifier) @type.builtin
+  (#any-of? @type.builtin
+    "Object" "Function" "Boolean" "Symbol" "Number" "Math" "Date" "String" "RegExp" "Map" "Set"
+    "WeakMap" "WeakSet" "Promise" "Array" "Int8Array" "Uint8Array" "Uint8ClampedArray" "Int16Array"
+    "Uint16Array" "Int32Array" "Uint32Array" "Float32Array" "Float64Array" "ArrayBuffer" "DataView"
+    "Error" "EvalError" "InternalError" "RangeError" "ReferenceError" "SyntaxError" "TypeError"
+    "URIError"))
+
+(statement_identifier) @label
+
+; Function and method definitions
+;--------------------------------
+(function_expression
+  name: (identifier) @function)
+
+(function_declaration
+  name: (identifier) @function)
+
+(generator_function
+  name: (identifier) @function)
+
+(generator_function_declaration
+  name: (identifier) @function)
+
+(method_definition
+  name: [
+    (property_identifier)
+    (private_property_identifier)
+  ] @function.method)
+
+(method_definition
+  name: (property_identifier) @constructor
+  (#eq? @constructor "constructor"))
+
+(pair
+  key: (property_identifier) @function.method
+  value: (function_expression))
+
+(pair
+  key: (property_identifier) @function.method
+  value: (arrow_function))
+
+(assignment_expression
+  left: (member_expression
+    property: (property_identifier) @function.method)
+  right: (arrow_function))
+
+(assignment_expression
+  left: (member_expression
+    property: (property_identifier) @function.method)
+  right: (function_expression))
+
+(variable_declarator
+  name: (identifier) @function
+  value: (arrow_function))
+
+(variable_declarator
+  name: (identifier) @function
+  value: (function_expression))
+
+(assignment_expression
+  left: (identifier) @function
+  right: (arrow_function))
+
+(assignment_expression
+  left: (identifier) @function
+  right: (function_expression))
+
+; Function and method calls
+;--------------------------
+(call_expression
+  function: (identifier) @function.call)
+
+(call_expression
+  function: (member_expression
+    property: [
+      (property_identifier)
+      (private_property_identifier)
+    ] @function.method.call))
+
+(call_expression
+  function: (await_expression
+    (identifier) @function.call))
+
+(call_expression
+  function: (await_expression
+    (member_expression
+      property: [
+        (property_identifier)
+        (private_property_identifier)
+      ] @function.method.call)))
+
+; Builtins
+;---------
+((identifier) @module.builtin
+  (#eq? @module.builtin "Intl"))
+
+((identifier) @function.builtin
+  (#any-of? @function.builtin
+    "eval" "isFinite" "isNaN" "parseFloat" "parseInt" "decodeURI" "decodeURIComponent" "encodeURI"
+    "encodeURIComponent" "require"))
+
+; Constructor
+;------------
+(new_expression
+  constructor: (identifier) @constructor)
+
+; Decorators
+;----------
+(decorator
+  "@" @attribute
+  (identifier) @attribute)
+
+(decorator
+  "@" @attribute
+  (call_expression
+    (identifier) @attribute))
+
+(decorator
+  "@" @attribute
+  (member_expression
+    (property_identifier) @attribute))
+
+(decorator
+  "@" @attribute
+  (call_expression
+    (member_expression
+      (property_identifier) @attribute)))
+
+; Literals
+;---------
+[
+  (this)
+  (super)
+] @variable.builtin
+
+((identifier) @variable.builtin
+  (#eq? @variable.builtin "self"))
+
+[
+  (true)
+  (false)
+] @boolean
+
+[
+  (null)
+  (undefined)
+] @constant.builtin
+
+[
+  (comment)
+  (html_comment)
+] @comment @spell
+
+((comment) @comment.documentation
+  (#lua-match? @comment.documentation "^/[*][*][^*].*[*]/$"))
+
+(hash_bang_line) @keyword.directive
+
+((string_fragment) @keyword.directive
+  (#eq? @keyword.directive "use strict"))
+
+(string) @string
+
+(template_string) @string
+
+(escape_sequence) @string.escape
+
+(regex_pattern) @string.regexp
+
+(regex_flags) @character.special
+
+(regex
+  "/" @punctuation.bracket) ; Regex delimiters
+
+(number) @number
+
+((identifier) @number
+  (#any-of? @number "NaN" "Infinity"))
+
+; Punctuation
+;------------
+[
+  ";"
+  "."
+  ","
+  ":"
+] @punctuation.delimiter
+
+[
+  "--"
+  "-"
+  "-="
+  "&&"
+  "+"
+  "++"
+  "+="
+  "&="
+  "/="
+  "**="
+  "<<="
+  "<"
+  "<="
+  "<<"
+  "="
+  "=="
+  "==="
+  "!="
+  "!=="
+  "=>"
+  ">"
+  ">="
+  ">>"
+  "||"
+  "%"
+  "%="
+  "*"
+  "**"
+  ">>>"
+  "&"
+  "|"
+  "^"
+  "??"
+  "*="
+  ">>="
+  ">>>="
+  "^="
+  "|="
+  "&&="
+  "||="
+  "??="
+  "..."
+] @operator
+
+(binary_expression
+  "/" @operator)
+
+(ternary_expression
+  [
+    "?"
+    ":"
+  ] @keyword.conditional.ternary)
+
+(unary_expression
+  [
+    "!"
+    "~"
+    "-"
+    "+"
+  ] @operator)
+
+(unary_expression
+  [
+    "delete"
+    "void"
+  ] @keyword.operator)
+
+[
+  "("
+  ")"
+  "["
+  "]"
+  "{"
+  "}"
+] @punctuation.bracket
+
+(template_substitution
+  [
+    "${"
+    "}"
+  ] @punctuation.special) @none
+
+; Imports
+;----------
+(namespace_import
+  "*" @character.special
+  (identifier) @module)
+
+(namespace_export
+  "*" @character.special
+  (identifier) @module)
+
+(export_statement
+  "*" @character.special)
+
+; Keywords
+;----------
+[
+  "if"
+  "else"
+  "switch"
+  "case"
+] @keyword.conditional
+
+[
+  "import"
+  "from"
+  "as"
+  "export"
+] @keyword.import
+
+[
+  "for"
+  "of"
+  "do"
+  "while"
+  "continue"
+] @keyword.repeat
+
+[
+  "break"
+  "const"
+  "debugger"
+  "extends"
+  "get"
+  "let"
+  "set"
+  "static"
+  "target"
+  "var"
+  "with"
+] @keyword
+
+"class" @keyword.type
+
+[
+  "async"
+  "await"
+] @keyword.coroutine
+
+[
+  "return"
+  "yield"
+] @keyword.return
+
+"function" @keyword.function
+
+[
+  "new"
+  "delete"
+  "in"
+  "instanceof"
+  "typeof"
+] @keyword.operator
+
+[
+  "throw"
+  "try"
+  "catch"
+  "finally"
+] @keyword.exception
+
+(export_statement
+  "default" @keyword)
+
+(switch_default
+  "default" @keyword.conditional)

bex/tag-preprocessor/queries/go.scm

@@ -0,0 +1,249 @@
+; Forked from tree-sitter-go
+; Copyright (c) 2014 Max Brunsfeld (The MIT License)
+;
+; Identifiers
+(type_identifier) @type
+
+(type_spec
+  name: (type_identifier) @type.definition)
+
+(field_identifier) @property
+
+(identifier) @variable
+
+(package_identifier) @module
+
+(parameter_declaration
+  (identifier) @variable.parameter)
+
+(variadic_parameter_declaration
+  (identifier) @variable.parameter)
+
+(label_name) @label
+
+(const_spec
+  name: (identifier) @constant)
+
+; Function calls
+(call_expression
+  function: (identifier) @function.call)
+
+(call_expression
+  function: (selector_expression
+    field: (field_identifier) @function.method.call))
+
+; Function definitions
+(function_declaration
+  name: (identifier) @function)
+
+(method_declaration
+  name: (field_identifier) @function.method)
+
+(method_elem
+  name: (field_identifier) @function.method)
+
+; Constructors
+((call_expression
+  (identifier) @constructor)
+  (#lua-match? @constructor "^[nN]ew.+$"))
+
+((call_expression
+  (identifier) @constructor)
+  (#lua-match? @constructor "^[mM]ake.+$"))
+
+; Operators
+[
+  "--"
+  "-"
+  "-="
+  ":="
+  "!"
+  "!="
+  "..."
+  "*"
+  "*="
+  "/"
+  "/="
+  "&"
+  "&&"
+  "&="
+  "&^"
+  "&^="
+  "%"
+  "%="
+  "^"
+  "^="
+  "+"
+  "++"
+  "+="
+  "<-"
+  "<"
+  "<<"
+  "<<="
+  "<="
+  "="
+  "=="
+  ">"
+  ">="
+  ">>"
+  ">>="
+  "|"
+  "|="
+  "||"
+  "~"
+] @operator
+
+; Keywords
+[
+  "break"
+  "const"
+  "continue"
+  "default"
+  "defer"
+  "goto"
+  "range"
+  "select"
+  "var"
+  "fallthrough"
+] @keyword
+
+[
+  "type"
+  "struct"
+  "interface"
+] @keyword.type
+
+"func" @keyword.function
+
+"return" @keyword.return
+
+"go" @keyword.coroutine
+
+"for" @keyword.repeat
+
+[
+  "import"
+  "package"
+] @keyword.import
+
+[
+  "else"
+  "case"
+  "switch"
+  "if"
+] @keyword.conditional
+
+; Builtin types
+[
+  "chan"
+  "map"
+] @type.builtin
+
+((type_identifier) @type.builtin
+  (#any-of? @type.builtin
+    "any" "bool" "byte" "comparable" "complex128" "complex64" "error" "float32" "float64" "int"
+    "int16" "int32" "int64" "int8" "rune" "string" "uint" "uint16" "uint32" "uint64" "uint8"
+    "uintptr"))
+
+; Builtin functions
+((identifier) @function.builtin
+  (#any-of? @function.builtin
+    "append" "cap" "clear" "close" "complex" "copy" "delete" "imag" "len" "make" "max" "min" "new"
+    "panic" "print" "println" "real" "recover"))
+
+; Delimiters
+[
+  "."
+  ","
+  ":"
+  ";"
+] @punctuation.delimiter
+
+[
+  "("
+  ")"
+  "{"
+  "}"
+  "["
+  "]"
+] @punctuation.bracket
+
+; Literals
+(interpreted_string_literal) @string
+
+(raw_string_literal) @string
+
+(rune_literal) @character
+
+(escape_sequence) @string.escape
+
+(int_literal) @number
+
+(float_literal) @number.float
+
+(imaginary_literal) @number
+
+[
+  (true)
+  (false)
+] @boolean
+
+[
+  (nil)
+  (iota)
+] @constant.builtin
+
+(keyed_element
+  .
+  (literal_element
+    (identifier) @variable.member))
+
+(field_declaration
+  name: (field_identifier) @variable.member)
+
+; Comments
+(comment) @comment @spell
+
+; Doc Comments
+(source_file
+  .
+  (comment)+ @comment.documentation)
+
+(source_file
+  (comment)+ @comment.documentation
+  .
+  (const_declaration))
+
+(source_file
+  (comment)+ @comment.documentation
+  .
+  (function_declaration))
+
+(source_file
+  (comment)+ @comment.documentation
+  .
+  (type_declaration))
+
+(source_file
+  (comment)+ @comment.documentation
+  .
+  (var_declaration))
+
+; Spell
+((interpreted_string_literal) @spell
+  (#not-has-parent? @spell import_spec))
+
+; Regex
+(call_expression
+  (selector_expression) @_function
+  (#any-of? @_function
+    "regexp.Match" "regexp.MatchReader" "regexp.MatchString" "regexp.Compile" "regexp.CompilePOSIX"
+    "regexp.MustCompile" "regexp.MustCompilePOSIX")
+  (argument_list
+    .
+    [
+      (raw_string_literal
+        (raw_string_literal_content) @string.regexp)
+      (interpreted_string_literal
+        (interpreted_string_literal_content) @string.regexp)
+    ]))

bex/tag-preprocessor/queries/java.scm

@@ -0,0 +1,333 @@
+; CREDITS @maxbrunsfeld (maxbrunsfeld@gmail.com)
+; Variables
+(identifier) @variable
+
+(underscore_pattern) @character.special
+
+; Methods
+(method_declaration
+  name: (identifier) @function.method)
+
+(method_invocation
+  name: (identifier) @function.method.call)
+
+(super) @function.builtin
+
+; Parameters
+(formal_parameter
+  name: (identifier) @variable.parameter)
+
+(spread_parameter
+  (variable_declarator
+    name: (identifier) @variable.parameter)) ; int... foo
+
+; Lambda parameter
+(inferred_parameters
+  (identifier) @variable.parameter) ; (x,y) -> ...
+
+(lambda_expression
+  parameters: (identifier) @variable.parameter) ; x -> ...
+
+; Operators
+[
+  "+"
+  ":"
+  "++"
+  "-"
+  "--"
+  "&"
+  "&&"
+  "|"
+  "||"
+  "!"
+  "!="
+  "=="
+  "*"
+  "/"
+  "%"
+  "<"
+  "<="
+  ">"
+  ">="
+  "="
+  "-="
+  "+="
+  "*="
+  "/="
+  "%="
+  "->"
+  "^"
+  "^="
+  "&="
+  "|="
+  "~"
+  ">>"
+  ">>>"
+  "<<"
+  "::"
+] @operator
+
+; Types
+(interface_declaration
+  name: (identifier) @type)
+
+(annotation_type_declaration
+  name: (identifier) @type)
+
+(class_declaration
+  name: (identifier) @type)
+
+(record_declaration
+  name: (identifier) @type)
+
+(enum_declaration
+  name: (identifier) @type)
+
+(constructor_declaration
+  name: (identifier) @type)
+
+(compact_constructor_declaration
+  name: (identifier) @type)
+
+(type_identifier) @type
+
+((type_identifier) @type.builtin
+  (#eq? @type.builtin "var"))
+
+((method_invocation
+  object: (identifier) @type)
+  (#lua-match? @type "^[A-Z]"))
+
+((method_reference
+  .
+  (identifier) @type)
+  (#lua-match? @type "^[A-Z]"))
+
+((field_access
+  object: (identifier) @type)
+  (#lua-match? @type "^[A-Z]"))
+
+(scoped_identifier
+  (identifier) @type
+  (#lua-match? @type "^[A-Z]"))
+
+; Fields
+(field_declaration
+  declarator: (variable_declarator
+    name: (identifier) @variable.member))
+
+(field_access
+  field: (identifier) @variable.member)
+
+[
+  (boolean_type)
+  (integral_type)
+  (floating_point_type)
+  (void_type)
+] @type.builtin
+
+; Variables
+((identifier) @constant
+  (#lua-match? @constant "^[A-Z_][A-Z%d_]+$"))
+
+(this) @variable.builtin
+
+; Annotations
+(annotation
+  "@" @attribute
+  name: (identifier) @attribute)
+
+(marker_annotation
+  "@" @attribute
+  name: (identifier) @attribute)
+
+; Literals
+(string_literal) @string
+
+(escape_sequence) @string.escape
+
+(character_literal) @character
+
+[
+  (hex_integer_literal)
+  (decimal_integer_literal)
+  (octal_integer_literal)
+  (binary_integer_literal)
+] @number
+
+[
+  (decimal_floating_point_literal)
+  (hex_floating_point_literal)
+] @number.float
+
+[
+  (true)
+  (false)
+] @boolean
+
+(null_literal) @constant.builtin
+
+; Keywords
+[
+  "assert"
+  "default"
+  "extends"
+  "implements"
+  "instanceof"
+  "@interface"
+  "permits"
+  "to"
+  "with"
+] @keyword
+
+[
+  "record"
+  "class"
+  "enum"
+  "interface"
+] @keyword.type
+
+(synchronized_statement
+  "synchronized" @keyword)
+
+[
+  "abstract"
+  "final"
+  "native"
+  "non-sealed"
+  "open"
+  "private"
+  "protected"
+  "public"
+  "sealed"
+  "static"
+  "strictfp"
+  "transitive"
+] @keyword.modifier
+
+(modifiers
+  "synchronized" @keyword.modifier)
+
+[
+  "transient"
+  "volatile"
+] @keyword.modifier
+
+[
+  "return"
+  "yield"
+] @keyword.return
+
+"new" @keyword.operator
+
+; Conditionals
+[
+  "if"
+  "else"
+  "switch"
+  "case"
+  "when"
+] @keyword.conditional
+
+(ternary_expression
+  [
+    "?"
+    ":"
+  ] @keyword.conditional.ternary)
+
+(wildcard
+  "?" @character.special)
+
+; Loops
+[
+  "for"
+  "while"
+  "do"
+  "continue"
+  "break"
+] @keyword.repeat
+
+; Includes
+[
+  "exports"
+  "import"
+  "module"
+  "opens"
+  "package"
+  "provides"
+  "requires"
+  "uses"
+] @keyword.import
+
+(import_declaration
+  (asterisk
+    "*" @character.special))
+
+; Punctuation
+[
+  ";"
+  "."
+  "..."
+  ","
+] @punctuation.delimiter
+
+[
+  "{"
+  "}"
+] @punctuation.bracket
+
+[
+  "["
+  "]"
+] @punctuation.bracket
+
+[
+  "("
+  ")"
+] @punctuation.bracket
+
+(type_arguments
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(type_parameters
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(string_interpolation
+  [
+    "\\{"
+    "}"
+  ] @punctuation.special)
+
+; Exceptions
+[
+  "throw"
+  "throws"
+  "finally"
+  "try"
+  "catch"
+] @keyword.exception
+
+; Labels
+(labeled_statement
+  (identifier) @label)
+
+; Comments
+[
+  (line_comment)
+  (block_comment)
+] @comment @spell
+
+((block_comment) @comment.documentation
+  (#lua-match? @comment.documentation "^/[*][*][^*].*[*]/$"))
+
+((line_comment) @comment.documentation
+  (#lua-match? @comment.documentation "^///[^/]"))
+
+((line_comment) @comment.documentation
+  (#lua-match? @comment.documentation "^///$"))

bex/tag-preprocessor/queries/javascript.scm

@@ -0,0 +1,56 @@
+; inherits: ecma,jsx
+
+; Parameters
+(formal_parameters
+  (identifier) @variable.parameter)
+
+(formal_parameters
+  (rest_pattern
+    (identifier) @variable.parameter))
+
+; ({ a }) => null
+(formal_parameters
+  (object_pattern
+    (shorthand_property_identifier_pattern) @variable.parameter))
+
+; ({ a = b }) => null
+(formal_parameters
+  (object_pattern
+    (object_assignment_pattern
+      (shorthand_property_identifier_pattern) @variable.parameter)))
+
+; ({ a: b }) => null
+(formal_parameters
+  (object_pattern
+    (pair_pattern
+      value: (identifier) @variable.parameter)))
+
+; ([ a ]) => null
+(formal_parameters
+  (array_pattern
+    (identifier) @variable.parameter))
+
+; ({ a } = { a }) => null
+(formal_parameters
+  (assignment_pattern
+    (object_pattern
+      (shorthand_property_identifier_pattern) @variable.parameter)))
+
+; ({ a = b } = { a }) => null
+(formal_parameters
+  (assignment_pattern
+    (object_pattern
+      (object_assignment_pattern
+        (shorthand_property_identifier_pattern) @variable.parameter))))
+
+; a => null
+(arrow_function
+  parameter: (identifier) @variable.parameter)
+
+; optional parameters
+(formal_parameters
+  (assignment_pattern
+    left: (identifier) @variable.parameter))
+
+; punctuation
+(optional_chain) @punctuation.delimiter

bex/tag-preprocessor/queries/jsx.scm

@@ -0,0 +1,153 @@
+(jsx_element
+  open_tag: (jsx_opening_element
+    [
+      "<"
+      ">"
+    ] @tag.delimiter))
+
+(jsx_element
+  close_tag: (jsx_closing_element
+    [
+      "</"
+      ">"
+    ] @tag.delimiter))
+
+(jsx_self_closing_element
+  [
+    "<"
+    "/>"
+  ] @tag.delimiter)
+
+(jsx_attribute
+  (property_identifier) @tag.attribute)
+
+(jsx_opening_element
+  name: (identifier) @tag.builtin)
+
+(jsx_closing_element
+  name: (identifier) @tag.builtin)
+
+(jsx_self_closing_element
+  name: (identifier) @tag.builtin)
+
+(jsx_opening_element
+  ((identifier) @tag
+    (#lua-match? @tag "^[A-Z]")))
+
+; Handle the dot operator effectively - <My.Component>
+(jsx_opening_element
+  (member_expression
+    (identifier) @tag.builtin
+    (property_identifier) @tag))
+
+(jsx_closing_element
+  ((identifier) @tag
+    (#lua-match? @tag "^[A-Z]")))
+
+; Handle the dot operator effectively - </My.Component>
+(jsx_closing_element
+  (member_expression
+    (identifier) @tag.builtin
+    (property_identifier) @tag))
+
+(jsx_self_closing_element
+  ((identifier) @tag
+    (#lua-match? @tag "^[A-Z]")))
+
+; Handle the dot operator effectively - <My.Component />
+(jsx_self_closing_element
+  (member_expression
+    (identifier) @tag.builtin
+    (property_identifier) @tag))
+
+(html_character_reference) @tag
+
+(jsx_text) @none @spell
+
+(html_character_reference) @character.special
+
+((jsx_element
+  (jsx_opening_element
+    name: (identifier) @_tag)
+  (jsx_text) @markup.heading)
+  (#eq? @_tag "title"))
+
+((jsx_element
+  (jsx_opening_element
+    name: (identifier) @_tag)
+  (jsx_text) @markup.heading.1)
+  (#eq? @_tag "h1"))
+
+((jsx_element
+  (jsx_opening_element
+    name: (identifier) @_tag)
+  (jsx_text) @markup.heading.2)
+  (#eq? @_tag "h2"))
+
+((jsx_element
+  (jsx_opening_element
+    name: (identifier) @_tag)
+  (jsx_text) @markup.heading.3)
+  (#eq? @_tag "h3"))
+
+((jsx_element
+  (jsx_opening_element
+    name: (identifier) @_tag)
+  (jsx_text) @markup.heading.4)
+  (#eq? @_tag "h4"))
+
+((jsx_element
+  (jsx_opening_element
+    name: (identifier) @_tag)
+  (jsx_text) @markup.heading.5)
+  (#eq? @_tag "h5"))
+
+((jsx_element
+  (jsx_opening_element
+    name: (identifier) @_tag)
+  (jsx_text) @markup.heading.6)
+  (#eq? @_tag "h6"))
+
+((jsx_element
+  (jsx_opening_element
+    name: (identifier) @_tag)
+  (jsx_text) @markup.strong)
+  (#any-of? @_tag "strong" "b"))
+
+((jsx_element
+  (jsx_opening_element
+    name: (identifier) @_tag)
+  (jsx_text) @markup.italic)
+  (#any-of? @_tag "em" "i"))
+
+((jsx_element
+  (jsx_opening_element
+    name: (identifier) @_tag)
+  (jsx_text) @markup.strikethrough)
+  (#any-of? @_tag "s" "del"))
+
+((jsx_element
+  (jsx_opening_element
+    name: (identifier) @_tag)
+  (jsx_text) @markup.underline)
+  (#eq? @_tag "u"))
+
+((jsx_element
+  (jsx_opening_element
+    name: (identifier) @_tag)
+  (jsx_text) @markup.raw)
+  (#any-of? @_tag "code" "kbd"))
+
+((jsx_element
+  (jsx_opening_element
+    name: (identifier) @_tag)
+  (jsx_text) @markup.link.label)
+  (#eq? @_tag "a"))
+
+((jsx_attribute
+  (property_identifier) @_attr
+  (string
+    (string_fragment) @string.special.url))
+  (#any-of? @_attr "href" "src"))
+
+

bex/tag-preprocessor/queries/kotlin.scm

@@ -183,6 +183,7 @@
 		"require"
 		"requireNotNull"
 		"with"
+		"suspend"
 		"synchronized"
 ))
 
@@ -346,11 +347,12 @@
 	"?:"
 	"!!"
 	"is"
+	"!is"
 	"in"
+	"!in"
 	"as"
 	"as?"
 	".."
-	"..<"
 	"->"
 ] @operator
 
@@ -370,9 +372,9 @@
 
 ; NOTE: `interpolated_identifier`s can be highlighted in any way
 (string_literal
-	(interpolation_identifier_start) @punctuation.special
+	"$" @punctuation.special
 	(interpolated_identifier) @none)
 (string_literal
-	(interpolation_expression_start) @punctuation.special
+	"${" @punctuation.special
 	(interpolated_expression) @none
-	(interpolation_expression_end) @punctuation.special)
+	"}" @punctuation.special)

bex/tag-preprocessor/queries/python.scm

@@ -0,0 +1,456 @@
+; From tree-sitter-python licensed under MIT License
+; Copyright (c) 2016 Max Brunsfeld
+; Variables
+(identifier) @variable
+
+; Reset highlighting in f-string interpolations
+(interpolation) @none @nospell
+
+; Identifier naming conventions
+((identifier) @type
+  (#lua-match? @type "^[A-Z].*[a-z]"))
+
+((identifier) @constant
+  (#lua-match? @constant "^[A-Z][A-Z_0-9]*$"))
+
+((identifier) @constant.builtin
+  (#lua-match? @constant.builtin "^__[a-zA-Z0-9_]*__$"))
+
+((identifier) @constant.builtin
+  (#any-of? @constant.builtin
+    ; https://docs.python.org/3/library/constants.html
+    "NotImplemented" "Ellipsis" "quit" "exit" "copyright" "credits" "license"))
+
+"_" @character.special ; match wildcard
+
+((assignment
+  left: (identifier) @type.definition
+  (type
+    (identifier) @_annotation))
+  (#eq? @_annotation "TypeAlias"))
+
+((assignment
+  left: (identifier) @type.definition
+  right: (call
+    function: (identifier) @_func))
+  (#any-of? @_func "TypeVar" "NewType"))
+
+; Function definitions
+(function_definition
+  name: (identifier) @function)
+
+(type
+  (identifier) @type)
+
+(type
+  (subscript
+    (identifier) @type)) ; type subscript: Tuple[int]
+
+((call
+  function: (identifier) @_isinstance
+  arguments: (argument_list
+    (_)
+    (identifier) @type))
+  (#eq? @_isinstance "isinstance"))
+
+; Literals
+(none) @constant.builtin
+
+[
+  (true)
+  (false)
+] @boolean
+
+(integer) @number
+
+(float) @number.float
+
+(comment) @comment @spell
+
+((module
+  .
+  (comment) @keyword.directive @nospell)
+  (#lua-match? @keyword.directive "^#!/"))
+
+(string) @string
+
+[
+  (escape_sequence)
+  (escape_interpolation)
+] @string.escape
+
+; doc-strings
+(expression_statement
+  (string
+    (string_content) @spell) @string.documentation)
+
+; Tokens
+[
+  "-"
+  "-="
+  ":="
+  "!="
+  "*"
+  "**"
+  "**="
+  "*="
+  "/"
+  "//"
+  "//="
+  "/="
+  "&"
+  "&="
+  "%"
+  "%="
+  "^"
+  "^="
+  "+"
+  "+="
+  "<"
+  "<<"
+  "<<="
+  "<="
+  "<>"
+  "="
+  "=="
+  ">"
+  ">="
+  ">>"
+  ">>="
+  "@"
+  "@="
+  "|"
+  "|="
+  "~"
+  "->"
+] @operator
+
+; Keywords
+[
+  "and"
+  "in"
+  "is"
+  "not"
+  "or"
+  "is not"
+  "not in"
+  "del"
+] @keyword.operator
+
+[
+  "def"
+  "lambda"
+] @keyword.function
+
+[
+  "assert"
+  "exec"
+  "global"
+  "nonlocal"
+  "pass"
+  "print"
+  "with"
+  "as"
+] @keyword
+
+[
+  "type"
+  "class"
+] @keyword.type
+
+[
+  "async"
+  "await"
+] @keyword.coroutine
+
+[
+  "return"
+  "yield"
+] @keyword.return
+
+(yield
+  "from" @keyword.return)
+
+(future_import_statement
+  "from" @keyword.import
+  "__future__" @module.builtin)
+
+(import_from_statement
+  "from" @keyword.import)
+
+"import" @keyword.import
+
+(aliased_import
+  "as" @keyword.import)
+
+(wildcard_import
+  "*" @character.special)
+
+(import_statement
+  name: (dotted_name
+    (identifier) @module))
+
+(import_statement
+  name: (aliased_import
+    name: (dotted_name
+      (identifier) @module)
+    alias: (identifier) @module))
+
+(import_from_statement
+  module_name: (dotted_name
+    (identifier) @module))
+
+(import_from_statement
+  module_name: (relative_import
+    (dotted_name
+      (identifier) @module)))
+
+[
+  "if"
+  "elif"
+  "else"
+  "match"
+  "case"
+] @keyword.conditional
+
+[
+  "for"
+  "while"
+  "break"
+  "continue"
+] @keyword.repeat
+
+[
+  "try"
+  "except"
+  "raise"
+  "finally"
+] @keyword.exception
+
+(raise_statement
+  "from" @keyword.exception)
+
+(try_statement
+  (else_clause
+    "else" @keyword.exception))
+
+[
+  "("
+  ")"
+  "["
+  "]"
+  "{"
+  "}"
+] @punctuation.bracket
+
+(interpolation
+  "{" @punctuation.special
+  "}" @punctuation.special)
+
+(format_expression
+  "{" @punctuation.special
+  "}" @punctuation.special)
+
+(line_continuation) @punctuation.special
+
+(type_conversion) @function.macro
+
+[
+  ","
+  "."
+  ":"
+  ";"
+  (ellipsis)
+] @punctuation.delimiter
+
+((identifier) @type.builtin
+  (#any-of? @type.builtin
+    ; https://docs.python.org/3/library/exceptions.html
+    "BaseException" "Exception" "ArithmeticError" "BufferError" "LookupError" "AssertionError"
+    "AttributeError" "EOFError" "FloatingPointError" "GeneratorExit" "ImportError"
+    "ModuleNotFoundError" "IndexError" "KeyError" "KeyboardInterrupt" "MemoryError" "NameError"
+    "NotImplementedError" "OSError" "OverflowError" "RecursionError" "ReferenceError" "RuntimeError"
+    "StopIteration" "StopAsyncIteration" "SyntaxError" "IndentationError" "TabError" "SystemError"
+    "SystemExit" "TypeError" "UnboundLocalError" "UnicodeError" "UnicodeEncodeError"
+    "UnicodeDecodeError" "UnicodeTranslateError" "ValueError" "ZeroDivisionError" "EnvironmentError"
+    "IOError" "WindowsError" "BlockingIOError" "ChildProcessError" "ConnectionError"
+    "BrokenPipeError" "ConnectionAbortedError" "ConnectionRefusedError" "ConnectionResetError"
+    "FileExistsError" "FileNotFoundError" "InterruptedError" "IsADirectoryError"
+    "NotADirectoryError" "PermissionError" "ProcessLookupError" "TimeoutError" "Warning"
+    "UserWarning" "DeprecationWarning" "PendingDeprecationWarning" "SyntaxWarning" "RuntimeWarning"
+    "FutureWarning" "ImportWarning" "UnicodeWarning" "BytesWarning" "ResourceWarning"
+    ; https://docs.python.org/3/library/stdtypes.html
+    "bool" "int" "float" "complex" "list" "tuple" "range" "str" "bytes" "bytearray" "memoryview"
+    "set" "frozenset" "dict" "type" "object"))
+
+; Normal parameters
+(parameters
+  (identifier) @variable.parameter)
+
+; Lambda parameters
+(lambda_parameters
+  (identifier) @variable.parameter)
+
+(lambda_parameters
+  (tuple_pattern
+    (identifier) @variable.parameter))
+
+; Default parameters
+(keyword_argument
+  name: (identifier) @variable.parameter)
+
+; Naming parameters on call-site
+(default_parameter
+  name: (identifier) @variable.parameter)
+
+(typed_parameter
+  (identifier) @variable.parameter)
+
+(typed_default_parameter
+  name: (identifier) @variable.parameter)
+
+; Variadic parameters *args, **kwargs
+(parameters
+  (list_splat_pattern ; *args
+    (identifier) @variable.parameter))
+
+(parameters
+  (dictionary_splat_pattern ; **kwargs
+    (identifier) @variable.parameter))
+
+; Typed variadic parameters
+(parameters
+  (typed_parameter
+    (list_splat_pattern ; *args: type
+      (identifier) @variable.parameter)))
+
+(parameters
+  (typed_parameter
+    (dictionary_splat_pattern ; *kwargs: type
+      (identifier) @variable.parameter)))
+
+; Lambda parameters
+(lambda_parameters
+  (list_splat_pattern
+    (identifier) @variable.parameter))
+
+(lambda_parameters
+  (dictionary_splat_pattern
+    (identifier) @variable.parameter))
+
+((identifier) @variable.builtin
+  (#eq? @variable.builtin "self"))
+
+((identifier) @variable.builtin
+  (#eq? @variable.builtin "cls"))
+
+; After @type.builtin bacause builtins (such as `type`) are valid as attribute name
+((attribute
+  attribute: (identifier) @variable.member)
+  (#lua-match? @variable.member "^[%l_].*$"))
+
+; Class definitions
+(class_definition
+  name: (identifier) @type)
+
+(class_definition
+  body: (block
+    (function_definition
+      name: (identifier) @function.method)))
+
+(class_definition
+  superclasses: (argument_list
+    (identifier) @type))
+
+((class_definition
+  body: (block
+    (expression_statement
+      (assignment
+        left: (identifier) @variable.member))))
+  (#lua-match? @variable.member "^[%l_].*$"))
+
+((class_definition
+  body: (block
+    (expression_statement
+      (assignment
+        left: (_
+          (identifier) @variable.member)))))
+  (#lua-match? @variable.member "^[%l_].*$"))
+
+((class_definition
+  (block
+    (function_definition
+      name: (identifier) @constructor)))
+  (#any-of? @constructor "__new__" "__init__"))
+
+; Function calls
+(call
+  function: (identifier) @function.call)
+
+(call
+  function: (attribute
+    attribute: (identifier) @function.method.call))
+
+((call
+  function: (identifier) @constructor)
+  (#lua-match? @constructor "^%u"))
+
+((call
+  function: (attribute
+    attribute: (identifier) @constructor))
+  (#lua-match? @constructor "^%u"))
+
+; Builtin functions
+((call
+  function: (identifier) @function.builtin)
+  (#any-of? @function.builtin
+    "abs" "all" "any" "ascii" "bin" "bool" "breakpoint" "bytearray" "bytes" "callable" "chr"
+    "classmethod" "compile" "complex" "delattr" "dict" "dir" "divmod" "enumerate" "eval" "exec"
+    "filter" "float" "format" "frozenset" "getattr" "globals" "hasattr" "hash" "help" "hex" "id"
+    "input" "int" "isinstance" "issubclass" "iter" "len" "list" "locals" "map" "max" "memoryview"
+    "min" "next" "object" "oct" "open" "ord" "pow" "print" "property" "range" "repr" "reversed"
+    "round" "set" "setattr" "slice" "sorted" "staticmethod" "str" "sum" "super" "tuple" "type"
+    "vars" "zip" "__import__"))
+
+; Regex from the `re` module
+(call
+  function: (attribute
+    object: (identifier) @_re)
+  arguments: (argument_list
+    (string
+      (string_content) @string.regexp))
+  (#eq? @_re "re"))
+
+(call
+  function: (attribute
+    object: (identifier) @_re)
+  arguments: (argument_list
+    (concatenated_string
+      (string
+        (string_content) @string.regexp)))
+  (#eq? @_re "re"))
+
+; Decorators
+((decorator
+  "@" @attribute)
+  (#set! priority 101))
+
+(decorator
+  (identifier) @attribute)
+
+(decorator
+  (attribute
+    attribute: (identifier) @attribute))
+
+(decorator
+  (call
+    (identifier) @attribute))
+
+(decorator
+  (call
+    (attribute
+      attribute: (identifier) @attribute)))
+
+((decorator
+  (identifier) @attribute.builtin)
+  (#any-of? @attribute.builtin "classmethod" "property" "staticmethod"))

bex/tag-preprocessor/queries/ruby.scm

@@ -0,0 +1,319 @@
+; Variables
+[
+  (identifier)
+  (global_variable)
+] @variable
+
+; Keywords
+[
+  "alias"
+  "begin"
+  "do"
+  "end"
+  "ensure"
+  "module"
+  "rescue"
+  "then"
+] @keyword
+
+"class" @keyword.type
+
+[
+  "return"
+  "yield"
+] @keyword.return
+
+[
+  "and"
+  "or"
+  "in"
+  "not"
+] @keyword.operator
+
+[
+  "def"
+  "undef"
+] @keyword.function
+
+(method
+  "end" @keyword.function)
+
+[
+  "case"
+  "else"
+  "elsif"
+  "if"
+  "unless"
+  "when"
+  "then"
+] @keyword.conditional
+
+(in_clause
+  "in" @keyword.conditional)
+
+(if
+  "end" @keyword.conditional)
+
+[
+  "for"
+  "until"
+  "while"
+  "break"
+  "redo"
+  "retry"
+  "next"
+] @keyword.repeat
+
+(in
+  "in" @keyword.repeat)
+
+(constant) @constant
+
+((identifier) @keyword.modifier
+  (#any-of? @keyword.modifier "private" "protected" "public"))
+
+[
+  "rescue"
+  "ensure"
+] @keyword.exception
+
+; Function calls
+"defined?" @function
+
+(call
+  receiver: (constant)? @type
+  method: [
+    (identifier)
+    (constant)
+  ] @function.call)
+
+(program
+  (call
+    (identifier) @keyword.import)
+  (#any-of? @keyword.import "require" "require_relative" "load"))
+
+; Function definitions
+(alias
+  (identifier) @function)
+
+(setter
+  (identifier) @function)
+
+(method
+  name: [
+    (identifier) @function
+    (constant) @type
+  ])
+
+(singleton_method
+  name: [
+    (identifier) @function
+    (constant) @type
+  ])
+
+(class
+  name: (constant) @type)
+
+(module
+  name: (constant) @type)
+
+(superclass
+  (constant) @type)
+
+; Identifiers
+[
+  (class_variable)
+  (instance_variable)
+] @variable.member
+
+((identifier) @constant.builtin
+  (#any-of? @constant.builtin
+    "__callee__" "__dir__" "__id__" "__method__" "__send__" "__ENCODING__" "__FILE__" "__LINE__"))
+
+((identifier) @function.builtin
+  (#any-of? @function.builtin "attr_reader" "attr_writer" "attr_accessor" "module_function"))
+
+((call
+  !receiver
+  method: (identifier) @function.builtin)
+  (#any-of? @function.builtin "include" "extend" "prepend" "refine" "using"))
+
+((identifier) @keyword.exception
+  (#any-of? @keyword.exception "raise" "fail" "catch" "throw"))
+
+((constant) @type
+  (#not-lua-match? @type "^[A-Z0-9_]+$"))
+
+[
+  (self)
+  (super)
+] @variable.builtin
+
+(method_parameters
+  (identifier) @variable.parameter)
+
+(lambda_parameters
+  (identifier) @variable.parameter)
+
+(block_parameters
+  (identifier) @variable.parameter)
+
+(splat_parameter
+  (identifier) @variable.parameter)
+
+(hash_splat_parameter
+  (identifier) @variable.parameter)
+
+(optional_parameter
+  (identifier) @variable.parameter)
+
+(destructured_parameter
+  (identifier) @variable.parameter)
+
+(block_parameter
+  (identifier) @variable.parameter)
+
+(keyword_parameter
+  (identifier) @variable.parameter)
+
+; Literals
+[
+  (string_content)
+  (heredoc_content)
+  "\""
+  "`"
+] @string
+
+[
+  (heredoc_beginning)
+  (heredoc_end)
+] @label
+
+[
+  (bare_symbol)
+  (simple_symbol)
+  (hash_key_symbol)
+] @string.special.symbol
+
+(delimited_symbol
+  ":\"" @string.special.symbol
+  (string_content) @string.special.symbol
+  "\"" @string.special.symbol)
+
+(regex
+  (string_content) @string.regexp)
+
+(escape_sequence) @string.escape
+
+(integer) @number
+
+(float) @number.float
+
+[
+  (true)
+  (false)
+] @boolean
+
+(nil) @constant.builtin
+
+(comment) @comment @spell
+
+((program
+  .
+  (comment) @keyword.directive @nospell)
+  (#lua-match? @keyword.directive "^#!/"))
+
+(program
+  (comment)+ @comment.documentation
+  (class))
+
+(module
+  (comment)+ @comment.documentation
+  (body_statement
+    (class)))
+
+(class
+  (comment)+ @comment.documentation
+  (body_statement
+    (method)))
+
+(body_statement
+  (comment)+ @comment.documentation
+  (method))
+
+; Operators
+[
+  "!"
+  "="
+  "=="
+  "==="
+  "<=>"
+  "=>"
+  "->"
+  ">>"
+  "<<"
+  ">"
+  "<"
+  ">="
+  "<="
+  "**"
+  "*"
+  "/"
+  "%"
+  "+"
+  "-"
+  "&"
+  "|"
+  "^"
+  "&&"
+  "||"
+  "||="
+  "&&="
+  "!="
+  "%="
+  "+="
+  "-="
+  "*="
+  "/="
+  "=~"
+  "!~"
+  "?"
+  ":"
+  ".."
+  "..."
+] @operator
+
+[
+  ","
+  ";"
+  "."
+  "&."
+  "::"
+] @punctuation.delimiter
+
+(regex
+  "/" @punctuation.bracket)
+
+(pair
+  ":" @punctuation.delimiter)
+
+(keyword_pattern
+  ":" @punctuation.delimiter)
+
+[
+  "("
+  ")"
+  "["
+  "]"
+  "{"
+  "}"
+  "%w("
+  "%i("
+] @punctuation.bracket
+
+(block_parameters
+  "|" @punctuation.bracket)
+
+(interpolation
+  "#{" @punctuation.special
+  "}" @punctuation.special)

bex/tag-preprocessor/queries/rust.scm

@@ -0,0 +1,534 @@
+; Forked from https://github.com/tree-sitter/tree-sitter-rust
+; Copyright (c) 2017 Maxim Sokolov
+; Licensed under the MIT license.
+; Identifier conventions
+(shebang) @keyword.directive
+
+(identifier) @variable
+
+((identifier) @type
+  (#lua-match? @type "^[A-Z]"))
+
+(const_item
+  name: (identifier) @constant)
+
+; Assume all-caps names are constants
+((identifier) @constant
+  (#lua-match? @constant "^[A-Z][A-Z%d_]*$"))
+
+; Other identifiers
+(type_identifier) @type
+
+(primitive_type) @type.builtin
+
+(field_identifier) @variable.member
+
+(shorthand_field_identifier) @variable.member
+
+(shorthand_field_initializer
+  (identifier) @variable.member)
+
+(mod_item
+  name: (identifier) @module)
+
+(self) @variable.builtin
+
+"_" @character.special
+
+(label
+  [
+    "'"
+    (identifier)
+  ] @label)
+
+; Function definitions
+(function_item
+  (identifier) @function)
+
+(function_signature_item
+  (identifier) @function)
+
+(parameter
+  [
+    (identifier)
+    "_"
+  ] @variable.parameter)
+
+(parameter
+  (ref_pattern
+    [
+      (mut_pattern
+        (identifier) @variable.parameter)
+      (identifier) @variable.parameter
+    ]))
+
+(closure_parameters
+  (_) @variable.parameter)
+
+; Function calls
+(call_expression
+  function: (identifier) @function.call)
+
+(call_expression
+  function: (scoped_identifier
+    (identifier) @function.call .))
+
+(call_expression
+  function: (field_expression
+    field: (field_identifier) @function.call))
+
+(generic_function
+  function: (identifier) @function.call)
+
+(generic_function
+  function: (scoped_identifier
+    name: (identifier) @function.call))
+
+(generic_function
+  function: (field_expression
+    field: (field_identifier) @function.call))
+
+; Assume other uppercase names are enum constructors
+((field_identifier) @constant
+  (#lua-match? @constant "^[A-Z]"))
+
+(enum_variant
+  name: (identifier) @constant)
+
+; Assume that uppercase names in paths are types
+(scoped_identifier
+  path: (identifier) @module)
+
+(scoped_identifier
+  (scoped_identifier
+    name: (identifier) @module))
+
+(scoped_type_identifier
+  path: (identifier) @module)
+
+(scoped_type_identifier
+  path: (identifier) @type
+  (#lua-match? @type "^[A-Z]"))
+
+(scoped_type_identifier
+  (scoped_identifier
+    name: (identifier) @module))
+
+((scoped_identifier
+  path: (identifier) @type)
+  (#lua-match? @type "^[A-Z]"))
+
+((scoped_identifier
+  name: (identifier) @type)
+  (#lua-match? @type "^[A-Z]"))
+
+((scoped_identifier
+  name: (identifier) @constant)
+  (#lua-match? @constant "^[A-Z][A-Z%d_]*$"))
+
+((scoped_identifier
+  path: (identifier) @type
+  name: (identifier) @constant)
+  (#lua-match? @type "^[A-Z]")
+  (#lua-match? @constant "^[A-Z]"))
+
+((scoped_type_identifier
+  path: (identifier) @type
+  name: (type_identifier) @constant)
+  (#lua-match? @type "^[A-Z]")
+  (#lua-match? @constant "^[A-Z]"))
+
+[
+  (crate)
+  (super)
+] @module
+
+(scoped_use_list
+  path: (identifier) @module)
+
+(scoped_use_list
+  path: (scoped_identifier
+    (identifier) @module))
+
+(use_list
+  (scoped_identifier
+    (identifier) @module
+    .
+    (_)))
+
+(use_list
+  (identifier) @type
+  (#lua-match? @type "^[A-Z]"))
+
+(use_as_clause
+  alias: (identifier) @type
+  (#lua-match? @type "^[A-Z]"))
+
+; Correct enum constructors
+(call_expression
+  function: (scoped_identifier
+    "::"
+    name: (identifier) @constant)
+  (#lua-match? @constant "^[A-Z]"))
+
+; Assume uppercase names in a match arm are constants.
+((match_arm
+  pattern: (match_pattern
+    (identifier) @constant))
+  (#lua-match? @constant "^[A-Z]"))
+
+((match_arm
+  pattern: (match_pattern
+    (scoped_identifier
+      name: (identifier) @constant)))
+  (#lua-match? @constant "^[A-Z]"))
+
+((identifier) @constant.builtin
+  (#any-of? @constant.builtin "Some" "None" "Ok" "Err"))
+
+; Macro definitions
+"$" @function.macro
+
+(metavariable) @function.macro
+
+(macro_definition
+  "macro_rules!" @function.macro)
+
+; Attribute macros
+(attribute_item
+  (attribute
+    (identifier) @function.macro))
+
+(inner_attribute_item
+  (attribute
+    (identifier) @function.macro))
+
+(attribute
+  (scoped_identifier
+    (identifier) @function.macro .))
+
+; Derive macros (assume all arguments are types)
+; (attribute
+;   (identifier) @_name
+;   arguments: (attribute (attribute (identifier) @type))
+;   (#eq? @_name "derive"))
+; Function-like macros
+(macro_invocation
+  macro: (identifier) @function.macro)
+
+(macro_invocation
+  macro: (scoped_identifier
+    (identifier) @function.macro .))
+
+; Literals
+(boolean_literal) @boolean
+
+(integer_literal) @number
+
+(float_literal) @number.float
+
+[
+  (raw_string_literal)
+  (string_literal)
+] @string
+
+(escape_sequence) @string.escape
+
+(char_literal) @character
+
+; Keywords
+[
+  "use"
+  "mod"
+] @keyword.import
+
+(use_as_clause
+  "as" @keyword.import)
+
+[
+  "default"
+  "impl"
+  "let"
+  "move"
+  "unsafe"
+  "where"
+] @keyword
+
+[
+  "enum"
+  "struct"
+  "union"
+  "trait"
+  "type"
+] @keyword.type
+
+[
+  "async"
+  "await"
+  "gen"
+] @keyword.coroutine
+
+"try" @keyword.exception
+
+[
+  "ref"
+  "pub"
+  "raw"
+  (mutable_specifier)
+  "const"
+  "static"
+  "dyn"
+  "extern"
+] @keyword.modifier
+
+(lifetime
+  "'" @keyword.modifier)
+
+(lifetime
+  (identifier) @attribute)
+
+(lifetime
+  (identifier) @attribute.builtin
+  (#any-of? @attribute.builtin "static" "_"))
+
+"fn" @keyword.function
+
+[
+  "return"
+  "yield"
+] @keyword.return
+
+(type_cast_expression
+  "as" @keyword.operator)
+
+(qualified_type
+  "as" @keyword.operator)
+
+(use_list
+  (self) @module)
+
+(scoped_use_list
+  (self) @module)
+
+(scoped_identifier
+  [
+    (crate)
+    (super)
+    (self)
+  ] @module)
+
+(visibility_modifier
+  [
+    (crate)
+    (super)
+    (self)
+  ] @module)
+
+[
+  "if"
+  "else"
+  "match"
+] @keyword.conditional
+
+[
+  "break"
+  "continue"
+  "in"
+  "loop"
+  "while"
+] @keyword.repeat
+
+"for" @keyword
+
+(for_expression
+  "for" @keyword.repeat)
+
+; Operators
+[
+  "!"
+  "!="
+  "%"
+  "%="
+  "&"
+  "&&"
+  "&="
+  "*"
+  "*="
+  "+"
+  "+="
+  "-"
+  "-="
+  ".."
+  "..="
+  "..."
+  "/"
+  "/="
+  "<"
+  "<<"
+  "<<="
+  "<="
+  "="
+  "=="
+  ">"
+  ">="
+  ">>"
+  ">>="
+  "?"
+  "@"
+  "^"
+  "^="
+  "|"
+  "|="
+  "||"
+] @operator
+
+(use_wildcard
+  "*" @character.special)
+
+(remaining_field_pattern
+  ".." @character.special)
+
+(range_pattern
+  [
+    ".."
+    "..="
+    "..."
+  ] @character.special)
+
+; Punctuation
+[
+  "("
+  ")"
+  "["
+  "]"
+  "{"
+  "}"
+] @punctuation.bracket
+
+(closure_parameters
+  "|" @punctuation.bracket)
+
+(type_arguments
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(type_parameters
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(bracketed_type
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(for_lifetimes
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+[
+  ","
+  "."
+  ":"
+  "::"
+  ";"
+  "->"
+  "=>"
+] @punctuation.delimiter
+
+(attribute_item
+  "#" @punctuation.special)
+
+(inner_attribute_item
+  [
+    "!"
+    "#"
+  ] @punctuation.special)
+
+(macro_invocation
+  "!" @function.macro)
+
+(never_type
+  "!" @type.builtin)
+
+(macro_invocation
+  macro: (identifier) @_identifier @keyword.exception
+  "!" @keyword.exception
+  (#eq? @_identifier "panic"))
+
+(macro_invocation
+  macro: (identifier) @_identifier @keyword.exception
+  "!" @keyword.exception
+  (#contains? @_identifier "assert"))
+
+(macro_invocation
+  macro: (identifier) @_identifier @keyword.debug
+  "!" @keyword.debug
+  (#eq? @_identifier "dbg"))
+
+; Comments
+[
+  (line_comment)
+  (block_comment)
+] @comment @spell
+
+[
+  (outer_doc_comment_marker)
+  (inner_doc_comment_marker)
+] @comment.documentation
+
+(line_comment
+  (doc_comment)) @comment.documentation
+
+(block_comment
+  (doc_comment)) @comment.documentation
+
+(call_expression
+  function: (scoped_identifier
+    path: (identifier) @_regex
+    (#any-of? @_regex "Regex" "ByteRegexBuilder")
+    name: (identifier) @_new
+    (#eq? @_new "new"))
+  arguments: (arguments
+    (raw_string_literal
+      (string_content) @string.regexp)))
+
+(call_expression
+  function: (scoped_identifier
+    path: (scoped_identifier
+      (identifier) @_regex
+      (#any-of? @_regex "Regex" "ByteRegexBuilder") .)
+    name: (identifier) @_new
+    (#eq? @_new "new"))
+  arguments: (arguments
+    (raw_string_literal
+      (string_content) @string.regexp)))
+
+(call_expression
+  function: (scoped_identifier
+    path: (identifier) @_regex
+    (#any-of? @_regex "RegexSet" "RegexSetBuilder")
+    name: (identifier) @_new
+    (#eq? @_new "new"))
+  arguments: (arguments
+    (array_expression
+      (raw_string_literal
+        (string_content) @string.regexp))))
+
+(call_expression
+  function: (scoped_identifier
+    path: (scoped_identifier
+      (identifier) @_regex
+      (#any-of? @_regex "RegexSet" "RegexSetBuilder") .)
+    name: (identifier) @_new
+    (#eq? @_new "new"))
+  arguments: (arguments
+    (array_expression
+      (raw_string_literal
+        (string_content) @string.regexp))))

bex/tag-preprocessor/queries/typescript.scm

@@ -0,0 +1,208 @@
+; inherits: ecma
+
+"require" @keyword.import
+
+(import_require_clause
+  source: (string) @string.special.url)
+
+[
+  "declare"
+  "implements"
+  "type"
+  "override"
+  "module"
+  "asserts"
+  "infer"
+  "is"
+  "using"
+] @keyword
+
+[
+  "namespace"
+  "interface"
+  "enum"
+] @keyword.type
+
+[
+  "keyof"
+  "satisfies"
+] @keyword.operator
+
+(as_expression
+  "as" @keyword.operator)
+
+(mapped_type_clause
+  "as" @keyword.operator)
+
+[
+  "abstract"
+  "private"
+  "protected"
+  "public"
+  "readonly"
+] @keyword.modifier
+
+; types
+(type_identifier) @type
+
+(predefined_type) @type.builtin
+
+(import_statement
+  "type"
+  (import_clause
+    (named_imports
+      (import_specifier
+        name: (identifier) @type))))
+
+(template_literal_type) @string
+
+(non_null_expression
+  "!" @operator)
+
+; punctuation
+(type_arguments
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(type_parameters
+  [
+    "<"
+    ">"
+  ] @punctuation.bracket)
+
+(object_type
+  [
+    "{|"
+    "|}"
+  ] @punctuation.bracket)
+
+(union_type
+  "|" @punctuation.delimiter)
+
+(intersection_type
+  "&" @punctuation.delimiter)
+
+(type_annotation
+  ":" @punctuation.delimiter)
+
+(type_predicate_annotation
+  ":" @punctuation.delimiter)
+
+(index_signature
+  ":" @punctuation.delimiter)
+
+(omitting_type_annotation
+  "-?:" @punctuation.delimiter)
+
+(adding_type_annotation
+  "+?:" @punctuation.delimiter)
+
+(opting_type_annotation
+  "?:" @punctuation.delimiter)
+
+"?." @punctuation.delimiter
+
+(abstract_method_signature
+  "?" @punctuation.special)
+
+(method_signature
+  "?" @punctuation.special)
+
+(method_definition
+  "?" @punctuation.special)
+
+(property_signature
+  "?" @punctuation.special)
+
+(optional_parameter
+  "?" @punctuation.special)
+
+(optional_type
+  "?" @punctuation.special)
+
+(public_field_definition
+  [
+    "?"
+    "!"
+  ] @punctuation.special)
+
+(flow_maybe_type
+  "?" @punctuation.special)
+
+(template_type
+  [
+    "${"
+    "}"
+  ] @punctuation.special)
+
+(conditional_type
+  [
+    "?"
+    ":"
+  ] @keyword.conditional.ternary)
+
+; Parameters
+(required_parameter
+  pattern: (identifier) @variable.parameter)
+
+(optional_parameter
+  pattern: (identifier) @variable.parameter)
+
+(required_parameter
+  (rest_pattern
+    (identifier) @variable.parameter))
+
+; ({ a }) => null
+(required_parameter
+  (object_pattern
+    (shorthand_property_identifier_pattern) @variable.parameter))
+
+; ({ a = b }) => null
+(required_parameter
+  (object_pattern
+    (object_assignment_pattern
+      (shorthand_property_identifier_pattern) @variable.parameter)))
+
+; ({ a: b }) => null
+(required_parameter
+  (object_pattern
+    (pair_pattern
+      value: (identifier) @variable.parameter)))
+
+; ([ a ]) => null
+(required_parameter
+  (array_pattern
+    (identifier) @variable.parameter))
+
+; a => null
+(arrow_function
+  parameter: (identifier) @variable.parameter)
+
+; global declaration
+(ambient_declaration
+  "global" @module)
+
+; function signatures
+(ambient_declaration
+  (function_signature
+    name: (identifier) @function))
+
+; method signatures
+(method_signature
+  name: (_) @function.method)
+
+(abstract_method_signature
+  name: (property_identifier) @function.method)
+
+; property signatures
+(property_signature
+  name: (property_identifier) @function.method
+  type: (type_annotation
+    [
+      (union_type
+        (parenthesized_type
+          (function_type)))
+      (function_type)
+    ]))

references/tags-queries/ANALYSIS.md

@@ -1,81 +1,212 @@
-# TreeSitter Tag Queries for Dervish
+# Community Tree-Sitter Query Analysis
 
-## What We Got
-
-Queries from 8 official TreeSitter language packages (`references/tags-queries/*.scm`):
-
-| Language | TAGS_QUERY | HIGHLIGHTS_QUERY | Tag nodes | Dervish-relevant |
-|----------|-----------|-----------------|-----------|-----------------|
-| Java | ✅ 20 lines | ✅ 60 lines | `class_declaration`, `method_declaration`, `method_invocation`, `annotation` | `annotation`, `marker_annotation`, `method_invocation` |
-| Python | ✅ 14 lines | ✅ 50 lines | `class_definition`, `function_definition`, `call`, `assignment` | `call`, `decorator` |
-| TypeScript | ✅ 23 lines | ✅ 30 lines | `function_signature`, `interface_declaration`, `method_signature` | (none directly) |
-| Go | ✅ 42 lines | ✅ 55 lines | `function_declaration`, `call_expression`, `method_declaration` | `call_expression` |
-| C# | empty | ✅ | — | — |
-| C++ | ✅ 15 lines | ✅ 40 lines | `struct_specifier`, `function_declarator` | `call_expression` |
-| Rust | ✅ 60 lines | ✅ 80 lines | `struct_item`, `function_item`, `call_expression`, `macro_invocation` | `call_expression`, `macro_invocation` |
-| YAML | — | ✅ 30 lines | — | — |
+Analyzed: July 3, 2026
+Source: nvim-treesitter (master branch) tag queries + highlight queries
 
 ## Key Finding
 
-**Community TAGS_QUERIES are for code navigation (Go to Definition), NOT for Dervish.**
+**Community TAGS queries are for code navigation (Go to Definition), NOT for Dervish.**
 
-They capture:
-- `@definition.class` — where classes are declared
-- `@definition.method` — where methods are declared
-- `@reference.call` — where methods are CALLED (this IS useful for us)
+Dervish needs **behavioral sequences**: what operations happen in what order.
+Tags queries only capture declaration sites and reference locations.
 
-## Dervish Needs Behavioral Nodes
+## Language-by-Language Gap Analysis
 
-From actual code parsing tests, these node types exist across languages:
+### JAVA
 
-| Pattern | Java | Python | Go | Rust |
-|---------|------|--------|----|------|
-| Function calls | `method_invocation` | `call` | `call_expression` | `call_expression` |
-| Annotations | `annotation`, `marker_annotation` | `decorator` | — | `macro_invocation` |
-| Conditionals | `if_statement` | `if_statement` | `if_statement` | `if_expression` |
-| Error throwing | `throw_statement` | `raise_statement` | `return`-based | `return`-based |
-| Error handling | `try_statement` | `try_statement` | — | — |
-| Variable decl | `local_variable_declaration` | `assignment` | `short_var_declaration` | `let_declaration` |
-| Returns | `return_statement` | `return_statement` | `return_statement` | `return` (no _statement) |
+**Tags captures:**
+- `@definition.class` — class declaration sites
+- `@definition.method` — method declaration sites
+- `@definition.interface` — interface declaration sites
+- `@reference.call` — method invocations (ONLY with `argument_list`)
+- `@reference.implementation` — implements clauses
+- `@reference.class` — `new Type()` expressions + superclass refs
 
-## Universal Query Approach (Confirmed Viable)
+**What is MISSING for Dervish:**
+- `@annotation` / `@decorator` — annotations only exist in highlights as `@attribute`, not in tags
+- `@reference.call` excludes parameterless calls like `foo()` — requires `argument_list`
+- No `throw_statement`, `try_statement`, `catch_clause` in tags
+- No `if_statement`, `return_statement` captures
+- No mechanism to extract ORDERED sequences
+- Highlights collapse all control-flow keywords into `@keyword`
 
-TreeSitter silently ignores non-existent node types in queries. One query for all languages:
+### KOTLIN (from highlights.scm since no tags.scm exists at that path)
 
-```scheme
-; === CALLS (all imperative langs) ===
-(call_expression) @call          ; Go, Rust, C++, TS/JS
-(call) @call                     ; Python
-(method_invocation) @call        ; Java
+**Available captures (highlights only):**
+- `@function.call` — `call_expression` with `simple_identifier`
+- `@constructor` — `constructor_invocation`, `primary_constructor`, secondary
+- `@attribute` — `annotation` with `user_type`
+- `@keyword.conditional` — `if`/`else`/`when`
+- `@keyword.repeat` — `for`/`do`/`while`
+- `@keyword.exception` — `try`/`catch`/`throw`/`finally`
+- `@keyword.return` — `return`
+- `@function` — `function_declaration`
 
-; === METADATA ===
-(annotation) @meta               ; Java, C#, Kotlin
-(marker_annotation) @meta         ; Java
-(decorator) @meta                 ; Python
-(macro_invocation) @meta          ; Rust macros
+**What is MISSING for Dervish:**
+- No tags.scm available on nvim-treesitter master for Kotlin
+- Call expressions captured as `@function.call` in highlights, not structured for sequence extraction
+- Navigation expressions (`obj.method()`) captured but as `@function.call` on the suffix
+- No `when_structure` / `when_condition` structural capture
+- No `navigation_expression` itself as a token — only the method name inside
+- No sequencing mechanism
 
-; === CONTROL FLOW ===
-(if_statement) @branch            ; Java, Go, Python, C++
-(if_expression) @branch           ; Rust
-(throw_statement) @throw          ; Java, C++, C#
-(raise_statement) @throw          ; Python
-(try_statement) @try              ; Java, Python, C++, TS/JS
-(catch_clause) @catch             ; Java, C++, TS/JS
-(except_clause) @catch            ; Python
-(return_statement) @return        ; Java, Go, Python, C++
+### PYTHON
 
-; === RESOURCE MANAGEMENT ===
-(with_statement) @resource        ; Python, TS/JS
-(defer_statement) @resource       ; Go
+**Tags captures:**
+- `@definition.constant` — module-level assignments
+- `@definition.class` — class definitions
+- `@definition.function` — function definitions
+- `@reference.call` — direct function calls + method calls via attribute
 
-; === OBJECT CREATION ===
-(object_creation_expression) @new ; Java, C++
-(new_expression) @new             ; TS/JS
-```
+**What is MISSING for Dervish:**
+- No `decorator` capture in tags (only in highlights as `@function`)
+- `call` only captured as reference, not as behavioral sequence token
+- No `raise_statement`, `try_statement`, `except_clause` in tags
+- No `if_statement`, `return_statement`, `with_statement` in tags
+- Highlights `@function` conflates decorators, definitions, and calls
 
-## Next Steps
+### GO
 
-1. Implement TreeSitter parser wrapper that loads correct grammar by file extension
-2. Apply the universal query to extract symbol sequences
-3. Add single-pass frequency analysis to filter noise
-4. Feed cleaned sequences into Dervish (CRX/iDRegEx)
+**Tags captures:**
+- `@definition.function` — function declarations (with doc comments)
+- `@definition.method` — method declarations
+- `@definition.type` — type specs
+- `@reference.call` — direct calls + selector calls (`obj.Method()`)
+- `@reference.type` — type identifier references
+- Plus: var/const/import/struct/interface tracking
+
+**What is MISSING for Dervish:**
+- No `defer_statement` capture (only `defer` keyword in highlights)
+- No `go` (goroutine launch) as structural capture
+- No `if_statement`, `return_statement`, `for_statement`, `switch_statement` in tags
+- `call_expression` well captured but only function name as `@name`, not whole expression
+- Highlights distinguish builtins (`append`, `len`, `make`, `panic`, etc.) but not structured
+
+### RUST
+
+**Tags captures:**
+- `@definition.class` — struct/enum/union/type alias
+- `@definition.method` — methods in impl blocks
+- `@definition.function` — free functions
+- `@definition.interface` — trait definitions
+- `@definition.module` — module definitions
+- `@definition.macro` — macro definitions
+- `@reference.call` — direct calls + method calls + macro invocations
+- `@reference.implementation` — trait/inherent impl tracking
+
+**What is MISSING for Dervish:**
+- Best coverage of any language — captures calls, macros, implementations
+- Still: no `if_expression` / `match_expression` / `return` in tags
+- No `unsafe` block capture
+- `@attribute` (`#[derive]`) only in highlights, not tags
+- No sequencing mechanism
+
+### TYPESCRIPT / JAVASCRIPT
+
+**Tags captures:**
+- `@definition.function` — function signatures only (definitions)
+- `@definition.method` — method signatures
+- `@definition.class` — class + abstract class declarations
+- `@definition.module` — module declarations
+- `@definition.interface` — interface declarations
+- `@reference.type` — type annotations
+- `@reference.class` — `new Foo()` constructor calls
+
+**What is MISSING for Dervish:**
+- **NO `call_expression` capture at all** — neither in tags nor highlights
+- **NO `@reference.call`** — critical gap
+- No function/method call tracking
+- Highlight query is extremely minimal (35 lines)
+- Missing: `arrow_function`, `call_expression`, `method_invocation`
+- Query file seems designed for `.d.ts` type definitions, not implementation code
+
+### C++
+
+**Tags captures:**
+- `@definition.class` — struct/union/class specifiers
+- `@definition.function` — function declarators
+- `@definition.method` — qualified methods (with namespace scope)
+- `@definition.type` — typedef/enum
+
+**What is MISSING for Dervish:**
+- **NO `call_expression` capture in tags** — call tracking only in highlights as `@function`
+- **NO `@reference.call`** in tags at all
+- No `template_function`, `template_method` in tags
+- No `new_expression`, `delete_expression` in tags
+- No `throw_statement`, `try_statement`, `catch_clause` in tags
+- No sequencing mechanism
+
+### YAML
+
+**What is MISSING for Dervish:**
+- No tags query exists at all
+- YAML is data-oriented, not code-oriented
+- Highlights only capture data types (strings, numbers, booleans) and key names
+- YAML sequence extraction (for Ansible/Helm) needs a different approach entirely
+
+## Cross-Cutting Findings
+
+### What community tags DO capture (for Dervish, partially useful):
+
+| Capture | Languages | Dervish Value |
+|---------|-----------|--------------|
+| `@reference.call` | Java, Python, Go, Rust | **Partial** — identifies call sites but per-language inconsistencies |
+| `@reference.class` / `new` | Java, TypeScript | **Partial** — constructor calls |
+| `@reference.implementation` | Java, Rust | Low — inheritance tracking |
+| macro invocations (as `@reference.call`) | Rust | **Useful** — Rust macros ARE behavioral tokens |
+
+### What community tags do NOT capture (GAPS):
+
+| Dervish Need | In Tags? | In Highlights? |
+|-------------|----------|---------------|
+| `@annotation` / `@decorator` / `@attribute` | **0 languages** | Java `@attribute`, Python `@function` (decorator), Rust `@attribute`, Kotlin `@attribute` |
+| Control flow (`if`/`else`/`when`) | **0 languages** | All: collapsed in `@keyword` |
+| Error handling (`try`/`catch`/`throw`) | **0 languages** | All: collapsed in `@keyword` |
+| `@return` | **0 languages** | All: collapsed in `@keyword` |
+| Call expressions | Java, Python, Go, Rust | All except TS |
+| Ordered sequences | **0 languages** | **0 languages** |
+| Variable declarations | Go only | Not structural |
+| Resource management (`defer`/`with`) | **0 languages** | Go: `defer` in keyword; Python: `with` in keyword |
+| Goroutines / async / coroutines | **0 languages** | Go `go` in keyword; Python async/await in keyword; Kotlin `suspend` as `@keyword.coroutine` |
+
+### The Naming Inconsistency Problem
+
+Same tree-sitter node types have DIFFERENT capture names across languages:
+
+| Node | Java | Python | Go | Rust | C++ | TS |
+|------|------|--------|----|------|-----|----|
+| call expr | `@reference.call` | `@reference.call` | `@reference.call` | `@reference.call` | NONE | NONE |
+| class def | `@definition.class` | `@definition.class` | -- | `@definition.class` | `@definition.class` | `@definition.class` |
+| function def | -- | `@definition.function` | `@definition.function` | `@definition.function` | `@definition.function` | `@definition.function` |
+
+Dervish cannot rely on capture names alone. Must either:
+1. Use universal query with Dervish-specific capture names, OR
+2. Map language-specific capture names to canonical Dervish vocabulary
+
+### Community tags.scm availability on nvim-treesitter master
+
+Checked July 3, 2026 via `raw.githubusercontent.com/nvim-treesitter/nvim-treesitter/master/queries/<lang>/tags.scm`:
+
+| Language | tags.scm exists? | highlights.scm? |
+|----------|-----------------|-----------------|
+| Java | 404 | yes (in refs) |
+| Kotlin | 404 | yes (newly downloaded) |
+| Python | 404 | yes (in refs) |
+| Go | 404 | yes (in refs) |
+| Rust | 404 | yes (in refs) |
+| TypeScript | 404 | yes (in refs) |
+| C++ | 404 | yes (in refs) |
+| YAML | never | yes (in refs) |
+
+All tags.scm returned 404 — nvim-treesitter may have restructured or moved to a different branch/tag.
+
+## Verdict
+
+**Community queries alone are insufficient for Dervish sequence extraction.** They:
+1. Purpose-built for navigation, not behavioral sequence extraction
+2. Lack critical behavioral captures (annotations, control flow, error handling)
+3. Inconsistent across languages
+4. No sequencing/traversal mechanism
+5. tags.scm no longer available on nvim-treesitter master
+
+A **universal query file** (like the deleted `universal.scm`) using actual tree-sitter node type names is the correct approach, supplemented by a custom AST traversal to produce ordered sequences.