Progress towards tree-sitter feature

[saniyafatima07]

Addresses PR #1080 and #2931

• Updated few outdated tree-sitter queries
• Ensure all related test cases pass

Checklist

• No CHANGELOG update needed

• No new tests needed

• No documentation update needed

• This submission includes AI-generated code and I have provided details in the description.

[gemini-code-assist]

Code Review

This pull request introduces Tree-Sitter Script Analysis to capa, enabling feature extraction from script languages such as C#, Python, HTML, and ASPX templates. It adds a new Tree-Sitter-based feature extractor, auto-detection capabilities, and signature-based tools, along with comprehensive tests and updated dependencies. The code review feedback primarily addresses compatibility issues with the upgraded tree-sitter library (version 0.25.0), specifically pointing out that QueryCursor has been removed and the Parser instantiation has changed in tree-sitter versions >= 0.21.0. The feedback provides actionable suggestions to execute queries directly and update parser usage. Additionally, it identifies a bug in integer suffix parsing and recommends replacing a deprecated importlib.resources API.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[gemini-code-assist]

Since QueryCursor is removed, you can pass the query directly to get_captured_nodes without instantiating a cursor.

Suggested change

	def get_function_call_names(self, node: Node) -> Iterator[Node]:
	cursor = QueryCursor(self.query.function_call_name)
	yield from self.get_captured_nodes(cursor, node)
	def get_imported_constants(self, node: Node) -> Iterator[Node]:
	cursor = QueryCursor(self.query.imported_constant_name)
	yield from self.get_captured_nodes(cursor, node)
	def get_function_call_names(self, node: Node) -> Iterator[Node]:
	yield from self.get_captured_nodes(self.query.function_call_name, node)
	def get_imported_constants(self, node: Node) -> Iterator[Node]:
	yield from self.get_captured_nodes(self.query.imported_constant_name, node)

[gemini-code-assist]

Since QueryCursor is removed in tree-sitter >= 0.21.0, you should execute the query directly using self.query.namespace.captures(target_node). This returns a list of (Node, str) tuples representing the captured nodes and their capture names.

Suggested change

	def get_namespaces(self, node: Optional[Node] = None) -> List[Tuple[Node, str]]:
	target_node = self.tree.root_node if node is None else node
	cursor = QueryCursor(self.query.namespace)
	namespace_captures: List[Tuple[Node, str]] = []
	for query_name, nodes in cursor.captures(target_node).items():
	for namespace_node in nodes:
	namespace_captures.append((namespace_node, query_name))
	return sorted(namespace_captures, key=self.get_node_capture_sort_key)
	def get_namespaces(self, node: Optional[Node] = None) -> List[Tuple[Node, str]]:
	target_node = self.tree.root_node if node is None else node
	captures = self.query.namespace.captures(target_node)
	namespace_captures: List[Tuple[Node, str]] = []
	for namespace_node, query_name in captures:
	namespace_captures.append((namespace_node, query_name))
	return sorted(namespace_captures, key=self.get_node_capture_sort_key)

[gemini-code-assist]

Since QueryCursor is removed in tree-sitter >= 0.21.0, you should execute the query directly using query.captures(node).

Suggested change

	def _contains_errors(ts_language, node: Node) -> bool:
	query = Query(ts_language, "(ERROR) @error")
	return bool(QueryCursor(query).captures(node))
	def _contains_errors(ts_language, node: Node) -> bool:
	query = Query(ts_language, "(ERROR) @error")
	return bool(query.captures(node))

[gemini-code-assist]

Since QueryCursor is removed, you can pass the query directly to get_captured_nodes without instantiating a cursor.

Suggested change

	def get_string_literals(self, node: Node) -> Iterator[Node]:
	cursor = QueryCursor(self.query.string_literal)
	yield from self.get_captured_nodes(cursor, node)
	def get_integer_literals(self, node: Node) -> Iterator[Node]:
	cursor = QueryCursor(self.query.integer_literal)
	yield from self.get_captured_nodes(cursor, node)
	def get_string_literals(self, node: Node) -> Iterator[Node]:
	yield from self.get_captured_nodes(self.query.string_literal, node)
	def get_integer_literals(self, node: Node) -> Iterator[Node]:
	yield from self.get_captured_nodes(self.query.integer_literal, node)

[gemini-code-assist]

In tree-sitter >= 0.21.0, the Parser constructor does not accept a Language argument. You must set the language attribute after instantiating the parser.

Suggested change

	def parse(self) -> Tree:
	parser = Parser(self.query.language)
	return parser.parse(self.buf)
	def parse(self) -> Tree:
	parser = Parser()
	parser.language = self.query.language
	return parser.parse(self.buf)

[gemini-code-assist]

Since QueryCursor is removed, you can pass the query directly to get_captured_nodes without instantiating a cursor.

Suggested change

	def get_content_sections(self) -> Iterator[Node]:
	cursor = QueryCursor(self.query.content)
	yield from self.get_captured_nodes(cursor, self.tree.root_node)
	def get_content_sections(self) -> Iterator[Node]:
	yield from self.get_captured_nodes(self.query.content, self.tree.root_node)

[gemini-code-assist]

In tree-sitter >= 0.21.0, QueryCursor has been removed. Import Query instead to execute queries directly.

Suggested change

	from tree_sitter import Node, Tree, Parser, QueryCursor
	from tree_sitter import Node, Tree, Parser, Query

[gemini-code-assist]

In tree-sitter >= 0.21.0, QueryCursor has been completely removed. Executing queries is now done directly via Query.captures or Language.query. Importing QueryCursor will raise an ImportError at runtime.

Suggested change

	from tree_sitter import Node, Tree, Query, Parser, Language, QueryCursor
	from tree_sitter import Node, Tree, Query, Parser, Language

[gemini-code-assist]

There is a bug in parse_integer when stripping suffixes. If an integer literal has multiple suffixes (e.g., 100ul in C#), the loop only strips the last character of the suffix that matched first, leaving the other suffix character intact (e.g., leaving 100u), which then fails to parse as an integer and raises a ValueError. Using rstrip with a combined set of uppercase and lowercase suffixes is more robust and correctly handles multi-character suffixes.

Suggested change

	def parse_integer(self, integer: str) -> int:
	for suffix in self.integer_suffixes:
	if integer.endswith(suffix):
	integer = integer[:-1]
	for prefix, base in self.integer_prefixes:
	if integer.startswith(prefix):
	return int(integer, base)
	return int(integer)
	def parse_integer(self, integer: str) -> int:
	suffixes = "".join(self.integer_suffixes)
	if suffixes:
	integer = integer.rstrip(suffixes + suffixes.upper())
	for prefix, base in self.integer_prefixes:
	if integer.startswith(prefix):
	return int(integer, base)
	return int(integer)

[gemini-code-assist]

importlib.resources.read_text is deprecated since Python 3.11. Use importlib.resources.files instead, which is fully supported in Python 3.10+.

Suggested change

	def load_import_signatures(self, signature_file: str) -> Dict[str, set[str]]:
	signatures = json.loads(importlib.resources.read_text(capa.features.extractors.ts.signatures, signature_file))
	return {category: set(names) for category, names in signatures.items()}
	def load_import_signatures(self, signature_file: str) -> Dict[str, set[str]]:
	ref = importlib.resources.files(capa.features.extractors.ts.signatures) / signature_file
	signatures = json.loads(ref.read_text(encoding="utf-8"))
	return {category: set(names) for category, names in signatures.items()}