mirror of
https://github.com/safishamsi/graphify.git
synced 2026-09-22 21:45:58 +00:00
feat: add VB.NET (.vb) language support via tree-sitter
This commit adds full VB.NET language support to graphify, raising the supported language count from 25 to 26. The implementation follows the established LanguageConfig pattern used by all other tree-sitter-backed extractors. New dependency: - Adds optional extra [vbnet] backed by tree-sitter-vbnet (published to PyPI at https://pypi.org/project/tree-sitter-vbnet/0.1.0/). Install with: pip install graphifyy[vbnet] graphify/detect.py: - Added .vb to CODE_EXTENSIONS so VB.NET files are discovered during corpus ingestion and file-system watching. graphify/extract.py: - _import_vbnet(): import handler for imports_statement nodes; emits imports edges using the namespace_name child text. - _vbnet_extra_walk(): extra-walk hook that intercepts namespace_block nodes, emits a namespace node, and recurses. - _VBNET_CONFIG: full LanguageConfig covering class_block / module_block / structure_block / interface_block as class types; method_declaration / constructor_declaration / property_declaration as function types; invocation call nodes with target/member_access fields. - VB.NET-specific branches in _extract_generic: * Class body: VB.NET has no wrapper body node; inherits and implements are named fields directly on the class_block. Emits separate inherits and implements edges for each base type, stripping generic arguments. * Constructor name: constructor_declaration carries no name field in the grammar; always resolves to New. * Function body: uses the declaration node itself as body sentinel so the call-graph pass can find invocations inside methods. - extract_vbnet(path): public wrapper that delegates to _extract_generic. - _DISPATCH['.vb']: routes .vb files to extract_vbnet. pyproject.toml: - Added vbnet = ['tree-sitter-vbnet'] optional dependency group. - Added 'tree-sitter-vbnet' to the all extra. tests/fixtures/sample.vb: - New fixture file exercising: Imports statements, Namespace block, Interface, Class with Inherits + Implements, Module, Structure, Sub/Function/Property methods, and method calls. tests/test_languages.py: - Added 13 tests covering: no-error, class/interface/module/structure detection, method detection, imports relation, inherits edge, implements edge, and no-dangling-edges invariant. README.md: - Updated language count 25 to 26. - Added VB.NET to language list and file-extension table.
This commit is contained in:
Rangarajan Ramaswamy
+1
-1
@@ -18,7 +18,7 @@ class FileType(str, Enum):
|
||||
|
||||
_MANIFEST_PATH = "graphify-out/manifest.json"
|
||||
|
||||
CODE_EXTENSIONS = {'.py', '.ts', '.js', '.jsx', '.tsx', '.mjs', '.ejs', '.go', '.rs', '.java', '.cpp', '.cc', '.cxx', '.c', '.h', '.hpp', '.rb', '.swift', '.kt', '.kts', '.cs', '.scala', '.php', '.lua', '.toc', '.zig', '.ps1', '.ex', '.exs', '.m', '.mm', '.jl', '.vue', '.svelte', '.dart', '.v', '.sv', '.sql'}
|
||||
CODE_EXTENSIONS = {'.py', '.ts', '.js', '.jsx', '.tsx', '.mjs', '.ejs', '.go', '.rs', '.java', '.cpp', '.cc', '.cxx', '.c', '.h', '.hpp', '.rb', '.swift', '.kt', '.kts', '.cs', '.scala', '.php', '.lua', '.toc', '.zig', '.ps1', '.ex', '.exs', '.m', '.mm', '.jl', '.vue', '.svelte', '.dart', '.v', '.sv', '.sql', '.vb'}
|
||||
DOC_EXTENSIONS = {'.md', '.mdx', '.txt', '.rst', '.html', '.yaml', '.yml'}
|
||||
PAPER_EXTENSIONS = {'.pdf'}
|
||||
IMAGE_EXTENSIONS = {'.png', '.jpg', '.jpeg', '.gif', '.webp', '.svg'}
|
||||
|
||||
@@ -472,6 +472,25 @@ def _swift_extra_walk(node, source: bytes, file_nid: str, stem: str, str_path: s
|
||||
return False
|
||||
|
||||
|
||||
def _vbnet_extra_walk(node, source: bytes, file_nid: str, stem: str, str_path: str,
|
||||
nodes: list, edges: list, seen_ids: set, function_bodies: list,
|
||||
parent_class_nid: str | None, add_node_fn, add_edge_fn,
|
||||
walk_fn) -> bool:
|
||||
"""Handle namespace_block for VB.NET. Returns True if handled."""
|
||||
if node.type == "namespace_block":
|
||||
name_node = node.child_by_field_name("name")
|
||||
if name_node:
|
||||
ns_name = _read_text(name_node, source)
|
||||
ns_nid = _make_id(stem, ns_name)
|
||||
line = node.start_point[0] + 1
|
||||
add_node_fn(ns_nid, ns_name, line)
|
||||
add_edge_fn(file_nid, ns_nid, "contains", line)
|
||||
for child in node.children:
|
||||
walk_fn(child, parent_class_nid)
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
# ── Language configs ──────────────────────────────────────────────────────────
|
||||
|
||||
_PYTHON_CONFIG = LanguageConfig(
|
||||
@@ -686,6 +705,24 @@ def _import_swift(node, source: bytes, file_nid: str, stem: str, edges: list, st
|
||||
break
|
||||
|
||||
|
||||
def _import_vbnet(node, source: bytes, file_nid: str, stem: str, edges: list, str_path: str) -> None:
|
||||
"""Handle VB.NET 'Imports System.Collections.Generic' statements."""
|
||||
for child in node.children:
|
||||
if child.type == "namespace_name":
|
||||
raw = _read_text(child, source).strip()
|
||||
if raw:
|
||||
tgt_nid = _make_id(raw)
|
||||
edges.append({
|
||||
"source": file_nid,
|
||||
"target": tgt_nid,
|
||||
"relation": "imports",
|
||||
"confidence": "EXTRACTED",
|
||||
"source_file": str_path,
|
||||
"source_location": f"L{node.start_point[0] + 1}",
|
||||
"weight": 1.0,
|
||||
})
|
||||
|
||||
|
||||
_SWIFT_CONFIG = LanguageConfig(
|
||||
ts_module="tree_sitter_swift",
|
||||
class_types=frozenset({"class_declaration", "protocol_declaration"}),
|
||||
@@ -701,6 +738,20 @@ _SWIFT_CONFIG = LanguageConfig(
|
||||
import_handler=_import_swift,
|
||||
)
|
||||
|
||||
_VBNET_CONFIG = LanguageConfig(
|
||||
ts_module="tree_sitter_vbnet",
|
||||
ts_language_fn="language",
|
||||
class_types=frozenset({"class_block", "module_block", "structure_block", "interface_block"}),
|
||||
function_types=frozenset({"method_declaration", "constructor_declaration", "property_declaration"}),
|
||||
import_types=frozenset({"imports_statement"}),
|
||||
call_types=frozenset({"invocation"}),
|
||||
call_function_field="target",
|
||||
call_accessor_node_types=frozenset({"member_access"}),
|
||||
call_accessor_field="member",
|
||||
function_boundary_types=frozenset({"method_declaration", "constructor_declaration", "property_declaration"}),
|
||||
import_handler=_import_vbnet,
|
||||
)
|
||||
|
||||
|
||||
# ── Generic extractor ─────────────────────────────────────────────────────────
|
||||
|
||||
@@ -904,6 +955,43 @@ def _extract_generic(path: Path, config: LanguageConfig) -> dict:
|
||||
if body:
|
||||
for child in body.children:
|
||||
walk(child, parent_class_nid=class_nid)
|
||||
elif config.ts_module == "tree_sitter_vbnet":
|
||||
# VB.NET class/module/structure/interface have no separate body node —
|
||||
# inherits/implements appear as named fields, members are inline children.
|
||||
def _emit_vbnet_parent(clause_node, rel: str) -> None:
|
||||
for child in clause_node.children:
|
||||
if not child.is_named:
|
||||
continue
|
||||
raw = _read_text(child, source).strip()
|
||||
if not raw:
|
||||
continue
|
||||
# Strip generic args e.g. IList(Of T) → IList
|
||||
base_name = raw.split("(")[0].strip().split(".")[-1]
|
||||
if not base_name:
|
||||
continue
|
||||
base_nid = _make_id(stem, base_name)
|
||||
if base_nid not in seen_ids:
|
||||
base_nid = _make_id(base_name)
|
||||
if base_nid not in seen_ids:
|
||||
nodes.append({
|
||||
"id": base_nid,
|
||||
"label": base_name,
|
||||
"file_type": "code",
|
||||
"source_file": "",
|
||||
"source_location": "",
|
||||
})
|
||||
seen_ids.add(base_nid)
|
||||
add_edge(class_nid, base_nid, rel, line)
|
||||
|
||||
inherits_node = node.child_by_field_name("inherits")
|
||||
if inherits_node:
|
||||
_emit_vbnet_parent(inherits_node, "inherits")
|
||||
implements_node = node.child_by_field_name("implements")
|
||||
if implements_node:
|
||||
_emit_vbnet_parent(implements_node, "implements")
|
||||
|
||||
for child in node.children:
|
||||
walk(child, parent_class_nid=class_nid)
|
||||
return
|
||||
|
||||
# Event listener property arrays: $listen = [Event::class => [Listener::class]]
|
||||
@@ -964,6 +1052,9 @@ def _extract_generic(path: Path, config: LanguageConfig) -> dict:
|
||||
func_name: str | None = "deinit"
|
||||
elif t == "subscript_declaration":
|
||||
func_name = "subscript"
|
||||
elif config.ts_module == "tree_sitter_vbnet" and t == "constructor_declaration":
|
||||
# VB.NET Sub New has no 'name' field — always named "New"
|
||||
func_name = "New"
|
||||
elif config.resolve_function_name_fn is not None:
|
||||
# C/C++ style: use declarator
|
||||
declarator = node.child_by_field_name("declarator")
|
||||
@@ -995,6 +1086,10 @@ def _extract_generic(path: Path, config: LanguageConfig) -> dict:
|
||||
body = _find_body(node, config)
|
||||
if body:
|
||||
function_bodies.append((func_nid, body))
|
||||
elif config.ts_module == "tree_sitter_vbnet":
|
||||
# VB.NET method/property/constructor bodies have no wrapper node —
|
||||
# use the declaration node itself so walk_calls can find invocations.
|
||||
function_bodies.append((func_nid, node))
|
||||
return
|
||||
|
||||
# JS/TS arrow functions and C# namespaces — language-specific extra handling
|
||||
@@ -1016,6 +1111,12 @@ def _extract_generic(path: Path, config: LanguageConfig) -> dict:
|
||||
parent_class_nid, add_node, add_edge):
|
||||
return
|
||||
|
||||
if config.ts_module == "tree_sitter_vbnet":
|
||||
if _vbnet_extra_walk(node, source, file_nid, stem, str_path,
|
||||
nodes, edges, seen_ids, function_bodies,
|
||||
parent_class_nid, add_node, add_edge, walk):
|
||||
return
|
||||
|
||||
# Default: recurse
|
||||
for child in node.children:
|
||||
walk(child, parent_class_nid=None)
|
||||
@@ -3491,6 +3592,7 @@ def extract(paths: list[Path], cache_root: Path | None = None) -> dict:
|
||||
".v": extract_verilog,
|
||||
".sv": extract_verilog,
|
||||
".sql": extract_sql,
|
||||
".vb": extract_vbnet,
|
||||
}
|
||||
|
||||
total = len(paths)
|
||||
|
||||
Reference in New Issue
Block a user