mirror of
https://github.com/colbymchenry/codegraph.git
synced 2026-11-15 02:44:22 +08:00
A Python class with a parameterized base had no extends edge. The grammar parses Base[str] in a base list as a subscript, and the base-list reader took only bare identifiers and attributes, so the base was skipped, on the wasm path and in the kernel alike. Everything that follows the class hierarchy missed such a class. The resolver's own text reader of a base list, pythonBases, also looked up Base[str] verbatim and split Pair[str, int] at its inner comma, so current = Leaf() then current.run() did not reach Base.run. A subscript base is now unwrapped to its value before the identifier or attribute check, in src/extraction/tree-sitter.ts and in the kernel's python.rs. pythonBases drops bracketed type arguments before splitting the list. Generic[T] and Protocol[T] stay outside the project like their plain forms; a computed base, a subscript of a subscript and keyword arguments link nothing. Validation: - The test file runs on both arms: red on main's source and kernel (12 of 16 fail, 6 per arm), green here (16 passed). - Kernel parity with this kernel on 3,155 Python files of flask, requests, mypy, litestar, sqlalchemy, polar and django: 0 diffs, and the same 5 files defer to wasm as on main. The kernel and wasm edge dumps of the repos run both ways are identical. - A/B against main on 7 Python repos, 457,948 edges: 1,492 added (901 extends, 555 calls, 36 references), 0 removed, 607 call sites moved, 223 kept their target with higher confidence. polar: 491 self.get_one_or_none() style calls move from the protocol stub RepositoryProtocol at 0.4 to RepositoryBase and its mixin at 0.9. litestar: 12 calls in GenericSyncMockRepository move from AbstractAsyncRepository to AbstractSyncRepository. sqlalchemy: 435 extends and 554 calls added, like t.insert() reaching TableClause.insert. We read 44 sampled changes and every small bucket. They read right, except 12 self.op() sites that move to the typing-only overload SQLCoreOperations.op and one Enum.copy that moves to TypeEngine.copy. - 3 of the 901 extends are wrong: sqlalchemy's Sequence[_T], Tuple[int, ...] and MutableSet[_T] from typing link to its own classes of those names. The plain form does this on main (28 class X(Enum) there), and none of the 3 brought a call edge. - Controls express and gin: full dumps byte-identical. - Index cost with PR #3001 on top, sqlalchemy, median of 3 interleaved: 23.7 s on main, 25.2 s here, with 1,143 more edges. Original PR #2998 by @JosefAschauer. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
248 lines
6.3 KiB
TypeScript
248 lines
6.3 KiB
TypeScript
/**
|
|
* A Python class with a parameterized base, `class Leaf(Base[str])`, extends
|
|
* `Base`. The grammar parses `Base[str]` in the base list as a `subscript`,
|
|
* and the base-list reader took only bare identifiers and attributes, so such
|
|
* a class had no `extends` edge at all. The reference now names the subscript's
|
|
* value, on the wasm path and in the kernel alike (python is kernel-routed in
|
|
* every published bundle, so each arm runs here; the kernel arm skips when no
|
|
* kernel binary is staged, like the parity suites). The resolver's own reading
|
|
* of a class's base list (`pythonBases`, behind module-global and
|
|
* `self.` dispatch) drops the type arguments the same way.
|
|
*/
|
|
import { describe, it, expect, beforeAll, afterAll } from 'vitest';
|
|
import * as fs from 'fs';
|
|
import * as os from 'os';
|
|
import * as path from 'path';
|
|
import { CodeGraph } from '../src';
|
|
|
|
const KERNEL_PATH = path.join(
|
|
__dirname,
|
|
'..',
|
|
'codegraph-kernel',
|
|
'prebuilds',
|
|
`${process.platform}-${process.arch}`,
|
|
'codegraph-kernel.node'
|
|
);
|
|
const kernelAvailable = fs.existsSync(KERNEL_PATH) || process.env.CODEGRAPH_KERNEL_EXPECT === '1';
|
|
|
|
const FILES: Record<string, string> = {
|
|
'app/models.py': `from typing import Generic, TypeVar
|
|
|
|
T = TypeVar("T")
|
|
U = TypeVar("U")
|
|
|
|
|
|
class Base(Generic[T]):
|
|
def run(self):
|
|
pass
|
|
|
|
|
|
class Pair(Generic[T, U]):
|
|
pass
|
|
|
|
|
|
class Mixin:
|
|
pass
|
|
|
|
|
|
class Meta(type):
|
|
pass
|
|
`,
|
|
'app/leaves.py': `from app import models
|
|
from app.models import Base, Pair, Mixin, Meta
|
|
|
|
|
|
class Plain(Base):
|
|
pass
|
|
|
|
|
|
class Leaf(Base[str]):
|
|
pass
|
|
|
|
|
|
class Nested(Base[list[int]]):
|
|
pass
|
|
|
|
|
|
class Two(Pair[str, dict[str, int]]):
|
|
pass
|
|
|
|
|
|
class Multi(
|
|
Base[
|
|
str
|
|
]
|
|
):
|
|
pass
|
|
|
|
|
|
class Chained(Base[int][str]):
|
|
pass
|
|
|
|
|
|
class Both(Mixin, Base[str]):
|
|
pass
|
|
|
|
|
|
class Dotted(models.Base[int]):
|
|
pass
|
|
|
|
|
|
class DottedPlain(models.Base):
|
|
pass
|
|
|
|
|
|
class Keyword(Base[str], metaclass=Meta):
|
|
pass
|
|
|
|
|
|
def make():
|
|
return Base
|
|
|
|
|
|
class Computed(make()[0]):
|
|
pass
|
|
`,
|
|
'app/globals.py': `from typing import Generic, TypeVar
|
|
|
|
T = TypeVar("T")
|
|
U = TypeVar("U")
|
|
|
|
|
|
class Base(Generic[T]):
|
|
def run(self):
|
|
pass
|
|
|
|
|
|
class Pair(Generic[T, U]):
|
|
def run(self):
|
|
pass
|
|
|
|
|
|
class Other:
|
|
def run(self):
|
|
pass
|
|
|
|
|
|
class Plain(Base):
|
|
pass
|
|
|
|
|
|
class Leaf(Base[str]):
|
|
pass
|
|
|
|
|
|
class Two(Pair[str, dict[str, int]]):
|
|
pass
|
|
|
|
|
|
current_a = Plain()
|
|
current_b = Leaf()
|
|
current_c = Two()
|
|
|
|
|
|
def use_plain():
|
|
current_a.run()
|
|
|
|
|
|
def use_leaf():
|
|
current_b.run()
|
|
|
|
|
|
def use_two():
|
|
current_c.run()
|
|
`,
|
|
};
|
|
|
|
const arms = [
|
|
{ arm: 'wasm', env: { CODEGRAPH_KERNEL: '0' }, skip: false },
|
|
{ arm: 'kernel', env: { CODEGRAPH_KERNEL_LANGS: 'python' }, skip: !kernelAvailable },
|
|
];
|
|
|
|
describe.each(arms)('a parameterized Python base names its class ($arm)', ({ env, skip }) => {
|
|
let root = '';
|
|
let cg: CodeGraph;
|
|
const saved: Record<string, string | undefined> = {};
|
|
|
|
beforeAll(async () => {
|
|
if (skip) return;
|
|
for (const [k, v] of Object.entries(env)) {
|
|
saved[k] = process.env[k];
|
|
process.env[k] = v;
|
|
}
|
|
root = fs.mkdtempSync(path.join(os.tmpdir(), 'cg-py-generic-bases-'));
|
|
for (const [rel, content] of Object.entries(FILES)) {
|
|
fs.mkdirSync(path.dirname(path.join(root, rel)), { recursive: true });
|
|
fs.writeFileSync(path.join(root, rel), content);
|
|
}
|
|
fs.writeFileSync(path.join(root, 'app/__init__.py'), '');
|
|
cg = await CodeGraph.init(root, { index: true });
|
|
});
|
|
|
|
afterAll(() => {
|
|
cg?.close();
|
|
if (root) fs.rmSync(root, { recursive: true, force: true });
|
|
for (const [k, v] of Object.entries(saved)) {
|
|
if (v === undefined) delete process.env[k];
|
|
else process.env[k] = v;
|
|
}
|
|
});
|
|
|
|
/** Names of the classes `name` in app/leaves.py extends. */
|
|
const bases = (name: string): string[] => {
|
|
const node = cg.getNodesInFile('app/leaves.py').find((n) => n.name === name && n.kind === 'class')!;
|
|
expect(node, name).toBeDefined();
|
|
return cg.getOutgoingEdges(node.id).filter((e) => e.kind === 'extends')
|
|
.map((e) => cg.getNode(e.target)!.name).sort();
|
|
};
|
|
|
|
it.skipIf(skip)('links Base[str], Base[list[int]] and Pair[str, dict[str, int]] like a plain base', () => {
|
|
expect(bases('Plain')).toEqual(['Base']);
|
|
expect(bases('Leaf')).toEqual(['Base']);
|
|
expect(bases('Nested')).toEqual(['Base']);
|
|
expect(bases('Two')).toEqual(['Pair']);
|
|
});
|
|
|
|
it.skipIf(skip)('links a parameterized base written over several lines', () => {
|
|
expect(bases('Multi')).toEqual(['Base']);
|
|
});
|
|
|
|
it.skipIf(skip)('links nothing for a subscript of a subscript, Base[int][str]', () => {
|
|
expect(bases('Chained')).toEqual([]);
|
|
});
|
|
|
|
it.skipIf(skip)('resolves a method a module global inherits through a parameterized base', () => {
|
|
// Base, Pair and Other each declare `run`, so only the class's own bases pick
|
|
// one; the globals are not named after their classes, so no name match does.
|
|
/** Qualified names of the methods `fn` in app/globals.py calls. */
|
|
const calls = (fn: string): string[] => {
|
|
const node = cg.getNodesInFile('app/globals.py').find((n) => n.name === fn && n.kind === 'function')!;
|
|
expect(node, fn).toBeDefined();
|
|
return cg.getOutgoingEdges(node.id).filter((e) => e.kind === 'calls')
|
|
.map((e) => cg.getNode(e.target)!).filter((n) => n.kind === 'method').map((n) => n.qualifiedName);
|
|
};
|
|
expect(calls('use_plain')).toEqual(['Base::run']);
|
|
expect(calls('use_leaf')).toEqual(['Base::run']);
|
|
expect(calls('use_two')).toEqual(['Pair::run']);
|
|
});
|
|
|
|
it.skipIf(skip)('keeps every base of a list that mixes plain and parameterized ones', () => {
|
|
expect(bases('Both')).toEqual(['Base', 'Mixin']);
|
|
});
|
|
|
|
it.skipIf(skip)('links a module-qualified parameterized base like its plain form', () => {
|
|
expect(bases('DottedPlain')).toEqual(['Base']);
|
|
expect(bases('Dotted')).toEqual(['Base']);
|
|
});
|
|
|
|
it.skipIf(skip)('ignores a keyword argument and a base that is not a name', () => {
|
|
expect(bases('Keyword')).toEqual(['Base']);
|
|
expect(bases('Computed')).toEqual([]);
|
|
});
|
|
|
|
it.skipIf(skip)('links nothing for Generic[T], a class outside the project', () => {
|
|
const base = cg.getNodesInFile('app/models.py').find((n) => n.name === 'Base' && n.kind === 'class')!;
|
|
expect(cg.getOutgoingEdges(base.id).filter((e) => e.kind === 'extends')).toEqual([]);
|
|
});
|
|
});
|