fix(rust): a module-path call links the function its module declares

CHANGELOG.md

@@ -119,6 +119,7 @@ and adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 - The call paths `codegraph context` prints now say what bridges each dynamic-dispatch hop, in the same words `codegraph_explore` uses: a call through an interface reads `interface → impl`, and a C++ override, a Redux thunk or a Gin middleware chain is named as one. Before, every hop of a kind it didn't know was labeled an "event", so a call through an interface looked like an event being emitted.
 - `codegraph_explore` and `codegraph context` now include some of the subtypes and implementors of a class or interface you ask about, and the type hierarchy the library returns for one (`getTypeHierarchy`) now lists all of them. Before, a bug in the hierarchy walk left every type without subtypes, so only what it extends or implements came back. Thanks @jocax for the report and @danusha2345 for the fix. (#2833)
 - In Rust, code that uses an enum only through its variants, like `mode::Mode::A` in an expression, a `Mode::B =>` match arm or `Self::A` inside the enum's own `impl`, now shows up in that enum's callers and impact, linked to the enum that actually declares the variant rather than to a same-named type elsewhere. Standard-library variants like `Ordering::Less` or `Option::Some` and associated items like `Foo::new()` or `Foo::MAX` don't count as using a project enum. Re-index Rust projects after upgrading. Thanks @mg-mg-mg for the report and @danusha2345. (#2328)
+- In Rust, a call written through a module path, like `crate::util::take(3)`, `super::util::take(3)` or `util::take(3)`, and a `use` of a function, like `use crate::util::take;`, now link to the function that module declares. Before, they could land on a method of the same name declared above it in that file, like an `impl Buf`'s `take`, or on a function written inside another function, and a call through a module the standard library provides, like `fs::read(…)` under `use std::fs;`, could link to your own `fs` module's `read`. Re-index Rust projects after upgrading. Thanks @danusha2345. (#2308)
 - Axum routes now link to their handler when rustfmt wraps the `.route(` call so the handler sits on a later line, and when the handler's name also appears elsewhere on the line, as in `delete(handlers::user::delete)` or `.route("/login", post(handlers::user::login))`; Actix's `web::resource(…)` and `.route(…)` registrations get the same fix. A call inside a closure handler is no longer mistaken for a route, and an Actix resource no longer takes the next route's handler as its own. Thanks @mg-mg-mg for the report and @danusha2345. (#2326)
 - In Play projects, a route or a call like `MediaType.parse(...)` now links to a method of the class or object it names, and a call to an overloaded one to the overload its arguments fit. Before, it went to the first method of that name anywhere in the class's file, often a nested or sibling class's. When a Scala and a Java type share a name, as Play's own `RequestAuthority` does, each language's calls now reach their own. Thanks @danusha2345.
 - In JavaScript and TypeScript, the functions written inside a named object literal are now symbols of their own even when the object isn't exported: a plain `const api = { load() {…} }`, an object declared inside an IIFE or a function, and a namespace hung on the page or on another object, like `window.App = { init() {…} }`, `App.utils = {…}` or `dw_page = {…}`. Calls such as `api.load()`, `window.App.init()`, `App.utils.pad()`, a sibling's `this.render()`, and `App.init()` from another script on the page now reach them, the calls made inside a member belong to that member instead of the object, and a bare `init()` is no longer taken for `App.init`, so script-tag apps no longer lose most of their code from `callers` and impact. A member's qualified name now carries its object, exported or not (`api::load`, `window.App::init`), so asking for `App.init` finds it. Re-index JavaScript and TypeScript projects after upgrading. Thanks @tkhoaaa for the report and @danusha2345. (#2300)

__tests__/rust-module-path-call.test.ts

@@ -0,0 +1,223 @@
+/**
+ * A Rust call written through a module path — `crate::util::take(3)`,
+ * `super::util::take(3)`, `self::util::take(3)`, `util::take(3)` after
+ * `use crate::util;` — is the free function that module declares, and so is
+ * a `use crate::util::take;`. A path never names a method (that takes
+ * `Type::method`), nor a function local to another function's body, even when
+ * the module's file declares one of the same name above the free function.
+ */
+import { describe, it, expect, afterAll, beforeAll } from 'vitest';
+import * as fs from 'fs';
+import * as os from 'os';
+import * as path from 'path';
+import { CodeGraph } from '../src';
+
+let root = '';
+let cg: CodeGraph;
+
+beforeAll(async () => {
+  root = fs.mkdtempSync(path.join(os.tmpdir(), 'cg-rust-module-path-'));
+  const files: Record<string, string> = {
+    'Cargo.toml': '[package]\nname = "app"\nversion = "0.1.0"\n',
+    'src/lib.rs': `mod util;
+mod only;
+mod a;
+mod caller;
+mod importer;
+mod handle;
+mod worker;
+mod twice;
+mod inline_reexport;
+mod fs;
+mod uses_std;
+
+pub fn via_self() -> usize {
+    self::util::take(1)
+}
+`,
+    // A namesake in an inline module, before the module's own item.
+    'src/twice.rs': `#[cfg(test)]
+mod tests {
+    pub fn pick() -> usize {
+        0
+    }
+}
+
+pub fn pick() -> usize {
+    1
+}
+
+pub fn via_twice() -> usize {
+    crate::twice::pick()
+}
+`,
+    // The item lives in an inline module the file passes on with a glob.
+    'src/inline_reexport.rs': `#[cfg(unix)]
+mod imp {
+    pub fn lone() {}
+}
+pub use imp::*;
+
+pub fn via_inline() {
+    crate::inline_reexport::lone();
+}
+`,
+    // A project module named like a module of the standard library.
+    'src/fs/mod.rs': 'pub fn read(path: &str) -> usize {\n    path.len()\n}\n',
+    'src/uses_std.rs': `use std::fs;
+
+pub fn loads() {
+    let _ = fs::read("config.toml");
+}
+`,
+    'src/util.rs': `pub struct Buf;
+
+impl Buf {
+    pub fn take(&self, n: usize) -> usize {
+        n
+    }
+}
+
+pub trait Take {
+    fn take(&self) -> usize;
+}
+
+fn outer() -> usize {
+    fn take() -> usize {
+        0
+    }
+    take()
+}
+
+pub fn take(n: usize) -> usize {
+    n
+}
+`,
+    'src/only.rs': `pub struct Only;
+
+impl Only {
+    pub fn grab(&self) -> usize {
+        0
+    }
+}
+`,
+    'src/a/mod.rs': 'pub mod b;\n',
+    'src/a/b.rs': `pub struct Deep;
+
+impl Deep {
+    pub fn get(&self) -> usize {
+        0
+    }
+}
+
+pub fn get() -> usize {
+    1
+}
+`,
+    'src/importer.rs': 'use crate::util::take;\n',
+    'src/handle.rs': 'pub struct Handle;\n',
+    'src/worker.rs': `pub use crate::handle::Handle;
+mod dump;
+
+pub trait Lock {
+    type Handle;
+}
+
+pub struct Guard;
+
+impl Lock for Guard {
+    type Handle = u8;
+}
+`,
+    'src/worker/dump.rs': 'use super::Handle;\n',
+    'src/caller.rs': `use crate::util;
+
+pub fn via_crate() -> usize {
+    crate::util::take(1)
+}
+
+pub fn via_super() -> usize {
+    super::util::take(1)
+}
+
+pub fn via_module() -> usize {
+    util::take(1)
+}
+
+pub fn via_nested() -> usize {
+    crate::a::b::get()
+}
+
+pub fn via_method_only() -> usize {
+    crate::only::grab()
+}
+
+pub fn via_missing() -> usize {
+    crate::nowhere::take(1)
+}
+`,
+  };
+  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);
+  }
+  cg = await CodeGraph.init(root, { index: true });
+});
+
+afterAll(() => {
+  cg?.close();
+  if (root) fs.rmSync(root, { recursive: true, force: true });
+});
+
+/** What the function `name` in `file` calls, as `kind qualifiedName file:line`. */
+const callsFrom = (file: string, name: string): string[] => {
+  const fn = cg.getNodesInFile(file).find((n) => n.name === name)!;
+  return cg.getOutgoingEdgesFrom([fn.id]).filter((e) => e.kind === 'calls')
+    .map((e) => cg.getNode(e.target)!).map((t) => `${t.kind} ${t.qualifiedName} ${t.filePath}:${t.startLine}`);
+};
+
+describe('Rust calls through a module path', () => {
+  it('reach the free function the module declares, never a same-named method or local fn', () => {
+    const take = 'function take src/util.rs:20';
+    expect(callsFrom('src/caller.rs', 'via_crate')).toEqual([take]);
+    expect(callsFrom('src/caller.rs', 'via_super')).toEqual([take]);
+    expect(callsFrom('src/caller.rs', 'via_module')).toEqual([take]);
+    expect(callsFrom('src/lib.rs', 'via_self')).toEqual([take]);
+  });
+
+  it('bind a use of the function to it', () => {
+    const ids = cg.getNodesInFile('src/importer.rs').map((n) => n.id);
+    const targets = cg.getOutgoingEdgesFrom(ids).filter((e) => e.kind === 'imports')
+      .map((e) => cg.getNode(e.target)!).map((t) => `${t.kind} ${t.qualifiedName} ${t.filePath}:${t.startLine}`);
+    expect(targets).toEqual(['function take src/util.rs:20']);
+  });
+
+  it('never bind a use to an associated type of the module\'s impl or trait', () => {
+    const ids = cg.getNodesInFile('src/worker/dump.rs').map((n) => n.id);
+    const targets = cg.getOutgoingEdgesFrom(ids).filter((e) => e.kind === 'imports')
+      .map((e) => cg.getNode(e.target)!).map((t) => `${t.kind} ${t.qualifiedName} ${t.filePath}:${t.startLine}`);
+    expect(targets.filter((t) => t.includes('src/worker.rs'))).toEqual([]);
+  });
+
+  it('walk a nested module path to its file', () => {
+    expect(callsFrom('src/caller.rs', 'via_nested')).toEqual(['function get src/a/b.rs:9']);
+  });
+
+  it('link nothing when the module declares no such free function, or is not in the index', () => {
+    expect(callsFrom('src/caller.rs', 'via_method_only')).toEqual([]);
+    expect(callsFrom('src/caller.rs', 'via_missing')).toEqual([]);
+  });
+
+  it('prefer the module\'s own item to a namesake in a module it declares inline', () => {
+    expect(callsFrom('src/twice.rs', 'via_twice')).toEqual(['function pick src/twice.rs:8']);
+  });
+
+  it('reach an inline module\'s item the module passes on, from the module\'s own file', () => {
+    expect(callsFrom('src/inline_reexport.rs', 'via_inline')).toEqual(['function lone src/inline_reexport.rs:3']);
+  });
+
+  it('leave a path through a module a `use` takes from the standard library to it', () => {
+    // `fs::read` under `use std::fs;` is std's, not `src/fs/mod.rs`'s `read`.
+    expect(callsFrom('src/uses_std.rs', 'loads')).toEqual([]);
+  });
+});

src/resolution/import-resolver.ts

@@ -33,6 +33,8 @@ import {
   isPythonFromImportModule,
   isRustAssociatedItem,
   tsGlobalScope,
+  isLexicallyReachable,
+  rustItemPlacement,
 } from './name-matcher';
 import { JS_ARRAY_METHODS } from './js-builtins';
 
@@ -3694,11 +3696,18 @@ function resolveRustPathReference(
   const modSegs = segments.slice(0, -1);
 
   const file = resolveRustModuleFile(modSegs, ref.filePath, context);
-  if (!file || file === ref.filePath) return null;
-
-  // A module's item, never an impl's associated one: serde's `use
-  // crate::de::Error` is not `de/mod.rs`'s `impl SeqAccess`'s `type Error`.
-  const target = context.getNodesInFile(file).find(
+  if (!file) return null;
+
+  // The module's own item. A path never names a method (that is
+  // `Type::method`), nor a fn local to another fn's body: the file's first
+  // same-named node was taken, so an `impl Buf { fn take }` above
+  // `pub fn take` caught every `crate::util::take(…)`. Two module-level items
+  // of one name are `#[cfg]` variants of it; the first one stands for both.
+  // With none, the path reaches an inline module's item through a re-export
+  // (`#[cfg(…)] mod imp { … }` + `pub use imp::*;`), never an associated item
+  // of an `impl` or `trait` body: serde's `use crate::de::Error` is not
+  // `de/mod.rs`'s `impl SeqAccess`'s `type Error`.
+  const candidates = context.getNodesInFile(file).filter(
     (n) =>
       n.name === leaf &&
       !isRustAssociatedItem(n) &&
@@ -3709,14 +3718,22 @@ function resolveRustPathReference(
         n.kind === 'trait' ||
         n.kind === 'type_alias' ||
         n.kind === 'constant' ||
-        n.kind === 'method' ||
         n.kind === 'class' ||
-        n.kind === 'interface')
+        n.kind === 'interface') &&
+      isLexicallyReachable(n, ref, context)
   );
-  if (target) {
-    return { original: ref, targetNodeId: target.id, confidence: 0.9, resolvedBy: 'import' };
-  }
-  return null;
+  const target =
+    candidates.find((n) => rustItemPlacement(n, context) === 'top') ??
+    candidates.find((n) => rustItemPlacement(n, context) === 'inline');
+  if (!target) return null;
+  // A path whose head a `use` binds from the standard library — `fs::read`
+  // under `use std::fs;`, `error::Error` under `use std::{error, io};` — is
+  // std's, whatever the module the project has of that name: `fs/mod.rs`'s own
+  // `read` is not `std::fs::read`. (Asked only here, where it changes the
+  // answer: the check reads the file's `use`s.)
+  const head = modSegs[0]!;
+  if (!/^(?:crate|self|super)$/.test(head) && isBoundToOutOfRepoImport({ ...ref, referenceName: head }, context)) return null;
+  return { original: ref, targetNodeId: target.id, confidence: 0.9, resolvedBy: 'import' };
 }
 
 /** The crate-root directory (holds `lib.rs`/`main.rs`), walking up from a file. */

src/resolution/name-matcher.ts

@@ -8994,6 +8994,21 @@ export function isRustAssociatedItem(n: Node): boolean {
   return n.language === 'rust' && RUST_ASSOCIATED_KINDS.has(n.kind) && n.qualifiedName.includes('::');
 }
 
+/**
+ * Where a Rust item sits in its file's module, as a path through the module
+ * reaches it: written at the file's top level ('top'), or in a module the
+ * file declares inline (`mod imp { … }`, 'inline'), which adds nothing to its
+ * qualified name. Null for an item a module path never names: a method, an
+ * `impl`'s or a trait's associated item, an item of a function body — each
+ * qualified by its owner.
+ */
+export function rustItemPlacement(n: Node, context: ResolutionContext): 'top' | 'inline' | null {
+  if (n.language !== 'rust' || n.qualifiedName !== n.name) return null;
+  const layout = rustUsesOf(n.filePath, context);
+  const at = (layout.lineStarts[n.startLine - 1] ?? 0) + Math.max(0, n.startColumn ?? 0);
+  return rustBlockAt(layout.blocks, at) === null ? 'top' : 'inline';
+}
+
 /** Does one of the file's globs bring in this candidate's module (or, for `use super::*`, its parent's)? */
 function rustGlobCovers(uses: RustUses, candidate: Node, ref: UnresolvedRef): boolean {
   if (uses.globs.has(rustModuleName(candidate.filePath))) return true;