fix(go): a constant in a const ( … ) group keeps its own doc comment

CHANGELOG.md

@@ -43,6 +43,7 @@ and adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 - In Go, a type declared on its own, like `type Point struct{…}` under a `// Point is …` comment, now keeps that comment as its documentation, as a type inside a `type ( … )` group already did, so searching for what a type does can find it. A comment at the end of a line of code, like `const sides = 4 // sides of a square.`, is no longer taken as the documentation of the declaration under it. Re-index Go projects after upgrading.
 - In Go, a declaration's documentation is now just the comment written right above it, as `go doc` shows it. A section banner, a TODO or commented-out code that a blank line separates from a function, type, constant or variable is no longer added to the front of its documentation, or taken as its documentation when it has none of its own. Re-index Go projects after upgrading.
 - In Go, a comment directive written above a declaration, like `//go:embed static`, `//go:generate stringer -type=Kind` or `//nolint:errcheck`, is no longer part of its documentation, as `go doc` shows it, so a variable whose only comment is a `//go:embed` line no longer has that line as its description. Re-index Go projects after upgrading.
+- In Go, a constant declared inside a `const ( … )` group now keeps the doc comment written above it, like gin's `// ErrorTypeBind is used when Context.Bind() fails.`, so searching for what a constant means can find it. Before, every member of the group got the group's comment, or nothing when the group had none; a member without a comment of its own still gets the group's. Re-index Go projects after upgrading.
 - Indexing a project that includes large bundled JavaScript files, such as a copy of pdf.js or d3, is fast again: since 1.6.2, resolving the calls in a JavaScript or TypeScript file re-read the file's text above each call, so a single bundled library could add many seconds to an index. The graph it builds is unchanged. Thanks @bompus for the report. (#2334)
 - Indexing a project that ships a large minified JavaScript file, such as the GraphiQL bundle inside go-ethereum, no longer stalls at "Resolving refs" when CodeGraph runs on Node 22, and linking such a file is faster on any Node version. The graph it builds is unchanged.
 - The time `codegraph init` and `codegraph index` print beside the node and edge counts now covers the whole run, resolving references and linking included, and `codegraph sync` reports its whole run the same way. Before, it counted only reading and parsing the files, which can be a small part of an index, so a slow index looked fast. Thanks @bompus for the report. (#2334)

__tests__/fixtures/kernel-parity/torture.go

@@ -8,6 +8,13 @@ import (
 
 const MAX_ITEMS = 128 // the line's own comment, not DefaultRegistry's doc
 
+// Limits: the group's comment, for a member without its own.
+const (
+	// MinItems is documented inside its group.
+	MinItems = 1
+	MaxSlots = 64
+)
+
 var DefaultRegistry = NewRegistry()
 
 var handlerTable = map[string]func(int){

__tests__/go-grouped-const-docs.test.ts

@@ -0,0 +1,157 @@
+/**
+ * A constant declared inside a `const ( … )` group lost the doc comment
+ * written above it:
+ *
+ *   const (
+ *   	// ErrorTypeBind is used when Context.Bind() fails.
+ *   	ErrorTypeBind ErrorType = 1 << 63
+ *
+ * gin's `ErrorTypeBind` had no docstring, because both extractors read every
+ * member's docstring from the comment above `const (`, the group's. A member's
+ * own doc comment, the one go doc prints beside it, is now its docstring; a
+ * member without one keeps the group's comment, as before.
+ *
+ * Runs against the native kernel (when built) and the wasm extractor, which
+ * must agree.
+ */
+import { describe, it, expect, beforeAll, beforeEach, afterEach } from 'vitest';
+import * as fs from 'fs';
+import * as path from 'path';
+import { extractFromSource } from '../src/extraction';
+import { initGrammars, loadGrammarsForLanguages } from '../src/extraction/grammars';
+import { tryKernelExtract, resetKernelForTests } from '../src/extraction/kernel';
+import type { ExtractionResult } from '../src/types';
+
+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 SOURCE = `// Package shapes is documented.
+package shapes
+
+// Kinds of shapes. The comment documents the group.
+const (
+	// Circle is documented on its own.
+	Circle = iota
+	Square
+	Pentagon = 5 // five sides
+	Heptagon
+	// A note a blank line separates from Hexagon.
+
+	Hexagon
+	// Octagon is documented on its own.
+	//nolint:revive
+	Octagon
+)
+
+const (
+	// Red is documented, and its group is not.
+	Red  = "red"
+	Blue = "blue"
+)
+
+// Answer is documented above its own declaration.
+const Answer = 42
+
+// Lone is the only member of its group.
+const (
+	Lone = 1
+)
+
+// Own's group comment.
+const (
+	// Own is documented inside its group of one.
+	Own = 2
+)
+
+// limit is documented above its own declaration.
+var limit = 10
+`;
+
+const ENV_KEYS = ['CODEGRAPH_KERNEL', 'CODEGRAPH_KERNEL_LANGS'] as const;
+
+describe('Go constants in a group keep their own doc comment', () => {
+  let savedEnv: Record<string, string | undefined> = {};
+
+  beforeAll(async () => {
+    await initGrammars();
+    await loadGrammarsForLanguages(['go']);
+  });
+
+  beforeEach(() => {
+    savedEnv = Object.fromEntries(ENV_KEYS.map((k) => [k, process.env[k]]));
+    resetKernelForTests();
+  });
+
+  afterEach(() => {
+    for (const k of ENV_KEYS) {
+      if (savedEnv[k] === undefined) delete process.env[k];
+      else process.env[k] = savedEnv[k];
+    }
+    resetKernelForTests();
+  });
+
+  function extract(backend: 'kernel' | 'wasm', source: string): ExtractionResult {
+    if (backend === 'wasm') {
+      process.env.CODEGRAPH_KERNEL = '0';
+      return extractFromSource('shapes/shapes.go', source, 'go');
+    }
+    delete process.env.CODEGRAPH_KERNEL;
+    process.env.CODEGRAPH_KERNEL_LANGS = 'all';
+    const result = tryKernelExtract('shapes/shapes.go', source, 'go');
+    expect(result, 'kernel extraction').not.toBeNull();
+    return result!;
+  }
+
+  const backends = kernelAvailable ? (['kernel', 'wasm'] as const) : (['wasm'] as const);
+
+  for (const crlf of [false, true]) {
+    it.each(backends)(`%s${crlf ? ' (CRLF)' : ''}`, (backend) => {
+      const result = extract(backend, crlf ? SOURCE.replace(/\n/g, '\r\n') : SOURCE);
+      const doc = (kind: string, name: string): string | null => {
+        const found = result.nodes.filter((n) => n.kind === kind && n.name === name);
+        expect(found, `${kind} ${name}`).toHaveLength(1);
+        return found[0].docstring ?? null;
+      };
+      const group = 'Kinds of shapes. The comment documents the group.';
+
+      expect({
+        // A member's own doc comment is its docstring, read the way go doc
+        // reads one: without a directive, and ended by a blank line.
+        Circle: doc('constant', 'Circle'),
+        Octagon: doc('constant', 'Octagon'),
+        Red: doc('constant', 'Red'),
+        Own: doc('constant', 'Own'),
+        // A member without one keeps the group's comment, if there is one; a
+        // comment after the code on the line above, or one a blank line
+        // separates from the member, is not its doc.
+        Square: doc('constant', 'Square'),
+        Heptagon: doc('constant', 'Heptagon'),
+        Hexagon: doc('constant', 'Hexagon'),
+        Blue: doc('constant', 'Blue'),
+        Lone: doc('constant', 'Lone'),
+        // A declaration on its own is read as before.
+        Answer: doc('constant', 'Answer'),
+        limit: doc('variable', 'limit'),
+      }).toEqual({
+        Circle: 'Circle is documented on its own.',
+        Octagon: 'Octagon is documented on its own.',
+        Red: 'Red is documented, and its group is not.',
+        Own: 'Own is documented inside its group of one.',
+        Square: group,
+        Heptagon: group,
+        Hexagon: group,
+        Blue: null,
+        Lone: 'Lone is the only member of its group.',
+        Answer: 'Answer is documented above its own declaration.',
+        limit: 'limit is documented above its own declaration.',
+      });
+    });
+  }
+});

codegraph-kernel/src/go.rs

@@ -697,11 +697,15 @@ impl<'t> Walker<'t> {
                         None
                     };
                     let signature = value_node.map(|v| util::init_signature(self.text(v)));
+                    // A member of a `const ( … )` group has its own doc
+                    // comment beside it in the parentheses; one without keeps
+                    // the group's.
+                    let doc = self.docstring_of(spec).or_else(|| docstring.clone());
                     var_row = self.create_node(
                         if is_const_decl { "constant" } else { "variable" },
                         &name,
                         spec,
-                        Extra { docstring: docstring.clone(), signature, ..Extra::default() },
+                        Extra { docstring: doc, signature, ..Extra::default() },
                     );
                 }
             }

src/extraction/tree-sitter.ts

@@ -3572,8 +3572,10 @@ export class TreeSitterExtractor {
           const initValue = valueNode ? getNodeText(valueNode, this.source).slice(0, 100) : undefined;
           const initSignature = initValue ? `= ${initValue}${initValue.length >= 100 ? '...' : ''}` : undefined;
 
+          // A member of a `const ( … )` group has its own doc comment beside
+          // it in the parentheses; one without keeps the group's.
           varNode = this.createNode(node.type === 'const_declaration' ? 'constant' : 'variable', name, spec, {
-            docstring,
+            docstring: this.docstringFor(spec) ?? docstring,
             signature: initSignature,
           });
         }