@colbymchenry/codegraph 0.9.8 → 1.0.0

package/dist/extraction/astro-extractor.d.ts

@@ -0,0 +1,79 @@
+import { ExtractionResult } from '../types';
+/**
+ * AstroExtractor - Extracts code relationships from Astro component files
+ *
+ * Astro files are multi-language: a TypeScript frontmatter block fenced by
+ * `---` lines, a JSX-like HTML template, and optional <script>/<style> blocks.
+ * Rather than parsing a full Astro grammar, we extract the frontmatter and
+ * <script> contents and delegate them to the TypeScript TreeSitterExtractor
+ * (Astro processes both as TypeScript by default — no `lang` attr needed).
+ *
+ * Also extracts function calls from template expressions (`{fn(...)}`) and
+ * component usages (`<PascalCase>`) so cross-file edges are captured even
+ * when the only reference lives in markup.
+ *
+ * Every .astro file produces a component node (Astro components are always
+ * importable).
+ */
+export declare class AstroExtractor {
+    private filePath;
+    private source;
+    private nodes;
+    private edges;
+    private unresolvedReferences;
+    private errors;
+    constructor(filePath: string, source: string);
+    /**
+     * Extract from Astro source
+     */
+    extract(): ExtractionResult;
+    /**
+     * Create a component node for the .astro file
+     */
+    private createComponentNode;
+    /**
+     * Extract the frontmatter block: the content between the opening `---`
+     * fence (first non-blank line of the file) and the closing `---` fence.
+     * An unclosed fence is treated as "no frontmatter" rather than swallowing
+     * the whole template as TypeScript.
+     *
+     * Returns the content plus its 0-indexed start line, or null.
+     */
+    private extractFrontmatter;
+    /**
+     * Extract <script> blocks from the template portion
+     */
+    private extractScriptBlocks;
+    /**
+     * Process frontmatter / script content by delegating to TreeSitterExtractor.
+     * Astro treats both as TypeScript by default.
+     */
+    private processScriptContent;
+    /**
+     * Line ranges (0-indexed, inclusive) the template scans must skip:
+     * the frontmatter block and <script>/<style> blocks.
+     */
+    private getCoveredRanges;
+    /**
+     * Extract function calls from Astro template expressions.
+     *
+     * Astro templates embed JSX-like expressions (`{formatDate(post.date)}`,
+     * `class:list={cn(...)}`), so calls frequently live in markup rather than
+     * the frontmatter. We scan template lines for `{expression}` groups and
+     * extract call patterns from them. A `{` group left open at end-of-line
+     * (the pervasive `{posts.map((post) => (` pattern) contributes the calls
+     * on its opening line.
+     */
+    private extractTemplateCalls;
+    /**
+     * Extract component usages from the Astro template.
+     *
+     * PascalCase tags like <Layout>, <PostCard /> represent component
+     * instantiations — analogous to function calls in imperative code.
+     * Lowercase tags are native HTML (Astro does not register kebab-case
+     * components the way Vue does, so those are real custom elements and
+     * are skipped).
+     */
+    private extractTemplateComponents;
+}
+//# sourceMappingURL=astro-extractor.d.ts.map

package/dist/extraction/extraction-version.d.ts

@@ -0,0 +1,25 @@
+/**
+ * Extraction version
+ *
+ * A monotonically-increasing integer that identifies the *shape and depth* of
+ * what the extractor writes into the graph. Unlike `CURRENT_SCHEMA_VERSION`
+ * (which tracks the SQLite table layout and is migrated in place), this tracks
+ * the EXTRACTED CONTENT — node kinds, edges, synthesizers, resolver coverage.
+ *
+ * When an index was built by an older engine whose `EXTRACTION_VERSION` is
+ * below the running engine's, the data on disk is structurally fine but
+ * *stale*: it's missing whatever a newer extractor would now produce. A schema
+ * migration can't backfill that — only a re-index can. So this is the signal
+ * `codegraph status` uses to recommend a re-index, and the reason `codegraph
+ * upgrade` reminds users to refresh their projects.
+ *
+ * BUMP THIS when a release changes extraction output enough that existing
+ * indexes should be rebuilt to benefit — e.g. a new language/framework
+ * extractor, a new dynamic-dispatch synthesizer, a new node/edge kind, or a
+ * resolver fix that materially changes which edges exist. Do NOT bump for
+ * pure bug fixes, CLI/UX changes, or schema-only migrations. Over-bumping
+ * turns the re-index hint into noise — keep it honest (see CLAUDE.md, "Honesty
+ * in the product is load-bearing").
+ */
+export declare const EXTRACTION_VERSION = 24;
+//# sourceMappingURL=extraction-version.d.ts.map

package/dist/extraction/function-ref.d.ts

@@ -0,0 +1,118 @@
+/**
+ * Function-as-value capture (#756) — registration-linking for callbacks.
+ *
+ * A function name used as a VALUE — passed as a call argument
+ * (`register_handler(target_cb)`, `signal(SIGINT, handler)`), assigned to a
+ * field or function pointer (`o->cb = target_cb`, `OnFire := TargetCb`),
+ * placed in a struct/object initializer (`{ .recv_cb = my_cb }`,
+ * `{ recv: targetCb }`, `Ops{Cb: targetCb}`), or listed in a function table
+ * (`static cb_t table[] = { cb_a, cb_b }`) — is a real dependency that static
+ * call extraction misses entirely: `callers(target_cb)` showed nothing but
+ * direct calls, so every callback looked dead and its registration sites were
+ * invisible to impact analysis.
+ *
+ * This module captures those value positions during the AST walk as
+ * `function_ref` candidates. Capture is table-driven per language (the value
+ * positions and wrapper forms differ per grammar — `&fn` in C, `Main::fn` in
+ * Java, `::fn` in Kotlin, `#selector(fn)` in Swift, `@TargetCb` in Pascal,
+ * `method(:fn)` in Ruby). Candidates are GATED at end-of-file extraction
+ * (see `TreeSitterExtractor.flushFnRefCandidates`): only names matching a
+ * same-file function/method or an imported binding survive, which bounds
+ * volume and keeps precision high. Resolution then matches survivors against
+ * function/method nodes ONLY (`matchFunctionRef` in
+ * `src/resolution/name-matcher.ts`) and persists them as `references` edges,
+ * which `callers`/`impact` already traverse.
+ *
+ * Deliberately NOT covered (resolving the *dispatch* — `o->cb(x)` → the
+ * registered function — needs data-flow through struct fields; a wrong edge
+ * is worse than none): indirect-call resolution and `obj.method` member
+ * values where `obj` isn't `this`/`self` (the receiver's type is statically
+ * unknowable without local data-flow).
+ */
+import type { Node as SyntaxNode } from 'web-tree-sitter';
+export interface FnRefCandidate {
+    name: string;
+    line: number;
+    column: number;
+    /** Which capture position produced this candidate (gate policy keys on it). */
+    mode: CaptureMode;
+    /**
+     * True when the value was an explicit reference form (`&fn`, `&Cls::m`,
+     * `::fn`, `#selector`, `method(:sym)`) rather than a bare identifier —
+     * C++'s flush policy keys on it.
+     */
+    explicitRef: boolean;
+    /**
+     * Skip the same-file/import name gate for this candidate. Set for PHP
+     * string callables in known HOF positions: PHP global functions are
+     * referenced cross-file WITHOUT imports (global namespace), so the gate
+     * can't see them — the strong positional prior (a string argument to
+     * `usort`/`array_map`/…) plus resolution's unique-or-drop rule carry the
+     * precision instead.
+     */
+    skipGate?: boolean;
+}
+/** How to pull candidate value nodes out of a dispatched container node. */
+type CaptureMode = 'args' | 'rhs' | 'value' | 'list' | 'varinit';
+interface CaptureRule {
+    mode: CaptureMode;
+    /** Field holding the value for rhs/value/varinit (defaults per mode). */
+    field?: string;
+}
+export interface FnRefSpec {
+    /** Bare identifier node types that can act as a function value. */
+    idTypes: Set<string>;
+    /** Container node type → how to extract candidate values from it. */
+    dispatch: Map<string, CaptureRule>;
+    /**
+     * Transparent wrapper layers between a container and its values
+     * (`argument`, `value_argument`, `literal_element`, `expression_list`…).
+     * Value: the field to descend into, or null for "named children".
+     * `expression_list` fans out to ALL named children (Go multi-assign).
+     */
+    layers?: Map<string, string | null>;
+    /**
+     * Unary wrappers whose operand is the function value — C/C++ `&fn`
+     * (pointer_expression), Pascal `@Fn` (exprUnary), Scala eta `fn _`
+     * (postfix_expression). Value: operand field, or null for first named child.
+     */
+    unwrap?: Map<string, string | null>;
+    /**
+     * Whole-node reference forms needing bespoke name extraction —
+     * `method_reference` (Java), `callable_reference` / `navigation_expression`
+     * (Kotlin), `selector_expression` (Swift `#selector` / ObjC `@selector`),
+     * Ruby `method(:sym)` calls, and `this.method` member forms.
+     */
+    special?: Set<string>;
+    /**
+     * Capture modes whose candidates skip the same-file/import gate and rely on
+     * resolution's unique-or-drop rule instead. C-family only: an initializer
+     * value, function-pointer assignment RHS, or table element is a
+     * function-pointer position by construction, and C has no symbol imports —
+     * the dominant repo-scale pattern (`server.c`'s command table naming
+     * handlers defined across files) would otherwise be invisible. Call
+     * arguments stay gated everywhere (locals passed as args dwarf callbacks).
+     */
+    ungatedModes?: Set<CaptureMode>;
+    /**
+     * C++ only: in args/rhs/varinit positions, accept ONLY explicit reference
+     * forms (`&fn`, `&Cls::method`) — never bare identifiers. C++ codebases are
+     * dense with generic free-function/accessor names (`begin`, `end`, `out`,
+     * `size`, `data`) that collide with parameters and locals, and out-of-line
+     * member definitions extract as function-kind nodes — bare-id matching on
+     * fmt was mostly wrong edges. File-scope initializer tables (value/list)
+     * still accept bare identifiers, same as C.
+     */
+    addressOfOnly?: boolean;
+}
+/**
+ * Capture specs by language.
+ */
+export declare const FN_REF_SPECS: Record<string, FnRefSpec | undefined>;
+/**
+ * Extract candidate names from a dispatched container node. Returns the
+ * (name, position) pairs of every function-value-shaped expression found.
+ */
+export declare function captureFnRefCandidates(container: SyntaxNode, rule: CaptureRule, spec: FnRefSpec, source: string): FnRefCandidate[];
+export {};
+//# sourceMappingURL=function-ref.d.ts.map

package/dist/extraction/grammars.d.ts

@@ -7,7 +7,7 @@
  */
 import { Parser } from 'web-tree-sitter';
 import { Language } from '../types';
-export type GrammarLanguage = Exclude<Language, 'svelte' | 'vue' | 'liquid' | 'yaml' | 'twig' | 'xml' | 'properties' | 'unknown'>;
+export type GrammarLanguage = Exclude<Language, 'svelte' | 'vue' | 'astro' | 'liquid' | 'razor' | 'yaml' | 'twig' | 'xml' | 'properties' | 'unknown'>;
 /**
  * File extension to Language mapping
  */
@@ -18,6 +18,12 @@ export declare const EXTENSION_MAP: Record<string, Language>;
  * from EXTENSION_MAP so parser support and indexing selection never drift.
  */
 export declare function isSourceFile(filePath: string): boolean;
+/**
+ * Shopify OS 2.0 JSON template (`templates/*.json`) or section group
+ * (`sections/*.json`) — these reference sections by `"type"`, so the Liquid
+ * extractor links them. (config/ + locales/ JSON have no section refs.)
+ */
+export declare function isShopifyLiquidJson(filePath: string): boolean;
 /**
  * Play Framework routes file: the extensionless `conf/routes` (and included
  * `conf/*.routes`). No grammar — route extraction is done by the Play framework

package/dist/extraction/index.d.ts

@@ -53,6 +53,40 @@ export declare function hashContent(content: string): string;
  * it project code; the explicit `.gitignore` negation is the only opt-in).
  */
 export declare function buildDefaultIgnore(rootDir: string): Ignore;
+/**
+ * Workspace-scope ignore matcher. Ordinary paths get the root's matcher
+ * (built-in defaults + root `.gitignore`); paths inside an EMBEDDED repo get
+ * that repo's own matcher (defaults + its root `.gitignore`) — the parent's
+ * `.gitignore` hides a child repo from git, not from the index (#514). A
+ * directory path (trailing slash) that is an ANCESTOR of an embedded root is
+ * never ignored, so directory-pruning callers (the Linux per-directory
+ * watcher) still descend to reach the embedded repos.
+ *
+ * Single source of truth for indexer and watcher scope — they must not diverge.
+ */
+export declare class ScopeIgnore {
+    private rootMatcher;
+    private embedded;
+    private defaults;
+    constructor(rootMatcher: Ignore, embedded: Array<{
+        root: string;
+        matcher: Ignore;
+    }>);
+    ignores(rel: string): boolean;
+}
+/**
+ * Build the workspace-scope matcher. When the caller already knows the
+ * embedded roots (the scanner discovers them during collection), pass them to
+ * skip rediscovery; otherwise they're discovered here (the watcher path).
+ */
+export declare function buildScopeIgnore(rootDir: string, embeddedRoots?: Iterable<string>): ScopeIgnore;
+/**
+ * Standalone discovery of every embedded repo root under `rootDir` (relative,
+ * trailing-slashed) — both the untracked kind (#193) and the gitignored kind
+ * (#514), recursively (an embedded repo can embed further repos). Returns []
+ * for non-git roots: the filesystem walk handles nested repos there already.
+ */
+export declare function discoverEmbeddedRepoRoots(rootDir: string): string[];
 /**
  * Recursively scan a directory for source files.
  *

package/dist/extraction/languages/c-cpp.d.ts

@@ -1,4 +1,12 @@
 import type { LanguageExtractor } from '../tree-sitter-types';
+/**
+ * Normalize a C++ return type to the bare class name a method could be called
+ * on. Unwraps smart-pointer / optional wrappers to their element type
+ * (`std::unique_ptr<Widget>` → `Widget`) so a factory's `->method()` resolves on
+ * the pointee. Strips cv-qualifiers, `&`/`*`, namespace qualifiers, and other
+ * template args. Returns undefined for primitives / void / `auto` / empty.
+ */
+export declare function normalizeCppReturnType(raw: string): string | undefined;
 export declare const cExtractor: LanguageExtractor;
 export declare const cppExtractor: LanguageExtractor;
 //# sourceMappingURL=c-cpp.d.ts.map

package/dist/extraction/languages/csharp.d.ts

@@ -1,3 +1,25 @@
 import type { LanguageExtractor } from '../tree-sitter-types';
+/**
+ * Blank C# conditional-compilation directive lines (`#if` / `#elif` / `#else` /
+ * `#endif`) before parsing. The vendored tree-sitter-c-sharp grammar mis-parses
+ * a `#if` that appears *inside an enum member list* — the canonical
+ * multi-targeting shape:
+ *
+ *   enum ReadType {
+ *   #if HAVE_DATE_TIME_OFFSET
+ *       ReadAsDateTimeOffset,
+ *   #endif
+ *       ReadAsDouble,
+ *   }
+ *
+ * It emits an ERROR that, for a nested enum, detaches the *enclosing class's*
+ * member list, so most of the class's methods drop out of the index. Removing
+ * the directive lines (keeping the guarded code) sidesteps it. Both branches of
+ * an `#if/#else` are kept — the same behaviour the previous grammar produced,
+ * and the right default for a code graph (index every symbol regardless of
+ * build flags). Replacement preserves byte offsets (directive text → spaces,
+ * newlines kept) so every symbol's line/column stays exact. (#237)
+ */
+export declare function blankCsharpPreprocessorDirectives(source: string): string;
 export declare const csharpExtractor: LanguageExtractor;
 //# sourceMappingURL=csharp.d.ts.map

package/dist/extraction/languages/r.d.ts

@@ -0,0 +1,3 @@
+import type { LanguageExtractor } from '../tree-sitter-types';
+export declare const rExtractor: LanguageExtractor;
+//# sourceMappingURL=r.d.ts.map

package/dist/extraction/languages/typescript.d.ts

@@ -1,3 +1,16 @@
 import type { LanguageExtractor } from '../tree-sitter-types';
+import type { Node as SyntaxNode } from 'web-tree-sitter';
+/**
+ * A TS/JS class field (`public_field_definition` / `field_definition`) is a
+ * METHOD only when its value is callable — an arrow function, a function
+ * expression, or a HOF call wrapping one (`onScroll = throttle(() => {…})`),
+ * exactly mirroring what `resolveBody` below knows how to walk. Everything
+ * else (`public fonts: Fonts;`, `count = 0`, `static defaults = {…}`) is a
+ * PROPERTY. Previously every field extracted as method-kind (#808), which
+ * misrepresented class shape and defeated kind-based filtering — the reason
+ * #756's function-ref resolution had to restrict TS/JS bare identifiers to
+ * function targets.
+ */
+export declare function classifyTsClassMember(node: SyntaxNode): 'method' | 'property';
 export declare const typescriptExtractor: LanguageExtractor;
 //# sourceMappingURL=typescript.d.ts.map

package/dist/extraction/liquid-extractor.d.ts

@@ -24,6 +24,13 @@ export declare class LiquidExtractor {
      * Create a file node for the Liquid template
      */
     private createFileNode;
+    /**
+     * Shopify OS 2.0 JSON template / section group. Both have a `sections` object
+     * mapping an id → `{ "type": "<section-name>", ... }`; the `type` names a
+     * `sections/<type>.liquid` file. Emit a `references` edge to each, so a section
+     * used only from a JSON template (the OS 2.0 norm) is no longer orphaned.
+     */
+    private extractShopifyJsonSections;
     /**
      * Extract {% render 'snippet' %} and {% include 'snippet' %} references
      */

package/dist/extraction/razor-extractor.d.ts

@@ -0,0 +1,42 @@
+import { ExtractionResult } from '../types';
+export declare class RazorExtractor {
+    private filePath;
+    private source;
+    private nodes;
+    private edges;
+    private unresolvedReferences;
+    private errors;
+    constructor(filePath: string, source: string);
+    extract(): ExtractionResult;
+    private createComponentNode;
+    /** Last `.`-segment (`App.ViewModels.RegisterModel` → `RegisterModel`). */
+    private lastSegment;
+    /**
+     * Split a type expression into the capitalized type names it contains — base
+     * type plus any generic arguments (`Bar<Foo, Baz>` → `Bar`, `Foo`, `Baz`),
+     * each reduced to its last namespace segment. Lowercase/keyword tokens drop out.
+     */
+    private typeNames;
+    private pushRef;
+    private extractDirectives;
+    private extractComponentTags;
+    /**
+     * Find the matching `}` for the `{` at `openIdx`, skipping string literals and
+     * comments so a brace inside `"{"` / `// }` doesn't throw off the count.
+     * Returns the index of the closing brace, or -1 if unbalanced.
+     */
+    private matchBrace;
+    /** `@code { … }` / `@functions { … }` (Blazor) and `@{ … }` (Razor) C# blocks. */
+    private extractCodeBlocks;
+    /**
+     * Delegate each `@code`/`@functions`/`@{` block's C# to the tree-sitter C#
+     * extractor and attribute the block's external references (service/DTO calls,
+     * `new X()`, type uses) to the component. The block is wrapped in a synthetic
+     * class so tree-sitter parses the component's fields/methods in a class context
+     * (a Blazor `@code` body compiles into the component's partial class). We keep
+     * only the dependency references — coverage just needs the edges to external
+     * types, not per-member nodes. Degrades gracefully if the C# grammar isn't loaded.
+     */
+    private processCodeBlocks;
+}
+//# sourceMappingURL=razor-extractor.d.ts.map

package/dist/extraction/tree-sitter-types.d.ts

@@ -69,6 +69,15 @@ export interface ExtractorContext {
  * language-specific details like signatures, visibility, and imports.
  */
 export interface LanguageExtractor {
+    /**
+     * Optional source transform applied immediately before the grammar parses the
+     * file. Used to work around grammar gaps that would otherwise corrupt the
+     * parse tree (e.g. C# blanks conditional-compilation directive lines the
+     * grammar mis-parses inside enum bodies). MUST preserve byte offsets (replace
+     * removed text with spaces, keep newlines) so node positions and getNodeText
+     * stay correct; the returned string is used for both parsing and extraction.
+     */
+    preParse?: (source: string) => string;
     /** Node types that represent functions */
     functionTypes: string[];
     /** Node types that represent classes */
@@ -119,6 +128,14 @@ export interface LanguageExtractor {
     isStatic?: (node: SyntaxNode) => boolean;
     /** Check if variable declaration is a constant (const vs let/var) */
     isConst?: (node: SyntaxNode) => boolean;
+    /**
+     * Extract extra symbol-level modifier keywords to persist on the node's
+     * `decorators` list (e.g. Kotlin `expect`/`actual` multiplatform markers).
+     * Called generically for every created node; return undefined/[] when none.
+     * Used by the resolver to link `expect` declarations to their `actual`
+     * implementations across source sets.
+     */
+    extractModifiers?: (node: SyntaxNode) => string[] | undefined;
     /** Additional node types to treat as class declarations (e.g. Dart: 'mixin_declaration') */
     extraClassNodeTypes?: string[];
     /** Whether methods can be top-level without enclosing class (Go: true) */
@@ -135,6 +152,14 @@ export interface LanguageExtractor {
      * for multiple concepts (e.g. Swift uses class_declaration for classes, structs, and enums).
      */
     classifyClassNode?: (node: SyntaxNode) => 'class' | 'struct' | 'enum' | 'interface' | 'trait';
+    /**
+     * Classify a methodTypes node when the grammar reuses one node type for
+     * both callable and data members (#808): TS/JS class FIELDS
+     * (`public_field_definition` / `field_definition`) are methods only when
+     * their value is callable (`onClick = () => {}`); a plain field
+     * (`public fonts: Fonts;`, `count = 0`) is a property. Default: 'method'.
+     */
+    classifyMethodNode?: (node: SyntaxNode) => 'method' | 'property';
     /**
      * Resolve the body node for a function/method/class when it's not a child field.
      * (e.g. Dart puts function_body as a sibling, not a child.)
@@ -156,6 +181,14 @@ export interface LanguageExtractor {
      * When present, the receiver type is included in the qualified name for better searchability.
      */
     getReceiverType?: (node: SyntaxNode, source: string) => string | undefined;
+    /**
+     * Extract a function/method's normalized return type name (bare class name,
+     * smart-pointer pointee unwrapped), stored on the node as `returnType`. Used
+     * by C/C++ so resolution can infer a chained receiver's type from what the
+     * inner call returns (`Foo::instance().bar()` → resolve `bar` on `Foo`,
+     * issue #645). Return undefined for primitives / void / constructors.
+     */
+    getReturnType?: (node: SyntaxNode, source: string) => string | undefined;
     /**
      * Resolve the actual node kind for a type alias declaration.
      * Used by Go where `type_spec` is the named declaration wrapper for structs/interfaces: