@bastani/atomic 0.8.31-alpha.4 → 0.9.0-alpha.1

package/dist/builtin/web-access/github-extract.ts

@@ -1,170 +1,19 @@
 import { existsSync, readFileSync, rmSync, statSync, readdirSync, openSync, readSync, closeSync, realpathSync } from "node:fs";
 import { execFile } from "node:child_process";
-import { homedir } from "node:os";
 import { extname, join, resolve as resolvePath, sep as pathSep } from "node:path";
-import { CONFIG_DIR_NAME } from "@bastani/atomic";
 import { activityMonitor } from "./activity.js";
 import type { ExtractedContent } from "./extract.js";
 import { checkGhAvailable, checkRepoSize, fetchViaApi, showGhHint } from "./github-api.js";
-import { findReadableConfigPath } from "./config-paths.ts";
-
-const CONFIG_PATH = findReadableConfigPath();
-
-const BINARY_EXTENSIONS = new Set([
-	".png", ".jpg", ".jpeg", ".gif", ".bmp", ".ico", ".webp", ".svg", ".tiff", ".tif",
-	".mp3", ".mp4", ".avi", ".mov", ".mkv", ".flv", ".wmv", ".wav", ".ogg", ".webm", ".flac", ".aac",
-	".zip", ".tar", ".gz", ".bz2", ".xz", ".7z", ".rar", ".zst",
-	".exe", ".dll", ".so", ".dylib", ".bin", ".o", ".a", ".lib",
-	".woff", ".woff2", ".ttf", ".otf", ".eot",
-	".pdf", ".doc", ".docx", ".xls", ".xlsx", ".ppt", ".pptx",
-	".sqlite", ".db", ".sqlite3",
-	".pyc", ".pyo", ".class", ".jar", ".war",
-	".iso", ".img", ".dmg",
-]);
-
-const NOISE_DIRS = new Set([
-	"node_modules", "vendor", ".next", "dist", "build", "__pycache__",
-	".venv", "venv", ".tox", ".mypy_cache", ".pytest_cache",
-	"target", ".gradle", ".idea", ".vscode",
-]);
-
-const MAX_INLINE_FILE_CHARS = 100_000;
-const MAX_TREE_ENTRIES = 200;
-
-export interface GitHubUrlInfo {
-	owner: string;
-	repo: string;
-	ref?: string;
-	refIsFullSha: boolean;
-	path?: string;
-	type: "root" | "blob" | "tree";
-}
+import { BINARY_EXTENSIONS, MAX_INLINE_FILE_CHARS, MAX_TREE_ENTRIES, NOISE_DIRS, loadGitHubConfig, parseGitHubUrl, resetGitHubConfig, type GitHubCloneConfig, type GitHubUrlInfo } from "./github-config.js";
+export { parseGitHubUrl, type GitHubUrlInfo } from "./github-config.js";
 
 interface CachedClone {
 	localPath: string;
 	clonePromise: Promise<string | null>;
 }
 
-interface GitHubCloneConfig {
-	enabled: boolean;
-	maxRepoSizeMB: number;
-	cloneTimeoutSeconds: number;
-	clonePath: string;
-}
-
 const cloneCache = new Map<string, CachedClone>();
 
-let cachedConfig: GitHubCloneConfig | null = null;
-
-function normalizeEnabled(value: unknown, fallback: boolean): boolean {
-	return typeof value === "boolean" ? value : fallback;
-}
-
-function normalizePositiveNumber(value: unknown, fallback: number): number {
-	if (typeof value !== "number" || !Number.isFinite(value)) return fallback;
-	return value > 0 ? value : fallback;
-}
-
-function normalizeClonePath(value: unknown, fallback: string): string {
-	if (typeof value !== "string") return fallback;
-	const normalized = value.trim();
-	return normalized.length > 0 ? normalized : fallback;
-}
-
-function loadGitHubConfig(): GitHubCloneConfig {
-	if (cachedConfig) return cachedConfig;
-
-	const defaults: GitHubCloneConfig = {
-		enabled: true,
-		maxRepoSizeMB: 350,
-		cloneTimeoutSeconds: 30,
-		clonePath: "/tmp/atomic-github-repos",
-	};
-
-	if (!existsSync(CONFIG_PATH)) {
-		cachedConfig = defaults;
-		return cachedConfig;
-	}
-
-	const rawText = readFileSync(CONFIG_PATH, "utf-8");
-	let raw: { githubClone?: { enabled?: unknown; maxRepoSizeMB?: unknown; cloneTimeoutSeconds?: unknown; clonePath?: unknown } };
-	try {
-		raw = JSON.parse(rawText) as { githubClone?: { enabled?: unknown; maxRepoSizeMB?: unknown; cloneTimeoutSeconds?: unknown; clonePath?: unknown } };
-	} catch (err) {
-		const message = err instanceof Error ? err.message : String(err);
-		throw new Error(`Failed to parse ${CONFIG_PATH}: ${message}`);
-	}
-
-	const gc = raw.githubClone ?? {};
-	cachedConfig = {
-		enabled: normalizeEnabled(gc.enabled, defaults.enabled),
-		maxRepoSizeMB: normalizePositiveNumber(gc.maxRepoSizeMB, defaults.maxRepoSizeMB),
-		cloneTimeoutSeconds: normalizePositiveNumber(gc.cloneTimeoutSeconds, defaults.cloneTimeoutSeconds),
-		clonePath: normalizeClonePath(gc.clonePath, defaults.clonePath),
-	};
-	return cachedConfig;
-}
-
-const NON_CODE_SEGMENTS = new Set([
-	"issues", "pull", "pulls", "discussions", "releases", "wiki",
-	"actions", "settings", "security", "projects", "graphs",
-	"compare", "commits", "tags", "branches", "stargazers",
-	"watchers", "network", "forks", "milestone", "labels",
-	"packages", "codespaces", "contribute", "community",
-	"sponsors", "invitations", "notifications", "insights",
-]);
-
-export function parseGitHubUrl(url: string): GitHubUrlInfo | null {
-	let parsed: URL;
-	try {
-		parsed = new URL(url);
-	} catch {
-		return null;
-	}
-
-	const host = parsed.hostname.toLowerCase();
-	if (host !== "github.com" && host !== "www.github.com") return null;
-
-	const segments = parsed.pathname
-		.split("/")
-		.filter(Boolean)
-		.map((segment) => {
-			try {
-				return decodeURIComponent(segment);
-			} catch {
-				return segment;
-			}
-		});
-	if (segments.length < 2) return null;
-
-	const owner = segments[0];
-	const repo = segments[1].replace(/\.git$/, "");
-
-	if (NON_CODE_SEGMENTS.has(segments[2]?.toLowerCase())) return null;
-
-	if (segments.length === 2) {
-		return { owner, repo, refIsFullSha: false, type: "root" };
-	}
-
-	const action = segments[2];
-	if (action !== "blob" && action !== "tree") return null;
-	if (segments.length < 4) return null;
-
-	const ref = segments[3];
-	const refIsFullSha = /^[0-9a-f]{40}$/.test(ref);
-	const pathParts = segments.slice(4);
-	const path = pathParts.length > 0 ? pathParts.join("/") : "";
-
-	return {
-		owner,
-		repo,
-		ref,
-		refIsFullSha,
-		path,
-		type: action as "blob" | "tree",
-	};
-}
-
 function cacheKey(owner: string, repo: string, ref?: string): string {
 	return ref ? `${owner}/${repo}@${ref}` : `${owner}/${repo}`;
 }
@@ -632,5 +481,5 @@ export function clearCloneCache(): void {
 		}
 	}
 	cloneCache.clear();
-	cachedConfig = null;
+	resetGitHubConfig();
 }