agentfootprint/dist/rag/loaders/pdf.js

The explainable agent framework — backtrack a wrong answer to the exact context that caused it (evidence, not guesses). Built on footprintjs.

"use strict";
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    var desc = Object.getOwnPropertyDescriptor(m, k);
    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
      desc = { enumerable: true, get: function() { return m[k]; } };
    }
    Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
    Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
    o["default"] = v;
});
var __importStar = (this && this.__importStar) || function (mod) {
    if (mod && mod.__esModule) return mod;
    var result = {};
    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
    __setModuleDefault(result, mod);
    return result;
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.pdfLoader = exports.MissingPdfSupportError = void 0;
/**
 * pdfLoader — PDF text extraction, page by page.
 *
 * Pattern: Adapter behind `DocumentLoader`, over a lazily-loaded optional peer.
 * Role:    rag/ layer. The ONE loader that needs a dependency, and the reason
 *          it is optional rather than bundled.
 * Emits:   N/A.
 *
 * ── Why `unpdf`, measured rather than assumed ───────────────────────────────
 * PDF text extraction cannot be done without a real library. The candidates
 * were installed and measured:
 *
 * | package | installed size | packages | deps | verdict |
 * |---|---|---|---|---|
 * | **`unpdf`** | **2.5 MB** | **1** | **none** | chosen |
 * | `pdf-parse@2` | 86 MB | 3 | `@napi-rs/canvas` (**native**) | a native binary, to read text |
 * | `pdf-parse@1` | 34 MB | 4 | debug, node-ensure | unmaintained since 2018 |
 * | `pdfjs-dist@6` | 62 MB | 2 | none | 25× the size for the same engine |
 *
 * `unpdf` is a serverless build of the same pdf.js engine the heavyweight
 * options wrap, with dual CJS/ESM exports and zero transitive dependencies.
 * A real 2-page PDF extracts in ~95 ms.
 *
 * ── Pages are the point ─────────────────────────────────────────────────────
 * It returns text PER PAGE, and that is why the page number in a citation is a
 * fact rather than a guess. `<source id="handbook.pdf#7" page="2">` can be
 * checked by opening page 2. A loader that flattened the document first could
 * only ever say "somewhere in this PDF".
 *
 * ── A known warning on Node 22 ──────────────────────────────────────────────
 * pdf.js v5 calls `Math.sumPrecise`, which arrives in V8 later than Node 22.
 * The extraction is correct; the console shows `Warning: TypeError:
 * Math.sumPrecise is not a function` per page. It is upstream and harmless,
 * and it is documented here so it does not read as data loss.
 */
const lazyRequire_js_1 = require("../../lib/lazyRequire.js");
/** Raised when a PDF is met and `unpdf` is not installed. */
class MissingPdfSupportError extends Error {
    code = 'ERR_MISSING_PDF_SUPPORT';
    /** The file that could not be read. */
    uri;
    constructor(uri) {
        super(`Reading '${uri}' requires the \`unpdf\` peer dependency.\n` +
            '  Install:  npm install unpdf\n' +
            '  Or pass `backend` to pdfLoader() if your bundler resolves it statically.');
        this.name = 'MissingPdfSupportError';
        this.uri = uri;
    }
}
exports.MissingPdfSupportError = MissingPdfSupportError;
function pdfLoader(options = {}) {
    let backend;
    const getBackend = (uri) => {
        if (options.backend)
            return Promise.resolve(options.backend);
        return (backend ??= (async () => {
            // `unpdf` is ESM-only in its import condition, so a dynamic import is
            // tried first and the CJS require is the fallback — one of the two works
            // on every runtime this package supports.
            try {
                const spec = 'unpdf';
                return (await Promise.resolve(`${spec}`).then(s => __importStar(require(s))));
            }
            catch {
                try {
                    return (0, lazyRequire_js_1.lazyRequire)('unpdf');
                }
                catch {
                    throw new MissingPdfSupportError(uri);
                }
            }
        })());
    };
    return {
        name: 'pdf',
        extensions: ['.pdf'],
        async load(input) {
            const unpdf = await getBackend(input.uri);
            const doc = await unpdf.getDocumentProxy(input.bytes);
            const extracted = await unpdf.extractText(doc, { mergePages: false });
            const pages = Array.isArray(extracted.text)
                ? extracted.text.map((p) => String(p))
                : [String(extracted.text)];
            // Pages are joined with a blank line so `byParagraph` sees a boundary at
            // every page break — and so the offsets a splitter computes index THIS
            // string, which is the one that gets stored.
            return { text: pages.join('\n\n'), pages };
        },
    };
}
exports.pdfLoader = pdfLoader;
//# sourceMappingURL=pdf.js.map