@struktoai/mirage-core/dist/core/dify/read.js

A Unified Virtual Filesystem For AI Agents

// ========= Copyright 2026 @ Strukto.AI All Rights Reserved. =========
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//     http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
// ========= Copyright 2026 @ Strukto.AI All Rights Reserved. =========
import { sliceWindow } from "../../utils/ranges.js";
import { fileEntry } from "../hierarchy/probe.js";
import { joinLines } from "../slug_tree/read.js";
import { scalarString } from "../slug_tree/rows.js";
import { getDocumentSegments, iterSegmentPages } from "./client.js";
const ENC = new TextEncoder();
export function segmentText(segment) {
    return scalarString(segment.content) ?? '';
}
/**
 * Read a document, optionally only a byte range of it.
 *
 * A document is rendered here from its segments, so its bytes do not exist
 * until we make them and the window can only be taken afterwards, the same
 * way the rendered branches of gdrive, slack and discord take theirs.
 *
 * Args:
 *   accessor: Dify accessor.
 *   path: the path to read.
 *   entry: what is at the path.
 *   options: `{offset, size}`, the byte window, or absent for the whole file.
 */
export async function read(accessor, path, entry = null, options) {
    const found = fileEntry(path, entry);
    const segments = await getDocumentSegments(accessor, String(found.extra.document_id));
    const rendered = ENC.encode(segments.map((segment) => segmentText(segment)).join('\n'));
    return sliceWindow(rendered, options?.offset ?? 0, options?.size ?? null);
}
export async function* readStream(accessor, path, entry = null) {
    const found = fileEntry(path, entry);
    yield* joinLines(segmentTexts(accessor, String(found.extra.document_id)));
}
async function* segmentTexts(accessor, documentId) {
    for await (const page of iterSegmentPages(accessor, documentId)) {
        for (const segment of page)
            yield segmentText(segment);
    }
}
//# sourceMappingURL=read.js.map