crawler.document.file.max.digest.length=200
# Whether to append meta content from files.
crawler.document.file.append.meta.content=true
# Whether to append body content from files.
crawler.document.file.append.body.content=true
# Default language for file documents.
crawler.document.file.default.lang=
# Patterns to include for file index processing.
crawler.document.file.default.include.index.patterns=

			{
				Status:     "Enabled",
				Filter:     Filter{Prefix: Prefix{string: "prefix-1", set: true}},
				Expiration: Expiration{Days: ExpirationDays(3)},
			},
			{
				Status:     "Enabled",
				Filter:     Filter{Prefix: Prefix{string: "prefix-1", set: true}},
				Expiration: Expiration{Date: midnightTS},
			},
			{
				Status:                      "Enabled",

import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.io.PrintStream;
import java.io.PrintWriter;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.HashSet;
import java.util.LinkedHashMap;
import java.util.List;
import java.util.Locale;
import java.util.Map;

/*
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you 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
 *

 * </p>
 *
 * <p>
 * The class uses temporary files for processing large input streams and ensures that these files are deleted after
 * processing.
 * </p>
 *
 */
public class TikaExtractor extends PasswordBasedExtractor {

    private static final Logger logger = LogManager.getLogger(TikaExtractor.class);

    /**
     * Tesseract config file path.
     */

                        Files.delete(handleFile);
                    }
                } catch (Exception e) {
                    log.error("Failed to load handle file: " + handleFile, e);
                    Files.deleteIfExists(handleFile);
                }
            }
        } catch (IOException e) {
            log.error("Failed to load persisted handles", e);
        }
    }
    

    path.write_bytes(b"<file content>")
    path2 = tmp_path / "test2.txt"
    path2.write_bytes(b"<file content2>")

    client = TestClient(app)
    with path.open("rb") as file, path2.open("rb") as file2:
        response = client.post(
            "/files/",
            files=(
                ("files", ("test.txt", file)),
                ("files", ("test2.txt", file2)),
            ),
        )

from typing import Optional

from fastapi import FastAPI, File
from fastapi.testclient import TestClient

app = FastAPI()


@app.post("/files")
async def upload_files(files: Optional[list[bytes]] = File(None)):
    if files is None:
        return {"files_count": 0}
    return {"files_count": len(files), "sizes": [len(f) for f in files]}


def test_optional_bytes_list():
    client = TestClient(app)
    response = client.post(

    }

    /**
     * Retrieves a stopwords file for a given dictionary ID.
     *
     * @param dictId The ID of the dictionary.
     * @return An optional entity containing the stopwords file, or empty if not found.
     */
    public OptionalEntity<StopwordsFile> getStopwordsFile(final String dictId) {
        return dictionaryManager.getDictionaryFile(dictId)
                .filter(StopwordsFile.class::isInstance)

    }

    /**
     * Retrieves a synonym file for a given dictionary ID.
     *
     * @param dictId The ID of the dictionary.
     * @return An optional entity containing the synonym file, or empty if not found.
     */
    public OptionalEntity<SynonymFile> getSynonymFile(final String dictId) {
        return dictionaryManager.getDictionaryFile(dictId)
                .filter(SynonymFile.class::isInstance)