#!/bin/sh

FESS_CLASSPATH=$FESS_HOME/lib/classes

# JAVA_OPTS is not a built-in JVM mechanism but some people think it is so we
# warn them that we are not observing the value of $JAVA_OPTS
if [ ! -z "$JAVA_OPTS" ]; then
  echo -n "warning: ignoring JAVA_OPTS=$JAVA_OPTS; "
  echo "pass JVM parameters via FESS_JAVA_OPTS"
fi

if [ "x$FESS_MIN_MEM" = "x" ]; then
    FESS_MIN_MEM=256m
fi
if [ "x$FESS_MAX_MEM" = "x" ]; then
    FESS_MAX_MEM=2g

@echo off

if DEFINED JAVA_HOME goto cont

:err
ECHO JAVA_HOME environment variable must be set! 1>&2
EXIT /B 1 

:cont
set SCRIPT_DIR=%~dp0
for %%I in ("%SCRIPT_DIR%..") do set FESS_HOME=%%~dpfI


REM ***** JAVA options *****

if "%FESS_MIN_MEM%" == "" (
set FESS_MIN_MEM=256m
)

if "%FESS_MAX_MEM%" == "" (
set FESS_MAX_MEM=1g
)

if NOT "%FESS_HEAP_SIZE%" == "" (
set FESS_MIN_MEM=%FESS_HEAP_SIZE%

    }

    public void test_getText() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/markdown/test.md");
        final ExtractData extractData = markdownExtractor.getText(in, null);
        CloseableUtil.closeQuietly(in);

        final String content = extractData.getContent();
        logger.info(content);

        // Verify plain text extraction

        final InputStream in = new ByteArrayInputStream(bytes);

        try {
            sitemapsHelper.parse(in);
            fail();
        } catch (final CrawlingAccessException e) {
            // NOP
        }
    }

    public void test_parseXmlSitemaps_invalid2() {
        final byte[] bytes = "test".getBytes();
        final InputStream in = new ByteArrayInputStream(bytes);

    /**
     * Extracts text from the PowerPoint input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        validateInputStream(in);
        try (final HSLFSlideShow slideShow = new HSLFSlideShow(in);

     */
    public TextExtractor() {
        super();
    }

    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        validateInputStream(in);
        try {
            final String content = new String(InputStreamUtil.getBytes(in), getEncoding());
            return new ExtractData(content);
        } catch (final Exception e) {

    }

    public void testParse() {
        RobotsTxt robotsTxt;
        final InputStream in = RobotsTxtHelperTest.class.getResourceAsStream("robots.txt");
        try {
            robotsTxt = robotsTxtHelper.parse(in);
        } finally {
            CloseableUtil.closeQuietly(in);
        }

        for (String userAgent : new String[] { "FessCrawler", "FessCrawler/1.0", "Mozilla FessCrawler" }) {

 *
 * 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,

        super();
    }

    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        validateInputStream(in);

        final MimeTypeHelper mimeTypeHelper = getMimeTypeHelper();
        final ExtractorFactory extractorFactory = getExtractorFactory();
        return new ExtractData(getTextInternal(in, mimeTypeHelper, extractorFactory));
    }

    /**

        int processedEntries = 0;
        int failedEntries = 0;

        try (final ArchiveInputStream ais =
                archiveStreamFactory.createArchiveInputStream(in.markSupported() ? in : new BufferedInputStream(in))) {
            ZipArchiveEntry entry = null;
            long contentSize = 0;
            while ((entry = (ZipArchiveEntry) ais.getNextEntry()) != null) {
                contentSize += entry.getSize();