# This workflow will build a Java project with Maven
# For more information see: https://help.github.com/actions/language-and-framework-guides/building-and-testing-java-with-maven

name: Java CI with Maven

on:
  push:
    branches:
    - master
    - "*.x"
  pull_request:
    branches:
    - master
    - "*.x"

jobs:
  build:
    runs-on: ${{ matrix.os }}

    strategy:
      matrix:

        // GCS patterns
        if (lowerEndpoint.contains("storage.googleapis.com") || lowerEndpoint.contains(".storage.cloud.google.com")) {
            return StorageType.GCS;
        }

        // S3 patterns
        if (lowerEndpoint.contains(".amazonaws.com") || lowerEndpoint.contains("s3.") || lowerEndpoint.contains("s3-")) {
            return StorageType.S3;
        }

 * </p>
 *
 * <pre>
 * {@code
 * RegexRule rule = new RegexRule();
 * rule.addRule("url", "https://example.com/.*");
 * rule.addRule("contentType", "text/html");
 * rule.setAllRequired(true); // Both URL and content type must match
 *
 * ResponseData responseData = new ResponseData();
 * responseData.setUrl("https://example.com/page1");
 * responseData.setContentType("text/html");
 *

                + "<doc>\n"//
                + "<field name=\"name\"><list><item>鈴木太郎</item><item>佐藤二朗</item><item>田中花子</item></list></field>\n"//
                + "<field name=\"access\"><list><item></item><item>http://www.taro.com/</item><item>******@****.***</item><item>090-xxxx-xxxx</item></list></field>\n"//
                + "<field name=\"image\"><list><item>taro.png</item><item>jiro.png</item><item>hanako.png</item></list></field>\n"//

# This workflow will build a Java project with Maven
# For more information see: https://help.github.com/actions/language-and-framework-guides/building-and-testing-java-with-maven

name: Java CI with Maven

on:
  push:
    branches: [ master ]
  pull_request:
    branches: [ master ]

jobs:
  build:

    runs-on: ubuntu-latest

    steps:
    - uses: actions/checkout@v4
    - name: Set up JDK 17

# Test multiple wildcards
User-agent: MultiWildcardBot
Disallow: /*.cgi*
Disallow: /*?*id=*

# Test literal $ in middle of pattern
User-agent: DollarBot
Disallow: /price$info

        CrawlingParameterUtil.setUrlQueue(urlQueue);

        // Verify it can be retrieved
        UrlQueue<?> retrieved = CrawlingParameterUtil.getUrlQueue();
        assertNotNull(retrieved);
        assertEquals("test-session", retrieved.getSessionId());
        assertEquals("http://example.com", retrieved.getUrl());
    }

# https://github.com/apache/lucene-solr/blob/master/lucene/analysis/common/src/resources/org/apache/lucene/analysis/ga/stopwords.txt
a
ach
ag
agus
an
aon
ar
arna
as
b'
ba
beirt
bhúr
caoga
ceathair
ceathrar
chomh
chtó
chuig
chun
cois
céad
cúig
cúigear
d'
daichead
dar
de
deich
deichniúr
den
dhá
do
don
dtí
dá
dár
dó
faoi
faoin
faoina

import org.slf4j.LoggerFactory;

import jcifs.CIFSException;
import jcifs.ResourceNameFilter;
import jcifs.SmbResource;
import jcifs.SmbResourceLocator;
import jcifs.internal.smb1.com.SmbComBlankResponse;
import jcifs.internal.smb1.com.SmbComFindClose2;
import jcifs.internal.smb1.trans.SmbComTransaction;
import jcifs.internal.smb1.trans2.Trans2FindFirst2;
import jcifs.internal.smb1.trans2.Trans2FindFirst2Response;

Crawl-delay: 3

User-agent: Crawler
Disallow: /aaa

User-agent: Crawler/1.0
Disallow: /bbb

User-agent: Crawler/2.0
Disallow: /ccc

User-agent: Hoge Crawler
Disallow: /ddd

sitemap: http://www.example.com/sitmap.xml