source: other-projects/nightly-tasks/diffcol/trunk/gs3-model-collect/Web-Download/archives/HASH016c.dir/doc.xml@ 38996

Last change on this file since 38996 was 38996, checked in by anupama, 5 weeks ago

SourceDirectory seems to be new metadata in doc.xml that is breaking diffcol (when diffcol attempted on Win VM)

File size: 1.5 KB
Line 
1<?xml version="1.0" encoding="utf-8" standalone="no"?>
2<!DOCTYPE Archive SYSTEM "https://greenstone.org/dtd/Archive/1.0/Archive.dtd">
3<Archive>
4<Section>
5 <Description>
6 <Metadata name="gsdlsourcefilename">import/englishhistory.net/robots.txt</Metadata>
7 <Metadata name="gsdlsourcefilerenamemethod">url</Metadata>
8 <Metadata name="gsdldoctype">indexed_doc</Metadata>
9 <Metadata name="Plugin">TextPlugin</Metadata>
10 <Metadata name="FileSize">223</Metadata>
11 <Metadata name="SourceDirectory">englishhistory.net</Metadata>
12 <Metadata name="Source">robots.txt</Metadata>
13 <Metadata name="SourceFile">robots.txt</Metadata>
14 <Metadata name="Language">en</Metadata>
15 <Metadata name="Encoding">utf8</Metadata>
16 <Metadata name="Title">User-agent: *</Metadata>
17 <Metadata name="FileFormat">Text</Metadata>
18 <Metadata name="Identifier">HASH016cef702b96182fac38a61b</Metadata>
19 <Metadata name="lastmodified">1714975834</Metadata>
20 <Metadata name="lastmodifieddate">20240506</Metadata>
21 <Metadata name="oailastmodified">1714976055</Metadata>
22 <Metadata name="oailastmodifieddate">20240506</Metadata>
23 <Metadata name="assocfilepath">HASH016c.dir</Metadata>
24 </Description>
25 <Content>&lt;pre&gt;
26User-agent: *
27Disallow: admin.php
28Disallow: /admin/
29Disallow: /images/
30Disallow: /includes/
31Disallow: /themes/
32Disallow: /blocks/
33Disallow: /modules/
34Disallow: /language/Sitemap:http://englishhistory.net/sitemap.xml
35&lt;/pre&gt;</Content>
36</Section>
37</Archive>
Note: See TracBrowser for help on using the repository browser.