Dyomedea
/
owark
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Hmmm... HTML should be serialized as HTML, of course!

This commit is contained in:
Eric van der Vlist 2012-04-28 16:52:28 +02:00
parent c79bd8e49c
commit a7c3525ef6
2 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
archiver/pipelines/actions/mediatypes/warc-html.xpl
View File

@ -71,12 +71,11 @@
<p:output name="data" id="html-rewritten" debug="rewritten"/>
</p:processor>
<p:processor name="oxf:xml-converter">
<p:processor name="oxf:html-converter">
<p:input name="config">
<config>
<content-type>application/xml</content-type>
<encoding>utf-8</encoding>
<version>1.0</version>
</config>
</p:input>
<p:input name="data" href="#html-rewritten"/>

2
archiver/pipelines/post-archive-request.xpl
View File

@ -23,7 +23,7 @@ declare namespace util = "http://exist-db.org/xquery/util";
for $q in /queue return
update
insert <action priority="0" uuid="{util:uuid()}" type="heritrix-archive-set" url="http://dyomedea.com"/>
insert <action priority="0" uuid="{util:uuid()}" type="heritrix-archive-set" url="http://eric.van-der-vlist.com/blog/"/>
into $q
]]></xquery>