diff options
| author | orbiter <orbiter@6c8d7289-2bf4-0310-a012-ef5d649a1542> | 2009-04-16 21:05:34 +0000 |
|---|---|---|
| committer | orbiter <orbiter@6c8d7289-2bf4-0310-a012-ef5d649a1542> | 2009-04-16 21:05:34 +0000 |
| commit | 3a1364ed5cc20c25264aa48523a050a087fe3267 (patch) | |
| tree | d11da480101f0c86b1d7941f415f0152b7ba25d7 | |
| parent | 9050a3c4c547b7bcbe3b0e9505fedc961603a296 (diff) | |
removed example lines from SurrogateReader sources; added additional example file
git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@5816 6c8d7289-2bf4-0310-a012-ef5d649a1542
| -rw-r--r-- | examples/surrogate_generic.xml | 38 | ||||
| -rw-r--r-- | source/de/anomic/xml/SurrogateReader.java | 47 |
2 files changed, 38 insertions, 47 deletions
diff --git a/examples/surrogate_generic.xml b/examples/surrogate_generic.xml new file mode 100644 index 000000000..ea75f78da --- /dev/null +++ b/examples/surrogate_generic.xml @@ -0,0 +1,38 @@ +<?xml version="1.0" encoding="utf-8"?> +<!-- YaCy surrogate file generic element notion --> +<!-- + This is a generic surrogate file which is an alternative + intermediate document description file for index harvesting. + + For details please see surrogate_dublin_core.xml + + This file format has a generic content description, but YaCy + is currently not flexible enough to allow generic index content + descriptions. This file only shows a possible framework + for future developments. +--> + +<surrogate> + + <document> + <element name="title"> + <value><![CDATA[Alan Smithee]]></value> + </element> + <element name="url"> + <value>http://de.wikipedia.org/wiki/Alan_Smithee</value> + </element> + <element name="docdatetime"> + <value>2009-04-14T00:00:00Z</value> + </element> + <element name="language"> + <value>de</value> + </element> + <element name="body"> + <value><![CDATA[Der als Filmregisseur oft genannte '''Alan Smithee''' ist ein Anagramm]]></value> + </element> + <element name="categories"> + <value><![CDATA[Fiktive Person;Pseudonym]]></value> + </element> + </document> + +</surrogate>
\ No newline at end of file diff --git a/source/de/anomic/xml/SurrogateReader.java b/source/de/anomic/xml/SurrogateReader.java index 833feae05..63e42c359 100644 --- a/source/de/anomic/xml/SurrogateReader.java +++ b/source/de/anomic/xml/SurrogateReader.java @@ -186,50 +186,3 @@ public class SurrogateReader extends DefaultHandler implements Runnable, Iterato }
}
}
- /*
-Example surrogate
-<?xml version="1.0" encoding="utf-8"?>
-<!-- YaCy surrogate file using dublin core notion -->
-<!-- see http://dublincore.org/documents/dc-xml-guidelines/ -->
-<surrogates
- xmlns:dc="http://purl.org/dc/elements/1.1/">
-
- <record>
- <dc:title><![CDATA[Alan Smithee]]></dc:title>
- <dc:identifier>http://de.wikipedia.org/wiki/Alan_Smithee</dc:identifier>
- <dc:description><![CDATA[Der als Filmregisseur oft genannte '''Alan Smithee''' ist ein Anagramm von ãThe Alias MenÒ.]]></dc:description>
- <dc:language>de</dc:language>
- <dc:date>2009-03-02T11:12:36Z</dc:date> <!-- date is in ISO 8601 -->
- </record>
-
-</surrogates>
-
-
-or
-
-<?xml version="1.0" encoding="utf-8"?>
-<documents>
- <document id="1">
- <element name="docdatetime">
- <value>2009-03-02T11:12:36Z</value>
- </element>
- <element name="url">
- <value>http://de.wikipedia.org/wiki/Alan_Smithee</value>
- </element>
- <element name="language">
- <value>de</value>
- </element>
- <element name="title">
- <value><![CDATA[Alan Smithee]]></value>
- </element>
- <element name="body">
- <value><![CDATA[Der als Filmregisseur oft genannte '''Alan Smithee''' ist ein Anagramm]]></value>
- </element>
- <element name="categories">
- <value><![CDATA[Fiktive Person;Pseudonym]]></value>
- </element>
- </document>
-</documents>
-
-docdatetime is in ISO 8601
- */
\ No newline at end of file |
