Revision: 18401
http://sourceforge.net/p/gate/code/18401
Author: ian_roberts
Date: 2014-10-21 18:34:59 +0000 (Tue, 21 Oct 2014)
Log Message:
-----------
Added option to *not* include the "text" property when saving annotations as
JSON. This gives us a format we can use to distribute annotations against
tweets without including the tweet text (just the ID) to comply with Twitter's
terms.
Modified Paths:
--------------
gate/trunk/src/main/gate/corpora/DocumentJsonUtils.java
Modified: gate/trunk/src/main/gate/corpora/DocumentJsonUtils.java
===================================================================
--- gate/trunk/src/main/gate/corpora/DocumentJsonUtils.java 2014-10-21
14:36:36 UTC (rev 18400)
+++ gate/trunk/src/main/gate/corpora/DocumentJsonUtils.java 2014-10-21
18:34:59 UTC (rev 18401)
@@ -229,7 +229,7 @@
public static void writeDocument(Document doc, Long start, Long end,
Map<String, Collection<Annotation>> annotationsMap, JsonGenerator
json)
throws JsonGenerationException, IOException, InvalidOffsetException {
- writeDocument(doc, start, end, annotationsMap, null, null, json);
+ writeDocument(doc, start, end, annotationsMap, null, null, true, json);
}
/**
@@ -259,7 +259,7 @@
Map<String, Collection<Annotation>> annotationsMap,
Map<?, ?> extraFeatures, JsonGenerator json)
throws JsonGenerationException, IOException, InvalidOffsetException {
- writeDocument(doc, start, end, annotationsMap, extraFeatures, null, json);
+ writeDocument(doc, start, end, annotationsMap, extraFeatures, null, true,
json);
}
/**
@@ -292,12 +292,49 @@
Map<?, ?> extraFeatures, String annotationTypeProperty,
JsonGenerator json) throws JsonGenerationException, IOException,
InvalidOffsetException {
+ writeDocument(doc, start, end, annotationsMap, extraFeatures,
+ annotationTypeProperty, true, json);
+ }
+ /**
+ * Write a substring of a GATE document to the specified
+ * JsonGenerator. The specified window of document text will
+ * optionally be written as a property named "text" and the specified
+ * annotations will be written as "entities", with their offsets
+ * adjusted to be relative to the specified window.
+ *
+ * @param doc the document to write
+ * @param start the start offset of the segment to write
+ * @param end the end offset of the segment to write
+ * @param extraFeatures additional properties to add to the generated
+ * JSON. If the map includes a "text" key this will be
+ * ignored, and if it contains a key "entities" whose value
+ * is a map then these entities will be merged with the
+ * generated ones derived from the annotationsMap. This would
+ * typically be used for documents that were originally
+ * derived from Twitter data, to re-create the original JSON.
+ * @param annotationTypeProperty if non-null, the annotation type will
+ * be written as a property under this name, as if it were an
+ * additional feature of each annotation.
+ * @param includeText should the "text" property be included?
+ * @param json the {@link JsonGenerator} to write to.
+ * @throws JsonGenerationException if a problem occurs while
+ * generating the JSON
+ * @throws IOException if an I/O error occurs.
+ */
+ public static void writeDocument(Document doc, Long start, Long end,
+ Map<String, Collection<Annotation>> annotationsMap,
+ Map<?, ?> extraFeatures, String annotationTypeProperty,
+ boolean includeText, JsonGenerator json) throws
JsonGenerationException, IOException,
+ InvalidOffsetException {
+
ObjectWriter writer = MAPPER.writer();
json.writeStartObject();
- json.writeStringField("text", doc.getContent().getContent(start, end)
- .toString());
+ if(includeText) {
+ json.writeStringField("text", doc.getContent().getContent(start, end)
+ .toString());
+ }
json.writeFieldName("entities");
json.writeStartObject();
// if the extraFeatures already includes entities, merge them with
This was sent by the SourceForge.net collaborative development platform, the
world's largest Open Source development site.
------------------------------------------------------------------------------
Comprehensive Server Monitoring with Site24x7.
Monitor 10 servers for $9/Month.
Get alerted through email, SMS, voice calls or mobile push notifications.
Take corrective actions from your mobile device.
http://p.sf.net/sfu/Zoho
_______________________________________________
GATE-cvs mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/gate-cvs
