Skip to end of metadata
Go to start of metadata

You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 2 Next »

Sample document

TODO

Source

TODO: geo (use docGeo.alternatives, retain only those metadata fields that are wanted)

{
    "description": "gnip test",
    "extractType": "File",
    "extractorOptions": {
        "app.alchemyapi-metadata.batchSize": 200,
        "app.alchemyapi-metadata.numKeywords": 5
    },
    "file": {
        "XmlPrimaryKey": "",
        "XmlRootLevelValues": [],
        "domain": "WORKGROUP",
        "password": "PASSWORD",
        "username": "PASSWORD"
    },
    "isApproved": true,
    "isPublic": true,
    "mediaType": "Social",
    "structuredAnalysis": {
        "associations": [
            {
                "assoc_type": "Event",
                "creationCriteriaScript": "$SCRIPT( return (null != _doc.metadata.json[0].object.actor); )",
                "entity1_index": "$SCRIPT( return _doc.metadata.json[0].actor.preferredUsername + '/twitterhandle';)",
                "entity2_index": "$SCRIPT( return _doc.metadata.json[0].object.actor.preferredUsername + '/twitterhandle';)",
                "verb": "retweets",
                "verb_category": "retweets"
            },
            {
                "assoc_type": "Event",
                "creationCriteriaScript": "$SCRIPT( return (null != _doc.metadata.json[0].object.actor) && (null != _doc.metadata.json[0].object.actor.location); )",
                "entity1_index": "$SCRIPT( return _doc.metadata.json[0].object.actor.preferredUsername + '/twitterhandle';)",
                "entity2_index": "$SCRIPT( return _doc.metadata.json[0].object.actor.location.displayName+ '/location';)",
                "verb": "twitter_location",
                "verb_category": "twitter_location"
            },
            {
                "assoc_type": "Event",
                "entity1_index": "$SCRIPT( return _doc.metadata.json[0].actor.preferredUsername + '/twitterhandle';)",
                "entity2_index": "$SCRIPT( return _iterator.text + '/hashtag'; )",
                "iterateOver": "json.twitter_entities.hashtags",
                "verb": "tweets_about",
                "verb_category": "tweets_about"
            },
            {
                "assoc_type": "Event",
                "entity1_index": "$SCRIPT( return _doc.metadata.json[0].actor.preferredUsername + '/twitterhandle';)",
                "entity2_index": "$SCRIPT( return _iterator.expanded_url + '/url'; )",
                "iterateOver": "json.gnip.urls",
                "verb": "tweets_link",
                "verb_category": "tweets_link"
            }
        ],
        "description": "$metadata.json.body",
        "entities": [
            {
                "actual_name": "$metadata.json.actor.displayName",
                "dimension": "Who",
                "disambiguated_name": "$metadata.json.actor.preferredUsername",
                "linkdata": "$metadata.json.actor.link",
                "type": "TwitterHandle"
            },
            {
                "actual_name": "$metadata.json.object.actor.displayName",
                "dimension": "Who",
                "disambiguated_name": "$metadata.json.object.actor.preferredUsername",
                "linkdata": "$metadata.json.object.actor.link",
                "type": "TwitterHandle"
            },
            {
                "dimension": "Where",
                "disambiguated_name": "$metadata.json.actor.location.displayName",
                "type": "Location"
            },
            {
                "dimension": "Where",
                "disambiguated_name": "$metadata.json.object.actor.location.displayName",
                "type": "Location"
            },
            {
                "disambiguated_name": "$SCRIPT(return _iterator.text;)",
                "iterateOver": "json.twitter_entities.hashtags",
                "type": "HashTag"
            },
            {
                "actual_name": "$SCRIPT(return _iterator.url)",
                "disambiguated_name": "$SCRIPT(return _iterator.expanded_url;)",
                "iterateOver": "json.gnip.urls",
                "type": "URL"
            }
        ],
        "fullText": "$metadata.json.body",
        "scriptEngine": "javascript",
        "title": "$metadata.json.body",
        "url": "$metadata.json.link"
    },
    "tags": [
        "twitter",
        "gnip"
    ],
    "title": "gnip test",
    "url": "smb://FILESHARE:139/datasift/gnip/",
    "useExtractor": "none",
    "useTextExtractor": "AlchemyAPI-metadata"
}

Sample output

TODO

  • No labels