Create hive table for JSON data - hadoop

Question

How to create hive table for the below twitter JSON data that is available in HDFS path. I tried some of the query from the web to create the table, but facing some issue.
{
"extended_entities": {
"media": [{
"display_url": "pic.twitter.com/9SoA83sVvP",
"indices": [100, 123],
"sizes": {
"small": {
"w": 340,
"h": 340,
"resize": "fit"
},
"large": {
"w": 480,
"h": 480,
"resize": "fit"
},
"thumb": {
"w": 150,
"h": 150,
"resize": "crop"
},
"medium": {
"w": 480,
"h": 480,
"resize": "fit"
}
},
"id_str": "685710180164579329",
"expanded_url": "http://twitter.com/add7dave/status/685710518456209408/video/1",
"media_url_https": "https://pbs.twimg.com/ext_tw_video_thumb/685710180164579329/pu/img/4wOqavTprNIaMgjK.jpg",
"id": 685710180164579329,
"type": "video",
"media_url": "http://pbs.twimg.com/ext_tw_video_thumb/685710180164579329/pu/img/4wOqavTprNIaMgjK.jpg",
"url": "https://t.co/9SoA83sVvP",
"video_info": {
"aspect_ratio": [1, 1],
"duration_millis": 7567,
"variants": [{
"content_type": "application/x-mpegURL",
"url": "https://video.twimg.com/ext_tw_video/685710180164579329/pu/pl/6JnchC_1FWviydJV.m3u8"
}, {
"content_type": "application/dash+xml",
"url": "https://video.twimg.com/ext_tw_video/685710180164579329/pu/pl/6JnchC_1FWviydJV.mpd"
}, {
"content_type": "video/mp4",
"bitrate": 320000,
"url": "https://video.twimg.com/ext_tw_video/685710180164579329/pu/vid/240x240/W7suov-YC1Iq1-QT.mp4"
}, {
"content_type": "video/webm",
"bitrate": 832000,
"url": "https://video.twimg.com/ext_tw_video/685710180164579329/pu/vid/480x480/bDG_UfEw3jBM7z4e.webm"
}, {
"content_type": "video/mp4",
"bitrate": 832000,
"url": "https://video.twimg.com/ext_tw_video/685710180164579329/pu/vid/480x480/bDG_UfEw3jBM7z4e.mp4"
}]
}
}]
},
"in_reply_to_status_id_str": null,
"in_reply_to_status_id": null,
"created_at": "Sat Jan 09 06:31:42 +0000 2016",
"in_reply_to_user_id_str": null,
"source": "<a href=\"http://twitter.com/download/android\" rel=\"nofollow\">Twitter for Android<\/a>",
"retweet_count": 0,
"retweeted": false,
"geo": null,
"filter_level": "low",
"in_reply_to_screen_name": null,
"is_quote_status": false,
"id_str": "685710518456209408",
"in_reply_to_user_id": null,
"favorite_count": 0,
"id": 685710518456209408,
"text": "New video NO-17\n#BritanniaFilmfareAwards\n#GoodDayCookies\n#BritanniaIndLtd\nAmitabh Bachchan dialogue https://t.co/9SoA83sVvP",
"place": null,
"lang": "en",
"favorited": false,
"possibly_sensitive": false,
"coordinates": null,
"truncated": false,
"timestamp_ms": "1452321102142",
"entities": {
"urls": [],
"hashtags": [{
"indices": [16, 40],
"text": "BritanniaFilmfareAwards"
}],
"media": [{
"display_url": "pic.twitter.com/9SoA83sVvP",
"indices": [100, 123],
"sizes": {
"small": {
"w": 340,
"h": 340,
"resize": "fit"
},
"large": {
"w": 480,
"h": 480,
"resize": "fit"
},
"thumb": {
"w": 150,
"h": 150,
"resize": "crop"
},
"medium": {
"w": 480,
"h": 480,
"resize": "fit"
}
},
"id_str": "685710180164579329",
"expanded_url": "http://twitter.com/add7dave/status/685710518456209408/video/1",
"media_url_https": "https://pbs.twimg.com/ext_tw_video_thumb/685710180164579329/pu/img/4wOqavTprNIaMgjK.jpg",
"id": 685710180164579329,
"type": "photo",
"media_url": "http://pbs.twimg.com/ext_tw_video_thumb/685710180164579329/pu/img/4wOqavTprNIaMgjK.jpg",
"url": "https://t.co/9SoA83sVvP"
}],
"user_mentions": [{
"indices": [41, 56],
"screen_name": "GoodDayCookies",
"id_str": "2197439803",
"name": "Britannia Good Day",
"id": 2197439803
}, {
"indices": [57, 73],
"screen_name": "BritanniaIndLtd",
"id_str": "3281245460",
"name": "Britannia Industries",
"id": 3281245460
}],
"symbols": []
},
"contributors": null,
"user": {
"utc_offset": 19800,
"friends_count": 1517,
"profile_image_url_https": "https://pbs.twimg.com/profile_images/593327096736256001/TT8Ds75__normal.jpg",
"listed_count": 1,
"profile_background_image_url": "http://abs.twimg.com/images/themes/theme19/bg.gif",
"default_profile_image": false,
"favourites_count": 25,
"description": "Sharukhan, Kapil sharma , Narendra modi Fan (Supporter) be happy *↓*",
"created_at": "Thu Sep 15 08:04:58 +0000 2011",
"is_translator": false,
"profile_background_image_url_https": "https://abs.twimg.com/images/themes/theme19/bg.gif",
"protected": false,
"screen_name": "add7dave",
"id_str": "373836462",
"profile_link_color": "9266CC",
"id": 373836462,
"geo_enabled": false,
"profile_background_color": "FFF04D",
"lang": "en",
"profile_sidebar_border_color": "000000",
"profile_text_color": "000000",
"verified": false,
"profile_image_url": "http://pbs.twimg.com/profile_images/593327096736256001/TT8Ds75__normal.jpg",
"time_zone": "Chennai",
"url": null,
"contributors_enabled": false,
"profile_background_tile": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/373836462/1428993069",
"statuses_count": 21397,
"follow_request_sent": null,
"followers_count": 438,
"profile_use_background_image": true,
"default_profile": false,
"following": null,
"name": "aditya dave",
"location": "Bhavnagar, Gujarat",
"profile_sidebar_fill_color": "000000",
"notifications": null
}
}
I tried the below table but it gives error.
hive> CREATE EXTERNAL TABLE tweets (
id BIGINT,
created_at STRING,
source STRING,
favorited BOOLEAN,
retweeted_status STRUCT<
text:STRING,
user:STRUCT<screen_name:STRING,name:STRING>,
retweet_count:INT>,
entities STRUCT<
urls:ARRAY<STRUCT<expanded_url:STRING>>,
user_mentions:ARRAY<STRUCT<screen_name:STRING,name:STRING>>,
hashtags:ARRAY<STRUCT<text:STRING>>>,
text STRING,
user STRUCT<
screen_name:STRING,
name:STRING,
friends_count:INT,
followers_count:INT,
statuses_count:INT,
verified:BOOLEAN,
utc_offset:INT,
time_zone:STRING>,
in_reply_to_screen_name STRING
)
PARTITIONED BY (datehour INT)
ROW FORMAT SERDE 'com.cloudera.hive.serde.JSONSerDe'
LOCATION '/user/flume/tweets/01092015';

Answer 1

You can use this utility https://github.com/quux00/hive-json-schema to create a hive schema from JSON. But as Ben Watson in his answer here if there are some columns like user that use a reserved name, you have to either enclose them with backticks or use a serde like https://github.com/rcongiu/Hive-JSON-Serde that can map hive columns to json elements.