[HADOOP] 트위터 데이터를로드하기위한 하이브 테이블 오류 생성
HADOOP트위터 데이터를로드하기위한 하이브 테이블 오류 생성
외부 테이블을 만들고 트위터 데이터를 테이블에로드하려고합니다. 테이블을 만드는 동안 다음과 같은 오류가 발생하여 오류를 추적 할 수 없습니다.
hive> ADD JAR /usr/local/hive/lib/hive-serdes-1.0-SNAPSHOT.jar
> ;
Added [/usr/local/hive/lib/hive-serdes-1.0-SNAPSHOT.jar] to class path
Added resources: [/usr/local/hive/lib/hive-serdes-1.0-SNAPSHOT.jar]
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';
아래는 오류입니다
FailedPredicateException(identifier,{useSQL11ReservedKeywordsForIdentifier()}?)
at org.apache.hadoop.hive.ql.parse.HiveParser_IdentifiersParser.identifier(HiveParser_IdentifiersParser.java:10924)
at org.apache.hadoop.hive.ql.parse.HiveParser.identifier(HiveParser.java:45850)
at org.apache.hadoop.hive.ql.parse.HiveParser.columnNameColonType(HiveParser.java:38211)
at org.apache.hadoop.hive.ql.parse.HiveParser.columnNameColonTypeList(HiveParser.java:36342)
at org.apache.hadoop.hive.ql.parse.HiveParser.structType(HiveParser.java:39707)
at org.apache.hadoop.hive.ql.parse.HiveParser.type(HiveParser.java:38655)
at org.apache.hadoop.hive.ql.parse.HiveParser.colType(HiveParser.java:38367)
at org.apache.hadoop.hive.ql.parse.HiveParser.columnNameType(HiveParser.java:38051)
at org.apache.hadoop.hive.ql.parse.HiveParser.columnNameTypeList(HiveParser.java:36203)
at org.apache.hadoop.hive.ql.parse.HiveParser.createTableStatement(HiveParser.java:5214)
at org.apache.hadoop.hive.ql.parse.HiveParser.ddlStatement(HiveParser.java:2640)
at org.apache.hadoop.hive.ql.parse.HiveParser.execStatement(HiveParser.java:1650)
at org.apache.hadoop.hive.ql.parse.HiveParser.statement(HiveParser.java:1109)
at org.apache.hadoop.hive.ql.parse.ParseDriver.parse(ParseDriver.java:202)
at org.apache.hadoop.hive.ql.parse.ParseDriver.parse(ParseDriver.java:166)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:396)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:308)
at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1122)
at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1170)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1059)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1049)
at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:213)
at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:165)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:736)
at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:681)
at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:621)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at org.apache.hadoop.util.RunJar.run(RunJar.java:221)
at org.apache.hadoop.util.RunJar.main(RunJar.java:136)
FAILED: ParseException line 9:2 Failed to recognize predicate 'user'. Failed rule: 'identifier' in column specification.
아래는 hdfs 경로에서 사용 가능한 트위터 데이터입니다. 아래 트위터 데이터에 적합한 테이블을 만드는 방법은 무엇입니까?
{
"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
}
}
해결법
-
==============================
1.이것을 사용하여 확인을 비활성화 할 수도 있습니다.
이것을 사용하여 확인을 비활성화 할 수도 있습니다.
SET hive.support.sql11.reserved.keywords=false; -
==============================
2.https://cwiki.apache.org/confluence/display/Hive/LanguageManual+DDL을 보면 예약 된 키워드 목록을 볼 수 있습니다. 열 사용자 이름을 지정할 수 없습니다.
https://cwiki.apache.org/confluence/display/Hive/LanguageManual+DDL을 보면 예약 된 키워드 목록을 볼 수 있습니다. 열 사용자 이름을 지정할 수 없습니다.
원하는 경우 사용자 이름을`user`로 지정할 수 있으며 쿼리는 다음과 같습니다.
SELECT `user` FROM table;그러나 알 수 있듯이 약간 추한 것이므로 다른 열 이름을 선택하는 것이 좋습니다.
from https://stackoverflow.com/questions/34696792/create-hive-table-error-to-load-twitter-data by cc-by-sa and MIT license
'HADOOP' 카테고리의 다른 글
| [HADOOP] Pig ERROR 2998 : 처리되지 않은 내부 오류입니다. 정적 (잘못된 이름 : com / company / Static) (0) | 2019.09.06 |
|---|---|
| [HADOOP] 분산 캐시 및 성능 하둡 (0) | 2019.09.06 |
| [HADOOP] Hive에서 15 분 미만의 날짜 차이 (0) | 2019.08.18 |
| [HADOOP] Apache Knox Gateway는 Cloudera 4.5와 호환됩니까? (0) | 2019.08.18 |
| [HADOOP] HDFS 연합 (0) | 2019.08.18 |