PageRenderTime 50ms CodeModel.GetById 14ms RepoModel.GetById 0ms app.codeStats 1ms

/tags/release-0.0.0-rc0/hive/external/ql/src/test/results/clientpositive/bucket_groupby.q.out

#
text | 1849 lines | 1780 code | 69 blank | 0 comment | 0 complexity | 03ae5c4b271adb9683bda8460a989aca MD5 | raw file
Possible License(s): Apache-2.0, BSD-3-Clause, JSON, CPL-1.0

Large files files are truncated, but you can click here to view the full file

    

  1. PREHOOK: query: create table clustergroupby(key string, value string) partitioned by(ds string)
    2. 

  2. PREHOOK: type: CREATETABLE
    3. 

  3. POSTHOOK: query: create table clustergroupby(key string, value string) partitioned by(ds string)
    4. 

  4. POSTHOOK: type: CREATETABLE
    5. 

  5. POSTHOOK: Output: default@clustergroupby
    6. 

  6. PREHOOK: query: describe extended clustergroupby
    7. 

  7. PREHOOK: type: DESCTABLE
    8. 

  8. POSTHOOK: query: describe extended clustergroupby
    9. 

  9. POSTHOOK: type: DESCTABLE
    10. 

  10. key	string	
    11. 

  11. value	string	
    12. 

  12. ds	string	
    13. 

  13. 	 	 
    14. 

  14. Detailed Table Information	Table(tableName:clustergroupby, dbName:default, owner:sdong, createTime:1297330264, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:value, type:string, comment:null), FieldSchema(name:ds, type:string, comment:null)], location:pfile:/data/users/sdong/www/open-source-hive1/build/ql/test/data/warehouse/clustergroupby, inputFormat:org.apache.hadoop.mapred.TextInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat, compressed:false, numBuckets:-1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe, parameters:{serialization.format=1}), bucketCols:[], sortCols:[], parameters:{}), partitionKeys:[FieldSchema(name:ds, type:string, comment:null)], parameters:{transient_lastDdlTime=1297330264}, viewOriginalText:null, viewExpandedText:null, tableType:MANAGED_TABLE)	
    15. 

  15. PREHOOK: query: insert overwrite table clustergroupby partition (ds='100') select key, value from src sort by key
    16. 

  16. PREHOOK: type: QUERY
    17. 

  17. PREHOOK: Input: default@src
    18. 

  18. PREHOOK: Output: default@clustergroupby@ds=100
    19. 

  19. POSTHOOK: query: insert overwrite table clustergroupby partition (ds='100') select key, value from src sort by key
    20. 

  20. POSTHOOK: type: QUERY
    21. 

  21. POSTHOOK: Input: default@src
    22. 

  22. POSTHOOK: Output: default@clustergroupby@ds=100
    23. 

  23. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    24. 

  24. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    25. 

  25. PREHOOK: query: explain
    26. 

  26. select key, count(1) from clustergroupby where ds='100' group by key limit 10
    27. 

  27. PREHOOK: type: QUERY
    28. 

  28. POSTHOOK: query: explain
    29. 

  29. select key, count(1) from clustergroupby where ds='100' group by key limit 10
    30. 

  30. POSTHOOK: type: QUERY
    31. 

  31. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    32. 

  32. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    33. 

  33. ABSTRACT SYNTAX TREE:
    34. 

  34.   (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '100')) (TOK_GROUPBY (TOK_TABLE_OR_COL key)) (TOK_LIMIT 10)))
    35. 

  35. 

  36. STAGE DEPENDENCIES:
    37. 

  37.   Stage-1 is a root stage
    38. 

  38.   Stage-0 is a root stage
    39. 

  39. 

  40. STAGE PLANS:
    41. 

  41.   Stage: Stage-1
    42. 

  42.     Map Reduce
    43. 

  43.       Alias -> Map Operator Tree:
    44. 

  44.         clustergroupby 
    45. 

  45.           TableScan
    46. 

  46.             alias: clustergroupby
    47. 

  47.             Filter Operator
    48. 

  48.               predicate:
    49. 

  49.                   expr: (ds = '100')
    50. 

  50.                   type: boolean
    51. 

  51.               Select Operator
    52. 

  52.                 expressions:
    53. 

  53.                       expr: key
    54. 

  54.                       type: string
    55. 

  55.                 outputColumnNames: key
    56. 

  56.                 Group By Operator
    57. 

  57.                   aggregations:
    58. 

  58.                         expr: count(1)
    59. 

  59.                   bucketGroup: false
    60. 

  60.                   keys:
    61. 

  61.                         expr: key
    62. 

  62.                         type: string
    63. 

  63.                   mode: hash
    64. 

  64.                   outputColumnNames: _col0, _col1
    65. 

  65.                   Reduce Output Operator
    66. 

  66.                     key expressions:
    67. 

  67.                           expr: _col0
    68. 

  68.                           type: string
    69. 

  69.                     sort order: +
    70. 

  70.                     Map-reduce partition columns:
    71. 

  71.                           expr: _col0
    72. 

  72.                           type: string
    73. 

  73.                     tag: -1
    74. 

  74.                     value expressions:
    75. 

  75.                           expr: _col1
    76. 

  76.                           type: bigint
    77. 

  77.       Reduce Operator Tree:
    78. 

  78.         Group By Operator
    79. 

  79.           aggregations:
    80. 

  80.                 expr: count(VALUE._col0)
    81. 

  81.           bucketGroup: false
    82. 

  82.           keys:
    83. 

  83.                 expr: KEY._col0
    84. 

  84.                 type: string
    85. 

  85.           mode: mergepartial
    86. 

  86.           outputColumnNames: _col0, _col1
    87. 

  87.           Select Operator
    88. 

  88.             expressions:
    89. 

  89.                   expr: _col0
    90. 

  90.                   type: string
    91. 

  91.                   expr: _col1
    92. 

  92.                   type: bigint
    93. 

  93.             outputColumnNames: _col0, _col1
    94. 

  94.             Limit
    95. 

  95.               File Output Operator
    96. 

  96.                 compressed: false
    97. 

  97.                 GlobalTableId: 0
    98. 

  98.                 table:
    99. 

  99.                     input format: org.apache.hadoop.mapred.TextInputFormat
    100. 

  100.                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    101. 

  101. 

  102.   Stage: Stage-0
    103. 

  103.     Fetch Operator
    104. 

  104.       limit: 10
    105. 

  105. 

  106. 

  107. PREHOOK: query: select key, count(1) from clustergroupby where ds='100' group by key limit 10
    108. 

  108. PREHOOK: type: QUERY
    109. 

  109. PREHOOK: Input: default@clustergroupby@ds=100
    110. 

  110. PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-09_571_4785800205176349032/-mr-10000
    111. 

  111. POSTHOOK: query: select key, count(1) from clustergroupby where ds='100' group by key limit 10
    112. 

  112. POSTHOOK: type: QUERY
    113. 

  113. POSTHOOK: Input: default@clustergroupby@ds=100
    114. 

  114. POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-09_571_4785800205176349032/-mr-10000
    115. 

  115. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    116. 

  116. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    117. 

  117. 0	3
    118. 

  118. 10	1
    119. 

  119. 100	2
    120. 

  120. 103	2
    121. 

  121. 104	2
    122. 

  122. 105	1
    123. 

  123. 11	1
    124. 

  124. 111	1
    125. 

  125. 113	2
    126. 

  126. 114	1
    127. 

  127. PREHOOK: query: alter table clustergroupby clustered by (key) into 1 buckets
    128. 

  128. PREHOOK: type: ALTERTABLE_CLUSTER_SORT
    129. 

  129. PREHOOK: Input: default@clustergroupby
    130. 

  130. PREHOOK: Output: default@clustergroupby
    131. 

  131. POSTHOOK: query: alter table clustergroupby clustered by (key) into 1 buckets
    132. 

  132. POSTHOOK: type: ALTERTABLE_CLUSTER_SORT
    133. 

  133. POSTHOOK: Input: default@clustergroupby
    134. 

  134. POSTHOOK: Output: default@clustergroupby
    135. 

  135. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    136. 

  136. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    137. 

  137. PREHOOK: query: describe extended clustergroupby
    138. 

  138. PREHOOK: type: DESCTABLE
    139. 

  139. POSTHOOK: query: describe extended clustergroupby
    140. 

  140. POSTHOOK: type: DESCTABLE
    141. 

  141. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    142. 

  142. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    143. 

  143. key	string	
    144. 

  144. value	string	
    145. 

  145. ds	string	
    146. 

  146. 	 	 
    147. 

  147. Detailed Table Information	Table(tableName:clustergroupby, dbName:default, owner:sdong, createTime:1297330264, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:value, type:string, comment:null), FieldSchema(name:ds, type:string, comment:null)], location:pfile:/data/users/sdong/www/open-source-hive1/build/ql/test/data/warehouse/clustergroupby, inputFormat:org.apache.hadoop.mapred.TextInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat, compressed:false, numBuckets:1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe, parameters:{serialization.format=1}), bucketCols:[key], sortCols:[], parameters:{}), partitionKeys:[FieldSchema(name:ds, type:string, comment:null)], parameters:{numPartitions=1, numFiles=1, last_modified_by=sdong, last_modified_time=1297330273, transient_lastDdlTime=1297330273, numRows=500, totalSize=5812}, viewOriginalText:null, viewExpandedText:null, tableType:MANAGED_TABLE)	
    148. 

  148. PREHOOK: query: insert overwrite table clustergroupby partition (ds='101') select key, value from src distribute by key
    149. 

  149. PREHOOK: type: QUERY
    150. 

  150. PREHOOK: Input: default@src
    151. 

  151. PREHOOK: Output: default@clustergroupby@ds=101
    152. 

  152. POSTHOOK: query: insert overwrite table clustergroupby partition (ds='101') select key, value from src distribute by key
    153. 

  153. POSTHOOK: type: QUERY
    154. 

  154. POSTHOOK: Input: default@src
    155. 

  155. POSTHOOK: Output: default@clustergroupby@ds=101
    156. 

  156. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    157. 

  157. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    158. 

  158. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    159. 

  159. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    160. 

  160. PREHOOK: query: --normal--
    161. 

  161. explain
    162. 

  162. select key, count(1) from clustergroupby  where ds='101'  group by key limit 10
    163. 

  163. PREHOOK: type: QUERY
    164. 

  164. POSTHOOK: query: --normal--
    165. 

  165. explain
    166. 

  166. select key, count(1) from clustergroupby  where ds='101'  group by key limit 10
    167. 

  167. POSTHOOK: type: QUERY
    168. 

  168. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    169. 

  169. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    170. 

  170. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    171. 

  171. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    172. 

  172. ABSTRACT SYNTAX TREE:
    173. 

  173.   (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '101')) (TOK_GROUPBY (TOK_TABLE_OR_COL key)) (TOK_LIMIT 10)))
    174. 

  174. 

  175. STAGE DEPENDENCIES:
    176. 

  176.   Stage-1 is a root stage
    177. 

  177.   Stage-0 is a root stage
    178. 

  178. 

  179. STAGE PLANS:
    180. 

  180.   Stage: Stage-1
    181. 

  181.     Map Reduce
    182. 

  182.       Alias -> Map Operator Tree:
    183. 

  183.         clustergroupby 
    184. 

  184.           TableScan
    185. 

  185.             alias: clustergroupby
    186. 

  186.             Filter Operator
    187. 

  187.               predicate:
    188. 

  188.                   expr: (ds = '101')
    189. 

  189.                   type: boolean
    190. 

  190.               Select Operator
    191. 

  191.                 expressions:
    192. 

  192.                       expr: key
    193. 

  193.                       type: string
    194. 

  194.                 outputColumnNames: key
    195. 

  195.                 Group By Operator
    196. 

  196.                   aggregations:
    197. 

  197.                         expr: count(1)
    198. 

  198.                   bucketGroup: true
    199. 

  199.                   keys:
    200. 

  200.                         expr: key
    201. 

  201.                         type: string
    202. 

  202.                   mode: hash
    203. 

  203.                   outputColumnNames: _col0, _col1
    204. 

  204.                   Reduce Output Operator
    205. 

  205.                     key expressions:
    206. 

  206.                           expr: _col0
    207. 

  207.                           type: string
    208. 

  208.                     sort order: +
    209. 

  209.                     Map-reduce partition columns:
    210. 

  210.                           expr: _col0
    211. 

  211.                           type: string
    212. 

  212.                     tag: -1
    213. 

  213.                     value expressions:
    214. 

  214.                           expr: _col1
    215. 

  215.                           type: bigint
    216. 

  216.       Reduce Operator Tree:
    217. 

  217.         Group By Operator
    218. 

  218.           aggregations:
    219. 

  219.                 expr: count(VALUE._col0)
    220. 

  220.           bucketGroup: false
    221. 

  221.           keys:
    222. 

  222.                 expr: KEY._col0
    223. 

  223.                 type: string
    224. 

  224.           mode: mergepartial
    225. 

  225.           outputColumnNames: _col0, _col1
    226. 

  226.           Select Operator
    227. 

  227.             expressions:
    228. 

  228.                   expr: _col0
    229. 

  229.                   type: string
    230. 

  230.                   expr: _col1
    231. 

  231.                   type: bigint
    232. 

  232.             outputColumnNames: _col0, _col1
    233. 

  233.             Limit
    234. 

  234.               File Output Operator
    235. 

  235.                 compressed: false
    236. 

  236.                 GlobalTableId: 0
    237. 

  237.                 table:
    238. 

  238.                     input format: org.apache.hadoop.mapred.TextInputFormat
    239. 

  239.                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    240. 

  240. 

  241.   Stage: Stage-0
    242. 

  242.     Fetch Operator
    243. 

  243.       limit: 10
    244. 

  244. 

  245. 

  246. PREHOOK: query: select key, count(1) from clustergroupby  where ds='101' group by key limit 10
    247. 

  247. PREHOOK: type: QUERY
    248. 

  248. PREHOOK: Input: default@clustergroupby@ds=101
    249. 

  249. PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-18_109_2103582873568530260/-mr-10000
    250. 

  250. POSTHOOK: query: select key, count(1) from clustergroupby  where ds='101' group by key limit 10
    251. 

  251. POSTHOOK: type: QUERY
    252. 

  252. POSTHOOK: Input: default@clustergroupby@ds=101
    253. 

  253. POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-18_109_2103582873568530260/-mr-10000
    254. 

  254. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    255. 

  255. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    256. 

  256. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    257. 

  257. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    258. 

  258. 0	3
    259. 

  259. 10	1
    260. 

  260. 100	2
    261. 

  261. 103	2
    262. 

  262. 104	2
    263. 

  263. 105	1
    264. 

  264. 11	1
    265. 

  265. 111	1
    266. 

  266. 113	2
    267. 

  267. 114	1
    268. 

  268. PREHOOK: query: --function--
    269. 

  269. explain
    270. 

  270. select length(key), count(1) from clustergroupby  where ds='101'  group by length(key) limit 10
    271. 

  271. PREHOOK: type: QUERY
    272. 

  272. POSTHOOK: query: --function--
    273. 

  273. explain
    274. 

  274. select length(key), count(1) from clustergroupby  where ds='101'  group by length(key) limit 10
    275. 

  275. POSTHOOK: type: QUERY
    276. 

  276. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    277. 

  277. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    278. 

  278. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    279. 

  279. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    280. 

  280. ABSTRACT SYNTAX TREE:
    281. 

  281.   (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION length (TOK_TABLE_OR_COL key))) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '101')) (TOK_GROUPBY (TOK_FUNCTION length (TOK_TABLE_OR_COL key))) (TOK_LIMIT 10)))
    282. 

  282. 

  283. STAGE DEPENDENCIES:
    284. 

  284.   Stage-1 is a root stage
    285. 

  285.   Stage-0 is a root stage
    286. 

  286. 

  287. STAGE PLANS:
    288. 

  288.   Stage: Stage-1
    289. 

  289.     Map Reduce
    290. 

  290.       Alias -> Map Operator Tree:
    291. 

  291.         clustergroupby 
    292. 

  292.           TableScan
    293. 

  293.             alias: clustergroupby
    294. 

  294.             Filter Operator
    295. 

  295.               predicate:
    296. 

  296.                   expr: (ds = '101')
    297. 

  297.                   type: boolean
    298. 

  298.               Select Operator
    299. 

  299.                 expressions:
    300. 

  300.                       expr: key
    301. 

  301.                       type: string
    302. 

  302.                 outputColumnNames: key
    303. 

  303.                 Group By Operator
    304. 

  304.                   aggregations:
    305. 

  305.                         expr: count(1)
    306. 

  306.                   bucketGroup: true
    307. 

  307.                   keys:
    308. 

  308.                         expr: length(key)
    309. 

  309.                         type: int
    310. 

  310.                   mode: hash
    311. 

  311.                   outputColumnNames: _col0, _col1
    312. 

  312.                   Reduce Output Operator
    313. 

  313.                     key expressions:
    314. 

  314.                           expr: _col0
    315. 

  315.                           type: int
    316. 

  316.                     sort order: +
    317. 

  317.                     Map-reduce partition columns:
    318. 

  318.                           expr: _col0
    319. 

  319.                           type: int
    320. 

  320.                     tag: -1
    321. 

  321.                     value expressions:
    322. 

  322.                           expr: _col1
    323. 

  323.                           type: bigint
    324. 

  324.       Reduce Operator Tree:
    325. 

  325.         Group By Operator
    326. 

  326.           aggregations:
    327. 

  327.                 expr: count(VALUE._col0)
    328. 

  328.           bucketGroup: false
    329. 

  329.           keys:
    330. 

  330.                 expr: KEY._col0
    331. 

  331.                 type: int
    332. 

  332.           mode: mergepartial
    333. 

  333.           outputColumnNames: _col0, _col1
    334. 

  334.           Select Operator
    335. 

  335.             expressions:
    336. 

  336.                   expr: _col0
    337. 

  337.                   type: int
    338. 

  338.                   expr: _col1
    339. 

  339.                   type: bigint
    340. 

  340.             outputColumnNames: _col0, _col1
    341. 

  341.             Limit
    342. 

  342.               File Output Operator
    343. 

  343.                 compressed: false
    344. 

  344.                 GlobalTableId: 0
    345. 

  345.                 table:
    346. 

  346.                     input format: org.apache.hadoop.mapred.TextInputFormat
    347. 

  347.                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    348. 

  348. 

  349.   Stage: Stage-0
    350. 

  350.     Fetch Operator
    351. 

  351.       limit: 10
    352. 

  352. 

  353. 

  354. PREHOOK: query: select length(key), count(1) from clustergroupby  where ds='101' group by length(key) limit 10
    355. 

  355. PREHOOK: type: QUERY
    356. 

  356. PREHOOK: Input: default@clustergroupby@ds=101
    357. 

  357. PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-21_764_2109263664206229253/-mr-10000
    358. 

  358. POSTHOOK: query: select length(key), count(1) from clustergroupby  where ds='101' group by length(key) limit 10
    359. 

  359. POSTHOOK: type: QUERY
    360. 

  360. POSTHOOK: Input: default@clustergroupby@ds=101
    361. 

  361. POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-21_764_2109263664206229253/-mr-10000
    362. 

  362. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    363. 

  363. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    364. 

  364. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    365. 

  365. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    366. 

  366. 1	10
    367. 

  367. 2	74
    368. 

  368. 3	416
    369. 

  369. PREHOOK: query: explain
    370. 

  370. select abs(length(key)), count(1) from clustergroupby  where ds='101'  group by abs(length(key)) limit 10
    371. 

  371. PREHOOK: type: QUERY
    372. 

  372. POSTHOOK: query: explain
    373. 

  373. select abs(length(key)), count(1) from clustergroupby  where ds='101'  group by abs(length(key)) limit 10
    374. 

  374. POSTHOOK: type: QUERY
    375. 

  375. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    376. 

  376. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    377. 

  377. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    378. 

  378. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    379. 

  379. ABSTRACT SYNTAX TREE:
    380. 

  380.   (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION abs (TOK_FUNCTION length (TOK_TABLE_OR_COL key)))) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '101')) (TOK_GROUPBY (TOK_FUNCTION abs (TOK_FUNCTION length (TOK_TABLE_OR_COL key)))) (TOK_LIMIT 10)))
    381. 

  381. 

  382. STAGE DEPENDENCIES:
    383. 

  383.   Stage-1 is a root stage
    384. 

  384.   Stage-0 is a root stage
    385. 

  385. 

  386. STAGE PLANS:
    387. 

  387.   Stage: Stage-1
    388. 

  388.     Map Reduce
    389. 

  389.       Alias -> Map Operator Tree:
    390. 

  390.         clustergroupby 
    391. 

  391.           TableScan
    392. 

  392.             alias: clustergroupby
    393. 

  393.             Filter Operator
    394. 

  394.               predicate:
    395. 

  395.                   expr: (ds = '101')
    396. 

  396.                   type: boolean
    397. 

  397.               Select Operator
    398. 

  398.                 expressions:
    399. 

  399.                       expr: key
    400. 

  400.                       type: string
    401. 

  401.                 outputColumnNames: key
    402. 

  402.                 Group By Operator
    403. 

  403.                   aggregations:
    404. 

  404.                         expr: count(1)
    405. 

  405.                   bucketGroup: true
    406. 

  406.                   keys:
    407. 

  407.                         expr: abs(length(key))
    408. 

  408.                         type: int
    409. 

  409.                   mode: hash
    410. 

  410.                   outputColumnNames: _col0, _col1
    411. 

  411.                   Reduce Output Operator
    412. 

  412.                     key expressions:
    413. 

  413.                           expr: _col0
    414. 

  414.                           type: int
    415. 

  415.                     sort order: +
    416. 

  416.                     Map-reduce partition columns:
    417. 

  417.                           expr: _col0
    418. 

  418.                           type: int
    419. 

  419.                     tag: -1
    420. 

  420.                     value expressions:
    421. 

  421.                           expr: _col1
    422. 

  422.                           type: bigint
    423. 

  423.       Reduce Operator Tree:
    424. 

  424.         Group By Operator
    425. 

  425.           aggregations:
    426. 

  426.                 expr: count(VALUE._col0)
    427. 

  427.           bucketGroup: false
    428. 

  428.           keys:
    429. 

  429.                 expr: KEY._col0
    430. 

  430.                 type: int
    431. 

  431.           mode: mergepartial
    432. 

  432.           outputColumnNames: _col0, _col1
    433. 

  433.           Select Operator
    434. 

  434.             expressions:
    435. 

  435.                   expr: _col0
    436. 

  436.                   type: int
    437. 

  437.                   expr: _col1
    438. 

  438.                   type: bigint
    439. 

  439.             outputColumnNames: _col0, _col1
    440. 

  440.             Limit
    441. 

  441.               File Output Operator
    442. 

  442.                 compressed: false
    443. 

  443.                 GlobalTableId: 0
    444. 

  444.                 table:
    445. 

  445.                     input format: org.apache.hadoop.mapred.TextInputFormat
    446. 

  446.                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    447. 

  447. 

  448.   Stage: Stage-0
    449. 

  449.     Fetch Operator
    450. 

  450.       limit: 10
    451. 

  451. 

  452. 

  453. PREHOOK: query: select abs(length(key)), count(1) from clustergroupby  where ds='101' group by abs(length(key)) limit 10
    454. 

  454. PREHOOK: type: QUERY
    455. 

  455. PREHOOK: Input: default@clustergroupby@ds=101
    456. 

  456. PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-26_110_671172006622360339/-mr-10000
    457. 

  457. POSTHOOK: query: select abs(length(key)), count(1) from clustergroupby  where ds='101' group by abs(length(key)) limit 10
    458. 

  458. POSTHOOK: type: QUERY
    459. 

  459. POSTHOOK: Input: default@clustergroupby@ds=101
    460. 

  460. POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-26_110_671172006622360339/-mr-10000
    461. 

  461. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    462. 

  462. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    463. 

  463. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    464. 

  464. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    465. 

  465. 1	10
    466. 

  466. 2	74
    467. 

  467. 3	416
    468. 

  468. PREHOOK: query: --constant--
    469. 

  469. explain
    470. 

  470. select key, count(1) from clustergroupby  where ds='101'  group by key,3 limit 10
    471. 

  471. PREHOOK: type: QUERY
    472. 

  472. POSTHOOK: query: --constant--
    473. 

  473. explain
    474. 

  474. select key, count(1) from clustergroupby  where ds='101'  group by key,3 limit 10
    475. 

  475. POSTHOOK: type: QUERY
    476. 

  476. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    477. 

  477. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    478. 

  478. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    479. 

  479. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    480. 

  480. ABSTRACT SYNTAX TREE:
    481. 

  481.   (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '101')) (TOK_GROUPBY (TOK_TABLE_OR_COL key) 3) (TOK_LIMIT 10)))
    482. 

  482. 

  483. STAGE DEPENDENCIES:
    484. 

  484.   Stage-1 is a root stage
    485. 

  485.   Stage-0 is a root stage
    486. 

  486. 

  487. STAGE PLANS:
    488. 

  488.   Stage: Stage-1
    489. 

  489.     Map Reduce
    490. 

  490.       Alias -> Map Operator Tree:
    491. 

  491.         clustergroupby 
    492. 

  492.           TableScan
    493. 

  493.             alias: clustergroupby
    494. 

  494.             Filter Operator
    495. 

  495.               predicate:
    496. 

  496.                   expr: (ds = '101')
    497. 

  497.                   type: boolean
    498. 

  498.               Select Operator
    499. 

  499.                 expressions:
    500. 

  500.                       expr: key
    501. 

  501.                       type: string
    502. 

  502.                 outputColumnNames: key
    503. 

  503.                 Group By Operator
    504. 

  504.                   aggregations:
    505. 

  505.                         expr: count(1)
    506. 

  506.                   bucketGroup: true
    507. 

  507.                   keys:
    508. 

  508.                         expr: key
    509. 

  509.                         type: string
    510. 

  510.                         expr: 3
    511. 

  511.                         type: int
    512. 

  512.                   mode: hash
    513. 

  513.                   outputColumnNames: _col0, _col1, _col2
    514. 

  514.                   Reduce Output Operator
    515. 

  515.                     key expressions:
    516. 

  516.                           expr: _col0
    517. 

  517.                           type: string
    518. 

  518.                           expr: _col1
    519. 

  519.                           type: int
    520. 

  520.                     sort order: ++
    521. 

  521.                     Map-reduce partition columns:
    522. 

  522.                           expr: _col0
    523. 

  523.                           type: string
    524. 

  524.                           expr: _col1
    525. 

  525.                           type: int
    526. 

  526.                     tag: -1
    527. 

  527.                     value expressions:
    528. 

  528.                           expr: _col2
    529. 

  529.                           type: bigint
    530. 

  530.       Reduce Operator Tree:
    531. 

  531.         Group By Operator
    532. 

  532.           aggregations:
    533. 

  533.                 expr: count(VALUE._col0)
    534. 

  534.           bucketGroup: false
    535. 

  535.           keys:
    536. 

  536.                 expr: KEY._col0
    537. 

  537.                 type: string
    538. 

  538.                 expr: KEY._col1
    539. 

  539.                 type: int
    540. 

  540.           mode: mergepartial
    541. 

  541.           outputColumnNames: _col0, _col1, _col2
    542. 

  542.           Select Operator
    543. 

  543.             expressions:
    544. 

  544.                   expr: _col0
    545. 

  545.                   type: string
    546. 

  546.                   expr: _col2
    547. 

  547.                   type: bigint
    548. 

  548.             outputColumnNames: _col0, _col1
    549. 

  549.             Limit
    550. 

  550.               File Output Operator
    551. 

  551.                 compressed: false
    552. 

  552.                 GlobalTableId: 0
    553. 

  553.                 table:
    554. 

  554.                     input format: org.apache.hadoop.mapred.TextInputFormat
    555. 

  555.                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    556. 

  556. 

  557.   Stage: Stage-0
    558. 

  558.     Fetch Operator
    559. 

  559.       limit: 10
    560. 

  560. 

  561. 

  562. PREHOOK: query: select key, count(1) from clustergroupby  where ds='101' group by key,3 limit 10
    563. 

  563. PREHOOK: type: QUERY
    564. 

  564. PREHOOK: Input: default@clustergroupby@ds=101
    565. 

  565. PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-29_764_2397216315877695624/-mr-10000
    566. 

  566. POSTHOOK: query: select key, count(1) from clustergroupby  where ds='101' group by key,3 limit 10
    567. 

  567. POSTHOOK: type: QUERY
    568. 

  568. POSTHOOK: Input: default@clustergroupby@ds=101
    569. 

  569. POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-29_764_2397216315877695624/-mr-10000
    570. 

  570. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    571. 

  571. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    572. 

  572. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    573. 

  573. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    574. 

  574. 0	3
    575. 

  575. 10	1
    576. 

  576. 100	2
    577. 

  577. 103	2
    578. 

  578. 104	2
    579. 

  579. 105	1
    580. 

  580. 11	1
    581. 

  581. 111	1
    582. 

  582. 113	2
    583. 

  583. 114	1
    584. 

  584. PREHOOK: query: --subquery--
    585. 

  585. explain
    586. 

  586. select key, count(1) from (select value as key, key as value from clustergroupby where ds='101')subq group by key limit 10
    587. 

  587. PREHOOK: type: QUERY
    588. 

  588. POSTHOOK: query: --subquery--
    589. 

  589. explain
    590. 

  590. select key, count(1) from (select value as key, key as value from clustergroupby where ds='101')subq group by key limit 10
    591. 

  591. POSTHOOK: type: QUERY
    592. 

  592. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    593. 

  593. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    594. 

  594. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    595. 

  595. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    596. 

  596. ABSTRACT SYNTAX TREE:
    597. 

  597.   (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL value) key) (TOK_SELEXPR (TOK_TABLE_OR_COL key) value)) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '101')))) subq)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL key)) (TOK_LIMIT 10)))
    598. 

  598. 

  599. STAGE DEPENDENCIES:
    600. 

  600.   Stage-1 is a root stage
    601. 

  601.   Stage-0 is a root stage
    602. 

  602. 

  603. STAGE PLANS:
    604. 

  604.   Stage: Stage-1
    605. 

  605.     Map Reduce
    606. 

  606.       Alias -> Map Operator Tree:
    607. 

  607.         subq:clustergroupby 
    608. 

  608.           TableScan
    609. 

  609.             alias: clustergroupby
    610. 

  610.             Filter Operator
    611. 

  611.               predicate:
    612. 

  612.                   expr: (ds = '101')
    613. 

  613.                   type: boolean
    614. 

  614.               Select Operator
    615. 

  615.                 expressions:
    616. 

  616.                       expr: value
    617. 

  617.                       type: string
    618. 

  618.                 outputColumnNames: _col0
    619. 

  619.                 Select Operator
    620. 

  620.                   expressions:
    621. 

  621.                         expr: _col0
    622. 

  622.                         type: string
    623. 

  623.                   outputColumnNames: _col0
    624. 

  624.                   Group By Operator
    625. 

  625.                     aggregations:
    626. 

  626.                           expr: count(1)
    627. 

  627.                     bucketGroup: false
    628. 

  628.                     keys:
    629. 

  629.                           expr: _col0
    630. 

  630.                           type: string
    631. 

  631.                     mode: hash
    632. 

  632.                     outputColumnNames: _col0, _col1
    633. 

  633.                     Reduce Output Operator
    634. 

  634.                       key expressions:
    635. 

  635.                             expr: _col0
    636. 

  636.                             type: string
    637. 

  637.                       sort order: +
    638. 

  638.                       Map-reduce partition columns:
    639. 

  639.                             expr: _col0
    640. 

  640.                             type: string
    641. 

  641.                       tag: -1
    642. 

  642.                       value expressions:
    643. 

  643.                             expr: _col1
    644. 

  644.                             type: bigint
    645. 

  645.       Reduce Operator Tree:
    646. 

  646.         Group By Operator
    647. 

  647.           aggregations:
    648. 

  648.                 expr: count(VALUE._col0)
    649. 

  649.           bucketGroup: false
    650. 

  650.           keys:
    651. 

  651.                 expr: KEY._col0
    652. 

  652.                 type: string
    653. 

  653.           mode: mergepartial
    654. 

  654.           outputColumnNames: _col0, _col1
    655. 

  655.           Select Operator
    656. 

  656.             expressions:
    657. 

  657.                   expr: _col0
    658. 

  658.                   type: string
    659. 

  659.                   expr: _col1
    660. 

  660.                   type: bigint
    661. 

  661.             outputColumnNames: _col0, _col1
    662. 

  662.             Limit
    663. 

  663.               File Output Operator
    664. 

  664.                 compressed: false
    665. 

  665.                 GlobalTableId: 0
    666. 

  666.                 table:
    667. 

  667.                     input format: org.apache.hadoop.mapred.TextInputFormat
    668. 

  668.                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    669. 

  669. 

  670.   Stage: Stage-0
    671. 

  671.     Fetch Operator
    672. 

  672.       limit: 10
    673. 

  673. 

  674. 

  675. PREHOOK: query: select key, count(1) from (select value as key, key as value from clustergroupby where ds='101')subq group by key limit 10
    676. 

  676. PREHOOK: type: QUERY
    677. 

  677. PREHOOK: Input: default@clustergroupby@ds=101
    678. 

  678. PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-33_487_1431386357774433664/-mr-10000
    679. 

  679. POSTHOOK: query: select key, count(1) from (select value as key, key as value from clustergroupby where ds='101')subq group by key limit 10
    680. 

  680. POSTHOOK: type: QUERY
    681. 

  681. POSTHOOK: Input: default@clustergroupby@ds=101
    682. 

  682. POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-33_487_1431386357774433664/-mr-10000
    683. 

  683. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    684. 

  684. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    685. 

  685. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    686. 

  686. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    687. 

  687. val_0	3
    688. 

  688. val_10	1
    689. 

  689. val_100	2
    690. 

  690. val_103	2
    691. 

  691. val_104	2
    692. 

  692. val_105	1
    693. 

  693. val_11	1
    694. 

  694. val_111	1
    695. 

  695. val_113	2
    696. 

  696. val_114	1
    697. 

  697. PREHOOK: query: explain
    698. 

  698. select key, count(1) from clustergroupby  group by key
    699. 

  699. PREHOOK: type: QUERY
    700. 

  700. POSTHOOK: query: explain
    701. 

  701. select key, count(1) from clustergroupby  group by key
    702. 

  702. POSTHOOK: type: QUERY
    703. 

  703. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    704. 

  704. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    705. 

  705. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    706. 

  706. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    707. 

  707. ABSTRACT SYNTAX TREE:
    708. 

  708.   (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL key))))
    709. 

  709. 

  710. STAGE DEPENDENCIES:
    711. 

  711.   Stage-1 is a root stage
    712. 

  712.   Stage-0 is a root stage
    713. 

  713. 

  714. STAGE PLANS:
    715. 

  715.   Stage: Stage-1
    716. 

  716.     Map Reduce
    717. 

  717.       Alias -> Map Operator Tree:
    718. 

  718.         clustergroupby 
    719. 

  719.           TableScan
    720. 

  720.             alias: clustergroupby
    721. 

  721.             Select Operator
    722. 

  722.               expressions:
    723. 

  723.                     expr: key
    724. 

  724.                     type: string
    725. 

  725.               outputColumnNames: key
    726. 

  726.               Group By Operator
    727. 

  727.                 aggregations:
    728. 

  728.                       expr: count(1)
    729. 

  729.                 bucketGroup: false
    730. 

  730.                 keys:
    731. 

  731.                       expr: key
    732. 

  732.                       type: string
    733. 

  733.                 mode: hash
    734. 

  734.                 outputColumnNames: _col0, _col1
    735. 

  735.                 Reduce Output Operator
    736. 

  736.                   key expressions:
    737. 

  737.                         expr: _col0
    738. 

  738.                         type: string
    739. 

  739.                   sort order: +
    740. 

  740.                   Map-reduce partition columns:
    741. 

  741.                         expr: _col0
    742. 

  742.                         type: string
    743. 

  743.                   tag: -1
    744. 

  744.                   value expressions:
    745. 

  745.                         expr: _col1
    746. 

  746.                         type: bigint
    747. 

  747.       Reduce Operator Tree:
    748. 

  748.         Group By Operator
    749. 

  749.           aggregations:
    750. 

  750.                 expr: count(VALUE._col0)
    751. 

  751.           bucketGroup: false
    752. 

  752.           keys:
    753. 

  753.                 expr: KEY._col0
    754. 

  754.                 type: string
    755. 

  755.           mode: mergepartial
    756. 

  756.           outputColumnNames: _col0, _col1
    757. 

  757.           Select Operator
    758. 

  758.             expressions:
    759. 

  759.                   expr: _col0
    760. 

  760.                   type: string
    761. 

  761.                   expr: _col1
    762. 

  762.                   type: bigint
    763. 

  763.             outputColumnNames: _col0, _col1
    764. 

  764.             File Output Operator
    765. 

  765.               compressed: false
    766. 

  766.               GlobalTableId: 0
    767. 

  767.               table:
    768. 

  768.                   input format: org.apache.hadoop.mapred.TextInputFormat
    769. 

  769.                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    770. 

  770. 

  771.   Stage: Stage-0
    772. 

  772.     Fetch Operator
    773. 

  773.       limit: -1
    774. 

  774. 

  775. 

  776. PREHOOK: query: select key, count(1) from clustergroupby  group by key
    777. 

  777. PREHOOK: type: QUERY
    778. 

  778. PREHOOK: Input: default@clustergroupby@ds=100
    779. 

  779. PREHOOK: Input: default@clustergroupby@ds=101
    780. 

  780. PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-37_126_6695656183965608913/-mr-10000
    781. 

  781. POSTHOOK: query: select key, count(1) from clustergroupby  group by key
    782. 

  782. POSTHOOK: type: QUERY
    783. 

  783. POSTHOOK: Input: default@clustergroupby@ds=100
    784. 

  784. POSTHOOK: Input: default@clustergroupby@ds=101
    785. 

  785. POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-37_126_6695656183965608913/-mr-10000
    786. 

  786. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    787. 

  787. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    788. 

  788. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    789. 

  789. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    790. 

  790. 0	6
    791. 

  791. 10	2
    792. 

  792. 100	4
    793. 

  793. 103	4
    794. 

  794. 104	4
    795. 

  795. 105	2
    796. 

  796. 11	2
    797. 

  797. 111	2
    798. 

  798. 113	4
    799. 

  799. 114	2
    800. 

  800. 116	2
    801. 

  801. 118	4
    802. 

  802. 119	6
    803. 

  803. 12	4
    804. 

  804. 120	4
    805. 

  805. 125	4
    806. 

  806. 126	2
    807. 

  807. 128	6
    808. 

  808. 129	4
    809. 

  809. 131	2
    810. 

  810. 133	2
    811. 

  811. 134	4
    812. 

  812. 136	2
    813. 

  813. 137	4
    814. 

  814. 138	8
    815. 

  815. 143	2
    816. 

  816. 145	2
    817. 

  817. 146	4
    818. 

  818. 149	4
    819. 

  819. 15	4
    820. 

  820. 150	2
    821. 

  821. 152	4
    822. 

  822. 153	2
    823. 

  823. 155	2
    824. 

  824. 156	2
    825. 

  825. 157	2
    826. 

  826. 158	2
    827. 

  827. 160	2
    828. 

  828. 162	2
    829. 

  829. 163	2
    830. 

  830. 164	4
    831. 

  831. 165	4
    832. 

  832. 166	2
    833. 

  833. 167	6
    834. 

  834. 168	2
    835. 

  835. 169	8
    836. 

  836. 17	2
    837. 

  837. 170	2
    838. 

  838. 172	4
    839. 

  839. 174	4
    840. 

  840. 175	4
    841. 

  841. 176	4
    842. 

  842. 177	2
    843. 

  843. 178	2
    844. 

  844. 179	4
    845. 

  845. 18	4
    846. 

  846. 180	2
    847. 

  847. 181	2
    848. 

  848. 183	2
    849. 

  849. 186	2
    850. 

  850. 187	6
    851. 

  851. 189	2
    852. 

  852. 19	2
    853. 

  853. 190	2
    854. 

  854. 191	4
    855. 

  855. 192	2
    856. 

  856. 193	6
    857. 

  857. 194	2
    858. 

  858. 195	4
    859. 

  859. 196	2
    860. 

  860. 197	4
    861. 

  861. 199	6
    862. 

  862. 2	2
    863. 

  863. 20	2
    864. 

  864. 200	4
    865. 

  865. 201	2
    866. 

  866. 202	2
    867. 

  867. 203	4
    868. 

  868. 205	4
    869. 

  869. 207	4
    870. 

  870. 208	6
    871. 

  871. 209	4
    872. 

  872. 213	4
    873. 

  873. 214	2
    874. 

  874. 216	4
    875. 

  875. 217	4
    876. 

  876. 218	2
    877. 

  877. 219	4
    878. 

  878. 221	4
    879. 

  879. 222	2
    880. 

  880. 223	4
    881. 

  881. 224	4
    882. 

  882. 226	2
    883. 

  883. 228	2
    884. 

  884. 229	4
    885. 

  885. 230	10
    886. 

  886. 233	4
    887. 

  887. 235	2
    888. 

  888. 237	4
    889. 

  889. 238	4
    890. 

  890. 239	4
    891. 

  891. 24	4
    892. 

  892. 241	2
    893. 

  893. 242	4
    894. 

  894. 244	2
    895. 

  895. 247	2
    896. 

  896. 248	2
    897. 

  897. 249	2
    898. 

  898. 252	2
    899. 

  899. 255	4
    900. 

  900. 256	4
    901. 

  901. 257	2
    902. 

  902. 258	2
    903. 

  903. 26	4
    904. 

  904. 260	2
    905. 

  905. 262	2
    906. 

  906. 263	2
    907. 

  907. 265	4
    908. 

  908. 266	2
    909. 

  909. 27	2
    910. 

  910. 272	4
    911. 

  911. 273	6
    912. 

  912. 274	2
    913. 

  913. 275	2
    914. 

  914. 277	8
    915. 

  915. 278	4
    916. 

  916. 28	2
    917. 

  917. 280	4
    918. 

  918. 281	4
    919. 

  919. 282	4
    920. 

  920. 283	2
    921. 

  921. 284	2
    922. 

  922. 285	2
    923. 

  923. 286	2
    924. 

  924. 287	2
    925. 

  925. 288	4
    926. 

  926. 289	2
    927. 

  927. 291	2
    928. 

  928. 292	2
    929. 

  929. 296	2
    930. 

  930. 298	6
    931. 

  931. 30	2
    932. 

  932. 302	2
    933. 

  933. 305	2
    934. 

  934. 306	2
    935. 

  935. 307	4
    936. 

  936. 308	2
    937. 

  937. 309	4
    938. 

  938. 310	2
    939. 

  939. 311	6
    940. 

  940. 315	2
    941. 

  941. 316	6
    942. 

  942. 317	4
    943. 

  943. 318	6
    944. 

  944. 321	4
    945. 

  945. 322	4
    946. 

  946. 323	2
    947. 

  947. 325	4
    948. 

  948. 327	6
    949. 

  949. 33	2
    950. 

  950. 331	4
    951. 

  951. 332	2
    952. 

  952. 333	4
    953. 

  953. 335	2
    954. 

  954. 336	2
    955. 

  955. 338	2
    956. 

  956. 339	2
    957. 

  957. 34	2
    958. 

  958. 341	2
    959. 

  959. 342	4
    960. 

  960. 344	4
    961. 

  961. 345	2
    962. 

  962. 348	10
    963. 

  963. 35	6
    964. 

  964. 351	2
    965. 

  965. 353	4
    966. 

  966. 356	2
    967. 

  967. 360	2
    968. 

  968. 362	2
    969. 

  969. 364	2
    970. 

  970. 365	2
    971. 

  971. 366	2
    972. 

  972. 367	4
    973. 

  973. 368	2
    974. 

  974. 369	6
    975. 

  975. 37	4
    976. 

  976. 373	2
    977. 

  977. 374	2
    978. 

  978. 375	2
    979. 

  979. 377	2
    980. 

  980. 378	2
    981. 

  981. 379	2
    982. 

  982. 382	4
    983. 

  983. 384	6
    984. 

  984. 386	2
    985. 

  985. 389	2
    986. 

  986. 392	2
    987. 

  987. 393	2
    988. 

  988. 394	2
    989. 

  989. 395	4
    990. 

  990. 396	6
    991. 

  991. 397	4
    992. 

  992. 399	4
    993. 

  993. 4	2
    994. 

  994. 400	2
    995. 

  995. 401	10
    996. 

  996. 402	2
    997. 

  997. 403	6
    998. 

  998. 404	4
    999. 

  999. 406	8
    1000. 

  1000. 407	2
    1001. 

  1001. 409	6
    1002. 

  1002. 41	2
    1003. 

  1003. 411	2
    1004. 

  1004. 413	4
    1005. 

  1005. 414	4
    1006. 

  1006. 417	6
    1007. 

  1007. 418	2
    1008. 

  1008. 419	2
    1009. 

  1009. 42	4
    1010. 

  1010. 421	2
    1011. 

  1011. 424	4
    1012. 

  1012. 427	2
    1013. 

  1013. 429	4
    1014. 

  1014. 43	2
    1015. 

  1015. 430	6
    1016. 

  1016. 431	6
    1017. 

  1017. 432	2
    1018. 

  1018. 435	2
    1019. 

  1019. 436	2
    1020. 

  1020. 437	2
    1021. 

  1021. 438	6
    1022. 

  1022. 439	4
    1023. 

  1023. 44	2
    1024. 

  1024. 443	2
    1025. 

  1025. 444	2
    1026. 

  1026. 446	2
    1027. 

  1027. 448	2
    1028. 

  1028. 449	2
    1029. 

  1029. 452	2
    1030. 

  1030. 453	2
    1031. 

  1031. 454	6
    1032. 

  1032. 455	2
    1033. 

  1033. 457	2
    1034. 

  1034. 458	4
    1035. 

  1035. 459	4
    1036. 

  1036. 460	2
    1037. 

  1037. 462	4
    1038. 

  1038. 463	4
    1039. 

  1039. 466	6
    1040. 

  1040. 467	2
    1041. 

  1041. 468	8
    1042. 

  1042. 469	10
    1043. 

  1043. 47	2
    1044. 

  1044. 470	2
    1045. 

  1045. 472	2
    1046. 

  1046. 475	2
    1047. 

  1047. 477	2
    1048. 

  1048. 478	4
    1049. 

  1049. 479	2
    1050. 

  1050. 480	6
    1051. 

  1051. 481	2
    1052. 

  1052. 482	2
    1053. 

  1053. 483	2
    1054. 

  1054. 484	2
    1055. 

  1055. 485	2
    1056. 

  1056. 487	2
    1057. 

  1057. 489	8
    1058. 

  1058. 490	2
    1059. 

  1059. 491	2
    1060. 

  1060. 492	4
    1061. 

  1061. 493	2
    1062. 

  1062. 494	2
    1063. 

  1063. 495	2
    1064. 

  1064. 496	2
    1065. 

  1065. 497	2
    1066. 

  1066. 498	6
    1067. 

  1067. 5	6
    1068. 

  1068. 51	4
    1069. 

  1069. 53	2
    1070. 

  1070. 54	2
    1071. 

  1071. 57	2
    1072. 

  1072. 58	4
    1073. 

  1073. 64	2
    1074. 

  1074. 65	2
    1075. 

  1075. 66	2
    1076. 

  1076. 67	4
    1077. 

  1077. 69	2
    1078. 

  1078. 70	6
    1079. 

  1079. 72	4
    1080. 

  1080. 74	2
    1081. 

  1081. 76	4
    1082. 

  1082. 77	2
    1083. 

  1083. 78	2
    1084. 

  1084. 8	2
    1085. 

  1085. 80	2
    1086. 

  1086. 82	2
    1087. 

  1087. 83	4
    1088. 

  1088. 84	4
    1089. 

  1089. 85	2
    1090. 

  1090. 86	2
    1091. 

  1091. 87	2
    1092. 

  1092. 9	2
    1093. 

  1093. 90	6
    1094. 

  1094. 92	2
    1095. 

  1095. 95	4
    1096. 

  1096. 96	2
    1097. 

  1097. 97	4
    1098. 

  1098. 98	4
    1099. 

  1099. PREHOOK: query: explain
    1100. 

  1100. select key, count(1) from clustergroupby  group by key, 3
    1101. 

  1101. PREHOOK: type: QUERY
    1102. 

  1102. POSTHOOK: query: explain
    1103. 

  1103. select key, count(1) from clustergroupby  group by key, 3
    1104. 

  1104. POSTHOOK: type: QUERY
    1105. 

  1105. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1106. 

  1106. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    1107. 

  1107. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1108. 

  1108. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    1109. 

  1109. ABSTRACT SYNTAX TREE:
    1110. 

  1110.   (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL key) 3)))
    1111. 

  1111. 

  1112. STAGE DEPENDENCIES:
    1113. 

  1113.   Stage-1 is a root stage
    1114. 

  1114.   Stage-0 is a root stage
    1115. 

  1115. 

  1116. STAGE PLANS:
    1117. 

  1117.   Stage: Stage-1
    1118. 

  1118.     Map Reduce
    1119. 

  1119.       Alias -> Map Operator Tree:
    1120. 

  1120.         clustergroupby 
    1121. 

  1121.           TableScan
    1122. 

  1122.             alias: clustergroupby
    1123. 

  1123.             Select Operator
    1124. 

  1124.               expressions:
    1125. 

  1125.                     expr: key
    1126. 

  1126.                     type: string
    1127. 

  1127.               outputColumnNames: key
    1128. 

  1128.               Group By Operator
    1129. 

  1129.                 aggregations:
    1130. 

  1130.                       expr: count(1)
    1131. 

  1131.                 bucketGroup: false
    1132. 

  1132.                 keys:
    1133. 

  1133.                       expr: key
    1134. 

  1134.                       type: string
    1135. 

  1135.                       expr: 3
    1136. 

  1136.                       type: int
    1137. 

  1137.                 mode: hash
    1138. 

  1138.                 outputColumnNames: _col0, _col1, _col2
    1139. 

  1139.                 Reduce Output Operator
    1140. 

  1140.                   key expressions:
    1141. 

  1141.                         expr: _col0
    1142. 

  1142.                         type: string
    1143. 

  1143.                         expr: _col1
    1144. 

  1144.                         type: int
    1145. 

  1145.                   sort order: ++
    1146. 

  1146.                   Map-reduce partition columns:
    1147. 

  1147.                         expr: _col0
    1148. 

  1148.                         type: string
    1149. 

  1149.                         expr: _col1
    1150. 

  1150.                         type: int
    1151. 

  1151.                   tag: -1
    1152. 

  1152.                   value expressions:
    1153. 

  1153.                         expr: _col2
    1154. 

  1154.                         type: bigint
    1155. 

  1155.       Reduce Operator Tree:
    1156. 

  1156.         Group By Operator
    1157. 

  1157.           aggregations:
    1158. 

  1158.                 expr: count(VALUE._col0)
    1159. 

  1159.           bucketGroup: false
    1160. 

  1160.           keys:
    1161. 

  1161.                 expr: KEY._col0
    1162. 

  1162.                 type: string
    1163. 

  1163.                 expr: KEY._col1
    1164. 

  1164.                 type: int
    1165. 

  1165.           mode: mergepartial
    1166. 

  1166.           outputColumnNames: _col0, _col1, _col2
    1167. 

  1167.           Select Operator
    1168. 

  1168.             expressions:
    1169. 

  1169.                   expr: _col0
    1170. 

  1170.                   type: string
    1171. 

  1171.                   expr: _col2
    1172. 

  1172.                   type: bigint
    1173. 

  1173.             outputColumnNames: _col0, _col1
    1174. 

  1174.             File Output Operator
    1175. 

  1175.               compressed: false
    1176. 

  1176.               GlobalTableId: 0
    1177. 

  1177.               table:
    1178. 

  1178.                   input format: org.apache.hadoop.mapred.TextInputFormat
    1179. 

  1179.                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    1180. 

  1180. 

  1181.   Stage: Stage-0
    1182. 

  1182.     Fetch Operator
    1183. 

  1183.       limit: -1
    1184. 

  1184. 

  1185. 

  1186. PREHOOK: query: --sort columns--
    1187. 

  1187. alter table clustergroupby clustered by (value) sorted by (key, value) into 1 buckets
    1188. 

  1188. PREHOOK: type: ALTERTABLE_CLUSTER_SORT
    1189. 

  1189. PREHOOK: Input: default@clustergroupby
    1190. 

  1190. PREHOOK: Output: default@clustergroupby
    1191. 

  1191. POSTHOOK: query: --sort columns--
    1192. 

  1192. alter table clustergroupby clustered by (value) sorted by (key, value) into 1 buckets
    1193. 

  1193. POSTHOOK: type: ALTERTABLE_CLUSTER_SORT
    1194. 

  1194. POSTHOOK: Input: default@clustergroupby
    1195. 

  1195. POSTHOOK: Output: default@clustergroupby
    1196. 

  1196. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1197. 

  1197. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    1198. 

  1198. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1199. 

  1199. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    1200. 

  1200. PREHOOK: query: describe extended clustergroupby
    1201. 

  1201. PREHOOK: type: DESCTABLE
    1202. 

  1202. POSTHOOK: query: describe extended clustergroupby
    1203. 

  1203. POSTHOOK: type: DESCTABLE
    1204. 

  1204. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1205. 

  1205. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    1206. 

  1206. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1207. 

  1207. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    1208. 

  1208. key	string	
    1209. 

  1209. value	string	
    1210. 

  1210. ds	string	
    1211. 

  1211. 	 	 
    1212. 

  1212. Detailed Table Information	Table(tableName:clustergroupby, dbName:default, owner:sdong, createTime:1297330264, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:value, type:string, comment:null), FieldSchema(name:ds, type:string, comment:null)], location:pfile:/data/users/sdong/www/open-source-hive1/build/ql/test/data/warehouse/clustergroupby, inputFormat:org.apache.hadoop.mapred.TextInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat, compressed:false, numBuckets:1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe, parameters:{serialization.format=1}), bucketCols:[value], sortCols:[Order(col:key, order:1), Order(col:value, order:1)], parameters:{}), partitionKeys:[FieldSchema(name:ds, type:string, comment:null)], parameters:{numPartitions=2, numFiles=2, last_modified_by=sdong, last_modified_time=1297330300, transient_lastDdlTime=1297330300, numRows=1000, totalSize=11624}, viewOriginalText:null, viewExpandedText:null, tableType:MANAGED_TABLE)	
    1213. 

  1213. PREHOOK: query: insert overwrite table clustergroupby partition (ds='102') select key, value from src distribute by value sort by key, value
    1214. 

  1214. PREHOOK: type: QUERY
    1215. 

  1215. PREHOOK: Input: default@src
    1216. 

  1216. PREHOOK: Output: default@clustergroupby@ds=102
    1217. 

  1217. POSTHOOK: query: insert overwrite table clustergroupby partition (ds='102') select key, value from src distribute by value sort by key, value
    1218. 

  1218. POSTHOOK: type: QUERY
    1219. 

  1219. POSTHOOK: Input: default@src
    1220. 

  1220. POSTHOOK: Output: default@clustergroupby@ds=102
    1221. 

  1221. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1222. 

  1222. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    1223. 

  1223. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1224. 

  1224. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    1225. 

  1225. POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1226. 

  1226. POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    1227. 

  1227. PREHOOK: query: explain
    1228. 

  1228. select key, count(1) from clustergroupby  where ds='102'  group by key limit 10
    1229. 

  1229. PREHOOK: type: QUERY
    1230. 

  1230. POSTHOOK: query: explain
    1231. 

  1231. select key, count(1) from clustergroupby  where ds='102'  group by key limit 10
    1232. 

  1232. POSTHOOK: type: QUERY
    1233. 

  1233. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1234. 

  1234. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    1235. 

  1235. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1236. 

  1236. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    1237. 

  1237. POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1238. 

  1238. POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    1239. 

  1239. ABSTRACT SYNTAX TREE:
    1240. 

  1240.   (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '102')) (TOK_GROUPBY (TOK_TABLE_OR_COL key)) (TOK_LIMIT 10)))
    1241. 

  1241. 

  1242. STAGE DEPENDENCIES:
    1243. 

  1243.   Stage-1 is a root stage
    1244. 

  1244.   Stage-0 is a root stage
    1245. 

  1245. 

  1246. STAGE PLANS:
    1247. 

  1247.   Stage: Stage-1
    1248. 

  1248.     Map Reduce
    1249. 

  1249.       Alias -> Map Operator Tree:
    1250. 

  1250.         clustergroupby 
    1251. 

  1251.           TableScan
    1252. 

  1252.             alias: clustergroupby
    1253. 

  1253.             Filter Operator
    1254. 

  1254.               predicate:
    1255. 

  1255.                   expr: (ds = '102')
    1256. 

  1256.                   type: boolean
    1257. 

  1257.               Select Operator
    1258. 

  1258.                 expressions:
    1259. 

  1259.                       expr: key
    1260. 

  1260.                       type: string
    1261. 

  1261.                 outputColumnNames: key
    1262. 

  1262.                 Group By Operator
    1263. 

  1263.                   aggregations:
    1264. 

  1264.                         expr: count(1)
    1265. 

  1265.                   bucketGroup: true
    1266. 

  1266.                   keys:
    1267. 

  1267.                         expr: key
    1268. 

  1268.                         type: string
    1269. 

  1269.                   mode: hash
    1270. 

  1270.                   outputColumnNames: _col0, _col1
    1271. 

  1271.                   Reduce Output Operator
    1272. 

  1272.                     key expressions:
    1273. 

  1273.                           expr: _col0
    1274. 

  1274.                           type: string
    1275. 

  1275.                     sort order: +
    1276. 

  1276.                     Map-reduce partition columns:
    1277. 

  1277.                           expr: _col0
    1278. 

  1278.                           type: string
    1279. 

  1279.                     tag: -1
    1280. 

  1280.                     value expressions:
    1281. 

  1281.                           expr: _col1
    1282. 

  1282.                           type: bigint
    1283. 

  1283.       Reduce Operator Tree:
    1284. 

  1284.         Group By Operator
    1285. 

  1285.           aggregations:
    1286. 

  1286.                 expr: count(VALUE._col0)
    1287. 

  1287.           bucketGroup: false
    1288. 

  1288.           keys:
    1289. 

  1289.                 expr: KEY._col0
    1290. 

  1290.                 type: string
    1291. 

  1291.           mode: mergepartial
    1292. 

  1292.           outputColumnNames: _col0, _col1
    1293. 

  1293.           Select Operator
    1294. 

  1294.             expressions:
    1295. 

  1295.                   expr: _col0
    1296. 

  1296.                   type: string
    1297. 

  1297.                   expr: _col1
    1298. 

  1298.                   type: bigint
    1299. 

  1299.             outputColumnNames: _col0, _col1
    1300. 

  1300.             Limit
    1301. 

  1301.               File Output Operator
    1302. 

  1302.                 compressed: false
    1303. 

  1303.                 GlobalTableId: 0
    1304. 

  1304.                 table:
    1305. 

  1305.                     input format: org.apache.hadoop.mapred.TextInputFormat
    1306. 

  1306.                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
    1307. 

  1307. 

  1308.   Stage: Stage-0
    1309. 

  1309.     Fetch Operator
    1310. 

  1310.       limit: 10
    1311. 

  1311. 

  1312. 

  1313. PREHOOK: query: select key, count(1) from clustergroupby  where ds='102' group by key limit 10
    1314. 

  1314. PREHOOK: type: QUERY
    1315. 

  1315. PREHOOK: Input: default@clustergroupby@ds=102
    1316. 

  1316. PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-45_956_2691533777800757183/-mr-10000
    1317. 

  1317. POSTHOOK: query: select key, count(1) from clustergroupby  where ds='102' group by key limit 10
    1318. 

  1318. POSTHOOK: type: QUERY
    1319. 

  1319. POSTHOOK: Input: default@clustergroupby@ds=102
    1320. 

  1320. POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-45_956_2691533777800757183/-mr-10000
    1321. 

  1321. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1322. 

  1322. POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    1323. 

  1323. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1324. 

  1324. POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
    1325. 

  1325. POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
    1326. 

  1326. POSTHOOK: Lineage: clustergroupby PARTITION(…
    1327.

Large files files are truncated, but you can click here to view the full file