{"id":9035,"date":"2026-08-24T09:22:38","date_gmt":"2026-08-24T01:22:38","guid":{"rendered":"https:\/\/nj.transwarp.cn:8180\/?p=9035"},"modified":"2026-08-24T09:22:38","modified_gmt":"2026-08-24T01:22:38","slug":"orc-tools%e5%9f%ba%e7%a1%80%e4%bd%bf%e7%94%a8%e5%a7%bf%e5%8a%bf","status":"publish","type":"post","link":"https:\/\/kbwp.transwarp.cn\/?p=9035","title":{"rendered":"orc-tools\u5de5\u5177\u4f7f\u7528\u6307\u5357"},"content":{"rendered":"

\u6982\u8981\u63cf\u8ff0<\/h3>\n
\n

\u5185\u90e8\u6587\u6863<\/p>\n

\u672c\u6587\u4e3b\u8981\u4ecb\u7ecd\u5982\u4f55\u901a\u8fc7orc-tools\u5de5\u5177\u89e3\u6790orc\u6587\u4ef6\uff0c\u65b9\u4fbf\u95ee\u9898\u6392\u67e5\u6570\u636e\u6587\u4ef6\u635f\u574f\u4e4b\u7c7b\u7684\u95ee\u9898\u3002<\/p>\n

\u8be6\u7ec6\u8bf4\u660e<\/h3>\n
\n

\u53ef\u4ee5\u901a\u8fc7-h<\/code>\u67e5\u770bjar\u5305\u7684\u4f7f\u7528\u5e2e\u52a9\u8bf4\u660e<\/p>\n

[root@st01~]$ java -jar orc-tools-1.6.3-uber.jar -h\nORC Java Tools\n\nusage: java -jar orc-tools-*.jar [--help] [--define X=Y]  \n\nCommands:\n   version - print the version of this ORC tool\n   meta - print the metadata about the ORC file\n   data - print the data from the ORC file\n   scan - scan the ORC file\n   convert - convert CSV and JSON files to ORC\n   json-schema - scan JSON files to determine their schema\n   key - print information about the keys\n\nTo get more help, provide -h to the command<\/code><\/pre>\n
\u901a\u8fc7version<\/code>\u53c2\u6570\u53ef\u4ee5\u770b\u5230orc-tools\u7684\u7248\u672c\u4fe1\u606f<\/p>\n
[root@st01~]$ java -jar orc-tools-1.6.3-uber.jar version\nORC 1.6.3<\/code><\/pre>\n
\u4e0b\u9762\u5217\u4e3e\u51e0\u4e2a\u5e38\u7528\u7684\u53c2\u6570\u4e3e\u4f8b\u5b50\u4ecb\u7ecd\uff1a<\/strong><\/p>\n
\u6211\u4eec\u521b\u5efa\u4e00\u5f20orc\u4e8b\u52a1\u8868\uff0c\u8868\u540d\u4e3aemp<\/code><\/p>\n
DROP TABLE IF EXISTS EMP;\nCREATE TABLE EMP(\n       EMPNO int,\n       ENAME string,\n       JOB string,\n       MGR INT,\n       HIREDATE DATE,\n       SAL INT,\n       COMM INT,\n       DEPTNO INT\n)CLUSTERED BY (empno) INTO 3 BUCKETS \nSTORED AS ORC_TRANSACTION;\n\nINSERT INTO EMP VALUES (7369,'SMITH','CLERK',7902,tdh_todate('17-12-1980','dd-mm-yyyy'),800,NULL,20);\nINSERT INTO EMP VALUES (7499,'ALLEN','SALESMAN',7698,tdh_todate('20-2-1981','dd-mm-yyyy'),1600,300,30);\nINSERT INTO EMP VALUES (7521,'WARD','SALESMAN',7698,tdh_todate('22-2-1981','dd-mm-yyyy'),1250,500,30);\nINSERT INTO EMP VALUES (7566,'JONES','MANAGER',7839,tdh_todate('2-4-1981','dd-mm-yyyy'),2975,NULL,20);\nINSERT INTO EMP VALUES (7654,'MARTIN','SALESMAN',7698,tdh_todate('28-9-1981','dd-mm-yyyy'),1250,1400,30);\nINSERT INTO EMP VALUES (7698,'BLAKE','MANAGER',7839,tdh_todate('1-5-1981','dd-mm-yyyy'),2850,NULL,30);\nINSERT INTO EMP VALUES (7782,'CLARK','MANAGER',7839,tdh_todate('9-6-1981','dd-mm-yyyy'),2450,NULL,10);\nINSERT INTO EMP VALUES (7788,'SCOTT','ANALYST',7566,tdh_todate('13-4-1987','dd-mm-yyyy'),3000,NULL,20);\nINSERT INTO EMP VALUES (7839,'KING','PRESIDENT',NULL,tdh_todate('17-11-1981','dd-mm-yyyy'),5000,NULL,10);\nINSERT INTO EMP VALUES (7844,'TURNER','SALESMAN',7698,tdh_todate('8-9-1981','dd-mm-yyyy'),1500,0,30);\nINSERT INTO EMP VALUES (7876,'ADAMS','CLERK',7788,tdh_todate('13-5-1987', 'dd-mm-yyyy'),1100,NULL,20);\nINSERT INTO EMP VALUES (7900,'JAMES','CLERK',7698,tdh_todate('3-12-1981','dd-mm-yyyy'),950,NULL,30);\nINSERT INTO EMP VALUES (7902,'FORD','ANALYST',7566,tdh_todate('3-12-1981','dd-mm-yyyy'),3000,NULL,20);\nINSERT INTO EMP VALUES (7934,'MILLER','CLERK',7782,tdh_todate('23-1-1982','dd-mm-yyyy'),1300,NULL,10);\n\nSELECT * FROM EMP;\nSHOW CREATE TABLE emp;\ndfs -ls hdfs:\/\/nameservice1\/inceptor1\/user\/hive\/warehouse\/default.db\/hive\/emp\ndfs -ls hdfs:\/\/nameservice1\/inceptor1\/user\/hive\/warehouse\/default.db\/hive\/emp\/base_0000079\n-rwx--x--x   3 hive hive       1393 2022-11-24 15:55 hdfs:\/\/nameservice1\/inceptor1\/user\/hive\/warehouse\/default.db\/hive\/emp\/base_0000079\/bucket_00000\n-rwx--x--x   3 hive hive       1303 2022-11-24 15:55 hdfs:\/\/nameservice1\/inceptor1\/user\/hive\/warehouse\/default.db\/hive\/emp\/base_0000079\/bucket_00001\n-rwx--x--x   3 hive hive       1292 2022-11-24 15:55 hdfs:\/\/nameservice1\/inceptor1\/user\/hive\/warehouse\/default.db\/hive\/emp\/base_0000079\/bucket_00002<\/code><\/pre>\n
\u5c06\u8fd93\u4e2abucket\u6587\u4ef6\u901a\u8fc7hdfs\u547d\u4ee4get\u5230\u672c\u5730\u6765\u89e3\u6790\uff08\u6ce8\u610f\uff01\u4e0d\u8981\u4f7f\u7528getmerge\u8fd9\u79cd\u5408\u5e76\u6587\u4ef6\u7684\u547d\u4ee4\uff0c\u4f1a\u5bfc\u81f4orc\u6587\u4ef6\u65e0\u6cd5\u89e3\u6790\uff09<\/p>\n
1\u3001\u89e3\u6790metadata<\/h4>\n
\u5143\u4fe1\u606f\u7ed3\u679c\u8f83\u957f\uff0c\u6211\u4eec\u53d6bucket_00000<\/code>\u7684\u6267\u884c\u7ed3\u679c\uff1a<\/p>\n
[root@st01~]$ java -jar orc-tools-1.6.3-uber.jar meta .\/bucket_00000\nlog4j:WARN No appenders could be found for logger (org.apache.hadoop.util.Shell).\nlog4j:WARN Please initialize the log4j system properly.\nlog4j:WARN See http:\/\/logging.apache.org\/log4j\/1.2\/faq.html#noconfig for more info.\nProcessing data file bucket_00000 [length: 1393]\nStructure for bucket_00000\nFile Version: 0.12 with HIVE_4243\nRows: 7\nCompression: ZLIB\nCompression size: 262144\nCalendar: Julian\/Gregorian\nType: struct>\n\nStripe Statistics:\n  Stripe 1:\n    Column 0: count: 7 hasNull: false\n    Column 1: count: 7 hasNull: false min: 0 max: 0 sum: 0\n    Column 2: count: 7 hasNull: false min: 68 max: 78 sum: 505\n    Column 3: count: 7 hasNull: false min: 0 max: 0 sum: 0\n    Column 4: count: 7 hasNull: false min: 0 max: 0 sum: 0\n    Column 5: count: 7 hasNull: false min: 68 max: 78 sum: 505\n    Column 6: count: 7 hasNull: false\n    Column 7: count: 7 hasNull: false min: 7521 max: 7902 sum: 54096\n    Column 8: count: 7 hasNull: false min: BLAKE max: WARD sum: 32\n    Column 9: count: 7 hasNull: false min: ANALYST max: SALESMAN sum: 52\n    Column 10: count: 6 hasNull: true min: 7566 max: 7839 sum: 46347\n    Column 11: count: 7 hasNull: false min: 1981-01-01 max: 1987-01-13\n    Column 12: count: 7 hasNull: false min: 1250 max: 5000 sum: 20525\n    Column 13: count: 1 hasNull: true min: 500 max: 500 sum: 500\n    Column 14: count: 7 hasNull: false min: 10 max: 30 sum: 140\n\nFile Statistics:\n  Column 0: count: 7 hasNull: false\n  Column 1: count: 7 hasNull: false min: 0 max: 0 sum: 0\n  Column 2: count: 7 hasNull: false min: 68 max: 78 sum: 505\n  Column 3: count: 7 hasNull: false min: 0 max: 0 sum: 0\n  Column 4: count: 7 hasNull: false min: 0 max: 0 sum: 0\n  Column 5: count: 7 hasNull: false min: 68 max: 78 sum: 505\n  Column 6: count: 7 hasNull: false\n  Column 7: count: 7 hasNull: false min: 7521 max: 7902 sum: 54096\n  Column 8: count: 7 hasNull: false min: BLAKE max: WARD sum: 32\n  Column 9: count: 7 hasNull: false min: ANALYST max: SALESMAN sum: 52\n  Column 10: count: 6 hasNull: true min: 7566 max: 7839 sum: 46347\n  Column 11: count: 7 hasNull: false min: 1981-01-01 max: 1987-01-13\n  Column 12: count: 7 hasNull: false min: 1250 max: 5000 sum: 20525\n  Column 13: count: 1 hasNull: true min: 500 max: 500 sum: 500\n  Column 14: count: 7 hasNull: false min: 10 max: 30 sum: 140\n\nStripes:\n  Stripe: offset: 3 data: 234 rows: 7 tail: 136 index: 385\n    Stream: column 0 section ROW_INDEX start: 3 length 11\n    Stream: column 1 section ROW_INDEX start: 14 length 24\n    Stream: column 2 section ROW_INDEX start: 38 length 27\n    Stream: column 3 section ROW_INDEX start: 65 length 24\n    Stream: column 4 section ROW_INDEX start: 89 length 24\n    Stream: column 5 section ROW_INDEX start: 113 length 27\n    Stream: column 6 section ROW_INDEX start: 140 length 11\n    Stream: column 7 section ROW_INDEX start: 151 length 28\n    Stream: column 8 section ROW_INDEX start: 179 length 34\n    Stream: column 9 section ROW_INDEX start: 213 length 39\n    Stream: column 10 section ROW_INDEX start: 252 length 30\n    Stream: column 11 section ROW_INDEX start: 282 length 24\n    Stream: column 12 section ROW_INDEX start: 306 length 28\n    Stream: column 13 section ROW_INDEX start: 334 length 29\n    Stream: column 14 section ROW_INDEX start: 363 length 25\n    Stream: column 1 section DATA start: 388 length 5\n    Stream: column 2 section DATA start: 393 length 11\n    Stream: column 3 section DATA start: 404 length 5\n    Stream: column 4 section DATA start: 409 length 5\n    Stream: column 5 section DATA start: 414 length 11\n    Stream: column 7 section DATA start: 425 length 13\n    Stream: column 8 section DATA start: 438 length 35\n    Stream: column 8 section LENGTH start: 473 length 14\n    Stream: column 9 section DATA start: 487 length 11\n    Stream: column 9 section LENGTH start: 498 length 7\n    Stream: column 9 section DICTIONARY_DATA start: 505 length 34\n    Stream: column 10 section PRESENT start: 539 length 5\n    Stream: column 10 section DATA start: 544 length 16\n    Stream: column 11 section DATA start: 560 length 19\n    Stream: column 12 section DATA start: 579 length 19\n    Stream: column 13 section PRESENT start: 598 length 5\n    Stream: column 13 section DATA start: 603 length 7\n    Stream: column 14 section DATA start: 610 length 12\n    Encoding column 0: DIRECT\n    Encoding column 1: DIRECT_V2\n    Encoding column 2: DIRECT_V2\n    Encoding column 3: DIRECT_V2\n    Encoding column 4: DIRECT_V2\n    Encoding column 5: DIRECT_V2\n    Encoding column 6: DIRECT\n    Encoding column 7: DIRECT_V2\n    Encoding column 8: DIRECT_V2\n    Encoding column 9: DICTIONARY_V2[4]\n    Encoding column 10: DIRECT_V2\n    Encoding column 11: DIRECT_V2\n    Encoding column 12: DIRECT_V2\n    Encoding column 13: DIRECT_V2\n    Encoding column 14: DIRECT_V2\n\nFile length: 1393 bytes\nPadding length: 0 bytes\nPadding ratio: 0%\n\nUser Metadata:\n  hive.acid.key.index=\n  hive.acid.stats=7,0,0\n  orc.bloomfilter.columns=\n  orc.column.index.concat.str=all\n________________________________________________________________________________________________________________________\n<\/code><\/pre>\n
2\u3001\u89e3\u6790data<\/h4>\n
\u53ef\u4ee5\u6e05\u6670\u7684\u770b\u5230\u6bcf\u4e2abucket\u6587\u4ef6\u5185\u7684\u6570\u636e\u5185\u5bb9<\/p>\n
[root@st01~]$ java -jar orc-tools-1.6.3-uber.jar data .\/bucket_00000\nlog4j:WARN No appenders could be found for logger (org.apache.hadoop.util.Shell).\nlog4j:WARN Please initialize the log4j system properly.\nlog4j:WARN See http:\/\/logging.apache.org\/log4j\/1.2\/faq.html#noconfig for more info.\nProcessing data file bucket_00000 [length: 1393]\n{\"operation\":0,\"originalTransaction\":68,\"bucket\":0,\"rowId\":0,\"currentTransaction\":68,\"row\":{\"empno\":7521,\"ename\":\"WARD\",\"job\":\"SALESMAN\",\"mgr\":7698,\"hiredate\":\"1981-01-22\",\"sal\":1250,\"comm\":500,\"deptno\":30}}\n{\"operation\":0,\"originalTransaction\":69,\"bucket\":0,\"rowId\":0,\"currentTransaction\":69,\"row\":{\"empno\":7566,\"ename\":\"JONES\",\"job\":\"MANAGER\",\"mgr\":7839,\"hiredate\":\"1981-01-02\",\"sal\":2975,\"comm\":null,\"deptno\":20}}\n{\"operation\":0,\"originalTransaction\":71,\"bucket\":0,\"rowId\":0,\"currentTransaction\":71,\"row\":{\"empno\":7698,\"ename\":\"BLAKE\",\"job\":\"MANAGER\",\"mgr\":7839,\"hiredate\":\"1981-01-01\",\"sal\":2850,\"comm\":null,\"deptno\":30}}\n{\"operation\":0,\"originalTransaction\":72,\"bucket\":0,\"rowId\":0,\"currentTransaction\":72,\"row\":{\"empno\":7782,\"ename\":\"CLARK\",\"job\":\"MANAGER\",\"mgr\":7839,\"hiredate\":\"1981-01-09\",\"sal\":2450,\"comm\":null,\"deptno\":10}}\n{\"operation\":0,\"originalTransaction\":73,\"bucket\":0,\"rowId\":0,\"currentTransaction\":73,\"row\":{\"empno\":7788,\"ename\":\"SCOTT\",\"job\":\"ANALYST\",\"mgr\":7566,\"hiredate\":\"1987-01-13\",\"sal\":3000,\"comm\":null,\"deptno\":20}}\n{\"operation\":0,\"originalTransaction\":74,\"bucket\":0,\"rowId\":0,\"currentTransaction\":74,\"row\":{\"empno\":7839,\"ename\":\"KING\",\"job\":\"PRESIDENT\",\"mgr\":null,\"hiredate\":\"1981-01-17\",\"sal\":5000,\"comm\":null,\"deptno\":10}}\n{\"operation\":0,\"originalTransaction\":78,\"bucket\":0,\"rowId\":0,\"currentTransaction\":78,\"row\":{\"empno\":7902,\"ename\":\"FORD\",\"job\":\"ANALYST\",\"mgr\":7566,\"hiredate\":\"1981-01-03\",\"sal\":3000,\"comm\":null,\"deptno\":20}}\n________________________________________________________________________________________________________________________\n[root@st01~]$ java -jar orc-tools-1.6.3-uber.jar data .\/bucket_00001\nlog4j:WARN No appenders could be found for logger (org.apache.hadoop.util.Shell).\nlog4j:WARN Please initialize the log4j system properly.\nlog4j:WARN See http:\/\/logging.apache.org\/log4j\/1.2\/faq.html#noconfig for more info.\nProcessing data file bucket_00001 [length: 1303]\n{\"operation\":0,\"originalTransaction\":66,\"bucket\":1,\"rowId\":0,\"currentTransaction\":66,\"row\":{\"empno\":7369,\"ename\":\"SMITH\",\"job\":\"CLERK\",\"mgr\":7902,\"hiredate\":\"1980-01-17\",\"sal\":800,\"comm\":null,\"deptno\":20}}\n{\"operation\":0,\"originalTransaction\":70,\"bucket\":1,\"rowId\":0,\"currentTransaction\":70,\"row\":{\"empno\":7654,\"ename\":\"MARTIN\",\"job\":\"SALESMAN\",\"mgr\":7698,\"hiredate\":\"1981-01-28\",\"sal\":1250,\"comm\":1400,\"deptno\":30}}\n{\"operation\":0,\"originalTransaction\":76,\"bucket\":1,\"rowId\":0,\"currentTransaction\":76,\"row\":{\"empno\":7876,\"ename\":\"ADAMS\",\"job\":\"CLERK\",\"mgr\":7788,\"hiredate\":\"1987-01-13\",\"sal\":1100,\"comm\":null,\"deptno\":20}}\n{\"operation\":0,\"originalTransaction\":77,\"bucket\":1,\"rowId\":0,\"currentTransaction\":77,\"row\":{\"empno\":7900,\"ename\":\"JAMES\",\"job\":\"CLERK\",\"mgr\":7698,\"hiredate\":\"1981-01-03\",\"sal\":950,\"comm\":null,\"deptno\":30}}\n________________________________________________________________________________________________________________________\n\n[root@st01~]$ java -jar orc-tools-1.6.3-uber.jar data .\/bucket_00002\nlog4j:WARN No appenders could be found for logger (org.apache.hadoop.util.Shell).\nlog4j:WARN Please initialize the log4j system properly.\nlog4j:WARN See http:\/\/logging.apache.org\/log4j\/1.2\/faq.html#noconfig for more info.\nProcessing data file bucket_00002 [length: 1292]\n{\"operation\":0,\"originalTransaction\":67,\"bucket\":2,\"rowId\":0,\"currentTransaction\":67,\"row\":{\"empno\":7499,\"ename\":\"ALLEN\",\"job\":\"SALESMAN\",\"mgr\":7698,\"hiredate\":\"1981-01-20\",\"sal\":1600,\"comm\":300,\"deptno\":30}}\n{\"operation\":0,\"originalTransaction\":75,\"bucket\":2,\"rowId\":0,\"currentTransaction\":75,\"row\":{\"empno\":7844,\"ename\":\"TURNER\",\"job\":\"SALESMAN\",\"mgr\":7698,\"hiredate\":\"1981-01-08\",\"sal\":1500,\"comm\":0,\"deptno\":30}}\n{\"operation\":0,\"originalTransaction\":79,\"bucket\":2,\"rowId\":0,\"currentTransaction\":79,\"row\":{\"empno\":7934,\"ename\":\"MILLER\",\"job\":\"CLERK\",\"mgr\":7782,\"hiredate\":\"1982-01-23\",\"sal\":1300,\"comm\":null,\"deptno\":10}}\n________________________________________________________________________________________________________________________<\/code><\/pre>\n
\u5176\u4ed6\u53c2\u6570\u4f7f\u7528\u8f83\u5c11\uff0c\u53ef\u4ee5\u81ea\u884c\u6d4b\u8bd5\u3002<\/p>\n
FAQ<\/h3>\n
1\u3001\u6267\u884c\u62a5\u9519org.apache.hadoop.security.AccessControlException: SIMPLE authentication is not enabled.  Available:[TOKEN, OAUTHBEARER, KERBEROS]<\/h4>\n
\u4e0d\u5efa\u8bae\u76f4\u63a5\u8bfb\u53d6hdfs\u8def\u5f84\u7684\u6570\u636e\u6587\u4ef6\uff0c\u5efa\u8bae\u5c06\u6570\u636e\u6587\u4ef6get\u5230\u672c\u5730\u76f4\u63a5\u8bfb\u53d6\u3002<\/p>\n
2\u3001\u6267\u884c\u62a5\u9519 Exception in thread "main" java.lang.UnsupportedClassVersionError: org\/apache\/hadoop\/hive\/common\/io\/DiskRange : Unsupported major.minor version 52.0<\/h4>\n
\u9700\u8981\u4f7f\u7528jdk1.8 \u6765\u8fd0\u884c<\/p>\n","protected":false},"excerpt":{"rendered":"
\u6982\u8981\u63cf\u8ff0 \u5185\u90e8\u6587\u6863 \u672c\u6587\u4e3b\u8981\u4ecb\u7ecd\u5982\u4f55\u901a\u8fc7orc-tools\u5de5\u5177\u89e3\u6790orc\u6587\u4ef6\uff0c\u65b9\u4fbf\u95ee\u9898\u6392\u67e5\u6570\u636e\u6587\u4ef6\u635f\u574f\u4e4b\u7c7b\u7684\u95ee ..<\/p>\n
<\/div>\n
Read more<\/a><\/p>\n","protected":false},"author":12,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[38],"tags":[],"class_list":["post-9035","post","type-post","status-publish","format-standard","hentry","category-configuration"],"acf":[],"_links":{"self":[{"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=\/wp\/v2\/posts\/9035","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=\/wp\/v2\/users\/12"}],"replies":[{"embeddable":true,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=9035"}],"version-history":[{"count":2,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=\/wp\/v2\/posts\/9035\/revisions"}],"predecessor-version":[{"id":14316,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=\/wp\/v2\/posts\/9035\/revisions\/14316"}],"wp:attachment":[{"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=9035"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=9035"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/kbwp.transwarp.cn\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=9035"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}