| 65 | | |
| 66 | | = Practice 2 : Word Count (Advanced) = |
| 67 | | |
| 68 | | {{{ |
| 69 | | $ echo "\." >pattern.txt && echo "\," >>pattern.txt |
| 70 | | $ hadoop fs -put pattern.txt . |
| 71 | | $ mkdir -p MyJava2 |
| 72 | | }}} |
| 73 | | |
| 74 | | |
| 75 | | * 下載 [http://hadoop.nchc.org.tw/WordCount2.java WordCount2.java] 並存到家目錄;[[BR]]Download [http://hadoop.nchc.org.tw/WordCount2.java WordCount2.java] to home directory |
| 76 | | {{{ |
| 77 | | ~$ wget http://hadoop.nchc.org.tw/WordCount2.java |
| 78 | | }}} |
| 79 | | |
| 80 | | {{{ |
| 81 | | $ javac -classpath hadoop-core.jar -d MyJava2 WordCount2.java |
| 82 | | $ jar -cvf wordcount2.jar -C MyJava2 . |
| 83 | | $ hadoop jar wordcount2.jar WordCount2 lab8_input lab8_out2 -skip pattern.txt |
| 84 | | $ hadoop fs -cat lab8_out2/part-00000 |
| 85 | | }}} |
| 86 | | |
| 87 | | * lab8_out2 執行結果[[BR]]You should see results like this: |
| 88 | | {{{ |
| 89 | | #!text |
| 90 | | Cloud 2 |
| 91 | | Course 2 |
| 92 | | I 2 |
| 93 | | NCTU 1 |
| 94 | | and 1 |
| 95 | | course 1 |
| 96 | | enjoy 1 |
| 97 | | like 2 |
| 98 | | nctu 1 |
| 99 | | this 1 |
| 100 | | we 1 |
| 101 | | }}} |
| 102 | | |
| 103 | | * Let's given case insensitive and ignore pattern for this example |
| 104 | | {{{ |
| 105 | | $ hadoop jar wordcount2.jar WordCount2 -Dwordcount.case.sensitive=false lab8_input lab8_out3 -skip pattern.txt |
| 106 | | $ hadoop fs -cat lab8_out3/part-00000 |
| 107 | | }}} |
| 108 | | |
| 109 | | * lab8_out3 執行結果[[BR]]You should see results like this: |
| 110 | | {{{ |
| 111 | | #!text |
| 112 | | and 1 |
| 113 | | cloud 2 |
| 114 | | course 3 |
| 115 | | enjoy 1 |
| 116 | | i 2 |
| 117 | | like 2 |
| 118 | | nctu 2 |
| 119 | | this 1 |
| 120 | | we 1 |
| 121 | | }}} |