Changes between Initial Version and Version 1 of Hinet120702/Lab9

Timestamp:

Jul 2, 2012, 1:42:39 AM (13 years ago)

Author:

jazz

Comment:

--

Hinet120702/Lab9

@@ +1 @@
+◢ <[wiki:Hinet120702/Lab8 實作八]> | <[wiki:Hinet120702 回課程大綱]> ▲ | <[wiki:Hinet120702/Lab10 實作十]> ◣
+
+= 實作九 Lab 9 =
+[[PageOutline]]
+{{{
+#!html
+<div style="text-align: center;"><big style="font-weight: bold;"><big>Hadoop Streaming 搭配不同程式語言練習<br/>Hadoop Streaming in different Language</big></big></div>
+}}}
+
+{{{
+#!text
+以下練習，請連線至 hadoop.nchc.org.tw 操作。底下的 hXXXX 等於您的用戶名稱。
+}}}
+
+== 搭配現存二進位執行檔 ==
+== Existing Binary ==
+
+{{{
+~$ hadoop fs -put /etc/hadoop/conf lab9_input
+~$ hadoop jar hadoop-streaming.jar -input lab9_input -output lab9_out1 -mapper /bin/cat -reducer /usr/bin/wc
+~$ hadoop fs -cat lab9_out1/part-00000
+}}}
+
+== 搭配 Bash Shell Script ==
+
+{{{
+~$ echo "sed -e \"s/ /\n/g\" | grep ." > streamingMapper.sh
+~$ echo "uniq -c | awk '{print \$2 \"\t\" \$1}'" > streamingReducer.sh
+~$ chmod a+x streamingMapper.sh
+~$ chmod a+x streamingReducer.sh
+~$ hadoop jar hadoop-streaming.jar -input lab9_input -output lab9_out2 -mapper streamingMapper.sh -reducer streamingReducer.sh -file streamingMapper.sh -file streamingReducer.sh
+~$ hadoop fs -cat lab9_out2/part-00000
+}}}
+
+== 搭配 PHP Script ==
+
+ * 編輯 mapper 的 php 程式 
+{{{
+~$ cat > mapper.php << EOF
+#!/usr/bin/php
+<?php
+
+\$word2count = array();
+
+// 標準輸入為 STDIN (standard input)
+while ((\$line = fgets(STDIN)) !== false) {
+   // 移除小寫與空白
+   \$line = strtolower(trim(\$line));
+   // 將行拆解成各個字於 words 陣列中
+   \$words = preg_split('/\W/', \$line, 0, PREG_SPLIT_NO_EMPTY);
+   // 將字 +1
+   foreach (\$words as \$word) {
+       \$word2count[\$word] += 1;
+   }
+}
+
+// 將結果寫到 STDOUT (standard output)
+foreach (\$word2count as \$word => \$count) {
+   // 印出 [字 , "tab符號" ,  "數字" , "結束字元"]
+   echo \$word, chr(9), \$count, PHP_EOL;
+}
+?>
+EOF
+}}}
+ * 編輯 reduce 的 php 程式 
+{{{
+~$ cat > reducer.php << EOF
+#!/usr/bin/php
+<?php
+
+\$word2count = array();
+
+// 輸入為 STDIN
+while ((\$line = fgets(STDIN)) !== false) {
+    // 移除多餘的空白
+    \$line = trim(\$line);
+    // 每一行的格式為 (單字 "tab" 數字) ，紀錄到(\$word, \$count)
+    list(\$word, \$count) = explode(chr(9), \$line);
+    // 轉換格式string -> int
+    \$count = intval(\$count);
+    // 加總
+    if (\$count > 0) \$word2count[\$word] += \$count;
+}
+
+// 此行不必要，但可讓output排列更完整
+ksort(\$word2count);
+
+// 將結果寫到 STDOUT (standard output)
+foreach (\$word2count as \$word => \$count) {
+    echo \$word, chr(9), \$count, PHP_EOL;
+}
+?>
+EOF
+}}}
+ * 修改執行權限
+{{{
+~$ chmod a+x *.php
+}}}
+ * 測試是否能運作
+{{{
+~$ echo "i love hadoop, hadoop love u" | ./mapper.php | ./reducer.php
+}}}
+ * 開始執行
+{{{
+~$ hadoop jar hadoop-streaming.jar -mapper mapper.php -reducer reducer.php -input lab9_input -output lab9_out3 -file mapper.php -file reducer.php
+}}}
+ * 檢查結果 
+{{{
+~$ hadoop fs -cat lab9_out3/part-00000
+}}}