Skip to content

Commit 7ed459e

Browse files
author
James Lee
committed
first commit
0 parents  commit 7ed459e

File tree

9 files changed

+356
-0
lines changed

9 files changed

+356
-0
lines changed

‎build.gradle

+23
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,23 @@
1+
group 'jameslee'
2+
version '1.0-SNAPSHOT'
3+
4+
apply plugin: 'java'
5+
apply plugin: 'idea'
6+
apply plugin: 'eclipse'
7+
8+
sourceCompatibility = 1.8
9+
10+
idea {
11+
project {
12+
jdkName = '1.8'
13+
languageLevel = '1.8'
14+
}
15+
}
16+
17+
repositories {
18+
mavenCentral()
19+
}
20+
21+
dependencies {
22+
compile group: 'org.apache.spark', name: 'spark-core_2.10', version: '2.0.0'
23+
}

‎gradle/wrapper/gradle-wrapper.jar

52.4 KB
Binary file not shown.

‎gradle/wrapper/gradle-wrapper.properties

+6
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
1+
#Tue Oct 25 21:49:41 BST 2016
2+
distributionBase=GRADLE_USER_HOME
3+
distributionPath=wrapper/dists
4+
zipStoreBase=GRADLE_USER_HOME
5+
zipStorePath=wrapper/dists
6+
distributionUrl=https\://services.gradle.org/distributions/gradle-3.2.1-bin.zip

‎gradlew

+160
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,160 @@
1+
#!/usr/bin/env bash
2+
3+
##############################################################################
4+
##
5+
## Gradle start up script for UN*X
6+
##
7+
##############################################################################
8+
9+
# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
10+
DEFAULT_JVM_OPTS=""
11+
12+
APP_NAME="Gradle"
13+
APP_BASE_NAME=`basename "$0"`
14+
15+
# Use the maximum available, or set MAX_FD != -1 to use that value.
16+
MAX_FD="maximum"
17+
18+
warn ( ) {
19+
echo "$*"
20+
}
21+
22+
die ( ) {
23+
echo
24+
echo "$*"
25+
echo
26+
exit 1
27+
}
28+
29+
# OS specific support (must be 'true' or 'false').
30+
cygwin=false
31+
msys=false
32+
darwin=false
33+
case "`uname`" in
34+
CYGWIN* )
35+
cygwin=true
36+
;;
37+
Darwin* )
38+
darwin=true
39+
;;
40+
MINGW* )
41+
msys=true
42+
;;
43+
esac
44+
45+
# Attempt to set APP_HOME
46+
# Resolve links: $0 may be a link
47+
PRG="$0"
48+
# Need this for relative symlinks.
49+
while [ -h "$PRG" ] ; do
50+
ls=`ls -ld "$PRG"`
51+
link=`expr "$ls" : '.*-> \(.*\)$'`
52+
if expr "$link" : '/.*' > /dev/null; then
53+
PRG="$link"
54+
else
55+
PRG=`dirname "$PRG"`"/$link"
56+
fi
57+
done
58+
SAVED="`pwd`"
59+
cd "`dirname \"$PRG\"`/" >/dev/null
60+
APP_HOME="`pwd -P`"
61+
cd "$SAVED" >/dev/null
62+
63+
CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
64+
65+
# Determine the Java command to use to start the JVM.
66+
if [ -n "$JAVA_HOME" ] ; then
67+
if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
68+
# IBM's JDK on AIX uses strange locations for the executables
69+
JAVACMD="$JAVA_HOME/jre/sh/java"
70+
else
71+
JAVACMD="$JAVA_HOME/bin/java"
72+
fi
73+
if [ ! -x "$JAVACMD" ] ; then
74+
die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
75+
76+
Please set the JAVA_HOME variable in your environment to match the
77+
location of your Java installation."
78+
fi
79+
else
80+
JAVACMD="java"
81+
which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
82+
83+
Please set the JAVA_HOME variable in your environment to match the
84+
location of your Java installation."
85+
fi
86+
87+
# Increase the maximum file descriptors if we can.
88+
if [ "$cygwin" = "false" -a "$darwin" = "false" ] ; then
89+
MAX_FD_LIMIT=`ulimit -H -n`
90+
if [ $? -eq 0 ] ; then
91+
if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
92+
MAX_FD="$MAX_FD_LIMIT"
93+
fi
94+
ulimit -n $MAX_FD
95+
if [ $? -ne 0 ] ; then
96+
warn "Could not set maximum file descriptor limit: $MAX_FD"
97+
fi
98+
else
99+
warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
100+
fi
101+
fi
102+
103+
# For Darwin, add options to specify how the application appears in the dock
104+
if $darwin; then
105+
GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
106+
fi
107+
108+
# For Cygwin, switch paths to Windows format before running java
109+
if $cygwin ; then
110+
APP_HOME=`cygpath --path --mixed "$APP_HOME"`
111+
CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
112+
JAVACMD=`cygpath --unix "$JAVACMD"`
113+
114+
# We build the pattern for arguments to be converted via cygpath
115+
ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
116+
SEP=""
117+
for dir in $ROOTDIRSRAW ; do
118+
ROOTDIRS="$ROOTDIRS$SEP$dir"
119+
SEP="|"
120+
done
121+
OURCYGPATTERN="(^($ROOTDIRS))"
122+
# Add a user-defined pattern to the cygpath arguments
123+
if [ "$GRADLE_CYGPATTERN" != "" ] ; then
124+
OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
125+
fi
126+
# Now convert the arguments - kludge to limit ourselves to /bin/sh
127+
i=0
128+
for arg in "$@" ; do
129+
CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
130+
CHECK2=`echo "$arg"|egrep -c "^-"` ### Determine if an option
131+
132+
if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then ### Added a condition
133+
eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
134+
else
135+
eval `echo args$i`="\"$arg\""
136+
fi
137+
i=$((i+1))
138+
done
139+
case $i in
140+
(0) set -- ;;
141+
(1) set -- "$args0" ;;
142+
(2) set -- "$args0" "$args1" ;;
143+
(3) set -- "$args0" "$args1" "$args2" ;;
144+
(4) set -- "$args0" "$args1" "$args2" "$args3" ;;
145+
(5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
146+
(6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
147+
(7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
148+
(8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
149+
(9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
150+
esac
151+
fi
152+
153+
# Split up the JVM_OPTS And GRADLE_OPTS values into an array, following the shell quoting and substitution rules
154+
function splitJvmOpts() {
155+
JVM_OPTS=("$@")
156+
}
157+
eval splitJvmOpts $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS
158+
JVM_OPTS[${#JVM_OPTS[*]}]="-Dorg.gradle.appname=$APP_BASE_NAME"
159+
160+
exec "$JAVACMD" "${JVM_OPTS[@]}" -classpath "$CLASSPATH" org.gradle.wrapper.GradleWrapperMain "$@"

‎gradlew.bat

+90
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,90 @@
1+
@if "%DEBUG%" == "" @echo off
2+
@rem ##########################################################################
3+
@rem
4+
@rem Gradle startup script for Windows
5+
@rem
6+
@rem ##########################################################################
7+
8+
@rem Set local scope for the variables with windows NT shell
9+
if "%OS%"=="Windows_NT" setlocal
10+
11+
@rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
12+
set DEFAULT_JVM_OPTS=
13+
14+
set DIRNAME=%~dp0
15+
if "%DIRNAME%" == "" set DIRNAME=.
16+
set APP_BASE_NAME=%~n0
17+
set APP_HOME=%DIRNAME%
18+
19+
@rem Find java.exe
20+
if defined JAVA_HOME goto findJavaFromJavaHome
21+
22+
set JAVA_EXE=java.exe
23+
%JAVA_EXE% -version >NUL 2>&1
24+
if "%ERRORLEVEL%" == "0" goto init
25+
26+
echo.
27+
echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
28+
echo.
29+
echo Please set the JAVA_HOME variable in your environment to match the
30+
echo location of your Java installation.
31+
32+
goto fail
33+
34+
:findJavaFromJavaHome
35+
set JAVA_HOME=%JAVA_HOME:"=%
36+
set JAVA_EXE=%JAVA_HOME%/bin/java.exe
37+
38+
if exist "%JAVA_EXE%" goto init
39+
40+
echo.
41+
echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
42+
echo.
43+
echo Please set the JAVA_HOME variable in your environment to match the
44+
echo location of your Java installation.
45+
46+
goto fail
47+
48+
:init
49+
@rem Get command-line arguments, handling Windowz variants
50+
51+
if not "%OS%" == "Windows_NT" goto win9xME_args
52+
if "%@eval[2+2]" == "4" goto 4NT_args
53+
54+
:win9xME_args
55+
@rem Slurp the command line arguments.
56+
set CMD_LINE_ARGS=
57+
set _SKIP=2
58+
59+
:win9xME_args_slurp
60+
if "x%~1" == "x" goto execute
61+
62+
set CMD_LINE_ARGS=%*
63+
goto execute
64+
65+
:4NT_args
66+
@rem Get arguments from the 4NT Shell from JP Software
67+
set CMD_LINE_ARGS=%$
68+
69+
:execute
70+
@rem Setup the command line
71+
72+
set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
73+
74+
@rem Execute Gradle
75+
"%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
76+
77+
:end
78+
@rem End local scope for the variables with windows NT shell
79+
if "%ERRORLEVEL%"=="0" goto mainEnd
80+
81+
:fail
82+
rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
83+
rem the _cmd.exe /c_ return code!
84+
if not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
85+
exit /b 1
86+
87+
:mainEnd
88+
if "%OS%"=="Windows_NT" endlocal
89+
90+
:omega

‎in/uppercase.text

+15
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
The history of New York begins around 10,000 BC, when the first Native Americans arrived. By 1100 AD, New York's main native cultures, the Iroquoian and Algonquian, had developed. European discovery of New York was led by the French in 1524 and the first land claim came in 1609 by the Dutch. As part of New Netherland, the colony was important in the fur trade and eventually became an agricultural resource thanks to the patroon system. In 1626 the Dutch bought the island of Manhattan from Native Americans.[1] In 1664, England renamed the colony New York, after the Duke of York (later James II & VII.) New York City gained prominence in the 18th century as a major trading port in the Thirteen Colonies.
2+
3+
New York played a pivotal role during the American Revolution and subsequent war. The Stamp Act Congress in 1765 brought together representatives from across the Thirteen Colonies to form a unified response to British policies. The Sons of Liberty were active in New York City to challenge British authority. After a major loss at the Battle of Long Island, the Continental Army suffered a series of additional defeats that forced a retreat from the New York City area, leaving the strategic port and harbor to the British army and navy as their North American base of operations for the rest of the war. The Battle of Saratoga was the turning point of the war in favor of the Americans, convincing France to formally ally with them. New York's constitution was adopted in 1777, and strongly influenced the United States Constitution. New York City was the national capital at various times between 1785 and 1790, where the Bill of Rights was drafted. Albany became the permanent state capital in 1797. In 1787, New York became the eleventh state to ratify the United States Constitution.
4+
5+
New York hosted significant transportation advancements in the 19th century, including the first steamboat line in 1807, the Erie Canal in 1825, and America's first regularly scheduled rail service in 1831. These advancements led to the expanded settlement of western New York and trade ties to the Midwest settlements around the Great Lakes.
6+
7+
Due to New York City's trade ties to the South, there were numerous southern sympathizers in the early days of the American Civil War and the mayor proposed secession. Far from any of the battles, New York ultimately sent the most men and money to support the Union cause. Thereafter, the state helped create the industrial age and consequently was home to some of the first labor unions.
8+
9+
During the 19th century, New York City became the main entry point for European immigrants to the United States, beginning with a wave of Irish during their Great Famine. Millions came through Castle Clinton in Battery Park before Ellis Island opened in 1892 to welcome millions more, increasingly from eastern and southern Europe. The Statue of Liberty opened in 1886 and became a symbol of hope. New York boomed during the Roaring Twenties, before the Wall Street Crash of 1929, and skyscrapers expressed the energy of the city. New York City was the site of successive tallest buildings in the world from 1913–74.
10+
11+
The buildup of defense industries for World War II turned around the state's economy from the Great Depression, as hundreds of thousands worked to defeat the Axis powers. Following the war, the state experienced significant suburbanization around all the major cities, and most central cities shrank. The Thruway system opened in 1956, signalling another era of transportation advances.
12+
13+
Following a period of near–bankruptcy in the late 1970s, New York City renewed its stature as a cultural center, attracted more immigration, and hosted the development of new music styles. The city developed from publishing to become a media capital over the second half of the 20th century, hosting most national news channels and broadcasts. Some of its newspapers became nationally and globallyrenowned. The state's manufacturing base eroded with the restructuring of industry, and the state transitioned into service industries.
14+
15+
The September 11 attacks of 2001 destroyed the World Trade Center, killing almost 3,000 people; they were the largest terrorist attacks on United States soil.

‎in/word_count.text

+15
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
The history of New York begins around 10,000 BC, when the first Native Americans arrived. By 1100 AD, New York's main native cultures, the Iroquoian and Algonquian, had developed. European discovery of New York was led by the French in 1524 and the first land claim came in 1609 by the Dutch. As part of New Netherland, the colony was important in the fur trade and eventually became an agricultural resource thanks to the patroon system. In 1626 the Dutch bought the island of Manhattan from Native Americans.[1] In 1664, England renamed the colony New York, after the Duke of York (later James II & VII.) New York City gained prominence in the 18th century as a major trading port in the Thirteen Colonies.
2+
3+
New York played a pivotal role during the American Revolution and subsequent war. The Stamp Act Congress in 1765 brought together representatives from across the Thirteen Colonies to form a unified response to British policies. The Sons of Liberty were active in New York City to challenge British authority. After a major loss at the Battle of Long Island, the Continental Army suffered a series of additional defeats that forced a retreat from the New York City area, leaving the strategic port and harbor to the British army and navy as their North American base of operations for the rest of the war. The Battle of Saratoga was the turning point of the war in favor of the Americans, convincing France to formally ally with them. New York's constitution was adopted in 1777, and strongly influenced the United States Constitution. New York City was the national capital at various times between 1785 and 1790, where the Bill of Rights was drafted. Albany became the permanent state capital in 1797. In 1787, New York became the eleventh state to ratify the United States Constitution.
4+
5+
New York hosted significant transportation advancements in the 19th century, including the first steamboat line in 1807, the Erie Canal in 1825, and America's first regularly scheduled rail service in 1831. These advancements led to the expanded settlement of western New York and trade ties to the Midwest settlements around the Great Lakes.
6+
7+
Due to New York City's trade ties to the South, there were numerous southern sympathizers in the early days of the American Civil War and the mayor proposed secession. Far from any of the battles, New York ultimately sent the most men and money to support the Union cause. Thereafter, the state helped create the industrial age and consequently was home to some of the first labor unions.
8+
9+
During the 19th century, New York City became the main entry point for European immigrants to the United States, beginning with a wave of Irish during their Great Famine. Millions came through Castle Clinton in Battery Park before Ellis Island opened in 1892 to welcome millions more, increasingly from eastern and southern Europe. The Statue of Liberty opened in 1886 and became a symbol of hope. New York boomed during the Roaring Twenties, before the Wall Street Crash of 1929, and skyscrapers expressed the energy of the city. New York City was the site of successive tallest buildings in the world from 1913–74.
10+
11+
The buildup of defense industries for World War II turned around the state's economy from the Great Depression, as hundreds of thousands worked to defeat the Axis powers. Following the war, the state experienced significant suburbanization around all the major cities, and most central cities shrank. The Thruway system opened in 1956, signalling another era of transportation advances.
12+
13+
Following a period of near–bankruptcy in the late 1970s, New York City renewed its stature as a cultural center, attracted more immigration, and hosted the development of new music styles. The city developed from publishing to become a media capital over the second half of the 20th century, hosting most national news channels and broadcasts. Some of its newspapers became nationally and globallyrenowned. The state's manufacturing base eroded with the restructuring of industry, and the state transitioned into service industries.
14+
15+
The September 11 attacks of 2001 destroyed the World Trade Center, killing almost 3,000 people; they were the largest terrorist attacks on United States soil.

‎src/main/java/com/sparkTutorial/rdd/Uppercase.java

+21
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,21 @@
1+
package com.sparkTutorial.rdd;
2+
3+
4+
import org.apache.spark.SparkConf;
5+
import org.apache.spark.api.java.JavaRDD;
6+
import org.apache.spark.api.java.JavaSparkContext;
7+
8+
public class Uppercase {
9+
10+
public static void main(String[] args) throws Exception {
11+
// Create a Java Spark Context.
12+
SparkConf conf = new SparkConf().setAppName("uppercase").setMaster("local[*]");
13+
14+
JavaSparkContext sc = new JavaSparkContext(conf);
15+
16+
JavaRDD<String> lines = sc.textFile("in/uppercase.text");
17+
JavaRDD<String> lowerCaseLines = lines.map(line -> line.toUpperCase());
18+
19+
lowerCaseLines.saveAsTextFile("out/uppercase.text");
20+
}
21+
}

‎src/main/java/com/sparkTutorial/rdd/WorldCount.java

+26
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,26 @@
1+
package com.sparkTutorial.rdd;
2+
3+
4+
import org.apache.spark.SparkConf;
5+
import org.apache.spark.api.java.JavaPairRDD;
6+
import org.apache.spark.api.java.JavaRDD;
7+
import org.apache.spark.api.java.JavaSparkContext;
8+
import scala.Tuple2;
9+
10+
import java.util.Arrays;
11+
12+
public class WorldCount {
13+
14+
public static void main(String[] args) throws Exception {
15+
// Create a Java Spark Context.
16+
SparkConf conf = new SparkConf().setAppName("wordCount").setMaster("local[3]");
17+
JavaSparkContext sc = new JavaSparkContext(conf);
18+
19+
JavaRDD<String> lines = sc.textFile("in/word_count.text");
20+
JavaRDD<String> words = lines.flatMap(line -> Arrays.asList(line.split(" ")).iterator());
21+
22+
JavaPairRDD<String, Integer> counts = words.mapToPair(w -> new Tuple2<>(w, 1))
23+
.reduceByKey((x, y) -> x + y);
24+
counts.saveAsTextFile("out/word_count.text");
25+
}
26+
}

0 commit comments

Comments
 (0)