embulk-filter-calc 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +12 -0
- data/.travis.yml +7 -0
- data/LICENSE.txt +21 -0
- data/README.md +67 -0
- data/build.gradle +104 -0
- data/config/checkstyle/checkstyle.xml +128 -0
- data/config/checkstyle/default.xml +108 -0
- data/example/config.yml +36 -0
- data/example/config2.yml +32 -0
- data/example/csv/sample_01.csv.gz +0 -0
- data/example/seed.yml +5 -0
- data/gradle/wrapper/gradle-wrapper.jar +0 -0
- data/gradle/wrapper/gradle-wrapper.properties +6 -0
- data/gradlew +160 -0
- data/gradlew.bat +90 -0
- data/lib/embulk/filter/calc.rb +3 -0
- data/src/main/antlr/org/embulk/filter/calc/Calculator.g4 +52 -0
- data/src/main/java/org/embulk/filter/calc/CalcConfigCheckVisitor.java +32 -0
- data/src/main/java/org/embulk/filter/calc/CalcConfigChecker.java +38 -0
- data/src/main/java/org/embulk/filter/calc/CalcFilterPlugin.java +140 -0
- data/src/main/java/org/embulk/filter/calc/CalcFormulaVisitor.java +130 -0
- data/src/main/java/org/embulk/filter/calc/CalcVisitorImpl.java +141 -0
- data/src/main/java/org/embulk/filter/calc/Calculator.java +30 -0
- data/src/main/java/org/embulk/filter/calc/ConfigErrorListener.java +27 -0
- data/src/test/java/org/embulk/filter/calc/TestCalcFilterPlugin.java +107 -0
- data/src/test/java/org/embulk/filter/calc/TestCalcVisitorImpl.java +448 -0
- metadata +100 -0
data/example/config.yml
ADDED
@@ -0,0 +1,36 @@
|
|
1
|
+
in:
|
2
|
+
type: file
|
3
|
+
path_prefix: example/csv/sample_
|
4
|
+
decoders:
|
5
|
+
- {type: gzip}
|
6
|
+
parser:
|
7
|
+
charset: UTF-8
|
8
|
+
newline: CRLF
|
9
|
+
type: csv
|
10
|
+
delimiter: ','
|
11
|
+
quote: '"'
|
12
|
+
escape: '"'
|
13
|
+
null_string: 'NULL'
|
14
|
+
trim_if_not_quoted: false
|
15
|
+
skip_header_lines: 1
|
16
|
+
allow_extra_columns: false
|
17
|
+
allow_optional_columns: false
|
18
|
+
columns:
|
19
|
+
- {name: id, type: long}
|
20
|
+
- {name: account, type: double}
|
21
|
+
- {name: time, type: timestamp, format: '%Y-%m-%d %H:%M:%S'}
|
22
|
+
- {name: purchase, type: timestamp, format: '%Y%m%d'}
|
23
|
+
- {name: comment, type: string}
|
24
|
+
filters:
|
25
|
+
- type: calc
|
26
|
+
columns:
|
27
|
+
- name: id
|
28
|
+
formula: "1 + id"
|
29
|
+
- name: account
|
30
|
+
formula: "0.5 + account"
|
31
|
+
# - name: hoge
|
32
|
+
# formula: "100 + id"
|
33
|
+
# output_columns:
|
34
|
+
# - { name: hoge, type: long }
|
35
|
+
|
36
|
+
out: {type: stdout}
|
data/example/config2.yml
ADDED
@@ -0,0 +1,32 @@
|
|
1
|
+
in:
|
2
|
+
type: file
|
3
|
+
path_prefix: example/csv/sample_
|
4
|
+
decoders:
|
5
|
+
- {type: gzip}
|
6
|
+
parser:
|
7
|
+
charset: UTF-8
|
8
|
+
newline: CRLF
|
9
|
+
type: csv
|
10
|
+
delimiter: ','
|
11
|
+
quote: '"'
|
12
|
+
escape: '"'
|
13
|
+
null_string: 'NULL'
|
14
|
+
trim_if_not_quoted: false
|
15
|
+
skip_header_lines: 1
|
16
|
+
allow_extra_columns: false
|
17
|
+
allow_optional_columns: false
|
18
|
+
columns:
|
19
|
+
- {name: id, type: long}
|
20
|
+
- {name: account, type: long}
|
21
|
+
- {name: time, type: timestamp, format: '%Y-%m-%d %H:%M:%S'}
|
22
|
+
- {name: purchase, type: timestamp, format: '%Y%m%d'}
|
23
|
+
- {name: comment, type: string}
|
24
|
+
filters:
|
25
|
+
- type: calc
|
26
|
+
columns:
|
27
|
+
- name: hoge
|
28
|
+
formula: "1 + 2 + 3 + account"
|
29
|
+
output_columns:
|
30
|
+
- { name: hoge, type: string }
|
31
|
+
|
32
|
+
out: {type: stdout}
|
Binary file
|
data/example/seed.yml
ADDED
Binary file
|
data/gradlew
ADDED
@@ -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 "$@"
|
data/gradlew.bat
ADDED
@@ -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
|
@@ -0,0 +1,52 @@
|
|
1
|
+
grammar Calculator;
|
2
|
+
@header {
|
3
|
+
package org.embulk.filter.calc;
|
4
|
+
}
|
5
|
+
|
6
|
+
expr: <assoc=right> expr '^' expr # Power
|
7
|
+
| expr op=('*'|'/'|'%') expr # MulDivMod
|
8
|
+
| expr op=('+'|'-') expr # AddSub
|
9
|
+
| NUM # Number
|
10
|
+
| ID # Identifier
|
11
|
+
| func # MathFunc
|
12
|
+
| '(' expr ')' # Paren
|
13
|
+
;
|
14
|
+
|
15
|
+
func: COS '(' expr ')' # FuncCos
|
16
|
+
| TAN '(' expr ')' # FuncTan
|
17
|
+
| SIN '(' expr ')' # FuncSin
|
18
|
+
// | ACOS
|
19
|
+
// | ATAN
|
20
|
+
// | ASIN
|
21
|
+
// | LOG
|
22
|
+
// | LN
|
23
|
+
// | ROUDUP
|
24
|
+
// | ROUDDOWN
|
25
|
+
;
|
26
|
+
|
27
|
+
ADD: '+';
|
28
|
+
SUB: '-';
|
29
|
+
MUL: '*';
|
30
|
+
DIV: '/';
|
31
|
+
MOD: '%';
|
32
|
+
|
33
|
+
COS: 'cos';
|
34
|
+
SIN: 'sin';
|
35
|
+
TAN: 'tan';
|
36
|
+
// ACOS: 'acos';
|
37
|
+
// ASIN: 'asin';
|
38
|
+
// ATAN: 'atan';
|
39
|
+
// LN: 'ln';
|
40
|
+
// LOG: 'log';
|
41
|
+
|
42
|
+
COMMA: ',';
|
43
|
+
|
44
|
+
ROUNDUP: 'roundup';
|
45
|
+
ROUNDDOWN: 'roundown';
|
46
|
+
|
47
|
+
NUM: '-'?[0-9]+('.' [0-9]+)?;
|
48
|
+
ID: [a-zA-Z][0-9A-Za-z_-]*;
|
49
|
+
WS: [ \t\r\n]+ -> skip;
|
50
|
+
|
51
|
+
|
52
|
+
|
@@ -0,0 +1,32 @@
|
|
1
|
+
package org.embulk.filter.calc;
|
2
|
+
|
3
|
+
import org.embulk.config.ConfigException;
|
4
|
+
import org.embulk.spi.Column;
|
5
|
+
import org.embulk.spi.Schema;
|
6
|
+
import org.embulk.spi.type.Types;
|
7
|
+
|
8
|
+
import static java.util.Locale.ENGLISH;
|
9
|
+
|
10
|
+
public class CalcConfigCheckVisitor
|
11
|
+
extends CalculatorBaseVisitor<Double>
|
12
|
+
{
|
13
|
+
private Schema outputSchema;
|
14
|
+
|
15
|
+
public CalcConfigCheckVisitor(Schema inputSchema)
|
16
|
+
{
|
17
|
+
this.outputSchema = inputSchema;
|
18
|
+
}
|
19
|
+
|
20
|
+
@Override
|
21
|
+
public Double visitIdentifier(CalculatorParser.IdentifierContext ctx)
|
22
|
+
throws ConfigException
|
23
|
+
{
|
24
|
+
String id = ctx.ID().getText();
|
25
|
+
Column column = outputSchema.lookupColumn(id); // throw ConfigException if column not found.
|
26
|
+
if (!Types.DOUBLE.equals(column.getType()) && !Types.LONG.equals(column.getType())) {
|
27
|
+
String err = String.format(ENGLISH, "\"%s\" is not long and double column", id);
|
28
|
+
throw new ConfigException(err);
|
29
|
+
}
|
30
|
+
return null;
|
31
|
+
}
|
32
|
+
}
|
@@ -0,0 +1,38 @@
|
|
1
|
+
package org.embulk.filter.calc;
|
2
|
+
|
3
|
+
import org.antlr.v4.runtime.ANTLRInputStream;
|
4
|
+
import org.antlr.v4.runtime.CommonTokenStream;
|
5
|
+
import org.antlr.v4.runtime.tree.ParseTree;
|
6
|
+
import org.embulk.spi.Schema;
|
7
|
+
|
8
|
+
public class CalcConfigChecker
|
9
|
+
{
|
10
|
+
private String name;
|
11
|
+
private String formula;
|
12
|
+
private Schema inputSchema;
|
13
|
+
|
14
|
+
public CalcConfigChecker(String name, String formula, Schema inputSchema)
|
15
|
+
{
|
16
|
+
this.formula = formula;
|
17
|
+
this.name = name;
|
18
|
+
this.inputSchema = inputSchema;
|
19
|
+
}
|
20
|
+
|
21
|
+
public Boolean validateFormula()
|
22
|
+
{
|
23
|
+
inputSchema.lookupColumn(name); // throw Exception
|
24
|
+
|
25
|
+
ANTLRInputStream input = new ANTLRInputStream(this.formula);
|
26
|
+
CalculatorLexer lexer = new CalculatorLexer(input);
|
27
|
+
CommonTokenStream tokens = new CommonTokenStream(lexer);
|
28
|
+
CalculatorParser parser = new CalculatorParser(tokens);
|
29
|
+
ConfigErrorListener errorListener = new ConfigErrorListener(name);
|
30
|
+
parser.removeErrorListeners();
|
31
|
+
parser.addErrorListener(errorListener);
|
32
|
+
ParseTree tree = parser.expr();
|
33
|
+
CalcConfigCheckVisitor eval = new CalcConfigCheckVisitor(inputSchema);
|
34
|
+
eval.visit(tree);
|
35
|
+
return true;
|
36
|
+
}
|
37
|
+
}
|
38
|
+
|