embulk-parser-xml2 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +13 -0
- data/LICENSE.txt +23 -0
- data/README.md +67 -0
- data/build.gradle +97 -0
- data/config/checkstyle/checkstyle.xml +128 -0
- data/config/checkstyle/default.xml +108 -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/guess/xml2.rb +61 -0
- data/lib/embulk/parser/xml2.rb +3 -0
- data/src/main/java/org/embulk/parser/xml2/Xml2ParserPlugin.java +256 -0
- data/src/test/java/org/embulk/parser/xml2/TestXml2ParserPlugin.java +240 -0
- data/src/test/resources/sample_01.xml +80 -0
- metadata +88 -0
|
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 +1,61 @@
|
|
|
1
|
+
module Embulk
|
|
2
|
+
module Guess
|
|
3
|
+
|
|
4
|
+
# TODO implement guess plugin to make this command work:
|
|
5
|
+
# $ embulk guess -g "xml2" partial-config.yml
|
|
6
|
+
#
|
|
7
|
+
# Depending on the file format the plugin uses, you can use choose
|
|
8
|
+
# one of binary guess (GuessPlugin), text guess (TextGuessPlugin),
|
|
9
|
+
# or line guess (LineGuessPlugin).
|
|
10
|
+
|
|
11
|
+
#class Xml2 < GuessPlugin
|
|
12
|
+
# Plugin.register_guess("xml2", self)
|
|
13
|
+
#
|
|
14
|
+
# def guess(config, sample_buffer)
|
|
15
|
+
# if sample_buffer[0,2] == GZIP_HEADER
|
|
16
|
+
# guessed = {}
|
|
17
|
+
# guessed["type"] = "xml2"
|
|
18
|
+
# guessed["property1"] = "guessed-value"
|
|
19
|
+
# return {"parser" => guessed}
|
|
20
|
+
# else
|
|
21
|
+
# return {}
|
|
22
|
+
# end
|
|
23
|
+
# end
|
|
24
|
+
#end
|
|
25
|
+
|
|
26
|
+
#class Xml2 < TextGuessPlugin
|
|
27
|
+
# Plugin.register_guess("xml2", self)
|
|
28
|
+
#
|
|
29
|
+
# def guess_text(config, sample_text)
|
|
30
|
+
# js = JSON.parse(sample_text) rescue nil
|
|
31
|
+
# if js && js["mykeyword"] == "keyword"
|
|
32
|
+
# guessed = {}
|
|
33
|
+
# guessed["type"] = "xml2"
|
|
34
|
+
# guessed["property1"] = "guessed-value"
|
|
35
|
+
# return {"parser" => guessed}
|
|
36
|
+
# else
|
|
37
|
+
# return {}
|
|
38
|
+
# end
|
|
39
|
+
# end
|
|
40
|
+
#end
|
|
41
|
+
|
|
42
|
+
#class Xml2 < LineGuessPlugin
|
|
43
|
+
# Plugin.register_guess("xml2", self)
|
|
44
|
+
#
|
|
45
|
+
# def guess_lines(config, sample_lines)
|
|
46
|
+
# all_line_matched = sample_lines.all? do |line|
|
|
47
|
+
# line =~ /mypattern/
|
|
48
|
+
# end
|
|
49
|
+
# if all_line_matched
|
|
50
|
+
# guessed = {}
|
|
51
|
+
# guessed["type"] = "xml2"
|
|
52
|
+
# guessed["property1"] = "guessed-value"
|
|
53
|
+
# return {"parser" => guessed}
|
|
54
|
+
# else
|
|
55
|
+
# return {}
|
|
56
|
+
# end
|
|
57
|
+
# end
|
|
58
|
+
#end
|
|
59
|
+
|
|
60
|
+
end
|
|
61
|
+
end
|
|
@@ -0,0 +1,256 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* The MIT License (MIT)
|
|
3
|
+
*
|
|
4
|
+
* Copyright (C) 2016 Yahoo Japan Corporation. All Rights Reserved.
|
|
5
|
+
*
|
|
6
|
+
* Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
7
|
+
* of this software and associated documentation files (the "Software"), to deal
|
|
8
|
+
* in the Software without restriction, including without limitation the rights
|
|
9
|
+
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
10
|
+
* copies of the Software, and to permit persons to whom the Software is
|
|
11
|
+
* furnished to do so, subject to the following conditions:
|
|
12
|
+
*
|
|
13
|
+
* The above copyright notice and this permission notice shall be included in
|
|
14
|
+
* all copies or substantial portions of the Software.
|
|
15
|
+
*
|
|
16
|
+
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
17
|
+
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
18
|
+
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
19
|
+
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
20
|
+
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
21
|
+
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
|
22
|
+
* THE SOFTWARE.
|
|
23
|
+
*/
|
|
24
|
+
|
|
25
|
+
package org.embulk.parser.xml2;
|
|
26
|
+
|
|
27
|
+
import com.google.common.base.Throwables;
|
|
28
|
+
|
|
29
|
+
import java.io.IOException;
|
|
30
|
+
import java.util.Stack;
|
|
31
|
+
|
|
32
|
+
import javax.xml.parsers.ParserConfigurationException;
|
|
33
|
+
import javax.xml.parsers.SAXParser;
|
|
34
|
+
import javax.xml.parsers.SAXParserFactory;
|
|
35
|
+
|
|
36
|
+
import org.embulk.config.Config;
|
|
37
|
+
import org.embulk.config.ConfigSource;
|
|
38
|
+
import org.embulk.config.Task;
|
|
39
|
+
import org.embulk.config.TaskSource;
|
|
40
|
+
import org.embulk.spi.ParserPlugin;
|
|
41
|
+
import org.embulk.spi.Column;
|
|
42
|
+
import org.embulk.spi.ColumnVisitor;
|
|
43
|
+
import org.embulk.spi.Exec;
|
|
44
|
+
import org.embulk.spi.FileInput;
|
|
45
|
+
import org.embulk.spi.PageBuilder;
|
|
46
|
+
import org.embulk.spi.PageOutput;
|
|
47
|
+
import org.embulk.spi.Schema;
|
|
48
|
+
import org.embulk.spi.SchemaConfig;
|
|
49
|
+
import org.embulk.spi.time.Timestamp;
|
|
50
|
+
import org.embulk.spi.time.TimestampParser;
|
|
51
|
+
import org.embulk.spi.util.FileInputInputStream;
|
|
52
|
+
import org.embulk.spi.util.Timestamps;
|
|
53
|
+
import org.xml.sax.Attributes;
|
|
54
|
+
import org.xml.sax.SAXException;
|
|
55
|
+
import org.xml.sax.helpers.DefaultHandler;
|
|
56
|
+
import org.slf4j.Logger;
|
|
57
|
+
|
|
58
|
+
public class Xml2ParserPlugin
|
|
59
|
+
implements ParserPlugin
|
|
60
|
+
{
|
|
61
|
+
public interface PluginTask
|
|
62
|
+
extends Task, TimestampParser.Task
|
|
63
|
+
{
|
|
64
|
+
@Config("root")
|
|
65
|
+
public String getRoot();
|
|
66
|
+
|
|
67
|
+
@Config("schema")
|
|
68
|
+
public SchemaConfig getSchema();
|
|
69
|
+
}
|
|
70
|
+
|
|
71
|
+
@Override
|
|
72
|
+
public void transaction(ConfigSource config, ParserPlugin.Control control)
|
|
73
|
+
{
|
|
74
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
|
75
|
+
|
|
76
|
+
Schema schema = task.getSchema().toSchema();
|
|
77
|
+
|
|
78
|
+
control.run(task.dump(), schema);
|
|
79
|
+
}
|
|
80
|
+
|
|
81
|
+
@Override
|
|
82
|
+
public void run(final TaskSource taskSource, final Schema schema,
|
|
83
|
+
FileInput input, PageOutput output)
|
|
84
|
+
{
|
|
85
|
+
PluginTask task = taskSource.loadTask(PluginTask.class);
|
|
86
|
+
final TimestampParser[] timestampParsers = Timestamps.newTimestampColumnParsers(task, task.getSchema());
|
|
87
|
+
|
|
88
|
+
final String rootElementName = task.getRoot();
|
|
89
|
+
|
|
90
|
+
SAXParser parser = createXMLParser();
|
|
91
|
+
try (FileInputInputStream is = new FileInputInputStream(input)) {
|
|
92
|
+
final PageBuilder pageBuilder = new PageBuilder(Exec.getBufferAllocator(), schema, output);
|
|
93
|
+
while(is.nextFile()) {
|
|
94
|
+
parser.parse(is, new DefaultHandler() {
|
|
95
|
+
|
|
96
|
+
private Stack<String> currentXPath;
|
|
97
|
+
private boolean isElementMatch = false;
|
|
98
|
+
private StringBuffer valueBuf = null;
|
|
99
|
+
private String currentSubElementName = null;
|
|
100
|
+
private int extractedTotalPageNum = 0;
|
|
101
|
+
private Logger logger = Exec.getLogger(getClass());;
|
|
102
|
+
|
|
103
|
+
@Override
|
|
104
|
+
public void startDocument() throws SAXException {
|
|
105
|
+
currentXPath = new Stack<String>();
|
|
106
|
+
logger.debug("start parsing document.");
|
|
107
|
+
}
|
|
108
|
+
|
|
109
|
+
@Override
|
|
110
|
+
public void startElement(String uri, String localName, String qName, Attributes attributes)
|
|
111
|
+
throws SAXException {
|
|
112
|
+
currentXPath.push(qName);
|
|
113
|
+
|
|
114
|
+
String path = toXPath(currentXPath);
|
|
115
|
+
// if this element is not under the root element, skip process.
|
|
116
|
+
if (!isChildOfRootElement(rootElementName, path)) {
|
|
117
|
+
return;
|
|
118
|
+
}
|
|
119
|
+
|
|
120
|
+
String subElementName = getSubElementName(rootElementName, path);
|
|
121
|
+
if (subElementName == null) {
|
|
122
|
+
return;
|
|
123
|
+
}
|
|
124
|
+
currentSubElementName = subElementName;
|
|
125
|
+
|
|
126
|
+
if(getColumn(schema, subElementName) != null){
|
|
127
|
+
isElementMatch = true;
|
|
128
|
+
valueBuf = new StringBuffer();
|
|
129
|
+
}
|
|
130
|
+
}
|
|
131
|
+
|
|
132
|
+
private Column getColumn(Schema schema, String subElementName) {
|
|
133
|
+
for (Column c : schema.getColumns()){
|
|
134
|
+
if (c.getName().equals(subElementName)) return c;
|
|
135
|
+
}
|
|
136
|
+
return null;
|
|
137
|
+
}
|
|
138
|
+
|
|
139
|
+
private String getSubElementName(String rootElementName, String path) {
|
|
140
|
+
if (rootElementName.equals(path) || !path.startsWith(rootElementName)) {
|
|
141
|
+
return null;
|
|
142
|
+
} else {
|
|
143
|
+
return path.substring(rootElementName.length() + 1);
|
|
144
|
+
}
|
|
145
|
+
}
|
|
146
|
+
|
|
147
|
+
private boolean isChildOfRootElement(String rootElementName, String xPath) {
|
|
148
|
+
return xPath.startsWith(rootElementName);
|
|
149
|
+
}
|
|
150
|
+
|
|
151
|
+
private String toXPath(Stack<String> stack) {
|
|
152
|
+
StringBuffer buf = new StringBuffer();
|
|
153
|
+
for(String p : stack) {
|
|
154
|
+
if (buf.length() > 0) {
|
|
155
|
+
buf.append("/");
|
|
156
|
+
}
|
|
157
|
+
buf.append(p);
|
|
158
|
+
}
|
|
159
|
+
return buf.toString();
|
|
160
|
+
}
|
|
161
|
+
|
|
162
|
+
@Override
|
|
163
|
+
public void endElement(String uri, String localName, String qName) throws SAXException {
|
|
164
|
+
|
|
165
|
+
String path = toXPath(currentXPath);
|
|
166
|
+
if (path.equals(rootElementName)) {
|
|
167
|
+
pageBuilder.addRecord();
|
|
168
|
+
extractedTotalPageNum++;
|
|
169
|
+
}
|
|
170
|
+
|
|
171
|
+
// if isElementMatch is true, set data to Page.
|
|
172
|
+
if (isElementMatch) {
|
|
173
|
+
final String strValue = valueBuf.toString();
|
|
174
|
+
|
|
175
|
+
schema.visitColumns(new ColumnVisitor() {
|
|
176
|
+
|
|
177
|
+
@Override
|
|
178
|
+
public void timestampColumn(Column column) {
|
|
179
|
+
if (!column.getName().equals(currentSubElementName)) return;
|
|
180
|
+
TimestampParser tsparser = timestampParsers[column.getIndex()];
|
|
181
|
+
Timestamp time = tsparser.parse(strValue);
|
|
182
|
+
pageBuilder.setTimestamp(column, time);
|
|
183
|
+
}
|
|
184
|
+
|
|
185
|
+
@Override
|
|
186
|
+
public void stringColumn(Column column) {
|
|
187
|
+
if (!column.getName().equals(currentSubElementName)) return;
|
|
188
|
+
pageBuilder.setString(column, strValue);
|
|
189
|
+
}
|
|
190
|
+
|
|
191
|
+
@Override
|
|
192
|
+
public void longColumn(Column column) {
|
|
193
|
+
if (!column.getName().equals(currentSubElementName)) return;
|
|
194
|
+
pageBuilder.setLong(column, Long.parseLong(strValue));
|
|
195
|
+
}
|
|
196
|
+
|
|
197
|
+
@Override
|
|
198
|
+
public void doubleColumn(Column column) {
|
|
199
|
+
if (!column.getName().equals(currentSubElementName)) return;
|
|
200
|
+
pageBuilder.setDouble(column, Double.parseDouble(strValue));
|
|
201
|
+
}
|
|
202
|
+
|
|
203
|
+
@Override
|
|
204
|
+
public void booleanColumn(Column column) {
|
|
205
|
+
if (!column.getName().equals(currentSubElementName)) return;
|
|
206
|
+
pageBuilder.setBoolean(column, Boolean.parseBoolean(strValue));
|
|
207
|
+
}
|
|
208
|
+
|
|
209
|
+
@Override
|
|
210
|
+
public void jsonColumn(Column column) {
|
|
211
|
+
if (!column.getName().equals(currentSubElementName)) return;
|
|
212
|
+
// treat json as string.
|
|
213
|
+
pageBuilder.setString(column, strValue);
|
|
214
|
+
}
|
|
215
|
+
});
|
|
216
|
+
}
|
|
217
|
+
|
|
218
|
+
currentXPath.pop();
|
|
219
|
+
isElementMatch = false;
|
|
220
|
+
valueBuf = null;
|
|
221
|
+
currentSubElementName = null;
|
|
222
|
+
}
|
|
223
|
+
|
|
224
|
+
@Override
|
|
225
|
+
public void characters(char[] ch, int offset, int length) {
|
|
226
|
+
if (!isElementMatch) {
|
|
227
|
+
return;
|
|
228
|
+
}
|
|
229
|
+
valueBuf.append(ch,offset,length);
|
|
230
|
+
}
|
|
231
|
+
|
|
232
|
+
@Override
|
|
233
|
+
public void endDocument() {
|
|
234
|
+
logger.debug("end parsing document. total extracted page count is : " + extractedTotalPageNum);
|
|
235
|
+
}
|
|
236
|
+
});
|
|
237
|
+
pageBuilder.flush();
|
|
238
|
+
}
|
|
239
|
+
pageBuilder.finish();
|
|
240
|
+
pageBuilder.close();
|
|
241
|
+
} catch (SAXException | IOException e) {
|
|
242
|
+
Throwables.propagate(e); // TODO error handling
|
|
243
|
+
}
|
|
244
|
+
}
|
|
245
|
+
|
|
246
|
+
private SAXParser createXMLParser() {
|
|
247
|
+
SAXParser parser;
|
|
248
|
+
try {
|
|
249
|
+
parser = SAXParserFactory.newInstance().newSAXParser();
|
|
250
|
+
return parser;
|
|
251
|
+
} catch (ParserConfigurationException | SAXException e) {
|
|
252
|
+
Throwables.propagate(e); // TODO error handling
|
|
253
|
+
}
|
|
254
|
+
return null;
|
|
255
|
+
}
|
|
256
|
+
}
|