embulk-output-snowflake 0.1.1 → 0.2.0

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.
@@ -0,0 +1,6 @@
1
+ #Wed Jun 24 17:19:08 JST 2020
2
+ distributionUrl=https\://services.gradle.org/distributions/gradle-4.1-all.zip
3
+ distributionBase=GRADLE_USER_HOME
4
+ distributionPath=wrapper/dists
5
+ zipStorePath=wrapper/dists
6
+ zipStoreBase=GRADLE_USER_HOME
data/gradlew ADDED
@@ -0,0 +1,172 @@
1
+ #!/usr/bin/env sh
2
+
3
+ ##############################################################################
4
+ ##
5
+ ## Gradle start up script for UN*X
6
+ ##
7
+ ##############################################################################
8
+
9
+ # Attempt to set APP_HOME
10
+ # Resolve links: $0 may be a link
11
+ PRG="$0"
12
+ # Need this for relative symlinks.
13
+ while [ -h "$PRG" ] ; do
14
+ ls=`ls -ld "$PRG"`
15
+ link=`expr "$ls" : '.*-> \(.*\)$'`
16
+ if expr "$link" : '/.*' > /dev/null; then
17
+ PRG="$link"
18
+ else
19
+ PRG=`dirname "$PRG"`"/$link"
20
+ fi
21
+ done
22
+ SAVED="`pwd`"
23
+ cd "`dirname \"$PRG\"`/" >/dev/null
24
+ APP_HOME="`pwd -P`"
25
+ cd "$SAVED" >/dev/null
26
+
27
+ APP_NAME="Gradle"
28
+ APP_BASE_NAME=`basename "$0"`
29
+
30
+ # Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
31
+ DEFAULT_JVM_OPTS=""
32
+
33
+ # Use the maximum available, or set MAX_FD != -1 to use that value.
34
+ MAX_FD="maximum"
35
+
36
+ warn () {
37
+ echo "$*"
38
+ }
39
+
40
+ die () {
41
+ echo
42
+ echo "$*"
43
+ echo
44
+ exit 1
45
+ }
46
+
47
+ # OS specific support (must be 'true' or 'false').
48
+ cygwin=false
49
+ msys=false
50
+ darwin=false
51
+ nonstop=false
52
+ case "`uname`" in
53
+ CYGWIN* )
54
+ cygwin=true
55
+ ;;
56
+ Darwin* )
57
+ darwin=true
58
+ ;;
59
+ MINGW* )
60
+ msys=true
61
+ ;;
62
+ NONSTOP* )
63
+ nonstop=true
64
+ ;;
65
+ esac
66
+
67
+ CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
68
+
69
+ # Determine the Java command to use to start the JVM.
70
+ if [ -n "$JAVA_HOME" ] ; then
71
+ if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
72
+ # IBM's JDK on AIX uses strange locations for the executables
73
+ JAVACMD="$JAVA_HOME/jre/sh/java"
74
+ else
75
+ JAVACMD="$JAVA_HOME/bin/java"
76
+ fi
77
+ if [ ! -x "$JAVACMD" ] ; then
78
+ die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
79
+
80
+ Please set the JAVA_HOME variable in your environment to match the
81
+ location of your Java installation."
82
+ fi
83
+ else
84
+ JAVACMD="java"
85
+ which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
86
+
87
+ Please set the JAVA_HOME variable in your environment to match the
88
+ location of your Java installation."
89
+ fi
90
+
91
+ # Increase the maximum file descriptors if we can.
92
+ if [ "$cygwin" = "false" -a "$darwin" = "false" -a "$nonstop" = "false" ] ; then
93
+ MAX_FD_LIMIT=`ulimit -H -n`
94
+ if [ $? -eq 0 ] ; then
95
+ if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
96
+ MAX_FD="$MAX_FD_LIMIT"
97
+ fi
98
+ ulimit -n $MAX_FD
99
+ if [ $? -ne 0 ] ; then
100
+ warn "Could not set maximum file descriptor limit: $MAX_FD"
101
+ fi
102
+ else
103
+ warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
104
+ fi
105
+ fi
106
+
107
+ # For Darwin, add options to specify how the application appears in the dock
108
+ if $darwin; then
109
+ GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
110
+ fi
111
+
112
+ # For Cygwin, switch paths to Windows format before running java
113
+ if $cygwin ; then
114
+ APP_HOME=`cygpath --path --mixed "$APP_HOME"`
115
+ CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
116
+ JAVACMD=`cygpath --unix "$JAVACMD"`
117
+
118
+ # We build the pattern for arguments to be converted via cygpath
119
+ ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
120
+ SEP=""
121
+ for dir in $ROOTDIRSRAW ; do
122
+ ROOTDIRS="$ROOTDIRS$SEP$dir"
123
+ SEP="|"
124
+ done
125
+ OURCYGPATTERN="(^($ROOTDIRS))"
126
+ # Add a user-defined pattern to the cygpath arguments
127
+ if [ "$GRADLE_CYGPATTERN" != "" ] ; then
128
+ OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
129
+ fi
130
+ # Now convert the arguments - kludge to limit ourselves to /bin/sh
131
+ i=0
132
+ for arg in "$@" ; do
133
+ CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
134
+ CHECK2=`echo "$arg"|egrep -c "^-"` ### Determine if an option
135
+
136
+ if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then ### Added a condition
137
+ eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
138
+ else
139
+ eval `echo args$i`="\"$arg\""
140
+ fi
141
+ i=$((i+1))
142
+ done
143
+ case $i in
144
+ (0) set -- ;;
145
+ (1) set -- "$args0" ;;
146
+ (2) set -- "$args0" "$args1" ;;
147
+ (3) set -- "$args0" "$args1" "$args2" ;;
148
+ (4) set -- "$args0" "$args1" "$args2" "$args3" ;;
149
+ (5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
150
+ (6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
151
+ (7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
152
+ (8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
153
+ (9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
154
+ esac
155
+ fi
156
+
157
+ # Escape application args
158
+ save () {
159
+ for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done
160
+ echo " "
161
+ }
162
+ APP_ARGS=$(save "$@")
163
+
164
+ # Collect all arguments for the java command, following the shell quoting and substitution rules
165
+ eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS"
166
+
167
+ # by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
168
+ if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then
169
+ cd "$(dirname "$0")"
170
+ fi
171
+
172
+ exec "$JAVACMD" "$@"
@@ -0,0 +1,84 @@
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
+ set DIRNAME=%~dp0
12
+ if "%DIRNAME%" == "" set DIRNAME=.
13
+ set APP_BASE_NAME=%~n0
14
+ set APP_HOME=%DIRNAME%
15
+
16
+ @rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
17
+ set DEFAULT_JVM_OPTS=
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 Windows variants
50
+
51
+ if not "%OS%" == "Windows_NT" goto win9xME_args
52
+
53
+ :win9xME_args
54
+ @rem Slurp the command line arguments.
55
+ set CMD_LINE_ARGS=
56
+ set _SKIP=2
57
+
58
+ :win9xME_args_slurp
59
+ if "x%~1" == "x" goto execute
60
+
61
+ set CMD_LINE_ARGS=%*
62
+
63
+ :execute
64
+ @rem Setup the command line
65
+
66
+ set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
67
+
68
+ @rem Execute Gradle
69
+ "%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
70
+
71
+ :end
72
+ @rem End local scope for the variables with windows NT shell
73
+ if "%ERRORLEVEL%"=="0" goto mainEnd
74
+
75
+ :fail
76
+ rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
77
+ rem the _cmd.exe /c_ return code!
78
+ if not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
79
+ exit /b 1
80
+
81
+ :mainEnd
82
+ if "%OS%"=="Windows_NT" endlocal
83
+
84
+ :omega
@@ -1,3 +1,3 @@
1
1
  Embulk::JavaPlugin.register_output(
2
- :snowflake, "org.embulk.output.SnowflakeOutputPlugin",
2
+ "snowflake", "org.embulk.output.SnowflakeOutputPlugin",
3
3
  File.expand_path('../../../../classpath', __FILE__))
@@ -1,165 +1,137 @@
1
1
  package org.embulk.output;
2
2
 
3
- import java.sql.*;
4
- import java.util.Properties;
5
- import java.util.List;
6
3
  import java.io.IOException;
7
- import java.util.Locale;
4
+ import java.sql.SQLException;
5
+ import java.util.Properties;
8
6
 
9
7
  import com.google.common.base.Optional;
10
8
  import com.google.common.collect.ImmutableSet;
11
- import com.google.common.collect.ImmutableList;
12
-
13
-
14
- import org.embulk.config.Config;
15
- import org.embulk.config.ConfigDefault;
9
+ import org.embulk.config.*;
16
10
  import org.embulk.output.jdbc.*;
17
- import org.embulk.output.snowflake.SnowflakeOutputConnector;
11
+ import org.embulk.output.snowflake.*;
12
+ import org.embulk.spi.OutputPlugin;
18
13
  import org.embulk.spi.Schema;
19
- import org.embulk.output.snowflake.SnowflakeOutputConnection;
20
14
 
21
15
  public class SnowflakeOutputPlugin
22
16
  extends AbstractJdbcOutputPlugin
23
17
  {
24
- public interface GenericPluginTask extends PluginTask
25
- {
18
+ private StageIdentifier stageIdentifier;
19
+
20
+ public interface SnowflakePluginTask extends PluginTask {
26
21
  @Config("driver_path")
27
22
  @ConfigDefault("null")
28
23
  public Optional<String> getDriverPath();
29
24
 
30
- @Config("url")
31
- public String getUrl();
25
+ @Config("host")
26
+ public String getHost();
32
27
 
33
28
  @Config("user")
34
- @ConfigDefault("null")
35
- public Optional<String> getUser();
29
+ @ConfigDefault("\"KEN\"")
30
+ public String getUser();
36
31
 
37
32
  @Config("password")
38
- @ConfigDefault("null")
39
- public Optional<String> getPassword();
33
+ @ConfigDefault("\"\"")
34
+ public String getPassword();
35
+
36
+ @Config("database")
37
+ public String getDatabase();
38
+
39
+ @Config("warehouse")
40
+ public String getWarehouse();
40
41
 
41
42
  @Config("schema")
42
- @ConfigDefault("null")
43
- public Optional<String> getSchema();
43
+ @ConfigDefault("\"public\"")
44
+ public String getSchema();
44
45
 
45
- @Config("max_table_name_length")
46
- @ConfigDefault("30")
47
- public int getMaxTableNameLength();
46
+ @Config("delete_stage")
47
+ @ConfigDefault("false")
48
+ public boolean getDeleteStage();
48
49
  }
49
50
 
50
51
  @Override
51
52
  protected Class<? extends PluginTask> getTaskClass()
52
53
  {
53
- return GenericPluginTask.class;
54
+ return SnowflakePluginTask.class;
54
55
  }
55
56
 
56
57
  @Override
57
58
  protected Features getFeatures(PluginTask task)
58
59
  {
59
- GenericPluginTask t = (GenericPluginTask) task;
60
60
  return new Features()
61
- .setMaxTableNameLength(t.getMaxTableNameLength())
62
- .setSupportedModes(ImmutableSet.of(Mode.INSERT, Mode.INSERT_DIRECT, Mode.TRUNCATE_INSERT, Mode.REPLACE));
61
+ .setMaxTableNameLength(127)
62
+ .setSupportedModes(ImmutableSet.of(Mode.INSERT, Mode.INSERT_DIRECT, Mode.TRUNCATE_INSERT, Mode.REPLACE))
63
+ .setIgnoreMergeKeys(false);
63
64
  }
64
-
65
65
  @Override
66
- protected SnowflakeOutputConnector getConnector(PluginTask task, boolean retryableMetadataOperation)
67
- {
68
- GenericPluginTask t = (GenericPluginTask) task;
66
+ protected JdbcOutputConnector getConnector(PluginTask task, boolean retryableMetadataOperation) {
67
+ SnowflakePluginTask t = (SnowflakePluginTask) task;
69
68
 
70
- if (t.getDriverPath().isPresent()) {
71
- addDriverJarToClasspath(t.getDriverPath().get());
72
- }
69
+ loadDriver("net.snowflake.client.jdbc.SnowflakeDriver", t.getDriverPath());
70
+
71
+ String url = String.format("jdbc:snowflake://%s", t.getHost());
73
72
 
74
73
  Properties props = new Properties();
75
74
 
75
+ props.setProperty("user", t.getUser());
76
+ props.setProperty("password", t.getPassword());
77
+ props.setProperty("warehouse", t.getWarehouse());
78
+ props.setProperty("db", t.getDatabase());
79
+ props.setProperty("schema", t.getSchema());
80
+
76
81
  props.putAll(t.getOptions());
77
82
 
78
- if (t.getUser().isPresent()) {
79
- props.setProperty("user", t.getUser().get());
80
- }
81
- if (t.getPassword().isPresent()) {
82
- props.setProperty("password", t.getPassword().get());
83
- }
84
- logConnectionProperties(t.getUrl(), props);
83
+ logConnectionProperties(url, props);
85
84
 
86
- return new SnowflakeOutputConnector(t.getUrl(), props,
87
- t.getSchema().orNull(), t.getTransactionIsolation());
85
+ return new SnowflakeOutputConnector(url, props, t.getTransactionIsolation());
88
86
  }
89
87
 
90
88
  @Override
91
- protected BatchInsert newBatchInsert(PluginTask task, Optional<MergeConfig> mergeConfig) throws IOException, SQLException
89
+ public ConfigDiff resume(TaskSource taskSource,
90
+ Schema schema, int taskCount,
91
+ OutputPlugin.Control control)
92
92
  {
93
- return new StandardBatchInsert(getConnector(task, true), mergeConfig);
93
+ throw new UnsupportedOperationException("snowflake output plugin does not support resuming");
94
94
  }
95
95
 
96
96
  @Override
97
97
  protected void doBegin(JdbcOutputConnection con,
98
98
  PluginTask task, final Schema schema, int taskCount) throws SQLException
99
99
  {
100
+ super.doBegin(con,task,schema,taskCount);
101
+ }
102
+
100
103
 
104
+ @Override
105
+ protected void doCommit(JdbcOutputConnection con, PluginTask task, int taskCount)
106
+ throws SQLException {
107
+ super.doCommit(con, task, taskCount);
101
108
  SnowflakeOutputConnection snowflakeCon = (SnowflakeOutputConnection)con;
102
109
 
103
- super.doBegin(snowflakeCon, task, schema, taskCount);
110
+ SnowflakePluginTask t = (SnowflakePluginTask) task;
111
+ if (this.stageIdentifier == null) {
112
+ this.stageIdentifier = StageIdentifierHolder.getStageIdentifier(t);
113
+ }
114
+
115
+ if (t.getDeleteStage()){
116
+ snowflakeCon.runDropStage(this.stageIdentifier);
117
+ }
104
118
  }
105
119
 
106
120
  @Override
107
- public Optional<JdbcSchema> newJdbcSchemaFromTableIfExists(JdbcOutputConnection connection,
108
- TableIdentifier table) throws SQLException
121
+ protected BatchInsert newBatchInsert(PluginTask task, Optional<MergeConfig> mergeConfig) throws IOException, SQLException
109
122
  {
110
- if (!connection.tableExists(table)) {
111
- // DatabaseMetaData.getPrimaryKeys fails if table does not exist
112
- return Optional.absent();
123
+ if (mergeConfig.isPresent()) {
124
+ throw new UnsupportedOperationException("Snowflake output plugin doesn't support 'merge_direct' mode.");
113
125
  }
114
126
 
115
- DatabaseMetaData dbm = connection.getMetaData();
116
- String escape = dbm.getSearchStringEscape();
117
- String catalog = dbm.getConnection().getCatalog();
118
-
119
- ResultSet rs = dbm.getPrimaryKeys(catalog, table.getSchemaName(), table.getTableName());
120
- ImmutableSet.Builder<String> primaryKeysBuilder = ImmutableSet.builder();
121
- try {
122
- while(rs.next()) {
123
- primaryKeysBuilder.add(rs.getString("COLUMN_NAME"));
124
- }
125
- } finally {
126
- rs.close();
127
- }
128
- ImmutableSet<String> primaryKeys = primaryKeysBuilder.build();
129
-
130
- ImmutableList.Builder<JdbcColumn> builder = ImmutableList.builder();
131
- rs = dbm.getColumns(
132
- catalog,
133
- JdbcUtils.escapeSearchString(table.getSchemaName(), escape),
134
- JdbcUtils.escapeSearchString(table.getTableName(), escape),
135
- null);
136
- try {
137
- while (rs.next()) {
138
- String columnName = rs.getString("COLUMN_NAME");
139
- String simpleTypeName = rs.getString("TYPE_NAME").toUpperCase(Locale.ENGLISH);
140
- boolean isUniqueKey = primaryKeys.contains(columnName);
141
- int sqlType = rs.getInt("DATA_TYPE");
142
- int colSize = rs.getInt("COLUMN_SIZE");
143
- int decDigit = rs.getInt("DECIMAL_DIGITS");
144
- if (rs.wasNull()) {
145
- decDigit = -1;
146
- }
147
- int charOctetLength = rs.getInt("CHAR_OCTET_LENGTH");
148
- boolean isNotNull = "NO".equals(rs.getString("IS_NULLABLE"));
149
- //rs.getString("COLUMN_DEF") // or null // TODO
150
- builder.add(JdbcColumn.newGenericTypeColumn(
151
- columnName, sqlType, simpleTypeName, colSize, decDigit, charOctetLength, isNotNull, isUniqueKey));
152
- // We can't get declared column name using JDBC API.
153
- // Subclasses need to overwrite it.
154
- }
155
- } finally {
156
- rs.close();
157
- }
158
- List<JdbcColumn> columns = builder.build();
159
- if (columns.isEmpty()) {
160
- return Optional.absent();
161
- } else {
162
- return Optional.of(new JdbcSchema(columns));
127
+ SnowflakePluginTask t = (SnowflakePluginTask) task;
128
+ // TODO: put some where executes once
129
+ if (this.stageIdentifier == null){
130
+ SnowflakeOutputConnection snowflakeCon = (SnowflakeOutputConnection) getConnector(task, true).connect(true);
131
+ this.stageIdentifier = StageIdentifierHolder.getStageIdentifier(t);
132
+ snowflakeCon.runCreateStage(this.stageIdentifier);
163
133
  }
134
+
135
+ return new SnowflakeCopyBatchInsert(getConnector(task, true), this.stageIdentifier,false);
164
136
  }
165
137
  }