embulk 0.7.0-java
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +15 -0
- data/.ruby-version +1 -0
- data/.travis.yml +18 -0
- data/COPYING +14 -0
- data/Gemfile +2 -0
- data/Gemfile.lock +31 -0
- data/README.md +206 -0
- data/Rakefile +26 -0
- data/appveyor.yml +20 -0
- data/bin/embulk +106 -0
- data/build.gradle +338 -0
- data/embulk-cli/build.gradle +6 -0
- data/embulk-cli/src/main/java/org/embulk/cli/Main.java +22 -0
- data/embulk-cli/src/main/sh/selfrun.sh +158 -0
- data/embulk-cli/src/test/java/org/embulk/cli/DummyMain.java +23 -0
- data/embulk-cli/src/test/java/org/embulk/cli/SelfrunTest.java +281 -0
- data/embulk-core/build.gradle +59 -0
- data/embulk-core/src/main/java/org/embulk/EmbulkEmbed.java +315 -0
- data/embulk-core/src/main/java/org/embulk/EmbulkService.java +76 -0
- data/embulk-core/src/main/java/org/embulk/command/PreviewPrinter.java +84 -0
- data/embulk-core/src/main/java/org/embulk/command/TablePreviewPrinter.java +107 -0
- data/embulk-core/src/main/java/org/embulk/command/VerticalPreviewPrinter.java +47 -0
- data/embulk-core/src/main/java/org/embulk/config/CommitReport.java +33 -0
- data/embulk-core/src/main/java/org/embulk/config/Config.java +15 -0
- data/embulk-core/src/main/java/org/embulk/config/ConfigDefault.java +15 -0
- data/embulk-core/src/main/java/org/embulk/config/ConfigDiff.java +29 -0
- data/embulk-core/src/main/java/org/embulk/config/ConfigException.java +20 -0
- data/embulk-core/src/main/java/org/embulk/config/ConfigInject.java +14 -0
- data/embulk-core/src/main/java/org/embulk/config/ConfigLoader.java +141 -0
- data/embulk-core/src/main/java/org/embulk/config/ConfigSource.java +31 -0
- data/embulk-core/src/main/java/org/embulk/config/DataSource.java +39 -0
- data/embulk-core/src/main/java/org/embulk/config/DataSourceImpl.java +231 -0
- data/embulk-core/src/main/java/org/embulk/config/DataSourceSerDe.java +84 -0
- data/embulk-core/src/main/java/org/embulk/config/GenericTypeReference.java +20 -0
- data/embulk-core/src/main/java/org/embulk/config/ModelManager.java +123 -0
- data/embulk-core/src/main/java/org/embulk/config/Task.java +10 -0
- data/embulk-core/src/main/java/org/embulk/config/TaskInvocationHandler.java +180 -0
- data/embulk-core/src/main/java/org/embulk/config/TaskReport.java +29 -0
- data/embulk-core/src/main/java/org/embulk/config/TaskSerDe.java +345 -0
- data/embulk-core/src/main/java/org/embulk/config/TaskSource.java +31 -0
- data/embulk-core/src/main/java/org/embulk/config/TaskValidationException.java +38 -0
- data/embulk-core/src/main/java/org/embulk/config/TaskValidator.java +24 -0
- data/embulk-core/src/main/java/org/embulk/exec/BulkLoader.java +652 -0
- data/embulk-core/src/main/java/org/embulk/exec/ExecModule.java +52 -0
- data/embulk-core/src/main/java/org/embulk/exec/ExecutionInterruptedException.java +10 -0
- data/embulk-core/src/main/java/org/embulk/exec/ExecutionResult.java +26 -0
- data/embulk-core/src/main/java/org/embulk/exec/ExtensionServiceLoaderModule.java +43 -0
- data/embulk-core/src/main/java/org/embulk/exec/ForGuess.java +16 -0
- data/embulk-core/src/main/java/org/embulk/exec/ForSystemConfig.java +16 -0
- data/embulk-core/src/main/java/org/embulk/exec/GuessExecutor.java +373 -0
- data/embulk-core/src/main/java/org/embulk/exec/LocalExecutorPlugin.java +129 -0
- data/embulk-core/src/main/java/org/embulk/exec/LocalThreadExecutor.java +34 -0
- data/embulk-core/src/main/java/org/embulk/exec/LoggerProvider.java +60 -0
- data/embulk-core/src/main/java/org/embulk/exec/NoSampleException.java +10 -0
- data/embulk-core/src/main/java/org/embulk/exec/PartialExecutionException.java +18 -0
- data/embulk-core/src/main/java/org/embulk/exec/PooledBufferAllocator.java +77 -0
- data/embulk-core/src/main/java/org/embulk/exec/PreviewExecutor.java +183 -0
- data/embulk-core/src/main/java/org/embulk/exec/PreviewResult.java +27 -0
- data/embulk-core/src/main/java/org/embulk/exec/PreviewedNoticeError.java +17 -0
- data/embulk-core/src/main/java/org/embulk/exec/ResumeState.java +100 -0
- data/embulk-core/src/main/java/org/embulk/exec/SamplingParserPlugin.java +136 -0
- data/embulk-core/src/main/java/org/embulk/exec/SetCurrentThreadName.java +19 -0
- data/embulk-core/src/main/java/org/embulk/exec/SystemConfigModule.java +24 -0
- data/embulk-core/src/main/java/org/embulk/exec/TempFileAllocator.java +35 -0
- data/embulk-core/src/main/java/org/embulk/guice/Bootstrap.java +157 -0
- data/embulk-core/src/main/java/org/embulk/guice/CloseableInjector.java +22 -0
- data/embulk-core/src/main/java/org/embulk/guice/InjectorProxy.java +145 -0
- data/embulk-core/src/main/java/org/embulk/guice/LifeCycleInjector.java +26 -0
- data/embulk-core/src/main/java/org/embulk/guice/LifeCycleInjectorProxy.java +61 -0
- data/embulk-core/src/main/java/org/embulk/guice/LifeCycleManager.java +187 -0
- data/embulk-core/src/main/java/org/embulk/guice/LifeCycleMethods.java +89 -0
- data/embulk-core/src/main/java/org/embulk/guice/LifeCycleMethodsMap.java +38 -0
- data/embulk-core/src/main/java/org/embulk/guice/LifeCycleModule.java +97 -0
- data/embulk-core/src/main/java/org/embulk/jruby/JRubyPluginSource.java +72 -0
- data/embulk-core/src/main/java/org/embulk/jruby/JRubyScriptingModule.java +119 -0
- data/embulk-core/src/main/java/org/embulk/plugin/BuiltinPluginSourceModule.java +17 -0
- data/embulk-core/src/main/java/org/embulk/plugin/InjectedPluginSource.java +96 -0
- data/embulk-core/src/main/java/org/embulk/plugin/PluginClassLoader.java +168 -0
- data/embulk-core/src/main/java/org/embulk/plugin/PluginClassLoaderFactory.java +9 -0
- data/embulk-core/src/main/java/org/embulk/plugin/PluginClassLoaderModule.java +71 -0
- data/embulk-core/src/main/java/org/embulk/plugin/PluginManager.java +78 -0
- data/embulk-core/src/main/java/org/embulk/plugin/PluginSource.java +6 -0
- data/embulk-core/src/main/java/org/embulk/plugin/PluginSourceNotMatchException.java +19 -0
- data/embulk-core/src/main/java/org/embulk/plugin/PluginType.java +47 -0
- data/embulk-core/src/main/java/org/embulk/plugin/compat/InputPluginWrapper.java +102 -0
- data/embulk-core/src/main/java/org/embulk/plugin/compat/PluginWrappers.java +30 -0
- data/embulk-core/src/main/java/org/embulk/plugin/compat/TransactionalFileInputWrapper.java +96 -0
- data/embulk-core/src/main/java/org/embulk/plugin/compat/TransactionalFileOutputWrapper.java +102 -0
- data/embulk-core/src/main/java/org/embulk/plugin/compat/TransactionalPageOutputWrapper.java +95 -0
- data/embulk-core/src/main/java/org/embulk/spi/Buffer.java +148 -0
- data/embulk-core/src/main/java/org/embulk/spi/BufferAllocator.java +8 -0
- data/embulk-core/src/main/java/org/embulk/spi/Column.java +92 -0
- data/embulk-core/src/main/java/org/embulk/spi/ColumnConfig.java +112 -0
- data/embulk-core/src/main/java/org/embulk/spi/ColumnVisitor.java +14 -0
- data/embulk-core/src/main/java/org/embulk/spi/DecoderPlugin.java +16 -0
- data/embulk-core/src/main/java/org/embulk/spi/EncoderPlugin.java +16 -0
- data/embulk-core/src/main/java/org/embulk/spi/Exec.java +113 -0
- data/embulk-core/src/main/java/org/embulk/spi/ExecAction.java +6 -0
- data/embulk-core/src/main/java/org/embulk/spi/ExecSession.java +217 -0
- data/embulk-core/src/main/java/org/embulk/spi/ExecutorPlugin.java +19 -0
- data/embulk-core/src/main/java/org/embulk/spi/Extension.java +44 -0
- data/embulk-core/src/main/java/org/embulk/spi/FileInput.java +11 -0
- data/embulk-core/src/main/java/org/embulk/spi/FileInputPlugin.java +30 -0
- data/embulk-core/src/main/java/org/embulk/spi/FileInputRunner.java +162 -0
- data/embulk-core/src/main/java/org/embulk/spi/FileOutput.java +13 -0
- data/embulk-core/src/main/java/org/embulk/spi/FileOutputPlugin.java +28 -0
- data/embulk-core/src/main/java/org/embulk/spi/FileOutputRunner.java +202 -0
- data/embulk-core/src/main/java/org/embulk/spi/FilterPlugin.java +18 -0
- data/embulk-core/src/main/java/org/embulk/spi/FormatterPlugin.java +18 -0
- data/embulk-core/src/main/java/org/embulk/spi/GuessPlugin.java +9 -0
- data/embulk-core/src/main/java/org/embulk/spi/InputPlugin.java +33 -0
- data/embulk-core/src/main/java/org/embulk/spi/OutputPlugin.java +29 -0
- data/embulk-core/src/main/java/org/embulk/spi/Page.java +51 -0
- data/embulk-core/src/main/java/org/embulk/spi/PageBuilder.java +338 -0
- data/embulk-core/src/main/java/org/embulk/spi/PageFormat.java +47 -0
- data/embulk-core/src/main/java/org/embulk/spi/PageOutput.java +11 -0
- data/embulk-core/src/main/java/org/embulk/spi/PageReader.java +226 -0
- data/embulk-core/src/main/java/org/embulk/spi/ParserPlugin.java +17 -0
- data/embulk-core/src/main/java/org/embulk/spi/ProcessState.java +10 -0
- data/embulk-core/src/main/java/org/embulk/spi/ProcessTask.java +117 -0
- data/embulk-core/src/main/java/org/embulk/spi/Schema.java +134 -0
- data/embulk-core/src/main/java/org/embulk/spi/SchemaConfig.java +93 -0
- data/embulk-core/src/main/java/org/embulk/spi/SchemaConfigException.java +22 -0
- data/embulk-core/src/main/java/org/embulk/spi/TaskState.java +81 -0
- data/embulk-core/src/main/java/org/embulk/spi/TempFileException.java +19 -0
- data/embulk-core/src/main/java/org/embulk/spi/TempFileSpace.java +87 -0
- data/embulk-core/src/main/java/org/embulk/spi/Transactional.java +10 -0
- data/embulk-core/src/main/java/org/embulk/spi/TransactionalFileInput.java +17 -0
- data/embulk-core/src/main/java/org/embulk/spi/TransactionalFileOutput.java +19 -0
- data/embulk-core/src/main/java/org/embulk/spi/TransactionalPageOutput.java +17 -0
- data/embulk-core/src/main/java/org/embulk/spi/time/DateTimeZoneSerDe.java +55 -0
- data/embulk-core/src/main/java/org/embulk/spi/time/JRubyTimeParserHelper.java +8 -0
- data/embulk-core/src/main/java/org/embulk/spi/time/JRubyTimeParserHelperFactory.java +6 -0
- data/embulk-core/src/main/java/org/embulk/spi/time/Timestamp.java +159 -0
- data/embulk-core/src/main/java/org/embulk/spi/time/TimestampFormat.java +100 -0
- data/embulk-core/src/main/java/org/embulk/spi/time/TimestampFormatter.java +97 -0
- data/embulk-core/src/main/java/org/embulk/spi/time/TimestampParseException.java +10 -0
- data/embulk-core/src/main/java/org/embulk/spi/time/TimestampParser.java +104 -0
- data/embulk-core/src/main/java/org/embulk/spi/time/TimestampSerDe.java +49 -0
- data/embulk-core/src/main/java/org/embulk/spi/type/AbstractType.java +58 -0
- data/embulk-core/src/main/java/org/embulk/spi/type/BooleanType.java +12 -0
- data/embulk-core/src/main/java/org/embulk/spi/type/DoubleType.java +12 -0
- data/embulk-core/src/main/java/org/embulk/spi/type/LongType.java +12 -0
- data/embulk-core/src/main/java/org/embulk/spi/type/StringType.java +12 -0
- data/embulk-core/src/main/java/org/embulk/spi/type/TimestampType.java +41 -0
- data/embulk-core/src/main/java/org/embulk/spi/type/Type.java +15 -0
- data/embulk-core/src/main/java/org/embulk/spi/type/TypeDeserializer.java +44 -0
- data/embulk-core/src/main/java/org/embulk/spi/type/Types.java +14 -0
- data/embulk-core/src/main/java/org/embulk/spi/unit/ByteSize.java +156 -0
- data/embulk-core/src/main/java/org/embulk/spi/unit/LocalFile.java +106 -0
- data/embulk-core/src/main/java/org/embulk/spi/unit/LocalFileSerDe.java +113 -0
- data/embulk-core/src/main/java/org/embulk/spi/unit/ToString.java +54 -0
- data/embulk-core/src/main/java/org/embulk/spi/unit/ToStringMap.java +34 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/CharsetSerDe.java +55 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/Decoders.java +81 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/DynamicColumnNotFoundException.java +10 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/DynamicColumnSetter.java +18 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/DynamicColumnSetterFactory.java +94 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/DynamicPageBuilder.java +161 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/Encoders.java +81 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/Executors.java +95 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/FileInputInputStream.java +111 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/FileOutputOutputStream.java +119 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/Filters.java +100 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/InputStreamFileInput.java +190 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/InputStreamTransactionalFileInput.java +25 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/Inputs.java +65 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/LineDecoder.java +118 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/LineEncoder.java +123 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/ListFileInput.java +52 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/Newline.java +38 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/OutputStreamFileOutput.java +88 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/PagePrinter.java +102 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/Pages.java +139 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/ResumableInputStream.java +128 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/RetryExecutor.java +130 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/Timestamps.java +53 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/dynamic/AbstractDynamicColumnSetter.java +79 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/dynamic/BooleanColumnSetter.java +64 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/dynamic/DefaultValueSetter.java +18 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/dynamic/DoubleColumnSetter.java +61 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/dynamic/LongColumnSetter.java +69 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/dynamic/NullDefaultValueSetter.java +34 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/dynamic/SkipColumnSetter.java +52 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/dynamic/StringColumnSetter.java +56 -0
- data/embulk-core/src/main/java/org/embulk/spi/util/dynamic/TimestampColumnSetter.java +64 -0
- data/embulk-core/src/main/resources/embulk/logback-color.xml +72 -0
- data/embulk-core/src/main/resources/embulk/logback-console.xml +14 -0
- data/embulk-core/src/main/resources/embulk/logback-file.xml +25 -0
- data/embulk-core/src/main/resources/embulk/parent_first_packages.properties +70 -0
- data/embulk-core/src/main/resources/embulk/parent_first_resources.properties +28 -0
- data/embulk-core/src/test/java/org/embulk/EmbulkTestRuntime.java +114 -0
- data/embulk-core/src/test/java/org/embulk/GuiceBinder.java +72 -0
- data/embulk-core/src/test/java/org/embulk/RandomManager.java +53 -0
- data/embulk-core/src/test/java/org/embulk/TestPluginSourceModule.java +23 -0
- data/embulk-core/src/test/java/org/embulk/TestUtilityModule.java +17 -0
- data/embulk-core/src/test/java/org/embulk/config/TestConfigLoader.java +66 -0
- data/embulk-core/src/test/java/org/embulk/config/TestConfigSource.java +114 -0
- data/embulk-core/src/test/java/org/embulk/config/TestTaskSource.java +70 -0
- data/embulk-core/src/test/java/org/embulk/plugin/MockPluginSource.java +58 -0
- data/embulk-core/src/test/java/org/embulk/plugin/TestPluginType.java +18 -0
- data/embulk-core/src/test/java/org/embulk/spi/MockFileOutput.java +63 -0
- data/embulk-core/src/test/java/org/embulk/spi/MockFormatterPlugin.java +101 -0
- data/embulk-core/src/test/java/org/embulk/spi/MockParserPlugin.java +73 -0
- data/embulk-core/src/test/java/org/embulk/spi/PageTestUtils.java +57 -0
- data/embulk-core/src/test/java/org/embulk/spi/TestBuffer.java +24 -0
- data/embulk-core/src/test/java/org/embulk/spi/TestFileInputInputStream.java +89 -0
- data/embulk-core/src/test/java/org/embulk/spi/TestFileInputRunner.java +196 -0
- data/embulk-core/src/test/java/org/embulk/spi/TestFileOutputRunner.java +207 -0
- data/embulk-core/src/test/java/org/embulk/spi/TestInputStreamFileInput.java +188 -0
- data/embulk-core/src/test/java/org/embulk/spi/TestPageBuilderReader.java +319 -0
- data/embulk-core/src/test/java/org/embulk/spi/time/TestTimestamp.java +116 -0
- data/embulk-core/src/test/java/org/embulk/spi/time/TestTimestampFormatterParser.java +63 -0
- data/embulk-core/src/test/java/org/embulk/spi/time/TestTimestampFormatterParserDeprecated.java +67 -0
- data/embulk-core/src/test/java/org/embulk/spi/type/TestTypeSerDe.java +45 -0
- data/embulk-core/src/test/java/org/embulk/spi/unit/TestByteSize.java +79 -0
- data/embulk-core/src/test/java/org/embulk/spi/util/TestLineDecoder.java +132 -0
- data/embulk-core/src/test/java/org/embulk/spi/util/TestLineEncoder.java +123 -0
- data/embulk-docs/Makefile +178 -0
- data/embulk-docs/build.gradle +32 -0
- data/embulk-docs/make.bat +243 -0
- data/embulk-docs/push-gh-pages.sh +49 -0
- data/embulk-docs/src/_static/embulk-architecture.png +0 -0
- data/embulk-docs/src/_static/embulk-logo.png +0 -0
- data/embulk-docs/src/_static/embulk-logo.svg +133 -0
- data/embulk-docs/src/built-in.rst +440 -0
- data/embulk-docs/src/conf.py +260 -0
- data/embulk-docs/src/customization.rst +184 -0
- data/embulk-docs/src/index.rst +84 -0
- data/embulk-docs/src/recipe.rst +8 -0
- data/embulk-docs/src/recipe/scheduled-csv-load-to-elasticsearch-kibana4.rst +153 -0
- data/embulk-docs/src/release.rst +57 -0
- data/embulk-docs/src/release/release-0.1.0.rst +8 -0
- data/embulk-docs/src/release/release-0.2.0.rst +16 -0
- data/embulk-docs/src/release/release-0.2.1.rst +19 -0
- data/embulk-docs/src/release/release-0.3.0.rst +34 -0
- data/embulk-docs/src/release/release-0.3.1.rst +11 -0
- data/embulk-docs/src/release/release-0.3.2.rst +15 -0
- data/embulk-docs/src/release/release-0.4.0.rst +74 -0
- data/embulk-docs/src/release/release-0.4.1.rst +18 -0
- data/embulk-docs/src/release/release-0.4.10.rst +17 -0
- data/embulk-docs/src/release/release-0.4.2.rst +18 -0
- data/embulk-docs/src/release/release-0.4.3.rst +34 -0
- data/embulk-docs/src/release/release-0.4.4.rst +39 -0
- data/embulk-docs/src/release/release-0.4.5.rst +24 -0
- data/embulk-docs/src/release/release-0.4.6.rst +30 -0
- data/embulk-docs/src/release/release-0.4.7.rst +16 -0
- data/embulk-docs/src/release/release-0.4.8.rst +15 -0
- data/embulk-docs/src/release/release-0.4.9.rst +23 -0
- data/embulk-docs/src/release/release-0.5.0.rst +89 -0
- data/embulk-docs/src/release/release-0.5.1.rst +13 -0
- data/embulk-docs/src/release/release-0.5.2.rst +30 -0
- data/embulk-docs/src/release/release-0.5.3.rst +22 -0
- data/embulk-docs/src/release/release-0.5.4.rst +24 -0
- data/embulk-docs/src/release/release-0.5.5.rst +18 -0
- data/embulk-docs/src/release/release-0.6.0.rst +34 -0
- data/embulk-docs/src/release/release-0.6.1.rst +11 -0
- data/embulk-docs/src/release/release-0.6.10.rst +15 -0
- data/embulk-docs/src/release/release-0.6.11.rst +19 -0
- data/embulk-docs/src/release/release-0.6.12.rst +31 -0
- data/embulk-docs/src/release/release-0.6.13.rst +23 -0
- data/embulk-docs/src/release/release-0.6.14.rst +47 -0
- data/embulk-docs/src/release/release-0.6.15.rst +26 -0
- data/embulk-docs/src/release/release-0.6.16.rst +26 -0
- data/embulk-docs/src/release/release-0.6.17.rst +39 -0
- data/embulk-docs/src/release/release-0.6.18.rst +14 -0
- data/embulk-docs/src/release/release-0.6.19.rst +18 -0
- data/embulk-docs/src/release/release-0.6.2.rst +17 -0
- data/embulk-docs/src/release/release-0.6.20.rst +19 -0
- data/embulk-docs/src/release/release-0.6.21.rst +20 -0
- data/embulk-docs/src/release/release-0.6.22.rst +26 -0
- data/embulk-docs/src/release/release-0.6.23.rst +17 -0
- data/embulk-docs/src/release/release-0.6.24.rst +13 -0
- data/embulk-docs/src/release/release-0.6.25.rst +12 -0
- data/embulk-docs/src/release/release-0.6.3.rst +23 -0
- data/embulk-docs/src/release/release-0.6.4.rst +13 -0
- data/embulk-docs/src/release/release-0.6.5.rst +17 -0
- data/embulk-docs/src/release/release-0.6.6.rst +17 -0
- data/embulk-docs/src/release/release-0.6.7.rst +17 -0
- data/embulk-docs/src/release/release-0.6.8.rst +24 -0
- data/embulk-docs/src/release/release-0.6.9.rst +24 -0
- data/embulk-docs/src/release/release-0.7.0.rst +96 -0
- data/embulk-standards/build.gradle +5 -0
- data/embulk-standards/src/main/java/org/embulk/standards/CsvFormatterPlugin.java +284 -0
- data/embulk-standards/src/main/java/org/embulk/standards/CsvParserPlugin.java +379 -0
- data/embulk-standards/src/main/java/org/embulk/standards/CsvTokenizer.java +411 -0
- data/embulk-standards/src/main/java/org/embulk/standards/GzipFileDecoderPlugin.java +55 -0
- data/embulk-standards/src/main/java/org/embulk/standards/GzipFileEncoderPlugin.java +71 -0
- data/embulk-standards/src/main/java/org/embulk/standards/LocalFileInputPlugin.java +203 -0
- data/embulk-standards/src/main/java/org/embulk/standards/LocalFileOutputPlugin.java +148 -0
- data/embulk-standards/src/main/java/org/embulk/standards/NullOutputPlugin.java +59 -0
- data/embulk-standards/src/main/java/org/embulk/standards/RenameFilterPlugin.java +56 -0
- data/embulk-standards/src/main/java/org/embulk/standards/StandardPluginExtension.java +16 -0
- data/embulk-standards/src/main/java/org/embulk/standards/StandardPluginModule.java +53 -0
- data/embulk-standards/src/main/java/org/embulk/standards/StdoutOutputPlugin.java +85 -0
- data/embulk-standards/src/main/resources/META-INF/services/org.embulk.spi.Extension +1 -0
- data/embulk-standards/src/test/java/org/embulk/standards/TestCsvFormatterPlugin.java +312 -0
- data/embulk-standards/src/test/java/org/embulk/standards/TestCsvParserPlugin.java +75 -0
- data/embulk-standards/src/test/java/org/embulk/standards/TestCsvTokenizer.java +360 -0
- data/embulk-standards/src/test/java/org/embulk/standards/TestRenameFilterPlugin.java +88 -0
- data/embulk.gemspec +39 -0
- data/gradle/wrapper/gradle-wrapper.jar +0 -0
- data/gradle/wrapper/gradle-wrapper.properties +6 -0
- data/gradlew +164 -0
- data/gradlew.bat +90 -0
- data/lib/embulk.rb +72 -0
- data/lib/embulk/buffer.rb +22 -0
- data/lib/embulk/column.rb +70 -0
- data/lib/embulk/command/embulk_bundle.rb +56 -0
- data/lib/embulk/command/embulk_example.rb +32 -0
- data/lib/embulk/command/embulk_generate_bin.rb +62 -0
- data/lib/embulk/command/embulk_main.rb +2 -0
- data/lib/embulk/command/embulk_migrate_plugin.rb +170 -0
- data/lib/embulk/command/embulk_new_plugin.rb +124 -0
- data/lib/embulk/command/embulk_run.rb +470 -0
- data/lib/embulk/command/embulk_selfupdate.rb +84 -0
- data/lib/embulk/data/bundle/.bundle/config +3 -0
- data/lib/embulk/data/bundle/.ruby-version +1 -0
- data/lib/embulk/data/bundle/Gemfile +26 -0
- data/lib/embulk/data/bundle/embulk/filter/example.rb +42 -0
- data/lib/embulk/data/bundle/embulk/input/example.rb +54 -0
- data/lib/embulk/data/bundle/embulk/output/example.rb +58 -0
- data/lib/embulk/data/new/LICENSE.txt +21 -0
- data/lib/embulk/data/new/README.md.erb +111 -0
- data/lib/embulk/data/new/gitignore.erb +13 -0
- data/lib/embulk/data/new/java/build.gradle.erb +73 -0
- data/lib/embulk/data/new/java/decoder.java.erb +84 -0
- data/lib/embulk/data/new/java/encoder.java.erb +86 -0
- data/lib/embulk/data/new/java/file_input.java.erb +143 -0
- data/lib/embulk/data/new/java/file_output.java.erb +93 -0
- data/lib/embulk/data/new/java/filter.java.erb +56 -0
- data/lib/embulk/data/new/java/formatter.java.erb +54 -0
- data/lib/embulk/data/new/java/gradle/wrapper/gradle-wrapper.jar +0 -0
- data/lib/embulk/data/new/java/gradle/wrapper/gradle-wrapper.properties +6 -0
- data/lib/embulk/data/new/java/gradlew +164 -0
- data/lib/embulk/data/new/java/gradlew.bat +90 -0
- data/lib/embulk/data/new/java/input.java.erb +87 -0
- data/lib/embulk/data/new/java/output.java.erb +77 -0
- data/lib/embulk/data/new/java/parser.java.erb +60 -0
- data/lib/embulk/data/new/java/plugin_loader.rb.erb +3 -0
- data/lib/embulk/data/new/java/test.java.erb +5 -0
- data/lib/embulk/data/new/ruby/.ruby-version +1 -0
- data/lib/embulk/data/new/ruby/Gemfile +2 -0
- data/lib/embulk/data/new/ruby/Rakefile +3 -0
- data/lib/embulk/data/new/ruby/decoder_guess.rb.erb +25 -0
- data/lib/embulk/data/new/ruby/filter.rb.erb +41 -0
- data/lib/embulk/data/new/ruby/formatter.rb.erb +49 -0
- data/lib/embulk/data/new/ruby/gemspec.erb +20 -0
- data/lib/embulk/data/new/ruby/input.rb.erb +59 -0
- data/lib/embulk/data/new/ruby/output.rb.erb +61 -0
- data/lib/embulk/data/new/ruby/parser.rb.erb +44 -0
- data/lib/embulk/data/new/ruby/parser_guess.rb.erb +65 -0
- data/lib/embulk/data/package_data.rb +50 -0
- data/lib/embulk/data_source.rb +220 -0
- data/lib/embulk/decoder_plugin.rb +27 -0
- data/lib/embulk/encoder_plugin.rb +27 -0
- data/lib/embulk/error.rb +8 -0
- data/lib/embulk/executor_plugin.rb +23 -0
- data/lib/embulk/file_input.rb +87 -0
- data/lib/embulk/file_input_plugin.rb +27 -0
- data/lib/embulk/file_output.rb +56 -0
- data/lib/embulk/file_output_plugin.rb +27 -0
- data/lib/embulk/filter_plugin.rb +105 -0
- data/lib/embulk/formatter_plugin.rb +105 -0
- data/lib/embulk/guess/charset.rb +44 -0
- data/lib/embulk/guess/csv.rb +327 -0
- data/lib/embulk/guess/gzip.rb +18 -0
- data/lib/embulk/guess/newline.rb +22 -0
- data/lib/embulk/guess/schema_guess.rb +118 -0
- data/lib/embulk/guess/time_format_guess.rb +394 -0
- data/lib/embulk/guess_plugin.rb +129 -0
- data/lib/embulk/input_plugin.rb +121 -0
- data/lib/embulk/java/bootstrap.rb +24 -0
- data/lib/embulk/java/imports.rb +69 -0
- data/lib/embulk/java/time_helper.rb +79 -0
- data/lib/embulk/java_plugin.rb +90 -0
- data/lib/embulk/logger.rb +154 -0
- data/lib/embulk/output_plugin.rb +150 -0
- data/lib/embulk/page.rb +30 -0
- data/lib/embulk/page_builder.rb +76 -0
- data/lib/embulk/parser_plugin.rb +78 -0
- data/lib/embulk/plugin.rb +239 -0
- data/lib/embulk/plugin_registry.rb +96 -0
- data/lib/embulk/runner.rb +184 -0
- data/lib/embulk/schema.rb +103 -0
- data/lib/embulk/version.rb +3 -0
- data/settings.gradle +6 -0
- data/test/guess/test_schema_guess.rb +11 -0
- data/test/guess/test_time_format_guess.rb +133 -0
- data/test/helper.rb +21 -0
- data/test/run-test.rb +14 -0
- metadata +566 -0
@@ -0,0 +1,27 @@
|
|
1
|
+
module Embulk
|
2
|
+
|
3
|
+
class FileInputPlugin
|
4
|
+
# TODO transaction, resume, cleanup
|
5
|
+
# TODO run
|
6
|
+
|
7
|
+
if Embulk.java?
|
8
|
+
# TODO to_java
|
9
|
+
|
10
|
+
def self.from_java(java_class)
|
11
|
+
JavaPlugin.ruby_adapter_class(java_class, FileInputPlugin, RubyAdapter)
|
12
|
+
end
|
13
|
+
|
14
|
+
module RubyAdapter
|
15
|
+
module ClassMethods
|
16
|
+
def new_java
|
17
|
+
Java::FileInputRunner.new(Java.injector.getInstance(java_class))
|
18
|
+
end
|
19
|
+
# TODO transaction, resume, cleanup
|
20
|
+
end
|
21
|
+
|
22
|
+
# TODO run
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
end
|
@@ -0,0 +1,56 @@
|
|
1
|
+
|
2
|
+
module Embulk
|
3
|
+
require 'embulk/buffer'
|
4
|
+
|
5
|
+
class FileOutput
|
6
|
+
def initialize(java_file_output)
|
7
|
+
@java_file_output = java_file_output
|
8
|
+
@buffer = Buffer.new
|
9
|
+
@buffer.force_encoding('ASCII-8BIT')
|
10
|
+
@flush_size = 32*1024
|
11
|
+
end
|
12
|
+
|
13
|
+
def next_file
|
14
|
+
flush
|
15
|
+
@java_file_output.nextFile
|
16
|
+
self
|
17
|
+
end
|
18
|
+
|
19
|
+
def write(buffer)
|
20
|
+
buffer.force_encoding('ASCII-8BIT') # TODO this is destructively change buffer
|
21
|
+
@buffer << buffer
|
22
|
+
if @buffer.size > @flush_size
|
23
|
+
flush
|
24
|
+
end
|
25
|
+
nil
|
26
|
+
end
|
27
|
+
|
28
|
+
def add(buffer)
|
29
|
+
flush
|
30
|
+
@java_file_output.add(Buffer.from_ruby_string(buffer))
|
31
|
+
nil
|
32
|
+
end
|
33
|
+
|
34
|
+
def flush
|
35
|
+
unless @buffer.empty?
|
36
|
+
@java_file_output.add(@buffer.to_java)
|
37
|
+
@buffer.clear
|
38
|
+
end
|
39
|
+
nil
|
40
|
+
end
|
41
|
+
|
42
|
+
def finish
|
43
|
+
flush
|
44
|
+
@java_file_output.finish
|
45
|
+
end
|
46
|
+
|
47
|
+
def close
|
48
|
+
@java_file_output.close
|
49
|
+
end
|
50
|
+
|
51
|
+
def to_java
|
52
|
+
@java_file_output
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
module Embulk
|
2
|
+
|
3
|
+
class FileOutputPlugin
|
4
|
+
# TODO transaction, resume, cleanup
|
5
|
+
# TODO add, finish, close, abort, commit
|
6
|
+
|
7
|
+
if Embulk.java?
|
8
|
+
# TODO to_java
|
9
|
+
|
10
|
+
def self.from_java(java_class)
|
11
|
+
JavaPlugin.ruby_adapter_class(java_class, FileOutputPlugin, RubyAdapter)
|
12
|
+
end
|
13
|
+
|
14
|
+
module RubyAdapter
|
15
|
+
module ClassMethods
|
16
|
+
def new_java
|
17
|
+
Java::FileOutputRunner.new(Java.injector.getInstance(java_class))
|
18
|
+
end
|
19
|
+
# TODO transaction, resume, cleanup
|
20
|
+
end
|
21
|
+
|
22
|
+
# TODO add, finish, close, abort, commit
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
end
|
@@ -0,0 +1,105 @@
|
|
1
|
+
module Embulk
|
2
|
+
|
3
|
+
require 'embulk/data_source'
|
4
|
+
require 'embulk/schema'
|
5
|
+
require 'embulk/page'
|
6
|
+
require 'embulk/page_builder'
|
7
|
+
|
8
|
+
class FilterPlugin
|
9
|
+
def self.transaction(config, in_schema, &control)
|
10
|
+
yield(config)
|
11
|
+
return {}
|
12
|
+
end
|
13
|
+
|
14
|
+
def initialize(task, in_schema, out_schema, page_builder)
|
15
|
+
@task = task
|
16
|
+
@in_schema = in_schema
|
17
|
+
@out_schema = out_schema
|
18
|
+
@page_builder = page_builder
|
19
|
+
init
|
20
|
+
end
|
21
|
+
|
22
|
+
attr_reader :task, :in_schema, :out_schema, :page_builder
|
23
|
+
|
24
|
+
def init
|
25
|
+
end
|
26
|
+
|
27
|
+
def add(page)
|
28
|
+
raise NotImplementedError, "FilterPlugin#add(page) must be implemented"
|
29
|
+
end
|
30
|
+
|
31
|
+
def finish
|
32
|
+
end
|
33
|
+
|
34
|
+
def close
|
35
|
+
end
|
36
|
+
|
37
|
+
if Embulk.java?
|
38
|
+
def self.new_java
|
39
|
+
JavaAdapter.new(self)
|
40
|
+
end
|
41
|
+
|
42
|
+
class JavaAdapter
|
43
|
+
include Java::FilterPlugin
|
44
|
+
|
45
|
+
def initialize(ruby_class)
|
46
|
+
@ruby_class = ruby_class
|
47
|
+
end
|
48
|
+
|
49
|
+
def transaction(java_config, java_in_schema, java_control)
|
50
|
+
config = DataSource.from_java(java_config)
|
51
|
+
in_schema = Schema.from_java(java_in_schema)
|
52
|
+
@ruby_class.transaction(config, in_schema) do |task_source_hash, out_columns|
|
53
|
+
java_task_source = DataSource.from_ruby_hash(task_source_hash).to_java
|
54
|
+
java_out_schemas = Schema.new(out_columns).to_java
|
55
|
+
java_control.run(java_task_source, java_out_schemas)
|
56
|
+
end
|
57
|
+
nil
|
58
|
+
end
|
59
|
+
|
60
|
+
def open(java_task_source, java_in_schema, java_out_schema, java_output)
|
61
|
+
task_source = DataSource.from_java(java_task_source)
|
62
|
+
in_schema = Schema.from_java(java_in_schema)
|
63
|
+
out_schema = Schema.from_java(java_out_schema)
|
64
|
+
page_builder = PageBuilder.new(out_schema, java_output)
|
65
|
+
ruby_object = @ruby_class.new(task_source, in_schema, out_schema, page_builder)
|
66
|
+
return OutputAdapter.new(ruby_object, in_schema, page_builder)
|
67
|
+
end
|
68
|
+
|
69
|
+
class OutputAdapter
|
70
|
+
include Java::TransactionalPageOutput
|
71
|
+
|
72
|
+
def initialize(ruby_object, in_schema, page_builder)
|
73
|
+
@ruby_object = ruby_object
|
74
|
+
@in_schema = in_schema
|
75
|
+
@page_builder = page_builder
|
76
|
+
end
|
77
|
+
|
78
|
+
def add(java_page)
|
79
|
+
@ruby_object.add Page.new(java_page, @in_schema)
|
80
|
+
end
|
81
|
+
|
82
|
+
def finish
|
83
|
+
@ruby_object.finish
|
84
|
+
end
|
85
|
+
|
86
|
+
def close
|
87
|
+
@ruby_object.close
|
88
|
+
ensure
|
89
|
+
@page_builder.close
|
90
|
+
end
|
91
|
+
end
|
92
|
+
end
|
93
|
+
|
94
|
+
def self.from_java(java_class)
|
95
|
+
JavaPlugin.ruby_adapter_class(java_class, FilterPlugin, RubyAdapter)
|
96
|
+
end
|
97
|
+
|
98
|
+
module RubyAdapter
|
99
|
+
module ClassMethods
|
100
|
+
end
|
101
|
+
# TODO
|
102
|
+
end
|
103
|
+
end
|
104
|
+
end
|
105
|
+
end
|
@@ -0,0 +1,105 @@
|
|
1
|
+
module Embulk
|
2
|
+
|
3
|
+
require 'embulk/data_source'
|
4
|
+
require 'embulk/schema'
|
5
|
+
require 'embulk/page'
|
6
|
+
require 'embulk/file_output'
|
7
|
+
|
8
|
+
class FormatterPlugin
|
9
|
+
def self.transaction(config, schema, &control)
|
10
|
+
yield(config)
|
11
|
+
return {}
|
12
|
+
end
|
13
|
+
|
14
|
+
def initialize(task, schema, file_output)
|
15
|
+
@task = task
|
16
|
+
@schema = schema
|
17
|
+
@file_output = file_output
|
18
|
+
init
|
19
|
+
end
|
20
|
+
|
21
|
+
attr_reader :task, :schema, :file_output
|
22
|
+
|
23
|
+
def init
|
24
|
+
end
|
25
|
+
|
26
|
+
def add(page)
|
27
|
+
raise NotImplementedError, "FormatterPlugin#add(page) must be implemented"
|
28
|
+
end
|
29
|
+
|
30
|
+
def finish
|
31
|
+
end
|
32
|
+
|
33
|
+
def close
|
34
|
+
end
|
35
|
+
|
36
|
+
if Embulk.java?
|
37
|
+
def self.new_java
|
38
|
+
JavaAdapter.new(self)
|
39
|
+
end
|
40
|
+
|
41
|
+
class JavaAdapter
|
42
|
+
include Java::FormatterPlugin
|
43
|
+
|
44
|
+
def initialize(ruby_class)
|
45
|
+
@ruby_class = ruby_class
|
46
|
+
end
|
47
|
+
|
48
|
+
def transaction(java_config, java_schema, java_control)
|
49
|
+
config = DataSource.from_java(java_config)
|
50
|
+
schema = Schema.from_java(java_schema)
|
51
|
+
@ruby_class.transaction(config, schema) do |task_source_hash|
|
52
|
+
java_task_source = DataSource.from_ruby_hash(task_source_hash).to_java
|
53
|
+
java_control.run(java_task_source)
|
54
|
+
end
|
55
|
+
nil
|
56
|
+
end
|
57
|
+
|
58
|
+
def open(java_task_source, java_schema, java_file_output)
|
59
|
+
task_source = DataSource.from_java(java_task_source)
|
60
|
+
schema = Schema.from_java(java_schema)
|
61
|
+
file_output = FileOutput.new(java_file_output)
|
62
|
+
ruby_object = @ruby_class.new(task_source, schema, file_output)
|
63
|
+
return OutputAdapter.new(ruby_object, schema, file_output)
|
64
|
+
end
|
65
|
+
|
66
|
+
class OutputAdapter
|
67
|
+
include Java::TransactionalPageOutput
|
68
|
+
|
69
|
+
def initialize(ruby_object, schema, file_output)
|
70
|
+
@ruby_object = ruby_object
|
71
|
+
@schema = schema
|
72
|
+
@file_output = file_output
|
73
|
+
end
|
74
|
+
|
75
|
+
def add(java_page)
|
76
|
+
# TODO reuse page reader
|
77
|
+
@ruby_object.add Page.new(java_page, @schema)
|
78
|
+
end
|
79
|
+
|
80
|
+
def finish
|
81
|
+
@ruby_object.finish
|
82
|
+
end
|
83
|
+
|
84
|
+
def close
|
85
|
+
@ruby_object.close
|
86
|
+
ensure
|
87
|
+
@file_output.close
|
88
|
+
end
|
89
|
+
end
|
90
|
+
end
|
91
|
+
|
92
|
+
def self.from_java(java_class)
|
93
|
+
JavaPlugin.ruby_adapter_class(java_class, FormatterPlugin, RubyAdapter)
|
94
|
+
end
|
95
|
+
|
96
|
+
module RubyAdapter
|
97
|
+
module ClassMethods
|
98
|
+
# TODO transaction, resume, cleanup
|
99
|
+
end
|
100
|
+
# TODO add, finish, close
|
101
|
+
end
|
102
|
+
end
|
103
|
+
end
|
104
|
+
|
105
|
+
end
|
@@ -0,0 +1,44 @@
|
|
1
|
+
module Embulk
|
2
|
+
module Guess
|
3
|
+
|
4
|
+
class CharsetGuessPlugin < GuessPlugin
|
5
|
+
Plugin.register_guess('charset', self)
|
6
|
+
|
7
|
+
STATIC_MAPPING = {
|
8
|
+
# ISO-8859-1 means ASCII which is a subset of UTF-8 in most of cases
|
9
|
+
# due to lack of sample data set.
|
10
|
+
"ISO-8859-1" => "UTF-8",
|
11
|
+
|
12
|
+
# Shift_JIS is used almost only by Windows that uses "CP932" in fact.
|
13
|
+
# And "CP932" called by Microsoft actually means "MS932" in Java.
|
14
|
+
"Shift_JIS" => "MS932",
|
15
|
+
}
|
16
|
+
|
17
|
+
def guess(config, sample_buffer)
|
18
|
+
# ICU4J
|
19
|
+
begin
|
20
|
+
detector_class = com.ibm.icu.text.CharsetDetector
|
21
|
+
rescue NameError
|
22
|
+
# icu4j is removed from embulk.gem package explicitly at embulk.gemspec
|
23
|
+
# if gem is packaged for JRuby to reduce binary size. Instead, if it's
|
24
|
+
# packaged for JRuby, embulk.gemspec adds rjack-icu to its dependency.
|
25
|
+
require 'rjack-icu'
|
26
|
+
detector_class = com.ibm.icu.text.CharsetDetector
|
27
|
+
end
|
28
|
+
detector = detector_class.new
|
29
|
+
detector.setText(sample_buffer.to_java_bytes)
|
30
|
+
best_match = detector.detect
|
31
|
+
if best_match.getConfidence < 50
|
32
|
+
name = "UTF-8"
|
33
|
+
else
|
34
|
+
name = best_match.getName
|
35
|
+
if mapped_name = STATIC_MAPPING[name]
|
36
|
+
name = mapped_name
|
37
|
+
end
|
38
|
+
end
|
39
|
+
return {"parser" => {"charset" => name}}
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
end
|
44
|
+
end
|
@@ -0,0 +1,327 @@
|
|
1
|
+
module Embulk
|
2
|
+
module Guess
|
3
|
+
require 'embulk/guess/schema_guess'
|
4
|
+
|
5
|
+
class CsvGuessPlugin < LineGuessPlugin
|
6
|
+
Plugin.register_guess('csv', self)
|
7
|
+
|
8
|
+
DELIMITER_CANDIDATES = [
|
9
|
+
",", "\t", "|"
|
10
|
+
]
|
11
|
+
|
12
|
+
QUOTE_CANDIDATES = [
|
13
|
+
"\"", "'"
|
14
|
+
]
|
15
|
+
|
16
|
+
ESCAPE_CANDIDATES = [
|
17
|
+
"\\", '"'
|
18
|
+
]
|
19
|
+
|
20
|
+
NULL_STRING_CANDIDATES = [
|
21
|
+
"null",
|
22
|
+
"NULL",
|
23
|
+
"#N/A",
|
24
|
+
"\\N", # MySQL LOAD, Hive STORED AS TEXTFILE
|
25
|
+
]
|
26
|
+
|
27
|
+
COMMENT_LINE_MARKER_CANDIDATES = [
|
28
|
+
"#",
|
29
|
+
"//",
|
30
|
+
]
|
31
|
+
|
32
|
+
MAX_SKIP_LINES = 10
|
33
|
+
NO_SKIP_DETECT_LINES = 10
|
34
|
+
|
35
|
+
def guess_lines(config, sample_lines)
|
36
|
+
return {} unless config.fetch("parser", {}).fetch("type", "csv") == "csv"
|
37
|
+
|
38
|
+
parser_config = config["parser"] || {}
|
39
|
+
if parser_config["type"] == "csv" && parser_config["delimiter"]
|
40
|
+
delim = parser_config["delimiter"]
|
41
|
+
else
|
42
|
+
delim = guess_delimiter(sample_lines)
|
43
|
+
unless delim
|
44
|
+
# not CSV file
|
45
|
+
return {}
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
parser_guessed = DataSource.new.merge(parser_config).merge({"type" => "csv", "delimiter" => delim})
|
50
|
+
|
51
|
+
unless parser_guessed.has_key?("quote")
|
52
|
+
quote = guess_quote(sample_lines, delim)
|
53
|
+
unless quote
|
54
|
+
if !guess_force_no_quote(sample_lines, delim, '"')
|
55
|
+
# assuming CSV follows RFC for quoting
|
56
|
+
quote = '"'
|
57
|
+
else
|
58
|
+
# disable quoting (set null)
|
59
|
+
end
|
60
|
+
end
|
61
|
+
parser_guessed["quote"] = quote
|
62
|
+
end
|
63
|
+
parser_guessed["quote"] = '"' if parser_guessed["quote"] == '' # setting '' is not allowed any more. this line converts obsoleted config syntax to explicit syntax.
|
64
|
+
|
65
|
+
unless parser_guessed.has_key?("escape")
|
66
|
+
if quote = parser_guessed["quote"]
|
67
|
+
escape = guess_escape(sample_lines, delim, quote)
|
68
|
+
unless escape
|
69
|
+
if quote == '"'
|
70
|
+
# assuming this CSV follows RFC for escaping
|
71
|
+
escape = '"'
|
72
|
+
else
|
73
|
+
# disable escaping (set null)
|
74
|
+
end
|
75
|
+
parser_guessed["escape"] = escape
|
76
|
+
end
|
77
|
+
else
|
78
|
+
# escape does nothing if quote is disabled
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
unless parser_guessed.has_key?("null_string")
|
83
|
+
null_string = guess_null_string(sample_lines, delim)
|
84
|
+
parser_guessed["null_string"] = null_string if null_string
|
85
|
+
# don't even set null_string to avoid confusion of null and 'null' in YAML format
|
86
|
+
end
|
87
|
+
|
88
|
+
# guessing skip_header_lines should be before guessing guess_comment_line_marker
|
89
|
+
# because lines supplied to CsvTokenizer already don't include skipped header lines.
|
90
|
+
# skipping empty lines is also disabled here because skipping header lines is done by
|
91
|
+
# CsvParser which doesn't skip empty lines automatically
|
92
|
+
sample_records = split_lines(parser_guessed, false, sample_lines, delim, {})
|
93
|
+
skip_header_lines = guess_skip_header_lines(sample_records)
|
94
|
+
sample_lines = sample_lines[skip_header_lines..-1]
|
95
|
+
sample_records = sample_records[skip_header_lines..-1]
|
96
|
+
|
97
|
+
unless parser_guessed.has_key?("comment_line_marker")
|
98
|
+
comment_line_marker, sample_lines =
|
99
|
+
guess_comment_line_marker(sample_lines, delim, parser_guessed["quote"], parser_guessed["null_string"])
|
100
|
+
if comment_line_marker
|
101
|
+
parser_guessed["comment_line_marker"] = comment_line_marker
|
102
|
+
end
|
103
|
+
end
|
104
|
+
|
105
|
+
sample_records = split_lines(parser_guessed, true, sample_lines, delim, {})
|
106
|
+
|
107
|
+
first_types = SchemaGuess.types_from_array_records(sample_records[0, 1])
|
108
|
+
other_types = SchemaGuess.types_from_array_records(sample_records[1..-1] || [])
|
109
|
+
|
110
|
+
if first_types.size <= 1 || other_types.size <= 1
|
111
|
+
# guess failed
|
112
|
+
return {}
|
113
|
+
end
|
114
|
+
|
115
|
+
unless parser_guessed.has_key?("trim_if_not_quoted")
|
116
|
+
sample_records_trimmed = split_lines(parser_guessed, true, sample_lines, delim, {"trim_if_not_quoted" => true})
|
117
|
+
other_types_trimmed = SchemaGuess.types_from_array_records(sample_records_trimmed[1..-1] || [])
|
118
|
+
if other_types != other_types_trimmed
|
119
|
+
parser_guessed["trim_if_not_quoted"] = true
|
120
|
+
other_types = other_types_trimmed
|
121
|
+
else
|
122
|
+
parser_guessed["trim_if_not_quoted"] = false
|
123
|
+
end
|
124
|
+
end
|
125
|
+
|
126
|
+
header_line = (first_types != other_types && first_types.all? {|t| ["string", "boolean"].include?(t) })
|
127
|
+
|
128
|
+
if header_line
|
129
|
+
parser_guessed["skip_header_lines"] = skip_header_lines + 1
|
130
|
+
else
|
131
|
+
parser_guessed["skip_header_lines"] = skip_header_lines
|
132
|
+
end
|
133
|
+
|
134
|
+
parser_guessed["allow_extra_columns"] = false unless parser_guessed.has_key?("allow_extra_columns")
|
135
|
+
parser_guessed["allow_optional_columns"] = false unless parser_guessed.has_key?("allow_optional_columns")
|
136
|
+
|
137
|
+
if header_line
|
138
|
+
column_names = sample_records.first
|
139
|
+
else
|
140
|
+
column_names = (0..other_types.size).to_a.map {|i| "c#{i}" }
|
141
|
+
end
|
142
|
+
schema = []
|
143
|
+
column_names.zip(other_types).each do |name,type|
|
144
|
+
if name && type
|
145
|
+
if type.is_a?(SchemaGuess::TimestampTypeMatch)
|
146
|
+
schema << {"name" => name, "type" => type, "format" => type.format}
|
147
|
+
else
|
148
|
+
schema << {"name" => name, "type" => type}
|
149
|
+
end
|
150
|
+
end
|
151
|
+
end
|
152
|
+
parser_guessed["columns"] = schema
|
153
|
+
|
154
|
+
return {"parser" => parser_guessed}
|
155
|
+
end
|
156
|
+
|
157
|
+
private
|
158
|
+
|
159
|
+
def split_lines(parser_config, skip_empty_lines, sample_lines, delim, extra_config)
|
160
|
+
null_string = parser_config["null_string"]
|
161
|
+
config = parser_config.merge(extra_config).merge({"charset" => "UTF-8", "columns" => []})
|
162
|
+
parser_task = config.load_config(org.embulk.standards.CsvParserPlugin::PluginTask)
|
163
|
+
data = sample_lines.map {|line| line.force_encoding('UTF-8') }.join(parser_task.getNewline.getString.encode('UTF-8'))
|
164
|
+
sample = Buffer.from_ruby_string(data)
|
165
|
+
decoder = Java::LineDecoder.new(Java::ListFileInput.new([[sample.to_java]]), parser_task)
|
166
|
+
tokenizer = org.embulk.standards.CsvTokenizer.new(decoder, parser_task)
|
167
|
+
rows = []
|
168
|
+
while tokenizer.nextFile
|
169
|
+
while tokenizer.nextRecord(skip_empty_lines)
|
170
|
+
begin
|
171
|
+
columns = []
|
172
|
+
while true
|
173
|
+
begin
|
174
|
+
column = tokenizer.nextColumn
|
175
|
+
quoted = tokenizer.wasQuotedColumn
|
176
|
+
if null_string && !quoted && column == null_string
|
177
|
+
column = nil
|
178
|
+
end
|
179
|
+
columns << column
|
180
|
+
rescue org.embulk.standards.CsvTokenizer::TooFewColumnsException
|
181
|
+
rows << columns
|
182
|
+
break
|
183
|
+
end
|
184
|
+
end
|
185
|
+
rescue org.embulk.standards.CsvTokenizer::InvalidValueException
|
186
|
+
# TODO warning
|
187
|
+
tokenizer.skipCurrentLine
|
188
|
+
end
|
189
|
+
end
|
190
|
+
end
|
191
|
+
return rows
|
192
|
+
rescue
|
193
|
+
# TODO warning if fallback to this ad-hoc implementation
|
194
|
+
sample_lines.map {|line| line.split(delim) }
|
195
|
+
end
|
196
|
+
|
197
|
+
def guess_delimiter(sample_lines)
|
198
|
+
delim_weights = DELIMITER_CANDIDATES.map do |d|
|
199
|
+
counts = sample_lines.map {|line| line.count(d) }
|
200
|
+
total = array_sum(counts)
|
201
|
+
if total > 0
|
202
|
+
stddev = array_standard_deviation(counts)
|
203
|
+
stddev = 0.000000001 if stddev == 0.0
|
204
|
+
weight = total / stddev
|
205
|
+
[d, weight]
|
206
|
+
else
|
207
|
+
[nil, 0]
|
208
|
+
end
|
209
|
+
end
|
210
|
+
|
211
|
+
delim, weight = *delim_weights.sort_by {|d,weight| weight }.last
|
212
|
+
if delim != nil && weight > 1
|
213
|
+
return delim
|
214
|
+
else
|
215
|
+
return nil
|
216
|
+
end
|
217
|
+
end
|
218
|
+
|
219
|
+
def guess_quote(sample_lines, delim)
|
220
|
+
delim_regexp = Regexp.escape(delim)
|
221
|
+
quote_weights = QUOTE_CANDIDATES.map do |q|
|
222
|
+
weights = sample_lines.map do |line|
|
223
|
+
q_regexp = Regexp.escape(q)
|
224
|
+
count = line.count(q)
|
225
|
+
if count > 0
|
226
|
+
weight = count
|
227
|
+
weight += line.scan(/(?:\A|#{delim_regexp})\s*#{q_regexp}(?:(?!#{q_regexp}).)*\s*#{q_regexp}(?:$|#{delim_regexp})/).size * 20
|
228
|
+
weight += line.scan(/(?:\A|#{delim_regexp})\s*#{q_regexp}(?:(?!#{delim_regexp}).)*\s*#{q_regexp}(?:$|#{delim_regexp})/).size * 40
|
229
|
+
weight
|
230
|
+
else
|
231
|
+
nil
|
232
|
+
end
|
233
|
+
end.compact
|
234
|
+
weights.empty? ? 0 : array_avg(weights)
|
235
|
+
end
|
236
|
+
quote, weight = QUOTE_CANDIDATES.zip(quote_weights).sort_by {|q,w| w }.last
|
237
|
+
if weight >= 10.0
|
238
|
+
return quote
|
239
|
+
else
|
240
|
+
return nil
|
241
|
+
end
|
242
|
+
end
|
243
|
+
|
244
|
+
def guess_force_no_quote(sample_lines, delim, quote_candidate)
|
245
|
+
delim_regexp = Regexp.escape(delim)
|
246
|
+
q_regexp = Regexp.escape(quote_candidate)
|
247
|
+
sample_lines.any? do |line|
|
248
|
+
# quoting character appear at the middle of a non-quoted value
|
249
|
+
line =~ /(?:\A|#{delim_regexp})\s*[^#{q_regexp}]+#{q_regexp}/
|
250
|
+
end
|
251
|
+
end
|
252
|
+
|
253
|
+
def guess_escape(sample_lines, delim, quote)
|
254
|
+
guessed = ESCAPE_CANDIDATES.map do |str|
|
255
|
+
regexp = /#{Regexp.quote(str)}(?:#{Regexp.quote(delim)}|#{Regexp.quote(quote)})/
|
256
|
+
counts = sample_lines.map {|line| line.scan(regexp).count }
|
257
|
+
count = counts.inject(0) {|r,c| r + c }
|
258
|
+
[str, count]
|
259
|
+
end.select {|str,count| count > 0 }.sort_by {|str,count| -count }
|
260
|
+
found = guessed.first
|
261
|
+
return found ? found[0] : nil
|
262
|
+
end
|
263
|
+
|
264
|
+
def guess_null_string(sample_lines, delim)
|
265
|
+
guessed = NULL_STRING_CANDIDATES.map do |str|
|
266
|
+
regexp = /(?:^|#{Regexp.quote(delim)})#{Regexp.quote(str)}(?:$|#{Regexp.quote(delim)})/
|
267
|
+
counts = sample_lines.map {|line| line.scan(regexp).count }
|
268
|
+
count = counts.inject(0) {|r,c| r + c }
|
269
|
+
[str, count]
|
270
|
+
end.select {|str,count| count > 0 }.sort_by {|str,count| -count }
|
271
|
+
found_str, found_count = guessed.first
|
272
|
+
return found_str ? found_str : nil
|
273
|
+
end
|
274
|
+
|
275
|
+
def guess_skip_header_lines(sample_records)
|
276
|
+
counts = sample_records.map {|records| records.size }
|
277
|
+
(1..[MAX_SKIP_LINES, counts.length - 1].min).each do |i|
|
278
|
+
check_row_count = counts[i-1]
|
279
|
+
if counts[i, NO_SKIP_DETECT_LINES].all? {|c| c <= check_row_count }
|
280
|
+
return i - 1
|
281
|
+
end
|
282
|
+
end
|
283
|
+
return 0
|
284
|
+
end
|
285
|
+
|
286
|
+
def guess_comment_line_marker(sample_lines, delim, quote, null_string)
|
287
|
+
exclude = []
|
288
|
+
exclude << /^#{Regexp.escape(quote)}/ if quote && !quote.empty?
|
289
|
+
exclude << /^#{Regexp.escape(null_string)}(?:#{Regexp.escape(delim)}|$)/ if null_string
|
290
|
+
|
291
|
+
guessed = COMMENT_LINE_MARKER_CANDIDATES.map do |str|
|
292
|
+
regexp = /^#{Regexp.quote(str)}/
|
293
|
+
unmatch_lines = sample_lines.reject do |line|
|
294
|
+
exclude.all? {|ex| line !~ ex } && line =~ regexp
|
295
|
+
end
|
296
|
+
match_count = sample_lines.size - unmatch_lines.size
|
297
|
+
[str, match_count, unmatch_lines]
|
298
|
+
end.select {|str,match_count,unmatch_lines| match_count > 0 }.sort_by {|str,match_count,unmatch_lines| -match_count }
|
299
|
+
|
300
|
+
str, match_count, unmatch_lines = guessed.first
|
301
|
+
if str
|
302
|
+
return str, unmatch_lines
|
303
|
+
else
|
304
|
+
return nil, sample_lines
|
305
|
+
end
|
306
|
+
end
|
307
|
+
|
308
|
+
def array_sum(array)
|
309
|
+
array.inject(0) {|r,i| r += i }
|
310
|
+
end
|
311
|
+
|
312
|
+
def array_avg(array)
|
313
|
+
array.inject(0.0) {|r,i| r += i } / array.size
|
314
|
+
end
|
315
|
+
|
316
|
+
def array_variance(array)
|
317
|
+
avg = array_avg(array)
|
318
|
+
array.inject(0.0) {|r,i| r += (i - avg) ** 2 } / array.size
|
319
|
+
end
|
320
|
+
|
321
|
+
def array_standard_deviation(array)
|
322
|
+
Math.sqrt(array_variance(array))
|
323
|
+
end
|
324
|
+
end
|
325
|
+
|
326
|
+
end
|
327
|
+
end
|