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 +1,379 @@
|
|
1
|
+
package org.embulk.standards;
|
2
|
+
|
3
|
+
import com.google.common.base.Optional;
|
4
|
+
import com.google.common.collect.ImmutableSet;
|
5
|
+
import com.fasterxml.jackson.annotation.JsonCreator;
|
6
|
+
import com.fasterxml.jackson.annotation.JsonIgnore;
|
7
|
+
import com.fasterxml.jackson.annotation.JsonValue;
|
8
|
+
import org.embulk.config.Task;
|
9
|
+
import org.embulk.config.Config;
|
10
|
+
import org.embulk.config.ConfigDefault;
|
11
|
+
import org.embulk.config.ConfigSource;
|
12
|
+
import org.embulk.config.ConfigException;
|
13
|
+
import org.embulk.config.TaskSource;
|
14
|
+
import org.embulk.spi.time.TimestampParser;
|
15
|
+
import org.embulk.spi.time.TimestampParseException;
|
16
|
+
import org.embulk.spi.Column;
|
17
|
+
import org.embulk.spi.Schema;
|
18
|
+
import org.embulk.spi.SchemaConfig;
|
19
|
+
import org.embulk.spi.ColumnVisitor;
|
20
|
+
import org.embulk.spi.PageBuilder;
|
21
|
+
import org.embulk.spi.ParserPlugin;
|
22
|
+
import org.embulk.spi.Exec;
|
23
|
+
import org.embulk.spi.FileInput;
|
24
|
+
import org.embulk.spi.PageOutput;
|
25
|
+
import org.embulk.spi.util.LineDecoder;
|
26
|
+
import org.embulk.spi.util.Timestamps;
|
27
|
+
import org.slf4j.Logger;
|
28
|
+
|
29
|
+
public class CsvParserPlugin
|
30
|
+
implements ParserPlugin
|
31
|
+
{
|
32
|
+
private static final ImmutableSet<String> TRUE_STRINGS =
|
33
|
+
ImmutableSet.of(
|
34
|
+
"true", "True", "TRUE",
|
35
|
+
"yes", "Yes", "YES",
|
36
|
+
"t", "T", "y", "Y",
|
37
|
+
"on", "On", "ON",
|
38
|
+
"1");
|
39
|
+
|
40
|
+
public interface PluginTask
|
41
|
+
extends Task, LineDecoder.DecoderTask, TimestampParser.Task
|
42
|
+
{
|
43
|
+
@Config("columns")
|
44
|
+
SchemaConfig getSchemaConfig();
|
45
|
+
|
46
|
+
@Config("header_line")
|
47
|
+
@ConfigDefault("null")
|
48
|
+
Optional<Boolean> getHeaderLine();
|
49
|
+
|
50
|
+
@Config("skip_header_lines")
|
51
|
+
@ConfigDefault("0")
|
52
|
+
int getSkipHeaderLines();
|
53
|
+
void setSkipHeaderLines(int n);
|
54
|
+
|
55
|
+
@Config("delimiter")
|
56
|
+
@ConfigDefault("\",\"")
|
57
|
+
char getDelimiterChar();
|
58
|
+
|
59
|
+
@Config("quote")
|
60
|
+
@ConfigDefault("\"\\\"\"")
|
61
|
+
Optional<QuoteCharacter> getQuoteChar();
|
62
|
+
|
63
|
+
@Config("escape")
|
64
|
+
@ConfigDefault("\"\\\\\"")
|
65
|
+
Optional<EscapeCharacter> getEscapeChar();
|
66
|
+
|
67
|
+
// Null value handling: if the CsvParser found 'non-quoted empty string's,
|
68
|
+
// it replaces them to string that users specified like "\N", "NULL".
|
69
|
+
@Config("null_string")
|
70
|
+
@ConfigDefault("null")
|
71
|
+
Optional<String> getNullString();
|
72
|
+
|
73
|
+
@Config("trim_if_not_quoted")
|
74
|
+
@ConfigDefault("false")
|
75
|
+
boolean getTrimIfNotQuoted();
|
76
|
+
|
77
|
+
@Config("max_quoted_size_limit")
|
78
|
+
@ConfigDefault("131072") //128kB
|
79
|
+
long getMaxQuotedSizeLimit();
|
80
|
+
|
81
|
+
@Config("comment_line_marker")
|
82
|
+
@ConfigDefault("null")
|
83
|
+
Optional<String> getCommentLineMarker();
|
84
|
+
|
85
|
+
@Config("allow_optional_columns")
|
86
|
+
@ConfigDefault("false")
|
87
|
+
boolean getAllowOptionalColumns();
|
88
|
+
|
89
|
+
@Config("allow_extra_columns")
|
90
|
+
@ConfigDefault("false")
|
91
|
+
boolean getAllowExtraColumns();
|
92
|
+
}
|
93
|
+
|
94
|
+
public static class QuoteCharacter
|
95
|
+
{
|
96
|
+
private final char character;
|
97
|
+
|
98
|
+
public QuoteCharacter(char character)
|
99
|
+
{
|
100
|
+
this.character = character;
|
101
|
+
}
|
102
|
+
|
103
|
+
public static QuoteCharacter noQuote()
|
104
|
+
{
|
105
|
+
return new QuoteCharacter(CsvTokenizer.NO_QUOTE);
|
106
|
+
}
|
107
|
+
|
108
|
+
@JsonCreator
|
109
|
+
public static QuoteCharacter ofString(String str)
|
110
|
+
{
|
111
|
+
if (str.length() >= 2) {
|
112
|
+
throw new ConfigException("\"quote\" option accepts only 1 character.");
|
113
|
+
} else if (str.isEmpty()) {
|
114
|
+
Exec.getLogger(CsvParserPlugin.class).warn("Setting '' (empty string) to \"quote\" option is obsoleted. Currently it becomes '\"' automatically but this behavior will be removed. Please set '\"' explicitly.");
|
115
|
+
return new QuoteCharacter('"');
|
116
|
+
} else {
|
117
|
+
return new QuoteCharacter(str.charAt(0));
|
118
|
+
}
|
119
|
+
}
|
120
|
+
|
121
|
+
@JsonIgnore
|
122
|
+
public char getCharacter()
|
123
|
+
{
|
124
|
+
return character;
|
125
|
+
}
|
126
|
+
|
127
|
+
@JsonValue
|
128
|
+
public String getOptionalString()
|
129
|
+
{
|
130
|
+
return new String(new char[] { character });
|
131
|
+
}
|
132
|
+
|
133
|
+
@Override
|
134
|
+
public boolean equals(Object obj)
|
135
|
+
{
|
136
|
+
if (!(obj instanceof QuoteCharacter)) {
|
137
|
+
return false;
|
138
|
+
}
|
139
|
+
QuoteCharacter o = (QuoteCharacter) obj;
|
140
|
+
return character == o.character;
|
141
|
+
}
|
142
|
+
}
|
143
|
+
|
144
|
+
public static class EscapeCharacter
|
145
|
+
{
|
146
|
+
private final char character;
|
147
|
+
|
148
|
+
public EscapeCharacter(char character)
|
149
|
+
{
|
150
|
+
this.character = character;
|
151
|
+
}
|
152
|
+
|
153
|
+
public static EscapeCharacter noEscape()
|
154
|
+
{
|
155
|
+
return new EscapeCharacter(CsvTokenizer.NO_ESCAPE);
|
156
|
+
}
|
157
|
+
|
158
|
+
@JsonCreator
|
159
|
+
public static EscapeCharacter ofString(String str)
|
160
|
+
{
|
161
|
+
if (str.length() >= 2) {
|
162
|
+
throw new ConfigException("\"escape\" option accepts only 1 character.");
|
163
|
+
} else if (str.isEmpty()) {
|
164
|
+
Exec.getLogger(CsvParserPlugin.class).warn("Setting '' (empty string) to \"escape\" option is obsoleted. Currently it becomes null automatically but this behavior will be removed. Please set \"escape: null\" explicitly.");
|
165
|
+
return noEscape();
|
166
|
+
} else {
|
167
|
+
return new EscapeCharacter(str.charAt(0));
|
168
|
+
}
|
169
|
+
}
|
170
|
+
|
171
|
+
@JsonIgnore
|
172
|
+
public char getCharacter()
|
173
|
+
{
|
174
|
+
return character;
|
175
|
+
}
|
176
|
+
|
177
|
+
@JsonValue
|
178
|
+
public String getOptionalString()
|
179
|
+
{
|
180
|
+
return new String(new char[] { character });
|
181
|
+
}
|
182
|
+
|
183
|
+
@Override
|
184
|
+
public boolean equals(Object obj)
|
185
|
+
{
|
186
|
+
if (!(obj instanceof EscapeCharacter)) {
|
187
|
+
return false;
|
188
|
+
}
|
189
|
+
EscapeCharacter o = (EscapeCharacter) obj;
|
190
|
+
return character == o.character;
|
191
|
+
}
|
192
|
+
}
|
193
|
+
|
194
|
+
private final Logger log;
|
195
|
+
|
196
|
+
public CsvParserPlugin()
|
197
|
+
{
|
198
|
+
log = Exec.getLogger(CsvParserPlugin.class);
|
199
|
+
}
|
200
|
+
|
201
|
+
@Override
|
202
|
+
public void transaction(ConfigSource config, ParserPlugin.Control control)
|
203
|
+
{
|
204
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
205
|
+
|
206
|
+
// backward compatibility
|
207
|
+
if (task.getHeaderLine().isPresent()) {
|
208
|
+
if (task.getSkipHeaderLines() > 0) {
|
209
|
+
throw new ConfigException("'header_line' option is invalid if 'skip_header_lines' is set.");
|
210
|
+
}
|
211
|
+
if (task.getHeaderLine().get()) {
|
212
|
+
task.setSkipHeaderLines(1);
|
213
|
+
} else {
|
214
|
+
task.setSkipHeaderLines(0);
|
215
|
+
}
|
216
|
+
}
|
217
|
+
|
218
|
+
control.run(task.dump(), task.getSchemaConfig().toSchema());
|
219
|
+
}
|
220
|
+
|
221
|
+
@Override
|
222
|
+
public void run(TaskSource taskSource, final Schema schema,
|
223
|
+
FileInput input, PageOutput output)
|
224
|
+
{
|
225
|
+
PluginTask task = taskSource.loadTask(PluginTask.class);
|
226
|
+
final TimestampParser[] timestampParsers = Timestamps.newTimestampColumnParsers(task, task.getSchemaConfig());
|
227
|
+
LineDecoder lineDecoder = new LineDecoder(input, task);
|
228
|
+
final CsvTokenizer tokenizer = new CsvTokenizer(lineDecoder, task);
|
229
|
+
final String nullStringOrNull = task.getNullString().orNull();
|
230
|
+
final boolean allowOptionalColumns = task.getAllowOptionalColumns();
|
231
|
+
final boolean allowExtraColumns = task.getAllowExtraColumns();
|
232
|
+
int skipHeaderLines = task.getSkipHeaderLines();
|
233
|
+
|
234
|
+
try (final PageBuilder pageBuilder = new PageBuilder(Exec.getBufferAllocator(), schema, output)) {
|
235
|
+
while (tokenizer.nextFile()) {
|
236
|
+
// skip the header lines for each file
|
237
|
+
for (; skipHeaderLines > 0; skipHeaderLines--) {
|
238
|
+
if (lineDecoder.poll() == null) {
|
239
|
+
break;
|
240
|
+
}
|
241
|
+
}
|
242
|
+
|
243
|
+
if (!tokenizer.nextRecord()) {
|
244
|
+
// empty file
|
245
|
+
continue;
|
246
|
+
}
|
247
|
+
|
248
|
+
while (true) {
|
249
|
+
boolean hasNextRecord;
|
250
|
+
|
251
|
+
try {
|
252
|
+
schema.visitColumns(new ColumnVisitor() {
|
253
|
+
public void booleanColumn(Column column)
|
254
|
+
{
|
255
|
+
String v = nextColumn();
|
256
|
+
if (v == null) {
|
257
|
+
pageBuilder.setNull(column);
|
258
|
+
} else {
|
259
|
+
pageBuilder.setBoolean(column, TRUE_STRINGS.contains(v));
|
260
|
+
}
|
261
|
+
}
|
262
|
+
|
263
|
+
public void longColumn(Column column)
|
264
|
+
{
|
265
|
+
String v = nextColumn();
|
266
|
+
if (v == null) {
|
267
|
+
pageBuilder.setNull(column);
|
268
|
+
} else {
|
269
|
+
try {
|
270
|
+
pageBuilder.setLong(column, Long.parseLong(v));
|
271
|
+
} catch (NumberFormatException e) {
|
272
|
+
// TODO support default value
|
273
|
+
throw new CsvRecordValidateException(e);
|
274
|
+
}
|
275
|
+
}
|
276
|
+
}
|
277
|
+
|
278
|
+
public void doubleColumn(Column column)
|
279
|
+
{
|
280
|
+
String v = nextColumn();
|
281
|
+
if (v == null) {
|
282
|
+
pageBuilder.setNull(column);
|
283
|
+
} else {
|
284
|
+
try {
|
285
|
+
pageBuilder.setDouble(column, Double.parseDouble(v));
|
286
|
+
} catch (NumberFormatException e) {
|
287
|
+
// TODO support default value
|
288
|
+
throw new CsvRecordValidateException(e);
|
289
|
+
}
|
290
|
+
}
|
291
|
+
}
|
292
|
+
|
293
|
+
public void stringColumn(Column column)
|
294
|
+
{
|
295
|
+
String v = nextColumn();
|
296
|
+
if (v == null) {
|
297
|
+
pageBuilder.setNull(column);
|
298
|
+
} else {
|
299
|
+
pageBuilder.setString(column, v);
|
300
|
+
}
|
301
|
+
}
|
302
|
+
|
303
|
+
public void timestampColumn(Column column)
|
304
|
+
{
|
305
|
+
String v = nextColumn();
|
306
|
+
if (v == null) {
|
307
|
+
pageBuilder.setNull(column);
|
308
|
+
} else {
|
309
|
+
try {
|
310
|
+
pageBuilder.setTimestamp(column, timestampParsers[column.getIndex()].parse(v));
|
311
|
+
} catch (TimestampParseException e) {
|
312
|
+
// TODO support default value
|
313
|
+
throw new CsvRecordValidateException(e);
|
314
|
+
}
|
315
|
+
}
|
316
|
+
}
|
317
|
+
|
318
|
+
private String nextColumn()
|
319
|
+
{
|
320
|
+
if (allowOptionalColumns && !tokenizer.hasNextColumn()) {
|
321
|
+
//TODO warning
|
322
|
+
return null;
|
323
|
+
}
|
324
|
+
String v = tokenizer.nextColumn();
|
325
|
+
if (!v.isEmpty()) {
|
326
|
+
if (v.equals(nullStringOrNull)) {
|
327
|
+
return null;
|
328
|
+
}
|
329
|
+
return v;
|
330
|
+
} else if (tokenizer.wasQuotedColumn()) {
|
331
|
+
return "";
|
332
|
+
} else {
|
333
|
+
return null;
|
334
|
+
}
|
335
|
+
}
|
336
|
+
});
|
337
|
+
|
338
|
+
try {
|
339
|
+
hasNextRecord = tokenizer.nextRecord();
|
340
|
+
} catch (CsvTokenizer.TooManyColumnsException ex) {
|
341
|
+
if (allowExtraColumns) {
|
342
|
+
String tooManyColumnsLine = tokenizer.skipCurrentLine();
|
343
|
+
// TODO warning
|
344
|
+
hasNextRecord = tokenizer.nextRecord();
|
345
|
+
} else {
|
346
|
+
// this line will be skipped at the following catch section
|
347
|
+
throw ex;
|
348
|
+
}
|
349
|
+
}
|
350
|
+
pageBuilder.addRecord();
|
351
|
+
|
352
|
+
} catch (CsvTokenizer.InvalidFormatException | CsvTokenizer.InvalidValueException | CsvRecordValidateException e) {
|
353
|
+
long lineNumber = tokenizer.getCurrentLineNumber();
|
354
|
+
String skippedLine = tokenizer.skipCurrentLine();
|
355
|
+
log.warn(String.format("Skipped line %d (%s): %s", lineNumber, e.getMessage(), skippedLine));
|
356
|
+
//exec.notice().skippedLine(skippedLine);
|
357
|
+
|
358
|
+
hasNextRecord = tokenizer.nextRecord();
|
359
|
+
}
|
360
|
+
|
361
|
+
if (!hasNextRecord) {
|
362
|
+
break;
|
363
|
+
}
|
364
|
+
}
|
365
|
+
}
|
366
|
+
|
367
|
+
pageBuilder.finish();
|
368
|
+
}
|
369
|
+
}
|
370
|
+
|
371
|
+
static class CsvRecordValidateException
|
372
|
+
extends RuntimeException
|
373
|
+
{
|
374
|
+
CsvRecordValidateException(Throwable cause)
|
375
|
+
{
|
376
|
+
super(cause);
|
377
|
+
}
|
378
|
+
}
|
379
|
+
}
|
@@ -0,0 +1,411 @@
|
|
1
|
+
package org.embulk.standards;
|
2
|
+
|
3
|
+
import com.google.common.base.Preconditions;
|
4
|
+
import java.util.List;
|
5
|
+
import java.util.ArrayList;
|
6
|
+
import java.util.Deque;
|
7
|
+
import java.util.ArrayDeque;
|
8
|
+
import org.embulk.spi.util.LineDecoder;
|
9
|
+
|
10
|
+
public class CsvTokenizer
|
11
|
+
{
|
12
|
+
static enum RecordState
|
13
|
+
{
|
14
|
+
NOT_END, END,
|
15
|
+
}
|
16
|
+
|
17
|
+
static enum ColumnState
|
18
|
+
{
|
19
|
+
BEGIN, VALUE, QUOTED_VALUE, AFTER_QUOTED_VALUE, FIRST_TRIM, LAST_TRIM_OR_VALUE,
|
20
|
+
}
|
21
|
+
|
22
|
+
private static final char END_OF_LINE = '\0';
|
23
|
+
static final char NO_QUOTE = '\0';
|
24
|
+
static final char NO_ESCAPE = '\0';
|
25
|
+
|
26
|
+
private final char delimiter;
|
27
|
+
private final char quote;
|
28
|
+
private final char escape;
|
29
|
+
private final String newline;
|
30
|
+
private final boolean trimIfNotQuoted;
|
31
|
+
private final long maxQuotedSizeLimit;
|
32
|
+
private final String commentLineMarker;
|
33
|
+
private final LineDecoder input;
|
34
|
+
|
35
|
+
private RecordState recordState = RecordState.END; // initial state is end of a record. nextRecord() must be called first
|
36
|
+
private long lineNumber = 0;
|
37
|
+
|
38
|
+
private String line = null;
|
39
|
+
private int linePos = 0;
|
40
|
+
private boolean wasQuotedColumn = false;
|
41
|
+
private List<String> quotedValueLines = new ArrayList<>();
|
42
|
+
private Deque<String> unreadLines = new ArrayDeque<>();
|
43
|
+
|
44
|
+
public CsvTokenizer(LineDecoder input, CsvParserPlugin.PluginTask task)
|
45
|
+
{
|
46
|
+
delimiter = task.getDelimiterChar();
|
47
|
+
quote = task.getQuoteChar().or(CsvParserPlugin.QuoteCharacter.noQuote()).getCharacter();
|
48
|
+
escape = task.getEscapeChar().or(CsvParserPlugin.EscapeCharacter.noEscape()).getCharacter();
|
49
|
+
newline = task.getNewline().getString();
|
50
|
+
trimIfNotQuoted = task.getTrimIfNotQuoted();
|
51
|
+
maxQuotedSizeLimit = task.getMaxQuotedSizeLimit();
|
52
|
+
commentLineMarker = task.getCommentLineMarker().orNull();
|
53
|
+
this.input = input;
|
54
|
+
}
|
55
|
+
|
56
|
+
public long getCurrentLineNumber()
|
57
|
+
{
|
58
|
+
// returns actual line number. Internally, lineNumber starts at 0.
|
59
|
+
return lineNumber + 1;
|
60
|
+
}
|
61
|
+
|
62
|
+
// returns skipped line
|
63
|
+
public String skipCurrentLine()
|
64
|
+
{
|
65
|
+
String skippedLine;
|
66
|
+
if (quotedValueLines.isEmpty()) {
|
67
|
+
skippedLine = line;
|
68
|
+
} else {
|
69
|
+
// recover lines of quoted value
|
70
|
+
skippedLine = quotedValueLines.remove(0); // TODO optimize performance
|
71
|
+
unreadLines.addAll(quotedValueLines);
|
72
|
+
unreadLines.add(line);
|
73
|
+
lineNumber -= quotedValueLines.size();
|
74
|
+
quotedValueLines.clear();
|
75
|
+
}
|
76
|
+
recordState = RecordState.END;
|
77
|
+
return skippedLine;
|
78
|
+
}
|
79
|
+
|
80
|
+
public boolean nextFile()
|
81
|
+
{
|
82
|
+
return input.nextFile();
|
83
|
+
}
|
84
|
+
|
85
|
+
// used by guess-csv
|
86
|
+
public boolean nextRecord()
|
87
|
+
{
|
88
|
+
return nextRecord(true);
|
89
|
+
}
|
90
|
+
|
91
|
+
public boolean nextRecord(boolean skipEmptyLine)
|
92
|
+
{
|
93
|
+
// If at the end of record, read the next line and initialize the state
|
94
|
+
if (recordState != RecordState.END) {
|
95
|
+
throw new TooManyColumnsException("Too many columns");
|
96
|
+
}
|
97
|
+
|
98
|
+
boolean hasNext = nextLine(skipEmptyLine);
|
99
|
+
if (hasNext) {
|
100
|
+
recordState = RecordState.NOT_END;
|
101
|
+
return true;
|
102
|
+
} else {
|
103
|
+
return false;
|
104
|
+
}
|
105
|
+
}
|
106
|
+
|
107
|
+
private boolean nextLine(boolean skipEmptyLine)
|
108
|
+
{
|
109
|
+
while (true) {
|
110
|
+
if (!unreadLines.isEmpty()) {
|
111
|
+
line = unreadLines.removeFirst();
|
112
|
+
} else {
|
113
|
+
line = input.poll();
|
114
|
+
if (line == null) {
|
115
|
+
return false;
|
116
|
+
}
|
117
|
+
}
|
118
|
+
linePos = 0;
|
119
|
+
lineNumber++;
|
120
|
+
|
121
|
+
boolean skip = skipEmptyLine && (
|
122
|
+
line.isEmpty() ||
|
123
|
+
(commentLineMarker != null && line.startsWith(commentLineMarker)));
|
124
|
+
if (!skip) {
|
125
|
+
return true;
|
126
|
+
}
|
127
|
+
}
|
128
|
+
}
|
129
|
+
|
130
|
+
public boolean hasNextColumn()
|
131
|
+
{
|
132
|
+
return recordState == RecordState.NOT_END;
|
133
|
+
}
|
134
|
+
|
135
|
+
public String nextColumn()
|
136
|
+
{
|
137
|
+
if (!hasNextColumn()) {
|
138
|
+
throw new TooFewColumnsException("Too few columns");
|
139
|
+
}
|
140
|
+
|
141
|
+
// reset last state
|
142
|
+
wasQuotedColumn = false;
|
143
|
+
quotedValueLines.clear();
|
144
|
+
|
145
|
+
// local state
|
146
|
+
int valueStartPos = linePos;
|
147
|
+
int valueEndPos = 0; // initialized by VALUE state and used by LAST_TRIM_OR_VALUE and
|
148
|
+
StringBuilder quotedValue = null; // initial by VALUE or FIRST_TRIM state and used by QUOTED_VALUE state
|
149
|
+
ColumnState columnState = ColumnState.BEGIN;
|
150
|
+
|
151
|
+
while (true) {
|
152
|
+
final char c = nextChar();
|
153
|
+
|
154
|
+
switch (columnState) {
|
155
|
+
case BEGIN:
|
156
|
+
// TODO optimization: state is BEGIN only at the first character of a column.
|
157
|
+
// this block can be out of the looop.
|
158
|
+
if (isDelimiter(c)) {
|
159
|
+
// empty value
|
160
|
+
return "";
|
161
|
+
|
162
|
+
} else if (isEndOfLine(c)) {
|
163
|
+
// empty value
|
164
|
+
recordState = RecordState.END;
|
165
|
+
return "";
|
166
|
+
|
167
|
+
} else if (isSpace(c) && trimIfNotQuoted) {
|
168
|
+
columnState = ColumnState.FIRST_TRIM;
|
169
|
+
|
170
|
+
} else if (isQuote(c)) {
|
171
|
+
valueStartPos = linePos; // == 1
|
172
|
+
wasQuotedColumn = true;
|
173
|
+
quotedValue = new StringBuilder();
|
174
|
+
columnState = ColumnState.QUOTED_VALUE;
|
175
|
+
|
176
|
+
} else {
|
177
|
+
columnState = ColumnState.VALUE;
|
178
|
+
}
|
179
|
+
break;
|
180
|
+
|
181
|
+
case FIRST_TRIM:
|
182
|
+
if (isDelimiter(c)) {
|
183
|
+
// empty value
|
184
|
+
return "";
|
185
|
+
|
186
|
+
} else if (isEndOfLine(c)) {
|
187
|
+
// empty value
|
188
|
+
recordState = RecordState.END;
|
189
|
+
return "";
|
190
|
+
|
191
|
+
} else if (isQuote(c)) {
|
192
|
+
// column has heading spaces and quoted. TODO should this be rejected?
|
193
|
+
valueStartPos = linePos;
|
194
|
+
wasQuotedColumn = true;
|
195
|
+
quotedValue = new StringBuilder();
|
196
|
+
columnState = ColumnState.QUOTED_VALUE;
|
197
|
+
|
198
|
+
} else if (isSpace(c)) {
|
199
|
+
// skip this character
|
200
|
+
|
201
|
+
} else {
|
202
|
+
valueStartPos = linePos - 1;
|
203
|
+
columnState = ColumnState.VALUE;
|
204
|
+
}
|
205
|
+
break;
|
206
|
+
|
207
|
+
case VALUE:
|
208
|
+
if (isDelimiter(c)) {
|
209
|
+
return line.substring(valueStartPos, linePos - 1);
|
210
|
+
|
211
|
+
} else if (isEndOfLine(c)) {
|
212
|
+
recordState = RecordState.END;
|
213
|
+
return line.substring(valueStartPos, linePos);
|
214
|
+
|
215
|
+
} else if (isSpace(c) && trimIfNotQuoted) {
|
216
|
+
valueEndPos = linePos - 1; // this is possibly end of value
|
217
|
+
columnState = ColumnState.LAST_TRIM_OR_VALUE;
|
218
|
+
|
219
|
+
// TODO not implemented yet foo""bar""baz -> [foo, bar, baz].append
|
220
|
+
//} else if (isQuote(c)) {
|
221
|
+
// // In RFC4180, If fields are not enclosed with double quotes, then
|
222
|
+
// // double quotes may not appear inside the fields. But they are often
|
223
|
+
// // included in the fields. We should care about them later.
|
224
|
+
|
225
|
+
} else {
|
226
|
+
// keep VALUE state
|
227
|
+
}
|
228
|
+
break;
|
229
|
+
|
230
|
+
case LAST_TRIM_OR_VALUE:
|
231
|
+
if (isDelimiter(c)) {
|
232
|
+
return line.substring(valueStartPos, valueEndPos);
|
233
|
+
|
234
|
+
} else if (isEndOfLine(c)) {
|
235
|
+
recordState = RecordState.END;
|
236
|
+
return line.substring(valueStartPos, valueEndPos);
|
237
|
+
|
238
|
+
} else if (isSpace(c)) {
|
239
|
+
// keep LAST_TRIM_OR_VALUE state
|
240
|
+
|
241
|
+
} else {
|
242
|
+
// this spaces are not trailing spaces. go back to VALUE state
|
243
|
+
columnState = ColumnState.BEGIN;
|
244
|
+
}
|
245
|
+
break;
|
246
|
+
|
247
|
+
case QUOTED_VALUE:
|
248
|
+
if (isEndOfLine(c)) {
|
249
|
+
// multi-line quoted value
|
250
|
+
quotedValue.append(line.substring(valueStartPos, linePos));
|
251
|
+
quotedValue.append(newline);
|
252
|
+
quotedValueLines.add(line);
|
253
|
+
if (!nextLine(false)) {
|
254
|
+
throw new InvalidValueException("Unexpected end of line during parsing a quoted value");
|
255
|
+
}
|
256
|
+
valueStartPos = 0;
|
257
|
+
|
258
|
+
} else if (isQuote(c)) {
|
259
|
+
char next = peekNextChar();
|
260
|
+
if (isQuote(next)) { // escaped quote
|
261
|
+
quotedValue.append(line.substring(valueStartPos, linePos));
|
262
|
+
valueStartPos = ++linePos;
|
263
|
+
} else {
|
264
|
+
quotedValue.append(line.substring(valueStartPos, linePos - 1));
|
265
|
+
columnState = ColumnState.AFTER_QUOTED_VALUE;
|
266
|
+
}
|
267
|
+
|
268
|
+
} else if (isEscape(c)) { // isQuote must be checked first in case of quote == escape
|
269
|
+
// In RFC 4180, CSV's escape char is '\"'. But '\\' is often used.
|
270
|
+
char next = peekNextChar();
|
271
|
+
if (isEndOfLine(c)) {
|
272
|
+
// escape end of line. TODO assuming multi-line quoted value without newline?
|
273
|
+
quotedValue.append(line.substring(valueStartPos, linePos));
|
274
|
+
quotedValueLines.add(line);
|
275
|
+
if (!nextLine(false)) {
|
276
|
+
throw new InvalidValueException("Unexpected end of line during parsing a quoted value");
|
277
|
+
}
|
278
|
+
valueStartPos = 0;
|
279
|
+
} else if (isQuote(next) || isEscape(next)) { // escaped quote
|
280
|
+
quotedValue.append(line.substring(valueStartPos, linePos - 1));
|
281
|
+
quotedValue.append(next);
|
282
|
+
valueStartPos = ++linePos;
|
283
|
+
}
|
284
|
+
|
285
|
+
} else {
|
286
|
+
if ((linePos - valueStartPos) + quotedValue.length() > maxQuotedSizeLimit) {
|
287
|
+
throw new QuotedSizeLimitExceededException("The size of the quoted value exceeds the limit size ("+maxQuotedSizeLimit+")");
|
288
|
+
}
|
289
|
+
// keep QUOTED_VALUE state
|
290
|
+
}
|
291
|
+
break;
|
292
|
+
|
293
|
+
case AFTER_QUOTED_VALUE:
|
294
|
+
if (isDelimiter(c)) {
|
295
|
+
return quotedValue.toString();
|
296
|
+
|
297
|
+
} else if (isEndOfLine(c)) {
|
298
|
+
recordState = RecordState.END;
|
299
|
+
return quotedValue.toString();
|
300
|
+
|
301
|
+
} else if (isSpace(c)) {
|
302
|
+
// column has trailing spaces and quoted. TODO should this be rejected?
|
303
|
+
|
304
|
+
} else {
|
305
|
+
throw new InvalidValueException(String.format("Unexpected extra character (%c) after quoted value in %s", c, line));
|
306
|
+
}
|
307
|
+
break;
|
308
|
+
|
309
|
+
default:
|
310
|
+
assert false;
|
311
|
+
}
|
312
|
+
}
|
313
|
+
}
|
314
|
+
|
315
|
+
public boolean wasQuotedColumn()
|
316
|
+
{
|
317
|
+
return wasQuotedColumn;
|
318
|
+
}
|
319
|
+
|
320
|
+
private char nextChar()
|
321
|
+
{
|
322
|
+
Preconditions.checkState(line != null, "nextColumn is called after end of file");
|
323
|
+
|
324
|
+
if (linePos >= line.length()) {
|
325
|
+
return END_OF_LINE;
|
326
|
+
} else {
|
327
|
+
return line.charAt(linePos++);
|
328
|
+
}
|
329
|
+
}
|
330
|
+
|
331
|
+
private char peekNextChar()
|
332
|
+
{
|
333
|
+
Preconditions.checkState(line != null, "peekNextChar is called after end of file");
|
334
|
+
|
335
|
+
if (linePos >= line.length()) {
|
336
|
+
return END_OF_LINE;
|
337
|
+
} else {
|
338
|
+
return line.charAt(linePos);
|
339
|
+
}
|
340
|
+
}
|
341
|
+
|
342
|
+
private boolean isSpace(char c)
|
343
|
+
{
|
344
|
+
return c == ' ';
|
345
|
+
}
|
346
|
+
|
347
|
+
private boolean isDelimiter(char c)
|
348
|
+
{
|
349
|
+
return c == delimiter;
|
350
|
+
}
|
351
|
+
|
352
|
+
private boolean isEndOfLine(char c)
|
353
|
+
{
|
354
|
+
return c == END_OF_LINE;
|
355
|
+
}
|
356
|
+
|
357
|
+
private boolean isQuote(char c)
|
358
|
+
{
|
359
|
+
return quote != NO_QUOTE && c == quote;
|
360
|
+
}
|
361
|
+
|
362
|
+
private boolean isEscape(char c)
|
363
|
+
{
|
364
|
+
return escape != NO_ESCAPE && c == escape;
|
365
|
+
}
|
366
|
+
|
367
|
+
public static class InvalidFormatException
|
368
|
+
extends RuntimeException
|
369
|
+
{
|
370
|
+
public InvalidFormatException(String message)
|
371
|
+
{
|
372
|
+
super(message);
|
373
|
+
}
|
374
|
+
}
|
375
|
+
|
376
|
+
public static class InvalidValueException
|
377
|
+
extends RuntimeException
|
378
|
+
{
|
379
|
+
public InvalidValueException(String message)
|
380
|
+
{
|
381
|
+
super(message);
|
382
|
+
}
|
383
|
+
}
|
384
|
+
|
385
|
+
public static class QuotedSizeLimitExceededException
|
386
|
+
extends InvalidValueException
|
387
|
+
{
|
388
|
+
public QuotedSizeLimitExceededException(String message)
|
389
|
+
{
|
390
|
+
super(message);
|
391
|
+
}
|
392
|
+
}
|
393
|
+
|
394
|
+
public class TooManyColumnsException
|
395
|
+
extends InvalidFormatException
|
396
|
+
{
|
397
|
+
public TooManyColumnsException(String message)
|
398
|
+
{
|
399
|
+
super(message);
|
400
|
+
}
|
401
|
+
}
|
402
|
+
|
403
|
+
public class TooFewColumnsException
|
404
|
+
extends InvalidFormatException
|
405
|
+
{
|
406
|
+
public TooFewColumnsException(String message)
|
407
|
+
{
|
408
|
+
super(message);
|
409
|
+
}
|
410
|
+
}
|
411
|
+
}
|