Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Get ready for v0.11 and v1.0 #8

Merged
merged 9 commits into from
May 9, 2021
Merged
Show file tree
Hide file tree
Changes from 8 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
112 changes: 55 additions & 57 deletions build.gradle
Original file line number Diff line number Diff line change
@@ -1,36 +1,60 @@
plugins {
id "com.jfrog.bintray" version "1.1"
id "com.github.jruby-gradle.base" version "0.1.5"
id "java"
id "checkstyle"
id "maven-publish"
id "org.embulk.embulk-plugins" version "0.4.2"
}
import com.github.jrubygradle.JRubyExec
repositories {
mavenCentral()
jcenter()
}
configurations {
provided

embulkPlugin {
mainClass = "org.embulk.filter.to_json.ToJsonFilterPlugin"
category = "filter"
type = "to_json"
}

group = "pro.civitaspo"
version = "0.0.5"
description = "To Json"

sourceCompatibility = 1.7
targetCompatibility = 1.7
sourceCompatibility = 1.8
targetCompatibility = 1.8

dependencies {
compile "org.embulk:embulk-core:0.8.1"
provided "org.embulk:embulk-core:0.8.1"
// compile "YOUR_JAR_DEPENDENCY_GROUP:YOUR_JAR_DEPENDENCY_MODULE:YOUR_JAR_DEPENDENCY_VERSION"
testCompile "junit:junit:4.+"
}
compileOnly "org.embulk:embulk-api:0.10.31"
compileOnly "org.embulk:embulk-spi:0.10.31"
compile("org.embulk:embulk-util-config:0.3.0") {
// They conflict with embulk-core. They are once excluded here,
// and added explicitly with versions exactly the same with embulk-core:0.10.19.
exclude group: "com.fasterxml.jackson.core", module: "jackson-annotations"
exclude group: "com.fasterxml.jackson.core", module: "jackson-core"
exclude group: "com.fasterxml.jackson.core", module: "jackson-databind"
exclude group: "com.fasterxml.jackson.datatype", module: "jackson-datatype-jdk8"
exclude group: "javax.validation", module: "validation-api"
}
compile "org.embulk:embulk-util-timestamp:0.2.1"
compile('org.embulk:embulk-util-json:0.1.0') {
exclude group: "org.msgpack", module: "msgpack-core"
}
// They are once excluded from transitive dependencies of other dependencies,
// and added explicitly with versions exactly the same with embulk-core:0.10.19.
compile "com.fasterxml.jackson.core:jackson-annotations:2.6.7"
compile "com.fasterxml.jackson.core:jackson-core:2.6.7"
compile "com.fasterxml.jackson.core:jackson-databind:2.6.7"
compile "com.fasterxml.jackson.datatype:jackson-datatype-jdk8:2.6.7"
compile "javax.validation:validation-api:1.1.0.Final"
//compile "joda-time:joda-time:2.9.2"


task classpath(type: Copy, dependsOn: ["jar"]) {
doFirst { file("classpath").deleteDir() }
from (configurations.runtime - configurations.provided + files(jar.archivePath))
into "classpath"
testCompile "org.embulk:embulk-api:0.10.31"
testCompile "org.embulk:embulk-spi:0.10.31"
testCompile "org.embulk:embulk-core:0.10.31"
testCompile "org.embulk:embulk-core:0.10.31:tests"
testCompile "org.embulk:embulk-deps:0.10.31"
// compile "YOUR_JAR_DEPENDENCY_GROUP:YOUR_JAR_DEPENDENCY_MODULE:YOUR_JAR_DEPENDENCY_VERSION"
testCompile "junit:junit:4.13.2"
}
clean { delete "classpath" }

checkstyle {
configFile = file("${project.rootDir}/config/checkstyle/checkstyle.xml")
Expand All @@ -49,46 +73,20 @@ task checkstyle(type: Checkstyle) {
source = sourceSets.main.allJava + sourceSets.test.allJava
}

task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
script "${project.name}.gemspec"
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
gem {
from("LICENSE.txt") // Optional -- if you need other files in the gem.
authors = [ "Civitaspo" ]
email = [ "civitaspo@gmail.com" ]
// "description" of the gem is copied from "description" of your Gradle project.
summary = "To Json filter plugin for Embulk"
homepage = "https://github.com/civitaspo/embulk-filter-to_json"
licenses = [ "MIT" ]
//metadata = []
}

task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "push"
script "pkg/${project.name}-${project.version}.gem"
}

task "package"(dependsOn: ["gemspec", "classpath"]) << {
println "> Build succeeded."
println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
gemPush {
host = "https://rubygems.org"
}

task gemspec {
ext.gemspecFile = file("${project.name}.gemspec")
inputs.file "build.gradle"
outputs.file gemspecFile
doLast { gemspecFile.write($/
Gem::Specification.new do |spec|
spec.name = "${project.name}"
spec.version = "${project.version}"
spec.authors = ["Civitaspo"]
spec.summary = %[To Json filter plugin for Embulk]
spec.description = %[To Json]
spec.email = ["civitaspo@gmail.com"]
spec.licenses = ["MIT"]
spec.homepage = "https://github.com/civitaspo/embulk-filter-to_json"

spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
spec.test_files = spec.files.grep(%r"^(test|spec)/")
spec.require_paths = ["lib"]

#spec.add_dependency 'YOUR_GEM_DEPENDENCY', ['~> YOUR_GEM_DEPENDENCY_VERSION']
spec.add_development_dependency 'bundler', ['~> 1.0']
spec.add_development_dependency 'rake', ['>= 10.0']
end
/$)
}
tasks.withType(JavaCompile) {
options.compilerArgs << "-Xlint:deprecation" << "-Xlint:unchecked"
}
clean { delete "${project.name}.gemspec" }
12 changes: 12 additions & 0 deletions gradle/dependency-locks/embulkPluginRuntime.lockfile
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
# This is a Gradle generated file for dependency locking.
# Manual edits can break the build and are not advised.
# This file is expected to be part of source control.
com.fasterxml.jackson.core:jackson-annotations:2.6.7
com.fasterxml.jackson.core:jackson-core:2.6.7
com.fasterxml.jackson.core:jackson-databind:2.6.7
com.fasterxml.jackson.datatype:jackson-datatype-jdk8:2.6.7
javax.validation:validation-api:1.1.0.Final
org.embulk:embulk-util-config:0.3.0
org.embulk:embulk-util-json:0.1.0
org.embulk:embulk-util-rubytime:0.3.2
org.embulk:embulk-util-timestamp:0.2.1
4 changes: 2 additions & 2 deletions gradle/wrapper/gradle-wrapper.properties
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
#Wed Jan 13 12:41:02 JST 2016
#Mon May 03 22:48:55 JST 2021
distributionBase=GRADLE_USER_HOME
distributionPath=wrapper/dists
zipStoreBase=GRADLE_USER_HOME
zipStorePath=wrapper/dists
distributionUrl=https\://services.gradle.org/distributions/gradle-2.10-bin.zip
distributionUrl=https\://services.gradle.org/distributions/gradle-6.8.3-bin.zip
hiroyuki-sato marked this conversation as resolved.
Show resolved Hide resolved
Original file line number Diff line number Diff line change
Expand Up @@ -2,18 +2,17 @@

import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.google.common.collect.Lists;
import com.google.common.collect.Maps;
import org.embulk.config.ConfigException;
import org.embulk.spi.Column;
import org.embulk.spi.ColumnVisitor;
import org.embulk.spi.PageBuilder;
import org.embulk.spi.PageReader;
import org.embulk.spi.json.JsonParser;
import org.embulk.spi.time.TimestampFormatter;
import org.embulk.util.json.JsonParser;
import org.embulk.util.timestamp.TimestampFormatter;
import org.embulk.spi.type.Types;

import java.io.IOException;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

Expand Down Expand Up @@ -107,13 +106,13 @@ private void setAsJson(int index, String json)
private final PageReader pageReader;
private final ColumnSetter columnSetter;
private final TimestampFormatter timestampFormatter;
private List<String> skipColumnsIfNull = Lists.newArrayList();
private final List<String> skipColumnsIfNull;
private boolean skipRecordFlag = false;

ColumnVisitorToJsonImpl(PageReader pageReader, PageBuilder pageBuilder,
Column outputColumn, TimestampFormatter timestampFormatter, List<String> skipColumnsIfNull)
{
this.map = Maps.newHashMap();
this.map = new HashMap<>();
this.pageReader = pageReader;
this.columnSetter = new ColumnSetter(pageBuilder, outputColumn);
this.timestampFormatter = timestampFormatter;
Expand Down Expand Up @@ -172,7 +171,8 @@ public void timestampColumn(Column column)
putNull(column);
return;
}
String value = timestampFormatter.format(pageReader.getTimestamp(column));
// TODO: Use pageReader.getTimestampInstant after dropping v0.9
String value = timestampFormatter.format(pageReader.getTimestamp(column).getInstant());
map.put(column.getName(), value);
}

Expand Down
63 changes: 34 additions & 29 deletions src/main/java/org/embulk/filter/to_json/ToJsonFilterPlugin.java
Original file line number Diff line number Diff line change
@@ -1,39 +1,47 @@
package org.embulk.filter.to_json;

import com.google.common.base.Optional;
import com.google.common.collect.ImmutableList;
import org.embulk.config.Config;
import org.embulk.config.ConfigDefault;
import java.util.Arrays;
import java.util.Collections;
import java.util.Optional;
import org.embulk.util.config.Config;
import org.embulk.util.config.ConfigDefault;
import org.embulk.config.ConfigException;
import org.embulk.config.ConfigInject;
import org.embulk.config.ConfigSource;
import org.embulk.config.Task;
import org.embulk.util.config.ConfigMapper;
import org.embulk.util.config.ConfigMapperFactory;
import org.embulk.util.config.Task;
import org.embulk.config.TaskSource;
import org.embulk.spi.Column;
import org.embulk.spi.ColumnConfig;
import org.embulk.util.config.TaskMapper;
import org.embulk.util.config.units.ColumnConfig;
import org.embulk.spi.Exec;
import org.embulk.spi.FilterPlugin;
import org.embulk.spi.Page;
import org.embulk.spi.PageBuilder;
import org.embulk.spi.PageOutput;
import org.embulk.spi.PageReader;
import org.embulk.spi.Schema;
import org.embulk.spi.time.TimestampFormatter;
import org.embulk.util.timestamp.TimestampFormatter;
import org.embulk.spi.type.Type;
import org.embulk.spi.type.Types;
import org.joda.time.DateTimeZone;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.util.List;

public class ToJsonFilterPlugin
implements FilterPlugin
{
private static final Logger logger = Exec.getLogger(ToJsonFilterPlugin.class);
private static final Logger logger = LoggerFactory.getLogger(ToJsonFilterPlugin.class);
private static final String DEFAULT_COLUMN_NAME = "json_payload";
private static final Type DEFAULT_COLUMN_TYPE = Types.STRING;
private static final ConfigSource DEFAULT_COLUMN_OPTION = Exec.newConfigSource();
private static final int JSON_COLUMN_INDEX = 0;
private static final ConfigMapperFactory CONFIG_MAPPER_FACTORY = ConfigMapperFactory
.builder()
.addDefaultModules()
.build();
private static final ConfigMapper CONFIG_MAPPER = CONFIG_MAPPER_FACTORY.createConfigMapper();
private static final ConfigSource DEFAULT_COLUMN_OPTION = CONFIG_MAPPER_FACTORY.newConfigSource();

public interface PluginTask
extends Task
Expand Down Expand Up @@ -76,7 +84,7 @@ private ColumnConfig buildJsonColumnConfig(PluginTask task)
JsonColumn jsonColumn = task.getJsonColumn().get();
Optional<String> name = jsonColumn.getName();
Optional<Type> type = jsonColumn.getType();
return newJsonColumnConfig(name.or(DEFAULT_COLUMN_NAME), type.or(DEFAULT_COLUMN_TYPE), DEFAULT_COLUMN_OPTION);
return newJsonColumnConfig(name.orElse(DEFAULT_COLUMN_NAME), type.orElse(DEFAULT_COLUMN_TYPE), DEFAULT_COLUMN_OPTION);
}

private ColumnConfig newJsonColumnConfig()
Expand All @@ -96,7 +104,7 @@ private ColumnConfig newJsonColumnConfig(String name, Type type, ConfigSource op
public void transaction(ConfigSource config, Schema inputSchema,
FilterPlugin.Control control)
{
PluginTask task = config.loadConfig(PluginTask.class);
final PluginTask task = CONFIG_MAPPER.map(config, PluginTask.class);

for (String columnName : task.getColumnNamesSkipIfNull()) {
logger.debug("Skip a record if `{}` is null", columnName);
Expand All @@ -106,37 +114,34 @@ public void transaction(ConfigSource config, Schema inputSchema,
for (Column column : outputSchema.getColumns()) {
logger.debug("OutputSchema: {}", column);
}

// TODO: Use task.toTaskSource() after dropping v0.9
control.run(task.dump(), outputSchema);
}

private Schema buildOutputSchema(PluginTask task)
{
final ColumnConfig jsonColumnConfig = buildJsonColumnConfig(task);

ImmutableList.Builder<Column> builder = ImmutableList.builder();
Column jsonColumn = new Column(JSON_COLUMN_INDEX, jsonColumnConfig.getName(), jsonColumnConfig.getType());
builder.add(jsonColumn);
List<Column> columns = Collections.unmodifiableList(Arrays.asList(jsonColumn));

return new Schema(builder.build());
return new Schema(columns);
}

private static interface FormatterIntlTask extends Task, TimestampFormatter.Task {}
private static interface FormatterIntlColumnOption extends Task, TimestampFormatter.TimestampColumnOption {}

@Override
public PageOutput open(TaskSource taskSource, final Schema inputSchema,
final Schema outputSchema, final PageOutput output)
{
final PluginTask task = taskSource.loadTask(PluginTask.class);
final DateTimeZone timezone = DateTimeZone.forID(task.getDefaultTimezone());
// TODO: Switch to a newer TimestampFormatter constructor after a reasonable interval.
// Traditional constructor is used here for compatibility.
final ConfigSource configSource = Exec.newConfigSource();
configSource.set("format", task.getDefaultFormat());
configSource.set("timezone", timezone);
final TimestampFormatter timestampFormatter = new TimestampFormatter(
Exec.newConfigSource().loadConfig(FormatterIntlTask.class),
Optional.fromNullable(configSource.loadConfig(FormatterIntlColumnOption.class)));
final TaskMapper taskMapper = CONFIG_MAPPER_FACTORY.createTaskMapper();
final PluginTask task = taskMapper.map(taskSource, PluginTask.class);
final String timezone = task.getDefaultTimezone();
final String format = task.getDefaultFormat();

TimestampFormatter timestampFormatter = TimestampFormatter.builder(format, true)
.setDefaultDateFromString("1970-01-01")
.setDefaultZoneFromString(timezone)
.build();
final List<String> columnNamesSkipIfNull = task.getColumnNamesSkipIfNull();

return new PageOutput()
Expand Down