dadoonet · toto1310 · Sep 27, 2019 · Sep 30, 2019 · Sep 30, 2019 · Oct 1, 2019
diff --git a/distribution/es6/pom.xml b/distribution/es6/pom.xml
@@ -12,6 +12,10 @@
     <artifactId>fscrawler-es6</artifactId>
     <name>FSCrawler ZIP Distribution for Elasticsearch 6.x</name>
 
+    <properties>
+        <module.name>es6</module.name>
+    </properties>
+
     <dependencies>
         <dependency>
             <groupId>fr.pilato.elasticsearch.crawler</groupId>
@@ -25,6 +29,10 @@
                 <groupId>org.apache.maven.plugins</groupId>
                 <artifactId>maven-assembly-plugin</artifactId>
             </plugin>
+            <plugin>
+                <groupId>io.fabric8</groupId>
+                <artifactId>docker-maven-plugin</artifactId>
+            </plugin>
         </plugins>
     </build>
 

diff --git a/distribution/es7/pom.xml b/distribution/es7/pom.xml
@@ -12,6 +12,13 @@
     <artifactId>fscrawler-es7</artifactId>
     <name>FSCrawler ZIP Distribution for Elasticsearch 7.x</name>
 
+    <properties>
+        <module.name>es7</module.name>
+
+        <docker.eng.tags.0>latest</docker.eng.tags.0>
+        <docker.eng.tags.1>${project.version}</docker.eng.tags.1>
+    </properties>
+
     <dependencies>
         <dependency>
             <groupId>fr.pilato.elasticsearch.crawler</groupId>
@@ -25,6 +32,10 @@
                 <groupId>org.apache.maven.plugins</groupId>
                 <artifactId>maven-assembly-plugin</artifactId>
             </plugin>
+            <plugin>
+                <groupId>io.fabric8</groupId>
+                <artifactId>docker-maven-plugin</artifactId>
+            </plugin>
         </plugins>
     </build>
 

diff --git a/distribution/pom.xml b/distribution/pom.xml
@@ -18,6 +18,54 @@
         <module>es6</module>
     </modules>
 
+    <properties>
+        <tesseract.version>3.04.*</tesseract.version>
+
+        <!-- Global configuration parameters for docker -->
+        <!-- By default, build docker images on each modules. -->
+        <docker.skip>${env.DOCKER_SKIP}</docker.skip>
+        <docker.verbose>build</docker.verbose>
+        <docker.username>dadoonet</docker.username>
+        <!-- The following assumes that each submodule will be overwritten. -->
+        <module.name>es7</module.name>
+
+        <!-- Docker Image Definitions -->
+        <!-- no install tesseract-ocr and data files for any languages -->
+        <docker.nolang.alias>${project.artifactId}-nolang</docker.nolang.alias>
+        <docker.nolang.name>${docker.username}/fscrawler:${project.version}-${module.name}-nolang</docker.nolang.name>
+        <docker.nolang.cacheFrom>${docker.nolang.name}</docker.nolang.cacheFrom>
+        <docker.nolang.dockerFile>${project.basedir}/../src/main/docker/Dockerfile</docker.nolang.dockerFile>
+        <docker.nolang.assembly.descriptor>${project.basedir}/../src/main/assembly/assembly.xml</docker.nolang.assembly.descriptor>
+        <docker.nolang.assembly.mode>tgz</docker.nolang.assembly.mode>
+
+        <!-- install tesseract-ocr and data files for English -->
+        <docker.eng.alias>${project.artifactId}-eng</docker.eng.alias>
+        <docker.eng.name>${docker.username}/fscrawler:${project.version}-${module.name}-eng</docker.eng.name>
+        <docker.eng.cacheFrom>${docker.eng.name}</docker.eng.cacheFrom>
+        <docker.eng.dockerFile>${docker.nolang.dockerFile}</docker.eng.dockerFile>
+        <docker.eng.assembly.descriptor>${docker.nolang.assembly.descriptor}</docker.eng.assembly.descriptor>
+        <docker.eng.assembly.mode>${docker.nolang.assembly.mode}</docker.eng.assembly.mode>
+        <docker.eng.args.langsPkg>tesseract-ocr=${tesseract.version} tesseract-ocr-eng=${tesseract.version}</docker.eng.args.langsPkg>
+
+        <!-- install tesseract-ocr and data files for French -->
+        <docker.fra.alias>${project.artifactId}-fra</docker.fra.alias>
+        <docker.fra.name>${docker.username}/fscrawler:${project.version}-${module.name}-fra</docker.fra.name>
+        <docker.fra.cacheFrom>${docker.fra.name}</docker.fra.cacheFrom>
+        <docker.fra.dockerFile>${docker.nolang.dockerFile}</docker.fra.dockerFile>
+        <docker.fra.assembly.descriptor>${docker.nolang.assembly.descriptor}</docker.fra.assembly.descriptor>
+        <docker.fra.assembly.mode>${docker.nolang.assembly.mode}</docker.fra.assembly.mode>
+        <docker.fra.args.langsPkg>tesseract-ocr=${tesseract.version} tesseract-ocr-fra=${tesseract.version}</docker.fra.args.langsPkg>
+
+        <!-- install tesseract-ocr and  data files for Japanese -->
+        <docker.jpn.alias>${project.artifactId}-jpn</docker.jpn.alias>
+        <docker.jpn.name>${docker.username}/fscrawler:${project.version}-${module.name}-jpn</docker.jpn.name>
+        <docker.jpn.cacheFrom>${docker.jpn.name}</docker.jpn.cacheFrom>
+        <docker.jpn.dockerFile>${docker.nolang.dockerFile}</docker.jpn.dockerFile>
+        <docker.jpn.assembly.descriptor>${docker.nolang.assembly.descriptor}</docker.jpn.assembly.descriptor>
+        <docker.jpn.assembly.mode>${docker.nolang.assembly.mode}</docker.jpn.assembly.mode>
+        <docker.jpn.args.langsPkg>tesseract-ocr=${tesseract.version} tesseract-ocr-jpn=${tesseract.version}</docker.jpn.args.langsPkg>
+    </properties>
+
     <dependencies>
         <dependency>
             <groupId>fr.pilato.elasticsearch.crawler</groupId>
@@ -109,6 +157,72 @@
                         </execution>
                     </executions>
                 </plugin>
+                <!-- Generate the docker images (run during package step) -->
+                <plugin>
+                    <groupId>io.fabric8</groupId>
+                    <artifactId>docker-maven-plugin</artifactId>
+                    <configuration>
+                        <authConfig>
+                            <push>
+                                <username>${docker.push.username}</username>
+                                <password>${docker.push.password}</password>
+                            </push>
+                        </authConfig>
+                        <!-- Disable configuration for IT -->
+                        <images combine.self="override">
+                            <image>
+                                <external>
+                                    <type>properties</type>
+                                    <prefix>docker.nolang</prefix>
+                                </external>
+                            </image>
+                            <image>
+                                <external>
+                                    <type>properties</type>
+                                    <prefix>docker.eng</prefix>
+                                </external>
+                            </image>
+                            <image>
+                                <external>
+                                    <type>properties</type>
+                                    <prefix>docker.fra</prefix>
+                                </external>
+                            </image>
+                            <image>
+                                <external>
+                                    <type>properties</type>
+                                    <prefix>docker.jpn</prefix>
+                                </external>
+                            </image>
+                        </images>
+                    </configuration>
+                    <executions>
+                        <execution>
+                            <id>docker-build</id>
+                            <phase>package</phase>
+                            <goals>
+                                <goal>build</goal>
+                            </goals>
+                        </execution>
+                        <execution>
+                            <id>docker-push</id>
+                            <phase>deploy</phase>
+                            <goals>
+                                <goal>push</goal>
+                            </goals>
+                        </execution>
+                        <execution>
+                            <!-- There is no integration test so we can skip that execution -->
+                            <id>start-elasticsearch</id>
+                            <phase>none</phase>
+                        </execution>
+                        <execution>
+                            <!-- There is no integration test so we can skip that execution -->
+                            <id>stop-elasticsearch</id>
+                            <phase>none</phase>
+                        </execution>
+                    </executions>
+                </plugin>
             </plugins>
         </pluginManagement>
     </build>

diff --git a/distribution/src/main/docker/Dockerfile b/distribution/src/main/docker/Dockerfile
@@ -0,0 +1,16 @@
+FROM openjdk:15.0.1
+
+ARG langsPkg
+RUN set -ex \
+    && apt update \
+    && apt install -y --no-install-recommends \
+        "gettext-base=0.19.*" \
+        ${langsPkg} \
+    && apt clean \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY maven /usr/share/fscrawler
+RUN set -ex \
+    && ln -sn /usr/share/fscrawler/bin/fscrawler /usr/bin/
+
+WORKDIR /usr/share/fscrawler
diff --git a/docs/source/dev/build.rst b/docs/source/dev/build.rst
@@ -229,3 +229,24 @@ If you want to skip the check, you can run with ``-Dossindex.fail=false``::
 
         mvn clean install -Dossindex.fail=false
 
+DockerHub publication
+^^^^^^^^^^^^^^^^^^^^^
+
+To publish the latest build to `DockerHub <https://hub.docker.com/r/dadoonet/fscrawler/>`_ you can manually
+call ``docker:push`` maven task and provide credentials ``docker.push.username`` and ``docker.push.password``::
+
+        mvn -f distribution/pom.xml docker:push \
+            -Ddocker.push.username=yourdockerhubaccount \
+            -Ddocker.push.password=yourverysecuredpassword
+
+Otherwise, if you call the maven ``deploy`` phase, it will be done automatically.
+Note that it will still require that you provide the credentials ``docker.push.username`` and ``docker.push.password``::
+
+        mvn deploy \
+            -Ddocker.push.username=yourdockerhubaccount \
+            -Ddocker.push.password=yourverysecuredpassword
+
+You can also provide the settings as environment variables:
+
+*  ``env.DOCKER_USERNAME`` or ``DOCKER_USERNAME``
+*  ``env.DOCKER_PASSWORD`` or ``DOCKER_PASSWORD``
diff --git a/docs/source/dev/release.rst b/docs/source/dev/release.rst
@@ -31,3 +31,6 @@ the tests while building the release.
 
     Only developers with write rights to the sonatype repository under ``fr.pilato`` space
     can perform the release.
+
+    Only developers with write rights to the `DockerHub repository <https://hub.docker.com/r/dadoonet/fscrawler/>`_
+    can push the Docker images.
diff --git a/docs/source/installation.rst b/docs/source/installation.rst
@@ -60,6 +60,150 @@ The distribution contains:
        ├── ... All needed jars
 
 
+Using docker
+------------
+
+Pull the Docker image:
+
+.. code:: sh
+
+   docker pull dadoonet/fscrawler
+
+Let say your documents are located in ``~/tmp`` dir and you want to store your fscrawler jobs in ``~/.fscrawler``.
+You can run FSCrawler with:
+
+.. code:: sh
+
+   docker run -it --rm -v ~/.fscrawler:/root/.fscrawler -v ~/tmp:/tmp/es:ro dadoonet/fscrawler fscrawler job_name
+
+On the first run, if the job does not exist yet in ``~/.fscrawler``, FSCrawler will ask you if you want to create it:
+
+::
+
+    10:16:53,880 INFO  [f.p.e.c.f.c.BootstrapChecks] Memory [Free/Total=Percent]: HEAP [67.3mb/876.5mb=7.69%], RAM [2.1gb/3.8gb=55.43%], Swap [1023.9mb/1023.9mb=100.0%].
+    10:16:53,899 WARN  [f.p.e.c.f.c.FsCrawlerCli] job [job_name] does not exist
+    10:16:53,900 INFO  [f.p.e.c.f.c.FsCrawlerCli] Do you want to create it (Y/N)?
+    y
+    10:16:56,745 INFO  [f.p.e.c.f.c.FsCrawlerCli] Settings have been created in [/root/.fscrawler/job_name/_settings.yaml]. Please review and edit before relaunch
+
+.. note::
+
+    The configuration file is actually stored on your machine in ``~/.fscrawler/job_name/_settings.yaml``.
+    Remember to change the URL of your elasticsearch instance as the container won't be able to see it
+    running under the default ``127.0.0.1``. You will need to use the actual IP address of the host.
+
+
+Using docker compose
+--------------------
+
+In this section, the following directory layout is assumed:
+
+.. code-block:: none
+
+  .
+  ├── config
+  │   └── job
+  │       └── _settings.yaml
+  ├── data
+  │   └── <your files>
+  └── docker-compose.yml
+
+For example, to connect to a docker container named ``elasticsearch``, modify your ``_settings.yaml``.
+
+.. code:: yaml
+
+  name: "test"
+  elasticsearch:
+    nodes:
+    - url: "http://elasticsearch:9200"
+
+And, prepare the following ``docker-compose.yml``.
+
+.. code:: yaml
+
+  version: '2.2'
+  services:
+    # FSCrawler
+    fscrawler:
+      image: dadoonet/fscrawler
+      container_name: fscrawler
+      volumes:
+        - ${PWD}/config:/root/.fscrawler
+        - ${PWD}/data:/tmp/es
+      networks:
+        - esnet
+      command: fscrawler job_name
+
+    # Elasticsearch Cluster
+    elasticsearch:
+      image: docker.elastic.co/elasticsearch/elasticsearch:7.3.2
+      container_name: elasticsearch
+      environment:
+        - node.name=elasticsearch
+        - discovery.seed_hosts=elasticsearch2
+        - cluster.initial_master_nodes=elasticsearch,elasticsearch2
+        - cluster.name=docker-cluster
+        - bootstrap.memory_lock=true
+        - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
+      ulimits:
+        memlock:
+          soft: -1
+          hard: -1
+      volumes:
+        - esdata01:/usr/share/elasticsearch/data
+      ports:
+        - 9200:9200
+      networks:
+        - esnet
+    elasticsearch2:
+      image: docker.elastic.co/elasticsearch/elasticsearch:7.3.2
+      container_name: elasticsearch2
+      environment:
+        - node.name=elasticsearch2
+        - discovery.seed_hosts=elasticsearch
+        - cluster.initial_master_nodes=elasticsearch,elasticsearch2
+        - cluster.name=docker-cluster
+        - bootstrap.memory_lock=true
+        - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
+      ulimits:
+        memlock:
+          soft: -1
+          hard: -1
+      volumes:
+        - esdata02:/usr/share/elasticsearch/data
+      networks:
+        - esnet
+
+  volumes:
+    esdata01:
+      driver: local
+    esdata02:
+      driver: local
+
+  networks:
+    esnet:
+
+Then, you can run Elasticsearch.
+
+.. code:: sh
+
+    docker-compose up -d elasticsearch
+    docker-compose logs -f elasticsearch
+
+Wait for elasticsearch to be started:
+
+::
+
+
+
+After starting Elasticsearch, you can run FSCrawler.
+
+.. code:: sh
+
+  docker-compose up fscrawler
+
+
+
 Running as a Service on Windows
 -------------------------------
 

diff --git a/docs/source/user/getting_started.rst b/docs/source/user/getting_started.rst
@@ -86,3 +86,4 @@ If you would like to ignore some folders to be scanned, just add a ``.fscrawleri
 The folder content and all sub folders will be ignored.
 
 For more information, read :ref:`includes_excludes`.
+
diff --git a/docs/source/user/tips.rst b/docs/source/user/tips.rst
@@ -31,12 +31,6 @@ machine <https://wiki.apache.org/hadoop/MountableHDFS>`__ and run FS
 crawler on this mount point. You can also read details about `HDFS NFS
 Gateway <http://hadoop.apache.org/docs/stable/hadoop-project-dist/hadoop-hdfs/HdfsNfsGateway.html>`__.
 
-Using docker
-------------
-
-To use FSCrawler with `docker <https://www.docker.com/>`__, check
-`docker-fscrawler <https://github.com/shadiakiki1986/docker-fscrawler>`__
-recipe.
 
 Using docker-compose
 --------------------
Original file line number	Diff line number	Diff line change
Expand Up		@@ -86,3 +86,4 @@ If you would like to ignore some folders to be scanned, just add a ``.fscrawleri
		The folder content and all sub folders will be ignored.

		For more information, read :ref:`includes_excludes`.