pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>ocr</groupId>
    <artifactId>ocr</artifactId>
    <version>1.0-SNAPSHOT</version>
    <packaging>pom</packaging>

    <name>ocr</name>

    <url>https://github.com/mmiklavc/scalable-ocr</url>

    <description>
        So much of our data is represented as human readable scans of documents. However, this kind of
        document-by-document analysis does not scale, so it is becoming evermore common to need to ingest large numbers
        of PDFs or scanned documents shows up in almost all sectors. Inevitably these scanned documents must be
        converted to text for analysis. And since dealing with unstructured data is one of the main selling points for a
        platform like Hadoop, it means that we must convert large volumes of potentially large documents into a textual
        representation. We will show you how to use open source tooling (Apache NiFi and Tesseract) to scalably convert
        volumes of PDFs and ingest into a platform that will allow you to analyze this data at scale.
    </description>

    <developers>
        <developer>
            <name>Casey Stella</name>
            <email>cestella@gmail.com</email>
            <organizationUrl>http://www.caseystella.com</organizationUrl>
        </developer>
        <developer>
            <name>Michael Miklavcic</name>
            <email>michael@clevelandflash.com</email>
            <organizationUrl>http://blog.michaelmiklavcic.com</organizationUrl>
        </developer>
    </developers>

    <modules>
        <module>conversion</module>
        <module>preprocessing</module>
        <module>extraction</module>
        <module>nifi</module>
        <module>common</module>
        <module>cli</module>
    </modules>

    <properties>
        <!-- platform encoding -->
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>

        <!-- source code versions -->
        <java-source.version>1.8</java-source.version>
        <java-target.version>1.8</java-target.version>

        <!-- scm locations -->
        <scm-connection.url>file://localhost/path/to/localrepo</scm-connection.url>
        <scm-developer-connection.url>file://localhost/path/to/localrepo</scm-developer-connection.url>

        <!-- build plugin versions -->
        <maven-shade-plugin.version>2.3</maven-shade-plugin.version>
        <maven-compiler-plugin.version>3.1</maven-compiler-plugin.version>
        <maven-surefire-plugin.version>2.18.1</maven-surefire-plugin.version>
        <maven-failsafe-plugin.version>2.17</maven-failsafe-plugin.version>
        <maven-source-plugin.version>3.0.0</maven-source-plugin.version>
        <maven-javadoc-plugin.version>2.10.3</maven-javadoc-plugin.version>
        <maven-release-plugin.version>2.5.3</maven-release-plugin.version>
        <scala-maven-plugin.version>3.2.1</scala-maven-plugin.version>
        <scalatest-maven-plugin.version>1.0</scalatest-maven-plugin.version>

        <!-- report plugin versions -->
        <maven-project-info-reports-plugin>2.9</maven-project-info-reports-plugin>

        <!-- main dependency versions -->
        <commons-io.version>2.4</commons-io.version>
        <guava.version>19.0</guava.version>
        <logback.version>1.1.6</logback.version>
        <hadoop.version>2.7.2</hadoop.version>
        <scala.version>2.11.8</scala.version>
        <scala.binary.version>2.11</scala.binary.version>

        <!-- test dependency versions -->
        <!-- junit version 4.12 does not require junit-dep to work with hamcrest matchers. hamcrest-core is now included as a dependency -->
        <junit.version>4.12</junit.version>
        <mockito.version>1.10.19</mockito.version>
        <scalatest.version>2.2.6</scalatest.version>
        <multiline-string.version>0.1.2</multiline-string.version>
    </properties>

    <scm>
        <connection>scm:git:${scm-connection.url}</connection>
        <developerConnection>scm:git:${scm-developer-connection.url}</developerConnection>
    </scm>

    <repositories>
        <repository>
            <id>multiline-release-repo</id>
            <url>https://raw.github.com/benelog/multiline/master/maven-repository</url>
            <snapshots>
                <enabled>false</enabled>
            </snapshots>
        </repository>
    </repositories>

    <dependencyManagement>
        <dependencies>
            <dependency>
                <groupId>org.scala-lang</groupId>
                <artifactId>scala-library</artifactId>
                <version>${scala.version}</version>
            </dependency>
            <dependency>
                <groupId>org.scalactic</groupId>
                <artifactId>scalactic_${scala.binary.version}</artifactId>
                <version>${scalatest.version}</version>
            </dependency>
            <dependency>
                <groupId>org.scalatest</groupId>
                <artifactId>scalatest_${scala.binary.version}</artifactId>
                <version>${scalatest.version}</version>
            </dependency>
        </dependencies>
    </dependencyManagement>

    <dependencies>
        <dependency>
            <groupId>ch.qos.logback</groupId>
            <artifactId>logback-classic</artifactId>
            <version>${logback.version}</version>
        </dependency>
        <dependency>
            <groupId>commons-io</groupId>
            <artifactId>commons-io</artifactId>
            <version>${commons-io.version}</version>
        </dependency>
        <dependency>
            <groupId>com.google.guava</groupId>
            <artifactId>guava</artifactId>
            <version>${guava.version}</version>
        </dependency>
        <!--    uncomment to include the hadoop client
                <dependency>
                    <groupId>org.apache.hadoop</groupId>
                    <artifactId>hadoop-client</artifactId>
                    <version>${hadoop.version}</version>
                    <exclusions>
                        <exclusion>
                            <groupId>org.slf4j</groupId>
                            <artifactId>slf4j-log4j12</artifactId>
                        </exclusion>
                    </exclusions>
                </dependency>
        -->
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>${junit.version}</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.mockito</groupId>
            <artifactId>mockito-all</artifactId>
            <version>${mockito.version}</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.adrianwalker</groupId>
            <artifactId>multiline-string</artifactId>
            <version>${multiline-string.version}</version>
            <scope>test</scope>
        </dependency>
    </dependencies>

    <build>
        <pluginManagement>
            <plugins>
                <plugin>
                    <groupId>net.alchim31.maven</groupId>
                    <artifactId>scala-maven-plugin</artifactId>
                    <version>${scala-maven-plugin.version}</version>
                    <configuration>
                        <recompileMode>incremental</recompileMode>
                        <useZincServer>true</useZincServer>
                        <javacArgs>
                            <javacArg>-Xlint:unchecked</javacArg>
                            <javacArg>-Xlint:deprecation</javacArg>
                        </javacArgs>
                        <args>
                            <arg>-unchecked</arg>
                            <arg>-deprecation</arg>
                            <arg>-explaintypes</arg>
                            <!-- work-around for https://issues.scala-lang.org/browse/SI-8358 -->
                            <arg>-nobootcp</arg>
                        </args>
                    </configuration>
                    <executions>
                        <execution>
                            <id>scala-compile-first</id>
                            <phase>process-resources</phase>
                            <goals>
                                <goal>add-source</goal>
                                <goal>compile</goal>
                            </goals>
                        </execution>
                        <execution>
                            <id>scala-test-compile</id>
                            <phase>process-test-resources</phase>
                            <goals>
                                <goal>testCompile</goal>
                            </goals>
                        </execution>
                    </executions>
                </plugin>
                <plugin>
                    <groupId>org.scalatest</groupId>
                    <artifactId>scalatest-maven-plugin</artifactId>
                    <version>${scalatest-maven-plugin.version}</version>
                    <configuration>
                        <reportsDirectory>${project.build.directory}/surefire-reports</reportsDirectory>
                        <junitxml>.</junitxml>
                        <filereports>WDF TestSuite.txt</filereports>
                    </configuration>
                    <executions>
                        <execution>
                            <id>test</id>
                            <goals>
                                <goal>test</goal>
                            </goals>
                        </execution>
                    </executions>
                </plugin>
                <plugin>
                    <groupId>org.apache.maven.plugins</groupId>
                    <artifactId>maven-shade-plugin</artifactId>
                    <version>${maven-shade-plugin.version}</version>
                    <executions>
                        <execution>
                            <phase>package</phase>
                            <goals>
                                <goal>shade</goal>
                            </goals>
                        </execution>
                    </executions>
                </plugin>
            </plugins>
        </pluginManagement>

        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>${maven-compiler-plugin.version}</version>
                <configuration>
                    <source>${java-source.version}</source>
                    <target>${java-target.version}</target>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-surefire-plugin</artifactId>
                <version>${maven-surefire-plugin.version}</version>
                <configuration>
                    <excludes>
                        <exclude>**/*AcceptanceTest*.java</exclude>
                    </excludes>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-failsafe-plugin</artifactId>
                <version>${maven-failsafe-plugin.version}</version>
                <configuration>
                    <includes>
                        <include>**/*AcceptanceTest*.java</include>
                    </includes>
                </configuration>
                <executions>
                    <execution>
                        <goals>
                            <goal>integration-test</goal>
                            <goal>verify</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-source-plugin</artifactId>
                <version>${maven-source-plugin.version}</version>
                <executions>
                    <execution>
                        <id>attach-sources</id>
                        <goals>
                            <goal>jar-no-fork</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-release-plugin</artifactId>
                <version>${maven-release-plugin.version}</version>
                <configuration>
                    <autoVersionSubmodules>true</autoVersionSubmodules>
                </configuration>
            </plugin>
        </plugins>
    </build>

    <reporting>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-project-info-reports-plugin</artifactId>
                <version>${maven-project-info-reports-plugin}</version>
                <configuration>
                    <dependencyLocationsEnabled>false</dependencyLocationsEnabled>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-javadoc-plugin</artifactId>
                <version>${maven-javadoc-plugin.version}</version>
                <reportSets>
                    <reportSet>
                        <id>default</id>
                        <reports>
                            <report>javadoc</report>
                            <report>test-javadoc</report>
                        </reports>
                    </reportSet>
                    <reportSet>
                        <id>aggregate</id>
                        <reports>
                            <report>aggregate</report>
                        </reports>
                    </reportSet>
                </reportSets>
            </plugin>
        </plugins>
    </reporting>

</project>