Regex, Header, and Footer Additions for the GUI

.gitignore

@@ -1,9 +1,9 @@
 static/pdfs
 local_settings.rb
 tabula.war
+.sass-cache
 
 lib/jars/javacv*
-.ruby-version
 .ruby-gemset
 
 TEST_PDFS

.project

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<projectDescription>
+	<name>484_P7_1-GUI</name>
+	<comment></comment>
+	<projects>
+	</projects>
+	<buildSpec>
+	</buildSpec>
+	<natures>
+	</natures>
+</projectDescription>

.ruby-version

@@ -0,0 +1 @@
+jruby-9.1.12.0

.travis.yml

@@ -0,0 +1,31 @@
+sudo: false
+language: java
+addons:
+  chrome: stable
+before_install:
+  # GUI
+  # "export DISPLAY=:99.0"
+  - "sh -e /etc/init.d/xvfb start"
+  - sleep 5
+  - bash run.sh &
+  - sleep 100
+  - bash waitForServerLoad.sh
+  - google-chrome-stable --headless --disable-gpu --remote-debugging-port=9222 http://localhost &
+  # google chrome standalone driver
+  - wget http://chromedriver.storage.googleapis.com/2.36/chromedriver_linux64.zip
+  - unzip chromedriver_linux64.zip
+  - sudo mv chromedriver /usr/local/bin
+  - sudo chmod a+x /usr/local/bin/chromedriver
+
+install:
+# - mvn install -DskipTests=true -Dmaven.javadoc.skip=true -Dgpg.skip=true -B -V
+
+
+jdk:
+  - openjdk8
+  - oraclejdk8
+script:
+  - mvn test -Dgpg.skip=true
+notifications:
+  email: false
+

484_P7_1-GUI.iml

@@ -0,0 +1,91 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module org.jetbrains.idea.maven.project.MavenProjectsManager.isMavenModule="true" type="JAVA_MODULE" version="4">
+  <component name="ModuleRunConfigurationManager">
+    <shared />
+  </component>
+  <component name="NewModuleRootManager" LANGUAGE_LEVEL="JDK_1_5">
+    <output url="file://$MODULE_DIR$/target/classes" />
+    <output-test url="file://$MODULE_DIR$/target/test-classes" />
+    <content url="file://$MODULE_DIR$">
+      <sourceFolder url="file://$MODULE_DIR$/test" isTestSource="false" />
+      <sourceFolder url="file://$MODULE_DIR$/src/main/java" isTestSource="false" />
+      <sourceFolder url="file://$MODULE_DIR$/src/main/resources" type="java-resource" />
+      <sourceFolder url="file://$MODULE_DIR$/src/test/java" isTestSource="true" />
+      <excludeFolder url="file://$MODULE_DIR$/target" />
+    </content>
+    <orderEntry type="jdk" jdkName="1.8" jdkType="JavaSDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+    <orderEntry type="module-library">
+      <library name="JUnit5.0">
+        <CLASSES>
+          <root url="jar://$MAVEN_REPOSITORY$/org/junit/jupiter/junit-jupiter-api/5.0.0/junit-jupiter-api-5.0.0.jar!/" />
+          <root url="jar://$MAVEN_REPOSITORY$/org/apiguardian/apiguardian-api/1.0.0/apiguardian-api-1.0.0.jar!/" />
+          <root url="jar://$MAVEN_REPOSITORY$/org/opentest4j/opentest4j/1.0.0/opentest4j-1.0.0.jar!/" />
+          <root url="jar://$MAVEN_REPOSITORY$/org/junit/platform/junit-platform-commons/1.0.0/junit-platform-commons-1.0.0.jar!/" />
+        </CLASSES>
+        <JAVADOC />
+        <SOURCES />
+      </library>
+    </orderEntry>
+    <orderEntry type="module-library" scope="TEST">
+      <library>
+        <CLASSES>
+          <root url="jar://$MODULE_DIR$/pdfbox-0.8.0-incubating.jar!/" />
+        </CLASSES>
+        <JAVADOC />
+        <SOURCES />
+      </library>
+    </orderEntry>
+    <orderEntry type="module-library" scope="TEST">
+      <library>
+        <CLASSES>
+          <root url="jar://$MODULE_DIR$/pdfbox-0.8.0-incubating_2.jar!/" />
+        </CLASSES>
+        <JAVADOC />
+        <SOURCES />
+      </library>
+    </orderEntry>
+    <orderEntry type="module-library" scope="TEST">
+      <library>
+        <CLASSES>
+          <root url="jar://$MODULE_DIR$/pdfbox-0.8.0-incubating_3.jar!/" />
+        </CLASSES>
+        <JAVADOC />
+        <SOURCES />
+      </library>
+    </orderEntry>
+    <orderEntry type="library" scope="TEST" name="Maven: junit:junit:4.12" level="project" />
+    <orderEntry type="library" scope="TEST" name="Maven: org.hamcrest:hamcrest-core:1.3" level="project" />
+    <orderEntry type="library" name="Maven: org.seleniumhq.selenium:selenium-java:3.11.0" level="project" />
+    <orderEntry type="library" name="Maven: org.seleniumhq.selenium:selenium-api:3.11.0" level="project" />
+    <orderEntry type="library" name="Maven: org.seleniumhq.selenium:selenium-chrome-driver:3.11.0" level="project" />
+    <orderEntry type="library" name="Maven: org.seleniumhq.selenium:selenium-edge-driver:3.11.0" level="project" />
+    <orderEntry type="library" name="Maven: org.seleniumhq.selenium:selenium-firefox-driver:3.11.0" level="project" />
+    <orderEntry type="library" name="Maven: org.seleniumhq.selenium:selenium-ie-driver:3.11.0" level="project" />
+    <orderEntry type="library" name="Maven: org.seleniumhq.selenium:selenium-opera-driver:3.11.0" level="project" />
+    <orderEntry type="library" name="Maven: org.seleniumhq.selenium:selenium-remote-driver:3.11.0" level="project" />
+    <orderEntry type="library" name="Maven: org.seleniumhq.selenium:selenium-safari-driver:3.11.0" level="project" />
+    <orderEntry type="library" name="Maven: org.seleniumhq.selenium:selenium-support:3.11.0" level="project" />
+    <orderEntry type="library" name="Maven: net.bytebuddy:byte-buddy:1.7.9" level="project" />
+    <orderEntry type="library" name="Maven: org.apache.commons:commons-exec:1.3" level="project" />
+    <orderEntry type="library" name="Maven: commons-codec:commons-codec:1.10" level="project" />
+    <orderEntry type="library" name="Maven: commons-logging:commons-logging:1.2" level="project" />
+    <orderEntry type="library" name="Maven: com.google.code.gson:gson:2.8.2" level="project" />
+    <orderEntry type="library" name="Maven: com.google.guava:guava:23.6-jre" level="project" />
+    <orderEntry type="library" name="Maven: com.google.code.findbugs:jsr305:1.3.9" level="project" />
+    <orderEntry type="library" name="Maven: org.checkerframework:checker-compat-qual:2.0.0" level="project" />
+    <orderEntry type="library" name="Maven: com.google.errorprone:error_prone_annotations:2.1.3" level="project" />
+    <orderEntry type="library" name="Maven: com.google.j2objc:j2objc-annotations:1.1" level="project" />
+    <orderEntry type="library" name="Maven: org.codehaus.mojo:animal-sniffer-annotations:1.14" level="project" />
+    <orderEntry type="library" name="Maven: org.apache.httpcomponents:httpclient:4.5.3" level="project" />
+    <orderEntry type="library" name="Maven: org.apache.httpcomponents:httpcore:4.4.6" level="project" />
+    <orderEntry type="library" name="Maven: com.squareup.okhttp3:okhttp:3.9.1" level="project" />
+    <orderEntry type="library" name="Maven: com.squareup.okio:okio:1.13.0" level="project" />
+    <orderEntry type="library" name="Maven: org.junit.jupiter:junit-jupiter-api:5.1.0" level="project" />
+    <orderEntry type="library" name="Maven: org.apiguardian:apiguardian-api:1.0.0" level="project" />
+    <orderEntry type="library" name="Maven: org.opentest4j:opentest4j:1.0.0" level="project" />
+    <orderEntry type="library" name="Maven: org.junit.platform:junit-platform-commons:1.1.0" level="project" />
+    <orderEntry type="library" name="Maven: org.apache.pdfbox:pdfbox:2.0.1" level="project" />
+    <orderEntry type="library" name="Maven: org.apache.pdfbox:fontbox:2.0.1" level="project" />
+  </component>
+</module>

AUTHORS.md

@@ -1,15 +1,21 @@
-Tabula was originally started by Manuel Aristarán in late 2012
+# Authors & Acknowledgments
+
+Tabula was originally started by Manuel Aristarán in late 2012.
 
 The PRIMARY AUTHORS are (and/or have been):
 
-* Manuel Aristarán - La Nación (Buenos Aires, Argentina), Knight-Mozilla OpenNews
+* Manuel Aristarán - MIT Media Lab (formerly La Nación, Knight-Mozilla OpenNews)
 * Mike Tigas - ProPublica, Knight-Mozilla OpenNews
-* Jeremy Merrill - ProPublica
+* Jeremy B. Merrill - The New York Times (formerly ProPublica)
+* Jason Das, designer <http://jasondas.com>
 * David Frackman
 * Travis Swicegood - Texas Tribune
 
 Special thanks to these organizations:
 
-* Knight-Mozilla OpenNews <http://www.mozillaopennews.org/>
+* Knight-Mozilla OpenNews <https://opennews.org/>
 * ProPublica <http://propublica.org>
 * La Nación <http://www.lanacion.com.ar>
+* The New York Times <http://www.nytimes.com>
+* Knight Lab at Northwestern University <http://knightlab.northwestern.edu/>
+* The John S. and James L. Knight Foundation <http://www.knightfoundation.org/>

CONTRIBUTING.md

@@ -0,0 +1,35 @@
+CONTRIBUTING
+============
+
+Tabula is an open-source project, which means it depends on volunteers to build and improve it.
+
+Interested in helping out? We'd love to have your help!
+
+You can help by:
+
+- [Reporting a bug](https://github.com/tabulapdf/tabula/issues/new).
+- Adding or editing documentation.
+- Contributing code via a Pull Request from ideas listed in the [Enhancements](https://github.com/tabulapdf/tabula/labels/enhancement) section of the issues.
+- Spreading the word about Tabula to people who might be able to benefit from using it.
+
+Did you have a problem? Guidelines for reporting a bug
+------------------------------------------------------
+
+Did Tabula not work for you? We'd like to know about it. We'd also like to know if Tabula worked, but wasn't as easy or useful as it could be. Here's what you can tell us to so we can help you better.
+
+1. What error message did you get? (We need the whole thing! If it looks like gobbledygook to you, it's probably very useful to us. That's why it's there!)
+2. What steps did you take? The more precise, the better.
+3. What PDF were you trying to extract data from? Some PDFs are wacky, so seeing the exact PDF will be useful. We understand that sometimes PDFs are confidential. If you can share it, just not publicly, send us an email. If you cant', we understand, but might not be able to help you.
+4. What version of Tabula are you using? If you're using an older version, we may have solved the problem already.
+5. What platform are you on? Windows 7 or 8? Mac? Linux? If your computer uses a language other than English or Spanish, we'd like to know that too.
+
+Guidelines for contributing code
+--------------------------------
+
+If you'd like to contribute code, here's some stuff you should know: You're also welcome to send us a note, if you'd like. All of our email addresses are listed on our Github pages.
+
+Tabula comes in a bunch of parts, all located in the [TabulaPDF Github organization](github.com/tabulapdf). 
+ -The [tabula](https://github.com/tabulapdf/tabula) repo is the UI. We aim for it to soon be all front-end, but right now has a small web server, written in Ruby, to interface between the front-end and extractor library, called "tabula-extractor"
+ - [tabula-java](https://github.com/tabulapdf/tabula-java/) is a pure Java port, for speed/wider usability. 
+
+The [Enhancements](https://github.com/tabulapdf/tabula/labels/enhancement) section of the issues lists some important improvements to Tabula that you could try out. They're well-suited to contributors, since they don't depend on a deep knowledge of all of Tabula's parts and they don't depend on close coordination.

Dockerfile

@@ -0,0 +1,27 @@
+FROM jruby:9.1-jdk
+
+RUN echo 'gem: --no-rdoc --no-ri' >> /.gemrc
+
+ENV GEM_HOME /usr/local/bundle
+ENV PATH $GEM_HOME/bin:$PATH
+RUN gem install bundler \
+  && bundle config --global path "$GEM_HOME" \
+  && bundle config --global bin "$GEM_HOME/bin"
+
+# don't create ".bundle" in all our apps
+ENV BUNDLE_APP_CONFIG $GEM_HOME
+
+RUN mkdir -p /usr/src/app
+WORKDIR /usr/src/app
+
+# these didn't work as ONBUILD, strangely. Idk why. -JBM
+ADD Gemfile /usr/src/app/
+ADD Gemfile.lock /usr/src/app/
+ADD Jarfile /usr/src/app/
+ADD Jarfile.lock /usr/src/app/
+RUN bundle install --system
+RUN jruby -S jbundle install
+ADD . /usr/src/app
+
+EXPOSE 9292
+CMD ["jruby", "-G", "-r", "jbundler", "-S", "rackup", "-o", "0.0.0.0"]

Gemfile

@@ -4,13 +4,21 @@
 
 source "https://rubygems.org"
 platform :jruby do
-  gem "cuba"
-  gem "rack"
-  gem "tilt"
-  gem "tabula-extractor", '~>0.6.4', :require => "tabula"
+  gem "cuba", "~> 3.9.2"
+  gem "rack", "~> 2.0.4"
+  gem "tilt", "~> 2.0.8"
 
   group :development do
+    gem 'jar-dependencies', '0.3.12'
+    gem 'jbundler', '~> 0.9.3'
     gem "rake"
-    gem "warbler"
+    gem "warbler", "~> 2.0.4"
+    gem "jruby-jars", "9.1.15.0"
+    gem "bootstrap-sass", "~> 3.2.0"
+    gem "compass"
+    gem "ruby-maven"
   end
+
+
 end
+

Gemfile.lock

@@ -1,30 +1,84 @@
 GEM
   remote: https://rubygems.org/
   specs:
-    cuba (3.1.0)
-      rack
-    jruby-jars (1.7.4)
-    jruby-rack (1.1.13.2)
-    rack (1.5.2)
-    rake (10.1.0)
-    rubyzip (0.9.9)
-    tabula-extractor (0.6.4-java)
-      trollop (~> 2.0)
-    tilt (1.4.1)
-    trollop (2.0)
-    warbler (1.3.8)
-      jruby-jars (>= 1.5.6)
-      jruby-rack (>= 1.0.0)
-      rake (>= 0.9.6)
-      rubyzip (>= 0.9.8)
+    axiom-types (0.1.1)
+      descendants_tracker (~> 0.0.4)
+      ice_nine (~> 0.11.0)
+      thread_safe (~> 0.3, >= 0.3.1)
+    bootstrap-sass (3.2.0.2)
+      sass (~> 3.2)
+    chunky_png (1.3.8)
+    coercible (1.0.0)
+      descendants_tracker (~> 0.0.1)
+    compass (1.0.3)
+      chunky_png (~> 1.2)
+      compass-core (~> 1.0.2)
+      compass-import-once (~> 1.0.5)
+      rb-fsevent (>= 0.9.3)
+      rb-inotify (>= 0.9)
+      sass (>= 3.3.13, < 3.5)
+    compass-core (1.0.3)
+      multi_json (~> 1.0)
+      sass (>= 3.3.0, < 3.5)
+    compass-import-once (1.0.5)
+      sass (>= 3.2, < 3.5)
+    cuba (3.9.2)
+      rack (>= 1.6.0)
+    descendants_tracker (0.0.4)
+      thread_safe (~> 0.3, >= 0.3.1)
+    equalizer (0.0.11)
+    ffi (1.9.18-java)
+    ice_nine (0.11.2)
+    jar-dependencies (0.3.12)
+    jbundler (0.9.3)
+      bundler (~> 1.5)
+      jar-dependencies (~> 0.3)
+      maven-tools (~> 1.1)
+      ruby-maven (~> 3.3, >= 3.3.8)
+    jruby-jars (9.1.12.0)
+    jruby-rack (1.1.21)
+    maven-tools (1.1.6)
+      virtus (~> 1.0)
+    multi_json (1.12.2)
+    rack (2.0.3)
+    rake (12.3.0)
+    rb-fsevent (0.10.2)
+    rb-inotify (0.9.10)
+      ffi (>= 0.5.0, < 2)
+    ruby-maven (3.3.12)
+      ruby-maven-libs (~> 3.3.9)
+    ruby-maven-libs (3.3.9)
+    rubyzip (1.2.1)
+    sass (3.4.25)
+    thread_safe (0.3.6-java)
+    tilt (2.0.8)
+    virtus (1.0.5)
+      axiom-types (~> 0.1)
+      coercible (~> 1.0)
+      descendants_tracker (~> 0.0, >= 0.0.3)
+      equalizer (~> 0.0, >= 0.0.9)
+    warbler (2.0.4)
+      jruby-jars (>= 9.0.0.0)
+      jruby-rack (>= 1.1.1, < 1.3)
+      rake (>= 10.1.0)
+      rubyzip (~> 1.0, < 1.4)
 
 PLATFORMS
   java
+  x86-mingw32
 
 DEPENDENCIES
-  cuba
-  rack
+  bootstrap-sass (~> 3.2.0)
+  compass
+  cuba (~> 3.8.1)
+  jar-dependencies (= 0.3.12)
+  jbundler (~> 0.9.3)
+  jruby-jars (= 9.1.15.0)
+  rack (~> 2.0.4)
   rake
-  tabula-extractor (~> 0.6.4)
-  tilt
-  warbler
+  ruby-maven
+  tilt (~> 2.0.7)
+  warbler (~> 2.0.3)
+
+BUNDLED WITH
+   1.16.1

Jarfile

@@ -0,0 +1,2 @@
+snapshot_repository :snapshots, "https://oss.sonatype.org/content/repositories/snapshots"
+jar 'technology.tabula:tabula', '1.0.2-SNAPSHOT'