tabulapdf · jeremybmerrill · Mar 8, 2018 · Mar 8, 2018 · Mar 10, 2018 · Mar 11, 2018
diff --git a/.gitignore b/.gitignore
@@ -32,3 +32,7 @@ spec/reports
 test/tmp
 test/version_tmp
 tmp
+
+
+SeleniumChrome
+target
diff --git a/.project b/.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>
diff --git a/.travis.yml b/.travis.yml
@@ -1,14 +1,31 @@
 sudo: false
-language: ruby
+language: java
+addons:
+  chrome: stable
 before_install:
-  - gem update --system
-  - gem install bundler
-  - gem install jbundler
-rvm:
-  - jruby-9.1.9.0
+  # 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
-  - openjdk7
-script: bundle exec jbundle install && bundle exec rake war && bundle exec rake jardist
+script:
+  - mvn test -Dgpg.skip=true
 notifications:
   email: false
+
diff --git a/Gemfile b/Gemfile
@@ -16,5 +16,9 @@ platform :jruby do
     gem "jruby-jars", "9.2.0.0"
     gem "bootstrap-sass", "~> 3.2.0"
     gem "compass"
+    gem "ruby-maven"
   end
+
+
 end
+
diff --git a/Gemfile.lock b/Gemfile.lock
@@ -75,8 +75,9 @@ DEPENDENCIES
   jruby-jars (= 9.2.0.0)
   rack (~> 2.0.4)
   rake
+  ruby-maven
   tilt (~> 2.0.8)
   warbler (~> 2.0.4)
 
 BUNDLED WITH
-   1.16.2
+   1.16.5
diff --git a/Jarfile b/Jarfile
@@ -1 +1,2 @@
-jar 'technology.tabula:tabula', '1.0.2'
+snapshot_repository :snapshots, "https://oss.sonatype.org/content/repositories/snapshots"
+jar 'technology.tabula:tabula', '1.0.2-SNAPSHOT'
diff --git a/Jarfile.lock b/Jarfile.lock
@@ -1,18 +1,36 @@
 ---
 :runtime:
-- org.apache.pdfbox:fontbox:jar:2.0.9
-- org.apache.commons:commons-csv:jar:1.4
-- commons-cli:commons-cli:jar:1.4
-- org.bouncycastle:bcprov-jdk15on:jar:1.56
-- org.locationtech.jts:jts-core:jar:1.15.0
-- org.slf4j:slf4j-simple:jar:1.7.25
-- org.bouncycastle:bcmail-jdk15on:jar:1.56
-- org.bouncycastle:bcpkix-jdk15on:jar:1.56
-- org.apache.pdfbox:pdfbox:jar:2.0.9
-- org.slf4j:slf4j-api:jar:1.7.25
+- com.squareup.okhttp3:okhttp:jar:3.9.1
+- com.squareup.okio:okio:jar:1.13.0
+- org.apache.httpcomponents:httpclient:jar:4.5.3
+- org.junit.platform:junit-platform-commons:jar:1.1.0
+- com.google.code.findbugs:jsr305:jar:1.3.9
+- org.checkerframework:checker-compat-qual:jar:2.0.0
+- org.apache.pdfbox:fontbox:jar:2.0.1
+- org.seleniumhq.selenium:selenium-opera-driver:jar:3.11.0
+- org.seleniumhq.selenium:selenium-remote-driver:jar:3.11.0
+- com.google.j2objc:j2objc-annotations:jar:1.1
+- org.codehaus.mojo:animal-sniffer-annotations:jar:1.14
+- org.junit.jupiter:junit-jupiter-api:jar:5.1.0
+- net.bytebuddy:byte-buddy:jar:1.7.9
+- org.seleniumhq.selenium:selenium-safari-driver:jar:3.11.0
+- org.seleniumhq.selenium:selenium-firefox-driver:jar:3.11.0
+- org.apache.pdfbox:pdfbox:jar:2.0.1
+- org.apache.commons:commons-exec:jar:1.3
+- com.google.code.gson:gson:jar:2.8.2
+- commons-codec:commons-codec:jar:1.10
+- com.google.errorprone:error_prone_annotations:jar:2.1.3
+- technology.tabula:tabula:jar:1.0.2-SNAPSHOT
+- org.opentest4j:opentest4j:jar:1.0.0
+- jline:jline:jar:2.11
+- org.apache.httpcomponents:httpcore:jar:4.4.6
+- org.seleniumhq.selenium:selenium-edge-driver:jar:3.11.0
 - commons-logging:commons-logging:jar:1.2
-- com.google.code.gson:gson:jar:2.8.0
-- com.github.jai-imageio:jai-imageio-core:jar:1.3.1
-- technology.tabula:tabula:jar:1.0.2
-- com.github.jai-imageio:jai-imageio-jpeg2000:jar:1.3.0
-- com.levigo.jbig2:levigo-jbig2-imageio:jar:2.0
+- org.seleniumhq.selenium:selenium-api:jar:3.11.0
+- org.seleniumhq.selenium:selenium-java:jar:3.11.0
+- org.seleniumhq.selenium:selenium-chrome-driver:jar:3.11.0
+- org.seleniumhq.selenium:selenium-ie-driver:jar:3.11.0
+- org.yaml:snakeyaml:jar:1.18
+- org.seleniumhq.selenium:selenium-support:jar:3.11.0
+- com.google.guava:guava:jar:23.6-jre
+- org.apiguardian:apiguardian-api:jar:1.0.0
diff --git a/README.md b/README.md
@@ -167,7 +167,7 @@ Tabula has bindings for JRuby and R. If you end up writing bindings for another
 
 The site instance should now be viewable at http://127.0.0.1:9292/ .
 
-You can a couple some options when executing the server in this manner:
+You can use some options when executing the server in this manner:
 
     TABULA_DATA_DIR="/tmp/tabula" \
     TABULA_DEBUG=1 \
@@ -195,6 +195,14 @@ If you intend to develop against an unreleased version of [`tabula-java`](https:
 
 Then, adjust the `Jarfile` accordingly.
 
+If you intend to make stylesheet changes, do NOT modify the CSS files in `webapp/static/css`. Instead, modify the SASS files in `webapp/static/sass`. You can compile SASS into CSS with `$ compass compile`; alternatively, you can run `$ compass watch` to watch for changes to SASS files and automatically compile them to CSS.
+
+### Testing.
+
+There are tests in `test/`. You can run them all with `mvn test` or individually, e.g. `mvn test -Dtest=TestExtractionPage`. The tests depend on having `chromedriver` installed locally.
+
+We do not have 100% test coverage, so you should not assume that passing tests mean a code change doesn't break anything. Additionally, I believe there's some possibility that tests will sporadically fail "by accident", so if you get a failure, it might not be indicative of something broken.
+
 ### Building a packaged application version
 
 After performing the above steps ("Running Tabula from source"), you can compile

diff --git a/Rakefile b/Rakefile
@@ -83,7 +83,7 @@ task :jardist => [:create_version_file, :war] do |t|
     File.delete(output)
   end
 
-  IO.popen("zip -r9 #{output} tabula") { |f|
+  IO.popen("7z -r9 #{output} tabula") { |f|
     f.each { |line| puts line }
   }
   FileUtils.rm_rf(dist_dir)
@@ -141,7 +141,7 @@ task :macosx => [:create_version_file, :war] do |t|
     File.delete(output)
   end
 
-  IO.popen("zip -r9 #{output} tabula") { |f|
+  IO.popen("7z -r9 #{output} tabula") { |f|
     f.each { |line| puts line }
   }
   FileUtils.rm_rf(dist_dir)
@@ -212,7 +212,7 @@ task :windows => [:create_version_file, :war] do |t|
     File.delete(output)
   end
 
-  IO.popen("zip -r9 #{output} tabula") { |f|
+  IO.popen("7z -r9 #{output} tabula") { |f|
     f.each { |line| puts line }
   }
   FileUtils.rm_rf(dist_dir)

diff --git a/lib/tabula_java_wrapper.rb b/lib/tabula_java_wrapper.rb
@@ -1,6 +1,14 @@
 java_import org.apache.pdfbox.pdmodel.PDDocument
 java_import org.apache.pdfbox.pdmodel.encryption.StandardDecryptionMaterial
 
+module JavaIO
+  include_package "java.io"
+end
+
+module Gson
+  include_package "com.google.gson"
+end
+
 class Java::TechnologyTabula::Table
   attr_accessor :spec_index
   def to_csv
@@ -25,11 +33,14 @@ def to_json(*a)
 module Tabula
 
   def Tabula.extract_tables(pdf_path, specs, options={})
+    puts 'In extract_tables'
+    puts 'Options:'
+    puts options
     options = {
       :password => '',
       :detect_ruling_lines => true,
       :vertical_rulings => [],
-      :extraction_method => "guess",
+      :extraction_method => '',#"guess", Commenting out guess because of its variable behavior (GUI vs CLI)...
     }.merge(options)
 
     specs.each_with_index{|spec, i| spec["spec_index"] = i }
@@ -56,7 +67,7 @@ def Tabula.extract_tables(pdf_path, specs, options={})
           table_extractor = use_spreadsheet_extraction_method ? sea : bea
           table_extractor.extract(area).each { |table| table.spec_index = spec["spec_index"]; y.yield table }
         end
-      end;
+      end
       extractor.close!
     end
 
@@ -108,3 +119,4 @@ def pages
     end
   end
 end
+
diff --git a/lib/tabula_workspace.rb b/lib/tabula_workspace.rb
@@ -75,7 +75,7 @@ def add_file(contents, document_id, filename)
     end
 
     def move_file(path, document_id, filename)
-      FileUtils.mv(path, File.join(get_document_dir(document_id), filename))
+      FileUtils.mv(path, File.join(get_document_dir(document_id), filename),:noop=> false, :verbose=> true, :force=> true)
     end
 
 	def copy_file(path, document_id, filename)
@@ -101,10 +101,10 @@ def add_template(template_metadata)
 
       # write template metadata to workspace
       @workspace["templates"].insert(0,{
-                                      "name" => template_metadata["name"].gsub(".tabula-template.json", ""), 
+                                      "name" => template_metadata["name"].gsub(".tabula-template.json", ""),
                                       "selection_count" => template_metadata["selection_count"],
-                                      "page_count" => template_metadata["page_count"], 
-                                      "time" => template_metadata["time"], 
+                                      "page_count" => template_metadata["page_count"],
+                                      "time" => template_metadata["time"],
                                       "id" => template_metadata["id"]
                                     })
       # write template file to disk

diff --git a/pom.xml b/pom.xml
@@ -0,0 +1,39 @@
+<?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>groupId</groupId>
+    <artifactId>484_P7_1-GUI</artifactId>
+    <version>1.0-SNAPSHOT</version>
+
+    <build>
+      <testSourceDirectory>test/</testSourceDirectory>
+    </build>
+
+
+    <dependencies>
+        <dependency>
+            <groupId>junit</groupId>
+            <artifactId>junit</artifactId>
+            <version>4.12</version>
+            <scope>test</scope>
+        </dependency>
+        <dependency>
+            <groupId>org.seleniumhq.selenium</groupId>
+            <artifactId>selenium-java</artifactId>
+            <version>3.11.0</version>
+        </dependency>
+        <dependency>
+            <groupId>org.junit.jupiter</groupId>
+            <artifactId>junit-jupiter-api</artifactId>
+            <version>5.1.0</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.pdfbox</groupId>
+            <artifactId>pdfbox</artifactId>
+            <version>2.0.1</version>
+        </dependency>
+    </dependencies>
+</project>
diff --git a/run.sh b/run.sh
@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+gem update --system
+# download and use jruby
+wget https://repo1.maven.org/maven2/org/jruby/jruby-dist/9.1.16.0/jruby-dist-9.1.16.0-bin.zip
+unzip jruby-dist-9.1.16.0-bin.zip
+mv jruby-9.1.16.0 ~/
+export PATH=~/jruby-9.1.16.0/bin:$PATH
+# create back-end jar
+echo 'CLONING BACK END REPO...'
+cd ~/
+git clone https://github.com/redmyers/tabula-java.git
+cd tabula-java
+echo 'CREATING BACK-END JAR...'
+mvn clean compile assembly:single
+mvn install:install-file -Dfile=../tabula-java/target/tabula-1.0.2-SNAPSHOT-jar-with-dependencies.jar -DgroupId=technology.tabula -DartifactId=tabula -Dversion=1.0.2-SNAPSHOT -Dpackaging=jar -DpomFile=pom.xml
+# start server via GUI repo
+cd ~/
+git clone https://github.com/redmyers/484_P7_1-GUI.git
+cd 484_P7_1-GUI
+git checkout Header_Addition
+export PATH=~/jruby-9.1.16.0/bin:$PATH
+gem install bundler
+bundle install
+jruby -S jbundle install
+jruby -G -r jbundler -S rackup
+
diff --git a/target/maven-status/maven-compiler-plugin/compile/default-compile/inputFiles.lst b/target/maven-status/maven-compiler-plugin/compile/default-compile/inputFiles.lst