pdf-textstream 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 21c6dc3e502ceac31180f160ad74c03e790fd1e5c228438f4155d7ff8254876b
+  data.tar.gz: e328c69e215c0b657eac56098347f3374765fe25d1feb455b2793ed1e83bb435
+SHA512:
+  metadata.gz: 84ce6cb92773f7c5513a351e499108295e4cf164da1a1762de6af51317b8ba887d8eb2f211364772d8169156eccf300ee4d398fe20e377b54878365223e8c37d
+  data.tar.gz: 2fccca0559bf5e25a215dc03e7dc3d80361fa1513d7c95cc629f115349dff5d25b30c84819728b1d152df5191ef26672c4dd9c990b271ac726966bd4bc7b16e3

data/.gitignore

@@ -0,0 +1,12 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.3.3
+before_install: gem install bundler -v 1.15.3

data/Gemfile

@@ -0,0 +1,6 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in pdf-textstream.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2018 Michał Kulesza
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/PDFLayoutTextStripper.java

@@ -0,0 +1,468 @@
+/*
+ * Author: Jonathan Link
+ * Email: jonathanlink[d o t]email[a t]gmail[d o t]com
+ * Date of creation: 13.11.2014
+ * Version: 2.2.2
+ * Description:
+ *
+ * Version 2.1 uses PDFBox 2.x. Version 1.0 used PDFBox 1.8.x
+ * Acknowledgement to James Sullivan for version 2.0
+ *
+ * What does it DO:
+ * This object converts the content of a PDF file into a String.
+ * The layout of the texts is transcribed as near as the one in the PDF given at the input.
+ *
+ * What does it NOT DO:
+ * Vertical texts in the PDF file are not handled for the moment.
+ *
+ * I would appreciate any feedback you could offer. (see my email address above)
+ *
+ * LICENSE:
+ *
+ * The MIT License (MIT)
+ *
+ * Copyright (c) 2014-2017 Jonathan Link
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ *
+ */
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.Iterator;
+import java.util.List;
+
+import org.apache.pdfbox.pdmodel.PDPage;
+import org.apache.pdfbox.pdmodel.common.PDRectangle;
+import org.apache.pdfbox.text.PDFTextStripper;
+import org.apache.pdfbox.text.TextPosition;
+import org.apache.pdfbox.text.TextPositionComparator;
+
+public class PDFLayoutTextStripper extends PDFTextStripper {
+
+    public static final boolean DEBUG = false;
+    public static final int OUTPUT_SPACE_CHARACTER_WIDTH_IN_PT = 4;
+
+    private double currentPageWidth;
+    private TextPosition previousTextPosition;
+    private List<TextLine> textLineList;
+
+    public PDFLayoutTextStripper() throws IOException {
+        super();
+        this.previousTextPosition = null;
+        this.textLineList = new ArrayList<TextLine>();
+    }
+
+    @Override
+    public void processPage(PDPage page) throws IOException {
+        PDRectangle pageRectangle = page.getMediaBox();
+        if (pageRectangle!= null) {
+            this.setCurrentPageWidth(pageRectangle.getWidth());
+            super.processPage(page);
+            this.previousTextPosition = null;
+            this.textLineList = new ArrayList<TextLine>();
+        }
+    }
+
+    @Override
+    protected void writePage() throws IOException {
+        List<List<TextPosition>> charactersByArticle = super.getCharactersByArticle();
+        for( int i = 0; i < charactersByArticle.size(); i++) {
+            List<TextPosition> textList = charactersByArticle.get(i);
+            try {
+                this.sortTextPositionList(textList);
+            } catch ( java.lang.IllegalArgumentException e) {
+                System.err.println(e);
+            }
+            this.iterateThroughTextList(textList.iterator()) ;
+        }
+        this.writeToOutputStream(this.getTextLineList());
+    }
+
+    private void writeToOutputStream(final List<TextLine> textLineList) throws IOException {
+        for (TextLine textLine : textLineList) {
+            char[] line = textLine.getLine().toCharArray();
+            super.getOutput().write(line);
+            super.getOutput().write('\n');
+            super.getOutput().flush();
+        }
+    }
+
+    /*
+     * In order to get rid of the warning:
+     * TextPositionComparator class should implement Comparator<TextPosition> instead of Comparator
+     */
+    @SuppressWarnings("unchecked")
+    private void sortTextPositionList(final List<TextPosition> textList) {
+        TextPositionComparator comparator = new TextPositionComparator();
+        Collections.sort(textList, comparator);
+    }
+
+    private void writeLine(final List<TextPosition> textPositionList) {
+        if ( textPositionList.size() > 0 ) {
+            TextLine textLine = this.addNewLine();
+            boolean firstCharacterOfLineFound = false;
+            for (TextPosition textPosition : textPositionList ) {
+                CharacterFactory characterFactory = new CharacterFactory(firstCharacterOfLineFound);
+                Character character = characterFactory.createCharacterFromTextPosition(textPosition, this.getPreviousTextPosition());
+                textLine.writeCharacterAtIndex(character);
+                this.setPreviousTextPosition(textPosition);
+                firstCharacterOfLineFound = true;
+            }
+        } else {
+            this.addNewLine(); // white line
+        }
+    }
+
+    private void iterateThroughTextList(Iterator<TextPosition> textIterator) {
+        List<TextPosition> textPositionList = new ArrayList<TextPosition>();
+
+        while ( textIterator.hasNext() ) {
+            TextPosition textPosition = (TextPosition)textIterator.next();
+            int numberOfNewLines = this.getNumberOfNewLinesFromPreviousTextPosition(textPosition);
+            if ( numberOfNewLines == 0 ) {
+                textPositionList.add(textPosition);
+            } else {
+                this.writeTextPositionList(textPositionList);
+                this.createNewEmptyNewLines(numberOfNewLines);
+                textPositionList.add(textPosition);
+            }
+            this.setPreviousTextPosition(textPosition);
+        }
+        if (!textPositionList.isEmpty()) {
+            this.writeTextPositionList(textPositionList);
+        }
+    }
+
+    private void writeTextPositionList(final List<TextPosition> textPositionList) {
+        this.writeLine(textPositionList);
+        textPositionList.clear();
+    }
+
+    private void createNewEmptyNewLines(int numberOfNewLines) {
+        for (int i = 0; i < numberOfNewLines - 1; ++i) {
+            this.addNewLine();
+        }
+    }
+
+    private int getNumberOfNewLinesFromPreviousTextPosition(final TextPosition textPosition) {
+        TextPosition previousTextPosition = this.getPreviousTextPosition();
+        if ( previousTextPosition == null ) {
+            return 1;
+        }
+
+        float textYPosition = Math.round( textPosition.getY() );
+        float previousTextYPosition = Math.round( previousTextPosition.getY() );
+
+        if ( textYPosition > previousTextYPosition && (textYPosition - previousTextYPosition > 5.5) ) {
+            double height = textPosition.getHeight();
+            int numberOfLines = (int) (Math.floor( textYPosition - previousTextYPosition) / height );
+            numberOfLines = Math.max(1, numberOfLines - 1); // exclude current new line
+            if (DEBUG) System.out.println(height + " " + numberOfLines);
+            return numberOfLines ;
+        } else {
+            return 0;
+        }
+    }
+
+    private TextLine addNewLine() {
+        TextLine textLine = new TextLine(this.getCurrentPageWidth());
+        textLineList.add(textLine);
+        return textLine;
+    }
+
+    private TextPosition getPreviousTextPosition() {
+        return this.previousTextPosition;
+    }
+
+    private void setPreviousTextPosition(final TextPosition setPreviousTextPosition) {
+        this.previousTextPosition = setPreviousTextPosition;
+    }
+
+    private int getCurrentPageWidth() {
+        return (int) Math.round(this.currentPageWidth);
+    }
+
+    private void setCurrentPageWidth(double currentPageWidth) {
+        this.currentPageWidth = currentPageWidth;
+    }
+
+    private List<TextLine> getTextLineList() {
+        return this.textLineList;
+    }
+
+}
+
+class TextLine {
+
+    private static final char SPACE_CHARACTER = ' ';
+    private int lineLength;
+    private String line;
+    private int lastIndex;
+
+    public TextLine(int lineLength) {
+        this.line = "";
+        this.lineLength = lineLength / PDFLayoutTextStripper.OUTPUT_SPACE_CHARACTER_WIDTH_IN_PT;
+        this.completeLineWithSpaces();
+    }
+
+    public void writeCharacterAtIndex(final Character character) {
+        character.setIndex(this.computeIndexForCharacter(character));
+        int index = character.getIndex();
+        char characterValue = character.getCharacterValue();
+        if ( this.indexIsInBounds(index) && this.line.charAt(index) == SPACE_CHARACTER) {
+            this.line = this.line.substring(0, index) + characterValue + this.line.substring(index + 1, this.getLineLength());
+        }
+    }
+
+    public int getLineLength() {
+        return this.lineLength;
+    }
+
+    public String getLine() {
+        return line;
+    }
+
+    private int computeIndexForCharacter(final Character character) {
+        int index = character.getIndex();
+        boolean isCharacterPartOfPreviousWord = character.isCharacterPartOfPreviousWord();
+        boolean isCharacterAtTheBeginningOfNewLine = character.isCharacterAtTheBeginningOfNewLine();
+        boolean isCharacterCloseToPreviousWord = character.isCharacterCloseToPreviousWord();
+
+        if ( !this.indexIsInBounds(index) ) {
+            return -1;
+        } else {
+            if ( isCharacterPartOfPreviousWord && !isCharacterAtTheBeginningOfNewLine ) {
+                index = this.findMinimumIndexWithSpaceCharacterFromIndex(index);
+            } else if ( isCharacterCloseToPreviousWord ) {
+                if ( this.line.charAt(index) != SPACE_CHARACTER ) {
+                    index = index + 1;
+                } else {
+                    index = this.findMinimumIndexWithSpaceCharacterFromIndex(index) + 1;
+                }
+            }
+            index = this.getNextValidIndex(index, isCharacterPartOfPreviousWord);
+            return index;
+        }
+    }
+
+    private boolean isSpaceCharacterAtIndex(int index) {
+        return this.line.charAt(index) != SPACE_CHARACTER;
+    }
+
+    private boolean isNewIndexGreaterThanLastIndex(int index) {
+        int lastIndex = this.getLastIndex();
+        return ( index > lastIndex );
+    }
+
+    private int getNextValidIndex(int index, boolean isCharacterPartOfPreviousWord) {
+        int nextValidIndex = index;
+        int lastIndex = this.getLastIndex();
+        if ( ! this.isNewIndexGreaterThanLastIndex(index) ) {
+            nextValidIndex = lastIndex + 1;
+        }
+        if ( !isCharacterPartOfPreviousWord && this.isSpaceCharacterAtIndex(index - 1) ) {
+            nextValidIndex = nextValidIndex + 1;
+        }
+        this.setLastIndex(nextValidIndex);
+        return nextValidIndex;
+    }
+
+    private int findMinimumIndexWithSpaceCharacterFromIndex(int index) {
+        int newIndex = index;
+        while( newIndex >= 0 && this.line.charAt(newIndex) == SPACE_CHARACTER ) {
+            newIndex = newIndex - 1;
+        }
+        return newIndex + 1;
+    }
+
+    private boolean indexIsInBounds(int index) {
+        return (index >= 0 && index < this.lineLength);
+    }
+
+    private void completeLineWithSpaces() {
+        for (int i = 0; i < this.getLineLength(); ++i) {
+            line += SPACE_CHARACTER;
+        }
+    }
+
+    private int getLastIndex() {
+        return this.lastIndex;
+    }
+
+    private void setLastIndex(int lastIndex) {
+        this.lastIndex = lastIndex;
+    }
+
+}
+
+
+class Character {
+
+    private char characterValue;
+    private int index;
+    private boolean isCharacterPartOfPreviousWord;
+    private boolean isFirstCharacterOfAWord;
+    private boolean isCharacterAtTheBeginningOfNewLine;
+    private boolean isCharacterCloseToPreviousWord;
+
+    public Character(char characterValue, int index, boolean isCharacterPartOfPreviousWord, boolean isFirstCharacterOfAWord, boolean isCharacterAtTheBeginningOfNewLine, boolean isCharacterPartOfASentence) {
+        this.characterValue = characterValue;
+        this.index = index;
+        this.isCharacterPartOfPreviousWord = isCharacterPartOfPreviousWord;
+        this.isFirstCharacterOfAWord = isFirstCharacterOfAWord;
+        this.isCharacterAtTheBeginningOfNewLine = isCharacterAtTheBeginningOfNewLine;
+        this.isCharacterCloseToPreviousWord = isCharacterPartOfASentence;
+        if (PDFLayoutTextStripper.DEBUG) System.out.println(this.toString());
+    }
+
+    public char getCharacterValue() {
+        return this.characterValue;
+    }
+
+    public int getIndex() {
+        return this.index;
+    }
+
+    public void setIndex(int index) {
+        this.index = index;
+    }
+
+    public boolean isCharacterPartOfPreviousWord() {
+        return this.isCharacterPartOfPreviousWord;
+    }
+
+    public boolean isFirstCharacterOfAWord() {
+        return this.isFirstCharacterOfAWord;
+    }
+
+    public boolean isCharacterAtTheBeginningOfNewLine() {
+        return this.isCharacterAtTheBeginningOfNewLine;
+    }
+
+    public boolean isCharacterCloseToPreviousWord() {
+        return this.isCharacterCloseToPreviousWord;
+    }
+
+    public String toString() {
+        String toString = "";
+        toString += index;
+        toString += " ";
+        toString += characterValue;
+        toString += " isCharacterPartOfPreviousWord=" + isCharacterPartOfPreviousWord;
+        toString += " isFirstCharacterOfAWord=" + isFirstCharacterOfAWord;
+        toString += " isCharacterAtTheBeginningOfNewLine=" + isCharacterAtTheBeginningOfNewLine;
+        toString += " isCharacterPartOfASentence=" + isCharacterCloseToPreviousWord;
+        toString += " isCharacterCloseToPreviousWord=" + isCharacterCloseToPreviousWord;
+        return toString;
+    }
+
+}
+
+
+class CharacterFactory {
+
+    private TextPosition previousTextPosition;
+    private boolean firstCharacterOfLineFound;
+    private boolean isCharacterPartOfPreviousWord;
+    private boolean isFirstCharacterOfAWord;
+    private boolean isCharacterAtTheBeginningOfNewLine;
+    private boolean isCharacterCloseToPreviousWord;
+
+    public CharacterFactory(boolean firstCharacterOfLineFound) {
+        this.firstCharacterOfLineFound = firstCharacterOfLineFound;
+    }
+
+    public Character createCharacterFromTextPosition(final TextPosition textPosition, final TextPosition previousTextPosition) {
+        this.setPreviousTextPosition(previousTextPosition);
+        this.isCharacterPartOfPreviousWord = this.isCharacterPartOfPreviousWord(textPosition);
+        this.isFirstCharacterOfAWord = this.isFirstCharacterOfAWord(textPosition);
+        this.isCharacterAtTheBeginningOfNewLine = this.isCharacterAtTheBeginningOfNewLine(textPosition);
+        this.isCharacterCloseToPreviousWord = this.isCharacterCloseToPreviousWord(textPosition);
+        char character = this.getCharacterFromTextPosition(textPosition);
+        int index = (int)textPosition.getX() / PDFLayoutTextStripper.OUTPUT_SPACE_CHARACTER_WIDTH_IN_PT;
+        return new Character(character,
+                             index,
+                             isCharacterPartOfPreviousWord,
+                             isFirstCharacterOfAWord,
+                             isCharacterAtTheBeginningOfNewLine,
+                             isCharacterCloseToPreviousWord);
+    }
+
+    private boolean isCharacterAtTheBeginningOfNewLine(final TextPosition textPosition) {
+        if ( ! firstCharacterOfLineFound ) {
+            return true;
+        }
+        TextPosition previousTextPosition = this.getPreviousTextPosition();
+        float previousTextYPosition = previousTextPosition.getY();
+        return ( Math.round( textPosition.getY() ) < Math.round(previousTextYPosition) );
+    }
+
+    private boolean isFirstCharacterOfAWord(final TextPosition textPosition) {
+        if ( ! firstCharacterOfLineFound ) {
+            return true;
+        }
+        double numberOfSpaces = this.numberOfSpacesBetweenTwoCharacters(previousTextPosition, textPosition);
+        return (numberOfSpaces > 1) || this.isCharacterAtTheBeginningOfNewLine(textPosition);
+    }
+
+    private boolean isCharacterCloseToPreviousWord(final TextPosition textPosition) {
+        if ( ! firstCharacterOfLineFound ) {
+            return false;
+        }
+        double numberOfSpaces = this.numberOfSpacesBetweenTwoCharacters(previousTextPosition, textPosition);
+        int widthOfSpace = (int) Math.ceil(textPosition.getWidthOfSpace());
+        return (numberOfSpaces > 1 && numberOfSpaces <= widthOfSpace);
+    }
+
+    private boolean isCharacterPartOfPreviousWord(final TextPosition textPosition) {
+        TextPosition previousTextPosition = this.getPreviousTextPosition();
+        if ( previousTextPosition.getUnicode().equals(" ") ) {
+            return false;
+        }
+        double numberOfSpaces = this.numberOfSpacesBetweenTwoCharacters(previousTextPosition, textPosition);
+        return (numberOfSpaces <= 1);
+    }
+
+    private double numberOfSpacesBetweenTwoCharacters(final TextPosition textPosition1, final TextPosition textPosition2) {
+        double previousTextXPosition = textPosition1.getX();
+        double previousTextWidth = textPosition1.getWidth();
+        double previousTextEndXPosition = (previousTextXPosition + previousTextWidth);
+        double numberOfSpaces = Math.abs(Math.round(textPosition2.getX() - previousTextEndXPosition));
+        return numberOfSpaces;
+    }
+
+
+
+    private char getCharacterFromTextPosition(final TextPosition textPosition) {
+        String string = textPosition.getUnicode();
+        char character = string.charAt(0);
+        return character;
+    }
+
+    private TextPosition getPreviousTextPosition() {
+        return this.previousTextPosition;
+    }
+
+    private void setPreviousTextPosition(final TextPosition previousTextPosition) {
+        this.previousTextPosition = previousTextPosition;
+    }
+
+}

data/README.md

@@ -0,0 +1,39 @@
+# Pdf::Textstream
+
+Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/pdf/textstream`. To experiment with that code, run `bin/console` for an interactive prompt.
+
+TODO: Delete this and the text above, and describe your gem
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'pdf-textstream'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install pdf-textstream
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/pdf-textstream.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "pdf/textstream"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/build.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+javac -d classes -cp .:./jars/pdfbox-2.0.6.jar:./jars/commons-logging-1.2.jar:./jars/fontbox-2.0.6.jar *.java

data/lib/pdf/textstream.rb

@@ -0,0 +1,30 @@
+require "pdf/textstream/version"
+require "java"
+
+# load jars
+require_relative "../../jars/pdfbox-2.0.6.jar"
+require_relative "../../jars/commons-logging-1.2.jar"
+require_relative "../../jars/fontbox-2.0.6.jar"
+
+$CLASSPATH << "#{File.expand_path(File.dirname(__FILE__))}/../../classes"
+module Pdf
+  module Textstream
+    PDFLayoutTextStripper = JavaUtilities.get_proxy_class("PDFLayoutTextStripper")
+
+    # change namespace
+    PDFParser = Java::OrgApachePdfboxPdfparser::PDFParser
+    RandomAccessFile = Java::OrgApachePdfboxIo::RandomAccessFile
+    PDDocument = Java::OrgApachePdfboxPdmodel::PDDocument
+    PDFTextStripper = Java::OrgApachePdfboxText::PDFTextStripper
+
+    def self.file_path_to_text(path)
+      # TODO: exception handling
+      pdfParser = PDFParser.new(RandomAccessFile.new(Java::JavaIo::File.new(path), "r"))
+      pdfParser.parse()
+      pdDocument = PDDocument.new(pdfParser.getDocument());
+      pdfTextStripper = PDFLayoutTextStripper.new
+      string = pdfTextStripper.getText(pdDocument);
+      return string
+    end
+  end
+end

data/lib/pdf/textstream/version.rb

@@ -0,0 +1,5 @@
+module Pdf
+  module Textstream
+    VERSION = "0.1.0"
+  end
+end

data/pdf-textstream.gemspec

@@ -0,0 +1,26 @@
+# coding: utf-8
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "pdf/textstream/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "pdf-textstream"
+  spec.version       = Pdf::Textstream::VERSION
+  spec.authors       = ["Michal Kulesza"]
+  spec.email         = ["michal.kulesza@netguru.co"]
+
+  spec.summary       = %q{JRuby gem converting PDF to text keeping the layout}
+  spec.homepage      = "https://github.com/mic-kul/pdf-textstream"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.15"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+end

metadata

@@ -0,0 +1,107 @@
+--- !ruby/object:Gem::Specification
+name: pdf-textstream
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Michal Kulesza
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2018-03-10 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+  name: bundler
+  prerelease: false
+  type: :development
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  name: rake
+  prerelease: false
+  type: :development
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  name: rspec
+  prerelease: false
+  type: :development
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description:
+email:
+- michal.kulesza@netguru.co
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- LICENSE.txt
+- PDFLayoutTextStripper.java
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- build.sh
+- classes/Character.class
+- classes/CharacterFactory.class
+- classes/PDFLayoutTextStripper.class
+- classes/TextLine.class
+- jars/commons-logging-1.2.jar
+- jars/fontbox-2.0.6.jar
+- jars/pdfbox-2.0.6.jar
+- lib/pdf/textstream.rb
+- lib/pdf/textstream/version.rb
+- pdf-textstream.gemspec
+homepage: https://github.com/mic-kul/pdf-textstream
+licenses:
+- MIT
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project:
+rubygems_version: 2.6.11
+signing_key:
+specification_version: 4
+summary: JRuby gem converting PDF to text keeping the layout
+test_files: []