It begins.

.travis.yml

@@ -0,0 +1,24 @@
+language: php
+
+before_install:
+ - sudo apt-get install -y antiword
+
+php:
+ - 7.0
+ - 7.1
+ - 7.2
+
+env:
+ matrix:
+ - COMPOSER_FLAGS="--prefer-lowest"
+ - COMPOSER_FLAGS=""
+
+before_script:
+ - travis_retry composer self-update
+ - travis_retry composer update ${COMPOSER_FLAGS} --no-interaction --prefer-source
+
+script:
+ - phpunit --coverage-text --coverage-clover=coverage.clover
+
+after_script:
+ - php vendor/bin/ocular code-coverage:upload --format=php-clover coverage.clover

CHANGELOG.md

@@ -0,0 +1,7 @@
+# Changelog
+
+All Notable changes to `doc-to-text` will be documented in this file
+
+## 1.0.0 - 2018-12-04
+
+Initial release

README.md

@@ -0,0 +1,112 @@
+# Extract text from a Word Doc
+
+[![Latest Version on Packagist](https://img.shields.io/packagist/v/jaybizzle/doc-to-text.svg?style=flat-square)](https://packagist.org/packages/jaybizzle/doc-to-text)
+[![Software License](https://img.shields.io/badge/license-MIT-brightgreen.svg?style=flat-square)](LICENSE.md)
+[![Build Status](https://img.shields.io/travis/jaybizzle/doc-to-text/master.svg?style=flat-square)](https://travis-ci.org/jaybizzle/doc-to-text)
+[![SensioLabsInsight](https://img.shields.io/sensiolabs/i/9d85e8dd-b444-4bef-a5d5-faa7f2d8d6bb.svg?style=flat-square)](https://insight.sensiolabs.com/projects/9d85e8dd-b444-4bef-a5d5-faa7f2d8d6bb)
+[![Quality Score](https://img.shields.io/scrutinizer/g/jaybizzle/doc-to-text.svg?style=flat-square)](https://scrutinizer-ci.com/g/jaybizzle/doc-to-text)
+[![Total Downloads](https://img.shields.io/packagist/dt/jaybizzle/doc-to-text.svg?style=flat-square)](https://packagist.org/packages/jaybizzle/doc-to-text)
+
+This package provides a class to extract text from a Word Doc.
+
+```php
+<?php
+
+use Jaybizzle\DocToText\Doc;
+
+echo Doc::getText('book.doc'); // returns the text from the doc
+```
+
+## Requirements
+
+Behind the scenes this package leverages [antiword](https://en.wikipedia.org/wiki/Antiword). You can verify if the binary installed on your system by issuing this command:
+
+```bash
+which antiword
+```
+
+If it is installed it will return the path to the binary.
+
+To install the binary you can use this command on Ubuntu or Debian:
+
+```bash
+apt-get install antiword
+```
+
+## Installation
+
+You can install the package via composer:
+
+```bash
+composer require jaybizzle/doc-to-text
+```
+
+## Usage
+
+Extracting text from a Doc is easy.
+
+```php
+$text = (new Doc())
+ ->setDoc('book.doc')
+ ->text();
+```
+
+Or easier:
+
+```php
+echo Doc::getText('book.doc');
+```
+
+By default the package will assume that the `antiword` command is located at `/usr/bin/antiword`.
+If it is located elsewhere pass its binary path to the constructor
+
+```php
+$text = (new Doc('/custom/path/to/antiword'))
+ ->setDoc('book.doc')
+ ->text();
+```
+
+or as the second parameter to the `getText` static method:
+
+```php
+echo Doc::getText('book.doc', '/custom/path/to/antiword');
+```
+
+Sometimes you may want to use [antiword options](https://linux.die.net/man/1/antiword). To do so you can set them up using the `setOptions` method.
+
+```php
+$text = (new Doc())
+ ->setDoc('table.doc')
+ ->setOptions(['layout', 'r 96'])
+ ->text()
+;
+```
+
+or as the third parameter to the `getText` static method:
+
+```php
+echo Doc::getText('book.doc', null, ['layout', 'opw myP1$$Word']);
+```
+
+## Change log
+
+Please see [CHANGELOG](CHANGELOG.md) for more information about what has changed recently.
+
+## Testing
+
+```bash
+ composer test
+```
+
+## Security
+
+If you discover any security related issues, please email [email protected] instead of using the issue tracker.
+
+## Credits
+
+- [Mark Beech](https://github.com/jaybizzle)
+- [All Contributors](../../contributors)
+
+## License
+
+The MIT License (MIT). Please see [License File](LICENSE.md) for more information.

build/report.junit.xml

@@ -0,0 +1,17 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<testsuites>
+ <testsuite name="Test Suite" tests="10" assertions="10" errors="0" failures="0" skipped="0" time="0.073678">
+ <testsuite name="Jaybizzle\DocToText\Test\DocToTextTest" file="/Users/markbeech/Desktop/doc-to-text/tests/DocToTextTest.php" tests="10" assertions="10" errors="0" failures="0" skipped="0" time="0.073678">
+ <testcase name="it_can_extract_text_from_a_doc" class="Jaybizzle\DocToText\Test\DocToTextTest" classname="Jaybizzle.DocToText.Test.DocToTextTest" file="/Users/markbeech/Desktop/doc-to-text/tests/DocToTextTest.php" line="16" assertions="1" time="0.014135"/>
+ <testcase name="it_provides_a_static_method_to_extract_text" class="Jaybizzle\DocToText\Test\DocToTextTest" classname="Jaybizzle.DocToText.Test.DocToTextTest" file="/Users/markbeech/Desktop/doc-to-text/tests/DocToTextTest.php" line="26" assertions="1" time="0.010763"/>
+ <testcase name="it_can_handle_paths_with_spaces" class="Jaybizzle\DocToText\Test\DocToTextTest" classname="Jaybizzle.DocToText.Test.DocToTextTest" file="/Users/markbeech/Desktop/doc-to-text/tests/DocToTextTest.php" line="32" assertions="1" time="0.006766"/>
+ <testcase name="it_can_handle_paths_with_single_quotes" class="Jaybizzle\DocToText\Test\DocToTextTest" classname="Jaybizzle.DocToText.Test.DocToTextTest" file="/Users/markbeech/Desktop/doc-to-text/tests/DocToTextTest.php" line="40" assertions="1" time="0.007283"/>
+ <testcase name="it_can_handle_doctotext_options_without_starting_hyphen" class="Jaybizzle\DocToText\Test\DocToTextTest" classname="Jaybizzle.DocToText.Test.DocToTextTest" file="/Users/markbeech/Desktop/doc-to-text/tests/DocToTextTest.php" line="48" assertions="1" time="0.007513"/>
+ <testcase name="it_can_handle_doctotext_options_with_starting_hyphen" class="Jaybizzle\DocToText\Test\DocToTextTest" classname="Jaybizzle.DocToText.Test.DocToTextTest" file="/Users/markbeech/Desktop/doc-to-text/tests/DocToTextTest.php" line="59" assertions="1" time="0.006695"/>
+ <testcase name="it_can_handle_doctotext_options_with_mixed_hyphen_status" class="Jaybizzle\DocToText\Test\DocToTextTest" classname="Jaybizzle.DocToText.Test.DocToTextTest" file="/Users/markbeech/Desktop/doc-to-text/tests/DocToTextTest.php" line="70" assertions="1" time="0.008278"/>
+ <testcase name="it_will_throw_an_exception_when_the_doc_is_not_found" class="Jaybizzle\DocToText\Test\DocToTextTest" classname="Jaybizzle.DocToText.Test.DocToTextTest" file="/Users/markbeech/Desktop/doc-to-text/tests/DocToTextTest.php" line="81" assertions="1" time="0.000954"/>
+ <testcase name="it_will_throw_an_exception_when_the_binary_is_not_found" class="Jaybizzle\DocToText\Test\DocToTextTest" classname="Jaybizzle.DocToText.Test.DocToTextTest" file="/Users/markbeech/Desktop/doc-to-text/tests/DocToTextTest.php" line="91" assertions="1" time="0.004240"/>
+ <testcase name="it_will_throw_an_exception_when_the_option_is_unknown" class="Jaybizzle\DocToText\Test\DocToTextTest" classname="Jaybizzle.DocToText.Test.DocToTextTest" file="/Users/markbeech/Desktop/doc-to-text/tests/DocToTextTest.php" line="101" assertions="1" time="0.007051"/>
+ </testsuite>
+ </testsuite>
+</testsuites>

composer.json

@@ -0,0 +1,38 @@
+{
+ "name": "jaybizzle/doc-to-text",
+ "description": "Extract text from a pdf",
+ "keywords": [
+ "jaybiizle",
+ "doc-to-text"
+ ],
+ "homepage": "https://github.com/jaybizzle/doc-to-text",
+ "license": "MIT",
+ "authors": [
+ {
+ "name": "Mark Beech",
+ "email": "[email protected]",
+ "homepage": "https://www.mark-beech.co.uk",
+ "role": "Developer"
+ }
+ ],
+ "require": {
+ "php" : "^7.0",
+ "symfony/process": "^3.3|^4.0"
+ },
+ "require-dev": {
+ "phpunit/phpunit" : "^6.4|^7.0"
+ },
+ "autoload": {
+ "psr-4": {
+ "Jaybizzle\\DocToText\\": "src"
+ }
+ },
+ "autoload-dev": {
+ "psr-4": {
+ "Jaybizzle\\DocToText\\Test\\": "tests"
+ }
+ },
+ "scripts": {
+ "test": "phpunit"
+ }
+}