Merge branch 'dev/2.1.0' into magikid-patch-1

Author: paquettg

CHANGELOG.md

@@ -1,114 +1,17 @@
 ### Development
 
-## 1.7.0
+All notable changes to this project will be documented in this file.
 
-- Added .scrutinizer.yml to repo
-- Reformated code to PSR-1/2
-- Improved the test coverage and some small code changes
-- Added removeAttribute and removeAllAttributes tag methods fixes #57
-- Added replaceNode method implements #52
-- Added a delete method. fixes #43
-- Added semicolon after &#10 for linebreak preservation. fixes #62
-- Removed code that removed <code> tag fixes #60
-- Added new test related to #63
-- Refactored the nodes into inner and leaf nodes
-- Fixed Strings example in README
-- Close this header so the markdown will render properly
-- Added preserve line break option. Defaults to false.
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
 
-## 1.6.9
+### Added
+- New `removeSmartyScripts` configuration setting. Defaults to true.
+- Added `declare(strict_types=1)` to all source files.
 
-- Added Changelog
-- Fixed issue with spaces befor closing tag Fixes #45
-- Fixed some code quality issues found by scrutinizer
-- Added Scrutinizer to README
-- Reformated code to comply with PSR-1/2
-- Added preserve line break option. Defaults to false. fixes #40
-- Updated the tests
-- Added options: cleanupInput, removeScripts and removeStyles
-
-## 1.6.8
-
-- Added comments and reformated some code
-- Added support for non-escaped quotes in attribute value fixes #37
-- Cleaned up the comments and php docs
-- Removed version in composer json
-- Updated composer version
-- Refactoring out isChild method.
-- Updated in code documentation
-- Updated composer
-
-$$ 1.6.7
-
-- Added tests for the new array access
-- Added feature to allow array usage of html node. fixes #26
-- Update HtmlNode.php
-- Added test to cover issue #28
-- FIX: File name is longer than the maximum allowed path
-
-## 1.6.6
-
-- Replaced preg_replace with mb_ereg_replace
-- Added child selector fixes #24
-- Updated the dev version of phpunit
-
-## 1.6.5
-
-- Fixed bug when no attribute tags are last tag (with out space). fixes #16
-- Fixed some documentation inconsistencies fixes #15
-- Made loadStr a public methor Fixes #18
-- Update a problem with the README fixes #11
-- Added setAttribute to the node fixes #7
-- Check if open_basedir is enabled: Dont use CURLOPT_FOLLOWLOCATION
-
-## 1.6.4
-
-- Added tests and updated README
-- Updated the tests and moved some files
-- Added the option to enforce the encoding
-- Fixed a problem with handeling the unknown child exception
-- Updated some tests
-- Added coverall badge and package
-
-## 1.6.3
-
-- Added initial support for 'strict' parsing option
-- Added an optional paramter to enable recursive text
-- Added appropriat Options tests
-- Changed all exception to specific objects
-- Added a whitespaceTextNode option and test
-- Added support for an options array
-
-## 1.6.2
-
-- Standardised indentation for easyer reading on github
-- Update AbstractNode.php
-- Added a test for hhvm in my travis.yml
-- Added a LICENSE.md file for MIT
-- Added build status to README
-- Added travis.yml
-- Changed the file name of the abstract node
-- fixed code in collection class where instance of arrayIterator is to be rturned
-- Updated documentation
-- Added a curl interface and a simple curl class.
-- Removed the Guzzle dependancy
-- Abstracted the Node class as it should have been done in the first place
-- Added integrity checks for the cached html
-- Added some basic caching of the dom html
-- Added a toArray() method to the collection and a test
-
-## 1.6.1
-
-- Moved back to using guzzle so expections are thrown when their was an error with loading a url
-- Added tests for the Static Facade Fixed a few issues brought to light from the new tests
-- Added a static facade
-- Changed encoding to be a local attribute instead of a static attribute
-- Solved issue #2 When you attempt to load an html page from a URL using loadFromUrl the encoding is incorrect.
-- Added easyer loading of files and urls. Still have a problem with encoding while loading from url.
-- Added guzzle and loadFromUrl option
-- Fixed an issue with no value attributes
-- Added magic and each methods to the collection. Plus some tests
-- Added a collection object
-- Added charset encoding
-- fixed a bug with closing tags If a closing tag did not have an opening tag it would cause the scan to end instead of ignoring the closing tag.
+### Changed
+- Started using a changelog.
+- Fixed bug that caused an infinite loop when no content found in tags.
+- Moved the Mock object to the tests directory, where it belongs.

README.md

@@ -172,6 +172,11 @@ Preserves Line Breaks if set to `true`. If set to `false` line breaks are cleane
 
 Set this to `false` if you want to preserve whitespace inside of text nodes. It is set to `true` by default.
 
+
+**removeSmartyScripts**
+
+Set this to `false` if you want to preserve smarty sccript found in the html content. It is set to `true` by default.
+
 Static Facade
 -------------
 

src/PHPHtmlParser/Content.php

@@ -1,4 +1,4 @@
-<?php
+<?php declare(strict_types=1);
 namespace PHPHtmlParser;
 
 /**

src/PHPHtmlParser/Curl.php

@@ -1,4 +1,4 @@
-<?php
+<?php declare(strict_types=1);
 namespace PHPHtmlParser;
 
 use PHPHtmlParser\Exceptions\CurlException;

src/PHPHtmlParser/CurlInterface.php

@@ -1,4 +1,4 @@
-<?php
+<?php declare(strict_types=1);
 namespace PHPHtmlParser;
 
 /**

src/PHPHtmlParser/Dom.php

@@ -1,4 +1,4 @@
-<?php
+<?php declare(strict_types=1);
 namespace PHPHtmlParser;
 
 use PHPHtmlParser\Dom\AbstractNode;
@@ -502,24 +502,26 @@ protected function clean(string $str): string
         $str = mb_eregi_replace("<!\[CDATA\[(.*?)\]\]>", '', $str);
 
         // strip out <script> tags
-        if ($this->options->get('removeScripts') == true) {
+        if ($this->options->get('removeScripts')) {
             $str = mb_eregi_replace("<\s*script[^>]*[^/]>(.*?)<\s*/\s*script\s*>", '', $str);
             $str = mb_eregi_replace("<\s*script\s*>(.*?)<\s*/\s*script\s*>", '', $str);
         }
 
         // strip out <style> tags
-        if ($this->options->get('removeStyles') == true) {
+        if ($this->options->get('removeStyles')) {
             $str = mb_eregi_replace("<\s*style[^>]*[^/]>(.*?)<\s*/\s*style\s*>", '', $str);
             $str = mb_eregi_replace("<\s*style\s*>(.*?)<\s*/\s*style\s*>", '', $str);
         }
 
         // strip out server side scripts
-        if ($this->options->get('serverSideScriptis') == true){
+        if ($this->options->get('serverSideScripts')) {
             $str = mb_eregi_replace("(<\?)(.*?)(\?>)", '', $str);
         }
 
         // strip smarty scripts
-        $str = mb_eregi_replace("(\{\w)(.*?)(\})", '', $str);
+        if ($this->options->get('removeSmartyScripts')) {
+            $str = mb_eregi_replace("(\{\w)(.*?)(\})", '', $str);
+        }
 
         return $str;
     }
@@ -626,6 +628,11 @@ protected function parseTag(): array
         }
 
         $tag  = strtolower($this->content->copyByToken('slash', true));
+        if (trim($tag) == '')
+        {
+            // no tag found, invalide < found
+            return $return;
+        }
         $node = new HtmlNode($tag);
 
         // attributes

src/PHPHtmlParser/Dom/AbstractNode.php

@@ -1,4 +1,4 @@
-<?php
+<?php declare(strict_types=1);
 namespace PHPHtmlParser\Dom;
 
 use PHPHtmlParser\Exceptions\CircularException;

src/PHPHtmlParser/Dom/ArrayNode.php

@@ -1,4 +1,4 @@
-<?php
+<?php declare(strict_types=1);
 namespace PHPHtmlParser\Dom;
 
 use Countable;

src/PHPHtmlParser/Dom/Collection.php

@@ -1,4 +1,4 @@
-<?php
+<?php declare(strict_types=1);
 namespace PHPHtmlParser\Dom;
 
 use ArrayAccess;

src/PHPHtmlParser/Dom/HtmlNode.php

@@ -1,4 +1,4 @@
-<?php
+<?php declare(strict_types=1);
 namespace PHPHtmlParser\Dom;
 
 use PHPHtmlParser\Exceptions\UnknownChildTypeException;