Replace Mardownify library with html-to-markdown library.

This commit is contained in:
Klaus Weidenbach 2017-05-23 00:32:11 +02:00
parent 50e9d02458
commit 547df2219a
44 changed files with 2379 additions and 3359 deletions

View File

@ -30,10 +30,10 @@
"ext-openssl" : "*",
"sabre/dav" : "~3.2",
"michelf/php-markdown" : "^1.7",
"pixel418/markdownify": "^2.2",
"bshaffer/oauth2-server-php": "^1.9",
"ezyang/htmlpurifier": "^4.9",
"simplepie/simplepie": "~1.5"
"simplepie/simplepie": "~1.5",
"league/html-to-markdown": "^4.4"
},
"require-dev" : {
"php" : ">=7.0",

122
composer.lock generated
View File

@ -4,7 +4,7 @@
"Read more about it at https://getcomposer.org/doc/01-basic-usage.md#composer-lock-the-lock-file",
"This file is @generated automatically"
],
"content-hash": "21511c39f481ecdc20210f885d840787",
"content-hash": "527df9ff589187351b62bffb0c38e3a6",
"packages": [
{
"name": "bshaffer/oauth2-server-php",
@ -109,6 +109,70 @@
],
"time": "2017-03-13T06:30:53+00:00"
},
{
"name": "league/html-to-markdown",
"version": "4.4.1",
"source": {
"type": "git",
"url": "https://github.com/thephpleague/html-to-markdown.git",
"reference": "82ea375b5b2b1da1da222644c0565c695bf88186"
},
"dist": {
"type": "zip",
"url": "https://api.github.com/repos/thephpleague/html-to-markdown/zipball/82ea375b5b2b1da1da222644c0565c695bf88186",
"reference": "82ea375b5b2b1da1da222644c0565c695bf88186",
"shasum": ""
},
"require": {
"ext-dom": "*",
"ext-xml": "*",
"php": ">=5.3.3"
},
"require-dev": {
"mikehaertl/php-shellcommand": "~1.1.0",
"phpunit/phpunit": "4.*",
"scrutinizer/ocular": "~1.1"
},
"bin": [
"bin/html-to-markdown"
],
"type": "library",
"extra": {
"branch-alias": {
"dev-master": "4.5-dev"
}
},
"autoload": {
"psr-4": {
"League\\HTMLToMarkdown\\": "src/"
}
},
"notification-url": "https://packagist.org/downloads/",
"license": [
"MIT"
],
"authors": [
{
"name": "Colin O'Dell",
"email": "colinodell@gmail.com",
"homepage": "http://www.colinodell.com",
"role": "Lead Developer"
},
{
"name": "Nick Cernis",
"email": "nick@cern.is",
"homepage": "http://modernnerd.net",
"role": "Original Author"
}
],
"description": "An HTML-to-markdown conversion helper for PHP",
"homepage": "https://github.com/thephpleague/html-to-markdown",
"keywords": [
"html",
"markdown"
],
"time": "2017-03-16T00:45:59+00:00"
},
{
"name": "michelf/php-markdown",
"version": "1.7.0",
@ -160,62 +224,6 @@
],
"time": "2016-10-29T18:58:20+00:00"
},
{
"name": "pixel418/markdownify",
"version": "v2.2.1",
"source": {
"type": "git",
"url": "https://github.com/Elephant418/Markdownify.git",
"reference": "0160677f04c784550dd10fd72fdf3994967db848"
},
"dist": {
"type": "zip",
"url": "https://api.github.com/repos/Elephant418/Markdownify/zipball/0160677f04c784550dd10fd72fdf3994967db848",
"reference": "0160677f04c784550dd10fd72fdf3994967db848",
"shasum": ""
},
"require": {
"php": ">=5.3.0"
},
"require-dev": {
"phpunit/phpunit": "^4.8"
},
"type": "lib",
"autoload": {
"psr-4": {
"Markdownify\\": "src",
"Test\\Markdownify\\": "test"
}
},
"notification-url": "https://packagist.org/downloads/",
"license": [
"LGPL"
],
"authors": [
{
"name": "Peter Kruithof",
"email": "pkruithof@gmail.com",
"homepage": "http://pkruithof.tumblr.com/"
},
{
"name": "Milian Wolff",
"email": "mail@milianw.de",
"homepage": "http://milianw.de"
},
{
"name": "Thomas Zilliox",
"email": "hello@tzi.fr",
"homepage": "http://tzi.fr"
}
],
"description": "The HTML to Markdown converter for PHP ",
"homepage": "https://github.com/elephant418/Markdownify",
"keywords": [
"markdown",
"markdownify"
],
"time": "2016-09-21T13:01:43+00:00"
},
{
"name": "psr/log",
"version": "1.0.2",

View File

@ -5,7 +5,7 @@
*/
use Michelf\MarkdownExtra;
use Markdownify\Converter;
use League\HTMLToMarkdown\HtmlConverter;
require_once("include/oembed.php");
require_once("include/event.php");
@ -495,9 +495,8 @@ function bb2diaspora($Text, $preserve_nl = false, $fordiaspora = true) {
$Text = str_replace(array('<','>','&'),array('&_lt_;','&_gt_;','&_amp_;'),$Text);
// Now convert HTML to Markdown
$md = new Converter(Converter::LINK_AFTER_CONTENT, false, false);
$Text = $md->parseString($Text);
$md = new HtmlConverter();
$Text = $md->convert($Text);
// It also adds backslashes to our attempt at getting around the html entity preservation for some weird reason.

1
vendor/bin/html-to-markdown vendored Symbolic link
View File

@ -0,0 +1 @@
../league/html-to-markdown/bin/html-to-markdown

View File

@ -241,9 +241,29 @@ return array(
'HTMLPurifier_VarParser_Native' => $vendorDir . '/ezyang/htmlpurifier/library/HTMLPurifier/VarParser/Native.php',
'HTMLPurifier_Zipper' => $vendorDir . '/ezyang/htmlpurifier/library/HTMLPurifier/Zipper.php',
'Hubzilla\\Import\\Import' => $baseDir . '/include/Import/Importer.php',
'Markdownify\\Converter' => $vendorDir . '/pixel418/markdownify/src/Converter.php',
'Markdownify\\ConverterExtra' => $vendorDir . '/pixel418/markdownify/src/ConverterExtra.php',
'Markdownify\\Parser' => $vendorDir . '/pixel418/markdownify/src/Parser.php',
'League\\HTMLToMarkdown\\Configuration' => $vendorDir . '/league/html-to-markdown/src/Configuration.php',
'League\\HTMLToMarkdown\\ConfigurationAwareInterface' => $vendorDir . '/league/html-to-markdown/src/ConfigurationAwareInterface.php',
'League\\HTMLToMarkdown\\Converter\\BlockquoteConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/BlockquoteConverter.php',
'League\\HTMLToMarkdown\\Converter\\CodeConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/CodeConverter.php',
'League\\HTMLToMarkdown\\Converter\\CommentConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/CommentConverter.php',
'League\\HTMLToMarkdown\\Converter\\ConverterInterface' => $vendorDir . '/league/html-to-markdown/src/Converter/ConverterInterface.php',
'League\\HTMLToMarkdown\\Converter\\DefaultConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/DefaultConverter.php',
'League\\HTMLToMarkdown\\Converter\\DivConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/DivConverter.php',
'League\\HTMLToMarkdown\\Converter\\EmphasisConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/EmphasisConverter.php',
'League\\HTMLToMarkdown\\Converter\\HardBreakConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/HardBreakConverter.php',
'League\\HTMLToMarkdown\\Converter\\HeaderConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/HeaderConverter.php',
'League\\HTMLToMarkdown\\Converter\\HorizontalRuleConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/HorizontalRuleConverter.php',
'League\\HTMLToMarkdown\\Converter\\ImageConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/ImageConverter.php',
'League\\HTMLToMarkdown\\Converter\\LinkConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/LinkConverter.php',
'League\\HTMLToMarkdown\\Converter\\ListBlockConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/ListBlockConverter.php',
'League\\HTMLToMarkdown\\Converter\\ListItemConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/ListItemConverter.php',
'League\\HTMLToMarkdown\\Converter\\ParagraphConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/ParagraphConverter.php',
'League\\HTMLToMarkdown\\Converter\\PreformattedConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/PreformattedConverter.php',
'League\\HTMLToMarkdown\\Converter\\TextConverter' => $vendorDir . '/league/html-to-markdown/src/Converter/TextConverter.php',
'League\\HTMLToMarkdown\\Element' => $vendorDir . '/league/html-to-markdown/src/Element.php',
'League\\HTMLToMarkdown\\ElementInterface' => $vendorDir . '/league/html-to-markdown/src/ElementInterface.php',
'League\\HTMLToMarkdown\\Environment' => $vendorDir . '/league/html-to-markdown/src/Environment.php',
'League\\HTMLToMarkdown\\HtmlConverter' => $vendorDir . '/league/html-to-markdown/src/HtmlConverter.php',
'Michelf\\Markdown' => $vendorDir . '/michelf/php-markdown/Michelf/Markdown.php',
'Michelf\\MarkdownExtra' => $vendorDir . '/michelf/php-markdown/Michelf/MarkdownExtra.php',
'Michelf\\MarkdownInterface' => $vendorDir . '/michelf/php-markdown/Michelf/MarkdownInterface.php',

View File

@ -7,7 +7,6 @@ $baseDir = dirname($vendorDir);
return array(
'Zotlabs\\' => array($baseDir . '/Zotlabs'),
'Test\\Markdownify\\' => array($vendorDir . '/pixel418/markdownify/test'),
'Sabre\\Xml\\' => array($vendorDir . '/sabre/xml/lib'),
'Sabre\\VObject\\' => array($vendorDir . '/sabre/vobject/lib'),
'Sabre\\Uri\\' => array($vendorDir . '/sabre/uri/lib'),
@ -18,6 +17,6 @@ return array(
'Sabre\\CardDAV\\' => array($vendorDir . '/sabre/dav/lib/CardDAV'),
'Sabre\\CalDAV\\' => array($vendorDir . '/sabre/dav/lib/CalDAV'),
'Psr\\Log\\' => array($vendorDir . '/psr/log/Psr/Log'),
'Markdownify\\' => array($vendorDir . '/pixel418/markdownify/src'),
'League\\HTMLToMarkdown\\' => array($vendorDir . '/league/html-to-markdown/src'),
'Hubzilla\\' => array($baseDir . '/include'),
);

View File

@ -22,10 +22,6 @@ class ComposerStaticInit7b34d7e50a62201ec5d5e526a5b8b35d
array (
'Zotlabs\\' => 8,
),
'T' =>
array (
'Test\\Markdownify\\' => 17,
),
'S' =>
array (
'Sabre\\Xml\\' => 10,
@ -42,9 +38,9 @@ class ComposerStaticInit7b34d7e50a62201ec5d5e526a5b8b35d
array (
'Psr\\Log\\' => 8,
),
'M' =>
'L' =>
array (
'Markdownify\\' => 12,
'League\\HTMLToMarkdown\\' => 22,
),
'H' =>
array (
@ -57,10 +53,6 @@ class ComposerStaticInit7b34d7e50a62201ec5d5e526a5b8b35d
array (
0 => __DIR__ . '/../..' . '/Zotlabs',
),
'Test\\Markdownify\\' =>
array (
0 => __DIR__ . '/..' . '/pixel418/markdownify/test',
),
'Sabre\\Xml\\' =>
array (
0 => __DIR__ . '/..' . '/sabre/xml/lib',
@ -101,9 +93,9 @@ class ComposerStaticInit7b34d7e50a62201ec5d5e526a5b8b35d
array (
0 => __DIR__ . '/..' . '/psr/log/Psr/Log',
),
'Markdownify\\' =>
'League\\HTMLToMarkdown\\' =>
array (
0 => __DIR__ . '/..' . '/pixel418/markdownify/src',
0 => __DIR__ . '/..' . '/league/html-to-markdown/src',
),
'Hubzilla\\' =>
array (
@ -378,9 +370,29 @@ class ComposerStaticInit7b34d7e50a62201ec5d5e526a5b8b35d
'HTMLPurifier_VarParser_Native' => __DIR__ . '/..' . '/ezyang/htmlpurifier/library/HTMLPurifier/VarParser/Native.php',
'HTMLPurifier_Zipper' => __DIR__ . '/..' . '/ezyang/htmlpurifier/library/HTMLPurifier/Zipper.php',
'Hubzilla\\Import\\Import' => __DIR__ . '/../..' . '/include/Import/Importer.php',
'Markdownify\\Converter' => __DIR__ . '/..' . '/pixel418/markdownify/src/Converter.php',
'Markdownify\\ConverterExtra' => __DIR__ . '/..' . '/pixel418/markdownify/src/ConverterExtra.php',
'Markdownify\\Parser' => __DIR__ . '/..' . '/pixel418/markdownify/src/Parser.php',
'League\\HTMLToMarkdown\\Configuration' => __DIR__ . '/..' . '/league/html-to-markdown/src/Configuration.php',
'League\\HTMLToMarkdown\\ConfigurationAwareInterface' => __DIR__ . '/..' . '/league/html-to-markdown/src/ConfigurationAwareInterface.php',
'League\\HTMLToMarkdown\\Converter\\BlockquoteConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/BlockquoteConverter.php',
'League\\HTMLToMarkdown\\Converter\\CodeConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/CodeConverter.php',
'League\\HTMLToMarkdown\\Converter\\CommentConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/CommentConverter.php',
'League\\HTMLToMarkdown\\Converter\\ConverterInterface' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/ConverterInterface.php',
'League\\HTMLToMarkdown\\Converter\\DefaultConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/DefaultConverter.php',
'League\\HTMLToMarkdown\\Converter\\DivConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/DivConverter.php',
'League\\HTMLToMarkdown\\Converter\\EmphasisConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/EmphasisConverter.php',
'League\\HTMLToMarkdown\\Converter\\HardBreakConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/HardBreakConverter.php',
'League\\HTMLToMarkdown\\Converter\\HeaderConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/HeaderConverter.php',
'League\\HTMLToMarkdown\\Converter\\HorizontalRuleConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/HorizontalRuleConverter.php',
'League\\HTMLToMarkdown\\Converter\\ImageConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/ImageConverter.php',
'League\\HTMLToMarkdown\\Converter\\LinkConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/LinkConverter.php',
'League\\HTMLToMarkdown\\Converter\\ListBlockConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/ListBlockConverter.php',
'League\\HTMLToMarkdown\\Converter\\ListItemConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/ListItemConverter.php',
'League\\HTMLToMarkdown\\Converter\\ParagraphConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/ParagraphConverter.php',
'League\\HTMLToMarkdown\\Converter\\PreformattedConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/PreformattedConverter.php',
'League\\HTMLToMarkdown\\Converter\\TextConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/Converter/TextConverter.php',
'League\\HTMLToMarkdown\\Element' => __DIR__ . '/..' . '/league/html-to-markdown/src/Element.php',
'League\\HTMLToMarkdown\\ElementInterface' => __DIR__ . '/..' . '/league/html-to-markdown/src/ElementInterface.php',
'League\\HTMLToMarkdown\\Environment' => __DIR__ . '/..' . '/league/html-to-markdown/src/Environment.php',
'League\\HTMLToMarkdown\\HtmlConverter' => __DIR__ . '/..' . '/league/html-to-markdown/src/HtmlConverter.php',
'Michelf\\Markdown' => __DIR__ . '/..' . '/michelf/php-markdown/Michelf/Markdown.php',
'Michelf\\MarkdownExtra' => __DIR__ . '/..' . '/michelf/php-markdown/Michelf/MarkdownExtra.php',
'Michelf\\MarkdownInterface' => __DIR__ . '/..' . '/michelf/php-markdown/Michelf/MarkdownInterface.php',

View File

@ -434,64 +434,6 @@
"markdown"
]
},
{
"name": "pixel418/markdownify",
"version": "v2.2.1",
"version_normalized": "2.2.1.0",
"source": {
"type": "git",
"url": "https://github.com/Elephant418/Markdownify.git",
"reference": "0160677f04c784550dd10fd72fdf3994967db848"
},
"dist": {
"type": "zip",
"url": "https://api.github.com/repos/Elephant418/Markdownify/zipball/0160677f04c784550dd10fd72fdf3994967db848",
"reference": "0160677f04c784550dd10fd72fdf3994967db848",
"shasum": ""
},
"require": {
"php": ">=5.3.0"
},
"require-dev": {
"phpunit/phpunit": "^4.8"
},
"time": "2016-09-21T13:01:43+00:00",
"type": "lib",
"installation-source": "dist",
"autoload": {
"psr-4": {
"Markdownify\\": "src",
"Test\\Markdownify\\": "test"
}
},
"notification-url": "https://packagist.org/downloads/",
"license": [
"LGPL"
],
"authors": [
{
"name": "Peter Kruithof",
"email": "pkruithof@gmail.com",
"homepage": "http://pkruithof.tumblr.com/"
},
{
"name": "Milian Wolff",
"email": "mail@milianw.de",
"homepage": "http://milianw.de"
},
{
"name": "Thomas Zilliox",
"email": "hello@tzi.fr",
"homepage": "http://tzi.fr"
}
],
"description": "The HTML to Markdown converter for PHP ",
"homepage": "https://github.com/elephant418/Markdownify",
"keywords": [
"markdown",
"markdownify"
]
},
{
"name": "bshaffer/oauth2-server-php",
"version": "v1.9.0",
@ -748,5 +690,71 @@
"framework",
"iCalendar"
]
},
{
"name": "league/html-to-markdown",
"version": "4.4.1",
"version_normalized": "4.4.1.0",
"source": {
"type": "git",
"url": "https://github.com/thephpleague/html-to-markdown.git",
"reference": "82ea375b5b2b1da1da222644c0565c695bf88186"
},
"dist": {
"type": "zip",
"url": "https://api.github.com/repos/thephpleague/html-to-markdown/zipball/82ea375b5b2b1da1da222644c0565c695bf88186",
"reference": "82ea375b5b2b1da1da222644c0565c695bf88186",
"shasum": ""
},
"require": {
"ext-dom": "*",
"ext-xml": "*",
"php": ">=5.3.3"
},
"require-dev": {
"mikehaertl/php-shellcommand": "~1.1.0",
"phpunit/phpunit": "4.*",
"scrutinizer/ocular": "~1.1"
},
"time": "2017-03-16T00:45:59+00:00",
"bin": [
"bin/html-to-markdown"
],
"type": "library",
"extra": {
"branch-alias": {
"dev-master": "4.5-dev"
}
},
"installation-source": "dist",
"autoload": {
"psr-4": {
"League\\HTMLToMarkdown\\": "src/"
}
},
"notification-url": "https://packagist.org/downloads/",
"license": [
"MIT"
],
"authors": [
{
"name": "Colin O'Dell",
"email": "colinodell@gmail.com",
"homepage": "http://www.colinodell.com",
"role": "Lead Developer"
},
{
"name": "Nick Cernis",
"email": "nick@cern.is",
"homepage": "http://modernnerd.net",
"role": "Original Author"
}
],
"description": "An HTML-to-markdown conversion helper for PHP",
"homepage": "https://github.com/thephpleague/html-to-markdown",
"keywords": [
"html",
"markdown"
]
}
]

View File

@ -0,0 +1,214 @@
# Change Log
All notable changes to this project will be documented in this file.
Updates should follow the [Keep a CHANGELOG](http://keepachangelog.com/) principles.
## [Unreleased][unreleased]
## [4.4.1]
### Fixed
- Fixed autolinking of invalid URLs (#129)
## [4.4.0]
### Added
- Added `hard_break` configuration option (#112, #115)
- The `HtmlConverter` can now be instantiated with an `Environment` (#118)
### Fixed
- Fixed handling of paragraphs in list item elements (#47, #110)
- Fixed phantom spaces when newlines follow `br` elements (#116, #117)
- Fixed link converter not sanitizing inner spaces properly (#119, #120)
## [4.3.1]
### Changed
- Revised the sanitization implementation (#109)
### Fixed
- Fixed tag-like content not being escaped (#67, #109)
- Fixed thematic break-like content not being escaped (#65, #109)
- Fixed codefence-like content not being escaped (#64, #109)
## [4.3.0]
### Added
- Added full support for PHP 7.0 and 7.1
### Changed
- Changed `<pre>` and `<pre><code>` conversions to use backticks instead of indendation (#102)
### Fixed
- Fixed issue where specified code language was not preserved (#70, #102)
- Fixed issue where `<code>` tags nested in `<pre>` was not converted properly (#70, #102)
- Fixed header-like content not being escaped (#76, #105)
- Fixed blockquote-like content not being escaped (#77, #103)
- Fixed ordered list-like content not being escaped (#73, #106)
- Fixed unordered list-like content not being escaped (#71, #107)
## [4.2.2]
### Fixed
- Fixed sanitization bug which sometimes removes desired content (#63, #101)
## [4.2.1]
### Fixed
- Fixed path to autoload.php when used as a library (#98)
- Fixed edge case for tags containing only whitespace (#99)
### Removed
- Removed double HTML entity decoding, as this is not desireable (#60)
## [4.2.0]
### Added
- Added the ability to invoke HtmlConverter objects as functions (#85)
### Fixed
- Fixed improper handling of nested list items (#19 and #84)
- Fixed preceeding or trailing spaces within emphasis tags (#83)
## [4.1.1]
### Fixed
- Fixed conversion of empty paragraphs (#78)
- Fixed `preg_replace` so it wouldn't break UTF-8 characters (#79)
## [4.1.0]
### Added
- Added `bin/html-to-markdown` script
### Changed
- Changed default italic character to `_` (#58)
## [4.0.1]
### Fixed
- Added escaping to avoid * and _ in a text being rendered as emphasis (#48)
### Removed
- Removed the demo (#51)
- `.styleci.yml` and `CONTRIBUTING.md` are no longer included in distributions (#50)
## [4.0.0]
This release changes the visibility of several methods/properties. #42 and #43 brought to light that some visiblities were
not ideally set, so this releases fixes that. Moving forwards this should reduce the chance of introducing BC-breaking changes.
### Added
- Added new `HtmlConverter::getEnvironment()` method to expose the `Environment` (#42, #43)
### Changed
- Changed `Environment::addConverter()` from `protected` to `public`, enabling custom converters to be added (#42, #43)
- Changed `HtmlConverter::createDOMDocument()` from `protected` to `private`
- Changed `Element::nextCached` from `protected` to `private`
- Made the `Environment` class `final`
## [3.1.1]
### Fixed
- Empty HTML strings now result in empty Markdown documents (#40, #41)
## [3.1.0]
### Added
- Added new `equals` method to `Element` to check for equality
### Changes
- Use Linux line endings consistently instead of plaform-specific line endings (#36)
### Fixed
- Cleaned up code style
## [3.0.0]
### Changed
- Changed namespace to `League\HTMLToMarkdown`
- Changed packagist name to `league/html-to-markdown`
- Re-organized code into several separate classes
- `<a>` tags with identical href and inner text are now rendered using angular bracket syntax (#31)
- `<div>` elements are now treated as block-level elements (#33)
## [2.2.2]
### Added
- Added support for PHP 5.6 and HHVM
- Enabled testing against PHP 7 nightlies
- Added this CHANGELOG.md
### Fixed
- Fixed whitespace preservation between inline elements (#9 and #10)
## [2.2.1]
### Fixed
- Preserve placeholder links (#22)
## [2.2.0]
### Added
- Added CircleCI config
### Changed
- `<pre>` blocks are now treated as code elements
### Removed
- Dropped support for PHP 5.2
- Removed incorrect README comment regarding `#text` nodes (#17)
## [2.1.2]
### Added
- Added the ability to blacklist/remove specific node types (#11)
### Changed
- Line breaks are now placed after divs instead of before them
- Newlines inside of link texts are now removed
- Updated the minimum PHPUnit version to 4.*
## [2.1.1]
### Added
- Added options to customize emphasis characters
## [2.1.0]
### Added
- Added option to strip HTML tags without Markdown equivalents
- Added `convert()` method for converter reuse
- Added ability to set options after instance construction
- Documented the required PHP extensions (#4)
### Changed
- ATX style now used for h1 and h2 tags inside blockquotes
### Fixed
- Newlines inside blockquotes are now started with a bracket
- Fixed some incorrect docblocks
- `__toString()` now returns an empty string if input is empty
- Convert head tag if body tag is empty (#7)
- Preserve special characters inside tags without md equivalents (#6)
## [2.0.1]
### Fixed
- Fixed first line indentation for multi-line code blocks
- Fixed consecutive anchors get separating spaces stripped (#3)
## [2.0.0]
### Added
- Initial release
[unreleased]: https://github.com/thephpleague/html-to-markdown/compare/4.4.1...master
[4.4.1]: https://github.com/thephpleague/html-to-markdown/compare/4.4.0...4.4.1
[4.4.0]: https://github.com/thephpleague/html-to-markdown/compare/4.3.1...4.4.0
[4.3.1]: https://github.com/thephpleague/html-to-markdown/compare/4.3.0...4.3.1
[4.3.0]: https://github.com/thephpleague/html-to-markdown/compare/4.2.2...4.3.0
[4.2.2]: https://github.com/thephpleague/html-to-markdown/compare/4.2.1...4.2.2
[4.2.1]: https://github.com/thephpleague/html-to-markdown/compare/4.2.0...4.2.1
[4.2.0]: https://github.com/thephpleague/html-to-markdown/compare/4.1.1...4.2.0
[4.1.1]: https://github.com/thephpleague/html-to-markdown/compare/4.1.0...4.1.1
[4.1.0]: https://github.com/thephpleague/html-to-markdown/compare/4.0.1...4.1.0
[4.0.1]: https://github.com/thephpleague/html-to-markdown/compare/4.0.0...4.0.1
[4.0.0]: https://github.com/thephpleague/html-to-markdown/compare/3.1.1...4.0.0
[3.1.1]: https://github.com/thephpleague/html-to-markdown/compare/3.1.0...3.1.1
[3.1.0]: https://github.com/thephpleague/html-to-markdown/compare/3.0.0...3.1.0
[3.0.0]: https://github.com/thephpleague/html-to-markdown/compare/2.2.2...3.0.0
[2.2.2]: https://github.com/thephpleague/html-to-markdown/compare/2.2.1...2.2.2
[2.2.1]: https://github.com/thephpleague/html-to-markdown/compare/2.2.0...2.2.1
[2.2.0]: https://github.com/thephpleague/html-to-markdown/compare/2.1.2...2.2.0
[2.1.2]: https://github.com/thephpleague/html-to-markdown/compare/2.1.1...2.1.2
[2.1.1]: https://github.com/thephpleague/html-to-markdown/compare/2.1.0...2.1.1
[2.1.0]: https://github.com/thephpleague/html-to-markdown/compare/2.0.1...2.1.0
[2.0.1]: https://github.com/thephpleague/html-to-markdown/compare/2.0.0...2.0.1
[2.0.0]: https://github.com/thephpleague/html-to-markdown/compare/775f91e...2.0.0

View File

@ -0,0 +1,22 @@
# Contributor Code of Conduct
As contributors and maintainers of this project, and in the interest of fostering an open and welcoming community, we pledge to respect all people who contribute through reporting issues, posting feature requests, updating documentation, submitting pull requests or patches, and other activities.
We are committed to making participation in this project a harassment-free experience for everyone, regardless of level of experience, gender, gender identity and expression, sexual orientation, disability, personal appearance, body size, race, ethnicity, age, religion, or nationality.
Examples of unacceptable behavior by participants include:
* The use of sexualized language or imagery
* Personal attacks
* Trolling or insulting/derogatory comments
* Public or private harassment
* Publishing other's private information, such as physical or electronic addresses, without explicit permission
* Other unethical or unprofessional conduct.
Project maintainers have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct. By adopting this Code of Conduct, project maintainers commit themselves to fairly and consistently applying these principles to every aspect of managing this project. Project maintainers who do not follow or enforce the Code of Conduct may be permanently removed from the project team.
This code of conduct applies both within project spaces and in public spaces when an individual is representing the project or its community.
Instances of abusive, harassing, or otherwise unacceptable behavior may be reported by opening an issue or contacting one or more of the project maintainers.
This Code of Conduct is adapted from the [Contributor Covenant](http://contributor-covenant.org), version 1.2.0, available at [http://contributor-covenant.org/version/1/2/0/](http://contributor-covenant.org/version/1/2/0/)

22
vendor/league/html-to-markdown/LICENSE vendored Normal file
View File

@ -0,0 +1,22 @@
The MIT License (MIT)
Copyright (c) 2015 Colin O'Dell
Originally created by Nick Cernis
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.

196
vendor/league/html-to-markdown/README.md vendored Normal file
View File

@ -0,0 +1,196 @@
HTML To Markdown for PHP
========================
[![Join the chat at https://gitter.im/thephpleague/html-to-markdown](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/thephpleague/html-to-markdown?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
[![Latest Version](https://img.shields.io/packagist/v/league/html-to-markdown.svg?style=flat-square)](https://packagist.org/packages/league/html-to-markdown)
[![Software License](http://img.shields.io/badge/license-MIT-brightgreen.svg?style=flat-square)](LICENSE)
[![Build Status](https://img.shields.io/travis/thephpleague/html-to-markdown/master.svg?style=flat-square)](https://travis-ci.org/thephpleague/html-to-markdown)
[![Coverage Status](https://img.shields.io/scrutinizer/coverage/g/thephpleague/html-to-markdown.svg?style=flat-square)](https://scrutinizer-ci.com/g/thephpleague/html-to-markdown/code-structure)
[![Quality Score](https://img.shields.io/scrutinizer/g/thephpleague/html-to-markdown.svg?style=flat-square)](https://scrutinizer-ci.com/g/thephpleague/html-to-markdown)
[![Total Downloads](https://img.shields.io/packagist/dt/league/html-to-markdown.svg?style=flat-square)](https://packagist.org/packages/league/html-to-markdown)
Library which converts HTML to [Markdown](http://daringfireball.net/projects/markdown/) for your sanity and convenience.
**Requires**: PHP 5.3+
**Lead Developer**: [@colinodell](http://twitter.com/colinodell)
**Original Author**: [@nickcernis](http://twitter.com/nickcernis)
### Why convert HTML to Markdown?
*"What alchemy is this?"* you mutter. *"I can see why you'd convert [Markdown to HTML](https://github.com/thephpleague/commonmark),"* you continue, already labouring the question somewhat, *"but why go the other way?"*
Typically you would convert HTML to Markdown if:
1. You have an existing HTML document that needs to be edited by people with good taste.
2. You want to store new content in HTML format but edit it as Markdown.
3. You want to convert HTML email to plain text email.
4. You know a guy who's been converting HTML to Markdown for years, and now he can speak Elvish. You'd quite like to be able to speak Elvish.
5. You just really like Markdown.
### How to use it
Require the library by issuing this command:
```bash
composer require league/html-to-markdown
```
Add `require 'vendor/autoload.php';` to the top of your script.
Next, create a new HtmlConverter instance, passing in your valid HTML code to its `convert()` function:
```php
use League\HTMLToMarkdown\HtmlConverter;
$converter = new HtmlConverter();
$html = "<h3>Quick, to the Batpoles!</h3>";
$markdown = $converter->convert($html);
```
The `$markdown` variable now contains the Markdown version of your HTML as a string:
```php
echo $markdown; // ==> ### Quick, to the Batpoles!
```
The included `demo` directory contains an HTML->Markdown conversion form to try out.
### Conversion options
By default, HTML To Markdown preserves HTML tags without Markdown equivalents, like `<span>` and `<div>`.
To strip HTML tags that don't have a Markdown equivalent while preserving the content inside them, set `strip_tags` to true, like this:
```php
$converter = new HtmlConverter(array('strip_tags' => true));
$html = '<span>Turnips!</span>';
$markdown = $converter->convert($html); // $markdown now contains "Turnips!"
```
Or more explicitly, like this:
```php
$converter = new HtmlConverter();
$converter->getConfig()->setOption('strip_tags', true);
$html = '<span>Turnips!</span>';
$markdown = $converter->convert($html); // $markdown now contains "Turnips!"
```
Note that only the tags themselves are stripped, not the content they hold.
To strip tags and their content, pass a space-separated list of tags in `remove_nodes`, like this:
```php
$converter = new HtmlConverter(array('remove_nodes' => 'span div'));
$html = '<span>Turnips!</span><div>Monkeys!</div>';
$markdown = $converter->convert($html); // $markdown now contains ""
```
### Style options
Bold and italic tags are converted using the asterisk syntax by default. Change this to the underlined syntax using the `bold_style` and `italic_style` options.
```php
$converter = new HtmlConverter();
$converter->getConfig()->setOption('italic_style', '_');
$converter->getConfig()->setOption('bold_style', '__');
$html = '<em>Italic</em> and a <strong>bold</strong>';
$markdown = $converter->convert($html); // $markdown now contains "_Italic_ and a __bold__"
```
### Line break options
By default, `br` tags are converted to two spaces followed by a newline character as per [traditional Markdown](https://daringfireball.net/projects/markdown/syntax#p). Set `hard_break` to `true` to omit the two spaces, as per GitHub Flavored Markdown (GFM).
```php
$converter = new HtmlConverter();
$html = '<p>test<br>line break</p>';
$converter->getConfig()->setOption('hard_break', true);
$markdown = $converter->convert($html); // $markdown now contains "test\nline break"
$converter->getConfig()->setOption('hard_break', false); // default
$markdown = $converter->convert($html); // $markdown now contains "test \nline break"
```
### Passing custom Environment object
You can pass current `Environment` object to customize i.e. which converters should be used.
```php
$environment = new Environment(array(
// your configuration here
));
$environment->addConverter(new HeaderConverter()); // optionally - add converter manually
$converter = new HtmlConverter($environment);
$html = '<h3>Header</h3>
<img src="" />
';
$markdown = $converter->convert($html); // $markdown now contains "### Header" and "<img src="" />"
```
### Limitations
- Markdown Extra, MultiMarkdown and other variants aren't supported just Markdown.
### Known issues
- Nested lists and lists containing multiple paragraphs aren't converted correctly.
- Lists inside blockquotes aren't converted correctly.
- Any reported [open issues here](https://github.com/thephpleague/html-to-markdown/issues?state=open).
[Report your issue or request a feature here.](https://github.com/thephpleague/html-to-markdown/issues/new) Issues with patches or failing tests are especially welcome.
### Style notes
- Setext (underlined) headers are the default for H1 and H2. If you prefer the ATX style for H1 and H2 (# Header 1 and ## Header 2), set `header_style` to 'atx' in the options array when you instantiate the object:
`$converter = new HtmlConverter(array('header_style'=>'atx'));`
Headers of H3 priority and lower always use atx style.
- Links and images are referenced inline. Footnote references (where image src and anchor href attributes are listed in the footnotes) are not used.
- Blockquotes aren't line wrapped it makes the converted Markdown easier to edit.
### Dependencies
HTML To Markdown requires PHP's [xml](http://www.php.net/manual/en/xml.installation.php), [lib-xml](http://www.php.net/manual/en/libxml.installation.php), and [dom](http://www.php.net/manual/en/dom.installation.php) extensions, all of which are enabled by default on most distributions.
Errors such as "Fatal error: Class 'DOMDocument' not found" on distributions such as CentOS that disable PHP's xml extension can be resolved by installing php-xml.
### Contributors
Many thanks to all [contributors](https://github.com/thephpleague/html-to-markdown/graphs/contributors) so far. Further improvements and feature suggestions are very welcome.
### How it works
HTML To Markdown creates a DOMDocument from the supplied HTML, walks through the tree, and converts each node to a text node containing the equivalent markdown, starting from the most deeply nested node and working inwards towards the root node.
### To-do
- Support for nested lists and lists inside blockquotes.
- Offer an option to preserve tags as HTML if they contain attributes that can't be represented with Markdown (e.g. `style`).
### Trying to convert Markdown to HTML?
Use one of these great libraries:
- [league/commonmark](https://github.com/thephpleague/commonmark) (recommended)
- [cebe/markdown](https://github.com/cebe/markdown)
- [PHP Markdown](https://michelf.ca/projects/php-markdown/)
- [Parsedown](https://github.com/erusev/parsedown)
No guarantees about the Elvish, though.

View File

@ -0,0 +1,108 @@
#!/usr/bin/env php
<?php
requireAutoloader();
ini_set('display_errors', 'stderr');
foreach ($argv as $i => $arg) {
if ($i === 0) {
continue;
}
if (substr($arg, 0, 1) === '-') {
switch ($arg) {
case '-h':
case '--help':
echo getHelpText();
exit(0);
default:
fail('Unknown option: ' . $arg);
}
} else {
$src = $argv[1];
}
}
if (isset($src)) {
if (!file_exists($src)) {
fail('File not found: ' . $src);
}
$html = file_get_contents($src);
} else {
$stdin = fopen('php://stdin', 'r');
stream_set_blocking($stdin, false);
$html = stream_get_contents($stdin);
fclose($stdin);
if (empty($html)) {
fail(getHelpText());
}
}
$converter = new League\HTMLToMarkdown\HtmlConverter();
echo $converter->convert($html);
/**
* Get help and usage info
*
* @return string
*/
function getHelpText()
{
return <<<HELP
HTML To Markdown
Usage: html-to-markdown [OPTIONS] [FILE]
-h, --help Shows help and usage information
If no file is given, input will be read from STDIN
Examples:
Converting a file named document.html:
html-to-markdown document.html
Converting a file and saving its output:
html-to-markdown document.html > output.md
Converting from STDIN:
echo -e '<h1>Hello World!</h1>' | html-to-markdown
Converting from STDIN and saving the output:
echo -e '<h1>Hello World!</h1>' | html-to-markdown > output.md
HELP;
}
/**
* @param string $message Error message
*/
function fail($message)
{
fwrite(STDERR, $message . "\n");
exit(1);
}
function requireAutoloader()
{
$autoloadPaths = array(
// Local package usage
__DIR__ . '/../vendor/autoload.php',
// Package was included as a library
__DIR__ . '/../../../autoload.php',
);
foreach ($autoloadPaths as $path) {
if (file_exists($path)) {
require_once $path;
break;
}
}
}

View File

@ -0,0 +1,48 @@
{
"name": "league/html-to-markdown",
"type": "library",
"description": "An HTML-to-markdown conversion helper for PHP",
"keywords": ["markdown", "html"],
"homepage": "https://github.com/thephpleague/html-to-markdown",
"license": "MIT",
"authors": [
{
"name": "Colin O'Dell",
"email": "colinodell@gmail.com",
"homepage": "http://www.colinodell.com",
"role": "Lead Developer"
},
{
"name": "Nick Cernis",
"email": "nick@cern.is",
"homepage": "http://modernnerd.net",
"role": "Original Author"
}
],
"autoload": {
"psr-4": {
"League\\HTMLToMarkdown\\": "src/"
}
},
"autoload-dev": {
"psr-4": {
"League\\HTMLToMarkdown\\Test\\": "tests"
}
},
"require": {
"php": ">=5.3.3",
"ext-dom": "*",
"ext-xml": "*"
},
"require-dev": {
"mikehaertl/php-shellcommand": "~1.1.0",
"phpunit/phpunit": "4.*",
"scrutinizer/ocular": "~1.1"
},
"bin": ["bin/html-to-markdown"],
"extra": {
"branch-alias": {
"dev-master": "4.5-dev"
}
}
}

View File

@ -0,0 +1,60 @@
<?php
namespace League\HTMLToMarkdown;
class Configuration
{
protected $config;
/**
* @param array $config
*/
public function __construct(array $config = array())
{
$this->config = $config;
}
/**
* @param array $config
*/
public function merge(array $config = array())
{
$this->config = array_replace_recursive($this->config, $config);
}
/**
* @param array $config
*/
public function replace(array $config = array())
{
$this->config = $config;
}
/**
* @param string $key
* @param mixed $value
*/
public function setOption($key, $value)
{
$this->config[$key] = $value;
}
/**
* @param string|null $key
* @param mixed|null $default
*
* @return mixed|null
*/
public function getOption($key = null, $default = null)
{
if ($key === null) {
return $this->config;
}
if (!isset($this->config[$key])) {
return $default;
}
return $this->config[$key];
}
}

View File

@ -0,0 +1,11 @@
<?php
namespace League\HTMLToMarkdown;
interface ConfigurationAwareInterface
{
/**
* @param Configuration $config
*/
public function setConfig(Configuration $config);
}

View File

@ -0,0 +1,44 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\ElementInterface;
class BlockquoteConverter implements ConverterInterface
{
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
// Contents should have already been converted to Markdown by this point,
// so we just need to add '>' symbols to each line.
$markdown = '';
$quote_content = trim($element->getValue());
$lines = preg_split('/\r\n|\r|\n/', $quote_content);
$total_lines = count($lines);
foreach ($lines as $i => $line) {
$markdown .= '> ' . $line . "\n";
if ($i + 1 === $total_lines) {
$markdown .= "\n";
}
}
return $markdown;
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('blockquote');
}
}

View File

@ -0,0 +1,62 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\ElementInterface;
class CodeConverter implements ConverterInterface
{
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
$language = null;
// Checking for language class on the code block
$classes = $element->getAttribute('class');
if ($classes) {
// Since tags can have more than one class, we need to find the one that starts with 'language-'
$classes = explode(' ', $classes);
foreach ($classes as $class) {
if (strpos($class, 'language-') !== false) {
// Found one, save it as the selected language and stop looping over the classes.
// The space after the language avoids gluing the actual code with the language tag
$language = str_replace('language-', '', $class) . ' ';
break;
}
}
}
$markdown = '';
$code = html_entity_decode($element->getChildrenAsString());
// In order to remove the code tags we need to search for them and, in the case of the opening tag
// use a regular expression to find the tag and the other attributes it might have
$code = preg_replace('/<code\b[^>]*>/', '', $code);
$code = str_replace('</code>', '', $code);
// Checking if the code has multiple lines
$lines = preg_split('/\r\n|\r|\n/', $code);
if (count($lines) > 1) {
// Multiple lines detected, adding three backticks and newlines
$markdown .= '```' . $language . "\n" . $code . "\n" . '```';
} else {
// One line of code, wrapping it on one backtick.
$markdown .= '`' . $language . $code . '`';
}
return $markdown;
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('code');
}
}

View File

@ -0,0 +1,26 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\ElementInterface;
class CommentConverter implements ConverterInterface
{
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
return '';
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('#comment');
}
}

View File

@ -0,0 +1,20 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\ElementInterface;
interface ConverterInterface
{
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element);
/**
* @return string[]
*/
public function getSupportedTags();
}

View File

@ -0,0 +1,50 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\Configuration;
use League\HTMLToMarkdown\ConfigurationAwareInterface;
use League\HTMLToMarkdown\ElementInterface;
class DefaultConverter implements ConverterInterface, ConfigurationAwareInterface
{
const DEFAULT_CONVERTER = '_default';
/**
* @var Configuration
*/
protected $config;
/**
* @param Configuration $config
*/
public function setConfig(Configuration $config)
{
$this->config = $config;
}
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
// If strip_tags is false (the default), preserve tags that don't have Markdown equivalents,
// such as <span> nodes on their own. C14N() canonicalizes the node to a string.
// See: http://www.php.net/manual/en/domnode.c14n.php
if ($this->config->getOption('strip_tags', false)) {
return $element->getValue();
}
return html_entity_decode($element->getChildrenAsString());
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array(self::DEFAULT_CONVERTER);
}
}

View File

@ -0,0 +1,45 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\Configuration;
use League\HTMLToMarkdown\ConfigurationAwareInterface;
use League\HTMLToMarkdown\ElementInterface;
class DivConverter implements ConverterInterface, ConfigurationAwareInterface
{
/**
* @var Configuration
*/
protected $config;
/**
* @param Configuration $config
*/
public function setConfig(Configuration $config)
{
$this->config = $config;
}
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
if ($this->config->getOption('strip_tags', false)) {
return $element->getValue() . "\n\n";
}
return html_entity_decode($element->getChildrenAsString());
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('div');
}
}

View File

@ -0,0 +1,57 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\Configuration;
use League\HTMLToMarkdown\ConfigurationAwareInterface;
use League\HTMLToMarkdown\ElementInterface;
class EmphasisConverter implements ConverterInterface, ConfigurationAwareInterface
{
/**
* @var Configuration
*/
protected $config;
/**
* @param Configuration $config
*/
public function setConfig(Configuration $config)
{
$this->config = $config;
}
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
$tag = $element->getTagName();
$value = $element->getValue();
if (!trim($value)) {
return '';
}
if ($tag === 'i' || $tag === 'em') {
$style = $this->config->getOption('italic_style');
} else {
$style = $this->config->getOption('bold_style');
}
$prefix = ltrim($value) !== $value ? ' ' : '';
$suffix = rtrim($value) !== $value ? ' ' : '';
return $prefix . $style . trim($value) . $style . $suffix;
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('em', 'i', 'strong', 'b');
}
}

View File

@ -0,0 +1,41 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\Configuration;
use League\HTMLToMarkdown\ConfigurationAwareInterface;
use League\HTMLToMarkdown\ElementInterface;
class HardBreakConverter implements ConverterInterface, ConfigurationAwareInterface
{
/**
* @var Configuration
*/
protected $config;
/**
* @param Configuration $config
*/
public function setConfig(Configuration $config)
{
$this->config = $config;
}
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
return $this->config->getOption('hard_break') ? "\n" : " \n";
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('br');
}
}

View File

@ -0,0 +1,78 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\Configuration;
use League\HTMLToMarkdown\ConfigurationAwareInterface;
use League\HTMLToMarkdown\ElementInterface;
class HeaderConverter implements ConverterInterface, ConfigurationAwareInterface
{
const STYLE_ATX = 'atx';
const STYLE_SETEXT = 'setext';
/**
* @var Configuration
*/
protected $config;
/**
* @param Configuration $config
*/
public function setConfig(Configuration $config)
{
$this->config = $config;
}
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
$level = (int) substr($element->getTagName(), 1, 1);
$style = $this->config->getOption('header_style', self::STYLE_SETEXT);
if (($level === 1 || $level === 2) && !$element->isDescendantOf('blockquote') && $style === self::STYLE_SETEXT) {
return $this->createSetextHeader($level, $element->getValue());
}
return $this->createAtxHeader($level, $element->getValue());
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('h1', 'h2', 'h3', 'h4', 'h5', 'h6');
}
/**
* @param int $level
* @param string $content
*
* @return string
*/
private function createSetextHeader($level, $content)
{
$length = function_exists('mb_strlen') ? mb_strlen($content, 'utf-8') : strlen($content);
$underline = ($level === 1) ? '=' : '-';
return $content . "\n" . str_repeat($underline, $length) . "\n\n";
}
/**
* @param int $level
* @param string $content
*
* @return string
*/
private function createAtxHeader($level, $content)
{
$prefix = str_repeat('#', $level) . ' ';
return $prefix . $content . "\n\n";
}
}

View File

@ -0,0 +1,26 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\ElementInterface;
class HorizontalRuleConverter implements ConverterInterface
{
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
return "- - - - - -\n\n";
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('hr');
}
}

View File

@ -0,0 +1,35 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\ElementInterface;
class ImageConverter implements ConverterInterface
{
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
$src = $element->getAttribute('src');
$alt = $element->getAttribute('alt');
$title = $element->getAttribute('title');
if ($title !== '') {
// No newlines added. <img> should be in a block-level element.
return '![' . $alt . '](' . $src . ' "' . $title . '")';
}
return '![' . $alt . '](' . $src . ')';
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('img');
}
}

View File

@ -0,0 +1,52 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\ElementInterface;
class LinkConverter implements ConverterInterface
{
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
$href = $element->getAttribute('href');
$title = $element->getAttribute('title');
$text = trim($element->getValue());
if ($title !== '') {
$markdown = '[' . $text . '](' . $href . ' "' . $title . '")';
} elseif ($href === $text && $this->isValidAutolink($href)) {
$markdown = '<' . $href . '>';
} else {
$markdown = '[' . $text . '](' . $href . ')';
}
if (!$href) {
$markdown = html_entity_decode($element->getChildrenAsString());
}
return $markdown;
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('a');
}
/**
* @param string $href
*
* @return bool
*/
private function isValidAutolink($href)
{
return preg_match('/^[A-Za-z][A-Za-z0-9.+-]{1,31}:[^<>\x00-\x20]*/i', $href) === 1;
}
}

View File

@ -0,0 +1,26 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\ElementInterface;
class ListBlockConverter implements ConverterInterface
{
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
return $element->getValue() . "\n";
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('ol', 'ul');
}
}

View File

@ -0,0 +1,47 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\ElementInterface;
class ListItemConverter implements ConverterInterface
{
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
// If parent is an ol, use numbers, otherwise, use dashes
$list_type = $element->getParent()->getTagName();
// Add spaces to start for nested list items
$level = $element->getListItemLevel($element);
$prefixForParagraph = str_repeat(' ', $level + 1);
$value = trim(implode("\n" . $prefixForParagraph, explode("\n", trim($element->getValue()))));
// If list item is the first in a nested list, add a newline before it
$prefix = '';
if ($level > 0 && $element->getSiblingPosition() === 1) {
$prefix = "\n";
}
if ($list_type === 'ul') {
return $prefix . '- ' . $value . "\n";
}
$number = $element->getSiblingPosition();
return $prefix . $number . '. ' . $value . "\n";
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('li');
}
}

View File

@ -0,0 +1,124 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\ElementInterface;
class ParagraphConverter implements ConverterInterface
{
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
$value = $element->getValue();
$markdown = '';
$lines = preg_split('/\r\n|\r|\n/', $value);
foreach ($lines as $line) {
/*
* Some special characters need to be escaped based on the position that they appear
* The following function will deal with those special cases.
*/
$markdown .= $this->escapeSpecialCharacters($line);
$markdown .= "\n";
}
return trim($markdown) !== '' ? rtrim($markdown) . "\n\n" : '';
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('p');
}
/**
* @param string $line
*
* @return string
*/
private function escapeSpecialCharacters($line)
{
$line = $this->escapeFirstCharacters($line);
$line = $this->escapeOtherCharacters($line);
$line = $this->escapeOtherCharactersRegex($line);
return $line;
}
/**
* @param string $line
*
* @return string
*/
private function escapeFirstCharacters($line)
{
$escapable = array(
'>',
'- ',
'+ ',
'--',
'~~~',
'---',
'- - -'
);
foreach ($escapable as $i) {
if (strpos(ltrim($line), $i) === 0) {
// Found a character that must be escaped, adding a backslash before
return '\\' . ltrim($line);
}
}
return $line;
}
/**
* @param string $line
*
* @return string
*/
private function escapeOtherCharacters($line)
{
$escapable = array(
'<!--'
);
foreach ($escapable as $i) {
if (strpos($line, $i) !== false) {
// Found an escapable character, escaping it
$line = substr_replace($line, '\\', strpos($line, $i), 0);
}
}
return $line;
}
/**
* @param string $line
*
* @return string
*/
private function escapeOtherCharactersRegex($line)
{
$regExs = array(
// Match numbers ending on ')' or '.' that are at the beginning of the line.
'/^[0-9]+(?=\)|\.)/'
);
foreach ($regExs as $i) {
if (preg_match($i, $line, $match)) {
// Matched an escapable character, adding a backslash on the string before the offending character
$line = substr_replace($line, '\\', strlen($match[0]), 0);
}
}
return $line;
}
}

View File

@ -0,0 +1,59 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\ElementInterface;
class PreformattedConverter implements ConverterInterface
{
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
$markdown = '';
$pre_content = html_entity_decode($element->getChildrenAsString());
$pre_content = str_replace(array('<pre>', '</pre>'), '', $pre_content);
/*
* Checking for the code tag.
* Usually pre tags are used along with code tags. This conditional will check for already converted code tags,
* which use backticks, and if those backticks are at the beginning and at the end of the string it means
* there's no more information to convert.
*/
$firstBacktick = strpos(trim($pre_content), '`');
$lastBacktick = strrpos(trim($pre_content), '`');
if ($firstBacktick === 0 && $lastBacktick === strlen(trim($pre_content)) - 1) {
return $pre_content;
}
// If the execution reaches this point it means it's just a pre tag, with no code tag nested
// Normalizing new lines
$pre_content = preg_replace('/\r\n|\r|\n/', PHP_EOL, $pre_content);
// Checking if the string has multiple lines
$lines = preg_split('/\r\n|\r|\n/', $pre_content);
if (count($lines) > 1) {
// Multiple lines detected, adding three backticks and newlines
$markdown .= '```' . "\n" . $pre_content . "\n" . '```';
} else {
// One line of code, wrapping it on one backtick.
$markdown .= '`' . $pre_content . '`';
}
return $markdown;
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('pre');
}
}

View File

@ -0,0 +1,46 @@
<?php
namespace League\HTMLToMarkdown\Converter;
use League\HTMLToMarkdown\ElementInterface;
class TextConverter implements ConverterInterface
{
/**
* @param ElementInterface $element
*
* @return string
*/
public function convert(ElementInterface $element)
{
$markdown = $element->getValue();
// Remove leftover \n at the beginning of the line
$markdown = ltrim($markdown, "\n");
// Replace sequences of invisible characters with spaces
$markdown = preg_replace('~\s+~u', ' ', $markdown);
// Escape the following characters: '*', '_', '[', ']' and '\'
$markdown = preg_replace('~([*_\\[\\]\\\\])~u', '\\\\$1', $markdown);
$markdown = preg_replace('~^#~u', '\\\\#', $markdown);
if ($markdown === ' ') {
$next = $element->getNext();
if (!$next || $next->isBlock()) {
$markdown = '';
}
}
return $markdown;
}
/**
* @return string[]
*/
public function getSupportedTags()
{
return array('#text');
}
}

View File

@ -0,0 +1,257 @@
<?php
namespace League\HTMLToMarkdown;
class Element implements ElementInterface
{
/**
* @var \DOMNode
*/
protected $node;
/**
* @var ElementInterface|null
*/
private $nextCached;
public function __construct(\DOMNode $node)
{
$this->node = $node;
}
/**
* @return bool
*/
public function isBlock()
{
switch ($this->getTagName()) {
case 'blockquote':
case 'body':
case 'code':
case 'div':
case 'h1':
case 'h2':
case 'h3':
case 'h4':
case 'h5':
case 'h6':
case 'hr':
case 'html':
case 'li':
case 'p':
case 'ol':
case 'ul':
return true;
default:
return false;
}
}
/**
* @return bool
*/
public function isText()
{
return $this->getTagName() === '#text';
}
/**
* @return bool
*/
public function isWhitespace()
{
return $this->getTagName() === '#text' && trim($this->getValue()) === '';
}
/**
* @return string
*/
public function getTagName()
{
return $this->node->nodeName;
}
/**
* @return string
*/
public function getValue()
{
return $this->node->nodeValue;
}
/**
* @return ElementInterface|null
*/
public function getParent()
{
return new static($this->node->parentNode) ?: null;
}
/**
* @return bool
*/
public function hasChildren()
{
return $this->node->hasChildNodes();
}
/**
* @return ElementInterface[]
*/
public function getChildren()
{
$ret = array();
/** @var \DOMNode $node */
foreach ($this->node->childNodes as $node) {
$ret[] = new static($node);
}
return $ret;
}
/**
* @return ElementInterface|null
*/
public function getNext()
{
if ($this->nextCached === null) {
$nextNode = $this->getNextNode($this->node);
if ($nextNode !== null) {
$this->nextCached = new static($nextNode);
}
}
return $this->nextCached;
}
/**
* @param \DomNode $node
* @param bool $checkChildren
*
* @return \DomNode|null
*/
private function getNextNode($node, $checkChildren = true)
{
if ($checkChildren && $node->firstChild) {
return $node->firstChild;
}
if ($node->nextSibling) {
return $node->nextSibling;
}
if ($node->parentNode) {
return $this->getNextNode($node->parentNode, false);
}
}
/**
* @param string[]|string $tagNames
*
* @return bool
*/
public function isDescendantOf($tagNames)
{
if (!is_array($tagNames)) {
$tagNames = array($tagNames);
}
for ($p = $this->node->parentNode; $p !== false; $p = $p->parentNode) {
if (is_null($p)) {
return false;
}
if (in_array($p->nodeName, $tagNames)) {
return true;
}
}
return false;
}
/**
* @param string $markdown
*/
public function setFinalMarkdown($markdown)
{
$markdown_node = $this->node->ownerDocument->createTextNode($markdown);
$this->node->parentNode->replaceChild($markdown_node, $this->node);
}
/**
* @return string
*/
public function getChildrenAsString()
{
return $this->node->C14N();
}
/**
* @return int
*/
public function getSiblingPosition()
{
$position = 0;
// Loop through all nodes and find the given $node
foreach ($this->getParent()->getChildren() as $current_node) {
if (!$current_node->isWhitespace()) {
$position++;
}
// TODO: Need a less-buggy way of comparing these
// Perhaps we can somehow ensure that we always have the exact same object and use === instead?
if ($this->equals($current_node)) {
break;
}
}
return $position;
}
/**
* @return int
*/
public function getListItemLevel()
{
$level = 0;
$parent = $this->getParent();
while ($parent !== null && $parent->node->parentNode) {
if ($parent->getTagName() === 'li') {
$level++;
}
$parent = $parent->getParent();
}
return $level;
}
/**
* @param string $name
*
* @return string
*/
public function getAttribute($name)
{
if ($this->node instanceof \DOMElement) {
return $this->node->getAttribute($name);
}
return '';
}
/**
* @param ElementInterface $element
*
* @return bool
*/
public function equals(ElementInterface $element)
{
if ($element instanceof self) {
return $element->node === $this->node;
}
return $element === $this;
}
}

View File

@ -0,0 +1,80 @@
<?php
namespace League\HTMLToMarkdown;
interface ElementInterface
{
/**
* @return bool
*/
public function isBlock();
/**
* @return bool
*/
public function isText();
/**
* @return bool
*/
public function isWhitespace();
/**
* @return string
*/
public function getTagName();
/**
* @return string
*/
public function getValue();
/**
* @return ElementInterface|null
*/
public function getParent();
/**
* @param string|string[] $tagNames
*
* @return bool
*/
public function isDescendantOf($tagNames);
/**
* @return bool
*/
public function hasChildren();
/**
* @return ElementInterface[]
*/
public function getChildren();
/**
* @return ElementInterface|null
*/
public function getNext();
/**
* @return int
*/
public function getSiblingPosition();
/**
* @return string
*/
public function getChildrenAsString();
/**
* @param string $markdown
*/
public function setFinalMarkdown($markdown);
/**
* @param string $name
*
* @return string
*/
public function getAttribute($name);
}

View File

@ -0,0 +1,104 @@
<?php
namespace League\HTMLToMarkdown;
use League\HTMLToMarkdown\Converter\BlockquoteConverter;
use League\HTMLToMarkdown\Converter\CodeConverter;
use League\HTMLToMarkdown\Converter\CommentConverter;
use League\HTMLToMarkdown\Converter\ConverterInterface;
use League\HTMLToMarkdown\Converter\DefaultConverter;
use League\HTMLToMarkdown\Converter\DivConverter;
use League\HTMLToMarkdown\Converter\EmphasisConverter;
use League\HTMLToMarkdown\Converter\HardBreakConverter;
use League\HTMLToMarkdown\Converter\HeaderConverter;
use League\HTMLToMarkdown\Converter\HorizontalRuleConverter;
use League\HTMLToMarkdown\Converter\ImageConverter;
use League\HTMLToMarkdown\Converter\LinkConverter;
use League\HTMLToMarkdown\Converter\ListBlockConverter;
use League\HTMLToMarkdown\Converter\ListItemConverter;
use League\HTMLToMarkdown\Converter\ParagraphConverter;
use League\HTMLToMarkdown\Converter\PreformattedConverter;
use League\HTMLToMarkdown\Converter\TextConverter;
final class Environment
{
/**
* @var Configuration
*/
protected $config;
/**
* @var ConverterInterface[]
*/
protected $converters = array();
public function __construct(array $config = array())
{
$this->config = new Configuration($config);
$this->addConverter(new DefaultConverter());
}
/**
* @return Configuration
*/
public function getConfig()
{
return $this->config;
}
/**
* @param ConverterInterface $converter
*/
public function addConverter(ConverterInterface $converter)
{
if ($converter instanceof ConfigurationAwareInterface) {
$converter->setConfig($this->config);
}
foreach ($converter->getSupportedTags() as $tag) {
$this->converters[$tag] = $converter;
}
}
/**
* @param string $tag
*
* @return ConverterInterface
*/
public function getConverterByTag($tag)
{
if (isset($this->converters[$tag])) {
return $this->converters[$tag];
}
return $this->converters[DefaultConverter::DEFAULT_CONVERTER];
}
/**
* @param array $config
*
* @return Environment
*/
public static function createDefaultEnvironment(array $config = array())
{
$environment = new static($config);
$environment->addConverter(new BlockquoteConverter());
$environment->addConverter(new CodeConverter());
$environment->addConverter(new CommentConverter());
$environment->addConverter(new DivConverter());
$environment->addConverter(new EmphasisConverter());
$environment->addConverter(new HardBreakConverter());
$environment->addConverter(new HeaderConverter());
$environment->addConverter(new HorizontalRuleConverter());
$environment->addConverter(new ImageConverter());
$environment->addConverter(new LinkConverter());
$environment->addConverter(new ListBlockConverter());
$environment->addConverter(new ListItemConverter());
$environment->addConverter(new ParagraphConverter());
$environment->addConverter(new PreformattedConverter());
$environment->addConverter(new TextConverter());
return $environment;
}
}

View File

@ -0,0 +1,231 @@
<?php
namespace League\HTMLToMarkdown;
/**
* Class HtmlConverter
*
* A helper class to convert HTML to Markdown.
*
* @author Colin O'Dell <colinodell@gmail.com>
* @author Nick Cernis <nick@cern.is>
*
* @link https://github.com/thephpleague/html-to-markdown/ Latest version on GitHub.
*
* @license http://www.opensource.org/licenses/mit-license.php MIT
*/
class HtmlConverter
{
/**
* @var Environment
*/
protected $environment;
/**
* Constructor
*
* @param Environment|array $options Environment object or configuration options
*/
public function __construct($options = array())
{
if ($options instanceof Environment) {
$this->environment = $options;
} elseif (is_array($options)) {
$defaults = array(
'header_style' => 'setext', // Set to 'atx' to output H1 and H2 headers as # Header1 and ## Header2
'suppress_errors' => true, // Set to false to show warnings when loading malformed HTML
'strip_tags' => false, // Set to true to strip tags that don't have markdown equivalents. N.B. Strips tags, not their content. Useful to clean MS Word HTML output.
'bold_style' => '**', // Set to '__' if you prefer the underlined style
'italic_style' => '_', // Set to '*' if you prefer the asterisk style
'remove_nodes' => '', // space-separated list of dom nodes that should be removed. example: 'meta style script'
'hard_break' => false,// Set to true to turn <br> into `\n` instead of ` \n`
);
$this->environment = Environment::createDefaultEnvironment($defaults);
$this->environment->getConfig()->merge($options);
}
}
/**
* @return Environment
*/
public function getEnvironment()
{
return $this->environment;
}
/**
* @return Configuration
*/
public function getConfig()
{
return $this->environment->getConfig();
}
/**
* Convert
*
* @see HtmlConverter::convert
*
* @param string $html
*
* @return string The Markdown version of the html
*/
public function __invoke($html)
{
return $this->convert($html);
}
/**
* Convert
*
* Loads HTML and passes to getMarkdown()
*
* @param string $html
*
* @throws \InvalidArgumentException
*
* @return string The Markdown version of the html
*/
public function convert($html)
{
if (trim($html) === '') {
return '';
}
$document = $this->createDOMDocument($html);
// Work on the entire DOM tree (including head and body)
if (!($root = $document->getElementsByTagName('html')->item(0))) {
throw new \InvalidArgumentException('Invalid HTML was provided');
}
$rootElement = new Element($root);
$this->convertChildren($rootElement);
// Store the now-modified DOMDocument as a string
$markdown = $document->saveHTML();
return $this->sanitize($markdown);
}
/**
* @param string $html
*
* @return \DOMDocument
*/
private function createDOMDocument($html)
{
$document = new \DOMDocument();
if ($this->getConfig()->getOption('suppress_errors')) {
// Suppress conversion errors (from http://bit.ly/pCCRSX)
libxml_use_internal_errors(true);
}
// Hack to load utf-8 HTML (from http://bit.ly/pVDyCt)
$document->loadHTML('<?xml encoding="UTF-8">' . $html);
$document->encoding = 'UTF-8';
if ($this->getConfig()->getOption('suppress_errors')) {
libxml_clear_errors();
}
return $document;
}
/**
* Convert Children
*
* Recursive function to drill into the DOM and convert each node into Markdown from the inside out.
*
* Finds children of each node and convert those to #text nodes containing their Markdown equivalent,
* starting with the innermost element and working up to the outermost element.
*
* @param ElementInterface $element
*/
private function convertChildren(ElementInterface $element)
{
// Don't convert HTML code inside <code> and <pre> blocks to Markdown - that should stay as HTML
// except if the current node is a code tag, which needs to be converted by the CodeConverter.
if ($element->isDescendantOf(array('pre', 'code')) && $element->getTagName() !== 'code') {
return;
}
// If the node has children, convert those to Markdown first
if ($element->hasChildren()) {
foreach ($element->getChildren() as $child) {
$this->convertChildren($child);
}
}
// Now that child nodes have been converted, convert the original node
$markdown = $this->convertToMarkdown($element);
// Create a DOM text node containing the Markdown equivalent of the original node
// Replace the old $node e.g. '<h3>Title</h3>' with the new $markdown_node e.g. '### Title'
$element->setFinalMarkdown($markdown);
}
/**
* Convert to Markdown
*
* Converts an individual node into a #text node containing a string of its Markdown equivalent.
*
* Example: An <h3> node with text content of 'Title' becomes a text node with content of '### Title'
*
* @param ElementInterface $element
*
* @return string The converted HTML as Markdown
*/
protected function convertToMarkdown(ElementInterface $element)
{
$tag = $element->getTagName();
// Strip nodes named in remove_nodes
$tags_to_remove = explode(' ', $this->getConfig()->getOption('remove_nodes'));
if (in_array($tag, $tags_to_remove)) {
return false;
}
$converter = $this->environment->getConverterByTag($tag);
return $converter->convert($element);
}
/**
* @param string $markdown
*
* @return string
*/
protected function sanitize($markdown)
{
$markdown = html_entity_decode($markdown, ENT_QUOTES, 'UTF-8');
$markdown = preg_replace('/<!DOCTYPE [^>]+>/', '', $markdown); // Strip doctype declaration
$markdown = trim($markdown); // Remove blank spaces at the beggining of the html
/*
* Removing unwanted tags. Tags should be added to the array in the order they are expected.
* XML, html and body opening tags should be in that order. Same case with closing tags
*/
$unwanted = array('<?xml encoding="UTF-8">', '<html>', '</html>', '<body>', '</body>', '<head>', '</head>', '&#xD;');
foreach ($unwanted as $tag) {
if (strpos($tag, '/') === false) {
// Opening tags
if (strpos($markdown, $tag) === 0) {
$markdown = substr($markdown, strlen($tag));
}
} else {
// Closing tags
if (strpos($markdown, $tag) === strlen($markdown) - strlen($tag)) {
$markdown = substr($markdown, 0, -strlen($tag));
}
}
}
return trim($markdown, "\n\r\0\x0B");
}
}

View File

@ -1,76 +0,0 @@
CHANGELOG
==============
21/09/2016 v2.2.1
--------------
* Fix: Moving trailing whitespace from inline elements outside of the element
* Feature: Use PSR-4
* Feature: PHP 7.0 support in continuous integration
* Doc: Update of the README
07/09/2016 v2.2.0
--------------
* Fix: Reset state between each parsing
19/02/2016 v2.1.11
--------------
* Fix: Empty table cell conversion
10/02/2016 v2.1.10
--------------
* Fix: Handle nested table.
01/04/2015 v2.1.9
--------------
* Fix: Handle HTML breaks & spaces in a less destructive way.
26/03/2015 v2.1.8
--------------
* Fix: Use alternative italic character
* Fix: Handle HTML breaks inside another tag
* Fix: Handle HTML spaces around tags
07/11/2014 v2.1.7
--------------
* Change composer name to "elephant418/markdownify"
14/07/2014 v2.1.6
--------------
* Fix: Simulate a paragraph for inline text preceding block element
* Fix: Nested lists
* Fix: setKeepHTML method
* Feature: PHP 5.5 & 5.6 support in continuous integration
16/03/2014 v2.1.5
--------------
Add display settings
* Test: Add tests for footnotes after every paragraph or not
* Feature: Allow to display link reference in paragraph, without footnotes
27/02/2014 v2.1.4
--------------
Improve how ConverterExtra handle id & class attributes:
* Feature: Allow id & class attributes on links
* Feature: Allow class attributes on headings

View File

@ -1,504 +0,0 @@
GNU LESSER GENERAL PUBLIC LICENSE
Version 2.1, February 1999
Copyright (C) 1991, 1999 Free Software Foundation, Inc.
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
[This is the first released version of the Lesser GPL. It also counts
as the successor of the GNU Library Public License, version 2, hence
the version number 2.1.]
Preamble
The licenses for most software are designed to take away your
freedom to share and change it. By contrast, the GNU General Public
Licenses are intended to guarantee your freedom to share and change
free software--to make sure the software is free for all its users.
This license, the Lesser General Public License, applies to some
specially designated software packages--typically libraries--of the
Free Software Foundation and other authors who decide to use it. You
can use it too, but we suggest you first think carefully about whether
this license or the ordinary General Public License is the better
strategy to use in any particular case, based on the explanations below.
When we speak of free software, we are referring to freedom of use,
not price. Our General Public Licenses are designed to make sure that
you have the freedom to distribute copies of free software (and charge
for this service if you wish); that you receive source code or can get
it if you want it; that you can change the software and use pieces of
it in new free programs; and that you are informed that you can do
these things.
To protect your rights, we need to make restrictions that forbid
distributors to deny you these rights or to ask you to surrender these
rights. These restrictions translate to certain responsibilities for
you if you distribute copies of the library or if you modify it.
For example, if you distribute copies of the library, whether gratis
or for a fee, you must give the recipients all the rights that we gave
you. You must make sure that they, too, receive or can get the source
code. If you link other code with the library, you must provide
complete object files to the recipients, so that they can relink them
with the library after making changes to the library and recompiling
it. And you must show them these terms so they know their rights.
We protect your rights with a two-step method: (1) we copyright the
library, and (2) we offer you this license, which gives you legal
permission to copy, distribute and/or modify the library.
To protect each distributor, we want to make it very clear that
there is no warranty for the free library. Also, if the library is
modified by someone else and passed on, the recipients should know
that what they have is not the original version, so that the original
author's reputation will not be affected by problems that might be
introduced by others.
Finally, software patents pose a constant threat to the existence of
any free program. We wish to make sure that a company cannot
effectively restrict the users of a free program by obtaining a
restrictive license from a patent holder. Therefore, we insist that
any patent license obtained for a version of the library must be
consistent with the full freedom of use specified in this license.
Most GNU software, including some libraries, is covered by the
ordinary GNU General Public License. This license, the GNU Lesser
General Public License, applies to certain designated libraries, and
is quite different from the ordinary General Public License. We use
this license for certain libraries in order to permit linking those
libraries into non-free programs.
When a program is linked with a library, whether statically or using
a shared library, the combination of the two is legally speaking a
combined work, a derivative of the original library. The ordinary
General Public License therefore permits such linking only if the
entire combination fits its criteria of freedom. The Lesser General
Public License permits more lax criteria for linking other code with
the library.
We call this license the "Lesser" General Public License because it
does Less to protect the user's freedom than the ordinary General
Public License. It also provides other free software developers Less
of an advantage over competing non-free programs. These disadvantages
are the reason we use the ordinary General Public License for many
libraries. However, the Lesser license provides advantages in certain
special circumstances.
For example, on rare occasions, there may be a special need to
encourage the widest possible use of a certain library, so that it becomes
a de-facto standard. To achieve this, non-free programs must be
allowed to use the library. A more frequent case is that a free
library does the same job as widely used non-free libraries. In this
case, there is little to gain by limiting the free library to free
software only, so we use the Lesser General Public License.
In other cases, permission to use a particular library in non-free
programs enables a greater number of people to use a large body of
free software. For example, permission to use the GNU C Library in
non-free programs enables many more people to use the whole GNU
operating system, as well as its variant, the GNU/Linux operating
system.
Although the Lesser General Public License is Less protective of the
users' freedom, it does ensure that the user of a program that is
linked with the Library has the freedom and the wherewithal to run
that program using a modified version of the Library.
The precise terms and conditions for copying, distribution and
modification follow. Pay close attention to the difference between a
"work based on the library" and a "work that uses the library". The
former contains code derived from the library, whereas the latter must
be combined with the library in order to run.
GNU LESSER GENERAL PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
0. This License Agreement applies to any software library or other
program which contains a notice placed by the copyright holder or
other authorized party saying it may be distributed under the terms of
this Lesser General Public License (also called "this License").
Each licensee is addressed as "you".
A "library" means a collection of software functions and/or data
prepared so as to be conveniently linked with application programs
(which use some of those functions and data) to form executables.
The "Library", below, refers to any such software library or work
which has been distributed under these terms. A "work based on the
Library" means either the Library or any derivative work under
copyright law: that is to say, a work containing the Library or a
portion of it, either verbatim or with modifications and/or translated
straightforwardly into another language. (Hereinafter, translation is
included without limitation in the term "modification".)
"Source code" for a work means the preferred form of the work for
making modifications to it. For a library, complete source code means
all the source code for all modules it contains, plus any associated
interface definition files, plus the scripts used to control compilation
and installation of the library.
Activities other than copying, distribution and modification are not
covered by this License; they are outside its scope. The act of
running a program using the Library is not restricted, and output from
such a program is covered only if its contents constitute a work based
on the Library (independent of the use of the Library in a tool for
writing it). Whether that is true depends on what the Library does
and what the program that uses the Library does.
1. You may copy and distribute verbatim copies of the Library's
complete source code as you receive it, in any medium, provided that
you conspicuously and appropriately publish on each copy an
appropriate copyright notice and disclaimer of warranty; keep intact
all the notices that refer to this License and to the absence of any
warranty; and distribute a copy of this License along with the
Library.
You may charge a fee for the physical act of transferring a copy,
and you may at your option offer warranty protection in exchange for a
fee.
2. You may modify your copy or copies of the Library or any portion
of it, thus forming a work based on the Library, and copy and
distribute such modifications or work under the terms of Section 1
above, provided that you also meet all of these conditions:
a) The modified work must itself be a software library.
b) You must cause the files modified to carry prominent notices
stating that you changed the files and the date of any change.
c) You must cause the whole of the work to be licensed at no
charge to all third parties under the terms of this License.
d) If a facility in the modified Library refers to a function or a
table of data to be supplied by an application program that uses
the facility, other than as an argument passed when the facility
is invoked, then you must make a good faith effort to ensure that,
in the event an application does not supply such function or
table, the facility still operates, and performs whatever part of
its purpose remains meaningful.
(For example, a function in a library to compute square roots has
a purpose that is entirely well-defined independent of the
application. Therefore, Subsection 2d requires that any
application-supplied function or table used by this function must
be optional: if the application does not supply it, the square
root function must still compute square roots.)
These requirements apply to the modified work as a whole. If
identifiable sections of that work are not derived from the Library,
and can be reasonably considered independent and separate works in
themselves, then this License, and its terms, do not apply to those
sections when you distribute them as separate works. But when you
distribute the same sections as part of a whole which is a work based
on the Library, the distribution of the whole must be on the terms of
this License, whose permissions for other licensees extend to the
entire whole, and thus to each and every part regardless of who wrote
it.
Thus, it is not the intent of this section to claim rights or contest
your rights to work written entirely by you; rather, the intent is to
exercise the right to control the distribution of derivative or
collective works based on the Library.
In addition, mere aggregation of another work not based on the Library
with the Library (or with a work based on the Library) on a volume of
a storage or distribution medium does not bring the other work under
the scope of this License.
3. You may opt to apply the terms of the ordinary GNU General Public
License instead of this License to a given copy of the Library. To do
this, you must alter all the notices that refer to this License, so
that they refer to the ordinary GNU General Public License, version 2,
instead of to this License. (If a newer version than version 2 of the
ordinary GNU General Public License has appeared, then you can specify
that version instead if you wish.) Do not make any other change in
these notices.
Once this change is made in a given copy, it is irreversible for
that copy, so the ordinary GNU General Public License applies to all
subsequent copies and derivative works made from that copy.
This option is useful when you wish to copy part of the code of
the Library into a program that is not a library.
4. You may copy and distribute the Library (or a portion or
derivative of it, under Section 2) in object code or executable form
under the terms of Sections 1 and 2 above provided that you accompany
it with the complete corresponding machine-readable source code, which
must be distributed under the terms of Sections 1 and 2 above on a
medium customarily used for software interchange.
If distribution of object code is made by offering access to copy
from a designated place, then offering equivalent access to copy the
source code from the same place satisfies the requirement to
distribute the source code, even though third parties are not
compelled to copy the source along with the object code.
5. A program that contains no derivative of any portion of the
Library, but is designed to work with the Library by being compiled or
linked with it, is called a "work that uses the Library". Such a
work, in isolation, is not a derivative work of the Library, and
therefore falls outside the scope of this License.
However, linking a "work that uses the Library" with the Library
creates an executable that is a derivative of the Library (because it
contains portions of the Library), rather than a "work that uses the
library". The executable is therefore covered by this License.
Section 6 states terms for distribution of such executables.
When a "work that uses the Library" uses material from a header file
that is part of the Library, the object code for the work may be a
derivative work of the Library even though the source code is not.
Whether this is true is especially significant if the work can be
linked without the Library, or if the work is itself a library. The
threshold for this to be true is not precisely defined by law.
If such an object file uses only numerical parameters, data
structure layouts and accessors, and small macros and small inline
functions (ten lines or less in length), then the use of the object
file is unrestricted, regardless of whether it is legally a derivative
work. (Executables containing this object code plus portions of the
Library will still fall under Section 6.)
Otherwise, if the work is a derivative of the Library, you may
distribute the object code for the work under the terms of Section 6.
Any executables containing that work also fall under Section 6,
whether or not they are linked directly with the Library itself.
6. As an exception to the Sections above, you may also combine or
link a "work that uses the Library" with the Library to produce a
work containing portions of the Library, and distribute that work
under terms of your choice, provided that the terms permit
modification of the work for the customer's own use and reverse
engineering for debugging such modifications.
You must give prominent notice with each copy of the work that the
Library is used in it and that the Library and its use are covered by
this License. You must supply a copy of this License. If the work
during execution displays copyright notices, you must include the
copyright notice for the Library among them, as well as a reference
directing the user to the copy of this License. Also, you must do one
of these things:
a) Accompany the work with the complete corresponding
machine-readable source code for the Library including whatever
changes were used in the work (which must be distributed under
Sections 1 and 2 above); and, if the work is an executable linked
with the Library, with the complete machine-readable "work that
uses the Library", as object code and/or source code, so that the
user can modify the Library and then relink to produce a modified
executable containing the modified Library. (It is understood
that the user who changes the contents of definitions files in the
Library will not necessarily be able to recompile the application
to use the modified definitions.)
b) Use a suitable shared library mechanism for linking with the
Library. A suitable mechanism is one that (1) uses at run time a
copy of the library already present on the user's computer system,
rather than copying library functions into the executable, and (2)
will operate properly with a modified version of the library, if
the user installs one, as long as the modified version is
interface-compatible with the version that the work was made with.
c) Accompany the work with a written offer, valid for at
least three years, to give the same user the materials
specified in Subsection 6a, above, for a charge no more
than the cost of performing this distribution.
d) If distribution of the work is made by offering access to copy
from a designated place, offer equivalent access to copy the above
specified materials from the same place.
e) Verify that the user has already received a copy of these
materials or that you have already sent this user a copy.
For an executable, the required form of the "work that uses the
Library" must include any data and utility programs needed for
reproducing the executable from it. However, as a special exception,
the materials to be distributed need not include anything that is
normally distributed (in either source or binary form) with the major
components (compiler, kernel, and so on) of the operating system on
which the executable runs, unless that component itself accompanies
the executable.
It may happen that this requirement contradicts the license
restrictions of other proprietary libraries that do not normally
accompany the operating system. Such a contradiction means you cannot
use both them and the Library together in an executable that you
distribute.
7. You may place library facilities that are a work based on the
Library side-by-side in a single library together with other library
facilities not covered by this License, and distribute such a combined
library, provided that the separate distribution of the work based on
the Library and of the other library facilities is otherwise
permitted, and provided that you do these two things:
a) Accompany the combined library with a copy of the same work
based on the Library, uncombined with any other library
facilities. This must be distributed under the terms of the
Sections above.
b) Give prominent notice with the combined library of the fact
that part of it is a work based on the Library, and explaining
where to find the accompanying uncombined form of the same work.
8. You may not copy, modify, sublicense, link with, or distribute
the Library except as expressly provided under this License. Any
attempt otherwise to copy, modify, sublicense, link with, or
distribute the Library is void, and will automatically terminate your
rights under this License. However, parties who have received copies,
or rights, from you under this License will not have their licenses
terminated so long as such parties remain in full compliance.
9. You are not required to accept this License, since you have not
signed it. However, nothing else grants you permission to modify or
distribute the Library or its derivative works. These actions are
prohibited by law if you do not accept this License. Therefore, by
modifying or distributing the Library (or any work based on the
Library), you indicate your acceptance of this License to do so, and
all its terms and conditions for copying, distributing or modifying
the Library or works based on it.
10. Each time you redistribute the Library (or any work based on the
Library), the recipient automatically receives a license from the
original licensor to copy, distribute, link with or modify the Library
subject to these terms and conditions. You may not impose any further
restrictions on the recipients' exercise of the rights granted herein.
You are not responsible for enforcing compliance by third parties with
this License.
11. If, as a consequence of a court judgment or allegation of patent
infringement or for any other reason (not limited to patent issues),
conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot
distribute so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you
may not distribute the Library at all. For example, if a patent
license would not permit royalty-free redistribution of the Library by
all those who receive copies directly or indirectly through you, then
the only way you could satisfy both it and this License would be to
refrain entirely from distribution of the Library.
If any portion of this section is held invalid or unenforceable under any
particular circumstance, the balance of the section is intended to apply,
and the section as a whole is intended to apply in other circumstances.
It is not the purpose of this section to induce you to infringe any
patents or other property right claims or to contest validity of any
such claims; this section has the sole purpose of protecting the
integrity of the free software distribution system which is
implemented by public license practices. Many people have made
generous contributions to the wide range of software distributed
through that system in reliance on consistent application of that
system; it is up to the author/donor to decide if he or she is willing
to distribute software through any other system and a licensee cannot
impose that choice.
This section is intended to make thoroughly clear what is believed to
be a consequence of the rest of this License.
12. If the distribution and/or use of the Library is restricted in
certain countries either by patents or by copyrighted interfaces, the
original copyright holder who places the Library under this License may add
an explicit geographical distribution limitation excluding those countries,
so that distribution is permitted only in or among countries not thus
excluded. In such case, this License incorporates the limitation as if
written in the body of this License.
13. The Free Software Foundation may publish revised and/or new
versions of the Lesser General Public License from time to time.
Such new versions will be similar in spirit to the present version,
but may differ in detail to address new problems or concerns.
Each version is given a distinguishing version number. If the Library
specifies a version number of this License which applies to it and
"any later version", you have the option of following the terms and
conditions either of that version or of any later version published by
the Free Software Foundation. If the Library does not specify a
license version number, you may choose any version ever published by
the Free Software Foundation.
14. If you wish to incorporate parts of the Library into other free
programs whose distribution conditions are incompatible with these,
write to the author to ask for permission. For software which is
copyrighted by the Free Software Foundation, write to the Free
Software Foundation; we sometimes make exceptions for this. Our
decision will be guided by the two goals of preserving the free status
of all derivatives of our free software and of promoting the sharing
and reuse of software generally.
NO WARRANTY
15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
DAMAGES.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Libraries
If you develop a new library, and you want it to be of the greatest
possible use to the public, we recommend making it free software that
everyone can redistribute and change. You can do so by permitting
redistribution under these terms (or, alternatively, under the terms of the
ordinary General Public License).
To apply these terms, attach the following notices to the library. It is
safest to attach them to the start of each source file to most effectively
convey the exclusion of warranty; and each file should have at least the
"copyright" line and a pointer to where the full notice is found.
<one line to give the library's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
This library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Also add information on how to contact you by electronic and paper mail.
You should also get your employer (if you work as a programmer) or your
school, if any, to sign a "copyright disclaimer" for the library, if
necessary. Here is a sample; alter the names:
Yoyodyne, Inc., hereby disclaims all copyright interest in the
library `Frob' (a library for tweaking knobs) written by James Random Hacker.
<signature of Ty Coon>, 1 April 1990
Ty Coon, President of Vice
That's all there is to it!

View File

@ -1,63 +0,0 @@
# Markdownify
[![Build Status](https://travis-ci.org/Elephant418/Markdownify.png?branch=master)](https://travis-ci.org/Elephant418/Markdownify?branch=master)
[![Total Downloads](https://poser.pugx.org/pixel418/markdownify/downloads)](https://packagist.org/packages/pixel418/markdownify)
[![License LGPL](https://poser.pugx.org/pixel418/markdownify/license)](https://opensource.org/licenses/lgpl-2.1.php)
The HTML to Markdown converter for PHP
[Code example](#code-example) | [How to Install](#how-to-install) | [How to Contribute](#how-to-contribute) | [Author & Community](#author--community)
Code example
--------
### Markdown
```php
$converter = new Markdownify\Converter;
$converter->parseString('<h1>Heading</h1>');
// Returns: # Heading
```
### Markdown Extra [as defined by @michelf](http://michelf.ca/projects/php-markdown/extra/)
```php
$converter = new Markdownify\ConverterExtra;
$converter->parseString('<h1 id="md">Heading</h1>');
// Returns: # Heading {#md}
```
How to Install
--------
This library package requires `PHP 5.3` or later.<br>
Install [Composer](http://getcomposer.org/doc/01-basic-usage.md#installation) and run the following command to get the latest version:
```sh
composer require pixel418/markdownify
```
How to Contribute
--------
1. Fork the Markdownify repository
2. Create a new branch for each feature or improvement
3. Send a pull request from each feature branch to the **v2.x** branch
If you don't know much about pull request, you can read [the Github article](https://help.github.com/articles/using-pull-requests)
Author & Community
--------
Markdownify is under [LGPL License](http://opensource.org/licenses/LGPL-2.1)<br>
It was created by [Milian Wolff](http://milianw.de)<br>
It was converted to a Symfony Bundle by [Peter Kruithof](https://github.com/pkruithof)<br>
It is maintained by [Thomas ZILLIOX](http://tzi.fr)

View File

@ -1,38 +0,0 @@
{
"name": "pixel418/markdownify",
"type": "lib",
"description": "The HTML to Markdown converter for PHP ",
"keywords": ["markdown", "markdownify"],
"license": "LGPL",
"homepage": "https://github.com/elephant418/Markdownify",
"authors": [
{
"name": "Milian Wolff",
"email": "mail@milianw.de",
"homepage": "http://milianw.de"
},
{
"name": "Peter Kruithof",
"email": "pkruithof@gmail.com",
"homepage": "http://pkruithof.tumblr.com/"
},
{
"name": "Thomas Zilliox",
"email": "hello@tzi.fr",
"homepage": "http://tzi.fr"
}
],
"require": {
"php": ">=5.3.0"
},
"require-dev": {
"phpunit/phpunit": "^4.8"
},
"autoload": {
"psr-4": {
"Markdownify\\": "src",
"Test\\Markdownify\\": "test"
}
}
}

File diff suppressed because it is too large Load Diff

View File

@ -1,573 +0,0 @@
<?php
/* This file is part of the Markdownify project, which is under LGPL license */
namespace Markdownify;
class ConverterExtra extends Converter
{
/**
* table data, including rows with content and the maximum width of each col
*
* @var array
*/
protected $table = array();
/**
* current col
*
* @var int
*/
protected $col = -1;
/**
* current row
*
* @var int
*/
protected $row = 0;
/**
* constructor, see Markdownify::Markdownify() for more information
*/
public function __construct($linksAfterEachParagraph = self::LINK_AFTER_CONTENT, $bodyWidth = MDFY_BODYWIDTH, $keepHTML = MDFY_KEEPHTML)
{
parent::__construct($linksAfterEachParagraph, $bodyWidth, $keepHTML);
// new markdownable tags & attributes
// header ids: # foo {bar}
$this->isMarkdownable['h1']['id'] = 'optional';
$this->isMarkdownable['h1']['class'] = 'optional';
$this->isMarkdownable['h2']['id'] = 'optional';
$this->isMarkdownable['h2']['class'] = 'optional';
$this->isMarkdownable['h3']['id'] = 'optional';
$this->isMarkdownable['h3']['class'] = 'optional';
$this->isMarkdownable['h4']['id'] = 'optional';
$this->isMarkdownable['h4']['class'] = 'optional';
$this->isMarkdownable['h5']['id'] = 'optional';
$this->isMarkdownable['h5']['class'] = 'optional';
$this->isMarkdownable['h6']['id'] = 'optional';
$this->isMarkdownable['h6']['class'] = 'optional';
// tables
$this->isMarkdownable['table'] = array();
$this->isMarkdownable['th'] = array(
'align' => 'optional',
);
$this->isMarkdownable['td'] = array(
'align' => 'optional',
);
$this->isMarkdownable['tr'] = array();
array_push($this->ignore, 'thead');
array_push($this->ignore, 'tbody');
array_push($this->ignore, 'tfoot');
// definition lists
$this->isMarkdownable['dl'] = array();
$this->isMarkdownable['dd'] = array();
$this->isMarkdownable['dt'] = array();
// link class
$this->isMarkdownable['a']['id'] = 'optional';
$this->isMarkdownable['a']['class'] = 'optional';
// footnotes
$this->isMarkdownable['fnref'] = array(
'target' => 'required',
);
$this->isMarkdownable['footnotes'] = array();
$this->isMarkdownable['fn'] = array(
'name' => 'required',
);
$this->parser->blockElements['fnref'] = false;
$this->parser->blockElements['fn'] = true;
$this->parser->blockElements['footnotes'] = true;
// abbr
$this->isMarkdownable['abbr'] = array(
'title' => 'required',
);
// build RegEx lookahead to decide wether table can pe parsed or not
$inlineTags = array_keys($this->parser->blockElements, false);
$colContents = '(?:[^<]|<(?:' . implode('|', $inlineTags) . '|[^a-z]))*';
$this->tableLookaheadHeader = '{
^\s*(?:<thead\s*>)?\s* # open optional thead
<tr\s*>\s*(?: # start required row with headers
<th(?:\s+align=("|\')(?:left|center|right)\1)?\s*> # header with optional align
\s*' . $colContents . '\s* # contents
</th>\s* # close header
)+</tr> # close row with headers
\s*(?:</thead>)? # close optional thead
}sxi';
$this->tdSubstitute = '\s*' . $colContents . '\s* # contents
</td>\s*';
$this->tableLookaheadBody = '{
\s*(?:<tbody\s*>)?\s* # open optional tbody
(?:<tr\s*>\s* # start row
%s # cols to be substituted
</tr>)+ # close row
\s*(?:</tbody>)? # close optional tbody
\s*</table> # close table
}sxi';
}
/**
* handle header tags (<h1> - <h6>)
*
* @param int $level 1-6
* @return void
*/
protected function handleHeader($level)
{
if ($this->parser->isStartTag) {
$this->parser->tagAttributes['cssSelector'] = $this->getCurrentCssSelector();
$this->stack();
} else {
$tag = $this->unstack();
if (!empty($tag['cssSelector'])) {
// {#id.class}
$this->out(' {' . $tag['cssSelector'] . '}');
}
}
parent::handleHeader($level);
}
/**
* handle <a> tags parsing
*
* @param void
* @return void
*/
protected function handleTag_a_parser()
{
parent::handleTag_a_parser();
$this->parser->tagAttributes['cssSelector'] = $this->getCurrentCssSelector();
}
/**
* handle <a> tags conversion
*
* @param array $tag
* @param string $buffer
* @return string The markdownified link
*/
protected function handleTag_a_converter($tag, $buffer)
{
$output = parent::handleTag_a_converter($tag, $buffer);
if (!empty($tag['cssSelector'])) {
// [This link][id]{#id.class}
$output .= '{' . $tag['cssSelector'] . '}';
}
return $output;
}
/**
* handle <abbr> tags
*
* @param void
* @return void
*/
protected function handleTag_abbr()
{
if ($this->parser->isStartTag) {
$this->stack();
$this->buffer();
} else {
$tag = $this->unstack();
$tag['text'] = $this->unbuffer();
$add = true;
foreach ($this->stack['abbr'] as $stacked) {
if ($stacked['text'] == $tag['text']) {
/** TODO: differing abbr definitions, i.e. different titles for same text **/
$add = false;
break;
}
}
$this->out($tag['text']);
if ($add) {
array_push($this->stack['abbr'], $tag);
}
}
}
/**
* flush stacked abbr tags
*
* @param void
* @return void
*/
protected function flushStacked_abbr()
{
$out = array();
foreach ($this->stack['abbr'] as $k => $tag) {
if (!isset($tag['unstacked'])) {
array_push($out, ' *[' . $tag['text'] . ']: ' . $tag['title']);
$tag['unstacked'] = true;
$this->stack['abbr'][$k] = $tag;
}
}
if (!empty($out)) {
$this->out("\n\n" . implode("\n", $out));
}
}
/**
* handle <table> tags
*
* @param void
* @return void
*/
protected function handleTag_table()
{
if ($this->parser->isStartTag) {
// check if upcoming table can be converted
if ($this->keepHTML) {
if (preg_match($this->tableLookaheadHeader, $this->parser->html, $matches)) {
// header seems good, now check body
// get align & number of cols
preg_match_all('#<th(?:\s+align=("|\')(left|right|center)\1)?\s*>#si', $matches[0], $cols);
$regEx = '';
$i = 1;
$aligns = array();
foreach ($cols[2] as $align) {
$align = strtolower($align);
array_push($aligns, $align);
if (empty($align)) {
$align = 'left'; // default value
}
$td = '\s+align=("|\')' . $align . '\\' . $i;
$i++;
if ($align == 'left') {
// look for empty align or left
$td = '(?:' . $td . ')?';
}
$td = '<td' . $td . '\s*>';
$regEx .= $td . $this->tdSubstitute;
}
$regEx = sprintf($this->tableLookaheadBody, $regEx);
if (preg_match($regEx, $this->parser->html, $matches, null, strlen($matches[0]))) {
// this is a markdownable table tag!
$this->table = array(
'rows' => array(),
'col_widths' => array(),
'aligns' => $aligns,
);
$this->row = 0;
} else {
// non markdownable table
$this->handleTagToText();
}
} else {
// non markdownable table
$this->handleTagToText();
}
} else {
$this->table = array(
'rows' => array(),
'col_widths' => array(),
'aligns' => array(),
);
$this->row = 0;
}
} else {
// finally build the table in Markdown Extra syntax
$separator = array();
if (!isset($this->table['aligns'])) {
$this->table['aligns'] = array();
}
// seperator with correct align identifiers
foreach ($this->table['aligns'] as $col => $align) {
if (!$this->keepHTML && !isset($this->table['col_widths'][$col])) {
break;
}
$left = ' ';
$right = ' ';
switch ($align) {
case 'left':
$left = ':';
break;
case 'center':
$right = ':';
$left = ':';
case 'right':
$right = ':';
break;
}
array_push($separator, $left . str_repeat('-', $this->table['col_widths'][$col]) . $right);
}
$separator = '|' . implode('|', $separator) . '|';
$rows = array();
// add padding
array_walk_recursive($this->table['rows'], array(&$this, 'alignTdContent'));
$header = array_shift($this->table['rows']);
array_push($rows, '| ' . implode(' | ', $header) . ' |');
array_push($rows, $separator);
foreach ($this->table['rows'] as $row) {
array_push($rows, '| ' . implode(' | ', $row) . ' |');
}
$this->out(implode("\n" . $this->indent, $rows));
$this->table = array();
$this->setLineBreaks(2);
}
}
/**
* properly pad content so it is aligned as whished
* should be used with array_walk_recursive on $this->table['rows']
*
* @param string &$content
* @param int $col
* @return void
*/
protected function alignTdContent(&$content, $col)
{
if (!isset($this->table['aligns'][$col])) {
$this->table['aligns'][$col] = 'left';
}
switch ($this->table['aligns'][$col]) {
default:
case 'left':
$content .= str_repeat(' ', $this->table['col_widths'][$col] - $this->strlen($content));
break;
case 'right':
$content = str_repeat(' ', $this->table['col_widths'][$col] - $this->strlen($content)) . $content;
break;
case 'center':
$paddingNeeded = $this->table['col_widths'][$col] - $this->strlen($content);
$left = floor($paddingNeeded / 2);
$right = $paddingNeeded - $left;
$content = str_repeat(' ', $left) . $content . str_repeat(' ', $right);
break;
}
}
/**
* handle <tr> tags
*
* @param void
* @return void
*/
protected function handleTag_tr()
{
if ($this->parser->isStartTag) {
$this->col = -1;
} else {
$this->row++;
}
}
/**
* handle <td> tags
*
* @param void
* @return void
*/
protected function handleTag_td()
{
if ($this->parser->isStartTag) {
$this->col++;
if (!isset($this->table['col_widths'][$this->col])) {
$this->table['col_widths'][$this->col] = 0;
}
$this->buffer();
} else {
$buffer = trim($this->unbuffer());
if (!isset($this->table['col_widths'][$this->col])) {
$this->table['col_widths'][$this->col] = 0;
}
$this->table['col_widths'][$this->col] = max($this->table['col_widths'][$this->col], $this->strlen($buffer));
$this->table['rows'][$this->row][$this->col] = $buffer;
}
}
/**
* handle <th> tags
*
* @param void
* @return void
*/
protected function handleTag_th()
{
if (!$this->keepHTML && !isset($this->table['rows'][1]) && !isset($this->table['aligns'][$this->col + 1])) {
if (isset($this->parser->tagAttributes['align'])) {
$this->table['aligns'][$this->col + 1] = $this->parser->tagAttributes['align'];
} else {
$this->table['aligns'][$this->col + 1] = '';
}
}
$this->handleTag_td();
}
/**
* handle <dl> tags
*
* @param void
* @return void
*/
protected function handleTag_dl()
{
if (!$this->parser->isStartTag) {
$this->setLineBreaks(2);
}
}
/**
* handle <dt> tags
*
* @param void
* @return void
**/
protected function handleTag_dt()
{
if (!$this->parser->isStartTag) {
$this->setLineBreaks(1);
}
}
/**
* handle <dd> tags
*
* @param void
* @return void
*/
protected function handleTag_dd()
{
if ($this->parser->isStartTag) {
if (substr(ltrim($this->parser->html), 0, 3) == '<p>') {
// next comes a paragraph, so we'll need an extra line
$this->out("\n" . $this->indent);
} elseif (substr($this->output, -2) == "\n\n") {
$this->output = substr($this->output, 0, -1);
}
$this->out(': ');
$this->indent(' ', false);
} else {
// lookahead for next dt
if (substr(ltrim($this->parser->html), 0, 4) == '<dt>') {
$this->setLineBreaks(2);
} else {
$this->setLineBreaks(1);
}
$this->indent(' ');
}
}
/**
* handle <fnref /> tags (custom footnote references, see markdownify_extra::parseString())
*
* @param void
* @return void
*/
protected function handleTag_fnref()
{
$this->out('[^' . $this->parser->tagAttributes['target'] . ']');
}
/**
* handle <fn> tags (custom footnotes, see markdownify_extra::parseString()
* and markdownify_extra::_makeFootnotes())
*
* @param void
* @return void
*/
protected function handleTag_fn()
{
if ($this->parser->isStartTag) {
$this->out('[^' . $this->parser->tagAttributes['name'] . ']:');
$this->setLineBreaks(1);
} else {
$this->setLineBreaks(2);
}
$this->indent(' ');
}
/**
* handle <footnotes> tag (custom footnotes, see markdownify_extra::parseString()
* and markdownify_extra::_makeFootnotes())
*
* @param void
* @return void
*/
protected function handleTag_footnotes()
{
if (!$this->parser->isStartTag) {
$this->setLineBreaks(2);
}
}
/**
* parse a HTML string, clean up footnotes prior
*
* @param string $HTML input
* @return string Markdown formatted output
*/
public function parseString($html)
{
/** TODO: custom markdown-extra options, e.g. titles & classes **/
// <sup id="fnref:..."><a href"#fn..." rel="footnote">...</a></sup>
// => <fnref target="..." />
$html = preg_replace('@<sup id="fnref:([^"]+)">\s*<a href="#fn:\1" rel="footnote">\s*\d+\s*</a>\s*</sup>@Us', '<fnref target="$1" />', $html);
// <div class="footnotes">
// <hr />
// <ol>
//
// <li id="fn:...">...</li>
// ...
//
// </ol>
// </div>
// =>
// <footnotes>
// <fn name="...">...</fn>
// ...
// </footnotes>
$html = preg_replace_callback('#<div class="footnotes">\s*<hr />\s*<ol>\s*(.+)\s*</ol>\s*</div>#Us', array(&$this, '_makeFootnotes'), $html);
return parent::parseString($html);
}
/**
* replace HTML representation of footnotes with something more easily parsable
*
* @note this is a callback to be used in parseString()
*
* @param array $matches
* @return string
*/
protected function _makeFootnotes($matches)
{
// <li id="fn:1">
// ...
// <a href="#fnref:block" rev="footnote">&#8617;</a></p>
// </li>
// => <fn name="1">...</fn>
// remove footnote link
$fns = preg_replace('@\s*(&#160;\s*)?<a href="#fnref:[^"]+" rev="footnote"[^>]*>&#8617;</a>\s*@s', '', $matches[1]);
// remove empty paragraph
$fns = preg_replace('@<p>\s*</p>@s', '', $fns);
// <li id="fn:1">...</li> -> <footnote nr="1">...</footnote>
$fns = str_replace('<li id="fn:', '<fn name="', $fns);
$fns = '<footnotes>' . $fns . '</footnotes>';
return preg_replace('#</li>\s*(?=(?:<fn|</footnotes>))#s', '</fn>$1', $fns);
}
/**
* handle <a> tags parsing
*
* @param void
* @return void
*/
protected function getCurrentCssSelector()
{
$cssSelector = '';
if (isset($this->parser->tagAttributes['id'])) {
$cssSelector .= '#' . $this->decode($this->parser->tagAttributes['id']);
}
if (isset($this->parser->tagAttributes['class'])) {
$classes = explode(' ', $this->decode($this->parser->tagAttributes['class']));
$classes = array_filter($classes);
$cssSelector .= '.' . join('.', $classes);
}
return $cssSelector;
}
}

View File

@ -1,564 +0,0 @@
<?php
/* This file is part of the Markdownify project, which is under LGPL license */
namespace Markdownify;
class Parser
{
public static $skipWhitespace = true;
public static $a_ord;
public static $z_ord;
public static $special_ords;
/**
* tags which are always empty (<br /> etc.)
*
* @var array<string>
*/
public $emptyTags = array(
'br',
'hr',
'input',
'img',
'area',
'link',
'meta',
'param',
);
/**
* tags with preformatted text
* whitespaces wont be touched in them
*
* @var array<string>
*/
public $preformattedTags = array(
'script',
'style',
'pre',
'code',
);
/**
* supress HTML tags inside preformatted tags (see above)
*
* @var bool
*/
public $noTagsInCode = false;
/**
* html to be parsed
*
* @var string
*/
public $html = '';
/**
* node type:
*
* - tag (see isStartTag)
* - text (includes cdata)
* - comment
* - doctype
* - pi (processing instruction)
*
* @var string
*/
public $nodeType = '';
/**
* current node content, i.e. either a
* simple string (text node), or something like
* <tag attrib="value"...>
*
* @var string
*/
public $node = '';
/**
* wether current node is an opening tag (<a>) or not (</a>)
* set to NULL if current node is not a tag
* NOTE: empty tags (<br />) set this to true as well!
*
* @var bool | null
*/
public $isStartTag = null;
/**
* wether current node is an empty tag (<br />) or not (<a></a>)
*
* @var bool | null
*/
public $isEmptyTag = null;
/**
* tag name
*
* @var string | null
*/
public $tagName = '';
/**
* attributes of current tag
*
* @var array (attribName=>value) | null
*/
public $tagAttributes = null;
/**
* whether or not the actual context is a inline context
*
* @var bool | null
*/
public $isInlineContext = null;
/**
* whether the current tag is a block element
*
* @var bool | null
*/
public $isBlockElement = null;
/**
* whether the previous tag (browser) is a block element
*
* @var bool | null
*/
public $isNextToInlineContext = null;
/**
* keep whitespace
*
* @var int
*/
public $keepWhitespace = 0;
/**
* list of open tags
* count this to get current depth
*
* @var array
*/
public $openTags = array();
/**
* list of block elements
*
* @var array
* TODO: what shall we do with <del> and <ins> ?!
*/
public $blockElements = array(
// tag name => <bool> is block
// block elements
'address' => true,
'blockquote' => true,
'center' => true,
'del' => true,
'dir' => true,
'div' => true,
'dl' => true,
'fieldset' => true,
'form' => true,
'h1' => true,
'h2' => true,
'h3' => true,
'h4' => true,
'h5' => true,
'h6' => true,
'hr' => true,
'ins' => true,
'isindex' => true,
'menu' => true,
'noframes' => true,
'noscript' => true,
'ol' => true,
'p' => true,
'pre' => true,
'table' => true,
'ul' => true,
// set table elements and list items to block as well
'thead' => true,
'tbody' => true,
'tfoot' => true,
'td' => true,
'tr' => true,
'th' => true,
'li' => true,
'dd' => true,
'dt' => true,
// header items and html / body as well
'html' => true,
'body' => true,
'head' => true,
'meta' => true,
'link' => true,
'style' => true,
'title' => true,
// unfancy media tags, when indented should be rendered as block
'map' => true,
'object' => true,
'param' => true,
'embed' => true,
'area' => true,
// inline elements
'a' => false,
'abbr' => false,
'acronym' => false,
'applet' => false,
'b' => false,
'basefont' => false,
'bdo' => false,
'big' => false,
'br' => false,
'button' => false,
'cite' => false,
'code' => false,
'del' => false,
'dfn' => false,
'em' => false,
'font' => false,
'i' => false,
'img' => false,
'ins' => false,
'input' => false,
'iframe' => false,
'kbd' => false,
'label' => false,
'q' => false,
'samp' => false,
'script' => false,
'select' => false,
'small' => false,
'span' => false,
'strong' => false,
'sub' => false,
'sup' => false,
'textarea' => false,
'tt' => false,
'var' => false,
);
/**
* get next node, set $this->html prior!
*
* @param void
* @return bool
*/
public function nextNode()
{
if (empty($this->html)) {
// we are done with parsing the html string
return false;
}
if ($this->isStartTag && !$this->isEmptyTag) {
array_push($this->openTags, $this->tagName);
if (in_array($this->tagName, $this->preformattedTags)) {
// dont truncate whitespaces for <code> or <pre> contents
$this->keepWhitespace++;
}
}
if ($this->html[0] == '<') {
$token = substr($this->html, 0, 9);
if (substr($token, 0, 2) == '<?') {
// xml prolog or other pi's
/** TODO **/
// trigger_error('this might need some work', E_USER_NOTICE);
$pos = strpos($this->html, '>');
$this->setNode('pi', $pos + 1);
return true;
}
if (substr($token, 0, 4) == '<!--') {
// comment
$pos = strpos($this->html, '-->');
if ($pos === false) {
// could not find a closing -->, use next gt instead
// this is firefox' behaviour
$pos = strpos($this->html, '>') + 1;
} else {
$pos += 3;
}
$this->setNode('comment', $pos);
static::$skipWhitespace = true;
return true;
}
if ($token == '<!DOCTYPE') {
// doctype
$this->setNode('doctype', strpos($this->html, '>') + 1);
static::$skipWhitespace = true;
return true;
}
if ($token == '<![CDATA[') {
// cdata, use text node
// remove leading <![CDATA[
$this->html = substr($this->html, 9);
$this->setNode('text', strpos($this->html, ']]>') + 3);
// remove trailing ]]> and trim
$this->node = substr($this->node, 0, -3);
$this->handleWhitespaces();
static::$skipWhitespace = true;
return true;
}
if ($this->parseTag()) {
// seems to be a tag
// handle whitespaces
if ($this->isBlockElement) {
static::$skipWhitespace = true;
} else {
static::$skipWhitespace = false;
}
return true;
}
}
if ($this->keepWhitespace) {
static::$skipWhitespace = false;
}
// when we get here it seems to be a text node
$pos = strpos($this->html, '<');
if ($pos === false) {
$pos = strlen($this->html);
}
$this->setNode('text', $pos);
$this->handleWhitespaces();
if (static::$skipWhitespace && $this->node == ' ') {
return $this->nextNode();
}
$this->isInlineContext = true;
static::$skipWhitespace = false;
return true;
}
/**
* parse tag, set tag name and attributes, see if it's a closing tag and so forth...
*
* @param void
* @return bool
*/
protected function parseTag()
{
if (!isset(static::$a_ord)) {
static::$a_ord = ord('a');
static::$z_ord = ord('z');
static::$special_ords = array(
ord(':'), // for xml:lang
ord('-'), // for http-equiv
);
}
$tagName = '';
$pos = 1;
$isStartTag = $this->html[$pos] != '/';
if (!$isStartTag) {
$pos++;
}
// get tagName
while (isset($this->html[$pos])) {
$pos_ord = ord(strtolower($this->html[$pos]));
if (($pos_ord >= static::$a_ord && $pos_ord <= static::$z_ord) || (!empty($tagName) && is_numeric($this->html[$pos]))) {
$tagName .= $this->html[$pos];
$pos++;
} else {
$pos--;
break;
}
}
$tagName = strtolower($tagName);
if (empty($tagName) || !isset($this->blockElements[$tagName])) {
// something went wrong => invalid tag
$this->invalidTag();
return false;
}
if ($this->noTagsInCode && end($this->openTags) == 'code' && !($tagName == 'code' && !$isStartTag)) {
// we supress all HTML tags inside code tags
$this->invalidTag();
return false;
}
// get tag attributes
/** TODO: in html 4 attributes do not need to be quoted **/
$isEmptyTag = false;
$attributes = array();
$currAttrib = '';
while (isset($this->html[$pos + 1])) {
$pos++;
// close tag
if ($this->html[$pos] == '>' || $this->html[$pos] . $this->html[$pos + 1] == '/>') {
if ($this->html[$pos] == '/') {
$isEmptyTag = true;
$pos++;
}
break;
}
$pos_ord = ord(strtolower($this->html[$pos]));
if (($pos_ord >= static::$a_ord && $pos_ord <= static::$z_ord) || in_array($pos_ord, static::$special_ords)) {
// attribute name
$currAttrib .= $this->html[$pos];
} elseif (in_array($this->html[$pos], array(' ', "\t", "\n"))) {
// drop whitespace
} elseif (in_array($this->html[$pos] . $this->html[$pos + 1], array('="', "='"))) {
// get attribute value
$pos++;
$await = $this->html[$pos]; // single or double quote
$pos++;
$value = '';
while (isset($this->html[$pos]) && $this->html[$pos] != $await) {
$value .= $this->html[$pos];
$pos++;
}
$attributes[$currAttrib] = $value;
$currAttrib = '';
} else {
$this->invalidTag();
return false;
}
}
if ($this->html[$pos] != '>') {
$this->invalidTag();
return false;
}
if (!empty($currAttrib)) {
// html 4 allows something like <option selected> instead of <option selected="selected">
$attributes[$currAttrib] = $currAttrib;
}
if (!$isStartTag) {
if (!empty($attributes) || $tagName != end($this->openTags)) {
// end tags must not contain any attributes
// or maybe we did not expect a different tag to be closed
$this->invalidTag();
return false;
}
array_pop($this->openTags);
if (in_array($tagName, $this->preformattedTags)) {
$this->keepWhitespace--;
}
}
$pos++;
$this->node = substr($this->html, 0, $pos);
$this->html = substr($this->html, $pos);
$this->tagName = $tagName;
$this->tagAttributes = $attributes;
$this->isStartTag = $isStartTag;
$this->isEmptyTag = $isEmptyTag || in_array($tagName, $this->emptyTags);
if ($this->isEmptyTag) {
// might be not well formed
$this->node = preg_replace('# */? *>$#', ' />', $this->node);
}
$this->nodeType = 'tag';
$this->isBlockElement = $this->blockElements[$tagName];
$this->isNextToInlineContext = $isStartTag && $this->isInlineContext;
$this->isInlineContext = !$this->isBlockElement;
return true;
}
/**
* handle invalid tags
*
* @param void
* @return void
*/
protected function invalidTag()
{
$this->html = substr_replace($this->html, '&lt;', 0, 1);
}
/**
* update all vars and make $this->html shorter
*
* @param string $type see description for $this->nodeType
* @param int $pos to which position shall we cut?
* @return void
*/
protected function setNode($type, $pos)
{
if ($this->nodeType == 'tag') {
// set tag specific vars to null
// $type == tag should not be called here
// see this::parseTag() for more
$this->tagName = null;
$this->tagAttributes = null;
$this->isStartTag = null;
$this->isEmptyTag = null;
$this->isBlockElement = null;
}
$this->nodeType = $type;
$this->node = substr($this->html, 0, $pos);
$this->html = substr($this->html, $pos);
}
/**
* check if $this->html begins with $str
*
* @param string $str
* @return bool
*/
protected function match($str)
{
return substr($this->html, 0, strlen($str)) == $str;
}
/**
* truncate whitespaces
*
* @param void
* @return void
*/
protected function handleWhitespaces()
{
if ($this->keepWhitespace) {
// <pre> or <code> before...
return;
}
// truncate multiple whitespaces to a single one
$this->node = preg_replace('#\s+#s', ' ', $this->node);
}
/**
* normalize self::node
*
* @param void
* @return void
*/
protected function normalizeNode()
{
$this->node = '<';
if (!$this->isStartTag) {
$this->node .= '/' . $this->tagName . '>';
return;
}
$this->node .= $this->tagName;
foreach ($this->tagAttributes as $name => $value) {
$this->node .= ' ' . $name . '="' . str_replace('"', '&quot;', $value) . '"';
}
if ($this->isEmptyTag) {
$this->node .= ' /';
}
$this->node .= '>';
}
}