Merge remote-tracking branch 'github/lib' into lib-1.x

This commit is contained in:
Michel Fortin 2022-09-22 23:23:01 -04:00
commit 5bbf780e31
9 changed files with 139 additions and 140 deletions

30
.github/workflows/ci.yml vendored Normal file
View file

@ -0,0 +1,30 @@
name: CI
on:
pull_request: null
push:
branches:
- lib
jobs:
tests:
runs-on: ubuntu-latest
strategy:
matrix:
php:
- '7.4'
- '8.0'
- '8.1'
- '8.2'
name: Linting - PHP ${{ matrix.php }}
steps:
- uses: actions/checkout@v2
- uses: shivammathur/setup-php@v2
with:
php-version: ${{ matrix.php }}
coverage: none
extensions: intl
- run: composer install --no-progress
# - run: composer codestyle
- run: composer phpstan
if: matrix.php == '8.1'
- run: composer tests

View file

@ -1,7 +1,7 @@
build:
environment:
php:
version: '7.0.20'
version: '7.4'
nodes:
analysis:
project_setup:

View file

@ -4,24 +4,10 @@ matrix:
include:
- php: hhvm-3.18
dist: trusty
- php: 5.3
dist: precise
- php: 5.4
dist: trusty
- php: 5.5
dist: trusty
- php: 5.6
dist: xenial
- php: 7.0
dist: xenial
- php: 7.1
dist: bionic
- php: 7.2
dist: bionic
- php: 7.3
dist: bionic
- php: 7.4
dist: bionic
- php: 8.0
dist: bionic
install:
- composer install --prefer-dist

View file

@ -31,7 +31,7 @@ class Markdown implements MarkdownInterface {
*/
public static function defaultTransform($text) {
// Take parser class on which this function was called.
$parser_class = \get_called_class();
$parser_class = static::class;
// Try to take parser from the static parser list
static $parser_list;
@ -49,39 +49,34 @@ class Markdown implements MarkdownInterface {
/**
* Configuration variables
*/
/**
* Change to ">" for HTML output.
* @var string
*/
public $empty_element_suffix = " />";
public string $empty_element_suffix = " />";
/**
* The width of indentation of the output markup
* @var int
*/
public $tab_width = 4;
public int $tab_width = 4;
/**
* Change to `true` to disallow markup or entities.
* @var boolean
*/
public $no_markup = false;
public $no_entities = false;
public bool $no_markup = false;
public bool $no_entities = false;
/**
* Change to `true` to enable line breaks on \n without two trailling spaces
* @var boolean
*/
public $hard_wrap = false;
public bool $hard_wrap = false;
/**
* Predefined URLs and titles for reference links and images.
* @var array
*/
public $predef_urls = array();
public $predef_titles = array();
public array $predef_urls = array();
public array $predef_titles = array();
/**
* Optional filter function for URLs
@ -121,32 +116,27 @@ class Markdown implements MarkdownInterface {
* <li>List item two</li>
* <li>List item three</li>
* </ol>
*
* @var bool
*/
public $enhanced_ordered_list = false;
public bool $enhanced_ordered_list = false;
/**
* Parser implementation
*/
/**
* Regex to match balanced [brackets].
* Needed to insert a maximum bracked depth while converting to PHP.
* @var int
*/
protected $nested_brackets_depth = 6;
protected int $nested_brackets_depth = 6;
protected $nested_brackets_re;
protected $nested_url_parenthesis_depth = 4;
protected int $nested_url_parenthesis_depth = 4;
protected $nested_url_parenthesis_re;
/**
* Table of hash values for escaped characters:
* @var string
*/
protected $escape_chars = '\`*_{}[]()>#+-.!';
protected $escape_chars_re;
protected string $escape_chars = '\`*_{}[]()>#+-.!';
protected string $escape_chars_re;
/**
* Constructor function. Initialize appropriate member variables.
@ -175,23 +165,20 @@ class Markdown implements MarkdownInterface {
/**
* Internal hashes used during transformation.
* @var array
*/
protected $urls = array();
protected array $urls = array();
protected $titles = array();
protected $html_hashes = array();
protected array $html_hashes = array();
/**
* Status flag to avoid invalid nesting.
* @var boolean
*/
protected $in_anchor = false;
protected bool $in_anchor = false;
/**
* Status flag to avoid invalid nesting.
* @var boolean
*/
protected $in_emphasis_processing = false;
protected bool $in_emphasis_processing = false;
/**
* Called before the transformation process starts to setup parser states.
@ -263,9 +250,8 @@ class Markdown implements MarkdownInterface {
/**
* Define the document gamut
* @var array
*/
protected $document_gamut = array(
protected array $document_gamut = array(
// Strip link definitions, store in hashes.
"stripLinkDefinitions" => 20,
"runBasicBlockGamut" => 30,
@ -525,9 +511,8 @@ class Markdown implements MarkdownInterface {
/**
* Define the block gamut - these are all the transformations that form
* block-level tags like paragraphs, headers, and list items.
* @var array
*/
protected $block_gamut = array(
protected array $block_gamut = array(
"doHeaders" => 10,
"doHorizontalRules" => 20,
"doLists" => 40,
@ -597,9 +582,8 @@ class Markdown implements MarkdownInterface {
/**
* These are all the transformations that occur *within* block-level
* tags like paragraphs, headers, and list items.
* @var array
*/
protected $span_gamut = array(
protected array $span_gamut = array(
// Process character escapes, code spans, and inline HTML
// in one shot.
"parseSpan" => -30,
@ -724,7 +708,7 @@ class Markdown implements MarkdownInterface {
/**
* Callback method to parse referenced anchors
* @param string $matches
* @param array $matches
* @return string
*/
protected function _doAnchors_reference_callback($matches) {
@ -763,7 +747,7 @@ class Markdown implements MarkdownInterface {
/**
* Callback method to parse inline anchors
* @param string $matches
* @param array $matches
* @return string
*/
protected function _doAnchors_inline_callback($matches) {
@ -781,7 +765,7 @@ class Markdown implements MarkdownInterface {
$url = $this->encodeURLAttribute($url);
$result = "<a href=\"$url\"";
if (isset($title)) {
if ($title) {
$title = $this->encodeAttribute($title);
$result .= " title=\"$title\"";
}
@ -1105,9 +1089,8 @@ class Markdown implements MarkdownInterface {
/**
* Nesting tracker for list levels
* @var integer
*/
protected $list_level = 0;
protected int $list_level = 0;
/**
* Process the contents of a single ordered or unordered list, splitting it
@ -1248,7 +1231,7 @@ class Markdown implements MarkdownInterface {
* Define the emphasis operators with their regex matches
* @var array
*/
protected $em_relist = array(
protected array $em_relist = array(
'' => '(?:(?<!\*)\*(?!\*)|(?<!_)_(?!_))(?![\.,:;]?\s)',
'*' => '(?<![\s*])\*(?!\*)',
'_' => '(?<![\s_])_(?!_)',
@ -1258,7 +1241,7 @@ class Markdown implements MarkdownInterface {
* Define the strong operators with their regex matches
* @var array
*/
protected $strong_relist = array(
protected array $strong_relist = array(
'' => '(?:(?<!\*)\*\*(?!\*)|(?<!_)__(?!_))(?![\.,:;]?\s)',
'**' => '(?<![\s*])\*\*(?!\*)',
'__' => '(?<![\s_])__(?!_)',
@ -1268,7 +1251,7 @@ class Markdown implements MarkdownInterface {
* Define the emphasis + strong operators with their regex matches
* @var array
*/
protected $em_strong_relist = array(
protected array $em_strong_relist = array(
'' => '(?:(?<!\*)\*\*\*(?!\*)|(?<!_)___(?!_))(?![\.,:;]?\s)',
'***' => '(?<![\s*])\*\*\*(?!\*)',
'___' => '(?<![\s_])___(?!_)',
@ -1276,9 +1259,8 @@ class Markdown implements MarkdownInterface {
/**
* Container for prepared regular expressions
* @var array
*/
protected $em_strong_prepared_relist;
protected ?array $em_strong_prepared_relist = null;
/**
* Prepare regular expressions for searching emphasis tokens in any
@ -1826,7 +1808,7 @@ class Markdown implements MarkdownInterface {
/**
* String length function for detab. `_initDetab` will create a function to
* handle UTF-8 if the default function does not exist.
* @var string
* can be a string or function
*/
protected $utf8_strlen = 'mb_strlen';
@ -1883,9 +1865,7 @@ class Markdown implements MarkdownInterface {
return;
}
$this->utf8_strlen = function($text) {
return preg_match_all('/[\x00-\xBF]|[\xC0-\xFF][\x80-\xBF]*/', $text, $m);
};
$this->utf8_strlen = fn($text) => preg_match_all('/[\x00-\xBF]|[\xC0-\xFF][\x80-\xBF]*/', $text, $m);
}
/**

View file

@ -17,25 +17,21 @@ class MarkdownExtra extends \Michelf\Markdown {
/**
* Configuration variables
*/
/**
* Prefix for footnote ids.
* @var string
*/
public $fn_id_prefix = "";
public string $fn_id_prefix = "";
/**
* Optional title attribute for footnote links.
* @var string
*/
public $fn_link_title = "";
public string $fn_link_title = "";
/**
* Optional class attribute for footnote links and backlinks.
* @var string
*/
public $fn_link_class = "footnote-ref";
public $fn_backlink_class = "footnote-backref";
public string $fn_link_class = "footnote-ref";
public string $fn_backlink_class = "footnote-backref";
/**
* Content to be displayed within footnote backlinks. The default is '↩';
@ -43,59 +39,51 @@ class MarkdownExtra extends \Michelf\Markdown {
* from displaying the arrow character as an emoji.
* Optionally use '^^' and '%%' to refer to the footnote number and
* reference number respectively. {@see parseFootnotePlaceholders()}
* @var string
*/
public $fn_backlink_html = '&#8617;&#xFE0E;';
public string $fn_backlink_html = '&#8617;&#xFE0E;';
/**
* Optional title and aria-label attributes for footnote backlinks for
* added accessibility (to ensure backlink uniqueness).
* Use '^^' and '%%' to refer to the footnote number and reference number
* respectively. {@see parseFootnotePlaceholders()}
* @var string
*/
public $fn_backlink_title = "";
public $fn_backlink_label = "";
public string $fn_backlink_title = "";
public string $fn_backlink_label = "";
/**
* Class name for table cell alignment (%% replaced left/center/right)
* For instance: 'go-%%' becomes 'go-left' or 'go-right' or 'go-center'
* If empty, the align attribute is used instead of a class name.
* @var string
*/
public $table_align_class_tmpl = '';
public string $table_align_class_tmpl = '';
/**
* Optional class prefix for fenced code block.
* @var string
*/
public $code_class_prefix = "";
public string $code_class_prefix = "";
/**
* Class attribute for code blocks goes on the `code` tag;
* setting this to true will put attributes on the `pre` tag instead.
* @var boolean
*/
public $code_attr_on_pre = false;
public bool $code_attr_on_pre = false;
/**
* Predefined abbreviations.
* @var array
*/
public $predef_abbr = array();
public array $predef_abbr = array();
/**
* Only convert atx-style headers if there's a space between the header and #
* @var boolean
*/
public $hashtag_protection = false;
public bool $hashtag_protection = false;
/**
* Determines whether footnotes should be appended to the end of the document.
* If true, footnote html can be retrieved from $this->footnotes_assembled.
* @var boolean
*/
public $omit_footnotes = false;
public bool $omit_footnotes = false;
/**
@ -107,9 +95,8 @@ class MarkdownExtra extends \Michelf\Markdown {
* `section` that will enclose the list of footnotes so they are
* reachable to accessibility tools the same way they would be with the
* default HTML output.
* @var null|string
*/
public $footnotes_assembled = null;
public ?string $footnotes_assembled = null;
/**
* Parser implementation
@ -149,27 +136,23 @@ class MarkdownExtra extends \Michelf\Markdown {
/**
* Extra variables used during extra transformations.
* @var array
*/
protected $footnotes = array();
protected $footnotes_ordered = array();
protected $footnotes_ref_count = array();
protected $footnotes_numbers = array();
protected $abbr_desciptions = array();
/** @var string */
protected $abbr_word_re = '';
protected array $footnotes = array();
protected array $footnotes_ordered = array();
protected array $footnotes_ref_count = array();
protected array $footnotes_numbers = array();
protected array $abbr_desciptions = array();
protected string $abbr_word_re = '';
/**
* Give the current footnote number.
* @var integer
*/
protected $footnote_counter = 1;
protected int $footnote_counter = 1;
/**
* Ref attribute for links
* @var array
*/
protected $ref_attr = array();
* Ref attribute for links
*/
protected array $ref_attr = array();
/**
* Setting up Extra-specific variables.
@ -215,18 +198,15 @@ class MarkdownExtra extends \Michelf\Markdown {
/**
* Extra attribute parser
*/
/**
* Expression to use to catch attributes (includes the braces)
* @var string
*/
protected $id_class_attr_catch_re = '\{((?>[ ]*[#.a-z][-_:a-zA-Z0-9=]+){1,})[ ]*\}';
protected string $id_class_attr_catch_re = '\{((?>[ ]*[#.a-z][-_:a-zA-Z0-9=]+){1,})[ ]*\}';
/**
* Expression to use when parsing in a context when no capture is desired
* @var string
*/
protected $id_class_attr_nocatch_re = '\{(?>[ ]*[#.a-z][-_:a-zA-Z0-9=]+){1,}[ ]*\}';
protected string $id_class_attr_nocatch_re = '\{(?>[ ]*[#.a-z][-_:a-zA-Z0-9=]+){1,}[ ]*\}';
/**
* Parse attributes caught by the $this->id_class_attr_catch_re expression
@ -340,37 +320,31 @@ class MarkdownExtra extends \Michelf\Markdown {
/**
* HTML block parser
*/
/**
* Tags that are always treated as block tags
* @var string
*/
protected $block_tags_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|form|fieldset|iframe|hr|legend|article|section|nav|aside|hgroup|header|footer|figcaption|figure|details|summary';
protected string $block_tags_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|form|fieldset|iframe|hr|legend|article|section|nav|aside|hgroup|header|footer|figcaption|figure|details|summary';
/**
* Tags treated as block tags only if the opening tag is alone on its line
* @var string
*/
protected $context_block_tags_re = 'script|noscript|style|ins|del|iframe|object|source|track|param|math|svg|canvas|audio|video';
protected string $context_block_tags_re = 'script|noscript|style|ins|del|iframe|object|source|track|param|math|svg|canvas|audio|video';
/**
* Tags where markdown="1" default to span mode:
* @var string
*/
protected $contain_span_tags_re = 'p|h[1-6]|li|dd|dt|td|th|legend|address';
protected string $contain_span_tags_re = 'p|h[1-6]|li|dd|dt|td|th|legend|address';
/**
* Tags which must not have their contents modified, no matter where
* they appear
* @var string
*/
protected $clean_tags_re = 'script|style|math|svg';
protected string $clean_tags_re = 'script|style|math|svg';
/**
* Tags that do not need to be closed.
* @var string
*/
protected $auto_close_tags_re = 'hr|img|param|source|track';
protected string $auto_close_tags_re = 'hr|img|param|source|track';
/**
* Hashify HTML Blocks and "clean tags".
@ -627,6 +601,7 @@ class MarkdownExtra extends \Michelf\Markdown {
else {
$parsed .= $tag;
}
// @phpstan-ignore-next-line
} while ($depth >= 0);
return array($parsed, $text);
@ -708,7 +683,7 @@ class MarkdownExtra extends \Michelf\Markdown {
// by the pattern.
$parts = preg_split($tag_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
if (count($parts) < 3) {
if ($parts === false || count($parts) < 3) {
// End of $text reached with unbalenced tag(s).
// In that case, we return original text unchanged and pass the
// first character as filtered to prevent an infinite loop in the
@ -1248,6 +1223,7 @@ class MarkdownExtra extends \Michelf\Markdown {
$head = $matches[1];
$underline = $matches[2];
$content = $matches[3];
$attr = [];
// Remove any tailing pipes for each line.
$head = preg_replace('/[|] *$/m', '', $head);
@ -1549,17 +1525,17 @@ class MarkdownExtra extends \Michelf\Markdown {
* work in the middle of a word.
* @var array
*/
protected $em_relist = array(
protected array $em_relist = array(
'' => '(?:(?<!\*)\*(?!\*)|(?<![a-zA-Z0-9_])_(?!_))(?![\.,:;]?\s)',
'*' => '(?<![\s*])\*(?!\*)',
'_' => '(?<![\s_])_(?![a-zA-Z0-9_])',
);
protected $strong_relist = array(
protected array $strong_relist = array(
'' => '(?:(?<!\*)\*\*(?!\*)|(?<![a-zA-Z0-9_])__(?!_))(?![\.,:;]?\s)',
'**' => '(?<![\s*])\*\*(?!\*)',
'__' => '(?<![\s_])__(?![a-zA-Z0-9_])',
);
protected $em_strong_relist = array(
protected array $em_strong_relist = array(
'' => '(?:(?<!\*)\*\*\*(?!\*)|(?<![a-zA-Z0-9_])___(?!_))(?![\.,:;]?\s)',
'***' => '(?<![\s*])\*\*\*(?!\*)',
'___' => '(?<![\s_])___(?![a-zA-Z0-9_])',

View file

@ -1,7 +1,7 @@
PHP Markdown
============
PHP Markdown Lib 1.9.1 - 23 Nov 2021
![ci.yml](https://github.com/michelf/php-markdown/actions/workflows/ci.yml/badge.svg)
by Michel Fortin
<https://michelf.ca/>
@ -34,15 +34,14 @@ program by John Gruber.
Requirement
-----------
This library package requires PHP 5.3 or later.
This library package requires PHP 7.4 or later.
Note: The older plugin/library hybrid package for PHP Markdown and
PHP Markdown Extra is no longer maintained but will work with PHP 4.0.5 and
later.
Before PHP 5.3.7, pcre.backtrack_limit defaults to 100 000, which is too small
in many situations. You might need to set it to higher values. Later PHP
releases defaults to 1 000 000, which is usually fine.
You might need to set pcre.backtrack_limit higher than 1 000 000
(the default), though the default is usually fine.
Usage

View file

@ -18,12 +18,37 @@
}
],
"require": {
"php": ">=5.3.0"
"php": ">=7.4"
},
"autoload": {
"psr-4": { "Michelf\\": "Michelf/" }
},
"require-dev": {
"phpunit/phpunit": ">=4.3 <5.8"
"friendsofphp/php-cs-fixer": "^3.0",
"phpunit/phpunit": "^9.5",
"phpstan/phpstan": ">=1.0",
"phpstan/phpstan-phpunit": ">=1.0"
},
"scripts": {
"tests": "vendor/bin/phpunit test/",
"phpstan": [
"vendor/bin/phpstan analyse Michelf/ --level=5",
"vendor/bin/phpstan analyse -c test/phpstan.neon test/ --level=5"
],
"codestyle": "vendor/bin/php-cs-fixer fix Michelf --dry-run --verbose --show-progress=none",
"codestyle-fix": "vendor/bin/php-cs-fixer fix Michelf"
},
"archive": {
"exclude": [
"/.github/",
"/test/",
"/.editorconfig",
"/.gitignore",
"/.scrutinizer.yml",
"/.travis.yml",
"/phpunit.xml.dist"
]
}
}

View file

@ -22,7 +22,6 @@ class MarkdownTestHelper
$dataValues = array();
/** @var SplFileInfo $inputFile */
foreach ($regexIterator as $inputFiles) {
foreach ($inputFiles as $inputMarkdownPath) {
$xhtml = true;
@ -163,6 +162,7 @@ class MarkdownTestHelper
foreach ($node_list as $node) {
switch ($node->nodeType) {
case XML_ELEMENT_NODE:
/** @var DOMElement $node */
static::normalizeElementContent($node, $whitespace_preserve);
static::normalizeElementAttributes($node);
@ -207,6 +207,7 @@ class MarkdownTestHelper
break;
case XML_TEXT_NODE:
/** @var DOMText $node */
if (!$whitespace_preserve) {
if (trim($node->data) === "") {
$node->data = $whitespace;
@ -222,8 +223,8 @@ class MarkdownTestHelper
($whitespace === "\n\n" || $whitespace === "\n")) {
if ($element->firstChild) {
if ($element->firstChild->nodeType == XML_TEXT_NODE) {
$element->firstChild->data =
preg_replace('{^\s+}', "\n", $element->firstChild->data);
$element->firstChild->data = // @phpstan-ignore-line
preg_replace('{^\s+}', "\n", $element->firstChild->data ?? '');
}
else {
$element->insertBefore(new DOMText("\n"), $element->firstChild);
@ -231,8 +232,8 @@ class MarkdownTestHelper
}
if ($element->lastChild) {
if ($element->lastChild->nodeType == XML_TEXT_NODE) {
$element->lastChild->data =
preg_replace('{\s+$}', "\n", $element->lastChild->data);
$element->lastChild->data = // @phpstan-ignore-line
preg_replace('{\s+$}', "\n", $element->lastChild->data ?? '');
}
else {
$element->insertBefore(new DOMText("\n"), null);

2
test/phpstan.neon Normal file
View file

@ -0,0 +1,2 @@
includes:
- ../vendor/phpstan/phpstan-phpunit/extension.neon