Documentation

RegexHelper
in package

Provides regular expressions and utilities for parsing Markdown

Table of Contents

PARTIAL_ATTRIBUTE  = '(?:' . '\s+' . self::PARTIAL_ATTRIBUTENAME . self::PARTIAL_ATTRIBUTEVALUESPEC . '?)'
PARTIAL_ATTRIBUTENAME  = '[a-zA-Z_:][a-zA-Z0-9:._-]*'
PARTIAL_ATTRIBUTEVALUE  = '(?:' . self::PARTIAL_UNQUOTEDVALUE . '|' . self::PARTIAL_SINGLEQUOTEDVALUE . '|' . self::PARTIAL_DOUBLEQUOTEDVALUE . ')'
PARTIAL_ATTRIBUTEVALUESPEC  = '(?:' . '\s*=' . '\s*' . self::PARTIAL_ATTRIBUTEVALUE . ')'
PARTIAL_BLOCKTAGNAME  = '(?:address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset|h1|head|header|hr|html|iframe|legend|li|link|main|menu|menuitem|nav|noframes|ol|optgroup|option|p|param|section|source|summary|table|tbody|td|tfoot|th|thead|title|tr|track|ul)'
PARTIAL_CDATA  = '<!\[CDATA\[[\s\S]*?]\]>'
PARTIAL_CLOSEBLOCKTAG  = '<\/' . self::PARTIAL_BLOCKTAGNAME . '\s*[>]'
PARTIAL_CLOSETAG  = '<\/' . self::PARTIAL_TAGNAME . '\s*[>]'
PARTIAL_DECLARATION  = '<![A-Z]+' . '\s+[^>]*>'
PARTIAL_DOUBLEQUOTEDVALUE  = '"[^"]*"'
PARTIAL_ENTITY  = '&(?:#x[a-f0-9]{1,6}|#[0-9]{1,7}|[a-z][a-z0-9]{1,31});'
PARTIAL_ESCAPABLE  = '[!"#$%&'()*+,.\/:;<=>?@[\\\]^_`{|}~-]'
PARTIAL_ESCAPED_CHAR  = '\\' . self::PARTIAL_ESCAPABLE
PARTIAL_HTMLBLOCKOPEN  = '<(?:' . self::PARTIAL_BLOCKTAGNAME . '(?:[\s\/>]|$)' . '|' . '\/' . self::PARTIAL_BLOCKTAGNAME . '(?:[\s>]|$)' . '|' . '[?!])'
PARTIAL_HTMLCOMMENT  = '<!---->|<!--(?:-?[^>-])(?:-?[^-])*-->'
PARTIAL_HTMLTAG  = '(?:' . self::PARTIAL_OPENTAG . '|' . self::PARTIAL_CLOSETAG . '|' . self::PARTIAL_HTMLCOMMENT . '|' . self::PARTIAL_PROCESSINGINSTRUCTION . '|' . self::PARTIAL_DECLARATION . '|' . self::PARTIAL_CDATA . ')'
PARTIAL_IN_DOUBLE_QUOTES  = '"(' . self::PARTIAL_ESCAPED_CHAR . '|[^"\x00])*"'
PARTIAL_IN_PARENS  = '\((' . self::PARTIAL_ESCAPED_CHAR . '|[^)\x00])*\)'
PARTIAL_IN_PARENS_NOSP  = '\((' . self::PARTIAL_REG_CHAR . '|' . self::PARTIAL_ESCAPED_CHAR . '|\\)*\)'
PARTIAL_IN_SINGLE_QUOTES  = ''(' . self::PARTIAL_ESCAPED_CHAR . '|[^'\x00])*''
PARTIAL_LINK_TITLE  = '^(?:"(' . self::PARTIAL_ESCAPED_CHAR . '|[^"\x00])*"' . '|' . ''(' . self::PARTIAL_ESCAPED_CHAR . '|[^'\x00])*'' . '|' . '\((' . self::PARTIAL_ESCAPED_CHAR . '|[^()\x00])*\))'
PARTIAL_OPENBLOCKTAG  = '<' . self::PARTIAL_BLOCKTAGNAME . self::PARTIAL_ATTRIBUTE . '*' . '\s*\/?>'
PARTIAL_OPENTAG  = '<' . self::PARTIAL_TAGNAME . self::PARTIAL_ATTRIBUTE . '*' . '\s*\/?>'
PARTIAL_PROCESSINGINSTRUCTION  = '[<][?].*?[?][>]'
PARTIAL_REG_CHAR  = '[^\\()\x00-\x20]'
PARTIAL_SINGLEQUOTEDVALUE  = ''[^']*''
PARTIAL_TAGNAME  = '[A-Za-z][A-Za-z0-9-]*'
PARTIAL_UNQUOTEDVALUE  = '[^"'=<>`\x00-\x20]+'
REGEX_LINK_DESTINATION_BRACES  = '/^(?:<(?:[^<>\n\\\x00]|\\.)*>)/'
REGEX_NON_SPACE  = '/[^ \t\f\v\r\n]/'
REGEX_PUNCTUATION  = '/^[\x{2000}-\x{206F}\x{2E00}-\x{2E7F}\p{Pc}\p{Pd}\p{Pe}\p{Pf}\p{Pi}\p{Po}\p{Ps}\\'!"#\$%&\(\)\*\+,\-\.\/:;<=>\?@\[\]\^_`\{\|\}~]/u'
REGEX_SAFE_DATA_PROTOCOL  = '/^data:image\/(?:png|gif|jpeg|webp)/i'
REGEX_THEMATIC_BREAK  = '/^(?:\*[ \t]*){3,}$|^(?:_[ \t]*){3,}$|^(?:-[ \t]*){3,}$/'
REGEX_UNICODE_WHITESPACE_CHAR  = '/^\pZ|\s/u'
REGEX_UNSAFE_PROTOCOL  = '/^javascript:|vbscript:|file:|data:/i'
REGEX_WHITESPACE  = '/[ \t\n\x0b\x0c\x0d]+/'
REGEX_WHITESPACE_CHAR  = '/^[ \t\n\x0b\x0c\x0d]/'
isEscapable()  : bool
isLinkPotentiallyUnsafe()  : bool
matchAll()  : array<string|int, string>|null
Functional wrapper around preg_match_all
matchAt()  : int|null
Attempt to match a regex in string s at offset offset
matchFirst()  : array<string|int, string>|null
Functional wrapper around preg_match_all which only returns the first set of matches
unescape()  : string
Replace backslash escapes with literal characters

Constants

PARTIAL_ATTRIBUTE

public mixed PARTIAL_ATTRIBUTE = '(?:' . '\s+' . self::PARTIAL_ATTRIBUTENAME . self::PARTIAL_ATTRIBUTEVALUESPEC . '?)'

PARTIAL_ATTRIBUTENAME

public mixed PARTIAL_ATTRIBUTENAME = '[a-zA-Z_:][a-zA-Z0-9:._-]*'

PARTIAL_ATTRIBUTEVALUE

public mixed PARTIAL_ATTRIBUTEVALUE = '(?:' . self::PARTIAL_UNQUOTEDVALUE . '|' . self::PARTIAL_SINGLEQUOTEDVALUE . '|' . self::PARTIAL_DOUBLEQUOTEDVALUE . ')'

PARTIAL_ATTRIBUTEVALUESPEC

public mixed PARTIAL_ATTRIBUTEVALUESPEC = '(?:' . '\s*=' . '\s*' . self::PARTIAL_ATTRIBUTEVALUE . ')'

PARTIAL_BLOCKTAGNAME

public mixed PARTIAL_BLOCKTAGNAME = '(?:address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset|h1|head|header|hr|html|iframe|legend|li|link|main|menu|menuitem|nav|noframes|ol|optgroup|option|p|param|section|source|summary|table|tbody|td|tfoot|th|thead|title|tr|track|ul)'

PARTIAL_CDATA

public mixed PARTIAL_CDATA = '<!\[CDATA\[[\s\S]*?]\]>'

PARTIAL_CLOSEBLOCKTAG

public mixed PARTIAL_CLOSEBLOCKTAG = '<\/' . self::PARTIAL_BLOCKTAGNAME . '\s*[>]'

PARTIAL_CLOSETAG

public mixed PARTIAL_CLOSETAG = '<\/' . self::PARTIAL_TAGNAME . '\s*[>]'

PARTIAL_DECLARATION

public mixed PARTIAL_DECLARATION = '<![A-Z]+' . '\s+[^>]*>'

PARTIAL_DOUBLEQUOTEDVALUE

public mixed PARTIAL_DOUBLEQUOTEDVALUE = '"[^"]*"'

PARTIAL_ENTITY

public mixed PARTIAL_ENTITY = '&(?:#x[a-f0-9]{1,6}|#[0-9]{1,7}|[a-z][a-z0-9]{1,31});'

PARTIAL_ESCAPABLE

public mixed PARTIAL_ESCAPABLE = '[!"#$%&'()*+,.\/:;<=>?@[\\\]^_`{|}~-]'

PARTIAL_ESCAPED_CHAR

public mixed PARTIAL_ESCAPED_CHAR = '\\' . self::PARTIAL_ESCAPABLE

PARTIAL_HTMLBLOCKOPEN

public mixed PARTIAL_HTMLBLOCKOPEN = '<(?:' . self::PARTIAL_BLOCKTAGNAME . '(?:[\s\/>]|$)' . '|' . '\/' . self::PARTIAL_BLOCKTAGNAME . '(?:[\s>]|$)' . '|' . '[?!])'

PARTIAL_HTMLCOMMENT

public mixed PARTIAL_HTMLCOMMENT = '<!---->|<!--(?:-?[^>-])(?:-?[^-])*-->'

PARTIAL_HTMLTAG

public mixed PARTIAL_HTMLTAG = '(?:' . self::PARTIAL_OPENTAG . '|' . self::PARTIAL_CLOSETAG . '|' . self::PARTIAL_HTMLCOMMENT . '|' . self::PARTIAL_PROCESSINGINSTRUCTION . '|' . self::PARTIAL_DECLARATION . '|' . self::PARTIAL_CDATA . ')'

PARTIAL_IN_DOUBLE_QUOTES

public mixed PARTIAL_IN_DOUBLE_QUOTES = '"(' . self::PARTIAL_ESCAPED_CHAR . '|[^"\x00])*"'

PARTIAL_IN_PARENS

public mixed PARTIAL_IN_PARENS = '\((' . self::PARTIAL_ESCAPED_CHAR . '|[^)\x00])*\)'

PARTIAL_IN_PARENS_NOSP

public mixed PARTIAL_IN_PARENS_NOSP = '\((' . self::PARTIAL_REG_CHAR . '|' . self::PARTIAL_ESCAPED_CHAR . '|\\)*\)'

PARTIAL_IN_SINGLE_QUOTES

public mixed PARTIAL_IN_SINGLE_QUOTES = ''(' . self::PARTIAL_ESCAPED_CHAR . '|[^'\x00])*''
public mixed PARTIAL_LINK_TITLE = '^(?:"(' . self::PARTIAL_ESCAPED_CHAR . '|[^"\x00])*"' . '|' . ''(' . self::PARTIAL_ESCAPED_CHAR . '|[^'\x00])*'' . '|' . '\((' . self::PARTIAL_ESCAPED_CHAR . '|[^()\x00])*\))'

PARTIAL_OPENBLOCKTAG

public mixed PARTIAL_OPENBLOCKTAG = '<' . self::PARTIAL_BLOCKTAGNAME . self::PARTIAL_ATTRIBUTE . '*' . '\s*\/?>'

PARTIAL_OPENTAG

public mixed PARTIAL_OPENTAG = '<' . self::PARTIAL_TAGNAME . self::PARTIAL_ATTRIBUTE . '*' . '\s*\/?>'

PARTIAL_PROCESSINGINSTRUCTION

public mixed PARTIAL_PROCESSINGINSTRUCTION = '[<][?].*?[?][>]'

PARTIAL_REG_CHAR

public mixed PARTIAL_REG_CHAR = '[^\\()\x00-\x20]'

PARTIAL_SINGLEQUOTEDVALUE

public mixed PARTIAL_SINGLEQUOTEDVALUE = ''[^']*''

PARTIAL_TAGNAME

public mixed PARTIAL_TAGNAME = '[A-Za-z][A-Za-z0-9-]*'

PARTIAL_UNQUOTEDVALUE

public mixed PARTIAL_UNQUOTEDVALUE = '[^"'=<>`\x00-\x20]+'
public mixed REGEX_LINK_DESTINATION_BRACES = '/^(?:<(?:[^<>\n\\\x00]|\\.)*>)/'

REGEX_NON_SPACE

public mixed REGEX_NON_SPACE = '/[^ \t\f\v\r\n]/'

REGEX_PUNCTUATION

public mixed REGEX_PUNCTUATION = '/^[\x{2000}-\x{206F}\x{2E00}-\x{2E7F}\p{Pc}\p{Pd}\p{Pe}\p{Pf}\p{Pi}\p{Po}\p{Ps}\\'!"#\$%&\(\)\*\+,\-\.\/:;<=>\?@\[\]\^_`\{\|\}~]/u'

REGEX_SAFE_DATA_PROTOCOL

public mixed REGEX_SAFE_DATA_PROTOCOL = '/^data:image\/(?:png|gif|jpeg|webp)/i'

REGEX_THEMATIC_BREAK

public mixed REGEX_THEMATIC_BREAK = '/^(?:\*[ \t]*){3,}$|^(?:_[ \t]*){3,}$|^(?:-[ \t]*){3,}$/'

REGEX_UNICODE_WHITESPACE_CHAR

public mixed REGEX_UNICODE_WHITESPACE_CHAR = '/^\pZ|\s/u'

REGEX_UNSAFE_PROTOCOL

public mixed REGEX_UNSAFE_PROTOCOL = '/^javascript:|vbscript:|file:|data:/i'

REGEX_WHITESPACE

public mixed REGEX_WHITESPACE = '/[ \t\n\x0b\x0c\x0d]+/'

REGEX_WHITESPACE_CHAR

public mixed REGEX_WHITESPACE_CHAR = '/^[ \t\n\x0b\x0c\x0d]/'

Methods

isEscapable()

public static isEscapable(string $character) : bool
Parameters
$character : string
Return values
bool

isLinkPotentiallyUnsafe()

public static isLinkPotentiallyUnsafe(string $url) : bool
Parameters
$url : string
Return values
bool

matchAll()

Functional wrapper around preg_match_all

public static matchAll(string $pattern, string $subject, int $offset) : array<string|int, string>|null
Parameters
$pattern : string
$subject : string
$offset : int
Tags
deprecated

in 1.6; use matchFirst() instead

Return values
array<string|int, string>|null

matchAt()

Attempt to match a regex in string s at offset offset

public static matchAt(string $regex, string $string, int $offset) : int|null
Parameters
$regex : string
$string : string
$offset : int
Return values
int|null

Index of match, or null

matchFirst()

Functional wrapper around preg_match_all which only returns the first set of matches

public static matchFirst(string $pattern, string $subject, int $offset) : array<string|int, string>|null
Parameters
$pattern : string
$subject : string
$offset : int
Tags
psalm-pure
Return values
array<string|int, string>|null

unescape()

Replace backslash escapes with literal characters

public static unescape(string $string) : string
Parameters
$string : string
Return values
string

Search results