File Coverage

blib/lib/Regexp/Common/Markdown.pm

Criterion	Covered	Total	%
statement	49	49	100.0
branch			n/a
condition			n/a
subroutine	9	9	100.0
pod			n/a
total	58	58	100.0

##----------------------------------------------------------------------------
## Markdown Common Regular Expressions - ~/lib/Regexp/Common/Markdown.pm
## Version v0.1.8
## Copyright(c) 2025 DEGUEST Pte. Ltd.
## Author: Jacques Deguest
## Created 2020/08/01
## Modified 2025/10/24
## All rights reserved
##
## This program is free software; you can redistribute  it  and/or  modify  it
## under the same terms as Perl itself.
##----------------------------------------------------------------------------
package Regexp::Common::Markdown;
BEGIN
{
    use strict;
    use warnings;
    use warnings::register;
    use Regexp::Common qw( pattern );
    use Regexp::Common qw( URI );
    use Regexp::Common qw( Email::Address );
    use Regexp::Common::URI::RFC2396 qw /$host $port $path_segments $query/;
    ## We use URI::tel instead of Regexp::Common::tel because its regular expression is antiquated
    ## URI::tel uses the latest rfc3966
    use URI::tel;
    # no warnings qw( experimental::vlb );
    our $VERSION = 'v0.1.8';

    our $SPACE_RE = qr/[[:blank:]\h]/;
    ## Including vertical space like new lines
    our $SPACE_EXTENDED_RE = qr/[[:blank:]\h\v]/;
    # Guards to keep other patterns from firing inside code
    our $MD_SKIP_FENCED = qr/
        (?:
            (?<=\n) | \A                      # start of line or start of string
        )
        [ ]{0,3}                              # up to 3 leading spaces
        (?`{3,}|~{3,})[^\n]*\n         # opening fence + optional info string
        (?:
            (?!^[ ]{0,3}\k[ \t]*\r?(?:\n|\z))  # not the closing fence line
            [^\n]*+(?:\n|\z)                  # consume exactly one full line
        )*
        [ ]{0,3}\k[ \t]*\r?(?:\n|\z)   # closing fence
        (*SKIP)(*F)
    /xms;

    our $MD_SKIP_INDENTED = qr/
        (?:(?<=\n)|\A)
        (?:
            (?:[ ]{4}|\t).*(?:\n|\z)
        )+
        (*SKIP)(*F)
    /xms;

    # `code` and `` code with ` inside ``
    our $MD_SKIP_INLINE_CODE = qr/
        (?
        (`+)(?!`)
        (?: .*? )
        \1(?!`)
        (*SKIP)(*F)
    /xms;

    our $ATTRIBUTE_RE = qr/
        [\w\-]+
        $SPACE_EXTENDED_RE*
        =
        $SPACE_EXTENDED_RE*
        (?:
            \"[^\"]+\"  # attribute="value"
            |
            \'[^\']+\'  # attribute='value'
            |
            \S+         # attribute=value
        )
        $SPACE_EXTENDED_RE*
    /x;
    our $LIST_TYPE_ORDERED = qr/(?\d+[\.])/;

    our $LIST_TYPE_UNORDERED_MINUS = qr/
        (?
            [\-]
            (?!
                (?:
                    [ ]?[\-][ ]?
                ){2,}
            )
        )
    /x;

    our $LIST_TYPE_UNORDERED_PLUS = qr/(?[\+])/;

    our $LIST_TYPE_UNORDERED_STAR = qr/
        (?
            [\*]
            (?!                     # Make sure not to catch horizontal lines marked with stars
                (?:
                    [ ]?[\*][ ]?
                ){2,}
            )
        )
    /x;

    our $LIST_TYPE_UNORDERED = qr/
        $LIST_TYPE_UNORDERED_STAR
        |
        $LIST_TYPE_UNORDERED_MINUS
        |
        $LIST_TYPE_UNORDERED_PLUS
    /x;

    # Taken from Markdown original author, John Gruber's original regular expression
    # See  to see it in action
    our $LIST_ALL = qr/
        (?                                                            # whole list
            (?                                                     # list prefix and type
                [\s]{0,3}
                (?                                               # Any of posible list prefix, but that aviod atching also horizontal rules
                    (?:
                        (?(?&list_unordered_star))
                        |
                        (?(?&list_unordered_minus))
                        |
                        (?(?&list_unordered_plus))
                        |
                        (?(?&list_ordered))
                    )
                )
                [ \t]+
            )
            (?(?s:.+?))                                           # list content
            (?
                \z
                |
                \n{2,}
                (?=\S)
                (?!                                                             # Negative lookahead for another list item marker
                    [ \t]*
                    (?
                        (?:
                        (?(?&list_unordered_star))
                        |
                        (?(?&list_unordered_minus))
                        |
                        (?(?&list_unordered_plus))
                        |
                        (?(?&list_ordered))
                        )
                    )
                    [ \t]+
                )
            )
        )
        (?(DEFINE)                                      # Definition block for recursive pattern matching
$LIST_TYPE_UNORDERED_STAR
$LIST_TYPE_UNORDERED_MINUS
$LIST_TYPE_UNORDERED_PLUS
$LIST_TYPE_ORDERED
        )
    /mx;

    # NOTE: global variables to build URI regular expressions compatible with IDN (rfc3986)
    our $HTTP_RFC2396_HOST = qr/$host/;
    # RFC 3986 / IDN host helpers
    # Accept "." and the IDNA dot equivalents
    our $IDN_DOT = qr/[.\x{3002}\x{FF0E}\x{FF61}]/;
    # ACE punycode prefix
    our $ACE     = qr/xn--/i;

    # RFC 3986: IPv6 literal inside [ ... ]
    # (very permissive; we only need the bracketed form to avoid false positives)
    our $IP_LITERAL = qr/\[(?:[0-9A-Fa-f:.]+)\]/;

    # IDN label (≤63 chars) with ACE or Unicode 3rd–4th hyphen rule
    our $IDN_U_LABEL = qr/
        (?:                                     # punycode label… (xn--)
            $ACE [\p{L}\p{N}\p{M}\p{Pc}-]{1,59}
            |
            (?! [\p{L}\p{N}]{2}-- )             # forbid "--" at pos 3–4 unless ACE
            [\p{L}\p{N}]                        # first
            [\p{L}\p{N}\p{M}\p{Pc}-]{0,61}      # middle
            (?
        )
    /ux;

    # IDN hostname: one or more labels separated by IDNA dots (atomic to reduce backtracking)
    our $IDN_HOST = qr/(?>$IDN_U_LABEL(?:$IDN_DOT$IDN_U_LABEL)*)/ux;
    # our $IDN_HOST = qr/(?>$IDN_U_LABEL(?:$IDN_DOT$IDN_U_LABEL)* $IDN_DOT?)/ux;

    # Unicode-friendly “tail” for path/query in inline links (non-<…> case).
    # RFC 3986 pchar allows pct-enc; for Markdown it is usually safer to “stop at obvious enders”.
    our $UNICODE_PATHQ = qr{ [^<>"'\s\)]* }ux;

    # RFC3986/IDN superset host: ASCII host-or-IPv4 (previous one based on RFC2396), or IDN host, or IPv6 literal
    my $HTTP_RFC3986_HOST = qr/
        (?:
            # (1) previous ASCII host-or-IPv4 branch based on RFC2396:
            $HTTP_RFC2396_HOST
            |
            # (2) New: Unicode IDN hostname
            $IDN_HOST
            |
            # (3) New: IPv6 literal in brackets
            $IP_LITERAL
        )
    /x;

    # Full HTTP(S) URI using RFC2396 path/query (strict ASCII), suitable for angle-bracket autolinks.
    our $HTTP_RFC3986_URI = qr{
        (?:
            (?:http|https)://
            $HTTP_RFC3986_HOST
            (?:: $port )?
            (?: /
                (?:
                    $path_segments
                    (?: \? $query )?
                )
            )?
        )
    }x;

    our $HTTP_R3986_URI_INLINE = qr{
        (?:
            (?:http|https)://
            $HTTP_RFC3986_HOST
            (?:: $port )?
            (?: / $UNICODE_PATHQ )?
            (?: \? $UNICODE_PATHQ )?
        )
    }x;

    our $REGEXP =
    {
    # NOTE: Bold
    # https://regex101.com/r/Jp2Kos/3
    bold => qr/
        (?
        (?
            (?\*{2}|\_{2})   # Emphasis type: * or _
            (?=                         # followed by non-space
                (?:
                    (?:[_*`\$\\])       # avoid punctuation except those
                    |
                    (?![[:punct:]])
                )
            \S)
            (?.+?[*_]*)      # enclosed text
            (?<=\S)                     # making sure preceding stuff was a non-space
            \g{bold_type}               # Balanced closing tag
        )
    /x,

    # NOTE: blockquote
    # Code borrowed from original Markdown author: John Gruber
    # https://regex101.com/r/TdKq0K/1
    bquote => qr/
        (?                  # Wrap whole match in $1
            (?>
                ^[ \t]*>[ \t]?          # '>' at the start of a line
                .+\n                    # rest of the first line
                (?.+\n)*  # subsequent consecutive lines
                \n*                     # blanks
            )+
        )
    /xm,

    # NOTE: code block
    # ```
    # Some code
    # ```
    # https://regex101.com/r/M6W99K/7
    # 2025-10-21: Updated
    # - Allows optional info string after the opening fence (ignored in base mode)
    # - Closes with the same fence run length & char
    # - Works with up to 3 leading spaces per CommonMark
    code_block => qr/
        (?:(?<=\n)|(?<=\A))            # Necessarily at the begining of a new line or start of string
        (?
            [ ]{0,3}                   # Possibly up to 3 leading spaces
            (?             # CAPTURE ONLY the fence run
                \`{3,}
            )
            [ \t]* [^\n]*              # optional info string (ignored in base)
            \n
            (?.*?)       # enclosed content
            \n
            [ ]{0,3}                   # up to 3 leading spaces on the closer line
            (?
            \g{code_start}             # close with the SAME fence run
            (?!`)                      # not followed by a backtick
            [ \t]*                     # optional trailing spaces
            \n                         # final newline (keep strict like your original)
        )
    /xms,

    # NOTE: code line
    # Marked by left hand indentation
    # https://regex101.com/r/toEboU/3
    code_line => qr/
        (?:(?<=^\n)|(?<=\A))            # Starting at beginning of string or with 2 new lines
        (?
            (?:
                (?         # Lines must start with a tab or a tab-width of spaces
                    [ ]{4}
                    |
                    \t
                )
                (?.*\n+)  # with some content, possibly nothing followed by a new line
            )+
        )
        (?
            (?=^[ ]{0,4}\S)             # Lookahead for non-space at line-start
            |
            \Z                          # or end of doc
        )
    /xm,

    # NOTE: code span
    # \x{0060} is ` in unicode; see perl -le 'printf "\\x%x", ord( "`" )'
    # Updated on 2025-10-19 to change the 'code_start', and 'code_content'
    # from (?.+?) to (?:[^`]|`(?!\g{code_start}))*?
    # Updated on 2025-10-21 to guard from capturing fenced blocks and indented codes
    code_span => qr{
        (?: $MD_SKIP_FENCED | $MD_SKIP_INDENTED )
        |
        (?
        (?
            (?!^[ ]{0,3}`{3,}[^\n]*\n)      # not a fence opener (needs /m)
            (?`+)               # opening, capture N backticks
            (?                # allow single ` inside when using more ticks
                (?:[^`]|`(?!\g{code_start}))*?
            )
            (?
            \g{code_start}                  # balanced closing ticks
        )
    }xms,

    # NOTE: emphasis
    # https://regex101.com/r/eDb6RN/5
    em => qr/
        (?
        (?
            (?\*|\_)       # Emphasis type: * or _
            (?=\S)                  # followed by non-space
            (?.+?)         # enclosed text
            (?<=\S)                 # making sure preceding stuff was a non-space
            (?
            \g{em_type}             # Balanced closing tag
        )
   /x,

    # NOTE: headers
    # Headers: #, ##, ###, ####, #####, ###### become h1..6
    # atx-style headers:
    #   # Header 1
    #   ## Header 2
    #   ## Header 2 with closing hashes ##
    #   ...
    #   ###### Header 6
    # https://regex101.com/r/9uQwBk/6
    # 2025-10-19: Added safeguards $MD_SKIP_FENCED and $MD_SKIP_INDENTED
    # other change avoids “#######” lines with no content and the occasional 7+ “#” oddity.
    header => qr/
        (?: $MD_SKIP_FENCED | $MD_SKIP_INDENTED )
        |
        (?
            ^
            (?
            (?\#{1,6})        # 1..6 # only
            [ \t]*                          # Possibly followed by some spaces or tabs
            (?![ \t]*$)                     # must have some content
            (?.*?)          # Possibly followed by some spaces or tabs or some dashes (don't need to match the opening ones)
            [ \t\#]*                        # optional closing hashes or spaces
            \n
        )
    /mx,

    # NOTE: setext-style headers
    # Setext-style headers:
    #     Header 1
    #     ========
    #
    #     Header 2
    #     --------
    #
    # This is to be on a single line of its own
    # https://regex101.com/r/sQLEqz/4
    # 2025-10-19: Added safeguards $MD_SKIP_FENCED and $MD_SKIP_INDENTED
    header_line => qr/
        (?: $MD_SKIP_FENCED | $MD_SKIP_INDENTED ) |
        (?
            ^
            (?.+?)          # Header content
            [ \t]*                          # Possibly followed by spaces or tabs
            \n                              # With then a new line
            (?
            (?={3,}|-{3,})     # underline, 3+ to avoid list dashes noise
            [ \t]*                          # Possibly followed by spaces or tabs
            \n                              # Terminated by a new line
        )
    /mx,

    # NOTE: html
    # https://regex101.com/r/SH8ki3/4
    # 2025-10-18: Added safeguards to exclude html embedded within code blocks
    # 2025-10-24: Added the fence guard $MD_SKIP_FENCED
    html => qr/
        #---------------------------------------------------------
        # 0) Indented-code guard
        #---------------------------------------------------------
        $MD_SKIP_INDENTED
        |
        #---------------------------------------------------------
        # 1) Ignore fenced code blocks (```lang … ``` or ~~~ … ~~~)
        #    We match them first, then (*SKIP)(*F) so the engine
        #    jumps past the whole block and resumes searching after it.
        #---------------------------------------------------------
        $MD_SKIP_FENCED
        |
        #---------------------------------------------------------
        # 2) The actual HTML matcher
        #---------------------------------------------------------
        (?:(?<=\n)|(?<=\A))                # Necessarily at the begining of a new line or start of string
        (?[ ]{0,3})
        (?
            (?:
                (?
                    <(?\S+)
                        [^\>]*
                    >\n*
                )
                (?.+?)
                \n*
                (?
                    (?()                     # If leading spaces were found
                        (?:
                            (?<=\n)\g{leading_space}        # Either there is a symmetry in leading space for open and closing tag
                            |
                            (?:(?<=\S)[[:blank:]\h]*)       # or the closing tag is on the same line with preceding data
                        )
                        |
                        (?=<[[:blank:]\h\v]*\/[[:blank:]\h\v]*\g{tag_name}[[:blank:]\h\v]*>)                # No leading space, so we don't expect anything before the closing tag other than what has already been caught in the 'content'
                    )
                    <[[:blank:]\h\v]*\/[[:blank:]\h\v]*\g{tag_name}[[:blank:]\h\v]*>
                )
                [[:blank:]\h]*\n
            )
            |
            (?:

            )
            |
            (?:
                <
                    [[:blank:]\h\v]*
                    (?[a-zA-Z0-9][\w\-]+)
                    (?(?&tag_attr))*
                    [[:blank:]\h\v]*
                    \/?
                    [[:blank:]\h\v]*
                >
            )
        )
        (?(DEFINE)
            (?
                (?:
                    [[:blank:]\h]*
                    [\w\-]+
                    [[:blank:]\h]*
                    =
                    [^\"\'[:blank:]\h]+
                    [[:blank:]\h]*
                )
                |
                (?:
                    [[:blank:]\h]*
                    [\w\-]+
                    [[:blank:]\h]*
                    =
                    [[:blank:]\h]*
                    (?["'])
                    (.*?)
                    \g{quote}
                    [[:blank:]\h]*
                )
            )
        )
    /xsm,

    # NOTE: image
    # Basically same as link, except there is an exclamation mark (!) just before:
    # Ex: ![alt text](url "optional title")
    # https://regex101.com/r/z0yH2F/10
    # 2025-10-19: Added safeguard $MD_SKIP_INLINE_CODE
    img => qr/
        $MD_SKIP_INLINE_CODE
        |
        (?
        (?
            \!\[(?.+?)\]                           # image alternative text, i.e. the text used when the image does not
            (?:
                (?:
                    [ ]?                                    # possibly followed by some spaces
                    (?:\n[ ]*)?                             # and a new line with some space
                    \[(?.*?)\]                      # with the link id in brackets, but may be empty
                )
                |
                (?:
                    (?:
                        \(
                            [ \t]*
                            <(?                    # link url within <>; or
                                .+?
                            )>
                            [ \t]*                              # possibly followed by some spaces or tabs
                            (?:
                                (?['"])    # Title is surrounded ether by double or single quotes
                                (?.*?)               # actual title, but could be empty as in ""
                                \g{img_title_container}         # make the sure enclosing mark balance
                            )?
                            [ \t]*
                        \)
                    )
                    |
                    (?:
                        \(
                            [ \t]*
                            (?                    # link url within <>; or
                                (?:((?!["']).)*+|.*)
                            )
                            [ \t]*
                            (?:
                                (?['"])    # Title is surrounded ether by double or single quotes
                                (?.*?)               # actual title, but could be empty as in ""
                                \g{img_title_container}         # make the sure enclosing mark balance
                            )?
                            [ \t]*
                        \)
                    )
                )
            )
        )
    /xm,

#     ^[ ]{0,2}([ ]?\*[ ]?){3,}[ \t]*$
    # NOTE: line
    # Horizontal line
    # https://daringfireball.net/projects/markdown/syntax#hr
    # https://regex101.com/r/Vlew4X/2
    # 20215-10-19: group the repeated unit atomically.
    line => qr/
        ^                               # At start of line
        $SPACE_RE{0,2}                  # with up to 3 spaces before
        (?
        (?
            (?:
                $SPACE_RE?
                (?\*|\-|\_)  # asterisk, hyphen or underscore
                $SPACE_RE?              # possibly followed by spaces
            ){3,}                       # 3 or more occurences
        )
        [ \t]*
        $                               # end of line or end of string
    /mx,

    # NOTE: line break
    # https://regex101.com/r/6VG46H/1
    line_break => qr/
        (?
            [ ]{2,}\n
        )
    /mx,

    # NOTE: Link
    # https://daringfireball.net/projects/markdown/syntax#link
    # https://regex101.com/r/sGsOIv/10
    # Links' id can be multiline, so we need the /s modifier
    # 2025-10-19 Added safeguard $MD_SKIP_INLINE_CODE
    link => qr/
        $MD_SKIP_INLINE_CODE
        |
        (?                                        # Check it was not escaped with a \
            (?:(?:\\|\!)\[(*SKIP)(*FAIL)|\[)                # Cannot be preceded by an anti-slash nor an exclamation mark (image)
            (?
                (?!\^)                                      # Make sure, this is not confused with a footnote
                (?>\\[\[\]]|[^\[\]])*+                      # Link text
            )
            (?
            \]
            (?:
                (?:
                    [ ]?                                    # possibly followed by some spaces
                    (?:\n[ ]*)?                             # and a new line with some space
                    (?
                        (?!\^)                              # Make sure, this is not confused with a footnote
                        (?.*?)
                    (?
                )
                |
                (?:
                    (?
                        [ \t]*
                        (?:
                            <(?.*?)>              # link url within <>; or
                            |
                            (?                    # link url without <>
                                $HTTP_R3986_URI_INLINE
                            )
                            |
                            (?.*?)
                        )
                        [ \t]*                              # possibly followed by some spaces or tabs
                        (?:
                            (?['"])   # Title is surrounded ether by double or single quotes
                            (?.*?)              # actual title, but could be empty as in ""
                            \g{link_title_container}        # make sure the enclosing mark balance
                        )?
                        [ \t]*
                    (?
                    (?![[:blank:]\h]+["'][^"']+["'])
                )
            )
        )
    /xms,

    # NOTE: link auto
    # https://regex101.com/r/bAUu1E/4/
    # 2025-10-19: Added safeguard $MD_SKIP_INLINE_CODE
    #             Added labels 'link_idn_http', 'link_idn_https', 'link_v6_http', and 'link_v6_https'
    link_auto => qr{
        $MD_SKIP_INLINE_CODE
        |
        (?
        (?
            <
            (?
                (?$RE{URI}{HTTP})                        # http
                |
                (?$RE{URI}{HTTP}{-scheme => 'https'})   # https
                |
                (?$RE{URI}{FTP})                          # ftp
                |
                (?$URI::tel::TEL_URI)                     # tel
                |
                (?$RE{URI}{file})                        # file
                |
                (?$RE{URI}{news})                        # news
                |
                (?(?:mailto\:)?$RE{Email}{Address})    # email address: mailto:[e-mail] or simply [e-mail]
                |
                (?  http://  $IDN_HOST  (?::(?:$port))?(?:/(?:(?:$path_segments)(?:[?](?:$query))?))? )  # IDN http hosts
                |
                (? https:// $IDN_HOST  (?::(?:$port))?(?:/(?:(?:$path_segments)(?:[?](?:$query))?))? )  # IDN https hosts
                |
                (?   http://  $IP_LITERAL (?::(?:$port))?(?:/(?:(?:$path_segments)(?:[?](?:$query))?))? ) # IPv6 http hosts
                |
                (?  https:// $IP_LITERAL (?::(?:$port))?(?:/(?:(?:$path_segments)(?:[?](?:$query))?))? ) # IPv6 https hosts
            )
            >
        )
    }x,

    # NOTE: link definition
    # Definition
    # https://daringfireball.net/projects/markdown/syntax#link
    # https://regex101.com/r/edg2F7/3
    link_def => qr/
        ^[ ]{0,3}                                       # Leading space up to 3
        (?
            (?
                (?!\^)                                  # Make sure, this is not confused with a footnote
                (?.+?)
            (?
            [ \t]*                                      # Possibly with some space before colon
            \:
            [ \t]*\n?[ \t]*                             # Possibly with some space after the colon, possibly with a new line in between?
            (?:
                <(?[^\>]+)>                   # link within <>
                |
                (?\S+)                        # or link without <>
            )
            (?:
                (?:
                    [ \t]+                              # Either some space or tabs
                    |
                    [ \t]*\n[ \t]*                      # or a new line surrounded by 0 or more spaces or tabs
                )
                (?:
                    (?:
                        (?['"])   # Title is surrounded ether by double or single quotes
                        (?.+?)
                        \g{link_title_container}        # make the sure enclosing mark balance
                    )
                    |                                   # or
                    \((?[^\)]+)\)           # by parenthesis
                )
            )?
            [ \t]*                      # Possibly ending with some trailing spaces or tab
        )
        (?:\n+|\Z)                      # terminated by a new line or end of file
    /xm,

    # NOTE: link reference
    # Link with reference to link definition id
    # https://daringfireball.net/projects/markdown/syntax#link
    # https://regex101.com/r/QmyfnH/1/
    # The /s switch is required for link name spawning multiple lines: [Some\nlink][]
    # 2025-10-19: Added safeguard $MD_SKIP_INLINE_CODE
    link_ref => qr/
        $MD_SKIP_INLINE_CODE
        |
        (?
            (?.+?)(?
            [ ]?                                # possibly followed by some spaces
            (?:\n[ ]*)?                         # and a new line with some space
            (?.*?)(?
        )
    /xms,

    # NOTE: list type ordered
    # regular expression for list, ordered or unordered
    list_type_ordered => $LIST_TYPE_ORDERED,

    # NOTE: list type unordered
    list_type_unordered => $LIST_TYPE_UNORDERED,

    # NOTE: list all
    # Taken from Markdown original author, John Gruber's original regular expression
    list => $LIST_ALL,

    # NOTE: list first level
    # https://regex101.com/r/RfhRVg/5
    list_first_level => qr/
        (?:(?<=^\n)|(?<=\A))
        $LIST_ALL
    /mx,

    # NOTE: list nth level
    list_nth_level => qr/
        ^
        $LIST_ALL
    /mx,

    # NOTE: list item
    # Minor deviation from John Gruber's original regular expression
    # Changed [ \t]+ to [ \t]* and .+? to .*? so that it catches empty list item, like:
    # *
    # * Something
    # https://regex101.com/r/bulBCP/1/
    list_item => qr/
        (?
            (?\n)?                                                        # leading line
            (?^[ \t]*)                                                   # leading whitespace
            (?                                                           # list marker
                (?:
                    (?:
                        (?(?&list_unordered_star))
                        |
                        (?(?&list_unordered_minus))
                        |
                        (?(?&list_unordered_plus))
                    )
                    |
                    (?(?&list_ordered))
                )
            )
            [ \t]*
            (?(?s:.*?)                                                      # list item text
            (\n{1,2}))
            (?= \n*
                (
                    \z
                    |
                    \g{li_lead_space}
                    (?
                        (?:
                            (?:
                                (?(?&list_unordered_star))
                                |
                                (?(?&list_unordered_minus))
                                |
                                (?(?&list_unordered_plus))
                            )
                            |
                            (?(?&list_ordered))
                        )
                    )
                    [ \t]*
                )
            )
        )
        (?(DEFINE)                                      # Definition block for recursive pattern matching
$LIST_TYPE_UNORDERED_STAR
$LIST_TYPE_UNORDERED_MINUS
$LIST_TYPE_UNORDERED_PLUS
$LIST_TYPE_ORDERED
        )
    /xm,

    # NOTE: paragraph
    # https://regexr.com/5929n
    # https://regex101.com/r/0B3gR4/5
    # 2025-10-19: updated to add safeguard, and improved 'para_content' to avoid swallowing definitions/footnotes/HTML starts.
    paragraph => qr/
        (?: $MD_SKIP_FENCED | $MD_SKIP_INDENTED )
        |
        (?:(?<=^\n)|(?<=\A))                        # Needs 1 or more new lines or start of string
        (?
            (?[ ]{0,3})                # Possibly some leading spaces, but less than a tab worth
            (?
                (?:
                    (?!                             # some line content not starting with those exceptions
                        [[:blank:]\h]{0,3}
                        (?:
                            \*{1}[ \t]+                 # a list
                            |
                            (?:\*(?:[ ]?\*){2,})        # a horizontal line
                            |
                            (?:\-*(?:[ ]?\-){2,})       # a horizontal line
                            |
                            (?:\_*(?:[ ]?\_){2,})       # a horizontal line
                            |
                            [>+-=\#]                    # bq, heading, setext line, etc.
                            |
                            \d+\.                       # ordered list
                            |
                            \`{3,}                      # code block (fenced)
                            |
                            \~{3,}                      # code block extended
                            |
                            \[ [^\]\n]+ \] [ \t]*:      # link def [id]:
                            |
                            \[\^ [^\]\n]+ \] [ \t]*:    # footnote def [^id]:
                            |
                            <[A-Za-z]                   # HTML block start
                        )
                    )
                    .+
                    (?!\n(?:[=-]+))
                    (?:\n|$)
                )+
            )
        )
    /mx
    };

    # NOTE: extended regular expressions
    # Extended regular expression
    our $REGEXP_EXT =
    {
    # NOTE: abbreviation
    # Ex: *[HTML]: Hyper Text Markup Language
    # This is similar, but different from definitions
    # https://regex101.com/r/ztM2Pw/2/
    ex_abbr => qr/
        (?
            (?
            (?.+?)(?
            [[:blank:]\h]*
            \:
            [[:blank:]\h]+
            (?.*?)
            (?:\n|\z)
        )
    /x,

    # NOTE: checkbox
    # https://regex101.com/r/ezMwsv/1/
    ex_checkbox => qr/
        (?
            [ ]?
            \[(?X|[[:blank:]\h])\]
            [ ]+
            (?=\S+)
        )
    /xi,

    # NOTE: code block extended
    # This is same as the regular code block, except this allows for a code class or a code definition with class, id, etc.
    # https://regex101.com/r/Y9lPAz/10
    # 2025-10-21: Updated
    ex_code_block => qr/
        (?:(?<=\n)|(?<=\A))                            # Necessarily at the begining of a new line or start of string
        (?
            [ ]{0,3}                                   # Possibly up to 3 leading spaces
            (?                             # CAPTURE ONLY the fence run
                (?[`]{3,})              # 3 code marks (backticks) or more
                |
                (?[~]{3,})                 # or 3 code marks (tilde) or more
            )
            [ \t]*
            (?:
                (?:                                    # .class[.class] {attrs}?   OR   .class only
                    (?(?&_code_class))
                    (?:
                        [ \t]*
                        \{ [[:blank:]\h]* (?(?&_code_attr)) [[:blank:]\h]* \}
                    )?
                )
              |                                        # OR  {attrs} only
                \{ [[:blank:]\h]* (?(?&_code_attr)) [[:blank:]\h]* \}
            )?
            \n+
            (?.*?)                       # enclosed content
            \n+
            [ ]{0,3}                                   # Possibly up to 3 leading spaces on the closing line
            \g{code_start}                             # balanced closing block marks (backticks or tildes)
            [ \t]*                                     # possibly followed by some space
            (?:\n|\Z)                                  # contrary to the vanilla version, we allow for no double line-break
        )
        (?(DEFINE)
            (?<_code_class>     [\w\-.]+)
            (?<_code_attr>      [^}]+)
        )
    /xms,

    # NOTE: footnote extended
    # https://regex101.com/r/WuB1FR/2/
    ex_footnote => qr/
        (?
            ^[ ]{0,3}
            \[\^(?.+?)\][ ]?:      # footnote id
            [ ]*
            \n?					                # maybe *one* newline
            (?					# footnote text (no blank lines allowed)
                (?:
                    .+				            # actual text
                    |
                    \n				            # newlines but
                    (?!\[.+?\][ ]?:\s)          # negative lookahead for footnote or link definition marker.
                    (?!\n+[ ]{0,3}\S)           # ensure line is not blank and followed
                                                # by non-indented content
                )*
            )
        )
    /xm,

    # NOTE: footnote reference extended
    # https://regex101.com/r/3eO7rJ/1/
    ex_footnote_ref => qr/
        (?                        # 3 possible patterns
            (?:
                \[\^(?.*?)\]       # extended patterns with possibly null id
                [[:blank:]\h]*                  # possibly some spaces
                \((?.+?)\)       # and some text in parenthesis
            )
            |
            (?:
                \[\^(?.+?)\]       # regular footnote with a mandatory id
                (?![[:blank:]\h]*\((?:.+?)\))   # but not followed by enclosing parenthesis
            )
            |
            (?:
                \^\[(?.+?)\]     # inline footnote with auto-generated id à la pandoc
            )
        )
    /xms,

    # NOTE: header extended
    # atx-style headers:
    #   # Header 1
    #   ## Header 2
    #   ## Header 2 with closing hashes ##
    #   ...
    #   ###### Header 6
    # ## Le Site ##    {.main .shine #the-site lang=fr}
    # Same as regular header + parameters insides curly braces in between
    # https://regex101.com/r/GyzbR2/3
    # 2025-10-19: Added safeguard
    #             Limited level to 6
    #             Must have some text in 'header_content'
    ex_header => qr/
        (?: $MD_SKIP_FENCED | $MD_SKIP_INDENTED )
        |
        (?
            ^
            (?
            (?\#{1,6})    # one or more #
            [ \t]*                      # Possibly followed by some spaces or tabs
            (?![ \t]*\{)                # Do not allow only attributes as “content”
            (?.+?)      # Header content enclosed
            [ \t\#]*                    # Possibly followed by some spaces or tabs or some dashes (don't need to match the opening ones)
            (?
            \{
                [[:blank:]\h]*          # Possibly with some spaces
                (?[^\}]*)  # and attributes instead braces
            \}
            \n                          # Terminated by a new line
        )
    /xm,

    # NOTE: setext-style headers
    # Setext-style headers:
    #     Header 1 {.main .shine #the-site lang=fr}
    #     ========
    #
    #     Header 2 {.main .shine #the-site lang=fr}
    #     --------
    #
    # This is to be on a single line of its own
    # https://regex101.com/r/berfAR/4
    # 2025-10-19: Added safeguard
    #             Added a limit to the number of header marker: up to 3
    ex_header_line => qr/
        (?: $MD_SKIP_FENCED | $MD_SKIP_INDENTED )
        |
        (?
            ^
            (?.+)       # Header content
            [ \t]*
            (?
            \{
                [[:blank:]\h]*          # Possibly with some spaces
                (?.+?)     # and attributes instead braces
                [[:blank:]\h]*
            \}
            [ \t]*                      # Possibly followed by spaces or tabs
            \n                          # With then a new line
            (?
            (?={3,}|-{3,}) # Multiple = or -, up to 3
            [ \t]*                      # Possibly followed by spaces or tabs
            \n                          # Terminated by a new line
        )
    /mx,

    # NOTE: html extended
    # https://regex101.com/r/M6KCjp/3
    # 2025-10-24: Added indent and fence guard
    ex_html_markdown => qr/
        #---------------------------------------------------------
        # 0) Indented-code guard
        #---------------------------------------------------------
        $MD_SKIP_INDENTED
        |
        #---------------------------------------------------------
        # 1) Fenced-code guard (```...``` or ~~~...~~~)
        #---------------------------------------------------------
        $MD_SKIP_FENCED
        |
        #---------------------------------------------------------
        # 2) The actual extended HTML-with-markdown matcher
        #---------------------------------------------------------
        (?
            (?
                (?:\n|\A)
                (?
                    (?[[:blank:]\h]*)
                    <(?\S+)
                        (?>
                            [[:blank:]\h\v]+[\w\_]+(?:[[:blank:]\h]*\=[[:blank:]\h]*["'][^"']*['"])?
                        )*
                        [[:blank:]\h\v]+markdown[[:blank:]\h]*\=[[:blank:]\h]*(?["']?)1\g{quote}
                        [^\>]*
                    >\n*
                )
                (?.+?)
                \n*
                (?
                    (?()                     # If leading spaces were found
                        (?:
                            (?<=\n)\g{leading_space}              # Either there is a symmetry in leading space for open and closing tag
                            |
                            (?:(?<=\S)[[:blank:]\h]*)       # or the closing tag is on the same line with preceding data
                        )
                        |
                        (?=<\/\g{tag_name}>)                # No leading space, so we don't expect anything before the closing tag other than what has already been caught in the 'content'
                    )
                    <\/\g{tag_name}>
                )
                [[:blank:]\h]*\n
            )
            |
            (?
                (?<=\S)
                (?
                    (?[[:blank:]\h]*)
                    <(?\S+)
                        (?>
                            [[:blank:]\h\v]+[\w\_]+(?:[[:blank:]\h]*\=[[:blank:]\h]*["'][^"']*['"])?
                        )*
                        [[:blank:]\h\v]+markdown[[:blank:]\h]*\=[[:blank:]\h]*(?["'])?1\g{quote}
                        [^\>]*
                    >
                )
                (?.+?)
                (?
                    [[:blank:]\h]*
                    <\/\g{tag_name}>
                )
                (?=\S|[[:blank:]\h\v]*)
            )
        )
    /xms,

    # NOTE: image extended
    # https://regex101.com/r/xetHV1/4
    # 2025-10-19: Added safeguard $MD_SKIP_INLINE_CODE
    ex_img => qr/
        $MD_SKIP_INLINE_CODE
        |
        (?
        (?
            \!\[(?.+?)\]                           # image alternative text, i.e. the text used when the image does not
            (?:
                (?:
                    [ ]?                                    # possibly followed by some spaces
                    (?:\n[ ]*)?                             # and a new line with some space
                    \[(?.*?)\]                      # with the link id in brackets, but may be empty
                )
                |
                (?:
                    (?:
                        \(
                            [ \t]*
                            <(?                    # link url within <>; or
                                .+?
                            )>
                            [ \t]*                              # possibly followed by some spaces or tabs
                            (?:
                                (?['"])    # Title is surrounded ether by double or single quotes
                                (?.*?)               # actual title, but could be empty as in ""
                                \g{img_title_container}         # make the sure enclosing mark balance
                            )?
                            [ \t]*
                        \)
                    )
                    |
                    (?:
                        \(
                            [ \t]*
                            (?                    # link url within <>; or
                                (?:((?!["']).)*+|.*)
                            )
                            [ \t]*
                            (?:
                                (?['"])    # Title is surrounded ether by double or single quotes
                                (?.*?)               # actual title, but could be empty as in ""
                                \g{img_title_container}         # make the sure enclosing mark balance
                            )?
                            [ \t]*
                        \)
                    )
                )
            )
            [ \t]*
            (?
            \{
                [[:blank:]\h]*
                (?.+?)
                [[:blank:]\h]*
            \}
        )
    /x,

    # NOTE: insertion extended
    # https://regex101.com/r/IZw4YU/1/
    # 2025-10-19: Added safeguard $MD_SKIP_INLINE_CODE
    ex_insertion => qr/
        $MD_SKIP_INLINE_CODE
        |
        (?                     # insertion can be multilines
            (?
            (?!\n)                      # but not followed by a new line to avoid any previous + getting caught
            (?             # the content which excludes any + unless they are escaped
                (?>\\[\+]|[^\+])*+
            )
            (?
        )
    /xm,

    # NOTE: katex dollar
    # https://regex101.com/r/43OuNT/1/
    # 2025-10-19: Added safeguard $MD_SKIP_INLINE_CODE
    ex_katex_dollar2 => qr/
        $MD_SKIP_INLINE_CODE
        |
        (?
        (?\${2})
        (?!\$)
        \n?
        (?.+?)\n?
        (?
        (?\g{katex_open})
        (?!\$)
        \n?
    /mxs,
    ex_katex_dollar1 => qr/
        $MD_SKIP_INLINE_CODE
        |
        (?
        (?\${1})
        (?!\$)
        \n?
        (?.+?)\n?
        (?
        (?\g{katex_open})
        (?!\$)
        \n?
    /mxs,
    # NOTE: katex bracket
    ex_katex_bracket => qr/
        $MD_SKIP_INLINE_CODE
        |
        (?
        (?\\\[)
        \n?
        (?.+?)\n?
        (?
        (?
            \\\]
        )\n?
    /mxs,
    # NOTE: katex parens
    ex_katex_parens => qr/
        $MD_SKIP_INLINE_CODE
        |
        (?
        (?\\\()
        \n?
        (?.+?)\n?
        (?
        (?
            \\\)
        )\n?
    /mxs,

    # NOTE: line break extended
    # https://regex101.com/r/6VG46H/1
    ex_line_break => qr/
        (?
            (?:[ ]{2,}\n|\n)
        )
    /mx,

    # NOTE: link extended
    # [Hyperlinked text](http://www.example.com)
    # [Hyperlinked text](http://www.example.com "Example Site")
    # https://regex101.com/r/7mLssJ/7
    # 2025-10-19: Added safeguard $MD_SKIP_INLINE_CODE
    ex_link => qr/
        $MD_SKIP_INLINE_CODE
        |
        (?
            (?:(?:\\|\!)\[(*SKIP)(*FAIL)|\[)                # Cannot be preceded by an anti-slash nor an exclamation mark (image)
                (?
                    (?!\^)                                  # Make sure, this is not confused with a footnote
                    (?>\\[\[\]]|[^\[\]])*+                  # Link text
                )
            (?
            (?:
                (?:
                    [ ]?
                    (?:\n[ ]*)?
                    (?
                        (?!\^)                              # Make sure, this is not confused with a footnote
                        (?.*?)
                    (?
                )
                |
                (?:
                    (?
                        [ \t]*
                        (?:
                            <(?.*?)>
                            |
                            (?                    # link url without <>
                                $HTTP_R3986_URI_INLINE
                            )
                            |
                            (?.*?)
                        )
                        [ \t]*
                        (?:
                            (?['"])
                            (?.*?)
                            \g{link_title_container}
                        )?
                        [ \t]*
                    (?
                    (?![[:blank:]\h]+["'][^"']+["'])
                )
            )
            [ \t]*
            (?
            \{
                [[:blank:]\h]*
                (?.+?)
                [[:blank:]\h]*
            \}
        )
    /x,

    # NOTE: link definition extended
    # https://regex101.com/r/hVfXCe/3
    ex_link_def => qr/
        ^[ ]{0,3}                                       # Leading space up to 3
        (?
            (?
                (?!\^)                                  # Make sure, this is not confused with a footnote
                (?.+?)
            (?
            [ \t]*                                      # Possibly with some space before colon
            \:
            [ \t]*\n?[ \t]*                             # Possibly with some space after the colon, possibly with a new line in between?
            (?:
                <(?[^\>]+)>                   # link within <>
                |
                (?\S+)                        # or link without <>
            )
            (?:
                (?:
                    [ \t]+                              # Either some space or tabs
                    |
                    [ \t]*\n[ \t]*                      # or a new line surrounded by 0 or more spaces or tabs
                )
                (?:
                    (?:
                        (?['"])   # Title is surrounded ether by double or single quotes
                        (?.+?)
                        \g{link_title_container}        # make the sure enclosing mark balance
                    )
                    |                                   # or
                    \((?[^\)]+)\)           # by parenthesis
                )
            )?
            [ \t]*
            (?
            \{
                [[:blank:]\h]*
                (?.+?)
                [[:blank:]\h]*
            \}
            [ \t]*                      # Possibly ending with some trailing spaces or tab
        )
        (?:\n+|\Z)                      # terminated by a new line or end of file
    /xm,

    # NOTE: markdown attributes
    # Ex: {#id1} or {.cl} or {#id.cl.class}
    md_attributes1 => qr/(?[^\}]*)\}/,

    # NOTE: subscript extended
    # https://regex101.com/r/gF6wVe/2
    # 2025-10-19: Added safeguard $MD_SKIP_INLINE_CODE
    ex_subscript => qr/
        $MD_SKIP_INLINE_CODE
        |
        (?
            (?:
                (?
                (?
                    (?>\\[\~[:blank:]\h]|[^\~[:blank:]\h\v])*+
                )
                (?
            )
            |
            (?:     # or the Microsoft way. Beurk
                \
                (?
                    ((?!\v).)+
                )
                \<\/sub\>
            )
        )
    /x,

    # NOTE: superscript extended
    # https://regex101.com/r/yAcNcX/1/
    # 2025-10-19: Added safeguard $MD_SKIP_INLINE_CODE
    ex_superscript => qr/
        $MD_SKIP_INLINE_CODE
        |
        (?
            (?:
                (?
                (?
                    (?>\\[\^[:blank:]\h]|[^\^[:blank:]\h\v])*+
                )
                (?
            )
            |
            (?:     # or the Microsoft way. Beurk
                \
                (?
                    ((?!\v).)+
                )
                \<\/sup\>
            )
        )
    /x,

    # NOTE: strikethrough extended
    # https://regex101.com/r/4Z3h4F/1/
    # 2025-10-19: Added safeguard $MD_SKIP_INLINE_CODE
    ex_strikethrough => qr/
        $MD_SKIP_INLINE_CODE
        |
        (?                  # strikethrough can be multilines
            (?
            (?!\n)                      # but not followed by a new line to avoid any previous tildes getting caught
            (?          # the content which excludes any tilde unless they are escaped
                (?>\\[\~]|[^\~])*+
            )
            (?
        )
    /x,

    # NOTE: table extended
    # https://regex101.com/r/01XCqB/13
    # 2025-10-19: Added safeguard
    ex_table => qr/
        (?: $MD_SKIP_FENCED | $MD_SKIP_INDENTED )
        |
        (?:(?<=^\n)|(?<=\A))
        (? 




1417




 





 





 





 





 





 



             (?(?&t_caption))?                    # maybe some caption at the top? 




1418




 





 





 





 





 





 



             (? 




1419




 





 





 





 





 





 



                 (?                                # Table header 




1420




 





 





 





 





 





 



                     (?(?&t_th_sep))?      # Possible top separator line 




1421




 





 





 





 





 





 



                     (?                           # First header row 




1422




 





 





 





 





 





 



                         [^\n]+\n 




1423




 





 





 





 





 





 



                     ) 




1424




 





 





 





 





 





 



                     (?(?&t_th_sep))           # a separator 




1425




 





 





 





 





 





 



                     (?                           # and possibly a second row of header 




1426




 





 





 





 





 





 



                         [^\n]+\n 




1427




 





 





 





 





 





 



                         (?(?&t_th_sep)) 




1428




 





 





 





 





 





 



                     )? 




1429




 





 





 





 





 





 



                 ) 




1430




 





 





 





 





 





 



             ) 




1431




 





 





 





 





 





 



             (?                                      # Multiple table rows 




1432




 





 





 





 





 





 



                 (?(?&t_row))+ 




1433




 





 





 





 





 





 



             ) 




1434




 





 





 





 





 





 



             (?(?&t_th_sep))?                  # Possibly ended by a separator line 




1435




 





 





 





 





 





 



             (?(?&t_caption))?                    # and maybe with some caption at the bottom 




1436




 





 





 





 





 





 



             (?=\n|\Z) 




1437




 





 





 





 





 





 



         ) 




1438




 





 





 





 





 





 



         (?(DEFINE) 




1439




 





 





 





 





 





 



             (? 




1440




 





 





 





 





 





 



                 [\+\-\|](?:[\: ]*\-+[\: ]*[\+\-\|]?)+\n 




1441




 





 





 





 





 





 



             ) 




1442




 





 





 





 





 





 



             (? 




1443




 





 





 





 





 





 



                 [ ]{0,3} 




1444




 





 





 





 





 





 



                 (?!(?&t_th_sep)|(?&t_caption)) 




1445




 





 





 





 





 





 



                 (?: 




1446




 





 





 





 





 





 



                     (?[\|\:]+)? 




1447




 





 





 





 





 





 



                     (?[^\|\:\n]+) 




1448




 





 





 





 





 





 



                     (?: 




1449




 





 





 





 





 





 



                         (?:[\|\:]{0,2}[ ]*(?=\n)) 




1450




 





 





 





 





 





 



                         | 




1451




 





 





 





 





 





 



                         [\|\:]{1,2} 




1452




 





 





 





 





 





 



                     ) 




1453




 





 





 





 





 





 



                 )+ 




1454




 





 





 





 





 





 



                 (?: 




1455




 





 





 





 





 





 



                     (?:\n(?=(?&t_th_sep))) 




1456




 





 





 





 





 





 



                     | 




1457




 





 





 





 





 





 



                     (?:\n(?=(?&t_caption))) 




1458




 





 





 





 





 





 



                     | 




1459




 





 





 





 





 





 



                     \n 




1460




 





 





 





 





 





 



                 ) 




1461




 





 





 





 





 





 



             ) 




1462




 





 





 





 





 





 



             (? 




1463




 





 





 





 





 





 



                 [ ]{0,3} 




1464




 





 





 





 





 





 



                 \[[^\]]+\] 




1465




 





 





 





 





 





 



                 [ ]* 




1466




 





 





 





 





 





 



                 \n 




1467




 





 





 





 





 





 



             ) 




1468




 





 





 





 





 





 



         ) 




1469




 





 





 





 





 





 



     /xms, 




1470




 





 





 





 





 





 



     }, 




1471




 





 





 





 





 





 



 }; 




1472




 





 





 





 





 





 



   




1473




 





 





 





 





 





 



 pattern name    => [qw( Markdown -extended=1 ) ], 




1474




 





 





 





 





 





 



         create  => sub 




1475




 





 





 





 





 





 



         { 




1476




 





 





 





 





 





 



             my( $self, $flags ) = @_; 




1477




 





 





 





 





 





 



             my %re = %$REGEXP; 




1478




 





 





 





 





 





 



             ## Override vanilla regular expressions by the extended ones 




1479




 





 





 





 





 





 



             if( $flags->{'-extended'} ) 




1480




 





 





 





 





 





 



             { 




1481




 





 





 





 





 





 



                 my @k = keys( %$REGEXP_EXT ); 




1482




 





 





 





 





 





 



                 @re{ @k } = @$REGEXP_EXT{ @k }; 




1483




 





 





 





 





 





 



             } 




1484




 





 





 





 





 





 



             my $pat =  join( '|' => values( %re ) ); 




1485




 





 





 





 





 





 



             return( "(?k:$pat)" ); 




1486




 





 





 





 





 





 



         }; 




1487




 





 





 





 





 





 



   




1488




 





 





 





 





 





 



 pattern name    => [qw( Markdown Bold ) ], 




1489




 





 





 





 





 





 



         create  => $REGEXP->{bold}; 




1490




 





 





 





 





 





 



   




1491




 





 





 





 





 





 



 pattern name    => [qw( Markdown Blockquote ) ], 




1492




 





 





 





 





 





 



         create  => $REGEXP->{bquote}; 




1493




 





 





 





 





 





 



   




1494




 





 





 





 





 





 



 pattern name    => [qw( Markdown CodeBlock ) ], 




1495




 





 





 





 





 





 



         create  => $REGEXP->{code_block}; 




1496




 





 





 





 





 





 



   




1497




 





 





 





 





 





 



 pattern name    => [qw( Markdown CodeLine ) ], 




1498




 





 





 





 





 





 



         create  => $REGEXP->{code_line }; 




1499




 





 





 





 





 





 



   




1500




 





 





 





 





 





 



 pattern name    => [qw( Markdown CodeSpan ) ], 




1501




 





 





 





 





 





 



         create  => $REGEXP->{code_span}; 




1502




 





 





 





 





 





 



   




1503




 





 





 





 





 





 



 pattern name    => [qw( Markdown Em ) ], 




1504




 





 





 





 





 





 



         create  => $REGEXP->{em}; 




1505




 





 





 





 





 





 



   




1506




 





 





 





 





 





 



 pattern name    => [qw( Markdown Header ) ], 




1507




 





 





 





 





 





 



         create  => $REGEXP->{header}; 




1508




 





 





 





 





 





 



   




1509




 





 





 





 





 





 



 pattern name    => [qw( Markdown HeaderLine ) ], 




1510




 





 





 





 





 





 



         create  => $REGEXP->{header_line}; 




1511




 





 





 





 





 





 



   




1512




 





 





 





 





 





 



 pattern name    => [qw( Markdown Html ) ], 




1513




 





 





 





 





 





 



         create  => $REGEXP->{html}; 




1514




 





 





 





 





 





 



   




1515




 





 





 





 





 





 



 pattern name    => [qw( Markdown Image ) ], 




1516




 





 





 





 





 





 



         create  => $REGEXP->{img}; 




1517




 





 





 





 





 





 



   




1518




 





 





 





 





 





 



 pattern name    => [qw( Markdown Line ) ], 




1519




 





 





 





 





 





 



         create  => $REGEXP->{line}; 




1520




 





 





 





 





 





 



   




1521




 





 





 





 





 





 



 pattern name    => [qw( Markdown LineBreak ) ], 




1522




 





 





 





 





 





 



         create  => $REGEXP->{line_break}; 




1523




 





 





 





 





 





 



   




1524




 





 





 





 





 





 



 pattern name    => [qw( Markdown Link ) ], 




1525




 





 





 





 





 





 



         create  => $REGEXP->{link}; 




1526




 





 





 





 





 





 



   




1527




 





 





 





 





 





 



 pattern name    => [qw( Markdown LinkAuto ) ], 




1528




 





 





 





 





 





 



         create  => $REGEXP->{link_auto}; 




1529




 





 





 





 





 





 



   




1530




 





 





 





 





 





 



 pattern name    => [qw( Markdown LinkDefinition ) ], 




1531




 





 





 





 





 





 



         create  => $REGEXP->{link_def}; 




1532




 





 





 





 





 





 



   




1533




 





 





 





 





 





 



 pattern name    => [qw( Markdown LinkRef ) ], 




1534




 





 





 





 





 





 



         create  => $REGEXP->{link_ref}; 




1535




 





 





 





 





 





 



   




1536




 





 





 





 





 





 



 pattern name    => [qw( Markdown List ) ], 




1537




 





 





 





 





 





 



         create  => $REGEXP->{list}; 




1538




 





 





 





 





 





 



   




1539




 





 





 





 





 





 



 pattern name    => [qw( Markdown ListFirstLevel ) ], 




1540




 





 





 





 





 





 



         create  => $REGEXP->{list_first_level}; 




1541




 





 





 





 





 





 



   




1542




 





 





 





 





 





 



 pattern name    => [qw( Markdown ListNthLevel ) ], 




1543




 





 





 





 





 





 



         create  => $REGEXP->{list_nth_level}; 




1544




 





 





 





 





 





 



   




1545




 





 





 





 





 





 



 pattern name    => [qw( Markdown ListItem ) ], 




1546




 





 





 





 





 





 



         create  => $REGEXP->{list_item}; 




1547




 





 





 





 





 





 



   




1548




 





 





 





 





 





 



 pattern name    => [qw( Markdown Paragraph ) ], 




1549




 





 





 





 





 





 



         create  => $REGEXP->{paragraph}; 




1550




 





 





 





 





 





 



   




1551




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtAbbr ) ], 




1552




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_abbr}; 




1553




 





 





 





 





 





 



   




1554




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtAttributes ) ], 




1555




 





 





 





 





 





 



         create  => $REGEXP_EXT->{md_attributes1}; 




1556




 





 





 





 





 





 



   




1557




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtCheckbox ) ], 




1558




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_checkbox}; 




1559




 





 





 





 





 





 



   




1560




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtCodeBlock ) ], 




1561




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_code_block}; 




1562




 





 





 





 





 





 



   




1563




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtFootnote ) ], 




1564




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_footnote}; 




1565




 





 





 





 





 





 



   




1566




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtFootnoteReference ) ], 




1567




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_footnote_ref}; 




1568




 





 





 





 





 





 



   




1569




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtHeader ) ], 




1570




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_header}; 




1571




 





 





 





 





 





 



   




1572




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtHeaderLine ) ], 




1573




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_header_line}; 




1574




 





 





 





 





 





 



   




1575




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtHtmlMarkdown ) ], 




1576




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_html_markdown}; 




1577




 





 





 





 





 





 



   




1578




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtImage )], 




1579




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_img}; 




1580




 





 





 





 





 





 



   




1581




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtInsertion )], 




1582




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_insertion}; 




1583




 





 





 





 





 





 



   




1584




 





 





 





 





 





 



 # pattern name    => [qw( Markdown ExtKatex ), -delimiter=], 




1585




 





 





 





 





 





 



 #         create  => $REGEXP_EXT->{ex_katex}; 




1586




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtKatex ), "-delimiter=\$\$,\$\$,\$,\$,\\\[,\\\],\\\(,\\\)"], 




1587




 





 





 





 





 





 



         create  => sub 




1588




 





 





 





 





 





 



         { 




1589




 





 





 





 





 





 



             my $delim = [split(/[[:blank:]\h]*\,[[:blank:]\h]*/, $_[1]->{'-delimiter'} )]; 




1590




 





 





 





 





 





 



             my $map = 




1591




 





 





 





 





 





 



             { 




1592




 





 





 





 





 





 



             '$$$$'  => 'ex_katex_dollar2', 




1593




 





 





 





 





 





 



             '$$'    => 'ex_katex_dollar1', 




1594




 





 





 





 





 





 



             '\[\]'  => 'ex_katex_bracket', 




1595




 





 





 





 





 





 



             '\(\)'  => 'ex_katex_parens', 




1596




 





 





 





 





 





 



             }; 




1597




 





 





 





 





 





 



             my $res = []; 




1598




 





 





 





 





 





 



             for( my $i = 0; $i < scalar( @$delim ); $i += 2 ) 




1599




 





 





 





 





 





 



             { 




1600




 





 





 





 





 





 



                 my $k = join( '', @$delim[ $i..$i+1 ] ); 




1601




 





 





 





 





 





 



                 push( @$res, $REGEXP_EXT->{ $map->{ $k } } ) if( exists( $map->{ $k } ) ); 




1602




 





 





 





 





 





 



             } 




1603




 





 





 





 





 





 



             my $re; 




1604




 





 





 





 





 





 



             if( scalar( @$res ) ) 




1605




 





 





 





 





 





 



             { 




1606




 





 





 





 





 





 



                 my $re_spec = "(?\n" . join( "\n|\n", @$res ) . "\n)"; 




1607




 





 





 





 





 





 



                 $re = qr/$re_spec/mxs; 




1608




 





 





 





 





 





 



             } 




1609




 





 





 





 





 





 



             $re; 




1610




 





 





 





 





 





 



         }; 




1611




 





 





 





 





 





 



   




1612




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtLineBreak ) ], 




1613




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_line_break}; 




1614




 





 





 





 





 





 



   




1615




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtLink ) ], 




1616




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_link}; 




1617




 





 





 





 





 





 



   




1618




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtLinkDefinition ) ], 




1619




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_link_def}; 




1620




 





 





 





 





 





 



   




1621




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtStrikeThrough ) ], 




1622




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_strikethrough}; 




1623




 





 





 





 





 





 



   




1624




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtSubscript ) ], 




1625




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_subscript}; 




1626




 





 





 





 





 





 



   




1627




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtSuperscript ) ], 




1628




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_superscript}; 




1629




 





 





 





 





 





 



   




1630




 





 





 





 





 





 



 pattern name    => [qw( Markdown ExtTable ) ], 




1631




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_table}; 




1632




 





 





 





 





 





 



   




1633




 





 





 





 





 





 



 1; 




1634




 





 





 





 





 





 



 # NOTE: POD 




1635




 





 





 





 





 





 



 __END__
            (?(?&t_caption))?                    # maybe some caption at the top?
            (?
                (?                                # Table header
                    (?(?&t_th_sep))?      # Possible top separator line
                    (?                           # First header row
                        [^\n]+\n
                    )
                    (?(?&t_th_sep))           # a separator
                    (?                           # and possibly a second row of header
                        [^\n]+\n
                        (?(?&t_th_sep))
                    )?
                )
            )
            (?                                      # Multiple table rows
                (?(?&t_row))+
            )
            (?(?&t_th_sep))?                  # Possibly ended by a separator line
            (?(?&t_caption))?                    # and maybe with some caption at the bottom
            (?=\n|\Z)
        )
        (?(DEFINE)
            (?
                [\+\-\|](?:[\: ]*\-+[\: ]*[\+\-\|]?)+\n
            )
            (?
                [ ]{0,3}
                (?!(?&t_th_sep)|(?&t_caption))
                (?:
                    (?[\|\:]+)?
                    (?[^\|\:\n]+)
                    (?:
                        (?:[\|\:]{0,2}[ ]*(?=\n))
                        |
                        [\|\:]{1,2}
                    )
                )+
                (?:
                    (?:\n(?=(?&t_th_sep)))
                    |
                    (?:\n(?=(?&t_caption)))
                    |
                    \n
                )
            )
            (?
                [ ]{0,3}
                \[[^\]]+\]
                [ ]*
                \n
            )
        )
    /xms,
    },
};

pattern name    => [qw( Markdown -extended=1 ) ],
        create  => sub
        {
            my( $self, $flags ) = @_;
            my %re = %$REGEXP;
            ## Override vanilla regular expressions by the extended ones
            if( $flags->{'-extended'} )
            {
                my @k = keys( %$REGEXP_EXT );
                @re{ @k } = @$REGEXP_EXT{ @k };
            }
            my $pat =  join( '|' => values( %re ) );
            return( "(?k:$pat)" );
        };

pattern name    => [qw( Markdown Bold ) ],
        create  => $REGEXP->{bold};

pattern name    => [qw( Markdown Blockquote ) ],
        create  => $REGEXP->{bquote};

pattern name    => [qw( Markdown CodeBlock ) ],
        create  => $REGEXP->{code_block};

pattern name    => [qw( Markdown CodeLine ) ],
        create  => $REGEXP->{code_line };

pattern name    => [qw( Markdown CodeSpan ) ],
        create  => $REGEXP->{code_span};

pattern name    => [qw( Markdown Em ) ],
        create  => $REGEXP->{em};

pattern name    => [qw( Markdown Header ) ],
        create  => $REGEXP->{header};

pattern name    => [qw( Markdown HeaderLine ) ],
        create  => $REGEXP->{header_line};

pattern name    => [qw( Markdown Html ) ],
        create  => $REGEXP->{html};

pattern name    => [qw( Markdown Image ) ],
        create  => $REGEXP->{img};

pattern name    => [qw( Markdown Line ) ],
        create  => $REGEXP->{line};

pattern name    => [qw( Markdown LineBreak ) ],
        create  => $REGEXP->{line_break};

pattern name    => [qw( Markdown Link ) ],
        create  => $REGEXP->{link};

pattern name    => [qw( Markdown LinkAuto ) ],
        create  => $REGEXP->{link_auto};

pattern name    => [qw( Markdown LinkDefinition ) ],
        create  => $REGEXP->{link_def};

pattern name    => [qw( Markdown LinkRef ) ],
        create  => $REGEXP->{link_ref};

pattern name    => [qw( Markdown List ) ],
        create  => $REGEXP->{list};

pattern name    => [qw( Markdown ListFirstLevel ) ],
        create  => $REGEXP->{list_first_level};

pattern name    => [qw( Markdown ListNthLevel ) ],
        create  => $REGEXP->{list_nth_level};

pattern name    => [qw( Markdown ListItem ) ],
        create  => $REGEXP->{list_item};

pattern name    => [qw( Markdown Paragraph ) ],
        create  => $REGEXP->{paragraph};

pattern name    => [qw( Markdown ExtAbbr ) ],
        create  => $REGEXP_EXT->{ex_abbr};

pattern name    => [qw( Markdown ExtAttributes ) ],
        create  => $REGEXP_EXT->{md_attributes1};

pattern name    => [qw( Markdown ExtCheckbox ) ],
        create  => $REGEXP_EXT->{ex_checkbox};

pattern name    => [qw( Markdown ExtCodeBlock ) ],
        create  => $REGEXP_EXT->{ex_code_block};

pattern name    => [qw( Markdown ExtFootnote ) ],
        create  => $REGEXP_EXT->{ex_footnote};

pattern name    => [qw( Markdown ExtFootnoteReference ) ],
        create  => $REGEXP_EXT->{ex_footnote_ref};

pattern name    => [qw( Markdown ExtHeader ) ],
        create  => $REGEXP_EXT->{ex_header};

pattern name    => [qw( Markdown ExtHeaderLine ) ],
        create  => $REGEXP_EXT->{ex_header_line};

pattern name    => [qw( Markdown ExtHtmlMarkdown ) ],
        create  => $REGEXP_EXT->{ex_html_markdown};

pattern name    => [qw( Markdown ExtImage )],
        create  => $REGEXP_EXT->{ex_img};

pattern name    => [qw( Markdown ExtInsertion )],
        create  => $REGEXP_EXT->{ex_insertion};

# pattern name    => [qw( Markdown ExtKatex ), -delimiter=],
#         create  => $REGEXP_EXT->{ex_katex};
pattern name    => [qw( Markdown ExtKatex ), "-delimiter=\$\$,\$\$,\$,\$,\\\[,\\\],\\\(,\\\)"],
        create  => sub
        {
            my $delim = [split(/[[:blank:]\h]*\,[[:blank:]\h]*/, $_[1]->{'-delimiter'} )];
            my $map =
            {
            '$$$$'  => 'ex_katex_dollar2',
            '$$'    => 'ex_katex_dollar1',
            '\[\]'  => 'ex_katex_bracket',
            '\(\)'  => 'ex_katex_parens',
            };
            my $res = [];
            for( my $i = 0; $i < scalar( @$delim ); $i += 2 )
            {
                my $k = join( '', @$delim[ $i..$i+1 ] );
                push( @$res, $REGEXP_EXT->{ $map->{ $k } } ) if( exists( $map->{ $k } ) );
            }
            my $re;
            if( scalar( @$res ) )
            {
                my $re_spec = "(?\n" . join( "\n|\n", @$res ) . "\n)";
                $re = qr/$re_spec/mxs;
            }
            $re;
        };

pattern name    => [qw( Markdown ExtLineBreak ) ],
        create  => $REGEXP_EXT->{ex_line_break};

pattern name    => [qw( Markdown ExtLink ) ],
        create  => $REGEXP_EXT->{ex_link};

pattern name    => [qw( Markdown ExtLinkDefinition ) ],
        create  => $REGEXP_EXT->{ex_link_def};

pattern name    => [qw( Markdown ExtStrikeThrough ) ],
        create  => $REGEXP_EXT->{ex_strikethrough};

pattern name    => [qw( Markdown ExtSubscript ) ],
        create  => $REGEXP_EXT->{ex_subscript};

pattern name    => [qw( Markdown ExtSuperscript ) ],
        create  => $REGEXP_EXT->{ex_superscript};

pattern name    => [qw( Markdown ExtTable ) ],
        create  => $REGEXP_EXT->{ex_table};

1;
# NOTE: POD
__END__