File Coverage

blib/lib/Regexp/Common/Markdown.pm

Criterion	Covered	Total	%
statement	33	33	100.0
branch			n/a
condition			n/a
subroutine	8	8	100.0
pod			n/a
total	41	41	100.0

##----------------------------------------------------------------------------
## Markdown Common Regular Expressions - ~/lib/Regexp/Common/Markdown.pm
## Version v0.1.4
## Copyright(c) 2020 DEGUEST Pte. Ltd.
## Author: Jacques Deguest <@sitael.tokyo.deguest.jp>
## Created 2020/08/01
## Modified 2020/08/16
##
##----------------------------------------------------------------------------
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 );
    ## We use URI::tel instead of Regexp::Common::tel because its regular expression is antiquated
    ## URI::tel uses the latest rfc3966
    use URI::tel;
    our $VERSION = 'v0.1.4';

    our $SPACE_RE = qr/[[:blank:]\h]/;
    ## Including vertical space like new lines
    our $SPACE_EXTENDED_RE = qr/[[:blank:]\h\v]/;
    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/
        (?:(?<=\n\n)|\A\n*|\n{2,})
        (?                                                            # 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;

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

    ## 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,

    ## ```
    ## Some code
    ## ```
    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
                \`{3,}                      # 3 code marks (backticks) or more
            )
            \n+
            (?.*?)            # enclosed content
            \n+
            (?
            \g{code_start}                  # balanced closing block marks
            (?!`)
            [ \t]*                          # possibly followed by some space
            \n
        )
        (?\n|\Z)    # and a new line or end of string
    /xms,

    ## Marked by left hand indentation
    ## https://regex101.com/r/toEboU/2/tests
    code_line => qr/
        (?:\n{2,}|\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,

    ## \x{0060} is ` in unicode; see perl -le 'printf "\\x%x", ord( "`" )'
    code_span => qr/
        (?
        (?
            (?\`{1,})   # One or more backtick(s)
            (?.+?)    # Code content inbetween back sticks
            (?
            \g{code_start}          # Balanced closing backtick(s)
            (?!`)                   # And not followed by a backtick
        )
    /x,

    ## https://regex101.com/r/eDb6RN/3/tests
    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,

    ## Headers: #, ##, ###, ####, #####, ###### become h1..6
    # atx-style headers:
    #   # Header 1
    #   ## Header 2
    #   ## Header 2 with closing hashes ##
    #   ...
    #   ###### Header 6
    ## https://regex101.com/r/9uQwBk/2/tests
    header => qr/
        (?
            (?
            (?\#+)        # one or more #
            [ \t]*                      # Possibly followed by some spaces or tabs
            (?.+?)      # Header content enclosed
            [ \t]*                      # Possibly followed by some spaces or tabs
            \g{header_level}*           # Possibly with closing balanced #
            \n+                         # Terminated by a new line
        )
    /mx,

    # Setext-style headers:
    #     Header 1
    #     ========
    #
    #     Header 2
    #     --------
    #
    ## This is to be on a single line of its own
    ## https://regex101.com/r/sQLEqz/2
    header_line => qr/
        (?
            (?.+)       # Header content
            [ \t]*                      # Possibly followed by spaces or tabs
            \n                          # With then a new line
            (?
            (?[\=|\-]+)    # Multiple = or -
            [ \t]*                      # Possibly followed by spaces or tabs
            \n+                         # Terminated by a new line
        )
    /mx,

    ## https://regex101.com/r/SH8ki3/2/tests
    html => qr/
(?:(?<=\n\n)|\A\n*|\n{2,})
[ ]{0,3}                                                                # up to 3 leading space
(?
    (?:
        (?:
            <                                                           # start of the html block withuot space before
                [[:blank:]\h\v]*
                (?[a-zA-Z0-9][\w\-]+)                         # tag name starting with alphanumeric character
                (?(?&tag_attr))*
                [[:blank:]\h\v]*
            >
            (?.*?)
            (?                                               # balanced closing tag
                <
                [[:blank:]\h\v]*
                \/
                \g{tag_name}
                [[:blank:]\h\v]*
                >
            )
        )
        |                                                               # or
        (?:
             # html comment
        )
        |                                                               # or
        (?:
            <                                                           # standalone tag
                [[:blank:]\h\v]*
                (?[a-zA-Z0-9][\w\-]+)
                (?(?&tag_attr))*
                [[:blank:]\h\v]*
                \/?
                [[:blank:]\h\v]*
            >
        )
    )
    (?                                                      # making sure what follows is
        \z                                                              # either end of string
        |                                                               # or
        [ ]*\n{1,2}
        (?!                                                             # not html data
            [[:blank:]\h\v]*
            (?:
                (?:
                    <
                        [[:blank:]\h\v]*
                        [a-zA-Z0-9][\w\-]+
                        (?:(?&tag_attr))*
                        [[:blank:]\h\v]*
                    >
                )
                |
                (?:
                    <
                        [[:blank:]\h\v]*
                        \/?
                        [[:blank:]\h\v]*
                        [\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,

    ## Basically same as link, except there is an exclamation mark (!) just before:
    ## Ex: ![alt text](url "optional title")
    ## https://regex101.com/r/z0yH2F/5/tests
    img => qr/
        (?
        (?
            \!\[(?.+?)\]                           # 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
                )
                |
                (?:
                    \(
                        [ \t]*
                        (?:
                            <(?.*?)>               # link url within <>; or
                            |
                            (?.*?)                 # link url without <>
                        )
                        [ \t]*                              # possibly followed by some spaces or tabs
                        (?:
                            (?['"])    # Title is surrounded ether by double or single quotes
                            (?.*?)               # actual title, but could be empty as in ""
                            \g{img_title_container}         # make the sure enclosing mark balance
                        )?
                    \)
                )
            )
        )
    /xm,

#     ^[ ]{0,2}([ ]?\*[ ]?){3,}[ \t]*$
    ## Horizontal line
    ## https://daringfireball.net/projects/markdown/syntax#hr
    ## https://regex101.com/r/Vlew4X/2
    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,

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

    ## Link
    ## https://daringfireball.net/projects/markdown/syntax#link
    ## https://regex101.com/r/sGsOIv/4
    ## Links' id can be multiline, so we need the /s modifier
    link => qr/
        (?                                        # Check it was not escaped with a \
            (?
            (?
                (?>\\[\[\]]|[^\[\]])*+                      # Link text
            )
            (?
            (?:
                (?:
                    [ ]?                                    # possibly followed by some spaces
                    (?:\n[ ]*)?                             # and a new line with some space
                    (?.*?)(?
                )
                |
                (?:
                    (?
                        [ \t]*
                        (?:
                            <(?.*?)>              # link url within <>; or
                            |
                            (?.*?)                # link url without <>
                        )
                        [ \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
                        )?
                    (?
                    (?![[:blank:]\h]+["'][^"']+["'])
                )
            )
        )
    /xms,

    ## https://regex101.com/r/bAUu1E/4/tests
    link_auto => qr/
        (?
        (?
            <
            (?
                (?$RE{URI}{HTTP})                        # http
                |
                (?$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]
            )
            >
        )
    /x,

    ## Definition
    ## https://daringfireball.net/projects/markdown/syntax#link
    ## https://regex101.com/r/edg2F7/2/tests
    link_def => qr/
        ^[ ]{0,3}                                       # Leading space up to 3
        (?
            (?.+?)(?
            [ \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,

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

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

    list_type_unordered => $LIST_TYPE_UNORDERED,

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

    ## https://regex101.com/r/RfhRVg/3
    list_first_level => qr/
        (?:(?<=\n\n)|\A\n*|\n{2,})
        $LIST_ALL
    /mx,

    list_nth_level => qr/
        ^
        $LIST_ALL
    /mx,

    ## 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/tests
    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,

    ## https://regexr.com/5929n
    ## https://regex101.com/r/0B3gR4/3
    paragraph => qr/
        (?
            (?:\n{2,}|^)                            # 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
                            |
                            [>+-=\#]
                            |
                            \d+\.                   # ordered list
                            |
                            \`{3,}                  # code block
                        )
                    )
                )
                .+
                (?!\n(?:[=-]+))
                (?:\n|$)
            )+
        )
    /mx
    };

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

    ## 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/2
    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
                (?:
                    (?[`]{3,})           # 3 code marks (backticks) or more
                    |
                    (?[~]{3,})              # or 3 code marks (tilde) or more
                )
            )
            [ \t]*
            (?:
                (?:
                    (?(?&_code_class))
                    (?:
                        [ \t]*
                        \{[[:blank:]\h]*(?(?&_code_attr))[[:blank:]\h]*\}
                    )?
                )
                |
                (?:
                    \{[[:blank:]\h]*(?(?&_code_attr))[[:blank:]\h]*\}
                )
            )?
            \n+
            (?.*?)                        # enclosed content
            \n+
            (?()
                (?:
                    (?
                    \g{code_start}                      # balanced closing block marks
                    (?!\`)
                )
                |
                (?:
                    (?
                    \g{code_start}                      # balanced closing block marks
                    (?!\~)
                )
            )
            [ \t]*                                      # possibly followed by some space
            (?:\n?|\Z)                                  # contrary to the vanilla version, we allow for no double line-break
        )
        (?\n|\Z)                # and a new line or end of string
        (?(DEFINE)
            (?<_code_class>     [\w\-\.]+)
            (?<_code_attr>      [^\}]+)
        )
    /xms,

    ## 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,

    ## 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,

    # 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/GyzbR2/1/tests
    ex_header => qr/
        (?
            (?
            (?\#+)        # one or more #
            [ \t]*                      # Possibly followed by some spaces or tabs
            (?.+?)      # Header content enclosed
            [ \t]*                      # Possibly followed by some spaces or tabs
            \g{header_level}*           # Possibly with closing balanced #
            (?
            \{
                $SPACE_RE*              # Possibly with some spaces
                (?[^\}]*)  # and attributes instead braces
            \}
            \n+                         # Terminated by a new line
        )
    /xm,

    # 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/2/tests
    ex_header_line => qr/
        (?
            (?.+)       # 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
            (?
            (?[\=|\-]+)    # Multiple = or -
            [ \t]*                      # Possibly followed by spaces or tabs
            \n+                         # Terminated by a new line
        )
    /mx,

    ## https://regex101.com/r/xetHV1/2
    ex_img => qr/
        (?
        (?
            \!\[(?.+?)\]                           # 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
                )
                |
                (?:
                    \(
                        [ \t]*
                        (?:
                            <(?.*?)>               # link url within <>; or
                            |
                            (?.*?)                 # link url without <>
                        )
                        [ \t]*                              # possibly followed by some spaces or tabs
                        (?:
                            (?['"])    # Title is surrounded ether by double or single quotes
                            (?.*?)               # actual title, but could be empty as in ""
                            \g{img_title_container}         # make the sure enclosing mark balance
                        )?
                    \)
                )
            )
            [ \t]*
            (?
            \{
                [[:blank:]\h]*
                (?.+?)
                [[:blank:]\h]*
            \}
        )
    /x,

    # [Hyperlinked text](http://www.example.com)
    # [Hyperlinked text](http://www.example.com "Example Site")
    ## https://regex101.com/r/7mLssJ/2
    ex_link => qr/
        (?
            (?.+?)(?
            (?:
                (?:
                    [ ]?
                    (?:\n[ ]*)?
                    (?.*?)(?
                )
                |
                (?:
                    (?
                        [ \t]*
                        (?:
                            <(?.*?)>
                            |
                            (?.*?)
                        )
                        [ \t]*
                        (?:
                            (?['"])
                            (?.*?)
                            \g{link_title_container}
                        )?
                    (?
                    (?![[:blank:]\h]+["'][^"']+["'])
                )
            )
            [ \t]*
            (?
            \{
                [[:blank:]\h]*
                (?.+?)
                [[:blank:]\h]*
            \}
        )
    /x,

    ## https://regex101.com/r/hVfXCe/2/
    ex_link_def => qr/
        ^[ ]{0,3}                                       # Leading space up to 3
        (?
            (?.+?)(?
            [ \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,

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

    ## https://regex101.com/r/gF6wVe/1/tests
    ex_subscript => qr/
        (?
            (?:
                (?
                (?
                    (?>\\[\~[:blank:]\h]|[^\~[:blank:]\h\v])*+
                )
                (?
            )
            |
            (?:     # or the Microsoft way. Beurk
                \
                (?
                    ((?!\v).)+
                )
                \<\/sub\>
            )
        )
    /x,

    ## https://regex101.com/r/yAcNcX/1/tests
    ex_superscript => qr/
        (?
            (?:
                (?
                (?
                    (?>\\[\^[:blank:]\h]|[^\^[:blank:]\h\v])*+
                )
                (?
            )
            |
            (?:     # or the Microsoft way. Beurk
                \
                (?
                    ((?!\v).)+
                )
                \<\/sup\>
            )
        )
    /x,

    ## https://regex101.com/r/01XCqB/9/tests
    ex_table => qr/
        (?:\n{2,}|\A)
        (? 




970




 





 





 





 





 





 



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




971




 





 





 





 





 





 



             (? 




972




 





 





 





 





 





 



                 (?                                # Table header 




973




 





 





 





 





 





 



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




974




 





 





 





 





 





 



                     (?                           # First header row 




975




 





 





 





 





 





 



                         [^\n]+\n 




976




 





 





 





 





 





 



                     ) 




977




 





 





 





 





 





 



                     (?(?&t_th_sep))           # a separator 




978




 





 





 





 





 





 



                     (?                           # and possibly a second row of header 




979




 





 





 





 





 





 



                         [^\n]+\n 




980




 





 





 





 





 





 



                         (?(?&t_th_sep)) 




981




 





 





 





 





 





 



                     )? 




982




 





 





 





 





 





 



                 ) 




983




 





 





 





 





 





 



             ) 




984




 





 





 





 





 





 



             (?                                      # Multiple table rows 




985




 





 





 





 





 





 



                 (?(?&t_row))* 




986




 





 





 





 





 





 



             ) 




987




 





 





 





 





 





 



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




988




 





 





 





 





 





 



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




989




 





 





 





 





 





 



             (? 




990




 





 





 





 





 





 



                 \z 




991




 





 





 





 





 





 



                 | 




992




 





 





 





 





 





 



                 \n{1,2} 




993




 





 





 





 





 





 



                 (?! 




994




 





 





 





 





 





 



                     (?(?&t_row)) 




995




 





 





 





 





 





 



                 ) 




996




 





 





 





 





 





 



             ) 




997




 





 





 





 





 





 



         ) 




998




 





 





 





 





 





 



   




999




 





 





 





 





 





 



         (?(DEFINE) 




1000




 





 





 





 





 





 



             (? 




1001




 





 





 





 





 





 



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




1002




 





 





 





 





 





 



             ) 




1003




 





 





 





 





 





 



             (? 




1004




 





 





 





 





 





 



                 [ ]{0,3} 




1005




 





 





 





 





 





 



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




1006




 





 





 





 





 





 



                 (?: 




1007




 





 





 





 





 





 



                     (?[\|\:]+)? 




1008




 





 





 





 





 





 



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




1009




 





 





 





 





 





 



                     (?: 




1010




 





 





 





 





 





 



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




1011




 





 





 





 





 





 



                         | 




1012




 





 





 





 





 





 



                         [\|\:]{1,2} 




1013




 





 





 





 





 





 



                     ) 




1014




 





 





 





 





 





 



                 )+ 




1015




 





 





 





 





 





 



                 (?: 




1016




 





 





 





 





 





 



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




1017




 





 





 





 





 





 



                     | 




1018




 





 





 





 





 





 



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




1019




 





 





 





 





 





 



                     | 




1020




 





 





 





 





 





 



                     \n{1,2} 




1021




 





 





 





 





 





 



                 ) 




1022




 





 





 





 





 





 



             ) 




1023




 





 





 





 





 





 



             (? 




1024




 





 





 





 





 





 



                 [ ]{0,3} 




1025




 





 





 





 





 





 



                 \[[^\]]+\] 




1026




 





 





 





 





 





 



                 [ ]* 




1027




 





 





 





 





 





 



                 \n 




1028




 





 





 





 





 





 



             ) 




1029




 





 





 





 





 





 



         ) 




1030




 





 





 





 





 





 



     /xms, 




1031




 





 





 





 





 





 



     }, 




1032




 





 





 





 





 





 



 }; 




1033




 





 





 





 





 





 



   




1034




 





 





 





 





 





 



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




1035




 





 





 





 





 





 



         create  => sub 




1036




 





 





 





 





 





 



         { 




1037




 





 





 





 





 





 



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




1038




 





 





 





 





 





 



             my %re = %$REGEXP; 




1039




 





 





 





 





 





 



             ## Override vanilla regular expressions by the extended ones 




1040




 





 





 





 





 





 



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




1041




 





 





 





 





 





 



             { 




1042




 





 





 





 





 





 



                 my @k = keys( %$REGEXP_EXT ); 




1043




 





 





 





 





 





 



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




1044




 





 





 





 





 





 



             } 




1045




 





 





 





 





 





 



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




1046




 





 





 





 





 





 



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




1047




 





 





 





 





 





 



         }; 




1048




 





 





 





 





 





 



   




1049




 





 





 





 





 





 



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




1050




 





 





 





 





 





 



         create  => $REGEXP->{bold}; 




1051




 





 





 





 





 





 



   




1052




 





 





 





 





 





 



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




1053




 





 





 





 





 





 



         create  => $REGEXP->{bquote}; 




1054




 





 





 





 





 





 



   




1055




 





 





 





 





 





 



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




1056




 





 





 





 





 





 



         create  => $REGEXP->{code_block}; 




1057




 





 





 





 





 





 



   




1058




 





 





 





 





 





 



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




1059




 





 





 





 





 





 



         create  => $REGEXP->{code_line }; 




1060




 





 





 





 





 





 



   




1061




 





 





 





 





 





 



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




1062




 





 





 





 





 





 



         create  => $REGEXP->{code_span}; 




1063




 





 





 





 





 





 



   




1064




 





 





 





 





 





 



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




1065




 





 





 





 





 





 



         create  => $REGEXP->{em}; 




1066




 





 





 





 





 





 



   




1067




 





 





 





 





 





 



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




1068




 





 





 





 





 





 



         create  => $REGEXP->{header}; 




1069




 





 





 





 





 





 



   




1070




 





 





 





 





 





 



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




1071




 





 





 





 





 





 



         create  => $REGEXP->{header_line}; 




1072




 





 





 





 





 





 



   




1073




 





 





 





 





 





 



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




1074




 





 





 





 





 





 



         create  => $REGEXP->{html}; 




1075




 





 





 





 





 





 



   




1076




 





 





 





 





 





 



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




1077




 





 





 





 





 





 



         create  => $REGEXP->{img}; 




1078




 





 





 





 





 





 



   




1079




 





 





 





 





 





 



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




1080




 





 





 





 





 





 



         create  => $REGEXP->{line}; 




1081




 





 





 





 





 





 



   




1082




 





 





 





 





 





 



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




1083




 





 





 





 





 





 



         create  => $REGEXP->{line_break}; 




1084




 





 





 





 





 





 



   




1085




 





 





 





 





 





 



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




1086




 





 





 





 





 





 



         create  => $REGEXP->{link}; 




1087




 





 





 





 





 





 



   




1088




 





 





 





 





 





 



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




1089




 





 





 





 





 





 



         create  => $REGEXP->{link_auto}; 




1090




 





 





 





 





 





 



   




1091




 





 





 





 





 





 



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




1092




 





 





 





 





 





 



         create  => $REGEXP->{link_def}; 




1093




 





 





 





 





 





 



   




1094




 





 





 





 





 





 



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




1095




 





 





 





 





 





 



         create  => $REGEXP->{link_ref}; 




1096




 





 





 





 





 





 



   




1097




 





 





 





 





 





 



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




1098




 





 





 





 





 





 



         create  => $REGEXP->{list}; 




1099




 





 





 





 





 





 



   




1100




 





 





 





 





 





 



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




1101




 





 





 





 





 





 



         create  => $REGEXP->{list_first_level}; 




1102




 





 





 





 





 





 



   




1103




 





 





 





 





 





 



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




1104




 





 





 





 





 





 



         create  => $REGEXP->{list_nth_level}; 




1105




 





 





 





 





 





 



   




1106




 





 





 





 





 





 



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




1107




 





 





 





 





 





 



         create  => $REGEXP->{list_item}; 




1108




 





 





 





 





 





 



   




1109




 





 





 





 





 





 



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




1110




 





 





 





 





 





 



         create  => $REGEXP->{paragraph}; 




1111




 





 





 





 





 





 



   




1112




 





 





 





 





 





 



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




1113




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_abbr}; 




1114




 





 





 





 





 





 



   




1115




 





 





 





 





 





 



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




1116




 





 





 





 





 





 



         create  => $REGEXP_EXT->{md_attributes1}; 




1117




 





 





 





 





 





 



   




1118




 





 





 





 





 





 



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




1119




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_code_block}; 




1120




 





 





 





 





 





 



   




1121




 





 





 





 





 





 



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




1122




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_footnote}; 




1123




 





 





 





 





 





 



   




1124




 





 





 





 





 





 



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




1125




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_footnote_ref}; 




1126




 





 





 





 





 





 



   




1127




 





 





 





 





 





 



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




1128




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_header}; 




1129




 





 





 





 





 





 



   




1130




 





 





 





 





 





 



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




1131




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_header_line}; 




1132




 





 





 





 





 





 



          




1133




 





 





 





 





 





 



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




1134




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_img}; 




1135




 





 





 





 





 





 



   




1136




 





 





 





 





 





 



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




1137




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_link}; 




1138




 





 





 





 





 





 



   




1139




 





 





 





 





 





 



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




1140




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_link_def}; 




1141




 





 





 





 





 





 



   




1142




 





 





 





 





 





 



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




1143




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_subscript}; 




1144




 





 





 





 





 





 



   




1145




 





 





 





 





 





 



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




1146




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_superscript}; 




1147




 





 





 





 





 





 



   




1148




 





 





 





 





 





 



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




1149




 





 





 





 





 





 



         create  => $REGEXP_EXT->{ex_table}; 




1150




 





 





 





 





 





 



   




1151




 





 





 





 





 





 



 1; 




1152




 





 





 





 





 





 



   




1153




 





 





 





 





 





 



 __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
            (?
                \z
                |
                \n{1,2}
                (?!
                    (?(?&t_row))
                )
            )
        )

        (?(DEFINE)
            (?
                [\+\-\|](?:[\: ]*\-+[\: ]*[\+\-\|]?)+\n
            )
            (?
                [ ]{0,3}
                (?!(?&t_th_sep)|(?&t_caption))
                (?:
                    (?[\|\:]+)?
                    (?[^\|\:\n]+)
                    (?:
                        (?:[\|\:]{0,2}[ ]*(?=\n))
                        |
                        [\|\:]{1,2}
                    )
                )+
                (?:
                    (?:\n(?=(?&t_th_sep)))
                    |
                    (?:\n(?=(?&t_caption)))
                    |
                    \n{1,2}
                )
            )
            (?
                [ ]{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 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 ExtImage )],
        create  => $REGEXP_EXT->{ex_img};

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 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;

__END__