X-Git-Url: http://git.plutz.net/?a=blobdiff_plain;f=markdown.awk;h=34879d25c22ba3498633c366374a9feeac6be943;hb=refs%2Fheads%2Fmaster;hp=7e29c572213e553df07563099cf52683ed11b960;hpb=fb015c84c44feea2ba863c89a6d4fc0f387144fd;p=cgilite diff --git a/markdown.awk b/markdown.awk index 7e29c57..90dddbf 100755 --- a/markdown.awk +++ b/markdown.awk @@ -5,7 +5,7 @@ # Meant to support all features of John Grubers basic Markdown # + a number of common extensions, mostly inspired by Pandoc Markdown -# Copyright 2021 - 2023 Paul Hänsch +# Copyright 2021 - 2024 Paul Hänsch # # Permission to use, copy, modify, and/or distribute this software for any # purpose with or without fee is hereby granted, provided that the above @@ -121,213 +121,268 @@ function URL ( text, sharp ) { return text; } -function inline( line, LOCAL, len, text, code, href, guard ) { - if ( line ~ /^$/ ) { # Recursion End - return ""; - - # omit processing of escaped characters - } else if ( line ~ /^\\./) { - return HTML(substr(line, 2, 1)) inline( substr(line, 3) ); - - # hard brakes - } else if ( match(line, /^ \n/) ) { - return "
\n" inline( substr(line, RLENGTH + 1) ); - - # ``code spans`` - } else if ( match( line, /^`+/) ) { - len = RLENGTH - guard = substr( line, 1, len ) - if ( match(line, guard ".*" guard) ) { - code = substr( line, len + 1, match( substr(line, len + 1), guard ) - 1) - len = 2 * length(guard) + length(code) - # strip single surrounding white spaces - gsub( /^ | $/, "", code) - # escape HTML within code span - gsub( /&/, "\\&", code ); gsub( //, "\\>", code ); - return "" code "" inline( substr( line, len + 1 ) ) - } +function inline( line, LOCAL, len, text, code, href, guard, ret ) { + ret = ""; + while (line !~ /^$/) { + # omit processing of escaped characters + if ( line ~ /^\\./) { + ret = ret HTML(substr(line, 2, 1)); line = substr(line, 3); + continue; + + # hard brakes + } else if ( match(line, /^ \n/) ) { + ret = ret "
\n"; line = substr(line, RLENGTH + 1); + continue; + + # ``code spans`` + } else if ( match( line, /^`+/) ) { + len = RLENGTH + guard = substr( line, 1, len ) + if ( match(line, guard ".*" guard) ) { + code = substr( line, len + 1, match( substr(line, len + 1), guard ) - 1) + len = 2 * length(guard) + length(code) + # strip single surrounding white spaces + gsub( /^ | $/, "", code) + # escape HTML within code span + gsub( /&/, "\\&", code ); gsub( //, "\\>", code ); + ret = ret "" code ""; line = substr( line, len + 1 ); + continue; + } - # Macros - } else if ( match( line, /^<<([^>]|>[^>])+>>/ ) ) { - len = RLENGTH; - return "" HTML( substr( line, 3, len - 4 ) ) "" inline(substr(line, len + 1)); - - # Wiki style links - } else if ( match( line, /^\[\[([^]|]+)(\|[^]]+)?\]\]/) ) { - len = RLENGTH; - href = gensub(/^\[\[([^]|]+)(\|([^]]+))?\]\]/, "\\1", 1, substr(line, 1, len) ); - text = gensub(/^\[\[([^]|]+)(\|([^]]+))?\]\]/, "\\3", 1, substr(line, 1, len) ); - if ( ! text ) text = href; - return "" HTML(text) "" inline( substr( line, len + 1) ); - - # quick links ("automatic links" in md doc) - } else if ( match( line, /^<[a-zA-Z]+:\/\/([-\.[:alnum:]]+)(:[0-9]*)?(\/[^>]*)?>/ ) ) { - len = RLENGTH; - href = URL( substr( line, 2, len - 2) ); - return "" href "" inline( substr( line, len + 1) ); - - # quick link email - } else if ( match( line, /^<[a-zA-Z0-9.!#$%&'\''*+\/=?^_`{|}~-]+@[a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(\.[a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*>/ ) ) { - len = RLENGTH; - href = URL( substr( line, 2, len - 2) ); - return "" href "" inline( substr( line, len + 1) ); - - # Verbatim inline HTML - } else if ( AllowHTML && match( line, /^(|<\?([^\?]|\?[^>])*\?>|]*>|])*\]\]>|<\/[A-Za-z][A-Za-z0-9-]*[[:space:]]*>|<[A-Za-z][A-Za-z0-9-]*([[:space:]]+[A-Za-z_:][A-Za-z0-9_\.:-]*([[:space:]]*=[[:space:]]*([[:space:]"'=<>`]+|"[^"]*"|'[^']*'))?)*[[:space:]]*\/?>)/) ) { - len = RLENGTH; - return substr( line, 1, len) inline(substr(line, len + 1)); - - # inline links - } else if ( match(line, "^" lii "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)") ) { - len = RLENGTH; - text = href = title = substr( line, 1, len); - sub("^\\[", "", text); sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)$", "", text); - sub("^" lii "\\([\n\t ]*", "", href); sub("([\n\t ]+" lit ")?[\n\t ]*\\)$", "", href); - sub("^" lii "\\([\n\t ]*" lid, "", title); sub("[\n\t ]*\\)$", "", title); sub("^[\n\t ]+", "", title); - - if ( match(href, /^<.*>$/) ) { sub(/^$/, "", href); } - if ( match(title, /^".*"$/) ) { sub(/^"/, "", title); sub(/"$/, "", title); } - else if ( match(title, /^'.*'$/) ) { sub(/^'/, "", title); sub(/'$/, "", title); } - else if ( match(title, /^\(.*\)$/) ) { sub(/^\(/, "", title); sub(/\)$/, "", title); } - - gsub(/\\/, "", href); gsub(/\\/, "", title); gsub(/[\n\t]+/, " ", title); - - return "" \ - inline( text ) "" inline( substr( line, len + 1) ); - - # reference style links - } else if ( match(line, /^\[([^]]+)\] ?\[([^]]*)\]/ ) ) { - len = RLENGTH; - text = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\1", 1, substr(line, 1, len) ); - id = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\2", 1, substr(line, 1, len) ); - if ( ! id ) id = text; - if ( rl_href[id] && rl_title[id] ) { - return "" inline(text) "" inline( substr( line, len + 1) ); - } else if ( rl_href[id] ) { - return "" inline(text) "" inline( substr( line, len + 1) ); - } else { - return "" HTML(substr(line, 1, len)) inline( substr(line, len + 1) ); - } + # Macros + } else if ( match( line, /^<<([^>]|>[^>])+>>/ ) ) { + len = RLENGTH; + ret = ret "" HTML( substr( line, 3, len - 4 ) ) ""; line = substr(line, len + 1); + continue; + + # Wiki style links + } else if ( match( line, /^\[\[([^]|]+)(\|[^]]+)?\]\]/) ) { + len = RLENGTH; href = text = substr(line, 1, len); + sub(/^\[\[/, "", href); sub(/(\|([^]]+))?\]\].*$/, "", href); + sub(/^\[\[([^]|]+)/, "", text); sub(/\]\].*$/, "", text); sub(/^\|/, "", text); + # sub(/^\[\[([^]|]+)(\|([^]]+))?\]\]/, "\\1", href ); + # sub(/^\[\[([^]|]+)(\|([^]]+))?\]\]/, "\\3", text ); + if ( ! text ) text = href; + ret = ret "" HTML(text) ""; line = substr( line, len + 1); + continue; + + # quick links ("automatic links" in md doc) + } else if ( match( line, /^<[a-zA-Z]+:\/\/([-\.[:alnum:]]+)(:[0-9]*)?(\/[^>]*)?>/ ) ) { + len = RLENGTH; + href = HTML( substr( line, 2, len - 2) ); + ret = ret "" href ""; line = substr( line, len + 1); + continue; + + # quick link email + # } else if ( match( line, /^<[a-zA-Z0-9.!#$%&'\''*+\/=?^_`{|}~-]+@[a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(\.[a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*>/ ) ) { + } else if ( match( line, /^<[a-zA-Z0-9.!#$%&'\''*+\/=?^_`{|}~-]+@([a-zA-Z0-9]\.[a-zA-Z0-9]|[a-zA-Z0-9-])+>/ ) ) { + len = RLENGTH; + href = HTML( substr( line, 2, len - 2) ); + ret = ret "" href ""; line = substr( line, len + 1); + continue; + + # Verbatim inline HTML + } else if ( AllowHTML && match( line, /^(|<\?([^\?]|\?[^>])*\?>|]*>|])*\]\]>|<\/[A-Za-z][A-Za-z0-9-]*[[:space:]]*>|<[A-Za-z][A-Za-z0-9-]*([[:space:]]+[A-Za-z_:][A-Za-z0-9_\.:-]*([[:space:]]*=[[:space:]]*([[:space:]"'=<>`]+|"[^"]*"|'[^']*'))?)*[[:space:]]*\/?>)/) ) { + len = RLENGTH; + ret = ret substr( line, 1, len); line =substr(line, len + 1); + continue; + + # inline links + } else if ( match(line, "^" lii "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)") ) { + len = RLENGTH; + text = href = title = substr( line, 1, len); + sub("^\\[", "", text); sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)$", "", text); + sub("^" lii "\\([\n\t ]*", "", href); sub("([\n\t ]+" lit ")?[\n\t ]*\\)$", "", href); + sub("^" lii "\\([\n\t ]*" lid, "", title); sub("[\n\t ]*\\)$", "", title); sub("^[\n\t ]+", "", title); + + if ( match(href, /^<.*>$/) ) { sub(/^$/, "", href); } + if ( match(title, /^".*"$/) ) { sub(/^"/, "", title); sub(/"$/, "", title); } + else if ( match(title, /^'.*'$/) ) { sub(/^'/, "", title); sub(/'$/, "", title); } + else if ( match(title, /^\(.*\)$/) ) { sub(/^\(/, "", title); sub(/\)$/, "", title); } + + gsub(/\\/, "", href); gsub(/\\/, "", title); gsub(/[\n\t]+/, " ", title); + + ret = ret "" \ + inline( text ) ""; + line = substr( line, len + 1); + continue; + + # reference style links + } else if ( match(line, /^\[([^]]+)\] ?\[([^]]*)\]/ ) ) { + len = RLENGTH; text = id = substr(line, 1, len); + sub(/\n.*$/, "", text); sub(/^\[/, "", text); sub(/\] ?\[([^\n]*)\].*$/, "", text); + sub(/\n.*$/, "", id); sub(/^\[([^]]+)\] ?\[/, "", id); sub(/\].*$/, "", id); + # text = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\1", 1, text ); + # id = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\2", 1, id ); + if ( ! id ) id = text; + + if ( rl_href[id] && rl_title[id] ) { + ret = ret "" inline(text) ""; + line = substr( line, len + 1); + continue; + + } else if ( rl_href[id] ) { + ret = ret "" inline(text) ""; line = substr( line, len + 1); + continue; + + } else { + ret = ret "" HTML(substr(line, 1, len)); line = substr(line, len + 1); + continue; + } - # inline images - } else if ( match(line, "^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?") ) { - len = RLENGTH; text = href = title = attrib = substr( line, 1, len); - - sub("^!\\[", "", text); - sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", text); - - sub("^!" lix "\\([\n\t ]*", "", href); - sub("([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", href); - - sub("^!" lix "\\([\n\t ]*" lid, "", title); - sub("[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", title); - sub("^[\n\t ]+", "", title); - - sub("^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)", "", attrib); - sub(/^\{[ \t]*/, "", attrib); sub(/[ \t]*\}$/, "", attrib); gsub(/[ \t]+/, " ", attrib); - - if ( match(href, /^<.*>$/) ) { sub(/^$/, "", href); } - if ( match(title, /^".*"$/) ) { sub(/^"/, "", title); sub(/"$/, "", title); } - else if ( match(title, /^'.*'$/) ) { sub(/^'/, "", title); sub(/'$/, "", title); } - else if ( match(title, /^\(.*\)$/) ) { sub(/^\(/, "", title); sub(/\)$/, "", title); } - - gsub(/^[\t ]+$/, "", text); gsub(/\\/, "", href); - gsub(/\\/, "", title); gsub(/[\n\t]+/, " ", title); - - return "\""" inline( substr( line, len + 1) ); - - # reference style images - } else if ( match(line, /^!\[([^]]*)\] ?\[([^]]*)\]/ ) ) { - len = RLENGTH; - text = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\].*/, "\\1", 1, substr(line, 1, len) ); - id = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\].*/, "\\2", 1, substr(line, 1, len) ); - if ( ! id ) id = text; - if ( rl_href[id] && rl_title[id] ) { - return "\""" \ - inline( substr( line, len + 1) ); - } else if ( rl_href[id] ) { - return "\""" \ - inline( substr( line, len + 1) ); - } else { - return "" HTML(substr(line, 1, len)) inline( substr(line, len + 1) ); - } + # inline images + } else if ( match(line, "^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?") ) { + len = RLENGTH; text = href = title = attrib = substr( line, 1, len); + + sub("^!\\[", "", text); + sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", text); + + sub("^!" lix "\\([\n\t ]*", "", href); + sub("([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", href); + + sub("^!" lix "\\([\n\t ]*" lid, "", title); + sub("[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", title); + sub("^[\n\t ]+", "", title); + + sub("^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)", "", attrib); + sub(/^\{[ \t]*/, "", attrib); sub(/[ \t]*\}$/, "", attrib); gsub(/[ \t]+/, " ", attrib); + + if ( match(href, /^<.*>$/) ) { sub(/^$/, "", href); } + if ( match(title, /^".*"$/) ) { sub(/^"/, "", title); sub(/"$/, "", title); } + else if ( match(title, /^'.*'$/) ) { sub(/^'/, "", title); sub(/'$/, "", title); } + else if ( match(title, /^\(.*\)$/) ) { sub(/^\(/, "", title); sub(/\)$/, "", title); } + + gsub(/^[\t ]+$/, "", text); gsub(/\\/, "", href); + gsub(/\\/, "", title); gsub(/[\n\t]+/, " ", title); + + ret = ret "\"""; + line = substr( line, len + 1); + continue; + + # reference style images + } else if ( match(line, /^!\[([^]]*)\] ?\[([^]]*)\]/ ) ) { + len = RLENGTH; text = id = substr(line, 1, len); + sub(/\n.*$/, "", text); sub(/^!\[/, "", text); sub(/\] ?\[([^\n]*)\].*$/, "", text); + sub(/\n.*$/, "", id); sub(/^!\[([^]]+)\] ?\[/, "", id); sub(/\].*$/, "", id); + # text = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\].*/, "\\1", 1, substr(line, 1, len) ); + # id = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\].*/, "\\2", 1, substr(line, 1, len) ); + if ( ! id ) id = text; + if ( rl_href[id] && rl_title[id] ) { + ret = ret "\"""; + line = substr( line, len + 1); + continue; + + } else if ( rl_href[id] ) { + ret = ret "\"""; + line = substr( line, len + 1); + continue; + + } else { + ret = ret "" HTML(substr(line, 1, len)); line = substr(line, len + 1); + continue; + } - # ~~strikeout~~ (pandoc) - } else if ( match(line, /^~~([[:graph:]]|[[:graph:]]([^~]|~[^~])*[[:graph:]])~~/) ) { - len = RLENGTH; - return "" inline( substr( line, 3, len - 4 ) ) "" inline( substr( line, len + 1 ) ); - - # ^superscript^ (pandoc) - } else if ( match(line, /^\^([^[:space:]^]|\\[ ^])+\^/) ) { - len = RLENGTH; - return "" inline( substr( line, 2, len - 2 ) ) "" inline( substr( line, len + 1 ) ); - - # ~subscript~ (pandoc) - } else if ( match(line, /^~([^[:space:]~]|\\[ ~])+~/) ) { - len = RLENGTH; - return "" inline( substr( line, 2, len - 2 ) ) "" inline( substr( line, len + 1 ) ); - - # ignore embedded underscores (pandoc, php md) - } else if ( match(line, "^[[:alnum:]](__|_)") ) { - return HTML(substr( line, 1, RLENGTH)) inline( substr(line, RLENGTH + 1) ); - - # __strong__$ - } else if ( match(line, "^__(([^_[:space:]]|" ieu ")|([^_[:space:]]|" ieu ")(" nu "|" ieu ")*([^_[:space:]]|" ieu "))__$") ) { - len = RLENGTH; - return "" inline( substr( line, 3, len - 4 ) ) "" inline( substr( line, len + 1 ) ); - - # __strong__ - } else if ( match(line, "^__(([^_[:space:]]|" ieu ")|([^_[:space:]]|" ieu ")(" nu "|" ieu ")*([^_[:space:]]|" ieu "))__[[:space:][:punct:]]") ) { - len = RLENGTH; - return "" inline( substr( line, 3, len - 5 ) ) "" inline( substr( line, len) ); - - # **strong** - } else if ( match(line, "^\\*\\*(([^\\*[:space:]]|" iea ")|([^\\*[:space:]]|" iea ")(" na "|" iea ")*([^\\*[:space:]]|" iea "))\\*\\*") ) { - len = RLENGTH; - return "" inline( substr( line, 3, len - 4 ) ) "" inline( substr( line, len + 1 ) ); - - # _em_$ - } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_$") ) { - len = RLENGTH; - return "" inline( substr( line, 2, len - 2 ) ) "" inline( substr( line, len + 1 ) ); - - # _em_ - } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_[[:space:][:punct:]]") ) { - len = RLENGTH; - return "" inline( substr( line, 2, len - 3 ) ) "" inline( substr( line, len ) ); - - # *em* - } else if ( match(line, "^\\*(([^\\*[:space:]]|" isa ")|([^\\*[:space:]]|" isa ")(" na "|" isa ")*([^\\*[:space:]]|" isa "))\\*") ) { - len = RLENGTH; - return "" inline( substr( line, 2, len - 2 ) ) "" inline( substr( line, len + 1 ) ); - - # Literal HTML entities - } else if ( match( line, /^&([a-zA-Z]{2,32}|#[0-9]{1,7}|#[xX][0-9a-fA-F]{1,6});/) ) { - len = RLENGTH; - return substr( line, 1, len ) inline(substr(line, len + 1)); - - # Arrows - } else if ( line ~ /^-->( |$)/) { # ignore multidash-arrow - return "-->" inline( substr(line, 4) ); - } else if ( line ~ /^<-( |$)/) { - return "←" inline( substr(line, 3) ); - } else if ( line ~ /^->( |$)/) { - return "→" inline( substr(line, 3) ); - - # Escape lone HTML character - } else if ( match( line, /^[&<>"']/) ) { - return HTML(substr(line, 1, 1)) inline(substr(line, 2)); - - # continue walk over string - } else { - return substr(line, 1, 1) inline( substr(line, 2) ); + # ~~strikeout~~ (pandoc) + } else if ( match(line, /^~~([[:graph:]]|[[:graph:]]([^~]|~[^~])*[[:graph:]])~~/) ) { + len = RLENGTH; + ret = ret "" inline( substr( line, 3, len - 4 ) ) ""; line = substr( line, len + 1 ); + continue; + + # ^superscript^ (pandoc) + } else if ( match(line, /^\^([^[:space:]^]|\\[ ^])+\^/) ) { + len = RLENGTH; + ret = ret "" inline( substr( line, 2, len - 2 ) ) ""; line = substr( line, len + 1 ); + continue; + + # ~subscript~ (pandoc) + } else if ( match(line, /^~([^[:space:]~]|\\[ ~])+~/) ) { + len = RLENGTH; + ret = ret "" inline( substr( line, 2, len - 2 ) ) ""; line = substr( line, len + 1 ); + continue; + + # ignore embedded underscores (pandoc, php md) + } else if ( match(line, "^[[:alnum:]](__|_)") ) { + ret = ret HTML(substr( line, 1, RLENGTH)); line = substr(line, RLENGTH + 1); + continue; + + # strong / em matchers use pre match pattern to make processing cheaper + # __strong__$ + } else if ( match(line, "^__(([^_[:space:]]|" ieu ")|([^_[:space:]]|" ieu ")(" nu "|" ieu ")*([^_[:space:]]|" ieu "))__$") ) { + len = RLENGTH; + ret = ret "" inline( substr( line, 3, len - 4 ) ) ""; line = substr( line, len + 1 ); + continue; + + # __strong__ + } else if ( match(line, "^__(([^_[:space:]]|" ieu ")|([^_[:space:]]|" ieu ")(" nu "|" ieu ")*([^_[:space:]]|" ieu "))__[[:space:][:punct:]]") ) { + len = RLENGTH; + ret = ret "" inline( substr( line, 3, len - 5 ) ) ""; line = substr( line, len); + continue; + + # **strong** + } else if ( match(line, "^\\*\\*(([^*[:space:]]|" iea ")|([^*[:space:]]|" iea ")(" na "|" iea ")*([^*[:space:]]|" iea "))\\*\\*") ) { + len = RLENGTH; + ret = ret "" inline( substr( line, 3, len - 4 ) ) ""; line = substr( line, len + 1 ); + continue; + + # _em_$ + } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_$") ) { + len = RLENGTH; + ret = ret "" inline( substr( line, 2, len - 2 ) ) ""; line = substr( line, len + 1 ); + continue; + + # _em_ + } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_[[:space:][:punct:]]") ) { + len = RLENGTH; + ret = ret "" inline( substr( line, 2, len - 3 ) ) ""; line = substr( line, len ); + continue; + + # *em* + } else if ( match(line, "^\\*(([^*[:space:]]|" isa ")|([^*[:space:]]|" isa ")(" na "|" isa ")*([^*[:space:]]|" isa "))\\*") ) { + len = RLENGTH; + ret = ret "" inline( substr( line, 2, len - 2 ) ) ""; line = substr( line, len + 1 ); + continue; + + # Literal HTML entities + # } else if ( match( line, /^&([a-zA-Z]{2,32}|#[0-9]{1,7}|#[xX][0-9a-fA-F]{1,6});/) ) { + # mawk does not support repitition ranges + } else if ( match( line, /^&[a-zA-Z][a-zA-Z][a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?[a-zA-Z]?;/) ) { + len = RLENGTH; + ret = ret substr( line, 1, len ); line = substr(line, len + 1); + continue; + } else if ( match( line, /^&(#[0-9][0-9]?[0-9]?[0-9]?[0-9]?[0-9]?[0-9]?|#[xX][0-9a-fA-F][0-9a-fA-F]?[0-9a-fA-F]?[0-9a-fA-F]?[0-9a-fA-F]?[0-9a-fA-F]?);/) ) { + len = RLENGTH; + ret = ret substr( line, 1, len ); line = substr(line, len + 1); + continue; + + # Arrows + } else if ( line ~ /^-->( |$)/) { # ignore multidash-arrow + ret = ret "-->"; line = substr(line, 4); + continue; + } else if ( line ~ /^<-( |$)/) { + ret = ret "←"; line = substr(line, 3); + continue; + } else if ( line ~ /^->( |$)/) { + ret = ret "→"; line = substr(line, 3); + continue; + + # Escape lone HTML character + } else if ( match( line, /^[&<>"']/) ) { + ret = ret HTML(substr(line, 1, 1)); line = substr(line, 2); + continue; + + } # inline patterns end + + # continue walk over string + ret = ret substr(line, 1, 1); line = substr(line, 2); } + return ret; } function headline( hlvl, htxt, attrib, LOCAL, sec, n, HL) { - match(hstack, /([0-9]+( [0-9]+){5})$/); split( substr(hstack, RSTART), HL); + # match(hstack, /([0-9]+( [0-9]+){5})$/); split( substr(hstack, RSTART), HL); + match(hstack, /([0-9]+( [0-9]+)( [0-9]+)( [0-9]+)( [0-9]+)( [0-9]+))$/); split( substr(hstack, RSTART), HL); for ( n = hlvl; n <= 6; n++ ) { sec = sec (HL[n]?"":""); } HL[hlvl]++; for ( n = hlvl + 1; n <= 6; n++) { HL[n] = 0;} @@ -336,7 +391,8 @@ function headline( hlvl, htxt, attrib, LOCAL, sec, n, HL) { hid = hid HL[1]; for ( n = 2; n <= hlvl; n++) { hid = hid "." HL[n] ; } hid = hid ":" URL(htxt, 1); - sub(/([0-9]+( [0-9]+){5})$/, "", hstack); + # sub(/([0-9]+( [0-9]+){5})$/, "", hstack); + sub(/([0-9]+( [0-9]+)( [0-9]+)( [0-9]+)( [0-9]+)( [0-9]+))$/, "", hstack); hstack = hstack HL[1] " " HL[2] " " HL[3] " " HL[4] " " HL[5] " " HL[6]; return sec "
" \ @@ -354,406 +410,467 @@ function _nblock( block, LOCAL, sec, n ) { for ( n = blvl + 1; n in BL; n++) { delete BL[n]; } block = _block( block ); - match(hstack, /([0-9]+( [0-9]+){5})$/); split( substr(hstack, RSTART), HL); + match(hstack, /([0-9]+( [0-9]+)( [0-9]+)?( [0-9]+)?( [0-9]+)?( [0-9]+)?)$/); split( substr(hstack, RSTART), HL); sec = ""; for ( n = 1; n <= 6; n++ ) { sec = sec (HL[n]?"
":""); } - sub("( +[0-9]+){6} *$", "", hstack); blvl--; + sub("( +[0-9]+)( +[0-9]+)?( +[0-9]+)?( +[0-9]+)?( +[0-9]+)?( +[0-9]+)? *$", "", hstack); blvl--; return block sec; } -function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, indent, list ) { - gsub( "(^\n+|\n+$)", "", block ); - - if ( block == "" ) { - return ""; - - # HTML #2 #3 #4 $5 - } else if ( AllowHTML && match( block, /(^|\n) ? ? ?(|$)|<\?([^\?]|\?[^>])*(\?>|$)|]*(>|$)|])*(\]\]>|$))/) ) { - len = RLENGTH; st = RSTART; - return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len)); - - # HTML #6 - } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<\/?(address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset|h[123456]|head|header|hr|html|iframe|legend|li|link|main|menu|menuitem|nav|noframes|ol|optgroup|option|p|param|section|source|summary|table|tbody|td|tfoot|th|thead|title|tr|track|ul)([[:space:]\n>]|\/>)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) { - len = RLENGTH; st = RSTART; - return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len)); - - # HTML #1 - } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<(script|pre|style)([[:space:]\n>]).*(<\/script>|<\/pre>|<\/style>|$)/) ) { - len = RLENGTH; st = RSTART; - match( tolower(substr(block, st, len)), /(<\/script>|<\/pre>|<\/style>)/); - len = RSTART + RLENGTH; - return _block(substr(block, 1, st - 1)) substr(block, st, len) _block(substr(block, st + len)); - - # HTML #7 - } else if ( AllowHTML && match( block, /^ ? ? ?(<\/[A-Za-z][A-Za-z0-9-]*[[:space:]]*>|<[A-Za-z][A-Za-z0-9-]*([[:space:]]+[A-Za-z_:][A-Za-z0-9_\.:-]*([[:space:]]*=[[:space:]]*([[:space:]"'=<>`]+|"[^"]*"|'[^']*'))?)*[[:space:]]*\/?>)([[:space:]]*\n)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) { - len = RLENGTH; st = RSTART; - return substr(block, st, len) _block(substr(block, st + len)); - - # Metadata (custom, block starting with %something) - # Metadata is ignored but can be interpreted externally - } else if ( match(block, /^%[a-zA-Z]+([[:space:]][^\n]*)?(\n|$)(%[a-zA-Z]+([[:space:]][^\n]*)?(\n|$)|%([[:space:]][^\n]*)?(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) { - len = RLENGTH; st = RSTART; - return _block( substr( block, len + 1) ); - - # Blockquote (leading >) - } else if ( match( block, /^> /) ) { - match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match(block, /$/); - len = RLENGTH; st = RSTART; - text = substr(block, 1, st - 1); gsub( /(^|\n)> /, "\n", text ); - text = _nblock( text ); gsub( /^\n|\n$/, "", text ) - return "
" text "
\n\n" _block( substr(block, st + len) ); - - # Pipe Tables (pandoc / php md / gfm ) - } else if ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?)\n" \ - "((\\|)?(:?-+:?[\\|+])+:?-+:?(\\|)?)\n" \ - "((\\|)?([^\n]+\\|)+[^\n]+(\\|)?(\n|$))+" ) ) { - len = RLENGTH; st = RSTART; - #initialize empty arrays - split("", talign); split("", tarray); - cols = 0; cnt=0; ttext = ""; - - # table header and alignment - split( gensub( /(^\||\|$)/, "", "g", \ - gensub( /(^|[^\\])\\\|/, "\\1\\|", "g", \ - substr(block, 1, match(block, /(\n|$)/)) \ - )), tarray, /\|/); - block = substr(block, match(block, /(\n|$)/) + 1 ); - cols = split( \ - gensub( /(^\||\|$)/, "", "g", \ - substr(block, 1, match(block, /(\n|$)/)) \ - ), talign, /[+\|]/); - block = substr(block, match(block, /(\n|$)/) + 1 ); - - for( cnt = 1; cnt < cols; cnt++ ) { - if (match(talign[cnt], /:-+:/)) talign[cnt]="center"; - else if (match(talign[cnt], /-+:/)) talign[cnt]="right"; - else if (match(talign[cnt], /:-+/)) talign[cnt]="left"; - else talign[cnt]=""; - } +function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, indent, list, tmp, ret) { + ret = ""; + while ( block != "" ) { + gsub( "(^\n+|\n+$)", "", block ); - ttext = "\n" - for (cnt = 1; cnt < cols; cnt++) - ttext = ttext "" inline(tarray[cnt]) "" - ttext = ttext "\n\n" + # HTML #2 #3 #4 $5 + if ( AllowHTML && match( block, /(^|\n) ? ? ?(|$)|<\?([^\?]|\?[^>])*(\?>|$)|]*(>|$)|])*(\]\]>|$))/) ) { + len = RLENGTH; st = RSTART; + ret = ret _block(substr(block, 1, st - 1)) substr(block, st, len); block = substr(block, st + len); + continue; - while ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?(\n|$))+" ) ){ - split( gensub( /(^\||\|$)/, "", "g", \ - gensub( /(^|[^\\])\\\|/, "\\1\\|", "g", \ - substr(block, 1, match(block, /(\n|$)/)) \ - )), tarray, /\|/); - block = substr(block, match(block, /(\n|$)/) + 1 ); + # HTML #6 (part1) + } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<\/?(address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset)([[:space:]\n>]|\/>)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) { + len = RLENGTH; st = RSTART; + ret = ret _block(substr(block, 1, st - 1)) substr(block, st, len); block = substr(block, st + len); + continue; - ttext = ttext "" - for (cnt = 1; cnt < cols; cnt++) - ttext = ttext "" inline(tarray[cnt]) "" - ttext = ttext "\n" - } - return "" ttext "
\n" _block(block); - - # Grid Tables (pandoc) - # (with, and without header) - } else if ( match( block, "^\\+(-+\\+)+\n" \ - "(\\|([^\n]+\\|)+\n)+" \ - "(\\+(:?=+:?\\+)+)\n" \ - "((\\|([^\n]+\\|)+\n)+" \ - "\\+(-+\\+)+(\n|$))+" \ - ) || \ - match( block, "^()()()" \ - "(\\+(:?-+:?\\+)+)\n" \ - "((\\|([^\n]+\\|)+\n)+" \ - "\\+(-+\\+)+(\n|$))+" \ - ) ) { - len = RLENGTH; st = RSTART; - #initialize empty arrays - split("", talign); split("", tarray); split("", tread); - cols = 0; cnt=0; ttext = ""; - - # Column Count - cols = split( gensub( "^(\\+(:?-+:?\\+)+)(\n.*)*$", "\\1", 1, block), tread, /\+/) - 2; - # debug(" Cols: " gensub( "^(\\+(:?-+:?\\+)+)(\n.*)*$", "\\1", 1, block )); - - # table alignment - split( gensub( "^(.*\n)?\\+((:?=+:?\\+|(:-+|-+:|:-+:)\\+)+)(\n.*)$", "\\2", "g", block ), talign, /\+/ ); - # debug("Align: " gensub( "^(.*\n)?\\+((:?=+:?\\+|(:-+|-+:|:-+:)\\+)+)(\n.*)$", "\\2", "g", block )); - - for (cnt = 1; cnt <= cols; cnt++) { - if (match(talign[cnt], /:(-+|=+):/)) talign[cnt]="center"; - else if (match(talign[cnt], /(-+|=+):/)) talign[cnt]="right"; - else if (match(talign[cnt], /:(-+|=+)/ )) talign[cnt]="left"; - else talign[cnt]=""; - } + # HTML #6 (part2) + } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<\/?(h[123456]|head|header|hr|html|iframe|legend|li|link|main|menu|menuitem|nav|noframes|ol|optgroup|option|p|param|section|source|summary|table|tbody|td|tfoot|th|thead|title|tr|track|ul)([[:space:]\n>]|\/>)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) { + len = RLENGTH; st = RSTART; + ret = ret _block(substr(block, 1, st - 1)) substr(block, st, len); block = substr(block, st + len); + continue; - if ( match(block, "^\\+(-+\\+)+\n" \ - "(\\|([^\n]+\\|)+\n)+" \ - "\\+(:?=+:?\\+)+\n" \ - "((\\|([^\n]+\\|)+\n)+" \ - "\\+(-+\\+)+(\n|$))+" \ - ) ) { - # table header + # HTML #1 + } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<(script|pre|style)([[:space:]\n>]).*(<\/script>|<\/pre>|<\/style>|$)/) ) { + len = RLENGTH; st = RSTART; + match( tolower(substr(block, st, len)), /(<\/script>|<\/pre>|<\/style>)/); + len = RSTART + RLENGTH; + ret = ret _block(substr(block, 1, st - 1)) substr(block, st, len); block = substr(block, st + len); + continue; + + # HTML #7 + } else if ( AllowHTML && match( block, /^ ? ? ?(<\/[A-Za-z][A-Za-z0-9-]*[[:space:]]*>|<[A-Za-z][A-Za-z0-9-]*([[:space:]]+[A-Za-z_:][A-Za-z0-9_\.:-]*([[:space:]]*=[[:space:]]*([[:space:]"'=<>`]+|"[^"]*"|'[^']*'))?)*[[:space:]]*\/?>)([[:space:]]*\n)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) { + len = RLENGTH; st = RSTART; + ret = ret substr(block, st, len); block = substr(block, st + len); + continue; + + # Metadata (custom, block starting with %something) + # Metadata is ignored but can be interpreted externally + } else if ( match(block, /^%[a-zA-Z-]+([[:space:]][^\n]*)?(\n|$)(%[a-zA-Z-]+([[:space:]][^\n]*)?(\n|$)|%([[:space:]][^\n]*)?(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) { + len = RLENGTH; st = RSTART; + block = substr( block, len + 1); + continue; + + # Blockquote (leading >) + } else if ( match( block, /^> /) ) { + match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match(block, /$/); + len = RLENGTH; st = RSTART; + text = substr(block, 1, st - 1); gsub( /(^|\n)> /, "\n", text ); + text = _nblock( text ); gsub( /^\n|\n$/, "", text ) + ret = ret "
" text "
\n\n"; block = substr(block, st + len); + continue; + + # Pipe Tables (pandoc / php md / gfm ) + } else if ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?)\n" \ + "((\\|)?(:?-+:?[\\|+])+:?-+:?(\\|)?)\n" \ + "((\\|)?([^\n]+\\|)+[^\n]+(\\|)?(\n|$))+" ) ) { + len = RLENGTH; st = RSTART; + #initialize empty arrays + split("", talign); split("", tarray); + cols = 0; cnt=0; ttext = ""; + + # table header and alignment + tmp = substr(block, 1, match(block, /(\n|$)/)); + gsub( /(^|[^\\])\\\|/, "\\1\\|", tmp ); + gsub( /(^\||\|$)/, "", tmp) + split( tmp, tarray, /\|/); block = substr(block, match(block, /(\n|$)/) + 1 ); - while ( match(block, "^\\|([^\n]+\\|)+\n") ) { - split( gensub( /(^\||\|$)/, "", "g", \ - gensub( /(^|[^\\])\\\|/, "\\1\\|", "g", \ - substr(block, 1, match(block, /(\n|$)/)) \ - )), tread, /\|/); - block = substr(block, match(block, /(\n|$)/) + 1 ); - for (cnt = 1; cnt <= cols; cnt++) - tarray[cnt] = tarray[cnt] "\n" tread[cnt]; + tmp = substr(block, 1, match(block, /(\n|$)/)); + gsub( /(^\||\|$)/, "", tmp ); + cols = split( tmp , talign, /[+\|]/); + block = substr(block, match(block, /(\n|$)/) + 1 ); + + for( cnt = 1; cnt < cols; cnt++ ) { + if (match(talign[cnt], /:-+:/)) talign[cnt]="center"; + else if (match(talign[cnt], /-+:/)) talign[cnt]="right"; + else if (match(talign[cnt], /:-+/)) talign[cnt]="left"; + else talign[cnt]=""; } ttext = "\n" - for (cnt = 1; cnt <= cols; cnt++) - ttext = ttext "" _nblock(tarray[cnt]) "" - ttext = ttext "\n" - } + for (cnt = 1; cnt < cols; cnt++) + ttext = ttext "" inline(tarray[cnt]) "" + ttext = ttext "\n\n" + + while ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?(\n|$))+" ) ){ + tmp = substr(block, 1, match(block, /(\n|$)/)); + gsub( /(^|[^\\])\\\|/, "\\1\\|", tmp ); + gsub( /(^\||\|$)/, "", tmp ); + split( tmp, tarray, /\|/); + block = substr(block, match(block, /(\n|$)/) + 1 ); - # table body - block = substr(block, match(block, /(\n|$)/) + 1 ); - ttext = ttext "\n" - - while ( match(block, /^((\|([^\n]+\|)+\n)+\+(-+\+)+(\n|$))+/ ) ){ - split("", tarray); - while ( match(block, /^\|([^\n]+\|)+\n/) ) { - split( gensub( /(^\||\|$)/, "", "g", \ - gensub( /(^|[^\\])\\\|/, "\\1\\|", "g", \ - substr(block, 1, match(block, /(\n|$)/)) \ - )), tread, /\|/); + ttext = ttext "" + for (cnt = 1; cnt < cols; cnt++) + ttext = ttext "" inline(tarray[cnt]) "" + ttext = ttext "\n" + } + ret = ret "" ttext "
\n"; + continue; + + # Grid Tables (pandoc) + # (with, and without header) + } else if ( match( block, "^\\+(-+\\+)+\n" \ + "(\\|([^\n]+\\|)+\n)+" \ + "(\\+(:?=+:?\\+)+)\n" \ + "((\\|([^\n]+\\|)+\n)+" \ + "\\+(-+\\+)+(\n|$))+" \ + ) || \ + match( block, "^(\\+(:?-+:?\\+)+)\n" \ + "((\\|([^\n]+\\|)+\n)+" \ + "\\+(-+\\+)+(\n|$))+" \ + ) ) { + len = RLENGTH; st = RSTART; + #initialize empty arrays + split("", talign); split("", tarray); split("", tread); + cols = 0; cnt=0; ttext = ""; + + # Column Count + tmp = block; sub( "(\n.*)*$", "", tmp); + cols = split( tmp, tread, /\+/) - 2; + # debug(" Cols: " gensub( "^(\\+(:?-+:?\\+)+)(\n.*)*$", "\\1", 1, block )); + + # table alignment + match(block, "((:?=+:?\\+|(:-+|-+:|:-+:)\\+)+)"); + split( substr(block, RSTART, RLENGTH) , talign, /\+/ ); + # split( gensub( "^(.*\n)?\\+((:?=+:?\\+|(:-+|-+:|:-+:)\\+)+)(\n.*)$", "\\2", "g", block ), talign, /\+/ ); + # debug("Align: " gensub( "^(.*\n)?\\+((:?=+:?\\+|(:-+|-+:|:-+:)\\+)+)(\n.*)$", "\\2", "g", block )); + + for (cnt = 1; cnt <= cols; cnt++) { + if (match(talign[cnt], /:(-+|=+):/)) talign[cnt]="center"; + else if (match(talign[cnt], /(-+|=+):/)) talign[cnt]="right"; + else if (match(talign[cnt], /:(-+|=+)/ )) talign[cnt]="left"; + else talign[cnt]=""; + } + + if ( match(block, "^\\+(-+\\+)+\n" \ + "(\\|([^\n]+\\|)+\n)+" \ + "\\+(:?=+:?\\+)+\n" \ + "((\\|([^\n]+\\|)+\n)+" \ + "\\+(-+\\+)+(\n|$))+" \ + ) ) { + # table header block = substr(block, match(block, /(\n|$)/) + 1 ); + while ( match(block, "^\\|([^\n]+\\|)+\n") ) { + tmp = substr(block, 1, match(block, /(\n|$)/)); + gsub( /\\\\/, "\\\", tmp); gsub(/\\\|/, "\\|", tmp); + gsub( /(^\||\|$)/, "", tmp ); + split(tmp, tread, /\|/); + block = substr(block, match(block, /(\n|$)/) + 1 ); + for (cnt = 1; cnt <= cols; cnt++) + tarray[cnt] = tarray[cnt] "\n" tread[cnt]; + } + + ttext = "\n" for (cnt = 1; cnt <= cols; cnt++) - tarray[cnt] = tarray[cnt] "\n" tread[cnt]; + ttext = ttext "" _nblock(tarray[cnt]) "" + ttext = ttext "\n" } + + # table body block = substr(block, match(block, /(\n|$)/) + 1 ); + ttext = ttext "\n" + + while ( match(block, /^((\|([^\n]+\|)+\n)+\+(-+\+)+(\n|$))+/ ) ){ + split("", tarray); + while ( match(block, /^\|([^\n]+\|)+\n/) ) { + tmp = substr(block, 1, match(block, /(\n|$)/)); + gsub( /\\\\/, "\\\", tmp); gsub(/\\\|/, "\\|", tmp); + gsub( /(^\||\|$)/, "", tmp); + split( tmp, tread, /\|/); + block = substr(block, match(block, /(\n|$)/) + 1 ); + for (cnt = 1; cnt <= cols; cnt++) + tarray[cnt] = tarray[cnt] "\n" tread[cnt]; + } + block = substr(block, match(block, /(\n|$)/) + 1 ); - ttext = ttext "" - for (cnt = 1; cnt <= cols; cnt++) - ttext = ttext "" _nblock(tarray[cnt]) "" - ttext = ttext "\n" - } - return "" ttext "
\n" _nblock(block); - - # Line Blocks (pandoc) - } else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\n]*(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) { - len = RLENGTH; st = RSTART; - - text = substr(block, 1, len); gsub(/\n[[:space:]]+/, " ", text); - gsub(/\n\| /, "\n", text); gsub(/^\| |\n$/, "", text); - text = inline(text); gsub(/\n/, "
\n", text); - - return "
" text "
\n" _block( substr( block, len + 1) ); - - # Indented Code Block - } else if ( match(block, /^( |\t)( *\t*[^ \t\n]+ *\t*)+(\n|$)(( |\t)[^\n]+(\n|$)|[ \t]*(\n|$))*/) ) { - len = RLENGTH; st = RSTART; - code = substr(block, 1, len); - gsub(/(^|\n)( |\t)/, "\n", code); - gsub(/^\n|\n+$/, "", code); - return "
" HTML( code ) "
\n" \ - _block( substr( block, len + 1 ) ); - - # Fenced Divs (pandoc, custom) - } else if ( match( block, /^(:::+)/ ) ) { - guard = substr( block, 1, RLENGTH ); - code = block; sub(/^[^\n]+\n/, "", code); - attrib = gensub(/^:::+[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\1", 1, block); - gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); - gsub(/(^ | $)/, "", attrib); - if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) { - len = RLENGTH; st = RSTART; - return "
" _nblock( substr(code, 1, st - 1) ) "
\n" \ - _block( substr( code, st + len ) ); - } else { - match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ ); - len = RLENGTH; st = RSTART; - return "

" inline( substr(block, 1, st - 1) ) "

\n" \ - _block( substr(block, st + len) ); - } + ttext = ttext "" + for (cnt = 1; cnt <= cols; cnt++) + ttext = ttext "" _nblock(tarray[cnt]) "" + ttext = ttext "\n" + } + return ret "" ttext "
\n" _nblock(block); - # Fenced Code Block (pandoc) - } else if ( match( block, /^(~~~+|```+)/ ) ) { - guard = substr( block, 1, RLENGTH ); - code = gensub(/^[^\n]+\n/, "", 1, block); - attrib = gensub(/^(~~~+|```+)[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\2", 1, block); - gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); - gsub(/(^ | $)/, "", attrib); - if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) { - len = RLENGTH; st = RSTART; - return "
" HTML( substr(code, 1, st - 1) ) "
\n" \ - _block( substr( code, st + len ) ); - } else { - match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ ); + # Line Blocks (pandoc) + } else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\n]*(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) { len = RLENGTH; st = RSTART; - return "

" inline( substr(block, 1, st - 1) ) "

\n" \ - _block( substr(block, st + len) ); - } - # First Order Heading H1 + Attrib - } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n===+(\n|$)/ ) ) { - len = RLENGTH; text = attrib = block; - sub(/([ \t]*\{([^\}\n]+)\})\n===+(\n.*)?$/, "", text); - sub(/\}\n===+(\n.*)?$/, "", attrib); sub(/^([^\n]+)[ \t]*\{/, "", attrib); - gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib); + text = substr(block, 1, len); gsub(/\n[[:space:]]+/, " ", text); + gsub(/\n\| /, "\n", text); gsub(/^\| |\n$/, "", text); + text = inline(text); gsub(/\n/, "
\n", text); - return headline(1, text, attrib) _block( substr( block, len + 1 ) ); + ret = ret "
" text "
\n"; block = substr( block, len + 1); + continue; - # First Order Heading H1 - } else if ( match( block, /^([^\n]+)\n===+(\n|$)/ ) ) { - len = RLENGTH; text = substr(block, 1, len); - sub(/\n===+(\n.*)?$/, "", text); - - return headline(1, text, 0) _block( substr( block, len + 1 ) ); - - # Second Order Heading H2 + Attrib - } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n---+(\n|$)/ ) ) { - len = RLENGTH; text = attrib = block; - sub(/([ \t]*\{([^\}\n]+)\})\n---+(\n.*)?$/, "", text); - sub(/\}\n---+(\n.*)?$/, "", attrib); sub(/^([^\n]+)[ \t]*\{/, "", attrib); - gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib); - - return headline(2, text, attrib) _block( substr( block, len + 1) ); + # Indented Code Block + } else if ( match(block, /^(( |\t)[^\n]*[^\n\t ][^\n]*(\n|$))(( |\t)[^\n]*(\n|$)|[\t ]*(\n|$))*/) ) { + len = RLENGTH; st = RSTART; - # Second Order Heading H2 - } else if ( match( block, /^([^\n]+)\n---+(\n|$)/ ) ) { - len = RLENGTH; text = substr(block, 1, len); - sub(/\n---+(\n.*)?$/, "", text); + code = substr(block, 1, len); + gsub(/(^|\n)( |\t)/, "\n", code); + gsub(/^\n|\n+$/, "", code); + ret = ret "
" HTML( code ) "
\n"; block = substr( block, len + 1 ); + continue; + + # Fenced Divs (pandoc, custom) + } else if ( match( block, /^(:::+)/ ) ) { + guard = substr( block, 1, RLENGTH ); attrib = code = block; + sub(/^[^\n]+\n/, "", code); + sub(/^:::+[ \t]*\{?[ \t]*/, "", attrib); sub(/\}?[ \t]*\n.*$/, "", attrib); + # attrib = gensub(/^:::+[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\1", 1, attrib); + gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); + gsub(/(^ | $)/, "", attrib); + if ( match(code, "(^|\n)" guard "+(\n|$)" ) && attrib ) { + len = RLENGTH; st = RSTART; + ret = ret "
" _nblock( substr(code, 1, st - 1) ) "
\n"; + block = substr( code, st + len ); + continue; + + } else if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) { + len = RLENGTH; st = RSTART; + ret = ret "
" _nblock( substr(code, 1, st - 1) ) "
\n"; block = substr( code, st + len ); + continue; + + } else { + match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ ); + len = RLENGTH; st = RSTART; + ret = ret "

" inline( substr(block, 1, st - 1) ) "

\n"; block = substr(block, st + len); + continue; + } - return headline(2, text, 0) _block( substr( block, len + 1) ); + # Fenced Code Block (pandoc) + } else if ( match( block, /^(~~~+|```+)/ ) ) { + guard = substr( block, 1, RLENGTH ); attrib = code = block; + sub(/^[^\n]+\n/, "", code); + sub(/^(~~~+|```+)[ \t]*\{?[ \t]*/, "", attrib); sub(/\}?[ \t]*\n.*$/, "", attrib); + # attrib = gensub(/^(~~~+|```+)[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\2", 1, attrib); + gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); + gsub(/(^ | $)/, "", attrib); + if ( match(code, "(^|\n)" guard "+(\n|$)" ) && attrib ) { + len = RLENGTH; st = RSTART; + ret = ret "
" HTML( substr(code, 1, st - 1) ) "
\n"; + block = substr( code, st + len ); + continue; + + } else if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) { + len = RLENGTH; st = RSTART; + ret = ret "
" HTML( substr(code, 1, st - 1) ) "
\n"; + block = substr( code, st + len ); + continue; + + } else { + match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ ); + len = RLENGTH; st = RSTART; + ret = ret "

" inline( substr(block, 1, st - 1) ) "

\n"; block = substr(block, st + len); + continue; + } - # Nth Order Heading H1 H2 H3 H4 H5 H6 + Attrib - } else if ( match( block, /^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n|$)/ ) ) { - len = RLENGTH; text = attrib = substr(block, 1, len); - match(block, /^#{1,6}/); n = RLENGTH; + # First Order Heading H1 + Attrib + } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n===+(\n|$)/ ) ) { + len = RLENGTH; text = attrib = block; + sub(/([ \t]*\{([^\}\n]+)\})\n===+(\n.*)?$/, "", text); + sub(/\}\n===+(\n.*)?$/, "", attrib); sub(/^([^\n]+)[ \t]*\{/, "", attrib); + gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib); + + ret = ret headline(1, text, attrib) ; block = substr( block, len + 1 ); + continue; + + # First Order Heading H1 + } else if ( match( block, /^([^\n]+)\n===+(\n|$)/ ) ) { + len = RLENGTH; text = substr(block, 1, len); + sub(/\n===+(\n.*)?$/, "", text); + + ret = ret headline(1, text, 0) ; block = substr( block, len + 1 ); + continue; + + # Second Order Heading H2 + Attrib + } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n---+(\n|$)/ ) ) { + len = RLENGTH; text = attrib = block; + sub(/([ \t]*\{([^\}\n]+)\})\n---+(\n.*)?$/, "", text); + sub(/\}\n---+(\n.*)?$/, "", attrib); sub(/^([^\n]+)[ \t]*\{/, "", attrib); + gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib); + + ret = ret headline(2, text, attrib) ; block = substr( block, len + 1); + continue; + + # Second Order Heading H2 + } else if ( match( block, /^([^\n]+)\n---+(\n|$)/ ) ) { + len = RLENGTH; text = substr(block, 1, len); + sub(/\n---+(\n.*)?$/, "", text); + + ret = ret headline(2, text, 0) ; block = substr( block, len + 1); + continue; + + # # Nth Order Heading H1 H2 H3 H4 H5 H6 + Attrib + # } else if ( match( block, /^(##?#?#?#?#?)[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*[ \t]*\{[a-zA-Z \t-]*\}(\n|$)/ ) ) { + } else if ( match( block, /^##?#?#?#?#?[^#\n]([^\n#]|#[^\t\n# ]|#[\t ]+[^\t\n ])+#*[\t ]*\{[\ta-zA-Z -]*\}(\n|$)/ ) ) { + len = RLENGTH; text = attrib = substr(block, 1, len); + match(block, /^##?#?#?#?#?[^#]/); n = RLENGTH - 1; + # sub(/^(##?#?#?#?#?)[ \t]*/, "", text); # not working in mawk + text = substr(text, n + 1); sub(/^[ \t]*/, "", text); + sub(/[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n.*)?$/, "", text); + + sub(/^##?#?#?#?#?[^#\n]([^\n#]|#[^\t\n# ]|#[\t ]+[^\t\n ])+#*[\t ]*\{/, "", attrib); + sub(/\}(\n.*)?$/, "", attrib); + gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib); + + ret = ret headline( n, text, attrib ); block = substr( block, len + 1); + continue; + + # Nth Order Heading H1 H2 H3 H4 H5 H6 + # } else if ( match( block, /^(##?#?#?#?#?)[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*(\n|$)/ ) ) { + } else if ( match( block, /^##?#?#?#?#?[^#\n]([^\n#]|#[^\t\n# ]|#[\t ]+[^\t\n ])+#*(\n|$)/ ) ) { + len = RLENGTH; text = substr(block, 1, len); + match(block, /^##?#?#?#?#?[^#]/); n = RLENGTH - 1; + # sub(/^(##?#?#?#?#?)[ \t]+/, "", text); # not working in mawk + text = substr(text, n + 1); sub(/^[ \t]*/, "", text); + sub(/[ \t]*#*(\n.*)?$/, "", text); + + ret = ret headline( n, text, 0 ) ; block = substr( block, len + 1); + continue; + + # block images (wrapped in
) + } else if ( match(block, "^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n|$)") ) { + len = RLENGTH; text = href = title = attrib = substr( block, 1, len); + + sub("^!\\[", "", text); + sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", text); + + sub("^!" lix "\\([\n\t ]*", "", href); + sub("([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", href); + + sub("^!" lix "\\([\n\t ]*" lid, "", title); + sub("[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", title); + sub("^[\n\t ]+", "", title); + + sub("^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)", "", attrib); + sub("(\n.*)?$", "", attrib); + sub(/^\{[ \t]*/, "", attrib); sub(/[ \t]*\}$/, "", attrib); gsub(/[ \t]+/, " ", attrib); + + if ( match(href, /^<.*>$/) ) { sub(/^$/, "", href); } + if ( match(title, /^".*"$/) ) { sub(/^"/, "", title); sub(/"$/, "", title); } + else if ( match(title, /^'.*'$/) ) { sub(/^'/, "", title); sub(/'$/, "", title); } + else if ( match(title, /^\(.*\)$/) ) { sub(/^\(/, "", title); sub(/\)$/, "", title); } + + gsub(/^[\t ]+$/, "", text); gsub(/\\/, "", href); + + ret = ret "
" \ + "\""" \ + (title?"
" inline(title) "
":"") \ + "
\n\n"; + block = substr( block, len + 1); + continue; + + } else if ( match(block, /^!\[([^]]*)\] ?\[([^]]*)\](\n|$)/ ) ) { + len = RLENGTH; text = id = block; + sub(/(\n.*)?$/, "", text); sub( /^!\[/, "", text); sub(/\] ?\[([^\n]*)\]$/, "", text); + sub(/(\n.*)?$/, "", id); sub( /^!\[([^\n]*)\] ?\[/, "", id); sub(/\]$/, "", id); + # text = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\](\n.*)?$/, "\\1", 1, block); + # id = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\](\n.*)?$/, "\\2", 1, block); + if ( ! id ) id = text; + if ( rl_href[id] && rl_title[id] ) { + ret = ret "
" \ + "\""" \ + "
" inline(rl_title[id]) "
" \ + "
\n\n"; + block = substr( block, len + 1); + continue; + + } else if ( rl_href[id] ) { + ret = ret "
" \ + "\""" \ + "
\n\n"; + block = substr( block, len + 1); + continue; + } else { + ret = ret "

" HTML(substr(block, 1, len)) "

\n" ; block = substr(block, len + 1); + continue; + } - sub(/^(#{1,6})[ \t]*/, "", text); sub(/[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n.*)?$/, "", text); - sub(/^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*[ \t]*\{/, "", attrib); - sub(/\})(\n.*)?$/, "", attrib); - gsub(/[^a-zA-Z0-9_-]+/, " ", attrib); gsub(/(^ | $)/, "", attrib); + # Macros (standalone <> calls handled as block, so they are not wrapped in paragraph) + } else if ( match( block, /^<<(([^>]|>[^>])+)>>(\n|$)/ ) ) { + len = RLENGTH; text = block; + sub(/^<>(\n.*)?$/, "", text); + # text = gensub(/^<<(([^>]|>[^>])+)>>(\n.*)?$/, "\\1", 1, block); + ret = ret "" HTML(text) "" ; block = substr(block, len + 1); + continue; + + # Definition list + } else if (match( block, "^(([ \t]*\n)*[^:\n \t][^\n]+\n" \ + "([ \t]*\n)* ? ? ?:[ \t][^\n]+(\n|$)" \ + "(([ \t]*\n)* ? ? ?:[ \t][^\n]+(\n|$)" \ + "|[^:\n \t][^\n]+(\n|$)" \ + "|( ? ? ?\t| +)[^\n]+(\n|$)" \ + "|([ \t]*\n)+( ? ? ?\t| +)[^\n]+(\n|$))*)+" \ + )) { + list = substr( block, 1, RLENGTH); block = substr( block, RLENGTH + 1); + ret = ret "
\n" _dlist( list ) "
\n"; + continue; + + # Unordered list types + } else if ( text = _startlist( block, "ul", "-", "([+*•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { + return ret text; + } else if ( text = _startlist( block, "ul", "\\+", "([-*•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { + return ret text; + } else if ( text = _startlist( block, "ul", "\\*", "([-+•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { + return ret text; + } else if ( text = _startlist( block, "ul", "•", "([-+*]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { + return ret text; + + # Ordered list types + } else if ( text = _startlist( block, "ol", "[0-9]+\\.", "([-+*•]|#\\.|[0-9]+\\)|#\\))") ) { + return ret text; + } else if ( text = _startlist( block, "ol", "[0-9]+\\)", "([-+*•]|[0-9]+\\.|#\\.|#\\))") ) { + return ret text; + } else if ( text = _startlist( block, "ol", "#\\.", "([-+*•]|[0-9]+\\.|[0-9]+\\)|#\\))") ) { + return ret text; + } else if ( text = _startlist( block, "ol", "#\\)", "([-+*•]|[0-9]+\\.|#\\.|[0-9]+\\))") ) { + return ret text; + + # Split paragraphs + } else if ( match( block, /(^|\n)[[:space:]]*(\n|$)/) ) { + len = RLENGTH; st = RSTART; + ret = ret _block( substr(block, 1, st - 1) ) "\n"; block = substr(block, st + len); + continue; - return headline( n, text, attrib ) _block( substr( block, len + 1) ); + # Horizontal rule + # } else if ( match( block, /(^|\n) ? ? ?((\* *){3,}|(- *){3,}|(_ *){3,})($|\n)/) ) { + } else if ( match( block, /(^|\n) ? ? ?((\* *)(\* *)(\* *)(\* *)*|(- *)(- *)(- *)(- *)*|(_ *)(_ *)(_ *)(_ *)*)($|\n)/) ) { + len = RLENGTH; st = RSTART; + ret = ret _block(substr(block, 1, st - 1)) "
\n"; block = substr(block, st + len); + continue; - # Nth Order Heading H1 H2 H3 H4 H5 H6 - } else if ( match( block, /^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*(\n|$)/ ) ) { - len = RLENGTH; text = substr(block, 1, len); - match(block, /^#{1,6}/); n = RLENGTH; - sub(/^(#{1,6})[ \t]*/, "", text); sub(/[ \t]*#*(\n.*)?$/, "", text); - - return headline( n, text, 0 ) _block( substr( block, len + 1) ); - - # block images (wrapped in
) - } else if ( match(block, "^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n|$)") ) { - len = RLENGTH; text = href = title = attrib = substr( block, 1, len); - - sub("^!\\[", "", text); - sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", text); - - sub("^!" lix "\\([\n\t ]*", "", href); - sub("([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", href); - - sub("^!" lix "\\([\n\t ]*" lid, "", title); - sub("[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", title); - sub("^[\n\t ]+", "", title); - - sub("^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)", "", attrib); - sub("(\n.*)?$", "", attrib); - sub(/^\{[ \t]*/, "", attrib); sub(/[ \t]*\}$/, "", attrib); gsub(/[ \t]+/, " ", attrib); - - if ( match(href, /^<.*>$/) ) { sub(/^$/, "", href); } - if ( match(title, /^".*"$/) ) { sub(/^"/, "", title); sub(/"$/, "", title); } - else if ( match(title, /^'.*'$/) ) { sub(/^'/, "", title); sub(/'$/, "", title); } - else if ( match(title, /^\(.*\)$/) ) { sub(/^\(/, "", title); sub(/\)$/, "", title); } - - gsub(/^[\t ]+$/, "", text); gsub(/\\/, "", href); - - return "
" \ - "\""" \ - (title?"
" inline(title) "
":"") \ - "
\n\n" \ - _block( substr( block, len + 1) ); - - # reference style images (block) - } else if ( match(line, /^!\[([^]]*)\] ?\[([^]]*)\](\n|$)/ ) ) { - len = RLENGTH; - text = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\](\n.*)?$/, "\\1", 1, block); - id = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\](\n.*)?$/, "\\2", 1, block); - if ( ! id ) id = text; - if ( rl_href[id] && rl_title[id] ) { - return "
" \ - "\""" \ - "
" inline(rl_title[id]) "
" \ - "
\n\n" \ - _block( substr( block, len + 1) ); - } else if ( rl_href[id] ) { - return "
" \ - "\""" \ - "
\n\n" \ - _block( substr( block, len + 1) ); - } else { - return "

" HTML(substr(block, 1, len)) "

\n" _block( substr(block, len + 1) ); - } + } # block patterns end - # Macros (standalone <> calls handled as block, so they are not wrapped in paragraph) - } else if ( match( block, /^<<(([^>]|>[^>])+)>>(\n|$)/ ) ) { - len = RLENGTH; - text = gensub(/^<<(([^>]|>[^>])+)>>(\n.*)?$/, "\\1", 1, block); - return "" HTML(text) "" _block(substr(block, len + 1) ); - - # Definition list - } else if (match( block, "^(([ \t]*\n)*[^:\n \t][^\n]+\n" \ - "([ \t]*\n)* ? ? ?:[ \t][^\n]+(\n|$)" \ - "(([ \t]*\n)* ? ? ?:[ \t][^\n]+(\n|$)" \ - "|[^:\n \t][^\n]+(\n|$)" \ - "|( ? ? ?\t| +)[^\n]+(\n|$)" \ - "|([ \t]*\n)+( ? ? ?\t| +)[^\n]+(\n|$))*)+" \ - )) { - list = substr( block, 1, RLENGTH); block = substr( block, RLENGTH + 1); - return "\n
\n" _dlist( list ) "
\n" _block( block ); - - # Unordered list types - } else if ( text = _startlist( block, "ul", "-", "([+*•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { - return text; - } else if ( text = _startlist( block, "ul", "\\+", "([-*•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { - return text; - } else if ( text = _startlist( block, "ul", "\\*", "([-+•]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { - return text; - } else if ( text = _startlist( block, "ul", "•", "([-+*]|[0-9]+\\.|#\\.|[0-9]+\\)|#\\))") ) { - return text; - - # Ordered list types - } else if ( text = _startlist( block, "ol", "[0-9]+\\.", "([-+*•]|#\\.|[0-9]+\\)|#\\))") ) { - return text; - } else if ( text = _startlist( block, "ol", "[0-9]+\\)", "([-+*•]|[0-9]+\\.|#\\.|#\\))") ) { - return text; - } else if ( text = _startlist( block, "ol", "#\\.", "([-+*•]|[0-9]+\\.|[0-9]+\\)|#\\))") ) { - return text; - } else if ( text = _startlist( block, "ol", "#\\)", "([-+*•]|[0-9]+\\.|#\\.|[0-9]+\\))") ) { - return text; - - # Split paragraphs - } else if ( match( block, /(^|\n)[[:space:]]*(\n|$)/) ) { - len = RLENGTH; st = RSTART; - return _block( substr(block, 1, st - 1) ) "\n" \ - _block( substr(block, st + len) ); - - # Horizontal rule - } else if ( match( block, /(^|\n) ? ? ?((\* *){3,}|(- *){3,}|(_ *){3,})($|\n)/) ) { - len = RLENGTH; st = RSTART; - return _block(substr(block, 1, st - 1)) "
\n" _block(substr(block, st + len)); - - # Plain paragraph - } else { - return "

" inline(block) "

\n"; + # Plain paragraph + return ret "

" inline(block) "

\n"; } + return ret; } -function _startlist(block, type, mark, exclude, LOCAL, st, len, list, indent, text) { +function _startlist(block, type, mark, exclude, LOCAL, st, len, list, indent, it, text) { if (match( block, "(^|\n) ? ? ?" mark "[ \t][^\n]+(\n|$)" \ "(([ \t]*\n)* ? ? ?" mark "[ \t][^\n]+(\n|$)" \ "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \ "|[^\n \t][^\n]+(\n|$))*" ) ) { st = RSTART; len = RLENGTH; list = substr( block, st, len); - sub("^\n", "", list); match(list, "^ ? ? ?"); indent = RLENGTH; - gsub( "(^|\n) {0," indent "}", "\n", list); sub("^\n", "", list); + sub("^\n", "", list); match(list, "^( | | )?"); indent = RLENGTH; + # gsub( "(^|\n) {0," indent "}", "\n", list); sub("^\n", "", list); + # emulate greedy range matcher for mawk + it = "("; while ( indent > 0 ) { for (k = indent; k > 0; k--) { it = it " "; } it = it "|"; indent--; } + sub(/\|$/, ")?", it); sub(/^\($/, "", it); + gsub( "(^|\n)" it, "\n", list ); sub("^\n", "", list); text = substr(block, 1, st - 1); block = substr(block, st + len); if (match(text, /\n[[:space:]]*\n/)) return 0; @@ -767,10 +884,11 @@ function _startlist(block, type, mark, exclude, LOCAL, st, len, list, indent, te } else return 0; } -function _list (block, mark, p, LOCAL, len, st, text, indent, task) { +function _list (block, mark, p, LOCAL, len, st, text, indent, it, task) { if ( match(block, "^([ \t]*\n)*$")) return; match(block, "^" mark "[ \t]"); indent = RLENGTH; + sub("^" mark "[ \t]", "", block); if (match(block, /\n[ \t]*\n/)) p = 1; @@ -779,7 +897,11 @@ function _list (block, mark, p, LOCAL, len, st, text, indent, task) { st = (RLENGTH == -1) ? length(block) + 1 : RSTART; text = substr(block, 1, st); block = substr(block, st + 1); - gsub("\n {0," indent "}", "\n", text); + # gsub("\n {0," indent "}", "\n", text); + # emulate greedy range matcher for mawk + it = "("; while ( indent > 0 ) { for (k = indent; k > 0; k--) { it = it " "; } it = it "|"; indent--; } + sub(/\|$/, ")?", it); sub(/^\($/, "", it); + gsub("\n" it, "\n", text); task = match( text, /^\[ \]/ ) ? "
  • " : \ match( text, /^\[-\]/ ) ? "
  • " : \ @@ -795,7 +917,7 @@ function _list (block, mark, p, LOCAL, len, st, text, indent, task) { return task text "
    • \n" _list(block, mark, p); } -function _dlist (block, LOCAL, len, st, text, indent, p) { +function _dlist (block, LOCAL, len, st, text, indent, it, p) { if (match( block, "^([ \t]*\n)*[^:\n \t][^\n]+\n" )) { len = RLENGTH; text = substr(block, 1, len); gsub( "(^\n*|\n*$)", "", text ); @@ -809,7 +931,11 @@ function _dlist (block, LOCAL, len, st, text, indent, p) { sub( "^([ \t]*\n)*", "", text); match(text, "^ ? ? ?:(\t| +)"); indent = RLENGTH; sub( "^ ? ? ?:(\t| +)", "", text); - gsub( "(^|\n) {0," indent "}", "\n", text ); + # gsub( "(^|\n) {0," indent "}", "\n", text ); + # emulate greedy range matcher for mawk + it = "("; while ( indent > 0 ) { for (k = indent; k > 0; k--) { it = it " "; } it = it "|"; indent--; } + sub(/\|$/, ")?", it); sub(/^\($/, "", it); + gsub( "(^|\n)" it, "\n", text ); text = _nblock(text); if (match( text, "^

    (]|\n$" )) @@ -827,12 +953,12 @@ BEGIN { # hls = "0 0 0 0 0 0"; # Universal Patterns - nu = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\_]|_[[:alnum:]])*" # not underline (except when escaped) - na = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\\\*])*" # not asterisk (except when escaped) - ieu = "_([^_[:space:]]|[^_[:space:]]" nu "[^_[:space:]])_" # inner (underline) - isu = "__([^_[:space:]]|[^_[:space:]]" nu "[^_[:space:]])__" # inner (underline) - iea = "\\*([^\\*[:space:]]|[^\\*[:space:]]" na "[^\\*[:space:]])\\*" # inner (asterisk) - isa = "\\*\\*([^\\*[:space:]]|[^\\*[:space:]]" na "[^\\*[:space:]])\\*\\*" # inner (asterisk) + nu = "([^_\\\\]|\\\\.|_[[:alnum:]])" # not underline (except when escaped, or inside a word) + na = "([^*\\\\]|\\\\.)" # not asterisk (except when escaped) + ieu = "_([^_[:space:]]|[^_[:space:]]" nu "*[^_[:space:]])_" # inner (underline) + isu = "__([^_[:space:]]|[^_[:space:]]" nu "*[^_[:space:]])__" # inner (underline) + iea = "\\*([^*[:space:]]|[^*[:space:]]" na "*[^*[:space:]])\\*" # inner (asterisk) + isa = "\\*\\*([^*[:space:]]|[^*[:space:]]" na "*[^*[:space:]])\\*\\*" # inner (asterisk) lix="\\[(\\\\[^\n]|[^]\n\\\\[])*\\]" # link text lid="(<(\\\\[^\n]|[^\n<>\\\\])*>|(\\\\.|[^()\"'\\\\])+|([^<\n\t ()\\\\]|\\\\[^\n])(\\\\[\n]|[^\n\t \\(\\)\\\\])*)" # link dest @@ -850,10 +976,17 @@ BEGIN { re_reflink = "(^|\n) ? ? ?\\[([^]\n]+)\\]: ([^ \t\n]+)(\n?[ \t]+(\"([^\"]+)\"|'([^']+)'|\\(([^)]+)\\)))?(\n|$)"; # /(^|\n) ? ? ?\[([^]\n]+)\]: ([^ \t\n]+)(\n?[ \t]+("([^"]+)"|'([^']+)'|\(([^)]+)\)))?(\n|$)/ while ( match(f, re_reflink ) ) { - rl_id = gensub( re_reflink, "\\2", 1, substr(f, RSTART, RLENGTH) ); - rl_href[rl_id] = gensub( re_reflink, "\\3", 1, substr(f, RSTART, RLENGTH) ); - rl_title[rl_id] = gensub( re_reflink, "\\5", 1, substr(f, RSTART, RLENGTH) ); - f = substr(f, RSTART + RLENGTH); + tt = th = ti = substr(f, RSTART, RLENGTH); f = substr(f, RSTART + RLENGTH); + sub("(^|\n) ? ? ?\\[", "", ti); sub("\\]: ([^ \t\n]+)(\n?[ \t]+(\"([^\"]+)\"|'([^']+)'|\\(([^)]+)\\)))?(\n.*)?$", "", ti); + sub("(^|\n) ? ? ?\\[([^]\n]+)\\]: ", "", th); sub("(\n?[ \t]+(\"([^\"]+)\"|'([^']+)'|\\(([^)]+)\\)))?(\n.*)?$", "", th); + if (match(tt, "(^|\n) ? ? ?\\[([^]\n]+)\\]: ([^ \t\n]+)(\n?[ \t]+(\"([^\"]+)\"|'([^']+)'|\\(([^)]+)\\)))(\n|$)")) { + sub("(^|\n) ? ? ?\\[([^]\n]+)\\]: ([^ \t\n]+)", "", tt); sub("^\n?[ \t]+", "", tt); sub("(\n.*)?$", "", tt); + } else { tt = ""; } + rl_id = ti; rl_href[rl_id] = th; rl_title[rl_id] = tt; + # rl_id = gensub( re_reflink, "\\2", 1, substr(f, RSTART, RLENGTH) ); + # rl_href[rl_id] = gensub( re_reflink, "\\3", 1, substr(f, RSTART, RLENGTH) ); + # rl_title[rl_id] = gensub( re_reflink, "\\5", 1, substr(f, RSTART, RLENGTH) ); + # f = substr(f, RSTART + RLENGTH); rl_title[rl_id] = substr( rl_title[rl_id], 2, length(rl_title[rl_id]) - 2 ); if ( rl_href[rl_id] ~ /<.*>/ ) rl_href[rl_id] = substr( rl_href[rl_id], 2, length(rl_href[rl_id]) - 2 ); }