X-Git-Url: https://git.plutz.net/?p=cgilite;a=blobdiff_plain;f=markdown.awk;h=361e6005c3fc42fa5e1f81859d69ec59d0c0a138;hp=eb352583a7c9b9aa6e2e6cbf76531ff030542c83;hb=HEAD;hpb=c1eb79536cd0c60151846c2c294581a029343e32 diff --git a/markdown.awk b/markdown.awk index eb35258..90dddbf 100755 --- a/markdown.awk +++ b/markdown.awk @@ -4,10 +4,20 @@ # EXPERIMENTAL Markdown processor with minimal dependencies. # Meant to support all features of John Grubers basic Markdown # + a number of common extensions, mostly inspired by Pandoc Markdown -# -# ToDo: -# - HTML processing / escaping (according to environment flag) -# - em-dashes and arrows + +# 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 +# copyright notice and this permission notice appear in all copies. +# +# THE SOFTWARE IS PROVIDED “AS IS” AND THE AUTHOR DISCLAIMS ALL WARRANTIES +# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF +# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY +# SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES +# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN +# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR +# IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. # Supported Features / TODO: # ========================== @@ -24,6 +34,7 @@ # - [x] Lists (ordered, unordered) # - [x] Code blocks (using indention) # - [x] Horizontal rules +# - [x] Verbatim HTML block (disabled by default) # # Basic Markdown - Inline elements: # --------------------------------- @@ -31,26 +42,38 @@ # - [x] Reference style links # - [x] Emphasis *em*/**strong** (*Asterisk*, _Underscore_) # - [x] `code`, also ``code containing `backticks` `` -# - [ ] Images / reference style images +# - [x] Images / reference style images # - [x] # - [x] backslash escapes +# - [x] Verbatim HTML inline (disabled by default) +# - [x] HTML escaping +# +# NOTE: Set the environment variable MD_HTML=true to enable verbatim HTML # # Extensions - Block elements: # ---------------------------- +# - [x] Automatic
-wrapping (custom) # - ? Heading identifiers (php md, pandoc) +# - [x] Heading attributes (custom) +# - [ ]
terminates section +# - [x] Automatic heading identifiers (custom) # - [x] Fenced code blocks (php md, pandoc) -# - [-] Fenced code attributes -# - [ ] Tables +# - [x] Fenced code attributes +# - [x] Images (as block elements,
-wrapped) (custom) +# - [x] reference style block images +# - [/] Tables # - ? Simple table (pandoc) # - ? Multiline table (pandoc) -# - ? Grid table (pandoc) -# - ? Pipe table (php md pandoc) +# - [x] Grid table (pandoc) +# - [x] Headerless +# - [x] Pipe table (php md, pandoc) # - [x] Line blocks (pandoc) -# - [ ] Task lists (pandoc) -# - [ ] Definition lists (php md, pandoc) +# - [x] Task lists (pandoc, custom) +# - [x] Definition lists (php md, pandoc) # - [-] Numbered example lists (pandoc) # - [-] Metadata blocks (pandoc) -# - [-] Fenced Divs (pandoc) +# - [x] Metadata blocks (custom) +# - [x] Fenced Divs (pandoc) # # Extensions - Inline elements: # ---------------------------- @@ -59,6 +82,8 @@ # - [x] ^Superscript^ ~Subscript~ (pandoc) # - [-] Bracketed spans (pandoc) # - [-] Inline attributes (pandoc) +# - [x] Image attributes (custom, pandoc inspired, not for reference style) +# - [x] Wiki style links [[PageName]] / [[PageName|Link Text]] # - [-] TEX-Math (pandoc) # - ? Footnotes (php md) # - ? Abbreviations (php md) @@ -67,7 +92,7 @@ # - ? ... three-dot ellipsis (smartypants) # - [-] en-dash (smartypants) # - [ ] Automatic em-dash / en-dash -# - [ ] Automatic -> Arrows <- +# - [x] Automatic -> Arrows <- (custom) function debug(text) { printf "\n---\n%s\n---\n", text > "/dev/stderr"; } @@ -81,273 +106,887 @@ function HTML ( text ) { return text; } -function inline( line, LOCAL, len, code, href, guard ) { - 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) - - if ( line ~ /^$/ ) { # Recursion End - return ""; - - # omit processing of escaped characters - } else if ( line ~ /^\\[]\\`\*_\{\}\(\)#\+-\.![]/) { - return 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 - code = gensub( / (.*) /, "\\1", "1" , code) - # escape HTML within code span - gsub( /&/, "\\&", code ); gsub( //, "\\>", code ); - return "" code "" inline( substr( line, len + 1 ) ) - } +function URL ( text, sharp ) { + gsub( /&/, "%26", text ); + gsub( /"/, "%22", text ); + gsub( /'/, "%27", text ); + gsub( /`/, "%60", text ); + gsub( /\?/, "%3F", text ); + if (sharp) gsub( /#/, "%23", text ); + gsub( /\[/, "%5B", text ); + gsub( /\]/, "%5D", text ); + gsub( / /, "%20", text ); + gsub( / /, "%09", text ); + gsub( /\\/, "%5C", text ); + return text; +} - # 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) ); - return "" href "" inline( substr( line, len + 1) ); - - # inline links - } else if ( match(line, /^\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/) ) { - len = RLENGTH; - text = gensub(/^\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\1", "g", line); - href = gensub(/^\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\2", "g", line); - title = gensub(/^\[([^]]+)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)/, "\\4", "g", line); - if ( title ) { - return "" inline( text ) "" inline( substr( line, len + 1) ); - } else { - return "" inline( text ) "" 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; + 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); + + 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; + 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; +} - # reference style links - } else if ( match(line, /^\[([^]]+)\] ?\[([^]]*)\]/ ) ) { - len = RLENGTH; - text = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\1", 1, line); - id = gensub(/^\[([^\n]+)\] ?\[([^\n]*)\].*/, "\\2", 1, line); - 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 "" substr(line, 1, len) inline( substr(line, len + 1) ); - } +function headline( hlvl, htxt, attrib, LOCAL, sec, n, HL) { + # match(hstack, /([0-9]+( [0-9]+){5})$/); split( substr(hstack, RSTART), HL); + match(hstack, /([0-9]+( [0-9]+)( [0-9]+)( [0-9]+)( [0-9]+)( [0-9]+))$/); split( substr(hstack, RSTART), HL); - # ~~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 substr( line, 1, RLENGTH) inline( substr(line, RLENGTH + 1) ); - - # __strong__$ - } else if ( match(line, "^__(([^_[:space:]]|" ieu ")|([^_[:space:]]|" ieu ")(" nu "|" ieu ")*([^_[:space:]]|" ieu "))__$") ) { - len = RLENGTH; - return "" inline( substr( line, 3, len - 4 ) ) "" inline( substr( line, len + 1 ) ); - - # __strong__ - } else if ( match(line, "^__(([^_[:space:]]|" ieu ")|([^_[:space:]]|" ieu ")(" nu "|" ieu ")*([^_[:space:]]|" ieu "))__[[:space:]]") ) { - len = RLENGTH; - return "" inline( substr( line, 3, len - 5 ) ) "" inline( substr( line, len) ); - - # **strong** - } else if ( match(line, "^\\*\\*(([^\\*[:space:]]|" iea ")|([^\\*[:space:]]|" iea ")(" na "|" iea ")*([^\\*[:space:]]|" iea "))\\*\\*") ) { - len = RLENGTH; - return "" inline( substr( line, 3, len - 4 ) ) "" inline( substr( line, len + 1 ) ); - - # _em_$ - } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_$") ) { - len = RLENGTH; - return "" inline( substr( line, 2, len - 2 ) ) "" inline( substr( line, len + 1 ) ); - - # _em_ - } else if ( match(line, "^_(([^_[:space:]]|" isu ")|([^_[:space:]]|" isu ")(" nu "|" isu ")*([^_[:space:]]|" isu "))_[[:space:]]") ) { - len = RLENGTH; - return "" inline( substr( line, 2, len - 3 ) ) "" inline( substr( line, len ) ); - - # *em* - } else if ( match(line, "^\\*(([^\\*[:space:]]|" isa ")|([^\\*[:space:]]|" isa ")(" na "|" isa ")*([^\\*[:space:]]|" isa "))\\*") ) { - len = RLENGTH; - return "" inline( substr( line, 2, len - 2 ) ) "" inline( substr( line, len + 1 ) ); - - # continue walk over string - } else { - return substr(line, 1, 1) inline( substr(line, 2) ); - } + for ( n = hlvl; n <= 6; n++ ) { sec = sec (HL[n]?"
":""); } + HL[hlvl]++; for ( n = hlvl + 1; n <= 6; n++) { HL[n] = 0;} + + hid = ""; for ( n = 2; n <= blvl; n++) { hid = hid BL[n] "/"; } + hid = hid HL[1]; for ( n = 2; n <= hlvl; n++) { hid = hid "." HL[n] ; } + hid = hid ":" URL(htxt, 1); + + # sub(/([0-9]+( [0-9]+){5})$/, "", hstack); + sub(/([0-9]+( [0-9]+)( [0-9]+)( [0-9]+)( [0-9]+)( [0-9]+))$/, "", hstack); + hstack = hstack HL[1] " " HL[2] " " HL[3] " " HL[4] " " HL[5] " " HL[6]; + + return sec "
" \ + "" inline( htxt ) \ + "" \ + "\n"; } -function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent ) { - gsub( /^\n+|\n+$/, "", block ); +# Nested Block, resets heading counters +function _nblock( block, LOCAL, sec, n ) { + hstack = hstack " 0 0 0 0 0 0"; - if ( block == "" ) { - return ""; + # Block Level + blvl++; BL[blvl]++; + for ( n = blvl + 1; n in BL; n++) { delete BL[n]; } + + block = _block( block ); + match(hstack, /([0-9]+( [0-9]+)( [0-9]+)?( [0-9]+)?( [0-9]+)?( [0-9]+)?)$/); split( substr(hstack, RSTART), HL); + sec = ""; for ( n = 1; n <= 6; n++ ) { sec = sec (HL[n]?"
":""); } + + sub("( +[0-9]+)( +[0-9]+)?( +[0-9]+)?( +[0-9]+)?( +[0-9]+)?( +[0-9]+)? *$", "", hstack); blvl--; + return block sec; +} + +function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, indent, list, tmp, ret) { + ret = ""; + while ( block != "" ) { + gsub( "(^\n+|\n+$)", "", block ); + + # HTML #2 #3 #4 $5 + if ( AllowHTML && match( block, /(^|\n) ? ? ?(|$)|<\?([^\?]|\?[^>])*(\?>|$)|]*(>|$)|])*(\]\]>|$))/) ) { + len = RLENGTH; st = RSTART; + ret = ret _block(substr(block, 1, st - 1)) substr(block, st, len); block = substr(block, st + len); + continue; + + # HTML #6 (part1) + } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<\/?(address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset)([[:space:]\n>]|\/>)([^\n]|\n[ \t]*[^\n])*(\n[[:space:]]*\n|$)/) ) { + len = RLENGTH; st = RSTART; + ret = ret _block(substr(block, 1, st - 1)) substr(block, st, len); block = substr(block, st + len); + continue; + + # 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|$)/) ) { + len = RLENGTH; st = RSTART; + ret = ret _block(substr(block, 1, st - 1)) substr(block, st, len); block = substr(block, st + len); + continue; + + # HTML #1 + } else if ( AllowHTML && match( tolower(block), /(^|\n) ? ? ?<(script|pre|style)([[:space:]\n>]).*(<\/script>|<\/pre>|<\/style>|$)/) ) { + 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|$)/) ) { + len = RLENGTH; st = RSTART; + ret = ret substr(block, st, len); block = substr(block, st + len); + continue; - # Horizontal rule - } else if ( match( block, /(^|\n) ? ? ?((\* *){3,}|(- *){3,}|(_ *){3,})($|\n)/) ) { - len = RLENGTH; st = RSTART; - return _block(substr(block, 1, st - 1)) "
\n" _block(substr(block, st + len)); + # 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; - return "
\n" _block( gensub( /(^|\n)> /, "\n", "g", substr(block, 1, st - 1) ) ) "
\n\n" \ - _block( substr(block, st + len) ); - - # Line Blocks (pandoc) - } else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\n]*(\n|$)|[ \t]+[^\n[:space:]][^\n]*(\n|$))*/) ) { - len = RLENGTH; st = RSTART; - code = substr(block, 1, len); - gsub(/\n[[:space:]]+/, " ", code); - gsub(/\n\| /, "\n", code); - gsub(/^\| |\n$/, "", code); - return "
" gensub(/\n/, "
\n", "g", inline( code )) "
\n" \ - _block( substr( block, len + 1) ); - - # Indented Code Block - } else if ( match(block, /^( |\t)[^\n]+(\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 Code Block (pandoc) - } else if ( match( block, /^(~~~+|```+)/ ) ) { - guard = substr( block, 1, RLENGTH ); - code = gensub(/^[^\n]+\n/, "", 1, block); - if ( match(code, "(^|\n)" guard "+(\n|$)" ) ) { + # Blockquote (leading >) + } else if ( match( block, /^> /) ) { + match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match(block, /$/); len = RLENGTH; st = RSTART; - return "
" HTML( substr(code, 1, st - 1) ) "
\n" \ - _block( substr( code, st + len ) ); - } else { - match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ ); + text = substr(block, 1, st - 1); gsub( /(^|\n)> /, "\n", text ); + text = _nblock( text ); gsub( /^\n|\n$/, "", 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; - return "

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

\n" \ - _block( substr(block, st + len) ); - } + #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|$)/) + 1 ); + tmp = substr(block, 1, match(block, /(\n|$)/)); + 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 "" 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 ); + + 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|$)/) + 1 ); + for (cnt = 1; cnt <= cols; cnt++) + tarray[cnt] = tarray[cnt] "\n" tread[cnt]; + } + + ttext = "\n" + for (cnt = 1; cnt <= cols; cnt++) + ttext = ttext "" _nblock(tarray[cnt]) "" + ttext = ttext "\n" + } + + # table body + block = substr(block, match(block, /(\n|$)/) + 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|$)/) + 1 ); + + ttext = ttext "" + for (cnt = 1; cnt <= cols; cnt++) + ttext = ttext "" _nblock(tarray[cnt]) "" + ttext = ttext "\n" + } + return ret "" ttext "
\n" _nblock(block); + + # Line Blocks (pandoc) + } else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\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$/, "", text); + text = inline(text); gsub(/\n/, "
\n", text); + + ret = ret "
" text "
\n"; block = substr( block, len + 1); + continue; + + # Indented Code Block + } else if ( match(block, /^(( |\t)[^\n]*[^\n\t ][^\n]*(\n|$))(( |\t)[^\n]*(\n|$)|[\t ]*(\n|$))*/) ) { + len = RLENGTH; st = RSTART; + + 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; + } + + # 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; + } + + # 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; + } + + # 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|$)/) ) { + len = RLENGTH; st = RSTART; + ret = ret _block( substr(block, 1, st - 1) ) "\n"; block = substr(block, st + len); + continue; - # Unordered list - } else if ( match( block, "^ ? ? ?[-+*][ \t]+[^\n]+(\n|$)" \ - "(([ \t]*\n)* ? ? ?[-+*][ \t]+[^\n]+(\n|$)" \ - "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \ - "|[^\n]+(\n|$))*" ) ) { - list = substr( block, 1, RLENGTH); - block = substr( block, RLENGTH + 1); - indent = length( gensub(/[-+*][ \t]+[^\n]+.*$/, "", 1, list) ); - - gsub("(^|\n) {0," indent "}", "\n", list); - return "\n
    \n" _list( substr(list, 2) ) "
\n" _block( block ); - - # Ordered list - } else if ( match( block, "^ ? ? ?([0-9]+|#)\\.[ \t]+[^\n]+(\n|$)" \ - "(([ \t]*\n)* ? ? ?([0-9]+|#)\\.[ \t]+[^\n]+(\n|$)" \ - "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \ - "|[^\n]+(\n|$))*" ) ) { - list = substr( block, 1, RLENGTH); - block = substr( block, RLENGTH + 1); - indent = length( gensub(/([0-9]+|#)\.[ \t]+[^\n]+.*$/, "", 1, list) ); - - gsub("(^|\n) {0," indent "}", "\n", list); - return "\n
    \n" _list( substr(list, 2) ) "
\n" _block( block ); - - # First Order Heading - } else if ( match( block, /^[^\n]+\n===+(\n|$)/ ) ) { - len = RLENGTH; - return "

" inline( gensub( /\n.*$/, "", "g", block ) ) "

\n\n" \ - _block( substr( block, len + 1 ) ); - - # Second Order Heading - } else if ( match( block, /^[^\n]+\n---+(\n|$)/ ) ) { - len = RLENGTH; - return "

" inline( gensub( /\n.*$/, "", "g", block ) ) "

\n\n" \ - _block( substr( block, len + 1) ); - - # Nth Order Heading - } else if ( match( block, /^#{1,6}[[:space:]]*[^\n]+([[:space:]]*#*)(\n|$)/ ) ) { - len = RLENGTH; - hlvl = length( gensub( /^(#{1,6}).*$/, "\\1", "g", block ) ); - htxt = gensub( /[[:space:]]*#*$/, "", "1", gensub( /^#{1,6}[[:space:]]*([^\n]+)([[:space:]]*#*)\n.*$/, "\\1", "g", block ) ) - return "" inline( htxt ) "\n\n" \ - _block( substr( block, len + 1) ); - - # Plain paragraph - } 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) ); + # 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; + + } # block patterns end + + # Plain paragraph + return ret "

" inline(block) "

\n"; } + return ret; } -function _list( block, last, LOCAL, p) { - if ( ! length(block) ) return ""; - gsub(/^([-+*]|[0-9]+\.|#\.)( ? ? ?|\t)/, "", block) +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); + # 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; + if (match(text, "(^|\n) ? ? ?" exclude "[ \t][^\n]+")) return 0; + if (match( list, "\n" exclude "[ \t]" )) { + block = substr(list, RSTART + 1) block; + list = substr(list, 1, RSTART); + } - # slice next list item from input - if ( match( block, /\n([-+*]|[0-9]+\.|#\.)[ \t]+[^\n]+/) ) { - p = substr( block, 1, RSTART); - block = substr( block, RSTART + 1); - } else { - p = block; block = ""; - } - sub( /\n +([-+*]|[0-9]+\.|#\.)/, "\n&", p ); - - # if this should be a paragraph item - # either previous item (last) or current item (p) contains blank lines - if (match(last, /\n[[:space:]]*\n/) || match(p, /\n[[:space:]]*\n/) ) { - last = p; p = _block(p); - } else { - last = p; p = _block(p); - sub( /^

/, "", p ); - sub( /<\/p>\n/, "", p ); + return _block( text ) "<" type ">\n" _list( list, mark ) "\n" _block( block ); + } else return 0; +} + +function _list (block, mark, p, LOCAL, len, st, text, indent, it, task) { + if ( match(block, "^([ \t]*\n)*$")) return; + + match(block, "^" mark "[ \t]"); indent = RLENGTH; + + sub("^" mark "[ \t]", "", block); + + if (match(block, /\n[ \t]*\n/)) p = 1; + + match( block, "\n" mark "[ \t][^\n]+(\n|$)" ); + st = (RLENGTH == -1) ? length(block) + 1 : RSTART; + text = substr(block, 1, st); block = substr(block, st + 1); + + # 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, /^\[-\]/ ) ? "
  • " : \ + match( text, /^\[\/\]/ ) ? "
  • " : \ + match( text, /^\[\?\]/ ) ? "
  • " : \ + match( text, /^\[[xX]\]/) ? "
  • " : "
  • "; + sub(/^\[[-? \/xX]\]/, "", text); + + text = _nblock( text ); + if ( ! p && match( text, "^

    (]|\n$" )) + gsub( "(^

    |

    \n$)", "", text); + + return task text "
    • \n" _list(block, mark, p); +} + +function _dlist (block, LOCAL, len, st, text, indent, it, p) { + if (match( block, "^([ \t]*\n)*[^:\n \t][^\n]+\n" )) { + len = RLENGTH; text = substr(block, 1, len); + gsub( "(^\n*|\n*$)", "", text ); + return "
    " inline( text ) "
    \n" _dlist( substr(block, len + 1) ); + } else if (match( block, "^([ \t]*\n)* ? ? ?:[ \t][^\n]+(\n|$)" \ + "([^:\n \t][^\n]+(\n|$)" \ + "|( ? ? ?\t| +)[^\n]+(\n|$)" \ + "|([ \t]*\n)+( ? ? ?\t| +)[^\n]+(\n|$))*" \ + )) { + len = RLENGTH; text = substr(block, 1, len); + sub( "^([ \t]*\n)*", "", text); + match(text, "^ ? ? ?:(\t| +)"); indent = RLENGTH; + sub( "^ ? ? ?:(\t| +)", "", 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$" )) + gsub( "(^

    |

    \n$)", "", text); + + return "
    " text "
    \n" _dlist( substr(block, len + 1) ); } - sub( /\n$/, "", p ); - return "
  • " p "
    • \n" _list( block, last ); } BEGIN { # Global Vars file = ""; rl_href[""] = ""; rl_title[""] = ""; + if (ENVIRON["MD_HTML"] == "true") { AllowHTML = "true"; } + HL[1] = 0; HL[2] = 0; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0; + # hls = "0 0 0 0 0 0"; + + # Universal Patterns + 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 + lit="(\"(\\\\.|[^\"\\\\])*\"|'(\\\\.|[^'\\\\])*'|\\((\\\\.|[^\\(\\)\\\\])*\\))" # link text + # link text with image def + lii="\\[(\\\\[^\n]|[^]\n\\\\[])*(!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\))?(\\\\[^\n]|[^]\n\\\\[])*\\]" # Buffering of full file ist necessary, e.g. to find reference links while (getline) { file = file $0 "\n"; } + # Clean up MS-DOS line breaks + gsub(/\r\n/, "\n", file); # Fill array of reference links f = file; rl_id; re_reflink = "(^|\n) ? ? ?\\[([^]\n]+)\\]: ([^ \t\n]+)(\n?[ \t]+(\"([^\"]+)\"|'([^']+)'|\\(([^)]+)\\)))?(\n|$)"; # /(^|\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 ); } @@ -356,5 +995,5 @@ BEGIN { # for (n in rl_href) { debug(n " | " rl_href[n] " | " rl_title[n] ); } # Run Block Processing -> The Actual Markdown! - printf "%s", _block( file ); + printf "%s", _nblock( file ); }