From f505048d7b0357564908696e23485a9015fede14 Mon Sep 17 00:00:00 2001 From: Christos Date: Sat, 4 Jan 2025 22:24:30 +0000 Subject: Adding original md2html awk script by Jesus Galan and renaming former personal fork to avoid confusion --- mh.awk | 122 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 122 insertions(+) create mode 100644 mh.awk (limited to 'mh.awk') diff --git a/mh.awk b/mh.awk new file mode 100644 index 0000000..a961ca1 --- /dev/null +++ b/mh.awk @@ -0,0 +1,122 @@ +#!/bin/awk -f +function eschtml(t) { +gsub("<", "\\<", t); +gsub("%", "\\%", t); + return t; } +function oprint(t) { if(nr == 0) otext = otext t; else otext = otext t; } +function nextil(t) { + if(!match(t, /[`<\[*_\\]|(\!\[)/)) return t + t1 = substr(t, 1, RSTART - 1) + tag = substr(t, RSTART, RLENGTH) + t2 = substr(t, RSTART + RLENGTH) + if(ilcode && tag != "`") + return eschtml(t1 tag) nextil(t2); + if(tag == "`"){ + if(sub(/^`/, "", t2)){ + if(!match(t2, /``/)) + return t1 "”" nextil(t2); + ilcode2 = !ilcode2; + } + else if(ilcode2) + return t1 tag nextil(t2); + tag = "
";
+                if(ilcode){
+#                       t1 = eschtml(t1);
+                        tag = "
"; + } + ilcode = !ilcode; + return t1 tag nextil(t2); + } + if(tag == "\\"){ if(match(t2, /^[\\*_{}\[\]()#+\-\.!]/)){ tag = substr(t2, 1, 1) + t2 = substr(t2, 2); } + return t1 tag nextil(t2); } + if(tag == "<"){ + if(match(t2, /^[A-Za-z\/!][^>]*>/)){ + tag = tag substr(t2, RSTART, RLENGTH) + t2 = substr(t2, RLENGTH + 1) + return t1 tag nextil(t2); + } + return t1 "<" nextil(t2); + } + if(tag == "["){ + if(!match(t2, /(\[.*\])|(\(.*\))/)) return t1 tag nextil(t2); match(t2, /^[^\]]*(\[[^\]]*\][^\]]*)*/) + linktext = substr(t2, 1, RLENGTH) + t2 = substr(t2, RLENGTH + 2); if(match(t2, /^\(/)){ match(t2, /^[^\)]+(\([^\)]+\)[^\)]*)*/) + url = substr(t2, 2, RLENGTH - 1) + pt2 = substr(t2, RLENGTH + 2) + title = "" + if(match(url, /[ ]+\".*\"[ ]*$/)){ title = substr(url, RSTART, RLENGTH) + url = substr(url, 1, RSTART - 1) + match(title, /\".*\"/) + title = " title=\"" substr(title, RSTART + 1, RLENGTH - 2) "\""; } if(match(url, /^<.*>$/)) url = substr(url, 2, RLENGTH - 2) +# url = eschtml(url) + return t1 ""nextil(linktext)"" nextil(pt2); } + } + if(match(tag, /[*_]/)){ ntag = tag; if(sub("^" tag, "", t2)){ if(stag[ns] == tag && match(t2, "^" tag)) t2 = tag t2; else ntag = tag tag; } n = length(ntag) + tag = (n == 2) ? "b" : "i" + if(match(t1, / $/) && match(t2, /^ /)) return t1 tag nextil(t2) + if(stag[ns] == ntag){ tag = "/" tag; ns--; } else stag[++ns] = ntag + tag = "<" tag ">" + return t1 tag nextil(t2); } } +function inline(t){ ilcode = 0; ilcode2 = 0; ns = 0; return nextil(t); } +function printp(tag){ if(!match(text, /^[ ]*$/)){ text = inline(text);if(tag != "") oprint("<" tag ">" text ""); else oprint(text); } text = ""; } +# function printp(tag){if(match(text,/^[ ]*$/)){text="";return}text=inline(text);if(tag=="p"){oprint("<"tag">"text)}else{oprint("<"tag">"text"")};text=""} +# ELSE function printp(tag){if(!match(text,/^[ ]*$/)){text=inline(text);if(tag=="p"){oprint("<"tag">"text)}else{oprint("<"tag">"text"")}}text=""} +BEGIN{blank=0;hr=0;nl=0;nr=0;text="";par="p";} +{ + for(nnl = 0; nnl < nl; nnl++) + if((match(block[nnl + 1], /[ou]l/) && !sub(/^( | )/, "")) || \ + (block[nnl + 1] == "blockquote" && !sub(/^> ?/, ""))) + break; +} +nnl < nl && !blank && text && ! /^ ? ? ?([*+-]|([0-9]+\.)+)( +| )/ { nnl = nl; } +{ hr = 0; } +block[nl] ~ /[ou]l/ && /^$/ { + blank = 1; + next; +} +{ newli = 0; } +!hr && (nnl != nl || !text || block[nl] ~ /[ou]l/) && /^ ? ? ?[*+-]( +| )/ { + sub(/^ ? ? ?[*+-]( +| )/, ""); + nnl++; + nblock[nnl] = "ul"; + newli = 1; +} +newli { + if(blank && nnl == nl && !par) + par = "p"; + blank = 0; + printp(par); + if(nnl == nl && block[nl] == nblock[nl]) + oprint("
  • "); +} +blank && ! /^$/ { + if(match(block[nnl], /[ou]l/) && !par) + par = "p"; + printp(par); + par = "p"; + blank = 0; +} +nnl != nl || nblock[nl] != block[nl] { + printp(par); + b = (nnl > nl) ? nblock[nnl] : block[nl]; + par = (match(b, /[ou]l/)) ? "" : "p"; +} +nnl < nl || (nnl == nl && nblock[nl] != block[nl]) { + for(; nl > nnl || (nnl == nl && pblock[nl] != block[nl]); nl--){ + oprint(""); + } +} +nnl > nl { + for(; nl < nnl; nl++){ + block[nl + 1] = nblock[nl + 1]; + oprint("<" block[nl + 1] ">"); + if(match(block[nl + 1], /[ou]l/)) + oprint("
  • "); + } +} +/^#+/ && (!newli || par=="p" || /^##/) { for(n = 0; n < 6 && sub(/^# */, ""); n++) sub(/#$/, ""); par = "h" n; } +/^$/ { printp(par); par = "p"; next; } +{ text = (text ? text " " : "") $0; } +END{printp(par);printf(otext);printf("ENTER FOOTER HERE")} +# maybe treat par as you do #h1 so to avoid closing tag -- cgit v1.2.3