Unified · Split
| @@ -0,0 +1,176 @@ | |||
| 1 | #!/bin/awk -f | ||
| 2 | |||
| 3 | # md2html.awk | ||
| 4 | # by: Jesus Galan (yiyus) <yiyu.jgl@gmail>, May 2009 | ||
| 5 | # Usage: | ||
| 6 | # md2html file.md > file.html | ||
| 7 | # Options: -v esc=false to not escape html | ||
| 8 | |||
| 9 | function newblock(nblock){ | ||
| 10 | if(text) | ||
| 11 | print "<" block ">" text "</" block ">"; | ||
| 12 | text = ""; | ||
| 13 | block = nblock ? nblock : "p"; | ||
| 14 | } | ||
| 15 | |||
| 16 | function subinline(tgl, inl){ | ||
| 17 | while(match($0, tgl)){ | ||
| 18 | if (inline[ni] == inl) | ||
| 19 | ni -= sub(tgl, "</" inl ">"); | ||
| 20 | else if (sub(tgl, "<" inl ">")) | ||
| 21 | inline[++ni] = inl; | ||
| 22 | } | ||
| 23 | } | ||
| 24 | |||
| 25 | function dolink(href, lnk){ | ||
| 26 | # Undo escaped html in uris | ||
| 27 | gsub(/&/, "\\&", href); | ||
| 28 | gsub(/</, "<", href); | ||
| 29 | gsub(/>/, ">", href); | ||
| 30 | # & can be tricky, and not standard: | ||
| 31 | gsub(/&/, "\\\\\\&", href); | ||
| 32 | gsub(/&/, "\\\\\\&", lnk); | ||
| 33 | return "<a href=\"" href "\">" lnk "</a>"; | ||
| 34 | } | ||
| 35 | |||
| 36 | BEGIN { | ||
| 37 | ni = 0; # inlines | ||
| 38 | nl = 0; # nested lists | ||
| 39 | text = ""; | ||
| 40 | block = "p"; | ||
| 41 | } | ||
| 42 | |||
| 43 | # Escape html | ||
| 44 | esc != "false" { | ||
| 45 | gsub("&", "\\&") | ||
| 46 | gsub("<", "\\<") | ||
| 47 | gsub(">", "\\>") | ||
| 48 | } | ||
| 49 | |||
| 50 | # Horizontal rules (_ is not in markdown) | ||
| 51 | /^[ ]*([-*_] ?)+[ ]*$/ && text == "" { | ||
| 52 | print "<hr>"; | ||
| 53 | next; | ||
| 54 | } | ||
| 55 | |||
| 56 | # Tables (not in markdown) | ||
| 57 | # Syntax: | ||
| 58 | # Right Align| Center Align |Left Align | ||
| 59 | /([ ]\|)|(\|[ ])/ { | ||
| 60 | if(block != "table") | ||
| 61 | newblock("table"); | ||
| 62 | nc = split($0, cells, "|"); | ||
| 63 | $0 = "<tr>\n"; | ||
| 64 | for(i = 1; i <= nc; i++){ | ||
| 65 | align = "left"; | ||
| 66 | if(sub(/^[ ]+/, "", cells[i])){ | ||
| 67 | if(sub(/[ ]+$/, "", cells[i])) | ||
| 68 | align = "center"; | ||
| 69 | else | ||
| 70 | align = "right"; | ||
| 71 | } | ||
| 72 | sub(/[ ]+$/,"", cells[i]); | ||
| 73 | $0 = $0 "<td align=\"" align "\">" cells[i] "</td>\n"; | ||
| 74 | } | ||
| 75 | $0 = $0 "</tr>"; | ||
| 76 | } | ||
| 77 | |||
| 78 | # Ordered and unordered (possibly nested) lists | ||
| 79 | /^[ ]*([*+-]|(([0-9]+[\.-]?)+))[ ]/ { | ||
| 80 | newblock("li"); | ||
| 81 | nnl = 1; | ||
| 82 | while(match($0, /^[ ]/)){ | ||
| 83 | sub(/^[ ]/,""); | ||
| 84 | nnl++; | ||
| 85 | } | ||
| 86 | while(nl > nnl) | ||
| 87 | print "</" list[nl--] ">"; | ||
| 88 | while(nl < nnl){ | ||
| 89 | list[++nl] = "ol"; | ||
| 90 | if(match($0, /^[*+-]/)) | ||
| 91 | list[nl] = "ul"; | ||
| 92 | print "<" list[nl] ">"; | ||
| 93 | } | ||
| 94 | sub(/^([*+-]|(([0-9]+[\.-]?)+))[ ]/,""); | ||
| 95 | } | ||
| 96 | |||
| 97 | # Multi line list items | ||
| 98 | block == "li" { | ||
| 99 | sub(/^( *)|( *)/,""); | ||
| 100 | } | ||
| 101 | |||
| 102 | # Code blocks | ||
| 103 | /^( | )/ { | ||
| 104 | if(block != "pre") | ||
| 105 | newblock("pre"); | ||
| 106 | sub(/^( | )/, ""); | ||
| 107 | text = text $0 "\n"; | ||
| 108 | next; | ||
| 109 | } | ||
| 110 | |||
| 111 | # Paragraph | ||
| 112 | /^$/ { | ||
| 113 | newblock(); | ||
| 114 | while(nl > 0) | ||
| 115 | print "</" list[nl--] ">"; | ||
| 116 | } | ||
| 117 | |||
| 118 | # Setex-style Headers | ||
| 119 | # (Plus h3 with underscores.) | ||
| 120 | /^=+$/ { | ||
| 121 | block = "h" 1; | ||
| 122 | next; | ||
| 123 | } | ||
| 124 | |||
| 125 | /^-+$/ { | ||
| 126 | block = "h" 2; | ||
| 127 | next; | ||
| 128 | } | ||
| 129 | |||
| 130 | /^_+$/ { | ||
| 131 | block = "h" 3; | ||
| 132 | next; | ||
| 133 | } | ||
| 134 | |||
| 135 | # Atx-style headers | ||
| 136 | /^#/ { | ||
| 137 | newblock(); | ||
| 138 | match($0, /#+/); | ||
| 139 | n = RLENGTH; | ||
| 140 | if(n > 6) | ||
| 141 | n = 6; | ||
| 142 | text = substr($0, RLENGTH + 1); | ||
| 143 | block = "h" n; | ||
| 144 | next; | ||
| 145 | } | ||
| 146 | |||
| 147 | // { | ||
| 148 | # Images | ||
| 149 | while(match($0, /!\[[^\]]+\]\([^\)]+\)/)){ | ||
| 150 | split(substr($0, RSTART + 2, RLENGTH - 3), a, /\]\(/); | ||
| 151 | sub(/!\[[^\]]+\]\([^\)]+\)/, "<img src=\"" a[2] "\" alt=\"" a[1] "\">"); | ||
| 152 | } | ||
| 153 | # Links | ||
| 154 | while(match($0, /\[[^\]]+\]\([^\)]+\)/)){ | ||
| 155 | split(substr($0, RSTART + 1, RLENGTH - 2), a, /\]\(/); | ||
| 156 | sub(/\[[^\]]+\]\([^\)]+\)/, dolink(a[2], a[1])); | ||
| 157 | } | ||
| 158 | # Auto links (uri matching is poor) | ||
| 159 | na = split($0, a, /(^\()|[ ]|([,\.\)]([ ]|$))/); | ||
| 160 | for(i = 1; i <= na; i++) | ||
| 161 | if(match(a[i], /^(((https?|ftp|file|news|irc):\/\/)|(mailto:)).+$/)) | ||
| 162 | sub(a[i], dolink(a[i], a[i])); | ||
| 163 | # Inline | ||
| 164 | subinline("(\\*\\*)|(__)", "strong"); | ||
| 165 | subinline("\\*", "em"); | ||
| 166 | subinline("`", "code"); | ||
| 167 | text = text (text ? " " : "") $0; | ||
| 168 | } | ||
| 169 | |||
| 170 | END { | ||
| 171 | while(ni > 0) | ||
| 172 | text = text "</" inline[ni--] ">"; | ||
| 173 | newblock(); | ||
| 174 | while(nl > 0) | ||
| 175 | print "</" list[nl--] ">"; | ||
| 176 | } | ||