X-Git-Url: http://git.plutz.net/?a=blobdiff_plain;f=markdown.awk;h=eb40210c9bc78c8cacadda40389c73df2e8d6d6b;hb=cc08744f66835d9ad6e9ec7f2c3fa9ed17e712ba;hp=33c12bdc9a5be4bcccd3e5bf1b504182291b0c36;hpb=d45e2c8bfc3c107cffc6771eae97988e11b2ceb5;p=cgilite
diff --git a/markdown.awk b/markdown.awk
index 33c12bd..eb40210 100755
--- a/markdown.awk
+++ b/markdown.awk
@@ -38,7 +38,10 @@
#
# Extensions - Block elements:
# ----------------------------
+# - [x] Automatic -wrapping (custom)
# - ? Heading identifiers (php md, pandoc)
+# - [x] Heading attributes (custom)
+# - [ ]
ends section
# - [x] Automatic heading identifiers (custom)
# - [x] Fenced code blocks (php md, pandoc)
# - [x] Fenced code attributes
@@ -52,7 +55,7 @@
# - [x] Pipe table (php md, pandoc)
# - [x] Line blocks (pandoc)
# - [x] Task lists (pandoc, custom)
-# - [ ] Definition lists (php md, pandoc)
+# - [x] Definition lists (php md, pandoc)
# - [-] Numbered example lists (pandoc)
# - [-] Metadata blocks (pandoc)
# - [x] Metadata blocks (custom)
@@ -89,12 +92,13 @@ function HTML ( text ) {
return text;
}
-function URL ( text ) {
+function URL ( text, sharp ) {
gsub( /&/, "%26", text );
gsub( /"/, "%22", text );
gsub( /'/, "%27", text );
+ gsub( /`/, "%60", text );
gsub( /\?/, "%3F", text );
- gsub( /#/, "%23", text );
+ if (sharp) gsub( /#/, "%23", text );
gsub( /\[/, "%5B", text );
gsub( /\]/, "%5D", text );
gsub( / /, "%20", text );
@@ -103,7 +107,7 @@ function URL ( text ) {
return text;
}
-function inline( line, LOCAL, len, code, href, guard ) {
+function inline( line, LOCAL, len, text, code, href, guard ) {
nu = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\_]|_[[:alnum:]])*" # not underline (except when escaped)
na = "(\\\\\\\\|\\\\[^\\\\]|[^\\\\\\*])*" # not asterisk (except when escaped)
ieu = "_([^_[:space:]]|[^_[:space:]]" nu "[^_[:space:]])_" # inner (underline)
@@ -115,8 +119,8 @@ function inline( line, LOCAL, len, code, href, guard ) {
return "";
# omit processing of escaped characters
- } else if ( line ~ /^\\[]\\`\*_\{\}\(\)#\+-\.![]/) {
- return substr(line, 2, 1) inline( substr(line, 3) );
+ } else if ( line ~ /^\\./) {
+ return HTML(substr(line, 2, 1)) inline( substr(line, 3) );
# hard brakes
} else if ( match(line, /^ \n/) ) {
@@ -130,7 +134,7 @@ function inline( line, LOCAL, len, code, href, 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)
+ gsub( /^ | $/, "", code)
# escape HTML within code span
gsub( /&/, "\\&", code ); gsub( //, "\\>", code );
return "" code "" inline( substr( line, len + 1 ) )
@@ -194,16 +198,16 @@ function inline( line, LOCAL, len, code, href, guard ) {
title = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/, "\\4", "g", substr(line, 1, len) );
attrib = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?/, "\\6", "g", substr(line, 1, len) );
if ( title && attrib ) {
- return "![\""](\"" "\\"\"")
" \
+ return "" \
inline( substr( line, len + 1) );
} else if ( title ) {
- return "" \
+ return "" \
inline( substr( line, len + 1) );
} else if ( attrib ) {
- return "" \
+ return "" \
inline( substr( line, len + 1) );
} else {
- return "" \
+ return "" \
inline( substr( line, len + 1) );
}
@@ -214,10 +218,10 @@ function inline( line, LOCAL, len, code, href, guard ) {
id = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\].*/, "\\2", 1, substr(line, 1, len) );
if ( ! id ) id = text;
if ( rl_href[id] && rl_title[id] ) {
- return "" \
+ return "" \
inline( substr( line, len + 1) );
} else if ( rl_href[id] ) {
- return "" \
+ return "" \
inline( substr( line, len + 1) );
} else {
return "" HTML(substr(line, 1, len)) inline( substr(line, len + 1) );
@@ -305,8 +309,43 @@ function inline( line, LOCAL, len, code, href, guard ) {
}
}
-function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib ) {
- gsub( /^\n+|\n+$/, "", block );
+function headline( hlvl, htxt, attrib, LOCAL, sec, n, HL) {
+ match(hstack, /([0-9]+( [0-9]+){5})$/); 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;}
+
+ 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})$/, "", hstack);
+ hstack = hstack HL[1] " " HL[2] " " HL[3] " " HL[4] " " HL[5] " " HL[6];
+
+ return sec "" \
+ "" inline( htxt ) \
+ "" \
+ "\n";
+}
+
+# Nested Block, resets heading counters
+function _nblock( block, LOCAL, sec, n ) {
+ hstack = hstack " 0 0 0 0 0 0";
+
+ # Block Level
+ blvl++; BL[blvl]++;
+ for ( n = blvl + 1; n in BL; n++) { delete BL[n]; }
+
+ block = _block( block );
+ match(hstack, /([0-9]+( [0-9]+){5})$/); split( substr(hstack, RSTART), HL);
+ sec = ""; for ( n = 1; n <= 6; n++ ) { sec = sec (HL[n]?"":""); }
+
+ sub("( +[0-9]+){6} *$", "", hstack); blvl--;
+ return block sec;
+}
+
+function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, indent, list ) {
+ gsub( "(^\n+|\n+$)", "", block );
if ( block == "" ) {
return "";
@@ -343,8 +382,9 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
} 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) );
+ text = substr(block, 1, st - 1); gsub( /(^|\n)> /, "\n", text );
+ text = _nblock( text ); gsub( /^\n|\n$/, "", text )
+ return "" text "
\n\n" _block( substr(block, st + len) );
# Pipe Tables (pandoc / php md / gfm )
} else if ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?)\n" \
@@ -399,22 +439,25 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
"(\\|([^\n]+\\|)+\n)+" \
"(\\+(:?=+:?\\+)+)\n" \
"((\\|([^\n]+\\|)+\n)+" \
- "\\+(-+\\+)+(\n|$))+", \
- tread \
+ "\\+(-+\\+)+(\n|$))+" \
) || \
match( block, "^()()()" \
"(\\+(:?-+:?\\+)+)\n" \
"((\\|([^\n]+\\|)+\n)+" \
- "\\+(-+\\+)+(\n|$))+", \
- tread \
+ "\\+(-+\\+)+(\n|$))+" \
) ) {
len = RLENGTH; st = RSTART;
#initialize empty arrays
- split("", talign); split("", tarray); # split("", tread);
+ split("", talign); split("", tarray); split("", tread);
cols = 0; cnt=0; ttext = "";
+ # Column Count
+ cols = split( gensub( "^(\\+(:?-+:?\\+)+)(\n.*)*$", "\\1", 1, block), tread, /\+/) - 2;
+ # debug(" Cols: " gensub( "^(\\+(:?-+:?\\+)+)(\n.*)*$", "\\1", 1, block ));
+
# table alignment
- cols = split( gensub( /(^\+|\+$)/, "", "g", tread[4] ), 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";
@@ -432,9 +475,9 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
# table header
block = substr(block, match(block, /(\n|$)/) + 1 );
while ( match(block, "^\\|([^\n]+\\|)+\n") ) {
- cols = split( gensub( /(^\||\|$)/, "", "g", \
- gensub( /(^|[^\\])\\\|/, "\\1\\|", "g", \
- substr(block, 1, match(block, /(\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++)
@@ -443,7 +486,7 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
ttext = "\n"
for (cnt = 1; cnt <= cols; cnt++)
- ttext = ttext "| " _block(tarray[cnt]) " | "
+ ttext = ttext "" _nblock(tarray[cnt]) " | "
ttext = ttext "
\n"
}
@@ -466,20 +509,20 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
ttext = ttext ""
for (cnt = 1; cnt <= cols; cnt++)
- ttext = ttext "| " _block(tarray[cnt]) " | "
+ ttext = ttext "" _nblock(tarray[cnt]) " | "
ttext = ttext "
\n"
}
- return "\n" _block(block);
+ return "\n" _nblock(block);
# 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) );
+
+ 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|$)|[ \t]*(\n|$))*/) ) {
@@ -493,13 +536,13 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
# Fenced Divs (pandoc, custom)
} else if ( match( block, /^(:::+)/ ) ) {
guard = substr( block, 1, RLENGTH );
- code = gensub(/^[^\n]+\n/, "", 1, block);
+ 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 "" _block( substr(code, 1, st - 1) ) "
\n" \
+ return "" _nblock( substr(code, 1, st - 1) ) "
\n" \
_block( substr( code, st + len ) );
} else {
match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match( block, /$/ );
@@ -526,60 +569,57 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
_block( substr(block, st + len) );
}
- # 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]+.*$/, "", 1, list) );
+ # First Order Heading H1 + Attrib
+ } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n===+(\n|$)/ ) ) {
+ 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(/(^ | $)/, "", attrib);
- gsub("(^|\n) {0," indent "}", "\n", list);
- return "\n\n" _list( substr(list, 2) ) "
\n" _block( block );
+ return headline(1, text, attrib) _block( substr( block, len + 1 ) );
- # Ordered list
- } else if ( match( block, "^ ? ? ?([0-9]+|#)\\.[ \t]+[^\n]+(\n|$)" \
- "(([ \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|$)/ ) ) {
- len = RLENGTH;
- HL[1]++; HL[2] = 0; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
- return "" \
- inline( gensub( /\n.*$/, "", "g", block ) ) \
- "
\n\n" \
- _block( substr( block, len + 1 ) );
+ # First Order Heading H1
+ } else if ( match( block, /^([^\n]+)\n===+(\n|$)/ ) ) {
+ len = RLENGTH; text = substr(block, 1, len);
+ sub(/\n===+(\n.*)?$/, "", text);
- # Second Order Heading
- } else if ( match( block, /^[^\n]+\n---+(\n|$)/ ) ) {
- len = RLENGTH;
- HL[2]++; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
- return "" \
- inline( gensub( /\n.*$/, "", "g", block ) ) \
- "
\n\n" \
- _block( substr( block, len + 1) );
-
- # Nth Order Heading
- } else if ( match( block, /^#{1,6}[ \t]*[^\n]+([ \t]*#*)(\n|$)/ ) ) {
- len = RLENGTH;
- hlvl = length( gensub( /^(#{1,6}).*$/, "\\1", "g", block ) );
- htxt = gensub(/^#{1,6}[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[^\n#])+)([ \t]*#*)(\n.*)?$/, "\\1", 1, block);
- HL[hlvl]++; for ( n = hlvl + 1; n < 7; n++) { HL[n] = 0;}
- hid = HL[1]; for ( n = 2; n <= hlvl; n++) { hid = hid "." HL[n] ; }
- return "" inline( htxt ) \
- "\n\n" \
- _block( substr( block, len + 1) );
+ return headline(1, text, 0) _block( substr( block, len + 1 ) );
+
+ # Second Order Heading H2 + Attrib
+ } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n---+(\n|$)/ ) ) {
+ 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(/(^ | $)/, "", attrib);
+
+ return headline(2, text, attrib) _block( substr( block, len + 1) );
+
+ # Second Order Heading H2
+ } else if ( match( block, /^([^\n]+)\n---+(\n|$)/ ) ) {
+ len = RLENGTH; text = substr(block, 1, len);
+ sub(/\n---+(\n.*)?$/, "", text);
+
+ return headline(2, text, 0) _block( substr( block, len + 1) );
+
+ # Nth Order Heading H1 H2 H3 H4 H5 H6 + Attrib
+ } else if ( match( block, /^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*([ \t]*\{([a-zA-Z \t-]*)\})(\n|$)/ ) ) {
+ len = RLENGTH; text = attrib = substr(block, 1, len);
+ match(block, /^#{1,6}/); n = RLENGTH;
+
+ 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(/(^ | $)/, "", attrib);
+
+ return headline( n, text, attrib ) _block( substr( block, len + 1) );
+
+ # Nth Order Heading H1 H2 H3 H4 H5 H6
+ } else if ( match( block, /^(#{1,6})[ \t]*(([^ \t\n]+|[ \t]+[^ \t\n#]|[ \t]+#+[ \t]*[^ \t\n#])+)[ \t]*#*(\n|$)/ ) ) {
+ 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, /^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?(\n|$)/) ) {
@@ -589,25 +629,25 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
title = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?(\n.*)?$/, "\\4", "g", block);
attrib = gensub(/^!\[([^]]*)\]\(([^"\)]+)([ \t]+"([^"]+)")?\)(\{([a-zA-Z \t-]*)\})?(\n.*)?$/, "\\6", "g", block);
if ( title && attrib ) {
- return "" \
- "" \
+ return "" \
+ "" \
"" inline(title) "" \
"\n\n" \
_block( substr( block, len + 1) );
} else if ( title ) {
- return "" \
- "" \
+ return "" \
+ "" \
"" inline(title) "" \
"\n\n" \
_block( substr( block, len + 1) );
} else if ( attrib ) {
- return "" \
- "" \
+ return "" \
+ "" \
"\n\n" \
_block( substr( block, len + 1) );
} else {
- return "" \
- "" \
+ return "" \
+ "" \
"\n\n" \
_block( substr( block, len + 1) );
}
@@ -619,14 +659,14 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
id = gensub(/^!\[([^\n]*)\] ?\[([^\n]*)\](\n.*)?$/, "\\2", 1, block);
if ( ! id ) id = text;
if ( rl_href[id] && rl_title[id] ) {
- return "" \
- "" \
+ return "" \
+ "" \
"" inline(rl_title[id]) "" \
"\n\n" \
_block( substr( block, len + 1) );
} else if ( rl_href[id] ) {
- return "" \
- "" \
+ return "" \
+ "" \
"\n\n" \
_block( substr( block, len + 1) );
} else {
@@ -637,7 +677,52 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
} else if ( AllowMacros && match( block, /^<<(([^>]|>[^>])+)>>(\n|$)/) ) {
len = RLENGTH;
text = gensub(/^<<(([^>]|>[^>])+)>>(\n.*)?$/, "\\1", 1, block);
- return macro(text) _block(substr(block, len + 1));
+ return macro(text) _block(substr(block, len + 1) );
+
+ # Definition list
+ } else if (match( block, "^(([ \t]*\n)*[^:\n \t][^\n]+\n" \
+ "([ \t]*\n)* ? ? ?:[ \t][^\n]+(\n|$)" \
+ "(([ \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
+ } else if ( match( block, "(^|\n) ? ? ?[-+*][ \t][^\n]+(\n|$)" \
+ "(([ \t]*\n)* ? ? ?[-+*][ \t][^\n]+(\n|$)" \
+ "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \
+ "|[^\n \t][^\n]+(\n|$))*" ) ) {
+ st = RSTART; len = RLENGTH; list = substr( block, RSTART, RLENGTH);
+ sub("^\n", "", list); match(list, "^ ? ? ?[-+*]"); indent = RLENGTH;
+ gsub( "(^|\n) {0," indent - 1 "}", "\n", list); sub("^\n", "", list);
+
+ text = substr(block, 1, st - 1); block = substr(block, st + len);
+ if (match( list, "\n([0-9]+\\.|#\\.)[ \t]" )) {
+ block = substr(list, RSTART + 1) block;
+ list = substr(list, 1, RSTART);
+ }
+
+ return _block( text ) "\n" _list( list, "[-+*]" ) "
\n" _block( block );
+
+ # Ordered list
+ } else if ( match( block, "(^|\n) ? ? ?([0-9]+\\.|#\\.)[ \t][^\n]+(\n|$)" \
+ "(([ \t]*\n)* ? ? ?([0-9]+\\.|#\\.)[ \t][^\n]+(\n|$)" \
+ "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \
+ "|[^\n \t][^\n]+(\n|$))*" ) ) {
+ st = RSTART; len = RLENGTH; list = substr( block, RSTART, RLENGTH);
+ sub("^\n", "", list); match(list, "^ ? ? ?[0-9#]"); indent = RLENGTH;
+ gsub( "(^|\n) {0," indent - 1 "}", "\n", list); sub("^\n", "", list);
+
+ text = substr(block, 1, st - 1); block = substr(block, st + len);
+ if (match( list, "\n[-+*][ \t]" )) {
+ block = substr(list, RSTART + 1) block;
+ list = substr(list, 1, RSTART);
+ }
+
+ return _block( text ) "\n" _list( list, "([0-9]+\\.|#\\.)" ) "
\n" _block( block );
# Split paragraphs
} else if ( match( block, /(^|\n)[[:space:]]*(\n|$)/) ) {
@@ -656,52 +741,56 @@ function _block( block, LOCAL, st, len, hlvl, htxt, guard, code, indent, attrib
}
}
-function _list( block, last, LOCAL, p) {
- if ( ! length(block) ) return "";
- gsub(/^([-+*]|[0-9]+\.|#\.)( ? ? ?|\t)/, "", block)
+function _list (block, mark, LOCAL, len, st, text, indent, task) {
+ if ( match(block, "^([ \t]*\n)*$")) return;
+ match(block, "^" mark "[ \t]"); indent = RLENGTH;
+ sub("^" mark "[ \t]", "", block);
- # 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 );
+ match( block, "\n" mark "[ \t][^\n]+(\n|$)" \
+ "(([ \t]*\n)* ? ? ?" mark "[ \t][^\n]+(\n|$)" \
+ "|([ \t]*\n)*( ? ? ?\t| +)[^\n]+(\n|$)" \
+ "|[^\n \t][^\n]+(\n|$))*");
+ (RLENGTH == -1) ? st = length(block) + 1 : st = RSTART;
+ text = substr(block, 1, st); block = substr(block, st + 1);
- # 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 );
+ gsub("\n {0," indent "}", "\n", text);
+
+ task = match( text, /^\[ \]/ ) ? "
" : \
+ match( text, /^\[-\]/ ) ? "" : \
+ match( text, /^\[\/\]/ ) ? "" : \
+ match( text, /^\[\?\]/ ) ? "" : \
+ match( text, /^\[[xX]\]/) ? "" : "";
+ sub(/^\[[-? /xX]\]/, "", text);
+
+ text = _nblock( text );
+ if (match( text, "^(]|\n$" ))
+ gsub( "(^
|
\n$)", "", text);
+
+ return task text "\n" _list(block, mark);
+}
+
+function _dlist (block, LOCAL, len, st, text, indent, 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|$))*" \
+ )) {
+ len = RLENGTH; text = substr(block, 1, len);
+ sub( "^([ \t]*\n)*", "", text);
+ match(text, "^ ? ? ?:(\t| +)"); indent = RLENGTH;
+ sub( "^ ? ? ?:(\t| +)", "", text);
+ gsub( "(^|\n) {0," indent "}", "\n", text );
+
+ text = _nblock(text);
+ if (match( text, "^(]|\n$" ))
+ gsub( "(^
|
\n$)", "", text);
+
+ return "" text "\n" _dlist( substr(block, len + 1) );
}
- sub( /\n$/, "", p );
-
- # Task List (pandoc, custom)
- if ( p ~ /^\[ \].*/ ) { return "" \
- substr(p, 4) "\n" _list( block, last );
- } else if ( p ~ /^\[-\].*/ ) { return "" \
- substr(p, 4) "\n" _list( block, last );
- } else if ( p ~ /^\[\?\].*/ ) { return "" \
- substr(p, 4) "\n" _list( block, last );
- } else if ( p ~ /^\[\/\].*/ ) { return "" \
- substr(p, 4) "\n" _list( block, last );
- } else if ( p ~ /^\[[xX]\].*/ ) { return "" \
- substr(p, 4) "\n" _list( block, last );
- } else if ( p ~ /^\[ \].*/ ) { return "
" \
- substr(p, 7) "
\n" _list( block, last );
- } else if ( p ~ /^\[-\].*/ ) { return "
" \
- substr(p, 7) "
\n" _list( block, last );
- } else if ( p ~ /^\[\?\].*/ ) { return "
" \
- substr(p, 7) "
\n" _list( block, last );
- } else if ( p ~ /^\[\/\].*/ ) { return "
" \
- substr(p, 7) "
\n" _list( block, last );
- } else if ( p ~ /^\[[xX]\].*/ ) { return "
" \
- substr(p, 7) "
\n" _list( block, last );
- } else { return "" p "\n" _list( block, last ); }
}
BEGIN {
@@ -709,6 +798,7 @@ BEGIN {
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";
# Buffering of full file ist necessary, e.g. to find reference links
while (getline) { file = file $0 "\n"; }
@@ -732,5 +822,5 @@ 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 );
}