X-Git-Url: https://git.plutz.net/?a=blobdiff_plain;f=markdown.awk;h=b5aa538055fe017b8c2b2827f23631f5d91d23b3;hb=d4da2a56ff96e4d6d79c246bdb0223f14ef3965e;hp=fbfc455355c14c6df2d34cd44a42daa8dee09794;hpb=e6442fb6aad465f6b0696b2ed1477d2dbc05bfc7;p=cgilite
diff --git a/markdown.awk b/markdown.awk
index fbfc455..b5aa538 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)
+# - [ ]
terminates 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)
@@ -89,13 +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 );
@@ -104,7 +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)
@@ -131,7 +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( /^ | $/, "", "g" , code)
+ gsub( /^ | $/, "", code)
# escape HTML within code span
gsub( /&/, "\\&", code ); gsub( /, "\\<", code ); gsub( />/, "\\>", code );
return "" code "
" inline( substr( line, len + 1 ) )
@@ -195,16 +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) );
}
@@ -215,10 +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) );
@@ -306,19 +309,43 @@ function inline( line, LOCAL, len, code, href, guard ) {
}
}
+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, st, len, hlvl, htxt, hlsav, sec, guard, code, indent, attrib ) {
- hlsav = HL[1] " " HL[2] " " HL[3] " " HL[4] " " HL[5] " " HL[6];
- HL[1] = 0; HL[2] = 0; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
+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})$/); split( substr(hstack, RSTART), HL);
sec = ""; for ( n = 1; n <= 6; n++ ) { sec = sec (HL[n]?"":""); }
- split(hlsav, HL);
+
+ sub("( +[0-9]+){6} *$", "", hstack); blvl--;
return block sec;
}
-function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, attrib ) {
- gsub( /^\n+|\n+$/, "", block );
+function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code, indent, list ) {
+ gsub( "(^\n+|\n+$)", "", block );
if ( block == "" ) {
return "";
@@ -355,8 +382,9 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at
} else if ( match( block, /^> /) ) {
match( block, /(^|\n)[[:space:]]*(\n|$)/ ) || match(block, /$/);
len = RLENGTH; st = RSTART;
- return "
\n" _nblock( 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$/, "", text )
+ return "" text "
\n\n" _block( substr(block, st + len) );
# Pipe Tables (pandoc / php md / gfm )
} else if ( match(block, "^((\\|)?([^\n]+\\|)+[^\n]+(\\|)?)\n" \
@@ -489,12 +517,12 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at
# Line Blocks (pandoc)
} else if ( match(block, /^\| [^\n]*(\n|$)(\| [^\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|$))*/) ) {
@@ -508,7 +536,7 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at
# Fenced Divs (pandoc, custom)
} else if ( match( block, /^(:::+)/ ) ) {
guard = substr( block, 1, RLENGTH );
- code = gensub(/^[^\n]+\n/, "", 1, block);
+ code = block; sub(/^[^\n]+\n/, "", code);
attrib = gensub(/^:::+[ \t]*\{?[ \t]*([^\}\n]*)\}?[ \t]*\n.*$/, "\\1", 1, block);
gsub(/[^a-zA-Z0-9_-]+/, " ", attrib);
gsub(/(^ | $)/, "", attrib);
@@ -541,63 +569,57 @@ function _block( block, LOCAL, st, len, hlvl, htxt, sec, guard, code, indent, at
_block( substr(block, st + len) );
}
- # Unordered list
- } else if ( match( block, "^ ? ? ?[-+*][ \t]+[^\n]+(\n|$)" \
- "(([ \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) );
-
- 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]+.*$/, "", 1, list) );
-
- gsub("(^|\n) {0," indent "}", "\n", list);
- return "\n\n" _list( substr(list, 2) ) "
\n" _block( block );
+ # First Order Heading H1 + Attrib
+ } else if ( match( block, /^([^\n]+)([ \t]*\{([^\}\n]+)\})\n===+(\n|$)/ ) ) {
+ 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(/(^ | $)/, "", attrib);
+
+ return headline(1, text, attrib) _block( substr( block, len + 1 ) );
# First Order Heading H1
- } else if ( match( block, /^[^\n]+\n===+(\n|$)/ ) ) {
- len = RLENGTH; sec = "";
- for ( n = 1; n <= 6; n++ ) { sec = sec (HL[n]?"":""); }
- HL[1]++; HL[2] = 0; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
- return sec "" \
- inline( gensub( /\n.*$/, "", "g", block ) ) \
- "
\n\n" \
- _block( substr( block, len + 1 ) );
+ } else if ( match( block, /^([^\n]+)\n===+(\n|$)/ ) ) {
+ 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(/(^ | $)/, "", attrib);
+
+ return headline(2, text, attrib) _block( substr( block, len + 1) );
# Second Order Heading H2
- } else if ( match( block, /^[^\n]+\n---+(\n|$)/ ) ) {
- len = RLENGTH; sec = "";
- for ( n = 2; n <= 6; n++ ) { sec = sec (HL[n]?"":""); }
- HL[2]++; HL[3] = 0; HL[4] = 0; HL[5] = 0; HL[6] = 0;
- return sec "" \
- "" inline( gensub( /\n.*$/, "", "g", block ) ) \
- "
\n\n" \
- _block( substr( block, len + 1) );
+ } else if ( match( block, /^([^\n]+)\n---+(\n|$)/ ) ) {
+ 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(/(^ | $)/, "", attrib);
+
+ return headline( n, text, attrib ) _block( substr( block, len + 1) );
# Nth Order Heading H1 H2 H3 H4 H5 H6
- } else if ( match( block, /^#{1,6}[ \t]*[^\n]+([ \t]*#*)(\n|$)/ ) ) {
- len = RLENGTH; sec = "";
- 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);
- for ( n = hlvl; n <= 6; n++ ) { sec = sec (HL[n]?"":""); }
- HL[hlvl]++; for ( n = hlvl + 1; n <= 6; n++) { HL[n] = 0;}
- hid = HL[1]; for ( n = 2; n <= hlvl; n++) { hid = hid "." HL[n] ; }
- return sec "" inline( htxt ) \
- "\n\n" \
- _block( substr( block, len + 1) );
+ } 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