allow link/image src pattern with whitespace, avoid confusion with comment

diff --git a/markdown.awk b/markdown.awk
index 249f5074b213b68511f94009b5d708db99b0b51a..7e29c572213e553df07563099cf52683ed11b960 100755 (executable)
--- a/markdown.awk
+++ b/markdown.awk
@@ -178,12 +178,12 @@ function inline( line, LOCAL, len, text, code, href, guard ) {
     return substr( line, 1, len) inline(substr(line, len + 1));
 
   # inline links
-  } else if ( match(line, "^" lii "\\([\\n\\t ]*" lid "([\\n\\t ]+" lit ")?[\\n\\t ]*\\)") ) {
+  } 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 ]*\\)$", "", title); sub("^[\\n\\t ]+", "", title);
+    sub("^\\[", "", text); sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)$", "", 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, /^<.*>$/) ) { sub(/^</, "", href); sub(/>$/, "", href); }
          if ( match(title, /^".*"$/) ) { sub(/^"/, "", title); sub(/"$/, "", title); }
@@ -210,20 +210,20 @@ function inline( line, LOCAL, len, text, code, href, guard ) {
     }
 
   # inline images
-  } else if ( match(line, "^!" lix "\\([\\n\\t ]*" lid "([\\n\\t ]+" lit ")?[\\n\\t ]*\\)(\\{[a-zA-Z \\t-]*\\})?") ) {
+  } 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-]*\\})?$", "", text);
+    sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", text);
 
-    sub("^!" lix "\\([\\n\\t ]*", "", href);
-    sub("([\\n\\t ]+" lit ")?[\\n\\t ]*\\)(\\{[a-zA-Z \\t-]*\\})?$", "", href);
+    sub("^!" lix "\\([\n\t ]*", "", href);
+    sub("([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", href);
 
-    sub("^!" lix "\\([\\n\\t ]*" lid, "", title);
-    sub("[\\n\\t ]*\\)(\\{[a-zA-Z \\t-]*\\})?$", "", title);
-    sub("^[\\n\\t ]+", "", title);
+    sub("^!" lix "\\([\n\t ]*" lid, "", title);
+    sub("[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?$", "", title);
+    sub("^[\n\t ]+", "", title);
 
-    sub("^!" lix "\\([\\n\\t ]*" lid "([\\n\\t ]+" lit ")?[\\n\\t ]*\\)", "", attrib);
+    sub("^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)", "", attrib);
     sub(/^\{[ \t]*/, "", attrib); sub(/[ \t]*\}$/, "", attrib); gsub(/[ \t]+/, " ", attrib);
 
     if ( match(href, /^<.*>$/) ) { sub(/^</, "", href); sub(/>$/, "", href); }
@@ -639,21 +639,21 @@ function _block( block, LOCAL, st, len, text, title, attrib, href, guard, code,
     return headline( n, text, 0 ) _block( substr( block, len + 1) );
 
   # block images (wrapped in <figure>)
-  } else if ( match(block, "^!" lix "\\([\\n\\t ]*" lid "([\\n\\t ]+" lit ")?[\\n\\t ]*\\)(\\{[a-zA-Z \\t-]*\\})?(\\n|$)") ) {
+  } else if ( match(block, "^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n|$)") ) {
     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.*)?$", "", text);
+    sub("\\]\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", text);
 
-    sub("^!" lix "\\([\\n\\t ]*", "", href);
-    sub("([\\n\\t ]+" lit ")?[\\n\\t ]*\\)(\\{[a-zA-Z \\t-]*\\})?(\\n.*)?$", "", href);
+    sub("^!" lix "\\([\n\t ]*", "", href);
+    sub("([\n\t ]+" lit ")?[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", href);
 
-    sub("^!" lix "\\([\\n\\t ]*" lid, "", title);
-    sub("[\\n\\t ]*\\)(\\{[a-zA-Z \\t-]*\\})?(\\n.*)?$", "", title);
-    sub("^[\\n\\t ]+", "", title);
+    sub("^!" lix "\\([\n\t ]*" lid, "", title);
+    sub("[\n\t ]*\\)(\\{[a-zA-Z \t-]*\\})?(\n.*)?$", "", title);
+    sub("^[\n\t ]+", "", title);
 
-    sub("^!" lix "\\([\\n\\t ]*" lid "([\\n\\t ]+" lit ")?[\\n\\t ]*\\)", "", attrib);
-    sub("(\\n.*)?$", "", attrib);
+    sub("^!" lix "\\([\n\t ]*" lid "([\n\t ]+" lit ")?[\n\t ]*\\)", "", attrib);
+    sub("(\n.*)?$", "", attrib);
     sub(/^\{[ \t]*/, "", attrib); sub(/[ \t]*\}$/, "", attrib); gsub(/[ \t]+/, " ", attrib);
 
     if ( match(href, /^<.*>$/) ) { sub(/^</, "", href); sub(/>$/, "", href); }
@@ -834,11 +834,11 @@ BEGIN {
   iea =    "\\*([^\\*[:space:]]|[^\\*[:space:]]" na "[^\\*[:space:]])\\*"     # inner <em> (asterisk)
   isa = "\\*\\*([^\\*[:space:]]|[^\\*[:space:]]" na "[^\\*[:space:]])\\*\\*"  # inner <strong> (asterisk)
 
-  lix="\\[(\\\\[^\\n]|[^]\\n\\\\[])*\\]"  # link text
-  lid="(<(\\\\[^\\n]|[^\\n<>\\\\])*>|([^<\\n\\t ()\\\\]|\\\\[^\\n])(\\\\[\\n]|[^\\n\\t ()\\\\])*)"  # link dest
-  lit="(\"(\\\\.|[^\"\\\\])*\"|'(\\\\.|[^'\\\\])*'|\\((\\\\.|[^()\\\\])*\\))"  # link text
+  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\\\\[])*\\]"
+  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"; }