improved anchor search, fixes #9

Author: ekalinin

gh-md-toc

@@ -9,14 +9,18 @@
 #  2. Discard rows where no substring 'user-content-' (github's markup):
 #       awk '/user-content-/ { ...
 #
-#  3. Get header level and insert corresponding number of spaces before '*':
+#  3.1 Get last number in each row like ' ... </span></a>sitemap.js</h1>'.
+#      It's a level of the current header (NF — number of fields):
+#       substr($NF, length($NF)-1, 1)
+#
+#  3.2 Get level from 3.1 and insert corresponding number of spaces before '*':
 #       sprintf("%*s", substr($NF, length($NF)-1, 1)*2, " ")
 #
 #  4. Find head's text and insert it inside "* [ ... ]":
 #       substr($0, match($0, /a>.*<\/h/)+2, RLENGTH-5)
 #
 #  5. Find anchor and insert it inside "(...)":
-#       substr($4, 7)
+#       substr($0, match($0, "href=\".*\" ")+5, RLENGTH-6)
 #
 
 gh_toc_version="0.4.0"
@@ -102,7 +106,7 @@ gh_toc(){
 #
 gh_toc_grab() {
     awk -v "gh_url=$1" '/user-content-/ {
-    print sprintf("%*s", substr($NF, length($NF)-1, 1)*2, " ") "* [" substr($0, match($0, /a>.*<\/h/)+2, RLENGTH-5)"](" gh_url substr($4, 7, length($4)-7) ")"}'
+    print sprintf("%*s", substr($NF, length($NF)-1, 1)*2, " ") "* [" substr($0, match($0, /a>.*<\/h/)+2, RLENGTH-5)"](" gh_url substr($0, match($0, "href=\".*\" ")+6, RLENGTH-8) ")"}'
 }
 
 #