shithub: werc

Info  •  Files  •  Log  •  Branches

Ignore leading spaces/tabs when extracting a title from HTML files.

--- a/bin/werclib.rc

+++ b/bin/werclib.rc

@@ -102,7 +102,7 @@

     # As a backup we might want to pick the first 'non-tag' text in the file with:

     if(~ $"t '')

-        t=`{sed -n -e 's/^(<[^>]+>)*([^<]+).*/\2/p; 32q' < $1 | sed 1q}

+        t=`{sed -n -e 's/^[ 	]*(<[^>]+>)*([^<]+).*/\2/p; 32q' < $1 | sed 1q}

     echo $t

 }