foreach (@files){ my $excerpt; my $match; my $start1 = time; #measure time for each file my $duration1; my $data = slurp($_); if($data!~m/table\s?of\s?contents?|\sindex\spart\s(?:1|I)/i){ if($data=~m/(?:Item|ITEM)[Ss]?\s?(?:\.|\-|:|\-\-|\,)?\s?(?:1|I)\s?(?:\.|\-|\:|\-\-|\,)?\s?(?:Description|DESCRIPTION)?\s?(?:[Oo][Ff])?\s?(?:[Tt][Hh][Ee])?\s?(?:Busine\s?ss|BUSINE\s?SS|Company|COMPANY)\s?(?:\.|\-|:|\-\-|\,|\()? (.*?)\s?(?:Item|ITEM)[Ss]?\s?(?:\.|\:|\-\-|\-|\,)?\s?(?:I|1A|1B|2)\s?(?:\.|\:|\-\-|\-|\,)?/x){ $excerpt=$1; $match=3; goto record; } if($data=~m/(?:Business\s?Development|BUSINESS\s?DEVELOPMENT)\s? (.*?)\s?(?:Item|ITEM)[Ss]?\s?(?:\.|\-|:|\-\-|\,)?\s?(?:I|1A|1B|2)\s?(?:\.|\:|\-\-|\-|\,)?/x){ $excerpt=$1; $match=4; goto record; } if($data=~m/(?:PART|Part)\s?(?:\.|\-|\:|\-\-|\,)?\s?(?:I|1)\s?(?:\.|\-|:|\-\-|\,)?\s?(?:BUSINESS|Business|GENERAL|general) (.*?)\s?(?:Item|ITEM)[Ss]?\s?(?:I|1A|1B|2|3)\s?(?:\:|\-|\,|\-\-|\.|\,)?/x){ $excerpt=$1; $match=5; goto record; } if($data=~m/(?:Item|ITEM)?[Ss]?\s?1\s?(?:\.|\-|\:|\-\-|\,)?(?:\.|\-|\:|\-\-|\,)?\s?(?:1A)?\s?(?:\.|\-|\:|\-\-|\,)?\s?(?:AND|[Aa]nd|\&)\s?2\s?(?:\.|\:|\-|\-\-|\,)?\s?(?:\.|\-|\:|\-\-|\,)?\s? (?:[Bb]usiness\s?\,\s?[Rr]isks?\s?[Ff]actors\s?(?:[Aa]nd|AND|\&)\s?[Pp]roperties|BUSINESS\s?\,\s?RISK\s?FACTORS?\s?AND\s?PROPERTIES) (.*?)\s?(?:Item|ITEM)\s?[Ss]?\s?(?:\:|\-|\,|\-\-|\.)?\s?(?:1A|1B|2|I|3)\s?(?:\.|\:|\-|\-\-|\,)?/x){ $excerpt=$1; $match=7; goto record; } if($data=~m/(?:Item|ITEM)[Ss]?\s?(?:\.|\-|:|\-\-|\,)?\s?(?:1|I)\s?(?:\.|\-|:|\-\-|,)?\s?(?:BUSINESS|[Bb]usiness)\s?(?:\.|\-|\:|\,)? (.*?)\s?(?:Item|ITEM)\s?(?:\.|\:|\-|\-\-|\,)?\s?(?:I|1A|1B|2)\s?(?:\.|\:|\-|\-\-|\,)?/x){ $match=8; $excerpt=$1; goto record; } } record: if(defined($excerpt)){ $excerpt=~s/\s{2,}|\.\s|\"|\(|\)|\,|\'|\r|\n/ /g; $excerpt=~s/^\s+|\s+$//; #trim $duration1 = ceil((time - $start1)/60); #measure execution time for each file until printing print "$match \n $duration1 \n $excerpt \n"; } }