in reply to Removing HTML Tags from a file

#!/usr/bin/perl use Switch; $/ = \1; $state = 'DOCUMENT'; while (<>) { switch ($state) { case 'DOCUMENT' { $state = 'TAG' if /\x3C/; } case 'TAG' { $state = /\x21/ ? 'DECLARATION' : 'ELEMENT'; } case 'ELEMENT' { $state = 'SINGLE_QUOTE' if /\x27/; $state = 'DOUBLE_QUOTE' if /\x22/; $state = 'DOCUMENT_TO_BE' if /\x3E/; } case 'SINGLE_QUOTE' { $state = 'ELEMENT' if /\x27/; } case 'DOUBLE_QUOTE' { $state = 'ELEMENT' if /\x22/; } case 'DECLARATION' { die "Parse error" unless /\x2D/; $state = 'COMMENT_START'; } case 'COMMENT_START' { die "Parse error" unless /\x2D/; $state = 'COMMENT'; } case 'COMMENT' { $state = 'COMMENT_END' if /\x2D/; } case 'COMMENT_END' { $state = /\x2D/ ? 'COMMENT_TRAIL' : 'COMMENT'; } case 'COMMENT_TRAIL' { die "Parse error" unless /[\x22\x3E\s]/; $state = 'COMMENT_START' if /\x22/; $state = 'DOCUMENT_TO_BE' if /\x3E/; } } print $state eq 'DOCUMENT' ? $_ : " "; $state = 'DOCUMENT' if $state eq 'DOCUMENT_TO_BE' }