"tokens while iterating. (default: none)",
true, "CLASSNAME", "Tokenizing Options");
options.addOption('F', "tokenFilter", "filters to apply to the input " +
"token stream", true, "FILTER_SPEC",
"Tokenizing Options");
options.addOption('C', "compoundWords", "a file where each line is a " +
"recognized compound word", true, "FILE",
"Tokenizing Options");
options.addOption('z', "wordLimit", "Set the maximum number of words " +
"an document can return",
true, "INT", "Tokenizing Options");