The StandardAnalyzer is the most advanced of the available analyzers. If it were implemented in Ruby it would look like this;
class StandardAnalyzer def initialize(stop_words = FULL_ENGLISH_STOP_WORDS, lower = true) @lower = lower @stop_words = stop_words end def token_stream(field, str) ts = StandardTokenizer.new(str) ts = LowerCaseFilter.new(ts) if @lower ts = StopFilter.new(ts, @stop_words) ts = HyphenFilter.new(ts) end end
As you can see it makes use of the StandardTokenizer and you can also add your own list of stopwords if you wish.
Create a new StandardAnalyzer which downcases tokens by default but can optionally leave case as is. Lowercasing will be done based on the current locale. You can also set the list of stop-words to be used by the StopFilter.
set to false if you don't want the field's tokens to be downcased
list of stop-words to pass to the StopFilter
static VALUE frb_standard_analyzer_init(int argc, VALUE *argv, VALUE self) { bool lower; VALUE rlower, rstop_words; Analyzer *a; #ifndef POSH_OS_WIN32 if (!frb_locale) frb_locale = setlocale(LC_CTYPE, ""); #endif rb_scan_args(argc, argv, "02", &rstop_words, &rlower); lower = ((rlower == Qnil) ? true : RTEST(rlower)); if (rstop_words != Qnil) { char **stop_words = get_stopwords(rstop_words); a = mb_standard_analyzer_new_with_words((const char **)stop_words, lower); free(stop_words); } else { a = mb_standard_analyzer_new(lower); } Frt_Wrap_Struct(self, NULL, &frb_analyzer_free, a); object_add(a, self); return self; }