class Linguist::Tokenizer

Generic programming language tokenizer.

Tokens are designed for use in the language bayes classifier. It strips any data strings or comments and preserves significant language symbols.

Public Class Methods

tokenize(data) click to toggle source

Public: Extract tokens from data

data - String to tokenize

Returns Array of token Strings.

# File lib/linguist/tokenizer.rb, line 16
def self.tokenize(data)
  new.extract_tokens(data)
end

Public Instance Methods

extract_tokens(p1) click to toggle source
static VALUE rb_tokenizer_extract_tokens(VALUE self, VALUE rb_data) {
        YY_BUFFER_STATE buf;
        yyscan_t scanner;
        struct tokenizer_extra extra;
        VALUE ary, s;
        long len;
        int r;

        Check_Type(rb_data, T_STRING);

        len = RSTRING_LEN(rb_data);
        if (len > 100000)
                len = 100000;

        linguist_yylex_init_extra(&extra, &scanner);
        buf = linguist_yy_scan_bytes(RSTRING_PTR(rb_data), (int) len, scanner);

        ary = rb_ary_new();
        do {
                extra.type = NO_ACTION;
                extra.token = NULL;
                r = linguist_yylex(scanner);
                switch (extra.type) {
                case NO_ACTION:
                        break;
                case REGULAR_TOKEN:
                        rb_ary_push(ary, rb_str_new2(extra.token));
                        free(extra.token);
                        break;
                case SHEBANG_TOKEN:
                        s = rb_str_new2("SHEBANG#!");
                        rb_str_cat2(s, extra.token);
                        rb_ary_push(ary, s);
                        free(extra.token);
                        break;
                case SGML_TOKEN:
                        s = rb_str_new2(extra.token);
                        rb_str_cat2(s, ">");
                        rb_ary_push(ary, s);
                        free(extra.token);
                        break;
                }
        } while (r);

        linguist_yy_delete_buffer(buf, scanner);
        linguist_yylex_destroy(scanner);

        return ary;
}