Class: Linguist::Tokenizer

Inherits:
Object
  • Object
show all
Defined in:
lib/linguist/tokenizer.rb,
ext/linguist/linguist.c

Overview

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.

Class Method Summary collapse

Instance Method Summary collapse

Class Method Details

.tokenize(data) ⇒ Object

Public: Extract tokens from data

data - String to tokenize

Returns Array of token Strings.



16
17
18
 
# File 'lib/linguist/tokenizer.rb', line 16

def self.tokenize(data)
  new.extract_tokens(data)
end

Instance Method Details

#extract_tokens(rb_data) ⇒ Object 



8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
 
# File 'ext/linguist/linguist.c', line 8

static VALUE rb_tokenizer_extract_tokens(VALUE self, VALUE rb_data) {
	YY_BUFFER_STATE buf;
	yyscan_t scanner;
	VALUE extra;
	VALUE ary;
	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 = 0;
		r = linguist_yylex(scanner);
		if (extra) {
			rb_ary_push(ary, extra);
		}
	} while (r);

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

	return ary;
}