File: test_wordtokenizer_main.cpp

package info (click to toggle)
source-highlight 3.1.6-1.1
  • links: PTS
  • area: main
  • in suites: wheezy
  • size: 10,080 kB
  • sloc: sh: 11,246; cpp: 9,911; ansic: 9,506; makefile: 1,852; lex: 1,184; yacc: 1,009; php: 213; perl: 211; awk: 98; erlang: 94; lisp: 90; java: 77; ruby: 69; python: 61; asm: 43; ml: 38; ada: 36; haskell: 27; xml: 23; cs: 11; sql: 8; tcl: 6; sed: 4
file content (42 lines) | stat: -rw-r--r-- 1,199 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
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
39
40
41
42
#include <iostream>

#include "asserttestexit.h"
#include "srchilite/wordtokenizer.h"
#include "srchilite/tostringcollection.h"

using namespace std;
using namespace srchilite;

static ostream &operator <<(ostream &os, const WordTokenizer::WordTokenizerResults::value_type &);

ostream &operator <<(ostream &os, const WordTokenizer::WordTokenizerResults::value_type &token) {
    if (token.first.size()) {
        os << "space: \"" << token.first << "\"" << endl;
    } else {
        os << "word : \"" << token.second << "\"" << endl;
    }

    return os;
}

int main() {
    WordTokenizer::WordTokenizerResults tokens;

    WordTokenizer::tokenize(" Here  are\t \t some_words!", tokens);

    cout << "tokens: " << collectionToString(&tokens) << endl;

    WordTokenizer::WordTokenizerResults::const_iterator tok = tokens.begin();

    assertTrue(tok != tokens.end());
    assertEquals(" ", (tok++)->first);
    assertEquals("Here", (tok++)->second);
    assertEquals("  ", (tok++)->first);
    assertEquals("are", (tok++)->second);
    assertEquals("\t \t ", (tok++)->first);
    assertEquals("some_words!", (tok++)->second);

    cout << "test_wordtokenizer: SUCCESS" << endl;

    return 0;
}