ass-core 0.1.2

High-performance ASS subtitle format parser and analyzer
Documentation 
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
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114

//! Basic construction and core token-type tokenization tests for [`AssTokenizer`].

use crate::tokenizer::{AssTokenizer, TokenType};

#[test]
fn tokenizer_new_without_bom() {
    let tokenizer = AssTokenizer::new("Hello World");
    assert_eq!(tokenizer.position(), 0);
    assert_eq!(tokenizer.line(), 1);
    assert_eq!(tokenizer.column(), 1);
}

#[test]
fn tokenizer_new_with_bom() {
    let tokenizer = AssTokenizer::new("\u{FEFF}Hello World");
    assert_eq!(tokenizer.position(), 3); // BOM is 3 bytes
    assert_eq!(tokenizer.line(), 1);
    assert_eq!(tokenizer.column(), 1);
}

#[test]
fn tokenize_empty_string() {
    let mut tokenizer = AssTokenizer::new("");
    let result = tokenizer.next_token().unwrap();
    assert!(result.is_none());
}

#[test]
fn tokenize_whitespace_only() {
    let mut tokenizer = AssTokenizer::new("   \t  ");
    let result = tokenizer.next_token().unwrap();
    assert!(result.is_none());
}

#[test]
fn tokenize_section_header_basic() {
    let mut tokenizer = AssTokenizer::new("[Script Info]");

    let token1 = tokenizer.next_token().unwrap().unwrap();
    assert_eq!(token1.token_type, TokenType::SectionHeader);
    assert_eq!(token1.span, "[Script Info");
    assert_eq!(token1.line, 1);
    assert_eq!(token1.column, 1);

    let token2 = tokenizer.next_token().unwrap().unwrap();
    assert_eq!(token2.token_type, TokenType::SectionClose);
    assert_eq!(token2.span, "]");

    let result = tokenizer.next_token().unwrap();
    assert!(result.is_none());
}

#[test]
fn tokenize_section_header_with_spaces() {
    let mut tokenizer = AssTokenizer::new("[ V4+ Styles ]");

    let token1 = tokenizer.next_token().unwrap().unwrap();
    assert_eq!(token1.token_type, TokenType::SectionHeader);
    assert_eq!(token1.span, "[ V4+ Styles ");

    let token2 = tokenizer.next_token().unwrap().unwrap();
    assert_eq!(token2.token_type, TokenType::SectionClose);
}

#[test]
fn tokenize_field_with_colon() {
    let mut tokenizer = AssTokenizer::new("Title: Test Script");

    let token1 = tokenizer.next_token().unwrap().unwrap();
    assert_eq!(token1.token_type, TokenType::Text);
    assert_eq!(token1.span, "Title");

    let token2 = tokenizer.next_token().unwrap().unwrap();
    assert_eq!(token2.token_type, TokenType::Colon);
    assert_eq!(token2.span, ":");

    let token3 = tokenizer.next_token().unwrap().unwrap();
    assert_eq!(token3.token_type, TokenType::Text);
    assert_eq!(token3.span, " Test Script");
}

#[test]
fn tokenize_style_override_simple() {
    let mut tokenizer = AssTokenizer::new("{\\b1}");

    let token1 = tokenizer.next_token().unwrap().unwrap();
    assert_eq!(token1.token_type, TokenType::OverrideBlock);
    assert_eq!(token1.span, "{\\b1");

    let token2 = tokenizer.next_token().unwrap().unwrap();
    assert_eq!(token2.token_type, TokenType::OverrideClose);
    assert_eq!(token2.span, "}");
}

#[test]
fn tokenize_style_override_complex() {
    let mut tokenizer = AssTokenizer::new("{\\c&H0000FF&\\fs20}Hello{\\r}");

    let token1 = tokenizer.next_token().unwrap().unwrap();
    assert_eq!(token1.token_type, TokenType::OverrideBlock);

    let token2 = tokenizer.next_token().unwrap().unwrap();
    assert_eq!(token2.token_type, TokenType::OverrideClose);

    let token3 = tokenizer.next_token().unwrap().unwrap();
    assert_eq!(token3.token_type, TokenType::Text);
    assert_eq!(token3.span, "Hello");

    let token4 = tokenizer.next_token().unwrap().unwrap();
    assert_eq!(token4.token_type, TokenType::OverrideBlock);

    let token5 = tokenizer.next_token().unwrap().unwrap();
    assert_eq!(token5.token_type, TokenType::OverrideClose);
}