tldr-cli 0.1.2

CLI binary for TLDR code analysis tool
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
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142

use std::collections::HashSet;

/// Per-language configuration for tree-sitter to difftastic Syntax conversion.
pub struct LangConfig {
    /// Tree-sitter node kinds that should be flattened into a single Syntax::Atom.
    pub atom_nodes: HashSet<&'static str>,
    /// Pairs of opening/closing tokens that define Syntax::List delimiters.
    pub delimiter_tokens: Vec<(&'static str, &'static str)>,
}

/// All our 18 languages prefer inner delimiters (C-like syntax).
/// Difftastic's prefer_outer is only for Lisp/JSON/TOML/HCL/SQL which we don't support.
pub const PREFER_OUTER_DELIMITER: bool = false;

impl LangConfig {
    pub fn for_language(lang: &str) -> LangConfig {
        match lang {
            "python" => LangConfig {
                atom_nodes: ["string"].into_iter().collect(),
                delimiter_tokens: vec![("(", ")"), ("[", "]"), ("{", "}")],
            },
            "typescript" => LangConfig {
                atom_nodes: ["string", "template_string", "regex", "predefined_type"]
                    .into_iter()
                    .collect(),
                delimiter_tokens: vec![("{", "}"), ("(", ")"), ("[", "]"), ("<", ">")],
            },
            "javascript" => LangConfig {
                atom_nodes: ["string", "template_string", "regex"].into_iter().collect(),
                delimiter_tokens: vec![("[", "]"), ("(", ")"), ("{", "}"), ("<", ">")],
            },
            "go" => LangConfig {
                atom_nodes: ["interpreted_string_literal", "raw_string_literal"]
                    .into_iter()
                    .collect(),
                delimiter_tokens: vec![("{", "}"), ("[", "]"), ("(", ")")],
            },
            "rust" => LangConfig {
                atom_nodes: ["char_literal", "string_literal", "raw_string_literal"]
                    .into_iter()
                    .collect(),
                delimiter_tokens: vec![("{", "}"), ("(", ")"), ("[", "]"), ("|", "|"), ("<", ">")],
            },
            "java" => LangConfig {
                atom_nodes: [
                    "string_literal",
                    "boolean_type",
                    "integral_type",
                    "floating_point_type",
                    "void_type",
                ]
                .into_iter()
                .collect(),
                delimiter_tokens: vec![("(", ")"), ("{", "}"), ("[", "]")],
            },
            "c" => LangConfig {
                atom_nodes: ["string_literal", "char_literal"].into_iter().collect(),
                delimiter_tokens: vec![("(", ")"), ("{", "}"), ("[", "]")],
            },
            "cpp" | "c++" => LangConfig {
                atom_nodes: ["string_literal", "char_literal"].into_iter().collect(),
                delimiter_tokens: vec![("(", ")"), ("{", "}"), ("[", "]"), ("<", ">")],
            },
            "ruby" => LangConfig {
                atom_nodes: ["string", "heredoc_body", "regex"].into_iter().collect(),
                delimiter_tokens: vec![
                    ("{", "}"),
                    ("(", ")"),
                    ("[", "]"),
                    ("|", "|"),
                    ("def", "end"),
                    ("begin", "end"),
                    ("class", "end"),
                ],
            },
            "kotlin" => LangConfig {
                atom_nodes: [
                    "nullable_type",
                    "string_literal",
                    "line_string_literal",
                    "character_literal",
                ]
                .into_iter()
                .collect(),
                delimiter_tokens: vec![("(", ")"), ("{", "}"), ("[", "]"), ("<", ">")],
            },
            "swift" => LangConfig {
                atom_nodes: ["line_string_literal"].into_iter().collect(),
                delimiter_tokens: vec![("{", "}"), ("(", ")"), ("[", "]"), ("<", ">")],
            },
            "csharp" | "c#" => LangConfig {
                atom_nodes: [
                    "string_literal",
                    "verbatim_string_literal",
                    "character_literal",
                    "modifier",
                ]
                .into_iter()
                .collect(),
                delimiter_tokens: vec![("{", "}"), ("(", ")")],
            },
            "scala" => LangConfig {
                atom_nodes: ["string", "template_string"].into_iter().collect(),
                delimiter_tokens: vec![("{", "}"), ("(", ")"), ("[", "]")],
            },
            "php" => LangConfig {
                atom_nodes: ["string", "encapsed_string"].into_iter().collect(),
                delimiter_tokens: vec![("(", ")"), ("[", "]"), ("{", "}")],
            },
            "lua" => LangConfig {
                atom_nodes: ["string"].into_iter().collect(),
                delimiter_tokens: vec![("(", ")"), ("{", "}"), ("[", "]")],
            },
            "luau" => LangConfig {
                atom_nodes: ["string"].into_iter().collect(),
                delimiter_tokens: vec![("(", ")"), ("{", "}"), ("[", "]")],
            },
            "elixir" => LangConfig {
                atom_nodes: ["string", "sigil", "heredoc"].into_iter().collect(),
                delimiter_tokens: vec![("(", ")"), ("{", "}"), ("do", "end")],
            },
            "ocaml" => LangConfig {
                atom_nodes: [
                    "character",
                    "string",
                    "quoted_string",
                    "tag",
                    "type_variable",
                    "attribute_id",
                ]
                .into_iter()
                .collect(),
                delimiter_tokens: vec![("(", ")"), ("[", "]"), ("{", "}")],
            },
            // Fallback: no special atoms, standard delimiters
            _ => LangConfig {
                atom_nodes: HashSet::new(),
                delimiter_tokens: vec![("(", ")"), ("[", "]"), ("{", "}")],
            },
        }
    }
}