difflib 0.1.0

Port of Python's difflib library to Rust.
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

pub mod sequencematcher;
pub mod differ;
mod utils;


use std::collections::HashMap;
use sequencematcher::{SequenceMatcher, Sequence};
use utils::{format_range_unified, format_range_context};


pub fn get_close_matches<'a>(word: &str, possibilities: Vec<&'a str>, n: usize, cutoff: f32) -> Vec<&'a str> {
	if !(0.0 <= cutoff && cutoff <= 1.0) {
		panic!("Cutoff must be greater than 0.0 and lower than 1.0");
	}
	let mut res: Vec<(f32, &str)> = Vec::new();
	let mut matcher = SequenceMatcher::new("", word);
	for i in &possibilities {
		matcher.set_first_seq(i);
		let ratio = matcher.ratio();
		if ratio >= cutoff {
			res.push((ratio, i));
		}
	}
	res.sort_by(|a, b| b.0.partial_cmp(&a.0).unwrap());
	res.truncate(n);
	res.iter().map(|x| x.1).collect()
}

pub fn unified_diff<T: Sequence>(first_sequence: &T, second_sequence: &T, from_file: &str, to_file: &str, 
	from_file_date: &str, to_file_date: &str, n: usize) -> Vec<String> {
	let mut res = Vec::new();
	let lineterm = '\n';
	let mut started = false;
	let mut matcher = SequenceMatcher::new(first_sequence, second_sequence);
	for group in &matcher.get_grouped_opcodes(n) {
		if !started {
			started = true;
			let from_date = format!("\t{}", from_file_date);
			let to_date = format!("\t{}", to_file_date);
			res.push( format!("--- {}{}{}", from_file, from_date, lineterm) );
			res.push( format!("+++ {}{}{}", to_file, to_date, lineterm) );
		}
		let (first, last) = (group.first().unwrap(), group.last().unwrap());
		let file1_range = format_range_unified(first.first_start, last.first_end); 
		let file2_range = format_range_unified(first.second_start, last.second_end);
		res.push( format!("@@ -{} +{} @@{}", file1_range, file2_range, lineterm) );
		for code in group {
			if code.tag == "equal" {
				for i in code.first_start..code.first_end {
					res.push( format!(" {}", first_sequence.at_index(i).unwrap()) );
				}
				continue;
			}
			if code.tag == "replace" || code.tag == "delete" {
				for i in code.first_start..code.first_end {
					res.push( format!("-{}", first_sequence.at_index(i).unwrap()) );
				}
			}
			if code.tag == "replace" || code.tag == "insert" {
				for i in code.second_start..code.second_end {
					res.push( format!("+{}", second_sequence.at_index(i).unwrap()) );
				}
			}
		}
	}
	res
}


pub fn context_diff<T: Sequence>(first_sequence: &T, second_sequence: &T, from_file: &str, to_file: &str, 
	from_file_date: &str, to_file_date: &str, n: usize) -> Vec<String> {
	let mut res = Vec::new();
	let lineterm = '\n';
	let mut prefix: HashMap<String, String> = HashMap::new();
	prefix.insert(String::from("insert"), String::from("+ "));
	prefix.insert(String::from("delete"), String::from("- "));
	prefix.insert(String::from("replace"), String::from("! "));
	prefix.insert(String::from("equal"), String::from("  "));
	let mut started = false;
	let mut matcher = SequenceMatcher::new(first_sequence, second_sequence);
	for group in &matcher.get_grouped_opcodes(n) {
		if !started {
			started = true;
			let from_date = format!("\t{}", from_file_date);
			let to_date = format!("\t{}", to_file_date);
			res.push( format!("*** {}{}{}", from_file, from_date, lineterm) );
			res.push( format!("--- {}{}{}", to_file, to_date, lineterm) );
		}
		let (first, last) = (group.first().unwrap(), group.last().unwrap());
		res.push(format!("***************{}", lineterm));
		let file1_range = format_range_context(first.first_start, last.first_end); 
		res.push(format!("*** {} ****{}", file1_range, lineterm));
		let mut any = false;
		for opcode in group {
			if opcode.tag == "replace" || opcode.tag == "delete" {
				any = true;
				break;
			}
		}
		if any {
			for opcode in group {
				if opcode.tag != "insert" {
					for i in opcode.first_start..opcode.first_end {
						res.push( format!("{}{}", prefix.get(&opcode.tag).unwrap(), first_sequence.at_index(i).unwrap()) );
					}
				}
			}
		}
		let file2_range = format_range_context(first.second_start, last.second_end);
		res.push(format!("--- {} ----{}", file2_range, lineterm));
		any = false;
		for opcode in group {
			if opcode.tag == "replace" || opcode.tag == "insert" {
				any = true;
				break;
			}
		}
		if any {
			for opcode in group {
				if opcode.tag != "delete" {
					for i in opcode.second_start..opcode.second_end {
						res.push( format!("{}{}", prefix.get(&opcode.tag).unwrap(), second_sequence.at_index(i).unwrap()) );
					}
				}
			}
		}
	}
	res
}