1 | pub mod differ; |
2 | pub mod sequencematcher; |
3 | mod utils; |
4 | |
5 | use sequencematcher::{Sequence, SequenceMatcher}; |
6 | use std::collections::HashMap; |
7 | use std::fmt::Display; |
8 | use utils::{format_range_context, format_range_unified}; |
9 | |
10 | pub fn get_close_matches<'a>( |
11 | word: &str, |
12 | possibilities: Vec<&'a str>, |
13 | n: usize, |
14 | cutoff: f32, |
15 | ) -> Vec<&'a str> { |
16 | if !(0.0 <= cutoff && cutoff <= 1.0) { |
17 | panic!("Cutoff must be greater than 0.0 and lower than 1.0" ); |
18 | } |
19 | let mut res: Vec<(f32, &str)> = Vec::new(); |
20 | let mut matcher = SequenceMatcher::new("" , word); |
21 | for i in &possibilities { |
22 | matcher.set_first_seq(i); |
23 | let ratio = matcher.ratio(); |
24 | if ratio >= cutoff { |
25 | res.push((ratio, i)); |
26 | } |
27 | } |
28 | res.sort_by(|a, b| b.0.partial_cmp(&a.0).unwrap()); |
29 | res.truncate(n); |
30 | res.iter().map(|x| x.1).collect() |
31 | } |
32 | |
33 | pub fn unified_diff<T: Sequence + Display>( |
34 | first_sequence: &[T], |
35 | second_sequence: &[T], |
36 | from_file: &str, |
37 | to_file: &str, |
38 | from_file_date: &str, |
39 | to_file_date: &str, |
40 | n: usize, |
41 | ) -> Vec<String> { |
42 | let mut res = Vec::new(); |
43 | let lineterm = ' \n' ; |
44 | let mut started = false; |
45 | let mut matcher = SequenceMatcher::new(first_sequence, second_sequence); |
46 | for group in &matcher.get_grouped_opcodes(n) { |
47 | if !started { |
48 | started = true; |
49 | let from_date = format!(" \t{}" , from_file_date); |
50 | let to_date = format!(" \t{}" , to_file_date); |
51 | res.push(format!("--- {}{}{}" , from_file, from_date, lineterm)); |
52 | res.push(format!("+++ {}{}{}" , to_file, to_date, lineterm)); |
53 | } |
54 | let (first, last) = (group.first().unwrap(), group.last().unwrap()); |
55 | let file1_range = format_range_unified(first.first_start, last.first_end); |
56 | let file2_range = format_range_unified(first.second_start, last.second_end); |
57 | res.push(format!( |
58 | "@@ -{} +{} @@{}" , |
59 | file1_range, file2_range, lineterm |
60 | )); |
61 | for code in group { |
62 | if code.tag == "equal" { |
63 | for item in first_sequence |
64 | .iter() |
65 | .take(code.first_end) |
66 | .skip(code.first_start) |
67 | { |
68 | res.push(format!(" {}" , item)); |
69 | } |
70 | continue; |
71 | } |
72 | if code.tag == "replace" || code.tag == "delete" { |
73 | for item in first_sequence |
74 | .iter() |
75 | .take(code.first_end) |
76 | .skip(code.first_start) |
77 | { |
78 | res.push(format!("-{}" , item)); |
79 | } |
80 | } |
81 | if code.tag == "replace" || code.tag == "insert" { |
82 | for item in second_sequence |
83 | .iter() |
84 | .take(code.second_end) |
85 | .skip(code.second_start) |
86 | { |
87 | res.push(format!("+{}" , item)); |
88 | } |
89 | } |
90 | } |
91 | } |
92 | res |
93 | } |
94 | |
95 | pub fn context_diff<T: Sequence + Display>( |
96 | first_sequence: &[T], |
97 | second_sequence: &[T], |
98 | from_file: &str, |
99 | to_file: &str, |
100 | from_file_date: &str, |
101 | to_file_date: &str, |
102 | n: usize, |
103 | ) -> Vec<String> { |
104 | let mut res = Vec::new(); |
105 | let lineterm = ' \n' ; |
106 | let mut prefix: HashMap<String, String> = HashMap::new(); |
107 | prefix.insert(String::from("insert" ), String::from("+ " )); |
108 | prefix.insert(String::from("delete" ), String::from("- " )); |
109 | prefix.insert(String::from("replace" ), String::from("! " )); |
110 | prefix.insert(String::from("equal" ), String::from(" " )); |
111 | let mut started = false; |
112 | let mut matcher = SequenceMatcher::new(first_sequence, second_sequence); |
113 | for group in &matcher.get_grouped_opcodes(n) { |
114 | if !started { |
115 | started = true; |
116 | let from_date = format!(" \t{}" , from_file_date); |
117 | let to_date = format!(" \t{}" , to_file_date); |
118 | res.push(format!("*** {}{}{}" , from_file, from_date, lineterm)); |
119 | res.push(format!("--- {}{}{}" , to_file, to_date, lineterm)); |
120 | } |
121 | let (first, last) = (group.first().unwrap(), group.last().unwrap()); |
122 | res.push(format!("***************{}" , lineterm)); |
123 | let file1_range = format_range_context(first.first_start, last.first_end); |
124 | res.push(format!("*** {} ****{}" , file1_range, lineterm)); |
125 | let mut any = false; |
126 | for opcode in group { |
127 | if opcode.tag == "replace" || opcode.tag == "delete" { |
128 | any = true; |
129 | break; |
130 | } |
131 | } |
132 | if any { |
133 | for opcode in group { |
134 | if opcode.tag != "insert" { |
135 | for item in first_sequence |
136 | .iter() |
137 | .take(opcode.first_end) |
138 | .skip(opcode.first_start) |
139 | { |
140 | res.push(format!("{}{}" , &prefix[&opcode.tag], item)); |
141 | } |
142 | } |
143 | } |
144 | } |
145 | let file2_range = format_range_context(first.second_start, last.second_end); |
146 | res.push(format!("--- {} ----{}" , file2_range, lineterm)); |
147 | any = false; |
148 | for opcode in group { |
149 | if opcode.tag == "replace" || opcode.tag == "insert" { |
150 | any = true; |
151 | break; |
152 | } |
153 | } |
154 | if any { |
155 | for opcode in group { |
156 | if opcode.tag != "delete" { |
157 | for item in second_sequence |
158 | .iter() |
159 | .take(opcode.second_end) |
160 | .skip(opcode.second_start) |
161 | { |
162 | res.push(format!("{}{}" , prefix[&opcode.tag], item)); |
163 | } |
164 | } |
165 | } |
166 | } |
167 | } |
168 | res |
169 | } |
170 | |