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
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
use crate::grade::{
    JavacDiagnostic,
    LineRef,
    MutationDiagnostic,
};

peg::parser! {
    /// includes some useful grammars for parsing JUNit/javac/pitest outputs.
    pub grammar parser() for str {
        /// matches any sequence of 1 or more numbers
        rule number() -> u32
            = n:$(['0'..='9']+) {? n.parse().or(Err("u32")) }

        /// matches any number of whitespace characters
        rule whitespace() = quiet!{[' ' | '\n' | '\t' | '\r']+}

        /// matches the keyword "tests successful"
        rule successful_tests()
            = " tests successful"

        /// matches the keyword "tests found"
        rule found_tests()
            = " tests found"

        /// parses and returns the number of tests passed
        pub rule num_tests_passed() -> u32
            = "[" whitespace()? l:number() successful_tests() whitespace()? "]" { l }

        /// parses and returns the number of tests found
        pub rule num_tests_found() -> u32
            = "[" whitespace()? l:number() found_tests() whitespace()? "]" { l }

        /// matches any path separator, hopefully cross-platform
        rule path_separator() =
            whitespace()?
            "."?
            "/" / "\\" / "\\\\"
            whitespace()?

        /// matches any sequence of upper and lowercase alphabets
        rule word() -> String
            = whitespace()?
                w:[
                    'a'..='z' |
                    'A'..='Z' |
                    '0'..='9' |
                    '-' | '.' | ' ' |
                    '[' | ']' | '_'
                ]+
                whitespace()?
            { w.iter().collect::<String>() }

        /// matches any sequence of upper and lowercase alphabets
        rule mutations_csv_word() -> String
            = whitespace()?
                w:[
                    'a'..='z' |
                    'A'..='Z' |
                    '0'..='9' |
                    '-' | '.' | ' ' |
                    '[' | ']' | ':' |
                    '<' | '>' | '_' |
                    '(' | ')'
                ]+
                whitespace()?
            { w.iter().collect::<String>() }

        /// matches any valid path, hopefully
        rule path() -> String
            = whitespace()?
              path_separator()?
              p:(word() ++ path_separator())
              whitespace()?
            { p.iter().fold(String::new(), |acc, w| format!("{acc}/{w}")) }

        /// matches line numbers (colon followed by numbers, eg. :23)
        rule line_number() -> u32
            = ":" n:number() ":" whitespace()? { n }

        /// matches "error" or "warning", returns true if error
        rule diag_type() -> bool
            = whitespace()?
              a:"error"? b:"warning"?
              ":"
              whitespace()?
            { a.is_some() }

        /// matches anything, placed where diagnostic should be
        rule diagnostic() -> String
            = a:([_]+)
            { a.iter().collect::<String>() }

        /// parses the first line of a javac diagnostic message and returns a `JavacDiagnostic`
        pub rule parse_diag() -> JavacDiagnostic
            = p:path() l:line_number() d:diag_type() m:diagnostic()
            {
                let p = std::path::PathBuf::from(p);
            let name = p.file_name().expect("Could not parse path to file in javac error/warning");

            JavacDiagnostic::builder()
                .path(format!(".{}", p.display()))
                .file_name(name.to_string_lossy().to_string())
                .line_number(l)
                .is_error(d)
                .message(if d { format!("Error: {m}") } else { m })
                .build()
            }

        rule mutation_test_examined_path() -> Vec<String>
            = a:mutations_csv_word()? "/"? b:mutations_csv_word()? "/"?  c:mutations_csv_word()?
            {
                let mut res = vec![];
                if let Some(a) = a { res.push(a); }
                if let Some(b) = b { res.push(b); }
                if let Some(c) = c { res.push(c); }
                res
            }

        rule mutation_test_examined_none() -> &'input str
            = $("none")

        /// parses one row of mutation report
        pub rule mutation_report_row() -> MutationDiagnostic
            = file_name:word()
              ","
              source_file_name:word()
              ","
              mutation:word()
              ","
              source_method:mutations_csv_word()
              ","
              line_no:number()
              ","
              result:word()
              ","
              test_method:mutation_test_examined_path()?
              whitespace()?
                {
                let test = test_method.unwrap_or_else(|| panic!("Had trouble parsing last column for mutation at {source_file_name}#{source_method}:{line_no}"));
                let mut test_file_name;
                let mut test_method;

    if test.len() == 3 {
                    let splitter = if test.get(1).unwrap().contains("[runner:") { "[runner:" } else { "[class:" };
                    test_file_name = test.get(1)
                                .unwrap()
                                .to_string()
                                .split_once(splitter)
                                .unwrap_or_else(|| panic!("had trouble parsing test_file_class for mutation at {source_file_name}#{source_method}:{line_no}"))
                                .1
                                .replace(']', "");

                    let splitter = if test.get(2).unwrap().contains("[test:") { "[test:" } else { "[method:" };
                    test_method = test.get(2)
                                    .unwrap()
                                    .to_string()
                                    .split_once(splitter)
                                    .unwrap_or_else(|| panic!("Had trouble parsing test_file_method for mutation at {source_file_name}#{source_method}:{line_no}"))
                                    .1
                                    .replace("()]", "");
                } else {
                    test_file_name = "NA".to_string();
                    test_method = "None".to_string()
                }
                let mutator = mutation
                                .to_string()
                                .split_once(".mutators.")
                                .expect("Could not split mutators while parsing mutations.csv.")
                                .1.to_string();

                MutationDiagnostic::builder()
                    .line_number(line_no)
                    .mutator(mutator)
                    .source_file_name(source_file_name)
                    .source_method(source_method)
                    .test_file_name(test_file_name)
                    .test_method(test_method)
                    .result(result)
                    .build()
            }

            /// Parses a word in a JUnit stacktrace
            rule junit_stacktrace_word() -> String
                = whitespace()?
                w:[
                    'a'..='z' |
                    'A'..='Z' |
                    '0'..='9' |
                    '-' | '.' | ' ' |
                    '[' | ']' | '/' |
                    '>' | '=' | '$'
                ]+
                whitespace()?
            { w.iter().collect::<String>() }

            /// Parses a filename from a JUnit stacktrace
            rule junit_stacktrace_filename() -> String
                = whitespace()?
                w:[
                    'a'..='z' |
                    'A'..='Z' |
                    '0'..='9' |
                    '-' | '_' | '$'
                ]+
                ".java:"
                whitespace()?
            { w.iter().collect::<String>() }


            /// Parses a LineRef from a JUnit stacktrace
            pub rule junit_stacktrace_line_ref() -> LineRef
                = whitespace()?
                junit_stacktrace_word()*
                whitespace()?
                "("
                c:junit_stacktrace_filename()
                d:number()
                whitespace()?
                ")"
                whitespace()?
                {
                    LineRef { line_number: d as usize, file_name: c }
                }
    }
}