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
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
pub mod parse {
extern crate regex;
use model::model::*;
use regex::Regex;
use std::fs::File;
use std::io::BufRead;
use std::io::BufReader;
use std::path::Path;
fn regex_match(text: &str, regex_str: &str) -> bool {
let reg = Regex::new(regex_str).unwrap();
reg.is_match(text)
}
fn start_doc_match(text: &String) -> bool {
if text.contains(r"/**") {
return true;
} else {
return false;
}
}
fn start_comment_match(text: &String) -> bool {
if text.contains(r"/*") && !text.contains("/**") {
return true;
} else {
return false;
}
}
fn end_doc_match(text: &String) -> bool {
if text.contains(r"**/") {
return true;
} else if text.contains(r"*/") {
return true;
} else {
return false;
}
}
fn trim_paren(part: String) -> String {
let no_paren: Vec<&str> = part.split(&[')', '{'][..]).collect();
no_paren.join("")
}
pub fn determine_line_type(line: &String, state: &ParseState) -> LineType {
let method_match = r"(public|protected|private|static|\s) +[\w\[\]]+\s+(\w+) *\([^\)]*\)";
if line.contains("package ") {
LineType::IsPackage
} else if line.contains("class ") && !state.comment && !state.doc {
LineType::IsClass
} else if line.contains("import ") {
LineType::IsImport
} else if regex_match(&line, method_match) {
LineType::IsMethod
} else if start_doc_match(&line) {
LineType::IsStartdoc
} else if start_comment_match(&line) {
LineType::IsStartdoc
} else if end_doc_match(&line) {
LineType::IsEnddoc
} else if line.contains("//") {
LineType::IsComment
} else {
LineType::IsOther
}
}
fn handle_class(mut class: Class, line: &String) -> Class {
let access_match = r"(public|protected|private)";
let split = line.split(" ");
let parts: Vec<&str> = split.collect();
for (num, class_part) in parts.iter().enumerate() {
if regex_match(&class_part, access_match) {
class.ch_access(class_part.clone().to_string());
} else if class_part.contains("class") {
if parts.len() > num + 1 {
class.ch_class_name(parts[num + 1].to_string());
}
} else if class_part.contains("exception") {
if parts.len() > num + 1 {
class.ch_class_name(parts[num + 1].to_string());
}
}
}
return class;
}
fn handle_method(line: &String) -> Result<Method, &str> {
let access_match = r"(public|protected|private)";
let parts = trim_whitespace(line);
let mut method = Method::new();
for (i, method_part) in parts.iter().enumerate() {
if regex_match(&method_part, access_match) {
method.ch_privacy(method_part.clone().to_string());
} else if method_part.contains("void") {
method.ch_return_type("void".to_string());
} else if method_part.contains("exception") {
if parts.len() > i + 1 {
let ex = Exception {
exception_type: String::new(),
desc: parts[i + 1].to_string(),
};
method.ch_exception(ex);
}
} else if method_part.contains("(") {
let name_parts: Vec<&str> = method_part.split("(").collect();
let mut param_def = false;
let mut param_type = String::new();
if name_parts[1] != "" {
param_type = name_parts[1].to_string();
param_def = true;
}
for j in (i + 1)..parts.len() {
let mut meth_part = parts[j].clone();
if parts[j].contains(")") {
meth_part = trim_paren(meth_part);
}
if param_def {
method.add_param(Param {
desc: String::new(),
var_type: param_type.clone(),
name: meth_part,
});
param_def = false;
} else {
param_type = meth_part;
param_def = true;
}
}
method.ch_method_name(name_parts[0].to_string());
}
}
Ok(method)
}
fn doc_desc(parts: &Vec<String>) -> String {
let mut description = String::new();
for i in 0..parts.len() {
description.push_str(format!("{} ", parts[i].as_str()).as_str());
}
description
}
pub fn trim_whitespace(line: &String) -> Vec<String> {
let sub_strs: Vec<&str> = line.split(" ").collect();
let mut trimmed: Vec<String> = Vec::new();
for sub in sub_strs {
let bytes: Vec<u8> = sub.to_string().into_bytes();
let mut new_str: Vec<u8> = Vec::new();
for b in bytes {
if b > 32 && b != 44 {
new_str.push(b);
}
}
if new_str.len() == 1 {
if new_str[0] == 42 {
continue;
}
} else if new_str.len() > 0 {
trimmed.push(unsafe { String::from_utf8_unchecked(new_str) });
}
}
trimmed
}
pub fn handle_doc(buffer: &Vec<String>) -> Doc {
let mut return_str = String::from("");
let mut desc = String::from("");
let mut parameters: Vec<Param> = Vec::new();
let mut author = String::new();
let mut version = String::new();
let mut deprecated = String::new();
let mut except = Exception::new();
for line in buffer {
let mut line_vec: Vec<String> = trim_whitespace(&line.to_string());
if line_vec.len() > 1 {
let len = line_vec.len();
if len > 1 {
if line.contains("@param") {
if len == 2 {
parameters.push(Param {
name: line_vec[1].clone(),
desc: String::from(""),
var_type: String::new(),
})
} else if len > 2 {
let description = doc_desc(&line_vec[2..].to_vec());
parameters.push(Param {
name: line_vec[1].clone(),
desc: description,
var_type: String::new(),
})
}
} else if line.contains("@return") {
return_str = doc_desc(&line_vec[1..].to_vec());
} else if line.contains("@author") {
author = doc_desc(&line_vec[1..].to_vec());
} else if line.contains("@expeption") {
if len > 2 {
let mut ex = Exception {
exception_type: line_vec[1].clone(),
desc: doc_desc(&line_vec[2..].to_vec()),
};
except = ex;
}
} else if line.contains("@throws") {
if len > 2 {
let mut ex = Exception {
exception_type: line_vec[1].clone(),
desc: doc_desc(&line_vec[2..].to_vec()),
};
except = ex;
}
} else if line.contains("@version") {
version = doc_desc(&line_vec[1..].to_vec());
} else if line.contains("@deprecated") {
deprecated = doc_desc(&line_vec[1..].to_vec());
}
}
if !line.contains("@") {
desc.push_str(format!(" {} ", doc_desc(&line_vec)).as_str());
}
}
}
Doc {
params: parameters,
description: desc,
return_desc: return_str,
author: author,
version: version,
exception: except,
deprecated: deprecated,
}
}
fn match_params(params: &Vec<Param>, jparams: &Vec<Param>) -> Vec<Param> {
let mut new_param: Vec<Param> = Vec::new();
for mut param in params {
let mut found = false;
for i in 0..jparams.len() {
if param.name == jparams[i].name {
new_param.push(Param {
name: param.name.clone(),
var_type: param.var_type.clone(),
desc: jparams[i].desc.clone(),
});
found = true;
}
}
if !found {
new_param.push(Param {
name: param.name.clone(),
var_type: param.var_type.clone(),
desc: "No description found".to_string(),
});
}
}
new_param
}
pub fn parse_file(path: &Path) -> Class {
use LineType::{
IsClass, IsComment, IsEnddoc, IsImport, IsMethod, IsOther, IsPackage, IsStartdoc,
};
let file = File::open(path).expect("File not found");
let buf = BufReader::new(&file);
let mut doc_buffer: Vec<String> = Vec::new();
let mut class = Class::new();
let mut parse_state = ParseState::new();
let mut jdoc = Doc::new();
for line in buf.lines() {
let l = line.unwrap();
let line_type = determine_line_type(&l, &parse_state);
match line_type {
IsPackage => {
let split = l.split(" ");
let parts: Vec<&str> = split.collect();
for (num, w) in parts.iter().enumerate() {
if w.contains("package") {
let mut pack_name = &parts[num + 1].trim();
class.ch_package_name(pack_name.to_string().replace(";", ""));
}
}
}
IsImport => {
let split = l.split(" ");
let mut parts: Vec<&str> = split.collect();
for (num, w) in parts.iter().enumerate() {
if w.contains("import") {
let mut im_name = &parts[num + 1].trim();
class.add_dependency(im_name.to_string().replace(";", ""));
}
}
}
IsClass => {
if !parse_state.class {
class = handle_class(class, &l);
if parse_state.doc_ready {
class.ch_description(jdoc.description.clone());
class.ch_author(jdoc.author.clone());
class.ch_version(jdoc.version.clone());
class.ch_deprecation(jdoc.deprecated.clone());
}
parse_state.ch_class(true);
parse_state.ch_doc_ready(false);
}
}
IsMethod => {
let method_res = handle_method(&l);
if method_res.is_ok() {
let mut j_method = method_res.unwrap();
if parse_state.doc_ready {
j_method.ch_description(jdoc.description.clone());
j_method.ch_return_type(jdoc.return_desc.clone());
let n_params: Vec<Param> =
match_params(&j_method.parameters, &jdoc.params);
j_method.ch_params(n_params);
if !jdoc.exception.is_empty() {
j_method.ch_exception(jdoc.exception.clone());
}
}
class.add_method(j_method);
}
parse_state.ch_doc_ready(false);
}
IsComment => {}
IsStartdoc => {
doc_buffer.clear();
parse_state.ch_doc(true);
}
IsEnddoc => {
if parse_state.doc {
jdoc = handle_doc(&doc_buffer);
parse_state.ch_doc(false);
parse_state.ch_doc_ready(true);
}
}
IsOther => {
if parse_state.doc {
doc_buffer.push(l);
}
}
}
}
class
}
}