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
|
//! ref: composer/vendor/composer/class-map-generator/src/PhpFileCleaner.php
use indexmap::IndexMap;
use shirabe_external_packages::composer::pcre::preg::Preg;
use shirabe_php_shim::preg_quote;
use std::sync::Mutex;
#[derive(Debug, Clone)]
struct TypeConfigEntry {
name: String,
length: usize,
pattern: String,
}
static TYPE_CONFIG: Mutex<Option<IndexMap<char, TypeConfigEntry>>> = Mutex::new(None);
static REST_PATTERN: Mutex<Option<String>> = Mutex::new(None);
#[derive(Debug)]
pub struct PhpFileCleaner {
contents: String,
len: usize,
max_matches: usize,
index: usize,
}
impl PhpFileCleaner {
pub fn set_type_config(types: Vec<String>) {
let mut type_config: IndexMap<char, TypeConfigEntry> = IndexMap::new();
for r#type in &types {
let first_char = r#type.chars().next().unwrap();
type_config.insert(
first_char,
TypeConfigEntry {
name: r#type.clone(),
length: r#type.len(),
pattern: format!(
"{{.\\b(?<![$:>]){}\\s++[a-zA-Z_\\x7f-\\xff:][a-zA-Z0-9_\\x7f-\\xff:\\-]*+}}Ais",
r#type
),
},
);
}
let keys: String = type_config.keys().collect();
let rest_pattern = format!("{{[^?\"'</{}]+}}A", keys);
*REST_PATTERN.lock().unwrap() = Some(rest_pattern);
*TYPE_CONFIG.lock().unwrap() = Some(type_config);
}
pub fn new(contents: String, max_matches: usize) -> Self {
let len = contents.len();
PhpFileCleaner {
contents,
len,
max_matches,
index: 0,
}
}
pub fn clean(&mut self) -> String {
let mut clean = String::new();
'outer: while self.index < self.len {
self.skip_to_php();
clean.push_str("<?");
while self.index < self.len {
let char = self.contents.as_bytes()[self.index] as char;
if char == '?' && self.peek('>') {
clean.push_str("?>");
self.index += 2;
continue 'outer;
}
if char == '"' {
self.skip_string('"');
clean.push_str("null");
continue;
}
if char == '\'' {
self.skip_string('\'');
clean.push_str("null");
continue;
}
if char == '<' && self.peek('<') {
let mut r#match: Vec<String> = vec![];
if self.r#match(
r#"{<<<[ \t]*+(['\"]?)([a-zA-Z_\x80-\xff][a-zA-Z0-9_\x80-\xff]*+)\1(?:\r\n|\n|\r)}A"#,
Some(&mut r#match),
) {
self.index += r#match[0].len();
let delimiter = r#match[2].clone();
self.skip_heredoc(&delimiter);
clean.push_str("null");
continue;
}
}
if char == '/' {
if self.peek('/') {
self.skip_to_newline();
continue;
}
if self.peek('*') {
self.skip_comment();
continue;
}
}
if self.max_matches == 1 {
let type_entry = {
let guard = TYPE_CONFIG.lock().unwrap();
guard.as_ref().and_then(|tc| tc.get(&char)).cloned()
};
if let Some(entry) = type_entry {
let end = self.index + entry.length;
if end <= self.len && &self.contents[self.index..end] == entry.name {
let offset = if self.index > 0 { self.index - 1 } else { 0 };
let mut r#match: Vec<String> = vec![];
if Preg::is_match_at(
&entry.pattern,
&self.contents,
&mut r#match,
0,
offset,
) {
return clean + &r#match[0];
}
}
}
}
self.index += 1;
let rest_pattern = REST_PATTERN.lock().unwrap().clone();
if let Some(rest_pattern) = rest_pattern {
let mut r#match: Vec<String> = vec![];
if self.r#match(&rest_pattern, Some(&mut r#match)) {
clean.push(char);
clean.push_str(&r#match[0]);
self.index += r#match[0].len();
} else {
clean.push(char);
}
} else {
clean.push(char);
}
}
}
clean
}
fn skip_to_php(&mut self) {
while self.index < self.len {
if self.contents.as_bytes()[self.index] as char == '<' && self.peek('?') {
self.index += 2;
break;
}
self.index += 1;
}
}
fn skip_string(&mut self, delimiter: char) {
self.index += 1;
while self.index < self.len {
let c = self.contents.as_bytes()[self.index] as char;
if c == '\\' && (self.peek('\\') || self.peek(delimiter)) {
self.index += 2;
continue;
}
if c == delimiter {
self.index += 1;
break;
}
self.index += 1;
}
}
fn skip_comment(&mut self) {
self.index += 2;
while self.index < self.len {
if self.contents.as_bytes()[self.index] as char == '*' && self.peek('/') {
self.index += 2;
break;
}
self.index += 1;
}
}
fn skip_to_newline(&mut self) {
while self.index < self.len {
let c = self.contents.as_bytes()[self.index] as char;
if c == '\r' || c == '\n' {
return;
}
self.index += 1;
}
}
fn skip_heredoc(&mut self, delimiter: &str) {
let first_delimiter_char = delimiter.chars().next().unwrap();
let delimiter_length = delimiter.len();
let delimiter_pattern = format!(
"{{{}(?![a-zA-Z0-9_\\x80-\\xff])}}A",
preg_quote(delimiter, None)
);
while self.index < self.len {
let c = self.contents.as_bytes()[self.index] as char;
// check if we find the delimiter after some spaces/tabs
match c {
'\t' | ' ' => {
self.index += 1;
continue;
}
_ if c == first_delimiter_char => {
let end = self.index + delimiter_length;
if end <= self.len
&& &self.contents[self.index..end] == delimiter
&& self.r#match(&delimiter_pattern, None)
{
self.index += delimiter_length;
return;
}
}
_ => {}
}
// skip the rest of the line
self.skip_to_newline();
// skip newlines
while self.index < self.len {
let c = self.contents.as_bytes()[self.index] as char;
if c == '\r' || c == '\n' {
self.index += 1;
} else {
break;
}
}
}
}
fn peek(&self, char: char) -> bool {
self.index + 1 < self.len && self.contents.as_bytes()[self.index + 1] as char == char
}
fn r#match(&self, regex: &str, r#match: Option<&mut Vec<String>>) -> bool {
Preg::is_match_strict_groups_at(regex, &self.contents, r#match, 0, self.index)
}
}
|
