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
use crate::lexer::eschar::{
    ESChar,
    CR, LF, LS, PS,
    TAB, VT, FF, SP, NBSP, ZWNBSP,
    BACKSPACE, 
};


#[derive(Debug, PartialEq, Eq, Hash, Clone, Copy)]
pub enum EscapeSequenceKind {
    // CharacterEscapeSequence
    // NullCharacter , 0 [lookahead ∉ DecimalDigit]
    // HexEscapeSequence
    // UnicodeEscapeSequence
    String,
    // LineTerminator
    // CharacterEscapeSequence
    // NullCharacter
    // HexEscapeSequence
    // UnicodeEscapeSequence
    TemplateString,
    // UnicodeEscapeSequence
    Identifier,
    JSXText,
}


#[inline]
pub fn single_escape_character(c: char) -> char {
    // https://www.ecma-international.org/ecma-262/9.0/index.html#prod-SingleEscapeCharacter
    // one of ' " \ b f n r t v
    debug_assert_eq!(c.is_es_single_escape_character(), true);
    match c {
        '\'' => c,
        '"'  => c,
        '\\' => c,
        'b'  => BACKSPACE,
        'f'  => FF,        // FORM FEED
        'n'  => LF,        // LINE FEED
        'r'  => CR,        // CARRIAGE RETURN
        't'  => TAB,       // CHARACTER TABULATION
        'v'  => VT,        // LINE TABULATION
        _    => unreachable!(),
    }
}

#[derive(Debug, PartialEq, Eq, Hash, Clone, Copy)]
pub enum EscapeErrorKind {
    Overflow,
    InvalidDigit,
    InvalidCodePoint,
    InvalidEscapeSequence,
    InvalidCharacter,
}

#[derive(Debug, PartialEq, Eq, Hash, Clone, Copy)]
pub struct EscapeError {
    kind: EscapeErrorKind,
    offset: usize,
}

impl EscapeError {
    pub const fn new(kind: EscapeErrorKind, offset: usize) -> Self {
        Self { kind, offset }
    }

    pub fn kind(&self) -> &EscapeErrorKind {
        &self.kind
    }

    pub fn offset(&self) -> usize {
        self.offset
    }
}


fn hex_to_char(digits: &[char], pre_offset: usize) -> Result<char, EscapeError> {
    let digits_len = digits.len() as u32;

    if digits_len == 0 {
        return Err(EscapeError::new(EscapeErrorKind::InvalidDigit, pre_offset));
    }

    let radix = 16u32;

    let mut offset: u32 = 0;
    let mut acc: u32 = 0;

    while offset < digits_len {
        let digit: u32 = digits[offset as usize]
                            .to_digit(radix)
                            .ok_or(EscapeError::new(EscapeErrorKind::InvalidDigit, pre_offset + offset as usize))?;

        let idx = digits_len - 1 - offset;
        match radix.checked_pow(idx) {
            Some(n) => match digit.checked_mul(n) {
                Some(n) => {
                    // acc += digit * radix.pow(idx);
                    acc += n;
                },
                None => {
                    return Err(EscapeError::new(EscapeErrorKind::Overflow, pre_offset + offset as usize));
                },
            },
            None => {
                return Err(EscapeError::new(EscapeErrorKind::Overflow, pre_offset + offset as usize));
            },
        }
        
        offset += 1;
    }

    std::char::from_u32(acc).ok_or(EscapeError::new(EscapeErrorKind::InvalidCodePoint, pre_offset + offset as usize))
}

#[inline]
pub fn escape(input: &[char], kind: EscapeSequenceKind) -> Result<Vec<char>, EscapeError> {
    let input_len: usize = input.len();
    let mut output: Vec<char> = Vec::with_capacity(input_len);
    let mut idx: usize = 0;
    
    loop {
        if idx >= input_len {
            break;
        }

        let c = input[idx];

        match c {
            '\\' => {
                idx += 1;
                let c = input.get(idx).ok_or(EscapeError::new(EscapeErrorKind::InvalidEscapeSequence, idx))?;
                match c {
                    '0' => {
                        // NullCharacter
                        // \0
                        if kind == EscapeSequenceKind::Identifier {
                            return Err(EscapeError::new(EscapeErrorKind::InvalidEscapeSequence, idx));
                        }

                        // lookahead
                        match input.get(idx+1) {
                            Some(c) => {
                                if c.is_ascii_digit() {
                                    return Err(EscapeError::new(EscapeErrorKind::InvalidEscapeSequence, idx));
                                }
                            },
                            None => { }
                        }

                        output.push('\0');
                    }
                    'x' => {
                        // HexEscapeSequence
                        // \x HexDigit HexDigit
                        if kind == EscapeSequenceKind::Identifier {
                            return Err(EscapeError::new(EscapeErrorKind::InvalidEscapeSequence, idx));
                        }

                        idx += 1;
                        let buffer: [char; 2] = [
                            *(input.get(idx).ok_or(EscapeError::new(EscapeErrorKind::InvalidEscapeSequence, idx))?),
                            *(input.get(idx+1).ok_or(EscapeError::new(EscapeErrorKind::InvalidEscapeSequence, idx))?),
                        ];

                        let c2 = hex_to_char(&buffer, idx)?;
                        idx += 1;

                        output.push(c2);
                    },
                    'u' => {
                        // UnicodeEscapeSequence
                        // \u HexDigit HexDigit HexDigit HexDigit
                        // \u { HexDigit HexDigit HexDigit ... }
                        idx += 1;
                        let c = input.get(idx).ok_or(EscapeError::new(EscapeErrorKind::InvalidEscapeSequence, idx))?;

                        if c != &'{' {
                            let buffer: [char; 4] = [
                                *(input.get(idx).ok_or(EscapeError::new(EscapeErrorKind::InvalidEscapeSequence, idx))?),
                                *(input.get(idx+1).ok_or(EscapeError::new(EscapeErrorKind::InvalidEscapeSequence, idx))?),
                                *(input.get(idx+2).ok_or(EscapeError::new(EscapeErrorKind::InvalidEscapeSequence, idx))?),
                                *(input.get(idx+3).ok_or(EscapeError::new(EscapeErrorKind::InvalidEscapeSequence, idx))?),
                            ];
                            
                            let c2 = hex_to_char(&buffer, idx)?;
                            idx += 3;

                            output.push(c2);
                        } else {
                            idx += 1;

                            let start = idx;

                            #[allow(unused_assignments)]
                            let mut end = idx;

                            loop {
                                idx += 1;
                                let c2 = input.get(idx).ok_or(EscapeError::new(EscapeErrorKind::InvalidEscapeSequence, idx))?;
                                if c2 == &'}' {
                                    end = idx;
                                    break;
                                }
                            }
                            
                            let c2 = hex_to_char(&input[start..end], start)?;

                            output.push(c2);
                        }
                    },
                    _ => {
                        if c.is_es_line_terminator() {
                            if kind == EscapeSequenceKind::Identifier {
                                return Err(EscapeError::new(EscapeErrorKind::InvalidEscapeSequence, idx));
                            }

                            // LineTerminatorSequence
                            if c == &CR {
                                // lookahead LF
                                match input.get(idx+1) {
                                    Some(&LF) => {
                                        idx += 1;

                                        output.push(CR);
                                        output.push(LF);
                                    },
                                    _ => {
                                        output.push(CR);
                                    }
                                }
                            } else {
                                output.push(*c);
                            }
                        } else if c.is_es_single_escape_character() {
                            // SingleEscapeCharacter
                            if kind == EscapeSequenceKind::Identifier {
                                return Err(EscapeError::new(EscapeErrorKind::InvalidEscapeSequence, idx));
                            }

                            output.push(single_escape_character(*c));
                        } else {
                            // NonEscapeCharacter
                            output.push(*c);
                        }
                    }
                }
            },
            _ => {
                if c.is_es_line_terminator() {
                    // LineTerminator

                    if kind != EscapeSequenceKind::TemplateString {
                        // NOTE: Only TemplateString allow LineTerminator
                        return Err(EscapeError::new(EscapeErrorKind::InvalidCharacter, idx));
                    }

                    if c == CR {
                        // lookahead LF
                        match input.get(idx+1) {
                            Some(&LF) => {
                                idx += 1;

                                output.push(CR);
                                output.push(LF);
                            },
                            _ => {
                                output.push(CR);
                            }
                        }
                    } else {
                        output.push(c);
                    }
                } else {
                    // Normal SourceCode
                    output.push(c);
                }
            }
        }

        idx += 1;
    }

    Ok(output)
}


#[inline]
pub fn unescape_string(input: &[char]) -> Result<Vec<char>, EscapeError> {
    escape(input, EscapeSequenceKind::String)
}

#[inline]
pub fn unescape_template(input: &[char]) -> Result<Vec<char>, EscapeError> {
    escape(input, EscapeSequenceKind::TemplateString)
}

#[inline]
pub fn unescape_identifier(input: &[char]) -> Result<Vec<char>, EscapeError> {
    escape(input, EscapeSequenceKind::Identifier)
}


#[test]
fn test_unescape_string() {
    let input = r#"我\u{9999999999969}"#.chars().collect::<Vec<char>>();
    let output = unescape_string(&input);
    assert_eq!(output.is_err(), true);

    let input = r#"我\u{69}"#.chars().collect::<Vec<char>>();
    let output = unescape_string(&input);
    assert_eq!(output, Ok("我i".chars().collect::<Vec<char>>()));

    let input = r#"我\u{69}
"#.chars().collect::<Vec<char>>();
    let output = unescape_string(&input);
    assert_eq!(output.is_err(), true);

    let input = r#"我\u{69}\n\
"#.chars().collect::<Vec<char>>();
    let output = unescape_string(&input);
    assert_eq!(output, Ok("我i\n\n".chars().collect::<Vec<char>>()));
}

#[test]
fn test_unescape_template() {
    let input = r#"我\u{69}\u0069\x69
\n"#.chars().collect::<Vec<char>>();
    let output = unescape_template(&input);
    assert_eq!(output, Ok("我iii\n\n".chars().collect::<Vec<char>>()));
}

#[test]
fn test_unescape_identifier() {
    let input = r#"我\u{69}\u0069"#.chars().collect::<Vec<char>>();
    let output = unescape_identifier(&input);
    assert_eq!(output, Ok("我ii".chars().collect::<Vec<char>>()));

    let input = r#"\x69"#.chars().collect::<Vec<char>>();
    let output = unescape_identifier(&input);
    assert_eq!(output.is_err(), true);

    let input = r#"\n"#.chars().collect::<Vec<char>>();
    let output = unescape_identifier(&input);
    assert_eq!(output.is_err(), true);

    let input = r#"\a"#.chars().collect::<Vec<char>>();
    let output = unescape_identifier(&input);
    assert_eq!(output, Ok("a".chars().collect::<Vec<char>>()));
}