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
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
use std::collections::HashMap;
use std::{fmt, mem};

use derivative::Derivative;

#[cfg(feature = "serde_support")]
use serde::{Deserialize, Serialize};

use crate::document::RtfDocument;
use crate::header::{CharacterSet, Color, ColorRef, ColorTable, Font, FontFamily, FontRef, FontTable, RtfHeader, StyleSheet};
use crate::paragraph::{Alignment, Paragraph, SpaceBetweenLine};
use crate::tokens::{ControlWord, Property, Token};

// Use to specify control word in parse_header
macro_rules! header_control_word {
    ($cw:ident) => {
        Token::ControlSymbol((ControlWord::$cw, _))
    };
    ($cw:ident, $prop:ident) => {
        Token::ControlSymbol((ControlWord::$cw, Property::$prop))
    };
}

#[cfg_attr(feature = "serde_support", derive(Deserialize, Serialize))]
#[derive(Debug, Default, PartialEq, Clone)]
pub struct StyleBlock {
    pub painter: Painter,
    pub paragraph: Paragraph,
    pub text: String,
}

#[cfg_attr(feature = "serde_support", derive(Deserialize, Serialize))]
#[derive(Derivative, Debug, Clone, PartialEq, Hash)]
#[derivative(Default)]
pub struct Painter {
    pub color_ref: ColorRef,
    pub font_ref: FontRef,
    #[derivative(Default(value = "12"))]
    pub font_size: u16,
    pub bold: bool,
    pub italic: bool,
    pub underline: bool,
    pub superscript: bool,
    pub subscript: bool,
    pub smallcaps: bool,
    pub strike: bool,
}

#[derive(Debug, Clone)]
pub enum ParserError {
    InvalidToken(String),
    IgnorableDestinationParsingError,
    MalformedPainterStack,
    InvalidFontIdentifier(Property),
    InvalidColorIdentifier(Property),
    NoMoreToken,
    ValueCastError(String),
}

impl std::error::Error for ParserError {}

impl fmt::Display for ParserError {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        let _ = write!(f, "[RTF Parser] : ");
        return match self {
            ParserError::InvalidToken(msg) => write!(f, "{}", msg),
            ParserError::IgnorableDestinationParsingError => write!(f, "No ignorable destination should be left"),
            ParserError::MalformedPainterStack => write!(f, "Malformed painter stack : Unbalanced number of brackets"),
            ParserError::InvalidFontIdentifier(property) => write!(f, "Invalid font identifier : {:?}", property),
            ParserError::InvalidColorIdentifier(property) => write!(f, "Invalid color identifier : {:?}", property),
            ParserError::NoMoreToken => write!(f, "No more token to parse"),
            ParserError::ValueCastError(T) => write!(f, "Unable to cast i32 to {T}"),
        };
    }
}

pub struct Parser<'a> {
    tokens: Vec<Token<'a>>,
    cursor: usize,
}

impl<'a> Parser<'a> {
    pub fn new(tokens: Vec<Token<'a>>) -> Self {
        return Self { tokens, cursor: 0 };
    }

    fn check_document_validity(&self) -> Result<(), ParserError> {
        // Check the document boundaries
        if let Some(token) = self.tokens.first() {
            if token != &Token::OpeningBracket {
                return Err(ParserError::InvalidToken(format!("Invalid first token : {:?} not a '{{'", token)));
            }
        } else {
            return Err(ParserError::NoMoreToken);
        }
        if let Some(token) = self.tokens.last() {
            if token != &Token::ClosingBracket {
                return Err(ParserError::InvalidToken(format!("Invalid last token : {:?} not a '}}'", token)));
            }
        } else {
            return Err(ParserError::NoMoreToken);
        }
        return Ok(());
    }

    pub fn parse(&mut self) -> Result<RtfDocument, ParserError> {
        self.check_document_validity()?;
        let mut document = RtfDocument::default(); // Init empty document
        self.parse_ignore_groups(); // delete the ignore groups
        document.header = self.parse_header()?;
        // Parse Body
        let mut painter_stack: Vec<Painter> = vec![Painter::default()];
        let mut paragraph = Paragraph::default();
        let mut it = self.tokens.iter();
        while let Some(token) = it.next() {
            match token {
                Token::OpeningBracket => {
                    painter_stack.push(Painter::default());
                }
                Token::ClosingBracket => {
                    let painter = painter_stack.pop();
                    if painter == None {
                        return Err(ParserError::MalformedPainterStack);
                    }
                }
                Token::ControlSymbol((control_word, property)) => {
                    let Some(current_painter) = painter_stack.last_mut() else {
                        return Err(ParserError::MalformedPainterStack);
                    };
                    #[rustfmt::skip]  // For now, rustfmt does not support this kind of alignement
                    match control_word {
                        ControlWord::ColorNumber        => current_painter.color_ref = property.get_value_as::<ColorRef>()?,
                        ControlWord::FontNumber         => current_painter.font_ref = property.get_value_as::<FontRef>()?,
                        ControlWord::FontSize           => current_painter.font_size = property.get_value_as::<u16>()?,
                        ControlWord::Bold               => current_painter.bold = property.as_bool(),
                        ControlWord::Italic             => current_painter.italic = property.as_bool(),
                        ControlWord::Underline          => current_painter.underline = property.as_bool(),
                        ControlWord::UnderlineNone      => current_painter.underline = false,
                        ControlWord::Superscript        => current_painter.superscript = property.as_bool(),
                        ControlWord::Subscript          => current_painter.subscript = property.as_bool(),
                        ControlWord::Smallcaps          => current_painter.smallcaps = property.as_bool(),
                        ControlWord::Strikethrough      => current_painter.strike = property.as_bool(),
                        // Paragraph
                        ControlWord::Pard               => paragraph = Paragraph::default(), // Reset the par
                        ControlWord::Plain              => *current_painter = Painter::default(), // Reset the painter
                        ControlWord::ParDefTab          => paragraph.tab_width = property.get_value(),
                        ControlWord::LeftAligned
                            | ControlWord::RightAligned
                            | ControlWord::Center
                            | ControlWord::Justify      => paragraph.alignment = Alignment::from(control_word),
                        ControlWord::SpaceBefore        => paragraph.spacing.before = property.get_value(),
                        ControlWord::SpaceAfter         => paragraph.spacing.after = property.get_value(),
                        ControlWord::SpaceBetweenLine   => paragraph.spacing.between_line = SpaceBetweenLine::from(property.get_value()),
                        ControlWord::SpaceLineMul       => paragraph.spacing.line_multiplier = property.get_value(),
                        ControlWord::Unicode            => {
                            let unicode = property.get_value_as::<u16>()?;
                            let str = String::from_utf16(&vec![unicode]).unwrap();
                            Self::add_text_to_document(&str, &painter_stack, &paragraph, &mut document)?
                        }
                        // Others
                        _ => {}
                    };
                }
                Token::EscapedChar(ch) => {
                    let mut tmp = [0u8; 4];
                    Self::add_text_to_document(ch.encode_utf8(&mut tmp), &painter_stack, &paragraph, &mut document)?
                }
                Token::PlainText(text) => Self::add_text_to_document(*text, &painter_stack, &paragraph, &mut document)?,
                Token::CRLF => Self::add_text_to_document("\n", &painter_stack, &paragraph, &mut document)?,
                Token::IgnorableDestination => {
                    return Err(ParserError::IgnorableDestinationParsingError);
                }
            };
        }
        return Ok(document);
    }

    fn add_text_to_document(text: &str, painter_stack: &Vec<Painter>, paragraph: &Paragraph, document: &mut RtfDocument) -> Result<(), ParserError> {
        let Some(current_painter) = painter_stack.last() else {
            return Err(ParserError::MalformedPainterStack);
        };
        let last_style_group = document.body.last_mut();
        // If the painter is the same as the previous one, merge the two block.
        if let Some(group) = last_style_group {
            if group.painter.eq(current_painter) && group.paragraph.eq(&paragraph) {
                group.text.push_str(text);
                return Ok(());
            }
        }
        // Else, push another StyleBlock on the stack with its own painter
        document.body.push(StyleBlock {
            painter: current_painter.clone(),
            paragraph: paragraph.clone(),
            text: String::from(text),
        });
        return Ok(());
    }

    fn get_token_at(&'a self, index: usize) -> Option<&'a Token<'a>> {
        return self.tokens.get(index);
    }

    // Get a view of the next token after cursor
    fn get_next_token(&'a self) -> Option<&'a Token<'a>> {
        return self.get_token_at(self.cursor);
    }

    fn consume_token_at(&mut self, index: usize) -> Option<Token<'a>> {
        if self.tokens.is_empty() {
            return None;
        }
        Some(self.tokens.remove(index))
    }

    fn consume_next_token(&mut self) -> Option<Token<'a>> {
        return self.consume_token_at(self.cursor);
    }

    // Consume token from cursor to <reference-token>
    fn _consume_tokens_until(&mut self, reference_token: Token<'a>) -> Vec<Token<'a>> {
        let mut ret = vec![];
        let token_type_id = mem::discriminant(&reference_token);
        while let Some(token) = self.consume_next_token() {
            let type_id = mem::discriminant(&token);
            ret.push(token);
            if type_id == token_type_id {
                break;
            }
        }
        return ret;
    }

    // The opening bracket should already be consumed
    fn consume_tokens_until_matching_bracket(&mut self) -> Vec<Token<'a>> {
        let mut ret = vec![];
        let mut count = 0;
        while let Some(token) = self.consume_next_token() {
            match token {
                Token::OpeningBracket => count += 1,
                Token::ClosingBracket => count -= 1,
                _ => {}
            }
            ret.push(token);
            if count < 0 {
                break;
            }
        }
        return ret;
    }

    // Consume all tokens until the header is read
    fn parse_header(&mut self) -> Result<RtfHeader, ParserError> {
        self.cursor = 0; // Reset the cursor
        let mut header = RtfHeader::default();
        while let (token, next_token) = (self.consume_next_token(), self.get_next_token()) {
            match (token, next_token) {
                (Some(Token::OpeningBracket), Some(&header_control_word!(FontTable, None))) => {
                    let font_table_tokens = self.consume_tokens_until_matching_bracket();
                    header.font_table = Self::parse_font_table(&font_table_tokens)?;
                    // After the font table, check if next token is plain text without consuming it. If so, break
                    if let Some(&Token::PlainText(_text)) = self.get_next_token() {
                        break;
                    }
                }
                (Some(Token::OpeningBracket), Some(&header_control_word!(ColorTable, None))) => {
                    let color_table_tokens = self.consume_tokens_until_matching_bracket();
                    header.color_table = Self::parse_color_table(&color_table_tokens)?;
                    // After the color table, check if next token is plain text without consuming it. If so, break
                    if let Some(&Token::PlainText(_text)) = self.get_next_token() {
                        break;
                    }
                }
                (Some(Token::OpeningBracket), Some(&header_control_word!(StyleSheet, None))) => {
                    let stylesheet_tokens = self.consume_tokens_until_matching_bracket();
                    header.stylesheet = Self::parse_stylesheet(&stylesheet_tokens)?;
                    // After the stylesheet, check if next token is plain text without consuming it. If so, break
                    if let Some(&Token::PlainText(_text)) = self.get_next_token() {
                        break;
                    }
                }
                // Break on par, pard, sectd, or plain - We no longer are in the header
                (Some(header_control_word!(Pard) | header_control_word!(Sectd) | header_control_word!(Plain) | header_control_word!(Par)), _) => break,
                // Break if it declares a font after the font table --> no more in the header
                (Some(header_control_word!(FontNumber)), _) => {
                    if !header.font_table.is_empty() {
                        break;
                    }
                }
                // Check and consume token
                (Some(ref token), _) => {
                    if let Some(charset) = CharacterSet::from(token) {
                        header.character_set = charset;
                    }
                }
                // Check next without consuming token : break conditions
                (_, Some(token)) => {
                    // Break on plain text not belonging to any table in the header
                    if let Token::PlainText(_text) = token {
                        break;
                    }
                }
                (None, None) => break,
            }
        }
        return Ok(header);
    }

    fn parse_font_table(font_tables_tokens: &Vec<Token<'a>>) -> Result<FontTable, ParserError> {
        let Some(font_table_first_token) = font_tables_tokens.get(0) else {
            return Err(ParserError::NoMoreToken);
        };
        if font_table_first_token != &header_control_word!(FontTable, None) {
            return Err(ParserError::InvalidToken(format!("{:?} is not a FontTable token", font_table_first_token)));
        }
        let mut table = HashMap::new();
        let mut current_key = 0;
        let mut current_font = Font::default();
        for token in font_tables_tokens.iter() {
            match token {
                Token::ControlSymbol((control_word, property)) => match control_word {
                    ControlWord::FontNumber => {
                        // Insert previous font
                        table.insert(current_key, current_font.clone());
                        if let Property::Value(key) = property {
                            current_key = *key as FontRef;
                        } else {
                            return Err(ParserError::InvalidFontIdentifier(*property));
                        }
                    }
                    ControlWord::Unknown(name) => {
                        if let Some(font_family) = FontFamily::from(name) {
                            current_font.font_family = font_family;
                        }
                    }
                    _ => {}
                },
                Token::PlainText(name) => {
                    current_font.name = name.trim_end_matches(';').to_string();
                }
                Token::ClosingBracket => {
                    table.insert(current_key, current_font.clone());
                } // Insert previous font
                _ => {}
            }
        }
        return Ok(table);
    }

    fn parse_color_table(color_table_tokens: &Vec<Token<'a>>) -> Result<ColorTable, ParserError> {
        let Some(color_table_first_token) = color_table_tokens.get(0) else {
            return Err(ParserError::NoMoreToken);
        };
        if color_table_first_token != &header_control_word!(ColorTable, None) {
            return Err(ParserError::InvalidToken(format!("ParserError: {:?} is not a ColorTable token", color_table_first_token)));
        }
        let mut table = HashMap::new();
        let mut current_key = 1;
        let mut current_color = Color::default();
        for token in color_table_tokens.iter() {
            match token {
                Token::ControlSymbol((control_word, property)) => match control_word {
                    ControlWord::ColorRed => current_color.red = property.get_value_as::<u8>()?,
                    ControlWord::ColorGreen => current_color.green = property.get_value_as::<u8>()?,
                    ControlWord::ColorBlue => {
                        current_color.blue = property.get_value_as::<u8>()?;
                        table.insert(current_key, current_color.clone());
                        current_key += 1;
                    }
                    _ => {}
                },
                _ => {}
            }
        }
        return Ok(table);
    }

    fn parse_stylesheet(stylesheet_tokens: &Vec<Token<'a>>) -> Result<StyleSheet, ParserError> {
        // TODO
        return Ok(StyleSheet::from([]));
    }

    // Traverse all the tokens and consume the ignore groups
    fn parse_ignore_groups(&mut self) {
        self.cursor = 0; // Reset the cursor
        while let (Some(token), Some(mut next_token)) = (self.get_token_at(self.cursor), self.get_token_at(self.cursor + 1)) {
            let mut i = 0;
            // Manage the case where there is CRLF between { and ignore_group
            // {\n /*/ignoregroup }
            while *next_token == Token::CRLF {
                if let Some(next_token_not_crlf) = self.get_token_at(self.cursor + 1 + i) {
                    next_token = next_token_not_crlf;
                    i += 1;
                } else {
                    break;
                }
            }
            match (token, next_token) {
                (Token::OpeningBracket, Token::IgnorableDestination) => {
                    self.consume_token_at(self.cursor); // Consume the opening bracket
                    self.consume_tokens_until_matching_bracket();
                }
                _ => {
                    self.cursor += 1;
                }
            }
        }
    }
}

#[cfg(test)]
pub mod tests {
    use super::*;
    use crate::header::CharacterSet::*;
    use crate::header::FontFamily::*;
    use crate::header::RtfHeader;
    use crate::include_test_file;
    use crate::lexer::Lexer;

    #[test]
    fn parser_header() {
        let tokens = Lexer::scan(r#"{ \rtf1\ansi{\fonttbl\f0\fswiss Helvetica;}\f0\pard Voici du texte en {\b gras}.\par }"#).unwrap();
        let doc = Parser::new(tokens).parse().unwrap();
        assert_eq!(
            doc.header,
            RtfHeader {
                character_set: Ansi,
                font_table: FontTable::from([(
                    0,
                    Font {
                        name: "Helvetica".into(),
                        character_set: 0,
                        font_family: Swiss
                    }
                )]),
                ..RtfHeader::default()
            }
        );
        assert_eq!(
            doc.body,
            [
                StyleBlock {
                    painter: Painter::default(),
                    paragraph: Default::default(),
                    text: "Voici du texte en ".into(),
                },
                StyleBlock {
                    painter: Painter { bold: true, ..Painter::default() },
                    paragraph: Default::default(),
                    text: "gras".into(),
                },
                StyleBlock {
                    painter: Painter::default(),
                    paragraph: Default::default(),
                    text: ".".into(),
                },
            ]
        );
    }

    #[test]
    fn parse_multiline_document() {
        let document = r"{\rtf1\ansi\deff0 {\fonttbl {\f0 Courier;}{\f1 ProFontWindows;}}
            {\colortbl;\red0\green0\blue0;\red255\green0\blue0;\red255\green255\blue0;}
            This line is font 0 which is courier\line
            \f1
            This line is font 1\line
            \f0
            This line is font 0 again\line
            This line has a \cf2 red \cf1 word\line
            \highlight3 while this line has a \cf2 red \cf1 word and is highlighted in yellow\highlight0\line
            Finally, back to the default color.\line
            }";
        let tokens = Lexer::scan(document).unwrap();
        let _doc = Parser::new(tokens).parse().unwrap();
    }

    #[test]
    fn parse_entire_file_header() {
        let file_content = include_test_file!("test-file.rtf");
        let tokens = Lexer::scan(file_content).unwrap();
        let doc = Parser::new(tokens).parse().unwrap();
        assert_eq!(
            doc.header,
            RtfHeader {
                character_set: Ansi,
                font_table: FontTable::from([
                    (
                        0,
                        Font {
                            name: "Helvetica".into(),
                            character_set: 0,
                            font_family: Swiss,
                        }
                    ),
                    (
                        1,
                        Font {
                            name: "Helvetica-Bold".into(),
                            character_set: 0,
                            font_family: Swiss,
                        }
                    )
                ]),
                color_table: ColorTable::from([(1, Color { red: 255, green: 255, blue: 255 }),]),
                ..RtfHeader::default()
            }
        );
    }

    #[test]
    fn parse_ignore_group() {
        let rtf = r"{\*\expandedcolortbl;;}";
        let tokens = Lexer::scan(rtf).unwrap();
        let mut parser = Parser::new(tokens);
        let document = parser.parse().unwrap();
        assert_eq!(parser.tokens, vec![]); // Should have consumed all the tokens
        assert_eq!(document.header, RtfHeader::default());
    }

    #[test]
    fn parse_ignore_group_with_crlf() {
        let rtf = r"{\
        \
        \*\expandedcolortbl;;}";
        let tokens = Lexer::scan(rtf).unwrap();
        let mut parser = Parser::new(tokens);
        let document = parser.parse().unwrap();
        assert_eq!(parser.tokens, vec![]); // Should have consumed all the tokens
        assert_eq!(document.header, RtfHeader::default());
    }

    #[test]
    fn parse_whitespaces() {
        let file_content = include_test_file!("list-item.rtf");
        let tokens = Lexer::scan(file_content).unwrap();
        let mut parser = Parser::new(tokens);
        let document = parser.parse().unwrap();
        assert_eq!(
            document.body,
            vec![StyleBlock {
                painter: Painter { font_size: 24, ..Painter::default() },
                paragraph: Default::default(),
                text: "\nEmpty start\n\nList test : \n - item 1\n - item 2\n - item 3\n - item 4".into(),
            },]
        );
    }

    #[test]
    fn parse_image_data() {
        // Try to parse without error
        let rtf_content = include_test_file!("file-with-image.rtf");
        let tokens = Lexer::scan(rtf_content).unwrap();
        let _document = Parser::new(tokens).parse();
    }

    #[test]
    fn parse_header_and_body() {
        let rtf = r#"{\rtf1\ansi\ansicpg1252\cocoartf2639
\cocoatextscaling0\cocoaplatform0{\fonttbl\f0\froman\fcharset0 Times-Bold;\f1\froman\fcharset0 Times-Roman;\f2\froman\fcharset0 Times-Italic;
\f3\fswiss\fcharset0 Helvetica;}
{\colortbl;\red255\green255\blue255;\red0\green0\blue10;\red0\green0\blue1;\red191\green191\blue191;
}
\f0\b\fs21 \cf2 Lorem ipsum
\fs56 \
\pard\pardeftab709\sl288\slmult1\sa225\qj\partightenfactor0

\f1\b0\fs21 \cf0 \
\pard\pardeftab709\fi-432\ri-1\sb240\sa120\partightenfactor0
\ls1\ilvl0
\f0\b\fs36\cf2\plain Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nunc ac faucibus odio. \
\pard\pardeftab709\sl288\slmult1\sa225\qj\partightenfactor0
}"#;
        let tokens = Lexer::scan(rtf).unwrap();
        let document = Parser::new(tokens).parse().unwrap();
        assert_eq!(document.body[0].text, "Lorem ipsum");
        assert_eq!(document.body[1].text, "\n");
        assert_eq!(document.body[2].text, "\n");
        assert_eq!(document.body[3].text, "Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nunc ac faucibus odio. \n");
    }

    #[test]
    fn parse_paragraph_aligment() {
        let rtf = r#"{\rtf1\ansi\deff0 {\fonttbl {\f0 Times;}}
        \fs34
        {\pard \qc \fs60 Annalium Romae\par}
        {\pard \qj
            Urbem Romam a principio reges habuere; libertatem et
            \par}
        {\pard \ql
            Non Cinnae, non Sullae longa dominatio; et Pompei Crassique potentia
            \par}"#;
        let tokens = Lexer::scan(rtf).unwrap();
        let document = Parser::new(tokens).parse().unwrap();
        assert_eq!(document.body[0].paragraph.alignment, Alignment::Center);
        assert_eq!(document.body[1].paragraph.alignment, Alignment::Justify);
        assert_eq!(document.body[2].paragraph.alignment, Alignment::LeftAligned);
    }

    #[test]
    fn should_parse_escaped_char() {
        let rtf = r"{\rtf1\ansi\deff0 {\fonttbl {\f0 Times;}}je suis une b\'eate}";
        let tokens = Lexer::scan(rtf).unwrap();
        let document = Parser::new(tokens).parse().unwrap();
        assert_eq!(document.body[0].text, "je suis une bête");
    }

    #[test]
    fn parse_plain_directive() {
        let rtf = r"{\rtf1{\fonttbl {\f0 Times;}}\f0\b\fs36\u\cf2\plain Plain text}";
        let tokens = Lexer::scan(rtf).unwrap();
        let document = Parser::new(tokens).parse().unwrap();
        let mut painter = Painter::default();
        painter.bold = true;
        painter.font_size = 36;
        assert_eq!(document.body[0].painter, painter);
    }

    #[test]
    fn parse_color_table() {
        // cf0 is unset color
        // cf1 is first color
        // cf2 is second color
        // etc...
        let rtf = r#"{\rtf1\ansi\ansicpg936\cocoartf2761
            \cocoatextscaling0\cocoaplatform0{\fonttbl\f0\fswiss\fcharset0 Helvetica;\f1\fnil\fcharset134 PingFangSC-Regular;}
            {\colortbl;\red255\green255\blue255;\red251\green2\blue7;\red114\green44\blue253;}
            {\*\expandedcolortbl;;\cssrgb\c100000\c14913\c0;\cssrgb\c52799\c30710\c99498;}
            \paperw11900\paperh16840\margl1440\margr1440\vieww11520\viewh8400\viewkind0
            \pard\tx720\tx1440\tx2160\tx2880\tx3600\tx4320\tx5040\tx5760\tx6480\tx7200\tx7920\tx8640\pardirnatural\partightenfactor0
            
            \f0\fs24 \cf2 A
            \f1 \cf3 B}"#;
        let tokens = Lexer::scan(rtf).unwrap();
        let document = Parser::new(tokens).parse().unwrap();
        assert_eq!(document.header.color_table.get(&document.body[0].painter.color_ref).unwrap(), &Color { red: 251, green: 2, blue: 7 });
    }

    #[test]
    fn parse_underline() {
        // \\ul underline true
        // \\ulnone underline false
        let rtf = r#"{\rtf1\ansi\ansicpg936\cocoartf2761
            \cocoatextscaling0\cocoaplatform0{\fonttbl\f0\fswiss\fcharset0 Helvetica;}
            {\colortbl;\red255\green255\blue255;}
            {\*\expandedcolortbl;;}
            \paperw11900\paperh16840\margl1440\margr1440\vieww11520\viewh8400\viewkind0
            \pard\tx720\tx1440\tx2160\tx2880\tx3600\tx4320\tx5040\tx5760\tx6480\tx7200\tx7920\tx8640\pardirnatural\partightenfactor0
            
            \f0\fs24 \cf0 \ul \ulc0 a\ulnone A}"#;
        let tokens = Lexer::scan(rtf).unwrap();
        let document = Parser::new(tokens).parse().unwrap();
        assert_eq!(&document.body[0].painter.underline, &true);
        assert_eq!(&document.body[1].painter.underline, &false);
    }

    #[test]
    fn parse_unicode() {
        // start with \\uc0
        // \u21834 => 啊
        let rtf = r#"{\rtf1\ansi\ansicpg936\cocoartf2761
            \cocoatextscaling0\cocoaplatform0{\fonttbl\f0\fswiss\fcharset0 Helvetica;}
            {\colortbl;\red255\green255\blue255;}
            {\*\expandedcolortbl;;}
            \paperw11900\paperh16840\margl1440\margr1440\vieww11520\viewh8400\viewkind0
            \pard\tx720\tx1440\tx2160\tx2880\tx3600\tx4320\tx5040\tx5760\tx6480\tx7200\tx7920\tx8640\pardirnatural\partightenfactor0
            
            \f0\fs24 \cf0 \uc0\u21834  \u21834 }"#;
        // \f0\fs24 \cf0 \uc0\u21834  \u21834 }"#;
        let tokens = Lexer::scan(rtf).unwrap();
        let document = Parser::new(tokens).parse().unwrap();
        assert_eq!(&document.body[0].text, "啊 啊");
    }
}