Nand2Tetris_Part2_10

Posted on | Edited on | In ,
| 36k | 5:01

Go Go Go🎯

Unit 10.1 Compiler I: Roadmap

roadmap

Unit 10.2 Lexical Analysis

Tokenizing(first approximation)

Tokenizing = grouping characters into tokens.
A token is a string of characters that has a meaning.
A programming language specification must document(among other things) it’s allowable tokens.

Jack tokens

  1. keywords
  2. symbols
  3. integers
  4. strings
  5. identifiers

Jack_tokens

Tokenizer:

  • Handles the compiler’s input
  • Allows advancing the input
  • Supplies the current token’s value and type

Unit 10.3 Grammars

  • A grammar is a set of rules, describing how tokens can be combined to create valid language constructs
  • Each rule consists of a left-hand side, listing a template’s name, and a right-hand side, describing how the template is composed.

Jack_grammar_subset

Parsing:

  • Determining if a given input conforms to a grammar
  • In the process, uncovering the grammatical structure of the given input.

Unit 10.4 Parse Trees

Parse tree is a data structure. If you have learned the course of data structure, it will be easy to understand parse tree.

Unit 10.5 Parser Logic

A. Parsing logic

  • Follow the rule, and parse the input accordingly
  • If get a non-terminal rule xxx, call compilexxx
  • Do this recursively

B. Init

  • Advance the tokenizer
  • Call compileWhileStatement(see the video for more details🔍)

C. Parser design

  • A set of compilexxx methods, one for each(non-trivial) rule xxx
  • The handing of some rules is embedded in other rules
  • The code of each compilexxx method follows the rule xxx
  • Each compilexxx method is responsible for advancing and handing it’s own part of the input

D. Some observations about grammars and parsing

  • LL grammar: can be parsed by a recursive descent parser without backtracking
  • LL(k) parser: a parser that needs to look ahead at most k tokens in order to determine which rule is applicable
  • The grammar that we saw so far is LL(1)(That means easier to implepement.🎉)

Unit 10.6 The Jack Grammar

grammar_notation

lexical elements

lexical_elements

program structure

program_structure

statements

statements

expressions

expressions_1

expressions_2

Unit 10.7 The Jack Analyzer

1
2
        parser
input ---------> XML output

terminal_rules

non-terminal_rules_1

non-terminal_rules_2

Unit 10.8 The Jack Analyzer: Proposed Implementations

Implementation plan: JackTokenizer -> CompilationEngine -> JackAnalyzer(top-most module)

The JackAnalyzer:

  • Uses the services of a JackTokenizer
  • Written according to the Jack grammar
  • The top-most module
  • Input: a single fileName.jack, or a directory containing 0 or more such files
  • For each file, goes through the following logic
    • Creates a JackTokenizer from fileName.jack
    • Creates an output file named fileName.xml and prepares it for writing
    • Creates and uses a CompilationEngine to compile the input JackTokenizer into the output file.

The JackTokenizer:

  • Handle the compiler’s input
  • Ignoring white space
  • Advancing the input, one token at a time
  • Getting the value and type of the current token

The CompilationEngine design:

  • Gets its input from a JackTokenizer, and emits its output to an output file
  • The output is generates by a series of compilexxx routines, one for (almost) every non-terminal rule xxx in the grammar
  • Each compilexxx routine is responsible for handling all the tokens that make up xxx, advancing the tokenizer exactly beyond these tokens, and outputing the parsing of xxx

Unit 10.9 Project: Building a Syntax Analyzer

A syntax Analyzer has three modules: JackAnalyzer, JackTokenizer and CompilationEngine. These modules are designed to handle the language’s syntax.

Here is the codes(top-down):

main.cpp
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
#include <iostream>
#include <string>

#include "jackanalyzer.h"

using namespace std;

int main(int argc, char** argv) {
    if(argc != 2) {
        cout << "Input error!\nUsage: .\\SyntaxAnalyzer.exe [filename or filepath]" << endl;
        return 0;
    }
    try {
        string path(argv[1]);
        JackAnalyzer jack(path);
        jack.doAnalyzing();
    } catch(exception& e) {
        cerr << e.what() << endl;
    }
    return 0;
}

✅ main.cpp: Start Analyzing and catch the exception for debugging.

jackanalyzer.h
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
#ifndef __JACK_ANALYZER_H__
#define __JACK_ANALYZER_H__

#include <vector>
#include <string>

using namespace std;

class JackAnalyzer {
public:
    JackAnalyzer(const string& filepath);    
    void doAnalyzing();
private:
    void parseFilePath(string path);
private:
    vector<string> m_filenames;
};

#endif
jackanalyzer.cpp
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
#include "jackanalyzer.h"
#include "compilationengine.h"

#include <fstream>
#include <iostream>
#include <stdexcept>
#include <windows.h>


JackAnalyzer::JackAnalyzer(const string& filepath) {
    parseFilePath(filepath);
}

void JackAnalyzer::doAnalyzing() {
    if(m_filenames.empty()) {
        throw runtime_error("Error! Input file or path are inappropriate");
        return;
    }
    for(auto& s: m_filenames) {
        // generate XxxT_.xml(tokenized) for test
        JackTokenizer jacktokenizer(s);
        string t1 = s.substr(0, s.find(".jack")) + "T_.xml";

        ofstream t_ofs(t1);
        t_ofs << "<tokens>\n";
        while(jacktokenizer.hasMoreTokens()) {
            jacktokenizer.advance();
            t_ofs << jacktokenizer.curTokenToXMLString() << '\n';
        }
        t_ofs << "</tokens>\n";
        t_ofs.close();
        
        // generate Xxx_.xml(compiled) for test
        string t2 = s.substr(0, s.find(".jack")) + "_.xml";
        CompilationEngine cengine(s, t2);
    }
}

void JackAnalyzer::parseFilePath(string path) {
    bool isDir = true;
    for(int i = path.length() - 1; i >= 0; --i) {
        if(path[i] == '\\') {
            break;
        } else if(path[i] == '.') {
            isDir = false;
        }
    }
    if(isDir) {
        WIN32_FIND_DATAA data;
        string tmp = path + "\\*";
        HANDLE hFind = FindFirstFileA(tmp.c_str(), &data);
        do {
            string t(data.cFileName);
            auto it = t.find(".jack");
            if(it != string::npos) {
                m_filenames.push_back(path + "\\" + t);
            }
        } while(FindNextFileA(hFind, &data));
    } else {
        m_filenames.push_back(path);
    }
}

✅ JackAnalyzer: Parse filepath for tokenizing and compiling.

jacktokenizer.h
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
#ifndef __JACK_TOKENIZER_H__
#define __JACK_TOKENIZER_H__

#include <string>
#include <sstream>

using namespace std;

class JackTokenizer {
public:
    enum TokenType {
        T_UNKNOWN,
        T_KEYWORD,
        T_SYMBOL,
        T_IDENTIFIER,
        T_INT_CONST,
        T_STRING_CONST,
    };
public:
    JackTokenizer(const string& filepath);
    bool hasMoreTokens();
    void advance();
    TokenType tokenType();
    string keyword();
    char symbol();
    string identifier();
    int intVal();
    string stringVal();

    string curTokenToXMLString();
    
private:
    stringstream m_iss;
    string m_curToken;
};

#endif
jacktokenizer.cpp
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
#include "jacktokenizer.h"

#include <iostream>
#include <fstream>
#include <regex>
#include <unordered_set>

static unordered_set<char> s_symbols = {
    '{', '}', '(', ')', '[', ']',
    '.', ',', ';', 
    '+', '-', '*', '/',
    '&', '|', '<', '>', '=', '~',
};

static unordered_set<string> s_keywords = {
    "class", "method", "int", "function",
    "boolean", "constructor", "char",
    "void", "var", "static", "field",
    "let", "do", "if", "else", "while",
    "return", "true", "false", "null", 
    "this",
};

static string removeComments(const string& source) {
    enum State {
        NORMAL,
        IN_STRING,
        IN_SINGLE_LINE_COMMENT,
        IN_MULT_LINE_COMMENT,
    };
    State state = NORMAL;
    string result;
    size_t i = 0;
    size_t len = source.length();

    while(i < len) {
        char current = source[i];
        char next = (i + 1 < len) ? source[i + 1] : '\0';
        switch(state) {
            case NORMAL:
                if(current == '"') {
                    result += current;
                    state = IN_STRING;
                } else if(current == '/' && next == '/') {
                    state = IN_SINGLE_LINE_COMMENT;
                    ++i;
                } else if(current == '/' && next == '*') {
                    state = IN_MULT_LINE_COMMENT;
                    ++i;
                } else {
                    result += current;
                }
                break;
            case IN_STRING:
                result += current;
                if(current == '"' && source[i - 1] != '\\') {
                    state = NORMAL;
                }
                break;
            case IN_SINGLE_LINE_COMMENT:
                if(current == '\n') {
                    result += '\n';
                    state = NORMAL;
                }
                break;
            case IN_MULT_LINE_COMMENT:
                if(current == '*' && next == '/') {
                    state = NORMAL;
                    ++i;
                }
                break;
        }
        ++i;
    }

    regex endl_re("\\r*\\n+");
    regex space_re("\\s+");
    regex tailSpace_re("\\s+$");
    result = regex_replace(result, endl_re, "");
    result = regex_replace(result, space_re, " ");
    result = regex_replace(result, tailSpace_re, "");

    return result;
}

JackTokenizer::JackTokenizer(const string& filepath) {
    ifstream ifs(filepath);
    if(!ifs) {
        throw runtime_error("JackTokenizer fails to open file: " + filepath);
    }
    string src_code((istreambuf_iterator<char>(ifs)), istreambuf_iterator<char>());
    ifs.close();
    string dst_code = removeComments(src_code);
    m_iss << dst_code;
}

bool JackTokenizer::hasMoreTokens() {
    return !m_iss.eof() && m_iss.peek() != EOF;
}

void JackTokenizer::advance() {
    if(!hasMoreTokens()) {
        throw runtime_error("JackTokenizer: expected a token");
        return;
    }

    m_curToken.clear();
    while(hasMoreTokens()) {
        char next = m_iss.peek();
        if(isalnum(next) || next == '"') {
            m_curToken.push_back(m_iss.get());
            if(m_curToken[0] == '"') {
                while(hasMoreTokens()) {
                    char c = m_iss.get();
                    m_curToken.push_back(c);
                    if(c == '"')
                        break;
                }
            }
        } else if(next == ' ') {
            m_iss.get();
            if(!m_curToken.empty())
                break;
        } else if(s_symbols.count(next)) {
            if(m_curToken.empty())
                m_curToken.push_back(m_iss.get());
            break;
        }
    }
}

JackTokenizer::TokenType JackTokenizer::tokenType() {
    TokenType ret = T_UNKNOWN;
    if(m_curToken.empty())
        return ret;
    else if(s_symbols.count(m_curToken[0]))
        ret = T_SYMBOL;
    else if(s_keywords.count(m_curToken))
        ret = T_KEYWORD;
    else if(all_of(m_curToken.begin(), m_curToken.end(), [](char c) { return isdigit(c); }))
        ret = T_INT_CONST;
    else if(m_curToken[0] == '"') 
        ret = T_STRING_CONST;
    else
        ret = T_IDENTIFIER;
    return ret;
}

string JackTokenizer::keyword() {
    return m_curToken;
}

char JackTokenizer::symbol() {
    return m_curToken[0];
}

string JackTokenizer::identifier() {
    return m_curToken;
}

int JackTokenizer::intVal() {
    return stoi(m_curToken);
}

string JackTokenizer::stringVal() {
    return m_curToken.substr(1, m_curToken.length() - 2);
}

string JackTokenizer::curTokenToXMLString() {
    stringstream ss;
    TokenType tt = tokenType();
    if(tt == JackTokenizer::TokenType::T_SYMBOL) {
        ss << "<symbol> ";
        if(m_curToken == "<")
            ss << "&lt;";
        else if(m_curToken == ">")
            ss << "&gt;";
        else if(m_curToken == "&")
            ss << "&amp;";
        else 
            ss << symbol();
        ss << " </symbol>";
    } else if(tt == JackTokenizer::TokenType::T_KEYWORD) {
        ss << "<keyword> " << keyword() << " </keyword>";
    } else if(tt == JackTokenizer::TokenType::T_INT_CONST) {
        ss << "<integerConstant> " << intVal() << " </integerConstant>";
    } else if(tt == JackTokenizer::TokenType::T_STRING_CONST) {
        ss << "<stringConstant> " << stringVal() << " </stringConstant>";
    } else if(tt == JackTokenizer::TokenType::T_IDENTIFIER) {
        ss << "<identifier> " << identifier() << " </identifier>";
    }
    return ss.str();
}

✅ JackTokenizer: Remove the comments from source file and tokenize the source code.

compliationengine.h
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
#ifndef __COMPILATION_ENGINE_H__
#define __COMPILATION_ENGINE_H__


#include <fstream>
#include <initializer_list>

#include "jacktokenizer.h"

using namespace std;

class CompilationEngine {
public:
    CompilationEngine(const string& input, const string& output);
    ~CompilationEngine();

private:    
    inline void outputAndAdvance();
    inline bool isType();
    inline bool isSymbol(char c);
    inline bool isSubroutine();
    
    void compileClass();
    void compileClassVarDec();
    void compileSubroutine();
    void compileParameterList();
    void compileVarDec();
    void compileStatements();
    void compileDo();
    void compileLet();
    void compileWhile();
    void compileReturn();
    void compileIf();
    void compileExpression();
    void compileTerm();
    void compileExpressionList();

private:
    ofstream m_ofs;
    JackTokenizer m_tokenizer;
};

#endif
compliationengine.cpp
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
#include "compilationengine.h"

#include <stdexcept>
#include <unordered_set>

CompilationEngine::CompilationEngine(const string& input, const string& output)
    : m_ofs(output), m_tokenizer(input) {
    if(!m_ofs) {
        throw(runtime_error("CompilationEngine fails to open file: " + output));
    }
    if(!m_tokenizer.hasMoreTokens())
        throw(runtime_error("The input file is empty"));

    m_tokenizer.advance();

    if(m_tokenizer.tokenType() == JackTokenizer::T_KEYWORD 
        && m_tokenizer.keyword() == "class") {
        compileClass();
    } else {
        throw(runtime_error("The first keyword is not class"));
    }
}

CompilationEngine::~CompilationEngine() {
    m_ofs.close();
}

inline void CompilationEngine::outputAndAdvance() {
    m_ofs << m_tokenizer.curTokenToXMLString() << '\n';
    m_tokenizer.advance();
}

inline bool CompilationEngine::isType() {
    return m_tokenizer.tokenType() == JackTokenizer::T_IDENTIFIER ||
          (m_tokenizer.tokenType() == JackTokenizer::T_KEYWORD && 
          (m_tokenizer.keyword() == "int" || 
           m_tokenizer.keyword() == "char" ||
           m_tokenizer.keyword() == "boolean"));
}

inline bool CompilationEngine::isSymbol(char c) {
    return m_tokenizer.tokenType() == JackTokenizer::T_SYMBOL &&
            m_tokenizer.symbol() == c;
}

inline bool CompilationEngine::isSubroutine() {
    return m_tokenizer.tokenType() == JackTokenizer::T_KEYWORD &&
          (m_tokenizer.keyword() == "constructor" ||
           m_tokenizer.keyword() == "function" ||
           m_tokenizer.keyword() == "method");
}

void CompilationEngine::compileClass() {
    m_ofs << "<class>\n";

    // class className { classVarDec* subroutineDec* }
    // class
    outputAndAdvance();
    // className
    if(m_tokenizer.tokenType() == JackTokenizer::T_IDENTIFIER) {
        outputAndAdvance();
    } else {
        throw runtime_error("(class)expected className");
    }
    // {
    if(isSymbol('{')) {
        outputAndAdvance();
    } else {
        throw runtime_error("(class)expected '{'");
    }
    // classVarDec*
    compileClassVarDec();
    // subroutineDec*
    compileSubroutine();
    // }
    if(isSymbol('}')) {
        m_ofs << m_tokenizer.curTokenToXMLString() << '\n';
    } else {
        throw runtime_error("(class)expected '}'");
    }

    m_ofs << "</class>\n";
}

void CompilationEngine::compileClassVarDec() {
    while(m_tokenizer.tokenType() == JackTokenizer::T_KEYWORD &&
         (m_tokenizer.keyword() == "static" || 
          m_tokenizer.keyword() == "field")) {
        m_ofs << "<classVarDec>\n";
        // (static | field) type varName (, varName)*;
        // static | field
        outputAndAdvance();
        // type
        if(isType()) {
            outputAndAdvance();
        } else {
            throw runtime_error("(classVarDec)expected type");
        }
        // varName
        if(m_tokenizer.tokenType() == JackTokenizer::T_IDENTIFIER) {
            outputAndAdvance();
            while(isSymbol(',')) {
                // ,
                outputAndAdvance();
                if(m_tokenizer.tokenType() == JackTokenizer::T_IDENTIFIER) {
                    outputAndAdvance();
                } else {
                    throw runtime_error("(classVarDec-,)expected varName");
                }
            }
        } else {
            throw runtime_error("(classVarDec)expected varName");
        }
        // ;
        if(isSymbol(';')) {
            outputAndAdvance();
        } else {
            throw runtime_error("(classVarDec)expected ';'");
        }

        m_ofs << "</classVarDec>\n";
    }
}



void CompilationEngine::compileSubroutine() {
    while(isSubroutine()) {
        m_ofs << "<subroutineDec>\n";
        // (constructor | function | method)
        // (void | type) subroutineName ( parameterList )
        // subroutineBody
        // (constructor | function | method)
        outputAndAdvance();
        // void | type    
        if((m_tokenizer.tokenType() == JackTokenizer::T_KEYWORD && m_tokenizer.keyword() == "void") ||
            isType()) {
            outputAndAdvance();
        } else {
            throw runtime_error("(subroutineDec)expected type");
        }
        // subroutineName
        if(m_tokenizer.tokenType() == JackTokenizer::T_IDENTIFIER) {
            outputAndAdvance();
        } else {
            throw runtime_error("(subroutineDec)expected subroutineName");
        }
        // (
        if(isSymbol('(')) {
            outputAndAdvance();
        } else {
            throw runtime_error("(subroutineDec)expected '('");
        }
        // parameterList
        compileParameterList();
        // )
        if(isSymbol(')')) {
            outputAndAdvance();
        } else {
            throw runtime_error("(subroutineDec)expected ')'");
        }
        // subroutineBody
        // { varDec* statements }
        m_ofs << "<subroutineBody>" << '\n';
        // {
        if(isSymbol('{')) {
            outputAndAdvance();
        } else {
            throw runtime_error("(subroutineBody)expected '{'");
        }
        // varDec
        compileVarDec();
        // statements
        compileStatements();
        // }
        if(isSymbol('}')) {
            outputAndAdvance();
        } else {
            throw runtime_error("(subroutineBody)expected '}'");
        }
        m_ofs << "</subroutineBody>" << '\n';

        m_ofs << "</subroutineDec>\n";
    }
}

void CompilationEngine::compileParameterList() {
    m_ofs << "<parameterList>\n";
    // ((type varName)(, type varName)*)?
    while(isType()) {
        // type
        outputAndAdvance();
        // varName
        if(m_tokenizer.tokenType() == JackTokenizer::T_IDENTIFIER) {
            outputAndAdvance();
            // ,
            if(isSymbol(',')) {
                outputAndAdvance();
            } else {
                break;
            }
        } else {
            throw runtime_error("(parameterlist)expected varName");
        }
    }

    m_ofs << "</parameterList>\n";
}

void CompilationEngine::compileVarDec() {
    // var type varName (, varName)* ;
    while(m_tokenizer.tokenType() == JackTokenizer::T_KEYWORD &&
            m_tokenizer.keyword() == "var") {
        m_ofs << "<varDec>\n";
        // var
        outputAndAdvance();
        if(isType()) {
            // type
            outputAndAdvance();
            while(m_tokenizer.tokenType() == JackTokenizer::T_IDENTIFIER) {
                // varName
                outputAndAdvance();
                // ,
                if(isSymbol(',')) {
                    outputAndAdvance();
                } else {
                    break;
                }
            }
            // ;
            if(isSymbol(';')) {
                outputAndAdvance();
            } else {
                throw runtime_error("(VarDec)expected ';'");
            }
        } else {
            throw runtime_error("(VarDec)expected type");
        }
        m_ofs << "</varDec>\n";
    }
}

void CompilationEngine::compileStatements() {
    m_ofs << "<statements>\n"; 

    while(m_tokenizer.tokenType() == JackTokenizer::T_KEYWORD) {
        if(m_tokenizer.keyword() == "let") {
            compileLet();
        } else if(m_tokenizer.keyword() == "if") {
            compileIf();
        } else if(m_tokenizer.keyword() == "while") {
            compileWhile();
        } else if(m_tokenizer.keyword() == "do") {
            compileDo();
        } else if(m_tokenizer.keyword() == "return") {
            compileReturn();
        } else {
            throw runtime_error("(statements)expected let or if or while or do or return");
            break;
        }
    }

    m_ofs << "</statements>\n";
}

void CompilationEngine::compileDo() {
    m_ofs << "<doStatement>\n";
    // do subroutineCall
    // do
    outputAndAdvance();
    // subroutineName | className | varName
    if(m_tokenizer.tokenType() == JackTokenizer::T_IDENTIFIER) {
        outputAndAdvance();
    } else {
        throw runtime_error("(Do)expected subroutineName");
    }
    // ( | .
    if(isSymbol('(')) {
        // (
        outputAndAdvance();
        // expressionList
        compileExpressionList();
        // )
        if(isSymbol(')')) {
            outputAndAdvance();
        } else {
            throw runtime_error("(SubroutineCall)expected ')'");
        }
    } else if(isSymbol('.')) {
        // .
        outputAndAdvance();
        // subroutineName
        if(m_tokenizer.tokenType() == JackTokenizer::T_IDENTIFIER) {
            outputAndAdvance();
        } else {
            throw runtime_error("(subroutineCall)expected 'subroutineName'");
        }
        // (
        if(isSymbol('(')) {
            outputAndAdvance();
        } else {
            throw runtime_error("(subroutineCall)expected '('");
        }
        // expressionList
        compileExpressionList();
        // )
        if(isSymbol(')')) {
            outputAndAdvance();
        } else {
            throw runtime_error("(subroutineCall)expected ')'");
        }
    } else {
        throw runtime_error("(subroutineCall)expected '(' or '.'");
    }
    // ;
    if(isSymbol(';')) {
        outputAndAdvance();
    } else {
        throw runtime_error("(Do)expected ';'");
    }

    m_ofs << "</doStatement>\n";
}

void CompilationEngine::compileLet() {
    m_ofs << "<letStatement>\n";

    // let
    outputAndAdvance();
    // varName
    if(m_tokenizer.tokenType() == JackTokenizer::T_IDENTIFIER) {
        outputAndAdvance();
    } else {
        throw runtime_error("(Let)expected varName");
    }
    // ([expression])?
    if(isSymbol('[')) {
        outputAndAdvance();
        compileExpression();
        if(isSymbol(']')) {
            outputAndAdvance();
        } else {
            throw runtime_error("(Let)expected ']'");
        }
    }
    // =
    if(isSymbol('=')) {
       outputAndAdvance();
    } else {
        throw runtime_error("(Let)expected '='");
    }
    // expression
    compileExpression();
    // ;
    if(isSymbol(';')) {
        outputAndAdvance();
    } else {
        throw runtime_error("(Let)expected ';'");
    }

    m_ofs << "</letStatement>\n";
}

void CompilationEngine::compileWhile() {
    m_ofs << "<whileStatement>\n";

    // while
    outputAndAdvance();
    // (
    if(isSymbol('(')) {
        outputAndAdvance();
    } else {
        throw runtime_error("(While)expected '('");
    }
    // expression
    compileExpression();
    // )
    if(isSymbol(')')) {
        outputAndAdvance();
    } else {
        throw runtime_error("(While)expected ')'");
    }
    // {
    if(isSymbol('{')) {
        outputAndAdvance();
    } else {
        throw runtime_error("(While)expected '{'");
    }
    // statements
    compileStatements();
    // }
    if(isSymbol('}')) {
        outputAndAdvance();
    } else {
        throw runtime_error("(While)expected '}'");
    }

    m_ofs << "</whileStatement>\n";
}

void CompilationEngine::compileReturn() {
    m_ofs << "<returnStatement>\n";

    // return expression?;
    // return
    outputAndAdvance();
    // expression?
    if(!isSymbol(';')) {
        compileExpression();
    }
    // ;
    if(isSymbol(';')) {
        outputAndAdvance();
    } else {
        throw runtime_error("(Return)expected ';'");
    }
    m_ofs << "</returnStatement>\n";
}

void CompilationEngine::compileIf() {
    m_ofs << "<ifStatement>\n";

    // if
    outputAndAdvance();
    // (
    if(isSymbol('(')) {
        outputAndAdvance();
    } else {
        throw runtime_error("(If)expected '('");
    }
    // expression
    compileExpression();
    // )
    if(isSymbol(')')) {
        outputAndAdvance();
    } else {
        throw runtime_error("(If)expected ')'");
    }
    // {
    if(isSymbol('{')) {
        outputAndAdvance();
    } else {
        throw runtime_error("(If)expected '{'");
    }
    // statements
    compileStatements();
    // }
    if(isSymbol('}')) {
        outputAndAdvance();
    } else {
        throw runtime_error("(If)expected '}'");
    }
    // (else { statements })?
    // else
    if(m_tokenizer.tokenType() == JackTokenizer::T_KEYWORD &&
        m_tokenizer.keyword() == "else") {
        outputAndAdvance();
        // {
        if(isSymbol('{')) {
            outputAndAdvance();
        } else {
            throw runtime_error("(If-else)expected '{'");
        }
        // statements
        compileStatements();
        // }
        if(isSymbol('}')) {
            outputAndAdvance();
        } else {
            throw runtime_error("(If-else)expected '}'");
        }
    }

    m_ofs << "</ifStatement>\n";
}

void CompilationEngine::compileExpression() {
    m_ofs << "<expression>\n";

    // term (op term)*
    // term
    compileTerm();
    static const unordered_set<char> s_op = {
        '+', '-', '*', '/', '&', '|', '<', '>', '=',
    };
    // op term
    while(m_tokenizer.tokenType() == JackTokenizer::T_SYMBOL &&
            s_op.count(m_tokenizer.symbol())) {
        outputAndAdvance();
        compileTerm();
    }

    m_ofs << "</expression>\n";
}

void CompilationEngine::compileTerm() {
    m_ofs << "<term>\n";
    // integerConstant | stringConstant | keywordConstant |
    // varName | varName [expression] | subroutineCall |
    // (expression) | unaryOp term
    JackTokenizer::TokenType tt = m_tokenizer.tokenType();
    if(tt == JackTokenizer::T_INT_CONST) {
        // integerConstant
        outputAndAdvance();
    } else if(tt == JackTokenizer::T_STRING_CONST) {
        // stringConstant
        outputAndAdvance();
    } else if(tt == JackTokenizer::T_KEYWORD) {
        if(m_tokenizer.keyword() == "true" || m_tokenizer.keyword() == "false" ||
            m_tokenizer.keyword() == "null" || m_tokenizer.keyword() == "this") {
            // kewordConstant
            outputAndAdvance();
        } else {
            throw runtime_error("(term)expected keyword: true, false, null or this");
        }
    } else if(tt == JackTokenizer::T_IDENTIFIER) {
        // varName | subroutineName
        outputAndAdvance();
        if(m_tokenizer.tokenType() == JackTokenizer::T_SYMBOL) {
            // [expression]
            if(m_tokenizer.symbol() == '[') {
                outputAndAdvance();
                compileExpression();
                if(isSymbol(']')) {
                    outputAndAdvance();
                } else {
                    throw runtime_error("(term)expected ']");
                }
            } else if(m_tokenizer.symbol() == '(') {
                // (expressionList)
                outputAndAdvance();
                compileExpressionList();
                if(isSymbol(')')) {
                    outputAndAdvance();
                } else {
                    throw runtime_error("(term)expected ')'");
                }
            } else if(m_tokenizer.symbol() == '.') {
                // . soubroutineName { expressionList }
                // .
                outputAndAdvance();
                if(m_tokenizer.tokenType() == JackTokenizer::T_IDENTIFIER) {
                    outputAndAdvance();
                } else {
                    throw runtime_error("(term)expected subroutineName");
                }
                // (
                if(isSymbol('(')) {
                    outputAndAdvance();
                } else {
                    throw runtime_error("(term)expected '('");
                }
                // expressionList
                compileExpressionList();
                // )
                if(isSymbol(')')) {
                    outputAndAdvance();
                } else {
                    throw runtime_error("(term)expected ')'");
                }
            }
        }
    } else if(tt == JackTokenizer::T_SYMBOL) {
        // ( expression )
        if(m_tokenizer.symbol() == '(') {
            outputAndAdvance();
            // expression
            compileExpression();
            // )
            if(isSymbol(')')) {
                outputAndAdvance();
            } else {
                throw runtime_error("(term)expected ')'");
            }
        } else if(m_tokenizer.symbol() == '-' ||
            m_tokenizer.symbol() == '~') {
            // unaryOp
            outputAndAdvance();
            // term
            compileTerm();
        }
    }

    m_ofs << "</term>\n";
}

void CompilationEngine::compileExpressionList() {
    m_ofs << "<expressionList>\n";

    if(!isSymbol(')')) {
        compileExpression();
        while(isSymbol(',')) {
            // ,
            outputAndAdvance();
            // expression
            compileExpression();
        }
    }

    m_ofs << "</expressionList>\n";
}

✅ CompilationEngine: use token parse code.

Unit 10.10 Perspective

  1. Compilers don’t only translate programs, they also find and report errors. Are we going to handle errors in our Jack compiler?
  • We decided to completely sidestep in this module. It’s an optional feature for you.
  1. Can we use the techniques that we learned in this module to develop parsers for other programming languages?
  • Parsers are quite useful not only for parsing programs but also for parsing any syntax-based text which happens a lot in the careers of many application programmers. But it’s not necessarily for language like Java and C++.
  1. Why didn’t we use lex and yacc?
  • lex and yacc are two software tools that come from the world of Unix. Lex stands for Lexical Analyzer which actually refers to a tool which is capable of generating tokenizing code automatically. Yacc stands for the whimsical compiler compiler which actually refers to a tool which is capable of generating parsing code automatically. They generate syntax analysis code that can be customized and developed into a full scale syntax analysis tool. But this course is about doing everything from scratch from the ground up in your bare hands in order to explore and understand. Using black box tools like lex and yacc go against the Nand2tetris spirit.✨
Buy me a coffee ? :)
0%