projects/dil: trunk/src/Lexer.d annotate

annotate trunk/src/Lexer.d @ 31:94f09f4e988e

- Added struct for strings to Token with 'pf' = postfix. - Added code for parsing hex string literals. - Added stub for parsing raw strings literals.

author	aziz
date	Mon, 25 Jun 2007 13:34:03 +0000
parents	426767b94635
children	d7011daa4740

rev	line source
0 8ba2570de175 Initial import. aziz parents: diff changeset	1 /++
8ba2570de175 Initial import. aziz parents: diff changeset	2 Author: Aziz Köksal
8ba2570de175 Initial import. aziz parents: diff changeset	3 License: GPL2
8ba2570de175 Initial import. aziz parents: diff changeset	4 +/
8ba2570de175 Initial import. aziz parents: diff changeset	5 module Lexer;
3 4bbce78bfb1e - Added TOK enum. aziz parents: 2 diff changeset	6 import Token;
28 3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	7 import Keywords;
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	8 import Identifier;
2 81c6cc33f5c8 - Initializing ptable with a precomputed array literal. aziz parents: 1 diff changeset	9 import std.stdio;
4 92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	10 import std.utf;
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	11 import std.uni;
30 426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	12 import std.conv;
0 8ba2570de175 Initial import. aziz parents: diff changeset	13
8ba2570de175 Initial import. aziz parents: diff changeset	14 /// ASCII character properties table.
2 81c6cc33f5c8 - Initializing ptable with a precomputed array literal. aziz parents: 1 diff changeset	15 static const int ptable[256] = [
16 476e8e55c1d4 - Added Whitespace to the character properties table. aziz parents: 15 diff changeset	16 0, 0, 0, 0, 0, 0, 0, 0, 0,32, 0,32,32, 0, 0, 0,
13 e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	17 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
16 476e8e55c1d4 - Added Whitespace to the character properties table. aziz parents: 15 diff changeset	18 32, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
13 e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	19 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 0, 0, 0, 0, 0, 0,
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	20 0,12,12,12,12,12,12, 8, 8, 8, 8, 8, 8, 8, 8, 8,
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	21 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 0, 0, 0, 0,16,
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	22 0,12,12,12,12,12,12, 8, 8, 8, 8, 8, 8, 8, 8, 8,
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	23 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 0, 0, 0, 0, 0,
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	24 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	25 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	26 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	27 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	28 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	29 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	30 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	31 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
2 81c6cc33f5c8 - Initializing ptable with a precomputed array literal. aziz parents: 1 diff changeset	32 ];
0 8ba2570de175 Initial import. aziz parents: diff changeset	33
8ba2570de175 Initial import. aziz parents: diff changeset	34 enum CProperty
8ba2570de175 Initial import. aziz parents: diff changeset	35 {
1 f3cd3bfde4ba - Corrected some errors to make the file compile. aziz parents: 0 diff changeset	36 Octal = 1,
0 8ba2570de175 Initial import. aziz parents: diff changeset	37 Digit = 1<<1,
8ba2570de175 Initial import. aziz parents: diff changeset	38 Hex = 1<<2,
8ba2570de175 Initial import. aziz parents: diff changeset	39 Alpha = 1<<3,
13 e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	40 Underscore = 1<<4,
16 476e8e55c1d4 - Added Whitespace to the character properties table. aziz parents: 15 diff changeset	41 Whitespace = 1<<5
0 8ba2570de175 Initial import. aziz parents: diff changeset	42 }
8ba2570de175 Initial import. aziz parents: diff changeset	43
13 e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	44 private alias CProperty CP;
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	45 int isoctal(char c) { return ptable[c] & CP.Octal; }
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	46 int isdigit(char c) { return ptable[c] & CP.Digit; }
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	47 int ishexad(char c) { return ptable[c] & CP.Hex; }
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	48 int isalpha(char c) { return ptable[c] & CP.Alpha; }
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	49 int isalnum(char c) { return ptable[c] & (CP.Alpha \| CP.Digit); }
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	50 int isidbeg(char c) { return ptable[c] & (CP.Alpha \| CP.Underscore); }
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	51 int isident(char c) { return ptable[c] & (CP.Alpha \| CP.Underscore \| CP.Digit); }
16 476e8e55c1d4 - Added Whitespace to the character properties table. aziz parents: 15 diff changeset	52 int isspace(char c) { return ptable[c] & CP.Whitespace; }
13 e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	53
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	54 version(gen_ptable)
0 8ba2570de175 Initial import. aziz parents: diff changeset	55 static this()
8ba2570de175 Initial import. aziz parents: diff changeset	56 {
2 81c6cc33f5c8 - Initializing ptable with a precomputed array literal. aziz parents: 1 diff changeset	57 // Initialize character properties table.
0 8ba2570de175 Initial import. aziz parents: diff changeset	58 for (int i; i < ptable.length; ++i)
8ba2570de175 Initial import. aziz parents: diff changeset	59 {
13 e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	60 ptable[i] = 0;
0 8ba2570de175 Initial import. aziz parents: diff changeset	61 if ('0' <= i && i <= '7')
13 e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	62 ptable[i] \|= CP.Octal;
0 8ba2570de175 Initial import. aziz parents: diff changeset	63 if ('0' <= i && i <= '9')
13 e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	64 ptable[i] \|= CP.Digit;
0 8ba2570de175 Initial import. aziz parents: diff changeset	65 if (isdigit(i) \|\| 'a' <= i && i <= 'f' \|\| 'A' <= i && i <= 'F')
13 e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	66 ptable[i] \|= CP.Hex;
0 8ba2570de175 Initial import. aziz parents: diff changeset	67 if ('a' <= i && i <= 'z' \|\| 'A' <= i && i <= 'Z')
13 e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	68 ptable[i] \|= CP.Alpha;
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	69 if (i == '_')
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	70 ptable[i] \|= CP.Underscore;
16 476e8e55c1d4 - Added Whitespace to the character properties table. aziz parents: 15 diff changeset	71 if (i == ' ' \|\| i == '\t' \|\| i == '\v'\|\| i == '\f')
476e8e55c1d4 - Added Whitespace to the character properties table. aziz parents: 15 diff changeset	72 ptable[i] \|= CP.Whitespace;
0 8ba2570de175 Initial import. aziz parents: diff changeset	73 }
2 81c6cc33f5c8 - Initializing ptable with a precomputed array literal. aziz parents: 1 diff changeset	74 // Print a formatted array literal.
81c6cc33f5c8 - Initializing ptable with a precomputed array literal. aziz parents: 1 diff changeset	75 char[] array = "[\n";
81c6cc33f5c8 - Initializing ptable with a precomputed array literal. aziz parents: 1 diff changeset	76 for (int i; i < ptable.length; ++i)
81c6cc33f5c8 - Initializing ptable with a precomputed array literal. aziz parents: 1 diff changeset	77 {
13 e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	78 int c = ptable[i];
e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	79 array ~= std.string.format("%2d,", c, ((i+1) % 16) ? "":"\n");
2 81c6cc33f5c8 - Initializing ptable with a precomputed array literal. aziz parents: 1 diff changeset	80 }
13 e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	81 array[$-2..$] = "\n]";
2 81c6cc33f5c8 - Initializing ptable with a precomputed array literal. aziz parents: 1 diff changeset	82 writefln(array);
0 8ba2570de175 Initial import. aziz parents: diff changeset	83 }
8ba2570de175 Initial import. aziz parents: diff changeset	84
11 dffcdaa7c47a - Added Unicode line and paragraph separators. aziz parents: 10 diff changeset	85 const char[3] LS = \u2028;
dffcdaa7c47a - Added Unicode line and paragraph separators. aziz parents: 10 diff changeset	86 const char[3] PS = \u2029;
dffcdaa7c47a - Added Unicode line and paragraph separators. aziz parents: 10 diff changeset	87
18 c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	88 const dchar LSd = 0x2028;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	89 const dchar PSd = 0x2029;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	90
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	91 /// Index into table of error messages.
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	92 enum MID
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	93 {
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	94 UnterminatedCharacterLiteral,
30 426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	95 EmptyCharacterLiteral,
31 94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	96 // #line
30 426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	97 ExpectedIdentifierLine,
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	98 NewlineInSpecialToken,
31 94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	99 UnterminatedSpecialToken,
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	100 // x""
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	101 NonHexCharInHexString,
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	102 OddNumberOfDigitsInHexString,
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	103 UnterminatedHexString
18 c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	104 }
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	105
31 94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	106 string[] messages = [
18 c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	107 "unterminated character literal."
30 426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	108 "empty character literal.",
31 94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	109 // #line
30 426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	110 "expected 'line' after '#'."
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	111 "newline not allowed inside special token."
31 94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	112 "expected newline after special token.",
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	113 // x""
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	114 "non-hex character '{1}' found in hex string.",
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	115 "odd number of hex digits in hex string.",
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	116 "unterminated hex string."
18 c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	117 ];
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	118
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	119 class Problem
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	120 {
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	121 enum Type
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	122 {
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	123 Lexer,
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	124 Parser,
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	125 Semantic
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	126 }
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	127
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	128 MID id;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	129 Type type;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	130 uint loc;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	131 this(Type type, MID id, uint loc)
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	132 {
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	133 this.id = id;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	134 this.type = type;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	135 this.loc = loc;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	136 }
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	137 }
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	138
0 8ba2570de175 Initial import. aziz parents: diff changeset	139 class Lexer
8ba2570de175 Initial import. aziz parents: diff changeset	140 {
4 92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	141 Token token;
30 426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	142 string text;
4 92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	143 char* p;
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	144 char* end;
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	145
17 9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	146 uint loc = 1; /// line of code
9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	147
30 426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	148 char[] fileName;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	149
18 c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	150 Problem[] errors;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	151
28 3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	152 Identifier[string] idtable;
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	153
30 426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	154 this(string text, string fileName)
4 92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	155 {
30 426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	156 this.fileName = fileName;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	157
4 92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	158 this.text = text;
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	159 this.text.length = this.text.length + 1;
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	160 this.text[$-1] = 0;
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	161
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	162 this.p = this.text.ptr;
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	163 this.end = this.p + this.text.length;
28 3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	164
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	165 loadKeywords();
4 92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	166 }
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	167
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	168 public void scan(out Token t)
3 4bbce78bfb1e - Added TOK enum. aziz parents: 2 diff changeset	169 {
4 92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	170 assert(p < end);
0 8ba2570de175 Initial import. aziz parents: diff changeset	171
10 3ee65d6e39c9 - Parsing // comments now. aziz parents: 9 diff changeset	172 uint c = *p;
4 92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	173
5 79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	174 while(1)
4 92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	175 {
5 79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	176 t.start = p;
16 476e8e55c1d4 - Added Whitespace to the character properties table. aziz parents: 15 diff changeset	177
5 79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	178 if (c == 0)
79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	179 {
17 9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	180 ++p;
5 79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	181 t.type = TOK.EOF;
17 9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	182 t.end = p;
5 79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	183 return;
79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	184 }
4 92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	185
17 9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	186 if (c == '\n')
9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	187 {
9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	188 c = *++p;
9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	189 ++loc;
9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	190 continue;
9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	191 }
9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	192 else if (c == '\r')
9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	193 {
9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	194 c = *++p;
9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	195 if (c != '\n')
9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	196 ++loc;
9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	197 continue;
9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	198 }
9bd0bac79479 - Removed Whitespace from enum list. aziz parents: 16 diff changeset	199
13 e5211758b63c - Added isidbeg() function. aziz parents: 12 diff changeset	200 if (isidbeg(c))
5 79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	201 {
31 94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	202 if (c == 'r' && p[1] == '"')
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	203 return scanRawStringLiteral(t);
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	204 if (c == 'x' && p[1] == '"')
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	205 return scanHexStringLiteral(t);
12 0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	206 Lidentifier:
5 79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	207 do
79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	208 { c = *++p; }
12 0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	209 while (isident(c) \|\| c & 128 && isUniAlpha(decodeUTF()))
28 3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	210
5 79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	211 t.end = p;
28 3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	212
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	213 string str = t.span;
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	214 Identifier* id = str in idtable;
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	215
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	216 if (!id)
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	217 {
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	218 idtable[str] = Identifier.Identifier(TOK.Identifier, str);
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	219 id = str in idtable;
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	220 }
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	221 assert(id);
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	222 t.type = id.type;
5 79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	223 return;
79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	224 }
79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	225
15 c70c028e47dd - Started implementation of lexing numbers. aziz parents: 14 diff changeset	226 if (isdigit(c))
c70c028e47dd - Started implementation of lexing numbers. aziz parents: 14 diff changeset	227 return scanNumber(t);
c70c028e47dd - Started implementation of lexing numbers. aziz parents: 14 diff changeset	228
8 d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	229 if (c == '/')
5 79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	230 {
8 d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	231 c = *++p;
14 cdf788d8bdaf - Parsing /= now. aziz parents: 13 diff changeset	232 switch(c)
5 79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	233 {
18 c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	234 case '=':
14 cdf788d8bdaf - Parsing /= now. aziz parents: 13 diff changeset	235 ++p;
cdf788d8bdaf - Parsing /= now. aziz parents: 13 diff changeset	236 t.type = TOK.DivisionAssign;
cdf788d8bdaf - Parsing /= now. aziz parents: 13 diff changeset	237 t.end = p;
cdf788d8bdaf - Parsing /= now. aziz parents: 13 diff changeset	238 return;
18 c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	239 case '+':
8 d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	240 uint level = 1;
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	241 do
7 07e45c06a024 - Parsing nested comments correctly now. aziz parents: 5 diff changeset	242 {
8 d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	243 c = *++p;
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	244 if (c == 0)
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	245 throw new Error("unterminated /+ +/ comment.");
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	246 else if (c == '/' && p[1] == '+')
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	247 {
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	248 ++p;
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	249 ++level;
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	250 }
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	251 else if (c == '+' && p[1] == '/')
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	252 {
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	253 ++p;
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	254 if (--level == 0)
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	255 break;
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	256 }
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	257 } while (1)
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	258 p += 2;
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	259 t.type = TOK.Comment;
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	260 t.end = p;
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	261 return;
18 c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	262 case '*':
8 d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	263 do
7 07e45c06a024 - Parsing nested comments correctly now. aziz parents: 5 diff changeset	264 {
8 d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	265 c = *++p;
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	266 if (c == 0)
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	267 throw new Error("unterminated /* */ comment.");
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	268 } while (c != '*' \|\| p[1] != '/')
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	269 p += 2;
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	270 t.type = TOK.Comment;
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	271 t.end = p;
d4ba94a5a282 - Parsing /* / comments now. aziz* parents: 7 diff changeset	272 return;
18 c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	273 case '/':
10 3ee65d6e39c9 - Parsing // comments now. aziz parents: 9 diff changeset	274 do
3ee65d6e39c9 - Parsing // comments now. aziz parents: 9 diff changeset	275 {
3ee65d6e39c9 - Parsing // comments now. aziz parents: 9 diff changeset	276 c = *++p;
11 dffcdaa7c47a - Added Unicode line and paragraph separators. aziz parents: 10 diff changeset	277 if (c == LS[0] && p[1] == LS[1] && (p[2] == LS[2] \|\| p[2] == PS[2]))
dffcdaa7c47a - Added Unicode line and paragraph separators. aziz parents: 10 diff changeset	278 break;
10 3ee65d6e39c9 - Parsing // comments now. aziz parents: 9 diff changeset	279 } while (c != '\n' && c != 0)
3ee65d6e39c9 - Parsing // comments now. aziz parents: 9 diff changeset	280 t.type = TOK.Comment;
3ee65d6e39c9 - Parsing // comments now. aziz parents: 9 diff changeset	281 t.end = p;
3ee65d6e39c9 - Parsing // comments now. aziz parents: 9 diff changeset	282 return;
3ee65d6e39c9 - Parsing // comments now. aziz parents: 9 diff changeset	283 }
5 79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	284 }
79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	285
9 5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	286 if (c == '"')
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	287 {
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	288 do {
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	289 c = *++p;
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	290 if (c == 0)
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	291 throw new Error("unterminated string literal.");
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	292 if (c == '\\')
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	293 ++p;
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	294 } while (c != '"')
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	295 ++p;
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	296 t.type = TOK.String;
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	297 t.end = p;
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	298 return;
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	299 }
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	300
5d6968cc751e - Parsing string and character literals now (rudimentary implementation.) aziz parents: 8 diff changeset	301 if (c == '\'')
18 c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	302 return scanCharacterLiteral(t);
12 0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	303
20 d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	304 switch(c)
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	305 {
22 b05fff8e2ce4 - Added code for parsing Dot, Slice and Ellipses tokens. aziz parents: 21 diff changeset	306 case '.':
b05fff8e2ce4 - Added code for parsing Dot, Slice and Ellipses tokens. aziz parents: 21 diff changeset	307 if (p[1] == '.')
b05fff8e2ce4 - Added code for parsing Dot, Slice and Ellipses tokens. aziz parents: 21 diff changeset	308 {
b05fff8e2ce4 - Added code for parsing Dot, Slice and Ellipses tokens. aziz parents: 21 diff changeset	309 ++p;
b05fff8e2ce4 - Added code for parsing Dot, Slice and Ellipses tokens. aziz parents: 21 diff changeset	310 if (p[1] == '.') {
b05fff8e2ce4 - Added code for parsing Dot, Slice and Ellipses tokens. aziz parents: 21 diff changeset	311 ++p;
b05fff8e2ce4 - Added code for parsing Dot, Slice and Ellipses tokens. aziz parents: 21 diff changeset	312 t.type = TOK.Ellipses;
b05fff8e2ce4 - Added code for parsing Dot, Slice and Ellipses tokens. aziz parents: 21 diff changeset	313 }
b05fff8e2ce4 - Added code for parsing Dot, Slice and Ellipses tokens. aziz parents: 21 diff changeset	314 else
b05fff8e2ce4 - Added code for parsing Dot, Slice and Ellipses tokens. aziz parents: 21 diff changeset	315 t.type = TOK.Slice;
b05fff8e2ce4 - Added code for parsing Dot, Slice and Ellipses tokens. aziz parents: 21 diff changeset	316 }
b05fff8e2ce4 - Added code for parsing Dot, Slice and Ellipses tokens. aziz parents: 21 diff changeset	317 else
b05fff8e2ce4 - Added code for parsing Dot, Slice and Ellipses tokens. aziz parents: 21 diff changeset	318 t.type = TOK.Dot;
b05fff8e2ce4 - Added code for parsing Dot, Slice and Ellipses tokens. aziz parents: 21 diff changeset	319 goto Lcommon;
23 1a7903701a3d - Added code for parsing OrAssign, OrLogical and OrBinary tokens. aziz parents: 22 diff changeset	320 case '\|':
1a7903701a3d - Added code for parsing OrAssign, OrLogical and OrBinary tokens. aziz parents: 22 diff changeset	321 c = *++p;
1a7903701a3d - Added code for parsing OrAssign, OrLogical and OrBinary tokens. aziz parents: 22 diff changeset	322 if (c == '=')
1a7903701a3d - Added code for parsing OrAssign, OrLogical and OrBinary tokens. aziz parents: 22 diff changeset	323 t.type = TOK.OrAssign;
1a7903701a3d - Added code for parsing OrAssign, OrLogical and OrBinary tokens. aziz parents: 22 diff changeset	324 else if (c == '\|')
1a7903701a3d - Added code for parsing OrAssign, OrLogical and OrBinary tokens. aziz parents: 22 diff changeset	325 t.type = TOK.OrLogical;
26 c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	326 else {
23 1a7903701a3d - Added code for parsing OrAssign, OrLogical and OrBinary tokens. aziz parents: 22 diff changeset	327 t.type = TOK.OrBinary;
26 c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	328 goto Lcommon2;
c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	329 }
23 1a7903701a3d - Added code for parsing OrAssign, OrLogical and OrBinary tokens. aziz parents: 22 diff changeset	330 goto Lcommon;
24 903f91163f23 - Added code for parsing AndAssign, AndLogical and AndBinary tokens. aziz parents: 23 diff changeset	331 case '&':
903f91163f23 - Added code for parsing AndAssign, AndLogical and AndBinary tokens. aziz parents: 23 diff changeset	332 c = *++p;
903f91163f23 - Added code for parsing AndAssign, AndLogical and AndBinary tokens. aziz parents: 23 diff changeset	333 if (c == '=')
903f91163f23 - Added code for parsing AndAssign, AndLogical and AndBinary tokens. aziz parents: 23 diff changeset	334 t.type = TOK.AndAssign;
903f91163f23 - Added code for parsing AndAssign, AndLogical and AndBinary tokens. aziz parents: 23 diff changeset	335 else if (c == '&')
903f91163f23 - Added code for parsing AndAssign, AndLogical and AndBinary tokens. aziz parents: 23 diff changeset	336 t.type = TOK.AndLogical;
26 c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	337 else {
24 903f91163f23 - Added code for parsing AndAssign, AndLogical and AndBinary tokens. aziz parents: 23 diff changeset	338 t.type = TOK.AndBinary;
26 c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	339 goto Lcommon2;
c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	340 }
24 903f91163f23 - Added code for parsing AndAssign, AndLogical and AndBinary tokens. aziz parents: 23 diff changeset	341 goto Lcommon;
25 9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	342 case '+':
9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	343 c = *++p;
9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	344 if (c == '=')
9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	345 t.type = TOK.PlusAssign;
9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	346 else if (c == '+')
9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	347 t.type = TOK.PlusPlus;
26 c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	348 else {
25 9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	349 t.type = TOK.Plus;
26 c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	350 goto Lcommon2;
c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	351 }
25 9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	352 goto Lcommon;
9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	353 case '-':
9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	354 c = *++p;
9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	355 if (c == '=')
9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	356 t.type = TOK.MinusAssign;
9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	357 else if (c == '-')
9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	358 t.type = TOK.MinusMinus;
26 c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	359 else {
c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	360 t.type = TOK.Minus;
c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	361 goto Lcommon2;
c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	362 }
c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	363 goto Lcommon;
c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	364 case '=':
c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	365 if (p[1] == '=') {
c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	366 ++p;
c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	367 t.type = TOK.Equal;
c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	368 }
25 9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	369 else
26 c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	370 t.type = TOK.Assign;
25 9c866208b3f6 - Added code for parsing PlusAssign, PlusPlus, Plus, MinusAssign, MinusMinus, Minus tokens. aziz parents: 24 diff changeset	371 goto Lcommon;
27 43b6bf56f0e9 - Added code for parsing CatAssign and Tilde tokens. aziz parents: 26 diff changeset	372 case '~':
43b6bf56f0e9 - Added code for parsing CatAssign and Tilde tokens. aziz parents: 26 diff changeset	373 if (p[1] == '=') {
43b6bf56f0e9 - Added code for parsing CatAssign and Tilde tokens. aziz parents: 26 diff changeset	374 ++p;
43b6bf56f0e9 - Added code for parsing CatAssign and Tilde tokens. aziz parents: 26 diff changeset	375 t.type = TOK.CatAssign;
43b6bf56f0e9 - Added code for parsing CatAssign and Tilde tokens. aziz parents: 26 diff changeset	376 }
43b6bf56f0e9 - Added code for parsing CatAssign and Tilde tokens. aziz parents: 26 diff changeset	377 else
43b6bf56f0e9 - Added code for parsing CatAssign and Tilde tokens. aziz parents: 26 diff changeset	378 t.type = TOK.Tilde;
43b6bf56f0e9 - Added code for parsing CatAssign and Tilde tokens. aziz parents: 26 diff changeset	379 goto Lcommon;
29 ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	380 case '*':
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	381 if (p[1] == '=') {
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	382 ++p;
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	383 t.type = TOK.MulAssign;
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	384 }
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	385 else
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	386 t.type = TOK.Mul;
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	387 goto Lcommon;
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	388 case '^':
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	389 if (p[1] == '=') {
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	390 ++p;
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	391 t.type = TOK.XorAssign;
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	392 }
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	393 else
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	394 t.type = TOK.Xor;
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	395 goto Lcommon;
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	396 case '%':
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	397 if (p[1] == '=') {
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	398 ++p;
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	399 t.type = TOK.ModAssign;
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	400 }
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	401 else
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	402 t.type = TOK.Mod;
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	403 goto Lcommon;
ef83eea26bbd - Added code for parsing MulAssign, Mul, ModAssign, Mod, XorAssign and Xor tokens. aziz parents: 28 diff changeset	404 // Single character tokens:
20 d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	405 case '(':
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	406 t.type = TOK.LParen;
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	407 goto Lcommon;
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	408 case ')':
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	409 t.type = TOK.RParen;
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	410 goto Lcommon;
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	411 case '[':
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	412 t.type = TOK.LBracket;
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	413 goto Lcommon;
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	414 case ']':
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	415 t.type = TOK.RBracket;
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	416 goto Lcommon;
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	417 case '{':
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	418 t.type = TOK.LBrace;
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	419 goto Lcommon;
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	420 case '}':
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	421 t.type = TOK.RBrace;
21 c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	422 goto Lcommon;
c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	423 case ':':
c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	424 t.type = TOK.Colon;
c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	425 goto Lcommon;
c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	426 case ';':
c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	427 t.type = TOK.Semicolon;
c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	428 goto Lcommon;
c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	429 case '?':
c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	430 t.type = TOK.Question;
c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	431 goto Lcommon;
c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	432 case ',':
c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	433 t.type = TOK.Comma;
c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	434 goto Lcommon;
c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	435 case '$':
c785c122e4e6 - Added code for parsing Colon, Semicolon, Question, Comma and Dollar. aziz parents: 20 diff changeset	436 t.type = TOK.Dollar;
20 d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	437 Lcommon:
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	438 ++p;
26 c3d7373db241 - Added code for parsing Assign and Equal tokens. aziz parents: 25 diff changeset	439 Lcommon2:
20 d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	440 t.end = p;
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	441 return;
30 426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	442 case '#':
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	443 ++p;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	444 scanSpecialToken();
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	445 break;
20 d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	446 default:
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	447 }
d6adfbd7c513 - Added code for parsing braces. aziz parents: 19 diff changeset	448
12 0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	449 if (c & 128 && isUniAlpha(decodeUTF()))
0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	450 goto Lidentifier;
5 79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	451 c = *++p;
4 92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	452 }
3 4bbce78bfb1e - Added TOK enum. aziz parents: 2 diff changeset	453 }
4 92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	454
30 426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	455 void peek(ref Token t)
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	456 {
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	457 char* tmp = p;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	458 scan(t);
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	459 p = tmp;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	460 }
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	461
18 c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	462 void scanCharacterLiteral(ref Token t)
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	463 {
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	464 assert(*p == '\'');
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	465 MID id = MID.UnterminatedCharacterLiteral;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	466 uint c = *++p;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	467 switch(c)
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	468 {
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	469 case '\\':
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	470 ++p;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	471 break;
31 94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	472 case 0, 26, '\n', '\r':
18 c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	473 goto Lerr;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	474 case '\'':
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	475 id = MID.EmptyCharacterLiteral;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	476 goto Lerr;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	477 default:
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	478 if (c & 128)
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	479 {
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	480 c = decodeUTF();
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	481 if (c == LSd \|\| c == PSd)
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	482 goto Lerr;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	483 t.chr = c;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	484 }
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	485 }
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	486
19 f85832f9f24e - Parsing character literals more correctly. aziz parents: 18 diff changeset	487 ++p;
18 c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	488 if (*p != '\'')
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	489 Lerr:
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	490 error(id);
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	491 ++p;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	492 t.type = TOK.Character;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	493 t.end = p;
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	494 }
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	495
31 94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	496 char scanPostFix()
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	497 {
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	498 switch (*p)
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	499 {
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	500 case 'c':
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	501 case 'w':
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	502 case 'd':
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	503 return *p++;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	504 default:
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	505 return 0;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	506 }
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	507 }
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	508
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	509 void scanRawStringLiteral(ref Token t)
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	510 {
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	511
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	512 }
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	513
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	514 void scanHexStringLiteral(ref Token t)
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	515 {
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	516 assert(p[0] == 'x' && p[1] == '"');
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	517 p+=2;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	518 t.type = TOK.String;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	519
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	520 uint c;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	521 ubyte[] buffer;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	522 ubyte h; // hex number
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	523 uint n; // number of hex digits
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	524 MID mid;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	525
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	526 while (1)
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	527 {
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	528 c = *p++;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	529 switch (c)
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	530 {
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	531 case '"':
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	532 if (n & 1)
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	533 {
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	534 mid = MID.OddNumberOfDigitsInHexString;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	535 error(mid);
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	536 }
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	537 t.str = cast(string) buffer;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	538 t.pf = scanPostFix();
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	539 t.end = p;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	540 return;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	541 case '\r':
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	542 if (*p == '\n')
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	543 ++p;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	544 case '\n':
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	545 ++loc;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	546 continue;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	547 case LS[0]:
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	548 if (*p == LS[1] && (p[1] == LS[2] \|\| p[1] == PS[2])) {
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	549 p += 2;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	550 ++loc;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	551 }
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	552 continue;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	553 case 0, 26:
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	554 mid = MID.UnterminatedHexString;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	555 goto Lerr;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	556 default:
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	557 if (ishexad(c))
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	558 {
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	559 if (c <= '9')
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	560 c -= '0';
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	561 else if (c <= 'F')
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	562 c -= 'A' - 10;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	563 else
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	564 c -= 'a' - 10;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	565
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	566 if (n & 1)
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	567 {
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	568 h <<= 4;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	569 h \|= c;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	570 buffer ~= h;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	571 }
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	572 else
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	573 h = c;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	574 ++n;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	575 continue;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	576 }
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	577 else if (isspace(c))
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	578 continue;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	579 mid = MID.NonHexCharInHexString;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	580 goto Lerr;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	581 }
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	582 }
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	583
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	584 return;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	585 Lerr:
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	586 error(mid);
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	587 t.pf = 0;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	588 t.end = p;
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	589 }
94f09f4e988e - Added struct for strings to Token with 'pf' = postfix. aziz parents: 30 diff changeset	590
15 c70c028e47dd - Started implementation of lexing numbers. aziz parents: 14 diff changeset	591 void scanNumber(ref Token t)
c70c028e47dd - Started implementation of lexing numbers. aziz parents: 14 diff changeset	592 {
c70c028e47dd - Started implementation of lexing numbers. aziz parents: 14 diff changeset	593 while (isdigit(*++p)) {}
c70c028e47dd - Started implementation of lexing numbers. aziz parents: 14 diff changeset	594 t.type = TOK.Number;
c70c028e47dd - Started implementation of lexing numbers. aziz parents: 14 diff changeset	595 t.end = p;
30 426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	596 t._uint = toInt(t.span);
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	597 }
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	598
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	599 /// Scan special token: #line Integer [Filespec] EndOfLine
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	600 void scanSpecialToken()
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	601 {
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	602 MID mid;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	603 Token t;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	604
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	605 scan(t);
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	606 if (!(t.type == TOK.Identifier && t.span == "line")) {
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	607 mid = MID.ExpectedIdentifierLine;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	608 goto Lerr;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	609 }
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	610
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	611 scan(t);
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	612 if (t.type == TOK.Number)
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	613 loc = t._uint - 1;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	614
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	615 uint loc = this.loc;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	616
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	617 char* wsstart = t.end;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	618
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	619 bool hasNewline(char* end)
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	620 {
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	621 alias wsstart p;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	622 uint c;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	623 for(; p != end; c = *++p)
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	624 if (c == '\n' \|\| c == '\r' \|\| c == LS[0] && p[1] == LS[1] && (p[2] == LS[2] \|\| p[2] == PS[2])) {
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	625 mid = MID.NewlineInSpecialToken;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	626 return true;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	627 }
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	628 return false;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	629 }
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	630
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	631 peek(t);
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	632
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	633 if (t.type == TOK.String)
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	634 {
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	635 // Check whole token with preceding whitespace for newline.
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	636 if (hasNewline(t.end))
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	637 goto Lerr;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	638 fileName = t.span[1..$-1]; // contents of "..."
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	639 p = t.end;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	640 }
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	641 else if (t.type == TOK.Identifier && t.span == "__FILE__")
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	642 {
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	643 // Check preceding whitespace for newline.
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	644 if (hasNewline(t.start))
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	645 goto Lerr;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	646 p = t.end;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	647 }
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	648
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	649 uint c;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	650 while (1)
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	651 {
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	652 c = *p++;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	653 if (isspace(c))
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	654 continue;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	655
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	656 if (c == '\n' \|\| c == '\r' \|\| c == 0 \|\|
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	657 c == LS[0] && p[1] == LS[1] && (p[2] == LS[2] \|\| p[2] == PS[2]))
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	658 break;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	659 else {
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	660 mid = MID.UnterminatedSpecialToken;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	661 goto Lerr;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	662 }
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	663 }
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	664
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	665 this.loc = loc;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	666 return;
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	667 Lerr:
426767b94635 - Added code for parsing the '#line' special token. aziz parents: 29 diff changeset	668 error(mid);
15 c70c028e47dd - Started implementation of lexing numbers. aziz parents: 14 diff changeset	669 }
c70c028e47dd - Started implementation of lexing numbers. aziz parents: 14 diff changeset	670
12 0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	671 uint decodeUTF()
0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	672 {
0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	673 assert(*p & 128);
0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	674 size_t idx;
0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	675 uint d;
0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	676 d = std.utf.decode(p[0 .. end-p], idx);
0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	677 p += idx -1;
0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	678 return d;
0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	679 }
0989206cf73c - Added code to decode Unicode characters in identifiers. aziz parents: 11 diff changeset	680
28 3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	681 void loadKeywords()
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	682 {
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	683 foreach(k; keywords)
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	684 idtable[k.str] = k;
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	685 }
3a9daccf7d96 - Added table for identifiers to Lexer. aziz parents: 27 diff changeset	686
18 c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	687 void error(MID id)
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	688 {
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	689 errors ~= new Problem(Problem.Type.Lexer, id, loc);
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	690 }
c48d2125f1e2 - Moved code for scanning character literals to separate function. aziz parents: 17 diff changeset	691
3 4bbce78bfb1e - Added TOK enum. aziz parents: 2 diff changeset	692 public TOK nextToken()
4bbce78bfb1e - Added TOK enum. aziz parents: 2 diff changeset	693 {
4 92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	694 scan(this.token);
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	695 return this.token.type;
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	696 }
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	697
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	698 Token[] getTokens()
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	699 {
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	700 Token[] tokens;
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	701 while (nextToken() != TOK.EOF)
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	702 tokens ~= this.token;
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	703 tokens ~= this.token;
92df59b1ec4a - Started implementation of scan(). aziz parents: 3 diff changeset	704 return tokens;
3 4bbce78bfb1e - Added TOK enum. aziz parents: 2 diff changeset	705 }
5 79b4e8848794 - Started writing XML generator. aziz parents: 4 diff changeset	706 }

Mercurial > projects > dil

annotate trunk/src/Lexer.d @ 31:94f09f4e988e