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
|
(***********************************************************************)
(* *)
(* CamlIDL *)
(* *)
(* Xavier Leroy, projet Cristal, INRIA Rocquencourt *)
(* *)
(* Copyright 1999 Institut National de Recherche en Informatique et *)
(* en Automatique. All rights reserved. This file is distributed *)
(* under the terms of the Q Public License version 1.0 *)
(* *)
(***********************************************************************)
(* $Id: lexer_midl.mll,v 1.13 2004-05-12 12:40:40 xleroy Exp $ *)
(* Lexer for IDL interface files *)
{
open Utils
open Parse_aux
open Parser_midl
let keywords = Hashtbl.create 29
let _ =
List.iter
(fun (txt, kwd) -> Hashtbl.add keywords txt kwd)
[ "boolean", BOOLEAN;
"byte", BYTE;
"case", CASE;
"char", CHAR;
"const", CONST;
"cpp_quote", CPP_QUOTE;
"default", DEFAULT;
"double", DOUBLE;
"enum", ENUM;
"false", FALSE;
"float", FLOAT;
"handle_t", HANDLE_T;
"hyper", HYPER;
"import", IMPORT;
"int", INT;
"__int64", INT64_COMPAT;
"int8", INT8;
"int16", INT16;
"int32", INT32;
"int64", INT64;
"interface", INTERFACE;
"long", LONG;
"NULL", NULL;
"quote", QUOTE;
"short", SHORT;
"signed", SIGNED;
"sizeof", SIZEOF;
"small", SMALL;
"struct", STRUCT;
"switch", SWITCH;
"true", TRUE;
"typedef", TYPEDEF;
"union", UNION;
"unsigned", UNSIGNED;
"uint8", UINT8;
"uint16", UINT16;
"uint32", UINT32;
"uint64", UINT64;
"void", VOID;
"wchar_t", WCHAR_T ]
let string_buffer = Buffer.create 80
(* To translate escape sequences *)
let char_for_backslash = function
| 'n' -> '\010'
| 'r' -> '\013'
| 'b' -> '\008'
| 't' -> '\009'
| c -> c
let char_for_code lexbuf i j =
let s = Lexing.lexeme lexbuf in
let s' = String.sub s i (String.length s - i - j) in
Char.chr(int_of_string("0o" ^ s'))
(* To report lexical errors *)
exception Lex_error of string
}
let blank = [' ' '\010' '\013' '\009' '\012']
let eol = ('\n' | '\r' | "\r\n")
let identstart = ['A'-'Z' 'a'-'z' '_']
let identchar = identstart | ['0'-'9']
let decimal_literal = ['0'-'9']+
let hex_literal = '0' ['x' 'X'] ['0'-'9' 'A'-'F' 'a'-'f']+
let octal_literal = '0' ['0'-'7']+
let hex = ['0'-'9' 'a'-'f' 'A'-'F']
let hex4 = hex hex hex hex
let hex8 = hex4 hex4
let hex12 = hex4 hex4 hex4
rule token = parse
blank +
{ token lexbuf }
| "/*"
{ comment lexbuf }
| "//" [ ^ '\n' ] * eol
{ token lexbuf }
| "#" ("line")? [' ' '\t']* ['0'-'9']+ [^ '\n' '\r'] * eol
(* # linenum "filename" flags \n *)
{ token lexbuf }
| "#" blank* "pragma" [^ '\n' '\r'] * eol
(* #pragma introduced by some C preprocessors *)
{ token lexbuf }
| identstart identchar *
{ let s = Lexing.lexeme lexbuf in
try
Hashtbl.find keywords s
with Not_found ->
if StringSet.mem s !type_names
then TYPEIDENT s
else IDENT s }
| octal_literal
{ INTEGER(Int64.of_string("0o" ^ Lexing.lexeme lexbuf)) }
| decimal_literal | hex_literal
{ INTEGER(Int64.of_string(Lexing.lexeme lexbuf)) }
| "\""
{ Buffer.reset string_buffer;
string lexbuf;
let s = Buffer.contents string_buffer in
Buffer.reset string_buffer;
STRING s }
| "'" [^ '\\' '\''] "'"
{ CHARACTER(Lexing.lexeme_char lexbuf 1) }
| "'" '\\' ['\\' '\'' 'n' 't' 'b' 'r'] "'"
{ CHARACTER(char_for_backslash (Lexing.lexeme_char lexbuf 2)) }
| "'" '\\' ['0'-'3'] ['0'-'7']? ['0'-'7']? "'"
{ CHARACTER(char_for_code lexbuf 2 1) }
| "&" { AMPER }
| "&&" { AMPERAMPER }
| "!" { BANG }
| "!=" { BANGEQUAL }
| "|" { BAR }
| "||" { BARBAR }
| "^" { CARET }
| ":" { COLON }
| "," { COMMA }
| "." { DOT }
| "=" { EQUAL }
| "==" { EQUALEQUAL }
| ">" { GREATER }
| ">=" { GREATEREQUAL }
| ">>" { GREATERGREATER }
| "{" { LBRACE }
| "[" { LBRACKET }
| "<" { LESS }
| "<=" { LESSEQUAL }
| "<<" { LESSLESS }
| "(" { LPAREN }
| "%" { PERCENT }
| "+" { PLUS }
| "}" { RBRACE }
| "]" { RBRACKET }
| ")" { RPAREN }
| ";" { SEMI }
| "/" { SLASH }
| "*" { STAR }
| "~" { TILDE }
| "-" { MINUS }
| "?" { QUESTIONMARK }
| '(' hex8 '-' hex4 '-' hex4 '-' hex4 '-' hex12 ')'
{ let s = Lexing.lexeme lexbuf in
UUID(String.sub s 1 (String.length s - 2)) }
| eof { EOF }
| _ { raise (Lex_error ("Illegal character " ^
Char.escaped(Lexing.lexeme_char lexbuf 0))) }
and comment = parse
"*/" { token lexbuf }
| _ { comment lexbuf }
| eof { raise (Lex_error "Unterminated comment") }
and string = parse
'"'
{ () }
| '\\' eol [' ' '\009'] *
{ string lexbuf }
| '\\' ['\\' '"' 'n' 't' 'b' 'r']
{ Buffer.add_char string_buffer
(char_for_backslash(Lexing.lexeme_char lexbuf 1));
string lexbuf }
| '\\' ['0'-'3'] ['0'-'7']? ['0'-'7']?
{ Buffer.add_char string_buffer (char_for_code lexbuf 1 0);
string lexbuf }
| eof
{ raise (Lex_error "Unterminated string") }
| _
{ Buffer.add_char string_buffer (Lexing.lexeme_char lexbuf 0);
string lexbuf }
|
