1 |
12 |
jlechner |
/* Language lexer definitions for the GNU compiler for the Java(TM) language.
|
2 |
|
|
Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004
|
3 |
|
|
Free Software Foundation, Inc.
|
4 |
|
|
Contributed by Alexandre Petit-Bianco (apbianco@cygnus.com)
|
5 |
|
|
|
6 |
|
|
This file is part of GCC.
|
7 |
|
|
|
8 |
|
|
GCC is free software; you can redistribute it and/or modify
|
9 |
|
|
it under the terms of the GNU General Public License as published by
|
10 |
|
|
the Free Software Foundation; either version 2, or (at your option)
|
11 |
|
|
any later version.
|
12 |
|
|
|
13 |
|
|
GCC is distributed in the hope that it will be useful,
|
14 |
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
15 |
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
16 |
|
|
GNU General Public License for more details.
|
17 |
|
|
|
18 |
|
|
You should have received a copy of the GNU General Public License
|
19 |
|
|
along with GCC; see the file COPYING. If not, write to
|
20 |
|
|
the Free Software Foundation, 51 Franklin Street, Fifth Floor,
|
21 |
|
|
Boston, MA 02110-1301, USA.
|
22 |
|
|
|
23 |
|
|
Java and all Java-based marks are trademarks or registered trademarks
|
24 |
|
|
of Sun Microsystems, Inc. in the United States and other countries.
|
25 |
|
|
The Free Software Foundation is independent of Sun Microsystems, Inc. */
|
26 |
|
|
|
27 |
|
|
#ifndef GCC_JAVA_LEX_H
|
28 |
|
|
#define GCC_JAVA_LEX_H
|
29 |
|
|
|
30 |
|
|
#include "input.h"
|
31 |
|
|
|
32 |
|
|
/* Extern global variables declarations */
|
33 |
|
|
extern FILE *finput;
|
34 |
|
|
|
35 |
|
|
/* A Unicode character, as read from the input file */
|
36 |
|
|
typedef unsigned short unicode_t;
|
37 |
|
|
|
38 |
|
|
#ifndef HAVE_ICONV_H
|
39 |
|
|
#undef HAVE_ICONV
|
40 |
|
|
#endif
|
41 |
|
|
|
42 |
|
|
#if defined HAVE_ICONV
|
43 |
|
|
#include <iconv.h>
|
44 |
|
|
#endif /* HAVE_ICONV */
|
45 |
|
|
|
46 |
|
|
/* Default encoding to use if no encoding is specified. */
|
47 |
|
|
#define DEFAULT_ENCODING "UTF-8"
|
48 |
|
|
|
49 |
|
|
typedef struct java_lc_s GTY(()) {
|
50 |
|
|
int line; /* line number (1-based) */
|
51 |
|
|
int col; /* column number number (1-based) */
|
52 |
|
|
} java_lc;
|
53 |
|
|
|
54 |
|
|
struct java_lexer
|
55 |
|
|
{
|
56 |
|
|
/* The file from which we're reading. */
|
57 |
|
|
FILE *finput;
|
58 |
|
|
|
59 |
|
|
/* Number of consecutive backslashes we've read. */
|
60 |
|
|
int bs_count;
|
61 |
|
|
|
62 |
|
|
/* Next available Unicode character.
|
63 |
|
|
* This is post-Unicode-escape-processing. -1 if EOF. */
|
64 |
|
|
int next_unicode;
|
65 |
|
|
|
66 |
|
|
/* True if next_unicode is next available character, or EOF. */
|
67 |
|
|
bool avail_unicode;
|
68 |
|
|
|
69 |
|
|
/* Number of source columns of the previous Unicode character (next_unicode).
|
70 |
|
|
If next_unicode==-2, then this is the number of columns of the previous
|
71 |
|
|
Unicode character (most recent result of java_{get,peek}_unicode). */
|
72 |
|
|
int next_columns;
|
73 |
|
|
|
74 |
|
|
/* If nonzero, a value that was pushed back. This is a unicode character,
|
75 |
|
|
but (unlike next_unicode) is pre-'\uXXXX'-processing. It is also used
|
76 |
|
|
when a '\r' is *not* followed by a '\n'. */
|
77 |
|
|
unicode_t unget_value;
|
78 |
|
|
|
79 |
|
|
/* Name of the character encoding we're using. */
|
80 |
|
|
const char *encoding;
|
81 |
|
|
|
82 |
|
|
/* Current source position. */
|
83 |
|
|
java_lc position;
|
84 |
|
|
|
85 |
|
|
#ifndef USE_MAPPED_LOCATION
|
86 |
|
|
java_lc token_start; /* Error's line column info */
|
87 |
|
|
#endif
|
88 |
|
|
|
89 |
|
|
#ifdef HAVE_ICONV
|
90 |
|
|
/* Nonzero if we've read any bytes. We only recognize the
|
91 |
|
|
byte-order-marker (BOM) as the first word. */
|
92 |
|
|
unsigned int read_anything : 1;
|
93 |
|
|
|
94 |
|
|
/* Nonzero if we have to byte swap. */
|
95 |
|
|
unsigned int byte_swap : 1;
|
96 |
|
|
|
97 |
|
|
/* Nonzero if we're using the fallback decoder. */
|
98 |
|
|
unsigned int use_fallback : 1;
|
99 |
|
|
|
100 |
|
|
/* The handle for the iconv converter we're using. */
|
101 |
|
|
iconv_t handle;
|
102 |
|
|
|
103 |
|
|
/* Bytes we've read from the file but have not sent to iconv. */
|
104 |
|
|
char buffer[1024];
|
105 |
|
|
|
106 |
|
|
/* Index of first valid character in buffer, -1 if no valid
|
107 |
|
|
characters. */
|
108 |
|
|
int first;
|
109 |
|
|
|
110 |
|
|
/* Index of last valid character in buffer, plus one. -1 if no
|
111 |
|
|
valid characters in buffer. */
|
112 |
|
|
int last;
|
113 |
|
|
|
114 |
|
|
/* This is a buffer of characters already converted by iconv. We
|
115 |
|
|
use `char' here because we're assuming that iconv() converts to
|
116 |
|
|
UCS-2, and then we convert it ourselves. */
|
117 |
|
|
unsigned char out_buffer[1024];
|
118 |
|
|
|
119 |
|
|
/* Index of first valid output character. -1 if no valid
|
120 |
|
|
characters. */
|
121 |
|
|
int out_first;
|
122 |
|
|
|
123 |
|
|
/* Index of last valid output character, plus one. -1 if no valid
|
124 |
|
|
characters. */
|
125 |
|
|
int out_last;
|
126 |
|
|
|
127 |
|
|
#endif /* HAVE_ICONV */
|
128 |
|
|
};
|
129 |
|
|
typedef struct java_lexer java_lexer;
|
130 |
|
|
|
131 |
|
|
/* Destroy a lexer object. */
|
132 |
|
|
extern void java_destroy_lexer (java_lexer *);
|
133 |
|
|
|
134 |
|
|
#define JAVA_LINE_MAX 80
|
135 |
|
|
|
136 |
|
|
/* Build a location compound integer */
|
137 |
|
|
#ifdef USE_MAPPED_LOCATION
|
138 |
|
|
#define BUILD_LOCATION() input_location
|
139 |
|
|
#else
|
140 |
|
|
#define BUILD_LOCATION() ((ctxp->lexer->token_start.line << 12) \
|
141 |
|
|
| (ctxp->lexer->token_start.col & 0xfff))
|
142 |
|
|
#endif
|
143 |
|
|
|
144 |
|
|
/* Those macros are defined differently if we compile jc1-lite
|
145 |
|
|
(JC1_LITE defined) or jc1. */
|
146 |
|
|
#ifdef JC1_LITE
|
147 |
|
|
|
148 |
|
|
#define DCONST0 0
|
149 |
|
|
#define REAL_VALUE_TYPE int
|
150 |
|
|
#define GET_IDENTIFIER(S) xstrdup ((S))
|
151 |
|
|
#define REAL_VALUE_ATOF(LIT,MODE) 0
|
152 |
|
|
#define REAL_VALUE_ISINF(VALUE) 0
|
153 |
|
|
#define REAL_VALUE_ISNAN(VALUE) 0
|
154 |
|
|
#define SET_REAL_VALUE_ATOF(TARGET,SOURCE)
|
155 |
|
|
#define FLOAT_TYPE_NODE 0
|
156 |
|
|
#define DOUBLE_TYPE_NODE 0
|
157 |
|
|
#define SET_MODIFIER_CTX(TOKEN) java_lval->value = (TOKEN)
|
158 |
|
|
#define GET_TYPE_PRECISION(NODE) 4
|
159 |
|
|
#define BUILD_OPERATOR(TOKEN) return TOKEN
|
160 |
|
|
#define BUILD_OPERATOR2(TOKEN) return ASSIGN_ANY_TK
|
161 |
|
|
#define SET_LVAL_NODE(NODE)
|
162 |
|
|
#define BUILD_ID_WFL(EXP) (EXP)
|
163 |
|
|
#define JAVA_FLOAT_RANGE_ERROR(S) {}
|
164 |
|
|
#define JAVA_RANGE_ERROR(S) do { } while (0)
|
165 |
|
|
|
166 |
|
|
#else
|
167 |
|
|
|
168 |
|
|
#define DCONST0 dconst0
|
169 |
|
|
#define GET_IDENTIFIER(S) get_identifier ((S))
|
170 |
|
|
#define SET_REAL_VALUE_ATOF(TARGET,SOURCE) (TARGET) = (SOURCE)
|
171 |
|
|
#define FLOAT_TYPE_NODE float_type_node
|
172 |
|
|
#define DOUBLE_TYPE_NODE double_type_node
|
173 |
|
|
/* Set modifier_ctx according to TOKEN */
|
174 |
|
|
#define SET_MODIFIER_CTX(TOKEN) \
|
175 |
|
|
{ \
|
176 |
|
|
ctxp->modifier_ctx [(TOKEN)-PUBLIC_TK] = build_wfl_node (NULL_TREE); \
|
177 |
|
|
java_lval->value = (TOKEN)-PUBLIC_TK; \
|
178 |
|
|
}
|
179 |
|
|
/* Type precision for long */
|
180 |
|
|
#define GET_TYPE_PRECISION(NODE) TYPE_PRECISION (long_type_node) / 8;
|
181 |
|
|
/* Build an operator tree node and return TOKEN */
|
182 |
|
|
#define BUILD_OPERATOR(TOKEN) \
|
183 |
|
|
{ \
|
184 |
|
|
java_lval->operator.token = (TOKEN); \
|
185 |
|
|
java_lval->operator.location = BUILD_LOCATION(); \
|
186 |
|
|
return (TOKEN); \
|
187 |
|
|
}
|
188 |
|
|
|
189 |
|
|
/* Build an operator tree node but return ASSIGN_ANY_TK */
|
190 |
|
|
#define BUILD_OPERATOR2(TOKEN) \
|
191 |
|
|
{ \
|
192 |
|
|
java_lval->operator.token = (TOKEN); \
|
193 |
|
|
java_lval->operator.location = BUILD_LOCATION(); \
|
194 |
|
|
return ASSIGN_ANY_TK; \
|
195 |
|
|
}
|
196 |
|
|
/* Set java_lval->node and TREE_TYPE(java_lval->node) in macros */
|
197 |
|
|
#define SET_LVAL_NODE(NODE) java_lval->node = (NODE)
|
198 |
|
|
/* Wrap identifier around a wfl */
|
199 |
|
|
#define BUILD_ID_WFL(EXP) build_wfl_node ((EXP))
|
200 |
|
|
/* Special ways to report error on numeric literals */
|
201 |
|
|
#define JAVA_FLOAT_RANGE_ERROR(m) \
|
202 |
|
|
{ \
|
203 |
|
|
char *msg = xmalloc (100 + strlen (m)); \
|
204 |
|
|
sprintf (msg, "Floating point literal exceeds range of `%s'", (m)); \
|
205 |
|
|
JAVA_RANGE_ERROR(msg); \
|
206 |
|
|
free (msg); \
|
207 |
|
|
}
|
208 |
|
|
#define JAVA_RANGE_ERROR(msg) \
|
209 |
|
|
do { \
|
210 |
|
|
int save_col = ctxp->lexer->position.col; \
|
211 |
|
|
ctxp->lexer->position.col = number_beginning; \
|
212 |
|
|
java_lex_error (msg, 0); \
|
213 |
|
|
ctxp->lexer->position.col = save_col; \
|
214 |
|
|
} while (0)
|
215 |
|
|
|
216 |
|
|
#endif /* Definitions for jc1 compilation only */
|
217 |
|
|
|
218 |
|
|
/* Macros to decode character ranges */
|
219 |
|
|
#define RANGE(c, l, h) (((c) >= l && (c) <= h))
|
220 |
|
|
#define JAVA_WHITE_SPACE_P(c) (c == ' ' || c == '\t' || c == '\f')
|
221 |
|
|
#define JAVA_START_CHAR_P(c) ((c < 128 \
|
222 |
|
|
&& (ISIDST (c) || c == '$')) \
|
223 |
|
|
|| (c >= 128 && java_start_char_p (c)))
|
224 |
|
|
#define JAVA_PART_CHAR_P(c) ((c < 128 \
|
225 |
|
|
&& (ISIDNUM (c) \
|
226 |
|
|
|| c == '$' \
|
227 |
|
|
|| c == 0x0000 \
|
228 |
|
|
|| RANGE (c, 0x01, 0x08) \
|
229 |
|
|
|| RANGE (c, 0x0e, 0x1b) \
|
230 |
|
|
|| c == 0x7f)) \
|
231 |
|
|
|| (c >= 128 && java_part_char_p (c)))
|
232 |
|
|
#define JAVA_ASCII_DIGIT(c) ISDIGIT (c)
|
233 |
|
|
#define JAVA_ASCII_OCTDIGIT(c) RANGE (c, '0', '7')
|
234 |
|
|
#define JAVA_ASCII_HEXDIGIT(c) ISXDIGIT (c)
|
235 |
|
|
#define JAVA_ASCII_FPCHAR(c) (RANGE (c, 'd', 'f') || RANGE (c, 'D', 'F') || \
|
236 |
|
|
c == '.' || JAVA_ASCII_DIGIT (c))
|
237 |
|
|
#define JAVA_FP_SUFFIX(c) (c == 'D' || c == 'd' || c == 'f' || c == 'F')
|
238 |
|
|
#define JAVA_FP_EXP(c) (c == 'E' || c == 'F')
|
239 |
|
|
#define JAVA_FP_PM(c) (c == '-' || c == '+')
|
240 |
|
|
#define JAVA_ASCII_LETTER(c) ISALPHA (c)
|
241 |
|
|
|
242 |
|
|
/* Constants */
|
243 |
|
|
#define JAVA_READ_BUFFER 256
|
244 |
|
|
#define JAVA_CHAR_ERROR -2
|
245 |
|
|
#define UEOF -1
|
246 |
|
|
|
247 |
|
|
#endif /* ! GCC_JAVA_LEX_H */
|