1 /* src/vm/utf8.h - utf8 string functions
3 Copyright (C) 1996-2005, 2006 R. Grafl, A. Krall, C. Kruegel,
4 C. Oates, R. Obermaisser, M. Platter, M. Probst, S. Ring,
5 E. Steiner, C. Thalinger, D. Thuernbeck, P. Tomsich, C. Ullrich,
6 J. Wenninger, Institut f. Computersprachen - TU Wien
8 This file is part of CACAO.
10 This program is free software; you can redistribute it and/or
11 modify it under the terms of the GNU General Public License as
12 published by the Free Software Foundation; either version 2, or (at
13 your option) any later version.
15 This program is distributed in the hope that it will be useful, but
16 WITHOUT ANY WARRANTY; without even the implied warranty of
17 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 General Public License for more details.
20 You should have received a copy of the GNU General Public License
21 along with this program; if not, write to the Free Software
22 Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
25 Contact: cacao@cacaojvm.org
27 Authors: Christian Thalinger
29 Changes: Edwin Steiner
31 $Id: utf8.h 5697 2006-10-05 17:23:48Z twisti $
43 /* forward typedefs ***********************************************************/
45 typedef struct utf utf;
48 #include "vm/global.h"
51 /* data structure for utf8 symbols ********************************************/
54 utf *hashlink; /* link for external hash chain */
55 s4 blength; /* text length in bytes */
56 char *text; /* pointer to text */
59 /* to determine the end of utf strings */
61 #define UTF_END(u) ((char *) u->text + u->blength)
64 /* utf-symbols for pointer comparison of frequently used strings **************/
66 extern utf *utf_java_lang_Object;
68 extern utf *utf_java_lang_Class;
69 extern utf *utf_java_lang_ClassLoader;
70 extern utf *utf_java_lang_Cloneable;
71 extern utf *utf_java_lang_SecurityManager;
72 extern utf *utf_java_lang_String;
73 extern utf *utf_java_lang_System;
74 extern utf *utf_java_lang_ThreadGroup;
75 extern utf *utf_java_io_Serializable;
77 extern utf *utf_java_lang_Throwable;
78 extern utf *utf_java_lang_VMThrowable;
79 extern utf *utf_java_lang_Error;
80 extern utf *utf_java_lang_AbstractMethodError;
81 extern utf *utf_java_lang_LinkageError;
82 extern utf *utf_java_lang_NoClassDefFoundError;
83 extern utf *utf_java_lang_NoSuchMethodError;
84 extern utf *utf_java_lang_OutOfMemoryError;
86 extern utf *utf_java_lang_Exception;
87 extern utf *utf_java_lang_ClassCastException;
88 extern utf *utf_java_lang_ClassNotFoundException;
89 extern utf *utf_java_lang_IllegalArgumentException;
90 extern utf *utf_java_lang_IllegalMonitorStateException;
92 extern utf *utf_java_lang_NullPointerException;
94 extern utf* utf_java_lang_Void;
95 extern utf* utf_java_lang_Boolean;
96 extern utf* utf_java_lang_Byte;
97 extern utf* utf_java_lang_Character;
98 extern utf* utf_java_lang_Short;
99 extern utf* utf_java_lang_Integer;
100 extern utf* utf_java_lang_Long;
101 extern utf* utf_java_lang_Float;
102 extern utf* utf_java_lang_Double;
104 extern utf *utf_java_lang_StackTraceElement;
105 extern utf *utf_java_lang_reflect_Constructor;
106 extern utf *utf_java_lang_reflect_Field;
107 extern utf *utf_java_lang_reflect_Method;
108 extern utf *utf_java_util_Vector;
111 extern utf *utf_InnerClasses;
112 extern utf *utf_ConstantValue;
113 extern utf *utf_Code;
114 extern utf *utf_Exceptions;
115 extern utf *utf_LineNumberTable;
116 extern utf *utf_SourceFile;
118 extern utf *utf_init;
119 extern utf *utf_clinit;
120 extern utf *utf_clone;
121 extern utf *utf_finalize;
125 extern utf *utf_remove;
126 extern utf *utf_removeThread;
129 extern utf *utf_value;
131 extern utf *utf_fillInStackTrace;
132 extern utf *utf_getSystemClassLoader;
133 extern utf *utf_loadClass;
134 extern utf *utf_printStackTrace;
145 extern utf *utf_void__void;
146 extern utf *utf_boolean__void;
147 extern utf *utf_byte__void;
148 extern utf *utf_char__void;
149 extern utf *utf_short__void;
150 extern utf *utf_int__void;
151 extern utf *utf_long__void;
152 extern utf *utf_float__void;
153 extern utf *utf_double__void;
155 extern utf *utf_void__java_lang_ClassLoader;
156 extern utf *utf_void__java_lang_Object;
157 extern utf *utf_void__java_lang_Throwable;
158 extern utf *utf_java_lang_Object__java_lang_Object;
159 extern utf *utf_java_lang_String__void;
160 extern utf *utf_java_lang_String__java_lang_Class;
161 extern utf *utf_java_lang_Thread__V;
162 extern utf *utf_java_lang_Throwable__void;
164 extern utf *utf_not_named_yet;
165 extern utf *utf_null;
166 extern utf *array_packagename;
169 /* function prototypes ********************************************************/
171 /* initialize the utf8 subsystem */
172 bool utf8_init(void);
174 u4 utf_hashkey(const char *text, u4 length);
175 u4 utf_full_hashkey(const char *text, u4 length);
177 /* determine hashkey of a unicode-symbol */
178 u4 unicode_hashkey(u2 *text, u2 length);
180 /* create new utf-symbol */
181 utf *utf_new(const char *text, u2 length);
183 /* make utf symbol from u2 array */
184 utf *utf_new_u2(u2 *unicodedata, u4 unicodelength, bool isclassname);
186 utf *utf_new_char(const char *text);
187 utf *utf_new_char_classname(const char *text);
189 /* get number of bytes */
190 u4 utf_bytes(utf *u);
192 /* get next unicode character of a utf-string */
193 u2 utf_nextu2(char **utf);
195 /* get number of unicode characters of a utf string */
196 u4 utf_get_number_of_u2s(utf *u);
197 u4 utf_get_number_of_u2s_for_buffer(const char *buffer, u4 blength);
199 /* determine utf length in bytes of a u2 array */
200 u4 u2_utflength(u2 *text, u4 u2_length);
202 void utf_copy(char *buffer, utf *u);
203 void utf_cat(char *buffer, utf *u);
204 void utf_copy_classname(char *buffer, utf *u);
205 void utf_cat_classname(char *buffer, utf *u);
207 /* write utf symbol to file/buffer */
208 void utf_display_printable_ascii(utf *u);
209 void utf_display_printable_ascii_classname(utf *u);
211 void utf_sprint_convert_to_latin1(char *buffer, utf *u);
212 void utf_sprint_convert_to_latin1_classname(char *buffer, utf *u);
214 void utf_strcat_convert_to_latin1(char *buffer, utf *u);
215 void utf_strcat_convert_to_latin1_classname(char *buffer, utf *u);
217 void utf_fprint_printable_ascii(FILE *file, utf *u);
218 void utf_fprint_printable_ascii_classname(FILE *file, utf *u);
220 /* check if a UTF-8 string is valid */
221 bool is_valid_utf(char *utf_ptr, char *end_pos);
223 /* check if a UTF-8 string may be used as a class/field/method name */
224 bool is_valid_name(char *utf_ptr, char *end_pos);
225 bool is_valid_name_utf(utf *u);
234 * These are local overrides for various environment variables in Emacs.
235 * Please do not remove this and leave it at the end of the file, where
236 * Emacs will automagically detect them.
237 * ---------------------------------------------------------------------
240 * indent-tabs-mode: t
244 * vim:noexpandtab:sw=4:ts=4: