1 /* The lexer multiplexer for Gedcom.
2 Copyright (C) 2001,2002 The Genes Development Team
3 This file is part of the Gedcom parser library.
4 Contributed by Peter Verthez <Peter.Verthez@advalvas.be>, 2001.
6 The Gedcom parser library is free software; you can redistribute it
7 and/or modify it under the terms of the GNU Lesser General Public
8 License as published by the Free Software Foundation; either
9 version 2.1 of the License, or (at your option) any later version.
11 The Gedcom parser library is distributed in the hope that it will be
12 useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
13 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 Lesser General Public License for more details.
16 You should have received a copy of the GNU Lesser General Public
17 License along with the Gedcom parser library; if not, write to the
18 Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
24 #include "gedcom_internal.h"
31 typedef int (*lex_func)(void);
34 int lexer_init(ENCODING enc, FILE* f)
36 if (enc == ONE_BYTE) {
38 lf = &gedcom_1byte_lex;
39 set_encoding_width(enc);
40 return open_conv_to_internal("ASCII");
42 else if (enc == TWO_BYTE_HILO) {
44 lf = &gedcom_hilo_lex;
45 set_encoding_width(enc);
46 return open_conv_to_internal("UNICODE");
48 else if (enc == TWO_BYTE_LOHI) {
50 lf = &gedcom_lohi_lex;
51 set_encoding_width(enc);
52 return open_conv_to_internal("UNICODE");
61 close_conv_to_internal();
69 int determine_encoding(FILE* f)
73 fread(first, 1, 2, f);
74 if ((first[0] == '0') && (first[1] == ' ')) {
75 gedcom_debug_print(_("One-byte encoding"));
79 else if ((first[0] == '\0') && (first[1] == '0'))
81 gedcom_debug_print(_("Two-byte encoding, high-low"));
85 else if ((first[0] == '\xFE') && (first[1] == '\xFF'))
87 gedcom_debug_print(_("Two-byte encoding, high-low, with BOM"));
90 else if ((first[0] == '0') && (first[1] == '\0'))
92 gedcom_debug_print(_("Two-byte encoding, low-high"));
96 else if ((first[0] == '\xFF') && (first[1] == '\xFE'))
98 gedcom_debug_print(_("Two-byte encoding, low-high, with BOM"));
102 gedcom_warning(_("Unknown encoding, falling back to one-byte"));
108 int gedcom_parse_file(char* file_name)
114 char *save_locale = strdup(setlocale(LC_ALL, NULL));
115 char *save_textdom = textdomain(NULL);
116 setlocale(LC_ALL, "");
117 bindtextdomain(PACKAGE, LOCALEDIR);
118 bind_textdomain_codeset(PACKAGE, INTERNAL_ENCODING);
122 file = fopen(file_name, "r");
124 gedcom_error(_("Could not open file '%s'"), file_name);
128 enc = determine_encoding(file);
130 if (lexer_init(enc, file)) {
133 result = gedcom_parse();
135 result = check_xref_table();
141 textdomain(save_textdom);
142 setlocale(LC_ALL, save_locale);