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
201
202
|
%{
//
//====================--------------------------------------------------------------
// Eran Ifrah 2014 (c)
//====================--------------------------------------------------------------
//
// To generate a source file from this .l file, you will need
// a flex version 2.5.34 and later
// Under Windows, you will need to run the following command
// from within *MSYS* terminal (or run codelite from an MSYS shell):
// /usr/bin/flex -Pxml --batch --outfile=XmlLexer.cpp XMLLexer.l
//
//====================--------------------------------------------------------------
//
extern "C" int yywrap(void*) { return 1; }
#include <wx/string.h>
#include <string>
#include <wx/filename.h>
#include "XMLLexerAPI.h"
#include "XMLLexerTokens.h"
#define YY_FATAL_ERROR(x)
#define YYSTYPE char*
#define ECHO
#define P(s) fprintf(stderr, "%s\n", s)
#define YY_NO_UNISTD_H
#define YY_USER_ACTION yycolumn += yyleng;
#define RETURN_WHITESPACE()
#define RETURN_NEWLINE()
%}
/* regex and modes */
/* options */
%option yylineno
%option default
%option reentrant
identifier [$a-zA-Z_][$0-9a-zA-Z_\-]*
exponent_part [eE][-+]?[0-9]+
fractional_constant ([0-9]*"."[0-9]+)|([0-9]+".")
floating_constant (({fractional_constant}{exponent_part}?)|([0-9]+{exponent_part}))[FfLl]?
integer_suffix_opt ([uU]?[lL]?)|([lL][uU])
decimal_constant [1-9][0-9]*{integer_suffix_opt}
octal_constant "0"[0-7]*{integer_suffix_opt}
hex_constant "0"[xX][0-9a-fA-F]+{integer_suffix_opt}
simple_escape [abfnrtv'"?\\]
octal_escape [0-7]{1,3}
hex_escape "x"[0-9a-fA-F]+
escape_sequence [\\]({simple_escape}|{octal_escape}|{hex_escape})
c_char [^'\\\n]|{escape_sequence}
s_char [^"\\\n]|{escape_sequence}
h_tab [\011]
form_feed [\014]
v_tab [\013]
c_return [\015]
horizontal_white [ ]|{h_tab}
%x CDATA
%x COMMENT
%x NOXML
%%
<<EOF>> {yyterminate();}
<INITIAL>{horizontal_white} {}
<INITIAL>"/>" {return kXML_T_CLOSE_TAG_SUFFIX;}
<INITIAL>"</" {return kXML_T_CLOSE_TAG_PREFIX;}
<INITIAL>"<?" { BEGIN NOXML; return kXML_T_XML_OPEN_TAG;}
<INITIAL>"<!DOCTYPE" {return kXML_T_HTML_DOCTYPE;}
<INITIAL>"<![CDATA[" { BEGIN CDATA; return kXML_T_CDATA_START; }
<INITIAL>"<" {return kXML_T_ENTITY_LT;}
<INITIAL>">" {return kXML_T_ENTITY_GT;}
<INITIAL>"&" {return kXML_T_ENTITY_AMP;}
<INITIAL>"'" {return kXML_T_ENTITY_APOS;}
<INITIAL>""" {return kXML_T_ENTITY_QUOATATION_MARK;}
<INITIAL>"<!--" { BEGIN COMMENT; return kXML_T_COMMENT_START;}
<INITIAL>{identifier} {return kXML_T_IDENTIFIER;}
<INITIAL>[']{c_char}*['] { return kXML_T_STRING;}
<INITIAL>["]{s_char}*["] { return kXML_T_STRING;}
<INITIAL>. { return yytext[0];}
<CDATA>"]]>" {
BEGIN INITIAL;
return kXML_T_CDATA_END;
}
<CDATA>. { return yytext[0];}
<COMMENT>"-->" {
BEGIN INITIAL;
return kXML_T_COMMENT_END;
}
<COMMENT>. { return yytext[0];}
<NOXML>"?>" {
BEGIN INITIAL;
return kXML_T_XML_CLOSE_TAG;
}
<NOXML>. { return yytext[0];}
%%
//=============-------------------------------
// API methods implementation
//=============-------------------------------
void* xmlLexerNew(const wxString& content)
{
yyscan_t scanner;
yylex_init(&scanner);
struct yyguts_t * yyg = (struct yyguts_t*)scanner;
XMLLexerUserData *userData = new XMLLexerUserData();
// keep the file pointer (and make sure we close it at the end)
userData->SetCurrentPF(NULL);
yyg->yyextra_r = userData;
wxCharBuffer cb = content.mb_str(wxConvUTF8);
yy_switch_to_buffer(yy_scan_string(cb.data(), scanner), scanner);
yycolumn = 1;
yylineno = 0;
return scanner;
}
void* xmlLexerNew(const wxFileName& filename)
{
wxFileName fn = filename;
if(fn.IsRelative()) {
fn.MakeAbsolute();
}
FILE* fp = ::fopen(fn.GetFullPath().mb_str(wxConvUTF8).data(), "rb");
if(!fp) {
return NULL;
}
yyscan_t scanner;
yylex_init(&scanner);
struct yyguts_t * yyg = (struct yyguts_t*)scanner;
XMLLexerUserData *userData = new XMLLexerUserData();
// keep the file pointer (and make sure we close it at the end)
userData->SetCurrentPF(fp);
yyg->yyextra_r = userData;
yy_switch_to_buffer(yy_create_buffer(fp, YY_BUF_SIZE, scanner), scanner);
yycolumn = 1;
yylineno = 0;
return scanner;
}
void xmlLexerDestroy(void** scanner)
{
struct yyguts_t * yyg = (struct yyguts_t*)(*scanner);
delete (XMLLexerUserData*)yyg->yyextra_r;
yy_delete_buffer(YY_CURRENT_BUFFER, *scanner);
yylex_destroy(*scanner);
*scanner = NULL;
}
void xmlLexerUnget(void* scanner)
{
// return the entire token back to the input stream
struct yyguts_t * yyg = (struct yyguts_t*)scanner;
yyless(0);
}
wxString xmlLexerText(void* scanner)
{
struct yyguts_t * yyg = (struct yyguts_t*)scanner;
return wxString(yytext, wxConvUTF8);
}
bool xmlLexerNext(void* scanner, XMLLexerToken& token)
{
struct yyguts_t * yyg = (struct yyguts_t*)scanner;
token.Clear();
token.column = 0;
token.type = yylex(scanner);
if(token.type != 0) {
token.lineNumber = yylineno;
token.text = wxString(yytext, wxConvUTF8);
token.column = yycolumn;
}
return token.type != 0;
}
wxString xmlLexerCurrentToken(void* scanner)
{
struct yyguts_t * yyg = (struct yyguts_t*)scanner;
return yytext;
}
XMLLexerUserData* xmlLexerGetUserData(void* scanner)
{
struct yyguts_t * yyg = (struct yyguts_t*)scanner;
return (XMLLexerUserData*) yyg->yyextra_r;
}
|
