adamh-hpricot 0.6.168
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG +62 -0
- data/COPYING +18 -0
- data/README +284 -0
- data/Rakefile +259 -0
- data/ext/fast_xs/FastXsService.java +1018 -0
- data/ext/fast_xs/extconf.rb +4 -0
- data/ext/fast_xs/fast_xs.c +194 -0
- data/ext/hpricot_scan/extconf.rb +6 -0
- data/ext/hpricot_scan/hpricot_common.rl +76 -0
- data/ext/hpricot_scan/hpricot_scan.h +79 -0
- data/ext/hpricot_scan/hpricot_scan.java.rl +373 -0
- data/ext/hpricot_scan/hpricot_scan.rl +649 -0
- data/extras/mingw-rbconfig.rb +176 -0
- data/lib/hpricot/blankslate.rb +63 -0
- data/lib/hpricot/builder.rb +209 -0
- data/lib/hpricot/elements.rb +510 -0
- data/lib/hpricot/htmlinfo.rb +672 -0
- data/lib/hpricot/inspect.rb +103 -0
- data/lib/hpricot/modules.rb +38 -0
- data/lib/hpricot/parse.rb +36 -0
- data/lib/hpricot/tag.rb +186 -0
- data/lib/hpricot/tags.rb +164 -0
- data/lib/hpricot/traverse.rb +838 -0
- data/lib/hpricot/xchar.rb +94 -0
- data/lib/hpricot.rb +26 -0
- data/test/files/basic.xhtml +17 -0
- data/test/files/boingboing.html +2266 -0
- data/test/files/cy0.html +3653 -0
- data/test/files/immob.html +400 -0
- data/test/files/pace_application.html +1320 -0
- data/test/files/tenderlove.html +16 -0
- data/test/files/uswebgen.html +220 -0
- data/test/files/utf8.html +1054 -0
- data/test/files/week9.html +1723 -0
- data/test/files/why.xml +19 -0
- data/test/load_files.rb +7 -0
- data/test/test_alter.rb +77 -0
- data/test/test_builder.rb +37 -0
- data/test/test_parser.rb +400 -0
- data/test/test_paths.rb +25 -0
- data/test/test_preserved.rb +66 -0
- data/test/test_xml.rb +28 -0
- metadata +107 -0
@@ -0,0 +1,194 @@
|
|
1
|
+
#define VERSION "0.1"
|
2
|
+
|
3
|
+
#include <ruby.h>
|
4
|
+
#include <assert.h>
|
5
|
+
/* #include <stdio.h> */
|
6
|
+
|
7
|
+
static ID unpack_id;
|
8
|
+
static VALUE U_fmt, C_fmt;
|
9
|
+
|
10
|
+
/* give GCC hints for better branch prediction
|
11
|
+
* (we layout branches so that ASCII characters are handled faster) */
|
12
|
+
#if defined(__GNUC__) && (__GNUC__ >= 3)
|
13
|
+
# define likely(x) __builtin_expect (!!(x), 1)
|
14
|
+
# define unlikely(x) __builtin_expect (!!(x), 0)
|
15
|
+
#else
|
16
|
+
# define unlikely(x) (x)
|
17
|
+
# define likely(x) (x)
|
18
|
+
#endif
|
19
|
+
|
20
|
+
/* pass-through certain characters for CP-1252 */
|
21
|
+
#define p(x) (x-128)
|
22
|
+
|
23
|
+
static const int cp_1252[] = {
|
24
|
+
8364, /* 128 => 8364, euro sign */
|
25
|
+
p(129), /* 129 => 129, pass-through */
|
26
|
+
8218, /* 130 => 8218, single low-9 quotation mark */
|
27
|
+
402, /* 131 => 402, latin small letter f with hook */
|
28
|
+
8222, /* 132 => 8222, double low-9 quotation mark */
|
29
|
+
8230, /* 133 => 8230, horizontal ellipsis */
|
30
|
+
8224, /* 134 => 8224, dagger */
|
31
|
+
8225, /* 135 => 8225, double dagger */
|
32
|
+
710, /* 136 => 710, modifier letter circumflex accent */
|
33
|
+
8240, /* 137 => 8240, per mille sign */
|
34
|
+
352, /* 138 => 352, latin capital letter s with caron */
|
35
|
+
8249, /* 139 => 8249, single left-pointing angle quotation mark */
|
36
|
+
338, /* 140 => 338, latin capital ligature oe */
|
37
|
+
p(141), /* 141 => 141, pass-through */
|
38
|
+
381, /* 142 => 381, latin capital letter z with caron */
|
39
|
+
p(143), /* 143 => 143, pass-through */
|
40
|
+
p(144), /* 144 => 144, pass-through */
|
41
|
+
8216, /* 145 => 8216, left single quotation mark */
|
42
|
+
8217, /* 146 => 8217, right single quotation mark */
|
43
|
+
8220, /* 147 => 8220, left double quotation mark */
|
44
|
+
8221, /* 148 => 8221, right double quotation mark */
|
45
|
+
8226, /* 149 => 8226, bullet */
|
46
|
+
8211, /* 150 => 8211, en dash */
|
47
|
+
8212, /* 151 => 8212, em dash */
|
48
|
+
732, /* 152 => 732, small tilde */
|
49
|
+
8482, /* 153 => 8482, trade mark sign */
|
50
|
+
353, /* 154 => 353, latin small letter s with caron */
|
51
|
+
8250, /* 155 => 8250, single right-pointing angle quotation mark */
|
52
|
+
339, /* 156 => 339, latin small ligature oe */
|
53
|
+
p(157), /* 157 => 157, pass-through */
|
54
|
+
382, /* 158 => 382, latin small letter z with caron */
|
55
|
+
376 /* 159 => 376} latin capital letter y with diaeresis */
|
56
|
+
};
|
57
|
+
|
58
|
+
#define VALID_VALUE(n) \
|
59
|
+
(n >= 0x20 && n <= 0xD7FF) || \
|
60
|
+
(n >= 0xE000 && n <= 0xFFFD) || \
|
61
|
+
(n >= 0x10000 && n <= 0x10FFFF)
|
62
|
+
|
63
|
+
#define CP_1252_ESCAPE(n) do { \
|
64
|
+
if (n >= 128 && n <= 159) \
|
65
|
+
n = cp_1252[n - 128]; \
|
66
|
+
} while(0)
|
67
|
+
|
68
|
+
#define return_const_len(x) do { \
|
69
|
+
memcpy(buf, x, sizeof(x) - 1); \
|
70
|
+
return (sizeof(x) - 1); \
|
71
|
+
} while (0)
|
72
|
+
|
73
|
+
static inline size_t bytes_for(int n)
|
74
|
+
{
|
75
|
+
if (n < 1000)
|
76
|
+
return sizeof("ϧ") - 1;
|
77
|
+
if (n < 10000)
|
78
|
+
return sizeof("✏") - 1;
|
79
|
+
if (n < 100000)
|
80
|
+
return sizeof("𘚟") - 1;
|
81
|
+
if (n < 1000000)
|
82
|
+
return sizeof("󴈿") - 1;
|
83
|
+
/* if (n < 10000000), we won't have cases above 0x10FFFF */
|
84
|
+
return sizeof("�") - 1;
|
85
|
+
}
|
86
|
+
|
87
|
+
static long escape(char *buf, int n)
|
88
|
+
{
|
89
|
+
/* handle ASCII first */
|
90
|
+
if (likely(n < 128)) {
|
91
|
+
if (likely(n >= 0x20 || n == 0x9 || n == 0xA || n == 0xD)) {
|
92
|
+
if (unlikely(n == 34))
|
93
|
+
return_const_len(""");
|
94
|
+
if (unlikely(n == 38))
|
95
|
+
return_const_len("&");
|
96
|
+
if (unlikely(n == 60))
|
97
|
+
return_const_len("<");
|
98
|
+
if (unlikely(n == 62))
|
99
|
+
return_const_len(">");
|
100
|
+
buf[0] = (char)n;
|
101
|
+
return 1;
|
102
|
+
}
|
103
|
+
|
104
|
+
buf[0] = '*';
|
105
|
+
return 1;
|
106
|
+
}
|
107
|
+
|
108
|
+
CP_1252_ESCAPE(n);
|
109
|
+
|
110
|
+
if (VALID_VALUE(n)) {
|
111
|
+
/* return snprintf(buf, sizeof(""), "&#%i;", n); */
|
112
|
+
extern const char ruby_digitmap[];
|
113
|
+
int rv = 3; /* &#; */
|
114
|
+
buf += bytes_for(n);
|
115
|
+
*--buf = ';';
|
116
|
+
do {
|
117
|
+
*--buf = ruby_digitmap[(int)(n % 10)];
|
118
|
+
++rv;
|
119
|
+
} while (n /= 10);
|
120
|
+
*--buf = '#';
|
121
|
+
*--buf = '&';
|
122
|
+
return rv;
|
123
|
+
}
|
124
|
+
buf[0] = '*';
|
125
|
+
return 1;
|
126
|
+
}
|
127
|
+
|
128
|
+
#undef return_const_len
|
129
|
+
|
130
|
+
static long escaped_len(int n)
|
131
|
+
{
|
132
|
+
if (likely(n < 128)) {
|
133
|
+
if (unlikely(n == 34))
|
134
|
+
return (sizeof(""") - 1);
|
135
|
+
if (unlikely(n == 38))
|
136
|
+
return (sizeof("&") - 1);
|
137
|
+
if (unlikely(n == 60 || n == 62))
|
138
|
+
return (sizeof(">") - 1);
|
139
|
+
return 1;
|
140
|
+
}
|
141
|
+
|
142
|
+
CP_1252_ESCAPE(n);
|
143
|
+
|
144
|
+
if (VALID_VALUE(n))
|
145
|
+
return bytes_for(n);
|
146
|
+
return 1;
|
147
|
+
}
|
148
|
+
|
149
|
+
static VALUE unpack_utf8(VALUE self)
|
150
|
+
{
|
151
|
+
return rb_funcall(self, unpack_id, 1, U_fmt);
|
152
|
+
}
|
153
|
+
|
154
|
+
static VALUE unpack_uchar(VALUE self)
|
155
|
+
{
|
156
|
+
return rb_funcall(self, unpack_id, 1, C_fmt);
|
157
|
+
}
|
158
|
+
|
159
|
+
VALUE fast_xs(VALUE self)
|
160
|
+
{
|
161
|
+
long i;
|
162
|
+
struct RArray *array;
|
163
|
+
char *s, *c;
|
164
|
+
long s_len = 0;
|
165
|
+
VALUE *tmp;
|
166
|
+
|
167
|
+
array = RARRAY(rb_rescue(unpack_utf8, self, unpack_uchar, self));
|
168
|
+
|
169
|
+
tmp = array->ptr;
|
170
|
+
for (i = array->len; --i >= 0; tmp++)
|
171
|
+
s_len += escaped_len(NUM2INT(*tmp));
|
172
|
+
|
173
|
+
c = s = alloca(s_len + 1);
|
174
|
+
|
175
|
+
tmp = array->ptr;
|
176
|
+
for (i = array->len; --i >= 0; tmp++)
|
177
|
+
c += escape(c, NUM2INT(*tmp));
|
178
|
+
|
179
|
+
*c = '\0';
|
180
|
+
return rb_str_new(s, s_len);
|
181
|
+
}
|
182
|
+
|
183
|
+
void Init_fast_xs(void)
|
184
|
+
{
|
185
|
+
assert(cp_1252[159 - 128] == 376); /* just in case I skipped a line */
|
186
|
+
|
187
|
+
unpack_id = rb_intern("unpack");
|
188
|
+
U_fmt = rb_str_new("U*", 2);
|
189
|
+
C_fmt = rb_str_new("C*", 2);
|
190
|
+
rb_global_variable(&U_fmt);
|
191
|
+
rb_global_variable(&C_fmt);
|
192
|
+
|
193
|
+
rb_define_method(rb_cString, "fast_xs", fast_xs, 0);
|
194
|
+
}
|
@@ -0,0 +1,76 @@
|
|
1
|
+
%%{
|
2
|
+
|
3
|
+
machine hpricot_common;
|
4
|
+
|
5
|
+
#
|
6
|
+
# HTML tokens
|
7
|
+
# (a blatant rip from HTree)
|
8
|
+
#
|
9
|
+
newline = '\n' @{curline += 1;} ;
|
10
|
+
NameChar = [\-A-Za-z0-9._:?] ;
|
11
|
+
Name = [A-Za-z_:] NameChar* ;
|
12
|
+
StartComment = "<!--" ;
|
13
|
+
EndComment = "-->" ;
|
14
|
+
StartCdata = "<![CDATA[" ;
|
15
|
+
EndCdata = "]]>" ;
|
16
|
+
|
17
|
+
NameCap = Name >_tag %tag;
|
18
|
+
NameAttr = NameChar+ >_akey %akey ;
|
19
|
+
Q1Char = ( "\\\'" | [^'] ) ;
|
20
|
+
Q1Attr = Q1Char* >_aval %aval ;
|
21
|
+
Q2Char = ( "\\\"" | [^"] ) ;
|
22
|
+
Q2Attr = Q2Char* >_aval %aval ;
|
23
|
+
UnqAttr = ( space >_aval | [^ \t\r\n<>"'] >_aval [^ \t\r\n<>]* %aunq ) ;
|
24
|
+
Nmtoken = NameChar+ >_akey %akey ;
|
25
|
+
|
26
|
+
Attr = NameAttr space* "=" space* ('"' Q2Attr '"' | "'" Q1Attr "'" | UnqAttr space+ ) space* ;
|
27
|
+
AttrEnd = ( NameAttr space* "=" space* UnqAttr? | Nmtoken >new_attr %save_attr ) ;
|
28
|
+
AttrSet = ( Attr >new_attr %save_attr | Nmtoken >new_attr space+ %save_attr ) ;
|
29
|
+
StartTag = "<" NameCap space+ AttrSet* (AttrEnd >new_attr %save_attr)? ">" | "<" NameCap ">";
|
30
|
+
EmptyTag = "<" NameCap space+ AttrSet* (AttrEnd >new_attr %save_attr)? "/>" | "<" NameCap "/>" ;
|
31
|
+
|
32
|
+
EndTag = "</" NameCap space* ">" ;
|
33
|
+
XmlVersionNum = [a-zA-Z0-9_.:\-]+ >_aval %xmlver ;
|
34
|
+
XmlVersionInfo = space+ "version" space* "=" space* ("'" XmlVersionNum "'" | '"' XmlVersionNum '"' ) ;
|
35
|
+
XmlEncName = [A-Za-z] >_aval [A-Za-z0-9._\-]* %xmlenc ;
|
36
|
+
XmlEncodingDecl = space+ "encoding" space* "=" space* ("'" XmlEncName "'" | '"' XmlEncName '"' ) ;
|
37
|
+
XmlYesNo = ("yes" | "no") >_aval %xmlsd ;
|
38
|
+
XmlSDDecl = space+ "standalone" space* "=" space* ("'" XmlYesNo "'" | '"' XmlYesNo '"') ;
|
39
|
+
XmlDecl = "<?xml" XmlVersionInfo XmlEncodingDecl? XmlSDDecl? space* "?"? ">" ;
|
40
|
+
|
41
|
+
SystemLiteral = '"' [^"]* >_aval %sysid '"' | "'" [^']* >_aval %sysid "'" ;
|
42
|
+
PubidLiteral = '"' [\t a-zA-Z0-9\-'()+,./:=?;!*\#@$_%]* >_aval %pubid '"' |
|
43
|
+
"'" [\t a-zA-Z0-9\-'()+,./:=?;!*\#@$_%]* >_aval %pubid "'" ;
|
44
|
+
ExternalID = ( "SYSTEM" | "PUBLIC" space+ PubidLiteral ) (space+ SystemLiteral)? ;
|
45
|
+
DocType = "<!DOCTYPE" space+ NameCap (space+ ExternalID)? space* ("[" [^\]]* "]" space*)? ">" ;
|
46
|
+
StartXmlProcIns = "<?" Name >{ TEXT_PASS(); } space+ ;
|
47
|
+
EndXmlProcIns = "?"? ">" ;
|
48
|
+
|
49
|
+
html_comment := |*
|
50
|
+
EndComment @{ EBLK(comment, 3); fgoto main; };
|
51
|
+
any | newline { TEXT_PASS(); };
|
52
|
+
*|;
|
53
|
+
|
54
|
+
html_cdata := |*
|
55
|
+
EndCdata @{ EBLK(cdata, 3); fgoto main; };
|
56
|
+
any | newline { TEXT_PASS(); };
|
57
|
+
*|;
|
58
|
+
|
59
|
+
html_procins := |*
|
60
|
+
EndXmlProcIns @{ EBLK(procins, 2); fgoto main; };
|
61
|
+
any | newline { TEXT_PASS(); };
|
62
|
+
*|;
|
63
|
+
|
64
|
+
main := |*
|
65
|
+
XmlDecl >newEle { ELE(xmldecl); };
|
66
|
+
DocType >newEle { ELE(doctype); };
|
67
|
+
StartXmlProcIns >newEle { fgoto html_procins; };
|
68
|
+
StartTag >newEle { ELE(stag); };
|
69
|
+
EndTag >newEle { ELE(etag); };
|
70
|
+
EmptyTag >newEle { ELE(emptytag); };
|
71
|
+
StartComment >newEle { fgoto html_comment; };
|
72
|
+
StartCdata >newEle { fgoto html_cdata; };
|
73
|
+
any | newline { TEXT_PASS(); };
|
74
|
+
*|;
|
75
|
+
|
76
|
+
}%%;
|
@@ -0,0 +1,79 @@
|
|
1
|
+
/*
|
2
|
+
* hpricot_scan.h
|
3
|
+
*
|
4
|
+
* $Author: why $
|
5
|
+
* $Date: 2006-05-08 22:03:50 -0600 (Mon, 08 May 2006) $
|
6
|
+
*
|
7
|
+
* Copyright (C) 2006 why the lucky stiff
|
8
|
+
* You can redistribute it and/or modify it under the same terms as Ruby.
|
9
|
+
*/
|
10
|
+
|
11
|
+
#ifndef hpricot_scan_h
|
12
|
+
#define hpricot_scan_h
|
13
|
+
|
14
|
+
#include <sys/types.h>
|
15
|
+
|
16
|
+
#if defined(_WIN32)
|
17
|
+
#include <stddef.h>
|
18
|
+
#endif
|
19
|
+
|
20
|
+
/*
|
21
|
+
* Memory Allocation
|
22
|
+
*/
|
23
|
+
#if defined(HAVE_ALLOCA_H) && !defined(__GNUC__)
|
24
|
+
#include <alloca.h>
|
25
|
+
#endif
|
26
|
+
|
27
|
+
#ifndef NULL
|
28
|
+
# define NULL (void *)0
|
29
|
+
#endif
|
30
|
+
|
31
|
+
#define BUFSIZE 16384
|
32
|
+
|
33
|
+
#define S_ALLOC_N(type,n) (type*)malloc(sizeof(type)*(n))
|
34
|
+
#define S_ALLOC(type) (type*)malloc(sizeof(type))
|
35
|
+
#define S_REALLOC_N(var,type,n) (var)=(type*)realloc((char*)(var),sizeof(type)*(n))
|
36
|
+
#define S_FREE(n) free(n); n = NULL;
|
37
|
+
|
38
|
+
#define S_ALLOCA_N(type,n) (type*)alloca(sizeof(type)*(n))
|
39
|
+
|
40
|
+
#define S_MEMZERO(p,type,n) memset((p), 0, sizeof(type)*(n))
|
41
|
+
#define S_MEMCPY(p1,p2,type,n) memcpy((p1), (p2), sizeof(type)*(n))
|
42
|
+
#define S_MEMMOVE(p1,p2,type,n) memmove((p1), (p2), sizeof(type)*(n))
|
43
|
+
#define S_MEMCMP(p1,p2,type,n) memcmp((p1), (p2), sizeof(type)*(n))
|
44
|
+
|
45
|
+
typedef struct {
|
46
|
+
void *name;
|
47
|
+
void *attributes;
|
48
|
+
} hpricot_element;
|
49
|
+
|
50
|
+
typedef void (*hpricot_element_cb)(void *data, hpricot_element *token);
|
51
|
+
|
52
|
+
typedef struct hpricot_scan {
|
53
|
+
int lineno;
|
54
|
+
int cs;
|
55
|
+
size_t nread;
|
56
|
+
size_t mark;
|
57
|
+
|
58
|
+
void *data;
|
59
|
+
|
60
|
+
hpricot_element_cb xmldecl;
|
61
|
+
hpricot_element_cb doctype;
|
62
|
+
hpricot_element_cb xmlprocins;
|
63
|
+
hpricot_element_cb starttag;
|
64
|
+
hpricot_element_cb endtag;
|
65
|
+
hpricot_element_cb emptytag;
|
66
|
+
hpricot_element_cb comment;
|
67
|
+
hpricot_element_cb cdata;
|
68
|
+
|
69
|
+
} http_scan;
|
70
|
+
|
71
|
+
// int hpricot_scan_init(hpricot_scan *scan);
|
72
|
+
// int hpricot_scan_finish(hpricot_scan *scan);
|
73
|
+
// size_t hpricot_scan_execute(hpricot_scan *scan, const char *data, size_t len, size_t off);
|
74
|
+
// int hpricot_scan_has_error(hpricot_scan *scan);
|
75
|
+
// int hpricot_scan_is_finished(hpricot_scan *scan);
|
76
|
+
//
|
77
|
+
// #define hpricot_scan_nread(scan) (scan)->nread
|
78
|
+
|
79
|
+
#endif
|