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
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
|
#include <string>
#include <cstdio>
#include <cstdlib>
#include <iostream>
#include <fstream>
#include "CharsetConverter.h"
#include "Uri.h"
#include "ParserDom.h"
#include "utils.h"
using namespace std;
using namespace htmlcxx;
#define myassert(x) \
do {\
if(!(x)) {\
fprintf(stderr, "Test at %s:%d failed!\n", __FILE__, __LINE__);\
exit(1);\
}\
} while(0)
bool my_tree_compare(tree<HTML::Node>::iterator begin, tree<HTML::Node>::iterator end, tree<HTML::Node>::iterator ref)
{
tree<HTML::Node>::iterator it(begin);
while (it != end && ref != end)
{
if (it.number_of_children() != ref.number_of_children())
return false;
if (it->text() != ref->text())
return false;
++it;
++ref;
}
return true;
}
class HtmlTest {
public:
bool parse() {
cerr << "Parsing some html... ";
tree<HTML::Node> tr;
string html = "<head></head><body>\n\n\n\n<center>\n<table width=\"600\">\n<tbody><tr>\n<td width=\"120\"><a href=\"/index.html\"><img src=\"/adt-SUA/images/ADT_LOGO.gif\" alt=\"adt logo\" align=\"middle\" border=\"0\"></a></td>\n<td width=\"480\"><font size=\"+2\" face=\"helvetica,arial\"><b>Australian Digital Theses Program<br></b></font></td>\n</tr>\n</tbody></table>\n</center>\n<center>\n</center>\n</body>";
HTML::ParserDom parser;
parser.parse(html);
tr = parser.getTree();
cerr << tr << endl;
cerr << " ok" << endl;
return true;
}
bool string_manip() {
string root_link = "http://www.akwan.com.br/teste/acton.asp?q=atletico";
string root_link2 = "http://answerbook.ime.usp.br:8888/ab2";
string link1 = "../a.html";
string link2 = "//b.html";
string link3 = "serviço.html";
string link4 = "./d/c.html";
string link5 = "http://www.fadazan.com.br/../../../../../Download/teste/../jacobmacanhan,%203276.jpg";
string link6 = "search?q=galo";
string link7 = "http://casadebruxa.com.br/anuncio/../banner/vai.asp?id=21&url=http://www.clickdirect.com.br";
string link8 = "/ab2/Help_C/ONLINEACCESS/@Ab2HelpView/idmatch(help-library-info)";
string link9 = "/ab2/coll.67.3/@Ab2CollView?";
string link10 = "http://www.a.com.br";
string link11 = "'http://www.b.com.br";
string link12 = "?q=mineiro";
string entities = "nos somos do clube atletico mineiro á á brasil &teste; ãä á â &end ";
string comments = "hello <!-- world --> brazil";
string multiblank = " 1 2 3\r\n 4 5 \r\n 6 \n";
string justblank = " \r\n \r\n \n";
string nonblank = "dsadasdada";
myassert(HTML::strip_comments(comments) == "hello brazil");
myassert(HTML::single_blank(multiblank) == "1 2 3 4 5 6");
myassert(HTML::single_blank(justblank) == "");
myassert(HTML::single_blank(nonblank) == nonblank);
myassert(HTML::decode_entities(entities) == "nos somos do clube atletico mineiro brasil &teste; á &end ");
myassert(HTML::convert_link(link1, root_link) == "http://www.akwan.com.br/a.html");
myassert(HTML::convert_link(link2, root_link) == "http://www.akwan.com.br/b.html");
myassert(HTML::convert_link(link3, root_link) == "http://www.akwan.com.br/teste/servio.html");
myassert(HTML::convert_link(link4, root_link) == "http://www.akwan.com.br/teste/d/c.html");
myassert(HTML::convert_link(link5, root_link) == "http://www.fadazan.com.br/Download/jacobmacanhan,%203276.jpg");
myassert(HTML::convert_link(link6, root_link) == "http://www.akwan.com.br/teste/search?q=galo");
myassert(HTML::convert_link(link7, root_link) == "http://casadebruxa.com.br/banner/vai.asp?id=21&url=http://www.clickdirect.com.br");
myassert(HTML::convert_link(link8, root_link2) == "http://answerbook.ime.usp.br:8888/ab2/Help_C/ONLINEACCESS/@Ab2HelpView/idmatch(help-library-info)");
myassert(HTML::convert_link(link9, root_link2) == "http://answerbook.ime.usp.br:8888/ab2/coll.67.3/@Ab2CollView?");
myassert(HTML::convert_link(link10, root_link2) == "http://www.a.com.br/");
myassert(HTML::convert_link(link11, root_link) == "http://www.akwan.com.br/teste/'http:/www.b.com.br");
myassert(HTML::convert_link(link12, root_link) == "http://www.akwan.com.br/teste/acton.asp?q=mineiro");
Uri root(root_link);
Uri fragment("#top");
Uri result(fragment.absolute(root));
myassert(result.unparse() == "http://www.akwan.com.br/teste/acton.asp?q=atletico#top");
return true;
}
};
class TagInitTest
{
public:
void test(void)
{
string html("<html><head><script language=javascript>if (0 < 2) saida = 1;</script></head></html>");
tree<HTML::Node> reference;
HTML::Node n;
reference.clear();
tree<HTML::Node>::iterator current = reference.begin();
n.offset(0);
n.length(html.size());
n.isTag(true);
n.isComment(false);
current = reference.insert(current,n);
n.offset(0);
n.length(html.size());
n.isTag(true);
n.isComment(false);
n.text("<html>");
n.tagName("html");
n.closingText("</html>");
current = reference.append_child(current,n);
n.offset(6);
n.length(71);
n.isTag(true);
n.isComment(false);
n.text("<head>");
n.tagName("head");
n.closingText("</head>");
current = reference.append_child(current,n);
n.offset(12);
n.length(58);
n.isTag(true);
n.isComment(false);
n.text("<script language=javascript>");
n.tagName("script");
n.closingText("</script>");
current = reference.append_child(current,n);
n.offset(40);
n.length(21);
n.isTag(false);
n.isComment(false);
n.text("if (0 < 2) saida = 1;");
n.tagName("if (0 < 2) saida = 1;");
n.closingText("");
current = reference.append_child(current,n);
tree<HTML::Node> tr;
HTML::ParserDom parser;
parser.parse(html);
tr = parser.getTree();
// cerr << reference << endl;
// cerr << tr << endl;
myassert(my_tree_compare(tr.begin(), tr.end(), reference.begin()));
}
};
class ParseAttrTest
{
public:
bool test()
{
string html("<a hRef=\"teste.htm\" attr3=\"http://www.caveofpain.kit.net/pati_10_(piercing).jpg \"target=\"_blank\" attr2=\" none \"centeR attr1='ComiDa>");
tree<HTML::Node> t;
HTML::ParserDom parser;
parser.parse(html);
t = parser.getTree();
tree<HTML::Node>::iterator it = t.begin();
++it;
it->parseAttributes();
myassert(it->attribute("href").second == "teste.htm");
myassert(it->attribute("center").second == "");
myassert(it->attribute("attr1").second == "ComiDa");
myassert(it->attribute("attr2").second == "none");
myassert(it->attribute("attr3").second == "http://www.caveofpain.kit.net/pati_10_(piercing).jpg");
return true;
}
};
class CharsetTest
{
public:
void test()
{
CharsetConverter cc("UTF8", "ISO-8859-1");
myassert(cc.convert("Você é o meu visitante número") == "Voc o meu visitante nmero");
CharsetConverter cc2("ISO-8859-1", "UTF8");
myassert(cc2.convert("Voc o meu visitante nmero") == "Você é o meu visitante número");
}
};
class ParserTest : public HTML::ParserSax
{
public:
ParserTest() {}
~ParserTest() {}
protected:
virtual void foundTag(HTML::Node node, bool isEnd)
{
// cerr << "foundTag: " << node << endl;
}
virtual void foundText(HTML::Node node)
{
// cerr << "foundText: " << node << endl;
}
virtual void foundComment(HTML::Node node)
{
// cerr << "foundComment: " << node << endl;
}
};
int main(int argc, char **argv) {
HtmlTest ht;
myassert(ht.parse());
myassert(ht.string_manip());
if (argc > 1)
{
ifstream f(argv[1]);
HTML::ParserSax parser;
// parser.parse(istreambuf_iterator<char>(f), istreambuf_iterator<char>());
// tree<HTML::Node> t = parser.getTree();
// cerr << t << endl;
}
TagInitTest test2;
test2.test();
ParseAttrTest test3;
test3.test();
CharsetTest test4;
test4.test();
return 0;
}
|
