|
1
27 package org.htmlparser.tests.filterTests;
28
29 import org.htmlparser.Parser;
30 import org.htmlparser.Tag;
31 import org.htmlparser.filters.AndFilter;
32 import org.htmlparser.filters.CssSelectorNodeFilter;
33 import org.htmlparser.filters.HasAttributeFilter;
34 import org.htmlparser.filters.HasChildFilter;
35 import org.htmlparser.filters.NodeClassFilter;
36 import org.htmlparser.filters.NotFilter;
37 import org.htmlparser.filters.OrFilter;
38 import org.htmlparser.filters.RegexFilter;
39 import org.htmlparser.filters.StringFilter;
40 import org.htmlparser.filters.TagNameFilter;
41 import org.htmlparser.lexer.Lexer;
42 import org.htmlparser.Text;
43 import org.htmlparser.tags.BodyTag;
44 import org.htmlparser.tags.LinkTag;
45 import org.htmlparser.tests.ParserTestCase;
46 import org.htmlparser.util.NodeIterator;
47 import org.htmlparser.util.NodeList;
48 import org.htmlparser.util.ParserException;
49
50
53 public class FilterTest extends ParserTestCase
54 {
55 static
56 {
57 System.setProperty ("org.htmlparser.tests.filterTests.FilterTest", "FilterTest");
58 }
59
60 public FilterTest (String  name)
61 {
62 super (name);
63 }
64
65
68 public void testNodeClass () throws ParserException
69 {
70 String guts;
71 String html;
72 NodeList list;
73
74 guts = "<body>Now is the time for all good men..</body>";
75 html = "<html>" + guts + "</html>";
76 createParser (html);
77 list = parser.extractAllNodesThatMatch (new NodeClassFilter (BodyTag.class));
78 assertEquals ("only one element", 1, list.size ());
79 assertType ("should be BodyTag", BodyTag.class, list.elementAt (0));
80 BodyTag body = (BodyTag)list.elementAt (0);
81 assertEquals ("only one child", 1, body.getChildCount ());
82 assertSuperType ("should be Text", Text.class, body.getChildren ().elementAt (0));
83 assertStringEquals("html", guts, body.toHtml ());
84 }
85
86
87
90 public void testTagName () throws ParserException
91 {
92 String guts;
93 String html;
94 NodeList list;
95
96 guts = "<booty>Now is the time for all good men..</booty>";
97 html = "<html>" + guts + "</html>";
98 createParser (html);
99 list = parser.extractAllNodesThatMatch (new TagNameFilter ("booty"));
100 assertEquals ("only one element", 1, list.size ());
101 assertSuperType ("should be Tag", Tag.class, list.elementAt (0));
102 assertStringEquals("name", "BOOTY", ((Tag)(list.elementAt (0))).getTagName ());
103 }
104
105
108 public void testString () throws ParserException
109 {
110 String guts;
111 String html;
112 NodeList list;
113
114 guts = "<body>Now is the <a id=target><b>time</b></a> for all good <time>men</time>..</body>";
115 html = "<html>" + guts + "</html>";
116 createParser (html);
117 list = parser.extractAllNodesThatMatch (new StringFilter ("Time"));
118 assertEquals ("only one element", 1, list.size ());
119 assertSuperType ("should be String", Text.class, list.elementAt (0));
120 assertStringEquals("name", "time", ((Text)list.elementAt (0)).getText ());
121 list = parser.extractAllNodesThatMatch (new StringFilter ("Time", true));
123 assertEquals ("should be no elements", 0, list.size ());
124 }
125
126
129 public void testChild () throws ParserException
130 {
131 String guts;
132 String html;
133 NodeList list;
134
135 guts = "<body>Now is the <a id=target><b>time</b></a> for all good <a HREF=http://bongo.com>men</a>..</body>";
136 html = "<html>" + guts + "</html>";
137 createParser (html);
138 list = parser.extractAllNodesThatMatch (new HasChildFilter (new TagNameFilter ("b")));
139 assertEquals ("only one element", 1, list.size ());
140 assertType ("should be LinkTag", LinkTag.class, list.elementAt (0));
141 LinkTag link = (LinkTag)list.elementAt (0);
142 assertEquals ("three children", 3, link.getChildCount ());
143 assertSuperType ("should be TagNode", Tag.class, link.getChildren ().elementAt (0));
144 Tag tag = (Tag)link.getChildren ().elementAt (0);
145 assertStringEquals("name", "B", tag.getTagName ());
146 }
147
148
151 public void testAttribute () throws ParserException
152 {
153 String guts;
154 String html;
155 NodeList list;
156
157 guts = "<body>Now is the <a id=target><b>time</b></a> for all good <a HREF=http://bongo.com>men</a>..</body>";
158 html = "<html>" + guts + "</html>";
159 createParser (html);
160 list = parser.extractAllNodesThatMatch (new HasAttributeFilter ("id"));
161 assertEquals ("only one element", 1, list.size ());
162 assertType ("should be LinkTag", LinkTag.class, list.elementAt (0));
163 LinkTag link = (LinkTag)list.elementAt (0);
164 assertEquals ("attribute value", "target", link.getAttribute ("id"));
165 }
166
167
170 public void testAnd () throws ParserException
171 {
172 String guts;
173 String html;
174 NodeList list;
175
176 guts = "<body>Now is the <a id=one><b>time</b></a> for all good <a id=two><b>men</b></a>..</body>";
177 html = "<html>" + guts + "</html>";
178 createParser (html);
179 list = parser.extractAllNodesThatMatch (
180 new AndFilter (
181 new HasChildFilter (
182 new TagNameFilter ("b")),
183 new HasChildFilter (
184 new StringFilter ("men")))
185 );
186 assertEquals ("only one element", 1, list.size ());
187 assertType ("should be LinkTag", LinkTag.class, list.elementAt (0));
188 LinkTag link = (LinkTag)list.elementAt (0);
189 assertEquals ("attribute value", "two", link.getAttribute ("id"));
190 }
191
192
195 public void testOr () throws ParserException
196 {
197 String guts;
198 String html;
199 NodeList list;
200
201 guts = "<body>Now is the <a id=one><b>time</b></a> for <a id=two><b>all</b></a> good <a id=three><b>men</b></a>..</body>";
202 html = "<html>" + guts + "</html>";
203 createParser (html);
204 list = parser.extractAllNodesThatMatch (
205 new OrFilter (
206 new HasChildFilter (
207 new StringFilter ("time")),
208 new HasChildFilter (
209 new StringFilter ("men")))
210 );
211 assertEquals ("two elements", 2, list.size ());
212 assertType ("should be LinkTag", LinkTag.class, list.elementAt (0));
213 LinkTag link = (LinkTag)list.elementAt (0);
214 assertEquals ("attribute value", "one", link.getAttribute ("id"));
215 assertType ("should be LinkTag", LinkTag.class, list.elementAt (1));
216 link = (LinkTag)list.elementAt (1);
217 assertEquals ("attribute value", "three", link.getAttribute ("id"));
218 }
219
220
223 public void testNot () throws ParserException
224 {
225 String guts;
226 String html;
227 NodeList list;
228
229 guts = "<body>Now is the <a id=one><b>time</b></a> for <a id=two><b>all</b></a> good <a id=three><b>men</b></a>..</body>";
230 html = "<html>" + guts + "</html>";
231 createParser (html);
232 list = parser.extractAllNodesThatMatch (
233 new AndFilter (
234 new HasChildFilter (
235 new TagNameFilter ("b")),
236 new NotFilter (
237 new HasChildFilter (
238 new StringFilter ("all"))))
239 );
240 assertEquals ("two elements", 2, list.size ());
241 assertType ("should be LinkTag", LinkTag.class, list.elementAt (0));
242 LinkTag link = (LinkTag)list.elementAt (0);
243 assertEquals ("attribute value", "one", link.getAttribute ("id"));
244 assertType ("should be LinkTag", LinkTag.class, list.elementAt (1));
245 link = (LinkTag)list.elementAt (1);
246 assertEquals ("attribute value", "three", link.getAttribute ("id"));
247 }
248
249 public void testEscape() throws Exception
250 {
251 assertEquals ("douchebag", CssSelectorNodeFilter.unescape ("doucheba\\g").toString ());
252 }
253
254 public void testSelectors() throws Exception
255 {
256 String html = "<html><head><title>sample title</title></head><body inserterr=\"true\" yomama=\"false\"><h3 id=\"heading\">big </invalid>heading</h3><ul id=\"things\"><li><br word=\"broken\"/>>moocow<li><applet/>doohickey<li class=\"last\"><b class=\"item\">final<br>item</b></ul></body></html>";
257 Lexer l;
258 Parser p;
259 CssSelectorNodeFilter it;
260 NodeIterator i;
261 int count;
262
263 l = new Lexer (html);
264 p = new Parser (l);
265 it = new CssSelectorNodeFilter ("li + li");
266 count = 0;
267 for (i = p.extractAllNodesThatMatch (it).elements (); i.hasMoreNodes ();)
268 {
269 assertEquals ("tag name wrong", "LI", ((Tag)i.nextNode()).getTagName());
270 count++;
271 }
272 assertEquals ("wrong count", 2, count);
273 }
274
275
278 public void testRegularExpression () throws Exception
279 {
280 String target =
281 "\n"
282 + "\n"
283 + "Most recently, in the Western Conference final, the Flames knocked off \n"
284 + "the San Jose Sharks, the Pacific Division champions, to become the first \n"
285 + "Canadian team to reach the Stanley Cup Championship series since 1994.";
286
287 String html =
288 "<html><head><title>CBC Sports Online: NHL Playoffs</title></head>"
289 + "<body><h1>CBC SPORTS ONLINE</h1>\n"
290 + "The Calgary Flames have already defeated three NHL division winners \n"
291 + "during their improbable playoff run. If they are to hoist the Stanley \n"
292 + "Cup they'll have to go through one more. <p><table ALIGN=\"Right\" width=196 CELLPADDING=0 cellspacing=0 hspace=4> <tr><td><img SRC=\"/gfx/topstory/sports/iginla_j0524.jpg\" width=194 height=194 hspace=3 border=1><br>\n"
293 + "\n"
294 + "<font SIZE=\"1\" FACE=\"verdana,arial\">\n"
295 + "Jarome Iginla skates during the Flames' practice on Monday. Calgary takes on the Tampa Bay Lightning in the Stanley Cup finals beginning Tuesday night in Tampa\n"
296 + "</font></td></tr></table>\n"
297 + "\n"
298 + "\n"
299 + "In the post-season's first round, the Flames defeated the Vancouver \n"
300 + "Canucks, the Northwest Division winners, in seven tough games. <p>\n"
301 + "\n"
302 + "In Round 2 it was the Detroit Red Wings, who not only won the Central \n"
303 + "Division, but also boasted the NHL's best overall record during the \n"
304 + "regular season, who fell to the Flames. <p>"
305 + target
306 + "<p>\n"
307 + "\n"
308 + "Up next for the Flames is the Tampa Bay Lighting -- the runaway winners \n"
309 + "of the NHL's Southeast Division and the Eastern Conference's best team \n"
310 + "during the regular season. <p>\n"
311 + "\n"
312 + "The Lighting advanced by beating the Philadelphia Flyers in the Eastern \n"
313 + "Conference final. <p>\n"
314 + "</body></html>\n";
315 Lexer lexer;
316 Parser parser;
317 RegexFilter filter;
318 NodeIterator iterator;
319 int count;
320
321 lexer = new Lexer (html);
322 parser = new Parser (lexer);
323 filter = new RegexFilter ("(19|20)\\d\\d([- \\\\/.](0[1-9]|1[012])[- \\\\/.](0[1-9]|[12][0-9]|3[01]))?");
324 count = 0;
325 for (iterator = parser.extractAllNodesThatMatch (filter).elements (); iterator.hasMoreNodes ();)
326 {
327 assertEquals ("text wrong", target, iterator.nextNode ().toHtml ());
328 count++;
329 }
330 assertEquals ("wrong count", 1, count);
331 }
332 }
333
334
|
Popular Tags
|
Java API By Example, From Geeks To Geeks.