| OLD | NEW |
|---|
| (Empty) | |
| 1 // Copyright 2014 The Chromium Authors. All rights reserved. |
| 2 // Use of this source code is governed by a BSD-style license that can be |
| 3 // found in the LICENSE file. |
| 4 |
| 5 package com.dom_distiller.client; |
| 6 |
| 7 import com.google.gwt.dom.client.Document; |
| 8 import com.google.gwt.dom.client.Element; |
| 9 import com.google.gwt.dom.client.ImageElement; |
| 10 import com.google.gwt.dom.client.MetaElement; |
| 11 import com.google.gwt.dom.client.NodeList; |
| 12 |
| 13 import com.google.gwt.junit.client.GWTTestCase; |
| 14 |
| 15 public class SchemaOrgParserTest extends GWTTestCase { |
| 16 @Override |
| 17 public String getModuleName() { |
| 18 return "com.dom_distiller.DomDistillerJUnit"; |
| 19 } |
| 20 |
| 21 public void testImageWithEmbeddedPublisher() { |
| 22 Element rootDiv = TestUtil.createDiv(0); |
| 23 setItemScopeAndType(rootDiv, "ImageObject"); |
| 24 mBody.appendChild(rootDiv); |
| 25 |
| 26 String expectedTitle = "Testcase for IMAGE"; |
| 27 Element h = TestUtil.createHeading(1, expectedTitle); |
| 28 setItemProp(h, "headline"); |
| 29 rootDiv.appendChild(h); |
| 30 |
| 31 String expectedDescription = "Testing IMAGE with embedded publisher"; |
| 32 h = TestUtil.createHeading(2, expectedDescription); |
| 33 setItemProp(h, "description"); |
| 34 rootDiv.appendChild(h); |
| 35 |
| 36 // This should extract the "href" attribute of the <a> tag. |
| 37 String expectedUrl = "http://test_image_with_embedded_item.html"; |
| 38 Element link = TestUtil.createAnchor(expectedUrl, "test results"); |
| 39 setItemProp(link, "contentUrl"); |
| 40 rootDiv.appendChild(link); |
| 41 |
| 42 Element div = TestUtil.createDiv(1); |
| 43 setItemProp(div, "publisher"); |
| 44 setItemScopeAndType(div, "Organization"); |
| 45 div.appendChild(TestUtil.createText("Publisher: ")); |
| 46 String expectedPublisher = "Whatever Image Incorporated"; |
| 47 Element span = TestUtil.createSpan(expectedPublisher); |
| 48 setItemProp(span, "name"); |
| 49 div.appendChild(span); |
| 50 rootDiv.appendChild(div); |
| 51 |
| 52 div = TestUtil.createDiv(2); |
| 53 String expectedCopyrightYear = "1999-2022"; |
| 54 span = TestUtil.createSpan(expectedCopyrightYear); |
| 55 setItemProp(span, "copyrightYear"); |
| 56 div.appendChild(span); |
| 57 |
| 58 String expectedCopyrightHolder = "Whoever Image Copyrighted"; |
| 59 span = TestUtil.createSpan(expectedCopyrightHolder); |
| 60 setItemProp(span, "copyrightHolder"); |
| 61 div.appendChild(span); |
| 62 rootDiv.appendChild(div); |
| 63 |
| 64 String expectedFormat = "jpeg"; |
| 65 span = TestUtil.createSpan(expectedFormat); |
| 66 setItemProp(span, "encodingFormat"); |
| 67 rootDiv.appendChild(span); |
| 68 |
| 69 String expectedCaption = "A test for IMAGE with embedded publisher"; |
| 70 span = TestUtil.createSpan(expectedCaption); |
| 71 setItemProp(span, "caption"); |
| 72 rootDiv.appendChild(span); |
| 73 |
| 74 // This should extract the "content" attribute of the <meta> tag. |
| 75 Element meta = TestUtil.createMetaName("no_name", "true"); |
| 76 setItemProp(meta, "representativeOfPage"); |
| 77 rootDiv.appendChild(meta); |
| 78 |
| 79 meta = TestUtil.createMetaName("no_name", "600"); |
| 80 setItemProp(meta, "width"); |
| 81 rootDiv.appendChild(meta); |
| 82 |
| 83 meta = TestUtil.createMetaName("no_name", "400"); |
| 84 setItemProp(meta, "height"); |
| 85 rootDiv.appendChild(meta); |
| 86 |
| 87 SchemaOrgParser parser = new SchemaOrgParser(mRoot); |
| 88 assertEquals("IMAGE", parser.getType()); |
| 89 assertEquals(expectedTitle, parser.getTitle()); |
| 90 assertEquals(expectedDescription, parser.getDescription()); |
| 91 assertEquals("", parser.getUrl()); |
| 92 assertEquals(expectedPublisher, parser.getPublisher()); |
| 93 assertEquals(null, parser.getArticle()); |
| 94 assertEquals("", parser.getAuthor()); |
| 95 assertEquals( |
| 96 "Copyright " + expectedCopyrightYear + " " + expectedCopyrightHolder
, |
| 97 parser.getCopyright()); |
| 98 MarkupParser.Image[] images = parser.getImages(); |
| 99 assertEquals(1, images.length); |
| 100 MarkupParser.Image image = images[0]; |
| 101 assertEquals(expectedUrl, image.image); |
| 102 assertEquals(expectedUrl, image.url); |
| 103 assertEquals(null, image.secureUrl); |
| 104 assertEquals(expectedFormat, image.type); |
| 105 assertEquals(expectedCaption, image.caption); |
| 106 assertEquals(600, image.width); |
| 107 assertEquals(400, image.height); |
| 108 } |
| 109 |
| 110 public void test2Images() { |
| 111 Element rootDiv = TestUtil.createDiv(0); |
| 112 setItemScopeAndType(rootDiv, "ImageObject"); |
| 113 mBody.appendChild(rootDiv); |
| 114 |
| 115 String expectedTitle1 = "Testcase for 1st IMAGE"; |
| 116 Element h = TestUtil.createHeading(1, expectedTitle1); |
| 117 setItemProp(h, "headline"); |
| 118 rootDiv.appendChild(h); |
| 119 |
| 120 String expectedDescription1 = "Testing 1st IMAGE"; |
| 121 h = TestUtil.createHeading(2, expectedDescription1); |
| 122 setItemProp(h, "description"); |
| 123 rootDiv.appendChild(h); |
| 124 |
| 125 // This should extract the "href" attribute of the <a> tag. |
| 126 String expectedUrl1 = "http://test_1st image.html"; |
| 127 Element link = TestUtil.createAnchor(expectedUrl1, "1st test results"); |
| 128 setItemProp(link, "contentUrl"); |
| 129 rootDiv.appendChild(link); |
| 130 |
| 131 String expectedPublisher1 = "Whatever 1st Image Incorporated"; |
| 132 Element div = TestUtil.createDiv(1); |
| 133 setItemProp(div, "publisher"); |
| 134 div.setInnerHTML(expectedPublisher1); |
| 135 rootDiv.appendChild(div); |
| 136 |
| 137 div = TestUtil.createDiv(2); |
| 138 String expectedCopyrightYear1 = "1000-1999"; |
| 139 Element span = TestUtil.createSpan(expectedCopyrightYear1); |
| 140 setItemProp(span, "copyrightYear"); |
| 141 div.appendChild(span); |
| 142 |
| 143 String expectedCopyrightHolder1 = "Whoever 1st Image Copyrighted"; |
| 144 span = TestUtil.createSpan(expectedCopyrightHolder1); |
| 145 setItemProp(span, "copyrightHolder"); |
| 146 div.appendChild(span); |
| 147 rootDiv.appendChild(div); |
| 148 |
| 149 String expectedFormat1 = "jpeg"; |
| 150 span = TestUtil.createSpan(expectedFormat1); |
| 151 setItemProp(span, "encodingFormat"); |
| 152 rootDiv.appendChild(span); |
| 153 |
| 154 String expectedCaption1 = "A test for 1st IMAGE"; |
| 155 span = TestUtil.createSpan(expectedCaption1); |
| 156 setItemProp(span, "caption"); |
| 157 rootDiv.appendChild(span); |
| 158 |
| 159 // This should extract the "content" attribute of the <meta> tag. |
| 160 Element meta = TestUtil.createMetaName("no_name", "false"); |
| 161 setItemProp(meta, "representativeOfPage"); |
| 162 rootDiv.appendChild(meta); |
| 163 |
| 164 meta = TestUtil.createMetaName("no_name", "400"); |
| 165 setItemProp(meta, "width"); |
| 166 rootDiv.appendChild(meta); |
| 167 |
| 168 meta = TestUtil.createMetaName("no_name", "300"); |
| 169 setItemProp(meta, "height"); |
| 170 rootDiv.appendChild(meta); |
| 171 |
| 172 rootDiv = TestUtil.createDiv(10); |
| 173 setItemScopeAndType(rootDiv, "ImageObject"); |
| 174 mBody.appendChild(rootDiv); |
| 175 |
| 176 String expectedTitle2 = "Testcase for 2nd IMAGE"; |
| 177 h = TestUtil.createHeading(2, expectedTitle2); |
| 178 setItemProp(h, "headline"); |
| 179 rootDiv.appendChild(h); |
| 180 |
| 181 String expectedDescription2 = "Testing 2nd IMAGE"; |
| 182 h = TestUtil.createHeading(2, expectedDescription2); |
| 183 setItemProp(h, "description"); |
| 184 rootDiv.appendChild(h); |
| 185 |
| 186 // This should extract the "href" attribute of the <a> tag. |
| 187 String expectedUrl2 = "http://test_2nd mage.html"; |
| 188 link = TestUtil.createAnchor(expectedUrl2, "2nd test results"); |
| 189 setItemProp(link, "contentUrl"); |
| 190 rootDiv.appendChild(link); |
| 191 |
| 192 String expectedPublisher2 = "Whatever 2nd Image Incorporated"; |
| 193 div = TestUtil.createDiv(11); |
| 194 setItemProp(div, "publisher"); |
| 195 div.setInnerHTML(expectedPublisher2); |
| 196 rootDiv.appendChild(div); |
| 197 |
| 198 div = TestUtil.createDiv(12); |
| 199 String expectedCopyrightYear2 = "2000-2999"; |
| 200 span = TestUtil.createSpan(expectedCopyrightYear2); |
| 201 setItemProp(span, "copyrightYear"); |
| 202 div.appendChild(span); |
| 203 |
| 204 String expectedCopyrightHolder2 = "Whoever 2nd Image Copyrighted"; |
| 205 span = TestUtil.createSpan(expectedCopyrightHolder2); |
| 206 setItemProp(span, "copyrightHolder"); |
| 207 div.appendChild(span); |
| 208 rootDiv.appendChild(div); |
| 209 |
| 210 String expectedFormat2 = "gif"; |
| 211 span = TestUtil.createSpan(expectedFormat2); |
| 212 setItemProp(span, "encodingFormat"); |
| 213 rootDiv.appendChild(span); |
| 214 |
| 215 String expectedCaption2 = "A test for 2nd IMAGE"; |
| 216 span = TestUtil.createSpan(expectedCaption2); |
| 217 setItemProp(span, "caption"); |
| 218 rootDiv.appendChild(span); |
| 219 |
| 220 // This should extract the "content" attribute of the <meta> tag. |
| 221 meta = TestUtil.createMetaName("no_name", "true"); |
| 222 setItemProp(meta, "representativeOfPage"); |
| 223 rootDiv.appendChild(meta); |
| 224 |
| 225 meta = TestUtil.createMetaName("no_name", "1000"); |
| 226 setItemProp(meta, "width"); |
| 227 rootDiv.appendChild(meta); |
| 228 |
| 229 meta = TestUtil.createMetaName("no_name", "600"); |
| 230 setItemProp(meta, "height"); |
| 231 rootDiv.appendChild(meta); |
| 232 |
| 233 SchemaOrgParser parser = new SchemaOrgParser(mRoot); |
| 234 // The basic properties of Thing should be from the first image that was |
| 235 // inserted. |
| 236 assertEquals("IMAGE", parser.getType()); |
| 237 assertEquals(expectedTitle1, parser.getTitle()); |
| 238 assertEquals(expectedDescription1, parser.getDescription()); |
| 239 assertEquals("", parser.getUrl()); |
| 240 assertEquals(expectedPublisher1, parser.getPublisher()); |
| 241 assertEquals(null, parser.getArticle()); |
| 242 assertEquals("", parser.getAuthor()); |
| 243 assertEquals("Copyright " + expectedCopyrightYear1 + " " + expectedCopyr
ightHolder1, |
| 244 parser.getCopyright()); |
| 245 |
| 246 MarkupParser.Image[] images = parser.getImages(); |
| 247 assertEquals(2, images.length); |
| 248 // The 2nd image that was inserted is representative of page, so the |
| 249 // images should be swapped in |images|. |
| 250 MarkupParser.Image image = images[0]; |
| 251 assertEquals(expectedUrl2, image.image); |
| 252 assertEquals(expectedUrl2, image.url); |
| 253 assertEquals(null, image.secureUrl); |
| 254 assertEquals(expectedFormat2, image.type); |
| 255 assertEquals(expectedCaption2, image.caption); |
| 256 assertEquals(1000, image.width); |
| 257 assertEquals(600, image.height); |
| 258 image = images[1]; |
| 259 assertEquals(expectedUrl1, image.image); |
| 260 assertEquals(expectedUrl1, image.url); |
| 261 assertEquals(null, image.secureUrl); |
| 262 assertEquals(expectedFormat1, image.type); |
| 263 assertEquals(expectedCaption1, image.caption); |
| 264 assertEquals(400, image.width); |
| 265 assertEquals(300, image.height); |
| 266 } |
| 267 |
| 268 public void testArticleWithEmbeddedAuthorAndPublisher() { |
| 269 Element rootDiv = TestUtil.createDiv(0); |
| 270 setItemScopeAndType(rootDiv, "Article"); |
| 271 mBody.appendChild(rootDiv); |
| 272 |
| 273 String expectedTitle = "Testcase for ARTICLE"; |
| 274 Element h = TestUtil.createHeading(1, expectedTitle); |
| 275 setItemProp(h, "headline"); |
| 276 rootDiv.appendChild(h); |
| 277 |
| 278 String expectedDescription = "Testing ARTICLE with embedded author and p
ublisher"; |
| 279 h = TestUtil.createHeading(2, expectedDescription); |
| 280 setItemProp(h, "description"); |
| 281 rootDiv.appendChild(h); |
| 282 |
| 283 // This should extract the "href" attribute of the <a> tag. |
| 284 String expectedUrl = "http://test_article_with_embedded_items.html"; |
| 285 Element link = TestUtil.createAnchor(expectedUrl, "test results"); |
| 286 setItemProp(link, "url"); |
| 287 rootDiv.appendChild(link); |
| 288 |
| 289 // This should extract the "src" attribute of the <image> tag. |
| 290 String expectedImage = "http://test_article_with_embedded_items.jpeg"; |
| 291 ImageElement image = TestUtil.createImage(); |
| 292 image.setSrc(expectedImage); |
| 293 setItemProp(image, "image"); |
| 294 rootDiv.appendChild(image); |
| 295 |
| 296 Element div = TestUtil.createDiv(1); |
| 297 setItemProp(div, "author"); |
| 298 setItemScopeAndType(div, "Person"); |
| 299 div.appendChild(TestUtil.createText("Author: ")); |
| 300 String expectedAuthor = "Whoever authored"; |
| 301 Element span = TestUtil.createSpan(expectedAuthor); |
| 302 setItemProp(span, "name"); |
| 303 div.appendChild(span); |
| 304 rootDiv.appendChild(div); |
| 305 |
| 306 div = TestUtil.createDiv(2); |
| 307 setItemProp(div, "publisher"); |
| 308 setItemScopeAndType(div, "Organization"); |
| 309 div.appendChild(TestUtil.createText("Publisher: ")); |
| 310 String expectedPublisher = "Whatever Article Incorporated"; |
| 311 span = TestUtil.createSpan(expectedPublisher); |
| 312 setItemProp(span, "name"); |
| 313 div.appendChild(span); |
| 314 rootDiv.appendChild(div); |
| 315 |
| 316 String expectedDatePublished = "April 15, 2014"; |
| 317 span = TestUtil.createSpan(expectedDatePublished); |
| 318 setItemProp(span, "datePublished"); |
| 319 rootDiv.appendChild(span); |
| 320 |
| 321 // This should extract the "datetime" attribute of the <time> tag. |
| 322 String expectedTimeModified = "2014-04-16T23:59"; |
| 323 Element time = Document.get().createElement("time"); |
| 324 time.setInnerHTML("April 16, 2014 11:59pm"); |
| 325 time.setAttribute("datetime", expectedTimeModified); |
| 326 setItemProp(time, "dateModified"); |
| 327 rootDiv.appendChild(time); |
| 328 |
| 329 String expectedCopyrightYear = "2000-2014"; |
| 330 span = TestUtil.createSpan(expectedCopyrightYear); |
| 331 setItemProp(span, "copyrightYear"); |
| 332 rootDiv.appendChild(span); |
| 333 |
| 334 String expectedCopyrightHolder = "Whoever Article Copyrighted"; |
| 335 span = TestUtil.createSpan(expectedCopyrightHolder); |
| 336 setItemProp(span, "copyrightHolder"); |
| 337 rootDiv.appendChild(span); |
| 338 |
| 339 String expectedSection = "Romance thriller"; |
| 340 span = TestUtil.createSpan(expectedSection); |
| 341 setItemProp(span, "articleSection"); |
| 342 rootDiv.appendChild(span); |
| 343 |
| 344 SchemaOrgParser parser = new SchemaOrgParser(mRoot); |
| 345 assertEquals("ARTICLE", parser.getType()); |
| 346 assertEquals(expectedTitle, parser.getTitle()); |
| 347 assertEquals(expectedDescription, parser.getDescription()); |
| 348 assertEquals(expectedUrl, parser.getUrl()); |
| 349 assertEquals(expectedAuthor, parser.getAuthor()); |
| 350 assertEquals(expectedPublisher, parser.getPublisher()); |
| 351 assertEquals( |
| 352 "Copyright " + expectedCopyrightYear + " " + expectedCopyrightHolder
, |
| 353 parser.getCopyright()); |
| 354 MarkupParser.Image[] images = parser.getImages(); |
| 355 assertEquals(1, images.length); |
| 356 assertEquals(expectedImage, images[0].image); |
| 357 assertEquals(expectedImage, images[0].url); |
| 358 MarkupParser.Article article = parser.getArticle(); |
| 359 assertEquals(expectedDatePublished, article.publishedTime); |
| 360 assertEquals(expectedTimeModified, article.modifiedTime); |
| 361 assertEquals(null, article.expirationTime); |
| 362 assertEquals(expectedSection, article.section); |
| 363 assertEquals(1, article.authors.length); |
| 364 assertEquals(expectedAuthor, article.authors[0]); |
| 365 } |
| 366 |
| 367 public void testItemscopeInHTMLTag() { |
| 368 setItemScopeAndType(mRoot, "Article"); |
| 369 |
| 370 String expectedTitle = "Testcase for ItemScope in HTML tag"; |
| 371 Element h = TestUtil.createHeading(1, expectedTitle); |
| 372 setItemProp(h, "headline"); |
| 373 mBody.appendChild(h); |
| 374 |
| 375 SchemaOrgParser parser = new SchemaOrgParser(mRoot); |
| 376 assertEquals("ARTICLE", parser.getType()); |
| 377 assertEquals(expectedTitle, parser.getTitle()); |
| 378 assertTrue(parser.getArticle() != null); |
| 379 |
| 380 // Remove "itemscope" and "itemtype" attributes in <html> tag, so that |
| 381 // other testcases won't be affected. |
| 382 mRoot.removeAttribute("ITEMSCOPE"); |
| 383 mRoot.removeAttribute("ITEMTYPE"); |
| 384 } |
| 385 |
| 386 @Override |
| 387 protected void gwtSetUp() throws Exception { |
| 388 // Get root element. |
| 389 mRoot = Document.get().getDocumentElement(); |
| 390 |
| 391 // Get <body> element. |
| 392 NodeList<Element> bodies = mRoot.getElementsByTagName("BODY"); |
| 393 if (bodies.getLength() != 1) |
| 394 throw new Exception("There shouldn't be more than 1 <body> tag"); |
| 395 mBody = bodies.getItem(0); |
| 396 |
| 397 // Remove all meta tags, otherwise a testcase may run with the meta tags |
| 398 // set up in a previous testcase, resulting in unexpected results. |
| 399 NodeList<Element> allMeta = mRoot.getElementsByTagName("META"); |
| 400 for (int i = allMeta.getLength() - 1; i >= 0; i--) { |
| 401 allMeta.getItem(i).removeFromParent(); |
| 402 } |
| 403 |
| 404 // Remove all div tags, otherwise a testcase may run with the div tags |
| 405 // set up in a previous testcase, resulting in unexpected results. |
| 406 NodeList<Element> allDiv = mRoot.getElementsByTagName("DIV"); |
| 407 for (int i = allDiv.getLength() - 1; i >= 0; i--) { |
| 408 allDiv.getItem(i).removeFromParent(); |
| 409 } |
| 410 } |
| 411 |
| 412 private void setItemScopeAndType(Element e, String type) { |
| 413 e.setAttribute("ITEMSCOPE", ""); |
| 414 e.setAttribute("ITEMTYPE", "http://schema.org/" + type); |
| 415 } |
| 416 |
| 417 private void setItemProp(Element e, String name) { |
| 418 e.setAttribute("itemprop", name); |
| 419 } |
| 420 |
| 421 private Element mRoot; |
| 422 private Element mBody; |
| 423 } |
| OLD | NEW |
|---|
Chromium Code Reviews
Issue 240073007:
recognize and parse Schema.org Markup (Closed)
Base URL: https://code.google.com/p/dom-distiller/@master