Package net.yacy.document.parser.html

Examples of net.yacy.document.parser.html.ImageEntry

313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
                i += putMediaInfo(prop, wordArray, i, document.getAudiolinks(), "audio", (i % 2 == 0));
                dark = (i % 2 == 0);

                final Map<MultiProtocolURI, ImageEntry> ts = document.getImages();
                final Iterator<ImageEntry> tsi = ts.values().iterator();
                ImageEntry entry;
                while (tsi.hasNext()) {
                    entry = tsi.next();
                    prop.put("viewMode_links_" + i + "_nr", i);
                    prop.put("viewMode_links_" + i + "_dark", dark ? "1" : "0");
                    prop.put("viewMode_links_" + i + "_type", "image");
                    prop.put("viewMode_links_" + i + "_text", (entry.alt().isEmpty()) ? "&nbsp;" : markup(wordArray, entry.alt()));
                    prop.put("viewMode_links_" + i + "_url", entry.url().toNormalform(false, true));
                    prop.put("viewMode_links_" + i + "_link", markup(wordArray, entry.url().toNormalform(false, true)));
                    if (entry.width() > 0 && entry.height() > 0)
                        prop.put("viewMode_links_" + i + "_attr", entry.width() + "x" + entry.height() + " Pixel");
                    else
                        prop.put("viewMode_links_" + i + "_attr", "unknown");
                    dark = !dark;
                    i++;
                }
View Full Code Here
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
        final SortedSet<ImageEntry> images = new TreeSet<ImageEntry>();
        images.addAll(document.getImages().values()); // iterates images in descending size order!
        // a measurement for the size of the images can be retrieved using the htmlFilterImageEntry.hashCode()

        final Iterator<ImageEntry> i = images.iterator();
        ImageEntry ientry;
        DigestURI url;
        String desc;
        final List<MediaSnippet> result = new ArrayList<MediaSnippet>();
        while (i.hasNext()) {
            ientry = i.next();
            url = new DigestURI(ientry.url());
            final String u = url.toString();
            if (u.indexOf(".ico") >= 0 || u.indexOf("favicon") >= 0) continue;
            if (ientry.height() > 0 && ientry.height() < 32) continue;
            if (ientry.width() > 0 && ientry.width() < 32) continue;
            desc = ientry.alt();
            final int appcount = queryhashes.size()  * 2 -
                           removeAppearanceHashes(url.toNormalform(false, false), queryhashes).size() -
                           removeAppearanceHashes(desc, queryhashes).size();
            final long ranking = Long.MAX_VALUE - (ientry.height() + 1) * (ientry.width() + 1) * (appcount + 1);
            result.add(new MediaSnippet(ContentDomain.IMAGE, url, MimeTable.url2mime(url), desc, ientry.fileSize(), ientry.width(), ientry.height(), ranking, source));
        }
        return result;
    }
View Full Code Here
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
                insertTextToWords(entry.getValue(), 99, flag_cat_hasapp, RESULT_FLAGS, true, meaningLib);
            }

            // images
            final Iterator<ImageEntry> j = document.getImages().values().iterator();
            ImageEntry ientry;
            MultiProtocolURI url;
            while (j.hasNext()) {
                ientry = j.next();
                url = ientry.url();
                if (url == null) continue;
                insertTextToWords(url.toNormalform(false, false), 99, flag_cat_hasimage, RESULT_FLAGS, false, meaningLib);
                insertTextToWords(ientry.alt(), 99, flag_cat_hasimage, RESULT_FLAGS, true, meaningLib);
            }
       
            // finally check all words for missing flag entry
            final Iterator<Map.Entry<String, Word>> k = words.entrySet().iterator();
            Word wprop;
View Full Code Here
426
427
428
429
430
431
432
433
434
435
436
                            ext = u.substring(extpos + 1).toLowerCase();
                        }
                        if (Classification.isMediaExtension(ext)) {
                            // this is not a normal anchor, its a media link
                            if (Classification.isImageExtension(ext)) {
                                ContentScraper.addImage(collectedImages, new ImageEntry(url, name, -1, -1, -1));
                            }
                            else if (Classification.isAudioExtension(ext)) this.audiolinks.put(url, name);
                            else if (Classification.isVideoExtension(ext)) this.videolinks.put(url, name);
                            else if (Classification.isApplicationExtension(ext)) this.applinks.put(url, name);
                        }
View Full Code Here
183
184
185
186
187
188
189
190
191
192
193
        final HashSet<String> languages = new HashSet<String>();
        final HashMap<MultiProtocolURI, Properties> anchors = new HashMap<MultiProtocolURI, Properties>();
        final HashMap<MultiProtocolURI, ImageEntry> images  = new HashMap<MultiProtocolURI, ImageEntry>();
        // add this image to the map of images
        String infoString = ii.info.toString();
        images.put(ii.location, new ImageEntry(location, "", ii.width, ii.height, -1));
       
        if (title == null || title.length() == 0) title = MultiProtocolURI.unescape(location.getFileName());
       
        return new Document[]{new Document(
             location,
View Full Code Here
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
                i += putMediaInfo(prop, wordArray, i, document.getAudiolinks(), "audio", (i % 2 == 0), document.getAnchors());
                dark = (i % 2 == 0);

                final Map<MultiProtocolURI, ImageEntry> ts = document.getImages();
                final Iterator<ImageEntry> tsi = ts.values().iterator();
                ImageEntry entry;
                while (tsi.hasNext()) {
                    entry = tsi.next();
                    prop.put("viewMode_links_" + i + "_nr", i);
                    prop.put("viewMode_links_" + i + "_dark", dark ? "1" : "0");
                    prop.put("viewMode_links_" + i + "_type", "image");
                    prop.put("viewMode_links_" + i + "_text", (entry.alt().isEmpty()) ? "&nbsp;" : markup(wordArray, entry.alt()));
                    prop.put("viewMode_links_" + i + "_url", entry.url().toNormalform(false, true));
                    prop.put("viewMode_links_" + i + "_link", markup(wordArray, entry.url().toNormalform(false, true)));
                    if (entry.width() > 0 && entry.height() > 0) {
                        prop.put("viewMode_links_" + i + "_rel", entry.width() + "x" + entry.height() + " Pixel");
                    } else {
                        prop.put("viewMode_links_" + i + "_rel", "");
                    }
                    prop.put("viewMode_links_" + i + "_name", "");
                    dark = !dark;
View Full Code Here
185
186
187
188
189
190
191
192
193
194
195
        final HashSet<String> languages = new HashSet<String>();
        final HashMap<MultiProtocolURI, Properties> anchors = new HashMap<MultiProtocolURI, Properties>();
        final HashMap<MultiProtocolURI, ImageEntry> images  = new HashMap<MultiProtocolURI, ImageEntry>();
        // add this image to the map of images
        final String infoString = ii.info.toString();
        images.put(ii.location, new ImageEntry(location, "", ii.width, ii.height, -1));

        if (title == null || title.length() == 0) title = MultiProtocolURI.unescape(location.getFileName());

        return new Document[]{new Document(
             location,
View Full Code Here
438
439
440
441
442
443
444
445
446
447
448
                            ext = u.substring(extpos + 1).toLowerCase();
                        }
                        if (Classification.isMediaExtension(ext)) {
                            // this is not a normal anchor, its a media link
                            if (Classification.isImageExtension(ext)) {
                                ContentScraper.addImage(collectedImages, new ImageEntry(url, name, -1, -1, -1));
                            }
                            else if (Classification.isAudioExtension(ext)) this.audiolinks.put(url, name);
                            else if (Classification.isVideoExtension(ext)) this.videolinks.put(url, name);
                            else if (Classification.isApplicationExtension(ext)) this.applinks.put(url, name);
                        }
View Full Code Here
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
                insertTextToWords(entry.getValue(), 99, flag_cat_hasapp, this.RESULT_FLAGS, true, meaningLib);
            }

            // images
            final Iterator<ImageEntry> j = document.getImages().values().iterator();
            ImageEntry ientry;
            MultiProtocolURI url;
            while (j.hasNext()) {
                ientry = j.next();
                url = ientry.url();
                if (url == null) continue;
                insertTextToWords(url.toNormalform(false, false), 99, flag_cat_hasimage, this.RESULT_FLAGS, false, meaningLib);
                insertTextToWords(ientry.alt(), 99, flag_cat_hasimage, this.RESULT_FLAGS, true, meaningLib);
            }

            // finally check all words for missing flag entry
            final Iterator<Map.Entry<String, Word>> k = this.words.entrySet().iterator();
            Word wprop;
View Full Code Here
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
        final SortedSet<ImageEntry> images = new TreeSet<ImageEntry>();
        images.addAll(document.getImages().values()); // iterates images in descending size order!
        // a measurement for the size of the images can be retrieved using the htmlFilterImageEntry.hashCode()

        final Iterator<ImageEntry> i = images.iterator();
        ImageEntry ientry;
        DigestURI url;
        String desc;
        final List<MediaSnippet> result = new ArrayList<MediaSnippet>();
        while (i.hasNext()) {
            ientry = i.next();
            url = new DigestURI(ientry.url());
            final String u = url.toString();
            if (u.indexOf(".ico",0) >= 0 || u.indexOf("favicon",0) >= 0) continue;
            if (ientry.height() > 0 && ientry.height() < 32) continue;
            if (ientry.width() > 0 && ientry.width() < 32) continue;
            desc = ientry.alt();
            final int appcount = queryhashes.size()  * 2 -
                           removeAppearanceHashes(url.toNormalform(false, false), queryhashes).size() -
                           removeAppearanceHashes(desc, queryhashes).size();
            final long ranking = Long.MAX_VALUE - (ientry.height() + 1) * (ientry.width() + 1) * (appcount + 1);
            result.add(new MediaSnippet(ContentDomain.IMAGE, url, Classification.url2mime(url), desc, ientry.fileSize(), ientry.width(), ientry.height(), ranking, source));
        }
        return result;
    }
View Full Code Here
TOP

Related Classes of net.yacy.document.parser.html.ImageEntry

  • de.anomic.search.MediaSnippet
  • net.yacy.document.Condenser
  • net.yacy.document.Document
  • net.yacy.document.parser.images.genericImageParser
  • net.yacy.search.snippet.MediaSnippet
  • ViewFile
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.