Marown/yacy_search_server
1
0
Fork 0
mirror of https://github.com/yacy/yacy_search_server.git synced 2024-09-19 00:01:41 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity

added an option to put image links to the crawl queue and handle these

Browse Source 
like normal documents. Using this option (by default on at this moment;
this might change soon) it is possible to get the exif data into the
search index to be used in image search.
This commit is contained in:
Michael Peter Christen 2013-09-03 11:13:45 +02:00
parent e8e558a9b7
commit 69f85265e1
3 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
defaults/yacy.init
View File

@ -796,6 +796,11 @@ search.excludehosth=
# the cases of nocache, iffresh and ifexist causes an index deletion
search.verify.delete = true
# images may be treated either as documents that are shown in search results or as objects
# that are only visible in special search environments, like image search
search.excludeintext.image = true
crawler.load.image = true;
# remote search details
remotesearch.maxcount = 10
remotesearch.maxtime = 3000

3
source/net/yacy/crawler/CrawlStacker.java
View File

@ -336,9 +336,10 @@ public final class CrawlStacker {
// check availability of parser and maxfilesize
String warning = null;
boolean loadImages = Switchboard.getSwitchboard().getConfigBool("crawler.load.image", true);
if ((maxFileSize >= 0 && entry.size() > maxFileSize) ||
entry.url().getContentDomain() == ContentDomain.APP ||
entry.url().getContentDomain() == ContentDomain.IMAGE ||
(!loadImages && entry.url().getContentDomain() == ContentDomain.IMAGE) ||
entry.url().getContentDomain() == ContentDomain.AUDIO ||
entry.url().getContentDomain() == ContentDomain.VIDEO ||
entry.url().getContentDomain() == ContentDomain.CTRL) {

4
source/net/yacy/search/Switchboard.java
View File

@ -2512,10 +2512,12 @@ public final class Switchboard extends serverSwitch {
) {
// get the hyperlinks
final Map<DigestURI, String> hl = Document.getHyperlinks(documents);
boolean loadImages = getConfigBool("crawler.load.image", true);
if (loadImages) hl.putAll(Document.getImagelinks(documents));
// add all media links also to the crawl stack. They will be re-sorted to the NOLOAD queue and indexed afterwards as pure links
if (response.profile().directDocByURL()) {
hl.putAll(Document.getImagelinks(documents));
if (!loadImages) hl.putAll(Document.getImagelinks(documents));
hl.putAll(Document.getApplinks(documents));
hl.putAll(Document.getVideolinks(documents));
hl.putAll(Document.getAudiolinks(documents));