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 comments about crawl profiles recrawl cycles

Browse Source
This commit is contained in:
luccioman 2018-01-13 12:13:04 +01:00
parent 3638e16c2e
commit adf3fa493d
1 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
source/net/yacy/crawler/CrawlSwitchboard.java
View File

@ -87,13 +87,15 @@ public final class CrawlSwitchboard {
public static final String DBFILE_ACTIVE_CRAWL_PROFILES = "crawlProfilesActive1.heap";
public static final String DBFILE_PASSIVE_CRAWL_PROFILES = "crawlProfilesPassive1.heap";
public static final long CRAWL_PROFILE_PROXY_RECRAWL_CYCLE = 60L * 24L;
public static final long CRAWL_PROFILE_SNIPPET_LOCAL_TEXT_RECRAWL_CYCLE = 60L * 24L * 30L;
public static final long CRAWL_PROFILE_SNIPPET_GLOBAL_TEXT_RECRAWL_CYCLE = 60L * 24L * 30L;
public static final long CRAWL_PROFILE_GREEDY_LEARNING_TEXT_RECRAWL_CYCLE = 60L * 24L * 30L;
public static final long CRAWL_PROFILE_SNIPPET_LOCAL_MEDIA_RECRAWL_CYCLE = 60L * 24L * 30L;
public static final long CRAWL_PROFILE_SNIPPET_GLOBAL_MEDIA_RECRAWL_CYCLE = 60L * 24L * 30L;
public static final long CRAWL_PROFILE_SURROGATE_RECRAWL_CYCLE = 60L * 24L * 30L;
// Default time cycle in minutes before an indexed URL by a given crawl profile can be accepted for recrawl */
public static final long CRAWL_PROFILE_PROXY_RECRAWL_CYCLE = 60L * 24L; // one day
public static final long CRAWL_PROFILE_SNIPPET_LOCAL_TEXT_RECRAWL_CYCLE = 60L * 24L * 30L; // 30 days
public static final long CRAWL_PROFILE_SNIPPET_GLOBAL_TEXT_RECRAWL_CYCLE = 60L * 24L * 30L; // 30 days
public static final long CRAWL_PROFILE_GREEDY_LEARNING_TEXT_RECRAWL_CYCLE = 60L * 24L * 30L; // 30 days
public static final long CRAWL_PROFILE_SNIPPET_LOCAL_MEDIA_RECRAWL_CYCLE = 60L * 24L * 30L; // 30 days
public static final long CRAWL_PROFILE_SNIPPET_GLOBAL_MEDIA_RECRAWL_CYCLE = 60L * 24L * 30L; // 30 days
public static final long CRAWL_PROFILE_SURROGATE_RECRAWL_CYCLE = 60L * 24L * 30L; // 30 days
private final ConcurrentLog log;
private MapHeap profilesActiveCrawls;