...
The table below provides a canonical, comprehensive collection of Nutch metrics.
Info | ||
---|---|---|
| ||
The table is arranged
|
Tool | Metric Group | Metric Name | Description |
---|---|---|---|
Injector | injector | urls_filtered | |
injector | urls_injected | ||
injector | urls_merged | ||
injector | urls_purged_404 | ||
injector | urls_purged_filter | ||
Generator | Generator | SCHEDULE_REJECTED | |
Generator | WAIT_FOR_UPDATE | ||
Generator | EXPR_REJECTED | ||
Generator | STATUS_REJECTED | ||
Generator | SCORE_TOO_LOW | ||
Generator | INTERVAL_REJECTED | ||
Generator | MALFORMED_URL | ||
Generator | HOSTS_AFFECTED_PER_HOST_OVERFLOW | ||
Generator | URLS_SKIPPED_PER_HOST_OVERFLOW | ||
./src/test/org/apache/nutch/crawl/CrawlDbUpdateUtil.java
./src/test/org/apache/nutch/crawl/CrawlDBTestUtil.java
./src/java/org/apache/nutch/tools/warc/WARCExporter.java
./src/java/org/apache/nutch/util/SitemapProcessor.java
./src/java/org/apache/nutch/util/domain/DomainStatistics.java
./src/java/org/apache/nutch/parse/ParseSegment.java
./src/java/org/apache/nutch/fetcher/Fetcher.java
./src/java/org/apache/nutch/fetcher/FetcherThread.java
./src/java/org/apache/nutch/fetcher/QueueFeeder.java
./src/java/org/apache/nutch/crawl/CrawlDb.java
./src/java/org/apache/nutch/crawl/CrawlDbReducer.java
./src/java/org/apache/nutch/crawl/DeduplicationJob.java
./src/java/org/apache/nutch/crawl/CrawlDbFilter.java
./src/java/org/apache/nutch/hostdb/UpdateHostDbMapper.java
./src/java/org/apache/nutch/hostdb/UpdateHostDbReducer.java
./src/java/org/apache/nutch/hostdb/ResolverThread.java
./src/java/org/apache/nutch/scoring/webgraph/WebGraph.java
./src/java/org/apache/nutch/indexer/IndexingJob.java
./src/java/org/apache/nutch/indexer/IndexerMapReduce.java
./src/java/org/apache/nutch/indexer/CleaningJob.java