[
https://issues.apache.org/jira/browse/NUTCH-2184?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15176368#comment-15176368
]
ASF GitHub Bot commented on NUTCH-2184:
---------------------------------------
Github user sebastian-nagel commented on a diff in the pull request:
https://github.com/apache/nutch/pull/95#discussion_r54782218
--- Diff: src/java/org/apache/nutch/indexer/IndexerMapReduce.java ---
@@ -166,235 +145,310 @@ private String filterUrl(String url) {
return url;
}
- public void map(Text key, Writable value,
- OutputCollector<Text, NutchWritable> output, Reporter reporter)
- throws IOException {
+ /**
+ * Implementation of {@link org.apache.hadoop.mapred.Mapper}
+ * which optionally normalizes then filters a URL before simply
+ * collecting key and values with the keys being URLs (manifested
+ * as {@link org.apache.hadoop.io.Text}) and the
+ * values as {@link org.apache.nutch.crawl.NutchWritable} instances
+ * of {@link org.apache.nutch.crawl.CrawlDatum}.
+ */
+ public static class IndexerMapReduceMapper implements Mapper<Text,
Writable, Text, NutchWritable> {
+
+ @Override
+ public void configure(JobConf job) {
+ }
+
+ public void map(Text key, Writable value,
+ OutputCollector<Text, NutchWritable> output, Reporter reporter)
+ throws IOException {
+
+ String urlString = filterUrl(normalizeUrl(key.toString()));
+ if (urlString == null) {
+ return;
+ } else {
+ key.set(urlString);
+ }
+
+ output.collect(key, new NutchWritable(value));
+ }
- String urlString = filterUrl(normalizeUrl(key.toString()));
- if (urlString == null) {
- return;
- } else {
- key.set(urlString);
+ @Override
+ public void close() throws IOException {
}
- output.collect(key, new NutchWritable(value));
}
- public void reduce(Text key, Iterator<NutchWritable> values,
- OutputCollector<Text, NutchIndexAction> output, Reporter reporter)
- throws IOException {
- Inlinks inlinks = null;
- CrawlDatum dbDatum = null;
- CrawlDatum fetchDatum = null;
- Content content = null;
- ParseData parseData = null;
- ParseText parseText = null;
-
- while (values.hasNext()) {
- final Writable value = values.next().get(); // unwrap
- if (value instanceof Inlinks) {
- inlinks = (Inlinks) value;
- } else if (value instanceof CrawlDatum) {
- final CrawlDatum datum = (CrawlDatum) value;
- if (CrawlDatum.hasDbStatus(datum)) {
- dbDatum = datum;
- } else if (CrawlDatum.hasFetchStatus(datum)) {
- // don't index unmodified (empty) pages
- if (datum.getStatus() != CrawlDatum.STATUS_FETCH_NOTMODIFIED) {
- fetchDatum = datum;
+ /**
+ * Implementation of {@link org.apache.hadoop.mapred.Reducer}
+ * which generates {@link org.apache.nutch.indexer.NutchIndexAction}'s
+ * from combinations of various Nutch data structures. Essentially
+ * teh result is a key representing a URL and a value representing a
+ * unit of indexing holding the document and action information.
+ */
+ public static class IndexerMapReduceReducer implements Reducer<Text,
NutchWritable, Text, NutchIndexAction> {
+
+ private boolean skip = false;
+ private boolean delete = false;
+ private boolean deleteRobotsNoIndex = false;
+ private boolean deleteSkippedByIndexingFilter = false;
+ private boolean base64 = false;
+ private IndexingFilters filters;
+ private ScoringFilters scfilters;
+
+ @Override
+ public void configure(JobConf job) {
+ Configuration conf = NutchConfiguration.create();
--- End diff --
JobConf extends Configuration, there should be no need to create a new
Configuration object.
> Enable IndexingJob to function with no crawldb
> ----------------------------------------------
>
> Key: NUTCH-2184
> URL: https://issues.apache.org/jira/browse/NUTCH-2184
> Project: Nutch
> Issue Type: Improvement
> Components: indexer
> Reporter: Lewis John McGibbney
> Assignee: Lewis John McGibbney
> Fix For: 1.12
>
> Attachments: NUTCH-2184.patch, NUTCH-2184v2.patch
>
>
> Sometimes when working with distributed team(s), we have found that we can
> 'loose' data structures which are currently considered as critical e.g.
> crawldb, linkdb and/or segments.
> In my current scenario I have a requirement to index segment data with no
> accompanying crawldb or linkdb.
> Absence of the latter is OK as linkdb is optional however currently in
> [IndexerMapReduce|https://github.com/apache/nutch/blob/trunk/src/java/org/apache/nutch/indexer/IndexerMapReduce.java]
> crawldb is mandatory.
> This ticket should enhance the IndexerMapReduce code to support the use case
> where you ONLY have segments and want to force an index for every record
> present.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
