You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by sn...@apache.org on 2020/05/05 14:00:08 UTC

[nutch] branch master updated: NUTCH-2753 Add -listen option to command-line help of CrawlDbReader and LinkDbReader

This is an automated email from the ASF dual-hosted git repository.

snagel pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/nutch.git


The following commit(s) were added to refs/heads/master by this push:
     new c573c70  NUTCH-2753 Add -listen option to command-line help of CrawlDbReader and LinkDbReader
     new ede1489  Merge pull request #523 from sebastian-nagel/NUTCH-2753
c573c70 is described below

commit c573c70d05331dcd572ddcd23831337f8208fff7
Author: Sebastian Nagel <sn...@apache.org>
AuthorDate: Thu Apr 30 17:07:30 2020 +0200

    NUTCH-2753 Add -listen option to command-line help of CrawlDbReader and LinkDbReader
---
 src/java/org/apache/nutch/crawl/CrawlDbReader.java | 6 +++++-
 src/java/org/apache/nutch/crawl/LinkDbReader.java  | 6 +++++-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/src/java/org/apache/nutch/crawl/CrawlDbReader.java b/src/java/org/apache/nutch/crawl/CrawlDbReader.java
index dfcc87a..603b2e3 100644
--- a/src/java/org/apache/nutch/crawl/CrawlDbReader.java
+++ b/src/java/org/apache/nutch/crawl/CrawlDbReader.java
@@ -979,7 +979,7 @@ public class CrawlDbReader extends AbstractChecker implements Closeable {
 
     if (args.length < 2) {
       System.err.println(
-          "Usage: CrawlDbReader <crawldb> (-stats | -dump <out_dir> | -topN <nnnn> <out_dir> [<min>] | -url <url>)");
+          "Usage: CrawlDbReader <crawldb> (-stats | -dump <out_dir> | -topN <nnnn> <out_dir> [<min>] | -url <url> | -listen <port>)");
       System.err
           .println("\t<crawldb>\tdirectory name where crawldb is located");
       System.err
@@ -1002,6 +1002,10 @@ public class CrawlDbReader extends AbstractChecker implements Closeable {
           "\t\t[-sample <fraction>]\tOnly process a random sample with this ratio");
       System.err
           .println("\t-url <url>\tprint information on <url> to System.out");
+      System.err
+        .println("\t-listen <port> [-keepClientCnxOpen]\tlisten on <port> for URLs and");
+      System.err
+            .println("\t\t\tsend information about <url> back");
       System.err.println(
           "\t-topN <nnnn> <out_dir> [<min>]\tdump top <nnnn> urls sorted by score to <out_dir>");
       System.err
diff --git a/src/java/org/apache/nutch/crawl/LinkDbReader.java b/src/java/org/apache/nutch/crawl/LinkDbReader.java
index 5d422b4..4cacd81 100644
--- a/src/java/org/apache/nutch/crawl/LinkDbReader.java
+++ b/src/java/org/apache/nutch/crawl/LinkDbReader.java
@@ -225,13 +225,17 @@ public class LinkDbReader extends AbstractChecker implements Closeable {
   public int run(String[] args) throws Exception {
     if (args.length < 2) {
       System.err
-          .println("Usage: LinkDbReader <linkdb> (-dump <out_dir> [-regex <regex>]) | -url <url>");
+          .println("Usage: LinkDbReader <linkdb> (-dump <out_dir> [-regex <regex>] | -url <url> | -listen <port>)");
       System.err
           .println("\t-dump <out_dir>\tdump whole link db to a text file in <out_dir>");
       System.err
           .println("\t\t-regex <regex>\trestrict to url's matching expression");
       System.err
           .println("\t-url <url>\tprint information about <url> to System.out");
+      System.err
+          .println("\t-listen <port> [-keepClientCnxOpen]\tlisten on <port> for URLs and");
+      System.err
+          .println("\t\t\tsend information about <url> back");
       return -1;
     }