You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@stormcrawler.apache.org by rz...@apache.org on 2026/08/01 16:27:35 UTC
(stormcrawler) branch main updated (883b8546 -> 747f5d0a)
This is an automated email from the ASF dual-hosted git repository.
rzo1 pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/stormcrawler.git
from 883b8546 [maven-release-plugin] prepare for next development iteration
new 214b23e1 Fix typo in OpenSearch configuration comment
new 747f5d0a Fix broken link to Guava's CacheBuilderSpec
The 2 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
Summary of changes:
.../stormcrawler/persistence/AbstractStatusUpdaterBolt.java | 6 +++---
.../org/apache/stormcrawler/protocol/RobotRulesParser.java | 13 ++++++-------
.../main/resources/archetype-resources/opensearch-conf.yaml | 2 +-
external/opensearch/opensearch-conf.yaml | 2 +-
4 files changed, 11 insertions(+), 12 deletions(-)
(stormcrawler) 01/02: Fix typo in OpenSearch configuration comment
Posted by rz...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
rzo1 pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/stormcrawler.git
commit 214b23e16717c32add54c035762ce4ec176697fe
Author: Sebastian Nagel <se...@commoncrawl.org>
AuthorDate: Thu May 7 12:12:01 2026 +0200
Fix typo in OpenSearch configuration comment
---
.../src/main/resources/archetype-resources/opensearch-conf.yaml | 2 +-
external/opensearch/opensearch-conf.yaml | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/external/opensearch/archetype/src/main/resources/archetype-resources/opensearch-conf.yaml b/external/opensearch/archetype/src/main/resources/archetype-resources/opensearch-conf.yaml
index 02c19533..597ff4f8 100644
--- a/external/opensearch/archetype/src/main/resources/archetype-resources/opensearch-conf.yaml
+++ b/external/opensearch/archetype/src/main/resources/archetype-resources/opensearch-conf.yaml
@@ -76,7 +76,7 @@ config:
# - "-(key:stormcrawler.net)"
# - "-(key:stormcrawler.apache.org)"
- # time in secs for which the URLs will be considered for fetching after a ack of fail
+ # time in secs for which the URLs will be considered for fetching after a ack or fail
spout.ttl.purgatory: 30
# Min time (in msecs) to allow between 2 successive queries to OpenSearch
diff --git a/external/opensearch/opensearch-conf.yaml b/external/opensearch/opensearch-conf.yaml
index 8dc8263c..dbbbc8d8 100644
--- a/external/opensearch/opensearch-conf.yaml
+++ b/external/opensearch/opensearch-conf.yaml
@@ -86,7 +86,7 @@ config:
# - "-(key:stormcrawler.net)"
# - "-(key:apache.stormcrawler.org)"
- # time in secs for which the URLs will be considered for fetching after a ack of fail
+ # time in secs for which the URLs will be considered for fetching after a ack or fail
spout.ttl.purgatory: 30
# Min time (in msecs) to allow between 2 successive queries to OpenSearch
(stormcrawler) 02/02: Fix broken link to Guava's CacheBuilderSpec
Posted by rz...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
rzo1 pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/stormcrawler.git
commit 747f5d0a8663335359edcfb446c87bb00ee5f1c7
Author: Sebastian Nagel <se...@commoncrawl.org>
AuthorDate: Wed Nov 26 11:43:45 2025 +0100
Fix broken link to Guava's CacheBuilderSpec
---
.../stormcrawler/persistence/AbstractStatusUpdaterBolt.java | 6 +++---
.../org/apache/stormcrawler/protocol/RobotRulesParser.java | 13 ++++++-------
2 files changed, 9 insertions(+), 10 deletions(-)
diff --git a/core/src/main/java/org/apache/stormcrawler/persistence/AbstractStatusUpdaterBolt.java b/core/src/main/java/org/apache/stormcrawler/persistence/AbstractStatusUpdaterBolt.java
index 0ff15ad1..2fb09e36 100644
--- a/core/src/main/java/org/apache/stormcrawler/persistence/AbstractStatusUpdaterBolt.java
+++ b/core/src/main/java/org/apache/stormcrawler/persistence/AbstractStatusUpdaterBolt.java
@@ -58,9 +58,9 @@ public abstract class AbstractStatusUpdaterBolt extends BaseRichBolt {
public static String maxFetchErrorsParamName = "max.fetch.errors";
/**
- * Parameter name to configure the cache. @see http://docs.guava-libraries.googlecode
- * .com/git/javadoc/com/google/common/cache/CacheBuilderSpec.html Default value is
- * "maximumSize=10000,expireAfterAccess=1h".
+ * Parameter name to configure the cache, see <a href=
+ * "https://guava.dev/releases/snapshot-jre/api/docs/com/google/common/cache/CacheBuilderSpec.html">Guava's
+ * CacheBuilderSpec</a> Default value is "maximumSize=10000,expireAfterAccess=1h".
*/
public static String cacheConfigParamName = "status.updater.cache.spec";
diff --git a/core/src/main/java/org/apache/stormcrawler/protocol/RobotRulesParser.java b/core/src/main/java/org/apache/stormcrawler/protocol/RobotRulesParser.java
index d6c36673..121dae61 100644
--- a/core/src/main/java/org/apache/stormcrawler/protocol/RobotRulesParser.java
+++ b/core/src/main/java/org/apache/stormcrawler/protocol/RobotRulesParser.java
@@ -54,17 +54,16 @@ public abstract class RobotRulesParser {
protected static Cache<String, RobotRules> ERRORCACHE;
/**
- * Parameter name to configure the cache for robots. @see http://docs.guava-libraries.googlecode
- * .com/git/javadoc/com/google/common/cache/CacheBuilderSpec.html Default value is
- * "maximumSize=10000,expireAfterWrite=6h"
+ * Parameter name to configure the cache for robots, see <a href=
+ * "https://guava.dev/releases/snapshot-jre/api/docs/com/google/common/cache/CacheBuilderSpec.html">Guava's
+ * CacheBuilderSpec</a>. Default value is "maximumSize=10000,expireAfterWrite=6h"
*/
public static final String cacheConfigParamName = "robots.cache.spec";
/**
- * Parameter name to configure the cache for robots errors. @see
- * http://docs.guava-libraries.googlecode
- * .com/git/javadoc/com/google/common/cache/CacheBuilderSpec.html Default value is
- * "maximumSize=10000,expireAfterWrite=1h"
+ * Parameter name to configure the cache for robots errors, see <a href=
+ * "https://guava.dev/releases/snapshot-jre/api/docs/com/google/common/cache/CacheBuilderSpec.html">Guava's
+ * CacheBuilderSpec</a>. Default value is "maximumSize=10000,expireAfterWrite=1h"
*/
public static final String errorcacheConfigParamName = "robots.error.cache.spec";