This is an automated email from the ASF dual-hosted git repository.
lewismc 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 78c179c6c NUTCH-3196 Yetus: stop failing the tree on known false
positives and non-source noise (#947)
78c179c6c is described below
commit 78c179c6c69490b88c6e1f197aaca7b3785f7ebc
Author: Lewis John McGibbney <[email protected]>
AuthorDate: Fri Aug 14 23:42:06 2026 -0600
NUTCH-3196 Yetus: stop failing the tree on known false positives and
non-source noise (#947)
---
.codespellrc | 14 +++++---
.yetus/detsecrets-ignored-hashes.txt | 39 ++++++++++++++++++++++
.yetus/excludes.txt | 16 +++++++++
README.md | 3 +-
src/java/org/apache/nutch/util/GZIPUtils.java | 2 +-
.../nutch/indexer/replace/TestIndexReplace.java | 2 +-
.../nutch/urlfilter/api/RegexURLFilterBase.java | 2 +-
.../nutch/protocol/htmlunit/HttpResponse.java | 2 +-
.../apache/nutch/protocol/http/HttpResponse.java | 2 +-
.../httpclient/TestProtocolHttpClient.java | 2 +-
.../urlfilter/validator/TestUrlValidator.java | 2 +-
11 files changed, 74 insertions(+), 12 deletions(-)
diff --git a/.codespellrc b/.codespellrc
index 377447ad9..dedef4624 100644
--- a/.codespellrc
+++ b/.codespellrc
@@ -1,5 +1,11 @@
[codespell]
-# JUnit 5 annotations incorrectly flagged as spelling errors
-ignore-words-list = AfterAll,BeforeAll
-# CHANGES.md is a historical changelog not maintained by this branch
-skip = CHANGES.md
+# JUnit 5 annotations incorrectly flagged as spelling errors.
+# Loction: intentional misspelling in protocol-http/okhttp TestResponse
fixtures
+# used to exercise SpellCheckedMetadata error-tolerant Location header
matching.
+# uery: intentional query-string token in urlnormalizer-protocol
TestProtocolURLNormalizer.
+ignore-words-list = AfterAll,BeforeAll,Loction,uery
+# CHANGES.md is a historical changelog not maintained by this branch.
+# Language-identifier corpora, binary license trees, and naivebayes training
+# sample are also listed in .yetus/excludes.txt for full-tree Yetus runs; skip
+# them here so local codespell matches CI.
+skip =
CHANGES.md,src/plugin/language-identifier/src/test,LICENSE-binary,NOTICE-binary,licenses-binary,conf/naivebayes-train.txt.template
diff --git a/.yetus/detsecrets-ignored-hashes.txt
b/.yetus/detsecrets-ignored-hashes.txt
new file mode 100644
index 000000000..42f240cb3
--- /dev/null
+++ b/.yetus/detsecrets-ignored-hashes.txt
@@ -0,0 +1,39 @@
+# detect-secrets hashed_secret values that Yetus should ignore.
+# Format: one hash per line; lines starting with # are comments.
+# Review any addition: confirm it is a false positive, not a real secret.
+# See apacheyetuspatchdir/results-detsecrets.txt from the failing master run
+# and NUTCH Yetus Child A (baselines / false positives).
+#
+# SHA-1 of the literal string "password" (and similar). Hits config property
+# names, URI documentation examples (amqp://username:password@...), and
+# constant values that name the password field — not live credentials.
+5baa61e4c9b93f3f0682250b6cf8331b7ee68fd8
+#
+# OpenSearch1xConstants: config key string "trust.store.password"
+ec05eda067a39ffdc229dff3a0d55db56656d678
+#
+# OpenSearch1xConstants: config key string "key.store.password"
+31fa62ac05693f4af2e2502db1f33f702afbdb43
+#
+# OpenSearch1xIndexWriter: documented default "admin" for local/dev broker
+# examples (not a production secret checked into the tree as a credential).
+d033e22ae348aeb5660fc2140aec35850c4da997
+#
+# TestExtParser: expected MD5 hex of sample parse content
+2fe42febe111596aa7070228ed35a41f3ffe444c
+#
+# protocol-httpclient auth unit-test fixture passwords (passx, ntlm_pass, ...)
+c05344161c34c6606402148288f1c554ae669c59
+00f18fe6a9b0aca8604af067990196a949ea954a
+085a30b5d2b112ebbbcbc8d54d41e4df58d02f39
+f0578f1e7174b1a41c4ea8c6e17f7a8a3b88c92a
+8be52126a6fde450a7162a3651d589bb51e9579d
+#
+# TestBadServerResponses: high-entropy alphabet string used as response body
+8332535894e68d6ff799a283a496515c03a78d94
+#
+# DumpFileUtilTest: expected MD5 hex assertion value
+b1da254a02ecdaa258432fa3f3292bd77243de2c
+#
+# TestStringUtil: example AMQP URI containing the documentation password token
+7e9c593cb78751c2c9c5e026e8b37bffbeb0ca75
diff --git a/.yetus/excludes.txt b/.yetus/excludes.txt
new file mode 100644
index 000000000..6cfe88d3c
--- /dev/null
+++ b/.yetus/excludes.txt
@@ -0,0 +1,16 @@
+# Regexes (one per line, no spaces) of paths Yetus should keep out of the
+# changed-file set passed to plugins. See --excludes / .yetus/excludes.txt.
+# Used especially by full-tree (master) runs so non-source noise does not drown
+# the report. Comments and blank lines are ignored.
+#
+# Language-identifier test corpora: non-English / sample text that codespell
+# treats as typos. Product Java under this plugin is not excluded.
+^src/plugin/language-identifier/src/test/
+#
+# Bundled third-party license/notice text (not Nutch prose to spell-check).
+^LICENSE-binary$
+^NOTICE-binary$
+^licenses-binary/
+#
+# Naive Bayes training sample (deliberately messy email/OCR-like text).
+^conf/naivebayes-train\.txt\.template$
diff --git a/README.md b/README.md
index d453d6584..2a4ec82fe 100644
--- a/README.md
+++ b/README.md
@@ -47,7 +47,8 @@ test-patch --basedir=/path/to/clean/repo --build-tool=nobuild
\
--plugins=all,-jira,-gitlab,-unit,-compile [patchfile]
```
-Exclude patterns can be added in `.yetus/excludes.txt` (regex, one per line).
+Exclude patterns and related Yetus baselines can be added under `.yetus/`
+(see `.yetus/excludes.txt`).
IDE setup
---------
diff --git a/src/java/org/apache/nutch/util/GZIPUtils.java
b/src/java/org/apache/nutch/util/GZIPUtils.java
index 7daa6a729..df137cc48 100644
--- a/src/java/org/apache/nutch/util/GZIPUtils.java
+++ b/src/java/org/apache/nutch/util/GZIPUtils.java
@@ -27,7 +27,7 @@ import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
- * A collection of utility methods for working on GZIPed data.
+ * A collection of utility methods for working on gzipped data.
*/
public class GZIPUtils {
diff --git
a/src/plugin/index-replace/src/test/org/apache/nutch/indexer/replace/TestIndexReplace.java
b/src/plugin/index-replace/src/test/org/apache/nutch/indexer/replace/TestIndexReplace.java
index 0e48cee0e..d4cabbe5f 100644
---
a/src/plugin/index-replace/src/test/org/apache/nutch/indexer/replace/TestIndexReplace.java
+++
b/src/plugin/index-replace/src/test/org/apache/nutch/indexer/replace/TestIndexReplace.java
@@ -418,7 +418,7 @@ public class TestIndexReplace {
/**
* Test a replacement pattern that uses the target field feature.
- * Check that the input is not modifid and that the taret field is added.
+ * Check that the input is not modified and that the target field is added.
*/
@Test
public void testReplacementsDifferentTarget() {
diff --git
a/src/plugin/lib-regex-filter/src/java/org/apache/nutch/urlfilter/api/RegexURLFilterBase.java
b/src/plugin/lib-regex-filter/src/java/org/apache/nutch/urlfilter/api/RegexURLFilterBase.java
index 2795c2cf8..9a357d88f 100644
---
a/src/plugin/lib-regex-filter/src/java/org/apache/nutch/urlfilter/api/RegexURLFilterBase.java
+++
b/src/plugin/lib-regex-filter/src/java/org/apache/nutch/urlfilter/api/RegexURLFilterBase.java
@@ -177,7 +177,7 @@ public abstract class RegexURLFilterBase implements
URLFilter {
try {
domain = URLUtil.getDomainName(url);
} catch (MalformedURLException e) {
- // shouldnt happen here right?
+ // shouldn't happen here right?
}
LOG.debug("URL belongs to host {} and domain {}", host, domain);
diff --git
a/src/plugin/protocol-htmlunit/src/java/org/apache/nutch/protocol/htmlunit/HttpResponse.java
b/src/plugin/protocol-htmlunit/src/java/org/apache/nutch/protocol/htmlunit/HttpResponse.java
index 0a4f0a68c..e77932e33 100644
---
a/src/plugin/protocol-htmlunit/src/java/org/apache/nutch/protocol/htmlunit/HttpResponse.java
+++
b/src/plugin/protocol-htmlunit/src/java/org/apache/nutch/protocol/htmlunit/HttpResponse.java
@@ -450,7 +450,7 @@ public class HttpResponse implements Response {
+ " bytes in successful chunks" + " and " + chunkBytesRead
+ " in current chunk");
- // DANGER!!! Will printed GZIPed stuff right to your
+ // DANGER!!! Will print gzipped stuff right to your
// terminal!
// if (LOG.isTraceEnabled()) { LOG.trace("read: " + new String(bytes,
0,
// len)); }
diff --git
a/src/plugin/protocol-http/src/java/org/apache/nutch/protocol/http/HttpResponse.java
b/src/plugin/protocol-http/src/java/org/apache/nutch/protocol/http/HttpResponse.java
index ead757574..bd2611ec1 100644
---
a/src/plugin/protocol-http/src/java/org/apache/nutch/protocol/http/HttpResponse.java
+++
b/src/plugin/protocol-http/src/java/org/apache/nutch/protocol/http/HttpResponse.java
@@ -524,7 +524,7 @@ public class HttpResponse implements Response {
+ " bytes in successful chunks" + " and " + chunkBytesRead
+ " in current chunk");
- // DANGER!!! Will printed GZIPed stuff right to your
+ // DANGER!!! Will print gzipped stuff right to your
// terminal!
// if (LOG.isTraceEnabled()) { LOG.trace("read: " + new String(bytes,
0,
// len)); }
diff --git
a/src/plugin/protocol-httpclient/src/test/org/apache/nutch/protocol/httpclient/TestProtocolHttpClient.java
b/src/plugin/protocol-httpclient/src/test/org/apache/nutch/protocol/httpclient/TestProtocolHttpClient.java
index 4873ae8ed..88315c2e9 100644
---
a/src/plugin/protocol-httpclient/src/test/org/apache/nutch/protocol/httpclient/TestProtocolHttpClient.java
+++
b/src/plugin/protocol-httpclient/src/test/org/apache/nutch/protocol/httpclient/TestProtocolHttpClient.java
@@ -92,7 +92,7 @@ public class TestProtocolHttpClient extends
AbstractHttpProtocolPluginTest {
}
/**
- * Tests that no pre-emptive authorization headers are sent by the client.
+ * Tests that no preemptive authorization headers are sent by the client.
*
* @throws Exception
* If an error occurs or the test case fails.
diff --git
a/src/plugin/urlfilter-validator/src/test/org/apache/nutch/urlfilter/validator/TestUrlValidator.java
b/src/plugin/urlfilter-validator/src/test/org/apache/nutch/urlfilter/validator/TestUrlValidator.java
index d815486de..9d9b60592 100644
---
a/src/plugin/urlfilter-validator/src/test/org/apache/nutch/urlfilter/validator/TestUrlValidator.java
+++
b/src/plugin/urlfilter-validator/src/test/org/apache/nutch/urlfilter/validator/TestUrlValidator.java
@@ -56,7 +56,7 @@ public class TestUrlValidator {
"Invalid url: ftp:www.example.com/main.html");
assertNull(
url_validator.filter("http://999.000.456.32/nutch/trunk/README.txt";),
- "Inalid url: http://999.000.456.32/nutch/trunk/README.txt";);
+ "Invalid url: http://999.000.456.32/nutch/trunk/README.txt";);
assertNull(url_validator.filter(" http://www.example.com/ma|in\\toc.html"),
"Invalid url: http://www.example.com/ma|in\\toc.html");
