From 2eb4f5dfbf1131111a7c935473376767a1bb4058 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Sat, 8 Aug 2026 07:05:45 +0000 Subject: [PATCH 1/2] Bump org.jsoup:jsoup from 1.20.1 to 1.23.1 Bumps [org.jsoup:jsoup](https://github.com/jhy/jsoup) from 1.20.1 to 1.23.1. - [Release notes](https://github.com/jhy/jsoup/releases) - [Changelog](https://github.com/jhy/jsoup/blob/master/CHANGES.md) - [Commits](https://github.com/jhy/jsoup/compare/jsoup-1.20.1...jsoup-1.23.1) --- updated-dependencies: - dependency-name: org.jsoup:jsoup dependency-version: 1.23.1 dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- pom.xml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pom.xml b/pom.xml index fb65c64af35..81c3b83884f 100644 --- a/pom.xml +++ b/pom.xml @@ -2896,7 +2896,7 @@ org.jsoup jsoup - 1.20.1 + 1.23.1 org.julienrf From 56442c72ffe6c28aef3c77f5d836d9294169d75d Mon Sep 17 00:00:00 2001 From: Rene Cordier Date: Mon, 10 Aug 2026 10:13:17 +0700 Subject: [PATCH 2/2] [Jsoup] null characters (\0) in HTML are replaced/removed during tokenization, not preserved. HTML-5-spec compliance fix in jsoup: Null characters in the HTML body were not consistently removed; and in foreign content were not correctly replaced. #2395 (https://github.com/jhy/jsoup/issues/2395) --- .../james/mailbox/store/extractor/JsoupTextExtractorTest.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mailbox/store/src/test/java/org/apache/james/mailbox/store/extractor/JsoupTextExtractorTest.java b/mailbox/store/src/test/java/org/apache/james/mailbox/store/extractor/JsoupTextExtractorTest.java index 00d00f9d5a0..7a027828693 100644 --- a/mailbox/store/src/test/java/org/apache/james/mailbox/store/extractor/JsoupTextExtractorTest.java +++ b/mailbox/store/src/test/java/org/apache/james/mailbox/store/extractor/JsoupTextExtractorTest.java @@ -99,7 +99,7 @@ void extractContentShouldNotThrowWhenContainingNullCharacters() throws Exception assertThat(textExtractor.extractContent(inputStream, TEXT_HTML_CONTENT_TYPE) .getTextualContent()) .hasValueSatisfying(text -> assertThat(text) - .contains(HTML_TEXT_CONTENT)); + .contains(HTML_TEXT_CONTENT.replace("\0", ""))); } @Test