From f758b18bc4e8c0203eb501618d803c46cb04d81a Mon Sep 17 00:00:00 2001 From: "Piotr P. Karwasz" Date: Mon, 31 Aug 2026 15:54:18 +0200 Subject: [PATCH 1/2] Harden XML parsing via commons-secure-xml Create XmlStringLookup's document builder and XPath factories through org.apache.commons:commons-secure-xml. The secure factories enable FEATURE_SECURE_PROCESSING and install a non-removable entity-resolver floor on every parser they produce: external DTD and entity lookups are resolved to empty content instead of being fetched, and internal entity expansion is bounded, regardless of the JAXP implementation on the classpath. Changes: - Add the commons-secure-xml dependency (1.0.0-SNAPSHOT until its first release). - Route factory creation through SecureDocumentBuilderFactory and SecureXPathFactory in XmlStringLookup when the instance's feature map enables secure processing. The documented opt-outs keep their meaning: feature maps without secure processing, and the standard javax.xml.accessExternalDTD system property (which the secure factory's resolver floor would otherwise ignore), keep using the plain JAXP factories, so external entity resolution can be restored where it is wanted. - Adapt the secure-path tests to the secure contract: a parser may either reject a document with an external reference or parse it with the reference resolved to empty content; the tests now assert that the external content does not leak into the result instead of expecting one fixed failure mode. - Run the CI and CodeQL builds with -Puse-apache-snapshots (inherited from the org.apache:apache parent POM) so the commons-secure-xml SNAPSHOT resolves; CodeQL's autobuild receives the profile through MAVEN_ARGS. Assisted-By: Claude Fable 5 Claude-Session: https://claude.ai/code/session_01MHgnMnGWHQoH2zD2jFdoMT --- .github/workflows/codeql-analysis.yml | 2 ++ .github/workflows/maven.yml | 2 +- pom.xml | 5 ++++ src/changes/changes.xml | 1 + .../commons/text/lookup/XmlStringLookup.java | 13 +++++++-- .../text/lookup/StringLookupFactoryTest.java | 5 ++-- .../text/lookup/XmlStringLookupTest.java | 27 ++++++++++++++----- 7 files changed, 44 insertions(+), 11 deletions(-) diff --git a/.github/workflows/codeql-analysis.yml b/.github/workflows/codeql-analysis.yml index eaf7ff5225..9a2a536446 100644 --- a/.github/workflows/codeql-analysis.yml +++ b/.github/workflows/codeql-analysis.yml @@ -70,6 +70,8 @@ jobs: # If this step fails, then you should remove it and run the build manually (see below) - name: Autobuild uses: github/codeql-action/autobuild@cdf488f595d80d6e07e03d4674febd5ab45fa938 # v4.37.9 + env: + MAVEN_ARGS: -Puse-apache-snapshots # ℹī¸ Command-line programs to run using the OS shell. # 📚 https://git.io/JvXDl diff --git a/.github/workflows/maven.yml b/.github/workflows/maven.yml index 5a8b24254a..4f58b6e53d 100644 --- a/.github/workflows/maven.yml +++ b/.github/workflows/maven.yml @@ -49,4 +49,4 @@ jobs: java-version: ${{ matrix.java }} cache: 'maven' - name: Build with Maven - run: mvn --errors --show-version --batch-mode --no-transfer-progress -Dpolyglot.engine.WarnInterpreterOnly=false + run: mvn --errors --show-version --batch-mode --no-transfer-progress -Dpolyglot.engine.WarnInterpreterOnly=false -Puse-apache-snapshots diff --git a/pom.xml b/pom.xml index 9f8e678457..649e0f71a1 100644 --- a/pom.xml +++ b/pom.xml @@ -87,6 +87,11 @@ commons-lang3 ${commons.lang3.version} + + org.apache.commons + commons-secure-xml + 1.0.0-SNAPSHOT + org.junit.jupiter diff --git a/src/changes/changes.xml b/src/changes/changes.xml index b9beac2ede..019f2acb75 100644 --- a/src/changes/changes.xml +++ b/src/changes/changes.xml @@ -45,6 +45,7 @@ The type attribute can be add,update,fix,remove. + XmlStringLookup creates its XML parser and XPath factories through org.apache.commons:commons-secure-xml; feature maps without secure processing and the javax.xml.accessExternalDTD system property still restore the previous behavior. Improve test coverage #732. TextStringBuilder.append(char[], int, int) uses wrong variable in exception message #735. StrBuilder.readFrom(Readable) exposes stale internal buffer to Readable parameter (#741). diff --git a/src/main/java/org/apache/commons/text/lookup/XmlStringLookup.java b/src/main/java/org/apache/commons/text/lookup/XmlStringLookup.java index 624c7d01e2..8b69cd639f 100644 --- a/src/main/java/org/apache/commons/text/lookup/XmlStringLookup.java +++ b/src/main/java/org/apache/commons/text/lookup/XmlStringLookup.java @@ -30,6 +30,8 @@ import javax.xml.xpath.XPathFactory; import org.apache.commons.lang3.StringUtils; +import org.apache.commons.xml.secure.SecureDocumentBuilderFactory; +import org.apache.commons.xml.secure.SecureXPathFactory; import org.w3c.dom.Document; /** @@ -128,14 +130,21 @@ public String lookup(final String key) { } final String documentPath = keys[0]; final String xpath = StringUtils.substringAfterLast(key, SPLIT_CH); - final DocumentBuilderFactory dbFactory = DocumentBuilderFactory.newInstance(); + // The secure factory installs a non-removable resolver floor that ignores the JAXP access properties, + // so the documented opt-outs keep a plain factory: a feature map without secure processing, or the + // standard javax.xml.accessExternalDTD system property re-allowing external access. + final boolean secure = Boolean.TRUE.equals(xmlFactoryFeatures.get(XMLConstants.FEATURE_SECURE_PROCESSING)) + && StringUtils.isEmpty(System.getProperty("javax.xml.accessExternalDTD")); + final DocumentBuilderFactory dbFactory = secure ? SecureDocumentBuilderFactory.newInstance() : DocumentBuilderFactory.newInstance(); try { for (final Entry p : xmlFactoryFeatures.entrySet()) { dbFactory.setFeature(p.getKey(), p.getValue()); } try (InputStream inputStream = Files.newInputStream(getPath(documentPath))) { final Document doc = dbFactory.newDocumentBuilder().parse(inputStream); - final XPathFactory xpFactory = XPathFactory.newInstance(); + final XPathFactory xpFactory = Boolean.TRUE.equals(xPathFactoryFeatures.get(XMLConstants.FEATURE_SECURE_PROCESSING)) + ? SecureXPathFactory.newInstance() + : XPathFactory.newInstance(); for (final Entry p : xPathFactoryFeatures.entrySet()) { xpFactory.setFeature(p.getKey(), p.getValue()); } diff --git a/src/test/java/org/apache/commons/text/lookup/StringLookupFactoryTest.java b/src/test/java/org/apache/commons/text/lookup/StringLookupFactoryTest.java index e0fdf8abe7..97ab564436 100644 --- a/src/test/java/org/apache/commons/text/lookup/StringLookupFactoryTest.java +++ b/src/test/java/org/apache/commons/text/lookup/StringLookupFactoryTest.java @@ -293,8 +293,9 @@ void testXmlStringLookup() { @Test void testXmlStringLookupExternalEntityOff() { - assertThrows(IllegalArgumentException.class, - () -> StringLookupFactory.INSTANCE.xmlStringLookup().apply(XmlStringLookupTest.DOC_DIR + "document-entity-ref.xml:/document/content")); + XmlStringLookupTest.assertBlocksOrDoesNotLeak( + () -> StringLookupFactory.INSTANCE.xmlStringLookup().apply(XmlStringLookupTest.DOC_DIR + "document-entity-ref.xml:/document/content"), + XmlStringLookupTest.DATA); } @Test diff --git a/src/test/java/org/apache/commons/text/lookup/XmlStringLookupTest.java b/src/test/java/org/apache/commons/text/lookup/XmlStringLookupTest.java index 862fdf812d..8c2309e1b0 100644 --- a/src/test/java/org/apache/commons/text/lookup/XmlStringLookupTest.java +++ b/src/test/java/org/apache/commons/text/lookup/XmlStringLookupTest.java @@ -29,6 +29,7 @@ import java.util.Collections; import java.util.HashMap; import java.util.Map; +import java.util.function.Supplier; import javax.xml.XMLConstants; @@ -50,6 +51,19 @@ class XmlStringLookupTest { private static final String DOC_RELATIVE = DOC_DIR + "document.xml"; private static final String DOC_ROOT = "/document.xml"; + /** + * Asserts the secure contract for an external reference: the parser either rejects the document or parses it + * with the reference resolved to empty content, but the external content never appears in the result. + */ + static void assertBlocksOrDoesNotLeak(final Supplier lookup, final String external) { + try { + final String result = lookup.get(); + assertFalse(result != null && result.contains(external), () -> "external content leaked: " + result); + } catch (final IllegalArgumentException e) { + // the parser rejected the external reference outright + } + } + static void assertLookup(final StringLookup xmlStringLookup) { assertNotNull(xmlStringLookup); assertInstanceOf(XmlStringLookup.class, xmlStringLookup); @@ -64,8 +78,8 @@ void testBadXPath() { @Test void testExternalEntityOff() { - assertThrows(IllegalArgumentException.class, - () -> new XmlStringLookup(XmlStringLookup.DEFAULT_XML_FEATURES, EMPTY_MAP).apply(DOC_DIR + "document-entity-ref.xml:/document/content")); + assertBlocksOrDoesNotLeak( + () -> new XmlStringLookup(XmlStringLookup.DEFAULT_XML_FEATURES, EMPTY_MAP).apply(DOC_DIR + "document-entity-ref.xml:/document/content"), DATA); } @Test @@ -78,7 +92,8 @@ void testExternalEntityOn() { @Test void testInterpolatorExternalDtdOff() { final StringSubstitutor stringSubstitutor = StringSubstitutor.createInterpolator(); - assertThrows(IllegalArgumentException.class, () -> stringSubstitutor.replace("${xml:" + DOC_DIR + "document-external-dtd.xml:/document/content}")); + assertBlocksOrDoesNotLeak(() -> stringSubstitutor.replace("${xml:" + DOC_DIR + "document-external-dtd.xml:/document/content}"), + "This is an external entity."); } @Test @@ -91,7 +106,7 @@ void testInterpolatorExternalDtdOn() { @Test void testInterpolatorExternalEntityOff() { final StringSubstitutor stringSubstitutor = StringSubstitutor.createInterpolator(); - assertThrows(IllegalArgumentException.class, () -> stringSubstitutor.replace("${xml:" + DOC_DIR + "document-entity-ref.xml:/document/content}")); + assertBlocksOrDoesNotLeak(() -> stringSubstitutor.replace("${xml:" + DOC_DIR + "document-entity-ref.xml:/document/content}"), DATA); } @Test @@ -104,13 +119,13 @@ void testInterpolatorExternalEntityOffOverride() { @Test void testInterpolatorExternalEntityOn() { final StringSubstitutor stringSubstitutor = StringSubstitutor.createInterpolator(); - assertThrows(IllegalArgumentException.class, () -> stringSubstitutor.replace("${xml:" + DOC_DIR + "document-entity-ref.xml:/document/content}")); + assertBlocksOrDoesNotLeak(() -> stringSubstitutor.replace("${xml:" + DOC_DIR + "document-entity-ref.xml:/document/content}"), DATA); } @Test void testInterpolatorExternalEntityOnOverride() { final StringSubstitutor stringSubstitutor = StringSubstitutor.createInterpolator(); - assertThrows(IllegalArgumentException.class, () -> stringSubstitutor.replace("${xml:" + DOC_DIR + "document-entity-ref.xml:/document/content}")); + assertBlocksOrDoesNotLeak(() -> stringSubstitutor.replace("${xml:" + DOC_DIR + "document-entity-ref.xml:/document/content}"), DATA); } @Test From ac4f28fc0d2e43928893f864e3baac3efb0a8486 Mon Sep 17 00:00:00 2001 From: "Piotr P. Karwasz" Date: Thu, 3 Sep 2026 07:04:11 +0200 Subject: [PATCH 2/2] Use the Commons Secure XML 1.0.0 release candidate Bump org.apache.commons:commons-secure-xml from 1.0.0-SNAPSHOT to 1.0.0 and add the temporary staging repository https://repository.apache.org/content/repositories/orgapachecommons-1962/ after Central, so the vote gets downstream CI results. Drop the -Puse-apache-snapshots profile from the CI workflows, which the release version no longer needs. Remove the staging repository once 1.0.0 is released. Assisted-By: Claude Fable 5.1 Claude-Session: https://claude.ai/code/session_0167e29ScPEdfzJnEFm95imK --- .github/workflows/codeql-analysis.yml | 2 -- .github/workflows/maven.yml | 2 +- pom.xml | 23 ++++++++++++++++++++++- 3 files changed, 23 insertions(+), 4 deletions(-) diff --git a/.github/workflows/codeql-analysis.yml b/.github/workflows/codeql-analysis.yml index 9a2a536446..eaf7ff5225 100644 --- a/.github/workflows/codeql-analysis.yml +++ b/.github/workflows/codeql-analysis.yml @@ -70,8 +70,6 @@ jobs: # If this step fails, then you should remove it and run the build manually (see below) - name: Autobuild uses: github/codeql-action/autobuild@cdf488f595d80d6e07e03d4674febd5ab45fa938 # v4.37.9 - env: - MAVEN_ARGS: -Puse-apache-snapshots # ℹī¸ Command-line programs to run using the OS shell. # 📚 https://git.io/JvXDl diff --git a/.github/workflows/maven.yml b/.github/workflows/maven.yml index 4f58b6e53d..5a8b24254a 100644 --- a/.github/workflows/maven.yml +++ b/.github/workflows/maven.yml @@ -49,4 +49,4 @@ jobs: java-version: ${{ matrix.java }} cache: 'maven' - name: Build with Maven - run: mvn --errors --show-version --batch-mode --no-transfer-progress -Dpolyglot.engine.WarnInterpreterOnly=false -Puse-apache-snapshots + run: mvn --errors --show-version --batch-mode --no-transfer-progress -Dpolyglot.engine.WarnInterpreterOnly=false diff --git a/pom.xml b/pom.xml index 649e0f71a1..42a20a8a6a 100644 --- a/pom.xml +++ b/pom.xml @@ -81,6 +81,27 @@ 0.99 0.97 + + + + central + Central Repository + https://repo.maven.apache.org/maven2 + + false + + + + + apache.commons.staging + Apache Commons Secure XML 1.0.0 release candidate + https://repository.apache.org/content/repositories/orgapachecommons-1962/ + + false + + + + org.apache.commons @@ -90,7 +111,7 @@ org.apache.commons commons-secure-xml - 1.0.0-SNAPSHOT + 1.0.0