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

pjfanning pushed a commit to branch trunk
in repository https://gitbox.apache.org/repos/asf/poi-xmlbeans.git


The following commit(s) were added to refs/heads/trunk by this push:
     new c50b9d69 join text split by a pi in 
ValidatingXMLStreamReader.bufferText (#140)
c50b9d69 is described below

commit c50b9d695a39d61f21b7ce7120affa1aeb99bdb7
Author: aizu-m <[email protected]>
AuthorDate: Mon Oct 19 14:47:08 2026 +0530

    join text split by a pi in ValidatingXMLStreamReader.bufferText (#140)
    
    * join text split by a pi in ValidatingXMLStreamReader.bufferText
    
    * pin the caller-visible events around a pi in ValidatingXMLStreamReader
    
    The packing reader is also what the caller reads, so a comment or pi
    after text is now consumed into the merged CHARACTERS event while one
    before any text is still passed on. Add a test that fixes that event
    sequence, and mark the intended fall-through in bufferText.
    
    Co-Authored-By: Claude Opus 5.5 <[email protected]>
    
    ---------
    
    Co-authored-by: PJ Fanning <[email protected]>
    Co-authored-by: Claude Opus 5.5 <[email protected]>
---
 .../impl/validator/ValidatingXMLStreamReader.java  |  6 +-
 .../checkin/ValidatingXMLStreamReaderTests.java    | 84 ++++++++++++++++++++++
 2 files changed, 89 insertions(+), 1 deletion(-)

diff --git 
a/src/main/java/org/apache/xmlbeans/impl/validator/ValidatingXMLStreamReader.java
 
b/src/main/java/org/apache/xmlbeans/impl/validator/ValidatingXMLStreamReader.java
index b314d312..08b5265b 100644
--- 
a/src/main/java/org/apache/xmlbeans/impl/validator/ValidatingXMLStreamReader.java
+++ 
b/src/main/java/org/apache/xmlbeans/impl/validator/ValidatingXMLStreamReader.java
@@ -189,9 +189,13 @@ public class ValidatingXMLStreamReader
                 case XMLEvent.SPACE:
                     if (super.hasText())
                         _buffer.append(super.getText());
+                    // fall through
 
                 case XMLEvent.COMMENT:
-                    //ignore
+                case XMLEvent.PROCESSING_INSTRUCTION:
+                    // neither contributes character data, so text on both
+                    // sides of it is one value - same as the Cur.COMMENT /
+                    // Cur.PROCINST handling in the store's Validate
                     continue;
                 default:
                     return;
diff --git 
a/src/test/java/ValidatingXSRTests/checkin/ValidatingXMLStreamReaderTests.java 
b/src/test/java/ValidatingXSRTests/checkin/ValidatingXMLStreamReaderTests.java
index aba74641..7da0ce75 100755
--- 
a/src/test/java/ValidatingXSRTests/checkin/ValidatingXMLStreamReaderTests.java
+++ 
b/src/test/java/ValidatingXSRTests/checkin/ValidatingXMLStreamReaderTests.java
@@ -16,6 +16,7 @@ package ValidatingXSRTests.checkin;
 
 import org.apache.xmlbeans.*;
 import org.apache.xmlbeans.impl.validator.ValidatingXMLStreamReader;
+import org.apache.xmlbeans.impl.xb.xsdschema.SchemaDocument;
 import org.junit.jupiter.api.Test;
 import org.junit.jupiter.params.ParameterizedTest;
 import org.junit.jupiter.params.provider.ValueSource;
@@ -25,15 +26,21 @@ import tools.util.JarUtil;
 import javax.xml.namespace.NamespaceContext;
 import javax.xml.namespace.QName;
 import javax.xml.stream.Location;
+import javax.xml.stream.XMLInputFactory;
 import javax.xml.stream.XMLStreamException;
 import javax.xml.stream.XMLStreamReader;
 import javax.xml.stream.events.XMLEvent;
 import java.io.File;
 import java.io.FileInputStream;
 import java.io.FileNotFoundException;
+import java.io.StringReader;
 import java.util.ArrayList;
+import java.util.Arrays;
 import java.util.Collection;
+import java.util.List;
 
+import static org.junit.jupiter.api.Assertions.assertEquals;
+import static org.junit.jupiter.api.Assertions.assertFalse;
 import static org.junit.jupiter.api.Assertions.assertTrue;
 
 public class ValidatingXMLStreamReaderTests {
@@ -383,4 +390,81 @@ public class ValidatingXMLStreamReaderTests {
 
         assertTrue(valXsr.isValid(), "Content2 validation is broken.");
     }
+
+    @ParameterizedTest
+    @ValueSource(strings = {
+        "<count xmlns='urn:t'>5<?pi x?>5</count>",
+        "<count xmlns='urn:t'>5<?pi x?><!--c-->5</count>",
+        "<count xmlns='urn:t'>5<!--c-->5</count>"
+    })
+    void testTextSplitByProcessingInstruction(String doc) throws Exception {
+        // a comment or pi between two text chunks contributes no character 
data,
+        // so the element value is 55 and must fail maxInclusive=9; the 
validator
+        // only checks the first TEXT event, so the chunks have to arrive as 
one
+        String xsd =
+            "<xs:schema xmlns:xs='http://www.w3.org/2001/XMLSchema' 
targetNamespace='urn:t'>" +
+            "  <xs:element name='count'>" +
+            "    <xs:simpleType><xs:restriction base='xs:int'><xs:maxInclusive 
value='9'/></xs:restriction></xs:simpleType>" +
+            "  </xs:element>" +
+            "</xs:schema>";
+        SchemaTypeLoader stl = XmlBeans.loadXsd(new 
XmlObject[]{SchemaDocument.Factory.parse(xsd)});
+
+        XMLStreamReader xsr = 
XMLInputFactory.newInstance().createXMLStreamReader(new StringReader(doc));
+        Collection<XmlError> errors = new ArrayList<>();
+
+        ValidatingXMLStreamReader valXsr = new ValidatingXMLStreamReader();
+        valXsr.init(xsr, false, null, stl, null, errors);
+
+        while (valXsr.hasNext()) {
+            valXsr.next();
+        }
+
+        assertFalse(valXsr.isValid(), "Text split by a pi was validated in 
pieces: " + doc);
+        assertEquals(1, errors.size(), errors.toString());
+        assertEquals("cvc-maxInclusive-valid", 
errors.iterator().next().getErrorCode());
+    }
+
+    @Test
+    void testEventsSeenAroundProcessingInstruction() throws Exception {
+        // the reader passes events through to its caller, so packing text also
+        // decides what the caller sees: a comment or pi after text is consumed
+        // into the merged CHARACTERS event, one before any text is passed on
+        String xsd =
+            "<xs:schema xmlns:xs='http://www.w3.org/2001/XMLSchema' 
targetNamespace='urn:t'>" +
+            "  <xs:element name='v' type='xs:string'/>" +
+            "</xs:schema>";
+        SchemaTypeLoader stl = XmlBeans.loadXsd(new 
XmlObject[]{SchemaDocument.Factory.parse(xsd)});
+        String doc = "<v xmlns='urn:t'><?lead x?>a<?pi x?><!--c-->b<?tail 
x?></v>";
+
+        XMLStreamReader xsr = 
XMLInputFactory.newInstance().createXMLStreamReader(new StringReader(doc));
+        Collection<XmlError> errors = new ArrayList<>();
+
+        ValidatingXMLStreamReader valXsr = new ValidatingXMLStreamReader();
+        valXsr.init(xsr, false, null, stl, null, errors);
+
+        List<String> events = new ArrayList<>();
+        while (valXsr.hasNext()) {
+            int evType = valXsr.next();
+            switch (evType) {
+                case XMLEvent.START_ELEMENT:
+                    events.add("start " + valXsr.getLocalName());
+                    break;
+                case XMLEvent.END_ELEMENT:
+                    events.add("end " + valXsr.getLocalName());
+                    break;
+                case XMLEvent.PROCESSING_INSTRUCTION:
+                    events.add("pi " + valXsr.getPITarget());
+                    break;
+                case XMLEvent.CHARACTERS:
+                    events.add("text " + valXsr.getText());
+                    break;
+                default:
+                    events.add("event " + evType);
+            }
+        }
+
+        assertEquals(Arrays.asList("start v", "pi lead", "text ab", "end v", 
"event " + XMLEvent.END_DOCUMENT),
+            events);
+        assertTrue(valXsr.isValid(), errors.toString());
+    }
 }


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to