Skip to content

MXParser tokenization fails when PI is before first tag (fixes #7) #12

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 14, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 3 additions & 8 deletions src/main/java/org/codehaus/plexus/util/xml/pull/MXParser.java
Original file line number Diff line number Diff line change
Expand Up @@ -1822,13 +1822,9 @@ else if ( ch == '\uFFFD' )
{
// check if it is 'xml'
// deal with XMLDecl
boolean isXMLDecl = parsePI();
parsePI();
if ( tokenize )
{
if ( isXMLDecl )
{
return eventType = START_DOCUMENT;
}
return eventType = PROCESSING_INSTRUCTION;
}
}
Expand Down Expand Up @@ -3111,7 +3107,7 @@ else if ( ch == '\n' )
}
}

private boolean parsePI()
private void parsePI()
throws XmlPullParserException, IOException
{
// implements XML 1.0 Section 2.6 Processing Instructions
Expand Down Expand Up @@ -3213,7 +3209,7 @@ else if ( ch == '<' )
final int off = piTargetStart + 3;
final int len = pos - 2 - off;
xmlDeclContent = newString( buf, off, len );
return false;
return;
}
}
}
Expand Down Expand Up @@ -3291,7 +3287,6 @@ else if ( ch == '\n' )
--pcEnd;
}
}
return true;
}

// protected final static char[] VERSION = {'v','e','r','s','i','o','n'};
Expand Down
42 changes: 42 additions & 0 deletions src/test/java/org/codehaus/plexus/util/xml/pull/MXParserTest.java
Original file line number Diff line number Diff line change
Expand Up @@ -1622,4 +1622,46 @@ public void testUnicode() throws IOException {
fail( "should not raise exception: " + e );
}
}

@Test
public void testProcessingInstructionTokenizeBeforeFirstTag()
throws Exception
{
String input = "<?a?><test>nnn</test>";

MXParser parser = new MXParser();
parser.setInput( new StringReader( input ) );

assertEquals( XmlPullParser.START_DOCUMENT, parser.getEventType() );
assertEquals( XmlPullParser.PROCESSING_INSTRUCTION, parser.nextToken() );
assertEquals( "a", parser.getText() );
assertEquals( XmlPullParser.START_TAG, parser.nextToken() );
assertEquals( "test", parser.getName() );
assertEquals( XmlPullParser.TEXT, parser.nextToken() );
assertEquals( "nnn", parser.getText() );
assertEquals( XmlPullParser.END_TAG, parser.nextToken() );
assertEquals( XmlPullParser.END_DOCUMENT, parser.nextToken() );
}

@Test
public void testProcessingInstructionTokenizeAfterXMLDeclAndBeforeFirstTag()
throws Exception
{
String input = "<?xml version=\"1.0\" encoding=\"UTF-8\"?><?a?><test>nnn</test>";

MXParser parser = new MXParser();
parser.setInput( new StringReader( input ) );

assertEquals( XmlPullParser.START_DOCUMENT, parser.getEventType() );
assertEquals( XmlPullParser.PROCESSING_INSTRUCTION, parser.nextToken() );
assertEquals( "xml version=\"1.0\" encoding=\"UTF-8\"", parser.getText() );
assertEquals( XmlPullParser.PROCESSING_INSTRUCTION, parser.nextToken() );
assertEquals( "a", parser.getText() );
assertEquals( XmlPullParser.START_TAG, parser.nextToken() );
assertEquals( "test", parser.getName() );
assertEquals( XmlPullParser.TEXT, parser.nextToken() );
assertEquals( "nnn", parser.getText() );
assertEquals( XmlPullParser.END_TAG, parser.nextToken() );
assertEquals( XmlPullParser.END_DOCUMENT, parser.nextToken() );
}
}