This is an automated email from the ASF dual-hosted git repository.
ggregory pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/commons-io.git
The following commit(s) were added to refs/heads/master by this push:
new 129eb40c XmlStreamReader can't parse XML an document with an external
parsed entity prolog
129eb40c is described below
commit 129eb40c2a2b3fcfed1d73b313a1a79578b79341
Author: Gary Gregory <[email protected]>
AuthorDate: Tue Jan 2 11:25:10 2024 -0500
XmlStreamReader can't parse XML an document with an external parsed
entity prolog
---
src/changes/changes.xml | 3 ++-
.../java/org/apache/commons/io/input/XmlStreamReader.java | 2 +-
.../org/apache/commons/io/input/XmlStreamReaderTest.java | 13 ++++++++++++-
3 files changed, 15 insertions(+), 3 deletions(-)
diff --git a/src/changes/changes.xml b/src/changes/changes.xml
index 7508b585..078be7b2 100644
--- a/src/changes/changes.xml
+++ b/src/changes/changes.xml
@@ -88,7 +88,8 @@ The <action> type attribute can be add,update,fix,remove.
<action dev="ggregory" type="fix" issue="IO-807" due-to="Elliotte Rusty
Harold, Gary Gregory">Characterization test for broken symlinks when copying
directories #547.</action>
<action dev="ggregory" type="fix" due-to="Gary
Gregory">ClosedInputStream.read(byte[], int, int) does not always return
-1.</action>
<action dev="ggregory" type="fix" due-to="Gary
Gregory">ClosedOutputStream.write(byte[], int, int) does not always throw
IOException.</action>
- <action dev="ggregory" type="fix" due-to="Sylwester Lachiewicz, Gary
Gregory">XmlStreamReader can't parse XML document with multi-line prolog
#550.</action>
+ <action dev="ggregory" type="fix" due-to="Sylwester Lachiewicz, Gary
Gregory">XmlStreamReader can't parse an XML document with a multi-line prolog
#550.</action>
+ <action dev="ggregory" type="fix" due-to="Andreas Hubold, Gary
Gregory">XmlStreamReader can't parse XML an document with an external parsed
entity prolog.</action>
<!-- Add -->
<action dev="ggregory" type="add" due-to="Gary
Gregory">Add and use PathUtils.getFileName(Path, Function<Path,
R>).</action>
<action dev="ggregory" type="add" due-to="Gary
Gregory">Add and use PathUtils.getFileNameString().</action>
diff --git a/src/main/java/org/apache/commons/io/input/XmlStreamReader.java
b/src/main/java/org/apache/commons/io/input/XmlStreamReader.java
index 21ce82db..37d1596e 100644
--- a/src/main/java/org/apache/commons/io/input/XmlStreamReader.java
+++ b/src/main/java/org/apache/commons/io/input/XmlStreamReader.java
@@ -228,7 +228,7 @@ public class XmlStreamReader extends Reader {
public static final Pattern ENCODING_PATTERN = Pattern.compile(
// @formatter:off
"^<\\?xml\\s+"
- + "version\\s*=\\s*(?:(?:\"1\\.[0-9]+\")|(?:'1.[0-9]+'))\\s+"
+ + "(?:version\\s*=\\s*(?:(?:\"1\\.[0-9]+\")|(?:'1.[0-9]+'))\\s+)??"
+ "encoding\\s*=\\s*"
+ "((?:\"[A-Za-z0-9][A-Za-z0-9._+:-]*\")" // double-quoted
+ "|(?:'[A-Za-z0-9][A-Za-z0-9._+:-]*'))", // single-quoted
diff --git a/src/test/java/org/apache/commons/io/input/XmlStreamReaderTest.java
b/src/test/java/org/apache/commons/io/input/XmlStreamReaderTest.java
index 46379abb..4260a1aa 100644
--- a/src/test/java/org/apache/commons/io/input/XmlStreamReaderTest.java
+++ b/src/test/java/org/apache/commons/io/input/XmlStreamReaderTest.java
@@ -64,6 +64,7 @@ public class XmlStreamReaderTest {
private static final String UTF_32BE = "UTF-32BE";
private static final String UTF_8 = StandardCharsets.UTF_8.name();
+ private static final String XML7 = "xml-prolog-encoding-no-version";
private static final String XML6 = "xml-prolog-encoding-new-line";
private static final String XML5 =
"xml-prolog-encoding-spaced-single-quotes";
private static final String XML4 = "xml-prolog-encoding-single-quotes";
@@ -107,9 +108,13 @@ public class XmlStreamReaderTest {
private static final MessageFormat XML_WITH_PROLOG = new MessageFormat(
"<?xml version=\"1.0\"?>\n<root>{2}</root>");
+
private static final MessageFormat XML_WITH_PROLOG_AND_ENCODING_NEW_LINES
= new MessageFormat(
"<?xml\nversion\n=\n\"1.0\"\nencoding\n=\n\"{1}\"\n?>\n<root>{2}</root>");
+ private static final MessageFormat XML_EXTERNAL_PARSED_ENTITY_NO_VERSION =
new MessageFormat(
+ "<?xml\nencoding\n=\n\"{1}\"\n?>\n<root>{2}</root>");
+
private static final MessageFormat
XML_WITH_PROLOG_AND_ENCODING_DOUBLE_QUOTES = new MessageFormat(
"<?xml version=\"1.0\" encoding=\"{1}\"?>\n<root>{2}</root>");
@@ -131,6 +136,7 @@ public class XmlStreamReaderTest {
XMLs.put(XML4, XML_WITH_PROLOG_AND_ENCODING_SINGLE_QUOTES);
XMLs.put(XML5, XML_WITH_PROLOG_AND_ENCODING_SPACED_SINGLE_QUOTES);
XMLs.put(XML6, XML_WITH_PROLOG_AND_ENCODING_NEW_LINES);
+ XMLs.put(XML7, XML_EXTERNAL_PARSED_ENTITY_NO_VERSION);
}
/**
@@ -637,5 +643,10 @@ public class XmlStreamReaderTest {
xmlReader = new XmlStreamReader(is);
assertEquals(xmlReader.getEncoding(), encoding);
xmlReader.close();
- }
+
+ is = getXmlInputStream("no-bom", XML7, encoding, encoding);
+ xmlReader = new XmlStreamReader(is);
+ assertEquals(xmlReader.getEncoding(), encoding);
+ xmlReader.close();
+}
}