Bug 760183: REGRESSION (v2.9.3): XML push parser fails with bogus UTF-8 encoding error when multi-byte character in large CDATA section is split across buffer <https://bugzilla.gnome.org/show_bug.cgi?id=760183>
* parser.c:
(xmlCheckCdataPush): Add 'complete' argument to describe whether
the buffer passed in is the whole CDATA buffer, or if there is
more data to parse. If there is more data to parse, don't
return a negative value for an invalid multi-byte UTF-8
character that is split between buffers.
(xmlParseTryOrFinish): Pass 'complete' argument to
xmlCheckCdataPush() as appropriate.
* result/cdata-2-byte-UTF-8.xml: Added.
* result/cdata-2-byte-UTF-8.xml.rde: Added.
* result/cdata-2-byte-UTF-8.xml.rdr: Added.
* result/cdata-2-byte-UTF-8.xml.sax: Added.
* result/cdata-2-byte-UTF-8.xml.sax2: Added.
* result/cdata-3-byte-UTF-8.xml: Added.
* result/cdata-3-byte-UTF-8.xml.rde: Added.
* result/cdata-3-byte-UTF-8.xml.rdr: Added.
* result/cdata-3-byte-UTF-8.xml.sax: Added.
* result/cdata-3-byte-UTF-8.xml.sax2: Added.
* result/cdata-4-byte-UTF-8.xml: Added.
* result/cdata-4-byte-UTF-8.xml.rde: Added.
* result/cdata-4-byte-UTF-8.xml.rdr: Added.
* result/cdata-4-byte-UTF-8.xml.sax: Added.
* result/cdata-4-byte-UTF-8.xml.sax2: Added.
* result/noent/cdata-2-byte-UTF-8.xml: Added.
* result/noent/cdata-3-byte-UTF-8.xml: Added.
* result/noent/cdata-4-byte-UTF-8.xml: Added.
* test/cdata-2-byte-UTF-8.xml: Added.
* test/cdata-3-byte-UTF-8.xml: Added.
* test/cdata-4-byte-UTF-8.xml: Added.
- Add tests and results. Only 'make Readertests XMLPushtests'
fails prior to the fix.
diff --git a/parser.c b/parser.c
index 0677030..9604a72 100644
--- a/parser.c
+++ b/parser.c
@@ -11210,8 +11210,9 @@
}
/**
* xmlCheckCdataPush:
- * @cur: pointer to the bock of characters
+ * @cur: pointer to the block of characters
* @len: length of the block in bytes
+ * @complete: 1 if complete CDATA block is passed in, 0 if partial block
*
* Check that the block of characters is okay as SCdata content [20]
*
@@ -11219,7 +11220,7 @@
* UTF-8 error occured otherwise
*/
static int
-xmlCheckCdataPush(const xmlChar *utf, int len) {
+xmlCheckCdataPush(const xmlChar *utf, int len, int complete) {
int ix;
unsigned char c;
int codepoint;
@@ -11237,7 +11238,7 @@
else
return(-ix);
} else if ((c & 0xe0) == 0xc0) {/* 2-byte code, starts with 110 */
- if (ix + 2 > len) return(-ix);
+ if (ix + 2 > len) return(complete ? -ix : ix);
if ((utf[ix+1] & 0xc0 ) != 0x80)
return(-ix);
codepoint = (utf[ix] & 0x1f) << 6;
@@ -11246,7 +11247,7 @@
return(-ix);
ix += 2;
} else if ((c & 0xf0) == 0xe0) {/* 3-byte code, starts with 1110 */
- if (ix + 3 > len) return(-ix);
+ if (ix + 3 > len) return(complete ? -ix : ix);
if (((utf[ix+1] & 0xc0) != 0x80) ||
((utf[ix+2] & 0xc0) != 0x80))
return(-ix);
@@ -11257,7 +11258,7 @@
return(-ix);
ix += 3;
} else if ((c & 0xf8) == 0xf0) {/* 4-byte code, starts with 11110 */
- if (ix + 4 > len) return(-ix);
+ if (ix + 4 > len) return(complete ? -ix : ix);
if (((utf[ix+1] & 0xc0) != 0x80) ||
((utf[ix+2] & 0xc0) != 0x80) ||
((utf[ix+3] & 0xc0) != 0x80))
@@ -11772,7 +11773,7 @@
int tmp;
tmp = xmlCheckCdataPush(ctxt->input->cur,
- XML_PARSER_BIG_BUFFER_SIZE);
+ XML_PARSER_BIG_BUFFER_SIZE, 0);
if (tmp < 0) {
tmp = -tmp;
ctxt->input->cur += tmp;
@@ -11795,7 +11796,7 @@
} else {
int tmp;
- tmp = xmlCheckCdataPush(ctxt->input->cur, base);
+ tmp = xmlCheckCdataPush(ctxt->input->cur, base, 1);
if ((tmp < 0) || (tmp != base)) {
tmp = -tmp;
ctxt->input->cur += tmp;
diff --git a/result/cdata-2-byte-UTF-8.xml b/result/cdata-2-byte-UTF-8.xml
new file mode 100644
index 0000000..8552efc
--- /dev/null
+++ b/result/cdata-2-byte-UTF-8.xml
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- This tests that two-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). -->
+<doc>
+<p><![CDATA[ČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČ]]></p>
+<p><![CDATA[ ČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČ]]></p>
+</doc>
diff --git a/result/cdata-2-byte-UTF-8.xml.rde b/result/cdata-2-byte-UTF-8.xml.rde
new file mode 100644
index 0000000..2eb2940
--- /dev/null
+++ b/result/cdata-2-byte-UTF-8.xml.rde
@@ -0,0 +1,15 @@
+0 8 #comment 0 1 This tests that two-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes).
+0 1 doc 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 ČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČ
+1 15 p 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 ČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČ
+1 15 p 0 0
+1 14 #text 0 1
+
+0 15 doc 0 0
diff --git a/result/cdata-2-byte-UTF-8.xml.rdr b/result/cdata-2-byte-UTF-8.xml.rdr
new file mode 100644
index 0000000..2eb2940
--- /dev/null
+++ b/result/cdata-2-byte-UTF-8.xml.rdr
@@ -0,0 +1,15 @@
+0 8 #comment 0 1 This tests that two-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes).
+0 1 doc 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 ČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČ
+1 15 p 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 ČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČ
+1 15 p 0 0
+1 14 #text 0 1
+
+0 15 doc 0 0
diff --git a/result/cdata-2-byte-UTF-8.xml.sax b/result/cdata-2-byte-UTF-8.xml.sax
new file mode 100644
index 0000000..f397f6a
--- /dev/null
+++ b/result/cdata-2-byte-UTF-8.xml.sax
@@ -0,0 +1,18 @@
+SAX.setDocumentLocator()
+SAX.startDocument()
+SAX.comment( This tests that two-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). )
+SAX.startElement(doc)
+SAX.characters(
+, 1)
+SAX.startElement(p)
+SAX.pcdata(ČČČČČČČČČČ, 1200)
+SAX.endElement(p)
+SAX.characters(
+, 1)
+SAX.startElement(p)
+SAX.pcdata( ÄÄÄÄÄÄÄÄÄÄ, 1201)
+SAX.endElement(p)
+SAX.characters(
+, 1)
+SAX.endElement(doc)
+SAX.endDocument()
diff --git a/result/cdata-2-byte-UTF-8.xml.sax2 b/result/cdata-2-byte-UTF-8.xml.sax2
new file mode 100644
index 0000000..2da2d50
--- /dev/null
+++ b/result/cdata-2-byte-UTF-8.xml.sax2
@@ -0,0 +1,18 @@
+SAX.setDocumentLocator()
+SAX.startDocument()
+SAX.comment( This tests that two-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). )
+SAX.startElementNs(doc, NULL, NULL, 0, 0, 0)
+SAX.characters(
+, 1)
+SAX.startElementNs(p, NULL, NULL, 0, 0, 0)
+SAX.pcdata(ČČČČČČČČČČ, 1200)
+SAX.endElementNs(p, NULL, NULL)
+SAX.characters(
+, 1)
+SAX.startElementNs(p, NULL, NULL, 0, 0, 0)
+SAX.pcdata( ÄÄÄÄÄÄÄÄÄÄ, 1201)
+SAX.endElementNs(p, NULL, NULL)
+SAX.characters(
+, 1)
+SAX.endElementNs(doc, NULL, NULL)
+SAX.endDocument()
diff --git a/result/cdata-3-byte-UTF-8.xml b/result/cdata-3-byte-UTF-8.xml
new file mode 100644
index 0000000..b959a12
--- /dev/null
+++ b/result/cdata-3-byte-UTF-8.xml
@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- This tests that three-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). -->
+<doc>
+<p><![CDATA[牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛]]></p>
+<p><![CDATA[ 牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛]]></p>
+<p><![CDATA[ 牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛]]></p>
+</doc>
diff --git a/result/cdata-3-byte-UTF-8.xml.rde b/result/cdata-3-byte-UTF-8.xml.rde
new file mode 100644
index 0000000..3f4d1c5
--- /dev/null
+++ b/result/cdata-3-byte-UTF-8.xml.rde
@@ -0,0 +1,20 @@
+0 8 #comment 0 1 This tests that three-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes).
+0 1 doc 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛
+1 15 p 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛
+1 15 p 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛
+1 15 p 0 0
+1 14 #text 0 1
+
+0 15 doc 0 0
diff --git a/result/cdata-3-byte-UTF-8.xml.rdr b/result/cdata-3-byte-UTF-8.xml.rdr
new file mode 100644
index 0000000..3f4d1c5
--- /dev/null
+++ b/result/cdata-3-byte-UTF-8.xml.rdr
@@ -0,0 +1,20 @@
+0 8 #comment 0 1 This tests that three-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes).
+0 1 doc 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛
+1 15 p 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛
+1 15 p 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛
+1 15 p 0 0
+1 14 #text 0 1
+
+0 15 doc 0 0
diff --git a/result/cdata-3-byte-UTF-8.xml.sax b/result/cdata-3-byte-UTF-8.xml.sax
new file mode 100644
index 0000000..2f73e7c
--- /dev/null
+++ b/result/cdata-3-byte-UTF-8.xml.sax
@@ -0,0 +1,23 @@
+SAX.setDocumentLocator()
+SAX.startDocument()
+SAX.comment( This tests that three-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). )
+SAX.startElement(doc)
+SAX.characters(
+, 1)
+SAX.startElement(p)
+SAX.pcdata(ççççççç, 1200)
+SAX.endElement(p)
+SAX.characters(
+, 1)
+SAX.startElement(p)
+SAX.pcdata( ççççççç, 1201)
+SAX.endElement(p)
+SAX.characters(
+, 1)
+SAX.startElement(p)
+SAX.pcdata( 牛牛牛牛牛牛, 1202)
+SAX.endElement(p)
+SAX.characters(
+, 1)
+SAX.endElement(doc)
+SAX.endDocument()
diff --git a/result/cdata-3-byte-UTF-8.xml.sax2 b/result/cdata-3-byte-UTF-8.xml.sax2
new file mode 100644
index 0000000..3969579
--- /dev/null
+++ b/result/cdata-3-byte-UTF-8.xml.sax2
@@ -0,0 +1,23 @@
+SAX.setDocumentLocator()
+SAX.startDocument()
+SAX.comment( This tests that three-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). )
+SAX.startElementNs(doc, NULL, NULL, 0, 0, 0)
+SAX.characters(
+, 1)
+SAX.startElementNs(p, NULL, NULL, 0, 0, 0)
+SAX.pcdata(ççççççç, 1200)
+SAX.endElementNs(p, NULL, NULL)
+SAX.characters(
+, 1)
+SAX.startElementNs(p, NULL, NULL, 0, 0, 0)
+SAX.pcdata( ççççççç, 1201)
+SAX.endElementNs(p, NULL, NULL)
+SAX.characters(
+, 1)
+SAX.startElementNs(p, NULL, NULL, 0, 0, 0)
+SAX.pcdata( 牛牛牛牛牛牛, 1202)
+SAX.endElementNs(p, NULL, NULL)
+SAX.characters(
+, 1)
+SAX.endElementNs(doc, NULL, NULL)
+SAX.endDocument()
diff --git a/result/cdata-4-byte-UTF-8.xml b/result/cdata-4-byte-UTF-8.xml
new file mode 100644
index 0000000..4d1d9a8
--- /dev/null
+++ b/result/cdata-4-byte-UTF-8.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- This tests that four-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). -->
+<doc>
+<p><![CDATA[🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦]]></p>
+<p><![CDATA[ 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦]]></p>
+<p><![CDATA[ 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦]]></p>
+<p><![CDATA[ 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦]]></p>
+</doc>
diff --git a/result/cdata-4-byte-UTF-8.xml.rde b/result/cdata-4-byte-UTF-8.xml.rde
new file mode 100644
index 0000000..437b79e
--- /dev/null
+++ b/result/cdata-4-byte-UTF-8.xml.rde
@@ -0,0 +1,25 @@
+0 8 #comment 0 1 This tests that four-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes).
+0 1 doc 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦
+1 15 p 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦
+1 15 p 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦
+1 15 p 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦
+1 15 p 0 0
+1 14 #text 0 1
+
+0 15 doc 0 0
diff --git a/result/cdata-4-byte-UTF-8.xml.rdr b/result/cdata-4-byte-UTF-8.xml.rdr
new file mode 100644
index 0000000..437b79e
--- /dev/null
+++ b/result/cdata-4-byte-UTF-8.xml.rdr
@@ -0,0 +1,25 @@
+0 8 #comment 0 1 This tests that four-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes).
+0 1 doc 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦
+1 15 p 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦
+1 15 p 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦
+1 15 p 0 0
+1 14 #text 0 1
+
+1 1 p 0 0
+2 4 #cdata-section 0 1 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦
+1 15 p 0 0
+1 14 #text 0 1
+
+0 15 doc 0 0
diff --git a/result/cdata-4-byte-UTF-8.xml.sax b/result/cdata-4-byte-UTF-8.xml.sax
new file mode 100644
index 0000000..d8abcfb
--- /dev/null
+++ b/result/cdata-4-byte-UTF-8.xml.sax
@@ -0,0 +1,28 @@
+SAX.setDocumentLocator()
+SAX.startDocument()
+SAX.comment( This tests that four-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). )
+SAX.startElement(doc)
+SAX.characters(
+, 1)
+SAX.startElement(p)
+SAX.pcdata(🍦🍦🍦🍦🍦, 1200)
+SAX.endElement(p)
+SAX.characters(
+, 1)
+SAX.startElement(p)
+SAX.pcdata( ð¦ð¦ð¦ð¦ð, 1201)
+SAX.endElement(p)
+SAX.characters(
+, 1)
+SAX.startElement(p)
+SAX.pcdata( ð¦ð¦ð¦ð¦ð, 1202)
+SAX.endElement(p)
+SAX.characters(
+, 1)
+SAX.startElement(p)
+SAX.pcdata( ð¦ð¦ð¦ð¦ð, 1203)
+SAX.endElement(p)
+SAX.characters(
+, 1)
+SAX.endElement(doc)
+SAX.endDocument()
diff --git a/result/cdata-4-byte-UTF-8.xml.sax2 b/result/cdata-4-byte-UTF-8.xml.sax2
new file mode 100644
index 0000000..5e07d83
--- /dev/null
+++ b/result/cdata-4-byte-UTF-8.xml.sax2
@@ -0,0 +1,28 @@
+SAX.setDocumentLocator()
+SAX.startDocument()
+SAX.comment( This tests that four-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). )
+SAX.startElementNs(doc, NULL, NULL, 0, 0, 0)
+SAX.characters(
+, 1)
+SAX.startElementNs(p, NULL, NULL, 0, 0, 0)
+SAX.pcdata(🍦🍦🍦🍦🍦, 1200)
+SAX.endElementNs(p, NULL, NULL)
+SAX.characters(
+, 1)
+SAX.startElementNs(p, NULL, NULL, 0, 0, 0)
+SAX.pcdata( ð¦ð¦ð¦ð¦ð, 1201)
+SAX.endElementNs(p, NULL, NULL)
+SAX.characters(
+, 1)
+SAX.startElementNs(p, NULL, NULL, 0, 0, 0)
+SAX.pcdata( ð¦ð¦ð¦ð¦ð, 1202)
+SAX.endElementNs(p, NULL, NULL)
+SAX.characters(
+, 1)
+SAX.startElementNs(p, NULL, NULL, 0, 0, 0)
+SAX.pcdata( ð¦ð¦ð¦ð¦ð, 1203)
+SAX.endElementNs(p, NULL, NULL)
+SAX.characters(
+, 1)
+SAX.endElementNs(doc, NULL, NULL)
+SAX.endDocument()
diff --git a/result/noent/cdata-2-byte-UTF-8.xml b/result/noent/cdata-2-byte-UTF-8.xml
new file mode 100644
index 0000000..8552efc
--- /dev/null
+++ b/result/noent/cdata-2-byte-UTF-8.xml
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- This tests that two-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). -->
+<doc>
+<p><![CDATA[ČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČ]]></p>
+<p><![CDATA[ ČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČ]]></p>
+</doc>
diff --git a/result/noent/cdata-3-byte-UTF-8.xml b/result/noent/cdata-3-byte-UTF-8.xml
new file mode 100644
index 0000000..b959a12
--- /dev/null
+++ b/result/noent/cdata-3-byte-UTF-8.xml
@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- This tests that three-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). -->
+<doc>
+<p><![CDATA[牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛]]></p>
+<p><![CDATA[ 牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛]]></p>
+<p><![CDATA[ 牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛]]></p>
+</doc>
diff --git a/result/noent/cdata-4-byte-UTF-8.xml b/result/noent/cdata-4-byte-UTF-8.xml
new file mode 100644
index 0000000..4d1d9a8
--- /dev/null
+++ b/result/noent/cdata-4-byte-UTF-8.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- This tests that four-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). -->
+<doc>
+<p><![CDATA[🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦]]></p>
+<p><![CDATA[ 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦]]></p>
+<p><![CDATA[ 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦]]></p>
+<p><![CDATA[ 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦]]></p>
+</doc>
diff --git a/test/cdata-2-byte-UTF-8.xml b/test/cdata-2-byte-UTF-8.xml
new file mode 100644
index 0000000..8552efc
--- /dev/null
+++ b/test/cdata-2-byte-UTF-8.xml
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- This tests that two-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). -->
+<doc>
+<p><![CDATA[ČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČ]]></p>
+<p><![CDATA[ ČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČČ]]></p>
+</doc>
diff --git a/test/cdata-3-byte-UTF-8.xml b/test/cdata-3-byte-UTF-8.xml
new file mode 100644
index 0000000..b959a12
--- /dev/null
+++ b/test/cdata-3-byte-UTF-8.xml
@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- This tests that three-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). -->
+<doc>
+<p><![CDATA[牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛]]></p>
+<p><![CDATA[ 牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛]]></p>
+<p><![CDATA[ 牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛牛]]></p>
+</doc>
diff --git a/test/cdata-4-byte-UTF-8.xml b/test/cdata-4-byte-UTF-8.xml
new file mode 100644
index 0000000..4d1d9a8
--- /dev/null
+++ b/test/cdata-4-byte-UTF-8.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- This tests that four-byte UTF-8 characters are parsed properly when split across a buffer boundary of length XML_PARSER_BIG_BUFFER_SIZE (300 bytes). -->
+<doc>
+<p><![CDATA[🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦]]></p>
+<p><![CDATA[ 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦]]></p>
+<p><![CDATA[ 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦]]></p>
+<p><![CDATA[ 🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦🍦]]></p>
+</doc>