115 lines
3.0 KiB
Diff
115 lines
3.0 KiB
Diff
|
From d7d0bc6581e332f49c9ff628f548eced03c65189 Mon Sep 17 00:00:00 2001
|
||
|
|
From: Nick Wellnhofer <wellnhofer@aevum.de>
|
||
|
|
Date: Fri, 31 Mar 2023 16:47:48 +0200
|
||
|
|
Subject: [PATCH] SAX2: Ignore namespaces in HTML documents
|
||
|
|
|
||
|
|
In commit 21ca8829, we started to ignore namespaces in HTML element
|
||
|
|
names but we still called xmlSplitQName, effectively stripping the
|
||
|
|
namespace prefix. This would cause elements like <o:p> being parsed
|
||
|
|
as <p>. Now we leave the name untouched.
|
||
|
|
|
||
|
|
Fixes #508.
|
||
|
|
|
||
|
|
Reference:https://github.com/GNOME/libxml2/commit/d7d0bc6581e332f49c9ff628f548eced03c65189
|
||
|
|
Conflict:NA
|
||
|
|
|
||
|
|
---
|
||
|
|
SAX2.c | 15 +++++++++------
|
||
|
|
result/HTML/names.html | 6 ++++++
|
||
|
|
result/HTML/names.html.err | 3 +++
|
||
|
|
result/HTML/names.html.sax | 20 ++++++++++++++++++++
|
||
|
|
test/HTML/names.html | 5 +++++
|
||
|
|
5 files changed, 43 insertions(+), 6 deletions(-)
|
||
|
|
create mode 100644 result/HTML/names.html
|
||
|
|
create mode 100644 result/HTML/names.html.err
|
||
|
|
create mode 100644 result/HTML/names.html.sax
|
||
|
|
create mode 100644 test/HTML/names.html
|
||
|
|
|
||
|
|
diff --git a/SAX2.c b/SAX2.c
|
||
|
|
index 3984bed..f8bc7c2 100644
|
||
|
|
--- a/SAX2.c
|
||
|
|
+++ b/SAX2.c
|
||
|
|
@@ -1589,12 +1589,15 @@ xmlSAX2StartElement(void *ctx, const xmlChar *fullname, const xmlChar **atts)
|
||
|
|
ctxt->validate = 0;
|
||
|
|
}
|
||
|
|
|
||
|
|
-
|
||
|
|
- /*
|
||
|
|
- * Split the full name into a namespace prefix and the tag name
|
||
|
|
- */
|
||
|
|
- name = xmlSplitQName(ctxt, fullname, &prefix);
|
||
|
|
-
|
||
|
|
+ if (ctxt->html) {
|
||
|
|
+ prefix = NULL;
|
||
|
|
+ name = xmlStrdup(fullname);
|
||
|
|
+ } else {
|
||
|
|
+ /*
|
||
|
|
+ * Split the full name into a namespace prefix and the tag name
|
||
|
|
+ */
|
||
|
|
+ name = xmlSplitQName(ctxt, fullname, &prefix);
|
||
|
|
+ }
|
||
|
|
|
||
|
|
/*
|
||
|
|
* Note : the namespace resolution is deferred until the end of the
|
||
|
|
diff --git a/result/HTML/names.html b/result/HTML/names.html
|
||
|
|
new file mode 100644
|
||
|
|
index 0000000..dd7dcc2
|
||
|
|
--- /dev/null
|
||
|
|
+++ b/result/HTML/names.html
|
||
|
|
@@ -0,0 +1,6 @@
|
||
|
|
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">
|
||
|
|
+<html>
|
||
|
|
+<body>
|
||
|
|
+ <o:p></o:p>
|
||
|
|
+</body>
|
||
|
|
+</html>
|
||
|
|
diff --git a/result/HTML/names.html.err b/result/HTML/names.html.err
|
||
|
|
new file mode 100644
|
||
|
|
index 0000000..4d91a5d
|
||
|
|
--- /dev/null
|
||
|
|
+++ b/result/HTML/names.html.err
|
||
|
|
@@ -0,0 +1,3 @@
|
||
|
|
+./test/HTML/names.html:3: HTML parser error : Tag o:p invalid
|
||
|
|
+ <o:p></o:p>
|
||
|
|
+ ^
|
||
|
|
diff --git a/result/HTML/names.html.sax b/result/HTML/names.html.sax
|
||
|
|
new file mode 100644
|
||
|
|
index 0000000..12a107f
|
||
|
|
--- /dev/null
|
||
|
|
+++ b/result/HTML/names.html.sax
|
||
|
|
@@ -0,0 +1,20 @@
|
||
|
|
+SAX.setDocumentLocator()
|
||
|
|
+SAX.startDocument()
|
||
|
|
+SAX.startElement(html)
|
||
|
|
+SAX.characters(
|
||
|
|
+, 1)
|
||
|
|
+SAX.startElement(body)
|
||
|
|
+SAX.characters(
|
||
|
|
+ , 3)
|
||
|
|
+SAX.startElement(o:p)
|
||
|
|
+SAX.error: Tag o:p invalid
|
||
|
|
+SAX.endElement(o:p)
|
||
|
|
+SAX.characters(
|
||
|
|
+, 1)
|
||
|
|
+SAX.endElement(body)
|
||
|
|
+SAX.characters(
|
||
|
|
+, 1)
|
||
|
|
+SAX.endElement(html)
|
||
|
|
+SAX.characters(
|
||
|
|
+, 1)
|
||
|
|
+SAX.endDocument()
|
||
|
|
diff --git a/test/HTML/names.html b/test/HTML/names.html
|
||
|
|
new file mode 100644
|
||
|
|
index 0000000..0dac7a4
|
||
|
|
--- /dev/null
|
||
|
|
+++ b/test/HTML/names.html
|
||
|
|
@@ -0,0 +1,5 @@
|
||
|
|
+<html>
|
||
|
|
+<body>
|
||
|
|
+ <o:p></o:p>
|
||
|
|
+</body>
|
||
|
|
+</html>
|
||
|
|
--
|
||
|
|
2.33.0
|
||
|
|
|