lxml 5.1.1__pp38-pypy38_pp73-win_amd64.whl → 5.2.1__pp38-pypy38_pp73-win_amd64.whl

lxml/__init__.py

@@ -1,6 +1,6 @@
 # this is a package
 
-__version__ = "5.1.1"
+__version__ = "5.2.1"
 
 
 def get_include():

lxml/etree.h

@@ -1,4 +1,4 @@
-/* Generated by Cython 3.0.9 */
+/* Generated by Cython 3.0.10 */
 
 #ifndef __PYX_HAVE__lxml__etree
 #define __PYX_HAVE__lxml__etree
@@ -66,7 +66,7 @@ struct LxmlElementTree {
   struct LxmlElement *_context_node;
 };
 
-/* "lxml/etree.pyx":2645
+/* "lxml/etree.pyx":2646
  * 
  * 
  * cdef public class _ElementTagMatcher [ object LxmlElementTagMatcher,             # <<<<<<<<<<<<<<
@@ -82,7 +82,7 @@ struct LxmlElementTagMatcher {
   char *_name;
 };
 
-/* "lxml/etree.pyx":2676
+/* "lxml/etree.pyx":2677
  *                 self._name = NULL
  * 
  * cdef public class _ElementIterator(_ElementTagMatcher) [             # <<<<<<<<<<<<<<

lxml/etree.pyx

@@ -2306,6 +2306,7 @@ cdef public class _ElementTree [ type LxmlElementTreeType,
         root = self.getroot()
         if _isString(path):
             if path[:1] == "/":
+                path = "." + path
                 from warnings import warn
                 warn(
                     "This search incorrectly ignores the root element, and will be "

lxml/etree_api.h

@@ -1,4 +1,4 @@
-/* Generated by Cython 3.0.9 */
+/* Generated by Cython 3.0.10 */
 
 #ifndef __PYX_HAVE_API__lxml__etree
 #define __PYX_HAVE_API__lxml__etree
@@ -98,9 +98,9 @@ static void (*__pyx_api_f_4lxml_5etree_initTagMatch)(struct LxmlElementTagMatche
 #define initTagMatch __pyx_api_f_4lxml_5etree_initTagMatch
 static xmlNs *(*__pyx_api_f_4lxml_5etree_findOrBuildNodeNsPrefix)(struct LxmlDocument *, xmlNode *, const xmlChar *, const xmlChar *) = 0;
 #define findOrBuildNodeNsPrefix __pyx_api_f_4lxml_5etree_findOrBuildNodeNsPrefix
-#ifndef __PYX_HAVE_RT_ImportFunction_3_0_9
-#define __PYX_HAVE_RT_ImportFunction_3_0_9
-static int __Pyx_ImportFunction_3_0_9(PyObject *module, const char *funcname, void (**f)(void), const char *sig) {
+#ifndef __PYX_HAVE_RT_ImportFunction_3_0_10
+#define __PYX_HAVE_RT_ImportFunction_3_0_10
+static int __Pyx_ImportFunction_3_0_10(PyObject *module, const char *funcname, void (**f)(void), const char *sig) {
     PyObject *d = 0;
     PyObject *cobj = 0;
     union {
@@ -140,51 +140,51 @@ static int import_lxml__etree(void) {
   PyObject *module = 0;
   module = PyImport_ImportModule("lxml.etree");
   if (!module) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "deepcopyNodeToDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_deepcopyNodeToDocument, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "elementTreeFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementTreeFactory, "struct LxmlElementTree *(struct LxmlElement *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "newElementTree", (void (**)(void))&__pyx_api_f_4lxml_5etree_newElementTree, "struct LxmlElementTree *(struct LxmlElement *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "adoptExternalDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_adoptExternalDocument, "struct LxmlElementTree *(xmlDoc *, PyObject *, int)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "elementFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementFactory, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "makeElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_makeElement, "struct LxmlElement *(PyObject *, struct LxmlDocument *, PyObject *, PyObject *, PyObject *, PyObject *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "makeSubElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_makeSubElement, "struct LxmlElement *(struct LxmlElement *, PyObject *, PyObject *, PyObject *, PyObject *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "setElementClassLookupFunction", (void (**)(void))&__pyx_api_f_4lxml_5etree_setElementClassLookupFunction, "void (_element_class_lookup_function, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "lookupDefaultElementClass", (void (**)(void))&__pyx_api_f_4lxml_5etree_lookupDefaultElementClass, "PyObject *(PyObject *, PyObject *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "lookupNamespaceElementClass", (void (**)(void))&__pyx_api_f_4lxml_5etree_lookupNamespaceElementClass, "PyObject *(PyObject *, PyObject *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "callLookupFallback", (void (**)(void))&__pyx_api_f_4lxml_5etree_callLookupFallback, "PyObject *(struct LxmlFallbackElementClassLookup *, struct LxmlDocument *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "tagMatches", (void (**)(void))&__pyx_api_f_4lxml_5etree_tagMatches, "int (xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "documentOrRaise", (void (**)(void))&__pyx_api_f_4lxml_5etree_documentOrRaise, "struct LxmlDocument *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "rootNodeOrRaise", (void (**)(void))&__pyx_api_f_4lxml_5etree_rootNodeOrRaise, "struct LxmlElement *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "hasText", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasText, "int (xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "hasTail", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasTail, "int (xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "textOf", (void (**)(void))&__pyx_api_f_4lxml_5etree_textOf, "PyObject *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "tailOf", (void (**)(void))&__pyx_api_f_4lxml_5etree_tailOf, "PyObject *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "setNodeText", (void (**)(void))&__pyx_api_f_4lxml_5etree_setNodeText, "int (xmlNode *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "setTailText", (void (**)(void))&__pyx_api_f_4lxml_5etree_setTailText, "int (xmlNode *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "attributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_attributeValue, "PyObject *(xmlNode *, xmlAttr *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "attributeValueFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_attributeValueFromNsName, "PyObject *(xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "getAttributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_getAttributeValue, "PyObject *(struct LxmlElement *, PyObject *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "iterattributes", (void (**)(void))&__pyx_api_f_4lxml_5etree_iterattributes, "PyObject *(struct LxmlElement *, int)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "collectAttributes", (void (**)(void))&__pyx_api_f_4lxml_5etree_collectAttributes, "PyObject *(xmlNode *, int)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "setAttributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_setAttributeValue, "int (struct LxmlElement *, PyObject *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "delAttribute", (void (**)(void))&__pyx_api_f_4lxml_5etree_delAttribute, "int (struct LxmlElement *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "delAttributeFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_delAttributeFromNsName, "int (xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "hasChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasChild, "int (xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "findChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChild, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "findChildForwards", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChildForwards, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "findChildBackwards", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChildBackwards, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "nextElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_nextElement, "xmlNode *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "previousElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_previousElement, "xmlNode *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "appendChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_appendChild, "void (struct LxmlElement *, struct LxmlElement *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "appendChildToElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_appendChildToElement, "int (struct LxmlElement *, struct LxmlElement *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "pyunicode", (void (**)(void))&__pyx_api_f_4lxml_5etree_pyunicode, "PyObject *(const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "utf8", (void (**)(void))&__pyx_api_f_4lxml_5etree_utf8, "PyObject *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "getNsTag", (void (**)(void))&__pyx_api_f_4lxml_5etree_getNsTag, "PyObject *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "getNsTagWithEmptyNs", (void (**)(void))&__pyx_api_f_4lxml_5etree_getNsTagWithEmptyNs, "PyObject *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "namespacedName", (void (**)(void))&__pyx_api_f_4lxml_5etree_namespacedName, "PyObject *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "namespacedNameFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_namespacedNameFromNsName, "PyObject *(const xmlChar *, const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "iteratorStoreNext", (void (**)(void))&__pyx_api_f_4lxml_5etree_iteratorStoreNext, "void (struct LxmlElementIterator *, struct LxmlElement *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "initTagMatch", (void (**)(void))&__pyx_api_f_4lxml_5etree_initTagMatch, "void (struct LxmlElementTagMatcher *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "findOrBuildNodeNsPrefix", (void (**)(void))&__pyx_api_f_4lxml_5etree_findOrBuildNodeNsPrefix, "xmlNs *(struct LxmlDocument *, xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "deepcopyNodeToDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_deepcopyNodeToDocument, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "elementTreeFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementTreeFactory, "struct LxmlElementTree *(struct LxmlElement *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "newElementTree", (void (**)(void))&__pyx_api_f_4lxml_5etree_newElementTree, "struct LxmlElementTree *(struct LxmlElement *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "adoptExternalDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_adoptExternalDocument, "struct LxmlElementTree *(xmlDoc *, PyObject *, int)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "elementFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementFactory, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "makeElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_makeElement, "struct LxmlElement *(PyObject *, struct LxmlDocument *, PyObject *, PyObject *, PyObject *, PyObject *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "makeSubElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_makeSubElement, "struct LxmlElement *(struct LxmlElement *, PyObject *, PyObject *, PyObject *, PyObject *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "setElementClassLookupFunction", (void (**)(void))&__pyx_api_f_4lxml_5etree_setElementClassLookupFunction, "void (_element_class_lookup_function, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "lookupDefaultElementClass", (void (**)(void))&__pyx_api_f_4lxml_5etree_lookupDefaultElementClass, "PyObject *(PyObject *, PyObject *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "lookupNamespaceElementClass", (void (**)(void))&__pyx_api_f_4lxml_5etree_lookupNamespaceElementClass, "PyObject *(PyObject *, PyObject *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "callLookupFallback", (void (**)(void))&__pyx_api_f_4lxml_5etree_callLookupFallback, "PyObject *(struct LxmlFallbackElementClassLookup *, struct LxmlDocument *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "tagMatches", (void (**)(void))&__pyx_api_f_4lxml_5etree_tagMatches, "int (xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "documentOrRaise", (void (**)(void))&__pyx_api_f_4lxml_5etree_documentOrRaise, "struct LxmlDocument *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "rootNodeOrRaise", (void (**)(void))&__pyx_api_f_4lxml_5etree_rootNodeOrRaise, "struct LxmlElement *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "hasText", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasText, "int (xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "hasTail", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasTail, "int (xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "textOf", (void (**)(void))&__pyx_api_f_4lxml_5etree_textOf, "PyObject *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "tailOf", (void (**)(void))&__pyx_api_f_4lxml_5etree_tailOf, "PyObject *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "setNodeText", (void (**)(void))&__pyx_api_f_4lxml_5etree_setNodeText, "int (xmlNode *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "setTailText", (void (**)(void))&__pyx_api_f_4lxml_5etree_setTailText, "int (xmlNode *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "attributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_attributeValue, "PyObject *(xmlNode *, xmlAttr *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "attributeValueFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_attributeValueFromNsName, "PyObject *(xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "getAttributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_getAttributeValue, "PyObject *(struct LxmlElement *, PyObject *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "iterattributes", (void (**)(void))&__pyx_api_f_4lxml_5etree_iterattributes, "PyObject *(struct LxmlElement *, int)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "collectAttributes", (void (**)(void))&__pyx_api_f_4lxml_5etree_collectAttributes, "PyObject *(xmlNode *, int)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "setAttributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_setAttributeValue, "int (struct LxmlElement *, PyObject *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "delAttribute", (void (**)(void))&__pyx_api_f_4lxml_5etree_delAttribute, "int (struct LxmlElement *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "delAttributeFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_delAttributeFromNsName, "int (xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "hasChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasChild, "int (xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "findChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChild, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "findChildForwards", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChildForwards, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "findChildBackwards", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChildBackwards, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "nextElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_nextElement, "xmlNode *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "previousElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_previousElement, "xmlNode *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "appendChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_appendChild, "void (struct LxmlElement *, struct LxmlElement *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "appendChildToElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_appendChildToElement, "int (struct LxmlElement *, struct LxmlElement *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "pyunicode", (void (**)(void))&__pyx_api_f_4lxml_5etree_pyunicode, "PyObject *(const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "utf8", (void (**)(void))&__pyx_api_f_4lxml_5etree_utf8, "PyObject *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "getNsTag", (void (**)(void))&__pyx_api_f_4lxml_5etree_getNsTag, "PyObject *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "getNsTagWithEmptyNs", (void (**)(void))&__pyx_api_f_4lxml_5etree_getNsTagWithEmptyNs, "PyObject *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "namespacedName", (void (**)(void))&__pyx_api_f_4lxml_5etree_namespacedName, "PyObject *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "namespacedNameFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_namespacedNameFromNsName, "PyObject *(const xmlChar *, const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "iteratorStoreNext", (void (**)(void))&__pyx_api_f_4lxml_5etree_iteratorStoreNext, "void (struct LxmlElementIterator *, struct LxmlElement *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "initTagMatch", (void (**)(void))&__pyx_api_f_4lxml_5etree_initTagMatch, "void (struct LxmlElementTagMatcher *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "findOrBuildNodeNsPrefix", (void (**)(void))&__pyx_api_f_4lxml_5etree_findOrBuildNodeNsPrefix, "xmlNs *(struct LxmlDocument *, xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
   Py_DECREF(module); module = 0;
   return 0;
   bad:

lxml/html/clean.py

@@ -1,772 +1,21 @@
 # cython: language_level=3str
 
-"""A cleanup tool for HTML.
-
-Removes unwanted tags and content.  See the `Cleaner` class for
-details.
-"""
-
-import copy
-import re
-from urllib.parse import urlsplit, unquote_plus
-
-from lxml import etree
-from lxml.html import defs
-from lxml.html import fromstring, XHTML_NAMESPACE
-from lxml.html import xhtml_to_html, _transform_result
-
-
-__all__ = ['clean_html', 'clean', 'Cleaner', 'autolink', 'autolink_html',
-           'word_break', 'word_break_html']
-
-# Look at http://code.sixapart.com/trac/livejournal/browser/trunk/cgi-bin/cleanhtml.pl
-#   Particularly the CSS cleaning; most of the tag cleaning is integrated now
-# I have multiple kinds of schemes searched; but should schemes be
-#   whitelisted instead?
-# max height?
-# remove images?  Also in CSS?  background attribute?
-# Some way to whitelist object, iframe, etc (e.g., if you want to
-#   allow *just* embedded YouTube movies)
-# Log what was deleted and why?
-# style="behavior: ..." might be bad in IE?
-# Should we have something for just <meta http-equiv>?  That's the worst of the
-#   metas.
-# UTF-7 detections?  Example:
-#     <HEAD><META HTTP-EQUIV="CONTENT-TYPE" CONTENT="text/html; charset=UTF-7"> </HEAD>+ADw-SCRIPT+AD4-alert('XSS');+ADw-/SCRIPT+AD4-
-#   you don't always have to have the charset set, if the page has no charset
-#   and there's UTF7-like code in it.
-# Look at these tests: http://htmlpurifier.org/live/smoketests/xssAttacks.php
-
-
-# This is an IE-specific construct you can have in a stylesheet to
-# run some Javascript:
-_replace_css_javascript = re.compile(
-    r'expression\s*\(.*?\)', re.S|re.I).sub
-
-# Do I have to worry about @\nimport?
-_replace_css_import = re.compile(
-    r'@\s*import', re.I).sub
-
-_looks_like_tag_content = re.compile(
-    r'</?[a-zA-Z]+|\son[a-zA-Z]+\s*=',
-    (re.ASCII)).search
-
-# All kinds of schemes besides just javascript: that can cause
-# execution:
-_find_image_dataurls = re.compile(
-    r'data:image/(.+);base64,', re.I).findall
-_possibly_malicious_schemes = re.compile(
-    r'(javascript|jscript|livescript|vbscript|data|about|mocha):',
-    re.I).findall
-# SVG images can contain script content
-_is_unsafe_image_type = re.compile(r"(xml|svg)", re.I).search
-
-def _has_javascript_scheme(s):
-    safe_image_urls = 0
-    for image_type in _find_image_dataurls(s):
-        if _is_unsafe_image_type(image_type):
-            return True
-        safe_image_urls += 1
-    return len(_possibly_malicious_schemes(s)) > safe_image_urls
-
-_substitute_whitespace = re.compile(r'[\s\x00-\x08\x0B\x0C\x0E-\x19]+').sub
-
-# FIXME: check against: http://msdn2.microsoft.com/en-us/library/ms537512.aspx
-_conditional_comment_re = re.compile(
-    r'\[if[\s\n\r]+.*?][\s\n\r]*>', re.I|re.S)
-
-_find_styled_elements = etree.XPath(
-    "descendant-or-self::*[@style]")
-
-_find_external_links = etree.XPath(
-    ("descendant-or-self::a  [normalize-space(@href) and substring(normalize-space(@href),1,1) != '#'] |"
-     "descendant-or-self::x:a[normalize-space(@href) and substring(normalize-space(@href),1,1) != '#']"),
-    namespaces={'x':XHTML_NAMESPACE})
-
-
-class Cleaner:
-    """
-    Instances cleans the document of each of the possible offending
-    elements.  The cleaning is controlled by attributes; you can
-    override attributes in a subclass, or set them in the constructor.
-
-    ``scripts``:
-        Removes any ``<script>`` tags.
-
-    ``javascript``:
-        Removes any Javascript, like an ``onclick`` attribute. Also removes stylesheets
-        as they could contain Javascript.
-
-    ``comments``:
-        Removes any comments.
-
-    ``style``:
-        Removes any style tags.
-
-    ``inline_style``
-        Removes any style attributes.  Defaults to the value of the ``style`` option.
-
-    ``links``:
-        Removes any ``<link>`` tags
-
-    ``meta``:
-        Removes any ``<meta>`` tags
-
-    ``page_structure``:
-        Structural parts of a page: ``<head>``, ``<html>``, ``<title>``.
-
-    ``processing_instructions``:
-        Removes any processing instructions.
-
-    ``embedded``:
-        Removes any embedded objects (flash, iframes)
-
-    ``frames``:
-        Removes any frame-related tags
-
-    ``forms``:
-        Removes any form tags
-
-    ``annoying_tags``:
-        Tags that aren't *wrong*, but are annoying.  ``<blink>`` and ``<marquee>``
-
-    ``remove_tags``:
-        A list of tags to remove.  Only the tags will be removed,
-        their content will get pulled up into the parent tag.
-
-    ``kill_tags``:
-        A list of tags to kill.  Killing also removes the tag's content,
-        i.e. the whole subtree, not just the tag itself.
-
-    ``allow_tags``:
-        A list of tags to include (default include all).
-
-    ``remove_unknown_tags``:
-        Remove any tags that aren't standard parts of HTML.
-
-    ``safe_attrs_only``:
-        If true, only include 'safe' attributes (specifically the list
-        from the feedparser HTML sanitisation web site).
-
-    ``safe_attrs``:
-        A set of attribute names to override the default list of attributes
-        considered 'safe' (when safe_attrs_only=True).
-
-    ``add_nofollow``:
-        If true, then any <a> tags will have ``rel="nofollow"`` added to them.
-
-    ``host_whitelist``:
-        A list or set of hosts that you can use for embedded content
-        (for content like ``<object>``, ``<link rel="stylesheet">``, etc).
-        You can also implement/override the method
-        ``allow_embedded_url(el, url)`` or ``allow_element(el)`` to
-        implement more complex rules for what can be embedded.
-        Anything that passes this test will be shown, regardless of
-        the value of (for instance) ``embedded``.
-
-        Note that this parameter might not work as intended if you do not
-        make the links absolute before doing the cleaning.
-
-        Note that you may also need to set ``whitelist_tags``.
-
-    ``whitelist_tags``:
-        A set of tags that can be included with ``host_whitelist``.
-        The default is ``iframe`` and ``embed``; you may wish to
-        include other tags like ``script``, or you may want to
-        implement ``allow_embedded_url`` for more control.  Set to None to
-        include all tags.
-
-    This modifies the document *in place*.
-    """
-
-    scripts = True
-    javascript = True
-    comments = True
-    style = False
-    inline_style = None
-    links = True
-    meta = True
-    page_structure = True
-    processing_instructions = True
-    embedded = True
-    frames = True
-    forms = True
-    annoying_tags = True
-    remove_tags = ()
-    allow_tags = ()
-    kill_tags = ()
-    remove_unknown_tags = True
-    safe_attrs_only = True
-    safe_attrs = defs.safe_attrs
-    add_nofollow = False
-    host_whitelist = ()
-    whitelist_tags = {'iframe', 'embed'}
-
-    def __init__(self, **kw):
-        not_an_attribute = object()
-        for name, value in kw.items():
-            default = getattr(self, name, not_an_attribute)
-            if default is None or default is True or default is False:
-                pass
-            elif isinstance(default, (frozenset, set, tuple, list)):
-                # Catch common error of passing ('host') instead of a tuple.
-                if isinstance(value, str):
-                    raise TypeError(
-                        f"Expected a collection, got str: {name}={value!r}")
-            else:
-                raise TypeError(
-                    f"Unknown parameter: {name}={value!r}")
-            setattr(self, name, value)
-
-        if self.inline_style is None and 'inline_style' not in kw:
-            self.inline_style = self.style
-
-        if kw.get("allow_tags"):
-            if kw.get("remove_unknown_tags"):
-                raise ValueError("It does not make sense to pass in both "
-                                 "allow_tags and remove_unknown_tags")
-            self.remove_unknown_tags = False
-
-        self.host_whitelist = frozenset(self.host_whitelist) if self.host_whitelist else ()
-
-    # Used to lookup the primary URL for a given tag that is up for
-    # removal:
-    _tag_link_attrs = dict(
-        script='src',
-        link='href',
-        # From: http://java.sun.com/j2se/1.4.2/docs/guide/misc/applet.html
-        # From what I can tell, both attributes can contain a link:
-        applet=['code', 'object'],
-        iframe='src',
-        embed='src',
-        layer='src',
-        # FIXME: there doesn't really seem like a general way to figure out what
-        # links an <object> tag uses; links often go in <param> tags with values
-        # that we don't really know.  You'd have to have knowledge about specific
-        # kinds of plugins (probably keyed off classid), and match against those.
-        ##object=?,
-        # FIXME: not looking at the action currently, because it is more complex
-        # than than -- if you keep the form, you should keep the form controls.
-        ##form='action',
-        a='href',
-        )
-
-    def __call__(self, doc):
-        """
-        Cleans the document.
-        """
-        try:
-            getroot = doc.getroot
-        except AttributeError:
-            pass  # Element instance
-        else:
-            doc = getroot()  # ElementTree instance, instead of an element
-        # convert XHTML to HTML
-        xhtml_to_html(doc)
-        # Normalize a case that IE treats <image> like <img>, and that
-        # can confuse either this step or later steps.
-        for el in doc.iter('image'):
-            el.tag = 'img'
-        if not self.comments:
-            # Of course, if we were going to kill comments anyway, we don't
-            # need to worry about this
-            self.kill_conditional_comments(doc)
-
-        kill_tags = set(self.kill_tags or ())
-        remove_tags = set(self.remove_tags or ())
-        allow_tags = set(self.allow_tags or ())
-
-        if self.scripts:
-            kill_tags.add('script')
-        if self.safe_attrs_only:
-            safe_attrs = set(self.safe_attrs)
-            for el in doc.iter(etree.Element):
-                attrib = el.attrib
-                for aname in attrib.keys():
-                    if aname not in safe_attrs:
-                        del attrib[aname]
-        if self.javascript:
-            if not (self.safe_attrs_only and
-                    self.safe_attrs == defs.safe_attrs):
-                # safe_attrs handles events attributes itself
-                for el in doc.iter(etree.Element):
-                    attrib = el.attrib
-                    for aname in attrib.keys():
-                        if aname.startswith('on'):
-                            del attrib[aname]
-            doc.rewrite_links(self._remove_javascript_link,
-                              resolve_base_href=False)
-            # If we're deleting style then we don't have to remove JS links
-            # from styles, otherwise...
-            if not self.inline_style:
-                for el in _find_styled_elements(doc):
-                    old = el.get('style')
-                    new = _replace_css_javascript('', old)
-                    new = _replace_css_import('', new)
-                    if self._has_sneaky_javascript(new):
-                        # Something tricky is going on...
-                        del el.attrib['style']
-                    elif new != old:
-                        el.set('style', new)
-            if not self.style:
-                for el in list(doc.iter('style')):
-                    if el.get('type', '').lower().strip() == 'text/javascript':
-                        el.drop_tree()
-                        continue
-                    old = el.text or ''
-                    new = _replace_css_javascript('', old)
-                    # The imported CSS can do anything; we just can't allow:
-                    new = _replace_css_import('', new)
-                    if self._has_sneaky_javascript(new):
-                        # Something tricky is going on...
-                        el.text = '/* deleted */'
-                    elif new != old:
-                        el.text = new
-        if self.comments:
-            kill_tags.add(etree.Comment)
-        if self.processing_instructions:
-            kill_tags.add(etree.ProcessingInstruction)
-        if self.style:
-            kill_tags.add('style')
-        if self.inline_style:
-            etree.strip_attributes(doc, 'style')
-        if self.links:
-            kill_tags.add('link')
-        elif self.style or self.javascript:
-            # We must get rid of included stylesheets if Javascript is not
-            # allowed, as you can put Javascript in them
-            for el in list(doc.iter('link')):
-                if 'stylesheet' in el.get('rel', '').lower():
-                    # Note this kills alternate stylesheets as well
-                    if not self.allow_element(el):
-                        el.drop_tree()
-        if self.meta:
-            kill_tags.add('meta')
-        if self.page_structure:
-            remove_tags.update(('head', 'html', 'title'))
-        if self.embedded:
-            # FIXME: is <layer> really embedded?
-            # We should get rid of any <param> tags not inside <applet>;
-            # These are not really valid anyway.
-            for el in list(doc.iter('param')):
-                parent = el.getparent()
-                while parent is not None and parent.tag not in ('applet', 'object'):
-                    parent = parent.getparent()
-                if parent is None:
-                    el.drop_tree()
-            kill_tags.update(('applet',))
-            # The alternate contents that are in an iframe are a good fallback:
-            remove_tags.update(('iframe', 'embed', 'layer', 'object', 'param'))
-        if self.frames:
-            # FIXME: ideally we should look at the frame links, but
-            # generally frames don't mix properly with an HTML
-            # fragment anyway.
-            kill_tags.update(defs.frame_tags)
-        if self.forms:
-            remove_tags.add('form')
-            kill_tags.update(('button', 'input', 'select', 'textarea'))
-        if self.annoying_tags:
-            remove_tags.update(('blink', 'marquee'))
-
-        _remove = []
-        _kill = []
-        for el in doc.iter():
-            if el.tag in kill_tags:
-                if self.allow_element(el):
-                    continue
-                _kill.append(el)
-            elif el.tag in remove_tags:
-                if self.allow_element(el):
-                    continue
-                _remove.append(el)
-
-        if _remove and _remove[0] == doc:
-            # We have to drop the parent-most tag, which we can't
-            # do.  Instead we'll rewrite it:
-            el = _remove.pop(0)
-            el.tag = 'div'
-            el.attrib.clear()
-        elif _kill and _kill[0] == doc:
-            # We have to drop the parent-most element, which we can't
-            # do.  Instead we'll clear it:
-            el = _kill.pop(0)
-            if el.tag != 'html':
-                el.tag = 'div'
-            el.clear()
-
-        _kill.reverse() # start with innermost tags
-        for el in _kill:
-            el.drop_tree()
-        for el in _remove:
-            el.drop_tag()
-
-        if self.remove_unknown_tags:
-            if allow_tags:
-                raise ValueError(
-                    "It does not make sense to pass in both allow_tags and remove_unknown_tags")
-            allow_tags = set(defs.tags)
-        if allow_tags:
-            # make sure we do not remove comments/PIs if users want them (which is rare enough)
-            if not self.comments:
-                allow_tags.add(etree.Comment)
-            if not self.processing_instructions:
-                allow_tags.add(etree.ProcessingInstruction)
-
-            bad = []
-            for el in doc.iter():
-                if el.tag not in allow_tags:
-                    bad.append(el)
-            if bad:
-                if bad[0] is doc:
-                    el = bad.pop(0)
-                    el.tag = 'div'
-                    el.attrib.clear()
-                for el in bad:
-                    el.drop_tag()
-        if self.add_nofollow:
-            for el in _find_external_links(doc):
-                if not self.allow_follow(el):
-                    rel = el.get('rel')
-                    if rel:
-                        if ('nofollow' in rel
-                                and ' nofollow ' in (' %s ' % rel)):
-                            continue
-                        rel = '%s nofollow' % rel
-                    else:
-                        rel = 'nofollow'
-                    el.set('rel', rel)
-
-    def allow_follow(self, anchor):
-        """
-        Override to suppress rel="nofollow" on some anchors.
-        """
-        return False
-
-    def allow_element(self, el):
-        """
-        Decide whether an element is configured to be accepted or rejected.
-
-        :param el: an element.
-        :return: true to accept the element or false to reject/discard it.
-        """
-        if el.tag not in self._tag_link_attrs:
-            return False
-        attr = self._tag_link_attrs[el.tag]
-        if isinstance(attr, (list, tuple)):
-            for one_attr in attr:
-                url = el.get(one_attr)
-                if not url:
-                    return False
-                if not self.allow_embedded_url(el, url):
-                    return False
-            return True
-        else:
-            url = el.get(attr)
-            if not url:
-                return False
-            return self.allow_embedded_url(el, url)
-
-    def allow_embedded_url(self, el, url):
-        """
-        Decide whether a URL that was found in an element's attributes or text
-        if configured to be accepted or rejected.
-
-        :param el: an element.
-        :param url: a URL found on the element.
-        :return: true to accept the URL and false to reject it.
-        """
-        if self.whitelist_tags is not None and el.tag not in self.whitelist_tags:
-            return False
-        parts = urlsplit(url)
-        if parts.scheme not in ('http', 'https'):
-            return False
-        if parts.hostname in self.host_whitelist:
-            return True
-        return False
-
-    def kill_conditional_comments(self, doc):
-        """
-        IE conditional comments basically embed HTML that the parser
-        doesn't normally see.  We can't allow anything like that, so
-        we'll kill any comments that could be conditional.
-        """
-        has_conditional_comment = _conditional_comment_re.search
-        self._kill_elements(
-            doc, lambda el: has_conditional_comment(el.text),
-            etree.Comment)                
-
-    def _kill_elements(self, doc, condition, iterate=None):
-        bad = []
-        for el in doc.iter(iterate):
-            if condition(el):
-                bad.append(el)
-        for el in bad:
-            el.drop_tree()
-
-    def _remove_javascript_link(self, link):
-        # links like "j a v a s c r i p t:" might be interpreted in IE
-        new = _substitute_whitespace('', unquote_plus(link))
-        if _has_javascript_scheme(new):
-            # FIXME: should this be None to delete?
-            return ''
-        return link
-
-    _substitute_comments = re.compile(r'/\*.*?\*/', re.S).sub
-
-    def _has_sneaky_javascript(self, style):
-        """
-        Depending on the browser, stuff like ``e x p r e s s i o n(...)``
-        can get interpreted, or ``expre/* stuff */ssion(...)``.  This
-        checks for attempt to do stuff like this.
-
-        Typically the response will be to kill the entire style; if you
-        have just a bit of Javascript in the style another rule will catch
-        that and remove only the Javascript from the style; this catches
-        more sneaky attempts.
-        """
-        style = self._substitute_comments('', style)
-        style = style.replace('\\', '')
-        style = _substitute_whitespace('', style)
-        style = style.lower()
-        if _has_javascript_scheme(style):
-            return True
-        if 'expression(' in style:
-            return True
-        if '@import' in style:
-            return True
-        if '</noscript' in style:
-            # e.g. '<noscript><style><a title="</noscript><img src=x onerror=alert(1)>">'
-            return True
-        if _looks_like_tag_content(style):
-            # e.g. '<math><style><img src=x onerror=alert(1)></style></math>'
-            return True
-        return False
-
-    def clean_html(self, html):
-        result_type = type(html)
-        if isinstance(html, (str, bytes)):
-            doc = fromstring(html)
-        else:
-            doc = copy.deepcopy(html)
-        self(doc)
-        return _transform_result(result_type, doc)
-
-clean = Cleaner()
-clean_html = clean.clean_html
-
-############################################################
-## Autolinking
-############################################################
-
-_link_regexes = [
-    re.compile(r'(?P<body>https?://(?P<host>[a-z0-9._-]+)(?:/[/\-_.,a-z0-9%&?;=~]*)?(?:\([/\-_.,a-z0-9%&?;=~]*\))?)', re.I),
-    # This is conservative, but autolinking can be a bit conservative:
-    re.compile(r'mailto:(?P<body>[a-z0-9._-]+@(?P<host>[a-z0-9_.-]+[a-z]))', re.I),
-    ]
-
-_avoid_elements = ['textarea', 'pre', 'code', 'head', 'select', 'a']
-
-_avoid_hosts = [
-    re.compile(r'^localhost', re.I),
-    re.compile(r'\bexample\.(?:com|org|net)$', re.I),
-    re.compile(r'^127\.0\.0\.1$'),
+"""Backward-compatibility module for lxml_html_clean"""
+
+try:
+    from lxml_html_clean import *
+
+    __all__ = [
+        "clean_html",
+        "clean",
+        "Cleaner",
+        "autolink",
+        "autolink_html",
+        "word_break",
+        "word_break_html",
     ]
-
-_avoid_classes = ['nolink']
-
-def autolink(el, link_regexes=_link_regexes,
-             avoid_elements=_avoid_elements,
-             avoid_hosts=_avoid_hosts,
-             avoid_classes=_avoid_classes):
-    """
-    Turn any URLs into links.
-
-    It will search for links identified by the given regular
-    expressions (by default mailto and http(s) links).
-
-    It won't link text in an element in avoid_elements, or an element
-    with a class in avoid_classes.  It won't link to anything with a
-    host that matches one of the regular expressions in avoid_hosts
-    (default localhost and 127.0.0.1).
-
-    If you pass in an element, the element's tail will not be
-    substituted, only the contents of the element.
-    """
-    if el.tag in avoid_elements:
-        return
-    class_name = el.get('class')
-    if class_name:
-        class_name = class_name.split()
-        for match_class in avoid_classes:
-            if match_class in class_name:
-                return
-    for child in list(el):
-        autolink(child, link_regexes=link_regexes,
-                 avoid_elements=avoid_elements,
-                 avoid_hosts=avoid_hosts,
-                 avoid_classes=avoid_classes)
-        if child.tail:
-            text, tail_children = _link_text(
-                child.tail, link_regexes, avoid_hosts, factory=el.makeelement)
-            if tail_children:
-                child.tail = text
-                index = el.index(child)
-                el[index+1:index+1] = tail_children
-    if el.text:
-        text, pre_children = _link_text(
-            el.text, link_regexes, avoid_hosts, factory=el.makeelement)
-        if pre_children:
-            el.text = text
-            el[:0] = pre_children
-
-def _link_text(text, link_regexes, avoid_hosts, factory):
-    leading_text = ''
-    links = []
-    last_pos = 0
-    while 1:
-        best_match, best_pos = None, None
-        for regex in link_regexes:
-            regex_pos = last_pos
-            while 1:
-                match = regex.search(text, pos=regex_pos)
-                if match is None:
-                    break
-                host = match.group('host')
-                for host_regex in avoid_hosts:
-                    if host_regex.search(host):
-                        regex_pos = match.end()
-                        break
-                else:
-                    break
-            if match is None:
-                continue
-            if best_pos is None or match.start() < best_pos:
-                best_match = match
-                best_pos = match.start()
-        if best_match is None:
-            # No more matches
-            if links:
-                assert not links[-1].tail
-                links[-1].tail = text
-            else:
-                assert not leading_text
-                leading_text = text
-            break
-        link = best_match.group(0)
-        end = best_match.end()
-        if link.endswith('.') or link.endswith(','):
-            # These punctuation marks shouldn't end a link
-            end -= 1
-            link = link[:-1]
-        prev_text = text[:best_match.start()]
-        if links:
-            assert not links[-1].tail
-            links[-1].tail = prev_text
-        else:
-            assert not leading_text
-            leading_text = prev_text
-        anchor = factory('a')
-        anchor.set('href', link)
-        body = best_match.group('body')
-        if not body:
-            body = link
-        if body.endswith('.') or body.endswith(','):
-            body = body[:-1]
-        anchor.text = body
-        links.append(anchor)
-        text = text[end:]
-    return leading_text, links
-                
-def autolink_html(html, *args, **kw):
-    result_type = type(html)
-    if isinstance(html, (str, bytes)):
-        doc = fromstring(html)
-    else:
-        doc = copy.deepcopy(html)
-    autolink(doc, *args, **kw)
-    return _transform_result(result_type, doc)
-
-autolink_html.__doc__ = autolink.__doc__
-
-############################################################
-## Word wrapping
-############################################################
-
-_avoid_word_break_elements = ['pre', 'textarea', 'code']
-_avoid_word_break_classes = ['nobreak']
-
-def word_break(el, max_width=40,
-               avoid_elements=_avoid_word_break_elements,
-               avoid_classes=_avoid_word_break_classes,
-               break_character=chr(0x200b)):
-    """
-    Breaks any long words found in the body of the text (not attributes).
-
-    Doesn't effect any of the tags in avoid_elements, by default
-    ``<textarea>`` and ``<pre>``
-
-    Breaks words by inserting &#8203;, which is a unicode character
-    for Zero Width Space character.  This generally takes up no space
-    in rendering, but does copy as a space, and in monospace contexts
-    usually takes up space.
-
-    See http://www.cs.tut.fi/~jkorpela/html/nobr.html for a discussion
-    """
-    # Character suggestion of &#8203 comes from:
-    #   http://www.cs.tut.fi/~jkorpela/html/nobr.html
-    if el.tag in _avoid_word_break_elements:
-        return
-    class_name = el.get('class')
-    if class_name:
-        dont_break = False
-        class_name = class_name.split()
-        for avoid in avoid_classes:
-            if avoid in class_name:
-                dont_break = True
-                break
-        if dont_break:
-            return
-    if el.text:
-        el.text = _break_text(el.text, max_width, break_character)
-    for child in el:
-        word_break(child, max_width=max_width,
-                   avoid_elements=avoid_elements,
-                   avoid_classes=avoid_classes,
-                   break_character=break_character)
-        if child.tail:
-            child.tail = _break_text(child.tail, max_width, break_character)
-
-def word_break_html(html, *args, **kw):
-    result_type = type(html)
-    doc = fromstring(html)
-    word_break(doc, *args, **kw)
-    return _transform_result(result_type, doc)
-
-def _break_text(text, max_width, break_character):
-    words = text.split()
-    for word in words:
-        if len(word) > max_width:
-            replacement = _insert_break(word, max_width, break_character)
-            text = text.replace(word, replacement)
-    return text
-
-_break_prefer_re = re.compile(r'[^a-z]', re.I)
-
-def _insert_break(word, width, break_character):
-    orig_word = word
-    result = ''
-    while len(word) > width:
-        start = word[:width]
-        breaks = list(_break_prefer_re.finditer(start))
-        if breaks:
-            last_break = breaks[-1]
-            # Only walk back up to 10 characters to find a nice break:
-            if last_break.end() > width-10:
-                # FIXME: should the break character be at the end of the
-                # chunk, or the beginning of the next chunk?
-                start = word[:last_break.end()]
-        result += start + break_character
-        word = word[len(start):]
-    result += word
-    return result
-    
+except ImportError:
+    raise ImportError(
+        "lxml.html.clean module is now a separate project lxml_html_clean.\n"
+        "Install lxml[html_clean] or lxml_html_clean directly."
+    ) from None

lxml/includes/lxml-version.h

@@ -1,3 +1,3 @@
 #ifndef LXML_VERSION_STRING
-#define LXML_VERSION_STRING "5.1.1"
+#define LXML_VERSION_STRING "5.2.1"
 #endif

lxml/lxml.etree.h

@@ -1,4 +1,4 @@
-/* Generated by Cython 3.0.9 */
+/* Generated by Cython 3.0.10 */
 
 #ifndef __PYX_HAVE__lxml__etree
 #define __PYX_HAVE__lxml__etree
@@ -66,7 +66,7 @@ struct LxmlElementTree {
   struct LxmlElement *_context_node;
 };
 
-/* "lxml/etree.pyx":2645
+/* "lxml/etree.pyx":2646
  * 
  * 
  * cdef public class _ElementTagMatcher [ object LxmlElementTagMatcher,             # <<<<<<<<<<<<<<
@@ -82,7 +82,7 @@ struct LxmlElementTagMatcher {
   char *_name;
 };
 
-/* "lxml/etree.pyx":2676
+/* "lxml/etree.pyx":2677
  *                 self._name = NULL
  * 
  * cdef public class _ElementIterator(_ElementTagMatcher) [             # <<<<<<<<<<<<<<

lxml/lxml.etree_api.h

@@ -1,4 +1,4 @@
-/* Generated by Cython 3.0.9 */
+/* Generated by Cython 3.0.10 */
 
 #ifndef __PYX_HAVE_API__lxml__etree
 #define __PYX_HAVE_API__lxml__etree
@@ -98,9 +98,9 @@ static void (*__pyx_api_f_4lxml_5etree_initTagMatch)(struct LxmlElementTagMatche
 #define initTagMatch __pyx_api_f_4lxml_5etree_initTagMatch
 static xmlNs *(*__pyx_api_f_4lxml_5etree_findOrBuildNodeNsPrefix)(struct LxmlDocument *, xmlNode *, const xmlChar *, const xmlChar *) = 0;
 #define findOrBuildNodeNsPrefix __pyx_api_f_4lxml_5etree_findOrBuildNodeNsPrefix
-#ifndef __PYX_HAVE_RT_ImportFunction_3_0_9
-#define __PYX_HAVE_RT_ImportFunction_3_0_9
-static int __Pyx_ImportFunction_3_0_9(PyObject *module, const char *funcname, void (**f)(void), const char *sig) {
+#ifndef __PYX_HAVE_RT_ImportFunction_3_0_10
+#define __PYX_HAVE_RT_ImportFunction_3_0_10
+static int __Pyx_ImportFunction_3_0_10(PyObject *module, const char *funcname, void (**f)(void), const char *sig) {
     PyObject *d = 0;
     PyObject *cobj = 0;
     union {
@@ -140,51 +140,51 @@ static int import_lxml__etree(void) {
   PyObject *module = 0;
   module = PyImport_ImportModule("lxml.etree");
   if (!module) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "deepcopyNodeToDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_deepcopyNodeToDocument, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "elementTreeFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementTreeFactory, "struct LxmlElementTree *(struct LxmlElement *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "newElementTree", (void (**)(void))&__pyx_api_f_4lxml_5etree_newElementTree, "struct LxmlElementTree *(struct LxmlElement *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "adoptExternalDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_adoptExternalDocument, "struct LxmlElementTree *(xmlDoc *, PyObject *, int)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "elementFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementFactory, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "makeElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_makeElement, "struct LxmlElement *(PyObject *, struct LxmlDocument *, PyObject *, PyObject *, PyObject *, PyObject *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "makeSubElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_makeSubElement, "struct LxmlElement *(struct LxmlElement *, PyObject *, PyObject *, PyObject *, PyObject *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "setElementClassLookupFunction", (void (**)(void))&__pyx_api_f_4lxml_5etree_setElementClassLookupFunction, "void (_element_class_lookup_function, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "lookupDefaultElementClass", (void (**)(void))&__pyx_api_f_4lxml_5etree_lookupDefaultElementClass, "PyObject *(PyObject *, PyObject *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "lookupNamespaceElementClass", (void (**)(void))&__pyx_api_f_4lxml_5etree_lookupNamespaceElementClass, "PyObject *(PyObject *, PyObject *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "callLookupFallback", (void (**)(void))&__pyx_api_f_4lxml_5etree_callLookupFallback, "PyObject *(struct LxmlFallbackElementClassLookup *, struct LxmlDocument *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "tagMatches", (void (**)(void))&__pyx_api_f_4lxml_5etree_tagMatches, "int (xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "documentOrRaise", (void (**)(void))&__pyx_api_f_4lxml_5etree_documentOrRaise, "struct LxmlDocument *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "rootNodeOrRaise", (void (**)(void))&__pyx_api_f_4lxml_5etree_rootNodeOrRaise, "struct LxmlElement *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "hasText", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasText, "int (xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "hasTail", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasTail, "int (xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "textOf", (void (**)(void))&__pyx_api_f_4lxml_5etree_textOf, "PyObject *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "tailOf", (void (**)(void))&__pyx_api_f_4lxml_5etree_tailOf, "PyObject *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "setNodeText", (void (**)(void))&__pyx_api_f_4lxml_5etree_setNodeText, "int (xmlNode *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "setTailText", (void (**)(void))&__pyx_api_f_4lxml_5etree_setTailText, "int (xmlNode *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "attributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_attributeValue, "PyObject *(xmlNode *, xmlAttr *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "attributeValueFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_attributeValueFromNsName, "PyObject *(xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "getAttributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_getAttributeValue, "PyObject *(struct LxmlElement *, PyObject *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "iterattributes", (void (**)(void))&__pyx_api_f_4lxml_5etree_iterattributes, "PyObject *(struct LxmlElement *, int)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "collectAttributes", (void (**)(void))&__pyx_api_f_4lxml_5etree_collectAttributes, "PyObject *(xmlNode *, int)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "setAttributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_setAttributeValue, "int (struct LxmlElement *, PyObject *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "delAttribute", (void (**)(void))&__pyx_api_f_4lxml_5etree_delAttribute, "int (struct LxmlElement *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "delAttributeFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_delAttributeFromNsName, "int (xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "hasChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasChild, "int (xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "findChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChild, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "findChildForwards", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChildForwards, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "findChildBackwards", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChildBackwards, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "nextElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_nextElement, "xmlNode *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "previousElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_previousElement, "xmlNode *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "appendChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_appendChild, "void (struct LxmlElement *, struct LxmlElement *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "appendChildToElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_appendChildToElement, "int (struct LxmlElement *, struct LxmlElement *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "pyunicode", (void (**)(void))&__pyx_api_f_4lxml_5etree_pyunicode, "PyObject *(const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "utf8", (void (**)(void))&__pyx_api_f_4lxml_5etree_utf8, "PyObject *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "getNsTag", (void (**)(void))&__pyx_api_f_4lxml_5etree_getNsTag, "PyObject *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "getNsTagWithEmptyNs", (void (**)(void))&__pyx_api_f_4lxml_5etree_getNsTagWithEmptyNs, "PyObject *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "namespacedName", (void (**)(void))&__pyx_api_f_4lxml_5etree_namespacedName, "PyObject *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "namespacedNameFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_namespacedNameFromNsName, "PyObject *(const xmlChar *, const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "iteratorStoreNext", (void (**)(void))&__pyx_api_f_4lxml_5etree_iteratorStoreNext, "void (struct LxmlElementIterator *, struct LxmlElement *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "initTagMatch", (void (**)(void))&__pyx_api_f_4lxml_5etree_initTagMatch, "void (struct LxmlElementTagMatcher *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_9(module, "findOrBuildNodeNsPrefix", (void (**)(void))&__pyx_api_f_4lxml_5etree_findOrBuildNodeNsPrefix, "xmlNs *(struct LxmlDocument *, xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "deepcopyNodeToDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_deepcopyNodeToDocument, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "elementTreeFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementTreeFactory, "struct LxmlElementTree *(struct LxmlElement *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "newElementTree", (void (**)(void))&__pyx_api_f_4lxml_5etree_newElementTree, "struct LxmlElementTree *(struct LxmlElement *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "adoptExternalDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_adoptExternalDocument, "struct LxmlElementTree *(xmlDoc *, PyObject *, int)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "elementFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementFactory, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "makeElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_makeElement, "struct LxmlElement *(PyObject *, struct LxmlDocument *, PyObject *, PyObject *, PyObject *, PyObject *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "makeSubElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_makeSubElement, "struct LxmlElement *(struct LxmlElement *, PyObject *, PyObject *, PyObject *, PyObject *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "setElementClassLookupFunction", (void (**)(void))&__pyx_api_f_4lxml_5etree_setElementClassLookupFunction, "void (_element_class_lookup_function, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "lookupDefaultElementClass", (void (**)(void))&__pyx_api_f_4lxml_5etree_lookupDefaultElementClass, "PyObject *(PyObject *, PyObject *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "lookupNamespaceElementClass", (void (**)(void))&__pyx_api_f_4lxml_5etree_lookupNamespaceElementClass, "PyObject *(PyObject *, PyObject *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "callLookupFallback", (void (**)(void))&__pyx_api_f_4lxml_5etree_callLookupFallback, "PyObject *(struct LxmlFallbackElementClassLookup *, struct LxmlDocument *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "tagMatches", (void (**)(void))&__pyx_api_f_4lxml_5etree_tagMatches, "int (xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "documentOrRaise", (void (**)(void))&__pyx_api_f_4lxml_5etree_documentOrRaise, "struct LxmlDocument *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "rootNodeOrRaise", (void (**)(void))&__pyx_api_f_4lxml_5etree_rootNodeOrRaise, "struct LxmlElement *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "hasText", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasText, "int (xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "hasTail", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasTail, "int (xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "textOf", (void (**)(void))&__pyx_api_f_4lxml_5etree_textOf, "PyObject *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "tailOf", (void (**)(void))&__pyx_api_f_4lxml_5etree_tailOf, "PyObject *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "setNodeText", (void (**)(void))&__pyx_api_f_4lxml_5etree_setNodeText, "int (xmlNode *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "setTailText", (void (**)(void))&__pyx_api_f_4lxml_5etree_setTailText, "int (xmlNode *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "attributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_attributeValue, "PyObject *(xmlNode *, xmlAttr *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "attributeValueFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_attributeValueFromNsName, "PyObject *(xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "getAttributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_getAttributeValue, "PyObject *(struct LxmlElement *, PyObject *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "iterattributes", (void (**)(void))&__pyx_api_f_4lxml_5etree_iterattributes, "PyObject *(struct LxmlElement *, int)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "collectAttributes", (void (**)(void))&__pyx_api_f_4lxml_5etree_collectAttributes, "PyObject *(xmlNode *, int)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "setAttributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_setAttributeValue, "int (struct LxmlElement *, PyObject *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "delAttribute", (void (**)(void))&__pyx_api_f_4lxml_5etree_delAttribute, "int (struct LxmlElement *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "delAttributeFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_delAttributeFromNsName, "int (xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "hasChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasChild, "int (xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "findChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChild, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "findChildForwards", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChildForwards, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "findChildBackwards", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChildBackwards, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "nextElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_nextElement, "xmlNode *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "previousElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_previousElement, "xmlNode *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "appendChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_appendChild, "void (struct LxmlElement *, struct LxmlElement *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "appendChildToElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_appendChildToElement, "int (struct LxmlElement *, struct LxmlElement *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "pyunicode", (void (**)(void))&__pyx_api_f_4lxml_5etree_pyunicode, "PyObject *(const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "utf8", (void (**)(void))&__pyx_api_f_4lxml_5etree_utf8, "PyObject *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "getNsTag", (void (**)(void))&__pyx_api_f_4lxml_5etree_getNsTag, "PyObject *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "getNsTagWithEmptyNs", (void (**)(void))&__pyx_api_f_4lxml_5etree_getNsTagWithEmptyNs, "PyObject *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "namespacedName", (void (**)(void))&__pyx_api_f_4lxml_5etree_namespacedName, "PyObject *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "namespacedNameFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_namespacedNameFromNsName, "PyObject *(const xmlChar *, const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "iteratorStoreNext", (void (**)(void))&__pyx_api_f_4lxml_5etree_iteratorStoreNext, "void (struct LxmlElementIterator *, struct LxmlElement *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "initTagMatch", (void (**)(void))&__pyx_api_f_4lxml_5etree_initTagMatch, "void (struct LxmlElementTagMatcher *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_0_10(module, "findOrBuildNodeNsPrefix", (void (**)(void))&__pyx_api_f_4lxml_5etree_findOrBuildNodeNsPrefix, "xmlNs *(struct LxmlDocument *, xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
   Py_DECREF(module); module = 0;
   return 0;
   bad:

{lxml-5.1.1.dist-info → lxml-5.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lxml
-Version: 5.1.1
+Version: 5.2.1
 Summary: Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API.
 Home-page: https://lxml.de/
 Author: lxml dev team
@@ -34,10 +34,12 @@ Provides-Extra: cssselect
 Requires-Dist: cssselect >=0.7 ; extra == 'cssselect'
 Provides-Extra: html5
 Requires-Dist: html5lib ; extra == 'html5'
+Provides-Extra: html_clean
+Requires-Dist: lxml-html-clean ; extra == 'html_clean'
 Provides-Extra: htmlsoup
 Requires-Dist: BeautifulSoup4 ; extra == 'htmlsoup'
 Provides-Extra: source
-Requires-Dist: Cython >=3.0.9 ; extra == 'source'
+Requires-Dist: Cython >=3.0.10 ; extra == 'source'
 
 lxml is a Pythonic, mature binding for the libxml2 and libxslt libraries.  It
 provides safe and convenient access to these libraries using the ElementTree
@@ -62,34 +64,26 @@ an appropriate version of Cython installed.
 
 After an official release of a new stable series, bug fixes may become
 available at
-https://github.com/lxml/lxml/tree/lxml-5.1 .
-Running ``easy_install lxml==5.1bugfix`` will install
+https://github.com/lxml/lxml/tree/lxml-5.2 .
+Running ``easy_install lxml==5.2bugfix`` will install
 the unreleased branch state from
-https://github.com/lxml/lxml/tarball/lxml-5.1#egg=lxml-5.1bugfix
+https://github.com/lxml/lxml/tarball/lxml-5.2#egg=lxml-5.2bugfix
 as soon as a maintenance branch has been established.  Note that this
 requires Cython to be installed at an appropriate version for the build.
 
-5.1.1 (2024-03-28)
+5.2.1 (2024-04-02)
 ==================
 
 Bugs fixed
 ----------
 
-* LP#2048920: ``iterlinks()`` in ``lxml.html`` rejected ``bytes`` input in 5.1.0.
+* LP#2059910: The minimum CPU architecture for the Linux x86 binary wheels was set back to
+  "core2", but with SSE 4.2 enabled.
 
-* High source line numbers from the parser are no longer truncated
-  (up to a C ``long``) when using libxml2 2.11 or later.
+* LP#2059977: ``Element.iterfind("//absolute_path")`` failed with a ``SyntaxError``
+  where it should have issued a warning.
 
-* GH#407: A compatibility test was adapted to recent expat versions.
-  Patch by Miro Hrončok.
-
-Other changes
--------------
-
-* Binary wheels use the library versions libxml2 2.12.6 and libxslt 1.1.39.
-
-* Windows binary wheels use the library versions libxml2 2.11.7 and libxslt 1.1.39.
-
-* Built with Cython 3.0.9.
+* GH#416: The documentation build was using the non-standard ``which`` command.
+  Patch by Michał Górny.
 
 

{lxml-5.1.1.dist-info → lxml-5.2.1.dist-info}/RECORD

@@ -1,5 +1,5 @@
 lxml/ElementInclude.py,sha256=pEvLKSyhNWtZTRr6liUJD-1mIqmbxbcurxcqZv7vNHg,8804
-lxml/__init__.py,sha256=RXd2OOpJetd-S9VxFcgMJb-dN7BvAaYuMeiHbthroig,596
+lxml/__init__.py,sha256=tzYdqsFAQjFVtpQ0r5v4iCKYBxYL3QCUaYNNBsKYgRc,596
 lxml/_elementpath.py,sha256=waZwwmgKbOlNaztLRUOXWBnHnZdQwDWwv7M0GgHwJ44,11229
 lxml/apihelpers.pxi,sha256=4S__cOXO4gq5tsr453GJPeRdbqI5B830SFYsxyUPok0,65403
 lxml/builder.py,sha256=5P0LKYgwJws2fmKAZOr9gkqsBtY-lUC9LDF2W5B5Aik,8332
@@ -10,16 +10,16 @@ lxml/debug.pxi,sha256=HdUEKw8hU1Wzz4nO3hheqrauZlPATsv7N4QPQxCdth4,3372
 lxml/docloader.pxi,sha256=tP6b_zZ5s0-Zj2kf2mFksI8U5whArwOVDOVuaZcbgtM,5950
 lxml/doctestcompare.py,sha256=1r23O3Ki1BypqzkVWh97FEdRq-ENvmFEWuABOWdE0Lo,18219
 lxml/dtd.pxi,sha256=-M93Bx2WbDuyjTW1Btl2eG0U7q7YtkAU9sz9ZQ_5pa4,15706
-lxml/etree.h,sha256=cJHoZm3ijtZPtr8H7LbOvA0PXCtYWTvMJkmo7yA5BNU,9911
-lxml/etree.pypy38-pp73-win_amd64.pyd,sha256=bXXiz-67-_5eYLcFzFelkYKofGYJNz-97-q7bDDwmDU,3973632
-lxml/etree.pyx,sha256=58IECKq3vwBdGgqwvAGnDclq6t7YALya1QKx4Sq3UIo,137562
-lxml/etree_api.h,sha256=NLn4SV8nwM2zqnFuV339sy-S3e2NOINiWKZJSN8l2Yk,17014
+lxml/etree.h,sha256=NPhL2CztGkHk3YgMx2j7pkimDavjx_8CTmCRrdMxslM,9912
+lxml/etree.pypy38-pp73-win_amd64.pyd,sha256=dLrxTDA_cSb6KxnGySwz1VE_0_LHuazpVuBHtLNi0TA,3972096
+lxml/etree.pyx,sha256=NYTMRlUmCau1qaPlc9OEe7lsGUq6MVLkic8gZmjBEkg,137597
+lxml/etree_api.h,sha256=XDHi7lgGoIcyoS8hB27di8OAb0RC6ubGs3ETzd3KDSE,17063
 lxml/extensions.pxi,sha256=s3IkovN6q7I1lvAEs3rh7F-8TtTjTGXRSkptYV9012I,32921
 lxml/iterparse.pxi,sha256=u-fbcHXv9WPz6aOnexe4Vwv5zHJz0-Gc8ScOL-qhcpQ,16965
-lxml/lxml.etree.h,sha256=FEusZqW8FOIvmzI5W_IpnqvSCbOPTQrFyQ-CXbUwt9c,10159
-lxml/lxml.etree_api.h,sha256=M7LaywvBBH99cgu8CtEayqEiygSqfuppNgz8qOJwYIQ,17214
+lxml/lxml.etree.h,sha256=1pHssiGfgydjVlSwEGghrwF4_y2kyELiSojvGEhFHzw,10160
+lxml/lxml.etree_api.h,sha256=vBxFPTxggSL251E5RupQ5ylcFTgKBxQJtF9dnmaofzI,17263
 lxml/nsclasses.pxi,sha256=9TiZjPbP73H8VN0Xu1RmuRB7G-D0pTTSqLPbdTJQt5U,9410
-lxml/objectify.pypy38-pp73-win_amd64.pyd,sha256=cvwhg_4PspkTWuKIi6hAwudlHRCluh7QH7QmdHpWxw8,1721344
+lxml/objectify.pypy38-pp73-win_amd64.pyd,sha256=ADRhMhvU6hHiWSJHW1NL1WlNgEMncf1YEcHNcj4FwnU,1721344
 lxml/objectify.pyx,sha256=IngqdSCtxUav_NklHutFR92AuuNfr9nYchEY3Zprchc,77880
 lxml/objectpath.pxi,sha256=og7LX-a88RrgJI3lUAtuJ8Hvx4RpNf57k7pmafzCuCA,11782
 lxml/parser.pxi,sha256=i4OJWLw7PbCMteTM5n-ur7LOhgy3cTNus5h_iy5-Dfo,83860
@@ -47,7 +47,7 @@ lxml/html/_diffcommand.py,sha256=MfccaYAAKCtzCRe_MCXihC3vnuPUKiJbmOx85Dt37To,216
 lxml/html/_html5builder.py,sha256=XfqNFDQ5HUOWTqubeOe1m5qmIut6I_3Egye75wer7tE,3330
 lxml/html/_setmixin.py,sha256=6cUyIeiMIn5zUytcWHsdWZXyMJXVsfJVVQoAIIe9h7Q,1244
 lxml/html/builder.py,sha256=X4-ZNqczoi9h035AN-4BmfSYDfsVyKpXXGsYPUFAh48,4625
-lxml/html/clean.py,sha256=uBjahSAbXoCfXB8N3d13V3ei7bD4v7FSbnSnsh5Wp6I,28938
+lxml/html/clean.py,sha256=B_rsm3Mz7pn_Z8LnkXeSocL257--sqWJGaxBp2LlmB8,524
 lxml/html/defs.py,sha256=w_8kGoMweUNZxTjQ9UlMeUo8wyTTvzjDG4ub24j8RRg,4371
 lxml/html/diff.py,sha256=Nygvg_a29fblqyj07CeCtl9_OV3AWPFTBjwqEOk8-PM,31271
 lxml/html/formfill.py,sha256=8yXFIO4DNVY-HG8q4O4OtxIQ8qmLpXYQ8T1rFUTkK8c,9980
@@ -62,7 +62,7 @@ lxml/includes/dtdvalid.pxd,sha256=VOt94bqe417bxvfkfbtbsd5kVnwQj4oYSHMfnV2pcsM,70
 lxml/includes/etree_defs.h,sha256=XXz1CliDqEBPvxGNtnmYEwE6D1Xtdib1sMk9JvvkHDM,14624
 lxml/includes/etreepublic.pxd,sha256=s2HRJSuZhwlDi3oHsSBPChA4dgTnWjWWMzBb3VxrtJw,10421
 lxml/includes/htmlparser.pxd,sha256=UEV2wIp8RHekwUAcPWMQe8KBfEv39u0c3LHOsdvRr0k,2858
-lxml/includes/lxml-version.h,sha256=NSdLWdmJLugVjJ1c96DK6f1SRE20OTvFbpjOvFp28YQ,74
+lxml/includes/lxml-version.h,sha256=mC7fdlttvjzautEbr-o-68YHVS5tRvZJLPoqsjmXNy4,74
 lxml/includes/relaxng.pxd,sha256=H5W5XObI5YtRpULeiRy6K6ldUZC0tDQauAFZ7PJSqE4,2679
 lxml/includes/schematron.pxd,sha256=JmKDG9ElNPXJ7rZzOpQjPaIdzIZ1pzMEOT_GjZRK98U,1638
 lxml/includes/tree.pxd,sha256=Uo6hPybaSgh6P9YdQfpr0mftCrSyYZ_w_Z0FyCtOr1c,20885
@@ -163,9 +163,9 @@ lxml/isoschematron/resources/xsl/iso-schematron-xslt1/iso_schematron_message.xsl
 lxml/isoschematron/resources/xsl/iso-schematron-xslt1/iso_schematron_skeleton_for_xslt1.xsl,sha256=Vo1F576odRkdLBmuEEWrLa5LF3SMTX9B6EEGnxUbv_8,73560
 lxml/isoschematron/resources/xsl/iso-schematron-xslt1/iso_svrl_for_xslt1.xsl,sha256=UI7xHx0leNXS9BaU6cyQ4CHeflufKmAE-zjOrihuH-E,20970
 lxml/isoschematron/resources/xsl/iso-schematron-xslt1/readme.txt,sha256=OGLiFswuLJEW5EPYKOeoauuCJFEtVa6jyzBE1OcJI98,3310
-lxml-5.1.1.dist-info/LICENSE.txt,sha256=tircdrXghpYNqK2q-tqeBOMqrzXhzLFM71dCQFqu0nw,1517
-lxml-5.1.1.dist-info/LICENSES.txt,sha256=zlP1CNDLiL20Yh4jbKNIgaP6GAX5ffzPOJYBKKTi6tk,1543
-lxml-5.1.1.dist-info/METADATA,sha256=VvoexjEomv_ZU8-YM7gLjv1vYmQGkPE3lIQUy_U40Po,3616
-lxml-5.1.1.dist-info/WHEEL,sha256=fAsO8Y4sTZ_pYj32GOpGS8gjaRg1Ie4l9VhGLuQJiq4,107
-lxml-5.1.1.dist-info/top_level.txt,sha256=NjD988wqaKq512nshNdLt-uDxsjkp4Bh51m6N-dhUrk,5
-lxml-5.1.1.dist-info/RECORD,,
+lxml-5.2.1.dist-info/LICENSE.txt,sha256=tircdrXghpYNqK2q-tqeBOMqrzXhzLFM71dCQFqu0nw,1517
+lxml-5.2.1.dist-info/LICENSES.txt,sha256=zlP1CNDLiL20Yh4jbKNIgaP6GAX5ffzPOJYBKKTi6tk,1543
+lxml-5.2.1.dist-info/METADATA,sha256=VmZHKN68I3oth5F5GL2yItClDMbCa-6Hxne8JLsILsc,3533
+lxml-5.2.1.dist-info/WHEEL,sha256=fAsO8Y4sTZ_pYj32GOpGS8gjaRg1Ie4l9VhGLuQJiq4,107
+lxml-5.2.1.dist-info/top_level.txt,sha256=NjD988wqaKq512nshNdLt-uDxsjkp4Bh51m6N-dhUrk,5
+lxml-5.2.1.dist-info/RECORD,,