lxml 5.3.2__cp312-cp312-win32.whl → 6.0.0__cp312-cp312-win32.whl

lxml/includes/etree_defs.h

@@ -159,6 +159,10 @@ static PyObject* PyBytes_FromFormat(const char* format, ...) {
 #  define xmlBufUse(buf) xmlBufferLength(buf)
 #endif
 
+#if LIBXML_VERSION < 21500
+#  define xmlCtxtIsStopped(p_ctxt)  ((p_ctxt)->disableSAX != 0)
+#endif
+
 /* libexslt 1.1.25+ support EXSLT functions in XPath */
 #if LIBXSLT_VERSION < 10125
 #define exsltDateXpathCtxtRegister(ctxt, prefix)
@@ -177,7 +181,7 @@ long _ftol2( double dblSource ) { return _ftol( dblSource ); }
 
 #ifdef __GNUC__
 /* Test for GCC > 2.95 */
-#if __GNUC__ > 2 || (__GNUC__ == 2 && (__GNUC_MINOR__ > 95)) 
+#if __GNUC__ > 2 || (__GNUC__ == 2 && (__GNUC_MINOR__ > 95))
 #define unlikely_condition(x) __builtin_expect((x), 0)
 #else /* __GNUC__ > 2 ... */
 #define unlikely_condition(x) (x)
@@ -190,10 +194,6 @@ long _ftol2( double dblSource ) { return _ftol( dblSource ); }
   #define Py_TYPE(ob)   (((PyObject*)(ob))->ob_type)
 #endif
 
-#define PY_NEW(T) \
-     (((PyTypeObject*)(T))->tp_new( \
-             (PyTypeObject*)(T), __pyx_empty_tuple, NULL))
-
 #define _fqtypename(o)  ((Py_TYPE(o))->tp_name)
 
 #define lxml_malloc(count, item_size) \
@@ -268,7 +268,7 @@ static void* lxml_unpack_xmldoc_capsule(PyObject* capsule, int* is_owned) {
  * 'inclusive' is 1).  The _ELEMENT_ variants will only stop on nodes
  * that match _isElement(), the normal variant will stop on every node
  * except text nodes.
- * 
+ *
  * To traverse the node and all of its children and siblings in Pyrex, call
  *    cdef xmlNode* some_node
  *    BEGIN_FOR_EACH_ELEMENT_FROM(some_node.parent, some_node, 1)

lxml/includes/lxml-version.h

@@ -1,3 +1,3 @@
 #ifndef LXML_VERSION_STRING
-#define LXML_VERSION_STRING "5.3.2"
+#define LXML_VERSION_STRING "6.0.0"
 #endif

lxml/includes/tree.pxd

@@ -6,8 +6,9 @@ cdef extern from "lxml-version.h":
     cdef char* LXML_VERSION_STRING
 
 cdef extern from "libxml/xmlversion.h":
-    cdef const_char* xmlParserVersion
-    cdef int LIBXML_VERSION
+    const char* xmlParserVersion
+    int LIBXML_VERSION
+
 
 cdef extern from "libxml/xmlstring.h" nogil:
     ctypedef unsigned char xmlChar
@@ -141,7 +142,7 @@ cdef extern from "libxml/tree.h" nogil:
         XML_ATTRIBUTE_NMTOKENS=    8
         XML_ATTRIBUTE_ENUMERATION= 9
         XML_ATTRIBUTE_NOTATION=    10
-    
+
     ctypedef enum xmlAttributeDefault:
         XML_ATTRIBUTE_NONE=     1
         XML_ATTRIBUTE_REQUIRED= 2
@@ -288,7 +289,7 @@ cdef extern from "libxml/tree.h" nogil:
         xmlDtd* intSubset
         xmlDtd* extSubset
         int properties
-        
+
     ctypedef struct xmlAttr:
         void* _private
         xmlElementType type
@@ -307,7 +308,7 @@ cdef extern from "libxml/tree.h" nogil:
         const_xmlChar* name
         xmlAttr* attr
         xmlDoc* doc
-        
+
     ctypedef struct xmlBuffer
 
     ctypedef struct xmlBuf   # new in libxml2 2.9
@@ -318,14 +319,14 @@ cdef extern from "libxml/tree.h" nogil:
         int error
 
     const_xmlChar* XML_XML_NAMESPACE
-        
+
     cdef void xmlFreeDoc(xmlDoc* cur)
     cdef void xmlFreeDtd(xmlDtd* cur)
     cdef void xmlFreeNode(xmlNode* cur)
     cdef void xmlFreeNsList(xmlNs* ns)
     cdef void xmlFreeNs(xmlNs* ns)
     cdef void xmlFree(void* buf)
-    
+
     cdef xmlNode* xmlNewNode(xmlNs* ns, const_xmlChar* name)
     cdef xmlNode* xmlNewDocText(xmlDoc* doc, const_xmlChar* content)
     cdef xmlNode* xmlNewDocComment(xmlDoc* doc, const_xmlChar* content)
@@ -437,7 +438,7 @@ cdef extern from "libxml/xmlIO.h":
     cdef xmlOutputBuffer* xmlOutputBufferCreateIO(
         xmlOutputWriteCallback iowrite,
         xmlOutputCloseCallback ioclose,
-        void * ioctx, 
+        void * ioctx,
         xmlCharEncodingHandler* encoder) nogil
     cdef xmlOutputBuffer* xmlOutputBufferCreateFile(
         stdio.FILE* file, xmlCharEncodingHandler* encoder) nogil
@@ -471,14 +472,11 @@ cdef extern from "libxml/globals.h" nogil:
     cdef int xmlThrDefKeepBlanksDefaultValue(int onoff)
     cdef int xmlThrDefLineNumbersDefaultValue(int onoff)
     cdef int xmlThrDefIndentTreeOutput(int onoff)
-    
+
 cdef extern from "libxml/xmlmemory.h" nogil:
     cdef void* xmlMalloc(size_t size)
     cdef int xmlMemBlocks()
     cdef int xmlMemUsed()
-    cdef void xmlMemDisplay(stdio.FILE* file)
-    cdef void xmlMemDisplayLast(stdio.FILE* file, long num_bytes)
-    cdef void xmlMemShow(stdio.FILE* file, int count)
 
 cdef extern from "etree_defs.h" nogil:
     cdef bint _isElement(xmlNode* node)

lxml/includes/xmlparser.pxd

@@ -32,11 +32,11 @@ cdef extern from "libxml/parser.h" nogil:
 
     ctypedef void (*commentSAXFunc)(void* ctx, const_xmlChar* value) noexcept
 
-    ctypedef void (*processingInstructionSAXFunc)(void* ctx, 
+    ctypedef void (*processingInstructionSAXFunc)(void* ctx,
                                                   const_xmlChar* target,
                                                   const_xmlChar* data) noexcept
 
-    ctypedef void (*internalSubsetSAXFunc)(void* ctx, 
+    ctypedef void (*internalSubsetSAXFunc)(void* ctx,
                                             const_xmlChar* name,
                                             const_xmlChar* externalID,
                                             const_xmlChar* systemID) noexcept
@@ -99,11 +99,48 @@ cdef extern from "libxml/xmlIO.h" nogil:
 
 cdef extern from "libxml/parser.h" nogil:
 
+    ctypedef enum xmlFeature:
+        XML_WITH_THREAD = 1
+        XML_WITH_TREE = 2
+        XML_WITH_OUTPUT = 3
+        XML_WITH_PUSH = 4
+        XML_WITH_READER = 5
+        XML_WITH_PATTERN = 6
+        XML_WITH_WRITER = 7
+        XML_WITH_SAX1 = 8
+        XML_WITH_FTP = 9
+        XML_WITH_HTTP = 10
+        XML_WITH_VALID = 11
+        XML_WITH_HTML = 12
+        XML_WITH_LEGACY = 13
+        XML_WITH_C14N = 14
+        XML_WITH_CATALOG = 15
+        XML_WITH_XPATH = 16
+        XML_WITH_XPTR = 17
+        XML_WITH_XINCLUDE = 18
+        XML_WITH_ICONV = 19
+        XML_WITH_ISO8859X = 20
+        XML_WITH_UNICODE = 21
+        XML_WITH_REGEXP = 22
+        XML_WITH_AUTOMATA = 23
+        XML_WITH_EXPR = 24
+        XML_WITH_SCHEMAS = 25
+        XML_WITH_SCHEMATRON = 26
+        XML_WITH_MODULES = 27
+        XML_WITH_DEBUG = 28
+        XML_WITH_DEBUG_MEM = 29
+        XML_WITH_DEBUG_RUN = 30
+        XML_WITH_ZLIB = 31
+        XML_WITH_ICU = 32
+        XML_WITH_LZMA = 33
+
+    cdef bint xmlHasFeature(xmlFeature feature)
+
     cdef xmlDict* xmlDictCreate()
     cdef xmlDict* xmlDictCreateSub(xmlDict* subdict)
     cdef void xmlDictFree(xmlDict* sub)
     cdef int xmlDictReference(xmlDict* dict)
-    
+
     cdef int XML_COMPLETE_ATTRS  # SAX option for adding DTD default attributes
     cdef int XML_SKIP_IDS        # SAX option for not building an XML ID dict
 
@@ -207,9 +244,9 @@ cdef extern from "libxml/parser.h" nogil:
     cdef xmlDoc* xmlCtxtReadFile(xmlParserCtxt* ctxt,
                                  char* filename, char* encoding,
                                  int options)
-    cdef xmlDoc* xmlCtxtReadIO(xmlParserCtxt* ctxt, 
-                               xmlInputReadCallback ioread, 
-                               xmlInputCloseCallback ioclose, 
+    cdef xmlDoc* xmlCtxtReadIO(xmlParserCtxt* ctxt,
+                               xmlInputReadCallback ioread,
+                               xmlInputCloseCallback ioclose,
                                void* ioctx,
                                char* URL, char* encoding,
                                int options)
@@ -257,9 +294,10 @@ cdef extern from "libxml/parser.h" nogil:
 
 cdef extern from "libxml/parserInternals.h" nogil:
     cdef xmlParserInput* xmlNewInputStream(xmlParserCtxt* ctxt)
-    cdef xmlParserInput* xmlNewStringInputStream(xmlParserCtxt* ctxt, 
+    cdef xmlParserInput* xmlNewStringInputStream(xmlParserCtxt* ctxt,
                                                  char* buffer)
-    cdef xmlParserInput* xmlNewInputFromFile(xmlParserCtxt* ctxt, 
+    cdef xmlParserInput* xmlNewInputFromFile(xmlParserCtxt* ctxt,
                                              char* filename)
     cdef void xmlFreeInputStream(xmlParserInput* input)
     cdef int xmlSwitchEncoding(xmlParserCtxt* ctxt, int enc)
+    cdef bint xmlCtxtIsStopped(xmlParserCtxt* ctxt)

lxml/lxml.etree.h

@@ -1,4 +1,4 @@
-/* Generated by Cython 3.0.12 */
+/* Generated by Cython 3.1.2 */
 
 #ifndef __PYX_HAVE__lxml__etree
 #define __PYX_HAVE__lxml__etree
@@ -13,22 +13,22 @@ struct LxmlElementBase;
 struct LxmlElementClassLookup;
 struct LxmlFallbackElementClassLookup;
 
-/* "lxml/etree.pyx":355
+/* "lxml/etree.pyx":451
  * 
  * # type of a function that steps from node to node
  * ctypedef public xmlNode* (*_node_to_node_function)(xmlNode*)             # <<<<<<<<<<<<<<
  * 
  * 
- */
+*/
 typedef xmlNode *(*_node_to_node_function)(xmlNode *);
 
-/* "lxml/etree.pyx":371
- * @cython.final
- * @cython.freelist(8)
- * cdef public class _Document [ type LxmlDocumentType, object LxmlDocument ]:             # <<<<<<<<<<<<<<
- *     """Internal base class to reference a libxml document.
+/* "lxml/etree.pyx":465
+ * # Public Python API
  * 
- */
+ * @cython.final             # <<<<<<<<<<<<<<
+ * @cython.freelist(8)
+ * cdef public class _Document [ type LxmlDocumentType, object LxmlDocument ]:
+*/
 struct LxmlDocument {
   PyObject_HEAD
   struct __pyx_vtabstruct_4lxml_5etree__Document *__pyx_vtab;
@@ -38,13 +38,13 @@ struct LxmlDocument {
   struct __pyx_obj_4lxml_5etree__BaseParser *_parser;
 };
 
-/* "lxml/etree.pyx":720
+/* "lxml/etree.pyx":817
  * 
- * @cython.no_gc_clear
- * cdef public class _Element [ type LxmlElementType, object LxmlElement ]:             # <<<<<<<<<<<<<<
- *     """Element class.
  * 
- */
+ * @cython.no_gc_clear             # <<<<<<<<<<<<<<
+ * cdef public class _Element [ type LxmlElementType, object LxmlElement ]:
+ *     """Element class.
+*/
 struct LxmlElement {
   PyObject_HEAD
   struct LxmlDocument *_doc;
@@ -52,13 +52,13 @@ struct LxmlElement {
   PyObject *_tag;
 };
 
-/* "lxml/etree.pyx":1895
+/* "lxml/etree.pyx":1991
  * 
  * 
  * cdef public class _ElementTree [ type LxmlElementTreeType,             # <<<<<<<<<<<<<<
  *                                  object LxmlElementTree ]:
  *     cdef _Document _doc
- */
+*/
 struct LxmlElementTree {
   PyObject_HEAD
   struct __pyx_vtabstruct_4lxml_5etree__ElementTree *__pyx_vtab;
@@ -66,13 +66,13 @@ struct LxmlElementTree {
   struct LxmlElement *_context_node;
 };
 
-/* "lxml/etree.pyx":2669
+/* "lxml/etree.pyx":2765
  * 
  * 
  * cdef public class _ElementTagMatcher [ object LxmlElementTagMatcher,             # <<<<<<<<<<<<<<
  *                                        type LxmlElementTagMatcherType ]:
  *     """
- */
+*/
 struct LxmlElementTagMatcher {
   PyObject_HEAD
   struct __pyx_vtabstruct_4lxml_5etree__ElementTagMatcher *__pyx_vtab;
@@ -82,13 +82,13 @@ struct LxmlElementTagMatcher {
   char *_name;
 };
 
-/* "lxml/etree.pyx":2700
+/* "lxml/etree.pyx":2796
  *                 self._name = NULL
  * 
  * cdef public class _ElementIterator(_ElementTagMatcher) [             # <<<<<<<<<<<<<<
  *     object LxmlElementIterator, type LxmlElementIteratorType ]:
  *     """
- */
+*/
 struct LxmlElementIterator {
   struct LxmlElementTagMatcher __pyx_base;
   struct LxmlElement *_node;
@@ -101,7 +101,7 @@ struct LxmlElementIterator {
  * cdef public class ElementBase(_Element) [ type LxmlElementBaseType,             # <<<<<<<<<<<<<<
  *                                           object LxmlElementBase ]:
  *     """ElementBase(*children, attrib=None, nsmap=None, **_extra)
- */
+*/
 struct LxmlElementBase {
   struct LxmlElement __pyx_base;
 };
@@ -112,7 +112,7 @@ struct LxmlElementBase {
  * ctypedef public object (*_element_class_lookup_function)(object, _Document, xmlNode*)             # <<<<<<<<<<<<<<
  * 
  * # class to store element class lookup functions
- */
+*/
 typedef PyObject *(*_element_class_lookup_function)(PyObject *, struct LxmlDocument *, xmlNode *);
 
 /* "src/lxml/classlookup.pxi":213
@@ -121,7 +121,7 @@ typedef PyObject *(*_element_class_lookup_function)(PyObject *, struct LxmlDocum
  * cdef public class ElementClassLookup [ type LxmlElementClassLookupType,             # <<<<<<<<<<<<<<
  *                                        object LxmlElementClassLookup ]:
  *     """ElementClassLookup(self)
- */
+*/
 struct LxmlElementClassLookup {
   PyObject_HEAD
   _element_class_lookup_function _lookup_function;
@@ -133,7 +133,7 @@ struct LxmlElementClassLookup {
  * cdef public class FallbackElementClassLookup(ElementClassLookup) \             # <<<<<<<<<<<<<<
  *          [ type LxmlFallbackElementClassLookupType,
  *            object LxmlFallbackElementClassLookup ]:
- */
+*/
 struct LxmlFallbackElementClassLookup {
   struct LxmlElementClassLookup __pyx_base;
   struct __pyx_vtabstruct_4lxml_5etree_FallbackElementClassLookup *__pyx_vtab;
@@ -224,9 +224,6 @@ __PYX_EXTERN_C xmlNs *findOrBuildNodeNsPrefix(struct LxmlDocument *, xmlNode *,
 /* WARNING: the interface of the module init function changed in CPython 3.5. */
 /* It now returns a PyModuleDef instance instead of a PyModule instance. */
 
-#if PY_MAJOR_VERSION < 3
-PyMODINIT_FUNC initetree(void);
-#else
 /* WARNING: Use PyImport_AppendInittab("etree", PyInit_etree) instead of calling PyInit_etree directly from Python 3.5 */
 PyMODINIT_FUNC PyInit_etree(void);
 
@@ -243,6 +240,5 @@ static PyObject* __PYX_WARN_IF_PyInit_etree_INIT_CALLED(PyObject* res) {
 }
 #define PyInit_etree() __PYX_WARN_IF_PyInit_etree_INIT_CALLED(PyInit_etree())
 #endif
-#endif
 
 #endif /* !__PYX_HAVE__lxml__etree */

lxml/lxml.etree_api.h

@@ -1,4 +1,4 @@
-/* Generated by Cython 3.0.12 */
+/* Generated by Cython 3.1.2 */
 
 #ifndef __PYX_HAVE_API__lxml__etree
 #define __PYX_HAVE_API__lxml__etree
@@ -98,19 +98,26 @@ 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_12
-#define __PYX_HAVE_RT_ImportFunction_3_0_12
-static int __Pyx_ImportFunction_3_0_12(PyObject *module, const char *funcname, void (**f)(void), const char *sig) {
+static int __Pyx_ImportFunction_3_1_2(PyObject *module, const char *funcname, void (**f)(void), const char *sig);
+
+#ifndef __PYX_HAVE_RT_ImportFunction_3_1_2
+#define __PYX_HAVE_RT_ImportFunction_3_1_2
+static int __Pyx_ImportFunction_3_1_2(PyObject *module, const char *funcname, void (**f)(void), const char *sig) {
     PyObject *d = 0;
     PyObject *cobj = 0;
     union {
         void (*fp)(void);
         void *p;
     } tmp;
-    d = PyObject_GetAttrString(module, (char *)"__pyx_capi__");
+    d = PyObject_GetAttrString(module, "__pyx_capi__");
     if (!d)
         goto bad;
+#if (defined(Py_LIMITED_API) && Py_LIMITED_API >= 0x030d0000) || (!defined(Py_LIMITED_API) && PY_VERSION_HEX >= 0x030d0000)
+    PyDict_GetItemStringRef(d, funcname, &cobj);
+#else
     cobj = PyDict_GetItemString(d, funcname);
+    Py_XINCREF(cobj);
+#endif
     if (!cobj) {
         PyErr_Format(PyExc_ImportError,
             "%.200s does not export expected C function %.200s",
@@ -128,9 +135,11 @@ static int __Pyx_ImportFunction_3_0_12(PyObject *module, const char *funcname, v
     if (!(*f))
         goto bad;
     Py_DECREF(d);
+    Py_DECREF(cobj);
     return 0;
 bad:
     Py_XDECREF(d);
+    Py_XDECREF(cobj);
     return -1;
 }
 #endif
@@ -140,51 +149,51 @@ static int import_lxml__etree(void) {
   PyObject *module = 0;
   module = PyImport_ImportModule("lxml.etree");
   if (!module) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "deepcopyNodeToDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_deepcopyNodeToDocument, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "elementTreeFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementTreeFactory, "struct LxmlElementTree *(struct LxmlElement *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "newElementTree", (void (**)(void))&__pyx_api_f_4lxml_5etree_newElementTree, "struct LxmlElementTree *(struct LxmlElement *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "adoptExternalDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_adoptExternalDocument, "struct LxmlElementTree *(xmlDoc *, PyObject *, int)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "elementFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementFactory, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(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_12(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_12(module, "setElementClassLookupFunction", (void (**)(void))&__pyx_api_f_4lxml_5etree_setElementClassLookupFunction, "void (_element_class_lookup_function, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "lookupDefaultElementClass", (void (**)(void))&__pyx_api_f_4lxml_5etree_lookupDefaultElementClass, "PyObject *(PyObject *, PyObject *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "lookupNamespaceElementClass", (void (**)(void))&__pyx_api_f_4lxml_5etree_lookupNamespaceElementClass, "PyObject *(PyObject *, PyObject *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "callLookupFallback", (void (**)(void))&__pyx_api_f_4lxml_5etree_callLookupFallback, "PyObject *(struct LxmlFallbackElementClassLookup *, struct LxmlDocument *, xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "tagMatches", (void (**)(void))&__pyx_api_f_4lxml_5etree_tagMatches, "int (xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "documentOrRaise", (void (**)(void))&__pyx_api_f_4lxml_5etree_documentOrRaise, "struct LxmlDocument *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "rootNodeOrRaise", (void (**)(void))&__pyx_api_f_4lxml_5etree_rootNodeOrRaise, "struct LxmlElement *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "hasText", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasText, "int (xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "hasTail", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasTail, "int (xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "textOf", (void (**)(void))&__pyx_api_f_4lxml_5etree_textOf, "PyObject *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "tailOf", (void (**)(void))&__pyx_api_f_4lxml_5etree_tailOf, "PyObject *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "setNodeText", (void (**)(void))&__pyx_api_f_4lxml_5etree_setNodeText, "int (xmlNode *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "setTailText", (void (**)(void))&__pyx_api_f_4lxml_5etree_setTailText, "int (xmlNode *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "attributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_attributeValue, "PyObject *(xmlNode *, xmlAttr *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "attributeValueFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_attributeValueFromNsName, "PyObject *(xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "getAttributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_getAttributeValue, "PyObject *(struct LxmlElement *, PyObject *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "iterattributes", (void (**)(void))&__pyx_api_f_4lxml_5etree_iterattributes, "PyObject *(struct LxmlElement *, int)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "collectAttributes", (void (**)(void))&__pyx_api_f_4lxml_5etree_collectAttributes, "PyObject *(xmlNode *, int)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "setAttributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_setAttributeValue, "int (struct LxmlElement *, PyObject *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "delAttribute", (void (**)(void))&__pyx_api_f_4lxml_5etree_delAttribute, "int (struct LxmlElement *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "delAttributeFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_delAttributeFromNsName, "int (xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "hasChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasChild, "int (xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "findChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChild, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "findChildForwards", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChildForwards, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "findChildBackwards", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChildBackwards, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "nextElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_nextElement, "xmlNode *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "previousElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_previousElement, "xmlNode *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "appendChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_appendChild, "void (struct LxmlElement *, struct LxmlElement *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "appendChildToElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_appendChildToElement, "int (struct LxmlElement *, struct LxmlElement *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "pyunicode", (void (**)(void))&__pyx_api_f_4lxml_5etree_pyunicode, "PyObject *(const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "utf8", (void (**)(void))&__pyx_api_f_4lxml_5etree_utf8, "PyObject *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "getNsTag", (void (**)(void))&__pyx_api_f_4lxml_5etree_getNsTag, "PyObject *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "getNsTagWithEmptyNs", (void (**)(void))&__pyx_api_f_4lxml_5etree_getNsTagWithEmptyNs, "PyObject *(PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "namespacedName", (void (**)(void))&__pyx_api_f_4lxml_5etree_namespacedName, "PyObject *(xmlNode *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "namespacedNameFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_namespacedNameFromNsName, "PyObject *(const xmlChar *, const xmlChar *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "iteratorStoreNext", (void (**)(void))&__pyx_api_f_4lxml_5etree_iteratorStoreNext, "void (struct LxmlElementIterator *, struct LxmlElement *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(module, "initTagMatch", (void (**)(void))&__pyx_api_f_4lxml_5etree_initTagMatch, "void (struct LxmlElementTagMatcher *, PyObject *)") < 0) goto bad;
-  if (__Pyx_ImportFunction_3_0_12(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_1_2(module, "deepcopyNodeToDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_deepcopyNodeToDocument, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "elementTreeFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementTreeFactory, "struct LxmlElementTree *(struct LxmlElement *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "newElementTree", (void (**)(void))&__pyx_api_f_4lxml_5etree_newElementTree, "struct LxmlElementTree *(struct LxmlElement *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "adoptExternalDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_adoptExternalDocument, "struct LxmlElementTree *(xmlDoc *, PyObject *, int)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "elementFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementFactory, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(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_1_2(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_1_2(module, "setElementClassLookupFunction", (void (**)(void))&__pyx_api_f_4lxml_5etree_setElementClassLookupFunction, "void (_element_class_lookup_function, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "lookupDefaultElementClass", (void (**)(void))&__pyx_api_f_4lxml_5etree_lookupDefaultElementClass, "PyObject *(PyObject *, PyObject *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "lookupNamespaceElementClass", (void (**)(void))&__pyx_api_f_4lxml_5etree_lookupNamespaceElementClass, "PyObject *(PyObject *, PyObject *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "callLookupFallback", (void (**)(void))&__pyx_api_f_4lxml_5etree_callLookupFallback, "PyObject *(struct LxmlFallbackElementClassLookup *, struct LxmlDocument *, xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "tagMatches", (void (**)(void))&__pyx_api_f_4lxml_5etree_tagMatches, "int (xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "documentOrRaise", (void (**)(void))&__pyx_api_f_4lxml_5etree_documentOrRaise, "struct LxmlDocument *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "rootNodeOrRaise", (void (**)(void))&__pyx_api_f_4lxml_5etree_rootNodeOrRaise, "struct LxmlElement *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "hasText", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasText, "int (xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "hasTail", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasTail, "int (xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "textOf", (void (**)(void))&__pyx_api_f_4lxml_5etree_textOf, "PyObject *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "tailOf", (void (**)(void))&__pyx_api_f_4lxml_5etree_tailOf, "PyObject *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "setNodeText", (void (**)(void))&__pyx_api_f_4lxml_5etree_setNodeText, "int (xmlNode *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "setTailText", (void (**)(void))&__pyx_api_f_4lxml_5etree_setTailText, "int (xmlNode *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "attributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_attributeValue, "PyObject *(xmlNode *, xmlAttr *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "attributeValueFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_attributeValueFromNsName, "PyObject *(xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "getAttributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_getAttributeValue, "PyObject *(struct LxmlElement *, PyObject *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "iterattributes", (void (**)(void))&__pyx_api_f_4lxml_5etree_iterattributes, "PyObject *(struct LxmlElement *, int)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "collectAttributes", (void (**)(void))&__pyx_api_f_4lxml_5etree_collectAttributes, "PyObject *(xmlNode *, int)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "setAttributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_setAttributeValue, "int (struct LxmlElement *, PyObject *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "delAttribute", (void (**)(void))&__pyx_api_f_4lxml_5etree_delAttribute, "int (struct LxmlElement *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "delAttributeFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_delAttributeFromNsName, "int (xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "hasChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasChild, "int (xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "findChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChild, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "findChildForwards", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChildForwards, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "findChildBackwards", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChildBackwards, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "nextElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_nextElement, "xmlNode *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "previousElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_previousElement, "xmlNode *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "appendChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_appendChild, "void (struct LxmlElement *, struct LxmlElement *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "appendChildToElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_appendChildToElement, "int (struct LxmlElement *, struct LxmlElement *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "pyunicode", (void (**)(void))&__pyx_api_f_4lxml_5etree_pyunicode, "PyObject *(const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "utf8", (void (**)(void))&__pyx_api_f_4lxml_5etree_utf8, "PyObject *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "getNsTag", (void (**)(void))&__pyx_api_f_4lxml_5etree_getNsTag, "PyObject *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "getNsTagWithEmptyNs", (void (**)(void))&__pyx_api_f_4lxml_5etree_getNsTagWithEmptyNs, "PyObject *(PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "namespacedName", (void (**)(void))&__pyx_api_f_4lxml_5etree_namespacedName, "PyObject *(xmlNode *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "namespacedNameFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_namespacedNameFromNsName, "PyObject *(const xmlChar *, const xmlChar *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "iteratorStoreNext", (void (**)(void))&__pyx_api_f_4lxml_5etree_iteratorStoreNext, "void (struct LxmlElementIterator *, struct LxmlElement *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(module, "initTagMatch", (void (**)(void))&__pyx_api_f_4lxml_5etree_initTagMatch, "void (struct LxmlElementTagMatcher *, PyObject *)") < 0) goto bad;
+  if (__Pyx_ImportFunction_3_1_2(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/objectify.pyx

@@ -18,6 +18,7 @@ from lxml.includes cimport tree
 cimport lxml.includes.etreepublic as cetree
 cimport libc.string as cstring_h   # not to be confused with stdlib 'string'
 from libc.string cimport const_char
+from libc cimport limits
 
 __all__ = ['BoolElement', 'DataElement', 'E', 'Element', 'ElementMaker',
            'FloatElement', 'IntElement', 'NoneElement',
@@ -420,8 +421,11 @@ cdef object _lookupChild(_Element parent, tag):
     cdef tree.xmlNode* c_node
     c_node = parent._c_node
     ns, tag = cetree.getNsTagWithEmptyNs(tag)
+    c_tag_len = len(<bytes> tag)
+    if c_tag_len > limits.INT_MAX:
+        return None
     c_tag = tree.xmlDictExists(
-        c_node.doc.dict, _xcstr(tag), python.PyBytes_GET_SIZE(tag))
+        c_node.doc.dict, _xcstr(tag), <int> c_tag_len)
     if c_tag is NULL:
         return None # not in the hash map => not in the tree
     if ns is None:
@@ -1283,7 +1287,7 @@ cdef object _guessElementClass(tree.xmlNode* c_node):
         return None
     if value == '':
         return StringElement
-    
+
     for type_check, pytype in _TYPE_CHECKS:
         try:
             type_check(value)
@@ -1689,8 +1693,8 @@ def annotate(element_or_tree, *, ignore_old=True, ignore_xsi=False,
 
     If the 'ignore_xsi' keyword argument is False (the default), existing
     'xsi:type' attributes will be used for the type annotation, if they fit the
-    element text values. 
-    
+    element text values.
+
     Note that the mapping from Python types to XSI types is usually ambiguous.
     Currently, only the first XSI type name in the corresponding PyType
     definition will be used for annotation.  Thus, you should consider naming
@@ -1705,7 +1709,7 @@ def annotate(element_or_tree, *, ignore_old=True, ignore_xsi=False,
     elements.  Pass 'string', for example, to make string values the default.
 
     The keyword arguments 'annotate_xsi' (default: 0) and 'annotate_pytype'
-    (default: 1) control which kind(s) of annotation to use. 
+    (default: 1) control which kind(s) of annotation to use.
     """
     cdef _Element  element
     element = cetree.rootNodeOrRaise(element_or_tree)
@@ -1878,7 +1882,7 @@ def deannotate(element_or_tree, *, bint pytype=True, bint xsi=True,
     and/or 'xsi:type' attributes and/or 'xsi:nil' attributes.
 
     If the 'pytype' keyword argument is True (the default), 'py:pytype'
-    attributes will be removed. If the 'xsi' keyword argument is True (the 
+    attributes will be removed. If the 'xsi' keyword argument is True (the
     default), 'xsi:type' attributes will be removed.
     If the 'xsi_nil' keyword argument is True (default: False), 'xsi:nil'
     attributes will be removed.
@@ -2124,7 +2128,7 @@ def DataElement(_value, attrib=None, nsmap=None, *, _pytype=None, _xsi=None,
         stringify = unicode if py_type is None else py_type.stringify
         strval = stringify(_value)
 
-    if _pytype is not None: 
+    if _pytype is not None:
         if _pytype == "NoneType" or _pytype == "none":
             strval = None
             _attributes[XML_SCHEMA_INSTANCE_NIL_ATTR] = "true"