lxml 6.0.0__cp312-cp312-macosx_10_13_universal2.whl

lxml/includes/etree_defs.h

@@ -0,0 +1,379 @@
+#ifndef HAS_ETREE_DEFS_H
+#define HAS_ETREE_DEFS_H
+
+/* quick check for Python/libxml2/libxslt devel setup */
+#include "Python.h"
+#ifndef PY_VERSION_HEX
+#  error the development package of Python (header files etc.) is not installed correctly
+#elif PY_VERSION_HEX < 0x03060000
+#  error this version of lxml requires Python 3.6 or later
+#endif
+
+#include "libxml/xmlversion.h"
+#ifndef LIBXML_VERSION
+#  error the development package of libxml2 (header files etc.) is not installed correctly
+#elif LIBXML_VERSION < 20700
+#  error minimum required version of libxml2 is 2.7.0
+#endif
+
+#include "libxslt/xsltconfig.h"
+#ifndef LIBXSLT_VERSION
+#  error the development package of libxslt (header files etc.) is not installed correctly
+#elif LIBXSLT_VERSION < 10123
+#  error minimum required version of libxslt is 1.1.23
+#endif
+
+
+/* v_arg functions */
+#define va_int(ap)     va_arg(ap, int)
+#define va_charptr(ap) va_arg(ap, char *)
+
+#ifdef PYPY_VERSION
+#    define IS_PYPY 1
+#else
+#    define IS_PYPY 0
+#endif
+
+/* unused */
+#define IS_PYTHON2 0
+#define IS_PYTHON3 1
+#undef LXML_UNICODE_STRINGS
+#define LXML_UNICODE_STRINGS 1
+
+#if !IS_PYPY
+#  define PyWeakref_LockObject(obj)          (NULL)
+#endif
+
+/* Threading is not currently supported by PyPy */
+#if IS_PYPY
+#  ifndef WITHOUT_THREADING
+#    define WITHOUT_THREADING
+#  endif
+#endif
+
+#if IS_PYPY
+#  ifndef PyUnicode_FromFormat
+#    define PyUnicode_FromFormat  PyString_FromFormat
+#  endif
+#  if !defined(PyBytes_FromFormat)
+#    ifdef PyString_FromFormat
+#      define PyBytes_FromFormat  PyString_FromFormat
+#    else
+#include <stdarg.h>
+static PyObject* PyBytes_FromFormat(const char* format, ...) {
+    PyObject *string;
+    va_list vargs;
+#ifdef HAVE_STDARG_PROTOTYPES
+    va_start(vargs, format);
+#else
+    va_start(vargs);
+#endif
+    string = PyUnicode_FromFormatV(format, vargs);
+    va_end(vargs);
+    if (string && PyUnicode_Check(string)) {
+        PyObject *bstring = PyUnicode_AsUTF8String(string);
+        Py_DECREF(string);
+        string = bstring;
+    }
+    if (string && !PyBytes_CheckExact(string)) {
+        Py_DECREF(string);
+        string = NULL;
+        PyErr_SetString(PyExc_TypeError, "String formatting and encoding failed to return bytes object");
+    }
+    return string;
+}
+#    endif
+#  endif
+#endif
+
+#if PY_VERSION_HEX >= 0x030B00A1
+/* Python 3.12 doesn't have wstr Unicode strings any more. */
+#undef PyUnicode_GET_DATA_SIZE
+#define PyUnicode_GET_DATA_SIZE(ustr)  (0)
+#undef PyUnicode_AS_DATA
+#define PyUnicode_AS_DATA(ustr)  (NULL)
+#undef PyUnicode_IS_READY
+#define PyUnicode_IS_READY(ustr)  (1)
+#endif
+
+#ifdef WITHOUT_THREADING
+#  undef PyEval_SaveThread
+#  define PyEval_SaveThread() (NULL)
+#  undef PyEval_RestoreThread
+#  define PyEval_RestoreThread(state)  if (state); else {}
+#  undef PyGILState_Ensure
+#  define PyGILState_Ensure() (PyGILState_UNLOCKED)
+#  undef PyGILState_Release
+#  define PyGILState_Release(state)  if (state); else {}
+#  undef  Py_UNBLOCK_THREADS
+#  define Py_UNBLOCK_THREADS  _save = NULL;
+#  undef  Py_BLOCK_THREADS
+#  define Py_BLOCK_THREADS  if (_save); else {}
+#endif
+
+#ifdef WITHOUT_THREADING
+#  define ENABLE_THREADING 0
+#else
+#  define ENABLE_THREADING 1
+#endif
+
+#if LIBXML_VERSION < 20704
+/* FIXME: hack to make new error reporting compile in old libxml2 versions */
+#  define xmlStructuredErrorContext NULL
+#  define xmlXIncludeProcessTreeFlagsData(n,o,d) xmlXIncludeProcessTreeFlags(n,o)
+#endif
+
+/* schematron was added in libxml2 2.6.21 */
+#ifdef LIBXML_SCHEMATRON_ENABLED
+#  define ENABLE_SCHEMATRON 1
+#else
+#  define ENABLE_SCHEMATRON 0
+#  define XML_SCHEMATRON_OUT_QUIET 0
+#  define XML_SCHEMATRON_OUT_XML 0
+#  define XML_SCHEMATRON_OUT_ERROR 0
+   typedef void xmlSchematron;
+   typedef void xmlSchematronParserCtxt;
+   typedef void xmlSchematronValidCtxt;
+#  define xmlSchematronNewDocParserCtxt(doc) NULL
+#  define xmlSchematronNewParserCtxt(file) NULL
+#  define xmlSchematronParse(ctxt) NULL
+#  define xmlSchematronFreeParserCtxt(ctxt)
+#  define xmlSchematronFree(schema)
+#  define xmlSchematronNewValidCtxt(schema, options) NULL
+#  define xmlSchematronValidateDoc(ctxt, doc) 0
+#  define xmlSchematronFreeValidCtxt(ctxt)
+#  define xmlSchematronSetValidStructuredErrors(ctxt, errorfunc, data)
+#endif
+
+#if LIBXML_VERSION < 20708
+#  define HTML_PARSE_NODEFDTD 4
+#endif
+#if LIBXML_VERSION < 20900
+#  define XML_PARSE_BIG_LINES 4194304
+#endif
+
+#include "libxml/tree.h"
+#ifndef LIBXML2_NEW_BUFFER
+   typedef xmlBuffer xmlBuf;
+#  define xmlBufContent(buf) xmlBufferContent(buf)
+#  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)
+#define exsltSetsXpathCtxtRegister(ctxt, prefix)
+#define exsltMathXpathCtxtRegister(ctxt, prefix)
+#define exsltStrXpathCtxtRegister(ctxt, prefix)
+#endif
+
+#define LXML_GET_XSLT_ENCODING(result_var, style) XSLT_GET_IMPORT_PTR(result_var, style, encoding)
+
+/* work around MSDEV 6.0 */
+#if (_MSC_VER == 1200) && (WINVER < 0x0500)
+long _ftol( double ); //defined by VC6 C libs
+long _ftol2( double dblSource ) { return _ftol( dblSource ); }
+#endif
+
+#ifdef __GNUC__
+/* Test for GCC > 2.95 */
+#if __GNUC__ > 2 || (__GNUC__ == 2 && (__GNUC_MINOR__ > 95))
+#define unlikely_condition(x) __builtin_expect((x), 0)
+#else /* __GNUC__ > 2 ... */
+#define unlikely_condition(x) (x)
+#endif /* __GNUC__ > 2 ... */
+#else /* __GNUC__ */
+#define unlikely_condition(x) (x)
+#endif /* __GNUC__ */
+
+#ifndef Py_TYPE
+  #define Py_TYPE(ob)   (((PyObject*)(ob))->ob_type)
+#endif
+
+#define _fqtypename(o)  ((Py_TYPE(o))->tp_name)
+
+#define lxml_malloc(count, item_size) \
+    (unlikely_condition((size_t)(count) > (size_t) (PY_SSIZE_T_MAX / item_size)) ? NULL : \
+     (PyMem_Malloc((count) * item_size)))
+
+#define lxml_realloc(mem, count, item_size) \
+    (unlikely_condition((size_t)(count) > (size_t) (PY_SSIZE_T_MAX / item_size)) ? NULL : \
+     (PyMem_Realloc(mem, (count) * item_size)))
+
+#define lxml_free(mem)  PyMem_Free(mem)
+
+#define _isString(obj)   (PyUnicode_Check(obj) || PyBytes_Check(obj))
+
+#define _isElement(c_node) \
+        (((c_node)->type == XML_ELEMENT_NODE) || \
+         ((c_node)->type == XML_COMMENT_NODE) || \
+         ((c_node)->type == XML_ENTITY_REF_NODE) || \
+         ((c_node)->type == XML_PI_NODE))
+
+#define _isElementOrXInclude(c_node) \
+        (_isElement(c_node)                     || \
+         ((c_node)->type == XML_XINCLUDE_START) || \
+         ((c_node)->type == XML_XINCLUDE_END))
+
+#define _getNs(c_node) \
+        (((c_node)->ns == 0) ? 0 : ((c_node)->ns->href))
+
+
+#include "string.h"
+static void* lxml_unpack_xmldoc_capsule(PyObject* capsule, int* is_owned) {
+    xmlDoc *c_doc;
+    void *context;
+    *is_owned = 0;
+    if (unlikely_condition(!PyCapsule_IsValid(capsule, (const char*)"libxml2:xmlDoc"))) {
+        PyErr_SetString(
+                PyExc_TypeError,
+                "Not a valid capsule. The capsule argument must be a capsule object with name libxml2:xmlDoc");
+        return NULL;
+    }
+    c_doc = (xmlDoc*) PyCapsule_GetPointer(capsule, (const char*)"libxml2:xmlDoc");
+    if (unlikely_condition(!c_doc)) return NULL;
+
+    if (unlikely_condition(c_doc->type != XML_DOCUMENT_NODE && c_doc->type != XML_HTML_DOCUMENT_NODE)) {
+        PyErr_Format(
+            PyExc_ValueError,
+            "Illegal document provided: expected XML or HTML, found %d", (int)c_doc->type);
+        return NULL;
+    }
+
+    context = PyCapsule_GetContext(capsule);
+    if (unlikely_condition(!context && PyErr_Occurred())) return NULL;
+    if (context && strcmp((const char*) context, "destructor:xmlFreeDoc") == 0) {
+        /* take ownership by setting destructor to NULL */
+        if (PyCapsule_SetDestructor(capsule, NULL) == 0) {
+            /* ownership transferred => invalidate capsule by clearing its name */
+            if (unlikely_condition(PyCapsule_SetName(capsule, NULL))) {
+                /* this should never happen since everything above succeeded */
+                xmlFreeDoc(c_doc);
+                return NULL;
+            }
+            *is_owned = 1;
+        }
+    }
+    return c_doc;
+}
+
+/* Macro pair implementation of a depth first tree walker
+ *
+ * Calls the code block between the BEGIN and END macros for all elements
+ * below c_tree_top (exclusively), starting at c_node (inclusively iff
+ * '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)
+ *    # do something with some_node
+ *    END_FOR_EACH_ELEMENT_FROM(some_node)
+ *
+ * To traverse only the children and siblings of a node, call
+ *    cdef xmlNode* some_node
+ *    BEGIN_FOR_EACH_ELEMENT_FROM(some_node.parent, some_node, 0)
+ *    # do something with some_node
+ *    END_FOR_EACH_ELEMENT_FROM(some_node)
+ *
+ * To traverse only the children, do:
+ *    cdef xmlNode* some_node
+ *    some_node = parent_node.children
+ *    BEGIN_FOR_EACH_ELEMENT_FROM(parent_node, some_node, 1)
+ *    # do something with some_node
+ *    END_FOR_EACH_ELEMENT_FROM(some_node)
+ *
+ * NOTE: 'some_node' MUST be a plain 'xmlNode*' !
+ *
+ * NOTE: parent modification during the walk can divert the iterator, but
+ *       should not segfault !
+ */
+
+#define _LX__ELEMENT_MATCH(c_node, only_elements)  \
+    ((only_elements) ? (_isElement(c_node)) : 1)
+
+#define _LX__ADVANCE_TO_NEXT(c_node, only_elements)                        \
+    while ((c_node != 0) && (!_LX__ELEMENT_MATCH(c_node, only_elements)))  \
+        c_node = c_node->next;
+
+#define _LX__TRAVERSE_TO_NEXT(c_stop_node, c_node, only_elements)   \
+{                                                                   \
+    /* walk through children first */                               \
+    xmlNode* _lx__next = c_node->children;		            \
+    if (_lx__next != 0) {                                           \
+        if (c_node->type == XML_ENTITY_REF_NODE || c_node->type == XML_DTD_NODE) { \
+            _lx__next = 0;                                          \
+        } else {                                                    \
+            _LX__ADVANCE_TO_NEXT(_lx__next, only_elements)	    \
+        }                                                           \
+    }							            \
+    if ((_lx__next == 0) && (c_node != c_stop_node)) {              \
+        /* try siblings */                                          \
+        _lx__next = c_node->next;                                   \
+        _LX__ADVANCE_TO_NEXT(_lx__next, only_elements)              \
+        /* back off through parents */                              \
+        while (_lx__next == 0) {                                    \
+            c_node = c_node->parent;                                \
+            if (c_node == 0)                                        \
+                break;                                              \
+            if (c_node == c_stop_node)                              \
+                break;                                              \
+            if ((only_elements) && !_isElement(c_node))	            \
+                break;                                              \
+            /* we already traversed the parents -> siblings */      \
+            _lx__next = c_node->next;                               \
+            _LX__ADVANCE_TO_NEXT(_lx__next, only_elements)	    \
+        }                                                           \
+    }                                                               \
+    c_node = _lx__next;                                             \
+}
+
+#define _LX__BEGIN_FOR_EACH_FROM(c_tree_top, c_node, inclusive, only_elements)     \
+{									      \
+    if (c_node != 0) {							      \
+        const xmlNode* _lx__tree_top = (c_tree_top);                          \
+        const int _lx__only_elements = (only_elements);                       \
+        /* make sure we start at an element */                   	      \
+        if (!_LX__ELEMENT_MATCH(c_node, _lx__only_elements)) {		      \
+            /* we skip the node, so 'inclusive' is irrelevant */              \
+            if (c_node == _lx__tree_top)                                      \
+                c_node = 0; /* nothing to traverse */                         \
+            else {                                                            \
+                c_node = c_node->next;                                        \
+                _LX__ADVANCE_TO_NEXT(c_node, _lx__only_elements)              \
+            }                                                                 \
+        } else if (! (inclusive)) {                                           \
+            /* skip the first node */                                         \
+            _LX__TRAVERSE_TO_NEXT(_lx__tree_top, c_node, _lx__only_elements)  \
+        }                                                                     \
+                                                                              \
+        /* now run the user code on the elements we find */                   \
+        while (c_node != 0) {                                                 \
+            /* here goes the code to be run for each element */
+
+#define _LX__END_FOR_EACH_FROM(c_node)                                        \
+            _LX__TRAVERSE_TO_NEXT(_lx__tree_top, c_node, _lx__only_elements)  \
+        }                                                                     \
+    }                                                                         \
+}
+
+
+#define BEGIN_FOR_EACH_ELEMENT_FROM(c_tree_top, c_node, inclusive)   \
+    _LX__BEGIN_FOR_EACH_FROM(c_tree_top, c_node, inclusive, 1)
+
+#define END_FOR_EACH_ELEMENT_FROM(c_node)   \
+    _LX__END_FOR_EACH_FROM(c_node)
+
+#define BEGIN_FOR_EACH_FROM(c_tree_top, c_node, inclusive)   \
+    _LX__BEGIN_FOR_EACH_FROM(c_tree_top, c_node, inclusive, 0)
+
+#define END_FOR_EACH_FROM(c_node)   \
+    _LX__END_FOR_EACH_FROM(c_node)
+
+
+#endif /* HAS_ETREE_DEFS_H */

lxml/includes/etreepublic.pxd

@@ -0,0 +1,237 @@
+# public Cython/C interface to lxml.etree
+
+from lxml.includes cimport tree
+from lxml.includes.tree cimport const_xmlChar
+
+cdef extern from "lxml-version.h":
+    cdef char* LXML_VERSION_STRING
+
+cdef extern from "etree_defs.h":
+    # test if c_node is considered an Element (i.e. Element, Comment, etc.)
+    cdef bint _isElement(tree.xmlNode* c_node) noexcept nogil
+
+    # return the namespace URI of the node or NULL
+    cdef const_xmlChar* _getNs(tree.xmlNode* node) noexcept nogil
+
+    # pair of macros for tree traversal
+    cdef void BEGIN_FOR_EACH_ELEMENT_FROM(tree.xmlNode* tree_top,
+                                          tree.xmlNode* start_node,
+                                          int start_node_inclusive) noexcept nogil
+    cdef void END_FOR_EACH_ELEMENT_FROM(tree.xmlNode* start_node) noexcept nogil
+
+cdef extern from "etree_api.h":
+
+    # first function to call!
+    cdef int import_lxml__etree() except -1
+
+    ##########################################################################
+    # public ElementTree API classes
+
+    cdef class lxml.etree._Document [ object LxmlDocument ]:
+        cdef tree.xmlDoc* _c_doc
+
+    cdef class lxml.etree._Element [ object LxmlElement ]:
+        cdef _Document _doc
+        cdef tree.xmlNode* _c_node
+
+    cdef class lxml.etree.ElementBase(_Element) [ object LxmlElementBase ]:
+        pass
+
+    cdef class lxml.etree._ElementTree [ object LxmlElementTree ]:
+        cdef _Document _doc
+        cdef _Element  _context_node
+
+    cdef class lxml.etree.ElementClassLookup [ object LxmlElementClassLookup ]:
+        cdef object (*_lookup_function)(object, _Document, tree.xmlNode*)
+
+    cdef class lxml.etree.FallbackElementClassLookup(ElementClassLookup) \
+             [ object LxmlFallbackElementClassLookup ]:
+        cdef ElementClassLookup fallback
+        cdef object (*_fallback_function)(object, _Document, tree.xmlNode*)
+
+    ##########################################################################
+    # creating Element objects
+
+    # create an Element for a C-node in the Document
+    cdef _Element elementFactory(_Document doc, tree.xmlNode* c_node)
+
+    # create an ElementTree for an Element
+    cdef _ElementTree elementTreeFactory(_Element context_node)
+
+    # create an ElementTree subclass for an Element
+    cdef _ElementTree newElementTree(_Element context_node, object subclass)
+
+    # create an ElementTree from an external document
+    cdef _ElementTree adoptExternalDocument(tree.xmlDoc* c_doc, parser, bint is_owned)
+
+    # create a new Element for an existing or new document (doc = None)
+    # builds Python object after setting text, tail, namespaces and attributes
+    cdef _Element makeElement(tag, _Document doc, parser,
+                              text, tail, attrib, nsmap)
+
+    # create a new SubElement for an existing parent
+    # builds Python object after setting text, tail, namespaces and attributes
+    cdef _Element makeSubElement(_Element parent, tag, text, tail,
+                                 attrib, nsmap)
+
+    # deep copy a node to include it in the Document
+    cdef _Element deepcopyNodeToDocument(_Document doc, tree.xmlNode* c_root)
+
+    # set the internal lookup function for Element/Comment/PI classes
+    # use setElementClassLookupFunction(NULL, None) to reset it
+    # note that the lookup function *must always* return an _Element subclass!
+    cdef void setElementClassLookupFunction(
+         object (*function)(object, _Document, tree.xmlNode*), object state)
+
+    # lookup function that always returns the default Element class
+    # note that the first argument is expected to be None!
+    cdef object lookupDefaultElementClass(_1, _Document _2,
+                                          tree.xmlNode* c_node)
+
+    # lookup function for namespace/tag specific Element classes
+    # note that the first argument is expected to be None!
+    cdef object lookupNamespaceElementClass(_1, _Document _2,
+                                            tree.xmlNode* c_node)
+
+    # call the fallback lookup function of a FallbackElementClassLookup
+    cdef object callLookupFallback(FallbackElementClassLookup lookup,
+                                   _Document doc, tree.xmlNode* c_node)
+
+    ##########################################################################
+    # XML attribute access
+
+    # return an attribute value for a C attribute on a C element node
+    cdef unicode attributeValue(tree.xmlNode* c_element,
+                                tree.xmlAttr* c_attrib_node)
+
+    # return the value of the attribute with 'ns' and 'name' (or None)
+    cdef unicode attributeValueFromNsName(tree.xmlNode* c_element,
+                                          const_xmlChar* c_ns, const_xmlChar* c_name)
+
+    # return the value of attribute "{ns}name", or the default value
+    cdef object getAttributeValue(_Element element, key, default)
+
+    # return an iterator over attribute names (1), values (2) or items (3)
+    # attributes must not be removed during iteration!
+    cdef object iterattributes(_Element element, int keysvalues)
+
+    # return the list of all attribute names (1), values (2) or items (3)
+    cdef list collectAttributes(tree.xmlNode* c_element, int keysvalues)
+
+    # set an attribute value on an element
+    # on failure, sets an exception and returns -1
+    cdef int setAttributeValue(_Element element, key, value) except -1
+
+    # delete an attribute
+    # on failure, sets an exception and returns -1
+    cdef int delAttribute(_Element element, key) except -1
+
+    # delete an attribute based on name and namespace URI
+    # returns -1 if the attribute was not found (no exception)
+    cdef int delAttributeFromNsName(tree.xmlNode* c_element,
+                                    const_xmlChar* c_href, const_xmlChar* c_name) noexcept
+
+    ##########################################################################
+    # XML node helper functions
+
+    # check if the element has at least one child
+    cdef bint hasChild(tree.xmlNode* c_node) noexcept nogil
+
+    # find child element number 'index' (supports negative indexes)
+    cdef tree.xmlNode* findChild(tree.xmlNode* c_node,
+                                 Py_ssize_t index) noexcept nogil
+
+    # find child element number 'index' starting at first one
+    cdef tree.xmlNode* findChildForwards(tree.xmlNode* c_node,
+                                         Py_ssize_t index) nogil
+
+    # find child element number 'index' starting at last one
+    cdef tree.xmlNode* findChildBackwards(tree.xmlNode* c_node,
+                                          Py_ssize_t index) nogil
+
+    # return next/previous sibling element of the node
+    cdef tree.xmlNode* nextElement(tree.xmlNode* c_node) nogil
+    cdef tree.xmlNode* previousElement(tree.xmlNode* c_node) nogil
+
+    ##########################################################################
+    # iterators (DEPRECATED API, don't use in new code!)
+
+    cdef class lxml.etree._ElementTagMatcher [ object LxmlElementTagMatcher ]:
+        cdef char* _href
+        cdef char* _name
+
+    # store "{ns}tag" (or None) filter for this matcher or element iterator
+    # ** unless _href *and* _name are set up 'by hand', this function *must*
+    # ** be called when subclassing the iterator below!
+    cdef void initTagMatch(_ElementTagMatcher matcher, tag)
+
+    cdef class lxml.etree._ElementIterator(_ElementTagMatcher) [
+        object LxmlElementIterator ]:
+        cdef _Element _node
+        cdef tree.xmlNode* (*_next_element)(tree.xmlNode*)
+
+    # store the initial node of the iterator if it matches the required tag
+    # or its next matching sibling if not
+    cdef void iteratorStoreNext(_ElementIterator iterator, _Element node)
+
+    ##########################################################################
+    # other helper functions
+
+    # check if a C node matches a tag name and namespace
+    # (NULL allowed for each => always matches)
+    cdef int tagMatches(tree.xmlNode* c_node, const_xmlChar* c_href, const_xmlChar* c_name)
+
+    # convert a UTF-8 char* to a Python unicode string
+    cdef unicode pyunicode(const_xmlChar* s)
+
+    # convert the string to UTF-8 using the normal lxml.etree semantics
+    cdef bytes utf8(object s)
+
+    # split a tag into a (URI, name) tuple, return None as URI for '{}tag'
+    cdef tuple getNsTag(object tag)
+
+    # split a tag into a (URI, name) tuple, return b'' as URI for '{}tag'
+    cdef tuple getNsTagWithEmptyNs(object tag)
+
+    # get the "{ns}tag" string for a C node
+    cdef unicode namespacedName(tree.xmlNode* c_node)
+
+    # get the "{ns}tag" string for a href/tagname pair (c_ns may be NULL)
+    cdef unicode namespacedNameFromNsName(const_xmlChar* c_ns, const_xmlChar* c_tag)
+
+    # check if the node has a text value (which may be '')
+    cdef bint hasText(tree.xmlNode* c_node) nogil
+
+    # check if the node has a tail value (which may be '')
+    cdef bint hasTail(tree.xmlNode* c_node) nogil
+
+    # get the text content of an element (or None)
+    cdef unicode textOf(tree.xmlNode* c_node)
+
+    # get the tail content of an element (or None)
+    cdef unicode tailOf(tree.xmlNode* c_node)
+
+    # set the text value of an element
+    cdef int setNodeText(tree.xmlNode* c_node, text) except -1
+
+    # set the tail text value of an element
+    cdef int setTailText(tree.xmlNode* c_node, text) except -1
+
+    # append an element to the children of a parent element
+    # deprecated: don't use, does not propagate exceptions!
+    # use appendChildToElement() instead
+    cdef void appendChild(_Element parent, _Element child)
+
+    # added in lxml 3.3 as a safe replacement for appendChild()
+    # return -1 for exception, 0 for ok
+    cdef int appendChildToElement(_Element parent, _Element child) except -1
+
+    # recursively lookup a namespace in element or ancestors, or create it
+    cdef tree.xmlNs* findOrBuildNodeNsPrefix(
+        _Document doc, tree.xmlNode* c_node, const_xmlChar* href, const_xmlChar* prefix)
+
+    # find the Document of an Element, ElementTree or Document (itself!)
+    cdef _Document documentOrRaise(object input)
+
+    # find the root Element of an Element (itself!), ElementTree or Document
+    cdef _Element rootNodeOrRaise(object input)

lxml/includes/extlibs/libcharset.h

@@ -0,0 +1,45 @@
+/* Copyright (C) 2003 Free Software Foundation, Inc.
+   This file is part of the GNU CHARSET Library.
+
+   The GNU CHARSET Library is free software; you can redistribute it and/or
+   modify it under the terms of the GNU Lesser General Public License as
+   published by the Free Software Foundation; either version 2 of the
+   License, or (at your option) any later version.
+
+   The GNU CHARSET Library is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public License
+   along with the GNU CHARSET Library; see the file COPYING.LIB.  If not,
+   see <https://www.gnu.org/licenses/>.  */
+
+#ifndef _LIBCHARSET_H
+#define _LIBCHARSET_H
+
+#include <localcharset.h>
+
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+/* Support for relocatable packages.  */
+
+/* Sets the original and the current installation prefix of the package.
+   Relocation simply replaces a pathname starting with the original prefix
+   by the corresponding pathname with the current prefix instead.  Both
+   prefixes should be directory names without trailing slash (i.e. use ""
+   instead of "/").  */
+extern void libcharset_set_relocation_prefix (const char *orig_prefix,
+                                              const char *curr_prefix);
+
+
+#ifdef __cplusplus
+}
+#endif
+
+
+#endif /* _LIBCHARSET_H */