lxml-3.5.0/0000775000175000017500000000000012621313457013263 5ustar stefanstefan00000000000000lxml-3.5.0/setupinfo.py0000664000175000017500000003660512576735275015702 0ustar stefanstefan00000000000000import sys, os, os.path from distutils.core import Extension from distutils.errors import CompileError, DistutilsOptionError from distutils.command.build_ext import build_ext as _build_ext from versioninfo import get_base_dir try: import Cython.Compiler.Version CYTHON_INSTALLED = True except ImportError: CYTHON_INSTALLED = False EXT_MODULES = ["lxml.etree", "lxml.objectify"] PACKAGE_PATH = "src%slxml%s" % (os.path.sep, os.path.sep) INCLUDE_PACKAGE_PATH = PACKAGE_PATH + 'includes' if sys.version_info[0] >= 3: _system_encoding = sys.getdefaultencoding() if _system_encoding is None: _system_encoding = "iso-8859-1" # :-) def decode_input(data): if isinstance(data, str): return data return data.decode(_system_encoding) else: def decode_input(data): return data def env_var(name): value = os.getenv(name) if value: value = decode_input(value) if sys.platform == 'win32' and ';' in value: return value.split(';') else: return value.split() else: return [] def _prefer_reldirs(base_dir, dirs): return [ os.path.relpath(path) if path.startswith(base_dir) else path for path in dirs ] def ext_modules(static_include_dirs, static_library_dirs, static_cflags, static_binaries): global XML2_CONFIG, XSLT_CONFIG if OPTION_BUILD_LIBXML2XSLT: from buildlibxml import build_libxml2xslt, get_prebuilt_libxml2xslt if sys.platform.startswith('win'): get_prebuilt_libxml2xslt( OPTION_DOWNLOAD_DIR, static_include_dirs, static_library_dirs) else: XML2_CONFIG, XSLT_CONFIG = build_libxml2xslt( OPTION_DOWNLOAD_DIR, 'build/tmp', static_include_dirs, static_library_dirs, static_cflags, static_binaries, libiconv_version=OPTION_LIBICONV_VERSION, libxml2_version=OPTION_LIBXML2_VERSION, libxslt_version=OPTION_LIBXSLT_VERSION, multicore=OPTION_MULTICORE) modules = EXT_MODULES if OPTION_WITHOUT_OBJECTIFY: modules = [entry for entry in modules if 'objectify' not in entry] c_files_exist = [os.path.exists('%s%s.c' % (PACKAGE_PATH, module)) for module in modules] source_extension = ".pyx" if CYTHON_INSTALLED and (OPTION_WITH_CYTHON or not all(c_files_exist)): print("Building with Cython %s." % Cython.Compiler.Version.version) # generate module cleanup code from Cython.Compiler import Options Options.generate_cleanup_code = 3 Options.clear_to_none = False elif not OPTION_WITHOUT_CYTHON and not all(c_files_exist): for exists, module in zip(c_files_exist, modules): if not exists: raise RuntimeError( "ERROR: Trying to build without Cython, but pre-generated '%s%s.c' " "is not available (pass --without-cython to ignore this error)." % ( PACKAGE_PATH, module)) else: if not all(c_files_exist): for exists, module in zip(c_files_exist, modules): if not exists: print("WARNING: Trying to build without Cython, but pre-generated " "'%s%s.c' is not available." % (PACKAGE_PATH, module)) source_extension = ".c" print("Building without Cython.") lib_versions = get_library_versions() versions_ok = True if lib_versions[0]: print("Using build configuration of libxml2 %s and libxslt %s" % lib_versions) versions_ok = check_min_version(lib_versions[0], (2, 7, 0), 'libxml2') else: print("Using build configuration of libxslt %s" % lib_versions[1]) versions_ok |= check_min_version(lib_versions[1], (1, 1, 23), 'libxslt') if not versions_ok: raise RuntimeError("Dependency missing") base_dir = get_base_dir() _include_dirs = _prefer_reldirs( base_dir, include_dirs(static_include_dirs) + [INCLUDE_PACKAGE_PATH]) _library_dirs = _prefer_reldirs(base_dir, library_dirs(static_library_dirs)) _cflags = cflags(static_cflags) _define_macros = define_macros() _libraries = libraries() if _library_dirs: message = "Building against libxml2/libxslt in " if len(_library_dirs) > 1: print(message + "one of the following directories:") for dir in _library_dirs: print(" " + dir) else: print(message + "the following directory: " + _library_dirs[0]) if OPTION_AUTO_RPATH: runtime_library_dirs = _library_dirs else: runtime_library_dirs = [] if CYTHON_INSTALLED and OPTION_SHOW_WARNINGS: from Cython.Compiler import Errors Errors.LEVEL = 0 cythonize_options = {} if OPTION_WITH_COVERAGE: cythonize_options['compiler_directives'] = {'linetrace': True} result = [] for module in modules: main_module_source = PACKAGE_PATH + module + source_extension result.append( Extension( module, sources = [main_module_source], depends = find_dependencies(module), extra_compile_args = _cflags, extra_objects = static_binaries, define_macros = _define_macros, include_dirs = _include_dirs, library_dirs = _library_dirs, runtime_library_dirs = runtime_library_dirs, libraries = _libraries, )) if CYTHON_INSTALLED and OPTION_WITH_CYTHON_GDB: for ext in result: ext.cython_gdb = True if CYTHON_INSTALLED and source_extension == '.pyx': # build .c files right now and convert Extension() objects from Cython.Build import cythonize result = cythonize(result, **cythonize_options) return result def find_dependencies(module): if not CYTHON_INSTALLED: return [] base_dir = get_base_dir() package_dir = os.path.join(base_dir, PACKAGE_PATH) includes_dir = os.path.join(base_dir, INCLUDE_PACKAGE_PATH) pxd_files = [ os.path.join(INCLUDE_PACKAGE_PATH, filename) for filename in os.listdir(includes_dir) if filename.endswith('.pxd') ] if 'etree' in module: pxi_files = [ os.path.join(PACKAGE_PATH, filename) for filename in os.listdir(package_dir) if filename.endswith('.pxi') and 'objectpath' not in filename ] pxd_files = [ filename for filename in pxd_files if 'etreepublic' not in filename ] elif 'objectify' in module: pxi_files = [os.path.join(PACKAGE_PATH, 'objectpath.pxi')] else: pxi_files = [] return pxd_files + pxi_files def extra_setup_args(): class CheckLibxml2BuildExt(_build_ext): """Subclass to check whether libxml2 is really available if the build fails""" def run(self): try: _build_ext.run(self) # old-style class in Py2 except CompileError as e: print('Compile failed: %s' % e) if not seems_to_have_libxml2(): print_libxml_error() raise result = {'cmdclass': {'build_ext': CheckLibxml2BuildExt}} return result def seems_to_have_libxml2(): from distutils import ccompiler compiler = ccompiler.new_compiler() return compiler.has_function( 'xmlXPathInit', include_dirs=include_dirs([]) + ['/usr/include/libxml2'], includes=['libxml/xpath.h'], library_dirs=library_dirs([]), libraries=['xml2']) def print_libxml_error(): print('*********************************************************************************') print('Could not find function xmlCheckVersion in library libxml2. Is libxml2 installed?') if sys.platform in ('darwin',): print('Perhaps try: xcode-select --install') print('*********************************************************************************') def libraries(): if sys.platform in ('win32',): libs = ['libxslt', 'libexslt', 'libxml2', 'iconv'] if OPTION_STATIC: libs = ['%s_a' % lib for lib in libs] libs.extend(['zlib', 'WS2_32']) elif OPTION_STATIC: libs = ['z', 'm'] else: libs = ['xslt', 'exslt', 'xml2', 'z', 'm'] return libs def library_dirs(static_library_dirs): if OPTION_STATIC: if not static_library_dirs: static_library_dirs = env_var('LIBRARY') assert static_library_dirs, "Static build not configured, see doc/build.txt" return static_library_dirs # filter them from xslt-config --libs result = [] possible_library_dirs = flags('libs') for possible_library_dir in possible_library_dirs: if possible_library_dir.startswith('-L'): result.append(possible_library_dir[2:]) return result def include_dirs(static_include_dirs): if OPTION_STATIC: if not static_include_dirs: static_include_dirs = env_var('INCLUDE') return static_include_dirs # filter them from xslt-config --cflags result = [] possible_include_dirs = flags('cflags') for possible_include_dir in possible_include_dirs: if possible_include_dir.startswith('-I'): result.append(possible_include_dir[2:]) return result def cflags(static_cflags): result = [] if not OPTION_SHOW_WARNINGS: result.append('-w') if OPTION_DEBUG_GCC: result.append('-g2') if OPTION_STATIC: if not static_cflags: static_cflags = env_var('CFLAGS') result.extend(static_cflags) else: # anything from xslt-config --cflags that doesn't start with -I possible_cflags = flags('cflags') for possible_cflag in possible_cflags: if not possible_cflag.startswith('-I'): result.append(possible_cflag) if sys.platform in ('darwin',): for opt in result: if 'flat_namespace' in opt: break else: result.append('-flat_namespace') return result def define_macros(): macros = [] if OPTION_WITHOUT_ASSERT: macros.append(('PYREX_WITHOUT_ASSERTIONS', None)) if OPTION_WITHOUT_THREADING: macros.append(('WITHOUT_THREADING', None)) if OPTION_WITH_REFNANNY: macros.append(('CYTHON_REFNANNY', None)) if OPTION_WITH_UNICODE_STRINGS: macros.append(('LXML_UNICODE_STRINGS', '1')) if OPTION_WITH_COVERAGE: macros.append(('CYTHON_TRACE_NOGIL', '1')) return macros _ERROR_PRINTED = False def run_command(cmd, *args): if not cmd: return '' if args: cmd = ' '.join((cmd,) + args) try: import subprocess except ImportError: # Python 2.3 sf, rf, ef = os.popen3(cmd) sf.close() errors = ef.read() stdout_data = rf.read() else: # Python 2.4+ p = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE) stdout_data, errors = p.communicate() global _ERROR_PRINTED if errors and not _ERROR_PRINTED: _ERROR_PRINTED = True print("ERROR: %s" % errors) print("** make sure the development packages of libxml2 and libxslt are installed **\n") return decode_input(stdout_data).strip() def check_min_version(version, min_version, error_name): if not version: # this is ok for targets like sdist etc. return True version = tuple(map(int, version.split('.')[:3])) min_version = tuple(min_version) if version < min_version: print("Minimum required version of %s is %s, found %s" % ( error_name, '.'.join(map(str, version)), '.'.join(map(str, min_version)))) return False return True def get_library_versions(): xml2_version = run_command(find_xml2_config(), "--version") xslt_version = run_command(find_xslt_config(), "--version") return xml2_version, xslt_version def flags(option): xml2_flags = run_command(find_xml2_config(), "--%s" % option) xslt_flags = run_command(find_xslt_config(), "--%s" % option) flag_list = xml2_flags.split() for flag in xslt_flags.split(): if flag not in flag_list: flag_list.append(flag) return flag_list XSLT_CONFIG = None XML2_CONFIG = None def find_xml2_config(): global XML2_CONFIG if XML2_CONFIG: return XML2_CONFIG option = '--with-xml2-config=' for arg in sys.argv: if arg.startswith(option): sys.argv.remove(arg) XML2_CONFIG = arg[len(option):] return XML2_CONFIG else: # default: do nothing, rely only on xslt-config XML2_CONFIG = os.getenv('XML2_CONFIG', '') return XML2_CONFIG def find_xslt_config(): global XSLT_CONFIG if XSLT_CONFIG: return XSLT_CONFIG option = '--with-xslt-config=' for arg in sys.argv: if arg.startswith(option): sys.argv.remove(arg) XSLT_CONFIG = arg[len(option):] return XSLT_CONFIG else: XSLT_CONFIG = os.getenv('XSLT_CONFIG', 'xslt-config') return XSLT_CONFIG ## Option handling: def has_option(name): try: sys.argv.remove('--%s' % name) return True except ValueError: pass # allow passing all cmd line options also as environment variables env_val = os.getenv(name.upper().replace('-', '_'), 'false').lower() if env_val == "true": return True return False def option_value(name): for index, option in enumerate(sys.argv): if option == '--' + name: if index+1 >= len(sys.argv): raise DistutilsOptionError( 'The option %s requires a value' % option) value = sys.argv[index+1] sys.argv[index:index+2] = [] return value if option.startswith('--' + name + '='): value = option[len(name)+3:] sys.argv[index:index+1] = [] return value env_val = os.getenv(name.upper().replace('-', '_')) return env_val staticbuild = bool(os.environ.get('STATICBUILD', '')) # pick up any commandline options and/or env variables OPTION_WITHOUT_OBJECTIFY = has_option('without-objectify') OPTION_WITH_UNICODE_STRINGS = has_option('with-unicode-strings') OPTION_WITHOUT_ASSERT = has_option('without-assert') OPTION_WITHOUT_THREADING = has_option('without-threading') OPTION_WITHOUT_CYTHON = has_option('without-cython') OPTION_WITH_CYTHON = has_option('with-cython') OPTION_WITH_CYTHON_GDB = has_option('cython-gdb') OPTION_WITH_REFNANNY = has_option('with-refnanny') OPTION_WITH_COVERAGE = has_option('with-coverage') if OPTION_WITHOUT_CYTHON: CYTHON_INSTALLED = False OPTION_STATIC = staticbuild or has_option('static') OPTION_DEBUG_GCC = has_option('debug-gcc') OPTION_SHOW_WARNINGS = has_option('warnings') OPTION_AUTO_RPATH = has_option('auto-rpath') OPTION_BUILD_LIBXML2XSLT = staticbuild or has_option('static-deps') if OPTION_BUILD_LIBXML2XSLT: OPTION_STATIC = True OPTION_LIBXML2_VERSION = option_value('libxml2-version') OPTION_LIBXSLT_VERSION = option_value('libxslt-version') OPTION_LIBICONV_VERSION = option_value('libiconv-version') OPTION_MULTICORE = option_value('multicore') OPTION_DOWNLOAD_DIR = option_value('download-dir') if OPTION_DOWNLOAD_DIR is None: OPTION_DOWNLOAD_DIR = 'libs' lxml-3.5.0/MANIFEST.in0000664000175000017500000000162112576735275015040 0ustar stefanstefan00000000000000exclude *.py include setup.py ez_setup.py setupinfo.py versioninfo.py buildlibxml.py include test.py include update-error-constants.py include MANIFEST.in Makefile version.txt requirements.txt include CHANGES.txt CREDITS.txt INSTALL.txt LICENSES.txt README.rst TODO.txt recursive-include src *.pyx *.pxd *.pxi *.py recursive-include src/lxml lxml.etree.c lxml.objectify.c recursive-include src/lxml lxml.etree.h lxml.etree_api.h etree_defs.h lxml_endian.h recursive-include src/lxml/isoschematron *.rng *.xsl *.txt recursive-include src/lxml/tests *.rng *.xslt *.xml *.dtd *.xsd *.sch *.html recursive-include src/lxml/html/tests *.data *.txt recursive-include samples *.xml recursive-include benchmark *.py recursive-include doc *.txt *.html *.css *.xml *.mgp pubkey.asc tagpython*.png Makefile recursive-include doc/s5/ui *.gif *.htc *.png *.js recursive-include doc/s5/ep2008 *.py *.png *.rng include doc/*.py lxml-3.5.0/update-error-constants.py0000664000175000017500000001250412034342037020254 0ustar stefanstefan00000000000000#!/usr/bin/env python import sys, os, os.path, re, codecs BUILD_SOURCE_FILE = os.path.join("src", "lxml", "xmlerror.pxi") BUILD_DEF_FILE = os.path.join("src", "lxml", "includes", "xmlerror.pxd") if len(sys.argv) < 2 or sys.argv[1].lower() in ('-h', '--help'): print("This script generates the constants in file %s" % BUILD_SOURCE_FILE) print("Call as") print(sys.argv[0], "/path/to/libxml2-doc-dir") sys.exit(len(sys.argv) > 1) HTML_DIR = os.path.join(sys.argv[1], 'html') os.stat(HTML_DIR) # raise an error if we can't find it sys.path.insert(0, 'src') from lxml import etree # map enum name to Python variable name and alignment for constant name ENUM_MAP = { 'xmlErrorLevel' : ('__ERROR_LEVELS', 'XML_ERR_'), 'xmlErrorDomain' : ('__ERROR_DOMAINS', 'XML_FROM_'), 'xmlParserErrors' : ('__PARSER_ERROR_TYPES', 'XML_'), # 'xmlXPathError' : ('__XPATH_ERROR_TYPES', ''), # 'xmlSchemaValidError' : ('__XMLSCHEMA_ERROR_TYPES', 'XML_'), 'xmlRelaxNGValidErr' : ('__RELAXNG_ERROR_TYPES', 'XML_'), } ENUM_ORDER = ( 'xmlErrorLevel', 'xmlErrorDomain', 'xmlParserErrors', # 'xmlXPathError', # 'xmlSchemaValidError', 'xmlRelaxNGValidErr') COMMENT = """ # This section is generated by the script '%s'. """ % os.path.basename(sys.argv[0]) def split(lines): lines = iter(lines) pre = [] for line in lines: pre.append(line) if line.startswith('#') and "BEGIN: GENERATED CONSTANTS" in line: break pre.append('') for line in lines: if line.startswith('#') and "END: GENERATED CONSTANTS" in line: break post = ['', line] post.extend(lines) post.append('') return pre, post def regenerate_file(filename, result): # read .pxi source file f = codecs.open(filename, 'r', encoding="utf-8") pre, post = split(f) f.close() # write .pxi source file f = codecs.open(filename, 'w', encoding="utf-8") f.write(''.join(pre)) f.write(COMMENT) f.write('\n'.join(result)) f.write(''.join(post)) f.close() collect_text = etree.XPath("string()") find_enums = etree.XPath( "//html:pre[@class = 'programlisting' and contains(text(), 'Enum')]", namespaces = {'html' : 'http://www.w3.org/1999/xhtml'}) def parse_enums(html_dir, html_filename, enum_dict): PARSE_ENUM_NAME = re.compile('\s*enum\s+(\w+)\s*{', re.I).match PARSE_ENUM_VALUE = re.compile('\s*=\s+([0-9]+)\s*(?::\s*(.*))?').match tree = etree.parse(os.path.join(html_dir, html_filename)) enums = find_enums(tree) for enum in enums: enum_name = PARSE_ENUM_NAME(collect_text(enum)) if not enum_name: continue enum_name = enum_name.group(1) if enum_name not in ENUM_MAP: continue print("Found enum", enum_name) entries = [] for child in enum: name = child.text match = PARSE_ENUM_VALUE(child.tail) if not match: print("Ignoring enum %s (failed to parse field '%s')" % ( enum_name, name)) break value, descr = match.groups() entries.append((name, int(value), descr)) else: enum_dict[enum_name] = entries return enum_dict enum_dict = {} parse_enums(HTML_DIR, 'libxml-xmlerror.html', enum_dict) #parse_enums(HTML_DIR, 'libxml-xpath.html', enum_dict) #parse_enums(HTML_DIR, 'libxml-xmlschemas.html', enum_dict) parse_enums(HTML_DIR, 'libxml-relaxng.html', enum_dict) # regenerate source files pxi_result = [] append_pxi = pxi_result.append pxd_result = [] append_pxd = pxd_result.append append_pxd('cdef extern from "libxml/xmlerror.h":') append_pxi('''\ # Constants are stored in tuples of strings, for which Cython generates very # efficient setup code. To parse them, iterate over the tuples and parse each # line in each string independently. Tuples of strings (instead of a plain # string) are required as some C-compilers of a certain well-known OS vendor # cannot handle strings that are a few thousand bytes in length. ''') ctypedef_indent = ' '*4 constant_indent = ctypedef_indent*2 for enum_name in ENUM_ORDER: constants = enum_dict[enum_name] pxi_name, prefix = ENUM_MAP[enum_name] append_pxd(ctypedef_indent + 'ctypedef enum %s:' % enum_name) append_pxi('cdef object %s = (u"""\\' % pxi_name) prefix_len = len(prefix) length = 2 # each string ends with '\n\0' for name, val, descr in constants: if descr and descr != str(val): line = '%-50s = %7d # %s' % (name, val, descr) else: line = '%-50s = %7d' % (name, val) append_pxd(constant_indent + line) if name[:prefix_len] == prefix and len(name) > prefix_len: name = name[prefix_len:] line = '%s=%d' % (name, val) if length + len(line) >= 2040: # max string length in MSVC is 2048 append_pxi('""",') append_pxi('u"""\\') length = 2 # each string ends with '\n\0' append_pxi(line) length += len(line) + 2 # + '\n\0' append_pxd('') append_pxi('""",)') append_pxi('') # write source files print("Updating file %s" % BUILD_SOURCE_FILE) regenerate_file(BUILD_SOURCE_FILE, pxi_result) print("Updating file %s" % BUILD_DEF_FILE) regenerate_file(BUILD_DEF_FILE, pxd_result) print("Done") lxml-3.5.0/requirements.txt0000664000175000017500000000001512576735275016562 0ustar stefanstefan00000000000000Cython>=0.20 lxml-3.5.0/TODO.txt0000664000175000017500000000266312402330047014567 0ustar stefanstefan00000000000000=============== ToDo's for lxml =============== lxml ==== In general ---------- * more testing on multi-threading * better exception messages for XPath and schemas based on error log, e.g. missing namespace mappings in XPath * when building statically, compile everything into one shared library instead of one for lxml.etree and one for lxml.objectify to prevent the redundant static linking of the library dependencies. * more testing on input/output of encoded filenames, including custom resolvers, relative XSLT imports, ... * always use '' as URL when tree was parsed from string? (can libxml2 handle this?) * follow PEP 8 in API naming (avoidCamelCase in_favour_of_underscores) * use per-call or per-thread error logs in XSLT/XPath/etc. to keep the messages separate, especially in exceptions * add 'nsmap' parameter to cleanup_namespaces() * fix tail text handling in addnext()/addprevious() * make Element nsmap editable to allow defining new namespaces (LP#555602) Entities -------- * clean support for entities (is the Entity element class enough?) Objectify --------- * emulate setting special __attributes__ on ObjectifiedElement's as Python attributes, not XML children Incremental parsing ------------------- * create all iterparse events only on start events and store the end events in the stack * rewrite SAX event creation in a more C-ish way to avoid having to acquire the GIL on each event lxml-3.5.0/CHANGES.txt0000664000175000017500000030260312621312540015070 0ustar stefanstefan00000000000000============== lxml changelog ============== 3.5.0 (2015-11-13) ================== Bugs fixed ---------- * Unicode string results failed XPath queries in PyPy. * LP#1497051: HTML target parser failed to terminate on exceptions and continued parsing instead. * Deprecated API usage in doctestcompare. 3.5.0b1 (2015-09-18) ==================== Features added -------------- * ``cleanup_namespaces()`` accepts a new argument ``keep_ns_prefixes`` that does not remove definitions of the provided prefix-namespace mapping from the tree. * ``cleanup_namespaces()`` accepts a new argument ``top_nsmap`` that moves definitions of the provided prefix-namespace mapping to the top of the tree. * LP#1490451: ``Element`` objects gained a ``cssselect()`` method as known from ``lxml.html``. Patch by Simon Sapin. * API functions and methods behave and look more like Python functions, which allows introspection on them etc. One side effect to be aware of is that the functions now bind as methods when assigned to a class variable. A quick fix is to wrap them in ``staticmethod()`` (as for normal Python functions). * ISO-Schematron support gained an option ``error_finder`` that allows passing a filter function for picking validation errors from reports. * LP#1243600: Elements in ``lxml.html`` gained a ``classes`` property that provides a set-like interface to the ``class`` attribute. Original patch by masklinn. * LP#1341964: The soupparser now handles DOCTYPE declarations, comments and processing instructions outside of the root element. Patch by Olli Pottonen. * LP#1421512: The ``docinfo`` of a tree was made editable to allow setting and removing the public ID and system ID of the DOCTYPE. Patch by Olli Pottonen. * LP#1442427: More work-arounds for quirks and bugs in pypy and pypy3. * ``lxml.html.soupparser`` now uses BeautifulSoup version 4 instead of version 3 if available. Bugs fixed ---------- * Memory errors that occur during tree adaptations (e.g. moving subtrees to foreign documents) could leave the tree in a crash prone state. * Calling ``process_children()`` in an XSLT extension element without an ``output_parent`` argument failed with a ``TypeError``. Fix by Jens Tröger. * GH#162: Image data in HTML ``data`` URLs is considered safe and no longer removed by ``lxml.html.clean`` JavaScript cleaner. * GH#166: Static build could link libraries in wrong order. * GH#172: Rely a bit more on libxml2 for encoding detection rather than rolling our own in some cases. Patch by Olli Pottonen. * GH#159: Validity checks for names and string content were tightened to detect the use of illegal characters early. Patch by Olli Pottonen. * LP#1421921: Comments/PIs before the DOCTYPE declaration were not serialised. Patch by Olli Pottonen. * LP#659367: Some HTML DOCTYPE declarations were not serialised. Patch by Olli Pottonen. * LP#1238503: lxml.doctestcompare is now consistent with stdlib's doctest in how it uses ``+`` and ``-`` to refer to unexpected and missing output. * Empty prefixes are explicitly rejected when a namespace mapping is used with ElementPath to avoid hiding bugs in user code. * Several problems with PyPy were fixed by switching to Cython 0.23. 3.4.4 (2015-04-25) ================== Bugs fixed ---------- * An ElementTree compatibility test added in lxml 3.4.3 that failed in Python 3.4+ was removed again. 3.4.3 (2015-04-15) ================== Bugs fixed ---------- * Expression cache in ElementPath was ignored. Fix by Changaco. * LP#1426868: Passing a default namespace and a prefixed namespace mapping as nsmap into ``xmlfile.element()`` raised a ``TypeError``. * LP#1421927: DOCTYPE system URLs were incorrectly quoted when containing double quotes. Patch by Olli Pottonen. * LP#1419354: meta-redirect URLs were incorrectly processed by ``iterlinks()`` if preceded by whitespace. 3.4.2 (2015-02-07) ================== Bugs fixed ---------- * LP#1415907: Crash when creating an XMLSchema from a non-root element of an XML document. * LP#1369362: HTML cleaning failed when hitting processing instructions with pseudo-attributes. * ``CDATA()`` wrapped content was rejected for tail text. * CDATA sections were not serialised as tail text of the top-level element. 3.4.1 (2014-11-20) ================== Features added -------------- * New ``htmlfile`` HTML generator to accompany the incremental ``xmlfile`` serialisation API. Patch by Burak Arslan. Bugs fixed ---------- * ``lxml.sax.ElementTreeContentHandler`` did not initialise its superclass. 3.4.0 (2014-09-10) ================== Features added -------------- * ``xmlfile(buffered=False)`` disables output buffering and flushes the content after each API operation (starting/ending element blocks or writes). A new method ``xf.flush()`` can alternatively be used to explicitly flush the output. * ``lxml.html.document_fromstring`` has a new option ``ensure_head_body=True`` which will add an empty head and/or body element to the result document if missing. * ``lxml.html.iterlinks`` now returns links inside meta refresh tags. * New ``XMLParser`` option ``collect_ids=False`` to disable ID hash table creation. This can substantially speed up parsing of documents with many different IDs that are not used. * The parser uses per-document hash tables for XML IDs. This reduces the load of the global parser dict and speeds up parsing for documents with many different IDs. * ``ElementTree.getelementpath(element)`` returns a structural ElementPath expression for the given element, which can be used for lookups later. * ``xmlfile()`` accepts a new argument ``close=True`` to close file(-like) objects after writing to them. Before, ``xmlfile()`` only closed the file if it had opened it internally. * Allow "bytearray" type for ASCII text input. Bugs fixed ---------- Other changes ------------- * LP#400588: decoding errors have become hard errors even in recovery mode. Previously, they could lead to an internal tree representation in a mixed encoding state, which lead to very late errors or even silently incorrect behaviour during tree traversal or serialisation. * Requires Python 2.6, 2.7, 3.2 or later. No longer supports Python 2.4, 2.5 and 3.1, use lxml 3.3.x for those. * Requires libxml2 2.7.0 or later and libxslt 1.1.23 or later, use lxml 3.3.x with older versions. 3.3.6 (2014-08-28) ================== Bugs fixed ---------- * Prevent tree cycle creation when adding Elements as siblings. * LP#1361948: crash when deallocating Element siblings without parent. * LP#1354652: crash when traversing internally loaded documents in XSLT extension functions. 3.3.5 (2014-04-18) ================== Bugs fixed ---------- * HTML cleaning could fail to strip javascript links that mix control characters into the link scheme. 3.3.4 (2014-04-03) ================== Features added -------------- * Source line numbers above 65535 are available on Elements when using libxml2 2.9 or later. Bugs fixed ---------- * ``lxml.html.fragment_fromstring()`` failed for bytes input in Py3. Other changes ------------- 3.3.3 (2014-03-04) ================== Bugs fixed ---------- * LP#1287118: Crash when using Element subtypes with ``__slots__``. Other changes ------------- * The internal classes ``_LogEntry`` and ``_Attrib`` can no longer be subclassed from Python code. 3.3.2 (2014-02-26) ================== Bugs fixed ---------- * The properties ``resolvers`` and ``version``, as well as the methods ``set_element_class_lookup()`` and ``makeelement()``, were lost from ``iterparse`` objects in 3.3.0. * LP#1222132: instances of ``XMLSchema``, ``Schematron`` and ``RelaxNG`` did not clear their local ``error_log`` before running a validation. * LP#1238500: lxml.doctestcompare mixed up "expected" and "actual" in attribute values. * Some file I/O tests were failing in MS-Windows due to non-portable temp file usage. Initial patch by Gabi Davar. * LP#910014: duplicate IDs in a document were not reported by DTD validation. * LP#1185332: ``tostring(method="html")`` did not use HTML serialisation semantics for trailing tail text. Initial patch by Sylvain Viollon. * LP#1281139: ``.attrib`` value of Comments lost its mutation methods in 3.3.0. Even though it is empty and immutable, it should still provide the same interface as that returned for Elements. 3.3.1 (2014-02-12) ================== Features added -------------- Bugs fixed ---------- * LP#1014290: HTML documents parsed with ``parser.feed()`` failed to find elements during tag iteration. * LP#1273709: Building in PyPy failed due to missing support for ``PyUnicode_Compare()`` and ``PyByteArray_*()`` in PyPy's C-API. * LP#1274413: Compilation in MSVC failed due to missing "stdint.h" standard header file. * LP#1274118: iterparse() failed to parse BOM prefixed files. Other changes ------------- 3.3.0 (2014-01-26) ================== Features added -------------- Bugs fixed ---------- * The heuristic that distinguishes file paths from URLs was tightened to produce less false negatives. Other changes ------------- 3.3.0beta5 (2014-01-18) ======================= Features added -------------- * The PEP 393 unicode parsing support gained a fallback for wchar strings which might still be somewhat common on Windows systems. Bugs fixed ---------- * Several error handling problems were fixed throughout the code base that could previously lead to exceptions being silently swallowed or not properly reported. * The C-API function ``appendChild()`` is now deprecated as it does not propagate exceptions (its return type is ``void``). The new function ``appendChildToElement()`` was added as a safe replacement. * Passing a string into ``fromstringlist()`` raises an exception instead of parsing the string character by character. Other changes ------------- * Document cleanup code was simplified using the new GC features in Cython 0.20. 3.3.0beta4 (2014-01-12) ======================= Features added -------------- Bugs fixed ---------- * The (empty) value returned by the ``attrib`` property of Entity and Comment objects was mutable. * Element class lookup wasn't available for the new pull parsers or when using a custom parser target. * Setting Element attributes on instantiation with both the ``attrib`` argument and keyword arguments could modify the mapping passed as ``attrib``. * LP#1266171: DTDs instantiated from internal/external subsets (i.e. through the docinfo property) lost their attribute declarations. Other changes ------------- * Built with Cython 0.20pre (gitrev 012ae82eb) to prepare support for Python 3.4. 3.3.0beta3 (2014-01-02) ======================= Features added -------------- * Unicode string parsing was optimised for Python 3.3 (PEP 393). Bugs fixed ---------- * HTML parsing of Unicode strings could misdecode the input on some platforms. * Crash in xmlfile() when closing open elements out of order in an error case. Other changes ------------- 3.3.0beta2 (2013-12-20) ======================= Features added -------------- * ``iterparse()`` supports the ``recover`` option. Bugs fixed ---------- * Crash in ``iterparse()`` for HTML parsing. * Crash in target parsing with attributes. Other changes ------------- * The safety check in the read-only tree implementation (e.g. used by ``PythonElementClassLookup``) raises a more appropriate ``ReferenceError`` for illegal access after tree disposal instead of an ``AssertionError``. This should only impact test code that specifically checks the original behaviour. 3.3.0beta1 (2013-12-12) ======================= Features added -------------- * New option ``handle_failures`` in ``make_links_absolute()`` and ``resolve_base_href()`` (lxml.html) that enables ignoring or discarding links that fail to parse as URLs. * New parser classes ``XMLPullParser`` and ``HTMLPullParser`` for incremental parsing, as implemented for ElementTree in Python 3.4. * ``iterparse()`` enables recovery mode by default for HTML parsing (``html=True``). Bugs fixed ---------- * LP#1255132: crash when trying to run validation over non-Element (e.g. comment or PI). * Error messages in the log and in exception messages that originated from libxml2 could accidentally be picked up from preceding warnings instead of the actual error. * The ``ElementMaker`` in lxml.objectify did not accept a dict as argument for adding attributes to the element it's building. This works as in lxml.builder now. * LP#1228881: ``repr(XSLTAccessControl)`` failed in Python 3. * Raise ``ValueError`` when trying to append an Element to itself or to one of its own descendants, instead of running into an infinite loop. * LP#1206077: htmldiff discarded whitespace from the output. * Compressed plain-text serialisation to file-like objects was broken. * lxml.html.formfill: Fix textarea form filling. The textarea used to be cleared before the new content was set, which removed the name attribute. Other changes ------------- * Some basic API classes use freelists internally for faster instantiation. This can speed up some ``iterparse()`` scenarios, for example. * ``iterparse()`` was rewritten to use the new ``*PullParser`` classes internally instead of being a parser itself. 3.2.5 (2014-01-02) ================== Features added -------------- Bugs fixed ---------- * Crash in xmlfile() when closing open elements out of order in an error case. * Crash in target parsing with attributes. * LP#1255132: crash when trying to run validation over non-Element (e.g. comment or PI). Other changes ------------- 3.2.4 (2013-11-07) ================== Features added -------------- Bugs fixed ---------- * Memory leak when creating an XPath evaluator in a thread. * LP#1228881: ``repr(XSLTAccessControl)`` failed in Python 3. * Raise ``ValueError`` when trying to append an Element to itself or to one of its own descendants. * LP#1206077: htmldiff discarded whitespace from the output. * Compressed plain-text serialisation to file-like objects was broken. Other changes ------------- 3.2.3 (2013-07-28) ================== Bugs fixed ---------- * Fix support for Python 2.4 which was lost in 3.2.2. 3.2.2 (2013-07-28) ================== Features added -------------- Bugs fixed ---------- * LP#1185701: spurious XMLSyntaxError after finishing iterparse(). * Crash in lxml.objectify during xsi annotation. Other changes ------------- * Return values of user provided element class lookup methods are now validated against the type of the XML node they represent to prevent API class mismatches. 3.2.1 (2013-05-11) ================== Features added -------------- * The methods ``apply_templates()`` and ``process_children()`` of XSLT extension elements have gained two new boolean options ``elements_only`` and ``remove_blank_text`` that discard either all strings or whitespace-only strings from the result list. Bugs fixed ---------- * When moving Elements to another tree, the namespace cleanup mechanism no longer drops namespace prefixes from attributes for which it finds a default namespace declaration, to prevent them from appearing as unnamespaced attributes after serialisation. * Returning non-type objects from a custom class lookup method could lead to a crash. * Instantiating and using subtypes of Comments and ProcessingInstructions crashed. Other changes ------------- 3.2.0 (2013-04-28) ================== Features added -------------- Bugs fixed ---------- * LP#690319: Leading whitespace could change the behaviour of the string parsing functions in ``lxml.html``. * LP#599318: The string parsing functions in ``lxml.html`` are more robust in the face of uncommon HTML content like framesets or missing body tags. Patch by Stefan Seelmann. * LP#712941: I/O errors while trying to access files with paths that contain non-ASCII characters could raise ``UnicodeDecodeError`` instead of properly reporting the ``IOError``. * LP#673205: Parsing from in-memory strings disabled network access in the default parser and made subsequent attempts to parse from a URL fail. * LP#971754: lxml.html.clean appends 'nofollow' to 'rel' attributes instead of overwriting the current value. * LP#715687: lxml.html.clean no longer discards scripts that are explicitly allowed by the user provided whitelist. Patch by Christine Koppelt. Other changes ------------- 3.1.2 (2013-04-12) ================== Features added -------------- Bugs fixed ---------- * LP#1136509: Passing attributes through the namespace-unaware API of the sax bridge (i.e. the ``handler.startElement()`` method) failed with a ``TypeError``. Patch by Mike Bayer. * LP#1123074: Fix serialisation error in XSLT output when converting the result tree to a Unicode string. * GH#105: Replace illegal usage of ``xmlBufLength()`` in libxml2 2.9.0 by properly exported API function ``xmlBufUse()``. Other changes ------------- 3.1.1 (2013-03-29) ================== Features added -------------- Bugs fixed ---------- * LP#1160386: Write access to ``lxml.html.FormElement.fields`` raised an AttributeError in Py3. * Illegal memory access during cleanup in incremental xmlfile writer. Other changes ------------- * The externally useless class ``lxml.etree._BaseParser`` was removed from the module dict. 3.1.0 (2013-02-10) ================== Features added -------------- * GH#89: lxml.html.clean allows overriding the set of attributes that it considers 'safe'. Patch by Francis Devereux. Bugs fixed ---------- * LP#1104370: ``copy.copy(el.attrib)`` raised an exception. It now returns a copy of the attributes as a plain Python dict. * GH#95: When used with namespace prefixes, the ``el.find*()`` methods always used the first namespace mapping that was provided for each path expression instead of using the one that was actually passed in for the current run. * LP#1092521, GH#91: Fix undefined C symbol in Python runtimes compiled without threading support. Patch by Ulrich Seidl. Other changes ------------- 3.1beta1 (2012-12-21) ===================== Features added -------------- * New build-time option ``--with-unicode-strings`` for Python 2 that makes the API always return Unicode strings for names and text instead of byte strings for plain ASCII content. * New incremental XML file writing API ``etree.xmlfile()``. * E factory in lxml.objectify is callable to simplify the creation of tags with non-identifier names without having to resort to getattr(). Bugs fixed ---------- * When starting from a non-namespaced element in lxml.objectify, searching for a child without explicitly specifying a namespace incorrectly found namespaced elements with the requested local name, instead of restricting the search to non-namespaced children. * GH#85: Deprecation warnings were fixed for Python 3.x. * GH#33: lxml.html.fromstring() failed to accept bytes input in Py3. * LP#1080792: Static build of libxml2 2.9.0 failed due to missing file. Other changes ------------- * The externally useless class ``_ObjectifyElementMakerCaller`` was removed from the module API of lxml.objectify. * LP#1075622: lxml.builder is faster for adding text to elements with many children. Patch by Anders Hammarquist. 3.0.2 (2012-12-14) ================== Features added -------------- Bugs fixed ---------- * Fix crash during interpreter shutdown by switching to Cython 0.17.3 for building. Other changes ------------- 3.0.1 (2012-10-14) ================== Features added -------------- Bugs fixed ---------- * LP#1065924: Element proxies could disappear during garbage collection in PyPy without proper cleanup. * GH#71: Failure to work with libxml2 2.6.x. * LP#1065139: static MacOS-X build failed in Py3. Other changes ------------- 3.0 (2012-10-08) ================ Features added -------------- Bugs fixed ---------- * End-of-file handling was incorrect in iterparse() when reading from a low-level C file stream and failed in libxml2 2.9.0 due to its improved consistency checks. Other changes ------------- * The build no longer uses Cython by default unless the generated C files are missing. To use Cython, pass the option "--with-cython". To ignore the fatal build error when Cython is required but not available (e.g. to run special setup.py commands that do not actually run a build), pass "--without-cython". 3.0beta1 (2012-09-26) ===================== Features added -------------- * Python level access to (optional) libxml2 memory debugging features to simplify debugging of memory leaks etc. Bugs fixed ---------- * Fix a memory leak in XPath by switching to Cython 0.17.1. * Some tests were adapted to work with PyPy. Other changes ------------- * The code was adapted to work with the upcoming libxml2 2.9.0 release. 3.0alpha2 (2012-08-23) ====================== Features added -------------- * The ``.iter()`` method of elements now accepts ``tag`` arguments like ``"{*}name"`` to search for elements with a given local name in any namespace. With this addition, all combinations of wildcards now work as expected: ``"{ns}name"``, ``"{}name"``, ``"{*}name"``, ``"{ns}*"``, ``"{}*"`` and ``"{*}*"``. Note that ``"name"`` is equivalent to ``"{}name"``, but ``"*"`` is ``"{*}*"``. The same change applies to the ``.getiterator()``, ``.itersiblings()``, ``.iterancestors()``, ``.iterdescendants()``, ``.iterchildren()`` and ``.itertext()`` methods;the ``strip_attributes()``, ``strip_elements()`` and ``strip_tags()`` functions as well as the ``iterparse()`` class. Patch by Simon Sapin. * C14N allows specifying the inclusive prefixes to be promoted to top-level during exclusive serialisation. Bugs fixed ---------- * Passing long Unicode strings into the ``feed()`` parser interface failed to read the entire string. Other changes ------------- 3.0alpha1 (2012-07-31) ====================== Features added -------------- * Initial support for building in PyPy (through cpyext). * DTD objects gained an API that allows read access to their declarations. * ``xpathgrep.py`` gained support for parsing line-by-line (e.g. from grep output) and for surrounding the output with a new root tag. * ``E-factory`` in ``lxml.builder`` accepts subtypes of known data types (such as string subtypes) when building elements around them. * Tree iteration and ``iterparse()`` with a selective ``tag`` argument supports passing a set of tags. Tree nodes will be returned by the iterators if they match any of the tags. Bugs fixed ---------- * The ``.find*()`` methods in ``lxml.objectify`` no longer use XPath internally, which makes them faster in many cases (especially when short circuiting after a single or couple of elements) and fixes some behavioural differences compared to ``lxml.etree``. Note that this means that they no longer support arbitrary XPath expressions but only the subset that the ``ElementPath`` language supports. The previous implementation was also redundant with the normal XPath support, which can be used as a replacement. * ``el.find('*')`` could accidentally return a comment or processing instruction that happened to be in the wrong spot. (Same for the other ``.find*()`` methods.) * The error logging is less intrusive and avoids a global setup where possible. * Fixed undefined names in html5lib parser. * ``xpathgrep.py`` did not work in Python 3. * ``Element.attrib.update()`` did not accept an ``attrib`` of another Element as parameter. * For subtypes of ``ElementBase`` that make the ``.text`` or ``.tail`` properties immutable (as in objectify, for example), inserting text when creating Elements through the E-Factory feature of the class constructor would fail with an exception, stating that the text cannot be modified. Other changes -------------- * The code base was overhauled to properly use 'const' where the API of libxml2 and libxslt requests it. This also has an impact on the public C-API of lxml itself, as defined in ``etreepublic.pxd``, as well as the provided declarations in the ``lxml/includes/`` directory. Code that uses these declarations may have to be adapted. On the plus side, this fixes several C compiler warnings, also for user code, thus making it easier to spot real problems again. * The functionality of "lxml.cssselect" was moved into a separate PyPI package called "cssselect". To continue using it, you must install that package separately. The "lxml.cssselect" module is still available and provides the same interface, provided the "cssselect" package can be imported at runtime. * Element attributes passed in as an ``attrib`` dict or as keyword arguments are now sorted by (namespaced) name before being created to make their order predictable for serialisation and iteration. Note that adding or deleting attributes afterwards does not take that order into account, i.e. setting a new attribute appends it after the existing ones. * Several classes that are for internal use only were removed from the ``lxml.etree`` module dict: ``_InputDocument, _ResolverRegistry, _ResolverContext, _BaseContext, _ExsltRegExp, _IterparseContext, _TempStore, _ExceptionContext, __ContentOnlyElement, _AttribIterator, _NamespaceRegistry, _ClassNamespaceRegistry, _FunctionNamespaceRegistry, _XPathFunctionNamespaceRegistry, _ParserDictionaryContext, _FileReaderContext, _ParserContext, _PythonSaxParserTarget, _TargetParserContext, _ReadOnlyProxy, _ReadOnlyPIProxy, _ReadOnlyEntityProxy, _ReadOnlyElementProxy, _OpaqueNodeWrapper, _OpaqueDocumentWrapper, _ModifyContentOnlyProxy, _ModifyContentOnlyPIProxy, _ModifyContentOnlyEntityProxy, _AppendOnlyElementProxy, _SaxParserContext, _FilelikeWriter, _ParserSchemaValidationContext, _XPathContext, _XSLTResolverContext, _XSLTContext, _XSLTQuotedStringParam`` * Several internal classes can no longer be inherited from: ``_InputDocument, _ResolverRegistry, _ExsltRegExp, _ElementUnicodeResult, _IterparseContext, _TempStore, _AttribIterator, _ClassNamespaceRegistry, _XPathFunctionNamespaceRegistry, _ParserDictionaryContext, _FileReaderContext, _PythonSaxParserTarget, _TargetParserContext, _ReadOnlyPIProxy, _ReadOnlyEntityProxy, _OpaqueDocumentWrapper, _ModifyContentOnlyPIProxy, _ModifyContentOnlyEntityProxy, _AppendOnlyElementProxy, _FilelikeWriter, _ParserSchemaValidationContext, _XPathContext, _XSLTResolverContext, _XSLTContext, _XSLTQuotedStringParam, _XSLTResultTree, _XSLTProcessingInstruction`` 2.3.6 (2012-09-28) ================== Features added -------------- Bugs fixed ---------- * Passing long Unicode strings into the ``feed()`` parser interface failed to read the entire string. Other changes -------------- 2.3.5 (2012-07-31) ================== Features added -------------- Bugs fixed ---------- * Crash when merging text nodes in ``element.remove()``. * Crash in sax/target parser when reporting empty doctype. Other changes -------------- 2.3.4 (2012-03-26) ================== Features added -------------- Bugs fixed ---------- * Crash when building an nsmap (Element property) with empty namespace URIs. * Crash due to race condition when errors (or user messages) occur during threaded XSLT processing. * XSLT stylesheet compilation could ignore compilation errors. Other changes -------------- 2.3.3 (2012-01-04) ================== Features added -------------- * ``lxml.html.tostring()`` gained new serialisation options ``with_tail`` and ``doctype``. Bugs fixed ---------- * Fixed a crash when using ``iterparse()`` for HTML parsing and requesting start events. * Fixed parsing of more selectors in cssselect. Whitespace before pseudo-elements and pseudo-classes is significant as it is a descendant combinator. "E :pseudo" should parse the same as "E \*:pseudo", not "E:pseudo". Patch by Simon Sapin. * lxml.html.diff no longer raises an exception when hitting 'img' tags without 'src' attribute. Other changes -------------- 2.3.2 (2011-11-11) ================== Features added -------------- * ``lxml.objectify.deannotate()`` has a new boolean option ``cleanup_namespaces`` to remove the objectify namespace declarations (and generally clean up the namespace declarations) after removing the type annotations. * ``lxml.objectify`` gained its own ``SubElement()`` function as a copy of ``etree.SubElement`` to avoid an otherwise redundant import of ``lxml.etree`` on the user side. Bugs fixed ---------- * Fixed the "descendant" bug in cssselect a second time (after a first fix in lxml 2.3.1). The previous change resulted in a serious performance regression for the XPath based evaluation of the translated expression. Note that this breaks the usage of some of the generated XPath expressions as XSLT location paths that previously worked in 2.3.1. * Fixed parsing of some selectors in cssselect. Whitespace after combinators ">", "+" and "~" is now correctly ignored. Previously is was parsed as a descendant combinator. For example, "div> .foo" was parsed the same as "div>* .foo" instead of "div>.foo". Patch by Simon Sapin. Other changes -------------- 2.3.1 (2011-09-25) ================== Features added -------------- * New option ``kill_tags`` in ``lxml.html.clean`` to remove specific tags and their content (i.e. their whole subtree). * ``pi.get()`` and ``pi.attrib`` on processing instructions to parse pseudo-attributes from the text content of processing instructions. * ``lxml.get_include()`` returns a list of include paths that can be used to compile external C code against lxml.etree. This is specifically required for statically linked lxml builds when code needs to compile against the exact same header file versions as lxml itself. * ``Resolver.resolve_file()`` takes an additional option ``close_file`` that configures if the file(-like) object will be closed after reading or not. By default, the file will be closed, as the user is not expected to keep a reference to it. Bugs fixed ---------- * HTML cleaning didn't remove 'data:' links. * The html5lib parser integration now uses the 'official' implementation in html5lib itself, which makes it work with newer releases of the library. * In ``lxml.sax``, ``endElementNS()`` could incorrectly reject a plain tag name when the corresponding start event inferred the same plain tag name to be in the default namespace. * When an open file-like object is passed into ``parse()`` or ``iterparse()``, the parser will no longer close it after use. This reverts a change in lxml 2.3 where all files would be closed. It is the users responsibility to properly close the file(-like) object, also in error cases. * Assertion error in lxml.html.cleaner when discarding top-level elements. * In lxml.cssselect, use the xpath 'A//B' (short for 'A/descendant-or-self::node()/B') instead of 'A/descendant::B' for the css descendant selector ('A B'). This makes a few edge cases like ``"div *:last-child"`` consistent with the selector behavior in WebKit and Firefox, and makes more css expressions valid location paths (for use in xsl:template match). * In lxml.html, non-selected ``