diff --git a/.DS_Store b/.DS_Store
new file mode 100644
index 0000000..9735057
Binary files /dev/null and b/.DS_Store differ
diff --git a/.venv/Lib/python3.9/site-packages/_distutils_hack/__init__.py b/.venv/Lib/python3.9/site-packages/_distutils_hack/__init__.py
new file mode 100644
index 0000000..5f40996
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/_distutils_hack/__init__.py
@@ -0,0 +1,128 @@
+import sys
+import os
+import re
+import importlib
+import warnings
+
+
+is_pypy = '__pypy__' in sys.builtin_module_names
+
+
+warnings.filterwarnings('ignore',
+ r'.+ distutils\b.+ deprecated',
+ DeprecationWarning)
+
+
+def warn_distutils_present():
+ if 'distutils' not in sys.modules:
+ return
+ if is_pypy and sys.version_info < (3, 7):
+ # PyPy for 3.6 unconditionally imports distutils, so bypass the warning
+ # https://foss.heptapod.net/pypy/pypy/-/blob/be829135bc0d758997b3566062999ee8b23872b4/lib-python/3/site.py#L250
+ return
+ warnings.warn(
+ "Distutils was imported before Setuptools, but importing Setuptools "
+ "also replaces the `distutils` module in `sys.modules`. This may lead "
+ "to undesirable behaviors or errors. To avoid these issues, avoid "
+ "using distutils directly, ensure that setuptools is installed in the "
+ "traditional way (e.g. not an editable install), and/or make sure "
+ "that setuptools is always imported before distutils.")
+
+
+def clear_distutils():
+ if 'distutils' not in sys.modules:
+ return
+ warnings.warn("Setuptools is replacing distutils.")
+ mods = [name for name in sys.modules if re.match(r'distutils\b', name)]
+ for name in mods:
+ del sys.modules[name]
+
+
+def enabled():
+ """
+ Allow selection of distutils by environment variable.
+ """
+ which = os.environ.get('SETUPTOOLS_USE_DISTUTILS', 'stdlib')
+ return which == 'local'
+
+
+def ensure_local_distutils():
+ clear_distutils()
+ distutils = importlib.import_module('setuptools._distutils')
+ distutils.__name__ = 'distutils'
+ sys.modules['distutils'] = distutils
+
+ # sanity check that submodules load as expected
+ core = importlib.import_module('distutils.core')
+ assert '_distutils' in core.__file__, core.__file__
+
+
+def do_override():
+ """
+ Ensure that the local copy of distutils is preferred over stdlib.
+
+ See https://github.com/pypa/setuptools/issues/417#issuecomment-392298401
+ for more motivation.
+ """
+ if enabled():
+ warn_distutils_present()
+ ensure_local_distutils()
+
+
+class DistutilsMetaFinder:
+ def find_spec(self, fullname, path, target=None):
+ if path is not None:
+ return
+
+ method_name = 'spec_for_{fullname}'.format(**locals())
+ method = getattr(self, method_name, lambda: None)
+ return method()
+
+ def spec_for_distutils(self):
+ import importlib.abc
+ import importlib.util
+
+ class DistutilsLoader(importlib.abc.Loader):
+
+ def create_module(self, spec):
+ return importlib.import_module('setuptools._distutils')
+
+ def exec_module(self, module):
+ pass
+
+ return importlib.util.spec_from_loader('distutils', DistutilsLoader())
+
+ def spec_for_pip(self):
+ """
+ Ensure stdlib distutils when running under pip.
+ See pypa/pip#8761 for rationale.
+ """
+ if self.pip_imported_during_build():
+ return
+ clear_distutils()
+ self.spec_for_distutils = lambda: None
+
+ @staticmethod
+ def pip_imported_during_build():
+ """
+ Detect if pip is being imported in a build script. Ref #2355.
+ """
+ import traceback
+ return any(
+ frame.f_globals['__file__'].endswith('setup.py')
+ for frame, line in traceback.walk_stack(None)
+ )
+
+
+DISTUTILS_FINDER = DistutilsMetaFinder()
+
+
+def add_shim():
+ sys.meta_path.insert(0, DISTUTILS_FINDER)
+
+
+def remove_shim():
+ try:
+ sys.meta_path.remove(DISTUTILS_FINDER)
+ except ValueError:
+ pass
diff --git a/.venv/Lib/python3.9/site-packages/_distutils_hack/override.py b/.venv/Lib/python3.9/site-packages/_distutils_hack/override.py
new file mode 100644
index 0000000..2cc433a
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/_distutils_hack/override.py
@@ -0,0 +1 @@
+__import__('_distutils_hack').do_override()
diff --git a/.venv/Lib/python3.9/site-packages/distutils-precedence.pth b/.venv/Lib/python3.9/site-packages/distutils-precedence.pth
new file mode 100644
index 0000000..6de4198
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/distutils-precedence.pth
@@ -0,0 +1 @@
+import os; var = 'SETUPTOOLS_USE_DISTUTILS'; enabled = os.environ.get(var, 'stdlib') == 'local'; enabled and __import__('_distutils_hack').add_shim();
diff --git a/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/INSTALLER b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/INSTALLER
new file mode 100644
index 0000000..a1b589e
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/INSTALLER
@@ -0,0 +1 @@
+pip
diff --git a/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/METADATA b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/METADATA
new file mode 100644
index 0000000..805cbb8
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/METADATA
@@ -0,0 +1,104 @@
+Metadata-Version: 2.4
+Name: lxml
+Version: 6.1.0
+Summary: Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API.
+Home-page: https://lxml.de/
+Author: lxml dev team
+Author-email: lxml@lxml.de
+Maintainer: lxml dev team
+Maintainer-email: lxml@lxml.de
+License: BSD-3-Clause
+Project-URL: Source, https://github.com/lxml/lxml
+Project-URL: Bug Tracker, https://bugs.launchpad.net/lxml
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: Programming Language :: Cython
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: C
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Text Processing :: Markup :: HTML
+Classifier: Topic :: Text Processing :: Markup :: XML
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.8
+License-File: LICENSE.txt
+License-File: LICENSES.txt
+Provides-Extra: source
+Provides-Extra: cssselect
+Requires-Dist: cssselect>=0.7; extra == "cssselect"
+Provides-Extra: html5
+Requires-Dist: html5lib; extra == "html5"
+Provides-Extra: htmlsoup
+Requires-Dist: BeautifulSoup4; extra == "htmlsoup"
+Provides-Extra: html-clean
+Requires-Dist: lxml_html_clean; extra == "html-clean"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: home-page
+Dynamic: license
+Dynamic: license-file
+Dynamic: maintainer
+Dynamic: maintainer-email
+Dynamic: project-url
+Dynamic: provides-extra
+Dynamic: requires-python
+Dynamic: summary
+
+lxml is a Pythonic, mature binding for the libxml2 and libxslt libraries.
+It provides safe and convenient access to these libraries using the
+ElementTree API.
+
+It extends the ElementTree API significantly to offer support for XPath,
+RelaxNG, XML Schema, XSLT, C14N and much more.
+
+To contact the project, go to the `project home page `_
+or see our bug tracker at https://launchpad.net/lxml
+
+In case you want to use the current in-development version of lxml,
+you can get it from the github repository at
+https://github.com/lxml/lxml . Note that this requires Cython to
+build the sources, see the build instructions on the project home page.
+
+
+After an official release of a new stable series, bug fixes may become available at
+https://github.com/lxml/lxml/tree/lxml-6.1 .
+Running ``pip install https://github.com/lxml/lxml/archive/refs/heads/lxml-6.1.tar.gz``
+will install the unreleased branch state as soon as a maintenance branch has been established.
+Note that this requires Cython to be installed at an appropriate version for the build.
+
+6.1.0 (2026-04-17)
+==================
+
+This release fixes a possible external entity injection (XXE) vulnerability in
+``iterparse()`` and the ``ETCompatXMLParser``.
+
+Features added
+--------------
+
+* GH#486: The HTML ARIA accessibility attributes were added to the set of safe attributes
+ in ``lxml.html.defs``. This allows ``lxml_html_clean`` to pass them through.
+ Patch by oomsveta.
+
+* The default chunk size for reading from file-likes in ``iterparse()`` is now configurable
+ with a new ``chunk_size`` argument.
+
+Bugs fixed
+----------
+
+* LP#2146291: The ``resolve_entities`` option was still set to ``True`` for
+ ``iterparse`` and ``ETCompatXMLParser``, allowing for external entity injection (XXE)
+ when using these parsers without setting this option explicitly.
+ The default was now changed to ``'internal'`` only (as for the normal XML and HTML parsers
+ since lxml 5.0).
+ Issue found by Sihao Qiu as CVE-2026-41066.
+
+
diff --git a/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/RECORD b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/RECORD
new file mode 100644
index 0000000..2905563
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/RECORD
@@ -0,0 +1,205 @@
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/ElementInclude.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/__init__.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/_elementpath.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/builder.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/cssselect.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/doctestcompare.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/html/ElementSoup.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/html/__init__.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/html/_diffcommand.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/html/_difflib.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/html/_html5builder.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/html/_setmixin.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/html/builder.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/html/clean.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/html/defs.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/html/diff.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/html/formfill.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/html/html5parser.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/html/soupparser.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/html/usedoctest.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/includes/__init__.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/includes/extlibs/__init__.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/includes/libexslt/__init__.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/includes/libxml/__init__.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/includes/libxslt/__init__.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/isoschematron/__init__.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/pyclasslookup.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/sax.cpython-39.pyc,,
+../../../../../../../Library/Caches/com.apple.python/Users/nicobalke/Projects/nazeka/nazeka-chromium/.venv/lib/python3.9/site-packages/lxml/usedoctest.cpython-39.pyc,,
+lxml-6.1.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+lxml-6.1.0.dist-info/METADATA,sha256=C22o5J3b-pRFqvsDJ8BZIZgShZshbyM4dD_WThX15FU,3953
+lxml-6.1.0.dist-info/RECORD,,
+lxml-6.1.0.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+lxml-6.1.0.dist-info/WHEEL,sha256=wVKWt0AtoluPjZmAD6HaTfsQfwFu4p-mJPYH_0AR-b0,139
+lxml-6.1.0.dist-info/licenses/LICENSE.txt,sha256=j8K1aBM1FuRoRdIUeRet7uFkjnCumrXtbFQXr-9M6FU,1507
+lxml-6.1.0.dist-info/licenses/LICENSES.txt,sha256=QdSd1AaqDhVIptXyGjDWv2OLPNlutyid00jYPtLkA5I,1514
+lxml-6.1.0.dist-info/top_level.txt,sha256=NjD988wqaKq512nshNdLt-uDxsjkp4Bh51m6N-dhUrk,5
+lxml/ElementInclude.py,sha256=PSLeZFvCa76WHJulPLxcZXJtCI2-4dK2CtqPRiYOAQg,8560
+lxml/__init__.py,sha256=nNZhK4w0_VI-AvQ3n1b4cWN1fFhYFdteghBR1mR7j1M,574
+lxml/_elementpath.cpython-39-darwin.so,sha256=yL6Jx2BqaCfFpoGgYNiq-w81CG9tNMa_gw7BkQH8nfY,475728
+lxml/_elementpath.py,sha256=b80hM3ndAkTtRX6v54za3LkkAqCcd0700BbMPZHnTBU,10959
+lxml/apihelpers.pxi,sha256=CugqfQgyn6aFtwp7eH144RUpV2v1ItxoalhJcFbORTQ,64604
+lxml/builder.cpython-39-darwin.so,sha256=GSWKSfmsLOErZ-7yUqxA35xRMbIy4LHu_Aweiq9NI6g,283696
+lxml/builder.py,sha256=KI1HxHTd4wJqqVfmTRtSbXBQdl2T-P36ih4hT-J3MNw,8485
+lxml/classlookup.pxi,sha256=Tax8Vhbm5C6UCjgmRFsYjW0pFHxIuTthH1MOgASDLgc,22435
+lxml/cleanup.pxi,sha256=ZNEpbv7qx_ICPzsxhCaMUHCOfiznOoZ_u3jlYXHAuh4,8454
+lxml/cssselect.py,sha256=_wZdX-B9p5MeIYABmENIYRWEkwXwX-7jO8Dkf-1rUZU,3306
+lxml/debug.pxi,sha256=KTcpR8-slUYvmIPbE35GoHDNTb-gjTEvD7bw6LltM4c,1125
+lxml/docloader.pxi,sha256=fcoVd_mwTFZhjItCv_TfwXpgVek7JlvFObSfRxmVqs0,5790
+lxml/doctestcompare.py,sha256=40EDnkwpcvW86qNa86990OXF42xdHaosSZoiBsEjkzU,17731
+lxml/dtd.pxi,sha256=IAKkmA4ZoC68sqAWcTqoS8jEGYcPQrVMCZgn4iLBYko,15281
+lxml/etree.cpython-39-darwin.so,sha256=CL6Td0sWFQJxc3nfqNyzm_aHqufv-r_qlIqnqFOc1eo,9434568
+lxml/etree.h,sha256=hWgHumv7DeTpH0nHhbsCIe693cIcimtLabExxwBxR-c,9792
+lxml/etree.pyx,sha256=zgobCeGw6lw902OA0FWuwlOpqA_0eZeLM2baWi1pzio,138216
+lxml/etree_api.h,sha256=UG16a1ThLt259FSG3vUy6ka6OIat-6LLJyVBLz6d3OM,17710
+lxml/extensions.pxi,sha256=saxxc1mZyA8WdwIIL90B4lQb351j8-G7ttLPI5k-8Hw,32248
+lxml/html/ElementSoup.py,sha256=s_dLobLMuKn2DhexR-iDXdZrMFg1RjLy1feHsIeZMpw,320
+lxml/html/__init__.py,sha256=CC5WdsvSptZhr9MZya1qsL6JKVbviYdrHOhXrGhmORg,64425
+lxml/html/_diffcommand.py,sha256=kz_7EP9PmYWuczlZcGiw74_rG0eTKvQ2lrO0rkiwlYE,2081
+lxml/html/_difflib.cpython-39-darwin.so,sha256=ME3lyrc-dethkeldLMta8OuRfpwPEuLC6SFEP6Jyi4g,1050992
+lxml/html/_difflib.py,sha256=GgH_jVrZQC8tI8WV_lFZQsXFJ3mOTAPup1zjBJNvkPo,84954
+lxml/html/_html5builder.py,sha256=NLaT-Ev-aBgJpeQl-6ZbJChLZK5GV-znDkHOJD5VQC4,3230
+lxml/html/_setmixin.py,sha256=8IFIOLmVz0G-XzsD2tCEkSFWO-dgPBHgvHufC8ni67s,1188
+lxml/html/builder.py,sha256=Uz3r5uiuCdoN0UPa7ngoLMwAadVIhslzGvlRPGigY_M,6187
+lxml/html/clean.py,sha256=WU0KfXAyjDFn2ojE7T1dfk4cl_FduBu5ZbFSTc9Up_o,503
+lxml/html/defs.py,sha256=IHIW70bC-m8RdCtGOyYak58hFiBqyhegTC83QlsO5As,5322
+lxml/html/diff.cpython-39-darwin.so,sha256=6S3BExSrEpp5zWuyQYasCVF69Vzyu3a80jc9CMo4v4c,700408
+lxml/html/diff.py,sha256=Za0By-yeYlQEjUu7m7xKB288kKiy8VBS5gT0RPOaFY0,32989
+lxml/html/formfill.py,sha256=umgk0BbkAI1W6q9musFbL-cDnI_aap2NsLBJqk0UmVI,9681
+lxml/html/html5parser.py,sha256=dnyC4cqHxywjZSzk0mu2L7THTZjxhg4yF4pncjusa_w,8634
+lxml/html/soupparser.py,sha256=xo8VvNeOEb-SChuXLKCRECh8J7HBiJLE9sAbEskoUUQ,10197
+lxml/html/usedoctest.py,sha256=tPlmVz4KK1GRKV5DJLrdVECeqsT9PlDzSqqTodVi5s0,249
+lxml/includes/__init__.pxd,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+lxml/includes/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+lxml/includes/c14n.pxd,sha256=DBQcOJ0c_YS245ohMb8fmuEC1kFyv1LrNY_8Mf-syZg,1110
+lxml/includes/config.pxd,sha256=H6Mrl8It21hzRI2hzMId9W48QqkYYkoLT4dniLNmdTw,96
+lxml/includes/dtdvalid.pxd,sha256=Nv0OykjYehv2lO-Zj--q6jS3TAC_dvQVPSgPMuse1NM,689
+lxml/includes/etree_defs.h,sha256=h_UjJTmNUqPyKNNrWB9hxmt6v4CF7_83XVY8dOfxqW0,14524
+lxml/includes/etreepublic.pxd,sha256=Bn4d3JkWPqXputXqI-eJ0xmPrwNFPTfDCa7axgjB7FM,10184
+lxml/includes/extlibs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+lxml/includes/extlibs/libcharset.h,sha256=GA0FumrbNI4VDGlzq3lf5CLaCwXgn4unw2l0btGQFwI,1510
+lxml/includes/extlibs/localcharset.h,sha256=Z_AagaQeq0aDE7NPsVOqEf4nO4KcUp46ggo4d0ONIOQ,6338
+lxml/includes/extlibs/zconf.h,sha256=BxihG-sylbNF-ymmO0S2VLKC2CxM0FE_YiVYfyspuLs,16921
+lxml/includes/extlibs/zlib.h,sha256=gYZn1qtqN_50acsGp_DLLCyy8slIoD5azPGkp0vzAgo,103848
+lxml/includes/htmlparser.pxd,sha256=9uASkP5dU7OE2lCOLT-z2e01qSbFlp4ehgwdostF_qk,2802
+lxml/includes/libexslt/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+lxml/includes/libexslt/exslt.h,sha256=eSW5tMJAewSUANLqk7AGEiU8b2BbCNRyauHnez7nKSU,3114
+lxml/includes/libexslt/exsltconfig.h,sha256=QHxzEbRlv_h0USBvpr0Zrl0Muzlc71VCrvgR6lqnLEY,1172
+lxml/includes/libexslt/exsltexports.h,sha256=1Jm9KTXm2FUUJIZ6V6-Uw55yG0BMULX3_goyxDd2LL8,1077
+lxml/includes/libxml/HTMLparser.h,sha256=sU4xGqj-vBtEvzlxA3hBPWJboifvkc4F1hynKXmsl3k,9569
+lxml/includes/libxml/HTMLtree.h,sha256=Q7UBKFbQ8fx4d_dMnmR6ay8JmfOhopFkDp2B63YkLDU,3517
+lxml/includes/libxml/SAX.h,sha256=SFnG27EFrYGUB9HDL_xSIGBwEns5pl07rApXWThFZFM,386
+lxml/includes/libxml/SAX2.h,sha256=RfFP5o3le-Rg8bnA2GW7L7L9_pfXCs3TieODcv1DTWY,4240
+lxml/includes/libxml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+lxml/includes/libxml/c14n.h,sha256=BSBXw6nIZutC8mWvbRrLLmoWjw3wRt-nM93vjXGMCm8,2742
+lxml/includes/libxml/catalog.h,sha256=H9ssTCaBjtDqc-AZqCk1R7h8F2iD9szqLjJyHpaczXg,4633
+lxml/includes/libxml/chvalid.h,sha256=TZcceNp6Cw0QlYwIqK9GxyYqL5UiAjpQyjt_yrZGTQE,5087
+lxml/includes/libxml/debugXML.h,sha256=XXRNI39gJW7bGRC4SzE4ad-SJ906BsUGz3AwOtkKuS4,1667
+lxml/includes/libxml/dict.h,sha256=SweaPGMtTTf4je6dNTIoEzcfEvpsAT9_PhR7FC0K-rQ,1770
+lxml/includes/libxml/encoding.h,sha256=haL7ratww2wkIERGmtwUqU2BbTVe52FZFU7MmrOpsPk,9623
+lxml/includes/libxml/entities.h,sha256=LEOCA826-0f8dhRJzC_2hvUVsSH7lKQjrea9hSTdBbo,4419
+lxml/includes/libxml/globals.h,sha256=NH8zyRI5cXJJGp5k2aLxOm-reJEGOFX6LYP82GBXRlY,583
+lxml/includes/libxml/hash.h,sha256=KIIpAYKBfGUU3ydWhGehUyfuauZz_Ps0gyambzQo_rc,7017
+lxml/includes/libxml/list.h,sha256=oh7iJNQajRA_cHsNk9CcFPYkaW2smf4J_MpedPPjC4k,3128
+lxml/includes/libxml/nanoftp.h,sha256=22PBtWhJueYLFvwukt4oFooRct_xJA83hbluHRBNXUM,302
+lxml/includes/libxml/nanohttp.h,sha256=bLbzYjAyAKmP3ComMOPH6XaUImu6bNAESF1HrVtRve0,2124
+lxml/includes/libxml/parser.h,sha256=Uq7-ce55UUAsvo4n6CiBlNQpmowewvWhOsQtgGM1UQ8,48498
+lxml/includes/libxml/parserInternals.h,sha256=8_Wr6UgRzm8BRn1RPLxyBkw6BagAdDvVqMA_e181_EI,14539
+lxml/includes/libxml/relaxng.h,sha256=VXZ74r5Yja06KqypdBHc8neDwPxQ2aMrsWHSdRt5oi4,5991
+lxml/includes/libxml/schemasInternals.h,sha256=V8M4In3zf24EX55Yt4dcfxwp7NpHGYViKnLKwtyrPJ4,26233
+lxml/includes/libxml/schematron.h,sha256=8EhPDhvtlMxl9e0C5rSbEruOvzJS5BC_OOFbq9RXZnY,4255
+lxml/includes/libxml/threads.h,sha256=mT3CgK4lXK7-NDnUOFXqYuCK6fyY70S3BsHF-TnT45k,1619
+lxml/includes/libxml/tree.h,sha256=zTRLt6h5x6ApyeXgs90CKQZSAl2hKm7b5NxtPKUQFAE,36106
+lxml/includes/libxml/uri.h,sha256=J9teJHme5z883c4twF5oImEYY-E3xSvhdSGpyRVtvIg,2855
+lxml/includes/libxml/valid.h,sha256=By61IbPvk_eLux7a8x0mOaly7oclFaSGaFE8b2xZcUE,13226
+lxml/includes/libxml/xinclude.h,sha256=K3I5jhw2zAMj26LuRNZc15Bwv2JE2hWxwVn4TCqv2b4,3258
+lxml/includes/libxml/xlink.h,sha256=TVLOkISrcKDelo9n_XIUyPiStDYa8NxuF2dz70aBFCI,5062
+lxml/includes/libxml/xmlIO.h,sha256=FvbuMYTy1-S5PScabE03wz0oWKf626pmXvOPZNuLm-w,11948
+lxml/includes/libxml/xmlautomata.h,sha256=7Sc3YgPz1ZIBKCHPSxs5oAwJEZWQ1RT2kyUw85pUtmU,4004
+lxml/includes/libxml/xmlerror.h,sha256=mMfltMxUza6kiSBfP2QfnY3UlMP_rEXKfX0wruBLl4A,37561
+lxml/includes/libxml/xmlexports.h,sha256=IyV3AMeQVbOl0wkjlnNX4B8WUZ-5GNKQmxZc6-maWUU,2025
+lxml/includes/libxml/xmlmemory.h,sha256=m7wGvVMxNzZiuOAo3vkjxaVWstc8aQLzb6obbjPsebE,4658
+lxml/includes/libxml/xmlmodule.h,sha256=ERUHUmDdZRmh6NjLYWUpse51rLWR8qNjPHOtdgmlLF0,1198
+lxml/includes/libxml/xmlreader.h,sha256=BAHinlSOTXX3DEax9BniaIIPAXJyLGfzym9R-27LCcU,12387
+lxml/includes/libxml/xmlregexp.h,sha256=_q6C1XRy8DS3kSmLbEKpvkKQciTgjTJgGc_zUQ6m22M,2632
+lxml/includes/libxml/xmlsave.h,sha256=zcEQr9sO5CsFrnoOLshhdsqMEr8k4AeFhbkYyNfO9Fs,2934
+lxml/includes/libxml/xmlschemas.h,sha256=5AfLnYUcfmxHRzg0dVpdHig--4ui1-XDwDgpKGDKCiU,7067
+lxml/includes/libxml/xmlschemastypes.h,sha256=MYwlGmoKAo3lHRaaKgnCXiLmPT9KRjdxyCJ7TEyZ6jM,4583
+lxml/includes/libxml/xmlstring.h,sha256=d5PpqxP1I1sfmCUHvVJtjoC9h7hLHcAAQ5ok_Rtf50I,5271
+lxml/includes/libxml/xmlunicode.h,sha256=8sq3wEW2AiyTCuc3ZceOEkce7lfrI7VnkRfwEQgc6pU,278
+lxml/includes/libxml/xmlversion.h,sha256=oVpaE_xbttaeZNFKSuSfcLOceWz7LQgKP71Z1msXZNo,5112
+lxml/includes/libxml/xmlwriter.h,sha256=BEUwYNKx3xymDE9vepksEK7yVq9SXYm1d2pQnzlPy90,20688
+lxml/includes/libxml/xpath.h,sha256=CQv6X_pRhuXoCVpqoDXYB7FfusLK7AuPxCNigwhNYAA,16156
+lxml/includes/libxml/xpathInternals.h,sha256=mc9B5tdpfssyz_NPUzww6dKuWCtBybBiBRJkTe4AE4U,18504
+lxml/includes/libxml/xpointer.h,sha256=DAxMsfPp2SSZgXFrPbxBA84RwTMRf35Qg_LBbUzPQhA,1026
+lxml/includes/libxslt/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+lxml/includes/libxslt/attributes.h,sha256=qKwzfGf7r89esLC65s96iYJWRA-s-Ezss2_V6Mmo1hk,957
+lxml/includes/libxslt/documents.h,sha256=kBihgH5pqRvFalhm_fOFHtJTFhTpBcm681yT5dxgwfw,2704
+lxml/includes/libxslt/extensions.h,sha256=W5UMyJqUP_1zt6sXZ0mgc0gAIwDJrZ8gjByhyrWqvd8,6899
+lxml/includes/libxslt/extra.h,sha256=6X3Wu3NdPtrlqz-Koo7dB-rccnnszi6j3zg599gTByg,1640
+lxml/includes/libxslt/functions.h,sha256=fc4CZj-9KeBHzO9-WWU_bNqmaEZAz3n7NNwClIBXk14,1972
+lxml/includes/libxslt/imports.h,sha256=18kIjoGqdFXR63Ce3ZtzxsTiYV3XGKpchYakMUPDuUI,1840
+lxml/includes/libxslt/keys.h,sha256=16v25VEluS7jYhgg6gYFwVxgGMn-1ctnlhhWWT4RcBY,1155
+lxml/includes/libxslt/namespaces.h,sha256=VofSn2Kkn-a5JyRKCmY3jPp7amQy3n09vzy0KUQt4q0,1666
+lxml/includes/libxslt/numbersInternals.h,sha256=Eg5gYZ5p3h0_e5wyI61S-0E6_ArVJzv0yr63j6BU2fc,2019
+lxml/includes/libxslt/pattern.h,sha256=tJ-BPfs9UYgiZMMoQZbhij3g7xVppYq7TrrOu25eR7Q,2110
+lxml/includes/libxslt/preproc.h,sha256=D_LjEdHhsdyBnEAvflnwFgoR4hGUb72kgEhXkkmPRsw,896
+lxml/includes/libxslt/security.h,sha256=fUD1cy_WxFCTvTNAF0WOQIU4p5CNWn1LHFyZJd-Fx5U,2652
+lxml/includes/libxslt/templates.h,sha256=bnt6Jqui6KU5pNUdMNPbQZkZ5d-VTWqC0TMGkOlVoIo,2268
+lxml/includes/libxslt/transform.h,sha256=ICT7meUV0OTAx27WaKVrKj-aUmR9LSpTNaOAJd2UStg,6311
+lxml/includes/libxslt/variables.h,sha256=cQAgPe4QCcK2uKbWg7Iz-9peM9xWGm7m3M6jQm0sjIA,3143
+lxml/includes/libxslt/xslt.h,sha256=wmFx2Q31Pd8Iq2phAQpY9J3QQatb8lWg3gABtqKFgEw,1964
+lxml/includes/libxslt/xsltInternals.h,sha256=2EbEKYmnYZq0HjGnUMAlpqnqZJurRXzjlgk5Js1WYaY,57949
+lxml/includes/libxslt/xsltconfig.h,sha256=cV5scdRK6xmOHeOg3OCw6hBfcQ_nrtNs_tKefX67304,2910
+lxml/includes/libxslt/xsltexports.h,sha256=1-luH-0bCIgBAlKAXhV-dqHBfwOAQNDamiYbxIlTf0k,1124
+lxml/includes/libxslt/xsltlocale.h,sha256=ppxGEmJfZIJgwRQzCM0_77p9WNekEWq1NrdYZrQl4IE,942
+lxml/includes/libxslt/xsltutils.h,sha256=1eguYgR9-jeNOVlBUktHboaq-VLX6JXraO80TfbARKM,9085
+lxml/includes/lxml-version.h,sha256=7Jwmesey8JmjKayzDkLgkjKNi77OGhOzjJ_JC41Oj_I,71
+lxml/includes/relaxng.pxd,sha256=HzHlQ6mCcf_tj_JZ9NAVJTVAv8ScCkE8Ifq15y3bS0c,2615
+lxml/includes/schematron.pxd,sha256=Hob7xh-K-MKqp7WiG8thMagf5EkQzmgfi4ds0EF91JA,1604
+lxml/includes/tree.pxd,sha256=XApzMRy_LSqCtQ-OTS-vNSW7CT_OWstybfIT2H84LsA,20179
+lxml/includes/uri.pxd,sha256=3vOXw6AbSPxAM9uo71T1qnfx-wd9ezXLDQtWsb2zX0I,145
+lxml/includes/xinclude.pxd,sha256=CuO_XZNB6E2JK1qXXWn11APrjFQV5kA6SMyb77WZn0A,804
+lxml/includes/xmlerror.pxd,sha256=OQqayytkV0NigAPbsQCCcvmy7luRe0XhVzpTdzJjP3g,58837
+lxml/includes/xmlparser.pxd,sha256=eDGyU5kZyNVksK0dUhMIi7rnE-LSevXsqyl72v99Ess,13730
+lxml/includes/xmlschema.pxd,sha256=OLZPd2WDJyopiXJJyo-dAyyYHaeSYFiMAI4tqIiv-Ik,1702
+lxml/includes/xpath.pxd,sha256=e8-ZYUbRG7N1mHETAlknJ_QqAteOosrYLRgpH-OsTkg,5603
+lxml/includes/xslt.pxd,sha256=4yl3pOu7pAvsx5Tc-W4IWCoB8wgtSSR62HI1jqu6jko,8241
+lxml/isoschematron/__init__.py,sha256=uauerYeKTlWFCJSqieIHhF5l6rYV2myeEJ0Imd1LzRc,13274
+lxml/isoschematron/resources/rng/iso-schematron.rng,sha256=VsWxPyi3iViJDDbjJJw0wWkEHkLrz9zoCA8zJLor9N4,18337
+lxml/isoschematron/resources/xsl/RNG2Schtrn.xsl,sha256=ObebsB8Wt-d3uIA_U5NU85TpnQ3PxPX38TdOAqosMac,3172
+lxml/isoschematron/resources/xsl/XSD2Schtrn.xsl,sha256=QweRrIIM-zFcgg98GXA2CaWfIbgVE0XKEeYSfvv67A0,4563
+lxml/isoschematron/resources/xsl/iso-schematron-xslt1/iso_abstract_expand.xsl,sha256=xSZ_Ekq_I-62ZpiE5AqYYHwFW_qh855zt9V4_s7rbkY,11703
+lxml/isoschematron/resources/xsl/iso-schematron-xslt1/iso_dsdl_include.xsl,sha256=x42QJ-dxQ1waPzydsCoQnp2Xj15y53nW43O7BuoDRHk,39957
+lxml/isoschematron/resources/xsl/iso-schematron-xslt1/iso_schematron_message.xsl,sha256=Tr9BnO6pzjVWwhqJfm10UlvAy95EgfSCz2iMlrVGT6Q,2015
+lxml/isoschematron/resources/xsl/iso-schematron-xslt1/iso_schematron_skeleton_for_xslt1.xsl,sha256=ue8q_88X4e_jsJizo31GRNBxNhdxkEE9fY20oq0Iqwk,71764
+lxml/isoschematron/resources/xsl/iso-schematron-xslt1/iso_svrl_for_xslt1.xsl,sha256=BBAdsVSi5zAzeGepuN6gS1saQINDqITXKplmmj4dTWg,20382
+lxml/isoschematron/resources/xsl/iso-schematron-xslt1/readme.txt,sha256=OGLiFswuLJEW5EPYKOeoauuCJFEtVa6jyzBE1OcJI98,3310
+lxml/iterparse.pxi,sha256=rERnJ9D0Cvn87YDMSq8V880DKV2WthXs5BXSSY2Baj4,16845
+lxml/lxml.etree.h,sha256=hWgHumv7DeTpH0nHhbsCIe693cIcimtLabExxwBxR-c,9792
+lxml/lxml.etree_api.h,sha256=O_s_RIicKl7_h5U0aKu9dKSzJCTYSDJI6jlX7b-2v0Q,17715
+lxml/nsclasses.pxi,sha256=5pzNBhBtlqObPdThL9QIGRs1Dxj1qnr0PyXuTCURqTg,9129
+lxml/objectify.cpython-39-darwin.so,sha256=mSZYNLRItE6jEAeBk3E77k5AG7otDsX94vtyKr6tw_E,5223056
+lxml/objectify.pyx,sha256=8lIjgklL3LJ3PYAcWZ5hPLuLFa7oLqEspco4bSz4EI4,75850
+lxml/objectpath.pxi,sha256=s5TNG2-EbaWWKLFAiX303B95zK_Ui8ausB__3QvFFGw,11450
+lxml/parser.pxi,sha256=lw230Za_GcJe-CFfznB1As9MSEi0d6gsMKidQxUR-7E,85817
+lxml/parsertarget.pxi,sha256=v1PidxRaG5giwXcTDkpBI7PDFmsZuOcK0y9LdkQaY8M,6326
+lxml/proxy.pxi,sha256=LnqqSZVUsJ5MnuVrhYrLwMbAKWuv1eOn-XYslut6CLM,24015
+lxml/public-api.pxi,sha256=yVPuZV2LwN5Ki73mD85V9hnUXxOs5VMeFMLtQMNf0Qk,6756
+lxml/pyclasslookup.py,sha256=gLD1HM2HtITYYiGzjEOewSwbB7XkVx_NZv_quCt79Oc,92
+lxml/readonlytree.pxi,sha256=n2MRjz81EADWBXJx0miosN8PJ4i5y3guQJT_RZF6qKg,19008
+lxml/relaxng.pxi,sha256=3OQ-fZMzP-KF5vM6HTozT_9ee3J0DJnpj9RcHC8LoMw,6339
+lxml/sax.cpython-39-darwin.so,sha256=ANw0CFSsJTJGfN7bBawmqJ__rrEUBtEtukUhr5Z4ZeY,391736
+lxml/sax.py,sha256=yrNvKD6rlon48jrR-1qpFXER8j4psYC2R5yt0u6TWLs,9706
+lxml/saxparser.pxi,sha256=yV67FWD60DfmFi7hbV_eLyJIMu7X2MOfV2g4X99iUR4,33538
+lxml/schematron.pxi,sha256=F2OHKZUl57-byBk_wWtPTnHZ1fwlj0FtwG3VuGtG-UY,6064
+lxml/serializer.pxi,sha256=iIXfechFHfvFs2sTk7wMIy3sDJxmaMPbNO33mkLLBUE,68063
+lxml/usedoctest.py,sha256=qRgZKQVcAZcl-zN0AIXVJnOsETUXz2nPXkxuzs1lGgk,230
+lxml/xinclude.pxi,sha256=7eBrI_OK47mmrHQ0ixbixRI8pKqQ1nwkMV-OmKUVlD4,2456
+lxml/xmlerror.pxi,sha256=MAQv92NXFoaMOzT8WeeM0L3YyksFoo48tpz3KZHTqcY,50234
+lxml/xmlid.pxi,sha256=5zf9oR6bsCtavGiOmilNyHqYwgG_bnrIabSd2SURtm0,6073
+lxml/xmlschema.pxi,sha256=mumNoHni5S3BQPtcmOHRd61KRaVWu4eOie2wQeB0e6E,8490
+lxml/xpath.pxi,sha256=aqW24V817dUxps4Gnc8h7Tm3QVlITKvxU5_9WgJUIFg,19132
+lxml/xslt.pxi,sha256=lLVwvlhMKL970rVqThP6Jnn79L3MK9UG0DGnXnNy7YI,36356
+lxml/xsltext.pxi,sha256=TImDiAPlAezC07P7RY1N9YChA7AuKFH-G53hXdel9yc,11088
diff --git a/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/REQUESTED b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/REQUESTED
new file mode 100644
index 0000000..e69de29
diff --git a/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/WHEEL b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/WHEEL
new file mode 100644
index 0000000..44f5206
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/WHEEL
@@ -0,0 +1,6 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: false
+Tag: cp39-cp39-macosx_10_9_universal2
+Generator: delocate 0.13.0
+
diff --git a/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/licenses/LICENSE.txt b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/licenses/LICENSE.txt
new file mode 100644
index 0000000..0bdf039
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/licenses/LICENSE.txt
@@ -0,0 +1,31 @@
+BSD 3-Clause License
+
+Copyright (c) 2004 Infrae. All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+ 1. Redistributions of source code must retain the above copyright
+ notice, this list of conditions and the following disclaimer.
+
+ 2. Redistributions in binary form must reproduce the above copyright
+ notice, this list of conditions and the following disclaimer in
+ the documentation and/or other materials provided with the
+ distribution.
+
+ 3. Neither the name of Infrae nor the names of its contributors may
+ be used to endorse or promote products derived from this software
+ without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INFRAE OR
+CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
diff --git a/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/licenses/LICENSES.txt b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/licenses/LICENSES.txt
new file mode 100644
index 0000000..9f97c18
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/licenses/LICENSES.txt
@@ -0,0 +1,29 @@
+lxml is copyright Infrae and distributed under the BSD license (see
+doc/licenses/BSD.txt), with the following exceptions:
+
+Some code, such a selftest.py, selftest2.py and
+src/lxml/_elementpath.py are derived from ElementTree and
+cElementTree. See doc/licenses/elementtree.txt for the license text.
+
+lxml.cssselect and lxml.html are copyright Ian Bicking and distributed
+under the BSD license (see doc/licenses/BSD.txt).
+
+test.py, the test-runner script, is GPL and copyright Shuttleworth
+Foundation. See doc/licenses/GPL.txt. It is believed the unchanged
+inclusion of test.py to run the unit test suite falls under the
+"aggregation" clause of the GPL and thus does not affect the license
+of the rest of the package.
+
+The isoschematron implementation uses several XSL and RelaxNG resources:
+ * The (XML syntax) RelaxNG schema for schematron, copyright International
+ Organization for Standardization (see
+ src/lxml/isoschematron/resources/rng/iso-schematron.rng for the license
+ text)
+ * The skeleton iso-schematron-xlt1 pure-xslt schematron implementation
+ xsl stylesheets, copyright Rick Jelliffe and Academia Sinica Computing
+ Center, Taiwan (see the xsl files here for the license text:
+ src/lxml/isoschematron/resources/xsl/iso-schematron-xslt1/)
+ * The xsd/rng schema schematron extraction xsl transformations are unlicensed
+ and copyright the respective authors as noted (see
+ src/lxml/isoschematron/resources/xsl/RNG2Schtrn.xsl and
+ src/lxml/isoschematron/resources/xsl/XSD2Schtrn.xsl)
diff --git a/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/top_level.txt b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/top_level.txt
new file mode 100644
index 0000000..ab90481
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/lxml-6.1.0.dist-info/top_level.txt
@@ -0,0 +1 @@
+lxml
diff --git a/.venv/Lib/python3.9/site-packages/lxml/ElementInclude.py b/.venv/Lib/python3.9/site-packages/lxml/ElementInclude.py
new file mode 100644
index 0000000..2188433
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/lxml/ElementInclude.py
@@ -0,0 +1,244 @@
+#
+# ElementTree
+# $Id: ElementInclude.py 1862 2004-06-18 07:31:02Z Fredrik $
+#
+# limited xinclude support for element trees
+#
+# history:
+# 2003-08-15 fl created
+# 2003-11-14 fl fixed default loader
+#
+# Copyright (c) 2003-2004 by Fredrik Lundh. All rights reserved.
+#
+# fredrik@pythonware.com
+# http://www.pythonware.com
+#
+# --------------------------------------------------------------------
+# The ElementTree toolkit is
+#
+# Copyright (c) 1999-2004 by Fredrik Lundh
+#
+# By obtaining, using, and/or copying this software and/or its
+# associated documentation, you agree that you have read, understood,
+# and will comply with the following terms and conditions:
+#
+# Permission to use, copy, modify, and distribute this software and
+# its associated documentation for any purpose and without fee is
+# hereby granted, provided that the above copyright notice appears in
+# all copies, and that both that copyright notice and this permission
+# notice appear in supporting documentation, and that the name of
+# Secret Labs AB or the author not be used in advertising or publicity
+# pertaining to distribution of the software without specific, written
+# prior permission.
+#
+# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
+# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
+# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
+# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
+# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
+# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
+# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
+# OF THIS SOFTWARE.
+# --------------------------------------------------------------------
+
+"""
+Limited XInclude support for the ElementTree package.
+
+While lxml.etree has full support for XInclude (see
+`etree.ElementTree.xinclude()`), this module provides a simpler, pure
+Python, ElementTree compatible implementation that supports a simple
+form of custom URL resolvers.
+"""
+
+from lxml import etree
+try:
+ from urlparse import urljoin
+ from urllib2 import urlopen
+except ImportError:
+ # Python 3
+ from urllib.parse import urljoin
+ from urllib.request import urlopen
+
+XINCLUDE = "{http://www.w3.org/2001/XInclude}"
+
+XINCLUDE_INCLUDE = XINCLUDE + "include"
+XINCLUDE_FALLBACK = XINCLUDE + "fallback"
+XINCLUDE_ITER_TAG = XINCLUDE + "*"
+
+# For security reasons, the inclusion depth is limited to this read-only value by default.
+DEFAULT_MAX_INCLUSION_DEPTH = 6
+
+
+##
+# Fatal include error.
+
+class FatalIncludeError(etree.LxmlSyntaxError):
+ pass
+
+
+class LimitedRecursiveIncludeError(FatalIncludeError):
+ pass
+
+
+##
+# ET compatible default loader.
+# This loader reads an included resource from disk.
+#
+# @param href Resource reference.
+# @param parse Parse mode. Either "xml" or "text".
+# @param encoding Optional text encoding.
+# @return The expanded resource. If the parse mode is "xml", this
+# is an ElementTree instance. If the parse mode is "text", this
+# is a Unicode string. If the loader fails, it can return None
+# or raise an IOError exception.
+# @throws IOError If the loader fails to load the resource.
+
+def default_loader(href, parse, encoding=None):
+ file = open(href, 'rb')
+ if parse == "xml":
+ data = etree.parse(file).getroot()
+ else:
+ data = file.read()
+ if not encoding:
+ encoding = 'utf-8'
+ data = data.decode(encoding)
+ file.close()
+ return data
+
+
+##
+# Default loader used by lxml.etree - handles custom resolvers properly
+#
+
+def _lxml_default_loader(href, parse, encoding=None, parser=None):
+ if parse == "xml":
+ data = etree.parse(href, parser).getroot()
+ else:
+ if "://" in href:
+ f = urlopen(href)
+ else:
+ f = open(href, 'rb')
+ data = f.read()
+ f.close()
+ if not encoding:
+ encoding = 'utf-8'
+ data = data.decode(encoding)
+ return data
+
+
+##
+# Wrapper for ET compatibility - drops the parser
+
+def _wrap_et_loader(loader):
+ def load(href, parse, encoding=None, parser=None):
+ return loader(href, parse, encoding)
+ return load
+
+
+##
+# Expand XInclude directives.
+#
+# @param elem Root element.
+# @param loader Optional resource loader. If omitted, it defaults
+# to {@link default_loader}. If given, it should be a callable
+# that implements the same interface as default_loader.
+# @param base_url The base URL of the original file, to resolve
+# relative include file references.
+# @param max_depth The maximum number of recursive inclusions.
+# Limited to reduce the risk of malicious content explosion.
+# Pass None to disable the limitation.
+# @throws LimitedRecursiveIncludeError If the {@link max_depth} was exceeded.
+# @throws FatalIncludeError If the function fails to include a given
+# resource, or if the tree contains malformed XInclude elements.
+# @throws IOError If the function fails to load a given resource.
+# @returns the node or its replacement if it was an XInclude node
+
+def include(elem, loader=None, base_url=None,
+ max_depth=DEFAULT_MAX_INCLUSION_DEPTH):
+ if max_depth is None:
+ max_depth = -1
+ elif max_depth < 0:
+ raise ValueError("expected non-negative depth or None for 'max_depth', got %r" % max_depth)
+
+ if base_url is None:
+ if hasattr(elem, 'getroot'):
+ tree = elem
+ elem = elem.getroot()
+ else:
+ tree = elem.getroottree()
+ if hasattr(tree, 'docinfo'):
+ base_url = tree.docinfo.URL
+ elif hasattr(elem, 'getroot'):
+ elem = elem.getroot()
+ _include(elem, loader, base_url, max_depth)
+
+
+def _include(elem, loader=None, base_url=None,
+ max_depth=DEFAULT_MAX_INCLUSION_DEPTH, _parent_hrefs=None):
+ if loader is not None:
+ load_include = _wrap_et_loader(loader)
+ else:
+ load_include = _lxml_default_loader
+
+ if _parent_hrefs is None:
+ _parent_hrefs = set()
+
+ parser = elem.getroottree().parser
+
+ include_elements = list(
+ elem.iter(XINCLUDE_ITER_TAG))
+
+ for e in include_elements:
+ if e.tag == XINCLUDE_INCLUDE:
+ # process xinclude directive
+ href = urljoin(base_url, e.get("href"))
+ parse = e.get("parse", "xml")
+ parent = e.getparent()
+ if parse == "xml":
+ if href in _parent_hrefs:
+ raise FatalIncludeError(
+ "recursive include of %r detected" % href
+ )
+ if max_depth == 0:
+ raise LimitedRecursiveIncludeError(
+ "maximum xinclude depth reached when including file %s" % href)
+ node = load_include(href, parse, parser=parser)
+ if node is None:
+ raise FatalIncludeError(
+ "cannot load %r as %r" % (href, parse)
+ )
+ node = _include(node, loader, href, max_depth - 1, {href} | _parent_hrefs)
+ if e.tail:
+ node.tail = (node.tail or "") + e.tail
+ if parent is None:
+ return node # replaced the root node!
+ parent.replace(e, node)
+ elif parse == "text":
+ text = load_include(href, parse, encoding=e.get("encoding"))
+ if text is None:
+ raise FatalIncludeError(
+ "cannot load %r as %r" % (href, parse)
+ )
+ predecessor = e.getprevious()
+ if predecessor is not None:
+ predecessor.tail = (predecessor.tail or "") + text
+ elif parent is None:
+ return text # replaced the root node!
+ else:
+ parent.text = (parent.text or "") + text + (e.tail or "")
+ parent.remove(e)
+ else:
+ raise FatalIncludeError(
+ "unknown parse type in xi:include tag (%r)" % parse
+ )
+ elif e.tag == XINCLUDE_FALLBACK:
+ parent = e.getparent()
+ if parent is not None and parent.tag != XINCLUDE_INCLUDE:
+ raise FatalIncludeError(
+ "xi:fallback tag must be child of xi:include (%r)" % e.tag
+ )
+ else:
+ raise FatalIncludeError(
+ "Invalid element found in XInclude namespace (%r)" % e.tag
+ )
+ return elem
diff --git a/.venv/Lib/python3.9/site-packages/lxml/__init__.py b/.venv/Lib/python3.9/site-packages/lxml/__init__.py
new file mode 100644
index 0000000..873696e
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/lxml/__init__.py
@@ -0,0 +1,22 @@
+# this is a package
+
+__version__ = "6.1.0"
+
+
+def get_include():
+ """
+ Returns a list of header include paths (for lxml itself, libxml2
+ and libxslt) needed to compile C code against lxml if it was built
+ with statically linked libraries.
+ """
+ import os
+ lxml_path = __path__[0]
+ include_path = os.path.join(lxml_path, 'includes')
+ includes = [include_path, lxml_path]
+
+ for name in os.listdir(include_path):
+ path = os.path.join(include_path, name)
+ if os.path.isdir(path):
+ includes.append(path)
+
+ return includes
diff --git a/.venv/Lib/python3.9/site-packages/lxml/_elementpath.cpython-39-darwin.so b/.venv/Lib/python3.9/site-packages/lxml/_elementpath.cpython-39-darwin.so
new file mode 100755
index 0000000..caafc34
Binary files /dev/null and b/.venv/Lib/python3.9/site-packages/lxml/_elementpath.cpython-39-darwin.so differ
diff --git a/.venv/Lib/python3.9/site-packages/lxml/_elementpath.py b/.venv/Lib/python3.9/site-packages/lxml/_elementpath.py
new file mode 100644
index 0000000..760a1e0
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/lxml/_elementpath.py
@@ -0,0 +1,343 @@
+# cython: language_level=3
+
+#
+# ElementTree
+# $Id: ElementPath.py 3375 2008-02-13 08:05:08Z fredrik $
+#
+# limited xpath support for element trees
+#
+# history:
+# 2003-05-23 fl created
+# 2003-05-28 fl added support for // etc
+# 2003-08-27 fl fixed parsing of periods in element names
+# 2007-09-10 fl new selection engine
+# 2007-09-12 fl fixed parent selector
+# 2007-09-13 fl added iterfind; changed findall to return a list
+# 2007-11-30 fl added namespaces support
+# 2009-10-30 fl added child element value filter
+#
+# Copyright (c) 2003-2009 by Fredrik Lundh. All rights reserved.
+#
+# fredrik@pythonware.com
+# http://www.pythonware.com
+#
+# --------------------------------------------------------------------
+# The ElementTree toolkit is
+#
+# Copyright (c) 1999-2009 by Fredrik Lundh
+#
+# By obtaining, using, and/or copying this software and/or its
+# associated documentation, you agree that you have read, understood,
+# and will comply with the following terms and conditions:
+#
+# Permission to use, copy, modify, and distribute this software and
+# its associated documentation for any purpose and without fee is
+# hereby granted, provided that the above copyright notice appears in
+# all copies, and that both that copyright notice and this permission
+# notice appear in supporting documentation, and that the name of
+# Secret Labs AB or the author not be used in advertising or publicity
+# pertaining to distribution of the software without specific, written
+# prior permission.
+#
+# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
+# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
+# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
+# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
+# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
+# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
+# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
+# OF THIS SOFTWARE.
+# --------------------------------------------------------------------
+
+##
+# Implementation module for XPath support. There's usually no reason
+# to import this module directly; the ElementTree does this for
+# you, if needed.
+##
+
+
+import re
+
+xpath_tokenizer_re = re.compile(
+ "("
+ "'[^']*'|\"[^\"]*\"|"
+ "::|"
+ "//?|"
+ r"\.\.|"
+ r"\(\)|"
+ r"[/.*:\[\]\(\)@=])|"
+ r"((?:\{[^}]+\})?[^/\[\]\(\)@=\s]+)|"
+ r"\s+"
+ )
+
+def xpath_tokenizer(pattern, namespaces=None, with_prefixes=True):
+ # ElementTree uses '', lxml used None originally.
+ default_namespace = (namespaces.get(None) or namespaces.get('')) if namespaces else None
+ parsing_attribute = False
+ for token in xpath_tokenizer_re.findall(pattern):
+ ttype, tag = token
+ if tag and tag[0] != "{":
+ if ":" in tag and with_prefixes:
+ prefix, uri = tag.split(":", 1)
+ try:
+ if not namespaces:
+ raise KeyError
+ yield ttype, "{%s}%s" % (namespaces[prefix], uri)
+ except KeyError:
+ raise SyntaxError("prefix %r not found in prefix map" % prefix)
+ elif tag.isdecimal():
+ yield token # index
+ elif default_namespace and not parsing_attribute:
+ yield ttype, "{%s}%s" % (default_namespace, tag)
+ else:
+ yield token
+ parsing_attribute = False
+ else:
+ yield token
+ parsing_attribute = ttype == '@'
+
+
+def prepare_child(next, token):
+ tag = token[1]
+ def select(result):
+ for elem in result:
+ yield from elem.iterchildren(tag)
+ return select
+
+def prepare_star(next, token):
+ def select(result):
+ for elem in result:
+ yield from elem.iterchildren('*')
+ return select
+
+def prepare_self(next, token):
+ def select(result):
+ return result
+ return select
+
+def prepare_descendant(next, token):
+ token = next()
+ if token[0] == "*":
+ tag = "*"
+ elif not token[0]:
+ tag = token[1]
+ else:
+ raise SyntaxError("invalid descendant")
+ def select(result):
+ for elem in result:
+ yield from elem.iterdescendants(tag)
+ return select
+
+def prepare_parent(next, token):
+ def select(result):
+ for elem in result:
+ parent = elem.getparent()
+ if parent is not None:
+ yield parent
+ return select
+
+def prepare_predicate(next, token):
+ # FIXME: replace with real parser!!! refs:
+ # http://effbot.org/zone/simple-iterator-parser.htm
+ # http://javascript.crockford.com/tdop/tdop.html
+ signature = ''
+ predicate = []
+ while 1:
+ token = next()
+ if token[0] == "]":
+ break
+ if token == ('', ''):
+ # ignore whitespace
+ continue
+ if token[0] and token[0][:1] in "'\"":
+ token = "'", token[0][1:-1]
+ signature += token[0] or "-"
+ predicate.append(token[1])
+
+ # use signature to determine predicate type
+ if signature == "@-":
+ # [@attribute] predicate
+ key = predicate[1]
+ def select(result):
+ for elem in result:
+ if elem.get(key) is not None:
+ yield elem
+ return select
+ if signature == "@-='":
+ # [@attribute='value']
+ key = predicate[1]
+ value = predicate[-1]
+ def select(result):
+ for elem in result:
+ if elem.get(key) == value:
+ yield elem
+ return select
+ if signature == "-" and not re.match(r"-?\d+$", predicate[0]):
+ # [tag]
+ tag = predicate[0]
+ def select(result):
+ for elem in result:
+ for _ in elem.iterchildren(tag):
+ yield elem
+ break
+ return select
+ if signature == ".='" or (signature == "-='" and not re.match(r"-?\d+$", predicate[0])):
+ # [.='value'] or [tag='value']
+ tag = predicate[0]
+ value = predicate[-1]
+ if tag:
+ def select(result):
+ for elem in result:
+ for e in elem.iterchildren(tag):
+ if "".join(e.itertext()) == value:
+ yield elem
+ break
+ else:
+ def select(result):
+ for elem in result:
+ if "".join(elem.itertext()) == value:
+ yield elem
+ return select
+ if signature == "-" or signature == "-()" or signature == "-()-":
+ # [index] or [last()] or [last()-index]
+ if signature == "-":
+ # [index]
+ index = int(predicate[0]) - 1
+ if index < 0:
+ if index == -1:
+ raise SyntaxError(
+ "indices in path predicates are 1-based, not 0-based")
+ else:
+ raise SyntaxError("path index >= 1 expected")
+ else:
+ if predicate[0] != "last":
+ raise SyntaxError("unsupported function")
+ if signature == "-()-":
+ try:
+ index = int(predicate[2]) - 1
+ except ValueError:
+ raise SyntaxError("unsupported expression")
+ else:
+ index = -1
+ def select(result):
+ for elem in result:
+ parent = elem.getparent()
+ if parent is None:
+ continue
+ try:
+ # FIXME: what if the selector is "*" ?
+ elems = list(parent.iterchildren(elem.tag))
+ if elems[index] is elem:
+ yield elem
+ except IndexError:
+ pass
+ return select
+ raise SyntaxError("invalid predicate")
+
+ops = {
+ "": prepare_child,
+ "*": prepare_star,
+ ".": prepare_self,
+ "..": prepare_parent,
+ "//": prepare_descendant,
+ "[": prepare_predicate,
+}
+
+
+# --------------------------------------------------------------------
+
+_cache = {}
+
+
+def _build_path_iterator(path, namespaces, with_prefixes=True):
+ """compile selector pattern"""
+ if path[-1:] == "/":
+ path += "*" # implicit all (FIXME: keep this?)
+
+ cache_key = (path,)
+ if namespaces:
+ # lxml originally used None for the default namespace but ElementTree uses the
+ # more convenient (all-strings-dict) empty string, so we support both here,
+ # preferring the more convenient '', as long as they aren't ambiguous.
+ if None in namespaces:
+ if '' in namespaces and namespaces[None] != namespaces['']:
+ raise ValueError("Ambiguous default namespace provided: %r versus %r" % (
+ namespaces[None], namespaces['']))
+ cache_key += (namespaces[None],) + tuple(sorted(
+ item for item in namespaces.items() if item[0] is not None))
+ else:
+ cache_key += tuple(sorted(namespaces.items()))
+
+ try:
+ return _cache[cache_key]
+ except KeyError:
+ pass
+ if len(_cache) > 100:
+ _cache.clear()
+
+ if path[:1] == "/":
+ raise SyntaxError("cannot use absolute path on element")
+ stream = iter(xpath_tokenizer(path, namespaces, with_prefixes=with_prefixes))
+ try:
+ _next = stream.next
+ except AttributeError:
+ # Python 3
+ _next = stream.__next__
+ try:
+ token = _next()
+ except StopIteration:
+ raise SyntaxError("empty path expression")
+ selector = []
+ while 1:
+ try:
+ selector.append(ops[token[0]](_next, token))
+ except StopIteration:
+ raise SyntaxError("invalid path")
+ try:
+ token = _next()
+ if token[0] == "/":
+ token = _next()
+ except StopIteration:
+ break
+ _cache[cache_key] = selector
+ return selector
+
+
+##
+# Iterate over the matching nodes
+
+def iterfind(elem, path, namespaces=None, with_prefixes=True):
+ selector = _build_path_iterator(path, namespaces, with_prefixes=with_prefixes)
+ result = iter((elem,))
+ for select in selector:
+ result = select(result)
+ return result
+
+
+##
+# Find first matching object.
+
+def find(elem, path, namespaces=None, with_prefixes=True):
+ it = iterfind(elem, path, namespaces, with_prefixes=with_prefixes)
+ try:
+ return next(it)
+ except StopIteration:
+ return None
+
+
+##
+# Find all matching objects.
+
+def findall(elem, path, namespaces=None, with_prefixes=True):
+ return list(iterfind(elem, path, namespaces))
+
+
+##
+# Find text for first matching object.
+
+def findtext(elem, path, default=None, namespaces=None, with_prefixes=True):
+ el = find(elem, path, namespaces, with_prefixes=with_prefixes)
+ if el is None:
+ return default
+ else:
+ return el.text or ''
diff --git a/.venv/Lib/python3.9/site-packages/lxml/apihelpers.pxi b/.venv/Lib/python3.9/site-packages/lxml/apihelpers.pxi
new file mode 100644
index 0000000..87a27d9
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/lxml/apihelpers.pxi
@@ -0,0 +1,1819 @@
+# Private/public helper functions for API functions
+
+from lxml.includes cimport uri
+
+
+cdef void displayNode(xmlNode* c_node, indent) noexcept:
+ # to help with debugging
+ cdef xmlNode* c_child
+ try:
+ print(indent * ' ', c_node)
+ c_child = c_node.children
+ while c_child is not NULL:
+ displayNode(c_child, indent + 1)
+ c_child = c_child.next
+ finally:
+ return # swallow any exceptions
+
+cdef inline bint _isHtmlDocument(_Element element) except -1:
+ cdef xmlNode* c_node = element._c_node
+ return (
+ c_node is not NULL and c_node.doc is not NULL and
+ c_node.doc.properties & tree.XML_DOC_HTML != 0
+ )
+
+cdef inline int _assertValidNode(_Element element) except -1:
+ assert element._c_node is not NULL, "invalid Element proxy at %s" % id(element)
+
+cdef inline int _assertValidDoc(_Document doc) except -1:
+ assert doc._c_doc is not NULL, "invalid Document proxy at %s" % id(doc)
+
+cdef _Document _documentOrRaise(object input):
+ """Call this to get the document of a _Document, _ElementTree or _Element
+ object, or to raise an exception if it can't be determined.
+
+ Should be used in all API functions for consistency.
+ """
+ cdef _Document doc
+ if isinstance(input, _ElementTree):
+ if (<_ElementTree>input)._context_node is not None:
+ doc = (<_ElementTree>input)._context_node._doc
+ else:
+ doc = None
+ elif isinstance(input, _Element):
+ doc = (<_Element>input)._doc
+ elif isinstance(input, _Document):
+ doc = <_Document>input
+ else:
+ raise TypeError, f"Invalid input object: {python._fqtypename(input).decode('utf8')}"
+ if doc is None:
+ raise ValueError, f"Input object has no document: {python._fqtypename(input).decode('utf8')}"
+ _assertValidDoc(doc)
+ return doc
+
+cdef _Element _rootNodeOrRaise(object input):
+ """Call this to get the root node of a _Document, _ElementTree or
+ _Element object, or to raise an exception if it can't be determined.
+
+ Should be used in all API functions for consistency.
+ """
+ cdef _Element node
+ if isinstance(input, _ElementTree):
+ node = (<_ElementTree>input)._context_node
+ elif isinstance(input, _Element):
+ node = <_Element>input
+ elif isinstance(input, _Document):
+ node = (<_Document>input).getroot()
+ else:
+ raise TypeError, f"Invalid input object: {python._fqtypename(input).decode('utf8')}"
+ if (node is None or not node._c_node or
+ node._c_node.type != tree.XML_ELEMENT_NODE):
+ raise ValueError, f"Input object is not an XML element: {python._fqtypename(input).decode('utf8')}"
+ _assertValidNode(node)
+ return node
+
+cdef bint _isAncestorOrSame(xmlNode* c_ancestor, xmlNode* c_node) noexcept:
+ while c_node:
+ if c_node is c_ancestor:
+ return True
+ c_node = c_node.parent
+ return False
+
+cdef _Element _makeElement(tag, xmlDoc* c_doc, _Document doc,
+ _BaseParser parser, text, tail, attrib, nsmap,
+ dict extra_attrs):
+ """Create a new element and initialize text content, namespaces and
+ attributes.
+
+ This helper function will reuse as much of the existing document as
+ possible:
+
+ If 'parser' is None, the parser will be inherited from 'doc' or the
+ default parser will be used.
+
+ If 'doc' is None, 'c_doc' is used to create a new _Document and the new
+ element is made its root node.
+
+ If 'c_doc' is also NULL, a new xmlDoc will be created.
+ """
+ cdef xmlNode* c_node
+ if doc is not None:
+ c_doc = doc._c_doc
+ ns_utf, name_utf = _getNsTag(tag)
+ if parser is not None and parser._for_html:
+ _htmlTagValidOrRaise(name_utf)
+ if c_doc is NULL:
+ c_doc = _newHTMLDoc()
+ else:
+ _tagValidOrRaise(name_utf)
+ if c_doc is NULL:
+ c_doc = _newXMLDoc()
+ c_node = _createElement(c_doc, name_utf)
+ if c_node is NULL:
+ if doc is None and c_doc is not NULL:
+ tree.xmlFreeDoc(c_doc)
+ raise MemoryError()
+ try:
+ if doc is None:
+ tree.xmlDocSetRootElement(c_doc, c_node)
+ doc = _documentFactory(c_doc, parser)
+ if text is not None:
+ _setNodeText(c_node, text)
+ if tail is not None:
+ _setTailText(c_node, tail)
+ # add namespaces to node if necessary
+ _setNodeNamespaces(c_node, doc, ns_utf, nsmap)
+ _initNodeAttributes(c_node, doc, attrib, extra_attrs)
+ return _elementFactory(doc, c_node)
+ except:
+ # free allocated c_node/c_doc unless Python does it for us
+ if c_node.doc is not c_doc:
+ # node not yet in document => will not be freed by document
+ if tail is not None:
+ _removeText(c_node.next) # tail
+ tree.xmlFreeNode(c_node)
+ if doc is None:
+ # c_doc will not be freed by doc
+ tree.xmlFreeDoc(c_doc)
+ raise
+
+cdef int _initNewElement(_Element element, bint is_html, name_utf, ns_utf,
+ _BaseParser parser, attrib, nsmap, dict extra_attrs) except -1:
+ """Initialise a new Element object.
+
+ This is used when users instantiate a Python Element subclass
+ directly, without it being mapped to an existing XML node.
+ """
+ cdef xmlDoc* c_doc
+ cdef xmlNode* c_node
+ cdef _Document doc
+ if is_html:
+ _htmlTagValidOrRaise(name_utf)
+ c_doc = _newHTMLDoc()
+ else:
+ _tagValidOrRaise(name_utf)
+ c_doc = _newXMLDoc()
+ c_node = _createElement(c_doc, name_utf)
+ if c_node is NULL:
+ if c_doc is not NULL:
+ tree.xmlFreeDoc(c_doc)
+ raise MemoryError()
+ tree.xmlDocSetRootElement(c_doc, c_node)
+ doc = _documentFactory(c_doc, parser)
+ # add namespaces to node if necessary
+ _setNodeNamespaces(c_node, doc, ns_utf, nsmap)
+ _initNodeAttributes(c_node, doc, attrib, extra_attrs)
+ _registerProxy(element, doc, c_node)
+ element._init()
+ return 0
+
+cdef _Element _makeSubElement(_Element parent, tag, text, tail,
+ attrib, nsmap, dict extra_attrs):
+ """Create a new child element and initialize text content, namespaces and
+ attributes.
+ """
+ cdef xmlNode* c_node
+ cdef xmlDoc* c_doc
+ if parent is None or parent._doc is None:
+ return None
+ _assertValidNode(parent)
+ ns_utf, name_utf = _getNsTag(tag)
+ c_doc = parent._doc._c_doc
+
+ if parent._doc._parser is not None and parent._doc._parser._for_html:
+ _htmlTagValidOrRaise(name_utf)
+ else:
+ _tagValidOrRaise(name_utf)
+
+ c_node = _createElement(c_doc, name_utf)
+ if c_node is NULL:
+ raise MemoryError()
+ tree.xmlAddChild(parent._c_node, c_node)
+
+ try:
+ if text is not None:
+ _setNodeText(c_node, text)
+ if tail is not None:
+ _setTailText(c_node, tail)
+
+ # add namespaces to node if necessary
+ _setNodeNamespaces(c_node, parent._doc, ns_utf, nsmap)
+ _initNodeAttributes(c_node, parent._doc, attrib, extra_attrs)
+ return _elementFactory(parent._doc, c_node)
+ except:
+ # make sure we clean up in case of an error
+ _removeNode(parent._doc, c_node)
+ raise
+
+
+cdef int _setNodeNamespaces(xmlNode* c_node, _Document doc,
+ object node_ns_utf, object nsmap) except -1:
+ """Lookup current namespace prefixes, then set namespace structure for
+ node (if 'node_ns_utf' was provided) and register new ns-prefix mappings.
+
+ 'node_ns_utf' should only be passed for a newly created node.
+ """
+ cdef xmlNs* c_ns
+ cdef list nsdefs
+
+ if nsmap:
+ for prefix, href in _iter_nsmap(nsmap):
+ href_utf = _utf8(href)
+ _uriValidOrRaise(href_utf)
+ c_href = _xcstr(href_utf)
+ if prefix is not None:
+ prefix_utf = _utf8(prefix)
+ _prefixValidOrRaise(prefix_utf)
+ c_prefix = _xcstr(prefix_utf)
+ else:
+ c_prefix = NULL
+ # add namespace with prefix if it is not already known
+ c_ns = tree.xmlSearchNs(doc._c_doc, c_node, c_prefix)
+ if c_ns is NULL or \
+ c_ns.href is NULL or \
+ tree.xmlStrcmp(c_ns.href, c_href) != 0:
+ c_ns = tree.xmlNewNs(c_node, c_href, c_prefix)
+ if c_ns is NULL:
+ # libxml2 has two error conditions: "out of memory" and "prefix exists already".
+ # We ignore the latter for compatibility reasons. It currently only appears
+ # during namespace cleanup.
+ c_ns = c_node.nsDef
+ while c_ns is not NULL:
+ if c_prefix is NULL:
+ if c_ns.prefix is NULL:
+ break
+ elif tree.xmlStrcmp(c_ns.prefix, c_prefix) == 0:
+ break
+ c_ns = c_ns.next
+ else:
+ raise MemoryError()
+ if href_utf == node_ns_utf:
+ tree.xmlSetNs(c_node, c_ns)
+ node_ns_utf = None
+
+ if node_ns_utf is not None:
+ _uriValidOrRaise(node_ns_utf)
+ doc._setNodeNs(c_node, _xcstr(node_ns_utf))
+ return 0
+
+
+cdef dict _build_nsmap(xmlNode* c_node):
+ """
+ Namespace prefix->URI mapping known in the context of this Element.
+ This includes all namespace declarations of the parents.
+ """
+ cdef xmlNs* c_ns
+ nsmap = {}
+ while c_node is not NULL and c_node.type == tree.XML_ELEMENT_NODE:
+ c_ns = c_node.nsDef
+ while c_ns is not NULL:
+ if c_ns.prefix or c_ns.href:
+ prefix = funicodeOrNone(c_ns.prefix)
+ if prefix not in nsmap:
+ nsmap[prefix] = funicodeOrNone(c_ns.href)
+ c_ns = c_ns.next
+ c_node = c_node.parent
+ return nsmap
+
+
+cdef _iter_nsmap(nsmap):
+ """
+ Create a reproducibly ordered iterable from an nsmap mapping.
+ Tries to preserve an existing order and sorts if it assumes no order.
+
+ The difference to _iter_attrib() is that None doesn't sort with strings
+ in Py3.x.
+ """
+ if isinstance(nsmap, dict):
+ # dicts are insertion-ordered in Py3.6+ => keep the user provided order.
+ return nsmap.items()
+ if len(nsmap) <= 1:
+ return nsmap.items()
+ if isinstance(nsmap, OrderedDict):
+ return nsmap.items() # keep existing order
+ if None not in nsmap:
+ return sorted(nsmap.items())
+
+ # Move the default namespace to the end. This makes sure libxml2
+ # prefers a prefix if the ns is defined redundantly on the same
+ # element. That way, users can work around a problem themselves
+ # where default namespace attributes on non-default namespaced
+ # elements serialise without prefix (i.e. into the non-default
+ # namespace).
+ default_ns = nsmap[None]
+ nsdefs = [(k, v) for k, v in nsmap.items() if k is not None]
+ nsdefs.sort()
+ nsdefs.append((None, default_ns))
+ return nsdefs
+
+
+cdef _iter_attrib(attrib):
+ """
+ Create a reproducibly ordered iterable from an attrib mapping.
+ Tries to preserve an existing order and sorts if it assumes no order.
+ """
+ # dicts are insertion-ordered in Py3.6+ => keep the user provided order.
+ if isinstance(attrib, (dict, _Attrib, OrderedDict)):
+ return attrib.items()
+ # assume it's an unordered mapping of some kind
+ return sorted(attrib.items())
+
+
+cdef _initNodeAttributes(xmlNode* c_node, _Document doc, attrib, dict extra):
+ """Initialise the attributes of an element node.
+ """
+ cdef bint is_html
+ cdef xmlNs* c_ns
+ if attrib is not None and not hasattr(attrib, 'items'):
+ raise TypeError, f"Invalid attribute dictionary: {python._fqtypename(attrib).decode('utf8')}"
+ if not attrib and not extra:
+ return # nothing to do
+ is_html = doc._parser._for_html
+ seen = set()
+ if extra:
+ for name, value in extra.items():
+ _addAttributeToNode(c_node, doc, is_html, name, value, seen)
+ if attrib:
+ for name, value in _iter_attrib(attrib):
+ _addAttributeToNode(c_node, doc, is_html, name, value, seen)
+
+
+cdef int _addAttributeToNode(xmlNode* c_node, _Document doc, bint is_html,
+ name, value, set seen_tags) except -1:
+ ns_utf, name_utf = tag = _getNsTag(name)
+ if tag in seen_tags:
+ return 0
+ seen_tags.add(tag)
+ if not is_html:
+ _attributeValidOrRaise(name_utf)
+ value_utf = _utf8(value)
+ if ns_utf is None:
+ new_attr = tree.xmlNewProp(c_node, _xcstr(name_utf), _xcstr(value_utf))
+ else:
+ _uriValidOrRaise(ns_utf)
+ c_ns = doc._findOrBuildNodeNs(c_node, _xcstr(ns_utf), NULL, 1)
+ new_attr = tree.xmlNewNsProp(c_node, c_ns, _xcstr(name_utf), _xcstr(value_utf))
+ if new_attr is NULL:
+ raise MemoryError()
+ return 0
+
+
+ctypedef struct _ns_node_ref:
+ xmlNs* ns
+ xmlNode* node
+
+
+cdef int _collectNsDefs(xmlNode* c_element, _ns_node_ref **_c_ns_list,
+ size_t *_c_ns_list_len, size_t *_c_ns_list_size) except -1:
+ c_ns_list = _c_ns_list[0]
+ cdef size_t c_ns_list_len = _c_ns_list_len[0]
+ cdef size_t c_ns_list_size = _c_ns_list_size[0]
+
+ c_nsdef = c_element.nsDef
+ while c_nsdef is not NULL:
+ if c_ns_list_len >= c_ns_list_size:
+ if c_ns_list is NULL:
+ c_ns_list_size = 20
+ else:
+ c_ns_list_size *= 2
+ c_nsref_ptr = <_ns_node_ref*> python.lxml_realloc(
+ c_ns_list, c_ns_list_size, sizeof(_ns_node_ref))
+ if c_nsref_ptr is NULL:
+ if c_ns_list is not NULL:
+ python.lxml_free(c_ns_list)
+ _c_ns_list[0] = NULL
+ raise MemoryError()
+ c_ns_list = c_nsref_ptr
+
+ c_ns_list[c_ns_list_len] = _ns_node_ref(c_nsdef, c_element)
+ c_ns_list_len += 1
+ c_nsdef = c_nsdef.next
+
+ _c_ns_list_size[0] = c_ns_list_size
+ _c_ns_list_len[0] = c_ns_list_len
+ _c_ns_list[0] = c_ns_list
+
+
+cdef int _removeUnusedNamespaceDeclarations(xmlNode* c_element, set prefixes_to_keep) except -1:
+ """Remove any namespace declarations from a subtree that are not used by
+ any of its elements (or attributes).
+
+ If a 'prefixes_to_keep' is provided, it must be a set of prefixes.
+ Any corresponding namespace mappings will not be removed as part of the cleanup.
+ """
+ cdef xmlNode* c_node
+ cdef _ns_node_ref* c_ns_list = NULL
+ cdef size_t c_ns_list_size = 0
+ cdef size_t c_ns_list_len = 0
+ cdef size_t i
+
+ if c_element.parent and c_element.parent.type == tree.XML_DOCUMENT_NODE:
+ # include declarations on the document node
+ _collectNsDefs(c_element.parent, &c_ns_list, &c_ns_list_len, &c_ns_list_size)
+
+ tree.BEGIN_FOR_EACH_ELEMENT_FROM(c_element, c_element, 1)
+ # collect all new namespace declarations into the ns list
+ if c_element.nsDef:
+ _collectNsDefs(c_element, &c_ns_list, &c_ns_list_len, &c_ns_list_size)
+
+ # remove all namespace declarations from the list that are referenced
+ if c_ns_list_len and c_element.type == tree.XML_ELEMENT_NODE:
+ c_node = c_element
+ while c_node and c_ns_list_len:
+ if c_node.ns:
+ for i in range(c_ns_list_len):
+ if c_node.ns is c_ns_list[i].ns:
+ c_ns_list_len -= 1
+ c_ns_list[i] = c_ns_list[c_ns_list_len]
+ #c_ns_list[c_ns_list_len] = _ns_node_ref(NULL, NULL)
+ break
+ if c_node is c_element:
+ # continue with attributes
+ c_node = c_element.properties
+ else:
+ c_node = c_node.next
+ tree.END_FOR_EACH_ELEMENT_FROM(c_element)
+
+ if c_ns_list is NULL:
+ return 0
+
+ # free all namespace declarations that remained in the list,
+ # except for those we should keep explicitly
+ cdef xmlNs* c_nsdef
+ for i in range(c_ns_list_len):
+ if prefixes_to_keep is not None:
+ if c_ns_list[i].ns.prefix and c_ns_list[i].ns.prefix in prefixes_to_keep:
+ continue
+ c_node = c_ns_list[i].node
+ c_nsdef = c_node.nsDef
+ if c_nsdef is c_ns_list[i].ns:
+ c_node.nsDef = c_node.nsDef.next
+ else:
+ while c_nsdef.next is not c_ns_list[i].ns:
+ c_nsdef = c_nsdef.next
+ c_nsdef.next = c_nsdef.next.next
+ tree.xmlFreeNs(c_ns_list[i].ns)
+
+ if c_ns_list is not NULL:
+ python.lxml_free(c_ns_list)
+ return 0
+
+cdef xmlNs* _searchNsByHref(xmlNode* c_node, const_xmlChar* c_href, bint is_attribute) noexcept:
+ """Search a namespace declaration that covers a node (element or
+ attribute).
+
+ For attributes, try to find a prefixed namespace declaration
+ instead of the default namespaces. This helps in supporting
+ round-trips for attributes on elements with a different namespace.
+ """
+ cdef xmlNs* c_ns
+ cdef xmlNs* c_default_ns = NULL
+ cdef xmlNode* c_element
+ if c_href is NULL or c_node is NULL or c_node.type == tree.XML_ENTITY_REF_NODE:
+ return NULL
+ if tree.xmlStrcmp(c_href, tree.XML_XML_NAMESPACE) == 0:
+ # no special cases here, let libxml2 handle this
+ return tree.xmlSearchNsByHref(c_node.doc, c_node, c_href)
+ if c_node.type == tree.XML_ATTRIBUTE_NODE:
+ is_attribute = 1
+ while c_node is not NULL and c_node.type != tree.XML_ELEMENT_NODE:
+ c_node = c_node.parent
+ c_element = c_node
+ while c_node is not NULL:
+ if c_node.type == tree.XML_ELEMENT_NODE:
+ c_ns = c_node.nsDef
+ while c_ns is not NULL:
+ if c_ns.href is not NULL and tree.xmlStrcmp(c_href, c_ns.href) == 0:
+ if c_ns.prefix is NULL and is_attribute:
+ # for attributes, continue searching a named
+ # prefix, but keep the first default namespace
+ # declaration that we found
+ if c_default_ns is NULL:
+ c_default_ns = c_ns
+ elif tree.xmlSearchNs(
+ c_element.doc, c_element, c_ns.prefix) is c_ns:
+ # start node is in namespace scope => found!
+ return c_ns
+ c_ns = c_ns.next
+ if c_node is not c_element and c_node.ns is not NULL:
+ # optimise: the node may have the namespace itself
+ c_ns = c_node.ns
+ if c_ns.href is not NULL and tree.xmlStrcmp(c_href, c_ns.href) == 0:
+ if c_ns.prefix is NULL and is_attribute:
+ # for attributes, continue searching a named
+ # prefix, but keep the first default namespace
+ # declaration that we found
+ if c_default_ns is NULL:
+ c_default_ns = c_ns
+ elif tree.xmlSearchNs(
+ c_element.doc, c_element, c_ns.prefix) is c_ns:
+ # start node is in namespace scope => found!
+ return c_ns
+ c_node = c_node.parent
+ # nothing found => use a matching default namespace or fail
+ if c_default_ns is not NULL:
+ if tree.xmlSearchNs(c_element.doc, c_element, NULL) is c_default_ns:
+ return c_default_ns
+ return NULL
+
+cdef int _replaceNodeByChildren(_Document doc, xmlNode* c_node) except -1:
+ # NOTE: this does not deallocate the node, just unlink it!
+ cdef xmlNode* c_parent
+ cdef xmlNode* c_child
+ if c_node.children is NULL:
+ tree.xmlUnlinkNode(c_node)
+ return 0
+
+ c_parent = c_node.parent
+ # fix parent links of children
+ c_child = c_node.children
+ while c_child is not NULL:
+ c_child.parent = c_parent
+ c_child = c_child.next
+
+ # fix namespace references of children if their parent's namespace
+ # declarations get lost
+ if c_node.nsDef is not NULL:
+ c_child = c_node.children
+ while c_child is not NULL:
+ moveNodeToDocument(doc, doc._c_doc, c_child)
+ c_child = c_child.next
+
+ # fix sibling links to/from child slice
+ if c_node.prev is NULL:
+ c_parent.children = c_node.children
+ else:
+ c_node.prev.next = c_node.children
+ c_node.children.prev = c_node.prev
+ if c_node.next is NULL:
+ c_parent.last = c_node.last
+ else:
+ c_node.next.prev = c_node.last
+ c_node.last.next = c_node.next
+
+ # unlink c_node
+ c_node.children = c_node.last = NULL
+ c_node.parent = c_node.next = c_node.prev = NULL
+ return 0
+
+cdef unicode _attributeValue(xmlNode* c_element, xmlAttr* c_attrib_node):
+ c_href = _getNs(c_attrib_node)
+ value = tree.xmlGetNsProp(c_element, c_attrib_node.name, c_href)
+ try:
+ result = funicode(value)
+ finally:
+ tree.xmlFree(value)
+ return result
+
+cdef unicode _attributeValueFromNsName(xmlNode* c_element,
+ const_xmlChar* c_href, const_xmlChar* c_name):
+ c_result = tree.xmlGetNsProp(c_element, c_name, c_href)
+ if c_result is NULL:
+ return None
+ try:
+ result = funicode(c_result)
+ finally:
+ tree.xmlFree(c_result)
+ return result
+
+cdef object _getNodeAttributeValue(xmlNode* c_node, key, default):
+ ns, tag = _getNsTag(key)
+ c_href = NULL if ns is None else _xcstr(ns)
+ c_result = tree.xmlGetNsProp(c_node, _xcstr(tag), c_href)
+ if c_result is NULL:
+ # XXX free namespace that is not in use..?
+ return default
+ try:
+ result = funicode(c_result)
+ finally:
+ tree.xmlFree(c_result)
+ return result
+
+cdef inline object _getAttributeValue(_Element element, key, default):
+ return _getNodeAttributeValue(element._c_node, key, default)
+
+cdef int _setAttributeValue(_Element element, key, value) except -1:
+ cdef const_xmlChar* c_value
+ cdef xmlNs* c_ns
+ ns, tag = _getNsTag(key)
+ is_html = element._doc._parser._for_html
+ if not is_html:
+ _attributeValidOrRaise(tag)
+ c_tag = _xcstr(tag)
+ if value is None and is_html:
+ c_value = NULL
+ else:
+ if isinstance(value, QName):
+ value = _resolveQNameText(element, value)
+ else:
+ value = _utf8(value)
+ c_value = _xcstr(value)
+ if ns is None:
+ c_ns = NULL
+ else:
+ c_ns = element._doc._findOrBuildNodeNs(element._c_node, _xcstr(ns), NULL, 1)
+ tree.xmlSetNsProp(element._c_node, c_ns, c_tag, c_value)
+ return 0
+
+cdef int _delAttribute(_Element element, key) except -1:
+ ns, tag = _getNsTag(key)
+ c_href = NULL if ns is None else _xcstr(ns)
+ if _delAttributeFromNsName(element._c_node, c_href, _xcstr(tag)):
+ raise KeyError, key
+ return 0
+
+cdef int _delAttributeFromNsName(xmlNode* c_node, const_xmlChar* c_href, const_xmlChar* c_name) noexcept:
+ c_attr = tree.xmlHasNsProp(c_node, c_name, c_href)
+ if c_attr is NULL:
+ # XXX free namespace that is not in use..?
+ return -1
+ tree.xmlRemoveProp(c_attr)
+ return 0
+
+cdef list _collectAttributes(xmlNode* c_node, int collecttype):
+ """Collect all attributes of a node in a list. Depending on collecttype,
+ it collects either the name (1), the value (2) or the name-value tuples.
+ """
+ cdef Py_ssize_t count
+ c_attr = c_node.properties
+ count = 0
+ while c_attr is not NULL:
+ if c_attr.type == tree.XML_ATTRIBUTE_NODE:
+ count += 1
+ c_attr = c_attr.next
+
+ if not count:
+ return []
+
+ attributes = [None] * count
+ c_attr = c_node.properties
+ count = 0
+ while c_attr is not NULL:
+ if c_attr.type == tree.XML_ATTRIBUTE_NODE:
+ if collecttype == 1:
+ item = _namespacedName(c_attr)
+ elif collecttype == 2:
+ item = _attributeValue(c_node, c_attr)
+ else:
+ item = (_namespacedName(c_attr),
+ _attributeValue(c_node, c_attr))
+ attributes[count] = item
+ count += 1
+ c_attr = c_attr.next
+ return attributes
+
+cdef object __RE_XML_ENCODING = re.compile(
+ r'^(<\?xml[^>]+)\s+encoding\s*=\s*["\'][^"\']*["\'](\s*\?>|)', re.U)
+
+cdef object __REPLACE_XML_ENCODING = __RE_XML_ENCODING.sub
+cdef object __HAS_XML_ENCODING = __RE_XML_ENCODING.match
+
+cdef object _stripEncodingDeclaration(object xml_string):
+ # this is a hack to remove the XML encoding declaration from unicode
+ return __REPLACE_XML_ENCODING(r'\g<1>\g<2>', xml_string)
+
+cdef bint _hasEncodingDeclaration(object xml_string) except -1:
+ # check if a (unicode) string has an XML encoding declaration
+ return __HAS_XML_ENCODING(xml_string) is not None
+
+cdef inline bint _hasText(xmlNode* c_node) noexcept:
+ return c_node is not NULL and _textNodeOrSkip(c_node.children) is not NULL
+
+cdef inline bint _hasTail(xmlNode* c_node) noexcept:
+ return c_node is not NULL and _textNodeOrSkip(c_node.next) is not NULL
+
+cdef inline bint _hasNonWhitespaceTail(xmlNode* c_node) except -1:
+ return _hasNonWhitespaceText(c_node, tail=True)
+
+cdef bint _hasNonWhitespaceText(xmlNode* c_node, bint tail=False) except -1:
+ c_text_node = c_node and _textNodeOrSkip(c_node.next if tail else c_node.children)
+ if c_text_node is NULL:
+ return False
+ while c_text_node is not NULL:
+ if c_text_node.content[0] != c'\0' and not _collectText(c_text_node).isspace():
+ return True
+ c_text_node = _textNodeOrSkip(c_text_node.next)
+ return False
+
+cdef unicode _collectText(xmlNode* c_node):
+ """Collect all text nodes and return them as a unicode string.
+
+ Start collecting at c_node.
+
+ If there was no text to collect, return None
+ """
+ cdef Py_ssize_t scount
+ cdef xmlChar* c_text
+ cdef xmlNode* c_node_cur
+ # check for multiple text nodes
+ scount = 0
+ c_text = NULL
+ c_node_cur = c_node = _textNodeOrSkip(c_node)
+ while c_node_cur is not NULL:
+ if c_node_cur.content[0] != c'\0':
+ c_text = c_node_cur.content
+ scount += 1
+ c_node_cur = _textNodeOrSkip(c_node_cur.next)
+
+ # handle two most common cases first
+ if c_text is NULL:
+ return '' if scount > 0 else None
+ if scount == 1:
+ return funicode(c_text)
+
+ # the rest is not performance critical anymore
+ result = b''
+ while c_node is not NULL:
+ result += c_node.content
+ c_node = _textNodeOrSkip(c_node.next)
+ return funicode(result)
+
+cdef void _removeText(xmlNode* c_node) noexcept:
+ """Remove all text nodes.
+
+ Start removing at c_node.
+ """
+ cdef xmlNode* c_next
+ c_node = _textNodeOrSkip(c_node)
+ while c_node is not NULL:
+ c_next = _textNodeOrSkip(c_node.next)
+ tree.xmlUnlinkNode(c_node)
+ tree.xmlFreeNode(c_node)
+ c_node = c_next
+
+cdef xmlNode* _createTextNode(xmlDoc* doc, value) except NULL:
+ cdef xmlNode* c_text_node
+ if isinstance(value, CDATA):
+ c_text_node = tree.xmlNewCDataBlock(
+ doc, _xcstr((value)._utf8_data),
+ python.PyBytes_GET_SIZE((value)._utf8_data))
+ else:
+ text = _utf8(value)
+ c_text_node = tree.xmlNewDocText(doc, _xcstr(text))
+ if not c_text_node:
+ raise MemoryError()
+ return c_text_node
+
+cdef int _setNodeText(xmlNode* c_node, value) except -1:
+ # remove all text nodes at the start first
+ _removeText(c_node.children)
+ if value is None:
+ return 0
+ # now add new text node with value at start
+ c_text_node = _createTextNode(c_node.doc, value)
+ if c_node.children is NULL:
+ tree.xmlAddChild(c_node, c_text_node)
+ else:
+ tree.xmlAddPrevSibling(c_node.children, c_text_node)
+ return 0
+
+cdef int _setTailText(xmlNode* c_node, value) except -1:
+ # remove all text nodes at the start first
+ _removeText(c_node.next)
+ if value is None:
+ return 0
+ # now append new text node with value
+ c_text_node = _createTextNode(c_node.doc, value)
+ tree.xmlAddNextSibling(c_node, c_text_node)
+ return 0
+
+cdef bytes _resolveQNameText(_Element element, value):
+ cdef xmlNs* c_ns
+ ns, tag = _getNsTag(value)
+ if ns is None:
+ return tag
+ else:
+ c_ns = element._doc._findOrBuildNodeNs(
+ element._c_node, _xcstr(ns), NULL, 0)
+ return python.PyBytes_FromFormat('%s:%s', c_ns.prefix, _cstr(tag))
+
+cdef inline bint _hasChild(xmlNode* c_node) noexcept:
+ return c_node is not NULL and _findChildForwards(c_node, 0) is not NULL
+
+cdef inline Py_ssize_t _countElements(xmlNode* c_node) noexcept:
+ "Counts the elements within the following siblings and the node itself."
+ cdef Py_ssize_t count
+ count = 0
+ while c_node is not NULL:
+ if _isElement(c_node):
+ count += 1
+ c_node = c_node.next
+ return count
+
+
+cdef int _findChildSlice(
+ slice sliceobject, xmlNode* c_parent,
+ xmlNode** c_start_node, Py_ssize_t* c_step, Py_ssize_t* c_length) except -1:
+ """Resolve a children slice.
+
+ Returns the start node, step size and the slice length in the
+ pointer arguments.
+ """
+ cdef Py_ssize_t start = 0, stop = 0, childcount
+ childcount = _countElements(c_parent.children)
+ if childcount == 0:
+ c_start_node[0] = NULL
+ c_length[0] = 0
+ if sliceobject.step is None:
+ c_step[0] = 1
+ else:
+ python._PyEval_SliceIndex(sliceobject.step, c_step)
+ return 0
+
+ python.PySlice_GetIndicesEx(
+ sliceobject, childcount, &start, &stop, c_step, c_length)
+
+ if start > childcount // 2:
+ c_start_node[0] = _findChildBackwards(c_parent, childcount - start - 1)
+ else:
+ c_start_node[0] = _findChild(c_parent, start)
+ return 0
+
+
+cdef bint _isFullSlice(slice sliceobject) except -1:
+ """Conservative guess if this slice is a full slice as in ``s[:]``.
+ """
+ cdef Py_ssize_t step = 0
+ if sliceobject is None:
+ return 0
+ if sliceobject.start is None and \
+ sliceobject.stop is None:
+ if sliceobject.step is None:
+ return 1
+ python._PyEval_SliceIndex(sliceobject.step, &step)
+ if step == 1:
+ return 1
+ return 0
+ return 0
+
+cdef _collectChildren(_Element element):
+ cdef xmlNode* c_node
+ cdef list result = []
+ c_node = element._c_node.children
+ if c_node is not NULL:
+ if not _isElement(c_node):
+ c_node = _nextElement(c_node)
+ while c_node is not NULL:
+ result.append(_elementFactory(element._doc, c_node))
+ c_node = _nextElement(c_node)
+ return result
+
+cdef inline xmlNode* _findChild(xmlNode* c_node, Py_ssize_t index) noexcept:
+ if index < 0:
+ return _findChildBackwards(c_node, -index - 1)
+ else:
+ return _findChildForwards(c_node, index)
+
+cdef inline xmlNode* _findChildForwards(xmlNode* c_node, Py_ssize_t index) noexcept:
+ """Return child element of c_node with index, or return NULL if not found.
+ """
+ cdef xmlNode* c_child
+ cdef Py_ssize_t c
+ c_child = c_node.children
+ c = 0
+ while c_child is not NULL:
+ if _isElement(c_child):
+ if c == index:
+ return c_child
+ c += 1
+ c_child = c_child.next
+ return NULL
+
+cdef inline xmlNode* _findChildBackwards(xmlNode* c_node, Py_ssize_t index) noexcept:
+ """Return child element of c_node with index, or return NULL if not found.
+ Search from the end.
+ """
+ cdef xmlNode* c_child
+ cdef Py_ssize_t c
+ c_child = c_node.last
+ c = 0
+ while c_child is not NULL:
+ if _isElement(c_child):
+ if c == index:
+ return c_child
+ c += 1
+ c_child = c_child.prev
+ return NULL
+
+cdef inline xmlNode* _textNodeOrSkip(xmlNode* c_node) noexcept nogil:
+ """Return the node if it's a text node. Skip over ignorable nodes in a
+ series of text nodes. Return NULL if a non-ignorable node is found.
+
+ This is used to skip over XInclude nodes when collecting adjacent text
+ nodes.
+ """
+ while c_node is not NULL:
+ if c_node.type == tree.XML_TEXT_NODE or \
+ c_node.type == tree.XML_CDATA_SECTION_NODE:
+ return c_node
+ elif c_node.type == tree.XML_XINCLUDE_START or \
+ c_node.type == tree.XML_XINCLUDE_END:
+ c_node = c_node.next
+ else:
+ return NULL
+ return NULL
+
+cdef inline xmlNode* _nextElement(xmlNode* c_node) noexcept:
+ """Given a node, find the next sibling that is an element.
+ """
+ if c_node is NULL:
+ return NULL
+ c_node = c_node.next
+ while c_node is not NULL:
+ if _isElement(c_node):
+ return c_node
+ c_node = c_node.next
+ return NULL
+
+cdef inline xmlNode* _previousElement(xmlNode* c_node) noexcept:
+ """Given a node, find the next sibling that is an element.
+ """
+ if c_node is NULL:
+ return NULL
+ c_node = c_node.prev
+ while c_node is not NULL:
+ if _isElement(c_node):
+ return c_node
+ c_node = c_node.prev
+ return NULL
+
+cdef inline xmlNode* _parentElement(xmlNode* c_node) noexcept:
+ "Given a node, find the parent element."
+ if c_node is NULL or not _isElement(c_node):
+ return NULL
+ c_node = c_node.parent
+ if c_node is NULL or not _isElement(c_node):
+ return NULL
+ return c_node
+
+cdef inline bint _tagMatches(xmlNode* c_node, const_xmlChar* c_href, const_xmlChar* c_name) noexcept:
+ """Tests if the node matches namespace URI and tag name.
+
+ A node matches if it matches both c_href and c_name.
+
+ A node matches c_href if any of the following is true:
+ * c_href is NULL
+ * its namespace is NULL and c_href is the empty string
+ * its namespace string equals the c_href string
+
+ A node matches c_name if any of the following is true:
+ * c_name is NULL
+ * its name string equals the c_name string
+ """
+ if c_node is NULL:
+ return 0
+ if c_node.type != tree.XML_ELEMENT_NODE:
+ # not an element, only succeed if we match everything
+ return c_name is NULL and c_href is NULL
+ if c_name is NULL:
+ if c_href is NULL:
+ # always match
+ return 1
+ else:
+ c_node_href = _getNs(c_node)
+ if c_node_href is NULL:
+ return c_href[0] == c'\0'
+ else:
+ return tree.xmlStrcmp(c_node_href, c_href) == 0
+ elif c_href is NULL:
+ if _getNs(c_node) is not NULL:
+ return 0
+ return c_node.name == c_name or tree.xmlStrcmp(c_node.name, c_name) == 0
+ elif c_node.name == c_name or tree.xmlStrcmp(c_node.name, c_name) == 0:
+ c_node_href = _getNs(c_node)
+ if c_node_href is NULL:
+ return c_href[0] == c'\0'
+ else:
+ return tree.xmlStrcmp(c_node_href, c_href) == 0
+ else:
+ return 0
+
+cdef inline bint _tagMatchesExactly(xmlNode* c_node, qname* c_qname) noexcept:
+ """Tests if the node matches namespace URI and tag name.
+
+ This differs from _tagMatches() in that it does not consider a
+ NULL value in qname.href a wildcard, and that it expects the c_name
+ to be taken from the doc dict, i.e. it only compares the names by
+ address.
+
+ A node matches if it matches both href and c_name of the qname.
+
+ A node matches c_href if any of the following is true:
+ * its namespace is NULL and c_href is the empty string
+ * its namespace string equals the c_href string
+
+ A node matches c_name if any of the following is true:
+ * c_name is NULL
+ * its name string points to the same address (!) as c_name
+ """
+ return _nsTagMatchesExactly(_getNs(c_node), c_node.name, c_qname)
+
+cdef inline bint _nsTagMatchesExactly(const_xmlChar* c_node_href,
+ const_xmlChar* c_node_name,
+ qname* c_qname) noexcept:
+ """Tests if name and namespace URI match those of c_qname.
+
+ This differs from _tagMatches() in that it does not consider a
+ NULL value in qname.href a wildcard, and that it expects the c_name
+ to be taken from the doc dict, i.e. it only compares the names by
+ address.
+
+ A node matches if it matches both href and c_name of the qname.
+
+ A node matches c_href if any of the following is true:
+ * its namespace is NULL and c_href is the empty string
+ * its namespace string equals the c_href string
+
+ A node matches c_name if any of the following is true:
+ * c_name is NULL
+ * its name string points to the same address (!) as c_name
+ """
+ cdef char* c_href
+ if c_qname.c_name is not NULL and c_qname.c_name is not c_node_name:
+ return 0
+ if c_qname.href is NULL:
+ return 1
+ c_href = python.__cstr(c_qname.href)
+ if c_href[0] == b'\0':
+ return c_node_href is NULL or c_node_href[0] == b'\0'
+ elif c_node_href is NULL:
+ return 0
+ else:
+ return tree.xmlStrcmp(c_href, c_node_href) == 0
+
+cdef Py_ssize_t _mapTagsToQnameMatchArray(xmlDoc* c_doc, list ns_tags,
+ qname* c_ns_tags, bint force_into_dict) except -1:
+ """Map a sequence of (name, namespace) pairs to a qname array for efficient
+ matching with _tagMatchesExactly() above.
+
+ Note that each qname struct in the array owns its href byte string object
+ if it is not NULL.
+ """
+ cdef Py_ssize_t count = 0, i, c_tag_len
+ cdef bytes ns, tag
+ cdef const_xmlChar* c_tag
+
+ for ns, tag in ns_tags:
+ if tag is None:
+ c_tag = NULL
+ else:
+ c_tag_len = len(tag)
+ if c_tag_len > limits.INT_MAX:
+ # too long, not in the dict => not in the document
+ continue
+ elif force_into_dict:
+ c_tag = tree.xmlDictLookup(c_doc.dict, _xcstr(tag), c_tag_len)
+ if c_tag is NULL:
+ # clean up before raising the error
+ for i in xrange(count):
+ cpython.ref.Py_XDECREF(c_ns_tags[i].href)
+ raise MemoryError()
+ else:
+ c_tag = tree.xmlDictExists(c_doc.dict, _xcstr(tag), c_tag_len)
+ if c_tag is NULL:
+ # not in the dict => not in the document
+ continue
+
+ c_ns_tags[count].c_name = c_tag
+ if ns is None:
+ c_ns_tags[count].href = NULL
+ else:
+ cpython.ref.Py_INCREF(ns) # keep an owned reference!
+ c_ns_tags[count].href = ns
+ count += 1
+ return count
+
+cdef int _removeNode(_Document doc, xmlNode* c_node) except -1:
+ """Unlink and free a node and subnodes if possible. Otherwise, make sure
+ it's self-contained.
+ """
+ cdef xmlNode* c_next
+ c_next = c_node.next
+ tree.xmlUnlinkNode(c_node)
+ _moveTail(c_next, c_node)
+ if not attemptDeallocation(c_node):
+ # make namespaces absolute
+ moveNodeToDocument(doc, c_node.doc, c_node)
+ return 0
+
+cdef int _removeSiblings(xmlNode* c_element, tree.xmlElementType node_type, bint with_tail) except -1:
+ cdef xmlNode* c_node
+ cdef xmlNode* c_next
+ c_node = c_element.next
+ while c_node is not NULL:
+ c_next = _nextElement(c_node)
+ if c_node.type == node_type:
+ if with_tail:
+ _removeText(c_node.next)
+ tree.xmlUnlinkNode(c_node)
+ attemptDeallocation(c_node)
+ c_node = c_next
+ c_node = c_element.prev
+ while c_node is not NULL:
+ c_next = _previousElement(c_node)
+ if c_node.type == node_type:
+ if with_tail:
+ _removeText(c_node.next)
+ tree.xmlUnlinkNode(c_node)
+ attemptDeallocation(c_node)
+ c_node = c_next
+ return 0
+
+cdef void _moveTail(xmlNode* c_tail, xmlNode* c_target) noexcept:
+ cdef xmlNode* c_next
+ # tail support: look for any text nodes trailing this node and
+ # move them too
+ c_tail = _textNodeOrSkip(c_tail)
+ while c_tail is not NULL:
+ c_next = _textNodeOrSkip(c_tail.next)
+ c_target = tree.xmlAddNextSibling(c_target, c_tail)
+ c_tail = c_next
+
+cdef int _copyTail(xmlNode* c_tail, xmlNode* c_target) except -1:
+ cdef xmlNode* c_new_tail
+ # tail copying support: look for any text nodes trailing this node and
+ # copy it to the target node
+ c_tail = _textNodeOrSkip(c_tail)
+ while c_tail is not NULL:
+ if c_target.doc is not c_tail.doc:
+ c_new_tail = tree.xmlDocCopyNode(c_tail, c_target.doc, 0)
+ else:
+ c_new_tail = tree.xmlCopyNode(c_tail, 0)
+ if c_new_tail is NULL:
+ raise MemoryError()
+ c_target = tree.xmlAddNextSibling(c_target, c_new_tail)
+ c_tail = _textNodeOrSkip(c_tail.next)
+ return 0
+
+cdef int _copyNonElementSiblings(xmlNode* c_node, xmlNode* c_target) except -1:
+ cdef xmlNode* c_copy
+ cdef xmlNode* c_sibling = c_node
+ while c_sibling.prev != NULL and \
+ (c_sibling.prev.type == tree.XML_PI_NODE or
+ c_sibling.prev.type == tree.XML_COMMENT_NODE or
+ c_sibling.prev.type == tree.XML_DTD_NODE):
+ c_sibling = c_sibling.prev
+ while c_sibling != c_node:
+ if c_sibling.type == tree.XML_DTD_NODE:
+ c_copy = _copyDtd(c_sibling)
+ if c_sibling == c_node.doc.intSubset:
+ c_target.doc.intSubset = c_copy
+ else: # c_sibling == c_node.doc.extSubset
+ c_target.doc.extSubset = c_copy
+ else:
+ c_copy = tree.xmlDocCopyNode(c_sibling, c_target.doc, 1)
+ if c_copy is NULL:
+ raise MemoryError()
+ tree.xmlAddPrevSibling(c_target, c_copy)
+ c_sibling = c_sibling.next
+ while c_sibling.next != NULL and \
+ (c_sibling.next.type == tree.XML_PI_NODE or
+ c_sibling.next.type == tree.XML_COMMENT_NODE):
+ c_sibling = c_sibling.next
+ c_copy = tree.xmlDocCopyNode(c_sibling, c_target.doc, 1)
+ if c_copy is NULL:
+ raise MemoryError()
+ tree.xmlAddNextSibling(c_target, c_copy)
+
+cdef int _deleteSlice(_Document doc, xmlNode* c_node,
+ Py_ssize_t count, Py_ssize_t step) except -1:
+ """Delete slice, ``count`` items starting with ``c_node`` with a step
+ width of ``step``.
+ """
+ cdef xmlNode* c_next
+ cdef Py_ssize_t c, i
+ cdef _node_to_node_function next_element
+ if c_node is NULL:
+ return 0
+ if step > 0:
+ next_element = _nextElement
+ else:
+ step = -step if step != python.PY_SSIZE_T_MIN else python.PY_SSIZE_T_MAX
+ next_element = _previousElement
+ # now start deleting nodes
+ c = 0
+ c_next = c_node
+ while c_node is not NULL and c < count:
+ for i in range(step):
+ c_next = next_element(c_next)
+ if c_next is NULL:
+ break
+ _removeNode(doc, c_node)
+ c += 1
+ c_node = c_next
+ return 0
+
+cdef int _replaceSlice(_Element parent, xmlNode* c_node,
+ Py_ssize_t slicelength, Py_ssize_t step,
+ bint left_to_right, elements) except -1:
+ """Replace the slice of ``count`` elements starting at ``c_node`` with
+ positive step width ``step`` by the Elements in ``elements``. The
+ direction is given by the boolean argument ``left_to_right``.
+
+ ``c_node`` may be NULL to indicate the end of the children list.
+ """
+ cdef xmlNode* c_orig_neighbour
+ cdef xmlNode* c_next
+ cdef xmlDoc* c_source_doc
+ cdef _Element element
+ cdef Py_ssize_t seqlength, i, c
+ cdef _node_to_node_function next_element
+ assert step > 0, step
+ if left_to_right:
+ next_element = _nextElement
+ else:
+ next_element = _previousElement
+
+ if not isinstance(elements, (list, tuple)):
+ elements = list(elements)
+
+ if step != 1 or not left_to_right:
+ # *replacing* children stepwise with list => check size!
+ seqlength = len(elements)
+ if seqlength != slicelength:
+ raise ValueError, f"attempt to assign sequence of size {seqlength} " \
+ f"to extended slice of size {slicelength}"
+
+ if c_node is NULL:
+ # no children yet => add all elements straight away
+ if left_to_right:
+ for element in elements:
+ assert element is not None, "Node must not be None"
+ _appendChild(parent, element)
+ else:
+ for element in elements:
+ assert element is not None, "Node must not be None"
+ _prependChild(parent, element)
+ return 0
+
+ # remove the elements first as some might be re-added
+ if left_to_right:
+ # L->R, remember left neighbour
+ c_orig_neighbour = _previousElement(c_node)
+ else:
+ # R->L, remember right neighbour
+ c_orig_neighbour = _nextElement(c_node)
+
+ # We remove the original slice elements one by one. Since we hold
+ # a Python reference to all elements that we will insert, it is
+ # safe to let _removeNode() try (and fail) to free them even if
+ # the element itself or one of its descendents will be reinserted.
+ c = 0
+ c_next = c_node
+ while c_node is not NULL and c < slicelength:
+ for i in range(step):
+ c_next = next_element(c_next)
+ if c_next is NULL:
+ break
+ _removeNode(parent._doc, c_node)
+ c += 1
+ c_node = c_next
+
+ # make sure each element is inserted only once
+ elements = iter(elements)
+
+ # find the first node right of the new insertion point
+ if left_to_right:
+ if c_orig_neighbour is not NULL:
+ c_node = next_element(c_orig_neighbour)
+ else:
+ # before the first element
+ c_node = _findChildForwards(parent._c_node, 0)
+ elif c_orig_neighbour is NULL:
+ # at the end, but reversed stepping
+ # append one element and go to the next insertion point
+ for element in elements:
+ assert element is not None, "Node must not be None"
+ _appendChild(parent, element)
+ c_node = element._c_node
+ if slicelength > 0:
+ slicelength -= 1
+ for i in range(1, step):
+ c_node = next_element(c_node)
+ if c_node is NULL:
+ break
+ break
+ else:
+ c_node = c_orig_neighbour
+
+ if left_to_right:
+ # adjust step size after removing slice as we are not stepping
+ # over the newly inserted elements
+ step -= 1
+
+ # now insert elements where we removed them
+ if c_node is not NULL:
+ for element in elements:
+ assert element is not None, "Node must not be None"
+ _assertValidNode(element)
+ # move element and tail over
+ c_source_doc = element._c_node.doc
+ c_next = element._c_node.next
+ tree.xmlAddPrevSibling(c_node, element._c_node)
+ _moveTail(c_next, element._c_node)
+
+ # integrate element into new document
+ moveNodeToDocument(parent._doc, c_source_doc, element._c_node)
+
+ # stop at the end of the slice
+ if slicelength > 0:
+ slicelength -= 1
+ for i in range(step):
+ c_node = next_element(c_node)
+ if c_node is NULL:
+ break
+ if c_node is NULL:
+ break
+ else:
+ # everything inserted
+ return 0
+
+ # append the remaining elements at the respective end
+ if left_to_right:
+ for element in elements:
+ assert element is not None, "Node must not be None"
+ _assertValidNode(element)
+ _appendChild(parent, element)
+ else:
+ for element in elements:
+ assert element is not None, "Node must not be None"
+ _assertValidNode(element)
+ _prependChild(parent, element)
+
+ return 0
+
+
+cdef int _linkChild(xmlNode* c_parent, xmlNode* c_node) except -1:
+ """Adaptation of 'xmlAddChild()' that deep-fix the document links iteratively.
+ """
+ assert _isElement(c_node)
+ c_node.parent = c_parent
+ if c_parent.children is NULL:
+ c_parent.children = c_parent.last = c_node
+ else:
+ c_node.prev = c_parent.last
+ c_parent.last.next = c_node
+ c_parent.last = c_node
+
+ _setTreeDoc(c_node, c_parent.doc)
+ return 0
+
+
+cdef int _appendChild(_Element parent, _Element child) except -1:
+ """Append a new child to a parent element.
+ """
+ c_node = child._c_node
+ c_source_doc = c_node.doc
+ # prevent cycles
+ if _isAncestorOrSame(c_node, parent._c_node):
+ raise ValueError("cannot append parent to itself")
+ # store possible text node
+ c_next = c_node.next
+ # move node itself
+ tree.xmlUnlinkNode(c_node)
+ # do not call xmlAddChild() here since it would deep-traverse the tree
+ _linkChild(parent._c_node, c_node)
+ _moveTail(c_next, c_node)
+ # uh oh, elements may be pointing to different doc when
+ # parent element has moved; change them too..
+ moveNodeToDocument(parent._doc, c_source_doc, c_node)
+ return 0
+
+cdef int _prependChild(_Element parent, _Element child) except -1:
+ """Prepend a new child to a parent element.
+ """
+ c_node = child._c_node
+ c_source_doc = c_node.doc
+ # prevent cycles
+ if _isAncestorOrSame(c_node, parent._c_node):
+ raise ValueError("cannot append parent to itself")
+ # store possible text node
+ c_next = c_node.next
+ # move node itself
+ c_child = _findChildForwards(parent._c_node, 0)
+ if c_child is NULL:
+ tree.xmlUnlinkNode(c_node)
+ # do not call xmlAddChild() here since it would deep-traverse the tree
+ _linkChild(parent._c_node, c_node)
+ else:
+ tree.xmlAddPrevSibling(c_child, c_node)
+ _moveTail(c_next, c_node)
+ # uh oh, elements may be pointing to different doc when
+ # parent element has moved; change them too..
+ moveNodeToDocument(parent._doc, c_source_doc, c_node)
+ return 0
+
+cdef int _appendSibling(_Element element, _Element sibling) except -1:
+ """Add a new sibling behind an element.
+ """
+ return _addSibling(element, sibling, as_next=True)
+
+cdef int _prependSibling(_Element element, _Element sibling) except -1:
+ """Add a new sibling before an element.
+ """
+ return _addSibling(element, sibling, as_next=False)
+
+cdef int _addSibling(_Element element, _Element sibling, bint as_next) except -1:
+ c_node = sibling._c_node
+ c_source_doc = c_node.doc
+ # prevent cycles
+ if _isAncestorOrSame(c_node, element._c_node):
+ if element._c_node is c_node:
+ return 0 # nothing to do
+ raise ValueError("cannot add ancestor as sibling, please break cycle first")
+ # store possible text node
+ c_next = c_node.next
+ # move node itself
+ if as_next:
+ # must insert after any tail text
+ c_next_node = _nextElement(element._c_node)
+ if c_next_node is NULL:
+ c_next_node = element._c_node
+ while c_next_node.next:
+ c_next_node = c_next_node.next
+ tree.xmlAddNextSibling(c_next_node, c_node)
+ else:
+ tree.xmlAddPrevSibling(c_next_node, c_node)
+ else:
+ tree.xmlAddPrevSibling(element._c_node, c_node)
+ _moveTail(c_next, c_node)
+ # uh oh, elements may be pointing to different doc when
+ # parent element has moved; change them too..
+ moveNodeToDocument(element._doc, c_source_doc, c_node)
+ return 0
+
+cdef inline bint isutf8(const_xmlChar* s) noexcept:
+ cdef xmlChar c = s[0]
+ while c != c'\0':
+ if c & 0x80:
+ return True
+ s += 1
+ c = s[0]
+ return False
+
+cdef bint isutf8l(const_xmlChar* s, size_t length) noexcept:
+ """
+ Search for non-ASCII characters in the string, knowing its length in advance.
+ """
+ cdef unsigned int i
+ cdef unsigned long non_ascii_mask
+ cdef const unsigned long *lptr = s
+
+ cdef const unsigned long *end = lptr + length // sizeof(unsigned long)
+ if length >= sizeof(non_ascii_mask):
+ # Build constant 0x80808080... mask (and let the C compiler fold it).
+ non_ascii_mask = 0
+ for i in range(sizeof(non_ascii_mask) // 2):
+ non_ascii_mask = (non_ascii_mask << 16) | 0x8080
+
+ # Advance to long-aligned character before we start reading longs.
+ while (s) % sizeof(unsigned long) and s < end:
+ if s[0] & 0x80:
+ return True
+ s += 1
+
+ # Read one long at a time
+ lptr = s
+ while lptr < end:
+ if lptr[0] & non_ascii_mask:
+ return True
+ lptr += 1
+ s = lptr
+
+ while s < (end + length % sizeof(unsigned long)):
+ if s[0] & 0x80:
+ return True
+ s += 1
+
+ return False
+
+cdef int _is_valid_xml_ascii(bytes pystring) except -1:
+ """Check if a string is XML ascii content."""
+ cdef signed char ch
+ # When ch is a *signed* char, non-ascii characters are negative integers
+ # and xmlIsChar_ch does not accept them.
+ for ch in pystring:
+ if not tree.xmlIsChar_ch(ch):
+ return 0
+ return 1
+
+cdef bint _is_valid_xml_utf8(bytes pystring) except -1:
+ """Check if a string is like valid UTF-8 XML content."""
+ cdef const_xmlChar* s = _xcstr(pystring)
+ cdef const_xmlChar* c_end = s + len(pystring)
+ cdef unsigned long next3 = 0
+ if s < c_end - 2:
+ next3 = (s[0] << 8) | (s[1])
+
+ while s < c_end - 2:
+ next3 = 0x00ffffff & ((next3 << 8) | s[2])
+ if s[0] & 0x80:
+ # 0xefbfbe and 0xefbfbf are utf-8 encodings of
+ # forbidden characters \ufffe and \uffff
+ if next3 == 0x00efbfbe or next3 == 0x00efbfbf:
+ return 0
+ # 0xeda080 and 0xedbfbf are utf-8 encodings of
+ # \ud800 and \udfff. Anything between them (inclusive)
+ # is forbidden, because they are surrogate blocks in utf-16.
+ if 0x00eda080 <= next3 <= 0x00edbfbf:
+ return 0
+ elif not tree.xmlIsChar_ch(s[0]):
+ return 0 # invalid ascii char
+ s += 1
+
+ while s < c_end:
+ if not s[0] & 0x80 and not tree.xmlIsChar_ch(s[0]):
+ return 0 # invalid ascii char
+ s += 1
+
+ return 1
+
+cdef inline unicode funicodeOrNone(const_xmlChar* s):
+ return funicode(s) if s is not NULL else None
+
+cdef inline unicode funicodeOrEmpty(const_xmlChar* s):
+ return funicode(s) if s is not NULL else ''
+
+cdef unicode funicode(const_xmlChar* s):
+ return s.decode('UTF-8')
+
+cdef bytes _utf8(object s):
+ """Test if a string is valid user input and encode it to UTF-8.
+ Reject all bytes/unicode input that contains non-XML characters.
+ Reject all bytes input that contains non-ASCII characters.
+ """
+ cdef int valid
+ cdef bytes utf8_string
+ if isinstance(s, unicode):
+ utf8_string = (s).encode('utf8')
+ valid = _is_valid_xml_utf8(utf8_string)
+ elif isinstance(s, (bytes, bytearray)):
+ utf8_string = s if type(s) is bytes else bytes(s)
+ valid = _is_valid_xml_ascii(utf8_string)
+ else:
+ raise TypeError("Argument must be bytes or unicode, got '%.200s'" % type(s).__name__)
+ if not valid:
+ raise ValueError(
+ "All strings must be XML compatible: Unicode or ASCII, no NULL bytes or control characters")
+ return utf8_string
+
+
+cdef bytes _utf8orNone(object s):
+ return _utf8(s) if s is not None else None
+
+
+cdef enum:
+ NO_FILE_PATH = 0
+ ABS_UNIX_FILE_PATH = 1
+ ABS_WIN_FILE_PATH = 2
+ REL_FILE_PATH = 3
+
+
+cdef bint _isFilePath(const_xmlChar* c_path) noexcept:
+ "simple heuristic to see if a path is a filename"
+ cdef xmlChar c
+ # test if it looks like an absolute Unix path or a Windows network path
+ if c_path[0] == c'/':
+ return ABS_UNIX_FILE_PATH
+
+ # test if it looks like an absolute Windows path or URL
+ if c'a' <= c_path[0] <= c'z' or c'A' <= c_path[0] <= c'Z':
+ c_path += 1
+ if c_path[0] == c':' and c_path[1] in b'\0\\':
+ return ABS_WIN_FILE_PATH # C: or C:\...
+
+ # test if it looks like a URL with scheme://
+ while c'a' <= c_path[0] <= c'z' or c'A' <= c_path[0] <= c'Z':
+ c_path += 1
+ if c_path[0] == c':' and c_path[1] == c'/' and c_path[2] == c'/':
+ return NO_FILE_PATH
+
+ # assume it's a relative path
+ return REL_FILE_PATH
+
+
+cdef object _getFSPathOrObject(object obj):
+ """
+ Get the __fspath__ attribute of an object if it exists.
+ Otherwise, the original object is returned.
+ """
+ if _isString(obj):
+ return obj
+ try:
+ return python.PyOS_FSPath(obj)
+ except TypeError:
+ return obj
+
+
+cdef object _encodeFilename(object filename):
+ """Make sure a filename is 8-bit encoded (or None).
+ """
+ if filename is None:
+ return None
+ elif isinstance(filename, bytes):
+ return filename
+ elif isinstance(filename, unicode):
+ filename8 = (filename).encode('utf8')
+ if _isFilePath(filename8):
+ try:
+ return python.PyUnicode_AsEncodedString(
+ filename, _C_FILENAME_ENCODING, NULL)
+ except UnicodeEncodeError:
+ pass
+ return filename8
+ else:
+ raise TypeError("Argument must be string or unicode.")
+
+cdef object _decodeFilename(const_xmlChar* c_path):
+ """Make the filename a unicode string if we are in Py3.
+ """
+ return _decodeFilenameWithLength(c_path, tree.xmlStrlen(c_path))
+
+cdef object _decodeFilenameWithLength(const_xmlChar* c_path, size_t c_len):
+ """Make the filename a unicode string if we are in Py3.
+ """
+ if _isFilePath(c_path):
+ try:
+ return python.PyUnicode_Decode(
+ c_path, c_len, _C_FILENAME_ENCODING, NULL)
+ except UnicodeDecodeError:
+ pass
+ try:
+ return (c_path)[:c_len].decode('UTF-8')
+ except UnicodeDecodeError:
+ # this is a stupid fallback, but it might still work...
+ return (c_path)[:c_len].decode('latin-1', 'replace')
+
+cdef object _encodeFilenameUTF8(object filename):
+ """Recode filename as UTF-8. Tries ASCII, local filesystem encoding and
+ UTF-8 as source encoding.
+ """
+ cdef char* c_filename
+ if filename is None:
+ return None
+ elif isinstance(filename, bytes):
+ if not isutf8l(filename, len(filename)):
+ # plain ASCII!
+ return filename
+ c_filename = _cstr(filename)
+ try:
+ # try to decode with default encoding
+ filename = python.PyUnicode_Decode(
+ c_filename, len(filename),
+ _C_FILENAME_ENCODING, NULL)
+ except UnicodeDecodeError as decode_exc:
+ try:
+ # try if it's proper UTF-8
+ (filename).decode('utf8')
+ return filename
+ except UnicodeDecodeError:
+ raise decode_exc # otherwise re-raise original exception
+ if isinstance(filename, unicode):
+ return (filename).encode('utf8')
+ else:
+ raise TypeError("Argument must be string or unicode.")
+
+cdef tuple _getNsTag(tag):
+ """Given a tag, find namespace URI and tag name.
+ Return None for NS uri if no namespace URI provided.
+ """
+ return __getNsTag(tag, 0)
+
+cdef tuple _getNsTagWithEmptyNs(tag):
+ """Given a tag, find namespace URI and tag name. Return None for NS uri
+ if no namespace URI provided, or the empty string if namespace
+ part is '{}'.
+ """
+ return __getNsTag(tag, 1)
+
+cdef tuple __getNsTag(tag, bint empty_ns):
+ cdef char* c_tag
+ cdef char* c_ns_end
+ cdef Py_ssize_t taglen
+ cdef Py_ssize_t nslen
+ cdef bytes ns = None
+ # _isString() is much faster than isinstance()
+ if not _isString(tag) and isinstance(tag, QName):
+ tag = (tag).text
+ tag = _utf8(tag)
+ c_tag = _cstr(tag)
+ if c_tag[0] == c'{':
+ c_tag += 1
+ c_ns_end = cstring_h.strchr(c_tag, c'}')
+ if c_ns_end is NULL:
+ raise ValueError, "Invalid tag name"
+ nslen = c_ns_end - c_tag
+ taglen = python.PyBytes_GET_SIZE(tag) - nslen - 2
+ if taglen == 0:
+ raise ValueError, "Empty tag name"
+ if nslen > 0:
+ ns = c_tag[:nslen]
+ elif empty_ns:
+ ns = b''
+ tag = c_ns_end[1:taglen+1]
+ elif python.PyBytes_GET_SIZE(tag) == 0:
+ raise ValueError, "Empty tag name"
+ return ns, tag
+
+cdef inline int _pyXmlNameIsValid(name_utf8):
+ return _xmlNameIsValid(_xcstr(name_utf8)) and b':' not in name_utf8
+
+cdef inline int _pyHtmlNameIsValid(name_utf8):
+ return _htmlNameIsValid(_xcstr(name_utf8))
+
+cdef inline int _xmlNameIsValid(const_xmlChar* c_name) noexcept:
+ return tree.xmlValidateNameValue(c_name)
+
+cdef int _htmlNameIsValid(const_xmlChar* c_name) noexcept:
+ if c_name is NULL or c_name[0] == c'\0':
+ return 0
+ while c_name[0] != c'\0':
+ if c_name[0] in b'&<>/"\'\t\n\x0B\x0C\r ':
+ return 0
+ c_name += 1
+ return 1
+
+cdef bint _characterReferenceIsValid(const_xmlChar* c_name) noexcept:
+ cdef bint is_hex
+ if c_name[0] == c'x':
+ c_name += 1
+ is_hex = 1
+ else:
+ is_hex = 0
+ if c_name[0] == c'\0':
+ return 0
+ while c_name[0] != c'\0':
+ if c_name[0] < c'0' or c_name[0] > c'9':
+ if not is_hex:
+ return 0
+ if not (c'a' <= c_name[0] <= c'f'):
+ if not (c'A' <= c_name[0] <= c'F'):
+ return 0
+ c_name += 1
+ return 1
+
+cdef int _tagValidOrRaise(tag_utf) except -1:
+ if not _pyXmlNameIsValid(tag_utf):
+ raise ValueError(f"Invalid tag name {(tag_utf).decode('utf8')!r}")
+ return 0
+
+cdef int _htmlTagValidOrRaise(tag_utf) except -1:
+ if not _pyHtmlNameIsValid(tag_utf):
+ raise ValueError(f"Invalid HTML tag name {(tag_utf).decode('utf8')!r}")
+ return 0
+
+cdef int _attributeValidOrRaise(name_utf) except -1:
+ if not _pyXmlNameIsValid(name_utf):
+ raise ValueError(f"Invalid attribute name {(name_utf).decode('utf8')!r}")
+ return 0
+
+cdef int _prefixValidOrRaise(tag_utf) except -1:
+ if not _pyXmlNameIsValid(tag_utf):
+ raise ValueError(f"Invalid namespace prefix {(tag_utf).decode('utf8')!r}")
+ return 0
+
+cdef int _uriValidOrRaise(uri_utf) except -1:
+ cdef uri.xmlURI* c_uri = uri.xmlParseURI(_cstr(uri_utf))
+ if c_uri is NULL:
+ raise ValueError(f"Invalid namespace URI {(uri_utf).decode('utf8')!r}")
+ uri.xmlFreeURI(c_uri)
+ return 0
+
+cdef inline unicode _namespacedName(xmlNode* c_node):
+ return _namespacedNameFromNsName(_getNs(c_node), c_node.name)
+
+
+cdef unicode _namespacedNameFromNsName(const_xmlChar* c_href, const_xmlChar* c_name):
+ name = funicode(c_name)
+ if c_href is NULL:
+ return name
+ href = funicode(c_href)
+ return f"{{{href}}}{name}"
+
+
+cdef _getFilenameForFile(source):
+ """Given a Python File or Gzip object, give filename back.
+
+ Returns None if not a file object.
+ """
+ # urllib2 provides a geturl() method
+ try:
+ return source.geturl()
+ except:
+ pass
+ # file instances have a name attribute
+ try:
+ filename = source.name
+ if _isString(filename):
+ return os_path_abspath(filename)
+ except:
+ pass
+ # gzip file instances have a filename attribute (before Py3k)
+ try:
+ filename = source.filename
+ if _isString(filename):
+ return os_path_abspath(filename)
+ except:
+ pass
+ # can't determine filename
+ return None
diff --git a/.venv/Lib/python3.9/site-packages/lxml/builder.cpython-39-darwin.so b/.venv/Lib/python3.9/site-packages/lxml/builder.cpython-39-darwin.so
new file mode 100755
index 0000000..7a7ccca
Binary files /dev/null and b/.venv/Lib/python3.9/site-packages/lxml/builder.cpython-39-darwin.so differ
diff --git a/.venv/Lib/python3.9/site-packages/lxml/builder.py b/.venv/Lib/python3.9/site-packages/lxml/builder.py
new file mode 100644
index 0000000..f5831fb
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/lxml/builder.py
@@ -0,0 +1,243 @@
+# cython: language_level=2
+
+#
+# Element generator factory by Fredrik Lundh.
+#
+# Source:
+# http://online.effbot.org/2006_11_01_archive.htm#et-builder
+# http://effbot.python-hosting.com/file/stuff/sandbox/elementlib/builder.py
+#
+# --------------------------------------------------------------------
+# The ElementTree toolkit is
+#
+# Copyright (c) 1999-2004 by Fredrik Lundh
+#
+# By obtaining, using, and/or copying this software and/or its
+# associated documentation, you agree that you have read, understood,
+# and will comply with the following terms and conditions:
+#
+# Permission to use, copy, modify, and distribute this software and
+# its associated documentation for any purpose and without fee is
+# hereby granted, provided that the above copyright notice appears in
+# all copies, and that both that copyright notice and this permission
+# notice appear in supporting documentation, and that the name of
+# Secret Labs AB or the author not be used in advertising or publicity
+# pertaining to distribution of the software without specific, written
+# prior permission.
+#
+# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
+# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
+# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
+# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
+# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
+# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
+# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
+# OF THIS SOFTWARE.
+# --------------------------------------------------------------------
+
+"""
+The ``E`` Element factory for generating XML documents.
+"""
+
+
+import lxml.etree as ET
+_QName = ET.QName
+
+from functools import partial
+
+try:
+ from types import GenericAlias as _GenericAlias
+except ImportError:
+ # Python 3.8 - we only need this as return value from "__class_getitem__"
+ def _GenericAlias(cls, item):
+ return f"{cls.__name__}[{item.__name__}]"
+
+try:
+ basestring
+except NameError:
+ basestring = str
+
+try:
+ unicode
+except NameError:
+ unicode = str
+
+
+class ElementMaker:
+ """Element generator factory.
+
+ Unlike the ordinary Element factory, the E factory allows you to pass in
+ more than just a tag and some optional attributes; you can also pass in
+ text and other elements. The text is added as either text or tail
+ attributes, and elements are inserted at the right spot. Some small
+ examples::
+
+ >>> from lxml import etree as ET
+ >>> from lxml.builder import E
+
+ >>> ET.tostring(E("tag"))
+ ''
+ >>> ET.tostring(E("tag", "text"))
+ 'text'
+ >>> ET.tostring(E("tag", "text", key="value"))
+ 'text'
+ >>> ET.tostring(E("tag", E("subtag", "text"), "tail"))
+ 'texttail'
+
+ For simple tags, the factory also allows you to write ``E.tag(...)`` instead
+ of ``E('tag', ...)``::
+
+ >>> ET.tostring(E.tag())
+ ''
+ >>> ET.tostring(E.tag("text"))
+ 'text'
+ >>> ET.tostring(E.tag(E.subtag("text"), "tail"))
+ 'texttail'
+
+ Here's a somewhat larger example; this shows how to generate HTML
+ documents, using a mix of prepared factory functions for inline elements,
+ nested ``E.tag`` calls, and embedded XHTML fragments::
+
+ # some common inline elements
+ A = E.a
+ I = E.i
+ B = E.b
+
+ def CLASS(v):
+ # helper function, 'class' is a reserved word
+ return {'class': v}
+
+ page = (
+ E.html(
+ E.head(
+ E.title("This is a sample document")
+ ),
+ E.body(
+ E.h1("Hello!", CLASS("title")),
+ E.p("This is a paragraph with ", B("bold"), " text in it!"),
+ E.p("This is another paragraph, with a ",
+ A("link", href="http://www.python.org"), "."),
+ E.p("Here are some reserved characters: ."),
+ ET.XML("
And finally, here is an embedded XHTML fragment.
"),
+ )
+ )
+ )
+
+ print ET.tostring(page)
+
+ Here's a prettyprinted version of the output from the above script::
+
+
+
+ This is a sample document
+
+
+
+
+
+
+ For namespace support, you can pass a namespace map (``nsmap``)
+ and/or a specific target ``namespace`` to the ElementMaker class::
+
+ >>> E = ElementMaker(namespace="http://my.ns/")
+ >>> print(ET.tostring( E.test ))
+
+
+ >>> E = ElementMaker(namespace="http://my.ns/", nsmap={'p':'http://my.ns/'})
+ >>> print(ET.tostring( E.test ))
+
+ """
+
+ def __init__(self, typemap=None,
+ namespace=None, nsmap=None, makeelement=None):
+ self._namespace = '{' + namespace + '}' if namespace is not None else None
+ self._nsmap = dict(nsmap) if nsmap else None
+
+ assert makeelement is None or callable(makeelement)
+ self._makeelement = makeelement if makeelement is not None else ET.Element
+
+ # initialize the default type map functions for this element factory
+ typemap = dict(typemap) if typemap else {}
+
+ def add_text(elem, item):
+ try:
+ last_child = elem[-1]
+ except IndexError:
+ elem.text = (elem.text or "") + item
+ else:
+ last_child.tail = (last_child.tail or "") + item
+
+ def add_cdata(elem, cdata):
+ if elem.text:
+ raise ValueError("Can't add a CDATA section. Element already has some text: %r" % elem.text)
+ elem.text = cdata
+
+ if str not in typemap:
+ typemap[str] = add_text
+ if unicode not in typemap:
+ typemap[unicode] = add_text
+ if ET.CDATA not in typemap:
+ typemap[ET.CDATA] = add_cdata
+
+ def add_dict(elem, item):
+ attrib = elem.attrib
+ for k, v in item.items():
+ if isinstance(v, basestring):
+ attrib[k] = v
+ else:
+ attrib[k] = typemap[type(v)](None, v)
+
+ if dict not in typemap:
+ typemap[dict] = add_dict
+
+ self._typemap = typemap
+
+ def __call__(self, tag, *children, **attrib):
+ typemap = self._typemap
+
+ # We'll usually get a 'str', and the compiled type check is very fast.
+ if not isinstance(tag, str) and isinstance(tag, _QName):
+ # A QName is explicitly qualified, do not look at self._namespace.
+ tag = tag.text
+ elif self._namespace is not None and tag[0] != '{':
+ tag = self._namespace + tag
+ elem = self._makeelement(tag, nsmap=self._nsmap)
+ if attrib:
+ typemap[dict](elem, attrib)
+
+ for item in children:
+ if callable(item):
+ item = item()
+ t = typemap.get(type(item))
+ if t is None:
+ if ET.iselement(item):
+ elem.append(item)
+ continue
+ for basetype in type(item).__mro__:
+ # See if the typemap knows of any of this type's bases.
+ t = typemap.get(basetype)
+ if t is not None:
+ break
+ else:
+ raise TypeError("bad argument type: %s(%r)" %
+ (type(item).__name__, item))
+ v = t(elem, item)
+ if v:
+ typemap.get(type(v))(elem, v)
+
+ return elem
+
+ def __getattr__(self, tag):
+ return partial(self, tag)
+
+ # Allow subscripting ElementMaker in type annotions (PEP 560)
+ def __class_getitem__(cls, item):
+ return _GenericAlias(cls, item)
+
+
+# create factory object
+E = ElementMaker()
diff --git a/.venv/Lib/python3.9/site-packages/lxml/classlookup.pxi b/.venv/Lib/python3.9/site-packages/lxml/classlookup.pxi
new file mode 100644
index 0000000..92d1d47
--- /dev/null
+++ b/.venv/Lib/python3.9/site-packages/lxml/classlookup.pxi
@@ -0,0 +1,580 @@
+# Configurable Element class lookup
+
+################################################################################
+# Custom Element classes
+
+cdef public class ElementBase(_Element) [ type LxmlElementBaseType,
+ object LxmlElementBase ]:
+ """ElementBase(*children, attrib=None, nsmap=None, **_extra)
+
+ The public Element class. All custom Element classes must inherit
+ from this one. To create an Element, use the `Element()` factory.
+
+ BIG FAT WARNING: Subclasses *must not* override __init__ or
+ __new__ as it is absolutely undefined when these objects will be
+ created or destroyed. All persistent state of Elements must be
+ stored in the underlying XML. If you really need to initialize
+ the object after creation, you can implement an ``_init(self)``
+ method that will be called directly after object creation.
+
+ Subclasses of this class can be instantiated to create a new
+ Element. By default, the tag name will be the class name and the
+ namespace will be empty. You can modify this with the following
+ class attributes:
+
+ * TAG - the tag name, possibly containing a namespace in Clark
+ notation
+
+ * NAMESPACE - the default namespace URI, unless provided as part
+ of the TAG attribute.
+
+ * HTML - flag if the class is an HTML tag, as opposed to an XML
+ tag. This only applies to un-namespaced tags and defaults to
+ false (i.e. XML).
+
+ * PARSER - the parser that provides the configuration for the
+ newly created document. Providing an HTML parser here will
+ default to creating an HTML element.
+
+ In user code, the latter three are commonly inherited in class
+ hierarchies that implement a common namespace.
+ """
+ def __init__(self, *children, attrib=None, nsmap=None, **_extra):
+ """ElementBase(*children, attrib=None, nsmap=None, **_extra)
+ """
+ cdef bint is_html = 0
+ cdef _BaseParser parser
+ cdef _Element last_child
+ # don't use normal attribute access as it might be overridden
+ _getattr = object.__getattribute__
+ try:
+ namespace = _utf8(_getattr(self, 'NAMESPACE'))
+ except AttributeError:
+ namespace = None
+ try:
+ ns, tag = _getNsTag(_getattr(self, 'TAG'))
+ if ns is not None:
+ namespace = ns
+ except AttributeError:
+ tag = _utf8(_getattr(_getattr(self, '__class__'), '__name__'))
+ if b'.' in tag:
+ tag = tag.split(b'.')[-1]
+ try:
+ parser = _getattr(self, 'PARSER')
+ except AttributeError:
+ parser = None
+ for child in children:
+ if isinstance(child, _Element):
+ parser = (<_Element>child)._doc._parser
+ break
+ if isinstance(parser, HTMLParser):
+ is_html = 1
+ if namespace is None:
+ try:
+ is_html = _getattr(self, 'HTML')
+ except AttributeError:
+ pass
+ _initNewElement(self, is_html, tag, namespace, parser,
+ attrib, nsmap, _extra)
+ last_child = None
+ for child in children:
+ if _isString(child):
+ if last_child is None:
+ _setNodeText(self._c_node,
+ (_collectText(self._c_node.children) or '') + child)
+ else:
+ _setTailText(last_child._c_node,
+ (_collectText(last_child._c_node.next) or '') + child)
+ elif isinstance(child, _Element):
+ last_child = child
+ _appendChild(self, last_child)
+ elif isinstance(child, type) and issubclass(child, ElementBase):
+ last_child = child()
+ _appendChild(self, last_child)
+ else:
+ raise TypeError, f"Invalid child type: {type(child)!r}"
+
+cdef class CommentBase(_Comment):
+ """All custom Comment classes must inherit from this one.
+
+ To create an XML Comment instance, use the ``Comment()`` factory.
+
+ Subclasses *must not* override __init__ or __new__ as it is
+ absolutely undefined when these objects will be created or
+ destroyed. All persistent state of Comments must be stored in the
+ underlying XML. If you really need to initialize the object after
+ creation, you can implement an ``_init(self)`` method that will be
+ called after object creation.
+ """
+ def __init__(self, text):
+ # copied from Comment() factory
+ cdef _Document doc
+ cdef xmlDoc* c_doc
+ if text is None:
+ text = b''
+ else:
+ text = _utf8(text)
+ c_doc = _newXMLDoc()
+ doc = _documentFactory(c_doc, None)
+ self._c_node = _createComment(c_doc, _xcstr(text))
+ if self._c_node is NULL:
+ raise MemoryError()
+ tree.xmlAddChild(c_doc, self._c_node)
+ _registerProxy(self, doc, self._c_node)
+ self._init()
+
+cdef class PIBase(_ProcessingInstruction):
+ """All custom Processing Instruction classes must inherit from this one.
+
+ To create an XML ProcessingInstruction instance, use the ``PI()``
+ factory.
+
+ Subclasses *must not* override __init__ or __new__ as it is
+ absolutely undefined when these objects will be created or
+ destroyed. All persistent state of PIs must be stored in the
+ underlying XML. If you really need to initialize the object after
+ creation, you can implement an ``_init(self)`` method that will be
+ called after object creation.
+ """
+ def __init__(self, target, text=None):
+ # copied from PI() factory
+ cdef _Document doc
+ cdef xmlDoc* c_doc
+ target = _utf8(target)
+ if text is None:
+ text = b''
+ else:
+ text = _utf8(text)
+ c_doc = _newXMLDoc()
+ doc = _documentFactory(c_doc, None)
+ self._c_node = _createPI(c_doc, _xcstr(target), _xcstr(text))
+ if self._c_node is NULL:
+ raise MemoryError()
+ tree.xmlAddChild(c_doc, self._c_node)
+ _registerProxy(self, doc, self._c_node)
+ self._init()
+
+cdef class EntityBase(_Entity):
+ """All custom Entity classes must inherit from this one.
+
+ To create an XML Entity instance, use the ``Entity()`` factory.
+
+ Subclasses *must not* override __init__ or __new__ as it is
+ absolutely undefined when these objects will be created or
+ destroyed. All persistent state of Entities must be stored in the
+ underlying XML. If you really need to initialize the object after
+ creation, you can implement an ``_init(self)`` method that will be
+ called after object creation.
+ """
+ def __init__(self, name):
+ cdef _Document doc
+ cdef xmlDoc* c_doc
+ name_utf = _utf8(name)
+ c_name = _xcstr(name_utf)
+ if c_name[0] == c'#':
+ if not _characterReferenceIsValid(c_name + 1):
+ raise ValueError, f"Invalid character reference: '{name}'"
+ elif not _xmlNameIsValid(c_name):
+ raise ValueError, f"Invalid entity reference: '{name}'"
+ c_doc = _newXMLDoc()
+ doc = _documentFactory(c_doc, None)
+ self._c_node = _createEntity(c_doc, c_name)
+ if self._c_node is NULL:
+ raise MemoryError()
+ tree.xmlAddChild(c_doc, self._c_node)
+ _registerProxy(self, doc, self._c_node)
+ self._init()
+
+
+cdef int _validateNodeClass(xmlNode* c_node, cls) except -1:
+ if c_node.type == tree.XML_ELEMENT_NODE:
+ expected = ElementBase
+ elif c_node.type == tree.XML_COMMENT_NODE:
+ expected = CommentBase
+ elif c_node.type == tree.XML_ENTITY_REF_NODE:
+ expected = EntityBase
+ elif c_node.type == tree.XML_PI_NODE:
+ expected = PIBase
+ else:
+ assert False, f"Unknown node type: {c_node.type}"
+
+ if not (isinstance(cls, type) and issubclass(cls, expected)):
+ raise TypeError(
+ f"result of class lookup must be subclass of {type(expected)}, got {type(cls)}")
+ return 0
+
+
+################################################################################
+# Element class lookup
+
+ctypedef public object (*_element_class_lookup_function)(object, _Document, xmlNode*)
+
+# class to store element class lookup functions
+cdef public class ElementClassLookup [ type LxmlElementClassLookupType,
+ object LxmlElementClassLookup ]:
+ """ElementClassLookup(self)
+ Superclass of Element class lookups.
+ """
+ cdef _element_class_lookup_function _lookup_function
+
+
+cdef public class FallbackElementClassLookup(ElementClassLookup) \
+ [ type LxmlFallbackElementClassLookupType,
+ object LxmlFallbackElementClassLookup ]:
+ """FallbackElementClassLookup(self, fallback=None)
+
+ Superclass of Element class lookups with additional fallback.
+ """
+ cdef readonly ElementClassLookup fallback
+ cdef _element_class_lookup_function _fallback_function
+ def __cinit__(self):
+ # fall back to default lookup
+ self._fallback_function = _lookupDefaultElementClass
+
+ def __init__(self, ElementClassLookup fallback=None):
+ if fallback is not None:
+ self._setFallback(fallback)
+ else:
+ self._fallback_function = _lookupDefaultElementClass
+
+ cdef void _setFallback(self, ElementClassLookup lookup):
+ """Sets the fallback scheme for this lookup method.
+ """
+ self.fallback = lookup
+ self._fallback_function = lookup._lookup_function
+ if self._fallback_function is NULL:
+ self._fallback_function = _lookupDefaultElementClass
+
+ def set_fallback(self, ElementClassLookup lookup not None):
+ """set_fallback(self, lookup)
+
+ Sets the fallback scheme for this lookup method.
+ """
+ self._setFallback(lookup)
+
+cdef inline object _callLookupFallback(FallbackElementClassLookup lookup,
+ _Document doc, xmlNode* c_node):
+ return lookup._fallback_function(lookup.fallback, doc, c_node)
+
+
+################################################################################
+# default lookup scheme
+
+cdef class ElementDefaultClassLookup(ElementClassLookup):
+ """ElementDefaultClassLookup(self, element=None, comment=None, pi=None, entity=None)
+ Element class lookup scheme that always returns the default Element
+ class.
+
+ The keyword arguments ``element``, ``comment``, ``pi`` and ``entity``
+ accept the respective Element classes.
+ """
+ cdef readonly object element_class
+ cdef readonly object comment_class
+ cdef readonly object pi_class
+ cdef readonly object entity_class
+ def __cinit__(self):
+ self._lookup_function = _lookupDefaultElementClass
+
+ def __init__(self, element=None, comment=None, pi=None, entity=None):
+ if element is None:
+ self.element_class = _Element
+ elif issubclass(element, ElementBase):
+ self.element_class = element
+ else:
+ raise TypeError, "element class must be subclass of ElementBase"
+
+ if comment is None:
+ self.comment_class = _Comment
+ elif issubclass(comment, CommentBase):
+ self.comment_class = comment
+ else:
+ raise TypeError, "comment class must be subclass of CommentBase"
+
+ if entity is None:
+ self.entity_class = _Entity
+ elif issubclass(entity, EntityBase):
+ self.entity_class = entity
+ else:
+ raise TypeError, "Entity class must be subclass of EntityBase"
+
+ if pi is None:
+ self.pi_class = None # special case, see below
+ elif issubclass(pi, PIBase):
+ self.pi_class = pi
+ else:
+ raise TypeError, "PI class must be subclass of PIBase"
+
+cdef object _lookupDefaultElementClass(state, _Document _doc, xmlNode* c_node):
+ "Trivial class lookup function that always returns the default class."
+ if c_node.type == tree.XML_ELEMENT_NODE:
+ if state is not None:
+ return (state).element_class
+ else:
+ return _Element
+ elif c_node.type == tree.XML_COMMENT_NODE:
+ if state is not None:
+ return (state).comment_class
+ else:
+ return _Comment
+ elif c_node.type == tree.XML_ENTITY_REF_NODE:
+ if state is not None:
+ return (state).entity_class
+ else:
+ return _Entity
+ elif c_node.type == tree.XML_PI_NODE:
+ if state is None or (state).pi_class is None:
+ # special case XSLT-PI
+ if c_node.name is not NULL and c_node.content is not NULL:
+ if tree.xmlStrcmp(c_node.name, "xml-stylesheet") == 0:
+ if tree.xmlStrstr(c_node.content, "text/xsl") is not NULL or \
+ tree.xmlStrstr(c_node.content, "text/xml") is not NULL:
+ return _XSLTProcessingInstruction
+ return _ProcessingInstruction
+ else:
+ return (state).pi_class
+ else:
+ assert False, f"Unknown node type: {c_node.type}"
+
+
+################################################################################
+# attribute based lookup scheme
+
+cdef class AttributeBasedElementClassLookup(FallbackElementClassLookup):
+ """AttributeBasedElementClassLookup(self, attribute_name, class_mapping, fallback=None)
+ Checks an attribute of an Element and looks up the value in a
+ class dictionary.
+
+ Arguments:
+ - attribute name - '{ns}name' style string
+ - class mapping - Python dict mapping attribute values to Element classes
+ - fallback - optional fallback lookup mechanism
+
+ A None key in the class mapping will be checked if the attribute is
+ missing.
+ """
+ cdef object _class_mapping
+ cdef tuple _pytag
+ cdef const_xmlChar* _c_ns
+ cdef const_xmlChar* _c_name
+ def __cinit__(self):
+ self._lookup_function = _attribute_class_lookup
+
+ def __init__(self, attribute_name, class_mapping,
+ ElementClassLookup fallback=None):
+ self._pytag = _getNsTag(attribute_name)
+ ns, name = self._pytag
+ if ns is None:
+ self._c_ns = NULL
+ else:
+ self._c_ns = _xcstr(ns)
+ self._c_name = _xcstr(name)
+ self._class_mapping = dict(class_mapping)
+
+ FallbackElementClassLookup.__init__(self, fallback)
+
+cdef object _attribute_class_lookup(state, _Document doc, xmlNode* c_node):
+ cdef AttributeBasedElementClassLookup lookup
+ cdef python.PyObject* dict_result
+
+ lookup = state
+ if c_node.type == tree.XML_ELEMENT_NODE:
+ value = _attributeValueFromNsName(
+ c_node, lookup._c_ns, lookup._c_name)
+ dict_result = python.PyDict_GetItem(lookup._class_mapping, value)
+ if dict_result is not NULL:
+ cls =