Differential D353 Diff 1133 swh/deposit/parsers.py

Changeset View

Standalone View

swh/deposit/parsers.py

	# Copyright (C) 2017-2018 The Software Heritage developers			# Copyright (C) 2017-2018 The Software Heritage developers
	# See the AUTHORS file at the top-level directory of this distribution			# See the AUTHORS file at the top-level directory of this distribution
	# License: GNU General Public License version 3, or any later version			# License: GNU General Public License version 3, or any later version
	# See top-level LICENSE file for more information			# See top-level LICENSE file for more information


	"""Module in charge of defining parsers with SWORD 2.0 supported mediatypes.			"""Module in charge of defining parsers with SWORD 2.0 supported mediatypes.

	"""			"""

				from collections import defaultdict
	from decimal import Decimal			from decimal import Decimal
	from rest_framework.parsers import FileUploadParser			from rest_framework.parsers import FileUploadParser
	from rest_framework.parsers import MultiPartParser			from rest_framework.parsers import MultiPartParser
	from rest_framework_xml.parsers import XMLParser			from rest_framework_xml.parsers import XMLParser


	class SWHFileUploadZipParser(FileUploadParser):			class SWHFileUploadZipParser(FileUploadParser):
	"""File upload parser limited to zip archive.			"""File upload parser limited to zip archive.

	"""			"""
	media_type = 'application/zip'			media_type = 'application/zip'


	class SWHFileUploadTarParser(FileUploadParser):			class SWHFileUploadTarParser(FileUploadParser):
	"""File upload parser limited to zip archive.			"""File upload parser limited to tarball (tar, tar.gz, tar.*) archives.

	"""			"""
	media_type = 'application/x-tar'			media_type = 'application/x-tar'


	class SWHXMLParser(XMLParser):			class ListXMLParser(XMLParser):
				"""Patch XMLParser behavior to not merge duplicated key entries.

				"""
				# special tags that must be cast to list
				_tags = [
				'{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}license',
				'{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}programmingLanguage',
				'{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}runtimePlatform',
				'{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}author',
				ardumontAuthorUnsubmitted Not Done Inline Actions I don't like that much but i think that will do for the moment. ardumont: I don't like that much but i think that will do for the moment.
				moraneggUnsubmitted Not Done Inline Actions I don't like it either, There are many more entries that can be lists and I don't know exactly which.. If you want I can check, but I feel like doing so we will always have the risk of loosing other data. And sometime there is only one entry per tag that will be forced into a list element. moranegg: I don't like it either, There are many more entries that can be lists and I don't know exactly…
				ardumontAuthorUnsubmitted Not Done Inline Actions Yes, that's one of the reason i don't like it. losing other data... affiliation comes to mind for example. For information, I'm currently working on another implementation that drops the XMLParser altogether. It takes care of the current limitation. It also permits to drop the extra repetitive namespace in keys. I'll update the diff as soon possible. ardumont: Yes, that's one of the reason i don't like it. > losing other data... affiliation comes to…
				]

				# converted tags to list
				_lists = None

				def __init__(self):
				self._reset()

				def _reset(self):
				self._lists = defaultdict(list)

				def parse(self, stream, media_type=None, parser_context=None):
				data = super().parse(
				stream, media_type=media_type, parser_context=parser_context)
				# Overriding and updating the list values
				for key, value in self._lists.items():
				data[key] = value
				self._reset()
				return data

				def _xml_convert(self, element):
				"""This patches the default behavior to detect entries that must be
				list. The current XMLParser's behavior is not correct as it
				merges entries with the same name.

				"""
				children = list(element)
				if len(children) == 0:
				data = self._type_convert(element.text)
				if element.tag in self._tags:
				if data not in self._lists[element.tag]:
				self._lists[element.tag].append(data)
				return data

				# if the first child tag is list-item, it means all
				# children are list-item
				if children[0].tag == "list-item":
				data = []
				for child in children:
				data.append(self._xml_convert(child))
				return data

				data = {}
				for child in children:
				data[child.tag] = self._xml_convert(child)

				if element.tag in self._tags:
				if data not in self._lists[element.tag]:
				self._lists[element.tag].append(data)

				return data


				class SWHXMLParser(ListXMLParser):
	def _type_convert(self, value):			def _type_convert(self, value):
	"""Override the default type converter to avoid having decimal in the			"""Override the default type converter to avoid having decimal in the
	resulting output.			resulting output.

	"""			"""
	value = super()._type_convert(value)			value = super()._type_convert(value)
	if isinstance(value, Decimal):			if isinstance(value, Decimal):
	value = str(value)			value = str(value)
	Show All 29 Lines