taiga-back/taiga/base/api/parsers.py

# Copyright (C) 2015 Andrey Antukh <niwi@niwi.be>
# Copyright (C) 2015 Jesús Espino <jespinog@gmail.com>
# Copyright (C) 2015 David Barragán <bameda@dbarragan.com>
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as
# published by the Free Software Foundation, either version 3 of the
# License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

# This code is partially taken from django-rest-framework:
# Copyright (c) 2011-2014, Tom Christie

"""
Parsers are used to parse the content of incoming HTTP requests.

They give us a generic way of being able to handle various media types
on the request, such as form content or json encoded data.
"""
from django.conf import settings
from django.core.files.uploadhandler import StopFutureHandlers
from django.http import QueryDict
from django.http.multipartparser import MultiPartParser as DjangoMultiPartParser
from django.http.multipartparser import MultiPartParserError, parse_header, ChunkIter

from django.utils import six

from taiga.base.exceptions import ParseError
from taiga.base.api import renderers

import json
import datetime
import decimal


class DataAndFiles(object):
    def __init__(self, data, files):
        self.data = data
        self.files = files


class BaseParser(object):
    """
    All parsers should extend `BaseParser`, specifying a `media_type`
    attribute, and overriding the `.parse()` method.
    """

    media_type = None

    def parse(self, stream, media_type=None, parser_context=None):
        """
        Given a stream to read from, return the parsed representation.
        Should return parsed data, or a `DataAndFiles` object consisting of the
        parsed data and files.
        """
        raise NotImplementedError(".parse() must be overridden.")


class JSONParser(BaseParser):
    """
    Parses JSON-serialized data.
    """

    media_type = "application/json"
    renderer_class = renderers.UnicodeJSONRenderer

    def parse(self, stream, media_type=None, parser_context=None):
        """
        Parses the incoming bytestream as JSON and returns the resulting data.
        """
        parser_context = parser_context or {}
        encoding = parser_context.get("encoding", settings.DEFAULT_CHARSET)

        try:
            data = stream.read().decode(encoding)
            return json.loads(data)
        except ValueError as exc:
            raise ParseError("JSON parse error - %s" % six.text_type(exc))


class FormParser(BaseParser):
    """
    Parser for form data.
    """

    media_type = "application/x-www-form-urlencoded"

    def parse(self, stream, media_type=None, parser_context=None):
        """
        Parses the incoming bytestream as a URL encoded form,
        and returns the resulting QueryDict.
        """
        parser_context = parser_context or {}
        encoding = parser_context.get("encoding", settings.DEFAULT_CHARSET)
        data = QueryDict(stream.read(), encoding=encoding)
        return data


class MultiPartParser(BaseParser):
    """
    Parser for multipart form data, which may include file data.
    """

    media_type = "multipart/form-data"

    def parse(self, stream, media_type=None, parser_context=None):
        """
        Parses the incoming bytestream as a multipart encoded form,
        and returns a DataAndFiles object.

        `.data` will be a `QueryDict` containing all the form parameters.
        `.files` will be a `QueryDict` containing all the form files.
        """
        parser_context = parser_context or {}
        request = parser_context["request"]
        encoding = parser_context.get("encoding", settings.DEFAULT_CHARSET)
        meta = request.META.copy()
        meta["CONTENT_TYPE"] = media_type
        upload_handlers = request.upload_handlers

        try:
            parser = DjangoMultiPartParser(meta, stream, upload_handlers, encoding)
            data, files = parser.parse()
            return DataAndFiles(data, files)
        except MultiPartParserError as exc:
            raise ParseError("Multipart form parse error - %s" % str(exc))


class FileUploadParser(BaseParser):
    """
    Parser for file upload data.
    """
    media_type = "*/*"

    def parse(self, stream, media_type=None, parser_context=None):
        """
        Treats the incoming bytestream as a raw file upload and returns
        a `DateAndFiles` object.

        `.data` will be None (we expect request body to be a file content).
        `.files` will be a `QueryDict` containing one "file" element.
        """

        parser_context = parser_context or {}
        request = parser_context["request"]
        encoding = parser_context.get("encoding", settings.DEFAULT_CHARSET)
        meta = request.META
        upload_handlers = request.upload_handlers
        filename = self.get_filename(stream, media_type, parser_context)

        # Note that this code is extracted from Django's handling of
        # file uploads in MultiPartParser.
        content_type = meta.get("HTTP_CONTENT_TYPE",
                                meta.get("CONTENT_TYPE", ""))
        try:
            content_length = int(meta.get("HTTP_CONTENT_LENGTH",
                                          meta.get("CONTENT_LENGTH", 0)))
        except (ValueError, TypeError):
            content_length = None

        # See if the handler will want to take care of the parsing.
        for handler in upload_handlers:
            result = handler.handle_raw_input(None,
                                              meta,
                                              content_length,
                                              None,
                                              encoding)
            if result is not None:
                return DataAndFiles(None, {"file": result[1]})

        # This is the standard case.
        possible_sizes = [x.chunk_size for x in upload_handlers if x.chunk_size]
        chunk_size = min([2 ** 31 - 4] + possible_sizes)
        chunks = ChunkIter(stream, chunk_size)
        counters = [0] * len(upload_handlers)

        for handler in upload_handlers:
            try:
                handler.new_file(None, filename, content_type,
                                 content_length, encoding)
            except StopFutureHandlers:
                break

        for chunk in chunks:
            for i, handler in enumerate(upload_handlers):
                chunk_length = len(chunk)
                chunk = handler.receive_data_chunk(chunk, counters[i])
                counters[i] += chunk_length
                if chunk is None:
                    break

        for i, handler in enumerate(upload_handlers):
            file_obj = handler.file_complete(counters[i])
            if file_obj:
                return DataAndFiles(None, {"file": file_obj})
        raise ParseError("FileUpload parse error - "
                         "none of upload handlers can handle the stream")

    def get_filename(self, stream, media_type, parser_context):
        """
        Detects the uploaded file name. First searches a "filename" url kwarg.
        Then tries to parse Content-Disposition header.
        """
        try:
            return parser_context["kwargs"]["filename"]
        except KeyError:
            pass

        try:
            meta = parser_context["request"].META
            disposition = parse_header(meta["HTTP_CONTENT_DISPOSITION"])
            return disposition[1]["filename"]
        except (AttributeError, KeyError):
            pass