def get_book_pdf(book_id, index):
"""
TODO: I'm a huge method that isn't easy to read
Please, refactor me ASAP
"""
items = item_index["id"].get(book_id, None)
if (index <= 0):
flask.abort(http.client.BAD_REQUEST, "Param index should be positive number")
if items is None:
flask.abort(http.client.NOT_FOUND, "Book with id {book_id} was not found".format(
book_id=book_id
))
item = utils.first(items)
item_url = item.get("url") or set()
request_path = flask.request.script_root + flask.request.path
request_url_production = "https://" + config.www.app_domain_production + request_path
if (
(book_id != item.id()) or
(request_url_production not in item_url) or
not utils.is_url_self_served(request_url_production, item)
):
flask.abort(404, "Book with id {book_id} isn't available for download".format(
book_id=book_id
))
file_name, file_size = utils.get_file_info_from_url(request_url_production, item)
#filenames start from slash, trimming it
pdf_full_path = os.path.join(config.www.elibrary_dir, file_name[1:])
if not os.path.isfile(pdf_full_path):
message = "Item {book_id} metadata is wrong: file for url {rel_url} is missing".format(
book_id=book_id,
rel_url=request_url_production
)
logging.error(message)
flask.abort(http.client.INTERNAL_SERVER_ERROR, message)
logging.info("Sending pdf file: {pdf_full_path}".format(
pdf_full_path=pdf_full_path
))
if config.working_mode == WorkingMode.Unittest:
#using send_file in unittest mode causes ResourceWarning due to unclosed file
response = flask.make_response("SOME_BINARY_PDF_LIKE_DATA")
response.headers["Content-Type"] = "application/pdf"
else:
#native send_file as_attrachment parameter works incorrectly with unicode data
#adding corrent Content-Disposition header manually
response = flask.make_response(flask.send_file(pdf_full_path))
basename = os.path.basename(pdf_full_path)
response.headers["Content-Disposition"] = \
"attachment;" \
"filename*=UTF-8''{utf_filename}".format(
utf_filename=urlparse.quote(basename)
)
return response
def get_book_pdf(book_id, index):
"""
TODO: I'm a huge method that isn't easy to read
Please, refactor me ASAP
"""
items = item_index["id"].get(book_id, None)
if (index <= 0):
flask.abort(http.client.BAD_REQUEST, "Param index should be positive number")
if items is None:
flask.abort(http.client.NOT_FOUND, "Book with id {book_id} was not found".format(
book_id=book_id
))
item = utils.first(items)
item_url = item.get("url") or set()
request_path = flask.request.script_root + flask.request.path
request_url_production = "https://" + config.www.app_domain_production + request_path
if (
(book_id != item.id()) or
(request_url_production not in item_url) or
not utils.is_url_self_served(request_url_production, item)
):
flask.abort(404, "Book with id {book_id} isn't available for download".format(
book_id=book_id
))
file_name, file_size = utils.get_file_info_from_url(request_url_production, item)
#filenames start from slash, trimming it
pdf_full_path = os.path.join(config.www.elibrary_dir, file_name[1:])
if not os.path.isfile(pdf_full_path):
message = "Item {book_id} metadata is wrong: file for url {rel_url} is missing".format(
book_id=book_id,
rel_url=request_url_production
)
logging.error(message)
flask.abort(http.client.INTERNAL_SERVER_ERROR, message)
logging.info("Sending pdf file: {pdf_full_path}".format(
pdf_full_path=pdf_full_path
))
if config.working_mode == WorkingMode.Unittest:
#using send_file in unittest mode causes ResourceWarning due to unclosed file
response = flask.make_response("SOME_BINARY_PDF_LIKE_DATA")
response.headers["Content-Type"] = "application/pdf"
else:
#native send_file as_attrachment parameter works incorrectly with unicode data
#adding corrent Content-Disposition header manually
response = flask.make_response(flask.send_file(pdf_full_path))
basename = os.path.basename(pdf_full_path)
response.headers["Content-Disposition"] = \
"attachment;" \
"filename*=UTF-8''{utf_filename}".format(
utf_filename=urlparse.quote(basename)
)
return response
def check_url_validity(item, errors):
"""
Checks url for validity
"""
url = item.get("url")
item_id = item.get("id")
if url is None:
return
for number, single_url in enumerate(url):
if not utils.is_url_valid(single_url, item):
errors.add("Field url with value [{single_url}] and number {number} is wrong".format(
single_url=single_url,
number=number
))
if not utils.is_url_self_served(single_url, item):
continue
match = utils.SELF_SERVED_URL_REGEXP.match(single_url)
if not match:
errors.add("Self served url [{single_url}] doesn't match SELF_SERVED_URL_REGEXP".format(
single_url=single_url
))
continue
if (match.group("item_id") != item_id):
errors.add("Wrong item_id specified in self-served url")
continue
single_filename, single_filesize = utils.get_file_info_from_url(single_url, item)
metadata = utils.extract_metadata_from_file(single_filename)
owners = metadata.get("owner").split("+")
if not owners:
errors.add("Owner specification expected for self-served url #{number} (url={url}, filename={filename})".format(
number=number,
url=single_url,
filename=single_filename
))
continue
for owner in owners:
owner_fullname = config.parser.bookkeepers.get(owner)
if owner_fullname:
annotation = item.get("annotation")
if (
(not annotation) or
(owner_fullname not in annotation)
):
errors.add("Owner fullname ({owner_fullname}) should be present in annotation".format(
owner_fullname=owner_fullname
))
def validate_url_validity(item, errors):
"""
Checks url for validity
"""
url = item.get("url")
item_id = item.get("id")
if url is None:
return
for number, single_url in enumerate(url):
if not utils.is_url_valid(single_url, item):
errors.add("Field url with value [{single_url}] and number {number} is wrong".format(
single_url=single_url,
number=number
))
if not utils.is_url_self_served(single_url, item):
continue
match = utils.SELF_SERVED_URL_REGEXP.match(single_url)
if not match:
errors.add("Self served url [{single_url}] doesn't match SELF_SERVED_URL_REGEXP".format(
single_url=single_url
))
continue
if (match.group("item_id") != item_id):
errors.add("Wrong item_id specified in self-served url")
continue
single_filename, single_filesize = utils.get_file_info_from_url(single_url, item)
metadata = utils.extract_metadata_from_file(single_filename)
owners = metadata.get("owner").split("+")
if not owners:
errors.add("Owner specification expected for self-served url #{number} (url={url}, filename={filename})".format(
number=number,
url=single_url,
filename=single_filename
))
continue
for owner in owners:
owner_fullname = config.parser.bookkeepers.get(owner)
if owner_fullname:
note = item.get("note")
if (
(not note) or
(owner_fullname not in note)
):
errors.add("Owner fullname ({owner_fullname}) should be present in note".format(
owner_fullname=owner_fullname
))
def from_url(single_url, item): if utils.is_url_self_served(single_url, item): return Availability.AvailableHere else: return Availability.AvailableElsewhere
def from_url(single_url, item): if utils.is_url_self_served(single_url, item): return Availability.AvailableHere else: return Availability.AvailableElsewhere
