#!/usr/bin/env python3
# coding: utf-8
#
# Copyright 2021 by Leipzig University Library, http://ub.uni-leipzig.de
#                   The Finc Authors, http://finc.info
#                   Robert Schenk, <robert.schenk@uni-leipzig.de>
#
# This file is part of some open source application.
#
# Some open source application is free software: you can redistribute
# it and/or modify it under the terms of the GNU General Public
# License as published by the Free Software Foundation, either
# version 3 of the License, or (at your option) any later version.
#
# Some open source application 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 General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Foobar. If not, see <http://www.gnu.org/licenses/>.
#
# @license GPL-3.0+ <http://spdx.org/licenses/GPL-3.0+>

"""

Source: OECD iLibrary
SID: 52
Ticket: #4911, #7051, #9157, #11575, #13260, #18863
Origin: HTTP

"""


import os
import sys
from io import BytesIO

import marcx
import pymarc
from siskin.configuration import Config
from siskin.utils import marc_clean_record, xmlstream, convert_to_finc_id
from siskin.arguments import FincArgumentParser


##################################################################################
# 1. Parse arguments and prepare outputfile
##################################################################################

SID = "52"

fip = FincArgumentParser()

# Get arguments
inputfile = fip.args.inputfile
outputformat = fip.args.outputformat

# Generates string for outputfilename, example: 196-output-20200701.fincmarc.mrc
outputfilename = fip.outputfilename(SID)

# Removes n old inputfiles and outputfiles as specified in input-hist-size and output-hist-size
fip.remove_old_outputfiles(SID)
fip.remove_old_inputfiles(SID)

# Set output format for MARC record
if outputformat == "xml":
    outputfile = pymarc.XMLWriter(open(outputfilename, "wb"))
else:
    outputfile = open(outputfilename, "wb")


##################################################################################
# 2. Get input data
##################################################################################

if not inputfile:    
    config = Config.instance()
    try:
        inputfile = config.get(SID, "input")
    except:
        inputfile = ""

    if not inputfile:
        try:
            url = config.get(SID, "url")
        except:
            sys.exit("No URL given in siskin.ini")
        inputfile = fip.inputfilename(SID)
        os.system("curl -sL --fail %s > %s" % (url, inputfile))


##################################################################################
# 3. Process data
##################################################################################

for oldrecord in xmlstream(inputfile, "record"):

    oldrecord = BytesIO(oldrecord)
    oldrecord = pymarc.marcxml.parse_xml_to_array(oldrecord)
    oldrecord = oldrecord[0]

    record = marcx.Record.from_record(oldrecord)
    record.force_utf8 = True
    record.strict = False

    # Identifier
    f001 = record["001"].data
    f001 = f001.replace("-", "")
    f001 = f001.replace("_", "")
    record.remove_fields("001")
    record.add("001", data="finc-52-" + f001)
    
    # Convert all identifier in 001, 770, 772 ... to Finc schema
    record = convert_to_finc_id(SID, record, encode=False, finc_prefix=True)

    # Remove empty subfields
    marc_clean_record(record)

    # Write record to file
    if outputformat == "xml":
        outputfile.write(record)
    else:
        outputfile.write(record.as_marc())

outputfile.close()
