Homec4science
Diffusion nietzsche-python Browse

nietzsche-python/fixes/add_faksimile_image.py
rNIETZSCHEPYTHON126

Last Change
Raw File

add_faksimile_image.py
View Options

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""This program can be used to add a faksimile image to a page xml file.
"""
# Copyright (C) University of Basel 2021 {{{1
#
# This program 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.
#
# 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 General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <https://www.gnu.org/licenses/> 1}}}
from colorama import Fore, Style
import csv
import getopt
import json
import lxml.etree as ET
import shutil
import subprocess
import sys
import os
import wget
from os import listdir, sep, path, setpgrp, devnull, mkdir, remove
from os.path import exists, isfile, isdir, dirname, basename
from progress.bar import Bar
import re
import warnings
from fix_old_data import save_page
from get_text_field import get_text_field_on_image
sys.path.append('svgscripts')
from datatypes.faksimile_image import FaksimileImage
from datatypes.faksimile import FaksimilePage
from datatypes.matrix import Matrix
from datatypes.archival_manuscript import ArchivalManuscriptUnity
from datatypes.page import Page, STATUS_MERGED_OK, STATUS_POSTMERGED_OK
from util import back_up, back_up_svg_file, copy_faksimile_update_image_location, copy_faksimile_svg_file
from process_files import update_svgposfile_status
from process_words_post_merging import update_faksimile_line_positions, MERGED_DIR
sys.path.append('shared_util')
from myxmlwriter import copy_to_bak_dir, write_pretty, xml_has_type, FILE_TYPE_SVG_WORD_POSITION, FILE_TYPE_XML_MANUSCRIPT
from main_util import create_function_dictionary
__author__ = "Christian Steiner"
__maintainer__ = __author__
__copyright__ = 'University of Basel'
__email__ = "christian.steiner@unibas.ch"
__status__ = "Development"
__license__ = "GPL v3"
__version__ = "0.0.1"
MAX_SVG_XY_THRESHOLD = 10
BLANK_STATUS = 'blank'
UNITTESTING = False
class FlippedSidesCSVHandler:
"""This class can be used to handle csv files that contain information about the title and layout of the svg files.
"""
ENTRY_KEY_PAGE = 'pdf_page_number'
ENTRY_KEY_FILE = 'svg_source_file'
ENTRY_KEY_TITLE = 'manuscript_title'
ENTRY_KEY_PAGE_NAMES = 'page_names'
ENTRY_KEY_MARG_PAGE = 'marginals_page_entry'
MANUSCRIPT_AE_REMOVAL = re.compile('[a-e]')
MANUSCRIPT_KEY = 'Ms'
MANUSCRIPT_PATTERN = re.compile(r'(\d+)(>\s)(.*)')
MANUSCRIPT_TITLE_EXTENSION = 'Mp'
MANUSCRIPT_TITLE_PARTS = re.compile(r'([I-X]+[a-e]*)(\s)(\d+\w*)(/\d+\w*)*')
MARGINALS_PAGE = re.compile(r'([I-X]+[a-e]*)(\s)(\d+\w*)(\s)(Marg)')
REMOVE_NONNUMERIC = re.compile('\D')
def __init__(self, csv_file_name: str, title: str):
self.page_dictionary = {}
self.title = title
self._init_csv_entries(csv_file_name)
def _init_csv_entries(self, csv_file_name):
"""Init csv entries by reading the csv_file.
"""
with open(csv_file_name, newline='') as csvfile:
reader = csv.DictReader(csvfile)
flipped_key = 'Gedrehte Seiten'
if len([ key for key in reader.fieldnames if flipped_key in key ]) > 0:
flipped_key = [ key for key in reader.fieldnames if flipped_key in key ][0]
for row in reader:
if bool(row[flipped_key]):
ms_string = row[self.MANUSCRIPT_KEY]
manuscript_match = re.match(self.MANUSCRIPT_PATTERN, ms_string)
for flipped_line in row[flipped_key].split('\n'):
flipped_msg = re.split(r'(\s*Drehung\s*|\s*\(.*)', flipped_line)
if len(flipped_msg) > 2 and manuscript_match is not None:
page_number = flipped_msg[0]
rotation = flipped_msg[2]
title_parts = re.match(self.MANUSCRIPT_TITLE_PARTS, manuscript_match.group(3))
if title_parts is not None\
and self.MANUSCRIPT_TITLE_EXTENSION + ' ' + self.MANUSCRIPT_AE_REMOVAL.sub('', title_parts.group(1)) == self.title:
self.page_dictionary.update({page_number: rotation})
def add_faksimile_image(page: Page, faksimile_dir: str) ->int:
"""Add faksimile image to page.
[:return:] exit_code
"""
svg_file = faksimile_dir + sep + basename(page.page_tree.docinfo.URL).replace('.xml','.svg')
if isfile(svg_file):
fp = FaksimilePage.get_faksimile_pages(svg_file, page_number=page.number, isBlank=True)
if len(fp) > 0 and fp[0].faksimile_image is not None:
fp[0].faksimile_image.text_field = fp[0].text_field
fp[0].faksimile_image.attach_object_to_tree(page.page_tree)
if not UNITTESTING:
save_page(page)
return 0
return 2
def update_faksimile_image(page: Page, csv_handler: FlippedSidesCSVHandler) ->int:
"""Update faksimile image of page: add rotation matrix.
[:return:] exit_code
"""
rotation = csv_handler.page_dictionary.get(page.number)
if rotation is not None:
matrix = Matrix(f'rotate({rotation})')
page.faksimile_image.transform = matrix
page.faksimile_image.attach_object_to_tree(page.page_tree)
if not UNITTESTING:
save_page(page)
return 0
else:
print(page.number, csv_handler.page_dictionary.keys())
return 2
def usage():
"""prints information on how to use the script
"""
print(main.__doc__)
def main(argv):
"""This program can be used to add or update a faksimile image to a page xml file.
fixes/add_faksimile_image.py [OPTIONS] <xmlManuscriptFile|svg_pos_file> <faksimile-dir|csv-file>
<xmlManuscriptFile> a xml file about a manuscript, containing information about its pages.
<svg_pos_file> a xml file about a page, containing information about svg word positions.
<faksimile-dir> a directory containing the blank faksimile svg files
<csv-file> a csv-file containing a column about the rotation of the transkription.
OPTIONS:
-h|--help show help
:return: exit code (int)
"""
try:
opts, args = getopt.getopt(argv, "h", ["help"])
except getopt.GetoptError:
usage()
return 2
for opt, arg in opts:
if opt in ('-h', '--help'):
usage()
return 0
exit_status = 0
if len(args) < 2:
usage()
return 2
xml_file = args[0]
manuscript_file = xml_file\
if len(xml_file.split('_')) < 3\
else '_'.join(xml_file.split('_')[0:2]) + '.xml'
task = add_faksimile_image
argument = args[1]
if argument.endswith('.csv'):
if isfile(argument):
argument = FlippedSidesCSVHandler(argument, basename(manuscript_file).replace('_', ' ').replace('.xml',''))
task = update_faksimile_image
else:
raise FileNotFoundError(f'File {argument} does not exist!')
elif not isdir(argument):
raise FileNotFoundError(f'Directory {argument} does not exist!')
if isfile(xml_file):
counter = 0
for page in Page.get_pages_from_xml_file(xml_file, status_contains=BLANK_STATUS):
if not UNITTESTING:
print(Fore.CYAN + f'{task.__name__}: {page.title}, {page.number} ...' + Style.RESET_ALL)
back_up(page, page.xml_file)
if task(page, argument) == 0:
counter += 1
if not UNITTESTING:
print(Style.RESET_ALL + f'[{counter} pages processed]')
else:
raise FileNotFoundError('File {} does not exist!'.format(xml_file))
return exit_status
if __name__ == "__main__":
sys.exit(main(sys.argv[1:]))
c4science · Help