Page MenuHomec4science
Files F62393216

page.py
No OneTemporary
Actions

File Metadata

Created
Sun, May 12, 21:30

page.py
View Options

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
""" This class can be used to represent a page.
"""
# Copyright (C) University of Basel 2019 {{{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}}}
__author__ = "Christian Steiner"
__maintainer__ = __author__
__copyright__ = 'University of Basel'
__email__ = "christian.steiner@unibas.ch"
__status__ = "Development"
__license__ = "GPL v3"
__version__ = "0.0.1"
from lxml import etree as ET
from os.path import isfile
#from myxmlwriter import write_pretty
from .class_spec import SemanticClass
from .image import Image
from .word import Word
from .lineNumber import LineNumber
from .word_insertion_mark import WordInsertionMark
from .transkriptionField import TranskriptionField
class Page(SemanticClass):
"""
This class represents a page.
Args:
xml_source_file (str): name of the xml file to be instantiated.
xml_target_file (str): name of the xml file to which page info will be written.
"""
class_dictionary = {}
def __init__(self, xml_source_file=None, xml_target_file=None, title=None, page_number=None, pdfFile=None, svg_file=None, extract_transkription_field_only=False):
self.title = title
self.line_numbers = []
self.style_dict = {}
self.sonderzeichen_list = []
self.svg_file = None
self.pdfFile = None
self.source = None
self.number = int(page_number) if page_number is not None else -1
if xml_source_file is not None:
if isfile(xml_source_file):
parser = ET.XMLParser(remove_blank_text=True)
self.page_tree = ET.parse(xml_source_file, parser)
self.title = self.page_tree.getroot().get('title')
self.number = self.page_tree.getroot().get('number')
self.source = self.page_tree.getroot().get('source')
self.init_words()
self.add_style(style_node=self.page_tree.getroot().find('.//style'))
self.svg_file = self.page_tree.xpath('.//svg/@file')[0]\
if len(self.page_tree.xpath('.//svg/@file')) > 0 else None
self.width = float(self.page_tree.xpath('.//svg/@width')[0])\
if len(self.page_tree.xpath('.//svg/@width')) > 0 else 0.0
self.height = float(self.page_tree.xpath('.//svg/@height')[0])\
if len(self.page_tree.xpath('.//svg/@height')) > 0 else 0.0
self.pdfFile = self.page_tree.xpath('.//pdf/@file')[0]\
if len(self.page_tree.xpath('.//pdf/@file')) > 0 else None
if pdfFile is not None and self.pdfFile is None:
self.pdfFile = pdfFile
ET.SubElement(self.page_tree.getroot(), 'pdf', attrib={'file': self.pdfFile})
#write_pretty(xml_element_tree=self.page_tree, file_name=xml_source_file, script_name=__file__, file_type='svgWordPosition')
if svg_file is not None and self.svg_file is None:
self.svg_file = svg_file
tf = TranskriptionField(svg_file)
self.width = round(tf.documentWidth, 3)
self.height = round(tf.documentHeight, 3)
ET.SubElement(self.page_tree.getroot(), 'svg', attrib={'width': str(self.width), 'height': str(self.height), 'file': self.svg_file})
#write_pretty(xml_element_tree=self.page_tree, file_name=xml_source_file, script_name=__file__, file_type='svgWordPosition')
else:
raise Exception('File "{}" does not exist!'.format(xml_source_file))
elif xml_target_file is not None:
self.word_insertion_marks = []
self.words = []
self.svg_file = svg_file
self.pdfFile = pdfFile
if isfile(xml_target_file):
parser = ET.XMLParser(remove_blank_text=True)
self.page_tree = ET.parse(xml_target_file, parser)
self.source = self.page_tree.getroot().get('source')
if bool(self.page_tree.getroot().get('title')):
self.title = self.page_tree.getroot().get('title')
elif title is not None:
self.page_tree.getroot().set('title', title)
if self.svg_file is None:
self.svg_file = self.page_tree.xpath('.//svg/@file')[0]\
if len(self.page_tree.xpath('.//svg/@file')) > 0 else None
self.width = float(self.page_tree.xpath('.//svg/@width')[0])\
if len(self.page_tree.xpath('.//svg/@width')) > 0 else 0.0
self.height = float(self.page_tree.xpath('.//svg/@height')[0])\
if len(self.page_tree.xpath('.//svg/@height')) > 0 else 0.0
elif len(self.page_tree.xpath('.//svg/@file')) == 0:
tf = TranskriptionField(svg_file)
self.width = round(tf.documentWidth, 3)
self.height = round(tf.documentHeight, 3)
ET.SubElement(self.page_tree.getroot(), 'svg', attrib={'width': str(self.width), 'height': str(self.height), 'file': self.svg_file})
else:
self.width = float(self.page_tree.xpath('.//svg/@width')[0])\
if len(self.page_tree.xpath('.//svg/@width')) > 0 else 0.0
self.height = float(self.page_tree.xpath('.//svg/@height')[0])\
if len(self.page_tree.xpath('.//svg/@height')) > 0 else 0.0
if self.pdfFile is None:
self.pdfFile = self.page_tree.xpath('.//pdf/@file')[0]\
if len(self.page_tree.xpath('.//pdf/@file')) > 0 else None
elif len(self.page_tree.xpath('.//pdf/@file')) == 0:
ET.SubElement(self.page_tree.getroot(), 'pdf', attrib={'file': self.pdfFile})
for xpath2remove in [ 'word', 'style', 'freehand', LineNumber.XML_TAG() ]:
for node in self.page_tree.xpath('//' + xpath2remove):
node.getparent().remove(node)
else:
self.page_tree = ET.ElementTree(ET.Element('page'))
self.pdfFile = pdfFile
self.svg_file = svg_file
if title is not None:
self.page_tree.getroot().set('title', title)
self.page_tree.getroot().set('transkription-field-only', str(extract_transkription_field_only).lower())
if page_number is not None:
self.page_tree.getroot().set('number', str(page_number))
if self.pdfFile is not None:
ET.SubElement(self.page_tree.getroot(), 'pdf', attrib={'file': self.pdfFile})
if self.svg_file is not None:
tf = TranskriptionField(self.svg_file)
self.width = round(tf.documentWidth, 3)
self.height = round(tf.documentHeight, 3)
ET.SubElement(self.page_tree.getroot(), 'svg', attrib={'width': str(self.width), 'height': str(self.height), 'file': self.svg_file})
self.svg_image = Image(file_name=self.svg_file, height=self.height, width=self.width) if self.svg_file is not None\
else None
self.create_semantic_dictionary(Page.class_dictionary)
def init_line_numbers(self, line_numbers, document_bottom):
"""Init line numbers.
"""
even_index = 0
MINABOVE = 1
self.line_numbers = []
if len(line_numbers) > 0:
first_line_bottom = line_numbers[even_index].top - MINABOVE
self.line_numbers.append(LineNumber(id=1, top=0, bottom=first_line_bottom))
self.line_numbers.append(line_numbers[even_index])
even_index += 1
while even_index < len(line_numbers):
self.line_numbers.append(LineNumber(id=line_numbers[even_index].id-1,\
top=line_numbers[even_index-1].bottom+MINABOVE,\
bottom=line_numbers[even_index].top-MINABOVE))
self.line_numbers.append(line_numbers[even_index])
even_index += 1
self.line_numbers.append(LineNumber(id=line_numbers[even_index-1].id+1,\
top=line_numbers[even_index-1].bottom+MINABOVE,\
bottom=document_bottom))
for line_number in self.line_numbers:
line_number.attach_object_to_tree(self.page_tree)
def init_words(self):
self.word_insertion_marks = [ WordInsertionMark(wim_node=wim_node) for wim_node in self.page_tree.getroot().xpath('//' + WordInsertionMark.XML_TAG()) ]
self.words = [ Word.CREATE_WORD(word_node=word_node) for word_node in self.page_tree.getroot().xpath('//word') ]
self.line_numbers = [ LineNumber(xml_text_node=line_number_node) for line_number_node in self.page_tree.getroot().xpath('//' + LineNumber.XML_TAG()) ]
for index, word in enumerate(self.words):
for word_insertion_mark in self.word_insertion_marks:
self.words[index] = word_insertion_mark.attach_and_update_word_if_involved(word)
if self.words[index] != word:
break
def add_style(self, sonderzeichen_list=[], letterspacing_list=[], style_dict={}, style_node=None):
"""Adds a list of classes that are sonderzeichen and a style dictionary to page.
"""
self.sonderzeichen_list = sonderzeichen_list
self.letterspacing_list = letterspacing_list
self.style_dict = style_dict
if style_node is not None:
self.style_dict = { item.get('name'): { key: value for key, value in item.attrib.items() if key != 'name' } for item in style_node.findall('.//class') }
self.sonderzeichen_list = [ item.get('name') for item in style_node.findall('.//class')\
if bool(item.get('font-family')) and 'Sonderzeichen' in item.get('font-family') ]
self.letterspacing_list = [ item.get('name') for item in style_node.findall('.//class')\
if bool(item.get('letterspacing-list')) ]
elif bool(self.style_dict):
style_node = ET.SubElement(self.page_tree.getroot(), 'style')
if len(self.sonderzeichen_list) > 0:
style_node.set('Sonderzeichen', ' '.join(self.sonderzeichen_list))
if len(self.letterspacing_list) > 0:
style_node.set('letterspacing-list', ' '.join(self.letterspacing_list))
for key in self.style_dict.keys():
self.style_dict[key]['name'] = key
ET.SubElement(style_node, 'class', attrib=self.style_dict[key])
def get_biggest_fontSize4styles(self, style_set={}):
"""Returns biggest font size from style_dict for a set of style class names.
[:returns:] (float) biggest font size OR 1 if style_dict is empty
"""
if bool(self.style_dict):
sorted_font_sizes = sorted( (float(self.style_dict[key]['font-size'].replace('px','')) for key in style_set if bool(self.style_dict[key].get('font-size'))), reverse=True)
return sorted_font_sizes[0] if len(sorted_font_sizes) > 0 else 1
else:
return 1
def get_line_number(self, y):
"""Returns line number id for element at y.
[:return:] (int) line number id or -1
"""
if len(self.line_numbers) > 0:
result_list = [ line_number.id for line_number in self.line_numbers if y >= line_number.top and y <= line_number.bottom ]
return result_list[0] if len(result_list) > 0 else -1
else:
return -1
def create_semantic_dictionary(self, dictionary):
""" Creates a semantic dictionary as specified by SemanticClass.
"""
if len(dictionary) == 0:
class_dict = self.get_class_dictionary()
if self.__class__ == Page:
class_dict.update({'rdf:subClassOf': 'http://www.knora.org/ontology/0000/information-carrier#Page'})
properties = {'title': (str, 1), 'number': (str, 1), 'line_numbers': (LineNumber, SemanticClass.LIST), 'words': (Word, SemanticClass.LIST),\
'svg_image': (Image, 1), 'word_insertion_marks': (WordInsertionMark, SemanticClass.LIST)}
dictionary.update({'class': class_dict})
dictionary.update({'properties': properties})
@staticmethod
def get_semantic_dictionary():
return __class__.class_dictionary

Event Timeline

c4science · Help