Пример #1
0
 def process_passage(self):
     index_root = deepcopy(self.models['PASSAGE']['index'])
     index_body = index_root.find('body')
     for year in self.bib.years:
         for pub in self.bib.refs_years[year]:
             urn, meta = pub
             if urn in self.txt.content:
                 f = urn
                 utility.create_html_link_node(meta, index_body,
                                               './' + f + '-1.html')
                 content = self.txt.content[urn]
                 passages = list(content.keys())
                 for i, k in enumerate(content):
                     root = deepcopy(self.models['PASSAGE']['content'])
                     body = root.find('body')
                     utility.create_html_text_node(meta, body)
                     utility.create_html_delimiter(body)
                     # re.findall(r"'(.*?)'", content[k][0])
                     utility.create_html_text_node(content[k], body)
                     utility.create_html_delimiter(body)
                     if i < len(passages) - 1:
                         np = i + 1
                         next_fp = './' + f + '-' + passages[np] + '.html'
                         utility.create_html_link_node('==>', body, next_fp)
                     fp = self.corp_pass_path + f + '-' + k + '.html'
                     utility.write_html_file_pretty(fp, root)
             else:
                 print("passage: can not find material", urn)
                 continue
     utility.create_html_delimiter(index_body)
     utility.write_html_file_pretty(self.corp_pass_path + 'index.html',
                                    index_root)
Пример #2
0
 def process_edition(self):
     index_root = deepcopy(self.models['EDITION']['index'])
     index_body = index_root.find('body')
     for year in self.bib.years:
         for pub in self.bib.refs_years[year]:
             urn, meta = pub
             if urn in self.txt.content:
                 f = './' + urn + '.html'
                 utility.create_html_link_node(meta, index_body, f)
                 content = self.txt.content[urn]
                 # passages = list(content.keys())
                 root = deepcopy(self.models['EDITION']['content'])
                 body = root.find('body')
                 utility.create_html_text_node(meta, body)
                 utility.create_html_delimiter(body)
                 for i, k in enumerate(content):
                     if i:
                         utility.create_html_delimiter(body)
                     # re.findall(r"'(.*?)'", content[k][0])
                     utility.create_html_text_node(content[k], body)
                 utility.create_html_delimiter(body)
                 utility.write_html_file_pretty(self.corp_ed_path + f[2:],
                                                root)
             else:
                 print("edition: can not find material", urn)
                 continue
     utility.create_html_delimiter(index_body)
     utility.write_html_file_pretty(self.corp_ed_path + 'index.html',
                                    index_root)
Пример #3
0
 def process_facsimile(self):
     index_root = deepcopy(self.models['FACSIMILE']['index'])
     index_body = index_root.find('body')
     for fac in self.facs:
         utility.create_html_link_node(fac, index_body, self.facs[fac],
                                       True)
     utility.create_html_delimiter(index_body)
     utility.write_html_file_pretty(self.facs_path + 'index.html',
                                    index_root)
Пример #4
0
 def process_corpus(self):
     index_root = deepcopy(self.models['CORPUS']['index'])
     index_body = index_root.find('body')
     utility.create_html_link_node('GROUP', index_body, './group/')
     utility.create_html_link_node('EDITION', index_body, './edition/')
     utility.create_html_link_node('PASSAGE', index_body, './passage/')
     utility.create_html_delimiter(index_body)
     utility.write_html_file_pretty(self.corp_path + 'index.html',
                                    index_root)
Пример #5
0
 def process_descriptor(self):
     index_root = deepcopy(self.models['DESCRIPTOR']['index'])
     index_body = index_root.find('body')
     descs = list(self.desc.keys())
     descs.sort()
     for desc in descs:
         desc_fp = './' + unidecode(desc).lower() + '.html'
         utility.create_html_link_node(desc, index_body, desc_fp)
         urns = self.desc[desc]
         desc_index = deepcopy(self.models['DESCRIPTOR']['content'])
         desc_body = desc_index.find('body')
         utility.create_html_text_node(desc, desc_body)
         utility.create_html_delimiter(desc_body)
         for urn in urns:
             if urn in self.txt.content:
                 if urn in self.bib.refs_bib:
                     meta = self.bib.refs_bib[urn]
                 else:
                     meta = urn
                     print("desc: could not find reference for", urn)
                 fp = './' + unidecode(desc).lower() + '_' + urn + '.html'
                 utility.create_html_link_node(meta, desc_body, fp)
                 passages = urns[urn]
                 text = ''
                 for p in passages:
                     passage = p.split("-")
                     if len(passage) > 1:
                         start = int(passage[0])
                         finish = int(passage[1])
                         text = ''
                         for i in range(start, finish + 1):
                             content = self.txt.content[urn][str(i)]
                             text += content + '\n\n'
                     else:
                         content = self.txt.content[urn][passage[0]]
                         text += content + '\n\n'
             else:
                 print("desc: can not find material", urn)
                 continue
             text = text[:-2]
             root = deepcopy(self.models['DESCRIPTOR']['content'])
             body = root.find('body')
             utility.create_html_link_node(desc, body, desc_fp)
             utility.create_html_delimiter(body)
             utility.create_html_text_node(meta, body)
             utility.create_html_delimiter(body)
             utility.create_html_text_node(text, body)
             utility.create_html_delimiter(body)
             fp = self.desc_path + unidecode(
                 desc).lower() + '_' + urn + '.html'
             utility.write_html_file_pretty(fp, root)
         utility.create_html_delimiter(desc_body)
         desc_fp = self.desc_path + unidecode(desc).lower() + '.html'
         utility.write_html_file_pretty(desc_fp, desc_index)
     utility.create_html_delimiter(index_body)
     utility.write_html_file_pretty(self.desc_path + 'index.html',
                                    index_root)
Пример #6
0
    def process_group(self):
        index_root = deepcopy(self.models['GROUP']['index'])
        index_body = index_root.find('body')
        a = list(self.levels.keys())
        a.sort()
        for auth in a:
            if auth in self.pers:
                name = self.pers[auth]['Forename'] + ' ' + self.pers[auth][
                    'Surname']
                pers_fp = './' + auth + '.html'
                utility.create_html_link_node(name, index_body, pers_fp)
                pers_index = deepcopy(self.models['GROUP']['content'])
                pers_body = pers_index.find('body')
                utility.create_html_text_node(name, pers_body)
                utility.create_html_delimiter(pers_body)
                for ref in self.bib.refs:
                    if auth in ref:
                        if ref in self.txt.content:
                            utility.create_html_link_node(
                                self.bib.refs[ref], pers_body,
                                './' + ref + '.html')
                            root = deepcopy(self.models['GROUP']['content'])
                            body = root.find('body')
                            utility.create_html_link_node(name, body, pers_fp)
                            utility.create_html_delimiter(body)
                            utility.create_html_text_node(
                                self.bib.refs[ref], body)
                            utility.create_html_delimiter(body)
                            content = self.txt.content[ref]
                            passages = list(content.keys())
                            for i, k in enumerate(content):
                                utility.create_html_text_node(content[k], body)
                                utility.create_html_delimiter(body)
                            fp = self.corp_group_path + ref + '.html'
                            utility.write_html_file_pretty(fp, root)
                        else:
                            print("group: can not find material", ref)

            else:
                print("group: can not find author", auth)
                continue
            utility.create_html_delimiter(pers_body)
            pers_fp = self.corp_group_path + auth + '.html'
            utility.write_html_file_pretty(pers_fp, pers_index)
        utility.create_html_delimiter(index_body)
        utility.write_html_file_pretty(self.corp_group_path + 'index.html',
                                       index_root)