def bkp_analyze_document(self, xml_filename, package, folder_table_name):
generic_document = None
json_data = self.xml2json.convert(xml_filename, package.report)
if type(json_data) != type({}):
package.report.write(' ! ERROR: Invalid JSON ' + xml_filename, False, False, False, json_data)
else:
img_files = package.return_matching_files(xml_filename, '.jpg')
self.json2model.set_data(json_data, xml_filename, package.report)
publication_title = self.json2model.publication_title
registered = self.registered_titles.return_registered(publication_title, package.report)
if registered != None:
specific_document, errors, warnings, refcount = self.json2model.return_document(registered, img_files)
if specific_document != None:
generic_document = Document(specific_document)
package.report.write(generic_document.display(), True, False, False)
specific_folder = self.all_folders.template(generic_document.folder)
if specific_folder.status == 'not_registered':
package.report.write("\n" + ' ! WARNING: ' + specific_folder.display() + ' is not registered in ' + folder_table_name + ', but it will be registered provisionally. After being oficially registered, it must be reprocessed.' + "\n" , True, True, True )
print('generic_document.folder toc:')
print(generic_document.folder.toc.return_json())
print('specific_folder toc:')
print(specific_folder.toc.return_json())
incoherences = self.all_folders.return_incoherences(specific_folder, generic_document.folder)
if len(incoherences) > 0:
package.report.write(' ! ERROR: There are inconsistencies of data ' + xml_filename, True, True, True)
for err in incoherences:
package.report.write(err, True, True, True)
generic_document.folder = specific_folder
#print('generic_document.folder = specific_folder')
generic_document.folder.toc.insert(generic_document.section, False)
print('generic_document.folder toc:')
print(generic_document.folder.toc.return_json())
if generic_document.folder.documents == None:
generic_document.folder.documents = Documents()
generic_document.folder.documents.insert(generic_document.document, True)
return generic_document
def process_document(self, xml_filename, package, folder_table_name):
fatal_errors = []
generic_document = None
if self.extract_data(xml_filename, package.report):
publication_title = self.json2model.publication_title
registered = None
if len(publication_title) > 0:
registered = self.registered_titles.return_registered(publication_title)
if registered == None:
package.report.write('Invalid publication title:' + publication_title, True, True)
else:
document_folder = self.json2model.return_folder(registered)
#print(';'*20)
#print('document_folder')
#print(document_folder)
#if document_folder is not None:
# #print(document_folder.documents)
# #if document_folder.documents is not None:
# #print(document_folder.documents.elements)
#print(';'*20)
selected_folder = self.check_folder(document_folder, package)
if selected_folder.status == 'registered':
#print('-'*20)
#print('selected_folder')
#print(selected_folder)
#if selected_folder is not None:
# #print(selected_folder.documents)
# if selected_folder.documents is not None:
# print(selected_folder.documents.elements)
#print('-'*20)
specific_document = self.json2model.return_doc(selected_folder)
#print(':'*20)
#print('specific_document')
#print(specific_document)
#print(specific_document.folder)
#if specific_document.folder is not None:
# print(specific_document.folder.documents)
# if specific_document.folder.documents is not None:
# print(specific_document.folder.documents.elements)
#print(':'*20)
if specific_document != None:
if not specific_document.doi == '':
if not 'ahead' in specific_document.issue.name:
pid, fname = self.ahead_articles.return_id_and_filename(specific_document.doi, specific_document.issue.journal.issn_id, specific_document.titles)
specific_document.set_previous_id(pid)
#print(':'*20)
#print('generic_document')
#print(generic_document)
#print(':'*20)
generic_document = Document(specific_document)
#print('>'*20)
#print('generic_document depois')
#print(generic_document)
#print(generic_document.folder)
#print(generic_document.folder.documents)
#if generic_document.folder.documents is not None:
# print(generic_document.folder.documents.elements)
#print('>'*20)
package.report.write(generic_document.display(), True, True, False)
img_files = package.return_matching_files(xml_filename, '.jpg')
fatal_errors, e, w, ref_count = self.json2model.evaluate_data(img_files)
if generic_document.folder.documents == None:
generic_document.folder.documents = Documents()
if specific_document.doi == '' and specific_document.issue.name[-2:] != 'pr':
fatal_errors.append('FATAL ERROR: Missing DOI')
package.report.write('FATAL ERROR: Missing DOI', True, True)
else:
if not generic_document.folder.documents.insert(generic_document.document, False):
package.report.write('FATAL ERROR: This document has doi (' + generic_document.document.doi + ') or order(' + generic_document.document.order + ') of another document.', True, True)
fatal_errors.append('FATAL ERROR: This document has doi (' + generic_document.document.doi + ') or order(' + generic_document.document.order + ') of another document.')
else:
package.report.write('', True, True)
return (fatal_errors, generic_document)
