def dividePdf(self):
"""
Cut up the volume into articles pdfs based on the data in the LIMB toc
"""
for _, articles in self.article_data.items():
for article in articles:
hash_name = tools.getHashName(article["TitleDocMain"])
start_page = article["start_page"]
end_page = article["end_page"]
# legr: TODO : should probably subtract 1 from end_page
output_name = tools.getArticleName(hash_name, start_page, end_page)
output_path = os.path.join(self.pdf_output_dir, output_name)
self.debug_message("creating file {0}".format(output_path))
# if our call to pdftk fails, get out quickly
if not tools.cutPdf(self.pdf_path, output_path, start_page, end_page):
error = "PDF division failed. Input file: {0}, " "start page: {1}, end page: {2}"
error = error.format(self.pdf_path, start_page, end_page)
raise IOError(error)
return None
def createArticleXML(self, doc, article, date_published):
'''
Given an article dict, create the OJS XML
corresponding to this data
'''
#=======================================================================
# Create article stub with title
#=======================================================================
article_tag = doc.createElement('article')
doc_language = tools.convertLangToLocale(article['DocLanguage'])
article_tag.setAttribute('locale',doc_language)
article_tag.setAttribute('language',article['DocLanguage'])
title_tag = self.createXMLTextTag(doc, 'title', article['TitleDocMain'])
article_tag.appendChild(title_tag)
#=======================================================================
# Add DBC-id to article
#=======================================================================
'''
this code causes OJS to panic - we don't know why it should be here.
so we're killing it.
dbc_marcx_id = article['dbcMarcxID'] if 'dbcMarcxID' in article else ''
dbc_id_tag = self.createXMLTextTag(doc, 'id', dbc_marcx_id)
dbc_id_tag.setAttribute('type','dbcMarcxID')
article_tag.appendChild(dbc_id_tag)
'''
#=======================================================================
# Add page range
#=======================================================================
start_page = article['start_page']
end_page = article['end_page']
# legr: Calculate offset so real start- and end page can be forwarded to OJS
offset = self.get_calculated_offset()
if offset == 0:
print("Warning: offset = 0. Maybe all pages are uncounted?")
else:
print("Information: Calculated offset value: {0}".format(offset))
page_range = "{0}-{1}".format(start_page + offset, end_page + offset)
pages_tag = self.createXMLTextTag(doc, 'pages', page_range)
article_tag.appendChild(pages_tag)
#=======================================================================
# Add date published tag
#=======================================================================
published_tag = self.createXMLTextTag(doc, 'date_published', date_published)
article_tag.appendChild(published_tag)
#=======================================================================
# Add authors
#=======================================================================
# don't add an author tag if we don't have one (e.g. Front Matter)
if 'Author' in article: #Author is a list of zero, one or multuple authors
for author in article['Author']:
author_tag = self.createAuthorXML(doc, author)
article_tag.appendChild(author_tag)
#=======================================================================
# Add subjects
# see http://pkp.sfu.ca/wiki/index.php/Importing_and_Exporting_Data#Creating_the_XML_Import_File
#=======================================================================
if 'Subject' in article: #Author is a list of zero, one or multuple authors
indexing_tag = doc.createElement('indexing')
subjects = ''
if isinstance(article['Subject'],list):
subjects = ';'.join(article['Subject'])
else:
subjects = article['Subject']
subject_tag = self.createXMLTextTag(doc,'subject',subjects)
subject_tag.setAttribute('locale',tools.convertLangToLocale('da'))
indexing_tag.appendChild(subject_tag)
article_tag.appendChild(indexing_tag)
#=======================================================================
# Add pdf-link
#=======================================================================
md5_hash = tools.getHashName(article['TitleDocMain'])
pdf_name = tools.getArticleName(md5_hash, start_page,end_page)
galley_tag = self.createGalleyXML(doc, pdf_name)
article_tag.appendChild(galley_tag)
return article_tag