def generate_html(bib_csl_data, style_name='harvard1'):
assert bib_csl_data
bib_source = bib_csl_data
bib_style = CitationStylesStyle(style_name, validate=False)
bibliography = CitationStylesBibliography(
bib_style, bib_source, formatter.html)
bib_cites = [Citation([CitationItem(item)]) for item in bib_source]
for item in bib_cites:
bibliography.register(item)
# FIXME: Can this be avoided?
for item in bib_cites:
bibliography.cite(item, _cite_warn)
out = ''
bibliography.sort()
for item in bibliography.bibliography():
line = '<p>' + ''.join(item) + '</p>\n'
out += line
return out
class RFIC2009Paper(Document):
rngschema = 'rfic.rng'
namespace = 'http://www.mos6581.org/ns/rficpaper'
def __init__(self, filename, bibliography_source):
super().__init__(backend=pdf)
self.styles = styles
parser = xml_frontend.Parser(CustomElement,
self.namespace,
schema=self.rngschema)
xml_tree = parser.parse(filename)
self.root = xml_tree.getroot()
bibliography_style = CitationStylesStyle('ieee.csl')
self.bibliography = CitationStylesBibliography(bibliography_style,
bibliography_source,
csl_formatter)
authors = [author.text for author in self.root.head.authors.author]
if len(authors) > 1:
self.author = ', '.join(authors[:-1]) + ', and ' + authors[-1]
else:
self.author = authors[0]
self.title = self.root.head.title.text
self.keywords = [term.text for term in self.root.head.indexterms.term]
self.parse_input()
def parse_input(self):
self.title_par = Paragraph(self.title, style='title')
self.author_par = Paragraph(self.author, style='author')
self.affiliation_par = Paragraph(self.root.head.affiliation.text,
style='affiliation')
self.content = Chain(self)
self.content << Abstract(self.root.head.abstract.text)
self.content << IndexTerms(self.keywords)
toc_heading = Heading('Table of Contents', style='unnumbered')
toc = TableOfContents()
self.content << rt.Section([toc_heading, toc])
for element in self.root.body.getchildren():
self.content << element.process()
bib_heading = Heading('References', style='unnumbered')
self.bibliography.sort()
bib = Bibliography(self.bibliography)
self.content << rt.Section([bib_heading, bib])
def setup(self):
self.page_count = 1
page = RFICPage(self, first=True)
self.add_page(page, self.page_count)
page.title_box << self.title_par
page.title_box << self.author_par
page.title_box << self.affiliation_par
def new_page(self, chains):
page = RFICPage(self)
self.page_count += 1
self.add_page(page, self.page_count)
class RFIC2009Paper(Document):
rngschema = 'rfic.rng'
namespace = 'http://www.mos6581.org/ns/rficpaper'
def __init__(self, filename, bibliography_source):
super().__init__(backend=pdf)
self.styles = styles
parser = xml_frontend.Parser(CustomElement, self.namespace,
schema=self.rngschema)
xml_tree = parser.parse(filename)
self.root = xml_tree.getroot()
bibliography_style = CitationStylesStyle('ieee.csl')
self.bibliography = CitationStylesBibliography(bibliography_style,
bibliography_source,
csl_formatter)
authors = [author.text for author in self.root.head.authors.author]
if len(authors) > 1:
self.author = ', '.join(authors[:-1]) + ', and ' + authors[-1]
else:
self.author = authors[0]
self.title = self.root.head.title.text
self.keywords = [term.text for term in self.root.head.indexterms.term]
self.parse_input()
def parse_input(self):
self.title_par = Paragraph(self.title, style='title')
self.author_par = Paragraph(self.author, style='author')
self.affiliation_par = Paragraph(self.root.head.affiliation.text,
style='affiliation')
self.content = Chain(self)
self.content << Abstract(self.root.head.abstract.text)
self.content << IndexTerms(self.keywords)
toc_heading = Heading('Table of Contents', style='unnumbered')
toc = TableOfContents()
self.content << rt.Section([toc_heading, toc])
for element in self.root.body.getchildren():
self.content << element.process()
bib_heading = Heading('References', style='unnumbered')
self.bibliography.sort()
bib = Bibliography(self.bibliography)
self.content << rt.Section([bib_heading, bib])
def setup(self):
self.page_count = 1
page = RFICPage(self, first=True)
self.add_page(page, self.page_count)
page.title_box << self.title_par
page.title_box << self.author_par
page.title_box << self.affiliation_par
def new_page(self, chains):
page = RFICPage(self)
self.page_count += 1
self.add_page(page, self.page_count)
class ProcessorTest(object):
"""Parses atest fixture and provides a method for processing the tests
defined in it."""
bib_prefix = '<div class="csl-bib-body">'
bib_suffix = '</div>'
item_prefix = ' <div class="csl-entry">'
item_suffix = '</div>'
def __init__(self, filename):
self.csl_test = CslTest({}, None, (filename, ),
os.path.basename(filename))
self.csl_test.parse()
csl_io = io.BytesIO(utf_8_encode(self.data['csl'])[0])
self.style = CitationStylesStyle(csl_io)
self._fix_input(self.data['input'])
self.references = [item['id'] for item in self.data['input']]
self.references_dict = CiteProcJSON(self.data['input'])
self.bibliography = CitationStylesBibliography(self.style,
self.references_dict)
self.expected = self.data['result'].splitlines()
@property
def data(self):
return self.csl_test.data
@staticmethod
def _fix_input(input_data):
for i, ref in enumerate(input_data):
if 'id' not in ref:
ref['id'] = i
if 'type' not in ref:
ref['type'] = 'book'
def execute(self):
if self.data['citation_items']:
citations = [
self.parse_citation(item)
for item in self.data['citation_items']
]
elif self.data['citations']:
citations = []
for cit in self.data['citations']:
cit = cit[0]
citation_items = [
self.parse_citation_item(cititem)
for cititem in cit['citationItems']
]
citation = Citation(citation_items)
if 'citationID' in cit:
citation.key = cit['citationID']
citation.note_index = cit['properties']['noteIndex']
citations.append(citation)
elif self.data['bibentries']:
citation_items = [
self.parse_citation_item({'id': entry})
for entry in self.data['bibentries'][-1]
]
citations = [Citation(citation_items)]
else:
citation_items = [
self.parse_citation_item({'id': ref})
for ref in self.references
]
citations = [Citation(citation_items)]
for citation in citations:
self.bibliography.register(citation)
if self.style.has_bibliography():
self.bibliography.sort()
results = []
do_nothing = lambda x: None # callback passed to cite()
if self.data['mode'] == 'citation':
if self.data['citations']:
for i, citation in enumerate(citations):
if i == len(citations) - 1:
dots_or_other = '>>'
else:
dots_or_other = '..'
results.append(
'{}[{}] '.format(dots_or_other, i) +
self.bibliography.cite(citation, do_nothing))
else:
for citation in citations:
results.append(self.bibliography.cite(
citation, do_nothing))
elif self.data['mode'] in ('bibliography', 'bibliography-nosort'):
results.append(self.bib_prefix)
for entry in self.bibliography.bibliography():
text = self.item_prefix + str(entry) + self.item_suffix
results.append(text)
results.append(self.bib_suffix)
return results
def parse_citation(self, citation_data):
citation_items = []
for item in citation_data:
citation_item = self.parse_citation_item(item)
citation_items.append(citation_item)
return Citation(citation_items)
def parse_citation_item(self, citation_item_data):
options = {}
for key, value in citation_item_data.items():
python_key = key.replace('-', '_')
if python_key == 'id':
reference_key = str(value)
continue
elif python_key == 'locator':
try:
options['locator'] = Locator(citation_item_data['label'],
value)
except KeyError:
# some tests don't specify the label
options['locator'] = Locator('page', value)
elif python_key == 'label':
pass
else:
options[python_key] = value
return CitationItem(reference_key, **options)
class ProcessorTest(object):
def __init__(self, filename):
with open(filename, encoding='UTF-8') as f:
self.json_data = json.load(f)
csl_io = io.BytesIO(utf_8_encode(self.json_data['csl'])[0])
self.style = CitationStylesStyle(csl_io)
self._fix_input(self.json_data['input'])
self.references = [item['id'] for item in self.json_data['input']]
self.references_dict = CiteProcJSON(self.json_data['input'])
self.bibliography = CitationStylesBibliography(self.style,
self.references_dict)
self.expected = self.json_data['result'].splitlines()
@staticmethod
def _fix_input(input_data):
for i, ref in enumerate(input_data):
if 'id' not in ref:
ref['id'] = i
if 'type' not in ref:
ref['type'] = 'book'
def execute(self):
if self.json_data['citation_items']:
citations = [self.parse_citation(item)
for item in self.json_data['citation_items']]
elif self.json_data['citations']:
citations = []
for cit in self.json_data['citations']:
cit = cit[0]
citation_items = [self.parse_citation_item(cititem)
for cititem in cit['citationItems']]
citation = Citation(citation_items)
citation.key = cit['citationID']
citation.note_index = cit['properties']['noteIndex']
citations.append(citation)
elif self.json_data['bibentries']:
citation_items = [self.parse_citation_item({'id': entry})
for entry in self.json_data['bibentries'][-1]]
citations = [Citation(citation_items)]
else:
citation_items = [self.parse_citation_item({'id': ref})
for ref in self.references]
citations = [Citation(citation_items)]
for citation in citations:
self.bibliography.register(citation)
if self.style.has_bibliography():
self.bibliography.sort()
results = []
do_nothing = lambda x: None # callback passed to cite()
if self.json_data['mode'] == 'citation':
if self.json_data['citations']:
for i, citation in enumerate(citations):
if i == len(citations) - 1:
dots_or_other = '>>'
else:
dots_or_other = '..'
results.append('{}[{}] '.format(dots_or_other, i) +
self.bibliography.cite(citation, do_nothing))
else:
for citation in citations:
results.append(self.bibliography.cite(citation, do_nothing))
elif self.json_data['mode'] in ('bibliography', 'bibliography-nosort'):
results.append(self.bibliography.bibliography())
return results
def parse_citation(self, citation_data):
citation_items = []
for item in citation_data:
citation_item = self.parse_citation_item(item)
citation_items.append(citation_item)
return Citation(citation_items)
def parse_citation_item(self, citation_item_data):
options = {}
for key, value in citation_item_data.items():
python_key = key.replace('-', '_')
if python_key == 'id':
reference_key = str(value)
continue
elif python_key == 'locator':
try:
options['locator'] = Locator(citation_item_data['label'],
value)
except KeyError:
# some tests don't specify the label
options['locator'] = Locator('page', value)
elif python_key == 'label':
pass
else:
options[python_key] = value
return CitationItem(reference_key, **options)
class RFIC2009Paper(Document):
rngschema = 'rfic.rng'
namespace = 'http://www.mos6581.org/ns/rficpaper'
def __init__(self, filename, bibliography_source):
super().__init__(backend=pdf)
parser = xml_frontend.Parser(CustomElement,
self.namespace,
schema=self.rngschema)
xml_tree = parser.parse(filename)
self.root = xml_tree.getroot()
bibliography_style = CitationStylesStyle('ieee.csl')
self.bibliography = CitationStylesBibliography(bibliography_style,
bibliography_source,
csl_formatter)
authors = [author.text for author in self.root.head.authors.author]
if len(authors) > 1:
self.author = ', '.join(authors[:-1]) + ', and ' + authors[-1]
else:
self.author = authors[0]
self.title = self.root.head.title.text
self.keywords = [term.text for term in self.root.head.indexterms.term]
self.parse_input()
def parse_input(self):
self.title_par = Paragraph(self.title, style=styles['title'])
self.author_par = Paragraph(self.author, style=styles['author'])
self.affiliation_par = Paragraph(self.root.head.affiliation.text,
style=styles['affiliation'])
self.content = Chain(self)
self.content << Abstract(self.root.head.abstract.text)
self.content << IndexTerms(self.keywords)
self.content << Heading(
self, 'Table of Contents', style=styles['unnumbered'], level=1)
toc = TableOfContents(
style=styles['toc'],
styles=[styles['toc1'], styles['toc2'], styles['toc3']])
self.content << toc
for section in self.root.body.section:
for flowable in section.process(self):
toc.register(flowable)
self.content << flowable
try:
for flowable in self.root.body.acknowledgement.process(self):
toc.register(flowable)
self.content << flowable
except AttributeError:
pass
self.content << Heading(
self, 'References', style=styles['unnumbered'], level=1)
self.bibliography.sort()
self.content << self.bibliography.bibliography()
def setup(self):
self.page_count = 1
page = RFICPage(self, first=True)
self.add_page(page, self.page_count)
page.title_box << self.title_par
page.title_box << self.author_par
page.title_box << self.affiliation_par
def new_page(self, chains):
page = RFICPage(self)
self.page_count += 1
self.add_page(page, self.page_count)
class RFIC2009Paper(Document):
rngschema = 'rfic.rng'
namespace = 'http://www.mos6581.org/ns/rficpaper'
def __init__(self, filename, bibliography_source):
super().__init__(backend=pdf)
parser = xml_frontend.Parser(CustomElement, self.namespace,
schema=self.rngschema)
xml_tree = parser.parse(filename)
self.root = xml_tree.getroot()
bibliography_style = CitationStylesStyle('ieee.csl')
self.bibliography = CitationStylesBibliography(bibliography_style,
bibliography_source,
csl_formatter)
authors = [author.text for author in self.root.head.authors.author]
if len(authors) > 1:
self.author = ', '.join(authors[:-1]) + ', and ' + authors[-1]
else:
self.author = authors[0]
self.title = self.root.head.title.text
self.keywords = [term.text for term in self.root.head.indexterms.term]
self.parse_input()
def parse_input(self):
self.title_par = Paragraph(self.title, style=styles['title'])
self.author_par = Paragraph(self.author, style=styles['author'])
self.affiliation_par = Paragraph(self.root.head.affiliation.text,
style=styles['affiliation'])
self.content = Chain(self)
self.content << Abstract(self.root.head.abstract.text)
self.content << IndexTerms(self.keywords)
self.content << Heading(self, 'Table of Contents',
style=styles['unnumbered'], level=1)
toc = TableOfContents(style=styles['toc'],
styles=[styles['toc1'], styles['toc2'],
styles['toc3']])
self.content << toc
for section in self.root.body.section:
for flowable in section.process(self):
toc.register(flowable)
self.content << flowable
try:
for flowable in self.root.body.acknowledgement.process(self):
toc.register(flowable)
self.content << flowable
except AttributeError:
pass
self.content << Heading(self, 'References', style=styles['unnumbered'],
level=1)
self.bibliography.sort()
self.content << self.bibliography.bibliography()
def setup(self):
self.page_count = 1
page = RFICPage(self, first=True)
self.add_page(page, self.page_count)
page.title_box << self.title_par
page.title_box << self.author_par
page.title_box << self.affiliation_par
def new_page(self, chains):
page = RFICPage(self)
self.page_count += 1
self.add_page(page, self.page_count)
class ProcessorTest(object):
def __init__(self, filename):
with open(filename, encoding='UTF-8') as f:
self.json_data = json.load(f)
csl_io = io.BytesIO(utf_8_encode(self.json_data['csl'])[0])
self.style = CitationStylesStyle(csl_io)
self._fix_input(self.json_data['input'])
self.references = [item['id'] for item in self.json_data['input']]
self.references_dict = CiteProcJSON(self.json_data['input'])
self.bibliography = CitationStylesBibliography(self.style,
self.references_dict)
self.expected = self.json_data['result'].splitlines()
@staticmethod
def _fix_input(input_data):
for i, ref in enumerate(input_data):
if 'id' not in ref:
ref['id'] = i
if 'type' not in ref:
ref['type'] = 'book'
def execute(self):
if self.json_data['citation_items']:
citations = [
self.parse_citation(item)
for item in self.json_data['citation_items']
]
elif self.json_data['citations']:
citations = []
for cit in self.json_data['citations']:
cit = cit[0]
citation_items = [
self.parse_citation_item(cititem)
for cititem in cit['citationItems']
]
citation = Citation(citation_items)
citation.key = cit['citationID']
citation.note_index = cit['properties']['noteIndex']
citations.append(citation)
elif self.json_data['bibentries']:
citation_items = [
self.parse_citation_item({'id': entry})
for entry in self.json_data['bibentries'][-1]
]
citations = [Citation(citation_items)]
else:
citation_items = [
self.parse_citation_item({'id': ref})
for ref in self.references
]
citations = [Citation(citation_items)]
for citation in citations:
self.bibliography.register(citation)
if self.style.has_bibliography():
self.bibliography.sort()
results = []
do_nothing = lambda x: None # callback passed to cite()
if self.json_data['mode'] == 'citation':
if self.json_data['citations']:
for i, citation in enumerate(citations):
if i == len(citations) - 1:
dots_or_other = '>>'
else:
dots_or_other = '..'
results.append(
'{}[{}] '.format(dots_or_other, i) +
self.bibliography.cite(citation, do_nothing))
else:
for citation in citations:
results.append(self.bibliography.cite(
citation, do_nothing))
elif self.json_data['mode'] in ('bibliography', 'bibliography-nosort'):
results.append(self.bibliography.bibliography())
return results
def parse_citation(self, citation_data):
citation_items = []
for item in citation_data:
citation_item = self.parse_citation_item(item)
citation_items.append(citation_item)
return Citation(citation_items)
def parse_citation_item(self, citation_item_data):
options = {}
for key, value in citation_item_data.items():
python_key = key.replace('-', '_')
if python_key == 'id':
reference_key = str(value)
continue
elif python_key == 'locator':
try:
options['locator'] = Locator(citation_item_data['label'],
value)
except KeyError:
# some tests don't specify the label
options['locator'] = Locator('page', value)
elif python_key == 'label':
pass
else:
options[python_key] = value
return CitationItem(reference_key, **options)
formatter.html)
######################################################################################################
######################################################################################################
####### docx document object
doc = docx.Document()
doc.add_heading("References", 0)
print("References")
for item in bib_source:
citation = Citation([CitationItem(item)])
bibliography.register(citation)
item_string = bibliography.cite(citation, warn)
html_helper = HTMLHelper()
bibliography.sort()
for item in bibliography.bibliography():
######################################################################################################
######################################################################################################
####### take out extra characters in citation, that are artifacts of the citeproc citation
####### creation process with some of our bib records
#######
####### Also make the editor label plural if there are multiple ("eds.")
item = str(item)
item = item.replace(", n.d..", "")
item = item.replace(',,', ',')
item = item.replace('..', '.')
item = re.sub(r'([^<]+?and[^<]+?)(ed.)(\s+<i>)', r'\1eds.\3', item)
item = item.replace(',.', '.')
######################################################################################################
