def _generate_pdf(self, rst_file_path, result_pdf_path):
"""
Generates a PDF file based on the input RST file.
"""
if not os.path.exists(rst_file_path):
raise DocGenerateException(
"Provided RST file: %s does not exists." % rst_file_path)
# We suppose all RST files have references relative to their folder
# So we have to force rst2pdf to be executed in the folder where RST file resides.
basedir = os.path.split(rst_file_path)[0]
baseurl = "file://" + basedir
r2p = RstToPdf(style_path=[self._styles_folder],
stylesheets=[self.PDF_STYLE],
basedir=basedir,
baseurl=baseurl,
breakside="any")
try:
with open(rst_file_path) as file_rst:
content = file_rst.read()
r2p.createPdf(text=content,
source_path=rst_file_path,
output=result_pdf_path)
self.logger.debug("PDF file %s generated successfully." %
result_pdf_path)
except Exception, ex:
self.logger.exception("Could not generate PDF documentation")
raise DocGenerateException("Could not generate PDF documentation",
ex)
def run():
inpdir=os.path.abspath('./input')
outdir=os.path.abspath('./tmp')
# Discard output, this is not about whether things
# work or not, that's testing ;-)
for f in os.listdir(inpdir):
if f.endswith('.txt'): # Test case
print 'Running: ', f
sheet=os.path.join(inpdir, f[:-4]+'.style')
if os.path.exists(sheet):
sheet=[sheet]
else:
sheet=[]
r2p=RstToPdf(stylesheets=sheet)
try:
fname=os.path.join(inpdir, f)
r2p.createPdf(
text=open(fname).read(),
output=os.path.join(outdir,f+'.pdf'),
source_path=fname,
)
except:
print 'FAIL'
def download(self, pageid):
p = model.FlatPage.by_id(pageid) or abort(404)
out = BytesIO()
rst2pdf = RstToPdf()
rst2pdf.createPdf(p.content, output=out)
out.seek(0)
return out.read()
def rst2pdf(content, theme=None):
topdf = RstToPdf(basedir=current_app.config.root_path, breaklevel=0)
buf = BytesIO()
if not content:
content = '\0'
content_utf8 = utf8codec.encode(content)[0]
topdf.createPdf(text=content_utf8, output=buf, compressed=False)
return buf.getvalue()
def pdf_output(locale, **extra_settings):
if "styleshees" not in extra_settings:
extra_settings["stylesheets"] = load_stylesheets("*.style")
if "breaklevel" not in extra_settings:
extra_settings["breaklevel"] = 0
parser = RstToPdf(**extra_settings)
with closing(StringIO()) as fp:
parser.createPdf(text=split_rst_file(locale), output=fp)
rs = fp.getvalue()
return rs
def rst2pdf(content, theme=None):
topdf = RstToPdf(basedir=current_app.config.root_path, breaklevel=0)
buf = StringIO()
if not content:
content = '\0'
content_utf8 = utf8codec.encode(content)[0]
topdf.createPdf(text=content_utf8, output=buf, compressed=False)
return buf.getvalue()
def download(self, pageid):
from rst2pdf.createpdf import RstToPdf
p = model.FlatPage.by_id(pageid) or abort(404)
out = BytesIO()
rst2pdf = RstToPdf()
rst2pdf.createPdf(p.content, output=out)
out.seek(0)
return out.read()
class PdfGenerator(Generator):
"""Generate PDFs on the output dir, for all articles and pages coming from
rst"""
def __init__(self, *args, **kwargs):
super(PdfGenerator, self).__init__(*args, **kwargs)
try:
from rst2pdf.createpdf import RstToPdf
if 'PDF_STYLE_PATH' in self.settings.keys():
pdf_style_path = os.path.join(self.settings['PDF_STYLE_PATH'])
else:
pdf_style_path = ''
if 'PDF_STYLE' in self.settings.keys():
pdf_style = self.settings.get('PDF_STYLE', 'twelvepoint')
self.pdfcreator = RstToPdf(breakside=0,
stylesheets=[pdf_style],
style_path=[pdf_style_path])
except ImportError:
raise Exception("unable to find rst2pdf")
def _create_pdf(self, obj, output_path):
if obj.source_path.endswith('.rst'):
filename = obj.slug + ".pdf"
output_pdf = os.path.join(output_path, filename)
# print('Generating pdf for', obj.source_path, 'in', output_pdf)
with open(obj.source_path) as f:
self.pdfcreator.createPdf(text=f.read(), output=output_pdf)
logger.info(' [ok] writing %s' % output_pdf)
def generate_context(self):
pass
def generate_output(self, writer=None):
# we don't use the writer passed as argument here
# since we write our own files
logger.info(' Generating PDF files...')
pdf_path = os.path.join(self.output_path, 'pdf')
if not os.path.exists(pdf_path):
try:
os.mkdir(pdf_path)
except OSError:
logger.error("Couldn't create the pdf output folder in " +
pdf_path)
for article in self.context['articles']:
self._create_pdf(article, pdf_path)
for page in self.context['pages']:
self._create_pdf(page, pdf_path)
class PdfGenerator(Generator):
"""Generate PDFs on the output dir, for all articles and pages coming from
rst"""
def __init__(self, *args, **kwargs):
super(PdfGenerator, self).__init__(*args, **kwargs)
try:
from rst2pdf.createpdf import RstToPdf
if 'PDF_STYLE_PATH' in self.settings.keys():
pdf_style_path = os.path.join(self.settings['PDF_STYLE_PATH'])
else:
pdf_style_path = ''
if 'PDF_STYLE' in self.settings.keys():
pdf_style = self.settings.get('PDF_STYLE', 'twelvepoint')
self.pdfcreator = RstToPdf(breakside=0,
stylesheets=[pdf_style],
style_path=[pdf_style_path])
except ImportError:
raise Exception("unable to find rst2pdf")
def _create_pdf(self, obj, output_path):
if obj.source_path.endswith('.rst'):
filename = obj.slug + ".pdf"
output_pdf = os.path.join(output_path, filename)
# print('Generating pdf for', obj.source_path, 'in', output_pdf)
with open(obj.source_path) as f:
self.pdfcreator.createPdf(text=f.read(), output=output_pdf)
logger.info(' [ok] writing %s' % output_pdf)
def generate_context(self):
pass
def generate_output(self, writer=None):
# we don't use the writer passed as argument here
# since we write our own files
logger.info(' Generating PDF files...')
pdf_path = os.path.join(self.output_path, 'pdf')
if not os.path.exists(pdf_path):
try:
os.mkdir(pdf_path)
except OSError:
logger.error("Couldn't create the pdf output folder in " +
pdf_path)
for article in self.context['articles']:
self._create_pdf(article, pdf_path)
for page in self.context['pages']:
self._create_pdf(page, pdf_path)
def get_submission_confirmation_report(submission):
sections = []
for section, fields in SUBMIT_CONFIRMATION:
cv_items = []
for field in fields:
model_field = Submission._meta.get_field_by_name(field)[0]
name = model_field.verbose_name
if getattr(model_field, 'choices', None):
value = getattr(submission, 'get_%s_display' % field)()
else:
value = getattr(submission, field)
cv_items.append((name, value))
sections.append((section, cv_items))
permissions = []
for field in SUBMIT_CONFIRMATION_PERMISSIONS:
value = getattr(submission, field)
if value != 1:
continue
model_field = Submission._meta.get_field_by_name(field)[0]
name = model_field.verbose_name
permissions.append(name)
if permissions:
permissions = [(_('Permissions'), permissions)]
docs = os.path.join(APP_ROOT, 'docs')
lang = translation.get_language().lower()
submission_rst = os.path.join(
docs, SUBMISSION_RST.get(lang, DEFAULT_SUBMISSION_RST))
with io.open(submission_rst, encoding='utf-8') as submission_head:
rst_data = submission_head.read() % _get_rst_fields(
sections, permissions)
from rst2pdf.createpdf import RstToPdf
pdf_creator = RstToPdf(
stylesheets=[os.path.join(docs, 'submission2.stylesheet')],
font_path=['/usr/share/fonts/TTF/'],
breaklevel=0,
)
with io.open('/tmp/cpm.rst', 'w', encoding='utf-8') as w:
w.write(rst_data)
pdf_content = StringIO()
pdf_creator.createPdf(text=rst_data, output=pdf_content)
return pdf_content.getvalue()
def generate_random_act_attach(cls, act, n=1):
"""
generates n random pdf attachments for an act
title and body, are built using a lorem ipsum generator
the attachments are built with text and a pdf file upload is simulated
"""
# random title and body generation
g = lipsum.MarkupGenerator()
for i in range(1, n + 1):
title = g.generate_sentences_plain(1)
body = g.generate_paragraphs_plain(random.randint(3, 50),
start_with_lorem=True)
# attach object created and saved
attach = Attach(act=act, title=title, text=body)
attach.save()
#
# pdf document generation and upload in proper directory
#
# document setup
if act is not None:
header = "Atto %s - ###Title###" % (act.idnum, )
else:
header = "###Title###"
footer = "###Section### - Pagina: ###Page###"
text = "%s\n%s\n%s\n" % ("=" * int(len(title) * 1.5), title,
"=" * int(len(title) * 1.5))
text += body
# pdf saved into tmp file
file_name = "%s_%s.pdf" % (act.idnum, attach.id)
tmp_file = os.path.join("/tmp", file_name)
rst2pdf = RstToPdf(breaklevel=0, header=header, footer=footer)
rst2pdf.createPdf(text=text, output=tmp_file)
# file is saved as attribute of the attach object and moved in the right path
# see https://docs.djangoproject.com/en/dev/ref/models/fields/#django.db.models.FieldFile.save
f = open(tmp_file, 'r')
attach.file.save(file_name, File(f))
attach.save()
os.remove(tmp_file)
print "%s: %s uploaded" % (i, file_name)
def generate_random_act_attach(cls, act, n=1):
"""
generates n random pdf attachments for an act
title and body, are built using a lorem ipsum generator
the attachments are built with text and a pdf file upload is simulated
"""
# random title and body generation
g = lipsum.MarkupGenerator()
for i in range(1, n+1):
title = g.generate_sentences_plain(1)
body = g.generate_paragraphs_plain(random.randint(3, 50), start_with_lorem=True)
# attach object created and saved
attach = Attach(act=act, title=title, text=body)
attach.save()
#
# pdf document generation and upload in proper directory
#
# document setup
if act is not None:
header = "Atto %s - ###Title###" % (act.idnum,)
else:
header = "###Title###"
footer = "###Section### - Pagina: ###Page###"
text = "%s\n%s\n%s\n" % ("=" * int(len(title)*1.5), title, "=" * int(len(title)*1.5))
text += body
# pdf saved into tmp file
file_name = "%s_%s.pdf" % (act.idnum, attach.id)
tmp_file = os.path.join("/tmp", file_name)
rst2pdf = RstToPdf(breaklevel=0, header=header, footer=footer)
rst2pdf.createPdf(text=text,
output=tmp_file)
# file is saved as attribute of the attach object and moved in the right path
# see https://docs.djangoproject.com/en/dev/ref/models/fields/#django.db.models.FieldFile.save
f = open(tmp_file, 'r')
attach.file.save(file_name, File(f))
attach.save()
os.remove(tmp_file)
print "%s: %s uploaded" % (i, file_name)
def get_submission_confirmation_report(submission):
sections = []
for section, fields in SUBMIT_CONFIRMATION:
cv_items = []
for field in fields:
model_field = Submission._meta.get_field_by_name(field)[0]
name = model_field.verbose_name
if getattr(model_field, 'choices', None):
value = getattr(submission, 'get_%s_display' % field)()
else:
value = getattr(submission, field)
cv_items.append((name, value))
sections.append((section, cv_items))
permissions = []
for field in SUBMIT_CONFIRMATION_PERMISSIONS:
value = getattr(submission, field)
if value != 1:
continue
model_field = Submission._meta.get_field_by_name(field)[0]
name = model_field.verbose_name
permissions.append(name)
if permissions:
permissions = [(_('Permissions'), permissions)]
docs = os.path.join(APP_ROOT, 'docs')
lang = translation.get_language().lower()
submission_rst = os.path.join(
docs, SUBMISSION_RST.get(lang, DEFAULT_SUBMISSION_RST))
with io.open(submission_rst, encoding='utf-8') as submission_head:
rst_data = submission_head.read() % _get_rst_fields(
sections, permissions)
from rst2pdf.createpdf import RstToPdf
pdf_creator = RstToPdf(
stylesheets=[os.path.join(docs, 'submission2.stylesheet')],
font_path=['/usr/share/fonts/TTF/'],
breaklevel=0,
)
with io.open('/tmp/cpm.rst', 'w', encoding='utf-8') as w:
w.write(rst_data)
pdf_content = StringIO()
pdf_creator.createPdf(text=rst_data, output=pdf_content)
return pdf_content.getvalue()
class PdfGenerator(Generator):
"""Generate PDFs on the output dir, for all articles and pages coming from
rst"""
def __init__(self, *args, **kwargs):
super(PdfGenerator, self).__init__(*args, **kwargs)
try:
from rst2pdf.createpdf import RstToPdf
pdf_style_path = (
os.path.join(self.settings["PDF_STYLE_PATH"]) if "PDF_STYLE_PATH" in self.settings.keys() else ""
)
pdf_style = self.settings["PDF_STYLE"] if "PDF_STYLE" in self.settings.keys() else "twelvepoint"
self.pdfcreator = RstToPdf(breakside=0, stylesheets=[pdf_style], style_path=[pdf_style_path])
except ImportError:
raise Exception("unable to find rst2pdf")
def _create_pdf(self, obj, output_path):
if obj.filename.endswith(".rst"):
filename = obj.slug + ".pdf"
output_pdf = os.path.join(output_path, filename)
# print "Generating pdf for", obj.filename, " in ", output_pdf
with open(obj.filename) as f:
self.pdfcreator.createPdf(text=f.read(), output=output_pdf)
logger.info(" [ok] writing %s" % output_pdf)
def generate_context(self):
pass
def generate_output(self, writer=None):
# we don't use the writer passed as argument here
# since we write our own files
logger.info(" Generating PDF files...")
pdf_path = os.path.join(self.output_path, "pdf")
if not os.path.exists(pdf_path):
try:
os.mkdir(pdf_path)
except OSError:
logger.error("Couldn't create the pdf output folder in " + pdf_path)
for article in self.context["articles"]:
self._create_pdf(article, pdf_path)
for page in self.context["pages"]:
self._create_pdf(page, pdf_path)
def test_rst2pdf(self):
assert RstToPdf, 'rst2pdf not installed - cannot test compatibility.'
rst2pdf = RstToPdf(breaklevel=0)
rst2pdf.styles['heading1'].spaceBefore = 36
buffer = BytesIO()
rst2pdf.createPdf(text, output=buffer)
pdf = buffer.getvalue()
buffer.close()
assert b'ReportLab generated PDF document' in pdf
assert b'Rst2Pdf MultiBuild Test Case For Wordaxe' in pdf
assert b'Test Section' in pdf
assert blah.encode() in pdf
class PdfGenerator(Generator):
"""Generate PDFs on the output dir, for all articles and pages coming from
rst"""
def __init__(self, *args, **kwargs):
try:
from rst2pdf.createpdf import RstToPdf
self.pdfcreator = RstToPdf(breakside=0,
stylesheets=['twelvepoint'])
except ImportError:
raise Exception("unable to find rst2pdf")
super(PdfGenerator, self).__init__(*args, **kwargs)
def _create_pdf(self, obj, output_path):
if obj.filename.endswith(".rst"):
filename = obj.slug + ".pdf"
output_pdf = os.path.join(output_path, filename)
# print "Generating pdf for", obj.filename, " in ", output_pdf
with open(obj.filename) as f:
self.pdfcreator.createPdf(text=f, output=output_pdf)
logger.info(u' [ok] writing %s' % output_pdf)
def generate_context(self):
pass
def generate_output(self, writer=None):
# we don't use the writer passed as argument here
# since we write our own files
logger.info(u' Generating PDF files...')
pdf_path = os.path.join(self.output_path, 'pdf')
if not os.path.exists(pdf_path):
try:
os.mkdir(pdf_path)
except OSError:
logger.error("Couldn't create the pdf output folder in " +
pdf_path)
pass
for article in self.context['articles']:
self._create_pdf(article, pdf_path)
for page in self.context['pages']:
self._create_pdf(page, pdf_path)
class PdfGenerator(Generator):
"""Generate PDFs on the output dir, for all articles and pages coming from
rst"""
def __init__(self, *args, **kwargs):
try:
from rst2pdf.createpdf import RstToPdf
self.pdfcreator = RstToPdf(breakside=0,
stylesheets=['twelvepoint'])
except ImportError:
raise Exception("unable to find rst2pdf")
super(PdfGenerator, self).__init__(*args, **kwargs)
def _create_pdf(self, obj, output_path):
if obj.filename.endswith(".rst"):
filename = obj.slug + ".pdf"
output_pdf = os.path.join(output_path, filename)
# print "Generating pdf for", obj.filename, " in ", output_pdf
with open(obj.filename) as f:
self.pdfcreator.createPdf(text=f, output=output_pdf)
logger.info(u' [ok] writing %s' % output_pdf)
def generate_context(self):
pass
def generate_output(self, writer=None):
# we don't use the writer passed as argument here
# since we write our own files
logger.info(u' Generating PDF files...')
pdf_path = os.path.join(self.output_path, 'pdf')
if not os.path.exists(pdf_path):
try:
os.mkdir(pdf_path)
except OSError:
logger.error("Couldn't create the pdf output folder in " + pdf_path)
pass
for article in self.context['articles']:
self._create_pdf(article, pdf_path)
for page in self.context['pages']:
self._create_pdf(page, pdf_path)
def produce_pdf(rst_content=None, doctree_content=None, filename=None):
"""produce a pdf content based of a given rst content
If filename is given, it will store the result using the given filename
if no filename is given, it will generate a pdf in /tmp/ with a random
name
"""
if filename is None:
filename = os.path.join(
"/tmp", ''.join([
random.choice(string.ascii_letters + string.digits)
for n in range(15)
]) + '.pdf')
r2p = RstToPdf(
stylesheets=['pdf.style'],
style_path=[os.path.join(os.path.dirname(__file__), 'styles')],
breaklevel=0,
splittables=True,
footer="""###Title### - ###Page###/###Total###""")
r2p.createPdf(text=rst_content, doctree=doctree_content, output=filename)
return filename
def produce_pdf(rst_content=None, doctree_content=None, filename=None):
"""produce a pdf content based of a given rst content
If filename is given, it will store the result using the given filename
if no filename is given, it will generate a pdf in /tmp/ with a random
name
"""
if filename is None:
filename = os.path.join(
"/tmp", ''.join([random.choice(string.ascii_letters +
string.digits) for n in range(15)]) + '.pdf')
r2p = RstToPdf(stylesheets=['pdf.style'],
style_path=[os.path.join(os.path.dirname(__file__),
'styles')],
breaklevel=0,
splittables=True,
footer="""###Title### - ###Page###/###Total###""")
r2p.createPdf(text=rst_content,
doctree=doctree_content,
output=filename)
return filename
def _generate_pdf(self, rst_file_path, result_pdf_path):
"""
Generates a PDF file based on the input RST file.
"""
if not os.path.exists(rst_file_path):
raise DocGenerateException("Provided RST file: %s does not exists." % rst_file_path)
# We suppose all RST files have references relative to their folder
# So we have to force rst2pdf to be executed in the folder where RST file resides.
basedir = os.path.split(rst_file_path)[0]
baseurl = "file://" + basedir
r2p = RstToPdf(style_path=[self._styles_folder], stylesheets=[self.PDF_STYLE],
basedir=basedir, baseurl=baseurl, breakside="any")
try:
with open(rst_file_path) as file_rst:
content = file_rst.read()
r2p.createPdf(text=content, source_path=rst_file_path, output=result_pdf_path)
self.logger.debug("PDF file %s generated successfully." % result_pdf_path)
except Exception, ex:
self.logger.exception("Could not generate PDF documentation")
raise DocGenerateException("Could not generate PDF documentation", ex)
def document(report, fmt='html'):
'''
Creates a document in the desired `fmt`. Defaults to html.
'''
if fmt == 'csv':
return report2csv(report)
doctree = doctree_factory(report, fmt=fmt)
dt_settings = {
'input_encoding': 'unicode',
}
if fmt == 'pdf':
if not RST2PDF:
raise Exception('rst2pdf is not available')
return None
buff = StringIO()
rst2pdf = RstToPdf()
rst2pdf.createPdf(doctree=doctree, output=buff)
return buff.getvalue()
if fmt in DOCUTILS_WRITER_NAMES:
if fmt == 'odt':
fmt = 'odf_odt' # Docutils writer name
if fmt in ('txt', 'rst'):
return gen_rst(doctree, 0)
return publish_from_doctree(
doctree,
writer_name=fmt,
settings_overrides=dt_settings
)
else:
raise Exception('Format not supported. Not in %s' % (
SUPPORTED_FORMATS,
)
)
class PdfGenerator(Generator):
"Generate PDFs on the output dir, for all articles and pages"
supported_md_fields = ['date']
def __init__(self, *args, **kwargs):
super(PdfGenerator, self).__init__(*args, **kwargs)
if 'PDF_STYLE_PATH' in self.settings:
pdf_style_path = [self.settings['PDF_STYLE_PATH']]
else:
pdf_style_path = []
if 'PDF_STYLE' in self.settings:
pdf_style = [self.settings['PDF_STYLE']]
else:
pdf_style = []
self.pdfcreator = RstToPdf(breakside=0,
stylesheets=pdf_style,
style_path=pdf_style_path,
raw_html=True)
def _create_pdf(self, obj, output_path):
filename = obj.slug + '.pdf'
output_pdf = os.path.join(output_path, filename)
mdreader = MarkdownReader(self.settings)
_, ext = os.path.splitext(obj.source_path)
if ext == '.rst':
with open(obj.source_path, encoding='utf-8') as f:
text = f.read()
header = ''
elif ext[1:] in mdreader.file_extensions and mdreader.enabled:
text, meta = mdreader.read(obj.source_path)
header = ''
if 'title' in meta:
title = meta['title']
header = title + '\n' + '#' * len(title) + '\n\n'
del meta['title']
for k in meta.keys():
# We can't support all fields, so we strip the ones that won't
# look good
if k not in self.supported_md_fields:
del meta[k]
header += '\n'.join([':%s: %s' % (k, meta[k]) for k in meta])
header += '\n\n.. raw:: html\n\n\t'
text = text.replace('\n', '\n\t')
# rst2pdf casts the text to str and will break if it finds
# non-escaped characters. Here we nicely escape them to XML/HTML
# entities before proceeding
text = text.encode('ascii', 'xmlcharrefreplace')
else:
# We don't support this format
logger.warn('Ignoring unsupported file ' + obj.source_path)
return
logger.info(' [ok] writing %s' % output_pdf)
self.pdfcreator.createPdf(text=(header+text),
output=output_pdf)
def generate_context(self):
pass
def generate_output(self, writer=None):
# we don't use the writer passed as argument here
# since we write our own files
logger.info(' Generating PDF files...')
pdf_path = os.path.join(self.output_path, 'pdf')
if not os.path.exists(pdf_path):
try:
os.mkdir(pdf_path)
except OSError:
logger.error("Couldn't create the pdf output folder in " +
pdf_path)
for article in self.context['articles']:
self._create_pdf(article, pdf_path)
for page in self.context['pages']:
self._create_pdf(page, pdf_path)
class PdfGenerator(Generator):
"Generate PDFs on the output dir, for all articles and pages"
supported_md_fields = ["date"]
def __init__(self, *args, **kwargs):
super(PdfGenerator, self).__init__(*args, **kwargs)
if "PDF_STYLE_PATH" in self.settings:
pdf_style_path = [self.settings["PDF_STYLE_PATH"]]
else:
pdf_style_path = []
if "PDF_STYLE" in self.settings:
pdf_style = [self.settings["PDF_STYLE"]]
else:
pdf_style = []
self.pdfcreator = RstToPdf(breakside=0,
stylesheets=pdf_style,
style_path=pdf_style_path,
raw_html=True)
def _create_pdf(self, obj, output_path):
filename = obj.slug + ".pdf"
output_pdf = os.path.join(output_path, filename)
mdreader = MarkdownReader(self.settings)
_, ext = os.path.splitext(obj.source_path)
if ext == ".rst":
with open(obj.source_path, encoding="utf-8") as f:
text = f.read()
header = ""
elif ext[1:] in mdreader.file_extensions and mdreader.enabled:
text, meta = mdreader.read(obj.source_path)
header = ""
if "title" in meta:
title = meta["title"]
header = title + "\n" + "#" * len(title) + "\n\n"
del meta["title"]
for k in meta.keys():
# We can't support all fields, so we strip the ones that won't
# look good
if k not in self.supported_md_fields:
del meta[k]
header += "\n".join([":%s: %s" % (k, meta[k]) for k in meta])
header += "\n\n.. raw:: html\n\n\t"
text = text.replace("\n", "\n\t")
# rst2pdf casts the text to str and will break if it finds
# non-escaped characters. Here we nicely escape them to XML/HTML
# entities before proceeding
text = text.encode("ascii", "xmlcharrefreplace").decode()
else:
# We don't support this format
logger.warn("Ignoring unsupported file " + obj.source_path)
return
logger.info(" [ok] writing %s" % output_pdf)
self.pdfcreator.createPdf(text=(header + text), output=output_pdf)
def generate_context(self):
pass
def generate_output(self, writer=None):
# we don't use the writer passed as argument here
# since we write our own files
logger.info(" Generating PDF files...")
pdf_path = os.path.join(self.output_path, "pdf")
if not os.path.exists(pdf_path):
try:
os.mkdir(pdf_path)
except OSError:
logger.error("Couldn't create the pdf output folder in " +
pdf_path)
for article in self.context["articles"]:
self._create_pdf(article, pdf_path)
for page in self.context["pages"]:
self._create_pdf(page, pdf_path)
class PdfGenerator(Generator):
"""Generate PDFs on the output dir, for all articles and pages coming from
rst"""
def __init__(self, *args, **kwargs):
super(PdfGenerator, self).__init__(*args, **kwargs)
pdf_style_path = os.path.join(self.settings['PDF_STYLE_PATH'])
pdf_style = self.settings['PDF_STYLE']
self.pdfcreator = RstToPdf(breakside=0,
stylesheets=[pdf_style],
style_path=[pdf_style_path],
def_dpi=100)
def _create_pdf(self, obj, output_path):
if obj.source_path.endswith('.rst'):
filename = obj.slug + ".pdf"
output_pdf = os.path.join(output_path, filename)
print('Generating pdf for', obj.source_path, 'in', output_pdf)
with open(obj.source_path) as f:
self.pdfcreator.createPdf(text=f.read(), output=output_pdf)
logger.info(' [ok] writing %s' % output_pdf)
def _upload_figshare(self, obj, output_path):
if obj.source_path.endswith('.rst'):
filename = obj.slug + ".pdf"
output_pdf = os.path.join(output_path, filename)
client_key = '8BeN60jNpgmgIN6G8oaCXQ'
client_secret = 'oSj6EZkWChEifWOADJcKUw'
token_key = 'sZegoc5oOgPsXfeATZGvRggVLkqc9lrYFCI9pYvDWkZAsZegoc5oOgPsXfeATZGvRg'
token_secret = 'fifOafUWFAFcKxN6ZO9fbg'
oauth = OAuth1(client_key=client_key, client_secret=client_secret,
resource_owner_key=token_key, resource_owner_secret=token_secret,
signature_type = 'auth_header')
client = requests.session()
body = {'title':obj.title, 'description':obj.summary,'defined_type':'dataset'}
headers = {'content-type':'application/json'}
#response = client.post('http://api.figshare.com/v1/my_data/articles', auth=oauth, data=json.dumps(body), headers=headers)
#results = json.loads(response.content)
#print(results["doi"])
#article_id = results["article_id"]
article_id = 852126
body = {'category_id':77} # applied computer science
headers = {'content-type':'application/json'}
response = client.put('http://api.figshare.com/v1/my_data/articles/%d/categories' % article_id, auth=oauth,
data=json.dumps(body), headers=headers)
results = json.loads(response.content)
body = {'tag_name':'proceedings'}
headers = {'content-type':'application/json'}
response = client.put('http://api.figshare.com/v1/my_data/articles/%d/tags' % article_id, auth=oauth,
data=json.dumps(body), headers=headers)
results = json.loads(response.content)
authors = [author.strip() for author in obj.author.name.split(",")]
for author in authors:
print(author)
response = client.get('http://api.figshare.com/v1/my_data/authors?search_for=Kapil Arya', auth=oauth)
results = json.loads(response.content)
print(results)
if results["results"] == 0:
body = {'full_name':author}
headers = {'content-type':'application/json'}
response = client.post('http://api.figshare.com/v1/my_data/authors', auth=oauth,
data=json.dumps(body), headers=headers)
results = json.loads(response.content)
print(results)
body = {'author_id':results["author_id"]}
headers = {'content-type':'application/json'}
response = client.put('http://api.figshare.com/v1/my_data/articles/%d/authors' % article_id, auth=oauth,
data=json.dumps(body), headers=headers)
results = json.loads(response.content)
files = {'filedata':(os.path.basename(output_pdf), open(output_pdf, 'rb'))}
response = client.put('http://api.figshare.com/v1/my_data/articles/%d/files' % article_id, auth=oauth,
files=files)
results = json.loads(response.content)
print(results)
#response = client.post('http://api.figshare.com/v1/my_data/articles/%d/action/make_public' % article_id, auth=oauth)
#results = json.loads(response.content)
def generate_context(self):
pass
def generate_output(self, writer=None):
# we don't use the writer passed as argument here
# since we write our own files
logger.info(' Generating PDF files...')
pdf_path = os.path.join(self.output_path, 'pdf')
if not os.path.exists(pdf_path):
try:
os.mkdir(pdf_path)
except OSError:
logger.error("Couldn't create the pdf output folder in " +
pdf_path)
for article in self.context['articles']:
self._create_pdf(article, pdf_path)
self._upload_figshare(article, pdf_path)
for page in self.context['pages']:
self._create_pdf(page, pdf_path)
class PdfGenerator(Generator):
"Generate PDFs on the output dir, for all articles and pages"
supported_md_fields = ["date"]
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
if "PDF_STYLE_PATH" in self.settings:
pdf_style_path = [self.settings["PDF_STYLE_PATH"]]
else:
pdf_style_path = []
if "PDF_STYLE" in self.settings:
pdf_style = [self.settings["PDF_STYLE"]]
else:
pdf_style = []
self.pdfcreator = RstToPdf(breakside=0,
stylesheets=pdf_style,
style_path=pdf_style_path,
raw_html=True)
def _create_pdf(self, obj, output_path):
filename = obj.slug + ".pdf"
output_pdf = os.path.join(output_path, filename)
mdreader = MarkdownReader(self.settings)
_, ext = os.path.splitext(obj.source_path)
if ext == ".rst":
with open(obj.source_path, encoding="utf-8") as f:
text = f.read()
header = ""
elif ext[1:] in mdreader.file_extensions and mdreader.enabled:
text, meta = mdreader.read(obj.source_path)
header = ""
if "title" in meta:
title = meta["title"]
header = title + "\n" + "#" * len(title) + "\n\n"
del meta["title"]
for k in list(meta):
# We can't support all fields, so we strip the ones that won't
# look good
if k not in self.supported_md_fields:
del meta[k]
header += "\n".join([":{}: {}".format(k, meta[k]) for k in meta])
header += "\n\n.. raw:: html\n\n\t"
text = text.replace("\n", "\n\t")
# rst2pdf casts the text to str and will break if it finds
# non-escaped characters. Here we nicely escape them to XML/HTML
# entities before proceeding
text = text.encode("ascii", "xmlcharrefreplace").decode()
else:
# We don't support this format
logger.warn("Ignoring unsupported file " + obj.source_path)
return
# Find intra-site links and replace placeholder with actual path / url
hrefs = self._get_intrasite_link_regex()
text = hrefs.sub(lambda m: obj._link_replacer(obj.get_siteurl(), m),
text)
logger.info(" [ok] writing %s" % output_pdf)
self.pdfcreator.createPdf(text=(header + text), output=output_pdf)
def _get_intrasite_link_regex(self):
intrasite_link_regex = self.settings["INTRASITE_LINK_REGEX"]
regex = r"""
(?P<markup>)(?P<quote>)(?P<path>(\:?){}(?P<value>.*?)(?=[>\n]))
""".format(intrasite_link_regex)
return re.compile(regex, re.X)
def generate_context(self):
pass
def generate_output(self, writer=None):
# we don't use the writer passed as argument here
# since we write our own files
logger.info(" Generating PDF files...")
pdf_path = os.path.join(self.output_path, "pdf")
if not os.path.exists(pdf_path):
try:
os.mkdir(pdf_path)
except OSError:
logger.error("Couldn't create the pdf output folder in " +
pdf_path)
for obj in chain(self.context["articles"], self.context["pages"]):
self._create_pdf(obj, pdf_path)
for obj_trans in obj.translations:
self._create_pdf(obj_trans, pdf_path)