message = six.text_type(args, encoding='utf-8', errors='ignore')
return message
+
class ParseError(UnicodeException):
pass
+
class ValidationError(UnicodeException):
pass
+
class NoDublinCore(ValidationError):
"""There's no DublinCore section, and it's required."""
pass
+
class NoProvider(UnicodeException):
"""There's no DocProvider specified, and it's needed."""
pass
+
class XMLNamespace(object):
'''A handy structure to repsent names in an XML namespace.'''
def __str__(self):
return '%s' % self.uri
+
class EmptyNamespace(XMLNamespace):
def __init__(self):
super(EmptyNamespace, self).__init__('')
def __call__(self, tag):
return tag
+
# some common namespaces we use
XMLNS = XMLNamespace('http://www.w3.org/XML/1998/namespace')
RDFNS = XMLNamespace('http://www.w3.org/1999/02/22-rdf-syntax-ns#')
slug = None
example = 'http://wolnelektury.pl/katalog/lektura/template/'
- _re_wl_uri = re.compile(r'http://(www\.)?wolnelektury.pl/katalog/lektur[ay]/'
- '(?P<slug>[-a-z0-9]+)/?$')
+ _re_wl_uri = re.compile(
+ r'http://(www\.)?wolnelektury.pl/katalog/lektur[ay]/'
+ '(?P<slug>[-a-z0-9]+)/?$'
+ )
def __init__(self, uri):
uri = six.text_type(uri)
from . import dcparser
+
DEFAULT_BOOKINFO = dcparser.BookInfo(
- { RDFNS('about'): u'http://wiki.wolnepodreczniki.pl/Lektury:Template'},
- { DCNS('creator'): [u'Some, Author'],
- DCNS('title'): [u'Some Title'],
- DCNS('subject.period'): [u'Unknown'],
- DCNS('subject.type'): [u'Unknown'],
- DCNS('subject.genre'): [u'Unknown'],
- DCNS('date'): ['1970-01-01'],
- DCNS('language'): [u'pol'],
- # DCNS('date'): [creation_date],
- DCNS('publisher'): [u"Fundacja Nowoczesna Polska"],
- DCNS('description'):
- [u"""Publikacja zrealizowana w ramach projektu
- Wolne Lektury (http://wolnelektury.pl). Reprodukcja cyfrowa
- wykonana przez Bibliotekę Narodową z egzemplarza
- pochodzącego ze zbiorów BN."""],
- DCNS('identifier.url'): [WLURI.example],
- DCNS('rights'):
- [u"Domena publiczna - zm. [OPIS STANU PRAWNEGO TEKSTU]"] })
+ {
+ RDFNS('about'): u'http://wiki.wolnepodreczniki.pl/Lektury:Template'
+ },
+ {
+ DCNS('creator'): [u'Some, Author'],
+ DCNS('title'): [u'Some Title'],
+ DCNS('subject.period'): [u'Unknown'],
+ DCNS('subject.type'): [u'Unknown'],
+ DCNS('subject.genre'): [u'Unknown'],
+ DCNS('date'): ['1970-01-01'],
+ DCNS('language'): [u'pol'],
+ # DCNS('date'): [creation_date],
+ DCNS('publisher'): [u"Fundacja Nowoczesna Polska"],
+ DCNS('description'):
+ [u"""Publikacja zrealizowana w ramach projektu
+ Wolne Lektury (http://wolnelektury.pl). Reprodukcja cyfrowa
+ wykonana przez Bibliotekę Narodową z egzemplarza
+ pochodzącego ze zbiorów BN."""],
+ DCNS('identifier.url'): [WLURI.example],
+ DCNS('rights'):
+ [u"Domena publiczna - zm. [OPIS STANU PRAWNEGO TEKSTU]"]
+ }
+)
+
def xinclude_forURI(uri):
e = etree.Element(XINS("include"))
e.set("href", uri)
return etree.tostring(e, encoding='unicode')
+
def wrap_text(ocrtext, creation_date, bookinfo=DEFAULT_BOOKINFO):
"""Wrap the text within the minimal XML structure with a DC template."""
bookinfo.created_at = creation_date
- dcstring = etree.tostring(bookinfo.to_etree(), \
- method='xml', encoding='unicode', pretty_print=True)
+ dcstring = etree.tostring(
+ bookinfo.to_etree(), method='xml', encoding='unicode',
+ pretty_print=True
+ )
return u'<utwor>\n' + dcstring + u'\n<plain-text>\n' + ocrtext + \
u'\n</plain-text>\n</utwor>'
for child in element.iterchildren():
e = etree.tostring(child, method='xml', encoding='unicode',
- pretty_print=True)
+ pretty_print=True)
b += e
return b
+
SERIALIZERS = {
'raw': serialize_raw,
}
+
def serialize_children(element, format='raw'):
return SERIALIZERS[format](element)
+
def get_resource(path):
return os.path.join(os.path.dirname(__file__), path)
class URLOpener(FancyURLopener):
version = 'FNP Librarian (http://github.com/fnp/librarian)'
+
+
urllib._urlopener = URLOpener()
"""
nt = node.text if node.text is not None else ''
- return ''.join([nt] + [etree.tostring(child, encoding='unicode') for child in node])
+ return ''.join(
+ [nt] + [etree.tostring(child, encoding='unicode') for child in node]
+ )
def set_inner_xml(node, text):
xml = etree.ElementTree(xml)
with open(sheet) as xsltf:
transform = etree.XSLT(etree.parse(xsltf))
- params = dict((key, transform.strparam(value)) for key, value in kwargs.items())
+ params = dict(
+ (key, transform.strparam(value))
+ for key, value in kwargs.items()
+ )
return transform(xml, **params)
Slashes may only occur directly in the stanza. Any slashes in subelements
will be ignored, and the subelements will be put inside verse elements.
- >>> s = etree.fromstring("<strofa>a <b>c</b> <b>c</b>/\\nb<x>x/\\ny</x>c/ \\nd</strofa>")
+ >>> s = etree.fromstring(
+ ... "<strofa>a <b>c</b> <b>c</b>/\\nb<x>x/\\ny</x>c/ \\nd</strofa>"
+ ... )
>>> Stanza(s).versify()
- >>> print(etree.tostring(s, encoding='unicode'))
- <strofa><wers_normalny>a <b>c</b><b>c</b></wers_normalny><wers_normalny>b<x>x/
- y</x>c</wers_normalny><wers_normalny>d</wers_normalny></strofa>
+ >>> print(etree.tostring(s, encoding='unicode', pretty_print=True).strip())
+ <strofa>
+ <wers_normalny>a <b>c</b><b>c</b></wers_normalny>
+ <wers_normalny>b<x>x/
+ y</x>c</wers_normalny>
+ <wers_normalny>d</wers_normalny>
+ </strofa>
"""
def __init__(self, stanza_elem):
tail = self.stanza.tail
self.stanza.clear()
self.stanza.tail = tail
- self.stanza.extend(verse for verse in self.verses if verse.text or len(verse) > 0)
+ self.stanza.extend(
+ verse for verse in self.verses
+ if verse.text or len(verse) > 0
+ )
def open_normal_verse(self):
self.open_verse = self.stanza.makeelement("wers_normalny")
def add_to_spine(spine, partno):
""" Adds a node to the spine section in content.opf file """
- e = spine.makeelement(OPFNS('itemref'), attrib={'idref': 'part%d' % partno})
+ e = spine.makeelement(
+ OPFNS('itemref'),
+ attrib={'idref': 'part%d' % partno}
+ )
spine.append(e)
last_node_part = False
- # the below loop are workaround for a problem with epubs in drama ebooks without acts
+ # The below loop are workaround for a problem with epubs
+ # in drama ebooks without acts.
is_scene = False
is_act = False
for one_part in main_text:
yield part_xml
last_node_part = True
main_xml_part[:] = [deepcopy(one_part)]
- elif not last_node_part and name in ("naglowek_rozdzial", "naglowek_akt", "srodtytul"):
+ elif (not last_node_part
+ and name in (
+ "naglowek_rozdzial", "naglowek_akt", "srodtytul"
+ )):
yield part_xml
main_xml_part[:] = [deepcopy(one_part)]
else:
yield part_xml
-def transform_chunk(chunk_xml, chunk_no, annotations, empty=False, _empty_html_static=[]):
- """ transforms one chunk, returns a HTML string, a TOC object and a set of used characters """
+def transform_chunk(chunk_xml, chunk_no, annotations, empty=False,
+ _empty_html_static=[]):
+ """
+ Transforms one chunk, returns a HTML string, a TOC object
+ and a set of used characters.
+ """
toc = TOC()
for element in chunk_xml[0]:
elif element.tag in ("naglowek_rozdzial", "naglowek_akt", "srodtytul"):
toc.add(node_name(element), "part%d.html" % chunk_no)
elif element.tag in ('naglowek_podrozdzial', 'naglowek_scena'):
- subnumber = toc.add(node_name(element), "part%d.html" % chunk_no, level=1, is_part=False)
+ subnumber = toc.add(node_name(element), "part%d.html" % chunk_no,
+ level=1, is_part=False)
element.set('sub', str(subnumber))
if empty:
if not _empty_html_static:
- _empty_html_static.append(open(get_resource('epub/emptyChunk.html')).read())
+ with open(get_resource('epub/emptyChunk.html')) as f:
+ _empty_html_static.append(f.read())
chars = set()
output_html = _empty_html_static[0]
else:
def transform(wldoc, verbose=False, style=None, html_toc=False,
- sample=None, cover=None, flags=None, hyphenate=False, ilustr_path='', output_type='epub'):
+ sample=None, cover=None, flags=None, hyphenate=False,
+ ilustr_path='', output_type='epub'):
""" produces a EPUB file
sample=n: generate sample e-book (with at least n paragraphs)
replace_characters(wldoc.edoc.getroot())
- hyphenator = set_hyph_language(wldoc.edoc.getroot()) if hyphenate else None
+ hyphenator = set_hyph_language(
+ wldoc.edoc.getroot()
+ ) if hyphenate else None
hyphenate_and_fix_conjunctions(wldoc.edoc.getroot(), hyphenator)
# every input file will have a TOC entry,
chars = set()
if first:
# write book title page
- html_tree = xslt(wldoc.edoc, get_resource('epub/xsltTitle.xsl'), outputtype=output_type)
+ html_tree = xslt(wldoc.edoc, get_resource('epub/xsltTitle.xsl'),
+ outputtype=output_type)
chars = used_chars(html_tree.getroot())
html_string = etree.tostring(
html_tree, pretty_print=True, xml_declaration=True,
chars = set()
html_string = open(get_resource('epub/emptyChunk.html')).read()
else:
- html_tree = xslt(wldoc.edoc, get_resource('epub/xsltChunkTitle.xsl'))
+ html_tree = xslt(wldoc.edoc,
+ get_resource('epub/xsltChunkTitle.xsl'))
chars = used_chars(html_tree.getroot())
html_string = etree.tostring(
html_tree, pretty_print=True, xml_declaration=True,
encoding="utf-8",
- doctype='<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"' +
+ doctype='<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"'
' "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">'
)
- zip.writestr('OPS/part%d.html' % chunk_counter, squeeze_whitespace(html_string))
+ zip.writestr('OPS/part%d.html' % chunk_counter,
+ squeeze_whitespace(html_string))
add_to_manifest(manifest, chunk_counter)
add_to_spine(spine, chunk_counter)
chunk_counter += 1
if sample <= 0:
empty = True
else:
- sample -= len(chunk_xml.xpath('//strofa|//akap|//akap_cd|//akap_dialog'))
- chunk_html, chunk_toc, chunk_chars = transform_chunk(chunk_xml, chunk_counter, annotations, empty)
+ sample -= len(chunk_xml.xpath(
+ '//strofa|//akap|//akap_cd|//akap_dialog'
+ ))
+ chunk_html, chunk_toc, chunk_chars = transform_chunk(
+ chunk_xml, chunk_counter, annotations, empty)
toc.extend(chunk_toc)
chars = chars.union(chunk_chars)
- zip.writestr('OPS/part%d.html' % chunk_counter, squeeze_whitespace(chunk_html))
+ zip.writestr('OPS/part%d.html' % chunk_counter,
+ squeeze_whitespace(chunk_html))
add_to_manifest(manifest, chunk_counter)
add_to_spine(spine, chunk_counter)
chunk_counter += 1
if document.book_info.thanks:
document.edoc.getroot().set('thanks', document.book_info.thanks)
- opf = xslt(document.book_info.to_etree(), get_resource('epub/xsltContent.xsl'))
+ opf = xslt(document.book_info.to_etree(),
+ get_resource('epub/xsltContent.xsl'))
manifest = opf.find('.//' + OPFNS('manifest'))
guide = opf.find('.//' + OPFNS('guide'))
spine = opf.find('.//' + OPFNS('spine'))
- output_file = NamedTemporaryFile(prefix='librarian', suffix='.epub', delete=False)
+ output_file = NamedTemporaryFile(prefix='librarian', suffix='.epub',
+ delete=False)
zip = zipfile.ZipFile(output_file, 'w', zipfile.ZIP_DEFLATED)
functions.reg_mathml_epub(zip)
if os.path.isdir(ilustr_path):
- ilustr_elements = set(ilustr.get('src') for ilustr in document.edoc.findall('//ilustr'))
+ ilustr_elements = set(ilustr.get('src')
+ for ilustr in document.edoc.findall('//ilustr'))
for i, filename in enumerate(os.listdir(ilustr_path)):
if filename not in ilustr_elements:
continue
zip.write(file_path, os.path.join('OPS', filename))
image_id = 'image%s' % i
manifest.append(etree.fromstring(
- '<item id="%s" href="%s" media-type="%s" />' % (image_id, filename, guess_type(file_path)[0])))
+ '<item id="%s" href="%s" media-type="%s" />' % (
+ image_id, filename, guess_type(file_path)[0])
+ ))
# write static elements
mime = zipfile.ZipInfo()
if bound_cover.uses_dc_cover:
if document.book_info.cover_by:
- document.edoc.getroot().set('data-cover-by', document.book_info.cover_by)
+ document.edoc.getroot().set('data-cover-by',
+ document.book_info.cover_by)
if document.book_info.cover_source:
- document.edoc.getroot().set('data-cover-source', document.book_info.cover_source)
+ document.edoc.getroot().set('data-cover-source',
+ document.book_info.cover_source)
manifest.append(etree.fromstring(
- '<item id="cover" href="cover.html" media-type="application/xhtml+xml" />'))
+ '<item id="cover" href="cover.html" '
+ 'media-type="application/xhtml+xml" />'
+ ))
manifest.append(etree.fromstring(
- '<item id="cover-image" href="%s" media-type="%s" />' % (cover_name, bound_cover.mime_type())))
+ '<item id="cover-image" href="%s" media-type="%s" />' % (
+ cover_name, bound_cover.mime_type()
+ )
+ ))
spine.insert(0, etree.fromstring('<itemref idref="cover"/>'))
- opf.getroot()[0].append(etree.fromstring('<meta name="cover" content="cover-image"/>'))
- guide.append(etree.fromstring('<reference href="cover.html" type="cover" title="Okładka"/>'))
+ opf.getroot()[0].append(etree.fromstring(
+ '<meta name="cover" content="cover-image"/>'
+ ))
+ guide.append(etree.fromstring(
+ '<reference href="cover.html" type="cover" title="Okładka"/>'
+ ))
annotations = etree.Element('annotations')
if html_toc:
manifest.append(etree.fromstring(
- '<item id="html_toc" href="toc.html" media-type="application/xhtml+xml" />'))
+ '<item id="html_toc" href="toc.html" '
+ 'media-type="application/xhtml+xml" />'
+ ))
spine.append(etree.fromstring(
'<itemref idref="html_toc" />'))
- guide.append(etree.fromstring('<reference href="toc.html" type="toc" title="Spis treści"/>'))
+ guide.append(etree.fromstring(
+ '<reference href="toc.html" type="toc" title="Spis treści"/>'
+ ))
toc, chunk_counter, chars, sample = transform_file(document, sample=sample)
if len(annotations) > 0:
toc.add("Przypisy", "annotations.html")
manifest.append(etree.fromstring(
- '<item id="annotations" href="annotations.html" media-type="application/xhtml+xml" />'))
+ '<item id="annotations" href="annotations.html" '
+ 'media-type="application/xhtml+xml" />'
+ ))
spine.append(etree.fromstring(
'<itemref idref="annotations" />'))
replace_by_verse(annotations)
toc.add("Wesprzyj Wolne Lektury", "support.html")
manifest.append(etree.fromstring(
- '<item id="support" href="support.html" media-type="application/xhtml+xml" />'))
+ '<item id="support" href="support.html" '
+ 'media-type="application/xhtml+xml" />'
+ ))
spine.append(etree.fromstring(
'<itemref idref="support" />'))
html_string = open(get_resource('epub/support.html'), 'rb').read()
toc.add("Strona redakcyjna", "last.html")
manifest.append(etree.fromstring(
- '<item id="last" href="last.html" media-type="application/xhtml+xml" />'))
+ '<item id="last" href="last.html" '
+ 'media-type="application/xhtml+xml" />'
+ ))
spine.append(etree.fromstring(
'<itemref idref="last" />'))
- html_tree = xslt(document.edoc, get_resource('epub/xsltLast.xsl'), outputtype=output_type)
+ html_tree = xslt(document.edoc, get_resource('epub/xsltLast.xsl'),
+ outputtype=output_type)
chars.update(used_chars(html_tree.getroot()))
zip.writestr('OPS/last.html', squeeze_whitespace(etree.tostring(
html_tree, pretty_print=True, xml_declaration=True,
except OSError:
cwd = None
- os.chdir(os.path.join(os.path.dirname(os.path.realpath(__file__)), 'font-optimizer'))
- for fname in 'DejaVuSerif.ttf', 'DejaVuSerif-Bold.ttf', 'DejaVuSerif-Italic.ttf', 'DejaVuSerif-BoldItalic.ttf':
+ os.chdir(os.path.join(os.path.dirname(os.path.realpath(__file__)),
+ 'font-optimizer'))
+ for fname in ('DejaVuSerif.ttf', 'DejaVuSerif-Bold.ttf',
+ 'DejaVuSerif-Italic.ttf', 'DejaVuSerif-BoldItalic.ttf'):
optimizer_call = ['perl', 'subset.pl', '--chars',
''.join(chars).encode('utf-8'),
get_resource('fonts/' + fname),
subprocess.check_call(optimizer_call, env=env)
else:
dev_null = open(os.devnull, 'w')
- subprocess.check_call(optimizer_call, stdout=dev_null, stderr=dev_null, env=env)
+ subprocess.check_call(optimizer_call, stdout=dev_null,
+ stderr=dev_null, env=env)
zip.write(os.path.join(tmpdir, fname), os.path.join('OPS', fname))
manifest.append(etree.fromstring(
- '<item id="%s" href="%s" media-type="application/x-font-truetype" />' % (fname, fname)))
+ '<item id="%s" href="%s" '
+ 'media-type="application/x-font-truetype" />'
+ % (fname, fname)
+ ))
rmtree(tmpdir)
if cwd is not None:
os.chdir(cwd)
zip.writestr('OPS/content.opf', etree.tostring(opf, pretty_print=True,
xml_declaration=True, encoding="utf-8"))
title = document.book_info.title
- attributes = "dtb:uid", "dtb:depth", "dtb:totalPageCount", "dtb:maxPageNumber"
+ attributes = ("dtb:uid", "dtb:depth", "dtb:totalPageCount",
+ "dtb:maxPageNumber")
for st in attributes:
meta = toc_file.makeelement(NCXNS('meta'))
meta.set('name', st)
dc_path = './/' + RDFNS('RDF')
if root_elem.tag != 'utwor':
- raise ValidationError("Invalid root element. Found '%s', should be 'utwor'" % root_elem.tag)
+ raise ValidationError(
+ "Invalid root element. Found '%s', should be 'utwor'"
+ % root_elem.tag
+ )
if parse_dublincore:
self.rdf_elem = root_elem.find(dc_path)
if self.rdf_elem is None:
- raise NoDublinCore("Document must have a '%s' element." % RDFNS('RDF'))
+ raise NoDublinCore(
+ "Document must have a '%s' element." % RDFNS('RDF')
+ )
self.book_info = dcparser.BookInfo.from_element(
- self.rdf_elem, fallbacks=meta_fallbacks, strict=strict)
+ self.rdf_elem, fallbacks=meta_fallbacks, strict=strict)
else:
self.book_info = None
if self.book_info is None:
raise NoDublinCore('No Dublin Core in document.')
for part_uri in self.book_info.parts:
- yield self.from_file(self.provider.by_uri(part_uri), provider=self.provider)
+ yield self.from_file(
+ self.provider.by_uri(part_uri), provider=self.provider
+ )
def chunk(self, path):
# convert the path to XPath
try:
xpath = self.path_to_xpath(key)
node = self.edoc.xpath(xpath)[0]
- repl = etree.fromstring(u"<%s>%s</%s>" % (node.tag, data, node.tag))
+ repl = etree.fromstring(
+ "<%s>%s</%s>" % (node.tag, data, node.tag)
+ )
node.getparent().replace(node, repl)
except Exception as e:
unmerged.append(repr((key, xpath, e)))
def clean_ed_note(self, note_tag='nota_red'):
""" deletes forbidden tags from nota_red """
- for node in self.edoc.xpath('|'.join('//%s//%s' % (note_tag, tag) for tag in
- ('pa', 'pe', 'pr', 'pt', 'begin', 'end', 'motyw'))):
+ for node in self.edoc.xpath('|'.join(
+ '//%s//%s' % (note_tag, tag) for tag in
+ ('pa', 'pe', 'pr', 'pt', 'begin', 'end', 'motyw'))):
tail = node.tail
node.clear()
node.tag = 'span'
"""
if self.book_info is None:
raise NoDublinCore('No Dublin Core in document.')
- persons = set(self.book_info.editors + self.book_info.technical_editors)
+ persons = set(self.book_info.editors
+ + self.book_info.technical_editors)
for child in self.parts():
persons.update(child.editors())
if None in persons:
from librarian import pdf
return pdf.transform(self, *args, **kwargs)
- def save_output_file(self, output_file, output_path=None, output_dir_path=None, make_author_dir=False, ext=None):
+ def save_output_file(self, output_file, output_path=None,
+ output_dir_path=None, make_author_dir=False,
+ ext=None):
if output_dir_path:
save_path = output_dir_path
if make_author_dir:
- save_path = os.path.join(save_path, six.text_type(self.book_info.author).encode('utf-8'))
+ save_path = os.path.join(
+ save_path,
+ six.text_type(self.book_info.author).encode('utf-8')
+ )
save_path = os.path.join(save_path, self.book_info.url.slug)
if ext:
save_path += '.%s' % ext
fnp / librarian.git / commitdiff