X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/215503e15ca9d6d1e8a053f7bfa359af1af102f3..a07a4a9202091de4902baa709e7ec83c837eb4b5:/librarian/parser.py?ds=inline diff --git a/librarian/parser.py b/librarian/parser.py old mode 100755 new mode 100644 index 225000b..2ece72f --- a/librarian/parser.py +++ b/librarian/parser.py @@ -1,25 +1,9 @@ # -*- coding: utf-8 -*- # -# This file is part of Librarian. +# This file is part of Librarian, licensed under GNU Affero GPLv3 or later. +# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information. # -# Copyright © 2008,2009,2010 Fundacja Nowoczesna Polska -# -# For full list of contributors see AUTHORS file. -# -# This program is free software: you can redistribute it and/or modify -# it under the terms of the GNU Affero General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU Affero General Public License for more details. -# -# You should have received a copy of the GNU Affero General Public License -# along with this program. If not, see . -# -from librarian import ValidationError, NoDublinCore, ParseError +from librarian import ValidationError, NoDublinCore, ParseError, NoProvider from librarian import RDFNS from librarian import dcparser @@ -27,19 +11,22 @@ from xml.parsers.expat import ExpatError from lxml import etree from lxml.etree import XMLSyntaxError, XSLTApplyError +import os import re from StringIO import StringIO class WLDocument(object): - LINE_SWAP_EXPR = re.compile(r'/\s', re.MULTILINE | re.UNICODE); + LINE_SWAP_EXPR = re.compile(r'/\s', re.MULTILINE | re.UNICODE) + provider = None - def __init__(self, edoc, parse_dublincore=True): + def __init__(self, edoc, parse_dublincore=True, provider=None, strict=False): self.edoc = edoc + self.provider = provider root_elem = edoc.getroot() - + dc_path = './/' + RDFNS('RDF') - + if root_elem.tag != 'utwor': raise ValidationError("Invalid root element. Found '%s', should be 'utwor'" % root_elem.tag) @@ -48,17 +35,18 @@ class WLDocument(object): if self.rdf_elem is None: raise NoDublinCore('Document has no DublinCore - which is required.') - - self.book_info = dcparser.BookInfo.from_element(self.rdf_elem) + + self.book_info = dcparser.BookInfo.from_element( + self.rdf_elem, strict=strict) else: self.book_info = None - + @classmethod - def from_string(cls, xml, swap_endlines=False, parse_dublincore=True): - return cls.from_file(StringIO(xml), swap_endlines, parse_dublincore=parse_dublincore) + def from_string(cls, xml, *args, **kwargs): + return cls.from_file(StringIO(xml), *args, **kwargs) @classmethod - def from_file(cls, xmlfile, swap_endlines=False, parse_dublincore=True): + def from_file(cls, xmlfile, parse_dublincore=True, provider=None): # first, prepare for parsing if isinstance(xmlfile, basestring): @@ -73,23 +61,54 @@ class WLDocument(object): if not isinstance(data, unicode): data = data.decode('utf-8') - if swap_endlines: - data = cls.LINE_SWAP_EXPR.sub(u'
\n', data) - + data = data.replace(u'\ufeff', '') + try: parser = etree.XMLParser(remove_blank_text=False) - return cls(etree.parse(StringIO(data), parser), parse_dublincore=parse_dublincore) + tree = etree.parse(StringIO(data.encode('utf-8')), parser) + + return cls(tree, parse_dublincore=parse_dublincore, provider=provider) except (ExpatError, XMLSyntaxError, XSLTApplyError), e: - raise ParseError(e) + raise ParseError(e) + + def swap_endlines(self): + """Converts line breaks in stanzas into
tags.""" + # only swap inside stanzas + for elem in self.edoc.iter('strofa'): + for child in list(elem): + if child.tail: + chunks = self.LINE_SWAP_EXPR.split(child.tail) + ins_index = elem.index(child) + 1 + while len(chunks) > 1: + ins = etree.Element('br') + ins.tail = chunks.pop() + elem.insert(ins_index, ins) + child.tail = chunks.pop(0) + if elem.text: + chunks = self.LINE_SWAP_EXPR.split(elem.text) + while len(chunks) > 1: + ins = etree.Element('br') + ins.tail = chunks.pop() + elem.insert(0, ins) + elem.text = chunks.pop(0) + + def parts(self): + if self.provider is None: + raise NoProvider('No document provider supplied.') + 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) def chunk(self, path): - # convert the path to XPath + # convert the path to XPath expr = self.path_to_xpath(path) elems = self.edoc.xpath(expr) if len(elems) == 0: return None - else: + else: return elems[0] def path_to_xpath(self, path): @@ -132,4 +151,52 @@ class WLDocument(object): except Exception, e: unmerged.append( repr( (key, xpath, e) ) ) - return unmerged \ No newline at end of file + return unmerged + + def clean_ed_note(self): + """ deletes forbidden tags from nota_red """ + + for node in self.edoc.xpath('|'.join('//nota_red//%s' % tag for tag in + ('pa', 'pe', 'pr', 'pt', 'begin', 'end', 'motyw'))): + tail = node.tail + node.clear() + node.tag = 'span' + node.tail = tail + + # Converters + + def as_html(self, *args, **kwargs): + from librarian import html + return html.transform(self, *args, **kwargs) + + def as_text(self, *args, **kwargs): + from librarian import text + return text.transform(self, *args, **kwargs) + + def as_epub(self, *args, **kwargs): + from librarian import epub + return epub.transform(self, *args, **kwargs) + + def as_pdf(self, *args, **kwargs): + from librarian import pdf + return pdf.transform(self, *args, **kwargs) + + def as_mobi(self, *args, **kwargs): + from librarian import mobi + return mobi.transform(self, *args, **kwargs) + + 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, + unicode(self.book_info.author).encode('utf-8')) + save_path = os.path.join(save_path, + self.book_info.uri.slug) + if ext: + save_path += '.%s' % ext + else: + save_path = output_path + + output_file.save_as(save_path)