From b9fb80d9b093bfecd87eb47d73ea81652d4e8057 Mon Sep 17 00:00:00 2001 From: Eli Schwartz Date: Thu, 18 Jul 2019 12:26:48 -0400 Subject: [PATCH 1/6] use raw strings where possible to avoid escaping issues --- src/calibre/ebooks/oeb/transforms/split.py | 2 +- src/calibre/ebooks/pml/pmlml.py | 24 +++++++++++----------- src/calibre/ebooks/readability/cleaners.py | 2 +- src/calibre/ebooks/rtf/rtfml.py | 12 +++++------ 4 files changed, 20 insertions(+), 20 deletions(-) diff --git a/src/calibre/ebooks/oeb/transforms/split.py b/src/calibre/ebooks/oeb/transforms/split.py index d0e1a334ec..a42bae67a5 100644 --- a/src/calibre/ebooks/oeb/transforms/split.py +++ b/src/calibre/ebooks/oeb/transforms/split.py @@ -294,7 +294,7 @@ class FlowSplitter(object): body = self.get_body(root) if body is None: return False - txt = re.sub(u'\\s+|\\xa0', '', + txt = re.sub(ur'\s+|\xa0', '', etree.tostring(body, method='text', encoding='unicode')) if len(txt) > 1: return False diff --git a/src/calibre/ebooks/pml/pmlml.py b/src/calibre/ebooks/pml/pmlml.py index 772117321c..e99ec66226 100644 --- a/src/calibre/ebooks/pml/pmlml.py +++ b/src/calibre/ebooks/pml/pmlml.py @@ -155,7 +155,7 @@ class PMLMLizer(object): def get_anchor(self, page, aid): aid = self.get_anchor_id(page.href, aid) - return u'\\Q="%s"' % aid + return ur'\Q="%s"' % aid def remove_newlines(self, text): text = text.replace('\r\n', ' ') @@ -186,10 +186,10 @@ class PMLMLizer(object): anchors = set(re.findall(r'(?<=\\Q=").+?(?=")', text)) links = set(re.findall(r'(?<=\\q="#).+?(?=")', text)) for unused in anchors.difference(links): - text = text.replace('\\Q="%s"' % unused, '') + text = text.replace(r'\Q="%s"' % unused, '') # Remove \Cn tags that are within \x and \Xn tags - text = re.sub(unicode_type(r'(?msu)(?P\\(x|X[0-4]))(?P.*?)(?P\\C[0-4]\s*=\s*"[^"]*")(?P.*?)(?P=t)'), '\\g\\g\\g\\g', text) + text = re.sub(unicode_type(r'(?msu)(?P\\(x|X[0-4]))(?P.*?)(?P\\C[0-4]\s*=\s*"[^"]*")(?P.*?)(?P=t)'), r'\g\g\g\g', text) # Replace bad characters. text = text.replace(u'\xc2', '') @@ -259,7 +259,7 @@ class PMLMLizer(object): '%s.png' % len(self.image_hrefs.keys()), self.image_hrefs.keys()).strip('\x00') text.append('\\m="%s"' % self.image_hrefs[page.abshref(elem.attrib['src'])]) elif tag == 'hr': - w = '\\w' + w = r'\w' width = elem.get('width') if width: if not width.endswith('%'): @@ -286,17 +286,17 @@ class PMLMLizer(object): toc_title, toc_depth = self.toc[toc_page].get(toc_x, (None, 0)) if toc_title: toc_depth = max(min(toc_depth, 4), 0) - text.append('\\C%s="%s"' % (toc_depth, toc_title)) + text.append(r'\C%s="%s"' % (toc_depth, toc_title)) # Process style information that needs holds a single tag. # Commented out because every page in an OEB book starts with this style. if style['page-break-before'] == 'always': - text.append('\\p') + text.append(r'\p') # Process basic PML tags. pml_tag = TAG_MAP.get(tag, None) if pml_tag and pml_tag not in tag_stack+tags: - text.append('\\%s' % pml_tag) + text.append(r'\%s' % pml_tag) tags.append(pml_tag) # Special processing of tags that require an argument. @@ -311,7 +311,7 @@ class PMLMLizer(object): if href not in self.link_hrefs.keys(): self.link_hrefs[href] = 'calibre_link-%s' % len(self.link_hrefs.keys()) href = '#%s' % self.link_hrefs[href] - text.append('\\q="%s"' % href) + text.append(r'\q="%s"' % href) tags.append('q') # Anchor ids @@ -325,14 +325,14 @@ class PMLMLizer(object): for s in STYLES: style_tag = s[1].get(style[s[0]], None) if style_tag and style_tag not in tag_stack+tags: - text.append('\\%s' % style_tag) + text.append('r\%s' % style_tag) tags.append(style_tag) # margin left try: mms = int(float(style['margin-left']) * 100 / style.height) if mms: - text.append('\\T="%s%%"' % mms) + text.append(r'\T="%s%%"' % mms) except: pass @@ -360,7 +360,7 @@ class PMLMLizer(object): # text.append('\n\n') if style['page-break-after'] == 'always': - text.append('\\p') + text.append(r'\p') # Process text after this tag but not within another. if hasattr(elem, 'tail') and elem.tail: @@ -382,5 +382,5 @@ class PMLMLizer(object): if tag in ('c', 'r'): text.append('\n\\%s' % tag) else: - text.append('\\%s' % tag) + text.append(r'\%s' % tag) return text diff --git a/src/calibre/ebooks/readability/cleaners.py b/src/calibre/ebooks/readability/cleaners.py index 057fcf17b3..d30216c4d8 100644 --- a/src/calibre/ebooks/readability/cleaners.py +++ b/src/calibre/ebooks/readability/cleaners.py @@ -17,7 +17,7 @@ htmlstrip = re.compile("<" # open def clean_attributes(html): while htmlstrip.search(html): - html = htmlstrip.sub('<\\1\\2>', html) + html = htmlstrip.sub(r'<\1\2>', html) return html diff --git a/src/calibre/ebooks/rtf/rtfml.py b/src/calibre/ebooks/rtf/rtfml.py index d4b339c53c..7f6cc91c50 100644 --- a/src/calibre/ebooks/rtf/rtfml.py +++ b/src/calibre/ebooks/rtf/rtfml.py @@ -83,7 +83,7 @@ def txt2rtf(text): for x in text: val = ord(x) if val == 160: - buf.write(u'\\~') + buf.write(ur'\~') elif val <= 127: buf.write(unicode_type(x)) else: @@ -115,7 +115,7 @@ class RTFMLizer(object): self.opts, self.opts.output_profile) self.currently_dumping_item = item output += self.dump_text(item.data.find(XHTML('body')), stylizer) - output += '{\\page }' + output += r'{\page }' for item in self.oeb_book.spine: self.log.debug('Converting %s to RTF markup...' % item.href) # Removing comments is needed as comments with -- inside them can @@ -127,7 +127,7 @@ class RTFMLizer(object): stylizer = Stylizer(content, item.href, self.oeb_book, self.opts, self.opts.output_profile) self.currently_dumping_item = item output += self.dump_text(content.find(XHTML('body')), stylizer) - output += '{\\page }' + output += r'{\page }' output += self.footer() output = self.insert_images(output) output = self.clean_text(output) @@ -259,7 +259,7 @@ class RTFMLizer(object): block_start = '' block_end = '' if 'block' not in tag_stack: - block_start = '{\\par\\pard\\hyphpar ' + block_start = r'{\par\pard\hyphpar ' block_end = '}' text += '%s SPECIAL_IMAGE-%s-REPLACE_ME %s' % (block_start, src, block_end) @@ -292,7 +292,7 @@ class RTFMLizer(object): end_tag = tag_stack.pop() if end_tag != 'block': if tag in BLOCK_TAGS: - text += u'\\par\\pard\\plain\\hyphpar}' + text += ur'\par\pard\plain\hyphpar}' else: text += u'}' @@ -300,6 +300,6 @@ class RTFMLizer(object): if 'block' in tag_stack: text += '%s' % txt2rtf(elem.tail) else: - text += '{\\par\\pard\\hyphpar %s}' % txt2rtf(elem.tail) + text += r'{\par\pard\hyphpar %s}' % txt2rtf(elem.tail) return text From 2212dfc64944ec78f9c731c6f29855582a05ab8b Mon Sep 17 00:00:00 2001 From: Eli Schwartz Date: Thu, 18 Jul 2019 12:28:02 -0400 Subject: [PATCH 2/6] fix imports from the wrong module when module_a.submodule_a imports module_b, then module_c should not use "from module_a.submodule_a import module_b" --- src/calibre/ebooks/oeb/transforms/split.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/src/calibre/ebooks/oeb/transforms/split.py b/src/calibre/ebooks/oeb/transforms/split.py index a42bae67a5..93fd1226c5 100644 --- a/src/calibre/ebooks/oeb/transforms/split.py +++ b/src/calibre/ebooks/oeb/transforms/split.py @@ -18,9 +18,10 @@ from lxml import etree from calibre import as_unicode, force_unicode from calibre.ebooks.epub import rules from calibre.ebooks.oeb.base import (OEB_STYLES, XPNSMAP as NAMESPACES, - urldefrag, rewrite_links, urlunquote, XHTML, urlnormalize) + urldefrag, rewrite_links, XHTML, urlnormalize) from calibre.ebooks.oeb.polish.split import do_split from polyglot.builtins import iteritems, range, map +from polyglot.urllib import unquote from css_selectors import Select, SelectorError XPath = functools.partial(_XPath, namespaces=NAMESPACES) @@ -179,7 +180,7 @@ class Split(object): nhref = anchor_map[frag if frag else None] nhref = self.current_item.relhref(nhref) if frag: - nhref = '#'.join((urlunquote(nhref), frag)) + nhref = '#'.join((unquote(nhref), frag)) return nhref return url From cba11fb969268d1e5d27c7e89c7b074cf8dbf596 Mon Sep 17 00:00:00 2001 From: Eli Schwartz Date: Mon, 22 Jul 2019 11:20:50 -0400 Subject: [PATCH 3/6] unicode_check: do not try to check pyuic-generated files --- setup/port.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/setup/port.py b/setup/port.py index ecd09e2e9e..401764fcb7 100644 --- a/setup/port.py +++ b/setup/port.py @@ -72,7 +72,8 @@ class Base(Command): def get_files(self): from calibre import walk for path in walk(os.path.join(self.SRC, 'calibre')): - if path.endswith('.py') and not os.path.basename(path) in self.EXCLUDED_BASENAMES: + if (path.endswith('.py') and not path.endswith('_ui.py') and not + os.path.basename(path) in self.EXCLUDED_BASENAMES): yield path def file_hash(self, f): From 4b280adcc93b44ffc207186cf4e236b329ba4a8a Mon Sep 17 00:00:00 2001 From: Eli Schwartz Date: Thu, 18 Jul 2019 12:29:39 -0400 Subject: [PATCH 4/6] py3: more work towards universal __future__s --- src/calibre/ebooks/oeb/transforms/flatcss.py | 42 +-- src/calibre/ebooks/oeb/transforms/jacket.py | 7 +- src/calibre/ebooks/oeb/transforms/metadata.py | 2 +- src/calibre/ebooks/oeb/transforms/split.py | 12 +- .../ebooks/oeb/transforms/structure.py | 12 +- .../ebooks/oeb/transforms/trimmanifest.py | 2 +- src/calibre/ebooks/pml/__init__.py | 1 + src/calibre/ebooks/pml/pmlconverter.py | 37 +-- src/calibre/ebooks/pml/pmlml.py | 13 +- src/calibre/ebooks/rb/__init__.py | 5 +- src/calibre/ebooks/rb/writer.py | 1 + src/calibre/ebooks/readability/cleaners.py | 2 + src/calibre/ebooks/readability/debug.py | 2 + src/calibre/ebooks/readability/htmls.py | 18 +- src/calibre/ebooks/readability/readability.py | 18 +- src/calibre/ebooks/rtf/input.py | 5 +- src/calibre/ebooks/rtf/preprocess.py | 3 +- src/calibre/ebooks/rtf/rtfml.py | 22 +- src/calibre/ebooks/rtf2xml/ParseRtf.py | 6 +- src/calibre/ebooks/rtf2xml/check_encoding.py | 6 +- src/calibre/ebooks/rtf2xml/footnote.py | 8 +- src/calibre/ebooks/rtf2xml/hex_2_utf8.py | 6 +- src/calibre/ebooks/rtf2xml/list_table.py | 15 +- src/calibre/ebooks/rtf2xml/make_lists.py | 5 +- src/calibre/ebooks/rtf2xml/old_rtf.py | 7 +- src/calibre/ebooks/rtf2xml/paragraph_def.py | 7 +- src/calibre/ebooks/rtf2xml/pict.py | 6 +- src/calibre/ebooks/rtf2xml/process_tokens.py | 8 +- src/calibre/ebooks/rtf2xml/sections.py | 16 +- src/calibre/ebooks/rtf2xml/table.py | 11 +- src/calibre/ebooks/snb/__init__.py | 3 +- src/calibre/ebooks/snb/snbml.py | 41 +-- src/calibre/ebooks/unihandecode/__init__.py | 7 +- .../ebooks/unihandecode/jacodepoints.py | 3 +- src/calibre/ebooks/unihandecode/jadecoder.py | 3 +- .../ebooks/unihandecode/krcodepoints.py | 3 +- src/calibre/ebooks/unihandecode/krdecoder.py | 2 +- .../ebooks/unihandecode/pykakasi/__init__.py | 3 +- .../ebooks/unihandecode/pykakasi/h2a.py | 239 +++++++++--------- .../ebooks/unihandecode/pykakasi/j2h.py | 3 +- .../ebooks/unihandecode/pykakasi/jisyo.py | 2 + .../ebooks/unihandecode/pykakasi/k2a.py | 1 + .../ebooks/unihandecode/pykakasi/kakasi.py | 2 +- .../ebooks/unihandecode/unicodepoints.py | 1 + src/calibre/ebooks/unihandecode/unidecoder.py | 1 + .../ebooks/unihandecode/vncodepoints.py | 3 +- src/calibre/ebooks/unihandecode/vndecoder.py | 2 +- .../ebooks/unihandecode/zhcodepoints.py | 3 +- src/calibre/gui2/book_details.py | 27 +- src/calibre/gui2/cover_flow.py | 9 +- src/calibre/gui2/custom_column_widgets.py | 3 +- src/calibre/gui2/email.py | 2 +- src/calibre/gui2/init.py | 5 +- src/calibre/gui2/jobs.py | 14 +- src/calibre/gui2/layout.py | 3 +- src/calibre/gui2/linux_file_dialogs.py | 6 +- src/calibre/gui2/shortcuts.py | 4 +- src/calibre/gui2/ui.py | 6 +- src/calibre/gui2/update.py | 16 +- 59 files changed, 393 insertions(+), 329 deletions(-) diff --git a/src/calibre/ebooks/oeb/transforms/flatcss.py b/src/calibre/ebooks/oeb/transforms/flatcss.py index 4b777dbc04..c02dfe9e34 100644 --- a/src/calibre/ebooks/oeb/transforms/flatcss.py +++ b/src/calibre/ebooks/oeb/transforms/flatcss.py @@ -1,7 +1,7 @@ ''' CSS flattening transform. ''' -from __future__ import with_statement +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL v3' __copyright__ = '2008, Marshall T. Vandegrift ' @@ -122,9 +122,9 @@ class EmbedFontsCSSRules(object): if not self.body_font_family: return None if not self.href: - iid, href = oeb.manifest.generate(u'page_styles', u'page_styles.css') + iid, href = oeb.manifest.generate('page_styles', 'page_styles.css') rules = [css_text(x) for x in self.rules] - rules = u'\n\n'.join(rules) + rules = '\n\n'.join(rules) sheet = css_parser.parseString(rules, validate=False) self.href = oeb.manifest.add(iid, href, guess_type(href)[0], data=sheet).href @@ -228,13 +228,13 @@ class CSSFlattener(object): try: faces = font_scanner.fonts_for_family(family) except NoFonts: - msg = (u'No embeddable fonts found for family: %r'%family) + msg = ('No embeddable fonts found for family: %r'%family) if failure_critical: raise ValueError(msg) self.oeb.log.warn(msg) return body_font_family, efi if not faces: - msg = (u'No embeddable fonts found for family: %r'%family) + msg = ('No embeddable fonts found for family: %r'%family) if failure_critical: raise ValueError(msg) self.oeb.log.warn(msg) @@ -243,26 +243,26 @@ class CSSFlattener(object): for i, font in enumerate(faces): ext = 'otf' if font['is_otf'] else 'ttf' fid, href = self.oeb.manifest.generate(id=u'font', - href=u'fonts/%s.%s'%(ascii_filename(font['full_name']).replace(u' ', u'-'), ext)) + href='fonts/%s.%s'%(ascii_filename(font['full_name']).replace(' ', '-'), ext)) item = self.oeb.manifest.add(fid, href, guess_type('dummy.'+ext)[0], data=font_scanner.get_font_data(font)) item.unload_data_from_memory() cfont = { - u'font-family':u'"%s"'%font['font-family'], - u'panose-1': u' '.join(map(unicode_type, font['panose'])), - u'src': u'url(%s)'%item.href, + 'font-family': '"%s"'%font['font-family'], + 'panose-1': ' '.join(map(unicode_type, font['panose'])), + 'src': 'url(%s)'%item.href, } if i == 0: generic_family = panose_to_css_generic_family(font['panose']) - body_font_family = u"'%s',%s"%(font['font-family'], generic_family) - self.oeb.log(u'Embedding font: %s'%font['font-family']) - for k in (u'font-weight', u'font-style', u'font-stretch'): - if font[k] != u'normal': + body_font_family = "'%s',%s"%(font['font-family'], generic_family) + self.oeb.log('Embedding font: %s'%font['font-family']) + for k in ('font-weight', 'font-style', 'font-stretch'): + if font[k] != 'normal': cfont[k] = font[k] - rule = '@font-face { %s }'%('; '.join(u'%s:%s'%(k, v) for k, v in + rule = '@font-face { %s }'%('; '.join('%s:%s'%(k, v) for k, v in iteritems(cfont))) rule = css_parser.parseString(rule) efi.append(rule) @@ -295,7 +295,7 @@ class CSSFlattener(object): if self.context.change_justification != 'original': bs.append('text-align: '+ self.context.change_justification) if self.body_font_family: - bs.append(u'font-family: '+self.body_font_family) + bs.append('font-family: '+self.body_font_family) body.set('style', '; '.join(bs)) stylizer = Stylizer(html, item.href, self.oeb, self.context, profile, user_css=self.context.extra_css, @@ -458,7 +458,7 @@ class CSSFlattener(object): dyn_rescale = node.attrib.pop('data-calibre-rescale', None) if dyn_rescale is not None: try: - dyn_rescale = float(dyn_rescale) / 100.0 + dyn_rescale = float(dyn_rescale) / 100 except Exception: dyn_rescale = 1 fsize = self.fmap[_sbase] @@ -476,7 +476,7 @@ class CSSFlattener(object): try: minlh = self.context.minimum_line_height / 100. if not is_drop_cap and style['line-height'] < minlh * fsize: - cssdict['line-height'] = str(minlh) + cssdict['line-height'] = unicode_type(minlh) except: self.oeb.logger.exception('Failed to set minimum line-height') @@ -528,7 +528,7 @@ class CSSFlattener(object): if cssdict: items = sorted(iteritems(cssdict)) - css = u';\n'.join(u'%s: %s' % (key, val) for key, val in items) + css = ';\n'.join(u'%s: %s' % (key, val) for key, val in items) classes = node.get('class', '').strip() or 'calibre' classes_list = classes.split() # lower() because otherwise if the document uses the same class @@ -538,7 +538,7 @@ class CSSFlattener(object): if css in styles: match = styles[css] else: - match = klass + str(names[klass] or '') + match = klass + unicode_type(names[klass] or '') styles[css] = match names[klass] += 1 node.attrib['class'] = match @@ -546,7 +546,7 @@ class CSSFlattener(object): for psel, cssdict in iteritems(pseudo_classes): items = sorted(iteritems(cssdict)) - css = u';\n'.join(u'%s: %s' % (key, val) for key, val in items) + css = ';\n'.join('%s: %s' % (key, val) for key, val in items) pstyles = pseudo_styles[psel] if css in pstyles: match = pstyles[css] @@ -558,7 +558,7 @@ class CSSFlattener(object): # then the class attribute for a.x tags will contain both # that class and the class for a.x:hover, which is wrong. klass = 'pcalibre' - match = klass + str(names[klass] or '') + match = klass + unicode_type(names[klass] or '') pstyles[css] = match names[klass] += 1 keep_classes.add(match) diff --git a/src/calibre/ebooks/oeb/transforms/jacket.py b/src/calibre/ebooks/oeb/transforms/jacket.py index 68ae89b8ba..35ead6a29a 100644 --- a/src/calibre/ebooks/oeb/transforms/jacket.py +++ b/src/calibre/ebooks/oeb/transforms/jacket.py @@ -1,7 +1,6 @@ #!/usr/bin/env python2 # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai -from __future__ import with_statement -from __future__ import print_function +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL v3' __copyright__ = '2009, Kovid Goyal ' @@ -188,7 +187,7 @@ class Series(unicode_type): combined = roman = escape(series or u'') s = unicode_type.__new__(self, combined) s.roman = roman - s.name = escape(series or u'') + s.name = escape(series or '') s.number = escape(fmt_sidx(series_index or 1.0, use_roman=False)) s.roman_number = escape(fmt_sidx(series_index or 1.0, use_roman=True)) return s @@ -260,7 +259,7 @@ def render_jacket(mi, output_profile, pubdate = '' else: dt = as_local_time(mi.pubdate) - pubdate = strftime(u'%Y', dt.timetuple()) + pubdate = strftime('%Y', dt.timetuple()) except: pubdate = '' diff --git a/src/calibre/ebooks/oeb/transforms/metadata.py b/src/calibre/ebooks/oeb/transforms/metadata.py index 7f5342d6f4..ed829dc92d 100644 --- a/src/calibre/ebooks/oeb/transforms/metadata.py +++ b/src/calibre/ebooks/oeb/transforms/metadata.py @@ -1,6 +1,6 @@ #!/usr/bin/env python2 # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai -from __future__ import with_statement +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL v3' __copyright__ = '2009, Kovid Goyal ' diff --git a/src/calibre/ebooks/oeb/transforms/split.py b/src/calibre/ebooks/oeb/transforms/split.py index 93fd1226c5..a54121e48c 100644 --- a/src/calibre/ebooks/oeb/transforms/split.py +++ b/src/calibre/ebooks/oeb/transforms/split.py @@ -1,4 +1,4 @@ -from __future__ import with_statement +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL v3' __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net' __docformat__ = 'restructuredtext en' @@ -20,7 +20,7 @@ from calibre.ebooks.epub import rules from calibre.ebooks.oeb.base import (OEB_STYLES, XPNSMAP as NAMESPACES, urldefrag, rewrite_links, XHTML, urlnormalize) from calibre.ebooks.oeb.polish.split import do_split -from polyglot.builtins import iteritems, range, map +from polyglot.builtins import iteritems, range, map, unicode_type from polyglot.urllib import unquote from css_selectors import Select, SelectorError @@ -123,7 +123,7 @@ class Split(object): for i, elem in enumerate(item.data.iter('*')): try: - elem.set('pb_order', str(i)) + elem.set('pb_order', unicode_type(i)) except TypeError: # Cant set attributes on comment nodes etc. continue @@ -202,7 +202,7 @@ class FlowSplitter(object): self.csp_counter = 0 base, ext = os.path.splitext(self.base) - self.base = base.replace('%', '%%')+u'_split_%.3d'+ext + self.base = base.replace('%', '%%')+'_split_%.3d'+ext self.trees = [self.item.data.getroottree()] self.splitting_on_page_breaks = True @@ -295,7 +295,7 @@ class FlowSplitter(object): body = self.get_body(root) if body is None: return False - txt = re.sub(ur'\s+|\xa0', '', + txt = re.sub(r'\s+|\xa0', '', etree.tostring(body, method='text', encoding='unicode')) if len(txt) > 1: return False @@ -338,7 +338,7 @@ class FlowSplitter(object): for frag in frags: pre2 = copy.copy(pre) pre2.text = frag - pre2.tail = u'' + pre2.tail = '' new_pres.append(pre2) new_pres[-1].tail = pre.tail p = pre.getparent() diff --git a/src/calibre/ebooks/oeb/transforms/structure.py b/src/calibre/ebooks/oeb/transforms/structure.py index 31c95c8aa1..cd5211c156 100644 --- a/src/calibre/ebooks/oeb/transforms/structure.py +++ b/src/calibre/ebooks/oeb/transforms/structure.py @@ -1,6 +1,6 @@ #!/usr/bin/env python2 # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai -from __future__ import with_statement +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL v3' __copyright__ = '2009, Kovid Goyal ' @@ -26,7 +26,7 @@ def XPath(x): def isspace(x): - return not x or x.replace(u'\xa0', u'').isspace() + return not x or x.replace('\xa0', '').isspace() def at_start(elem): @@ -124,11 +124,11 @@ class DetectStructure(object): elem = matches[0] eid = elem.get('id', None) if not eid: - eid = u'start_reading_at_'+unicode_type(uuid.uuid4()).replace(u'-', u'') + eid = 'start_reading_at_'+unicode_type(uuid.uuid4()).replace('-', '') elem.set('id', eid) - if u'text' in self.oeb.guide: - self.oeb.guide.remove(u'text') - self.oeb.guide.add(u'text', u'Start', item.href+u'#'+eid) + if 'text' in self.oeb.guide: + self.oeb.guide.remove('text') + self.oeb.guide.add('text', 'Start', item.href+'#'+eid) self.log('Setting start reading at position to %s in %s'%( self.opts.start_reading_at, item.href)) return diff --git a/src/calibre/ebooks/oeb/transforms/trimmanifest.py b/src/calibre/ebooks/oeb/transforms/trimmanifest.py index c9d9b04b6e..d67f0e471c 100644 --- a/src/calibre/ebooks/oeb/transforms/trimmanifest.py +++ b/src/calibre/ebooks/oeb/transforms/trimmanifest.py @@ -1,7 +1,7 @@ ''' OPF manifest trimming transform. ''' -from __future__ import with_statement +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL v3' __copyright__ = '2008, Marshall T. Vandegrift ' diff --git a/src/calibre/ebooks/pml/__init__.py b/src/calibre/ebooks/pml/__init__.py index c01caf569d..2260f2fe7c 100644 --- a/src/calibre/ebooks/pml/__init__.py +++ b/src/calibre/ebooks/pml/__init__.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL v3' __copyright__ = '2009, John Schember ' diff --git a/src/calibre/ebooks/pml/pmlconverter.py b/src/calibre/ebooks/pml/pmlconverter.py index da748469c2..4bef9a306b 100644 --- a/src/calibre/ebooks/pml/pmlconverter.py +++ b/src/calibre/ebooks/pml/pmlconverter.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals ''' Convert pml markup to and from html @@ -229,7 +230,7 @@ class PML_HTMLizer(object): return html def start_line(self): - start = u'' + start = '' state = deepcopy(self.state) div = [] @@ -258,10 +259,10 @@ class PML_HTMLizer(object): else: start += self.STATES_TAGS[key][0] - return u'

%s' % start + return '

%s' % start def end_line(self): - end = u'' + end = '' div = [] span = [] @@ -281,10 +282,10 @@ class PML_HTMLizer(object): else: end += self.STATES_TAGS[key][1] - return u'%s

' % end + return '%s

' % end def process_code(self, code, stream, pre=''): - text = u'' + text = '' code = self.CODE_STATES.get(code, None) if not code: @@ -309,7 +310,7 @@ class PML_HTMLizer(object): return text def process_code_simple(self, code, stream): - text = u'' + text = '' if self.state[code][0]: if code in self.STATES_CLOSE_VALUE_REQ: @@ -330,7 +331,7 @@ class PML_HTMLizer(object): return text def process_code_div(self, code, stream): - text = u'' + text = '' # Close code. if self.state[code][0]: @@ -384,7 +385,7 @@ class PML_HTMLizer(object): return text def process_code_span(self, code, stream): - text = u'' + text = '' # Close code. if self.state[code][0]: @@ -422,7 +423,7 @@ class PML_HTMLizer(object): return text def process_code_block(self, code, stream, pre=''): - text = u'' + text = '' # Close all spans for c in self.SPAN_STATES: @@ -467,7 +468,7 @@ class PML_HTMLizer(object): return text def code_value(self, stream): - value = u'' + value = '' # state 0 is before = # state 1 is before the first " # state 2 is before the second " @@ -506,7 +507,7 @@ class PML_HTMLizer(object): # Unable to complete the sequence to reterieve the value. Reset # the stream to the location it started. stream.seek(loc) - value = u'' + value = '' return value.strip() @@ -565,7 +566,7 @@ class PML_HTMLizer(object): c = line.read(1) while c != '': - text = u'' + text = '' if c == '\\': c = line.read(1) @@ -673,10 +674,10 @@ class PML_HTMLizer(object): indent_state['T'] = False adv_indent_val = '' - output.append(u''.join(parsed)) + output.append(''.join(parsed)) line.close() - output = self.cleanup_html(u'\n'.join(output)) + output = self.cleanup_html('\n'.join(output)) return output @@ -700,18 +701,18 @@ class PML_HTMLizer(object): t_l3 = None for level, (href, id, text) in self.toc: - if level == u'0': + if level == '0': t_l0 = n_toc.add_item(href, id, text) t_l1 = None t_l2 = None t_l3 = None - elif level == u'1': + elif level == '1': if t_l0 is None: t_l0 = n_toc t_l1 = t_l0.add_item(href, id, text) t_l2 = None t_l3 = None - elif level == u'2': + elif level == '2': if t_l1 is None: if t_l0 is None: t_l1 = n_toc @@ -719,7 +720,7 @@ class PML_HTMLizer(object): t_l1 = t_l0 t_l2 = t_l1.add_item(href, id, text) t_l3 = None - elif level == u'3': + elif level == '3': if t_l2 is None: if t_l1 is None: if t_l0 is None: diff --git a/src/calibre/ebooks/pml/pmlml.py b/src/calibre/ebooks/pml/pmlml.py index e99ec66226..7685036733 100644 --- a/src/calibre/ebooks/pml/pmlml.py +++ b/src/calibre/ebooks/pml/pmlml.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL 3' __copyright__ = '2009, John Schember ' @@ -103,7 +104,7 @@ class PMLMLizer(object): def pmlmlize_spine(self): self.image_hrefs = {} self.link_hrefs = {} - output = [u''] + output = [''] output.append(self.get_cover_page()) output.append(self.get_text()) output = ''.join(output) @@ -114,7 +115,7 @@ class PMLMLizer(object): from calibre.ebooks.oeb.stylizer import Stylizer from calibre.ebooks.oeb.base import XHTML - output = u'' + output = '' if 'cover' in self.oeb_book.guide: output += '\\m="cover.png"\n' self.image_hrefs[self.oeb_book.guide['cover'].href] = 'cover.png' @@ -132,7 +133,7 @@ class PMLMLizer(object): from calibre.ebooks.oeb.stylizer import Stylizer from calibre.ebooks.oeb.base import XHTML - text = [u''] + text = [''] for item in self.oeb_book.spine: self.log.debug('Converting %s to PML markup...' % item.href) content = etree.tostring(item.data, encoding='unicode') @@ -155,7 +156,7 @@ class PMLMLizer(object): def get_anchor(self, page, aid): aid = self.get_anchor_id(page.href, aid) - return ur'\Q="%s"' % aid + return r'\Q="%s"' % aid def remove_newlines(self, text): text = text.replace('\r\n', ' ') @@ -192,8 +193,8 @@ class PMLMLizer(object): text = re.sub(unicode_type(r'(?msu)(?P\\(x|X[0-4]))(?P.*?)(?P\\C[0-4]\s*=\s*"[^"]*")(?P.*?)(?P=t)'), r'\g\g\g\g', text) # Replace bad characters. - text = text.replace(u'\xc2', '') - text = text.replace(u'\xa0', ' ') + text = text.replace('\xc2', '') + text = text.replace('\xa0', ' ') # Turn all characters that cannot be represented by themself into their # PML code equivelent diff --git a/src/calibre/ebooks/rb/__init__.py b/src/calibre/ebooks/rb/__init__.py index f45b966dad..f942dc3eb2 100644 --- a/src/calibre/ebooks/rb/__init__.py +++ b/src/calibre/ebooks/rb/__init__.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL 3' __copyright__ = '2009, John Schember ' @@ -6,6 +7,8 @@ __docformat__ = 'restructuredtext en' import os +from polyglot.builtins import unicode_type + HEADER = b'\xb0\x0c\xb0\x0c\x02\x00NUVO\x00\x00\x00\x00' @@ -21,7 +24,7 @@ def unique_name(name, used_names): ext = os.path.splitext(name)[1][:3] base_name = name[:22] for i in range(0, 9999): - name = '%s-%s.%s' % (str(i).rjust('0', 4)[:4], base_name, ext) + name = '%s-%s.%s' % (unicode_type(i).rjust('0', 4)[:4], base_name, ext) if name not in used_names: break return name diff --git a/src/calibre/ebooks/rb/writer.py b/src/calibre/ebooks/rb/writer.py index 9f4818725f..af671295bc 100644 --- a/src/calibre/ebooks/rb/writer.py +++ b/src/calibre/ebooks/rb/writer.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL 3' __copyright__ = '2009, John Schember ' diff --git a/src/calibre/ebooks/readability/cleaners.py b/src/calibre/ebooks/readability/cleaners.py index d30216c4d8..ee160f594b 100644 --- a/src/calibre/ebooks/readability/cleaners.py +++ b/src/calibre/ebooks/readability/cleaners.py @@ -1,3 +1,5 @@ +from __future__ import absolute_import, division, print_function, unicode_literals + # strip out a set of nuisance html attributes that can mess up rendering in RSS feeds import re from lxml.html.clean import Cleaner diff --git a/src/calibre/ebooks/readability/debug.py b/src/calibre/ebooks/readability/debug.py index 103bb5f9f0..c8acf510cf 100644 --- a/src/calibre/ebooks/readability/debug.py +++ b/src/calibre/ebooks/readability/debug.py @@ -1,3 +1,5 @@ +from __future__ import absolute_import, division, print_function, unicode_literals + def save_to_file(text, filename): f = open(filename, 'wt') f.write('') diff --git a/src/calibre/ebooks/readability/htmls.py b/src/calibre/ebooks/readability/htmls.py index 692f26c2ca..56aa159508 100644 --- a/src/calibre/ebooks/readability/htmls.py +++ b/src/calibre/ebooks/readability/htmls.py @@ -1,3 +1,5 @@ +from __future__ import absolute_import, division, print_function, unicode_literals + import re from lxml.html import tostring @@ -20,14 +22,14 @@ def js_re(src, pattern, flags, repl): def normalize_entities(cur_title): entities = { - u'\u2014':'-', - u'\u2013':'-', - u'—': '-', - u'–': '-', - u'\u00A0': ' ', - u'\u00AB': '"', - u'\u00BB': '"', - u'"': '"', + '\u2014':'-', + '\u2013':'-', + '—': '-', + '–': '-', + '\u00A0': ' ', + '\u00AB': '"', + '\u00BB': '"', + '"': '"', } for c, r in iteritems(entities): if c in cur_title: diff --git a/src/calibre/ebooks/readability/readability.py b/src/calibre/ebooks/readability/readability.py index bef8caf307..e8cb581b10 100644 --- a/src/calibre/ebooks/readability/readability.py +++ b/src/calibre/ebooks/readability/readability.py @@ -156,7 +156,7 @@ class Document: return cleaned_article except Exception as e: self.log.exception('error getting summary: ') - reraise(Unparseable, Unparseable(str(e)), sys.exc_info()[2]) + reraise(Unparseable, Unparseable(unicode_type(e)), sys.exc_info()[2]) def get_article(self, candidates, best_candidate): # Now that we have the top candidate, look through its siblings for content that might also be related. @@ -216,7 +216,7 @@ class Document: def score_paragraphs(self, ): MIN_LEN = self.options.get('min_text_length', self.TEXT_LENGTH_THRESHOLD) candidates = {} - # self.debug(str([describe(node) for node in self.tags(self.html, "div")])) + # self.debug(unicode_type([describe(node) for node in self.tags(self.html, "div")])) ordered = [] for elem in self.tags(self.html, "p", "pre", "td"): @@ -316,7 +316,7 @@ class Document: if not REGEXES['divToPElementsRe'].search(unicode_type(''.join(map(tounicode, list(elem))))): # self.debug("Altering %s to p" % (describe(elem))) elem.tag = "p" - # print "Fixed element "+describe(elem) + # print("Fixed element "+describe(elem)) for elem in self.tags(self.html, 'div'): if elem.text and elem.text.strip(): @@ -324,7 +324,7 @@ class Document: p.text = elem.text elem.text = None elem.insert(0, p) - # print "Appended "+tounicode(p)+" to "+describe(elem) + # print("Appended "+tounicode(p)+" to "+describe(elem)) for pos, child in reversed(list(enumerate(elem))): if child.tail and child.tail.strip(): @@ -332,9 +332,9 @@ class Document: p.text = child.tail child.tail = None elem.insert(pos + 1, p) - # print "Inserted "+tounicode(p)+" to "+describe(elem) + # print("Inserted "+tounicode(p)+" to "+describe(elem)) if child.tag == 'br': - # print 'Dropped
at '+describe(elem) + # print('Dropped
at '+describe(elem)) child.drop_tree() def tags(self, node, *tag_names): @@ -363,7 +363,7 @@ class Document: weight = self.class_weight(el) if el in candidates: content_score = candidates[el]['content_score'] - # print '!',el, '-> %6.3f' % content_score + # print('!',el, '-> %6.3f' % content_score) else: content_score = 0 tag = el.tag @@ -457,7 +457,7 @@ class Document: siblings.append(sib_content_length) if j == x: break - # self.debug(str(siblings)) + # self.debug(unicode_type(siblings)) if siblings and sum(siblings) > 1000 : to_remove = False self.debug("Allowing %s" % describe(el)) @@ -467,7 +467,7 @@ class Document: if to_remove: self.debug("Cleaned %6.3f %s with weight %s cause it has %s." % (content_score, describe(el), weight, reason)) - # print tounicode(el) + # print(tounicode(el)) # self.debug("pname %s pweight %.3f" %(pname, pweight)) el.drop_tree() diff --git a/src/calibre/ebooks/rtf/input.py b/src/calibre/ebooks/rtf/input.py index 8ff793b5d4..075eaaa36b 100644 --- a/src/calibre/ebooks/rtf/input.py +++ b/src/calibre/ebooks/rtf/input.py @@ -1,4 +1,5 @@ -from __future__ import with_statement +from __future__ import absolute_import, division, print_function, unicode_literals + __license__ = 'GPL v3' __copyright__ = '2008, Kovid Goyal ' @@ -36,5 +37,3 @@ class InlineClass(etree.XSLTExtension): classes.append('col%d'%self.colors.index(fc)) output_parent.text = ' '.join(classes) - - diff --git a/src/calibre/ebooks/rtf/preprocess.py b/src/calibre/ebooks/rtf/preprocess.py index aae0a1502d..04d3c1124b 100644 --- a/src/calibre/ebooks/rtf/preprocess.py +++ b/src/calibre/ebooks/rtf/preprocess.py @@ -1,7 +1,6 @@ #!/usr/bin/env python2 # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai -from __future__ import with_statement -from __future__ import print_function +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL v3' __copyright__ = '2010, Gerendi Sandor Attila' diff --git a/src/calibre/ebooks/rtf/rtfml.py b/src/calibre/ebooks/rtf/rtfml.py index 7f6cc91c50..5944c4f228 100644 --- a/src/calibre/ebooks/rtf/rtfml.py +++ b/src/calibre/ebooks/rtf/rtfml.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL 3' __copyright__ = '2009, John Schember ' @@ -83,11 +84,12 @@ def txt2rtf(text): for x in text: val = ord(x) if val == 160: - buf.write(ur'\~') + buf.write(r'\~') elif val <= 127: buf.write(unicode_type(x)) else: - c = unicode_type(r'\u{0:d}?'.format(val)) + # python2 and ur'\u' does not work + c = unicode_type('\\u{0:d}?'.format(val)) buf.write(c) return buf.getvalue() @@ -120,7 +122,7 @@ class RTFMLizer(object): self.log.debug('Converting %s to RTF markup...' % item.href) # Removing comments is needed as comments with -- inside them can # cause fromstring() to fail - content = re.sub(u'', u'', etree.tostring(item.data, encoding='unicode'), flags=re.DOTALL) + content = re.sub('', '', etree.tostring(item.data, encoding='unicode'), flags=re.DOTALL) content = self.remove_newlines(content) content = self.remove_tabs(content) content = etree.fromstring(content) @@ -149,7 +151,7 @@ class RTFMLizer(object): return text def header(self): - header = u'{\\rtf1{\\info{\\title %s}{\\author %s}}\\ansi\\ansicpg1252\\deff0\\deflang1033\n' % ( + header = '{\\rtf1{\\info{\\title %s}{\\author %s}}\\ansi\\ansicpg1252\\deff0\\deflang1033\n' % ( self.oeb_book.metadata.title[0].value, authors_to_string([x.value for x in self.oeb_book.metadata.creator])) return header + ( '{\\fonttbl{\\f0\\froman\\fprq2\\fcharset128 Times New Roman;}{\\f1\\froman\\fprq2\\fcharset128 Times New Roman;}{\\f2\\fswiss\\fprq2\\fcharset128 Arial;}{\\f3\\fnil\\fprq2\\fcharset128 Arial;}{\\f4\\fnil\\fprq2\\fcharset128 MS Mincho;}{\\f5\\fnil\\fprq2\\fcharset128 Tahoma;}{\\f6\\fnil\\fprq0\\fcharset128 Tahoma;}}\n' # noqa @@ -215,7 +217,7 @@ class RTFMLizer(object): text = re.sub(r'(\{\\line \}\s*){3,}', r'{\\line }{\\line }', text) # Remove non-breaking spaces - text = text.replace(u'\xa0', ' ') + text = text.replace('\xa0', ' ') text = text.replace('\n\r', '\n') return text @@ -230,16 +232,16 @@ class RTFMLizer(object): if p is not None and isinstance(p.tag, string_or_bytes) and namespace(p.tag) == XHTML_NS \ and elem.tail: return elem.tail - return u'' + return '' - text = u'' + text = '' style = stylizer.style(elem) if style['display'] in ('none', 'oeb-page-head', 'oeb-page-foot') \ or style['visibility'] == 'hidden': if hasattr(elem, 'tail') and elem.tail: return elem.tail - return u'' + return '' tag = barename(elem.tag) tag_count = 0 @@ -292,9 +294,9 @@ class RTFMLizer(object): end_tag = tag_stack.pop() if end_tag != 'block': if tag in BLOCK_TAGS: - text += ur'\par\pard\plain\hyphpar}' + text += r'\par\pard\plain\hyphpar}' else: - text += u'}' + text += '}' if hasattr(elem, 'tail') and elem.tail: if 'block' in tag_stack: diff --git a/src/calibre/ebooks/rtf2xml/ParseRtf.py b/src/calibre/ebooks/rtf2xml/ParseRtf.py index 01a26ba85c..164e706a03 100644 --- a/src/calibre/ebooks/rtf2xml/ParseRtf.py +++ b/src/calibre/ebooks/rtf2xml/ParseRtf.py @@ -1,4 +1,4 @@ -from __future__ import unicode_literals, absolute_import, print_function, division +from __future__ import absolute_import, division, print_function, unicode_literals ######################################################################### # # # # @@ -26,6 +26,8 @@ from calibre.ebooks.rtf2xml import headings_to_sections, \ body_styles, preamble_rest, group_styles, \ inline from calibre.ebooks.rtf2xml.old_rtf import OldRtf +from polyglot.builtins import unicode_type + from . import open_for_read, open_for_write """ @@ -248,7 +250,7 @@ class ParseRtf: enc = encode_obj.get_codepage() # TODO: to check if cp is a good idea or if I should use a dict to convert enc = 'cp' + enc - msg = '%s\nException in token processing' % str(msg) + msg = '%s\nException in token processing' % unicode_type(msg) if check_encoding_obj.check_encoding(self.__file, enc): file_name = self.__file if isinstance(self.__file, bytes) \ else self.__file.encode('utf-8') diff --git a/src/calibre/ebooks/rtf2xml/check_encoding.py b/src/calibre/ebooks/rtf2xml/check_encoding.py index 37ac305e1f..4f8a04ceda 100644 --- a/src/calibre/ebooks/rtf2xml/check_encoding.py +++ b/src/calibre/ebooks/rtf2xml/check_encoding.py @@ -1,7 +1,9 @@ #!/usr/bin/env python2 -from __future__ import unicode_literals, absolute_import, print_function, division +from __future__ import absolute_import, division, print_function, unicode_literals + import sys +from polyglot.builtins import unicode_type class CheckEncoding: @@ -15,7 +17,7 @@ class CheckEncoding: try: char.decode(encoding) except ValueError as msg: - sys.stderr.write('line: %s char: %s\n%s\n' % (line_num, char_position, str(msg))) + sys.stderr.write('line: %s char: %s\n%s\n' % (line_num, char_position, unicode_type(msg))) def check_encoding(self, path, encoding='us-ascii', verbose=True): line_num = 0 diff --git a/src/calibre/ebooks/rtf2xml/footnote.py b/src/calibre/ebooks/rtf2xml/footnote.py index 007febb775..36e7624134 100644 --- a/src/calibre/ebooks/rtf2xml/footnote.py +++ b/src/calibre/ebooks/rtf2xml/footnote.py @@ -1,4 +1,4 @@ -from __future__ import unicode_literals, absolute_import, print_function, division +from __future__ import absolute_import, division, print_function, unicode_literals ######################################################################### # # # # @@ -15,6 +15,8 @@ import os from calibre.ebooks.rtf2xml import copy from calibre.ptempfile import better_mktemp +from polyglot.builtins import unicode_type + from . import open_for_read, open_for_write @@ -56,7 +58,7 @@ class Footnote: if self.__first_line: self.__first_line_func(line) if self.__token_info == 'cw 3: sys.stderr.write( 'Old rtf construction %s (bracket %s, line %s)\n' % ( - self.__inline_info, str(self.__ob_group), line_num) + self.__inline_info, unicode_type(self.__ob_group), line_num) ) return True self.__previous_token = line[6:16] diff --git a/src/calibre/ebooks/rtf2xml/paragraph_def.py b/src/calibre/ebooks/rtf2xml/paragraph_def.py index 45c2f136ec..f5aab5df05 100644 --- a/src/calibre/ebooks/rtf2xml/paragraph_def.py +++ b/src/calibre/ebooks/rtf2xml/paragraph_def.py @@ -1,4 +1,4 @@ -from __future__ import unicode_literals, absolute_import, print_function, division +from __future__ import absolute_import, division, print_function, unicode_literals ######################################################################### # # # # @@ -12,8 +12,11 @@ from __future__ import unicode_literals, absolute_import, print_function, divisi # # ######################################################################### import sys, os + from calibre.ebooks.rtf2xml import copy, border_parse from calibre.ptempfile import better_mktemp +from polyglot.builtins import unicode_type + from . import open_for_read, open_for_write @@ -621,7 +624,7 @@ if another paragraph_def is found, the state changes to collect_tokens. num = len(self.__style_num_strings) new_style = 1 num = '%04d' % num - self.__att_val_dict['style-num'] = 's' + str(num) + self.__att_val_dict['style-num'] = 's' + unicode_type(num) if new_style: self.__write_body_styles() diff --git a/src/calibre/ebooks/rtf2xml/pict.py b/src/calibre/ebooks/rtf2xml/pict.py index 62fa905db5..f3b1f74f18 100644 --- a/src/calibre/ebooks/rtf2xml/pict.py +++ b/src/calibre/ebooks/rtf2xml/pict.py @@ -1,4 +1,4 @@ -from __future__ import unicode_literals, absolute_import, print_function, division +from __future__ import absolute_import, division, print_function, unicode_literals ######################################################################### # # # # @@ -15,6 +15,8 @@ import sys, os from calibre.ebooks.rtf2xml import copy from calibre.ptempfile import better_mktemp +from polyglot.builtins import unicode_type + from . import open_for_read, open_for_write @@ -76,7 +78,7 @@ class Pict: try: os.mkdir(self.__dir_name) except OSError as msg: - msg = "%sCouldn't make directory '%s':\n" % (str(msg), self.__dir_name) + msg = "%sCouldn't make directory '%s':\n" % (unicode_type(msg), self.__dir_name) raise self.__bug_handler else: if self.__run_level > 1: diff --git a/src/calibre/ebooks/rtf2xml/process_tokens.py b/src/calibre/ebooks/rtf2xml/process_tokens.py index c7a720f152..e64fba4d8c 100644 --- a/src/calibre/ebooks/rtf2xml/process_tokens.py +++ b/src/calibre/ebooks/rtf2xml/process_tokens.py @@ -1,4 +1,4 @@ -from __future__ import unicode_literals, absolute_import, print_function, division +from __future__ import absolute_import, division, print_function, unicode_literals ######################################################################### # # # # @@ -15,6 +15,8 @@ import os, re from calibre.ebooks.rtf2xml import copy, check_brackets from calibre.ptempfile import better_mktemp +from polyglot.builtins import unicode_type + from . import open_for_read, open_for_write @@ -693,7 +695,7 @@ class ProcessTokens: if num[-1] == ';': num = num[:-1] third_field = 'en' - num = str('%X' % int(num)) + num = unicode_type('%X' % int(num)) if len(num) != 2: num = "0" + num return 'cw<%s<%s<%s<%s\n' % (pre, token, third_field, num) @@ -730,7 +732,7 @@ class ProcessTokens: return 0 num = '%0.2f' % round(numerator/denominator, 2) return num - string_num = str(num) + string_num = unicode_type(num) if string_num[-2:] == ".0": string_num = string_num[:-2] return string_num diff --git a/src/calibre/ebooks/rtf2xml/sections.py b/src/calibre/ebooks/rtf2xml/sections.py index 3fbd7b3187..fdc0ed4eb6 100644 --- a/src/calibre/ebooks/rtf2xml/sections.py +++ b/src/calibre/ebooks/rtf2xml/sections.py @@ -1,4 +1,4 @@ -from __future__ import unicode_literals, absolute_import, print_function, division +from __future__ import absolute_import, division, print_function, unicode_literals ######################################################################### # # # # @@ -15,6 +15,8 @@ import sys, os from calibre.ebooks.rtf2xml import copy from calibre.ptempfile import better_mktemp +from polyglot.builtins import unicode_type + from . import open_for_read, open_for_write @@ -274,8 +276,8 @@ class Sections: my_string += 'mi%s' 'rtf-native' '0\n' - % (str(self.__section_num), str(self.__section_num)) + % (unicode_type(self.__section_num), unicode_type(self.__section_num)) ) self.__found_first_sec = 1 elif self.__token_info == 'tx%s' 'rtf-native' '0\n' - % (str(self.__section_num), str(self.__section_num)) + % (unicode_type(self.__section_num), unicode_type(self.__section_num)) ) self.__write_obj.write( 'cw%s' % str(num) + 'mi%s' % unicode_type(num) ) if self.__list_of_sec_values: keys = self.__list_of_sec_values[0].keys() @@ -471,7 +473,7 @@ class Sections: self.__list_of_sec_values = self.__list_of_sec_values[1:] self.__write_obj.write('0') self.__write_obj.write('rtf-native') - self.__write_obj.write('%s' % str(self.__section_num)) + self.__write_obj.write('%s' % unicode_type(self.__section_num)) self.__write_obj.write('\n') # Look here diff --git a/src/calibre/ebooks/rtf2xml/table.py b/src/calibre/ebooks/rtf2xml/table.py index 4424a4978a..139dea4971 100644 --- a/src/calibre/ebooks/rtf2xml/table.py +++ b/src/calibre/ebooks/rtf2xml/table.py @@ -1,4 +1,4 @@ -from __future__ import unicode_literals, absolute_import, print_function, division +from __future__ import absolute_import, division, print_function, unicode_literals ######################################################################### # # # # @@ -12,8 +12,11 @@ from __future__ import unicode_literals, absolute_import, print_function, divisi # # ######################################################################### import sys, os + from calibre.ebooks.rtf2xml import copy, border_parse from calibre.ptempfile import better_mktemp +from polyglot.builtins import unicode_type + from . import open_for_read, open_for_write """ @@ -397,13 +400,13 @@ class Table: left_position = float(left_position) width = new_cell_position - self.__last_cell_position - left_position # width = round(width, 2) - width = str('%.2f' % width) + width = unicode_type('%.2f' % width) self.__last_cell_position = new_cell_position widths_exists = self.__row_dict.get('widths') if widths_exists: - self.__row_dict['widths'] += ', %s' % str(width) + self.__row_dict['widths'] += ', %s' % unicode_type(width) else: - self.__row_dict['widths'] = str(width) + self.__row_dict['widths'] = unicode_type(width) self.__cell_list[-1]['width'] = width self.__cell_list.append({}) self.__cell_widths.append(width) diff --git a/src/calibre/ebooks/snb/__init__.py b/src/calibre/ebooks/snb/__init__.py index 3d97812b9b..25d2014767 100644 --- a/src/calibre/ebooks/snb/__init__.py +++ b/src/calibre/ebooks/snb/__init__.py @@ -1,4 +1,6 @@ #!/usr/bin/env python2 +from __future__ import absolute_import, division, print_function, unicode_literals + __license__ = 'GPL v3' __copyright__ = '2010, Li Fanxi ' __docformat__ = 'restructuredtext en' @@ -6,4 +8,3 @@ __docformat__ = 'restructuredtext en' ''' Used for snb output ''' - diff --git a/src/calibre/ebooks/snb/snbml.py b/src/calibre/ebooks/snb/snbml.py index 659959e6f0..c93d3d3701 100644 --- a/src/calibre/ebooks/snb/snbml.py +++ b/src/calibre/ebooks/snb/snbml.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL 3' __copyright__ = '2010, Li Fanxi ' @@ -93,19 +94,19 @@ class SNBMLizer(object): snbcHead = etree.SubElement(snbcTree, "head") etree.SubElement(snbcHead, "title").text = subtitle if self.opts and self.opts.snb_hide_chapter_name: - etree.SubElement(snbcHead, "hidetitle").text = u"true" + etree.SubElement(snbcHead, "hidetitle").text = "true" etree.SubElement(snbcTree, "body") trees[subitem] = snbcTree - output.append(u'%s%s\n\n' % (CALIBRE_SNB_BM_TAG, "")) + output.append('%s%s\n\n' % (CALIBRE_SNB_BM_TAG, "")) output += self.dump_text(self.subitems, etree.fromstring(content), stylizer)[0] - output = self.cleanup_text(u''.join(output)) + output = self.cleanup_text(''.join(output)) subitem = '' bodyTree = trees[subitem].find(".//body") for line in output.splitlines(): pos = line.find(CALIBRE_SNB_PRE_TAG) if pos == -1: - line = line.strip(u' \t\n\r\u3000') + line = line.strip(' \t\n\r\u3000') else: etree.SubElement(bodyTree, "text").text = \ etree.CDATA(line[pos+len(CALIBRE_SNB_PRE_TAG):]) @@ -124,14 +125,14 @@ class SNBMLizer(object): bodyTree = trees[subitem].find(".//body") else: if self.opts and not self.opts.snb_dont_indent_first_line: - prefix = u'\u3000\u3000' + prefix = '\u3000\u3000' else: - prefix = u'' + prefix = '' etree.SubElement(bodyTree, "text").text = \ etree.CDATA(unicode_type(prefix + line)) if self.opts and self.opts.snb_insert_empty_line: etree.SubElement(bodyTree, "text").text = \ - etree.CDATA(u'') + etree.CDATA('') return trees @@ -146,9 +147,9 @@ class SNBMLizer(object): def cleanup_text(self, text): self.log.debug('\tClean up text...') # Replace bad characters. - text = text.replace(u'\xc2', '') - text = text.replace(u'\xa0', ' ') - text = text.replace(u'\xa9', '(C)') + text = text.replace('\xc2', '') + text = text.replace('\xa0', ' ') + text = text.replace('\xa9', '(C)') # Replace tabs, vertical tags and form feeds with single space. text = text.replace('\t+', ' ') @@ -226,7 +227,7 @@ class SNBMLizer(object): if elem.attrib.get('id') is not None and elem.attrib['id'] in [href for href, title in subitems]: if self.curSubItem is not None and self.curSubItem != elem.attrib['id']: self.curSubItem = elem.attrib['id'] - text.append(u'\n\n%s%s\n\n' % (CALIBRE_SNB_BM_TAG, self.curSubItem)) + text.append('\n\n%s%s\n\n' % (CALIBRE_SNB_BM_TAG, self.curSubItem)) if style['display'] in ('none', 'oeb-page-head', 'oeb-page-foot') \ or style['visibility'] == 'hidden': @@ -240,18 +241,18 @@ class SNBMLizer(object): # Are we in a paragraph block? if tag in BLOCK_TAGS or style['display'] in BLOCK_STYLES: in_block = True - if not end.endswith(u'\n\n') and hasattr(elem, 'text') and elem.text: - text.append(u'\n\n') + if not end.endswith('\n\n') and hasattr(elem, 'text') and elem.text: + text.append('\n\n') if tag in SPACE_TAGS: if not end.endswith('u ') and hasattr(elem, 'text') and elem.text: - text.append(u' ') + text.append(' ') if tag == 'img': - text.append(u'\n\n%s%s\n\n' % (CALIBRE_SNB_IMG_TAG, ProcessFileName(elem.attrib['src']))) + text.append('\n\n%s%s\n\n' % (CALIBRE_SNB_IMG_TAG, ProcessFileName(elem.attrib['src']))) if tag == 'br': - text.append(u'\n\n') + text.append('\n\n') if tag == 'li': li = '- ' @@ -260,24 +261,24 @@ class SNBMLizer(object): # Process tags that contain text. if hasattr(elem, 'text') and elem.text: if pre: - text.append((u'\n\n%s' % CALIBRE_SNB_PRE_TAG).join((li + elem.text).splitlines())) + text.append(('\n\n%s' % CALIBRE_SNB_PRE_TAG).join((li + elem.text).splitlines())) else: text.append(li + elem.text) li = '' for item in elem: - en = u'' + en = '' if len(text) >= 2: en = text[-1][-2:] t = self.dump_text(subitems, item, stylizer, en, pre, li)[0] text += t if in_block: - text.append(u'\n\n') + text.append('\n\n') if hasattr(elem, 'tail') and elem.tail: if pre: - text.append((u'\n\n%s' % CALIBRE_SNB_PRE_TAG).join(elem.tail.splitlines())) + text.append(('\n\n%s' % CALIBRE_SNB_PRE_TAG).join(elem.tail.splitlines())) else: text.append(li + elem.tail) li = '' diff --git a/src/calibre/ebooks/unihandecode/__init__.py b/src/calibre/ebooks/unihandecode/__init__.py index 153d8221fe..91238eddaa 100644 --- a/src/calibre/ebooks/unihandecode/__init__.py +++ b/src/calibre/ebooks/unihandecode/__init__.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL 3' __copyright__ = '2010, Hiroshi Miura ' @@ -27,13 +28,13 @@ class Unihandecoder(object): def __init__(self, lang="zh", encoding='utf-8'): self.preferred_encoding = encoding lang = lang.lower() - if lang[:2] == u'ja': + if lang[:2] == 'ja': from calibre.ebooks.unihandecode.jadecoder import Jadecoder self.decoder = Jadecoder() - elif lang[:2] == u'kr' or lang == u'korean': + elif lang[:2] == 'kr' or lang == 'korean': from calibre.ebooks.unihandecode.krdecoder import Krdecoder self.decoder = Krdecoder() - elif lang[:2] == u'vn' or lang == u'vietnum': + elif lang[:2] == 'vn' or lang == 'vietnum': from calibre.ebooks.unihandecode.vndecoder import Vndecoder self.decoder = Vndecoder() else: # zh and others diff --git a/src/calibre/ebooks/unihandecode/jacodepoints.py b/src/calibre/ebooks/unihandecode/jacodepoints.py index 5d8e3db279..89d83d94b6 100644 --- a/src/calibre/ebooks/unihandecode/jacodepoints.py +++ b/src/calibre/ebooks/unihandecode/jacodepoints.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL 3' __copyright__ = '2010 Hiroshi Miura ' @@ -9,7 +10,7 @@ Unicode code point dictionary. Based on Unicode.org Unihan database. ''' -CODEPOINTS = { +CODEPOINTS = { 'x34':[ 'Qiu ','Tian ','','','Kua ','Wu ','Yin ','','','','','','Si ','','','', '','','','','','','Ye ','','','','','','Chou ','','','', diff --git a/src/calibre/ebooks/unihandecode/jadecoder.py b/src/calibre/ebooks/unihandecode/jadecoder.py index b49c1144c0..d6318c270d 100644 --- a/src/calibre/ebooks/unihandecode/jadecoder.py +++ b/src/calibre/ebooks/unihandecode/jadecoder.py @@ -1,4 +1,6 @@ # coding:utf-8 +from __future__ import absolute_import, division, print_function, unicode_literals + __license__ = 'GPL 3' __copyright__ = '2010, Hiroshi Miura ' __docformat__ = 'restructuredtext en' @@ -39,4 +41,3 @@ class Jadecoder(Unidecoder): return re.sub('[^\x00-\x7f]', lambda x: self.replace_point(x.group()),result) except: return re.sub('[^\x00-\x7f]', lambda x: self.replace_point(x.group()),text) - diff --git a/src/calibre/ebooks/unihandecode/krcodepoints.py b/src/calibre/ebooks/unihandecode/krcodepoints.py index cdb711afdd..bca8e3f4b4 100644 --- a/src/calibre/ebooks/unihandecode/krcodepoints.py +++ b/src/calibre/ebooks/unihandecode/krcodepoints.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL 3' __copyright__ = '2010 Hiroshi Miura ' @@ -9,7 +10,7 @@ Unicode code point dictionary. Based on Unicode.org Unihan database. ''' -CODEPOINTS = { +CODEPOINTS = { 'x34':[ 'Qiu ','Tian ','','','Kua ','Wu ','Yin ','','','','','','Si ','','','', '','','','','','','Ye ','','','','','','Chou ','','','', diff --git a/src/calibre/ebooks/unihandecode/krdecoder.py b/src/calibre/ebooks/unihandecode/krdecoder.py index af5b3b39e8..914f6f41c6 100644 --- a/src/calibre/ebooks/unihandecode/krdecoder.py +++ b/src/calibre/ebooks/unihandecode/krdecoder.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL 3' __copyright__ = '2010, Hiroshi Miura ' @@ -22,4 +23,3 @@ class Krdecoder(Unidecoder): def __init__(self): self.codepoints = CODEPOINTS self.codepoints.update(HANCODES) - diff --git a/src/calibre/ebooks/unihandecode/pykakasi/__init__.py b/src/calibre/ebooks/unihandecode/pykakasi/__init__.py index c92e541a82..4995491752 100644 --- a/src/calibre/ebooks/unihandecode/pykakasi/__init__.py +++ b/src/calibre/ebooks/unihandecode/pykakasi/__init__.py @@ -1,5 +1,6 @@ +from __future__ import absolute_import, division, print_function, unicode_literals + from calibre.ebooks.unihandecode.pykakasi.kakasi import kakasi kakasi __all__ = ["pykakasi"] - diff --git a/src/calibre/ebooks/unihandecode/pykakasi/h2a.py b/src/calibre/ebooks/unihandecode/pykakasi/h2a.py index 409a110093..ebbf06fdf3 100644 --- a/src/calibre/ebooks/unihandecode/pykakasi/h2a.py +++ b/src/calibre/ebooks/unihandecode/pykakasi/h2a.py @@ -20,6 +20,7 @@ # * GNU General Public License for more details. # * # */ +from __future__ import absolute_import, division, print_function, unicode_literals from polyglot.builtins import range @@ -27,137 +28,137 @@ from polyglot.builtins import range class H2a (object): H2a_table = { - u"\u3041":"a", u"\u3042":"a", - u"\u3043":"i", u"\u3044":"i", - u"\u3045":"u", u"\u3046":"u", - u"\u3046\u309b":"vu", u"\u3046\u309b\u3041":"va", - u"\u3046\u309b\u3043":"vi", u"\u3046\u309b\u3047":"ve", - u"\u3046\u309b\u3049":"vo", - u"\u3047":"e", u"\u3048":"e", - u"\u3049":"o", u"\u304a":"o", + "\u3041":"a", "\u3042":"a", + "\u3043":"i", "\u3044":"i", + "\u3045":"u", "\u3046":"u", + "\u3046\u309b":"vu", "\u3046\u309b\u3041":"va", + "\u3046\u309b\u3043":"vi", "\u3046\u309b\u3047":"ve", + "\u3046\u309b\u3049":"vo", + "\u3047":"e", "\u3048":"e", + "\u3049":"o", "\u304a":"o", - u"\u304b":"ka", u"\u304c":"ga", - u"\u304d":"ki", u"\u304d\u3041":"kya", - u"\u304d\u3045":"kyu", u"\u304d\u3049":"kyo", - u"\u304e":"gi", u"\u3050\u3083":"gya", - u"\u304e\u3045":"gyu", u"\u304e\u3087":"gyo", - u"\u304f":"ku", u"\u3050":"gu", - u"\u3051":"ke", u"\u3052":"ge", - u"\u3053":"ko", u"\u3054":"go", + "\u304b":"ka", "\u304c":"ga", + "\u304d":"ki", "\u304d\u3041":"kya", + "\u304d\u3045":"kyu", "\u304d\u3049":"kyo", + "\u304e":"gi", "\u3050\u3083":"gya", + "\u304e\u3045":"gyu", "\u304e\u3087":"gyo", + "\u304f":"ku", "\u3050":"gu", + "\u3051":"ke", "\u3052":"ge", + "\u3053":"ko", "\u3054":"go", - u"\u3055":"sa", u"\u3056":"za", - u"\u3057":"shi", u"\u3057\u3083":"sha", - u"\u3057\u3085":"shu", u"\u3057\u3087":"sho", - u"\u3058":"ji", u"\u3058\u3083":"ja", - u"\u3058\u3085":"ju", u"\u3058\u3087":"jo", - u"\u3059":"su", u"\u305a":"zu", - u"\u305b":"se", u"\u305c":"ze", - u"\u305d":"so", u"\u305e":"zo", + "\u3055":"sa", "\u3056":"za", + "\u3057":"shi", "\u3057\u3083":"sha", + "\u3057\u3085":"shu", "\u3057\u3087":"sho", + "\u3058":"ji", "\u3058\u3083":"ja", + "\u3058\u3085":"ju", "\u3058\u3087":"jo", + "\u3059":"su", "\u305a":"zu", + "\u305b":"se", "\u305c":"ze", + "\u305d":"so", "\u305e":"zo", - u"\u305f":"ta", u"\u3060":"da", - u"\u3061":"chi", u"\u3061\u3047":"che", u"\u3061\u3083":"cha", - u"\u3061\u3085":"chu", u"\u3061\u3087":"cho", - u"\u3062":"ji", u"\u3062\u3083":"ja", - u"\u3062\u3085":"ju", u"\u3062\u3087":"jo", + "\u305f":"ta", "\u3060":"da", + "\u3061":"chi", "\u3061\u3047":"che", "\u3061\u3083":"cha", + "\u3061\u3085":"chu", "\u3061\u3087":"cho", + "\u3062":"ji", "\u3062\u3083":"ja", + "\u3062\u3085":"ju", "\u3062\u3087":"jo", - u"\u3063":"tsu", - u"\u3063\u3046\u309b":"vvu", - u"\u3063\u3046\u309b\u3041":"vva", - u"\u3063\u3046\u309b\u3043":"vvi", - u"\u3063\u3046\u309b\u3047":"vve", - u"\u3063\u3046\u309b\u3049":"vvo", - u"\u3063\u304b":"kka", u"\u3063\u304c":"gga", - u"\u3063\u304d":"kki", u"\u3063\u304d\u3083":"kkya", - u"\u3063\u304d\u3085":"kkyu", u"\u3063\u304d\u3087":"kkyo", - u"\u3063\u304e":"ggi", u"\u3063\u304e\u3083":"ggya", - u"\u3063\u304e\u3085":"ggyu", u"\u3063\u304e\u3087":"ggyo", - u"\u3063\u304f":"kku", u"\u3063\u3050":"ggu", - u"\u3063\u3051":"kke", u"\u3063\u3052":"gge", - u"\u3063\u3053":"kko", u"\u3063\u3054":"ggo", - u"\u3063\u3055":"ssa", u"\u3063\u3056":"zza", - u"\u3063\u3057":"sshi", u"\u3063\u3057\u3083":"ssha", - u"\u3063\u3057\u3085":"sshu", u"\u3063\u3057\u3087":"ssho", - u"\u3063\u3058":"jji", u"\u3063\u3058\u3083":"jja", - u"\u3063\u3058\u3085":"jju", u"\u3063\u3058\u3087":"jjo", - u"\u3063\u3059":"ssu", u"\u3063\u305a":"zzu", - u"\u3063\u305b":"sse", u"\u3063\u305e":"zze", - u"\u3063\u305d":"sso", u"\u3063\u305c":"zzo", - u"\u3063\u305f":"tta", u"\u3063\u3060":"dda", - u"\u3063\u3061":"tchi", u"\u3063\u3061\u3083":"tcha", - u"\u3063\u3061\u3085":"tchu", u"\u3063\u3061\u3087":"tcho", - u"\u3063\u3062":"jji", u"\u3063\u3062\u3083":"jjya", - u"\u3063\u3062\u3085":"jjyu", u"\u3063\u3062\u3087":"jjyo", - u"\u3063\u3064":"ttsu", u"\u3063\u3065":"zzu", - u"\u3063\u3066":"tte", u"\u3063\u3067":"dde", - u"\u3063\u3068":"tto", u"\u3063\u3069":"ddo", - u"\u3063\u306f":"hha", u"\u3063\u3070":"bba", - u"\u3063\u3071":"ppa", - u"\u3063\u3072":"hhi", u"\u3063\u3072\u3083":"hhya", - u"\u3063\u3072\u3085":"hhyu", u"\u3063\u3072\u3087":"hhyo", - u"\u3063\u3073":"bbi", u"\u3063\u3073\u3083":"bbya", - u"\u3063\u3073\u3085":"bbyu", u"\u3063\u3073\u3087":"bbyo", - u"\u3063\u3074":"ppi", u"\u3063\u3074\u3083":"ppya", - u"\u3063\u3074\u3085":"ppyu", u"\u3063\u3074\u3087":"ppyo", - u"\u3063\u3075":"ffu", u"\u3063\u3075\u3041":"ffa", - u"\u3063\u3075\u3043":"ffi", u"\u3063\u3075\u3047":"ffe", - u"\u3063\u3075\u3049":"ffo", - u"\u3063\u3076":"bbu", u"\u3063\u3077":"ppu", - u"\u3063\u3078":"hhe", u"\u3063\u3079":"bbe", - u"\u3063\u307a":"ppe", - u"\u3063\u307b":"hho", u"\u3063\u307c":"bbo", - u"\u3063\u307d":"ppo", - u"\u3063\u3084":"yya", u"\u3063\u3086":"yyu", - u"\u3063\u3088":"yyo", - u"\u3063\u3089":"rra", u"\u3063\u308a":"rri", - u"\u3063\u308a\u3083":"rrya", u"\u3063\u308a\u3085":"rryu", - u"\u3063\u308a\u3087":"rryo", - u"\u3063\u308b":"rru", u"\u3063\u308c":"rre", - u"\u3063\u308d":"rro", + "\u3063":"tsu", + "\u3063\u3046\u309b":"vvu", + "\u3063\u3046\u309b\u3041":"vva", + "\u3063\u3046\u309b\u3043":"vvi", + "\u3063\u3046\u309b\u3047":"vve", + "\u3063\u3046\u309b\u3049":"vvo", + "\u3063\u304b":"kka", "\u3063\u304c":"gga", + "\u3063\u304d":"kki", "\u3063\u304d\u3083":"kkya", + "\u3063\u304d\u3085":"kkyu", "\u3063\u304d\u3087":"kkyo", + "\u3063\u304e":"ggi", "\u3063\u304e\u3083":"ggya", + "\u3063\u304e\u3085":"ggyu", "\u3063\u304e\u3087":"ggyo", + "\u3063\u304f":"kku", "\u3063\u3050":"ggu", + "\u3063\u3051":"kke", "\u3063\u3052":"gge", + "\u3063\u3053":"kko", "\u3063\u3054":"ggo", + "\u3063\u3055":"ssa", "\u3063\u3056":"zza", + "\u3063\u3057":"sshi", "\u3063\u3057\u3083":"ssha", + "\u3063\u3057\u3085":"sshu", "\u3063\u3057\u3087":"ssho", + "\u3063\u3058":"jji", "\u3063\u3058\u3083":"jja", + "\u3063\u3058\u3085":"jju", "\u3063\u3058\u3087":"jjo", + "\u3063\u3059":"ssu", "\u3063\u305a":"zzu", + "\u3063\u305b":"sse", "\u3063\u305e":"zze", + "\u3063\u305d":"sso", "\u3063\u305c":"zzo", + "\u3063\u305f":"tta", "\u3063\u3060":"dda", + "\u3063\u3061":"tchi", "\u3063\u3061\u3083":"tcha", + "\u3063\u3061\u3085":"tchu", "\u3063\u3061\u3087":"tcho", + "\u3063\u3062":"jji", "\u3063\u3062\u3083":"jjya", + "\u3063\u3062\u3085":"jjyu", "\u3063\u3062\u3087":"jjyo", + "\u3063\u3064":"ttsu", "\u3063\u3065":"zzu", + "\u3063\u3066":"tte", "\u3063\u3067":"dde", + "\u3063\u3068":"tto", "\u3063\u3069":"ddo", + "\u3063\u306f":"hha", "\u3063\u3070":"bba", + "\u3063\u3071":"ppa", + "\u3063\u3072":"hhi", "\u3063\u3072\u3083":"hhya", + "\u3063\u3072\u3085":"hhyu", "\u3063\u3072\u3087":"hhyo", + "\u3063\u3073":"bbi", "\u3063\u3073\u3083":"bbya", + "\u3063\u3073\u3085":"bbyu", "\u3063\u3073\u3087":"bbyo", + "\u3063\u3074":"ppi", "\u3063\u3074\u3083":"ppya", + "\u3063\u3074\u3085":"ppyu", "\u3063\u3074\u3087":"ppyo", + "\u3063\u3075":"ffu", "\u3063\u3075\u3041":"ffa", + "\u3063\u3075\u3043":"ffi", "\u3063\u3075\u3047":"ffe", + "\u3063\u3075\u3049":"ffo", + "\u3063\u3076":"bbu", "\u3063\u3077":"ppu", + "\u3063\u3078":"hhe", "\u3063\u3079":"bbe", + "\u3063\u307a":"ppe", + "\u3063\u307b":"hho", "\u3063\u307c":"bbo", + "\u3063\u307d":"ppo", + "\u3063\u3084":"yya", "\u3063\u3086":"yyu", + "\u3063\u3088":"yyo", + "\u3063\u3089":"rra", "\u3063\u308a":"rri", + "\u3063\u308a\u3083":"rrya", "\u3063\u308a\u3085":"rryu", + "\u3063\u308a\u3087":"rryo", + "\u3063\u308b":"rru", "\u3063\u308c":"rre", + "\u3063\u308d":"rro", - u"\u3064":"tsu", u"\u3065":"zu", - u"\u3066":"te", u"\u3067":"de", u"\u3067\u3043":"di", - u"\u3068":"to", u"\u3069":"do", + "\u3064":"tsu", "\u3065":"zu", + "\u3066":"te", "\u3067":"de", "\u3067\u3043":"di", + "\u3068":"to", "\u3069":"do", - u"\u306a":"na", - u"\u306b":"ni", u"\u306b\u3083":"nya", - u"\u306b\u3085":"nyu", u"\u306b\u3087":"nyo", - u"\u306c":"nu", u"\u306d":"ne", u"\u306e":"no", + "\u306a":"na", + "\u306b":"ni", "\u306b\u3083":"nya", + "\u306b\u3085":"nyu", "\u306b\u3087":"nyo", + "\u306c":"nu", "\u306d":"ne", "\u306e":"no", - u"\u306f":"ha", u"\u3070":"ba", u"\u3071":"pa", - u"\u3072":"hi", u"\u3072\u3083":"hya", - u"\u3072\u3085":"hyu", u"\u3072\u3087":"hyo", - u"\u3073":"bi", u"\u3073\u3083":"bya", - u"\u3073\u3085":"byu", u"\u3073\u3087":"byo", - u"\u3074":"pi", u"\u3074\u3083":"pya", - u"\u3074\u3085":"pyu", u"\u3074\u3087":"pyo", - u"\u3075":"fu", u"\u3075\u3041":"fa", - u"\u3075\u3043":"fi", u"\u3075\u3047":"fe", - u"\u3075\u3049":"fo", - u"\u3076":"bu", u"\u3077":"pu", - u"\u3078":"he", u"\u3079":"be", u"\u307a":"pe", - u"\u307b":"ho", u"\u307c":"bo", u"\u307d":"po", + "\u306f":"ha", "\u3070":"ba", "\u3071":"pa", + "\u3072":"hi", "\u3072\u3083":"hya", + "\u3072\u3085":"hyu", "\u3072\u3087":"hyo", + "\u3073":"bi", "\u3073\u3083":"bya", + "\u3073\u3085":"byu", "\u3073\u3087":"byo", + "\u3074":"pi", "\u3074\u3083":"pya", + "\u3074\u3085":"pyu", "\u3074\u3087":"pyo", + "\u3075":"fu", "\u3075\u3041":"fa", + "\u3075\u3043":"fi", "\u3075\u3047":"fe", + "\u3075\u3049":"fo", + "\u3076":"bu", "\u3077":"pu", + "\u3078":"he", "\u3079":"be", "\u307a":"pe", + "\u307b":"ho", "\u307c":"bo", "\u307d":"po", - u"\u307e":"ma", - u"\u307f":"mi", u"\u307f\u3083":"mya", - u"\u307f\u3085":"myu", u"\u307f\u3087":"myo", - u"\u3080":"mu", u"\u3081":"me", u"\u3082":"mo", + "\u307e":"ma", + "\u307f":"mi", "\u307f\u3083":"mya", + "\u307f\u3085":"myu", "\u307f\u3087":"myo", + "\u3080":"mu", "\u3081":"me", "\u3082":"mo", - u"\u3083":"ya", u"\u3084":"ya", - u"\u3085":"yu", u"\u3086":"yu", - u"\u3087":"yo", u"\u3088":"yo", + "\u3083":"ya", "\u3084":"ya", + "\u3085":"yu", "\u3086":"yu", + "\u3087":"yo", "\u3088":"yo", - u"\u3089":"ra", - u"\u308a":"ri", u"\u308a\u3083":"rya", - u"\u308a\u3085":"ryu", u"\u308a\u3087":"ryo", - u"\u308b":"ru", u"\u308c":"re", u"\u308d":"ro", + "\u3089":"ra", + "\u308a":"ri", "\u308a\u3083":"rya", + "\u308a\u3085":"ryu", "\u308a\u3087":"ryo", + "\u308b":"ru", "\u308c":"re", "\u308d":"ro", - u"\u308e":"wa", u"\u308f":"wa", - u"\u3090":"i", u"\u3091":"e", - u"\u3092":"wo", u"\u3093":"n", + "\u308e":"wa", "\u308f":"wa", + "\u3090":"i", "\u3091":"e", + "\u3092":"wo", "\u3093":"n", - u"\u3093\u3042":"n'a", u"\u3093\u3044":"n'i", - u"\u3093\u3046":"n'u", u"\u3093\u3048":"n'e", - u"\u3093\u304a":"n'o", + "\u3093\u3042":"n'a", "\u3093\u3044":"n'i", + "\u3093\u3046":"n'u", "\u3093\u3048":"n'e", + "\u3093\u304a":"n'o", } # this class is Borg diff --git a/src/calibre/ebooks/unihandecode/pykakasi/j2h.py b/src/calibre/ebooks/unihandecode/pykakasi/j2h.py index 79cd2c29ac..3a9d836df2 100644 --- a/src/calibre/ebooks/unihandecode/pykakasi/j2h.py +++ b/src/calibre/ebooks/unihandecode/pykakasi/j2h.py @@ -20,6 +20,7 @@ # * GNU General Public License for more details. # * # */ +from __future__ import absolute_import, division, print_function, unicode_literals import re @@ -48,7 +49,7 @@ class J2H (object): return (0x3400 <= ord(c) and ord(c) < 0xfa2e) def isCletter(self, l, c): - if (ord(u"ぁ") <= ord(c) and ord(c) <= 0x309f) and (l in self.cl_table[ord(c) - ord(u"ぁ")-1]): + if (ord("ぁ") <= ord(c) and ord(c) <= 0x309f) and (l in self.cl_table[ord(c) - ord("ぁ")-1]): return True return False diff --git a/src/calibre/ebooks/unihandecode/pykakasi/jisyo.py b/src/calibre/ebooks/unihandecode/pykakasi/jisyo.py index 6ff55ad90d..2c1c95f32a 100644 --- a/src/calibre/ebooks/unihandecode/pykakasi/jisyo.py +++ b/src/calibre/ebooks/unihandecode/pykakasi/jisyo.py @@ -2,6 +2,8 @@ # jisyo.py # # Copyright 2011 Hiroshi Miura +from __future__ import absolute_import, division, print_function, unicode_literals + from zlib import decompress from polyglot.builtins import unicode_type diff --git a/src/calibre/ebooks/unihandecode/pykakasi/k2a.py b/src/calibre/ebooks/unihandecode/pykakasi/k2a.py index 7650199128..fb5b5da1ac 100644 --- a/src/calibre/ebooks/unihandecode/pykakasi/k2a.py +++ b/src/calibre/ebooks/unihandecode/pykakasi/k2a.py @@ -20,6 +20,7 @@ # * GNU General Public License for more details. # * # */ +from __future__ import absolute_import, division, print_function, unicode_literals from calibre.ebooks.unihandecode.pykakasi.jisyo import jisyo from polyglot.builtins import range diff --git a/src/calibre/ebooks/unihandecode/pykakasi/kakasi.py b/src/calibre/ebooks/unihandecode/pykakasi/kakasi.py index 39b84b545a..47a8c026f8 100644 --- a/src/calibre/ebooks/unihandecode/pykakasi/kakasi.py +++ b/src/calibre/ebooks/unihandecode/pykakasi/kakasi.py @@ -20,6 +20,7 @@ # * GNU General Public License for more details. # * # */ +from __future__ import absolute_import, division, print_function, unicode_literals from calibre.ebooks.unihandecode.pykakasi.j2h import J2H from calibre.ebooks.unihandecode.pykakasi.h2a import H2a @@ -94,4 +95,3 @@ class kakasi(object): i += 1 return otext - diff --git a/src/calibre/ebooks/unihandecode/unicodepoints.py b/src/calibre/ebooks/unihandecode/unicodepoints.py index d9130123fb..13eeed2e03 100644 --- a/src/calibre/ebooks/unihandecode/unicodepoints.py +++ b/src/calibre/ebooks/unihandecode/unicodepoints.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL 3' __copyright__ = '2009, John Schember ' diff --git a/src/calibre/ebooks/unihandecode/unidecoder.py b/src/calibre/ebooks/unihandecode/unidecoder.py index 748fcb64f1..e66a11da2f 100644 --- a/src/calibre/ebooks/unihandecode/unidecoder.py +++ b/src/calibre/ebooks/unihandecode/unidecoder.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL 3' __copyright__ = '2010, Hiroshi Miura ' diff --git a/src/calibre/ebooks/unihandecode/vncodepoints.py b/src/calibre/ebooks/unihandecode/vncodepoints.py index 7e10fde1c8..2a74bb157b 100644 --- a/src/calibre/ebooks/unihandecode/vncodepoints.py +++ b/src/calibre/ebooks/unihandecode/vncodepoints.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL 3' __copyright__ = '2010 Hiroshi Miura ' @@ -9,7 +10,7 @@ Unicode code point dictionary. Based on Unicode.org Unihan database. ''' -CODEPOINTS = { +CODEPOINTS = { 'x34':[ 'Qiu ','Tian ','','','Kua ','Wu ','Yin ','','','','','','Si ','','','', '','','','','','','Ye ','','','','','','Chou ','','','', diff --git a/src/calibre/ebooks/unihandecode/vndecoder.py b/src/calibre/ebooks/unihandecode/vndecoder.py index 76d926d7b7..60ee7fbdf9 100644 --- a/src/calibre/ebooks/unihandecode/vndecoder.py +++ b/src/calibre/ebooks/unihandecode/vndecoder.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL 3' __copyright__ = '2010, Hiroshi Miura ' @@ -21,4 +22,3 @@ class Vndecoder(Unidecoder): def __init__(self): self.codepoints = CODEPOINTS self.codepoints.update(HANCODES) - diff --git a/src/calibre/ebooks/unihandecode/zhcodepoints.py b/src/calibre/ebooks/unihandecode/zhcodepoints.py index 1715ecb46e..57e4de3326 100644 --- a/src/calibre/ebooks/unihandecode/zhcodepoints.py +++ b/src/calibre/ebooks/unihandecode/zhcodepoints.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +from __future__ import absolute_import, division, print_function, unicode_literals __license__ = 'GPL 3' __copyright__ = '2010 Hiroshi Miura ' @@ -9,7 +10,7 @@ Unicode code point dictionary. Based on Unicode.org Unihan database. ''' -CODEPOINTS = { +CODEPOINTS = { 'x34':[ 'Qiu ','Tian ','','','Kua ','Wu ','Yin ','','','','','','Si ','','','', '','','','','','','Ye ','','','','','','Chou ','','','', diff --git a/src/calibre/gui2/book_details.py b/src/calibre/gui2/book_details.py index 031cbac7b4..357ea55c65 100644 --- a/src/calibre/gui2/book_details.py +++ b/src/calibre/gui2/book_details.py @@ -1,6 +1,7 @@ #!/usr/bin/env python2 # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # License: GPLv3 Copyright: 2010, Kovid Goyal +from __future__ import absolute_import, division, print_function, unicode_literals import os import re @@ -59,7 +60,7 @@ def css(): val = P('templates/book_details.css', data=True).decode('utf-8') col = QApplication.instance().palette().color(QPalette.Link).name() val = val.replace('LINK_COLOR', col) - _css = re.sub(unicode_type(r'/\*.*?\*/'), u'', val, flags=re.DOTALL) + _css = re.sub(unicode_type(r'/\*.*?\*/'), '', val, flags=re.DOTALL) return _css @@ -127,7 +128,7 @@ def render_html(mi, css, vertical, widget, all_fields=False, render_data_func=No c = color_to_string(QApplication.palette().color(QPalette.Normal, QPalette.WindowText)) - templ = u'''\ + templ = '''\