diff --git a/recipes/al_monitor.recipe b/recipes/al_monitor.recipe index 5842f5c73f..0067f9ed2f 100644 --- a/recipes/al_monitor.recipe +++ b/recipes/al_monitor.recipe @@ -162,7 +162,7 @@ class AlMonitor(BasicNewsRecipe): def scrape_article_date(self, soup): for span in soup.findAll('span'): txt = self.text(span) - rgx = re.compile('Posted ([a-zA-Z]+ \d\d?, \d\d\d\d).*') + rgx = re.compile(unicode(r'Posted ([a-zA-Z]+ \d\d?, \d\d\d\d).*')) hit = rgx.match(txt) if hit: return self.date_from_string(txt) diff --git a/recipes/appledaily_tw.recipe b/recipes/appledaily_tw.recipe index 14e5be20a0..700ee4c7f1 100644 --- a/recipes/appledaily_tw.recipe +++ b/recipes/appledaily_tw.recipe @@ -106,5 +106,5 @@ class AppledailyTW(BasicNewsRecipe): def preprocess_raw_html(self, raw_html, url): raw_html = re.sub(unicode(r'', re.DOTALL), lambda match: ''), # fix malformed HTML with 2 body tags... - (re.compile(u'(?:)?\(kliknij\,\ aby powiększyć\)(?:)?', re.IGNORECASE), lambda m: ''), + (re.compile(u'(?:)?\\(kliknij\\,\\ aby powiększyć\\)(?:)?', re.IGNORECASE), lambda m: ''), (re.compile(unicode(r'(
\s*?
\s*?)+'), re.IGNORECASE), lambda m: '
') ] remove_tags = [dict(attrs={'class':['infoParent', 'likeBar', diff --git a/recipes/huffingtonpost.recipe b/recipes/huffingtonpost.recipe index 82fcd3d2ba..d5e023c6db 100644 --- a/recipes/huffingtonpost.recipe +++ b/recipes/huffingtonpost.recipe @@ -62,7 +62,7 @@ class HuffingtonPostRecipe(BasicNewsRecipe): remove_tags = [] remove_tags.append(dict(name='a', attrs={'href': re.compile( - 'http://feedads\.g\.doubleclick.net.*')})) + 'http://feedads\\.g\\.doubleclick.net.*')})) remove_tags.append(dict(name='div', attrs={'class': 'feedflare'})) remove_tags.append(dict(name='a', attrs={'class': 'home_pixie'})) remove_tags.append(dict(name='div', attrs={'id': [ diff --git a/recipes/lenta_ru.recipe b/recipes/lenta_ru.recipe index 7a1a28652c..1e633b2c17 100644 --- a/recipes/lenta_ru.recipe +++ b/recipes/lenta_ru.recipe @@ -144,7 +144,7 @@ class LentaRURecipe(BasicNewsRecipe): # Place article date after header dates = soup.findAll(text=re.compile( - '\d{2}\.\d{2}\.\d{4}, \d{2}:\d{2}:\d{2}')) + r'\d{2}\.\d{2}\.\d{4}, \d{2}:\d{2}:\d{2}')) if dates: for date in dates: for string in date: diff --git a/recipes/lwn_weekly.recipe b/recipes/lwn_weekly.recipe index d2a9f11a9b..39da52ef98 100644 --- a/recipes/lwn_weekly.recipe +++ b/recipes/lwn_weekly.recipe @@ -121,7 +121,7 @@ class WeeklyLWN(BasicNewsRecipe): if article_anchor: article_url = article_anchor.get('href') if not article_url: - print('article_url is None for article_anchor "%s": "%s"' \ + print('article_url is None for article_anchor "%s": "%s"' % (str(article_anchor), article_title), file=sys.stderr) continue diff --git a/recipes/metro_news_nl.recipe b/recipes/metro_news_nl.recipe index 8f2127130f..205f71c596 100644 --- a/recipes/metro_news_nl.recipe +++ b/recipes/metro_news_nl.recipe @@ -84,11 +84,11 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe): remove_tags = [ dict(name=['iframe', 'script', 'noscript', 'style']), dict(name='div', attrs={'class': ['fact-related-box', 'aside clearfix', 'aside clearfix middle-col-line', 'comments', 'share-tools', 'article-right-column', 'column-4-5', 'column-1-5', 'ad-msg', 'col-179 ', 'col-373 ', 'clear', 'ad', 'navigation', re.compile('share-tools(-top)?'), 'tools', 'metroCommentFormWrap', 'article-tools-below-title', 'related-links', 'padding-top-15', re.compile('^promo.*?$'), 'teaser-component', re.compile('fb(-comments|_iframe_widget)'), 'promos', 'header-links', 'promo-2']}), # noqa - dict(id=['super-carousel', 'article-2', 'googleads', 'column-1-5-bottom', 'column-4-5', re.compile('^ad(\d+|adcomp.*?)?$'), 'adadcomp-4', 'margin-5', 'sidebar', re.compile('^article-\d'), 'comments', 'gallery-1', 'sharez_container', 'ts-container', 'topshares', 'ts-title']), # noqa + dict(id=['super-carousel', 'article-2', 'googleads', 'column-1-5-bottom', 'column-4-5', re.compile('^ad(\\d+|adcomp.*?)?$'), 'adadcomp-4', 'margin-5', 'sidebar', re.compile('^article-\\d'), 'comments', 'gallery-1', 'sharez_container', 'ts-container', 'topshares', 'ts-title']), # noqa dict(name='a', attrs={'name': 'comments'}), dict(name='img', attrs={'class': 'top-line', 'title': 'volledig scherm'}), - dict(attrs={'style': re.compile('^(.*(display\s?:\s?none|img-mask|white)\s?;?.*)$'), 'title': 'volledig scherm'})] + dict(attrs={'style': re.compile('^(.*(display\\s?:\\s?none|img-mask|white)\\s?;?.*)$'), 'title': 'volledig scherm'})] '''removed by before/after: id: @@ -223,7 +223,7 @@ class MerryProcess(BeautifulSoup): return self.myKiller.safeRemovePart(souparray, True) def removeEmptyTags(self, soup, run=0): - emptymatches = re.compile('^[ \s\n\r\t ]*$') + emptymatches = re.compile('^[ \\s\n\r\t ]*$') emptytags = soup.findAll(lambda tag: tag.find(True) is None and ( tag.string is None or tag.string.strip() == "" or tag.string.strip() == emptymatches) and not tag.isSelfClosing) if emptytags and not (emptytags is None or emptytags == []): diff --git a/recipes/observatorul_cultural.recipe b/recipes/observatorul_cultural.recipe index 34b7ebe8f3..6f786b199e 100644 --- a/recipes/observatorul_cultural.recipe +++ b/recipes/observatorul_cultural.recipe @@ -29,7 +29,7 @@ class ObservatorulCultural(BasicNewsRecipe): soup = self.index_to_soup( 'http://www.observatorcultural.ro/Arhiva*-archive.html') issueTag = soup.find('a', href=re.compile( - "observatorcultural.ro\/Numarul")) + "observatorcultural.ro\\/Numarul")) issueURL = issueTag['href'] print(issueURL) issueSoup = self.index_to_soup(issueURL) diff --git a/src/calibre/customize/zipplugin.py b/src/calibre/customize/zipplugin.py index 6028e5cb33..3c82c72640 100644 --- a/src/calibre/customize/zipplugin.py +++ b/src/calibre/customize/zipplugin.py @@ -83,6 +83,7 @@ def get_icons(zfp, name_or_list_of_names): ians = ians.pop(names[0]) return ians + _translations_cache = {} @@ -316,4 +317,3 @@ if __name__ == '__main__': zf.write(os.path.join(x, y)) add_plugin(f.name) print('Added plugin from', sys.argv[-1]) - diff --git a/src/calibre/db/tests/profiling.py b/src/calibre/db/tests/profiling.py index c8d77301a1..8e40524b48 100644 --- a/src/calibre/db/tests/profiling.py +++ b/src/calibre/db/tests/profiling.py @@ -40,5 +40,6 @@ def main(): show_stats(stats) print('Stats saved to', stats) + if __name__ == '__main__': main() diff --git a/src/calibre/devices/cli.py b/src/calibre/devices/cli.py index d9182d0c94..8dd8ca282b 100755 --- a/src/calibre/devices/cli.py +++ b/src/calibre/devices/cli.py @@ -221,7 +221,7 @@ def main(): try: d.startup() except: - print ('Startup failed for device plugin: %s'%d) + print('Startup failed for device plugin: %s'%d) if d.MANAGES_DEVICE_PRESENCE: cd = d.detect_managed_devices(scanner.devices) if cd is not None: @@ -395,5 +395,6 @@ def main(): return 0 + if __name__ == '__main__': main() diff --git a/src/calibre/devices/mtp/windows/remote.py b/src/calibre/devices/mtp/windows/remote.py index 8974388164..fc0b78879c 100644 --- a/src/calibre/devices/mtp/windows/remote.py +++ b/src/calibre/devices/mtp/windows/remote.py @@ -93,8 +93,8 @@ def main(): finally: dev.shutdown() - print ('Device connection shutdown') + print('Device connection shutdown') + if __name__ == '__main__': main() - diff --git a/src/calibre/devices/udisks.py b/src/calibre/devices/udisks.py index 70d7bbbfac..70e924eac5 100644 --- a/src/calibre/devices/udisks.py +++ b/src/calibre/devices/udisks.py @@ -211,7 +211,6 @@ def test_udisks(ver=None): print('Ejecting:') u.eject(dev) + if __name__ == '__main__': test_udisks() - - diff --git a/src/calibre/devices/winusb.py b/src/calibre/devices/winusb.py index ce8b239555..5b1a005328 100644 --- a/src/calibre/devices/winusb.py +++ b/src/calibre/devices/winusb.py @@ -53,6 +53,7 @@ class GUID(Structure): ''.join(["%02x" % d for d in self.data4[2:]]), ) + CONFIGRET = DWORD DEVINST = DWORD LPDWORD = POINTER(DWORD) @@ -70,6 +71,8 @@ def CTL_CODE(DeviceType, Function, Method, Access): def USB_CTL(id): # CTL_CODE(FILE_DEVICE_USB, (id), METHOD_BUFFERED, FILE_ANY_ACCESS) return CTL_CODE(0x22, id, 0, 0) + + IOCTL_USB_GET_ROOT_HUB_NAME = USB_CTL(258) IOCTL_USB_GET_NODE_INFORMATION = USB_CTL(258) IOCTL_USB_GET_NODE_CONNECTION_INFORMATION = USB_CTL(259) @@ -108,6 +111,7 @@ class SP_DEVINFO_DATA(Structure): def __str__(self): return "ClassGuid:%s DevInst:%s" % (self.ClassGuid, self.DevInst) + PSP_DEVINFO_DATA = POINTER(SP_DEVINFO_DATA) @@ -122,6 +126,7 @@ class SP_DEVICE_INTERFACE_DATA(Structure): def __str__(self): return "InterfaceClassGuid:%s Flags:%s" % (self.InterfaceClassGuid, self.Flags) + ANYSIZE_ARRAY = 1 @@ -131,6 +136,7 @@ class SP_DEVICE_INTERFACE_DETAIL_DATA(Structure): ("DevicePath", c_wchar*ANYSIZE_ARRAY) ] + UCHAR = c_ubyte @@ -216,6 +222,7 @@ class USB_DESCRIPTOR_REQUEST(Structure): ('Data', USB_STRING_DESCRIPTOR), ) + PUSB_DESCRIPTOR_REQUEST = POINTER(USB_DESCRIPTOR_REQUEST) PSP_DEVICE_INTERFACE_DETAIL_DATA = POINTER(SP_DEVICE_INTERFACE_DETAIL_DATA) PSP_DEVICE_INTERFACE_DATA = POINTER(SP_DEVICE_INTERFACE_DATA) @@ -390,6 +397,7 @@ def config_err_check(result, func, args): raise WindowsError(result, 'The cfgmgr32 function failed with err: %s' % CR_CODE_NAMES.get(result, result)) return args + GetLogicalDrives = cwrap('GetLogicalDrives', DWORD, errcheck=bool_err_check, lib=kernel32) GetDriveType = cwrap('GetDriveTypeW', UINT, LPCWSTR, lib=kernel32) GetVolumeNameForVolumeMountPoint = cwrap('GetVolumeNameForVolumeMountPointW', BOOL, LPCWSTR, LPWSTR, DWORD, errcheck=bool_err_check, lib=kernel32) @@ -675,6 +683,7 @@ def get_volume_pathnames(volume_id, buf=None): # def scan_usb_devices(): {{{ + _USBDevice = namedtuple('USBDevice', 'vendor_id product_id bcd devid devinst') @@ -1017,6 +1026,7 @@ def drives_for(vendor_id, product_id=None): pprint(get_drive_letters_for_device(usbdev, debug=True)) print('USB info:', get_usb_info(usbdev, debug=True)) + if __name__ == '__main__': develop() # }}} diff --git a/src/calibre/ebooks/conversion/utils.py b/src/calibre/ebooks/conversion/utils.py index 3e74f87e7e..886c9a97be 100644 --- a/src/calibre/ebooks/conversion/utils.py +++ b/src/calibre/ebooks/conversion/utils.py @@ -32,11 +32,11 @@ class HeuristicProcessor(object): self.multi_blank = re.compile(r'(\s*]*>\s*

(\s*]*>\s*\s*)*){2,}(?!\s*]*>\s*

(\s*]*>\s*\s*)*){2,}', re.IGNORECASE) self.line_open = "<(?Pp|div)[^>]*>\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*" # noqa - self.line_close = "()?\s*()?\s*()?\s*" + self.line_close = "()?\\s*()?\\s*()?\\s*" self.single_blank = re.compile(r'(\s*<(p|div)[^>]*>\s*)', re.IGNORECASE) self.scene_break_open = '

' - self.common_in_text_endings = u'[\"\'—’”,\.!\?\…\)„\w]' - self.common_in_text_beginnings = u'[\w\'\"“‘‛]' + self.common_in_text_endings = u'[\"\'—’”,\\.!\\?\\…\\)„\\w]' + self.common_in_text_beginnings = u'[\\w\'\"“‘‛]' def is_pdftohtml(self, src): return '' in src[:1000] @@ -54,10 +54,10 @@ class HeuristicProcessor(object): " chapters. - " + unicode(chap)) return '

'+chap+'

\n' else: - delete_whitespace = re.compile('^\s*(?P.*?)\s*$') + delete_whitespace = re.compile('^\\s*(?P.*?)\\s*$') delete_quotes = re.compile('\'\"') - txt_chap = delete_quotes.sub('', delete_whitespace.sub('\g', html2text(chap))) - txt_title = delete_quotes.sub('', delete_whitespace.sub('\g', html2text(title))) + txt_chap = delete_quotes.sub('', delete_whitespace.sub('\\g', html2text(chap))) + txt_title = delete_quotes.sub('', delete_whitespace.sub('\\g', html2text(title))) self.html_preprocess_sections = self.html_preprocess_sections + 1 self.log.debug("marked " + unicode(self.html_preprocess_sections) + " chapters & titles. - " + unicode(chap) + ", " + unicode(title)) @@ -216,24 +216,24 @@ class HeuristicProcessor(object): title_line_open = "<(?Pp|div)[^>]*>\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*" # noqa chapter_header_open = r"(?P" title_header_open = r"(?P" - chapter_header_close = ")\s*" + chapter_header_close = ")\\s*" title_header_close = ")" chapter_line_close = self.line_close - title_line_close = "(</(?P=inner6)>)?\s*(</(?P=inner5)>)?\s*(</(?P=inner4)>)?\s*</(?P=outer2)>" + title_line_close = "(</(?P=inner6)>)?\\s*(</(?P=inner5)>)?\\s*(</(?P=inner4)>)?\\s*</(?P=outer2)>" is_pdftohtml = self.is_pdftohtml(html) if is_pdftohtml: - title_line_open = "<(?P<outer2>p)[^>]*>\s*" - title_line_close = "\s*</(?P=outer2)>" + title_line_open = "<(?P<outer2>p)[^>]*>\\s*" + title_line_close = "\\s*</(?P=outer2)>" if blanks_between_paragraphs: - blank_lines = "(\s*<p[^>]*>\s*</p>){0,2}\s*" + blank_lines = "(\\s*<p[^>]*>\\s*</p>){0,2}\\s*" else: blank_lines = "" opt_title_open = "(" opt_title_close = ")?" - n_lookahead_open = "(?!\s*" - n_lookahead_close = ")\s*" + n_lookahead_open = "(?!\\s*" + n_lookahead_close = ")\\s*" default_title = r"(<[ibu][^>]*>)?\s{0,3}(?!Chapter)([\w\:\'’\"-]+\s{0,3}){1,5}?(</[ibu][^>]*>)?(?=<)" simple_title = r"(<[ibu][^>]*>)?\s{0,3}(?!(Chapter|\s+<)).{0,65}?(</[ibu][^>]*>)?(?=<)" @@ -358,12 +358,12 @@ class HeuristicProcessor(object): # define the pieces of the regex # (?<!\&\w{4});) is a semicolon not part of an entity - lookahead = "(?<=.{"+unicode(length)+u"}([a-zა-ჰäëïöüàèìòùáćéíĺóŕńśúýâêîôûçąężıãõñæøþðßěľščťžňďřů,:)\IA\u00DF]|(?<!\&\w{4});))" + lookahead = "(?<=.{"+unicode(length)+u"}([a-zა-ჰäëïöüàèìòùáćéíĺóŕńśúýâêîôûçąężıãõñæøþðßěľščťžňďřů,:)\\IA\u00DF]|(?<!\\&\\w{4});))" em_en_lookahead = "(?<=.{"+unicode(length)+u"}[\u2013\u2014])" soft_hyphen = u"\xad" - line_ending = "\s*(?P<style_close></(span|[iub])>)?\s*(</(p|div)>)?" - blanklines = "\s*(?P<up2threeblanks><(p|span|div)[^>]*>\s*(<(p|span|div)[^>]*>\s*</(span|p|div)>\s*)</(span|p|div)>\s*){0,3}\s*" - line_opening = "<(p|div)[^>]*>\s*(?P<style_open><(span|[iub])[^>]*>)?\s*" + line_ending = "\\s*(?P<style_close></(span|[iub])>)?\\s*(</(p|div)>)?" + blanklines = "\\s*(?P<up2threeblanks><(p|span|div)[^>]*>\\s*(<(p|span|div)[^>]*>\\s*</(span|p|div)>\\s*)</(span|p|div)>\\s*){0,3}\\s*" + line_opening = "<(p|div)[^>]*>\\s*(?P<style_open><(span|[iub])[^>]*>)?\\s*" txt_line_wrap = u"((\u0020|\u0009)*\n){1,4}" if format == 'txt': @@ -414,8 +414,8 @@ class HeuristicProcessor(object): return html def arrange_htm_line_endings(self, html): - html = re.sub(r"\s*</(?P<tag>p|div)>", "</"+"\g<tag>"+">\n", html) - html = re.sub(r"\s*<(?P<tag>p|div)(?P<style>[^>]*)>\s*", "\n<"+"\g<tag>"+"\g<style>"+">", html) + html = re.sub(r"\s*</(?P<tag>p|div)>", "</"+"\\g<tag>"+">\n", html) + html = re.sub(r"\s*<(?P<tag>p|div)(?P<style>[^>]*)>\s*", "\n<"+"\\g<tag>"+"\\g<style>"+">", html) return html def fix_nbsp_indents(self, html): @@ -432,7 +432,7 @@ class HeuristicProcessor(object): # Get rid of empty <o:p> tags to simplify other processing html = re.sub(unicode(r'\s*<o:p>\s*</o:p>'), ' ', html) # Delete microsoft 'smart' tags - html = re.sub('(?i)</?st1:\w+>', '', html) + html = re.sub('(?i)</?st1:\\w+>', '', html) # Re-open self closing paragraph tags html = re.sub('<p[^>/]*/>', '<p> </p>', html) # Get rid of empty span, bold, font, em, & italics tags @@ -443,7 +443,7 @@ class HeuristicProcessor(object): html = re.sub( r"\s*{open}\s*({open}\s*{close}\s*){{0,2}}\s*{close}".format(open=open_fmt_pat, close=close_fmt_pat) , " ", html) # delete surrounding divs from empty paragraphs - html = re.sub('<div[^>]*>\s*<p[^>]*>\s*</p>\s*</div>', '<p> </p>', html) + html = re.sub('<div[^>]*>\\s*<p[^>]*>\\s*</p>\\s*</div>', '<p> </p>', html) # Empty heading tags html = re.sub(r'(?i)<h\d+>\s*</h\d+>', '', html) self.deleted_nbsps = True @@ -527,7 +527,7 @@ class HeuristicProcessor(object): elif content.find('scenebreak') != -1: return content else: - content = re.sub('(?i)<h(?P<hnum>\d+)[^>]*>', '\n\n<h'+'\g<hnum>'+' style="'+top_margin+bottom_margin+'">', content) + content = re.sub('(?i)<h(?P<hnum>\\d+)[^>]*>', '\n\n<h'+'\\g<hnum>'+' style="'+top_margin+bottom_margin+'">', content) return content html = blanks_around_headings.sub(merge_header_whitespace, html) @@ -540,15 +540,15 @@ class HeuristicProcessor(object): html = blanks_n_nopunct.sub(markup_whitespaces, html) if self.html_preprocess_sections > self.min_chapters: - html = re.sub('(?si)^.*?(?=<h\d)', markup_whitespaces, html) + html = re.sub('(?si)^.*?(?=<h\\d)', markup_whitespaces, html) return html def detect_soft_breaks(self, html): - line = '(?P<initline>'+self.line_open+'\s*(?P<init_content>.*?)'+self.line_close+')' + line = '(?P<initline>'+self.line_open+'\\s*(?P<init_content>.*?)'+self.line_close+')' line_two = '(?P<line_two>'+re.sub('(ou|in|cha)', 'linetwo_', self.line_open)+ \ - '\s*(?P<line_two_content>.*?)'+re.sub('(ou|in|cha)', 'linetwo_', self.line_close)+')' - div_break_candidate_pattern = line+'\s*<div[^>]*>\s*</div>\s*'+line_two + '\\s*(?P<line_two_content>.*?)'+re.sub('(ou|in|cha)', 'linetwo_', self.line_close)+')' + div_break_candidate_pattern = line+'\\s*<div[^>]*>\\s*</div>\\s*'+line_two div_break_candidate = re.compile(r'%s' % div_break_candidate_pattern, re.IGNORECASE|re.UNICODE) def convert_div_softbreaks(match): @@ -571,9 +571,9 @@ class HeuristicProcessor(object): def detect_scene_breaks(self, html): scene_break_regex = self.line_open+'(?!('+self.common_in_text_beginnings+'|.*?'+self.common_in_text_endings+ \ - '<))(?P<break>((?P<break_char>((?!\s)\W))\s*(?P=break_char)?)+)\s*'+self.line_close + '<))(?P<break>((?P<break_char>((?!\\s)\\W))\\s*(?P=break_char)?)+)\\s*'+self.line_close scene_breaks = re.compile(r'%s' % scene_break_regex, re.IGNORECASE|re.UNICODE) - html = scene_breaks.sub(self.scene_break_open+'\g<break>'+'</p>', html) + html = scene_breaks.sub(self.scene_break_open+'\\g<break>'+'</p>', html) return html def markup_user_break(self, replacement_break): @@ -589,13 +589,13 @@ class HeuristicProcessor(object): if re.match('^<hr', replacement_break): if replacement_break.find('width') != -1: try: - width = int(re.sub('.*?width(:|=)(?P<wnum>\d+).*', '\g<wnum>', replacement_break)) + width = int(re.sub('.*?width(:|=)(?P<wnum>\\d+).*', '\\g<wnum>', replacement_break)) except: scene_break = hr_open+'<hr style="height: 3px; background:#505050" /></div>' self.log.warn('Invalid replacement scene break' ' expression, using default') else: - replacement_break = re.sub('(?i)(width=\d+\%?|width:\s*\d+(\%|px|pt|em)?;?)', '', replacement_break) + replacement_break = re.sub('(?i)(width=\\d+\\%?|width:\\s*\\d+(\\%|px|pt|em)?;?)', '', replacement_break) divpercent = (100 - width) / 2 hr_open = re.sub('45', unicode(divpercent), hr_open) scene_break = hr_open+replacement_break+'</div>' @@ -606,16 +606,16 @@ class HeuristicProcessor(object): else: from calibre.utils.html2text import html2text replacement_break = html2text(replacement_break) - replacement_break = re.sub('\s', ' ', replacement_break) + replacement_break = re.sub('\\s', ' ', replacement_break) scene_break = self.scene_break_open+replacement_break+'</p>' else: - replacement_break = re.sub('\s', ' ', replacement_break) + replacement_break = re.sub('\\s', ' ', replacement_break) scene_break = self.scene_break_open+replacement_break+'</p>' return scene_break def check_paragraph(self, content): - content = re.sub('\s*</?span[^>]*>\s*', '', content) + content = re.sub('\\s*</?span[^>]*>\\s*', '', content) if re.match('.*[\"\'.!?:]$', content): # print "detected this as a paragraph" return True @@ -623,7 +623,7 @@ class HeuristicProcessor(object): return False def abbyy_processor(self, html): - abbyy_line = re.compile('((?P<linestart><p\sstyle="(?P<styles>[^\"]*?);?">)(?P<content>.*?)(?P<lineend></p>)|(?P<image><img[^>]*>))', re.IGNORECASE) + abbyy_line = re.compile('((?P<linestart><p\\sstyle="(?P<styles>[^\"]*?);?">)(?P<content>.*?)(?P<lineend></p>)|(?P<image><img[^>]*>))', re.IGNORECASE) empty_paragraph = '\n<p> </p>\n' self.in_blockquote = False self.previous_was_paragraph = False @@ -669,7 +669,7 @@ class HeuristicProcessor(object): if style == 'text-align' and setting != 'left': text_align = style+':'+setting+';' if style == 'text-indent': - setting = int(re.sub('\s*pt\s*', '', setting)) + setting = int(re.sub('\\s*pt\\s*', '', setting)) if 9 < setting < 14: text_indent = indented_text else: @@ -757,8 +757,8 @@ class HeuristicProcessor(object): is_pdftohtml = self.is_pdftohtml(html) if is_pdftohtml: - self.line_open = "<(?P<outer>p)[^>]*>(\s*<[ibu][^>]*>)?\s*" - self.line_close = "\s*(</[ibu][^>]*>\s*)?</(?P=outer)>" + self.line_open = "<(?P<outer>p)[^>]*>(\\s*<[ibu][^>]*>)?\\s*" + self.line_close = "\\s*(</[ibu][^>]*>\\s*)?</(?P=outer)>" # ADE doesn't render <br />, change to empty paragraphs # html = re.sub('<br[^>]*>', u'<p>\u00a0</p>', html) @@ -831,7 +831,7 @@ class HeuristicProcessor(object): # headings and titles, images, etc doubleheading = re.compile( r'(?P<firsthead><h(1|2)[^>]*>.+?</h(1|2)>\s*(<(?!h\d)[^>]*>\s*)*)<h(1|2)(?P<secondhead>[^>]*>.+?)</h(1|2)>', re.IGNORECASE) - html = doubleheading.sub('\g<firsthead>'+'\n<h3'+'\g<secondhead>'+'</h3>', html) + html = doubleheading.sub('\\g<firsthead>'+'\n<h3'+'\\g<secondhead>'+'</h3>', html) # If scene break formatting is enabled, find all blank paragraphs that definitely aren't scenebreaks, # style it with the 'whitespace' class. All remaining blank lines are styled as softbreaks. @@ -839,7 +839,7 @@ class HeuristicProcessor(object): # If non-blank scene breaks exist they are center aligned and styled with appropriate margins. if getattr(self.extra_opts, 'format_scene_breaks', False): self.log.debug('Formatting scene breaks') - html = re.sub('(?i)<div[^>]*>\s*<br(\s?/)?>\s*</div>', '<p></p>', html) + html = re.sub('(?i)<div[^>]*>\\s*<br(\\s?/)?>\\s*</div>', '<p></p>', html) html = self.detect_scene_breaks(html) html = self.detect_whitespace(html) html = self.detect_soft_breaks(html) @@ -856,9 +856,9 @@ class HeuristicProcessor(object): replacement_break = self.markup_user_break(replacement_break) if scene_break_count >= 1: html = detected_scene_break.sub(replacement_break, html) - html = re.sub('<p\s+class="softbreak"[^>]*>\s*</p>', replacement_break, html) + html = re.sub('<p\\s+class="softbreak"[^>]*>\\s*</p>', replacement_break, html) else: - html = re.sub('<p\s+class="softbreak"[^>]*>\s*</p>', replacement_break, html) + html = re.sub('<p\\s+class="softbreak"[^>]*>\\s*</p>', replacement_break, html) if self.deleted_nbsps: # put back non-breaking spaces in empty paragraphs so they render correctly diff --git a/src/calibre/ebooks/docx/dump.py b/src/calibre/ebooks/docx/dump.py index b2b112c389..33e27e16e1 100644 --- a/src/calibre/ebooks/docx/dump.py +++ b/src/calibre/ebooks/docx/dump.py @@ -41,6 +41,6 @@ def dump(path): print(path, 'dumped to', dest) + if __name__ == '__main__': dump(sys.argv[-1]) - diff --git a/src/calibre/ebooks/epub/cfi/parse.py b/src/calibre/ebooks/epub/cfi/parse.py index 1b0b991976..74c6a98599 100644 --- a/src/calibre/ebooks/epub/cfi/parse.py +++ b/src/calibre/ebooks/epub/cfi/parse.py @@ -165,6 +165,7 @@ class Parser(object): ans['text_assertion'] = ta return raw[1:] + _parser = None @@ -203,5 +204,3 @@ def cfi_sort_key(cfi, only_path=True): step = steps[-1] if steps else {} offsets = (step.get('temporal_offset', 0), tuple(reversed(step.get('spatial_offset', (0, 0)))), step.get('text_offset', 0), ) return (step_nums, offsets) - - diff --git a/src/calibre/ebooks/epub/cfi/tests.py b/src/calibre/ebooks/epub/cfi/tests.py index 99d033cf44..88baac1f2e 100644 --- a/src/calibre/ebooks/epub/cfi/tests.py +++ b/src/calibre/ebooks/epub/cfi/tests.py @@ -100,5 +100,6 @@ class Tests(unittest.TestCase): def find_tests(): return unittest.TestLoader().loadTestsFromTestCase(Tests) + if __name__ == '__main__': unittest.TextTestRunner(verbosity=2).run(find_tests()) diff --git a/src/calibre/ebooks/lit/from_any.py b/src/calibre/ebooks/lit/from_any.py index 4e242b06f0..05345b6749 100644 --- a/src/calibre/ebooks/lit/from_any.py +++ b/src/calibre/ebooks/lit/from_any.py @@ -62,5 +62,6 @@ def main(args=sys.argv): any2lit(opts, args[1]) return 0 + if __name__ == '__main__': sys.exit(main()) diff --git a/src/calibre/ebooks/lit/mssha1.py b/src/calibre/ebooks/lit/mssha1.py index bc3d44e318..9982bd592c 100644 --- a/src/calibre/ebooks/lit/mssha1.py +++ b/src/calibre/ebooks/lit/mssha1.py @@ -104,6 +104,7 @@ def f60_79(B, C, D): def f6_42(B, C, D): return (B + C) ^ C + f = [f0_19]*20 + [f20_39]*20 + [f40_59]*20 + [f60_79]*20 # ...and delightful changes @@ -321,6 +322,7 @@ def new(arg=None): return crypto + if __name__ == '__main__': def main(): import sys diff --git a/src/calibre/ebooks/lit/writer.py b/src/calibre/ebooks/lit/writer.py index 8ba0f03663..3200f02fbe 100644 --- a/src/calibre/ebooks/lit/writer.py +++ b/src/calibre/ebooks/lit/writer.py @@ -57,6 +57,7 @@ def invert_tag_map(tag_map): tattrs[0] = dattrs return tags, tattrs + OPF_MAP = invert_tag_map(maps.OPF_MAP) HTML_MAP = invert_tag_map(maps.HTML_MAP) @@ -76,6 +77,7 @@ def packguid(guid): values = [int(value, 16) for value in values] return pack("<LHHBBBBBBBB", *values) + FLAG_OPENING = (1 << 0) FLAG_CLOSING = (1 << 1) FLAG_BLOCK = (1 << 2) diff --git a/src/calibre/ebooks/lrf/html/convert_from.py b/src/calibre/ebooks/lrf/html/convert_from.py index e596959f47..12f1765872 100644 --- a/src/calibre/ebooks/lrf/html/convert_from.py +++ b/src/calibre/ebooks/lrf/html/convert_from.py @@ -153,9 +153,9 @@ class HTMLConverter(object): (re.compile('<hr>', re.IGNORECASE), lambda match : '<span style="page-break-after:always"> </span>'), # Create header tags - (re.compile('<h2[^><]*?id=BookTitle[^><]*?(align=)*(?(1)(\w+))*[^><]*?>[^><]*?</h2>', re.IGNORECASE), + (re.compile('<h2[^><]*?id=BookTitle[^><]*?(align=)*(?(1)(\\w+))*[^><]*?>[^><]*?</h2>', re.IGNORECASE), lambda match : '<h1 id="BookTitle" align="%s">%s</h1>'%(match.group(2) if match.group(2) else 'center', match.group(3))), - (re.compile('<h2[^><]*?id=BookAuthor[^><]*?(align=)*(?(1)(\w+))*[^><]*?>[^><]*?</h2>', re.IGNORECASE), + (re.compile('<h2[^><]*?id=BookAuthor[^><]*?(align=)*(?(1)(\\w+))*[^><]*?>[^><]*?</h2>', re.IGNORECASE), lambda match : '<h2 id="BookAuthor" align="%s">%s</h2>'%(match.group(2) if match.group(2) else 'center', match.group(3))), (re.compile('<span[^><]*?id=title[^><]*?>(.*?)</span>', re.IGNORECASE|re.DOTALL), lambda match : '<h2 class="title">%s</h2>'%(match.group(1),)), @@ -409,7 +409,7 @@ class HTMLConverter(object): selector name and the value is a dictionary of properties """ sdict, pdict = {}, {} - style = re.sub('/\*.*?\*/', '', style) # Remove /*...*/ comments + style = re.sub('/\\*.*?\\*/', '', style) # Remove /*...*/ comments for sel in re.findall(HTMLConverter.SELECTOR_PAT, style): for key in sel[0].split(','): val = self.parse_style_properties(sel[1]) diff --git a/src/calibre/ebooks/metadata/sources/overdrive.py b/src/calibre/ebooks/metadata/sources/overdrive.py index 19766fd72e..51ed5c8136 100755 --- a/src/calibre/ebooks/metadata/sources/overdrive.py +++ b/src/calibre/ebooks/metadata/sources/overdrive.py @@ -148,7 +148,7 @@ class OverDrive(Source): fix_slashes = re.compile(r'\\/') thumbimage = fix_slashes.sub('/', thumbimage) worldcatlink = fix_slashes.sub('/', worldcatlink) - cover_url = re.sub('(?P<img>(Ima?g(eType-)?))200', '\g<img>100', thumbimage) + cover_url = re.sub('(?P<img>(Ima?g(eType-)?))200', '\\g<img>100', thumbimage) social_metadata_url = base_url+'TitleInfo.aspx?ReserveID='+reserveid+'&FormatID='+formatid series_num = '' if not series: @@ -254,7 +254,7 @@ class OverDrive(Source): def sort_ovrdrv_results(self, raw, log, title=None, title_tokens=None, author=None, author_tokens=None, ovrdrv_id=None): close_matches = [] - raw = re.sub('.*?\[\[(?P<content>.*?)\]\].*', '[[\g<content>]]', raw) + raw = re.sub('.*?\\[\\[(?P<content>.*?)\\]\\].*', '[[\\g<content>]]', raw) results = json.loads(raw) # log.error('raw results are:'+str(results)) # The search results are either from a keyword search or a multi-format list from a single ID, diff --git a/src/calibre/ebooks/metadata/sources/ozon.py b/src/calibre/ebooks/metadata/sources/ozon.py index 0467ef4d1d..b125c45f26 100644 --- a/src/calibre/ebooks/metadata/sources/ozon.py +++ b/src/calibre/ebooks/metadata/sources/ozon.py @@ -149,7 +149,7 @@ class Ozon(Source): # Redirect page: trying to extract ozon_id from javascript data h = HTMLParser() entry_string = (h.unescape(etree.tostring(doc, pretty_print=True, encoding=unicode))) - json_pat = re.compile(u'dataLayer\s*=\s*(.+)?;') + json_pat = re.compile(r'dataLayer\s*=\s*(.+)?;') json_info = re.search(json_pat, entry_string) jsondata = json_info.group(1) if json_info else None if jsondata: @@ -344,7 +344,7 @@ class Ozon(Source): pub_year = None pub_year_block = entry.xpath(u'.//div[@class="bOneTileProperty"]/text()') - year_pattern = re.compile('\d{4}') + year_pattern = re.compile(r'\d{4}') if pub_year_block: pub_year = re.search(year_pattern, pub_year_block[0]) if pub_year: @@ -625,8 +625,8 @@ def _translageLanguageToCode(displayLang): # {{{ def _normalizeAuthorNameWithInitials(name): # {{{ res = name if name: - re1 = u'^(?P<lname>\S+)\s+(?P<fname>[^\d\W]\.)(?:\s*(?P<mname>[^\d\W]\.))?$' - re2 = u'^(?P<fname>[^\d\W]\.)(?:\s*(?P<mname>[^\d\W]\.))?\s+(?P<lname>\S+)$' + re1 = r'^(?P<lname>\S+)\s+(?P<fname>[^\d\W]\.)(?:\s*(?P<mname>[^\d\W]\.))?$' + re2 = r'^(?P<fname>[^\d\W]\.)(?:\s*(?P<mname>[^\d\W]\.))?\s+(?P<lname>\S+)$' matcher = re.match(re1, unicode(name), re.UNICODE) if not matcher: matcher = re.match(re2, unicode(name), re.UNICODE) diff --git a/src/calibre/ebooks/metadata/topaz.py b/src/calibre/ebooks/metadata/topaz.py index 15ac2f9509..38ccce1fbe 100644 --- a/src/calibre/ebooks/metadata/topaz.py +++ b/src/calibre/ebooks/metadata/topaz.py @@ -370,6 +370,7 @@ def set_metadata(stream, mi): mu.update(mi) return + if __name__ == '__main__': if False: # Test get_metadata() @@ -388,4 +389,3 @@ if __name__ == '__main__': updated_data = open(tokens[0]+'-updated' + '.' + tokens[2],'wb') updated_data.write(stream.getvalue()) updated_data.close() - diff --git a/src/calibre/ebooks/mobi/debug/main.py b/src/calibre/ebooks/mobi/debug/main.py index d13155aeb0..c669e0e64b 100644 --- a/src/calibre/ebooks/mobi/debug/main.py +++ b/src/calibre/ebooks/mobi/debug/main.py @@ -45,6 +45,6 @@ def inspect_mobi(path_or_stream, ddir=None): # {{{ def main(): inspect_mobi(sys.argv[1]) + if __name__ == '__main__': main() - diff --git a/src/calibre/ebooks/mobi/reader/mobi6.py b/src/calibre/ebooks/mobi/reader/mobi6.py index d7c2ae1736..8d0f2ce1ee 100644 --- a/src/calibre/ebooks/mobi/reader/mobi6.py +++ b/src/calibre/ebooks/mobi/reader/mobi6.py @@ -350,13 +350,13 @@ class MobiReader(object): # Swap inline and block level elements, and order block level elements according to priority # - lxml and beautifulsoup expect/assume a specific order based on xhtml spec self.processed_html = re.sub( - r'(?i)(?P<styletags>(<(h\d+|i|b|u|em|small|big|strong|tt)>\s*){1,})(?P<para><p[^>]*>)', '\g<para>'+'\g<styletags>', self.processed_html) + r'(?i)(?P<styletags>(<(h\d+|i|b|u|em|small|big|strong|tt)>\s*){1,})(?P<para><p[^>]*>)', '\\g<para>'+'\\g<styletags>', self.processed_html) self.processed_html = re.sub( - r'(?i)(?P<para></p[^>]*>)\s*(?P<styletags>(</(h\d+|i|b|u|em|small|big|strong|tt)>\s*){1,})', '\g<styletags>'+'\g<para>', self.processed_html) + r'(?i)(?P<para></p[^>]*>)\s*(?P<styletags>(</(h\d+|i|b|u|em|small|big|strong|tt)>\s*){1,})', '\\g<styletags>'+'\\g<para>', self.processed_html) self.processed_html = re.sub( - r'(?i)(?P<blockquote>(</(blockquote|div)[^>]*>\s*){1,})(?P<para></p[^>]*>)', '\g<para>'+'\g<blockquote>', self.processed_html) + r'(?i)(?P<blockquote>(</(blockquote|div)[^>]*>\s*){1,})(?P<para></p[^>]*>)', '\\g<para>'+'\\g<blockquote>', self.processed_html) self.processed_html = re.sub( - r'(?i)(?P<para><p[^>]*>)\s*(?P<blockquote>(<(blockquote|div)[^>]*>\s*){1,})', '\g<blockquote>'+'\g<para>', self.processed_html) + r'(?i)(?P<para><p[^>]*>)\s*(?P<blockquote>(<(blockquote|div)[^>]*>\s*){1,})', '\\g<blockquote>'+'\\g<para>', self.processed_html) bods = htmls = 0 for x in re.finditer(u'</body>|</html>', self.processed_html): if x == '</body>': @@ -692,7 +692,7 @@ class MobiReader(object): continue if reached and x.tag == 'a': href = x.get('href', '') - if href and re.match('\w+://', href) is None: + if href and re.match('\\w+://', href) is None: try: text = u' '.join([t.strip() for t in x.xpath('descendant::text()')]) diff --git a/src/calibre/ebooks/mobi/writer8/index.py b/src/calibre/ebooks/mobi/writer8/index.py index 265758846a..12905d5858 100644 --- a/src/calibre/ebooks/mobi/writer8/index.py +++ b/src/calibre/ebooks/mobi/writer8/index.py @@ -374,6 +374,7 @@ class NonLinearNCXIndex(NCXIndex): EndTagTable ))) + if __name__ == '__main__': # Generate a document with a large number of index entries using both # calibre and kindlegen and compare the output @@ -393,4 +394,3 @@ if __name__ == '__main__': from calibre.gui2.tweak_book.diff.main import main main(['cdiff', 'decompiled_index/mobi8/ncx.record', 'x/ncx.record']) - diff --git a/src/calibre/ebooks/oeb/normalize_css.py b/src/calibre/ebooks/oeb/normalize_css.py index 91cc745f15..c318cd932d 100644 --- a/src/calibre/ebooks/oeb/normalize_css.py +++ b/src/calibre/ebooks/oeb/normalize_css.py @@ -114,6 +114,7 @@ def normalize_simple_composition(name, cssvalue, composition, check_inherit=True break return style + font_composition = ('font-style', 'font-variant', 'font-weight', 'font-size', 'line-height', 'font-family') @@ -144,6 +145,7 @@ def normalize_border(name, cssvalue): style.update({k.replace(EDGES[0], edge):v for k, v in vals.iteritems()}) return style + normalizers = { 'list-style': simple_normalizer('list-style', ('type', 'position', 'image')), 'font': lambda prop, v: normalize_font(v), @@ -243,6 +245,7 @@ def condense_border(style, props): style.removeProperty(prop.name) style.setProperty('border', edge_vals[0].value) + condensers = {'margin': simple_condenser('margin', condense_edge), 'padding': simple_condenser('padding', condense_edge), 'border': condense_border} @@ -430,5 +433,6 @@ def test_normalization(return_tests=False): # {{{ unittest.TextTestRunner(verbosity=4).run(tests) # }}} + if __name__ == '__main__': test_normalization() diff --git a/src/calibre/ebooks/oeb/polish/cascade.py b/src/calibre/ebooks/oeb/polish/cascade.py index b756f9dfc2..ce8e33f86b 100644 --- a/src/calibre/ebooks/oeb/polish/cascade.py +++ b/src/calibre/ebooks/oeb/polish/cascade.py @@ -82,6 +82,7 @@ def iterrules(container, sheet_name, rules=None, media_rule_ok=media_allowed, ru importing.discard(sheet_name) + StyleDeclaration = namedtuple('StyleDeclaration', 'index declaration pseudo_element') Specificity = namedtuple('Specificity', 'is_style num_id num_class num_elem rule_index') @@ -224,6 +225,7 @@ def resolve_styles(container, name, select=None, sheet_callback=None): return partial(resolve_property, style_map), partial(resolve_pseudo_property, style_map, pseudo_style_map), select + _defvals = None diff --git a/src/calibre/ebooks/oeb/polish/create.py b/src/calibre/ebooks/oeb/polish/create.py index 926b05ded4..c284dda445 100644 --- a/src/calibre/ebooks/oeb/polish/create.py +++ b/src/calibre/ebooks/oeb/polish/create.py @@ -115,6 +115,7 @@ def create_book(mi, path, fmt='epub', opf_name='metadata.opf', html_name='start. zf.writestr(html_name, HTML) zf.writestr(toc_name, ncx) + if __name__ == '__main__': from calibre.ebooks.metadata.book.base import Metadata mi = Metadata('Test book', authors=('Kovid Goyal',)) diff --git a/src/calibre/ebooks/pdb/ereader/inspector.py b/src/calibre/ebooks/pdb/ereader/inspector.py index 73c1ad8894..2291c74a1b 100644 --- a/src/calibre/ebooks/pdb/ereader/inspector.py +++ b/src/calibre/ebooks/pdb/ereader/inspector.py @@ -140,5 +140,6 @@ def main(args=sys.argv): return 0 + if __name__ == '__main__': sys.exit(main()) diff --git a/src/calibre/ebooks/pdf/render/test.py b/src/calibre/ebooks/pdf/render/test.py index 35600e33b3..da283f785c 100644 --- a/src/calibre/ebooks/pdf/render/test.py +++ b/src/calibre/ebooks/pdf/render/test.py @@ -134,7 +134,6 @@ def main(): print('PDF written to:', pdf) print('Image written to:', path) + if __name__ == '__main__': main() - - diff --git a/src/calibre/ebooks/pml/pmlml.py b/src/calibre/ebooks/pml/pmlml.py index 60d3df084b..7a121cb4de 100644 --- a/src/calibre/ebooks/pml/pmlml.py +++ b/src/calibre/ebooks/pml/pmlml.py @@ -188,7 +188,7 @@ class PMLMLizer(object): text = text.replace('\\Q="%s"' % unused, '') # Remove \Cn tags that are within \x and \Xn tags - text = re.sub(unicode(r'(?msu)(?P<t>\\(x|X[0-4]))(?P<a>.*?)(?P<c>\\C[0-4]\s*=\s*"[^"]*")(?P<b>.*?)(?P=t)'), '\g<t>\g<a>\g<b>\g<t>', text) + text = re.sub(unicode(r'(?msu)(?P<t>\\(x|X[0-4]))(?P<a>.*?)(?P<c>\\C[0-4]\s*=\s*"[^"]*")(?P<b>.*?)(?P=t)'), '\\g<t>\\g<a>\\g<b>\\g<t>', text) # Replace bad characters. text = text.replace(u'\xc2', '') @@ -206,7 +206,7 @@ class PMLMLizer(object): text = re.sub('[ ]{2,}', ' ', text) # Condense excessive \c empty line sequences. - text = re.sub('(\\c\s*\\c\s*){2,}', '\\c \n\\c\n', text) + text = re.sub('(\\c\\s*\\c\\s*){2,}', '\\c \n\\c\n', text) # Remove excessive newlines. text = re.sub('\n[ ]+\n', '\n\n', text) diff --git a/src/calibre/ebooks/rtf/rtfml.py b/src/calibre/ebooks/rtf/rtfml.py index 1f4cb3b420..bb602aa4d8 100644 --- a/src/calibre/ebooks/rtf/rtfml.py +++ b/src/calibre/ebooks/rtf/rtfml.py @@ -142,7 +142,7 @@ class RTFMLizer(object): return text def remove_tabs(self, text): - self.log.debug('\Replace tabs with space for processing...') + self.log.debug('Replace tabs with space for processing...') text = text.replace('\t', ' ') return text diff --git a/src/calibre/ebooks/rtf2xml/check_encoding.py b/src/calibre/ebooks/rtf2xml/check_encoding.py index 040f3892e8..91e4f5bae8 100755 --- a/src/calibre/ebooks/rtf2xml/check_encoding.py +++ b/src/calibre/ebooks/rtf2xml/check_encoding.py @@ -32,6 +32,7 @@ class CheckEncoding: return True return False + if __name__ == '__main__': check_encoding_obj = CheckEncoding() check_encoding_obj.check_encoding(sys.argv[1]) diff --git a/src/calibre/ebooks/rtf2xml/default_encoding.py b/src/calibre/ebooks/rtf2xml/default_encoding.py index 1dde71d464..7a0fd03cc5 100755 --- a/src/calibre/ebooks/rtf2xml/default_encoding.py +++ b/src/calibre/ebooks/rtf2xml/default_encoding.py @@ -175,6 +175,7 @@ class DefaultEncoding: elif enc == 'pca': self.__code_page = '850' + if __name__ == '__main__': import sys encode_obj = DefaultEncoding( diff --git a/src/calibre/ebooks/rtf2xml/field_strings.py b/src/calibre/ebooks/rtf2xml/field_strings.py index 6691e2f449..522dabef29 100755 --- a/src/calibre/ebooks/rtf2xml/field_strings.py +++ b/src/calibre/ebooks/rtf2xml/field_strings.py @@ -411,8 +411,6 @@ class FieldStrings: line -- the string to be parse Retuns: The name of the field - Logic: - self.__link_switch = re.compile(r'\\l\s{1,}(.*?)\s') """ self.__link_switch = re.compile(r'\\l\s{1,}"{0,1}(.*?)"{0,1}\s') the_string = name diff --git a/src/calibre/ebooks/rtf2xml/hex_2_utf8.py b/src/calibre/ebooks/rtf2xml/hex_2_utf8.py index c064e6e77d..201f3c6ab2 100755 --- a/src/calibre/ebooks/rtf2xml/hex_2_utf8.py +++ b/src/calibre/ebooks/rtf2xml/hex_2_utf8.py @@ -562,6 +562,8 @@ class Hex2Utf8: self.__convert_preamble() else: self.__convert_body() + + """ how to swap case for non-capitals my_string.swapcase() diff --git a/src/calibre/ebooks/rtf2xml/list_table.py b/src/calibre/ebooks/rtf2xml/list_table.py index aeb6b6f62f..183b31b6ea 100755 --- a/src/calibre/ebooks/rtf2xml/list_table.py +++ b/src/calibre/ebooks/rtf2xml/list_table.py @@ -120,7 +120,7 @@ class ListTable: Requires: line -- line to process Returns: nothing Logic: - I have found \list. + I have found \\list. Change the state to list Get the open bracket count so you know when this state ends. Append an empty list to all lists. @@ -162,7 +162,7 @@ class ListTable: Requires: line -- line to process Returns: nothing Logic: - I have found \listlevel. + I have found \\listlevel. Change the state to level Get the open bracket count so you know when this state ends. Append an empty list to the last list inside all lists. @@ -285,7 +285,7 @@ class ListTable: Returns: nothing Logic: - Method is used for to parse text in the \leveltext group. + Method is used for to parse text in the \\leveltext group. """ num = line[18:] the_num = int(num, 16) diff --git a/src/calibre/ebooks/rtf2xml/options_trem.py b/src/calibre/ebooks/rtf2xml/options_trem.py index d768b8b232..ff6ba5194f 100755 --- a/src/calibre/ebooks/rtf2xml/options_trem.py +++ b/src/calibre/ebooks/rtf2xml/options_trem.py @@ -270,6 +270,8 @@ class ParseOptions: return options_dict, arguments else: return 0,0 + + if __name__ == '__main__': this_dict = { 'indents': [0, 'i'], diff --git a/src/calibre/ebooks/rtf2xml/override_table.py b/src/calibre/ebooks/rtf2xml/override_table.py index 6eb5e24d88..5477f289f3 100755 --- a/src/calibre/ebooks/rtf2xml/override_table.py +++ b/src/calibre/ebooks/rtf2xml/override_table.py @@ -52,7 +52,7 @@ class OverrideTable: Returns: nothing Logic: - The group {\override has been found. + The group {\\override has been found. Check for the end of the group. Otherwise, add appropriate tokens to the override dictionary. """ diff --git a/src/calibre/ebooks/rtf2xml/paragraph_def.py b/src/calibre/ebooks/rtf2xml/paragraph_def.py index 8b062e524b..82962fe9ea 100755 --- a/src/calibre/ebooks/rtf2xml/paragraph_def.py +++ b/src/calibre/ebooks/rtf2xml/paragraph_def.py @@ -128,7 +128,7 @@ if another paragraph_def is found, the state changes to collect_tokens. 'list-conti' : 'list-continue', 'list-hang_' : 'list-hang', # 'list-tebef' : 'list-text-before', - 'list-level' : 'level', + # 'list-level' : 'level', 'list-id___' : 'list-id', 'list-start' : 'list-start', 'nest-level' : 'nest-level', @@ -198,7 +198,7 @@ if another paragraph_def is found, the state changes to collect_tokens. 'bor-cel-to' : 'border-cell-top', 'bor-cel-le' : 'border-cell-left', 'bor-cel-ri' : 'border-cell-right', - 'bor-par-bo' : 'border-paragraph-bottom', + # 'bor-par-bo' : 'border-paragraph-bottom', 'bor-par-to' : 'border-paragraph-top', 'bor-par-le' : 'border-paragraph-left', 'bor-par-ri' : 'border-paragraph-right', @@ -413,7 +413,7 @@ if another paragraph_def is found, the state changes to collect_tokens. Returns: nothing Logic: - I have found a \pard while I am collecting tokens. I want to reset + I have found a \\pard while I am collecting tokens. I want to reset the dectionary and do nothing else. """ # Change this diff --git a/src/calibre/ebooks/rtf2xml/process_tokens.py b/src/calibre/ebooks/rtf2xml/process_tokens.py index b0ea1dff97..0f18d5ff9b 100755 --- a/src/calibre/ebooks/rtf2xml/process_tokens.py +++ b/src/calibre/ebooks/rtf2xml/process_tokens.py @@ -584,7 +584,7 @@ class ProcessTokens: } """ # unknown - # These must get passed on because they occure after \* + # These must get passed on because they occure after \\* 'do' : ('un', 'unknown___', self.default_func), 'company' : ('un', 'company___', self.default_func), 'shpinst' : ('un', 'unknown___', self.default_func), @@ -716,10 +716,10 @@ class ProcessTokens: def divide_num(self, numerator, denominator): try: # calibre why ignore negative number? Wrong in case of \fi - numerator = float(re.search('[0-9.\-]+', numerator).group()) + numerator = float(re.search('[0-9.\\-]+', numerator).group()) except TypeError as msg: if self.__run_level > 3: - msg = ('No number to process?\nthis indicates that the token \(\\li\) \ + msg = ('No number to process?\nthis indicates that the token \\(\\li\\) \ should have a number and does not\nnumerator is \ "%s"\ndenominator is "%s"\n') % (numerator, denominator) raise self.__bug_handler(msg) diff --git a/src/calibre/ebooks/rtf2xml/sections.py b/src/calibre/ebooks/rtf2xml/sections.py index 3bdebb6838..86ec6ede5d 100755 --- a/src/calibre/ebooks/rtf2xml/sections.py +++ b/src/calibre/ebooks/rtf2xml/sections.py @@ -27,19 +27,19 @@ class Sections: logic --------------- The tags for the first section breaks have already been written. - RTF stores section breaks with the \sect tag. Each time this tag is + RTF stores section breaks with the \\sect tag. Each time this tag is encountered, add one to the counter. - When I encounter the \sectd tag, I want to collect all the appropriate tokens - that describe the section. When I reach a \pard, I know I an stop collecting + When I encounter the \\sectd tag, I want to collect all the appropriate tokens + that describe the section. When I reach a \\pard, I know I an stop collecting tokens and write the section tags. The exception to this method occurs when sections occur in field blocks, such as the index. Normally, two section break occur within the index and other - field-blocks. (If less or more section breaks occurr, this code may not work.) + field-blocks. (If less or more section breaks occur, this code may not work.) I want the sections to occur outside of the index. That is, the index should be nested inside one section tag. After the index is complete, a new section should begin. In order to write the sections outside of the field blocks, I have to store - all of the field block as a string. When I ecounter the \sect tag, add one to + all of the field block as a string. When I ecounter the \\sect tag, add one to the section counter, but store this number in a list. Likewise, store the information describing the section in another list. When I reach the end of the field block, choose the first item from the @@ -243,7 +243,7 @@ class Sections: nothing Logic: Text or control words indicating text have been found - before \pard. This shoud indicate older RTF. Reset the state + before \\pard. This shoud indicate older RTF. Reset the state Write the section defintion. Insert a paragraph definition. Insert {} to mark the end of a paragraph defintion """ diff --git a/src/calibre/ebooks/rtf2xml/styles.py b/src/calibre/ebooks/rtf2xml/styles.py index 6f0b48ae3d..813778b2e9 100755 --- a/src/calibre/ebooks/rtf2xml/styles.py +++ b/src/calibre/ebooks/rtf2xml/styles.py @@ -121,7 +121,7 @@ class Styles: 'list-conti' : 'list-continue', 'list-hang_' : 'list-hang', # 'list-tebef' : 'list-text-before', - 'list-level' : 'level', + # 'list-level' : 'level', 'list-id___' : 'list-id', 'list-start' : 'list-start', 'nest-level' : 'nest-level', @@ -192,7 +192,7 @@ class Styles: 'bor-cel-to' : 'border-cell-top', 'bor-cel-le' : 'border-cell-left', 'bor-cel-ri' : 'border-cell-right', - 'bor-par-bo' : 'border-paragraph-bottom', + # 'bor-par-bo' : 'border-paragraph-bottom', 'bor-par-to' : 'border-paragraph-top', 'bor-par-le' : 'border-paragraph-left', 'bor-par-ri' : 'border-paragraph-right', diff --git a/src/calibre/ebooks/snb/snbfile.py b/src/calibre/ebooks/snb/snbfile.py index b3820955da..a50eb0a710 100644 --- a/src/calibre/ebooks/snb/snbfile.py +++ b/src/calibre/ebooks/snb/snbfile.py @@ -333,6 +333,7 @@ def main(): return 1 return 0 + if __name__ == "__main__": """SNB file unit test""" sys.exit(main()) diff --git a/src/calibre/gui2/dbus_export/demo.py b/src/calibre/gui2/dbus_export/demo.py index e3e4f7d712..4a298bc373 100644 --- a/src/calibre/gui2/dbus_export/demo.py +++ b/src/calibre/gui2/dbus_export/demo.py @@ -160,6 +160,7 @@ class MainWindow(QMainWindow): self.window_unblocked.emit() return QMainWindow.event(self, ev) + app=QApplication([]) app.setAttribute(Qt.AA_DontUseNativeMenuBar, False) app.setApplicationName('com.calibre-ebook.DBusExportDemo') diff --git a/src/calibre/gui2/dialogs/template_dialog.py b/src/calibre/gui2/dialogs/template_dialog.py index 4bfa3280ed..8f1dc4a539 100644 --- a/src/calibre/gui2/dialogs/template_dialog.py +++ b/src/calibre/gui2/dialogs/template_dialog.py @@ -456,6 +456,7 @@ class TemplateDialog(QDialog, Ui_TemplateDialog): self.rule = ('', txt) QDialog.accept(self) + if __name__ == '__main__': app = QApplication([]) from calibre.ebooks.metadata.book.base import field_metadata diff --git a/src/calibre/gui2/lrf_renderer/text.py b/src/calibre/gui2/lrf_renderer/text.py index 8ab88fd5a8..3bcbe21b1e 100644 --- a/src/calibre/gui2/lrf_renderer/text.py +++ b/src/calibre/gui2/lrf_renderer/text.py @@ -581,5 +581,6 @@ class Word(object): def main(args=sys.argv): return 0 + if __name__ == '__main__': sys.exit(main()) diff --git a/src/calibre/gui2/preferences/behavior.py b/src/calibre/gui2/preferences/behavior.py index c7f3047860..6f7e56596a 100644 --- a/src/calibre/gui2/preferences/behavior.py +++ b/src/calibre/gui2/preferences/behavior.py @@ -171,8 +171,8 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form): info_dialog(self, _('Done'), _('Confirmation dialogs have all been reset'), show=True) + if __name__ == '__main__': from PyQt5.Qt import QApplication app = QApplication([]) test_widget('Interface', 'Behavior') - diff --git a/src/calibre/gui2/store/loader.py b/src/calibre/gui2/store/loader.py index a36c1b3959..e6d9b5252c 100644 --- a/src/calibre/gui2/store/loader.py +++ b/src/calibre/gui2/store/loader.py @@ -190,6 +190,7 @@ class Stores(OrderedDict): return cls(builtin.gui, builtin.name, config=builtin.config, base_plugin=builtin.base_plugin), ver + if __name__ == '__main__': st = time.time() count = 0 @@ -199,5 +200,3 @@ if __name__ == '__main__': print(code.encode('utf-8')) print('\n', '_'*80, '\n', sep='') print ('Time to download all %d plugins: %.2f seconds'%(count, time.time() - st)) - - diff --git a/src/calibre/gui2/store/search/models.py b/src/calibre/gui2/store/search/models.py index be743e1584..b7ac6e11b6 100644 --- a/src/calibre/gui2/store/search/models.py +++ b/src/calibre/gui2/store/search/models.py @@ -153,15 +153,15 @@ class Matches(QAbstractItemModel): # Remove filter identifiers # Remove the prefix. for loc in ('all', 'author', 'author2', 'authors', 'title', 'title2'): - query = re.sub(r'%s:"(?P<a>[^\s"]+)"' % loc, '\g<a>', query) + query = re.sub(r'%s:"(?P<a>[^\s"]+)"' % loc, r'\g<a>', query) query = query.replace('%s:' % loc, '') # Remove the prefix and search text. for loc in ('cover', 'download', 'downloads', 'drm', 'format', 'formats', 'price', 'store'): query = re.sub(r'%s:"[^"]"' % loc, '', query) query = re.sub(r'%s:[^\s]*' % loc, '', query) # Remove whitespace - query = re.sub('\s', '', query) - mod_query = re.sub('\s', '', mod_query) + query = re.sub(r'\s', '', query) + mod_query = re.sub(r'\s', '', mod_query) # If mod_query and query are the same then there were no filter modifiers # so this isn't a filterable query. if mod_query == query: diff --git a/src/calibre/library/caches.py b/src/calibre/library/caches.py index ef0c8ef9ef..9ac22bd6a9 100644 --- a/src/calibre/library/caches.py +++ b/src/calibre/library/caches.py @@ -128,6 +128,7 @@ def set_use_primary_find_in_search(toWhat): global pref_use_primary_find_in_search pref_use_primary_find_in_search = toWhat + y, c, n, u = map(icu_lower, (_('yes'), _('checked'), _('no'), _('unchecked'))) yes_vals = {y, c, 'true'} no_vals = {n, u, 'false'} @@ -1215,5 +1216,3 @@ class SortKeyGenerator(object): # }}} # }}} - - diff --git a/src/calibre/library/catalogs/bibtex.py b/src/calibre/library/catalogs/bibtex.py index 989916ce82..66efa81571 100644 --- a/src/calibre/library/catalogs/bibtex.py +++ b/src/calibre/library/catalogs/bibtex.py @@ -241,7 +241,7 @@ class BIBTEX(CatalogPlugin): # define a function to replace the template entry by its value def tpl_replace(objtplname) : - tpl_field = re.sub(u'[\{\}]', u'', objtplname.group()) + tpl_field = re.sub(u'[\\{\\}]', u'', objtplname.group()) if tpl_field in TEMPLATE_ALLOWED_FIELDS : if tpl_field in ['pubdate', 'timestamp'] : @@ -258,14 +258,14 @@ class BIBTEX(CatalogPlugin): if len(template_citation) >0 : tpl_citation = bibtexclass.utf8ToBibtex( - bibtexclass.ValidateCitationKey(re.sub(u'\{[^{}]*\}', + bibtexclass.ValidateCitationKey(re.sub(u'\\{[^{}]*\\}', tpl_replace, template_citation))) if len(tpl_citation) >0 : return tpl_citation if len(entry["isbn"]) > 0 : - template_citation = u'%s' % re.sub(u'[\D]',u'', entry["isbn"]) + template_citation = u'%s' % re.sub(u'[\\D]',u'', entry["isbn"]) else : template_citation = u'%s' % str(entry["id"]) diff --git a/src/calibre/library/catalogs/csv_xml.py b/src/calibre/library/catalogs/csv_xml.py index fbd5ba4a91..f4d8719bd3 100644 --- a/src/calibre/library/catalogs/csv_xml.py +++ b/src/calibre/library/catalogs/csv_xml.py @@ -154,9 +154,9 @@ class CSV_XML(CatalogPlugin): # Convert HTML to markdown text if type(item) is unicode: - opening_tag = re.search('<(\w+)(\x20|>)', item) + opening_tag = re.search('<(\\w+)(\x20|>)', item) if opening_tag: - closing_tag = re.search('<\/%s>$' % opening_tag.group(1), item) + closing_tag = re.search('<\\/%s>$' % opening_tag.group(1), item) if closing_tag: item = html2text(item) diff --git a/src/calibre/library/catalogs/epub_mobi.py b/src/calibre/library/catalogs/epub_mobi.py index 2d0ee5842b..e1cb46813c 100644 --- a/src/calibre/library/catalogs/epub_mobi.py +++ b/src/calibre/library/catalogs/epub_mobi.py @@ -61,7 +61,7 @@ class EPUB_MOBI(CatalogPlugin): "Default: '%default'\n" "Applies to: AZW3, EPUB, MOBI output formats")), Option('--exclude-genre', - default='\[.+\]|^\+$', + default='\\[.+\\]|^\\+$', dest='exclude_genre', action=None, help=_("Regex describing tags to exclude as genres.\n" diff --git a/src/calibre/library/catalogs/epub_mobi_builder.py b/src/calibre/library/catalogs/epub_mobi_builder.py index b0b42dbc60..bf0e00dd66 100644 --- a/src/calibre/library/catalogs/epub_mobi_builder.py +++ b/src/calibre/library/catalogs/epub_mobi_builder.py @@ -1209,11 +1209,11 @@ class CatalogBuilder(object): clipped to max_len """ - normalized = massaged = re.sub('\s', '', ascii_text(tag).lower()) - if re.search('\W', normalized): + normalized = massaged = re.sub('\\s', '', ascii_text(tag).lower()) + if re.search('\\W', normalized): normalized = '' for c in massaged: - if re.search('\W', c): + if re.search('\\W', c): normalized += self.generate_unicode_name(c) else: normalized += c @@ -1376,7 +1376,7 @@ class CatalogBuilder(object): Return: (str): asciized version of author """ - return re.sub("\W", "", ascii_text(author)) + return re.sub("\\W", "", ascii_text(author)) def generate_format_args(self, book): """ Generate the format args for template substitution. @@ -4209,9 +4209,9 @@ class CatalogBuilder(object): # Generate a legal XHTML id/href string if self.letter_or_symbol(series) == self.SYMBOLS: - return "symbol_%s_series" % re.sub('\W', '', series).lower() + return "symbol_%s_series" % re.sub('\\W', '', series).lower() else: - return "%s_series" % re.sub('\W', '', ascii_text(series)).lower() + return "%s_series" % re.sub('\\W', '', ascii_text(series)).lower() def generate_short_description(self, description, dest=None): """ Generate a truncated version of the supplied string. @@ -4292,7 +4292,7 @@ class CatalogBuilder(object): else: if re.match('[0-9]+', word[0]): word = word.replace(',', '') - suffix = re.search('[\D]', word) + suffix = re.search('[\\D]', word) if suffix: word = '%10.0f%s' % (float(word[:suffix.start()]), word[suffix.start():]) else: @@ -4308,7 +4308,7 @@ class CatalogBuilder(object): else: if re.search('[0-9]+', word[0]): word = word.replace(',', '') - suffix = re.search('[\D]', word) + suffix = re.search('[\\D]', word) if suffix: word = '%10.0f%s' % (float(word[:suffix.start()]), word[suffix.start():]) else: @@ -4638,7 +4638,7 @@ class CatalogBuilder(object): # confusion with decimal points. # Explode lost CRs to \n\n - for lost_cr in re.finditer('([a-z])([\.\?!])([A-Z])', comments): + for lost_cr in re.finditer('([a-z])([\\.\\?!])([A-Z])', comments): comments = comments.replace(lost_cr.group(), '%s%s\n\n%s' % (lost_cr.group(1), lost_cr.group(2), diff --git a/src/calibre/library/catalogs/utils.py b/src/calibre/library/catalogs/utils.py index cc7e6aa6ec..09d4ad84bc 100644 --- a/src/calibre/library/catalogs/utils.py +++ b/src/calibre/library/catalogs/utils.py @@ -90,8 +90,8 @@ class NumberToText(object): # {{{ # Special case ordinals if re.search('[st|nd|rd|th]',self.number): self.number = re.sub(',','',self.number) - ordinal_suffix = re.search('[\D]', self.number) - ordinal_number = re.sub('\D','',re.sub(',','',self.number)) + ordinal_suffix = re.search('[\\D]', self.number) + ordinal_number = re.sub('\\D','',re.sub(',','',self.number)) if self.verbose: self.log("Ordinal: %s" % ordinal_number) self.number_as_float = ordinal_number @@ -120,7 +120,7 @@ class NumberToText(object): # {{{ self.text = NumberToText(self.number.replace('%',' percent')).text # Test for decimal - elif re.search('\.',self.number): + elif re.search('\\.',self.number): if self.verbose: self.log("Decimal: %s" % self.number) self.number_as_float = self.number @@ -151,12 +151,12 @@ class NumberToText(object): # {{{ self.text = NumberToText(self.number_as_float).text # Test for hybrid e.g., 'K2, 2nd, 10@10' - elif re.search('[\D]+', self.number): + elif re.search('[\\D]+', self.number): if self.verbose: self.log("Hybrid: %s" % self.number) # Split the token into number/text - number_position = re.search('\d',self.number).start() - text_position = re.search('\D',self.number).start() + number_position = re.search('\\d',self.number).start() + text_position = re.search('\\D',self.number).start() if number_position < text_position: number = self.number[:text_position] text = self.number[text_position:] @@ -225,4 +225,3 @@ class NumberToText(object): # {{{ self.log(u'resultString: %s' % resultString) self.text = resultString.strip().capitalize() # }}} - diff --git a/src/calibre/library/comments.py b/src/calibre/library/comments.py index d3fb0659bb..dc458268b9 100644 --- a/src/calibre/library/comments.py +++ b/src/calibre/library/comments.py @@ -16,7 +16,7 @@ from calibre.utils.html2text import html2text # Hackish - ignoring sentences ending or beginning in numbers to avoid # confusion with decimal points. -lost_cr_pat = re.compile('([a-z])([\.\?!])([A-Z])') +lost_cr_pat = re.compile('([a-z])([\\.\\?!])([A-Z])') lost_cr_exception_pat = re.compile(r'(Ph\.D)|(D\.Phil)|((Dr|Mr|Mrs|Ms)\.[A-Z])') sanitize_pat = re.compile(r'<script|<table|<tr|<td|<th|<style|<iframe', re.IGNORECASE) diff --git a/src/calibre/library/custom_columns.py b/src/calibre/library/custom_columns.py index 74a7a150ac..b3fc46013c 100644 --- a/src/calibre/library/custom_columns.py +++ b/src/calibre/library/custom_columns.py @@ -657,7 +657,7 @@ class CustomColumns(object): editable=True, display={}): if not label: raise ValueError(_('No label was provided')) - if re.match('^\w*$', label) is None or not label[0].isalpha() or label.lower() != label: + if re.match('^\\w*$', label) is None or not label[0].isalpha() or label.lower() != label: raise ValueError(_('The label must contain only lower case letters, digits and underscores, and start with a letter')) if datatype not in self.CUSTOM_DATA_TYPES: raise ValueError('%r is not a supported data type'%datatype) @@ -809,5 +809,3 @@ class CustomColumns(object): self.conn.executescript(script) self.conn.commit() return num - - diff --git a/src/calibre/library/database.py b/src/calibre/library/database.py index af860fbb14..0a4e1349ef 100644 --- a/src/calibre/library/database.py +++ b/src/calibre/library/database.py @@ -50,7 +50,7 @@ def _connect(path): conn = sqlite.connect(path, factory=Connection, detect_types=sqlite.PARSE_DECLTYPES|sqlite.PARSE_COLNAMES) conn.row_factory = lambda cursor, row : list(row) conn.create_aggregate('concat', 1, Concatenate) - title_pat = re.compile('^(A|The|An)\s+', re.IGNORECASE) + title_pat = re.compile('^(A|The|An)\\s+', re.IGNORECASE) def title_sort(title): match = title_pat.search(title) @@ -1514,6 +1514,7 @@ def text_to_tokens(text): continue return ans, OR + if __name__ == '__main__': sqlite.enable_callback_tracebacks(True) db = LibraryDatabase('/home/kovid/temp/library1.db.orig') diff --git a/src/calibre/library/sqlite.py b/src/calibre/library/sqlite.py index d615b8abbf..6f5ac75d74 100644 --- a/src/calibre/library/sqlite.py +++ b/src/calibre/library/sqlite.py @@ -68,6 +68,7 @@ def _py_convert_timestamp(val): return parse_date(val, as_utc=False) return None + convert_timestamp = _py_convert_timestamp if _c_speedup is None else \ _c_convert_timestamp @@ -75,6 +76,7 @@ convert_timestamp = _py_convert_timestamp if _c_speedup is None else \ def adapt_datetime(dt): return isoformat(dt, sep=' ') + sqlite.register_adapter(datetime, adapt_datetime) sqlite.register_converter('timestamp', convert_timestamp) @@ -82,6 +84,7 @@ sqlite.register_converter('timestamp', convert_timestamp) def convert_bool(val): return val != '0' + sqlite.register_adapter(bool, lambda x : 1 if x else 0) sqlite.register_converter('bool', convert_bool) sqlite.register_converter('BOOL', convert_bool) @@ -411,4 +414,3 @@ def test(): c = sqlite.connect(':memory:') if load_c_extensions(c, True): print('Loaded C extension successfully') - diff --git a/src/calibre/libunzip.py b/src/calibre/libunzip.py index f0d664c667..38fd1e6158 100644 --- a/src/calibre/libunzip.py +++ b/src/calibre/libunzip.py @@ -64,6 +64,7 @@ def extract_member(filename, match=re.compile(r'\.(jpg|jpeg|gif|png)\s*$', re.I) if match.search(name): return name, zf.read(name) + comic_exts = {'png', 'jpg', 'jpeg', 'gif', 'webp'} diff --git a/src/calibre/srv/pre_activated.py b/src/calibre/srv/pre_activated.py index 12dfaa0882..94f0993eb5 100644 --- a/src/calibre/srv/pre_activated.py +++ b/src/calibre/srv/pre_activated.py @@ -14,6 +14,8 @@ from calibre.constants import islinux def pre_activated_socket(): return None + + has_preactivated_support = False if islinux: diff --git a/src/calibre/translations/__init__.py b/src/calibre/translations/__init__.py index 7ec2240d14..4c50ab4751 100644 --- a/src/calibre/translations/__init__.py +++ b/src/calibre/translations/__init__.py @@ -73,7 +73,7 @@ def check_for_critical_bugs(): print('WARNING: Translation errors detected') print('See the .errors directory and http://translate.sourceforge.net/wiki/toolkit/using_pofilter') + if __name__ == '__main__': import sys import_from_launchpad(sys.argv[1]) - diff --git a/src/calibre/translations/msgfmt.py b/src/calibre/translations/msgfmt.py index 0c7ed120a9..0bbb521663 100644 --- a/src/calibre/translations/msgfmt.py +++ b/src/calibre/translations/msgfmt.py @@ -146,7 +146,7 @@ def make(filename, outfile): # This is a message with plural forms elif l.startswith('msgid_plural'): if section != ID: - print('msgid_plural not preceeded by msgid on %s:%d' %\ + print('msgid_plural not preceeded by msgid on %s:%d' % (infile, lno), file=sys.stderr) sys.exit(1) l = l[12:] @@ -157,7 +157,7 @@ def make(filename, outfile): section = STR if l.startswith('msgstr['): if not is_plural: - print('plural without msgid_plural on %s:%d' %\ + print('plural without msgid_plural on %s:%d' % (infile, lno), file=sys.stderr) sys.exit(1) l = l.split(']', 1)[1] @@ -165,7 +165,7 @@ def make(filename, outfile): msgstr += '\0' # Separator of the various plural forms else: if is_plural: - print('indexed msgstr required for plural on %s:%d' %\ + print('indexed msgstr required for plural on %s:%d' % (infile, lno), file=sys.stderr) sys.exit(1) l = l[6:] @@ -180,7 +180,7 @@ def make(filename, outfile): elif section == STR: msgstr += l else: - print('Syntax error on %s:%d' % (infile, lno), \ + print('Syntax error on %s:%d' % (infile, lno), 'before:', file=sys.stderr) print(l, file=sys.stderr) sys.exit(1) diff --git a/src/calibre/utils/Zeroconf.py b/src/calibre/utils/Zeroconf.py index 76bc03e189..2d0c760279 100755 --- a/src/calibre/utils/Zeroconf.py +++ b/src/calibre/utils/Zeroconf.py @@ -1627,6 +1627,7 @@ class Zeroconf(object): # Test a few module features, including service registration, service # query (for Zoe), and service unregistration. + if __name__ == '__main__': print("Multicast DNS Service Discovery for Python, version", __version__) r = Zeroconf() diff --git a/src/calibre/utils/cleantext.py b/src/calibre/utils/cleantext.py index 7c86cbb4c5..6c4392427c 100644 --- a/src/calibre/utils/cleantext.py +++ b/src/calibre/utils/cleantext.py @@ -49,6 +49,7 @@ def allowed(x): def py_clean_xml_chars(unicode_string): return u''.join(filter(allowed, unicode_string)) + clean_xml_chars = native_clean_xml_chars or py_clean_xml_chars @@ -85,5 +86,4 @@ def unescape(text, rm=False, rchar=u''): if rm: return rchar # replace by char return text # leave as is - return re.sub("&#?\w+;", fixup, text) - + return re.sub("&#?\\w+;", fixup, text) diff --git a/src/calibre/utils/fonts/free_type.py b/src/calibre/utils/fonts/free_type.py index 1de12d1dd1..fc7c27b598 100644 --- a/src/calibre/utils/fonts/free_type.py +++ b/src/calibre/utils/fonts/free_type.py @@ -30,6 +30,7 @@ def same_thread(func): return func(self, *args, **kwargs) return check_thread + FreeTypeError = getattr(plugins['freetype'][0], 'FreeTypeError', Exception) @@ -80,5 +81,3 @@ class FreeType(object): @same_thread def load_font(self, data): return Face(self.ft.load_font(data)) - - diff --git a/src/calibre/utils/fonts/sfnt/metrics.py b/src/calibre/utils/fonts/sfnt/metrics.py index dcded27e76..792b64f072 100644 --- a/src/calibre/utils/fonts/sfnt/metrics.py +++ b/src/calibre/utils/fonts/sfnt/metrics.py @@ -113,6 +113,7 @@ class FontMetrics(object): 'The width of the string at the specified pixel size and stretch, in pixels' return sum(self.advance_widths(string, pixel_size, stretch)) + if __name__ == '__main__': import sys from calibre.utils.fonts.sfnt.container import Sfnt @@ -127,4 +128,3 @@ if __name__ == '__main__': print('AvgWidth:', m.pdf_avg_width) print('ItalicAngle', m.post.italic_angle) print('StemV', m.pdf_stemv) - diff --git a/src/calibre/utils/formatter_functions.py b/src/calibre/utils/formatter_functions.py index d7be115ed3..8c56154659 100644 --- a/src/calibre/utils/formatter_functions.py +++ b/src/calibre/utils/formatter_functions.py @@ -640,7 +640,7 @@ class BuiltinReGroup(BuiltinFormatterFunction): 'the template and the eval functions, you use [[ for { and ]] for }.' ' The following example in template program mode looks for series ' 'with more than one word and uppercases the first word: ' - "{series:'re_group($, \"(\S* )(.*)\", \"[[$:uppercase()]]\", \"[[$]]\")'}") + "{series:'re_group($, \"(\\S* )(.*)\", \"[[$:uppercase()]]\", \"[[$]]\")'}") def evaluate(self, formatter, kwargs, mi, locals, val, pattern, *args): from formatter import EvalFormatter @@ -924,9 +924,9 @@ class BuiltinSublist(BuiltinFormatterFunction): 'of zero is assumed to be the length of the list. Examples using ' 'basic template mode and assuming that the tags column (which is ' 'comma-separated) contains "A, B, C": ' - '{tags:sublist(0,1,\,)} returns "A". ' - '{tags:sublist(-1,0,\,)} returns "C". ' - '{tags:sublist(0,-1,\,)} returns "A, B".' + '{tags:sublist(0,1,\\,)} returns "A". ' + '{tags:sublist(-1,0,\\,)} returns "C". ' + '{tags:sublist(0,-1,\\,)} returns "A, B".' ) def evaluate(self, formatter, kwargs, mi, locals, val, start_index, end_index, sep): diff --git a/src/calibre/utils/inotify.py b/src/calibre/utils/inotify.py index 17548c65ec..728b0bb5b4 100644 --- a/src/calibre/utils/inotify.py +++ b/src/calibre/utils/inotify.py @@ -26,6 +26,7 @@ class DirTooLarge(ValueError): def __init__(self, bdir): ValueError.__init__(self, 'The directory {0} is too large to monitor. Try increasing the value in /proc/sys/fs/inotify/max_user_watches'.format(bdir)) + _inotify = None @@ -320,6 +321,7 @@ class INotifyTreeWatcher(INotify): self.modified = set() return ret + if __name__ == '__main__': w = INotifyTreeWatcher(sys.argv[-1]) w() diff --git a/src/calibre/utils/ipc/server.py b/src/calibre/utils/ipc/server.py index 176a2e0699..810fde9761 100644 --- a/src/calibre/utils/ipc/server.py +++ b/src/calibre/utils/ipc/server.py @@ -87,6 +87,7 @@ class ConnectedWorker(Thread): class CriticalError(Exception): pass + _name_counter = itertools.count() if islinux: @@ -384,4 +385,3 @@ class Server(Thread): def __exit__(self, *args): self.close() - diff --git a/src/calibre/utils/sftp.py b/src/calibre/utils/sftp.py index 32e7094acb..07a66917da 100644 --- a/src/calibre/utils/sftp.py +++ b/src/calibre/utils/sftp.py @@ -85,5 +85,6 @@ def main(args=sys.argv): f.close() return 0 + if __name__ == '__main__': sys.exit(main()) diff --git a/src/calibre/utils/threadpool.py b/src/calibre/utils/threadpool.py index 73a654ee01..9d6503173a 100644 --- a/src/calibre/utils/threadpool.py +++ b/src/calibre/utils/threadpool.py @@ -292,7 +292,7 @@ if __name__ == '__main__': # this will be called when an exception occurs within a thread def handle_exception(request, exc_info): - print("Exception occured in request #%s: %s" % \ + print("Exception occured in request #%s: %s" % (request.requestID, exc_info[1])) # assemble the arguments for each job to a list... diff --git a/src/calibre/utils/titlecase.py b/src/calibre/utils/titlecase.py index 465cc53db8..8155e586e0 100755 --- a/src/calibre/utils/titlecase.py +++ b/src/calibre/utils/titlecase.py @@ -15,7 +15,7 @@ from calibre.utils.icu import capitalize, upper __all__ = ['titlecase'] __version__ = '0.5' -SMALL = 'a|an|and|as|at|but|by|en|for|if|in|of|on|or|the|to|v\.?|via|vs\.?' +SMALL = 'a|an|and|as|at|but|by|en|for|if|in|of|on|or|the|to|v\\.?|via|vs\\.?' PUNCT = r"""!"#$%&'‘’()*+,\-‒–—―./:;?@[\\\]_`{|}~""" SMALL_WORDS = re.compile(r'^(%s)$' % SMALL, re.I) @@ -54,7 +54,7 @@ def titlecase(text): all_caps = upper(text) == text - words = re.split('\s+', text) + words = re.split('\\s+', text) line = [] for word in words: if all_caps: diff --git a/src/calibre/web/fetch/simple.py b/src/calibre/web/fetch/simple.py index 238ccfe049..453220522d 100644 --- a/src/calibre/web/fetch/simple.py +++ b/src/calibre/web/fetch/simple.py @@ -1,6 +1,5 @@ #!/usr/bin/env python2 -from __future__ import with_statement -from __future__ import print_function +from __future__ import with_statement, print_function __license__ = 'GPL v3' __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>' @@ -110,7 +109,7 @@ def default_is_link_wanted(url, tag): class RecursiveFetcher(object): LINK_FILTER = tuple(re.compile(i, re.IGNORECASE) for i in - ('.exe\s*$', '.mp3\s*$', '.ogg\s*$', '^\s*mailto:', '^\s*$')) + ('.exe\\s*$', '.mp3\\s*$', '.ogg\\s*$', '^\\s*mailto:', '^\\s*$')) # ADBLOCK_FILTER = tuple(re.compile(i, re.IGNORECASE) for it in # ( #