diff --git a/manual/conversion.rst b/manual/conversion.rst index 817821a9b1..bf451d0980 100644 --- a/manual/conversion.rst +++ b/manual/conversion.rst @@ -434,6 +434,18 @@ a number of older formats either do not support a metadata based Table of Conten documents do not have one. In these cases, the options in this section can help you automatically generate a Table of Contents in the converted ebook, based on the actual content in the input document. +.. note:: Using these options can be a little challenging to get exactly right. + If you prefer creating/editing the Table of Contents by hand, convert to + the EPUB or AZW3 formats and select the checkbox at the bottom of the + screen that says + :guilabel:`Manually fine-tune the Table of Contents after conversion`. + This will launch the ToC Editor tool after the conversion. It allows you to + create entries in the Table of Contents by simply clicking the place in the + book where you want the entry to point. You can also use the ToC Editor by + itself, without doing a conversion. Go to :guilabel:`Preferences->Toolbars` + and add the ToC Editor to the main toolbar. Then just select the book you + want to edit and click the ToC Editor button. + The first option is :guilabel:`Force use of auto-generated Table of Contents`. By checking this option you can have |app| override any Table of Contents found in the metadata of the input document with the auto generated one. @@ -456,7 +468,7 @@ For example, to remove all entries titles "Next" or "Previous" use:: Next|Previous -Finally, the :guilabel:`Level 1,2,3 TOC` options allow you to create a sophisticated multi-level Table of Contents. +The :guilabel:`Level 1,2,3 TOC` options allow you to create a sophisticated multi-level Table of Contents. They are XPath expressions that match tags in the intermediate XHTML produced by the conversion pipeline. See the :ref:`conversion-introduction` for how to get access to this XHTML. Also read the :ref:`xpath-tutorial`, to learn how to construct XPath expressions. Next to each option is a button that launches a wizard to help with the creation diff --git a/manual/faq.rst b/manual/faq.rst index ba11c865f3..7ef0f20a95 100644 --- a/manual/faq.rst +++ b/manual/faq.rst @@ -87,7 +87,9 @@ this bug. How do I convert a collection of HTML files in a specific order? ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -In order to convert a collection of HTML files in a specific oder, you have to create a table of contents file. That is, another HTML file that contains links to all the other files in the desired order. Such a file looks like:: +In order to convert a collection of HTML files in a specific oder, you have to +create a table of contents file. That is, another HTML file that contains links +to all the other files in the desired order. Such a file looks like:: @@ -102,18 +104,35 @@ In order to convert a collection of HTML files in a specific oder, you have to c -Then just add this HTML file to the GUI and use the convert button to create your ebook. +Then, just add this HTML file to the GUI and use the convert button to create +your ebook. You can use the option in the Table of Contents section in the +conversion dialog to control how the Table of Contents is generated. -.. note:: By default, when adding HTML files, |app| follows links in the files in *depth first* order. This means that if file A.html links to B.html and C.html and D.html, but B.html also links to D.html, then the files will be in the order A.html, B.html, D.html, C.html. If instead you want the order to be A.html, B.html, C.html, D.html then you must tell |app| to add your files in *breadth first* order. Do this by going to Preferences->Plugins and customizing the HTML to ZIP plugin. +.. note:: By default, when adding HTML files, |app| follows links in the files + in *depth first* order. This means that if file A.html links to B.html and + C.html and D.html, but B.html also links to D.html, then the files will be + in the order A.html, B.html, D.html, C.html. If instead you want the order + to be A.html, B.html, C.html, D.html then you must tell |app| to add your + files in *breadth first* order. Do this by going to Preferences->Plugins + and customizing the HTML to ZIP plugin. The EPUB I produced with |app| is not valid? ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -|app| does not guarantee that an EPUB produced by it is valid. The only guarantee it makes is that if you feed it valid XHTML 1.1 + CSS 2.1 it will output a valid EPUB. |app| is designed for ebook consumers, not producers. It tries hard to ensure that EPUBs it produces actually work as intended on a wide variety of devices, a goal that is incompatible with producing valid EPUBs, and one that is far more important to the vast majority of its users. If you need a tool that always produces valid EPUBs, |app| is not for you. +|app| does not guarantee that an EPUB produced by it is valid. The only +guarantee it makes is that if you feed it valid XHTML 1.1 + CSS 2.1 it will +output a valid EPUB. |app| is designed for ebook consumers, not producers. It +tries hard to ensure that EPUBs it produces actually work as intended on a wide +variety of devices, a goal that is incompatible with producing valid EPUBs, and +one that is far more important to the vast majority of its users. If you need a +tool that always produces valid EPUBs, |app| is not for you. How do I use some of the advanced features of the conversion tools? ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - You can get help on any individual feature of the converters by mousing over it in the GUI or running ``ebook-convert dummy.html .epub -h`` at a terminal. A good place to start is to look at the following demo files that demonstrate some of the advanced features: + You can get help on any individual feature of the converters by mousing over + it in the GUI or running ``ebook-convert dummy.html .epub -h`` at a terminal. + A good place to start is to look at the following demo files that demonstrate + some of the advanced features: * `html-demo.zip `_ @@ -126,11 +145,11 @@ Device Integration What devices does |app| support? ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -|app| can directly connect to all the major (and most of the minor) ebook reading devices, -smarthphones, tablets, etc. -In addition, using the :guilabel:`Connect to folder` function you can use it with any ebook reader that exports itself as a USB disk. -You can even connect to Apple devices (via iTunes), using the :guilabel:`Connect to iTunes` -function. +|app| can directly connect to all the major (and most of the minor) ebook +reading devices, smarthphones, tablets, etc. In addition, using the +:guilabel:`Connect to folder` function you can use it with any ebook reader +that exports itself as a USB disk. You can even connect to Apple devices (via +iTunes), using the :guilabel:`Connect to iTunes` function. .. _devsupport: diff --git a/recipes/eclipseonline.recipe b/recipes/eclipseonline.recipe new file mode 100644 index 0000000000..6d98120470 --- /dev/null +++ b/recipes/eclipseonline.recipe @@ -0,0 +1,38 @@ +from calibre.web.feeds.news import BasicNewsRecipe +class EclipseOnline(BasicNewsRecipe): + + # + # oldest_article specifies the maximum age, in days, of posts to retrieve. + # The default of 32 is intended to work well with a "days of month = 1" + # recipe schedule to download "monthly issues" of Eclipse Online. + # Increase this value to include additional posts. However, the RSS feed + # currently only includes the 10 most recent posts, so that's the max. + # + oldest_article = 32 + + title = u'Eclipse Online' + description = u'"Where strange and wonderful things happen, where reality is eclipsed for a little while with something magical and new." Eclipse Online is edited by Jonathan Strahan and published online by Night Shade Books. http://www.nightshadebooks.com/category/eclipse/' + publication_type = 'magazine' + language = 'en' + + __author__ = u'Jim DeVona' + __version__ = '1.0' + + # For now, use this Eclipse Online logo as the ebook cover image. + # (Disable the cover_url line to let Calibre generate a default cover, including date.) + cover_url = 'http://www.nightshadebooks.com/wp-content/uploads/2012/10/Eclipse-Logo.jpg' + + # Extract the "post" div containing the story (minus redundant metadata) from each page. + keep_only_tags = [dict(name='div', attrs={'class':lambda x: x and 'post' in x})] + remove_tags = [dict(name='span', attrs={'class': ['post-author', 'post-category', 'small']})] + + # Nice plain markup (like Eclipse's) works best for most e-readers. + # Disregard any special styling rules, but center illustrations. + auto_cleanup = False + no_stylesheets = True + remove_attributes = ['style', 'align'] + extra_css = '.wp-caption {text-align: center;} .wp-caption-text {font-size: small; font-style: italic;}' + + # Tell Calibre where to look for article links. It will proceed to retrieve + # these posts and format them into an ebook according to the above rules. + feeds = ['http://www.nightshadebooks.com/category/eclipse/feed/'] diff --git a/recipes/hindu.recipe b/recipes/hindu.recipe index 74c0d6539a..82cef40e1f 100644 --- a/recipes/hindu.recipe +++ b/recipes/hindu.recipe @@ -2,7 +2,6 @@ __license__ = 'GPL 3' __copyright__ = '2009, Kovid Goyal ' -import time from calibre.web.feeds.news import BasicNewsRecipe class TheHindu(BasicNewsRecipe): @@ -14,44 +13,42 @@ class TheHindu(BasicNewsRecipe): max_articles_per_feed = 100 no_stylesheets = True - keep_only_tags = [dict(id='content')] - remove_tags = [dict(attrs={'class':['article-links', 'breadcr']}), - dict(id=['email-section', 'right-column', 'printfooter', 'topover', - 'slidebox', 'th_footer'])] + auto_cleanup = True + extra_css = '.photo-caption { font-size: smaller }' - def preprocess_raw_html(self, raw, url): - return raw.replace('

', '

').replace('

', '

') - - def postprocess_html(self, soup, first_fetch): - for t in soup.findAll(['table', 'tr', 'td','center']): - t.name = 'div' - return soup - def parse_index(self): - today = time.strftime('%Y-%m-%d') - soup = self.index_to_soup( - 'http://www.thehindu.com/todays-paper/tp-index/?date=' + today) - div = soup.find(id='left-column') - feeds = [] + soup = self.index_to_soup('http://www.thehindu.com/todays-paper/') + div = soup.find('div', attrs={'id':'left-column'}) + soup.find(id='subnav-tpbar').extract() + + + current_section = None current_articles = [] - for x in div.findAll(['h3', 'div']): - if current_section and x.get('class', '') == 'tpaper': - a = x.find('a', href=True) - if a is not None: - title = self.tag_to_string(a) - self.log('\tFound article:', title) - current_articles.append({'url':a['href']+'?css=print', - 'title':title, 'date': '', - 'description':''}) - if x.name == 'h3': - if current_section and current_articles: + feeds = [] + for x in div.findAll(['a', 'span']): + if x.name == 'span' and x['class'] == 's-link': + # Section heading found + if current_articles and current_section: feeds.append((current_section, current_articles)) current_section = self.tag_to_string(x) - self.log('Found section:', current_section) current_articles = [] + self.log('\tFound section:', current_section) + elif x.name == 'a': + + title = self.tag_to_string(x) + url = x.get('href', False) + if not url or not title: + continue + self.log('\t\tFound article:', title) + self.log('\t\t\t', url) + current_articles.append({'title': title, 'url':url, + 'description':'', 'date':''}) + + if current_articles and current_section: + feeds.append((current_section, current_articles)) + return feeds - diff --git a/recipes/interia_fakty.recipe b/recipes/interia_fakty.recipe index baedd35d0c..053a264e7e 100644 --- a/recipes/interia_fakty.recipe +++ b/recipes/interia_fakty.recipe @@ -5,7 +5,7 @@ ''' fakty.interia.pl ''' - +import re from calibre.web.feeds.news import BasicNewsRecipe class InteriaFakty(BasicNewsRecipe): diff --git a/recipes/irish_times.recipe b/recipes/irish_times.recipe index 31ccd306e4..075d3dd4dd 100644 --- a/recipes/irish_times.recipe +++ b/recipes/irish_times.recipe @@ -1,65 +1,62 @@ __license__ = 'GPL v3' -__copyright__ = "2008, Derry FitzGerald. 2009 Modified by Ray Kinsella and David O'Callaghan, 2011 Modified by Phil Burns" +__copyright__ = "2008, Derry FitzGerald. 2009 Modified by Ray Kinsella and David O'Callaghan, 2011 Modified by Phil Burns, 2013 Tom Scholl" ''' irishtimes.com ''' -import re +import urlparse, re from calibre.web.feeds.news import BasicNewsRecipe +from calibre.ptempfile import PersistentTemporaryFile + class IrishTimes(BasicNewsRecipe): title = u'The Irish Times' - encoding = 'ISO-8859-15' - __author__ = "Derry FitzGerald, Ray Kinsella, David O'Callaghan and Phil Burns" + __author__ = "Derry FitzGerald, Ray Kinsella, David O'Callaghan and Phil Burns, Tom Scholl" language = 'en_IE' - timefmt = ' (%A, %B %d, %Y)' + masthead_url = 'http://www.irishtimes.com/assets/images/generic/website/logo_theirishtimes.png' + encoding = 'utf-8' oldest_article = 1.0 - max_articles_per_feed = 100 + max_articles_per_feed = 100 + remove_empty_feeds = True no_stylesheets = True - simultaneous_downloads= 5 - - r = re.compile('.*(?Phttp:\/\/(www.irishtimes.com)|(rss.feedsportal.com\/c)\/.*\.html?).*') - remove_tags = [dict(name='div', attrs={'class':'footer'})] - extra_css = 'p, div { margin: 0pt; border: 0pt; text-indent: 0.5em } .headline {font-size: large;} \n .fact { padding-top: 10pt }' + temp_files = [] + articles_are_obfuscated = True feeds = [ - ('Frontpage', 'http://www.irishtimes.com/feeds/rss/newspaper/index.rss'), - ('Ireland', 'http://www.irishtimes.com/feeds/rss/newspaper/ireland.rss'), - ('World', 'http://www.irishtimes.com/feeds/rss/newspaper/world.rss'), - ('Finance', 'http://www.irishtimes.com/feeds/rss/newspaper/finance.rss'), - ('Features', 'http://www.irishtimes.com/feeds/rss/newspaper/features.rss'), - ('Sport', 'http://www.irishtimes.com/feeds/rss/newspaper/sport.rss'), - ('Opinion', 'http://www.irishtimes.com/feeds/rss/newspaper/opinion.rss'), - ('Letters', 'http://www.irishtimes.com/feeds/rss/newspaper/letters.rss'), - ('Magazine', 'http://www.irishtimes.com/feeds/rss/newspaper/magazine.rss'), - ('Health', 'http://www.irishtimes.com/feeds/rss/newspaper/health.rss'), - ('Education & Parenting', 'http://www.irishtimes.com/feeds/rss/newspaper/education.rss'), - ('Motors', 'http://www.irishtimes.com/feeds/rss/newspaper/motors.rss'), - ('An Teanga Bheo', 'http://www.irishtimes.com/feeds/rss/newspaper/anteangabheo.rss'), - ('Commercial Property', 'http://www.irishtimes.com/feeds/rss/newspaper/commercialproperty.rss'), - ('Science Today', 'http://www.irishtimes.com/feeds/rss/newspaper/sciencetoday.rss'), - ('Property', 'http://www.irishtimes.com/feeds/rss/newspaper/property.rss'), - ('The Tickets', 'http://www.irishtimes.com/feeds/rss/newspaper/theticket.rss'), - ('Weekend', 'http://www.irishtimes.com/feeds/rss/newspaper/weekend.rss'), - ('News features', 'http://www.irishtimes.com/feeds/rss/newspaper/newsfeatures.rss'), - ('Obituaries', 'http://www.irishtimes.com/feeds/rss/newspaper/obituaries.rss'), + ('News', 'http://www.irishtimes.com/cmlink/the-irish-times-news-1.1319192'), + ('World', 'http://www.irishtimes.com/cmlink/irishtimesworldfeed-1.1321046'), + ('Politics', 'http://www.irishtimes.com/cmlink/irish-times-politics-rss-1.1315953'), + ('Business', 'http://www.irishtimes.com/cmlink/the-irish-times-business-1.1319195'), + ('Culture', 'http://www.irishtimes.com/cmlink/the-irish-times-culture-1.1319213'), + ('Sport', 'http://www.irishtimes.com/cmlink/the-irish-times-sport-1.1319194'), + ('Debate', 'http://www.irishtimes.com/cmlink/debate-1.1319211'), + ('Life & Style', 'http://www.irishtimes.com/cmlink/the-irish-times-life-style-1.1319214'), ] - def print_version(self, url): - if url.count('rss.feedsportal.com'): - #u = url.replace('0Bhtml/story01.htm','_pf0Bhtml/story01.htm') - u = url.find('irishtimes') - u = 'http://www.irishtimes.com' + url[u + 12:] - u = u.replace('0C', '/') - u = u.replace('A', '') - u = u.replace('0Bhtml/story01.htm', '_pf.html') - else: - u = url.replace('.html','_pf.html') - return u + def get_obfuscated_article(self, url): + # Insert a pic from the original url, but use content from the print url + pic = None + pics = self.index_to_soup(url) + div = pics.find('div', {'class' : re.compile('image-carousel')}) + if div: + pic = div.img + if pic: + try: + pic['src'] = urlparse.urljoin(url, pic['src']) + pic.extract() + except: + pic = None + + content = self.index_to_soup(url + '?mode=print&ot=example.AjaxPageLayout.ot') + if pic: + content.p.insert(0, pic) + + self.temp_files.append(PersistentTemporaryFile('_fa.html')) + self.temp_files[-1].write(content.prettify()) + self.temp_files[-1].close() + return self.temp_files[-1].name - def get_article_url(self, article): - return article.link diff --git a/recipes/ledevoir.recipe b/recipes/ledevoir.recipe index 6208229386..723f0360c6 100644 --- a/recipes/ledevoir.recipe +++ b/recipes/ledevoir.recipe @@ -2,7 +2,7 @@ __author__ = 'Lorenzo Vigentini and Olivier Daigle' __copyright__ = '2012, Lorenzo Vigentini , Olivier Daigle ' __version__ = 'v1.01' -__date__ = '22, December 2012' +__date__ = '17, March 2013' __description__ = 'Canadian Paper ' ''' @@ -12,6 +12,7 @@ import re from calibre.web.feeds.news import BasicNewsRecipe +from calibre.utils.magick import Image class ledevoir(BasicNewsRecipe): author = 'Lorenzo Vigentini' @@ -28,10 +29,14 @@ class ledevoir(BasicNewsRecipe): oldest_article = 1 max_articles_per_feed = 200 + min_articles_per_feed = 0 use_embedded_content = False recursion = 10 needs_subscription = 'optional' + compress_news_images = True + compress_news_images_auto_size = 4 + filterDuplicates = False url_list = [] @@ -66,16 +71,16 @@ class ledevoir(BasicNewsRecipe): feeds = [ (u'A la une', 'http://www.ledevoir.com/rss/manchettes.xml'), -# (u'Édition complete', 'http://feeds2.feedburner.com/fluxdudevoir'), -# (u'Opinions', 'http://www.ledevoir.com/rss/opinions.xml'), -# (u'Chroniques', 'http://www.ledevoir.com/rss/chroniques.xml'), -# (u'Politique', 'http://www.ledevoir.com/rss/section/politique.xml?id=51'), -# (u'International', 'http://www.ledevoir.com/rss/section/international.xml?id=76'), -# (u'Culture', 'http://www.ledevoir.com/rss/section/culture.xml?id=48'), -# (u'Environnement', 'http://www.ledevoir.com/rss/section/environnement.xml?id=78'), -# (u'Societe', 'http://www.ledevoir.com/rss/section/societe.xml?id=52'), -# (u'Economie', 'http://www.ledevoir.com/rss/section/economie.xml?id=49'), -# (u'Sports', 'http://www.ledevoir.com/rss/section/sports.xml?id=85'), + (u'Édition complete', 'http://feeds2.feedburner.com/fluxdudevoir'), + (u'Opinions', 'http://www.ledevoir.com/rss/opinions.xml'), + (u'Chroniques', 'http://www.ledevoir.com/rss/chroniques.xml'), + (u'Politique', 'http://www.ledevoir.com/rss/section/politique.xml?id=51'), + (u'International', 'http://www.ledevoir.com/rss/section/international.xml?id=76'), + (u'Culture', 'http://www.ledevoir.com/rss/section/culture.xml?id=48'), + (u'Environnement', 'http://www.ledevoir.com/rss/section/environnement.xml?id=78'), + (u'Societe', 'http://www.ledevoir.com/rss/section/societe.xml?id=52'), + (u'Economie', 'http://www.ledevoir.com/rss/section/economie.xml?id=49'), + (u'Sports', 'http://www.ledevoir.com/rss/section/sports.xml?id=85'), (u'Art de vivre', 'http://www.ledevoir.com/rss/section/art-de-vivre.xml?id=50') ] @@ -113,3 +118,23 @@ def print_version(self, url): self.url_list.append(url) return url +''' + def postprocess_html(self, soup, first): + #process all the images. assumes that the new html has the correct path + if first == 0: + return soup + + for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')): + iurl = tag['src'] + img = Image() + img.open(iurl) + # width, height = img.size + # print 'img is: ', iurl, 'width is: ', width, 'height is: ', height + if img < 0: + raise RuntimeError('Out of memory') + img.set_compression_quality(30) + img.save(iurl) + return soup +''' + + \ No newline at end of file diff --git a/src/calibre/db/tests/writing.py b/src/calibre/db/tests/writing.py index 875329558b..de40052c9b 100644 --- a/src/calibre/db/tests/writing.py +++ b/src/calibre/db/tests/writing.py @@ -252,7 +252,21 @@ def test_many_many_basic(self): # {{{ ae(cache.field_for('author_sort', 1), 'GoyaL, KoviD') ae(cache.field_for('author_sort', 3), 'GoyaL, KoviD & Layog, Divok') - # TODO: identifiers, languages + # Languages + f = cache.fields['languages'] + ae(f.table.id_map, {1: 'eng', 2: 'deu'}) + ae(sf('languages', {1:''}), set([1])) + ae(cache.field_for('languages', 1), ()) + ae(sf('languages', {2:('und',)}), set([2])) + af(f.table.id_map) + ae(sf('languages', {1:'eng,fra,deu', 2:'es,Dutch', 3:'English'}), {1, 2, 3}) + ae(cache.field_for('languages', 1), ('eng', 'fra', 'deu')) + ae(cache.field_for('languages', 2), ('spa', 'nld')) + ae(cache.field_for('languages', 3), ('eng',)) + ae(sf('languages', {3:None}), set([3])) + ae(cache.field_for('languages', 3), ()) + + # TODO: identifiers # }}} diff --git a/src/calibre/db/write.py b/src/calibre/db/write.py index e558c95fe5..764be65900 100644 --- a/src/calibre/db/write.py +++ b/src/calibre/db/write.py @@ -15,6 +15,7 @@ from calibre.ebooks.metadata import author_to_author_sort from calibre.utils.date import (parse_only_date, parse_date, UNDEFINED_DATE, isoformat) +from calibre.utils.localization import canonicalize_lang from calibre.utils.icu import strcmp if ispy3: @@ -96,6 +97,15 @@ def adapt_bool(x): x = bool(int(x)) return x if x is None else bool(x) +def adapt_languages(to_tuple, x): + ans = [] + for lang in to_tuple(x): + lc = canonicalize_lang(lang) + if not lc or lc in ans or lc in ('und', 'zxx', 'mis', 'mul'): + continue + ans.append(lc) + return tuple(ans) + def get_adapter(name, metadata): dt = metadata['datatype'] if dt == 'text': @@ -133,6 +143,8 @@ def get_adapter(name, metadata): return lambda x: ans(x) or UNDEFINED_DATE if name == 'series_index': return lambda x: 1.0 if ans(x) is None else ans(x) + if name == 'languages': + return partial(adapt_languages, ans) return ans # }}} diff --git a/src/calibre/gui2/actions/convert.py b/src/calibre/gui2/actions/convert.py index 68415db748..c5e1580c6d 100644 --- a/src/calibre/gui2/actions/convert.py +++ b/src/calibre/gui2/actions/convert.py @@ -167,8 +167,8 @@ def do_convert(self, book_ids, bulk=None): def queue_convert_jobs(self, jobs, changed, bad, rows, previous, converted_func, extra_job_args=[], rows_are_ids=False): for func, args, desc, fmt, id, temp_files in jobs: - func, _, same_fmt = func.partition(':') - same_fmt = same_fmt == 'same_fmt' + func, _, parts = func.partition(':') + parts = {x for x in parts.split(';')} input_file = args[0] input_fmt = os.path.splitext(input_file)[1] core_usage = 1 @@ -182,7 +182,8 @@ def queue_convert_jobs(self, jobs, changed, bad, rows, previous, job = self.gui.job_manager.run_job(Dispatcher(converted_func), func, args=args, description=desc, core_usage=core_usage) - job.conversion_of_same_fmt = same_fmt + job.conversion_of_same_fmt = 'same_fmt' in parts + job.manually_fine_tune_toc = 'manually_fine_tune_toc' in parts args = [temp_files, fmt, id]+extra_job_args self.conversion_jobs[job] = tuple(args) @@ -223,6 +224,7 @@ def book_converted(self, job): self.gui.job_exception(job) return same_fmt = getattr(job, 'conversion_of_same_fmt', False) + manually_fine_tune_toc = getattr(job, 'manually_fine_tune_toc', False) fmtf = temp_files[-1].name if os.stat(fmtf).st_size < 1: raise Exception(_('Empty output file, ' @@ -248,4 +250,7 @@ def book_converted(self, job): current = self.gui.library_view.currentIndex() if current.isValid(): self.gui.library_view.model().current_changed(current, QModelIndex()) + if manually_fine_tune_toc: + self.gui.iactions['Edit ToC'].do_one(book_id, fmt.upper()) + diff --git a/src/calibre/gui2/convert/bulk.py b/src/calibre/gui2/convert/bulk.py index 213f23ced2..b1c3de122b 100644 --- a/src/calibre/gui2/convert/bulk.py +++ b/src/calibre/gui2/convert/bulk.py @@ -88,6 +88,7 @@ def widget_factory(cls): ps = widget_factory(PageSetupWidget) sd = widget_factory(StructureDetectionWidget) toc = widget_factory(TOCWidget) + toc.manually_fine_tune_toc.hide() output_widget = self.plumber.output_plugin.gui_configuration_widget( self.stack, self.plumber.get_option_by_name, diff --git a/src/calibre/gui2/convert/single.py b/src/calibre/gui2/convert/single.py index cff7ee8c3d..469091162b 100644 --- a/src/calibre/gui2/convert/single.py +++ b/src/calibre/gui2/convert/single.py @@ -165,6 +165,12 @@ def input_format(self): def output_format(self): return unicode(self.output_formats.currentText()).lower() + @property + def manually_fine_tune_toc(self): + for i in xrange(self.stack.count()): + w = self.stack.widget(i) + if hasattr(w, 'manually_fine_tune_toc'): + return w.manually_fine_tune_toc.isChecked() def setup_pipeline(self, *args): oidx = self.groups.currentIndex().row() @@ -191,6 +197,8 @@ def widget_factory(cls): ps = widget_factory(PageSetupWidget) sd = widget_factory(StructureDetectionWidget) toc = widget_factory(TOCWidget) + from calibre.gui2.actions.toc_edit import SUPPORTED + toc.manually_fine_tune_toc.setVisible(output_format.upper() in SUPPORTED) debug = widget_factory(DebugWidget) output_widget = self.plumber.output_plugin.gui_configuration_widget( diff --git a/src/calibre/gui2/convert/toc.ui b/src/calibre/gui2/convert/toc.ui index da15551f80..6140816804 100644 --- a/src/calibre/gui2/convert/toc.ui +++ b/src/calibre/gui2/convert/toc.ui @@ -6,22 +6,32 @@ 0 0 - 436 - 382 + 596 + 493 Form + + + + + + &Force use of auto-generated Table of Contents + + + + Do not add &detected chapters to the Table of Contents - + Number of &links to add to Table of Contents @@ -31,34 +41,7 @@ - - - - 10000 - - - - - - - Chapter &threshold - - - opt_toc_threshold - - - - - - - - - - &Force use of auto-generated Table of Contents - - - - + TOC &Filter: @@ -68,19 +51,27 @@ - - - - - - - - - - + - + + + + 10000 + + + + + + + Chapter &threshold + + + opt_toc_threshold + + + + Qt::Vertical @@ -93,13 +84,47 @@ - + Allow &duplicate links when creating the Table of Contents + + + + + + + + + + + + + <a href="http://manual.calibre-ebook.com/conversion.html#table-of-contents">Help with using these options to generate a Table of Contents</a> + + + true + + + true + + + + + + + This option will cause calibre to popup the Table of Contents Editor tool, + which will allow you to manually edit the Table of Contents, to fix any errors + caused by automatic generation. + + + &Manually fine-tune the ToC after conversion is completed + + + diff --git a/src/calibre/gui2/dialogs/book_info.py b/src/calibre/gui2/dialogs/book_info.py index b3ff2e03fd..284d17a349 100644 --- a/src/calibre/gui2/dialogs/book_info.py +++ b/src/calibre/gui2/dialogs/book_info.py @@ -5,7 +5,7 @@ from PyQt4.Qt import (QCoreApplication, SIGNAL, QModelIndex, QTimer, Qt, - QDialog, QPixmap, QIcon, QSize, QPalette) + QDialog, QPixmap, QIcon, QSize, QPalette, QShortcut, QKeySequence) from calibre.gui2.dialogs.book_info_ui import Ui_BookInfo from calibre.gui2 import dynamic @@ -43,6 +43,14 @@ def __init__(self, parent, view, row, link_delegate): self.fit_cover.stateChanged.connect(self.toggle_cover_fit) self.cover.resizeEvent = self.cover_view_resized self.cover.cover_changed.connect(self.cover_changed) + self.ns = QShortcut(QKeySequence('Alt+Right'), self) + self.ns.activated.connect(self.next) + self.ps = QShortcut(QKeySequence('Alt+Left'), self) + self.ps.activated.connect(self.previous) + self.next_button.setToolTip(_('Next [%s]')% + unicode(self.ns.key().toString(QKeySequence.NativeText))) + self.previous_button.setToolTip(_('Previous [%s]')% + unicode(self.ps.key().toString(QKeySequence.NativeText))) desktop = QCoreApplication.instance().desktop() screen_height = desktop.availableGeometry().height() - 100 diff --git a/src/calibre/gui2/email.py b/src/calibre/gui2/email.py index f4164befe6..9ebb94b00a 100644 --- a/src/calibre/gui2/email.py +++ b/src/calibre/gui2/email.py @@ -160,7 +160,7 @@ def email_news(mi, remove, get_fmts, done, job_manager): return sent_mails plugboard_email_value = 'email' -plugboard_email_formats = ['epub', 'mobi'] +plugboard_email_formats = ['epub', 'mobi', 'azw3'] class EmailMixin(object): # {{{ diff --git a/src/calibre/gui2/preferences/conversion.py b/src/calibre/gui2/preferences/conversion.py index a15ee0a750..6c9e1f8f5b 100644 --- a/src/calibre/gui2/preferences/conversion.py +++ b/src/calibre/gui2/preferences/conversion.py @@ -61,6 +61,8 @@ def widget_factory(cls): for w in widgets: w.changed_signal.connect(self.changed_signal) self.stack.addWidget(w) + if isinstance(w, TOCWidget): + w.manually_fine_tune_toc.hide() self.list.currentChanged = self.category_current_changed self.list.setCurrentIndex(self.model.index(0)) diff --git a/src/calibre/gui2/toc/location.py b/src/calibre/gui2/toc/location.py index ec10ec7c5f..28268d0998 100644 --- a/src/calibre/gui2/toc/location.py +++ b/src/calibre/gui2/toc/location.py @@ -11,10 +11,11 @@ from PyQt4.Qt import (QWidget, QGridLayout, QListWidget, QSize, Qt, QUrl, pyqtSlot, pyqtSignal, QVBoxLayout, QFrame, QLabel, - QLineEdit, QTimer) + QLineEdit, QTimer, QPushButton, QIcon) from PyQt4.QtWebKit import QWebView, QWebPage, QWebElement from calibre.ebooks.oeb.display.webview import load_html +from calibre.gui2 import error_dialog, question_dialog from calibre.utils.logging import default_log class Page(QWebPage): # {{{ @@ -115,16 +116,26 @@ def __init__(self, parent): self.dest_list = dl = QListWidget(self) dl.setMinimumWidth(250) dl.currentItemChanged.connect(self.current_changed) - l.addWidget(dl, 1, 0) + l.addWidget(dl, 1, 0, 2, 1) self.view = WebView(self) self.view.elem_clicked.connect(self.elem_clicked) - l.addWidget(self.view, 1, 1) + l.addWidget(self.view, 1, 1, 1, 3) self.f = f = QFrame() f.setFrameShape(f.StyledPanel) f.setMinimumWidth(250) - l.addWidget(f, 1, 2) + l.addWidget(f, 1, 4, 2, 1) + self.search_text = s = QLineEdit(self) + s.setPlaceholderText(_('Search for text...')) + l.addWidget(s, 2, 1, 1, 1) + self.ns_button = b = QPushButton(QIcon(I('arrow-down.png')), _('Find &next'), self) + b.clicked.connect(self.find_next) + l.addWidget(b, 2, 2, 1, 1) + self.ps_button = b = QPushButton(QIcon(I('arrow-up.png')), _('Find &previous'), self) + l.addWidget(b, 2, 3, 1, 1) + b.clicked.connect(self.find_previous) + l.setRowStretch(1, 10) l = f.l = QVBoxLayout() f.setLayout(l) @@ -156,6 +167,42 @@ def __init__(self, parent): l.addStretch() + def keyPressEvent(self, ev): + if ev.key() in (Qt.Key_Return, Qt.Key_Enter) and self.search_text.hasFocus(): + # Prevent pressing enter in the search box from triggering the dialog's accept() method + ev.accept() + return + return super(ItemEdit, self).keyPressEvent(ev) + + def find(self, forwards=True): + text = unicode(self.search_text.text()).strip() + flags = QWebPage.FindFlags(0) if forwards else QWebPage.FindBackward + d = self.dest_list + if d.count() == 1: + flags |= QWebPage.FindWrapsAroundDocument + if not self.view.findText(text, flags) and text: + if d.count() == 1: + return error_dialog(self, _('No match found'), + _('No match found for: %s')%text, show=True) + + delta = 1 if forwards else -1 + current = unicode(d.currentItem().data(Qt.DisplayRole).toString()) + next_index = (d.currentRow() + delta)%d.count() + next = unicode(d.item(next_index).data(Qt.DisplayRole).toString()) + msg = '

'+_('No matches for %(text)s found in the current file [%(current)s].' + ' Do you want to search in the %(which)s file [%(next)s]?') + msg = msg%dict(text=text, current=current, next=next, + which=_('next') if forwards else _('previous')) + if question_dialog(self, _('No match found'), msg): + self.pending_search = self.find_next if forwards else self.find_previous + d.setCurrentRow(next_index) + + def find_next(self): + return self.find() + + def find_previous(self): + return self.find(forwards=False) + def load(self, container): self.container = container spine_names = [container.abspath_to_name(p) for p in @@ -175,6 +222,10 @@ def current_changed(self, item): self.view.load_js() self.dest_label.setText(self.base_msg + '
' + _('File:') + ' ' + name + '
' + _('Top of the file')) + if hasattr(self, 'pending_search'): + f = self.pending_search + del self.pending_search + f() def __call__(self, item, where): self.current_item, self.current_where = item, where diff --git a/src/calibre/gui2/tools.py b/src/calibre/gui2/tools.py index 98a59ccdd5..eda60a4fec 100644 --- a/src/calibre/gui2/tools.py +++ b/src/calibre/gui2/tools.py @@ -82,8 +82,13 @@ def convert_single_ebook(parent, db, book_ids, auto_conversion=False, # {{{ args = [in_file.name, out_file.name, recs] temp_files.append(out_file) func = 'gui_convert_override' + parts = [] + if not auto_conversion and d.manually_fine_tune_toc: + parts.append('manually_fine_tune_toc') if same_fmt: - func += ':same_fmt' + parts.append('same_fmt') + if parts: + func += ':%s'%(';'.join(parts)) jobs.append((func, args, desc, d.output_format.upper(), book_id, temp_files)) changed = True