font|span|[ibu])[^>]*>)?\s*"
+ self.line_close = "((?P=inner3)>)?\s*((?P=inner2)>)?\s*((?P=inner1)>)?\s*(?P=outer)>"
+ self.single_blank = re.compile(r'(\s*]*>\s*
)', re.IGNORECASE)
+ self.scene_break_open = ''
def is_pdftohtml(self, src):
return '' in src[:1000]
@@ -187,19 +192,17 @@ class HeuristicProcessor(object):
# Build the Regular Expressions in pieces
init_lookahead = "(?=<(p|div))"
- chapter_line_open = "<(?Pp|div)[^>]*>\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*"
+ chapter_line_open = self.line_open
title_line_open = "<(?Pp|div)[^>]*>\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*"
chapter_header_open = r"(?P"
title_header_open = r"(?P"
chapter_header_close = ")\s*"
title_header_close = ")"
- chapter_line_close = "((?P=inner3)>)?\s*((?P=inner2)>)?\s*((?P=inner1)>)?\s*(?P=outer)>"
+ chapter_line_close = self.line_close
title_line_close = "((?P=inner6)>)?\s*((?P=inner5)>)?\s*((?P=inner4)>)?\s*(?P=outer2)>"
is_pdftohtml = self.is_pdftohtml(html)
if is_pdftohtml:
- chapter_line_open = "<(?Pp)[^>]*>(\s*<[ibu][^>]*>)?\s*"
- chapter_line_close = "\s*([ibu][^>]*>\s*)?(?P=outer)>"
title_line_open = "<(?Pp)[^>]*>\s*"
title_line_close = "\s*(?P=outer2)>"
@@ -374,13 +377,15 @@ class HeuristicProcessor(object):
html = re.sub(ur'\s*\s*', ' ', html)
# Delete microsoft 'smart' tags
html = re.sub('(?i)?st1:\w+>', '', html)
- # Delete self closing paragraph tags
- html = re.sub('', '', html)
+ # Re-open self closing paragraph tags
+ html = re.sub('/]*/>', '
', html)
# Get rid of empty span, bold, font, em, & italics tags
html = re.sub(r"\s*]*>\s*(]*>\s*){0,2}\s*\s*", " ", html)
html = re.sub(r"\s*<(font|[ibu]|em|strong)[^>]*>\s*(<(font|[ibu]|em|strong)[^>]*>\s*(font|[ibu]|em|strong)>\s*){0,2}\s*(font|[ibu]|em|strong)>", " ", html)
html = re.sub(r"\s*]*>\s*(]>\s*){0,2}\s*\s*", " ", html)
html = re.sub(r"\s*<(font|[ibu]|em|strong)[^>]*>\s*(<(font|[ibu]|em|strong)[^>]*>\s*(font|[ibu]|em|strong)>\s*){0,2}\s*(font|[ibu]|em|strong)>", " ", html)
+ # Empty heading tags
+ html = re.sub(r'(?i)\s*', '', html)
self.deleted_nbsps = True
return html
@@ -419,32 +424,98 @@ class HeuristicProcessor(object):
return True
return False
- def detect_blank_formatting(self, html):
- blanks_before_headings = re.compile(r'(\s*]*>\s*
){1,}(?=\s*)(\s*]*>\s*
){1,}', re.IGNORECASE)
-
- def markup_spacers(match):
- blanks = match.group(0)
- blanks = self.blankreg.sub('\n
', blanks)
- return blanks
- html = blanks_before_headings.sub(markup_spacers, html)
- html = blanks_after_headings.sub(markup_spacers, html)
+ def merge_blanks(self, html, blanks_count=None):
+ base_em = .5 # Baseline is 1.5em per blank line, 1st line is .5 em css and 1em for the nbsp
+ em_per_line = 1.5 # Add another 1.5 em for each additional blank
+
+ def merge_matches(match):
+ to_merge = match.group(0)
+ lines = float(len(self.single_blank.findall(to_merge))) - 1.
+ em = base_em + (em_per_line * lines)
+ if to_merge.find('whitespace'):
+ newline = self.any_multi_blank.sub('\n
', match.group(0))
+ else:
+ newline = self.any_multi_blank.sub('\n
', match.group(0))
+ return newline
+
+ html = self.any_multi_blank.sub(merge_matches, html)
+ return html
+
+ def detect_whitespace(self, html):
+ blanks_around_headings = re.compile(r'(?P(]*>\s*
\s*){1,}\s*)?(?P\d+)[^>]*>.*?)(?P\s*(]*>\s*
\s*){1,})?', re.IGNORECASE)
+ blanks_n_nopunct = re.compile(r'(?P(]*>\s*
\s*){1,}\s*)?]*>\s*(<(span|[ibu]|em|strong|font)[^>]*>\s*)*.{1,100}?[^\W]((span|[ibu]|em|strong|font)>\s*)*
(?P\s*(]*>\s*
\s*){1,})?', re.IGNORECASE)
+
+ def merge_header_whitespace(match):
+ initblanks = match.group('initparas')
+ endblanks = match.group('initparas')
+ heading = match.group('heading')
+ top_margin = ''
+ bottom_margin = ''
+ if initblanks is not None:
+ top_margin = 'margin-top:'+str(len(self.single_blank.findall(initblanks)))+'em;'
+ if endblanks is not None:
+ bottom_margin = 'margin-bottom:'+str(len(self.single_blank.findall(initblanks)))+'em;'
+
+ if initblanks == None and endblanks == None:
+ return heading
+ else:
+ heading = re.sub('(?i)\d+)[^>]*>', '\n\n'+' style="'+top_margin+bottom_margin+'">', heading)
+ return heading
+
+ html = blanks_around_headings.sub(merge_header_whitespace, html)
+
+ def markup_whitespaces(match):
+ blanks = match.group(0)
+ blanks = self.blankreg.sub('\n
', blanks)
+ return blanks
+
+ html = blanks_n_nopunct.sub(markup_whitespaces, html)
if self.html_preprocess_sections > self.min_chapters:
- html = re.sub('(?si)^.*?(?=
', html)
+ html = self.multi_blank.sub('\n
', html)
else:
- html = self.blankreg.sub('\n
', html)
+ html = self.blankreg.sub('\n
', html)
return html
+ def markup_user_break(self, replacement_break):
+ '''
+ Takes string a user supplies and wraps it in markup that will be centered with
+ appropriate margins.
and
tags are allowed. If the user specifies
+ a style with width attributes in the
tag then the appropriate margins are
+ applied to wrapping divs. This is because many ebook devices don't support margin:auto
+ All other html is converted to text.
+ '''
+ hr_open = ''
+ if re.findall('(<|>)', replacement_break):
+ if re.match('^
\d+).*', '\g', replacement_break))
+ divpercent = (100 - width) / 2
+ hr_open = re.sub('45', str(divpercent), hr_open)
+ scene_break = hr_open+replacement_break+''
+ else:
+ scene_break = hr_open+'
'
+ elif re.match('^
'
+ else:
+ from calibre.utils.html2text import html2text
+ replacement_break = html2text(replacement_break)
+ replacement_break = re.sub('\s', ' ', replacement_break)
+ scene_break = self.scene_break_open+replacement_break+''
+ else:
+ replacement_break = re.sub('\s', ' ', replacement_break)
+ scene_break = self.scene_break_open+replacement_break+''
+
+ return scene_break
def __call__(self, html):
self.log.debug("********* Heuristic processing HTML *********")
-
# Count the words in the document to estimate how many chapters to look for and whether
# other types of processing are attempted
try:
@@ -458,7 +529,7 @@ class HeuristicProcessor(object):
# Arrange line feeds and tags so the line_length and no_markup functions work correctly
html = self.arrange_htm_line_endings(html)
-
+ #self.dump(html, 'after_arrange_line_endings')
if self.cleanup_required():
###### Check Markup ######
#
@@ -478,6 +549,11 @@ class HeuristicProcessor(object):
# fix indents must run before this step, as it removes non-breaking spaces
html = self.cleanup_markup(html)
+ is_pdftohtml = self.is_pdftohtml(html)
+ if is_pdftohtml:
+ self.line_open = "<(?Pp)[^>]*>(\s*<[ibu][^>]*>)?\s*"
+ self.line_close = "\s*([ibu][^>]*>\s*)?(?P=outer)>"
+
# ADE doesn't render
, change to empty paragraphs
#html = re.sub('
]*>', u'\u00a0
', html)
@@ -489,6 +565,7 @@ class HeuristicProcessor(object):
if getattr(self.extra_opts, 'markup_chapter_headings', False):
html = self.markup_chapters(html, self.totalwords, self.blanks_between_paragraphs)
+ #self.dump(html, 'after_chapter_markup')
if getattr(self.extra_opts, 'italicize_common_cases', False):
html = self.markup_italicis(html)
@@ -498,7 +575,7 @@ class HeuristicProcessor(object):
if self.blanks_between_paragraphs and getattr(self.extra_opts, 'delete_blank_paragraphs', False):
self.log.debug("deleting blank lines")
self.blanks_deleted = True
- html = self.multi_blank.sub('\n
', html)
+ html = self.multi_blank.sub('\n
', html)
html = self.blankreg.sub('', html)
# Determine line ending type
@@ -539,7 +616,7 @@ class HeuristicProcessor(object):
if self.html_preprocess_sections < self.min_chapters and getattr(self.extra_opts, 'markup_chapter_headings', False):
self.log.debug("Looking for more split points based on punctuation,"
" currently have " + unicode(self.html_preprocess_sections))
- chapdetect3 = re.compile(r'<(?P(p|div)[^>]*)>\s*(?P(]*>)?\s*(?!([*#•]+\s*)+)(<[ibu][^>]*>){0,2}\s*(]*>)?\s*(<[ibu][^>]*>){0,2}\s*(]*>)?\s*.?(?=[a-z#\-*\s]+<)([a-z#-*]+\s*){1,5}\s*\s*()?([ibu]>){0,2}\s*()?\s*([ibu]>){0,2}\s*()?\s*(p|div)>)', re.IGNORECASE)
+ chapdetect3 = re.compile(r'<(?P(p|div)[^>]*)>\s*(?P(]*>)?\s*(?!([\W]+\s*)+)(<[ibu][^>]*>){0,2}\s*(]*>)?\s*(<[ibu][^>]*>){0,2}\s*(]*>)?\s*.?(?=[a-z#\-*\s]+<)([a-z#-*]+\s*){1,5}\s*\s*()?([ibu]>){0,2}\s*()?\s*([ibu]>){0,2}\s*()?\s*(p|div)>)', re.IGNORECASE)
html = chapdetect3.sub(self.chapter_break, html)
if getattr(self.extra_opts, 'renumber_headings', False):
@@ -549,14 +626,32 @@ class HeuristicProcessor(object):
doubleheading = re.compile(r'(?P]*>.+?\s*(<(?!h\d)[^>]*>\s*)*)[^>]*>.+?)', re.IGNORECASE)
html = doubleheading.sub('\g'+'\n'+'
', 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.
+ # Multiple sequential blank paragraphs are merged with appropriate margins
+ # If non-blank scene breaks exist they are center aligned and styled with appropriate margins.
if getattr(self.extra_opts, 'format_scene_breaks', False):
- html = self.detect_blank_formatting(html)
+ html = self.detect_whitespace(html)
html = self.detect_soft_breaks(html)
- # Center separator lines
- html = re.sub(u'<(?Pp|div)[^>]*>\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*(?P([*#•=✦]+\s*)+)\s*((?P=inner3)>)?\s*((?P=inner2)>)?\s*((?P=inner1)>)?\s*(?P=outer)>', '' + '\g' + '
', html)
- #html = re.sub(']*>\s*
', '
', html)
+ blanks_count = len(self.any_multi_blank.findall(html))
+ if blanks_count >= 1:
+ html = self.merge_blanks(html, blanks_count)
+ scene_break_regex = self.line_open+'(?![\w\'\"])(?P((?P((?!\s)\W))\s*(?P=break_char)?)+)\s*'+self.line_close
+ scene_break = re.compile(r'%s' % scene_break_regex, re.IGNORECASE|re.UNICODE)
+ # If the user has enabled scene break replacement, then either softbreaks
+ # or 'hard' scene breaks are replaced, depending on which is in use
+ # Otherwise separator lines are centered, use a bit larger margin in this case
+ replacement_break = getattr(self.extra_opts, 'replace_scene_breaks', None)
+ if replacement_break is not None:
+ replacement_break = self.markup_user_break(replacement_break)
+ if len(scene_break.findall(html)) >= 1:
+ html = scene_break.sub(replacement_break, html)
+ else:
+ html = re.sub(']*>\s*
', replacement_break, html)
+ else:
+ html = scene_break.sub(self.scene_break_open+'\g'+'', html)
if self.deleted_nbsps:
- # put back non-breaking spaces in empty paragraphs to preserve original formatting
+ # put back non-breaking spaces in empty paragraphs so they render correctly
html = self.anyblank.sub('\n'+r'\g'+u'\u00a0'+r'\g', html)
return html
diff --git a/src/calibre/gui2/convert/heuristics.py b/src/calibre/gui2/convert/heuristics.py
index e788888257..8ca4cab455 100644
--- a/src/calibre/gui2/convert/heuristics.py
+++ b/src/calibre/gui2/convert/heuristics.py
@@ -6,6 +6,7 @@ __docformat__ = 'restructuredtext en'
from PyQt4.Qt import Qt
+from calibre.gui2 import gprefs
from calibre.gui2.convert.heuristics_ui import Ui_Form
from calibre.gui2.convert import Widget
@@ -21,17 +22,35 @@ class HeuristicsWidget(Widget, Ui_Form):
['enable_heuristics', 'markup_chapter_headings',
'italicize_common_cases', 'fix_indents',
'html_unwrap_factor', 'unwrap_lines',
- 'delete_blank_paragraphs', 'format_scene_breaks',
+ 'delete_blank_paragraphs',
+ 'format_scene_breaks', 'replace_scene_breaks',
'dehyphenate', 'renumber_headings']
)
self.db, self.book_id = db, book_id
+ self.rssb_defaults = ['', '
', '* * *']
self.initialize_options(get_option, get_help, db, book_id)
+ self.load_histories()
+
self.opt_enable_heuristics.stateChanged.connect(self.enable_heuristics)
self.opt_unwrap_lines.stateChanged.connect(self.enable_unwrap)
self.enable_heuristics(self.opt_enable_heuristics.checkState())
+ def restore_defaults(self, get_option):
+ Widget.restore_defaults(self, get_option)
+
+ rssb_hist = gprefs['replace_scene_breaks_history']
+ for x in self.rssb_defaults:
+ if x in rssb_hist:
+ del rssb_hist[rssb_hist.index(x)]
+ gprefs['replace_scene_breaks_history'] = self.rssb_defaults + gprefs['replace_scene_breaks_history']
+
+ def commit_options(self, save_defaults=False):
+ self.save_histories()
+
+ return Widget.commit_options(self, save_defaults)
+
def break_cycles(self):
Widget.break_cycles(self)
@@ -45,6 +64,30 @@ class HeuristicsWidget(Widget, Ui_Form):
if val is None and g is self.opt_html_unwrap_factor:
g.setValue(0.0)
return True
+ if not val and g is self.opt_replace_scene_breaks:
+ g.lineEdit().setText('')
+ return True
+
+ def load_histories(self):
+ val = unicode(self.opt_replace_scene_breaks.currentText())
+ rssb_hist = gprefs.get('replace_scene_breaks_history', self.rssb_defaults)
+ if val in rssb_hist:
+ del rssb_hist[rssb_hist.index(val)]
+ rssb_hist.insert(0, val)
+ for v in rssb_hist:
+ # Ensure we don't have duplicate items.
+ if self.opt_replace_scene_breaks.findText(v) == -1:
+ self.opt_replace_scene_breaks.addItem(v)
+ self.opt_replace_scene_breaks.setCurrentIndex(0)
+
+ def save_histories(self):
+ rssb_history = []
+ history_pats = [unicode(self.opt_replace_scene_breaks.lineEdit().text())] + [unicode(self.opt_replace_scene_breaks.itemText(i)) for i in xrange(self.opt_replace_scene_breaks.count())]
+ for p in history_pats[:10]:
+ # Ensure we don't have duplicate items.
+ if p not in rssb_history:
+ rssb_history.append(p)
+ gprefs['replace_scene_breaks_history'] = rssb_history
def enable_heuristics(self, state):
state = state == Qt.Checked
diff --git a/src/calibre/gui2/convert/heuristics.ui b/src/calibre/gui2/convert/heuristics.ui
index 6863fcf8e6..46d62061af 100644
--- a/src/calibre/gui2/convert/heuristics.ui
+++ b/src/calibre/gui2/convert/heuristics.ui
@@ -150,6 +150,45 @@
+ -
+
+
+ QLayout::SetDefaultConstraint
+
+
-
+
+
+
+ 0
+ 0
+
+
+
+ Replace soft scene &breaks:
+
+
+ opt_replace_scene_breaks
+
+
+
+ -
+
+
+
+ 0
+ 0
+
+
+
+ true
+
+
+ QComboBox::InsertAtTop
+
+
+
+
+
-
diff --git a/src/calibre/manual/conversion.rst b/src/calibre/manual/conversion.rst
index 7f3ff21fe0..ecd8609ecc 100644
--- a/src/calibre/manual/conversion.rst
+++ b/src/calibre/manual/conversion.rst
@@ -311,10 +311,15 @@ remove all non-breaking-space entities, or may include false positive matches re
:guilabel:`Ensure scene breaks are consistently formatted`
With this option |app| will attempt to detect common scene-break markers and ensure that they are center aligned.
- It also attempts to detect scene breaks defined by white space and replace them with a horizontal rule 15% of the
- page width. Some readers may find this desirable as these 'soft' scene breaks often become page breaks on readers, and
- thus become difficult to distinguish.
+ 'Soft' scene break markers, i.e. scene breaks only defined by extra white space, are styled to ensure that they
+ will not be displayed in conjunction with page breaks.
+:guilabel:`Replace scene breaks`
+ If this option is configured then |app| will replace scene break markers it finds with the replacement text specified by the
+ user. In general you should avoid using html tags, |app| will discard any tags and use pre-defined markup.
+ tags, i.e. horizontal rules, are an exception. These can optionally be specified with styles, if you choose to add your own
+ style be sure to include the 'width' setting, otherwise the style information will be discarded.
+
:guilabel:`Remove unnecessary hyphens`
|app| will analyze all hyphenated content in the document when this option is enabled. The document itself is used
as a dictionary for analysis. This allows |app| to accurately remove hyphens for any words in the document in any language,
@@ -628,7 +633,7 @@ between 0 and 1. The default is 0.45, just under the median line length. Lower t
text in the unwrapping. Increase to include less. You can adjust this value in the conversion settings under :guilabel:`PDF Input`.
Also, they often have headers and footers as part of the document that will become included with the text.
-Use the options to remove headers and footers to mitigate this issue. If the headers and footers are not
+Use the Search and Replace panel to remove headers and footers to mitigate this issue. If the headers and footers are not
removed from the text it can throw off the paragraph unwrapping. To learn how to use the header and footer removal options, read
:ref:`regexptutorial`.