diff --git a/src/calibre/ebooks/conversion/preprocess.py b/src/calibre/ebooks/conversion/preprocess.py index 08a46cb8d9..56c3077118 100644 --- a/src/calibre/ebooks/conversion/preprocess.py +++ b/src/calibre/ebooks/conversion/preprocess.py @@ -360,7 +360,7 @@ class HTMLPreProcessor(object): (re.compile(r'((?<=)\s*file:////?[A-Z].*
|file:////?[A-Z].*
(?=\s*
))', re.IGNORECASE), lambda match: ''), # Center separator lines - (re.compile(u'
\s*(?P([*#•✦]+\s*)+)\s*
'), lambda match: '

\n

' + match.group(1) + '

'), + (re.compile(u'
\s*(?P([*#•✦=]+\s*)+)\s*
'), lambda match: '

\n

' + match.group(1) + '

'), # Remove page links (re.compile(r'', re.IGNORECASE), lambda match: ''), @@ -480,7 +480,7 @@ class HTMLPreProcessor(object): end_rules.append((re.compile(u'(?<=.{%i}[–—])\s*

\s*(?=[[a-z\d])' % length), lambda match: '')) end_rules.append( # Un wrap using punctuation - (re.compile(u'(?<=.{%i}([a-zäëïöüàèìòùáćéíóńśúâêîôûçąężıãõñæøþðß,:)\IA\u00DF]|(?)?\s*(

\s*

\s*)+\s*(?=(<(i|b|u)>)?\s*[\w\d$(])' % length, re.UNICODE), wrap_lines), + (re.compile(u'(?<=.{%i}([a-zäëïöüàèìòùáćéíóńśúâêîôûçąężıãõñæøþðßě,:)\IA\u00DF]|(?)?\s*(

\s*

\s*)+\s*(?=(<(i|b|u)>)?\s*[\w\d$(])' % length, re.UNICODE), wrap_lines), ) for rule in self.PREPROCESS + start_rules: diff --git a/src/calibre/ebooks/conversion/utils.py b/src/calibre/ebooks/conversion/utils.py index dac93fa2e2..7732bb2b4d 100644 --- a/src/calibre/ebooks/conversion/utils.py +++ b/src/calibre/ebooks/conversion/utils.py @@ -151,13 +151,13 @@ class PreProcessor(object): n_lookahead_open = "\s+(?!" n_lookahead_close = ")" - default_title = r"(<[ibu][^>]*>)?\s{0,3}([\w\'\"-]+\s{0,3}){1,5}?(]*>)?(?=<)" + default_title = r"(<[ibu][^>]*>)?\s{0,3}([\w\:\'\"-]+\s{0,3}){1,5}?(]*>)?(?=<)" chapter_types = [ [r"[^'\"]?(Introduction|Synopsis|Acknowledgements|Chapter|Kapitel|Epilogue|Volume\s|Prologue|Book\s|Part\s|Dedication|Preface)\s*([\d\w-]+\:?\'?\s*){0,5}", True, "Searching for common Chapter Headings"], + [r"([A-Z-]\s+){3,}\s*([\d\w-]+\s*){0,3}\s*", True, "Searching for letter spaced headings"], # Spaced Lettering [r"]*>\s*(]*>)?\s*(?!([*#•]+\s*)+)(\s*(?=[\d.\w#\-*\s]+<)([\d.\w#-*]+\s*){1,5}\s*)(?!\.)()?\s*", True, "Searching for emphasized lines"], # Emphasized lines [r"[^'\"]?(\d+(\.|:)|CHAPTER)\s*([\dA-Z\-\'\"#,]+\s*){0,7}\s*", True, "Searching for numeric chapter headings"], # Numeric Chapters - [r"([A-Z]\s+){3,}\s*([\d\w-]+\s*){0,3}\s*", True, "Searching for letter spaced headings"], # Spaced Lettering [r"[^'\"]?(\d+\.?\s+([\d\w-]+\:?\'?-?\s?){0,5})\s*", True, "Searching for numeric chapters with titles"], # Numeric Titles [r"[^'\"]?(\d+|CHAPTER)\s*([\dA-Z\-\'\"\?!#,]+\s*){0,7}\s*", True, "Searching for simple numeric chapter headings"], # Numeric Chapters, no dot or colon [r"\s*[^'\"]?([A-Z#]+(\s|-){0,3}){1,5}\s*", False, "Searching for chapters with Uppercase Characters" ] # Uppercase Chapters @@ -186,7 +186,7 @@ class PreProcessor(object): def punctuation_unwrap(self, length, content, format): # define the pieces of the regex - lookahead = "(?<=.{"+str(length)+"}([a-zäëïöüàèìòùáćéíóńśúâêîôûçąężıãõñæøþðß,:)\IA\u00DF]|(?\s*()?" blanklines = "\s*(?P<(p|span|div)[^>]*>\s*(<(p|span|div)[^>]*>\s*\s*)\s*){0,3}\s*" line_opening = "<(span|div|p)[^>]*>\s*(<(span|div|p)[^>]*>)?\s*" @@ -357,6 +357,6 @@ class PreProcessor(object): html = blankreg.sub('\n'+r'\g'+u'\u00a0'+r'\g', 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*()?\s*()?\s*()?\s*', '

' + '\g' + '

', html) + html = re.sub(u'<(?Pp|div)[^>]*>\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*(<(?Pfont|span|[ibu])[^>]*>)?\s*(?P([*#•=✦]+\s*)+)\s*()?\s*()?\s*()?\s*', '

' + '\g' + '

', html) return html