X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/5f92f5a341c58a30c0a5c0d64ba3ed498bb9db85..6b75d94412c089b10bd7637b1008bdaf9057a440:/librarian/epub.py?ds=sidebyside diff --git a/librarian/epub.py b/librarian/epub.py index bf58a9f..9e7010a 100644 --- a/librarian/epub.py +++ b/librarian/epub.py @@ -51,19 +51,21 @@ def set_hyph_language(source_tree): def hyphenate_and_fix_conjunctions(source_tree, hyph): - if hyph is not None: - texts = etree.XPath('/utwor/*[2]//text()')(source_tree) - for t in texts: - parent = t.getparent() + texts = etree.XPath('/utwor/*[2]//text()')(source_tree) + for t in texts: + parent = t.getparent() + if hyph is not None: newt = '' wlist = re.compile(r'\w+|[^\w]', re.UNICODE).findall(t) for w in wlist: newt += hyph.inserted(w, u'\u00AD') - newt = re.sub(r'(?<=\s\w)\s+', u'\u00A0', newt) - if t.is_text: - parent.text = newt - elif t.is_tail: - parent.tail = newt + else: + newt = t + newt = re.sub(r'(?<=\s\w)\s+', u'\u00A0', newt) + if t.is_text: + parent.text = newt + elif t.is_tail: + parent.tail = newt def inner_xml(node): @@ -406,7 +408,7 @@ def transform_chunk(chunk_xml, chunk_no, annotations, empty=False, _empty_html_s def transform(wldoc, verbose=False, style=None, html_toc=False, - sample=None, cover=None, flags=None): + sample=None, cover=None, flags=None, hyphenate=False): """ produces a EPUB file sample=n: generate sample e-book (with at least n paragraphs) @@ -419,7 +421,7 @@ def transform(wldoc, verbose=False, replace_characters(wldoc.edoc.getroot()) - hyphenator = set_hyph_language(wldoc.edoc.getroot()) + hyphenator = set_hyph_language(wldoc.edoc.getroot()) if hyphenate else None hyphenate_and_fix_conjunctions(wldoc.edoc.getroot(), hyphenator) # every input file will have a TOC entry, @@ -501,6 +503,9 @@ def transform(wldoc, verbose=False, for flag in flags: document.edoc.getroot().set(flag, 'yes') + document.clean_ed_note() + document.clean_ed_note('abstrakt') + # add editors info editors = document.editors() if editors: @@ -643,7 +648,7 @@ def transform(wldoc, verbose=False, '"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">' )) - if not flags or not 'without-fonts' in flags: + if not flags or 'without-fonts' not in flags: # strip fonts tmpdir = mkdtemp('-librarian-epub') try: