Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

ereader input: support footnotes and sidebars

Browse Source
This commit is contained in:
John Schember 2009-04-24 21:10:58 -04:00
parent 202958cb4d
commit ae86b2a44b
2 changed files with 27 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
src/calibre/ebooks/pdb/ereader/pmlconverter.py
View File

@ -12,10 +12,12 @@ import re
from calibre.ebooks.htmlsymbols import HTML_SYMBOLS
from BeautifulSoup import BeautifulSoup
PML_HTML_RULES = [
(re.compile(r'\\p'), lambda match: '<br /><br style="page-break-after: always;" />'),
(re.compile(r'\\x(?P<text>.+?)\\x', re.DOTALL), lambda match: '<h1 style="page-break-before: always;">%s</h1>' % match.group('text')),
(re.compile(r'\\X(?P<val>[0-4])(?P<text>.+?)\\X[0-4]', re.DOTALL), lambda match: '<h%i style="page-break-before: always;">%s</h%i>' % (int(match.group('val')) + 1, match.group('text'), int(match.group('val')) + 1)),
(re.compile(r'\\X(?P<val>[0-4])(?P<text>.+?)\\X[0-4]', re.DOTALL), lambda match: '<h%s style="page-break-before: always;">%s</h%s>' % (int(match.group('val')) + 1, match.group('text'), int(match.group('val')) + 1)),
(re.compile(r'\\C\d=".+"'), lambda match: ''), # This should be made to create a TOC entry
(re.compile(r'\\c(?P<text>.+?)\\c', re.DOTALL), lambda match: '<div style="text-align: center; display: block; margin: auto;">%s</div>' % match.group('text')),
(re.compile(r'\\r(?P<text>.+?)\\r', re.DOTALL), lambda match: '<div style="text-align: right; display: block;">%s</div>' % match.group('text')),
@ -34,10 +36,10 @@ PML_HTML_RULES = [
(re.compile(r'\\Sp(?P<text>.+?)\\Sp', re.DOTALL), lambda match: '<sup>%s</sup>' % match.group('text')),
(re.compile(r'\\Sb(?P<text>.+?)\\Sb', re.DOTALL), lambda match: '<sub>%s</sub>' % match.group('text')),
(re.compile(r'\\k(?P<text>.+?)\\k', re.DOTALL), lambda match: '<small>%s</small>' % match.group('text')),
(re.compile(r'\\a(?P<num>\d\d\d)'), lambda match: '&#%i;' % match.group('num')),
(re.compile(r'\\U(?P<num>\d\d\d\d)'), lambda match: '&#%i;' % int(match.group('num'))),
(re.compile(r'\\a(?P<num>\d\d\d)'), lambda match: '&#%s;' % match.group('num')),
(re.compile(r'\\U(?P<num>\d+)'), lambda match: '%s' % unichr(int(match.group('num'), 16))),
(re.compile(r'\\m="(?P<name>.+?)"'), lambda match: '<img src="images/%s" />' % match.group('name')),
(re.compile(r'\\q="(?P<target>#.+?)"(?P<text>)\\q', re.DOTALL), lambda match: '<a href="%s">%s</a>' % (match.group('target'), match.group('text'))),
(re.compile(r'\\q="(?P<target>#.+?)"(?P<text>.+?)\\q', re.DOTALL), lambda match: '<a href="%s">%s</a>' % (match.group('target'), match.group('text'))),
(re.compile(r'\\Q="(?P<target>.+?)"'), lambda match: '<div id="%s"></div>' % match.group('target')),
(re.compile(r'\\-'), lambda match: ''),
(re.compile(r'\\Fn="(?P<target>.+?)"(?P<text>.+?)\\Fn'), lambda match: '<a href="#footnote-%s">%s</a>' % (match.group('target'), match.group('text'))),
@ -67,23 +69,23 @@ HTML_PML_RULES = [
(re.compile('<div.*?id="(?P<target>.+?).*?"></div>'), lambda match: '\\\\Q="%s"' % match.group('target')),
(re.compile('<a.*?href="(?P<target>#.+?).*?">(?P<text>)</a>', re.DOTALL), lambda match: '\\q="%s"%s\\q' % (match.group('target'), match.group('text'))),
(re.compile('<img.*?src="images/(?P<name>.+?)".*?>'), lambda match: '\\m="%s"' % match.group('name')),
(re.compile('&#(?P<num>\d\d\d\d);'), lambda match: '\\U%i' % int(match.group('num'))),
(re.compile('&#(?P<num>\d\d\d);'), lambda match: '\\a%i' % match.group('num')),
#(re.compile('&#(?P<num>\d\d\d\d);'), lambda match: '\\U%s' % int(match.group('num'))),
(re.compile('&#(?P<num>\d\d\d);'), lambda match: '\\a%s' % match.group('num')),
(re.compile('<small.*?>(?P<text>.+?)</small>', re.DOTALL), lambda match: '\\k%s\\k' % match.group('text')),
(re.compile('<sub.*?>(?P<text>.+?)</sub>', re.DOTALL), lambda match: '\\Sb%s\\Sb' % match.group('text')),
(re.compile('<sup.*?>(?P<text>.+?)</sup>', re.DOTALL), lambda match: '\\Sp%s\\Sp' % match.group('text')),
(re.compile('<b.*?>(?P<text>.+?)</b>', re.DOTALL), lambda match: '\\B%s\\B' % match.group('text')),
(re.compile('<big.*?>(?P<text>.+?)</big>', re.DOTALL), lambda match: '\\l%s\\l' % match.group('text')),
(re.compile('<hr.*?width="(?P<val>\d+)%%".*?>'), lambda match: '\\w="%s%%"' % match.group('val')),
(re.compile('<div.*?style.*?margin-left: (?P<val>\d+)%%*;.*?>(?P<text>.+?)</div>', re.MULTILINE), lambda match: '\\T="%i%%"%s$' % (match.group('val'), match.group('text'))),
(re.compile('<div.*?style.*?margin-left: \d{1,3}%%;.*?>(?P<text>.+?)</div>', re.DOTALL), lambda match: '\\t%s\\t' % match.group('text')),
(re.compile('<hr.*?width="(?P<val>\d+)%".*?>'), lambda match: '\\w="%s%%"' % match.group('val')),
(re.compile('<div.*?style.*?margin-left: (?P<val>\d+)%*;.*?>(?P<text>.+?)</div>', re.MULTILINE), lambda match: '\\T="%s%%"%s$' % (match.group('val'), match.group('text'))),
(re.compile('<div.*?style.*?margin-left: \d{1,3}%;.*?>(?P<text>.+?)</div>', re.DOTALL), lambda match: '\\t%s\\t' % match.group('text')),
(re.compile('<!-- (?P<text>.+?) -->', re.DOTALL), lambda match: '\\v%s\\v' % match.group('text')),
(re.compile('<del.*?>(?P<text>.+?)</del>', re.DOTALL), lambda match: '\\o%s\\o' % match.group('text')),
(re.compile('<div.*?style.*?text-decoration: underline;.*?>(?P<text>.+?)</div>', re.DOTALL), lambda match: '\\u%s\\u' % match.group('text')),
(re.compile('<i.*?>(?P<text>.+?)</i>', re.DOTALL), lambda match: '\\\\i%s\\i' % match.group('text')),
(re.compile('<div.*?style.*?text-align: right;.*?>(?P<text>.+?)</div>', re.DOTALL), lambda match: '\\r%s\\r' % match.group('text')),
(re.compile('<div.*?style.*?text-align: center;.*?".*?>(?P<text>.+?)</div>', re.DOTALL), lambda match: '\\c%s\\c' % match.group('text')),
(re.compile('<h(?P<val>[0-4]).*?>(?P<text>.+?)</h[0-4]>', re.DOTALL), lambda match: '\\X%i%s\\X%i' % (int(match.group('val')) + 1, match.group('text'), int(match.group('val')) + 1)),
(re.compile('<h(?P<val>[0-4]).*?>(?P<text>.+?)</h[0-4]>', re.DOTALL), lambda match: '\\X%s%s\\X%s' % (int(match.group('val')) + 1, match.group('text'), int(match.group('val')) + 1)),
(re.compile('<h1.*?>(?P<text>.+?)</h1>', re.DOTALL), lambda match: '\\x%s\\x' % match.group('text')),
(re.compile('<br.*?>'), lambda match: '\\p'),
(re.compile('<.*?>'), lambda match: ''),
@ -102,13 +104,19 @@ def pml_to_html(pml):
return html
def footnote_sidebar_to_html(id, pml):
html = '<div id="sidebar-%s">%s</div>' % (id, pml_to_html(pml))
html = '<div id="sidebar-%s"><dt>%s</dt></div><dd>%s</dd>' % (id, id, pml_to_html(pml))
return html
def html_to_pml(html):
pml = html
for rule in HTML_PML_RULES:
pml = rule[0].sub(rule[1], pml)
pml = ''
for dom_tree in BeautifulSoup(html).findAll('body'):
body = unicode(dom_tree.pretty_print())
for rule in HTML_PML_RULES:
body = rule[0].sub(rule[1], pml)
pml += body
# Replace symbols outside of cp1512 wtih \Uxxxx

5
src/calibre/ebooks/pdb/ereader/reader.py
View File

@ -108,14 +108,19 @@ class Reader(FormatReader):
footnoteids = re.findall('\w+(?=\x00)', self.section_data(self.header_record.footnote_offset).decode('cp1252' if self.encoding is None else self.encoding))
for fid, i in enumerate(range(self.header_record.footnote_offset + 1, self.header_record.footnote_offset + self.header_record.footnote_rec)):
self.log.debug('Extracting footnote page %i' % i)
html += '<dl>'
html += footnote_sidebar_to_html(footnoteids[fid], self.decompress_text(i))
html += '</dl>'
if self.header_record.sidebar_rec > 0:
html += '<br /><h1>%s</h1>' % _('Sidebar')
sidebarids = re.findall('\w+(?=\x00)', self.section_data(self.header_record.sidebar_offset).decode('cp1252' if self.encoding is None else self.encoding))
for sid, i in enumerate(range(self.header_record.sidebar_offset + 1, self.header_record.sidebar_offset + self.header_record.sidebar_rec)):
self.log.debug('Extracting sidebar page %i' % i)
html += '<dl>'
html += footnote_sidebar_to_html(sidebarids[sid], self.decompress_text(i))
html += '</dl>'
html += '</body></html>'