Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix detection of top of a page and change handling of <a name> elements to prevent reader slowdowns.

Browse Source
This commit is contained in:
Kovid Goyal 2007-05-02 19:35:45 +00:00
parent c44bd5ab55
commit 21af20d036
3 changed files with 42 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
src/libprs500/lrf/html/convert_from.py
View File

@ -31,7 +31,7 @@ from libprs500.lrf.html.BeautifulSoup import BeautifulSoup, Comment, Tag, \
NavigableString, Declaration, ProcessingInstruction NavigableString, Declaration, ProcessingInstruction
from libprs500.lrf.pylrs.pylrs import Paragraph, CR, Italic, ImageStream, TextBlock, \ from libprs500.lrf.pylrs.pylrs import Paragraph, CR, Italic, ImageStream, TextBlock, \
ImageBlock, JumpButton, CharButton, BlockStyle,\ ImageBlock, JumpButton, CharButton, BlockStyle,\
Page, Bold, Space, Plot, TextStyle, Image Page, Bold, Space, Plot, TextStyle, Image, BlockSpace
from libprs500.lrf.pylrs.pylrs import Span as _Span from libprs500.lrf.pylrs.pylrs import Span as _Span
from libprs500.lrf import ConversionError, option_parser, Book from libprs500.lrf import ConversionError, option_parser, Book
from libprs500 import extract from libprs500 import extract
@ -377,15 +377,16 @@ class HTMLConverter(object):
self.current_block.append_to(self.current_page) self.current_block.append_to(self.current_page)
if self.current_page and self.current_page.get_text().strip(): if self.current_page and self.current_page.get_text().strip():
self.book.append(self.current_page) self.book.append(self.current_page)
previous = self.current_page
if not self.top.parent: if not self.top.parent:
if not previous: if not previous:
previous = self.current_page self.top = self.book.pages()[0].contents[0]
else:
found = False found = False
for page in self.book.pages(): for page in self.book.pages():
if page == previous: if page == previous:
found = True found = True
continue
if found: if found:
self.top = page.contents[0] self.top = page.contents[0]
break break
@ -588,37 +589,33 @@ class HTMLConverter(object):
pass pass
elif tagname == 'a' and self.max_link_levels >= 0: elif tagname == 'a' and self.max_link_levels >= 0:
if tag.has_key('name'): if tag.has_key('name'):
self.current_para.append_to(self.current_block)
self.current_block.append_to(self.current_page)
previous = self.current_block previous = self.current_block
tb = TextBlock()
self.current_block = tb
self.current_para = Paragraph()
self.targets[tag['name']] = tb
self.process_children(tag, tag_css) self.process_children(tag, tag_css)
if tb.parent == None: target = None
if self.current_block == tb: if self.current_block == previous:
self.current_para.append_to(self.current_block) self.current_para.append_to(self.current_block)
self.current_para = Paragraph() self.current_para = Paragraph()
if not self.current_block.get_text().strip(): if self.current_block.get_text().strip():
# This is neccessary as apparently the reader target = self.current_block
# cannot handle empty TextBlocks, although
# the Connect software displays them correctly
mkr = TextBlock()
mkr.append(Paragraph(text=' '))
self.current_page.append(mkr)
#self.current_page.append(self.current_block)
#self.current_block = TextBlock()
else: else:
found, marked = False, False target = BlockSpace()
self.current_page.append(target)
else:
found = False
for item in self.current_page.contents: for item in self.current_page.contents:
if item == previous: if item == previous:
found = True found = True
if found and isinstance(item, TextBlock): continue
self.targets[tag['name']] = item if found:
marked = True target = item
if not marked: break
self.current_page.append(tb) if target == None:
if self.current_block.get_text().strip():
target = self.current_block
else:
target = BlockSpace()
self.current_page.append(target)
self.targets[tag['name']] = target
elif tag.has_key('href'): elif tag.has_key('href'):
purl = urlparse(tag['href']) purl = urlparse(tag['href'])
path = purl[2] path = purl[2]
@ -699,9 +696,13 @@ class HTMLConverter(object):
elif tagname in ['ul', 'ol']: elif tagname in ['ul', 'ol']:
self.in_ol = 1 if tagname == 'ol' else 0 self.in_ol = 1 if tagname == 'ol' else 0
self.end_current_para() self.end_current_para()
self.current_block.append_to(self.current_page)
self.current_block = TextBlock()
self.process_children(tag, tag_css) self.process_children(tag, tag_css)
self.in_ol = 0 self.in_ol = 0
self.end_current_para() self.end_current_para()
self.current_block.append_to(self.current_page)
self.current_block = TextBlock()
elif tagname == 'li': elif tagname == 'li':
prepend = str(self.in_ol)+'. ' if self.in_ol else u'\u2022' + ' ' prepend = str(self.in_ol)+'. ' if self.in_ol else u'\u2022' + ' '
if self.current_para.get_text().strip(): if self.current_para.get_text().strip():

3
src/libprs500/lrf/pylrs/pylrs.py
View File

@ -1791,9 +1791,10 @@ class Bold(Span):
return e return e
class BlockSpace(LrsContainer): class BlockSpace(LrsContainer, LrsObject):
""" Can be appended to a page to move the text point. """ """ Can be appended to a page to move the text point. """
def __init__(self, xspace=0, yspace=0, x=0, y=0): def __init__(self, xspace=0, yspace=0, x=0, y=0):
LrsObject.__init__(self)
LrsContainer.__init__(self, []) LrsContainer.__init__(self, [])
if xspace == 0 and x != 0: xspace = x if xspace == 0 and x != 0: xspace = x
if yspace == 0 and y != 0: yspace = y if yspace == 0 and y != 0: yspace = y