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

Add --ignore-tables option.

Browse Source
This commit is contained in:
Kovid Goyal 2007-07-20 17:34:11 +00:00
parent 1a59652103
commit 59e0787f68
3 changed files with 17 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/libprs500/__init__.py
View File

@ -13,7 +13,7 @@
## with this program; if not, write to the Free Software Foundation, Inc., ## with this program; if not, write to the Free Software Foundation, Inc.,
## 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. ## 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
''' E-book management software''' ''' E-book management software'''
__version__ = "0.3.77" __version__ = "0.3.78"
__docformat__ = "epytext" __docformat__ = "epytext"
__author__ = "Kovid Goyal <kovid@kovidgoyal.net>" __author__ = "Kovid Goyal <kovid@kovidgoyal.net>"
__appname__ = 'libprs500' __appname__ = 'libprs500'

2
src/libprs500/ebooks/lrf/__init__.py
View File

@ -91,6 +91,8 @@ def option_parser(usage):
profiles=['prs500'] profiles=['prs500']
parser.add_option('-o', '--output', action='store', default=None, \ parser.add_option('-o', '--output', action='store', default=None, \
help='Output file name. Default is derived from input filename') help='Output file name. Default is derived from input filename')
parser.add_option('--ignore-tables', action='store_true', default=False,
help='Render HTML tables as blocks of text instead of actual tables. This is neccessary if the HTML contains very large or complex tables.')
laf = parser.add_option_group('LOOK AND FEEL') laf = parser.add_option_group('LOOK AND FEEL')
laf.add_option('--cover', action='store', dest='cover', default=None, \ laf.add_option('--cover', action='store', dest='cover', default=None, \
help='Path to file containing image to be used as cover') help='Path to file containing image to be used as cover')

22
src/libprs500/ebooks/lrf/html/convert_from.py
View File

@ -260,7 +260,8 @@ class HTMLConverter(object):
page_break=re.compile('h[12]', re.IGNORECASE), page_break=re.compile('h[12]', re.IGNORECASE),
force_page_break=re.compile('$', re.IGNORECASE), force_page_break=re.compile('$', re.IGNORECASE),
profile=PRS500_PROFILE, profile=PRS500_PROFILE,
disable_autorotation=False): disable_autorotation=False,
ignore_tables=False):
''' '''
Convert HTML file at C{path} and add it to C{book}. After creating Convert HTML file at C{path} and add it to C{book}. After creating
the object, you must call L{self.process_links} on it to create the links and the object, you must call L{self.process_links} on it to create the links and
@ -342,6 +343,7 @@ class HTMLConverter(object):
self.files = {} #: links that point to other files self.files = {} #: links that point to other files
self.links_processed = False #: Whether links_processed has been called on this object self.links_processed = False #: Whether links_processed has been called on this object
self.font_delta = font_delta self.font_delta = font_delta
self.ignore_tables = ignore_tables
# Set by table processing code so that any <a name> within the table # Set by table processing code so that any <a name> within the table
# point to the previous element # point to the previous element
self.anchor_to_previous = None self.anchor_to_previous = None
@ -611,7 +613,8 @@ class HTMLConverter(object):
link_exclude=self.link_exclude, link_exclude=self.link_exclude,
page_break=self.page_break, page_break=self.page_break,
force_page_break=self.force_page_break, force_page_break=self.force_page_break,
disable_autorotation=self.disable_autorotation) disable_autorotation=self.disable_autorotation,
ignore_tables=self.ignore_tables)
HTMLConverter.processed_files[path] = self.files[path] HTMLConverter.processed_files[path] = self.files[path]
except Exception: except Exception:
print >>sys.stderr, 'Unable to process', path print >>sys.stderr, 'Unable to process', path
@ -1189,14 +1192,16 @@ class HTMLConverter(object):
self.end_current_para() self.end_current_para()
self.current_block.append(CR()) self.current_block.append(CR())
self.end_current_block() self.end_current_block()
self.current_page.RuledLine(linelength=int(self.current_page.pageStyle.attrs['textwidth'])) if tagname == 'hr':
elif tagname == 'td': # Needed for nested tables self.current_page.RuledLine(linelength=int(self.current_page.pageStyle.attrs['textwidth']))
self.current_para.append(" ")
self.process_children(tag, tag_css) self.process_children(tag, tag_css)
elif tagname == 'table' and not self.in_table: elif tagname == 'td': # Needed for nested tables
self.current_para.append(' ')
self.process_children(tag, tag_css)
elif tagname == 'table' and not self.ignore_tables and not self.in_table:
tag_css = self.tag_css(tag) # Table should not inherit CSS tag_css = self.tag_css(tag) # Table should not inherit CSS
self.process_table(tag, tag_css) self.process_table(tag, tag_css)
else: else:
self.process_children(tag, tag_css) self.process_children(tag, tag_css)
if end_page: if end_page:
self.end_page() self.end_page()
@ -1291,7 +1296,8 @@ def process_file(path, options):
chapter_detection=options.chapter_detection, chapter_detection=options.chapter_detection,
chapter_regex=re.compile(options.chapter_regex, re.IGNORECASE), chapter_regex=re.compile(options.chapter_regex, re.IGNORECASE),
link_exclude=re.compile(le), page_break=pb, force_page_break=fpb, link_exclude=re.compile(le), page_break=pb, force_page_break=fpb,
disable_autorotation=options.disable_autorotation) disable_autorotation=options.disable_autorotation,
ignore_tables=options.ignore_tables)
conv.process_links() conv.process_links()
oname = options.output oname = options.output
if not oname: if not oname: