mirror of
https://github.com/gryf/ebook-converter.git
synced 2025-12-28 12:12:26 +01:00
Here is the first batch of modules, which are needed for converting several formats to LRF. Some of the logic has been change, more cleanups will follow.
134 lines
4.0 KiB
Python
134 lines
4.0 KiB
Python
#!/usr/bin/env python2
|
|
# vim:fileencoding=utf-8
|
|
from __future__ import absolute_import, division, print_function, unicode_literals
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2015, Kovid Goyal <kovid at kovidgoyal.net>'
|
|
|
|
import collections
|
|
from ebook_converter.polyglot.builtins import string_or_bytes
|
|
|
|
SLICE_ALL = slice(None)
|
|
|
|
|
|
def is_iterable(obj):
|
|
"""
|
|
Are we being asked to look up a list of things, instead of a single thing?
|
|
We check for the `__iter__` attribute so that this can cover types that
|
|
don't have to be known by this module, such as NumPy arrays.
|
|
|
|
Strings, however, should be considered as atomic values to look up, not
|
|
iterables.
|
|
"""
|
|
return hasattr(obj, '__iter__') and not isinstance(obj, string_or_bytes)
|
|
|
|
|
|
class OrderedSet(collections.MutableSet):
|
|
"""
|
|
An OrderedSet is a custom MutableSet that remembers its order, so that
|
|
every entry has an index that can be looked up.
|
|
"""
|
|
def __init__(self, iterable=None):
|
|
self.items = []
|
|
self.map = {}
|
|
if iterable is not None:
|
|
for item in iterable:
|
|
idx = self.map.get(item)
|
|
if idx is None:
|
|
self.map[item] = len(self.items)
|
|
self.items.append(item)
|
|
|
|
def __len__(self):
|
|
return len(self.items)
|
|
|
|
def __getitem__(self, index):
|
|
"""
|
|
Get the item at a given index.
|
|
|
|
If `index` is a slice, you will get back that slice of items. If it's
|
|
the slice [:], exactly the same object is returned. (If you want an
|
|
independent copy of an OrderedSet, use `OrderedSet.copy()`.)
|
|
|
|
If `index` is an iterable, you'll get the OrderedSet of items
|
|
corresponding to those indices. This is similar to NumPy's
|
|
"fancy indexing".
|
|
"""
|
|
if index == SLICE_ALL:
|
|
return self
|
|
elif hasattr(index, '__index__') or isinstance(index, slice):
|
|
result = self.items[index]
|
|
if isinstance(result, list):
|
|
return OrderedSet(result)
|
|
else:
|
|
return result
|
|
elif is_iterable(index):
|
|
return OrderedSet([self.items[i] for i in index])
|
|
else:
|
|
raise TypeError("Don't know how to index an OrderedSet by %r" %
|
|
index)
|
|
|
|
def copy(self):
|
|
return OrderedSet(self)
|
|
|
|
def __getstate__(self):
|
|
return tuple(self)
|
|
|
|
def __setstate__(self, state):
|
|
self.__init__(state)
|
|
|
|
def __contains__(self, key):
|
|
return key in self.map
|
|
|
|
def add(self, key):
|
|
"""
|
|
Add `key` as an item to this OrderedSet, then return its index.
|
|
|
|
If `key` is already in the OrderedSet, return the index it already
|
|
had.
|
|
"""
|
|
index = self.map.get(key)
|
|
if index is None:
|
|
self.map[key] = index = len(self.items)
|
|
self.items.append(key)
|
|
return index
|
|
|
|
def index(self, key):
|
|
"""
|
|
Get the index of a given entry, raising an IndexError if it's not
|
|
present.
|
|
|
|
`key` can be an iterable of entries that is not a string, in which case
|
|
this returns a list of indices.
|
|
"""
|
|
if is_iterable(key):
|
|
return [self.index(subkey) for subkey in key]
|
|
return self.map[key]
|
|
|
|
def discard(self, key):
|
|
index = self.map.get(key)
|
|
if index is not None:
|
|
self.items.pop(index)
|
|
for item in self.items[index:]:
|
|
self.map[item] -= 1
|
|
return True
|
|
return False
|
|
|
|
def __iter__(self):
|
|
return iter(self.items)
|
|
|
|
def __reversed__(self):
|
|
return reversed(self.items)
|
|
|
|
def __repr__(self):
|
|
if not self:
|
|
return '%s()' % (self.__class__.__name__,)
|
|
return '%s(%r)' % (self.__class__.__name__, list(self))
|
|
|
|
def __eq__(self, other):
|
|
if isinstance(other, OrderedSet):
|
|
return len(self) == len(other) and self.items == other.items
|
|
try:
|
|
return type(other)(self.map) == other
|
|
except TypeError:
|
|
return False
|