def __init__(self,
lang=None,
text=None,
tokenize=None,
chunkers=None,
filters=None):
"""Constructor for the SpellChecker class.
SpellChecker objects can be created in two ways, depending on
the nature of the first argument. If it is a string, it
specifies a language tag from which a dictionary is created.
Otherwise, it must be an enchant Dict object to be used.
Optional keyword arguments are:
* text: to set the text to be checked at creation time
* tokenize: a custom tokenization function to use
* chunkers: a list of chunkers to apply during tokenization
* filters: a list of filters to apply during tokenization
If <tokenize> is not given and the first argument is a Dict,
its 'tag' attribute must be a language tag so that a tokenization
function can be created automatically. If this attribute is missing
the user's default language will be used.
"""
if lang is None:
lang = get_default_language()
if isinstance(lang, basestring):
dict = enchant.Dict(lang)
else:
dict = lang
try:
lang = dict.tag
except AttributeError:
lang = get_default_language()
if lang is None:
raise DefaultLanguageNotFoundError
self.lang = lang
self.dict = dict
if tokenize is None:
try:
tokenize = get_tokenizer(lang, chunkers, filters)
except TokenizerNotFoundError:
# Fall back to default tokenization if no match for 'lang'
tokenize = get_tokenizer(None, chunkers, filters)
self._tokenize = tokenize
self.word = None
self.wordpos = None
self._ignore_words = {}
self._replace_words = {}
# Default to the empty string as the text to be checked
self._text = array.array('u')
self._use_tostring = False
self._tokens = iter([])
if text is not None:
self.set_text(text)
def __init__(self,lang=None,text=None,tokenize=None,chunkers=None,filters=None):
"""Constructor for the SpellChecker class.
SpellChecker objects can be created in two ways, depending on
the nature of the first argument. If it is a string, it
specifies a language tag from which a dictionary is created.
Otherwise, it must be an enchant Dict object to be used.
Optional keyword arguments are:
* text: to set the text to be checked at creation time
* tokenize: a custom tokenization function to use
* chunkers: a list of chunkers to apply during tokenization
* filters: a list of filters to apply during tokenization
If <tokenize> is not given and the first argument is a Dict,
its 'tag' attribute must be a language tag so that a tokenization
function can be created automatically. If this attribute is missing
the user's default language will be used.
"""
if lang is None:
lang = get_default_language()
if isinstance(lang,basestring):
dict = enchant.Dict(lang)
else:
dict = lang
try:
lang = dict.tag
except AttributeError:
lang = get_default_language()
if lang is None:
raise DefaultLanguageNotFoundError
self.lang = lang
self.dict = dict
if tokenize is None:
try:
tokenize = get_tokenizer(lang,chunkers,filters)
except TokenizerNotFoundError:
# Fall back to default tokenization if no match for 'lang'
tokenize = get_tokenizer(None,chunkers,filters)
self._tokenize = tokenize
self.word = None
self.wordpos = None
self._ignore_words = {}
self._replace_words = {}
# Default to the empty string as the text to be checked
self._text = array.array('u')
self._use_tostring = False
self._tokens = iter([])
if text is not None:
self.set_text(text)
def __init__(self, tag=None, broker=None):
"""Dict object constructor.
A dictionary belongs to a specific language, identified by the
string <tag>. If the tag is not given or is None, an attempt to
determine the language currently in use is made using the 'locale'
module. If the current language cannot be determined, Error is raised.
If <tag> is instead given the value of False, a 'dead' Dict object
is created without any reference to a language. This is typically
only useful within PyEnchant itself. Any other non-string value
for <tag> raises Error.
Each dictionary must also have an associated Broker object which
obtains the dictionary information from the underlying system. This
may be specified using <broker>. If not given, the default broker
is used.
"""
# Initialise misc object attributes to None
self.provider = None
# If no tag was given, use the default language
if tag is None:
tag = get_default_language()
if tag is None:
err = "No tag specified and default language could not "
err = err + "be determined."
raise Error(err)
self.tag = tag
# If no broker was given, use the default broker
if broker is None:
broker = _broker
self._broker = broker
# Now let the superclass initialise the C-library object
super().__init__()
def __init__(self,tag=None,broker=None):
"""Dict object constructor.
A dictionary belongs to a specific language, identified by the
string <tag>. If the tag is not given or is None, an attempt to
determine the language currently in use is made using the 'locale'
module. If the current language cannot be determined, Error is raised.
If <tag> is instead given the value of False, a 'dead' Dict object
is created without any reference to a language. This is typically
only useful within PyEnchant itself. Any other non-string value
for <tag> raises Error.
Each dictionary must also have an associated Broker object which
obtains the dictionary information from the underlying system. This
may be specified using <broker>. If not given, the default broker
is used.
"""
# Initialise misc object attributes to None
self.provider = None
# If no tag was given, use the default language
if tag is None:
tag = get_default_language()
if tag is None:
err = "No tag specified and default language could not "
err = err + "be determined."
raise Error(err)
self.tag = tag
# If no broker was given, use the default broker
if broker is None:
broker = _broker
self._broker = broker
# Now let the superclass initialise the C-library object
_EnchantObject.__init__(self)
def test_default_language():
lang = get_default_language()
if lang is None:
with pytest.raises(DefaultLanguageNotFoundError):
SpellChecker()
else:
checker = SpellChecker()
assert checker.lang == lang
def test_DefaultLang(en_us_dict):
"""Test behaviour of default language selection."""
defLang = get_default_language()
if defLang is None:
# If no default language, shouldn't work
with pytest.raises(Error):
Dict()
else:
# If there is a default language, should use it
# Of course, no need for the dict to actually exist
try:
d = Dict()
assert d.tag == defLang
except DictNotFoundError:
pass
def test_default_language():
# Two cases: either SpellChecker() without argument works
# and its lang is the default language, or
# it does not and we get a DefaultLanguageNotFoundError
caught_err = None
try:
checker = SpellChecker()
except DefaultLanguageNotFoundError as e:
caught_err = e
if caught_err:
# At this point, caught_err must be DefaultLanguageNotFoundError, so
# we're done testing
return
assert checker.lang == get_default_language()
def __init__(self, lang=None, *args, **kwargs):
"""
Initialize a new CKEnchanter object
"""
# Make sure the desired default dictionary exists
# if it doesn't, get the default language
if lang is None:
lang = get_default_language()
# If a word list was given, add it to the default dictionary
if kwargs.get('wl_path', None):
master_dict = enchant.DictWithPWL(lang, kwargs.pop('wl_path'))
else:
master_dict = lang
# Finish creating a pyenchant spellchecker
SpellChecker.__init__(self, master_dict, *args, **kwargs)
def __init__(self, tag=None, broker=None):
"""Dict object constructor.
A dictionary belongs to a specific language, identified by the
string <tag>. If the tag is not given or is None, an attempt to
determine the language currently in use is made using the 'locale'
module. If the current language cannot be determined, Error is raised.
If <tag> is instead given the value of False, a 'dead' Dict object
is created without any reference to a language. This is typically
only useful within PyEnchant itself. Any other non-string value
for <tag> raises Error.
Each dictionary must also have an associated Broker object which
obtains the dictionary information from the underlying system. This
may be specified using <broker>. If not given, the default broker
is used.
"""
# Superclass initialisation
_EnchantObject.__init__(self)
# Initialise object attributes to None
self._broker = None
self.tag = None
self.provider = None
# Create dead object if False was given
if tag is False:
self._this = None
else:
if tag is None:
tag = get_default_language()
if tag is None:
err = "No tag specified and default language could not "
err = err + "be determined."
raise Error(err)
# Use module-level broker if none given
if broker is None:
broker = _broker
# Use the broker to get C-library pointer data
self._switch_this(broker._request_dict_data(tag), broker)
