"""
Xapian is a highly adaptable toolkit which allows developers to easily
add advanced indexing and search facilities to their own
applications. It supports the Probabilistic Information Retrieval
model and also supports a rich set of boolean query operators.
In addition to the doc strings provided by this python library, you
may wish to look at the library's overall documentation, either
installed along with the bindings or online at
, as well as the library's
documentation, possibly installed with the library or with its
development files, or again online at .
"""
# This file was automatically generated by SWIG (http://www.swig.org).
# Version 2.0.5
#
# Do not make changes to this file unless you know what you are doing--modify
# the SWIG interface file instead.
from sys import version_info
if version_info >= (3,0,0):
new_instancemethod = lambda func, inst, cls: _xapian.SWIG_PyInstanceMethod_New(func)
else:
from new import instancemethod as new_instancemethod
if version_info >= (2,6,0):
def swig_import_helper():
from os.path import dirname
import imp
fp = None
try:
fp, pathname, description = imp.find_module('_xapian', [dirname(__file__)])
except ImportError:
import _xapian
return _xapian
if fp is not None:
try:
_mod = imp.load_module('_xapian', fp, pathname, description)
finally:
fp.close()
return _mod
_xapian = swig_import_helper()
del swig_import_helper
else:
import _xapian
del version_info
try:
_swig_property = property
except NameError:
pass # Python < 2.2 doesn't have 'property'.
def _swig_setattr_nondynamic(self,class_type,name,value,static=1):
if (name == "thisown"): return self.this.own(value)
if (name == "this"):
if type(value).__name__ == 'SwigPyObject':
self.__dict__[name] = value
return
method = class_type.__swig_setmethods__.get(name,None)
if method: return method(self,value)
if (not static):
self.__dict__[name] = value
else:
raise AttributeError("You cannot add attributes to %s" % self)
def _swig_setattr(self,class_type,name,value):
return _swig_setattr_nondynamic(self,class_type,name,value,0)
def _swig_getattr(self,class_type,name):
if (name == "thisown"): return self.this.own()
method = class_type.__swig_getmethods__.get(name,None)
if method: return method(self)
raise AttributeError(name)
def _swig_repr(self):
try: strthis = "proxy of " + self.this.__repr__()
except: strthis = ""
return "<%s.%s; %s >" % (self.__class__.__module__, self.__class__.__name__, strthis,)
try:
_object = object
_newclass = 1
except AttributeError:
class _object : pass
_newclass = 0
def _swig_setattr_nondynamic_method(set):
def set_attr(self,name,value):
if (name == "thisown"): return self.this.own(value)
if hasattr(self,name) or (name == "this"):
set(self,name,value)
else:
raise AttributeError("You cannot add attributes to %s" % self)
return set_attr
try:
import weakref
weakref_proxy = weakref.proxy
except:
weakref_proxy = lambda x: x
class SwigPyIterator(object):
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
def __init__(self, *args, **kwargs): raise AttributeError("No constructor defined - class is abstract")
__repr__ = _swig_repr
__swig_destroy__ = _xapian.delete_SwigPyIterator
def __iter__(self): return self
SwigPyIterator.value = new_instancemethod(_xapian.SwigPyIterator_value,None,SwigPyIterator)
SwigPyIterator.incr = new_instancemethod(_xapian.SwigPyIterator_incr,None,SwigPyIterator)
SwigPyIterator.decr = new_instancemethod(_xapian.SwigPyIterator_decr,None,SwigPyIterator)
SwigPyIterator.distance = new_instancemethod(_xapian.SwigPyIterator_distance,None,SwigPyIterator)
SwigPyIterator.equal = new_instancemethod(_xapian.SwigPyIterator_equal,None,SwigPyIterator)
SwigPyIterator.copy = new_instancemethod(_xapian.SwigPyIterator_copy,None,SwigPyIterator)
SwigPyIterator.next = new_instancemethod(_xapian.SwigPyIterator_next,None,SwigPyIterator)
SwigPyIterator.__next__ = new_instancemethod(_xapian.SwigPyIterator___next__,None,SwigPyIterator)
SwigPyIterator.previous = new_instancemethod(_xapian.SwigPyIterator_previous,None,SwigPyIterator)
SwigPyIterator.advance = new_instancemethod(_xapian.SwigPyIterator_advance,None,SwigPyIterator)
SwigPyIterator.__eq__ = new_instancemethod(_xapian.SwigPyIterator___eq__,None,SwigPyIterator)
SwigPyIterator.__ne__ = new_instancemethod(_xapian.SwigPyIterator___ne__,None,SwigPyIterator)
SwigPyIterator.__iadd__ = new_instancemethod(_xapian.SwigPyIterator___iadd__,None,SwigPyIterator)
SwigPyIterator.__isub__ = new_instancemethod(_xapian.SwigPyIterator___isub__,None,SwigPyIterator)
SwigPyIterator.__add__ = new_instancemethod(_xapian.SwigPyIterator___add__,None,SwigPyIterator)
SwigPyIterator.__sub__ = new_instancemethod(_xapian.SwigPyIterator___sub__,None,SwigPyIterator)
SwigPyIterator_swigregister = _xapian.SwigPyIterator_swigregister
SwigPyIterator_swigregister(SwigPyIterator)
__version__ = '1.2.16'
BAD_VALUENO = _xapian.BAD_VALUENO
MSET_DID = _xapian.MSET_DID
MSET_WT = _xapian.MSET_WT
MSET_RANK = _xapian.MSET_RANK
MSET_PERCENT = _xapian.MSET_PERCENT
MSET_DOCUMENT = _xapian.MSET_DOCUMENT
ESET_TNAME = _xapian.ESET_TNAME
ESET_WT = _xapian.ESET_WT
class Error(Exception):
"""
All exceptions thrown by Xapian are subclasses of Xapian::Error.
This class can not be instantiated directly - instead a subclass
should be used.
"""
__swig_setmethods__ = {}
__setattr__ = lambda self, name, value: _swig_setattr(self, Error, name, value)
__swig_getmethods__ = {}
__getattr__ = lambda self, name: _swig_getattr(self, Error, name)
def __init__(self, *args, **kwargs): raise AttributeError("No constructor defined")
__repr__ = _swig_repr
def get_type(self):
"""
The type of this error (e.g. "DocNotFoundError".)
const char* Xapian::Error::get_type() const
"""
return _xapian.Error_get_type(self)
def get_msg(self):
"""
Message giving details of the error, intended for human consumption.
const std::string& Xapian::Error::get_msg() const
"""
return _xapian.Error_get_msg(self)
def get_context(self):
"""
Optional context information.
const std::string& Xapian::Error::get_context() const
This context is intended for use by Xapian::ErrorHandler (for example
so it can know which remote server is unreliable and report the
problem and remove that server from those being searched). But it's
typically a plain-text string, and so also fit for human consumption.
"""
return _xapian.Error_get_context(self)
def get_error_string(self):
"""
Returns any system error string associated with this exception.
const char* Xapian::Error::get_error_string() const
The system error string may come from errno, h_errno (on UNIX), or
GetLastError() (on MS Windows). If there is no associated system error
string, NULL is returned.
"""
return _xapian.Error_get_error_string(self)
__swig_destroy__ = _xapian.delete_Error
Error.get_type = new_instancemethod(_xapian.Error_get_type,None,Error)
Error.get_msg = new_instancemethod(_xapian.Error_get_msg,None,Error)
Error.get_context = new_instancemethod(_xapian.Error_get_context,None,Error)
Error.get_error_string = new_instancemethod(_xapian.Error_get_error_string,None,Error)
Error.__str__ = new_instancemethod(_xapian.Error___str__,None,Error)
Error_swigregister = _xapian.Error_swigregister
Error_swigregister(Error)
class LogicError(Error):
"""
The base class for exceptions indicating errors in the program logic.
A subclass of LogicError will be thrown if Xapian detects a violation
of a class invariant or a logical precondition or postcondition, etc.
"""
__swig_setmethods__ = {}
for _s in [Error]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, LogicError, name, value)
__swig_getmethods__ = {}
for _s in [Error]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, LogicError, name)
def __init__(self, *args, **kwargs): raise AttributeError("No constructor defined")
__repr__ = _swig_repr
__swig_destroy__ = _xapian.delete_LogicError
LogicError_swigregister = _xapian.LogicError_swigregister
LogicError_swigregister(LogicError)
class RuntimeError(Error):
"""
The base class for exceptions indicating errors only detectable at
runtime.
A subclass of RuntimeError will be thrown if Xapian detects an error
which is exception derived from RuntimeError is thrown when an error
is caused by problems with the data or environment rather than a
programming mistake.
"""
__swig_setmethods__ = {}
for _s in [Error]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, RuntimeError, name, value)
__swig_getmethods__ = {}
for _s in [Error]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, RuntimeError, name)
def __init__(self, *args, **kwargs): raise AttributeError("No constructor defined")
__repr__ = _swig_repr
__swig_destroy__ = _xapian.delete_RuntimeError
RuntimeError_swigregister = _xapian.RuntimeError_swigregister
RuntimeError_swigregister(RuntimeError)
class AssertionError(LogicError):
"""
AssertionError is thrown if a logical assertion inside Xapian fails.
In a debug build of Xapian, a failed assertion in the core library
code will cause AssertionError to be thrown.
This represents a bug in Xapian (either an invariant, precondition,
etc has been violated, or the assertion is incorrect!)
"""
__swig_setmethods__ = {}
for _s in [LogicError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, AssertionError, name, value)
__swig_getmethods__ = {}
for _s in [LogicError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, AssertionError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::AssertionError::AssertionError(const std::string &msg_, int
errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.AssertionError_swiginit(self,_xapian.new_AssertionError(*args))
__swig_destroy__ = _xapian.delete_AssertionError
AssertionError_swigregister = _xapian.AssertionError_swigregister
AssertionError_swigregister(AssertionError)
class InvalidArgumentError(LogicError):
"""
InvalidArgumentError indicates an invalid parameter value was passed
to the API.
"""
__swig_setmethods__ = {}
for _s in [LogicError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, InvalidArgumentError, name, value)
__swig_getmethods__ = {}
for _s in [LogicError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, InvalidArgumentError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::InvalidArgumentError::InvalidArgumentError(const std::string
&msg_, int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.InvalidArgumentError_swiginit(self,_xapian.new_InvalidArgumentError(*args))
__swig_destroy__ = _xapian.delete_InvalidArgumentError
InvalidArgumentError_swigregister = _xapian.InvalidArgumentError_swigregister
InvalidArgumentError_swigregister(InvalidArgumentError)
class InvalidOperationError(LogicError):
"""
InvalidOperationError indicates the API was used in an invalid way.
"""
__swig_setmethods__ = {}
for _s in [LogicError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, InvalidOperationError, name, value)
__swig_getmethods__ = {}
for _s in [LogicError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, InvalidOperationError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::InvalidOperationError::InvalidOperationError(const std::string
&msg_, int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.InvalidOperationError_swiginit(self,_xapian.new_InvalidOperationError(*args))
__swig_destroy__ = _xapian.delete_InvalidOperationError
InvalidOperationError_swigregister = _xapian.InvalidOperationError_swigregister
InvalidOperationError_swigregister(InvalidOperationError)
class UnimplementedError(LogicError):
"""
UnimplementedError indicates an attempt to use an unimplemented
feature.
"""
__swig_setmethods__ = {}
for _s in [LogicError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, UnimplementedError, name, value)
__swig_getmethods__ = {}
for _s in [LogicError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, UnimplementedError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::UnimplementedError::UnimplementedError(const std::string
&msg_, int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.UnimplementedError_swiginit(self,_xapian.new_UnimplementedError(*args))
__swig_destroy__ = _xapian.delete_UnimplementedError
UnimplementedError_swigregister = _xapian.UnimplementedError_swigregister
UnimplementedError_swigregister(UnimplementedError)
class DatabaseError(RuntimeError):
"""
DatabaseError indicates some sort of database related error.
"""
__swig_setmethods__ = {}
for _s in [RuntimeError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, DatabaseError, name, value)
__swig_getmethods__ = {}
for _s in [RuntimeError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, DatabaseError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::DatabaseError::DatabaseError(const std::string &msg_, int
errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.DatabaseError_swiginit(self,_xapian.new_DatabaseError(*args))
__swig_destroy__ = _xapian.delete_DatabaseError
DatabaseError_swigregister = _xapian.DatabaseError_swigregister
DatabaseError_swigregister(DatabaseError)
class DatabaseCorruptError(DatabaseError):
"""
DatabaseCorruptError indicates database corruption was detected.
"""
__swig_setmethods__ = {}
for _s in [DatabaseError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, DatabaseCorruptError, name, value)
__swig_getmethods__ = {}
for _s in [DatabaseError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, DatabaseCorruptError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::DatabaseCorruptError::DatabaseCorruptError(const std::string
&msg_, int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.DatabaseCorruptError_swiginit(self,_xapian.new_DatabaseCorruptError(*args))
__swig_destroy__ = _xapian.delete_DatabaseCorruptError
DatabaseCorruptError_swigregister = _xapian.DatabaseCorruptError_swigregister
DatabaseCorruptError_swigregister(DatabaseCorruptError)
class DatabaseCreateError(DatabaseError):
"""
DatabaseCreateError indicates a failure to create a database.
"""
__swig_setmethods__ = {}
for _s in [DatabaseError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, DatabaseCreateError, name, value)
__swig_getmethods__ = {}
for _s in [DatabaseError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, DatabaseCreateError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::DatabaseCreateError::DatabaseCreateError(const std::string
&msg_, int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.DatabaseCreateError_swiginit(self,_xapian.new_DatabaseCreateError(*args))
__swig_destroy__ = _xapian.delete_DatabaseCreateError
DatabaseCreateError_swigregister = _xapian.DatabaseCreateError_swigregister
DatabaseCreateError_swigregister(DatabaseCreateError)
class DatabaseLockError(DatabaseError):
"""
DatabaseLockError indicates failure to lock a database.
"""
__swig_setmethods__ = {}
for _s in [DatabaseError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, DatabaseLockError, name, value)
__swig_getmethods__ = {}
for _s in [DatabaseError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, DatabaseLockError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::DatabaseLockError::DatabaseLockError(const std::string &msg_,
int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.DatabaseLockError_swiginit(self,_xapian.new_DatabaseLockError(*args))
__swig_destroy__ = _xapian.delete_DatabaseLockError
DatabaseLockError_swigregister = _xapian.DatabaseLockError_swigregister
DatabaseLockError_swigregister(DatabaseLockError)
class DatabaseModifiedError(DatabaseError):
"""
DatabaseModifiedError indicates a database was modified.
To recover after catching this error, you need to call
Xapian::Database::reopen() on the Database and repeat the operation
which failed.
"""
__swig_setmethods__ = {}
for _s in [DatabaseError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, DatabaseModifiedError, name, value)
__swig_getmethods__ = {}
for _s in [DatabaseError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, DatabaseModifiedError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::DatabaseModifiedError::DatabaseModifiedError(const std::string
&msg_, int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.DatabaseModifiedError_swiginit(self,_xapian.new_DatabaseModifiedError(*args))
__swig_destroy__ = _xapian.delete_DatabaseModifiedError
DatabaseModifiedError_swigregister = _xapian.DatabaseModifiedError_swigregister
DatabaseModifiedError_swigregister(DatabaseModifiedError)
class DatabaseOpeningError(DatabaseError):
"""
DatabaseOpeningError indicates failure to open a database.
"""
__swig_setmethods__ = {}
for _s in [DatabaseError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, DatabaseOpeningError, name, value)
__swig_getmethods__ = {}
for _s in [DatabaseError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, DatabaseOpeningError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::DatabaseOpeningError::DatabaseOpeningError(const std::string
&msg_, int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.DatabaseOpeningError_swiginit(self,_xapian.new_DatabaseOpeningError(*args))
__swig_destroy__ = _xapian.delete_DatabaseOpeningError
DatabaseOpeningError_swigregister = _xapian.DatabaseOpeningError_swigregister
DatabaseOpeningError_swigregister(DatabaseOpeningError)
class DatabaseVersionError(DatabaseOpeningError):
"""
DatabaseVersionError indicates that a database is in an unsupported
format.
From time to time, new versions of Xapian will require the database
format to be changed, to allow new information to be stored or new
optimisations to be performed. Backwards compatibility will sometimes
be maintained, so that new versions of Xapian can open old databases,
but in some cases Xapian will be unable to open a database because it
is in too old (or new) a format. This can be resolved either be
upgrading or downgrading the version of Xapian in use, or by
rebuilding the database from scratch with the current version of
Xapian.
"""
__swig_setmethods__ = {}
for _s in [DatabaseOpeningError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, DatabaseVersionError, name, value)
__swig_getmethods__ = {}
for _s in [DatabaseOpeningError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, DatabaseVersionError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::DatabaseVersionError::DatabaseVersionError(const std::string
&msg_, int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.DatabaseVersionError_swiginit(self,_xapian.new_DatabaseVersionError(*args))
__swig_destroy__ = _xapian.delete_DatabaseVersionError
DatabaseVersionError_swigregister = _xapian.DatabaseVersionError_swigregister
DatabaseVersionError_swigregister(DatabaseVersionError)
class DocNotFoundError(RuntimeError):
"""
Indicates an attempt to access a document not present in the database.
"""
__swig_setmethods__ = {}
for _s in [RuntimeError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, DocNotFoundError, name, value)
__swig_getmethods__ = {}
for _s in [RuntimeError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, DocNotFoundError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::DocNotFoundError::DocNotFoundError(const std::string &msg_,
int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.DocNotFoundError_swiginit(self,_xapian.new_DocNotFoundError(*args))
__swig_destroy__ = _xapian.delete_DocNotFoundError
DocNotFoundError_swigregister = _xapian.DocNotFoundError_swigregister
DocNotFoundError_swigregister(DocNotFoundError)
class FeatureUnavailableError(RuntimeError):
"""
Indicates an attempt to use a feature which is unavailable.
Typically a feature is unavailable because it wasn't compiled in, or
because it requires other software or facilities which aren't
available.
"""
__swig_setmethods__ = {}
for _s in [RuntimeError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, FeatureUnavailableError, name, value)
__swig_getmethods__ = {}
for _s in [RuntimeError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, FeatureUnavailableError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::FeatureUnavailableError::FeatureUnavailableError(const
std::string &msg_, int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.FeatureUnavailableError_swiginit(self,_xapian.new_FeatureUnavailableError(*args))
__swig_destroy__ = _xapian.delete_FeatureUnavailableError
FeatureUnavailableError_swigregister = _xapian.FeatureUnavailableError_swigregister
FeatureUnavailableError_swigregister(FeatureUnavailableError)
class InternalError(RuntimeError):
"""
InternalError indicates a runtime problem of some sort.
"""
__swig_setmethods__ = {}
for _s in [RuntimeError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, InternalError, name, value)
__swig_getmethods__ = {}
for _s in [RuntimeError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, InternalError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::InternalError::InternalError(const std::string &msg_, int
errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.InternalError_swiginit(self,_xapian.new_InternalError(*args))
__swig_destroy__ = _xapian.delete_InternalError
InternalError_swigregister = _xapian.InternalError_swigregister
InternalError_swigregister(InternalError)
class NetworkError(RuntimeError):
"""
Indicates a problem communicating with a remote database.
"""
__swig_setmethods__ = {}
for _s in [RuntimeError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, NetworkError, name, value)
__swig_getmethods__ = {}
for _s in [RuntimeError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, NetworkError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::NetworkError::NetworkError(const std::string &msg_, int
errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.NetworkError_swiginit(self,_xapian.new_NetworkError(*args))
__swig_destroy__ = _xapian.delete_NetworkError
NetworkError_swigregister = _xapian.NetworkError_swigregister
NetworkError_swigregister(NetworkError)
class NetworkTimeoutError(NetworkError):
"""
Indicates a timeout expired while communicating with a remote
database.
"""
__swig_setmethods__ = {}
for _s in [NetworkError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, NetworkTimeoutError, name, value)
__swig_getmethods__ = {}
for _s in [NetworkError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, NetworkTimeoutError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::NetworkTimeoutError::NetworkTimeoutError(const std::string
&msg_, int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.NetworkTimeoutError_swiginit(self,_xapian.new_NetworkTimeoutError(*args))
__swig_destroy__ = _xapian.delete_NetworkTimeoutError
NetworkTimeoutError_swigregister = _xapian.NetworkTimeoutError_swigregister
NetworkTimeoutError_swigregister(NetworkTimeoutError)
class QueryParserError(RuntimeError):
"""
Indicates a query string can't be parsed.
"""
__swig_setmethods__ = {}
for _s in [RuntimeError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, QueryParserError, name, value)
__swig_getmethods__ = {}
for _s in [RuntimeError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, QueryParserError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::QueryParserError::QueryParserError(const std::string &msg_,
int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.QueryParserError_swiginit(self,_xapian.new_QueryParserError(*args))
__swig_destroy__ = _xapian.delete_QueryParserError
QueryParserError_swigregister = _xapian.QueryParserError_swigregister
QueryParserError_swigregister(QueryParserError)
class SerialisationError(RuntimeError):
"""
Indicates an error in the std::string serialisation of an object.
"""
__swig_setmethods__ = {}
for _s in [RuntimeError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, SerialisationError, name, value)
__swig_getmethods__ = {}
for _s in [RuntimeError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, SerialisationError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::SerialisationError::SerialisationError(const std::string
&msg_, int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.SerialisationError_swiginit(self,_xapian.new_SerialisationError(*args))
__swig_destroy__ = _xapian.delete_SerialisationError
SerialisationError_swigregister = _xapian.SerialisationError_swigregister
SerialisationError_swigregister(SerialisationError)
class RangeError(RuntimeError):
"""
RangeError indicates an attempt to access outside the bounds of a
container.
"""
__swig_setmethods__ = {}
for _s in [RuntimeError]: __swig_setmethods__.update(getattr(_s,'__swig_setmethods__',{}))
__setattr__ = lambda self, name, value: _swig_setattr(self, RangeError, name, value)
__swig_getmethods__ = {}
for _s in [RuntimeError]: __swig_getmethods__.update(getattr(_s,'__swig_getmethods__',{}))
__getattr__ = lambda self, name: _swig_getattr(self, RangeError, name)
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct from message and errno value.
Xapian::RangeError::RangeError(const std::string &msg_, int errno_)
Parameters:
-----------
msg_: Message giving details of the error, intended for human
consumption.
errno_: Optional errno value associated with this error.
"""
_xapian.RangeError_swiginit(self,_xapian.new_RangeError(*args))
__swig_destroy__ = _xapian.delete_RangeError
RangeError_swigregister = _xapian.RangeError_swigregister
RangeError_swigregister(RangeError)
def version_string():
return _xapian.version_string()
version_string = _xapian.version_string
def major_version():
return _xapian.major_version()
major_version = _xapian.major_version
def minor_version():
return _xapian.minor_version()
minor_version = _xapian.minor_version
def revision():
return _xapian.revision()
revision = _xapian.revision
class PositionIterator(object):
"""
An iterator pointing to items in a list of positions.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Copying is allowed.
Xapian::PositionIterator::PositionIterator(const PositionIterator &o)
The internals are reference counted, so copying is also cheap.
"""
_xapian.PositionIterator_swiginit(self,_xapian.new_PositionIterator(*args))
__swig_destroy__ = _xapian.delete_PositionIterator
def skip_to(self, *args):
"""
Advance the iterator to the specified termpos.
void Xapian::PositionIterator::skip_to(Xapian::termpos pos)
If the specified termpos isn't in the list, position ourselves on the
first termpos after it (or at_end() if no greater term positions are
present).
"""
return _xapian.PositionIterator_skip_to(self, *args)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::PositionIterator::get_description() const
"""
return _xapian.PositionIterator___str__(self)
PositionIterator.get_termpos = new_instancemethod(_xapian.PositionIterator_get_termpos,None,PositionIterator)
PositionIterator.next = new_instancemethod(_xapian.PositionIterator_next,None,PositionIterator)
PositionIterator.equals = new_instancemethod(_xapian.PositionIterator_equals,None,PositionIterator)
PositionIterator.skip_to = new_instancemethod(_xapian.PositionIterator_skip_to,None,PositionIterator)
PositionIterator.__str__ = new_instancemethod(_xapian.PositionIterator___str__,None,PositionIterator)
PositionIterator.__eq__ = new_instancemethod(_xapian.PositionIterator___eq__,None,PositionIterator)
PositionIterator.__ne__ = new_instancemethod(_xapian.PositionIterator___ne__,None,PositionIterator)
PositionIterator_swigregister = _xapian.PositionIterator_swigregister
PositionIterator_swigregister(PositionIterator)
class PostingIterator(object):
"""
An iterator pointing to items in a list of postings.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
__swig_destroy__ = _xapian.delete_PostingIterator
def __init__(self, *args):
"""
Copying is allowed.
Xapian::PostingIterator::PostingIterator(const PostingIterator &other)
The internals are reference counted, so copying is also cheap.
"""
_xapian.PostingIterator_swiginit(self,_xapian.new_PostingIterator(*args))
def skip_to(self, *args):
"""
Advance the iterator to the specified docid.
void Xapian::PostingIterator::skip_to(Xapian::docid did)
If the specified docid isn't in the list, position ourselves on the
first document after it (or at_end() if no greater docids are
present).
"""
return _xapian.PostingIterator_skip_to(self, *args)
def get_doclength(self):
"""
Get the length of the document at the current position in the
postlist.
Xapian::termcount Xapian::PostingIterator::get_doclength() const
This information may be stored in the postlist, in which case this
lookup should be extremely fast (indeed, not require further disk
access). If the information is not present in the postlist, it will be
retrieved from the database, at a greater performance cost.
"""
return _xapian.PostingIterator_get_doclength(self)
def get_wdf(self):
"""
Get the within document frequency of the document at the current
position in the postlist.
Xapian::termcount Xapian::PostingIterator::get_wdf() const
"""
return _xapian.PostingIterator_get_wdf(self)
def positionlist_begin(self):
"""
Return PositionIterator pointing to start of positionlist for current
document.
PositionIterator Xapian::PostingIterator::positionlist_begin() const
"""
return _xapian.PostingIterator_positionlist_begin(self)
def positionlist_end(self):
"""
Return PositionIterator pointing to end of positionlist for current
document.
PositionIterator Xapian::PostingIterator::positionlist_end() const
"""
return _xapian.PostingIterator_positionlist_end(self)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::PostingIterator::get_description() const
"""
return _xapian.PostingIterator___str__(self)
PostingIterator.skip_to = new_instancemethod(_xapian.PostingIterator_skip_to,None,PostingIterator)
PostingIterator.get_doclength = new_instancemethod(_xapian.PostingIterator_get_doclength,None,PostingIterator)
PostingIterator.get_wdf = new_instancemethod(_xapian.PostingIterator_get_wdf,None,PostingIterator)
PostingIterator.positionlist_begin = new_instancemethod(_xapian.PostingIterator_positionlist_begin,None,PostingIterator)
PostingIterator.positionlist_end = new_instancemethod(_xapian.PostingIterator_positionlist_end,None,PostingIterator)
PostingIterator.__str__ = new_instancemethod(_xapian.PostingIterator___str__,None,PostingIterator)
PostingIterator.__eq__ = new_instancemethod(_xapian.PostingIterator___eq__,None,PostingIterator)
PostingIterator.__ne__ = new_instancemethod(_xapian.PostingIterator___ne__,None,PostingIterator)
PostingIterator.get_docid = new_instancemethod(_xapian.PostingIterator_get_docid,None,PostingIterator)
PostingIterator.next = new_instancemethod(_xapian.PostingIterator_next,None,PostingIterator)
PostingIterator.equals = new_instancemethod(_xapian.PostingIterator_equals,None,PostingIterator)
PostingIterator_swigregister = _xapian.PostingIterator_swigregister
PostingIterator_swigregister(PostingIterator)
def __eq__(*args):
return _xapian.__eq__(*args)
__eq__ = _xapian.__eq__
def __ne__(*args):
return _xapian.__ne__(*args)
__ne__ = _xapian.__ne__
class TermIterator(object):
"""
An iterator pointing to items in a list of terms.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Copying is allowed.
Xapian::TermIterator::TermIterator(const TermIterator &other)
The internals are reference counted, so copying is also cheap.
"""
_xapian.TermIterator_swiginit(self,_xapian.new_TermIterator(*args))
__swig_destroy__ = _xapian.delete_TermIterator
def skip_to(self, *args):
"""
Advance the iterator to the specified term.
void Xapian::TermIterator::skip_to(const std::string &tname)
If the specified term isn't in the list, position ourselves on the
first term after it (or at_end() if no greater terms are present).
"""
return _xapian.TermIterator_skip_to(self, *args)
def get_wdf(self):
"""
Return the wdf of the current term (if meaningful).
Xapian::termcount Xapian::TermIterator::get_wdf() const
The wdf (within document frequency) is the number of occurrences of a
term in a particular document.
"""
return _xapian.TermIterator_get_wdf(self)
def get_termfreq(self):
"""
Return the term frequency of the current term (if meaningful).
Xapian::doccount Xapian::TermIterator::get_termfreq() const
The term frequency is the number of documents which a term indexes.
"""
return _xapian.TermIterator_get_termfreq(self)
def positionlist_count(self):
"""
Return length of positionlist for current term.
Xapian::termcount Xapian::TermIterator::positionlist_count() const
"""
return _xapian.TermIterator_positionlist_count(self)
def positionlist_begin(self):
"""
Return PositionIterator pointing to start of positionlist for current
term.
PositionIterator Xapian::TermIterator::positionlist_begin() const
"""
return _xapian.TermIterator_positionlist_begin(self)
def positionlist_end(self):
"""
Return PositionIterator pointing to end of positionlist for current
term.
PositionIterator Xapian::TermIterator::positionlist_end() const
"""
return _xapian.TermIterator_positionlist_end(self)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::TermIterator::get_description() const
"""
return _xapian.TermIterator___str__(self)
TermIterator.get_term = new_instancemethod(_xapian.TermIterator_get_term,None,TermIterator)
TermIterator.next = new_instancemethod(_xapian.TermIterator_next,None,TermIterator)
TermIterator.equals = new_instancemethod(_xapian.TermIterator_equals,None,TermIterator)
TermIterator.skip_to = new_instancemethod(_xapian.TermIterator_skip_to,None,TermIterator)
TermIterator.get_wdf = new_instancemethod(_xapian.TermIterator_get_wdf,None,TermIterator)
TermIterator.get_termfreq = new_instancemethod(_xapian.TermIterator_get_termfreq,None,TermIterator)
TermIterator.positionlist_count = new_instancemethod(_xapian.TermIterator_positionlist_count,None,TermIterator)
TermIterator.positionlist_begin = new_instancemethod(_xapian.TermIterator_positionlist_begin,None,TermIterator)
TermIterator.positionlist_end = new_instancemethod(_xapian.TermIterator_positionlist_end,None,TermIterator)
TermIterator.__str__ = new_instancemethod(_xapian.TermIterator___str__,None,TermIterator)
TermIterator.__eq__ = new_instancemethod(_xapian.TermIterator___eq__,None,TermIterator)
TermIterator.__ne__ = new_instancemethod(_xapian.TermIterator___ne__,None,TermIterator)
TermIterator_swigregister = _xapian.TermIterator_swigregister
TermIterator_swigregister(TermIterator)
class ValueIterator(object):
"""
Class for iterating over document values.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Default constructor.
Xapian::ValueIterator::ValueIterator()
Creates an uninitialised iterator, which can't be used before being
assigned to, but is sometimes syntactically convenient.
"""
_xapian.ValueIterator_swiginit(self,_xapian.new_ValueIterator(*args))
__swig_destroy__ = _xapian.delete_ValueIterator
def get_docid(self):
"""
Return the docid at the current position.
Xapian::docid Xapian::ValueIterator::get_docid() const
If we're iterating over values of a document, this method will throw
Xapian::InvalidOperationError.
"""
return _xapian.ValueIterator_get_docid(self)
def get_valueno(self):
"""
Return the value slot number for the current position.
Xapian::valueno Xapian::ValueIterator::get_valueno() const
If the iterator is over all values in a slot, this returns that slot's
number. If the iterator is over the values in a particular document,
it returns the number of each slot in turn.
"""
return _xapian.ValueIterator_get_valueno(self)
def skip_to(self, *args):
"""
Advance the iterator to document id or value slot docid_or_slot.
void Xapian::ValueIterator::skip_to(Xapian::docid docid_or_slot)
If this iterator is over values in a document, then this method
advances the iterator to value slot docid_or_slot, or the first slot
after it if there is no value in slot slot.
If this iterator is over values in a particular slot, then this method
advances the iterator to document id docid_or_slot, or the first
document id after it if there is no value in the slot we're iterating
over for document docid_or_slot.
Note: The "two-faced" nature of this method is due to how C++
overloading works. Xapian::docid and Xapian::valueno are both typedefs
for the same unsigned integer type, so overloading can't distinguish
them.
Parameters:
-----------
docid_or_slot: The docid/slot to advance to.
"""
return _xapian.ValueIterator_skip_to(self, *args)
def check(self, *args):
"""
Check if the specified docid occurs.
bool Xapian::ValueIterator::check(Xapian::docid docid)
The caller is required to ensure that the specified document id did
actually exists in the database.
This method acts like skip_to() if that can be done at little extra
cost, in which case it then returns true. This is how brass and chert
databases behave because they store values in streams which allow for
an efficient implementation of skip_to().
Otherwise it simply checks if a particular docid is present. If it is,
it returns true. If it isn't, it returns false, and leaves the
position unspecified (and hence the result of calling methods which
depends on the current position, such as get_docid(), are also
unspecified). In this state, next() will advance to the first matching
position after document did, and skip_to() will act as it would if the
position was the first matching position after document did.
Currently the inmemory, flint, and remote backends behave in the
latter way because they don't support streamed values and so skip_to()
must check each document it skips over which is significantly slower.
Parameters:
-----------
docid: The document id to check.
"""
return _xapian.ValueIterator_check(self, *args)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::ValueIterator::get_description() const
"""
return _xapian.ValueIterator___str__(self)
ValueIterator.get_value = new_instancemethod(_xapian.ValueIterator_get_value,None,ValueIterator)
ValueIterator.next = new_instancemethod(_xapian.ValueIterator_next,None,ValueIterator)
ValueIterator.equals = new_instancemethod(_xapian.ValueIterator_equals,None,ValueIterator)
ValueIterator.get_docid = new_instancemethod(_xapian.ValueIterator_get_docid,None,ValueIterator)
ValueIterator.get_valueno = new_instancemethod(_xapian.ValueIterator_get_valueno,None,ValueIterator)
ValueIterator.skip_to = new_instancemethod(_xapian.ValueIterator_skip_to,None,ValueIterator)
ValueIterator.check = new_instancemethod(_xapian.ValueIterator_check,None,ValueIterator)
ValueIterator.__str__ = new_instancemethod(_xapian.ValueIterator___str__,None,ValueIterator)
ValueIterator.__eq__ = new_instancemethod(_xapian.ValueIterator___eq__,None,ValueIterator)
ValueIterator.__ne__ = new_instancemethod(_xapian.ValueIterator___ne__,None,ValueIterator)
ValueIterator_swigregister = _xapian.ValueIterator_swigregister
ValueIterator_swigregister(ValueIterator)
class Document(object):
"""
A handle representing a document in a Xapian database.
The Document class fetches information from the database lazily.
Usually this behaviour isn't visible to users (except for the speed
benefits), but if the document in the database is modified or deleted,
then preexisting Document objects may return the old or new versions
of data (or throw Xapian::DocNotFoundError in the case of deletion).
Since Database objects work on a snapshot of the database's state, the
situation above can only happen with a WritableDatabase object, or if
you call Database::reopen() on a Database object.
We recommend you avoid designs where this behaviour is an issue, but
if you need a way to make a non-lazy version of a Document object, you
can do this like so:doc =
Xapian::Document::unserialise(doc.serialise());
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Make a new empty Document.
Xapian::Document::Document()
"""
_xapian.Document_swiginit(self,_xapian.new_Document(*args))
__swig_destroy__ = _xapian.delete_Document
def get_value(self, *args):
"""
Get value by number.
std::string Xapian::Document::get_value(Xapian::valueno slot) const
Returns an empty string if no value with the given number is present
in the document.
Parameters:
-----------
slot: The number of the value.
"""
return _xapian.Document_get_value(self, *args)
def add_value(self, *args):
"""
Add a new value.
void Xapian::Document::add_value(Xapian::valueno slot, const
std::string &value)
The new value will replace any existing value with the same number (or
if the new value is empty, it will remove any existing value with the
same number).
Parameters:
-----------
slot: The value slot to add the value in.
value: The value to set.
"""
return _xapian.Document_add_value(self, *args)
def remove_value(self, *args):
"""
Remove any value with the given number.
void Xapian::Document::remove_value(Xapian::valueno slot)
"""
return _xapian.Document_remove_value(self, *args)
def clear_values(self):
"""
Remove all values associated with the document.
void Xapian::Document::clear_values()
"""
return _xapian.Document_clear_values(self)
def get_data(self):
"""
Get data stored in the document.
std::string Xapian::Document::get_data() const
This is potentially a relatively expensive operation, and shouldn't
normally be used during the match (e.g. in a PostingSource or match
decider functor. Put data for use by match deciders in a value
instead.
"""
return _xapian.Document_get_data(self)
def set_data(self, *args):
"""
Set data stored in the document.
void Xapian::Document::set_data(const std::string &data)
Xapian treats the data as an opaque blob. It may try to compress it,
but other than that it will just store it and return it when
requested.
Parameters:
-----------
data: The data to store.
"""
return _xapian.Document_set_data(self, *args)
def add_posting(self, *args):
"""
Add an occurrence of a term at a particular position.
void Xapian::Document::add_posting(const std::string &tname,
Xapian::termpos tpos, Xapian::termcount wdfinc=1)
Multiple occurrences of the term at the same position are represented
only once in the positional information, but do increase the wdf.
If the term is not already in the document, it will be added to it.
Parameters:
-----------
tname: The name of the term.
tpos: The position of the term.
wdfinc: The increment that will be applied to the wdf for this term.
"""
return _xapian.Document_add_posting(self, *args)
def add_term(self, *args):
"""
Add a term to the document, without positional information.
void Xapian::Document::add_term(const std::string &tname,
Xapian::termcount wdfinc=1)
Any existing positional information for the term will be left
unmodified.
Parameters:
-----------
tname: The name of the term.
wdfinc: The increment that will be applied to the wdf for this term
(default: 1).
"""
return _xapian.Document_add_term(self, *args)
def add_boolean_term(self, *args):
"""
Add a boolean filter term to the document.
void Xapian::Document::add_boolean_term(const std::string &term)
This method adds term to the document with wdf of 0 - this is
generally what you want for a term used for boolean filtering as the
wdf of such terms is ignored, and it doesn't make sense for them to
contribute to the document's length.
If the specified term already indexes this document, this method has
no effect.
It is exactly the same as add_term(term, 0).
This method was added in Xapian 1.0.18.
Parameters:
-----------
term: The term to add.
"""
return _xapian.Document_add_boolean_term(self, *args)
def remove_posting(self, *args):
"""
Remove a posting of a term from the document.
void Xapian::Document::remove_posting(const std::string &tname,
Xapian::termpos tpos, Xapian::termcount wdfdec=1)
Note that the term will still index the document even if all
occurrences are removed. To remove a term from a document completely,
use remove_term().
Parameters:
-----------
tname: The name of the term.
tpos: The position of the term.
wdfdec: The decrement that will be applied to the wdf when removing
this posting. The wdf will not go below the value of 0.
Parameters:
-----------
Xapian::InvalidArgumentError: will be thrown if the term is not at
the position specified in the position list for this term in this
document.
Xapian::InvalidArgumentError: will be thrown if the term is not in
the document
"""
return _xapian.Document_remove_posting(self, *args)
def remove_term(self, *args):
"""
Remove a term and all postings associated with it.
void Xapian::Document::remove_term(const std::string &tname)
Parameters:
-----------
tname: The name of the term.
Parameters:
-----------
Xapian::InvalidArgumentError: will be thrown if the term is not in
the document
"""
return _xapian.Document_remove_term(self, *args)
def clear_terms(self):
"""
Remove all terms (and postings) from the document.
void Xapian::Document::clear_terms()
"""
return _xapian.Document_clear_terms(self)
def termlist_count(self):
"""
The length of the termlist - i.e.
Xapian::termcount Xapian::Document::termlist_count() const
the number of different terms which index this document.
"""
return _xapian.Document_termlist_count(self)
def termlist_begin(self):
"""
Iterator for the terms in this document.
TermIterator Xapian::Document::termlist_begin() const
"""
return _xapian.Document_termlist_begin(self)
def termlist_end(self):
"""
Equivalent end iterator for termlist_begin().
TermIterator Xapian::Document::termlist_end() const
"""
return _xapian.Document_termlist_end(self)
def values_count(self):
"""
Count the values in this document.
Xapian::termcount Xapian::Document::values_count() const
"""
return _xapian.Document_values_count(self)
def values_begin(self):
"""
Iterator for the values in this document.
ValueIterator Xapian::Document::values_begin() const
"""
return _xapian.Document_values_begin(self)
def values_end(self):
"""
Equivalent end iterator for values_begin().
ValueIteratorEnd_ Xapian::Document::values_end() const
"""
return _xapian.Document_values_end(self)
def get_docid(self):
"""
Get the document id which is associated with this document (if any).
docid Xapian::Document::get_docid() const
NB If multiple databases are being searched together, then this will
be the document id in the individual database, not the merged
database!
If this document came from a database, return the document id in that
database. Otherwise, return 0 (in Xapian 1.0.22/1.2.4 or later; prior
to this the returned value was uninitialised).
"""
return _xapian.Document_get_docid(self)
def serialise(self):
"""
Serialise document into a string.
std::string Xapian::Document::serialise() const
The document representation may change between Xapian releases: even
between minor versions. However, it is guaranteed not to change if the
remote database protocol has not changed between releases.
"""
return _xapian.Document_serialise(self)
unserialise = staticmethod(_xapian.Document_unserialise)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::Document::get_description() const
"""
return _xapian.Document___str__(self)
Document.get_value = new_instancemethod(_xapian.Document_get_value,None,Document)
Document.add_value = new_instancemethod(_xapian.Document_add_value,None,Document)
Document.remove_value = new_instancemethod(_xapian.Document_remove_value,None,Document)
Document.clear_values = new_instancemethod(_xapian.Document_clear_values,None,Document)
Document.get_data = new_instancemethod(_xapian.Document_get_data,None,Document)
Document.set_data = new_instancemethod(_xapian.Document_set_data,None,Document)
Document.add_posting = new_instancemethod(_xapian.Document_add_posting,None,Document)
Document.add_term = new_instancemethod(_xapian.Document_add_term,None,Document)
Document.add_boolean_term = new_instancemethod(_xapian.Document_add_boolean_term,None,Document)
Document.remove_posting = new_instancemethod(_xapian.Document_remove_posting,None,Document)
Document.remove_term = new_instancemethod(_xapian.Document_remove_term,None,Document)
Document.clear_terms = new_instancemethod(_xapian.Document_clear_terms,None,Document)
Document.termlist_count = new_instancemethod(_xapian.Document_termlist_count,None,Document)
Document.termlist_begin = new_instancemethod(_xapian.Document_termlist_begin,None,Document)
Document.termlist_end = new_instancemethod(_xapian.Document_termlist_end,None,Document)
Document.values_count = new_instancemethod(_xapian.Document_values_count,None,Document)
Document.values_begin = new_instancemethod(_xapian.Document_values_begin,None,Document)
Document.values_end = new_instancemethod(_xapian.Document_values_end,None,Document)
Document.get_docid = new_instancemethod(_xapian.Document_get_docid,None,Document)
Document.serialise = new_instancemethod(_xapian.Document_serialise,None,Document)
Document.__str__ = new_instancemethod(_xapian.Document___str__,None,Document)
Document_swigregister = _xapian.Document_swigregister
Document_swigregister(Document)
def Document_unserialise(*args):
return _xapian.Document_unserialise(*args)
Document_unserialise = _xapian.Document_unserialise
class PostingSource(object):
"""
Base class which provides an "external" source of postings.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self):
if self.__class__ == PostingSource:
_self = None
else:
_self = self
_xapian.PostingSource_swiginit(self,_xapian.new_PostingSource(_self, ))
__swig_destroy__ = _xapian.delete_PostingSource
def get_termfreq_min(self):
"""
A lower bound on the number of documents this object can return.
virtual Xapian::doccount Xapian::PostingSource::get_termfreq_min()
const =0
Xapian will always call init() on a PostingSource before calling this
for the first time.
"""
return _xapian.PostingSource_get_termfreq_min(self)
def get_termfreq_est(self):
"""
An estimate of the number of documents this object can return.
virtual Xapian::doccount Xapian::PostingSource::get_termfreq_est()
const =0
It must always be true that:
get_termfreq_min() <= get_termfreq_est() <= get_termfreq_max()
Xapian will always call init() on a PostingSource before calling this
for the first time.
"""
return _xapian.PostingSource_get_termfreq_est(self)
def get_termfreq_max(self):
"""
An upper bound on the number of documents this object can return.
virtual Xapian::doccount Xapian::PostingSource::get_termfreq_max()
const =0
Xapian will always call init() on a PostingSource before calling this
for the first time.
"""
return _xapian.PostingSource_get_termfreq_max(self)
def get_maxweight(self):
"""
Return the currently set upper bound on what get_weight() can return.
Xapian::weight Xapian::PostingSource::get_maxweight() const
"""
return _xapian.PostingSource_get_maxweight(self)
def get_weight(self):
"""
Return the weight contribution for the current document.
virtual Xapian::weight Xapian::PostingSource::get_weight() const
This default implementation always returns 0, for convenience when
implementing "weight-less" PostingSource subclasses.
This method may assume that it will only be called when there is a
"current document". In detail: Xapian will always call init() on a
PostingSource before calling this for the first time. It will also
only call this if the PostingSource reports that it is pointing to a
valid document (ie, it will not call it before calling at least one of
next(), skip_to() or check(), and will ensure that the PostingSource
is not at the end by calling at_end()).
"""
return _xapian.PostingSource_get_weight(self)
def get_docid(self):
"""
Return the current docid.
virtual Xapian::docid Xapian::PostingSource::get_docid() const =0
This method may assume that it will only be called when there is a
"current document". See get_weight() for details.
Note: in the case of a multi-database search, the returned docid
should be in the single subdatabase relevant to this posting source.
See the init() method for details.
"""
return _xapian.PostingSource_get_docid(self)
def next(self, *args):
"""
Advance the current position to the next matching document.
virtual void Xapian::PostingSource::next(Xapian::weight min_wt)=0
The PostingSource starts before the first entry in the list, so next()
must be called before any methods which need the context of the
current position.
Xapian will always call init() on a PostingSource before calling this
for the first time.
Parameters:
-----------
min_wt: The minimum weight contribution that is needed (this is just
a hint which subclasses may ignore).
"""
return _xapian.PostingSource_next(self, *args)
def skip_to(self, *args):
"""
Advance to the specified docid.
virtual void Xapian::PostingSource::skip_to(Xapian::docid did,
Xapian::weight min_wt)
If the specified docid isn't in the list, position ourselves on the
first document after it (or at_end() if no greater docids are
present).
If the current position is already the specified docid, this method
will leave the position unmodified.
If the specified docid is earlier than the current position, the
behaviour is unspecified. A sensible behaviour would be to leave the
current position unmodified, but it is also reasonable to move to the
specified docid.
The default implementation calls next() repeatedly, which works but
skip_to() can often be implemented much more efficiently.
Xapian will always call init() on a PostingSource before calling this
for the first time.
Note: in the case of a multi-database search, the docid specified is
the docid in the single subdatabase relevant to this posting source.
See the init() method for details.
Parameters:
-----------
did: The document id to advance to.
min_wt: The minimum weight contribution that is needed (this is just
a hint which subclasses may ignore).
"""
return _xapian.PostingSource_skip_to(self, *args)
def check(self, *args):
"""
Check if the specified docid occurs.
virtual bool Xapian::PostingSource::check(Xapian::docid did,
Xapian::weight min_wt)
The caller is required to ensure that the specified document id did
actually exists in the database. If it does, it must move to that
document id, and return true. If it does not, it may either:
return true, having moved to a definite position (including
"at_end"), which must be the same position as skip_to() would have
moved to.
or
return false, having moved to an "indeterminate" position, such that
a subsequent call to next() or skip_to() will move to the next
matching position after did.
Generally, this method should act like skip_to() and return true if
that can be done at little extra cost.
Otherwise it should simply check if a particular docid is present,
returning true if it is, and false if it isn't.
The default implementation calls skip_to() and always returns true.
Xapian will always call init() on a PostingSource before calling this
for the first time.
Note: in the case of a multi-database search, the docid specified is
the docid in the single subdatabase relevant to this posting source.
See the init() method for details.
Parameters:
-----------
did: The document id to check.
min_wt: The minimum weight contribution that is needed (this is just
a hint which subclasses may ignore).
"""
return _xapian.PostingSource_check(self, *args)
def at_end(self):
"""
Return true if the current position is past the last entry in this
list.
virtual bool Xapian::PostingSource::at_end() const =0
At least one of next(), skip_to() or check() will be called before
this method is first called.
"""
return _xapian.PostingSource_at_end(self)
def name(self):
"""
Name of the posting source class.
virtual std::string Xapian::PostingSource::name() const
This is used when serialising and unserialising posting sources; for
example, for performing remote searches.
If the subclass is in a C++ namespace, the namespace should be
included in the name, using "::" as a separator. For example, for a
PostingSource subclass called "FooPostingSource" in the "Xapian"
namespace the result of this call should be
"Xapian::FooPostingSource".
This should only be implemented if serialise() and unserialise() are
also implemented. The default implementation returns an empty string.
If this returns an empty string, Xapian will assume that serialise()
and unserialise() are not implemented.
"""
return _xapian.PostingSource_name(self)
def init(self, *args):
"""
Set this PostingSource to the start of the list of postings.
virtual void Xapian::PostingSource::init(const Database &db)=0
This is called automatically by the matcher prior to each query being
processed.
If a PostingSource is used for multiple searches, init() will
therefore be called multiple times, and must handle this by using the
database passed in the most recent call.
Parameters:
-----------
db: The database which the PostingSource should iterate through.
Note: the database supplied to this method must not be modified: in
particular, the reopen() method should not be called on it.
Note: in the case of a multi-database search, a separate PostingSource
will be used for each database (the separate PostingSources will be
obtained using clone()), and each PostingSource will be passed one of
the sub-databases as the db parameter here. The db parameter will
therefore always refer to a single database. All docids passed to, or
returned from, the PostingSource refer to docids in that single
database, rather than in the multi- database.
"""
return _xapian.PostingSource_init(self, *args)
def __str__(self):
"""
Return a string describing this object.
virtual std::string Xapian::PostingSource::get_description() const
This default implementation returns a generic answer. This default it
provided to avoid forcing those deriving their own PostingSource
subclass from having to implement this (they may not care what
get_description() gives for their subclass).
"""
return _xapian.PostingSource___str__(self)
def __disown__(self):
self.this.disown()
_xapian.disown_PostingSource(self)
return weakref_proxy(self)
PostingSource.get_termfreq_min = new_instancemethod(_xapian.PostingSource_get_termfreq_min,None,PostingSource)
PostingSource.get_termfreq_est = new_instancemethod(_xapian.PostingSource_get_termfreq_est,None,PostingSource)
PostingSource.get_termfreq_max = new_instancemethod(_xapian.PostingSource_get_termfreq_max,None,PostingSource)
PostingSource.get_maxweight = new_instancemethod(_xapian.PostingSource_get_maxweight,None,PostingSource)
PostingSource.get_weight = new_instancemethod(_xapian.PostingSource_get_weight,None,PostingSource)
PostingSource.get_docid = new_instancemethod(_xapian.PostingSource_get_docid,None,PostingSource)
PostingSource.next = new_instancemethod(_xapian.PostingSource_next,None,PostingSource)
PostingSource.skip_to = new_instancemethod(_xapian.PostingSource_skip_to,None,PostingSource)
PostingSource.check = new_instancemethod(_xapian.PostingSource_check,None,PostingSource)
PostingSource.at_end = new_instancemethod(_xapian.PostingSource_at_end,None,PostingSource)
PostingSource.name = new_instancemethod(_xapian.PostingSource_name,None,PostingSource)
PostingSource.init = new_instancemethod(_xapian.PostingSource_init,None,PostingSource)
PostingSource.__str__ = new_instancemethod(_xapian.PostingSource___str__,None,PostingSource)
PostingSource_swigregister = _xapian.PostingSource_swigregister
PostingSource_swigregister(PostingSource)
class ValuePostingSource(PostingSource):
"""
A posting source which generates weights from a value slot.
This is a base class for classes which generate weights using values
stored in the specified slot. For example, ValueWeightPostingSource
uses sortable_unserialise to convert values directly to weights.
The upper bound on the weight returned is set to DBL_MAX. Subclasses
should call set_maxweight() in their init() methods after calling
ValuePostingSource::init() if they know a tighter bound on the weight.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct a ValuePostingSource.
Xapian::ValuePostingSource::ValuePostingSource(Xapian::valueno slot_)
Parameters:
-----------
slot_: The value slot to read values from.
"""
_xapian.ValuePostingSource_swiginit(self,_xapian.new_ValuePostingSource(*args))
__swig_destroy__ = _xapian.delete_ValuePostingSource
ValuePostingSource_swigregister = _xapian.ValuePostingSource_swigregister
ValuePostingSource_swigregister(ValuePostingSource)
class ValueWeightPostingSource(ValuePostingSource):
"""
A posting source which reads weights from a value slot.
This returns entries for all documents in the given database which
have a non empty values in the specified slot. It returns a weight
calculated by applying sortable_unserialise to the value stored in the
slot (so the values stored should probably have been calculated by
applying sortable_serialise to a floating point number at index time).
The upper bound on the weight returned is set using the upper bound on
the values in the specified slot, or DBL_MAX if value bounds aren't
supported by the current backend.
For efficiency, this posting source doesn't check that the stored
values are valid in any way, so it will never raise an exception due
to invalid stored values. In particular, it doesn't ensure that the
unserialised values are positive, which is a requirement for weights.
The behaviour if the slot contains values which unserialise to
negative values is undefined.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct a ValueWeightPostingSource.
Xapian::ValueWeightPostingSource::ValueWeightPostingSource(Xapian::valueno
slot_)
Parameters:
-----------
slot_: The value slot to read values from.
"""
_xapian.ValueWeightPostingSource_swiginit(self,_xapian.new_ValueWeightPostingSource(*args))
__swig_destroy__ = _xapian.delete_ValueWeightPostingSource
ValueWeightPostingSource_swigregister = _xapian.ValueWeightPostingSource_swigregister
ValueWeightPostingSource_swigregister(ValueWeightPostingSource)
class DecreasingValueWeightPostingSource(ValueWeightPostingSource):
"""
Read weights from a value which is known to decrease as docid
increases.
This posting source can be used, like ValueWeightPostingSource, to add
a weight contribution to a query based on the values stored in a slot.
The values in the slot must be serialised as by sortable_serialise().
However, this posting source is additionally given a range of document
IDs, within which the weight is known to be decreasing. ie, for all
documents with ids A and B within this range (including the
endpoints), where A is less than B, the weight of A is less than or
equal to the weight of B. This can allow the posting source to skip to
the end of the range quickly if insufficient weight is left in the
posting source for a particular source.
By default, the range is assumed to cover all document IDs.
The ordering property can be arranged at index time, or by sorting an
indexed database to produce a new, sorted, database.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Xapian::DecreasingValueWeightPostingSource::DecreasingValueWeightPostingSource(Xapian::valueno
slot_, Xapian::docid range_start_=0, Xapian::docid range_end_=0)
"""
_xapian.DecreasingValueWeightPostingSource_swiginit(self,_xapian.new_DecreasingValueWeightPostingSource(*args))
__swig_destroy__ = _xapian.delete_DecreasingValueWeightPostingSource
DecreasingValueWeightPostingSource_swigregister = _xapian.DecreasingValueWeightPostingSource_swigregister
DecreasingValueWeightPostingSource_swigregister(DecreasingValueWeightPostingSource)
class ValueMapPostingSource(ValuePostingSource):
"""
A posting source which looks up weights in a map using values as the
key.
This allows will return entries for all documents in the given
database which have a value in the slot specified. The values will be
mapped to the corresponding weight in the weight map. If there is no
mapping for a particular value, the default weight will be returned
(which itself defaults to 0.0).
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct a ValueWeightPostingSource.
Xapian::ValueMapPostingSource::ValueMapPostingSource(Xapian::valueno
slot_)
Parameters:
-----------
slot_: The value slot to read values from.
"""
_xapian.ValueMapPostingSource_swiginit(self,_xapian.new_ValueMapPostingSource(*args))
def add_mapping(self, *args):
"""
Add a mapping.
void Xapian::ValueMapPostingSource::add_mapping(const std::string
&key, double wt)
Parameters:
-----------
key: The key looked up from the value slot.
wt: The weight to give this key.
"""
return _xapian.ValueMapPostingSource_add_mapping(self, *args)
def clear_mappings(self):
"""
Clear all mappings.
void Xapian::ValueMapPostingSource::clear_mappings()
"""
return _xapian.ValueMapPostingSource_clear_mappings(self)
def set_default_weight(self, *args):
"""
Set a default weight for document values not in the map.
void Xapian::ValueMapPostingSource::set_default_weight(double wt)
Parameters:
-----------
wt: The weight to set as the default.
"""
return _xapian.ValueMapPostingSource_set_default_weight(self, *args)
__swig_destroy__ = _xapian.delete_ValueMapPostingSource
ValueMapPostingSource.add_mapping = new_instancemethod(_xapian.ValueMapPostingSource_add_mapping,None,ValueMapPostingSource)
ValueMapPostingSource.clear_mappings = new_instancemethod(_xapian.ValueMapPostingSource_clear_mappings,None,ValueMapPostingSource)
ValueMapPostingSource.set_default_weight = new_instancemethod(_xapian.ValueMapPostingSource_set_default_weight,None,ValueMapPostingSource)
ValueMapPostingSource_swigregister = _xapian.ValueMapPostingSource_swigregister
ValueMapPostingSource_swigregister(ValueMapPostingSource)
class FixedWeightPostingSource(PostingSource):
"""
A posting source which returns a fixed weight for all documents.
This returns entries for all documents in the given database, with a
fixed weight (specified by a parameter to the constructor).
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct a FixedWeightPostingSource.
Xapian::FixedWeightPostingSource::FixedWeightPostingSource(Xapian::weight
wt)
Parameters:
-----------
wt: The fixed weight to return.
"""
_xapian.FixedWeightPostingSource_swiginit(self,_xapian.new_FixedWeightPostingSource(*args))
__swig_destroy__ = _xapian.delete_FixedWeightPostingSource
FixedWeightPostingSource_swigregister = _xapian.FixedWeightPostingSource_swigregister
FixedWeightPostingSource_swigregister(FixedWeightPostingSource)
class MSet(object):
"""
A match set ( MSet).
This class represents (a portion of) the results of a query.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Copying is allowed (and is cheap).
Xapian::MSet::MSet(const MSet &other)
"""
_xapian.MSet_swiginit(self,_xapian.new_MSet(*args))
__swig_destroy__ = _xapian.delete_MSet
def fetch(self, *args):
"""
Fetch all the items in the MSet.
void Xapian::MSet::fetch() const
"""
return _xapian.MSet_fetch(self, *args)
def convert_to_percent(self, *args):
"""
Return the percentage score for a particular item.
Xapian::percent Xapian::MSet::convert_to_percent(const MSetIterator
&it) const
"""
return _xapian.MSet_convert_to_percent(self, *args)
def get_termfreq(self, *args):
"""
Return the term frequency of the given query term.
Xapian::doccount Xapian::MSet::get_termfreq(const std::string &tname)
const
Parameters:
-----------
tname: The term to look for.
This is sometimes more efficient than asking the database directly for
the term frequency - in particular, if the term was in the query, its
frequency will usually be cached in the MSet.
"""
return _xapian.MSet_get_termfreq(self, *args)
def get_termweight(self, *args):
"""
Return the term weight of the given query term.
Xapian::weight Xapian::MSet::get_termweight(const std::string &tname)
const
Parameters:
-----------
tname: The term to look for.
Parameters:
-----------
Xapian::InvalidArgumentError: is thrown if the term was not in the
query.
"""
return _xapian.MSet_get_termweight(self, *args)
def get_firstitem(self):
"""
The index of the first item in the result which was put into the MSet.
Xapian::doccount Xapian::MSet::get_firstitem() const
This corresponds to the parameter "first" specified in
Xapian::Enquire::get_mset(). A value of 0 corresponds to the highest
result being the first item in the MSet.
"""
return _xapian.MSet_get_firstitem(self)
def get_matches_lower_bound(self):
"""
A lower bound on the number of documents in the database which match
the query.
Xapian::doccount Xapian::MSet::get_matches_lower_bound() const
This figure takes into account collapsing of duplicates, and weighting
cutoff values.
This number is usually considerably less than the actual number of
documents which match the query.
"""
return _xapian.MSet_get_matches_lower_bound(self)
def get_matches_estimated(self):
"""
An estimate for the number of documents in the database which match
the query.
Xapian::doccount Xapian::MSet::get_matches_estimated() const
This figure takes into account collapsing of duplicates, and weighting
cutoff values.
This value is returned because there is sometimes a request to display
such information. However, our experience is that presenting this
value to users causes them to worry about the large number of results,
rather than how useful those at the top of the result set are, and is
thus undesirable.
"""
return _xapian.MSet_get_matches_estimated(self)
def get_matches_upper_bound(self):
"""
An upper bound on the number of documents in the database which match
the query.
Xapian::doccount Xapian::MSet::get_matches_upper_bound() const
This figure takes into account collapsing of duplicates, and weighting
cutoff values.
This number is usually considerably greater than the actual number of
documents which match the query.
"""
return _xapian.MSet_get_matches_upper_bound(self)
def get_uncollapsed_matches_lower_bound(self):
"""
A lower bound on the number of documents in the database which would
match the query if collapsing wasn't used.
Xapian::doccount Xapian::MSet::get_uncollapsed_matches_lower_bound()
const
"""
return _xapian.MSet_get_uncollapsed_matches_lower_bound(self)
def get_uncollapsed_matches_estimated(self):
"""
A estimate of the number of documents in the database which would
match the query if collapsing wasn't used.
Xapian::doccount Xapian::MSet::get_uncollapsed_matches_estimated()
const
"""
return _xapian.MSet_get_uncollapsed_matches_estimated(self)
def get_uncollapsed_matches_upper_bound(self):
"""
A upper bound on the number of documents in the database which would
match the query if collapsing wasn't used.
Xapian::doccount Xapian::MSet::get_uncollapsed_matches_upper_bound()
const
"""
return _xapian.MSet_get_uncollapsed_matches_upper_bound(self)
def get_max_possible(self):
"""
The maximum possible weight in the MSet.
Xapian::weight Xapian::MSet::get_max_possible() const
This weight is likely not to be attained in the set of results, but
represents an upper bound on the weight which a document could attain
for the given query.
"""
return _xapian.MSet_get_max_possible(self)
def get_max_attained(self):
"""
The greatest weight which is attained by any document in the database.
Xapian::weight Xapian::MSet::get_max_attained() const
If firstitem == 0 and the primary ordering is by relevance, this is
the weight of the first entry in the MSet.
If no documents are found by the query, this will be 0.
Note that calculation of max_attained requires calculation of at least
one result item - therefore, if no items were requested when the query
was performed (by specifying maxitems = 0 in
Xapian::Enquire::get_mset()), this value will be 0.
"""
return _xapian.MSet_get_max_attained(self)
def size(self):
"""
The number of items in this MSet.
Xapian::doccount Xapian::MSet::size() const
"""
return _xapian.MSet_size(self)
def empty(self):
"""
Test if this MSet is empty.
bool Xapian::MSet::empty() const
"""
return _xapian.MSet_empty(self)
def begin(self):
"""
Iterator for the items in this MSet.
MSetIterator Xapian::MSet::begin() const
"""
return _xapian.MSet_begin(self)
def end(self):
"""
End iterator corresponding to begin()
MSetIterator Xapian::MSet::end() const
"""
return _xapian.MSet_end(self)
def back(self):
"""
Iterator pointing to the last element of this MSet.
MSetIterator Xapian::MSet::back() const
"""
return _xapian.MSet_back(self)
def _get_hit_internal(self, *args):
"""
Get an item from the MSet.
The supplied index is relative to the start of the MSet, not the absolute rank
of the item.
"""
return _xapian.MSet__get_hit_internal(self, *args)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::MSet::get_description() const
"""
return _xapian.MSet___str__(self)
items = _swig_property(_xapian.MSet_items_get)
MSet.fetch = new_instancemethod(_xapian.MSet_fetch,None,MSet)
MSet.convert_to_percent = new_instancemethod(_xapian.MSet_convert_to_percent,None,MSet)
MSet.get_termfreq = new_instancemethod(_xapian.MSet_get_termfreq,None,MSet)
MSet.get_termweight = new_instancemethod(_xapian.MSet_get_termweight,None,MSet)
MSet.get_firstitem = new_instancemethod(_xapian.MSet_get_firstitem,None,MSet)
MSet.get_matches_lower_bound = new_instancemethod(_xapian.MSet_get_matches_lower_bound,None,MSet)
MSet.get_matches_estimated = new_instancemethod(_xapian.MSet_get_matches_estimated,None,MSet)
MSet.get_matches_upper_bound = new_instancemethod(_xapian.MSet_get_matches_upper_bound,None,MSet)
MSet.get_uncollapsed_matches_lower_bound = new_instancemethod(_xapian.MSet_get_uncollapsed_matches_lower_bound,None,MSet)
MSet.get_uncollapsed_matches_estimated = new_instancemethod(_xapian.MSet_get_uncollapsed_matches_estimated,None,MSet)
MSet.get_uncollapsed_matches_upper_bound = new_instancemethod(_xapian.MSet_get_uncollapsed_matches_upper_bound,None,MSet)
MSet.get_max_possible = new_instancemethod(_xapian.MSet_get_max_possible,None,MSet)
MSet.get_max_attained = new_instancemethod(_xapian.MSet_get_max_attained,None,MSet)
MSet.size = new_instancemethod(_xapian.MSet_size,None,MSet)
MSet.empty = new_instancemethod(_xapian.MSet_empty,None,MSet)
MSet.begin = new_instancemethod(_xapian.MSet_begin,None,MSet)
MSet.end = new_instancemethod(_xapian.MSet_end,None,MSet)
MSet.back = new_instancemethod(_xapian.MSet_back,None,MSet)
MSet._get_hit_internal = new_instancemethod(_xapian.MSet__get_hit_internal,None,MSet)
MSet.get_document_percentage = new_instancemethod(_xapian.MSet_get_document_percentage,None,MSet)
MSet.get_document = new_instancemethod(_xapian.MSet_get_document,None,MSet)
MSet.get_docid = new_instancemethod(_xapian.MSet_get_docid,None,MSet)
MSet.__str__ = new_instancemethod(_xapian.MSet___str__,None,MSet)
MSet.__cmp__ = new_instancemethod(_xapian.MSet___cmp__,None,MSet)
MSet_swigregister = _xapian.MSet_swigregister
MSet_swigregister(MSet)
class MSetIterator(object):
"""
An iterator pointing to items in an MSet.
This is used for access to individual results of a match.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Copying is allowed (and is cheap).
Xapian::MSetIterator::MSetIterator(const MSetIterator &other)
"""
_xapian.MSetIterator_swiginit(self,_xapian.new_MSetIterator(*args))
__swig_destroy__ = _xapian.delete_MSetIterator
def get_document(self):
"""
Get a Xapian::Document object for the current position.
Xapian::Document Xapian::MSetIterator::get_document() const
This method returns a Xapian::Document object which provides the
information about the document pointed to by the MSetIterator.
If the underlying database has suitable support, using this call
(rather than asking the database for a document based on its document
ID) will enable the system to ensure that the correct data is
returned, and that the document has not been deleted or changed since
the query was performed.
A Xapian::Document object containing the document data.
Parameters:
-----------
Xapian::DocNotFoundError: The document specified could not be found
in the database.
"""
return _xapian.MSetIterator_get_document(self)
def get_rank(self):
"""
Get the rank of the document at the current position.
Xapian::doccount Xapian::MSetIterator::get_rank() const
The rank is the position that this document is at in the ordered list
of results of the query. The result is 0-based - i.e. the top-ranked
document has a rank of 0.
"""
return _xapian.MSetIterator_get_rank(self)
def get_weight(self):
"""
Get the weight of the document at the current position.
Xapian::weight Xapian::MSetIterator::get_weight() const
"""
return _xapian.MSetIterator_get_weight(self)
def get_collapse_key(self):
"""
Get the collapse key for this document.
std::string Xapian::MSetIterator::get_collapse_key() const
"""
return _xapian.MSetIterator_get_collapse_key(self)
def get_collapse_count(self):
"""
Get an estimate of the number of documents that have been collapsed
into this one.
Xapian::doccount Xapian::MSetIterator::get_collapse_count() const
The estimate will always be less than or equal to the actual number of
other documents satisfying the match criteria with the same collapse
key as this document.
This method may return 0 even though there are other documents with
the same collapse key which satisfying the match criteria. However if
this method returns non-zero, there definitely are other such
documents. So this method may be used to inform the user that there
are "at least N other matches in this group", or to control whether
to offer a "show other documents in this group" feature (but note
that it may not offer it in every case where it would show other
documents).
"""
return _xapian.MSetIterator_get_collapse_count(self)
def get_percent(self):
"""
This returns the weight of the document as a percentage score.
Xapian::percent Xapian::MSetIterator::get_percent() const
The return value will be an integer in the range 0 to 100: 0 meaning
that the item did not match the query at all.
The intention is that the highest weighted document will get 100 if it
matches all the weight-contributing terms in the query. However,
currently it may get a lower percentage score if you use a
MatchDecider and the sorting is primarily by value. In this case, the
percentage for a particular document may vary depending on the first,
max_size, and checkatleast parameters passed to Enquire::get_mset()
(this bug is hard to fix without having to apply the MatchDecider to
potentially many more documents, which is potentially costly).
"""
return _xapian.MSetIterator_get_percent(self)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::MSetIterator::get_description() const
"""
return _xapian.MSetIterator___str__(self)
MSetIterator.get_docid = new_instancemethod(_xapian.MSetIterator_get_docid,None,MSetIterator)
MSetIterator.next = new_instancemethod(_xapian.MSetIterator_next,None,MSetIterator)
MSetIterator.prev = new_instancemethod(_xapian.MSetIterator_prev,None,MSetIterator)
MSetIterator.equals = new_instancemethod(_xapian.MSetIterator_equals,None,MSetIterator)
MSetIterator.get_document = new_instancemethod(_xapian.MSetIterator_get_document,None,MSetIterator)
MSetIterator.get_rank = new_instancemethod(_xapian.MSetIterator_get_rank,None,MSetIterator)
MSetIterator.get_weight = new_instancemethod(_xapian.MSetIterator_get_weight,None,MSetIterator)
MSetIterator.get_collapse_key = new_instancemethod(_xapian.MSetIterator_get_collapse_key,None,MSetIterator)
MSetIterator.get_collapse_count = new_instancemethod(_xapian.MSetIterator_get_collapse_count,None,MSetIterator)
MSetIterator.get_percent = new_instancemethod(_xapian.MSetIterator_get_percent,None,MSetIterator)
MSetIterator.__str__ = new_instancemethod(_xapian.MSetIterator___str__,None,MSetIterator)
MSetIterator.__eq__ = new_instancemethod(_xapian.MSetIterator___eq__,None,MSetIterator)
MSetIterator.__ne__ = new_instancemethod(_xapian.MSetIterator___ne__,None,MSetIterator)
MSetIterator_swigregister = _xapian.MSetIterator_swigregister
MSetIterator_swigregister(MSetIterator)
class ESet(object):
"""
Class representing an ordered set of expand terms (an ESet).
This set represents the results of an expand operation, which is
performed by Xapian::Enquire::get_eset().
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Copying is allowed (and is cheap).
Xapian::ESet::ESet(const ESet &other)
"""
_xapian.ESet_swiginit(self,_xapian.new_ESet(*args))
__swig_destroy__ = _xapian.delete_ESet
def get_ebound(self):
"""
A lower bound on the number of terms which are in the full set of
results of the expand.
Xapian::termcount Xapian::ESet::get_ebound() const
This will be greater than or equal to size()
"""
return _xapian.ESet_get_ebound(self)
def size(self):
"""
The number of terms in this E-Set.
Xapian::termcount Xapian::ESet::size() const
"""
return _xapian.ESet_size(self)
def empty(self):
"""
Test if this E-Set is empty.
bool Xapian::ESet::empty() const
"""
return _xapian.ESet_empty(self)
def begin(self):
"""
Iterator for the terms in this E-Set.
ESetIterator Xapian::ESet::begin() const
"""
return _xapian.ESet_begin(self)
def end(self):
"""
End iterator corresponding to begin()
ESetIterator Xapian::ESet::end() const
"""
return _xapian.ESet_end(self)
def back(self):
"""
Iterator pointing to the last element of this E-Set.
ESetIterator Xapian::ESet::back() const
"""
return _xapian.ESet_back(self)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::ESet::get_description() const
"""
return _xapian.ESet___str__(self)
items = _swig_property(_xapian.ESet_items_get)
ESet.get_ebound = new_instancemethod(_xapian.ESet_get_ebound,None,ESet)
ESet.size = new_instancemethod(_xapian.ESet_size,None,ESet)
ESet.empty = new_instancemethod(_xapian.ESet_empty,None,ESet)
ESet.begin = new_instancemethod(_xapian.ESet_begin,None,ESet)
ESet.end = new_instancemethod(_xapian.ESet_end,None,ESet)
ESet.back = new_instancemethod(_xapian.ESet_back,None,ESet)
ESet.__str__ = new_instancemethod(_xapian.ESet___str__,None,ESet)
ESet_swigregister = _xapian.ESet_swigregister
ESet_swigregister(ESet)
class ESetIterator(object):
"""
Iterate through terms in the ESet.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Copying is allowed (and is cheap).
Xapian::ESetIterator::ESetIterator(const ESetIterator &other)
"""
_xapian.ESetIterator_swiginit(self,_xapian.new_ESetIterator(*args))
__swig_destroy__ = _xapian.delete_ESetIterator
def get_weight(self):
"""
Get the weight of the term at the current position.
Xapian::weight Xapian::ESetIterator::get_weight() const
"""
return _xapian.ESetIterator_get_weight(self)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::ESetIterator::get_description() const
"""
return _xapian.ESetIterator___str__(self)
ESetIterator.get_term = new_instancemethod(_xapian.ESetIterator_get_term,None,ESetIterator)
ESetIterator.next = new_instancemethod(_xapian.ESetIterator_next,None,ESetIterator)
ESetIterator.prev = new_instancemethod(_xapian.ESetIterator_prev,None,ESetIterator)
ESetIterator.equals = new_instancemethod(_xapian.ESetIterator_equals,None,ESetIterator)
ESetIterator.get_weight = new_instancemethod(_xapian.ESetIterator_get_weight,None,ESetIterator)
ESetIterator.__str__ = new_instancemethod(_xapian.ESetIterator___str__,None,ESetIterator)
ESetIterator.__eq__ = new_instancemethod(_xapian.ESetIterator___eq__,None,ESetIterator)
ESetIterator.__ne__ = new_instancemethod(_xapian.ESetIterator___ne__,None,ESetIterator)
ESetIterator_swigregister = _xapian.ESetIterator_swigregister
ESetIterator_swigregister(ESetIterator)
class RSet(object):
"""
A relevance set (R-Set).
This is the set of documents which are marked as relevant, for use in
modifying the term weights, and in performing query expansion.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Default constructor.
Xapian::RSet::RSet()
"""
_xapian.RSet_swiginit(self,_xapian.new_RSet(*args))
__swig_destroy__ = _xapian.delete_RSet
def size(self):
"""
The number of documents in this R-Set.
Xapian::doccount Xapian::RSet::size() const
"""
return _xapian.RSet_size(self)
def empty(self):
"""
Test if this R-Set is empty.
bool Xapian::RSet::empty() const
"""
return _xapian.RSet_empty(self)
def add_document(self, *args):
"""
Add a document to the relevance set.
void Xapian::RSet::add_document(const Xapian::MSetIterator &i)
"""
return _xapian.RSet_add_document(self, *args)
def remove_document(self, *args):
"""
Remove a document from the relevance set.
void Xapian::RSet::remove_document(const Xapian::MSetIterator &i)
"""
return _xapian.RSet_remove_document(self, *args)
def contains(self, *args):
"""
Test if a given document in the relevance set.
bool Xapian::RSet::contains(const Xapian::MSetIterator &i) const
"""
return _xapian.RSet_contains(self, *args)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::RSet::get_description() const
"""
return _xapian.RSet___str__(self)
RSet.size = new_instancemethod(_xapian.RSet_size,None,RSet)
RSet.empty = new_instancemethod(_xapian.RSet_empty,None,RSet)
RSet.add_document = new_instancemethod(_xapian.RSet_add_document,None,RSet)
RSet.remove_document = new_instancemethod(_xapian.RSet_remove_document,None,RSet)
RSet.contains = new_instancemethod(_xapian.RSet_contains,None,RSet)
RSet.__str__ = new_instancemethod(_xapian.RSet___str__,None,RSet)
RSet_swigregister = _xapian.RSet_swigregister
RSet_swigregister(RSet)
class MatchDecider(object):
"""
Base class for matcher decision functor.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
__swig_destroy__ = _xapian.delete_MatchDecider
def __init__(self):
if self.__class__ == MatchDecider:
_self = None
else:
_self = self
_xapian.MatchDecider_swiginit(self,_xapian.new_MatchDecider(_self, ))
def __disown__(self):
self.this.disown()
_xapian.disown_MatchDecider(self)
return weakref_proxy(self)
MatchDecider.__call__ = new_instancemethod(_xapian.MatchDecider___call__,None,MatchDecider)
MatchDecider_swigregister = _xapian.MatchDecider_swigregister
MatchDecider_swigregister(MatchDecider)
class ExpandDecider(object):
"""
Virtual base class for expand decider functor.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
__swig_destroy__ = _xapian.delete_ExpandDecider
def __init__(self):
if self.__class__ == ExpandDecider:
_self = None
else:
_self = self
_xapian.ExpandDecider_swiginit(self,_xapian.new_ExpandDecider(_self, ))
def __disown__(self):
self.this.disown()
_xapian.disown_ExpandDecider(self)
return weakref_proxy(self)
ExpandDecider.__call__ = new_instancemethod(_xapian.ExpandDecider___call__,None,ExpandDecider)
ExpandDecider_swigregister = _xapian.ExpandDecider_swigregister
ExpandDecider_swigregister(ExpandDecider)
class Enquire(object):
"""
This class provides an interface to the information retrieval system
for the purpose of searching.
Databases are usually opened lazily, so exceptions may not be thrown
where you would expect them to be. You should catch Xapian::Error
exceptions when calling any method in Xapian::Enquire.
Parameters:
-----------
Xapian::InvalidArgumentError: will be thrown if an invalid argument
is supplied, for example, an unknown database type.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Create a Xapian::Enquire object.
Xapian::Enquire::Enquire(const Database &database, ErrorHandler
*errorhandler_=0)
This specification cannot be changed once the Xapian::Enquire is
opened: you must create a new Xapian::Enquire object to access a
different database, or set of databases.
The database supplied must have been initialised (ie, must not be the
result of calling the Database::Database() constructor). If you need
to handle a situation where you have no index gracefully, a database
created with InMemory::open() can be passed here, which represents a
completely empty database.
Parameters:
-----------
database: Specification of the database or databases to use.
errorhandler_: A pointer to the error handler to use. Ownership of
the object pointed to is not assumed by the Xapian::Enquire object -
the user should delete the Xapian::ErrorHandler object after the
Xapian::Enquire object is deleted. To use no error handler, this
parameter should be 0.
Parameters:
-----------
Xapian::InvalidArgumentError: will be thrown if an empty Database
object is supplied.
"""
_xapian.Enquire_swiginit(self,_xapian.new_Enquire(*args))
__swig_destroy__ = _xapian.delete_Enquire
def set_query(self, *args):
"""
Set the query to run.
void Xapian::Enquire::set_query(const Xapian::Query &query,
Xapian::termcount qlen=0)
Parameters:
-----------
query: the new query to run.
qlen: the query length to use in weight calculations - by default the
sum of the wqf of all terms is used.
"""
return _xapian.Enquire_set_query(self, *args)
def get_query(self):
"""
Get the query which has been set.
const Xapian::Query& Xapian::Enquire::get_query() const
This is only valid after set_query() has been called.
Parameters:
-----------
Xapian::InvalidArgumentError: will be thrown if query has not yet
been set.
"""
return _xapian.Enquire_get_query(self)
def add_matchspy(self, *args):
"""
Add a matchspy.
void Xapian::Enquire::add_matchspy(MatchSpy *spy)
This matchspy will be called with some of the documents which match
the query, during the match process. Exactly which of the matching
documents are passed to it depends on exactly when certain
optimisations occur during the match process, but it can be controlled
to some extent by setting the checkatleast parameter to get_mset().
In particular, if there are enough matching documents, at least the
number specified by checkatleast will be passed to the matchspy. This
means that you can force the matchspy to be shown all matching
documents by setting checkatleast to the number of documents in the
database.
Parameters:
-----------
spy: The MatchSpy subclass to add. The caller must ensure that this
remains valid while the Enquire object remains active, or until
clear_matchspies() is called.
"""
return _xapian.Enquire_add_matchspy(self, *args)
def clear_matchspies(self):
"""
Remove all the matchspies.
void Xapian::Enquire::clear_matchspies()
"""
return _xapian.Enquire_clear_matchspies(self)
def set_weighting_scheme(self, *args):
"""
Set the weighting scheme to use for queries.
void Xapian::Enquire::set_weighting_scheme(const Weight &weight_)
Parameters:
-----------
weight_: the new weighting scheme. If no weighting scheme is
specified, the default is BM25 with the default parameters.
"""
return _xapian.Enquire_set_weighting_scheme(self, *args)
def set_collapse_key(self, *args):
"""
Set the collapse key to use for queries.
void Xapian::Enquire::set_collapse_key(Xapian::valueno collapse_key,
Xapian::doccount collapse_max=1)
Parameters:
-----------
collapse_key: value number to collapse on - at most one MSet entry
with each particular value will be returned (default is
Xapian::BAD_VALUENO which means no collapsing).
collapse_max: Max number of items with the same key to leave after
collapsing (default 1).
The MSet returned by get_mset() will have only the "best" (at most)
collapse_max entries with each particular value of collapse_key
("best" being highest ranked - i.e. highest weight or highest
sorting key).
An example use might be to create a value for each document containing
an MD5 hash of the document contents. Then duplicate documents from
different sources can be eliminated at search time by collapsing with
collapse_max = 1 (it's better to eliminate duplicates at index time,
but this may not be always be possible - for example the search may be
over more than one Xapian database).
Another use is to group matches in a particular category (e.g. you
might collapse a mailing list search on the Subject: so that there's
only one result per discussion thread). In this case you can use
get_collapse_count() to give the user some idea how many other results
there are. And if you index the Subject: as a boolean term as well as
putting it in a value, you can offer a link to a non-collapsed search
restricted to that thread using a boolean filter.
"""
return _xapian.Enquire_set_collapse_key(self, *args)
ASCENDING = _xapian.Enquire_ASCENDING
DESCENDING = _xapian.Enquire_DESCENDING
DONT_CARE = _xapian.Enquire_DONT_CARE
def set_docid_order(self, *args):
"""
Set the direction in which documents are ordered by document id in the
returned MSet.
void Xapian::Enquire::set_docid_order(docid_order order)
This order only has an effect on documents which would otherwise have
equal rank. For a weighted probabilistic match with no sort value,
this means documents with equal weight. For a boolean match, with no
sort value, this means all documents. And if a sort value is used,
this means documents with equal sort value (and also equal weight if
ordering on relevance after the sort).
Parameters:
-----------
order: This can be: Xapian::Enquire::ASCENDING docids sort in
ascending order (default)
Xapian::Enquire::DESCENDING docids sort in descending order
Xapian::Enquire::DONT_CARE docids sort in whatever order is most
efficient for the backend
Note: If you add documents in strict date order, then a boolean search
- i.e. set_weighting_scheme( Xapian::BoolWeight()) - with
set_docid_order(Xapian::Enquire::DESCENDING) is an efficient way to
perform "sort by date, newest first", and with
set_docid_order(Xapian::Enquire::ASCENDING) a very efficient way to
perform "sort by date, oldest first".
"""
return _xapian.Enquire_set_docid_order(self, *args)
def set_cutoff(self, *args):
"""
Set the percentage and/or weight cutoffs.
void Xapian::Enquire::set_cutoff(Xapian::percent percent_cutoff,
Xapian::weight weight_cutoff=0)
Parameters:
-----------
percent_cutoff: Minimum percentage score for returned documents. If a
document has a lower percentage score than this, it will not appear in
the MSet. If your intention is to return only matches which contain
all the terms in the query, then it's more efficient to use
Xapian::Query::OP_AND instead of Xapian::Query::OP_OR in the query
than to use set_cutoff(100). (default 0 => no percentage cut-off).
weight_cutoff: Minimum weight for a document to be returned. If a
document has a lower score that this, it will not appear in the MSet.
It is usually only possible to choose an appropriate weight for cutoff
based on the results of a previous run of the same query; this is thus
mainly useful for alerting operations. The other potential use is with
a user specified weighting scheme. (default 0 => no weight cut-off).
"""
return _xapian.Enquire_set_cutoff(self, *args)
def set_sort_by_relevance(self):
"""
Set the sorting to be by relevance only.
void Xapian::Enquire::set_sort_by_relevance()
This is the default.
"""
return _xapian.Enquire_set_sort_by_relevance(self)
def set_sort_by_value(self, *args):
"""
void
Xapian::Enquire::set_sort_by_value(Xapian::valueno sort_key)
"""
return _xapian.Enquire_set_sort_by_value(self, *args)
def set_sort_by_value_then_relevance(self, *args):
"""
void
Xapian::Enquire::set_sort_by_value_then_relevance(Xapian::valueno
sort_key)
"""
return _xapian.Enquire_set_sort_by_value_then_relevance(self, *args)
def set_sort_by_relevance_then_value(self, *args):
"""
void
Xapian::Enquire::set_sort_by_relevance_then_value(Xapian::valueno
sort_key)
"""
return _xapian.Enquire_set_sort_by_relevance_then_value(self, *args)
def set_sort_by_key(self, *args):
"""
void
Xapian::Enquire::set_sort_by_key(Xapian::KeyMaker *sorter)
"""
return _xapian.Enquire_set_sort_by_key(self, *args)
def set_sort_by_key_then_relevance(self, *args):
"""
void
Xapian::Enquire::set_sort_by_key_then_relevance(Xapian::KeyMaker
*sorter)
"""
return _xapian.Enquire_set_sort_by_key_then_relevance(self, *args)
def set_sort_by_relevance_then_key(self, *args):
"""
void
Xapian::Enquire::set_sort_by_relevance_then_key(Xapian::KeyMaker
*sorter)
"""
return _xapian.Enquire_set_sort_by_relevance_then_key(self, *args)
INCLUDE_QUERY_TERMS = _xapian.Enquire_INCLUDE_QUERY_TERMS
USE_EXACT_TERMFREQ = _xapian.Enquire_USE_EXACT_TERMFREQ
def get_eset(self, *args):
"""
Get the expand set for the given rset.
ESet Xapian::Enquire::get_eset(Xapian::termcount maxitems, const RSet
&omrset, int flags, double k, const Xapian::ExpandDecider *edecider,
Xapian::weight min_wt) const
Parameters:
-----------
maxitems: the maximum number of items to return.
omrset: the relevance set to use when performing the expand
operation.
flags: zero or more of these values |-ed together:
Xapian::Enquire::INCLUDE_QUERY_TERMS query terms may be returned from
expand
Xapian::Enquire::USE_EXACT_TERMFREQ for multi dbs, calculate the exact
termfreq; otherwise an approximation is used which can greatly improve
efficiency, but still returns good results.
k: the parameter k in the query expansion algorithm (default is 1.0)
edecider: a decision functor to use to decide whether a given term
should be put in the ESet
min_wt: the minimum weight for included terms
An ESet object containing the results of the expand.
Parameters:
-----------
Xapian::InvalidArgumentError: See class documentation.
"""
return _xapian.Enquire_get_eset(self, *args)
def get_matching_terms_begin(self, *args):
"""
Get terms which match a given document, by match set item.
TermIterator Xapian::Enquire::get_matching_terms_begin(const
MSetIterator &it) const
This method returns the terms in the current query which match the
given document.
If the underlying database has suitable support, using this call
(rather than passing a Xapian::docid) will enable the system to ensure
that the correct data is returned, and that the document has not been
deleted or changed since the query was performed.
Parameters:
-----------
it: The iterator for which to retrieve the matching terms.
An iterator returning the terms which match the document. The terms
will be returned (as far as this makes any sense) in the same order as
the terms in the query. Terms will not occur more than once, even if
they do in the query.
Parameters:
-----------
Xapian::InvalidArgumentError: See class documentation.
Xapian::DocNotFoundError: The document specified could not be found
in the database.
"""
return _xapian.Enquire_get_matching_terms_begin(self, *args)
def get_matching_terms_end(self, *args):
"""
End iterator corresponding to get_matching_terms_begin()
TermIterator Xapian::Enquire::get_matching_terms_end(const
MSetIterator &) const
"""
return _xapian.Enquire_get_matching_terms_end(self, *args)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::Enquire::get_description() const
"""
return _xapian.Enquire___str__(self)
Enquire.set_query = new_instancemethod(_xapian.Enquire_set_query,None,Enquire)
Enquire.get_query = new_instancemethod(_xapian.Enquire_get_query,None,Enquire)
Enquire.add_matchspy = new_instancemethod(_xapian.Enquire_add_matchspy,None,Enquire)
Enquire.clear_matchspies = new_instancemethod(_xapian.Enquire_clear_matchspies,None,Enquire)
Enquire.set_weighting_scheme = new_instancemethod(_xapian.Enquire_set_weighting_scheme,None,Enquire)
Enquire.set_collapse_key = new_instancemethod(_xapian.Enquire_set_collapse_key,None,Enquire)
Enquire.set_docid_order = new_instancemethod(_xapian.Enquire_set_docid_order,None,Enquire)
Enquire.set_cutoff = new_instancemethod(_xapian.Enquire_set_cutoff,None,Enquire)
Enquire.set_sort_by_relevance = new_instancemethod(_xapian.Enquire_set_sort_by_relevance,None,Enquire)
Enquire.set_sort_by_value = new_instancemethod(_xapian.Enquire_set_sort_by_value,None,Enquire)
Enquire.set_sort_by_value_then_relevance = new_instancemethod(_xapian.Enquire_set_sort_by_value_then_relevance,None,Enquire)
Enquire.set_sort_by_relevance_then_value = new_instancemethod(_xapian.Enquire_set_sort_by_relevance_then_value,None,Enquire)
Enquire.set_sort_by_key = new_instancemethod(_xapian.Enquire_set_sort_by_key,None,Enquire)
Enquire.set_sort_by_key_then_relevance = new_instancemethod(_xapian.Enquire_set_sort_by_key_then_relevance,None,Enquire)
Enquire.set_sort_by_relevance_then_key = new_instancemethod(_xapian.Enquire_set_sort_by_relevance_then_key,None,Enquire)
Enquire.get_mset = new_instancemethod(_xapian.Enquire_get_mset,None,Enquire)
Enquire.get_eset = new_instancemethod(_xapian.Enquire_get_eset,None,Enquire)
Enquire.get_matching_terms_begin = new_instancemethod(_xapian.Enquire_get_matching_terms_begin,None,Enquire)
Enquire.get_matching_terms_end = new_instancemethod(_xapian.Enquire_get_matching_terms_end,None,Enquire)
Enquire.__str__ = new_instancemethod(_xapian.Enquire___str__,None,Enquire)
Enquire_swigregister = _xapian.Enquire_swigregister
Enquire_swigregister(Enquire)
class Registry(object):
"""
Registry for user subclasses.
This class provides a way for the remote server to look up user
subclasses when unserialising.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Default constructor.
Xapian::Registry::Registry()
The registry will contain all standard subclasses of user-subclassable
classes.
"""
_xapian.Registry_swiginit(self,_xapian.new_Registry(*args))
__swig_destroy__ = _xapian.delete_Registry
def register_weighting_scheme(self, *args):
"""
Register a weighting scheme.
void Xapian::Registry::register_weighting_scheme(const Xapian::Weight
&wt)
Parameters:
-----------
wt: The weighting scheme to register.
"""
return _xapian.Registry_register_weighting_scheme(self, *args)
def get_weighting_scheme(self, *args):
"""
Get the weighting scheme given a name.
const Xapian::Weight* Xapian::Registry::get_weighting_scheme(const
std::string &name) const
Parameters:
-----------
name: The name of the weighting scheme to find.
An object with the requested name, or NULL if the weighting scheme
could not be found. The returned object is owned by the registry and
so must not be deleted by the caller.
"""
return _xapian.Registry_get_weighting_scheme(self, *args)
def register_posting_source(self, *args):
"""
Register a user-defined posting source class.
void Xapian::Registry::register_posting_source(const
Xapian::PostingSource &source)
Parameters:
-----------
source: The posting source to register.
"""
return _xapian.Registry_register_posting_source(self, *args)
def get_posting_source(self, *args):
"""
Get a posting source given a name.
const Xapian::PostingSource*
Xapian::Registry::get_posting_source(const std::string &name) const
Parameters:
-----------
name: The name of the posting source to find.
An object with the requested name, or NULL if the posting source could
not be found. The returned object is owned by the registry and so must
not be deleted by the caller.
"""
return _xapian.Registry_get_posting_source(self, *args)
def register_match_spy(self, *args):
"""
Register a user-defined match spy class.
void Xapian::Registry::register_match_spy(const Xapian::MatchSpy &spy)
Parameters:
-----------
spy: The match spy to register.
"""
return _xapian.Registry_register_match_spy(self, *args)
def get_match_spy(self, *args):
"""
Get a match spy given a name.
const Xapian::MatchSpy* Xapian::Registry::get_match_spy(const
std::string &name) const
Parameters:
-----------
name: The name of the match spy to find.
An object with the requested name, or NULL if the match spy could not
be found. The returned object is owned by the registry and so must not
be deleted by the caller.
"""
return _xapian.Registry_get_match_spy(self, *args)
Registry.register_weighting_scheme = new_instancemethod(_xapian.Registry_register_weighting_scheme,None,Registry)
Registry.get_weighting_scheme = new_instancemethod(_xapian.Registry_get_weighting_scheme,None,Registry)
Registry.register_posting_source = new_instancemethod(_xapian.Registry_register_posting_source,None,Registry)
Registry.get_posting_source = new_instancemethod(_xapian.Registry_get_posting_source,None,Registry)
Registry.register_match_spy = new_instancemethod(_xapian.Registry_register_match_spy,None,Registry)
Registry.get_match_spy = new_instancemethod(_xapian.Registry_get_match_spy,None,Registry)
Registry_swigregister = _xapian.Registry_swigregister
Registry_swigregister(Registry)
class Weight(object):
"""
Abstract base class for weighting schemes.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
def __init__(self, *args, **kwargs): raise AttributeError("No constructor defined - class is abstract")
__repr__ = _swig_repr
__swig_destroy__ = _xapian.delete_Weight
def name(self):
"""
Return the name of this weighting scheme.
virtual std::string Xapian::Weight::name() const
This name is used by the remote backend. It is passed along with the
serialised parameters to the remote server so that it knows which
class to create.
Return the full namespace-qualified name of your class here - if your
class is called FooWeight, return "FooWeight" from this method (
Xapian::BM25Weight returns "Xapian::BM25Weight" here).
If you don't want to support the remote backend, you can use the
default implementation which simply returns an empty string.
"""
return _xapian.Weight_name(self)
def get_sumpart(self, *args):
"""
Calculate the weight contribution for this object's term to a
document.
virtual Xapian::weight Xapian::Weight::get_sumpart(Xapian::termcount
wdf, Xapian::termcount doclen) const =0
The parameters give information about the document which may be used
in the calculations:
Parameters:
-----------
wdf: The within document frequency of the term in the document.
doclen: The document's length (unnormalised).
"""
return _xapian.Weight_get_sumpart(self, *args)
def get_maxpart(self):
"""
Return an upper bound on what get_sumpart() can return for any
document.
virtual Xapian::weight Xapian::Weight::get_maxpart() const =0
This information is used by the matcher to perform various
optimisations, so strive to make the bound as tight as possible.
"""
return _xapian.Weight_get_maxpart(self)
def get_sumextra(self, *args):
"""
Calculate the term-independent weight component for a document.
virtual Xapian::weight Xapian::Weight::get_sumextra(Xapian::termcount
doclen) const =0
The parameter gives information about the document which may be used
in the calculations:
Parameters:
-----------
doclen: The document's length (unnormalised).
"""
return _xapian.Weight_get_sumextra(self, *args)
def get_maxextra(self):
"""
Return an upper bound on what get_sumextra() can return for any
document.
virtual Xapian::weight Xapian::Weight::get_maxextra() const =0
This information is used by the matcher to perform various
optimisations, so strive to make the bound as tight as possible.
"""
return _xapian.Weight_get_maxextra(self)
Weight.name = new_instancemethod(_xapian.Weight_name,None,Weight)
Weight.get_sumpart = new_instancemethod(_xapian.Weight_get_sumpart,None,Weight)
Weight.get_maxpart = new_instancemethod(_xapian.Weight_get_maxpart,None,Weight)
Weight.get_sumextra = new_instancemethod(_xapian.Weight_get_sumextra,None,Weight)
Weight.get_maxextra = new_instancemethod(_xapian.Weight_get_maxextra,None,Weight)
Weight.get_sumpart_needs_doclength_ = new_instancemethod(_xapian.Weight_get_sumpart_needs_doclength_,None,Weight)
Weight.get_sumpart_needs_wdf_ = new_instancemethod(_xapian.Weight_get_sumpart_needs_wdf_,None,Weight)
Weight_swigregister = _xapian.Weight_swigregister
Weight_swigregister(Weight)
class BoolWeight(Weight):
"""
Class implementing a "boolean" weighting scheme.
This weighting scheme gives all documents zero weight.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self):
"""
Construct a BoolWeight.
Xapian::BoolWeight::BoolWeight()
"""
_xapian.BoolWeight_swiginit(self,_xapian.new_BoolWeight())
__swig_destroy__ = _xapian.delete_BoolWeight
BoolWeight_swigregister = _xapian.BoolWeight_swigregister
BoolWeight_swigregister(BoolWeight)
class BM25Weight(Weight):
"""
Xapian::Weight subclass implementing the BM25 probabilistic formula.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""Xapian::BM25Weight::BM25Weight() """
_xapian.BM25Weight_swiginit(self,_xapian.new_BM25Weight(*args))
__swig_destroy__ = _xapian.delete_BM25Weight
BM25Weight_swigregister = _xapian.BM25Weight_swigregister
BM25Weight_swigregister(BM25Weight)
class TradWeight(Weight):
"""
Xapian::Weight subclass implementing the traditional probabilistic
formula.
This class implements the "traditional" Probabilistic Weighting
scheme, as described by the early papers on Probabilistic Retrieval.
BM25 generally gives better results.
TradWeight(k) is equivalent to BM25Weight(k, 0, 0, 1, 0), except that
the latter returns weights (k+1) times larger.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, k=1.0):
"""
Construct a TradWeight.
Xapian::TradWeight::TradWeight(double k=1.0)
Parameters:
-----------
k: A non-negative parameter controlling how influential within-
document- frequency (wdf) and document length are. k=0 means that wdf
and document length don't affect the weights. The larger k is, the
more they do. (default 1)
"""
_xapian.TradWeight_swiginit(self,_xapian.new_TradWeight(k))
__swig_destroy__ = _xapian.delete_TradWeight
TradWeight_swigregister = _xapian.TradWeight_swigregister
TradWeight_swigregister(TradWeight)
class MatchSpy(object):
"""
Abstract base class for match spies.
The subclasses will generally accumulate information seen during the
match, to calculate aggregate functions, or other profiles of the
matching documents.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self):
if self.__class__ == MatchSpy:
_self = None
else:
_self = self
_xapian.MatchSpy_swiginit(self,_xapian.new_MatchSpy(_self, ))
__swig_destroy__ = _xapian.delete_MatchSpy
def name(self):
"""
Return the name of this match spy.
virtual std::string Xapian::MatchSpy::name() const
This name is used by the remote backend. It is passed with the
serialised parameters to the remote server so that it knows which
class to create.
Return the full namespace-qualified name of your class here - if your
class is called MyApp::FooMatchSpy, return "MyApp::FooMatchSpy" from
this method.
If you don't want to support the remote backend in your match spy, you
can use the default implementation which simply throws
Xapian::UnimplementedError.
"""
return _xapian.MatchSpy_name(self)
def merge_results(self, *args):
"""
Unserialise some results, and merge them into this matchspy.
virtual void Xapian::MatchSpy::merge_results(const std::string &s)
The order in which results are merged should not be significant, since
this order is not specified (and will vary depending on the speed of
the search in each sub-database).
If you don't want to support the remote backend in your match spy, you
can use the default implementation which simply throws
Xapian::UnimplementedError.
Parameters:
-----------
s: A string containing the serialised results.
"""
return _xapian.MatchSpy_merge_results(self, *args)
def __str__(self):
"""
Return a string describing this object.
virtual std::string Xapian::MatchSpy::get_description() const
This default implementation returns a generic answer, to avoid forcing
those deriving their own MatchSpy subclasses from having to implement
this (they may not care what get_description() gives for their
subclass).
"""
return _xapian.MatchSpy___str__(self)
def __disown__(self):
self.this.disown()
_xapian.disown_MatchSpy(self)
return weakref_proxy(self)
MatchSpy.__call__ = new_instancemethod(_xapian.MatchSpy___call__,None,MatchSpy)
MatchSpy.name = new_instancemethod(_xapian.MatchSpy_name,None,MatchSpy)
MatchSpy.merge_results = new_instancemethod(_xapian.MatchSpy_merge_results,None,MatchSpy)
MatchSpy.__str__ = new_instancemethod(_xapian.MatchSpy___str__,None,MatchSpy)
MatchSpy_swigregister = _xapian.MatchSpy_swigregister
MatchSpy_swigregister(MatchSpy)
class ValueCountMatchSpy(MatchSpy):
"""
Class for counting the frequencies of values in the matching
documents.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct a MatchSpy which counts the values in a particular slot.
Xapian::ValueCountMatchSpy::ValueCountMatchSpy(Xapian::valueno slot_)
"""
_xapian.ValueCountMatchSpy_swiginit(self,_xapian.new_ValueCountMatchSpy(*args))
def get_total(self):
"""
Return the total number of documents tallied.
size_t Xapian::ValueCountMatchSpy::get_total() const
"""
return _xapian.ValueCountMatchSpy_get_total(self)
def values_begin(self):
"""
Get an iterator over the values seen in the slot.
TermIterator Xapian::ValueCountMatchSpy::values_begin() const
Items will be returned in ascending alphabetical order.
During the iteration, the frequency of the current value can be
obtained with the get_termfreq() method on the iterator.
"""
return _xapian.ValueCountMatchSpy_values_begin(self)
def values_end(self):
"""
End iterator corresponding to values_begin()
TermIterator Xapian::ValueCountMatchSpy::values_end() const
"""
return _xapian.ValueCountMatchSpy_values_end(self)
def top_values_begin(self, *args):
"""
Get an iterator over the most frequent values seen in the slot.
TermIterator Xapian::ValueCountMatchSpy::top_values_begin(size_t
maxvalues) const
Items will be returned in descending order of frequency. Values with
the same frequency will be returned in ascending alphabetical order.
During the iteration, the frequency of the current value can be
obtained with the get_termfreq() method on the iterator.
Parameters:
-----------
maxvalues: The maximum number of values to return.
"""
return _xapian.ValueCountMatchSpy_top_values_begin(self, *args)
def top_values_end(self, *args):
"""
End iterator corresponding to top_values_begin()
TermIterator Xapian::ValueCountMatchSpy::top_values_end(size_t) const
"""
return _xapian.ValueCountMatchSpy_top_values_end(self, *args)
__swig_destroy__ = _xapian.delete_ValueCountMatchSpy
ValueCountMatchSpy.get_total = new_instancemethod(_xapian.ValueCountMatchSpy_get_total,None,ValueCountMatchSpy)
ValueCountMatchSpy.values_begin = new_instancemethod(_xapian.ValueCountMatchSpy_values_begin,None,ValueCountMatchSpy)
ValueCountMatchSpy.values_end = new_instancemethod(_xapian.ValueCountMatchSpy_values_end,None,ValueCountMatchSpy)
ValueCountMatchSpy.top_values_begin = new_instancemethod(_xapian.ValueCountMatchSpy_top_values_begin,None,ValueCountMatchSpy)
ValueCountMatchSpy.top_values_end = new_instancemethod(_xapian.ValueCountMatchSpy_top_values_end,None,ValueCountMatchSpy)
ValueCountMatchSpy_swigregister = _xapian.ValueCountMatchSpy_swigregister
ValueCountMatchSpy_swigregister(ValueCountMatchSpy)
class Database(object):
"""
This class is used to access a database, or a group of databases.
For searching, this class is used in conjunction with an Enquire
object.
Parameters:
-----------
InvalidArgumentError: will be thrown if an invalid argument is
supplied, for example, an unknown database type.
DatabaseOpeningError: may be thrown if the database cannot be opened
(for example, a required file cannot be found).
DatabaseVersionError: may be thrown if the database is in an
unsupported format (for example, created by a newer version of Xapian
which uses an incompatible format).
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def add_database(self, *args):
"""
Add an existing database (or group of databases) to those accessed by
this object.
void Xapian::Database::add_database(const Database &database)
Parameters:
-----------
database: the database(s) to add.
"""
return _xapian.Database_add_database(self, *args)
__swig_destroy__ = _xapian.delete_Database
def __init__(self, *args):
"""
Copying is allowed.
Xapian::Database::Database(const Database &other)
The internals are reference counted, so copying is cheap.
Parameters:
-----------
other: The object to copy.
"""
_xapian.Database_swiginit(self,_xapian.new_Database(*args))
def reopen(self):
"""
Re-open the database.
void Xapian::Database::reopen()
This re-opens the database(s) to the latest available version(s). It
can be used either to make sure the latest results are returned, or to
recover from a Xapian::DatabaseModifiedError.
Calling reopen() on a database which has been closed (with close())
will always raise a Xapian::DatabaseError.
"""
return _xapian.Database_reopen(self)
def close(self):
"""
Close the database.
virtual void Xapian::Database::close()
This closes the database and closes all its file handles.
For a WritableDatabase, if a transaction is active it will be aborted,
while if no transaction is active commit() will be implicitly called.
Also the write lock is released.
Closing a database cannot be undone - in particular, calling reopen()
after close() will not reopen it, but will instead throw a
Xapian::DatabaseError exception.
Calling close() again on a database which has already been closed has
no effect (and doesn't raise an exception).
After close() has been called, calls to other methods of the database,
and to methods of other objects associated with the database, will
either:
behave exactly as they would have done if the database had not been
closed (this can only happen if all the required data is cached)
raise a Xapian::DatabaseError exception indicating that the database
is closed.
The reason for this behaviour is that otherwise we'd have to check
that the database is still open on every method call on every object
associated with a Database, when in many cases they are working on
data which has already been loaded and so they are able to just behave
correctly.
This method was added in Xapian 1.1.0.
"""
return _xapian.Database_close(self)
def __str__(self):
"""
Return a string describing this object.
virtual std::string Xapian::Database::get_description() const
"""
return _xapian.Database___str__(self)
def postlist_begin(self, *args):
"""
An iterator pointing to the start of the postlist for a given term.
PostingIterator Xapian::Database::postlist_begin(const std::string
&tname) const
Parameters:
-----------
tname: The termname to iterate postings for. If the term name is the
empty string, the iterator returned will list all the documents in the
database. Such an iterator will always return a WDF value of 1, since
there is no obvious meaning for this quantity in this case.
"""
return _xapian.Database_postlist_begin(self, *args)
def postlist_end(self, *args):
"""
Corresponding end iterator to postlist_begin().
PostingIterator Xapian::Database::postlist_end(const std::string &)
const
"""
return _xapian.Database_postlist_end(self, *args)
def termlist_begin(self, *args):
"""
An iterator pointing to the start of the termlist for a given
document.
TermIterator Xapian::Database::termlist_begin(Xapian::docid did) const
Parameters:
-----------
did: The document id of the document to iterate terms for.
"""
return _xapian.Database_termlist_begin(self, *args)
def termlist_end(self, *args):
"""
Corresponding end iterator to termlist_begin().
TermIterator Xapian::Database::termlist_end(Xapian::docid) const
"""
return _xapian.Database_termlist_end(self, *args)
def positionlist_begin(self, *args):
"""
An iterator pointing to the start of the position list for a given
term in a given document.
PositionIterator Xapian::Database::positionlist_begin(Xapian::docid
did, const std::string &tname) const
"""
return _xapian.Database_positionlist_begin(self, *args)
def positionlist_end(self, *args):
"""
Corresponding end iterator to positionlist_begin().
PositionIterator Xapian::Database::positionlist_end(Xapian::docid,
const std::string &) const
"""
return _xapian.Database_positionlist_end(self, *args)
def allterms_begin(self, *args):
"""
An iterator which runs across all terms with a given prefix.
TermIterator Xapian::Database::allterms_begin(const std::string
&prefix) const
This is functionally similar to getting an iterator with
allterms_begin() and then calling skip_to(prefix) on that iterator to
move to the start of the prefix, but is more convenient (because it
detects the end of the prefixed terms), and may be more efficient than
simply calling skip_to() after opening the iterator, particularly for
remote databases.
Parameters:
-----------
prefix: The prefix to restrict the returned terms to.
"""
return _xapian.Database_allterms_begin(self, *args)
def allterms_end(self, *args):
"""
Corresponding end iterator to allterms_begin(prefix).
TermIterator Xapian::Database::allterms_end(const std::string &) const
"""
return _xapian.Database_allterms_end(self, *args)
def get_doccount(self):
"""
Get the number of documents in the database.
Xapian::doccount Xapian::Database::get_doccount() const
"""
return _xapian.Database_get_doccount(self)
def get_lastdocid(self):
"""
Get the highest document id which has been used in the database.
Xapian::docid Xapian::Database::get_lastdocid() const
"""
return _xapian.Database_get_lastdocid(self)
def get_avlength(self):
"""
Get the average length of the documents in the database.
Xapian::doclength Xapian::Database::get_avlength() const
"""
return _xapian.Database_get_avlength(self)
def get_termfreq(self, *args):
"""
Get the number of documents in the database indexed by a given term.
Xapian::doccount Xapian::Database::get_termfreq(const std::string
&tname) const
"""
return _xapian.Database_get_termfreq(self, *args)
def term_exists(self, *args):
"""
Check if a given term exists in the database.
bool Xapian::Database::term_exists(const std::string &tname) const
Parameters:
-----------
tname: The term to test the existence of.
true if and only if the term exists in the database. This is the same
as (get_termfreq(tname) != 0), but will often be more efficient.
"""
return _xapian.Database_term_exists(self, *args)
def get_collection_freq(self, *args):
"""
Return the total number of occurrences of the given term.
Xapian::termcount Xapian::Database::get_collection_freq(const
std::string &tname) const
This is the sum of the number of occurrences of the term in each
document it indexes: i.e., the sum of the within document frequencies
of the term.
Parameters:
-----------
tname: The term whose collection frequency is being requested.
"""
return _xapian.Database_get_collection_freq(self, *args)
def get_value_freq(self, *args):
"""
Return the frequency of a given value slot.
Xapian::doccount Xapian::Database::get_value_freq(Xapian::valueno
slot) const
This is the number of documents which have a (non-empty) value stored
in the slot.
Parameters:
-----------
slot: The value slot to examine.
Parameters:
-----------
UnimplementedError: The frequency of the value isn't available for
this database type.
"""
return _xapian.Database_get_value_freq(self, *args)
def get_value_lower_bound(self, *args):
"""
Get a lower bound on the values stored in the given value slot.
std::string Xapian::Database::get_value_lower_bound(Xapian::valueno
slot) const
If there are no values stored in the given value slot, this will
return an empty string.
If the lower bound isn't available for the given database type, this
will return the lowest possible bound - the empty string.
Parameters:
-----------
slot: The value slot to examine.
"""
return _xapian.Database_get_value_lower_bound(self, *args)
def get_value_upper_bound(self, *args):
"""
Get an upper bound on the values stored in the given value slot.
std::string Xapian::Database::get_value_upper_bound(Xapian::valueno
slot) const
If there are no values stored in the given value slot, this will
return an empty string.
Parameters:
-----------
slot: The value slot to examine.
Parameters:
-----------
UnimplementedError: The upper bound of the values isn't available for
this database type.
"""
return _xapian.Database_get_value_upper_bound(self, *args)
def get_doclength_lower_bound(self):
"""
Get a lower bound on the length of a document in this DB.
Xapian::termcount Xapian::Database::get_doclength_lower_bound() const
This bound does not include any zero-length documents.
"""
return _xapian.Database_get_doclength_lower_bound(self)
def get_doclength_upper_bound(self):
"""
Get an upper bound on the length of a document in this DB.
Xapian::termcount Xapian::Database::get_doclength_upper_bound() const
"""
return _xapian.Database_get_doclength_upper_bound(self)
def get_wdf_upper_bound(self, *args):
"""
Get an upper bound on the wdf of term term.
Xapian::termcount Xapian::Database::get_wdf_upper_bound(const
std::string &term) const
"""
return _xapian.Database_get_wdf_upper_bound(self, *args)
def valuestream_begin(self, *args):
"""
Return an iterator over the value in slot slot for each document.
ValueIterator Xapian::Database::valuestream_begin(Xapian::valueno
slot) const
"""
return _xapian.Database_valuestream_begin(self, *args)
def valuestream_end(self, *args):
"""
Return end iterator corresponding to valuestream_begin().
ValueIteratorEnd_ Xapian::Database::valuestream_end(Xapian::valueno)
const
"""
return _xapian.Database_valuestream_end(self, *args)
def get_doclength(self, *args):
"""
Get the length of a document.
Xapian::termcount Xapian::Database::get_doclength(Xapian::docid did)
const
"""
return _xapian.Database_get_doclength(self, *args)
def keep_alive(self):
"""
Send a "keep-alive" to remote databases to stop them timing out.
void Xapian::Database::keep_alive()
Has no effect on non-remote databases.
"""
return _xapian.Database_keep_alive(self)
def get_document(self, *args):
"""
Get a document from the database, given its document id.
Xapian::Document Xapian::Database::get_document(Xapian::docid did)
const
This method returns a Xapian::Document object which provides the
information about a document.
Parameters:
-----------
did: The document id of the document to retrieve.
A Xapian::Document object containing the document data
Parameters:
-----------
Xapian::DocNotFoundError: The document specified could not be found
in the database.
Xapian::InvalidArgumentError: did was 0, which is not a valid
document id.
"""
return _xapian.Database_get_document(self, *args)
def get_spelling_suggestion(self, *args):
"""
Suggest a spelling correction.
std::string Xapian::Database::get_spelling_suggestion(const
std::string &word, unsigned max_edit_distance=2) const
Parameters:
-----------
word: The potentially misspelled word.
max_edit_distance: Only consider words which are at most
max_edit_distance edits from word. An edit is a character insertion,
deletion, or the transposition of two adjacent characters (default is
2).
"""
return _xapian.Database_get_spelling_suggestion(self, *args)
def spellings_begin(self):
"""
An iterator which returns all the spelling correction targets.
Xapian::TermIterator Xapian::Database::spellings_begin() const
This returns all the words which are considered as targets for the
spelling correction algorithm. The frequency of each word is available
as the term frequency of each entry in the returned iterator.
"""
return _xapian.Database_spellings_begin(self)
def spellings_end(self):
"""
Corresponding end iterator to spellings_begin().
Xapian::TermIterator Xapian::Database::spellings_end() const
"""
return _xapian.Database_spellings_end(self)
def synonyms_begin(self, *args):
"""
An iterator which returns all the synonyms for a given term.
Xapian::TermIterator Xapian::Database::synonyms_begin(const
std::string &term) const
Parameters:
-----------
term: The term to return synonyms for.
"""
return _xapian.Database_synonyms_begin(self, *args)
def synonyms_end(self, *args):
"""
Corresponding end iterator to synonyms_begin(term).
Xapian::TermIterator Xapian::Database::synonyms_end(const std::string
&) const
"""
return _xapian.Database_synonyms_end(self, *args)
def synonym_keys_begin(self, prefix=""):
"""
An iterator which returns all terms which have synonyms.
Xapian::TermIterator Xapian::Database::synonym_keys_begin(const
std::string &prefix=std::string()) const
Parameters:
-----------
prefix: If non-empty, only terms with this prefix are returned.
"""
return _xapian.Database_synonym_keys_begin(self, prefix)
def synonym_keys_end(self, prefix=""):
"""
Corresponding end iterator to synonym_keys_begin(prefix).
Xapian::TermIterator Xapian::Database::synonym_keys_end(const
std::string &=std::string()) const
"""
return _xapian.Database_synonym_keys_end(self, prefix)
def get_metadata(self, *args):
"""
Get the user-specified metadata associated with a given key.
std::string Xapian::Database::get_metadata(const std::string &key)
const
User-specified metadata allows you to store arbitrary information in
the form of (key,tag) pairs. See WritableDatabase::set_metadata() for
more information.
When invoked on a Xapian::Database object representing multiple
databases, currently only the metadata for the first is considered but
this behaviour may change in the future.
If there is no piece of metadata associated with the specified key, an
empty string is returned (this applies even for backends which don't
support metadata).
Empty keys are not valid, and specifying one will cause an exception.
Parameters:
-----------
key: The key of the metadata item to access.
The retrieved metadata item's value.
Parameters:
-----------
Xapian::InvalidArgumentError: will be thrown if the key supplied is
empty.
"""
return _xapian.Database_get_metadata(self, *args)
def _metadata_keys_begin(self, prefix=""):
"""
An iterator which returns all user-specified metadata keys.
Xapian::TermIterator Xapian::Database::metadata_keys_begin(const
std::string &prefix=std::string()) const
When invoked on a Xapian::Database object representing multiple
databases, currently only the metadata for the first is considered but
this behaviour may change in the future.
If the backend doesn't support metadata, then this method returns an
iterator which compares equal to that returned by metadata_keys_end().
Parameters:
-----------
prefix: If non-empty, only keys with this prefix are returned.
Parameters:
-----------
Xapian::UnimplementedError: will be thrown if the backend implements
user-specified metadata, but doesn't implement iterating its keys
(currently this happens for the InMemory backend).
"""
return _xapian.Database__metadata_keys_begin(self, prefix)
def _metadata_keys_end(self, prefix=""):
"""
Corresponding end iterator to metadata_keys_begin().
Xapian::TermIterator Xapian::Database::metadata_keys_end(const
std::string &=std::string()) const
"""
return _xapian.Database__metadata_keys_end(self, prefix)
def get_uuid(self):
"""
Get a UUID for the database.
std::string Xapian::Database::get_uuid() const
The UUID will persist for the lifetime of the database.
Replicas (eg, made with the replication protocol, or by copying all
the database files) will have the same UUID. However, copies (made
with copydatabase, or xapian-compact) will have different UUIDs.
If the backend does not support UUIDs or this database has no
subdatabases, the UUID will be empty.
If this database has multiple sub-databases, the UUID string will
contain the UUIDs of all the sub-databases.
"""
return _xapian.Database_get_uuid(self)
def has_positions(self):
"""
Does this database have any positional information?
bool Xapian::Database::has_positions() const
"""
return _xapian.Database_has_positions(self)
Database.add_database = new_instancemethod(_xapian.Database_add_database,None,Database)
Database.reopen = new_instancemethod(_xapian.Database_reopen,None,Database)
Database.close = new_instancemethod(_xapian.Database_close,None,Database)
Database.__str__ = new_instancemethod(_xapian.Database___str__,None,Database)
Database.postlist_begin = new_instancemethod(_xapian.Database_postlist_begin,None,Database)
Database.postlist_end = new_instancemethod(_xapian.Database_postlist_end,None,Database)
Database.termlist_begin = new_instancemethod(_xapian.Database_termlist_begin,None,Database)
Database.termlist_end = new_instancemethod(_xapian.Database_termlist_end,None,Database)
Database.positionlist_begin = new_instancemethod(_xapian.Database_positionlist_begin,None,Database)
Database.positionlist_end = new_instancemethod(_xapian.Database_positionlist_end,None,Database)
Database.allterms_begin = new_instancemethod(_xapian.Database_allterms_begin,None,Database)
Database.allterms_end = new_instancemethod(_xapian.Database_allterms_end,None,Database)
Database.get_doccount = new_instancemethod(_xapian.Database_get_doccount,None,Database)
Database.get_lastdocid = new_instancemethod(_xapian.Database_get_lastdocid,None,Database)
Database.get_avlength = new_instancemethod(_xapian.Database_get_avlength,None,Database)
Database.get_termfreq = new_instancemethod(_xapian.Database_get_termfreq,None,Database)
Database.term_exists = new_instancemethod(_xapian.Database_term_exists,None,Database)
Database.get_collection_freq = new_instancemethod(_xapian.Database_get_collection_freq,None,Database)
Database.get_value_freq = new_instancemethod(_xapian.Database_get_value_freq,None,Database)
Database.get_value_lower_bound = new_instancemethod(_xapian.Database_get_value_lower_bound,None,Database)
Database.get_value_upper_bound = new_instancemethod(_xapian.Database_get_value_upper_bound,None,Database)
Database.get_doclength_lower_bound = new_instancemethod(_xapian.Database_get_doclength_lower_bound,None,Database)
Database.get_doclength_upper_bound = new_instancemethod(_xapian.Database_get_doclength_upper_bound,None,Database)
Database.get_wdf_upper_bound = new_instancemethod(_xapian.Database_get_wdf_upper_bound,None,Database)
Database.valuestream_begin = new_instancemethod(_xapian.Database_valuestream_begin,None,Database)
Database.valuestream_end = new_instancemethod(_xapian.Database_valuestream_end,None,Database)
Database.get_doclength = new_instancemethod(_xapian.Database_get_doclength,None,Database)
Database.keep_alive = new_instancemethod(_xapian.Database_keep_alive,None,Database)
Database.get_document = new_instancemethod(_xapian.Database_get_document,None,Database)
Database.get_spelling_suggestion = new_instancemethod(_xapian.Database_get_spelling_suggestion,None,Database)
Database.spellings_begin = new_instancemethod(_xapian.Database_spellings_begin,None,Database)
Database.spellings_end = new_instancemethod(_xapian.Database_spellings_end,None,Database)
Database.synonyms_begin = new_instancemethod(_xapian.Database_synonyms_begin,None,Database)
Database.synonyms_end = new_instancemethod(_xapian.Database_synonyms_end,None,Database)
Database.synonym_keys_begin = new_instancemethod(_xapian.Database_synonym_keys_begin,None,Database)
Database.synonym_keys_end = new_instancemethod(_xapian.Database_synonym_keys_end,None,Database)
Database.get_metadata = new_instancemethod(_xapian.Database_get_metadata,None,Database)
Database._metadata_keys_begin = new_instancemethod(_xapian.Database__metadata_keys_begin,None,Database)
Database._metadata_keys_end = new_instancemethod(_xapian.Database__metadata_keys_end,None,Database)
Database.get_uuid = new_instancemethod(_xapian.Database_get_uuid,None,Database)
Database.has_positions = new_instancemethod(_xapian.Database_has_positions,None,Database)
Database_swigregister = _xapian.Database_swigregister
Database_swigregister(Database)
class WritableDatabase(Database):
"""
This class provides read/write access to a database.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
__swig_destroy__ = _xapian.delete_WritableDatabase
def __init__(self, *args):
"""
Copying is allowed.
Xapian::WritableDatabase::WritableDatabase(const WritableDatabase
&other)
The internals are reference counted, so copying is cheap.
Parameters:
-----------
other: The object to copy.
"""
_xapian.WritableDatabase_swiginit(self,_xapian.new_WritableDatabase(*args))
def commit(self):
"""
Commit any pending modifications made to the database.
void Xapian::WritableDatabase::commit()
For efficiency reasons, when performing multiple updates to a database
it is best (indeed, almost essential) to make as many modifications as
memory will permit in a single pass through the database. To ensure
this, Xapian batches up modifications.
This method may be called at any time to commit any pending
modifications to the database.
If any of the modifications fail, an exception will be thrown and the
database will be left in a state in which each separate addition,
replacement or deletion operation has either been fully performed or
not performed at all: it is then up to the application to work out
which operations need to be repeated.
It's not valid to call commit() within a transaction.
Beware of calling commit() too frequently: this will make indexing
take much longer.
Note that commit() need not be called explicitly: it will be called
automatically when the database is closed, or when a sufficient number
of modifications have been made. By default, this is every 10000
documents added, deleted, or modified. This value is rather
conservative, and if you have a machine with plenty of memory, you can
improve indexing throughput dramatically by setting
XAPIAN_FLUSH_THRESHOLD in the environment to a larger value.
This method was new in Xapian 1.1.0 - in earlier versions it was
called flush().
Parameters:
-----------
Xapian::DatabaseError: will be thrown if a problem occurs while
modifying the database.
Xapian::DatabaseCorruptError: will be thrown if the database is in a
corrupt state.
"""
return _xapian.WritableDatabase_commit(self)
def flush(self):
"""
Pre-1.1.0 name for commit().
void Xapian::WritableDatabase::flush()
Use commit() instead in new code. This alias may be deprecated in the
future.
"""
return _xapian.WritableDatabase_flush(self)
def begin_transaction(self, flushed=True):
"""
Begin a transaction.
void Xapian::WritableDatabase::begin_transaction(bool flushed=true)
In Xapian a transaction is a group of modifications to the database
which are linked such that either all will be applied simultaneously
or none will be applied at all. Even in the case of a power failure,
this characteristic should be preserved (as long as the filesystem
isn't corrupted, etc).
A transaction is started with begin_transaction() and can either be
committed by calling commit_transaction() or aborted by calling
cancel_transaction().
By default, a transaction implicitly calls commit() before and after
so that the modifications stand and fall without affecting
modifications before or after.
The downside of these implicit calls to commit() is that small
transactions can harm indexing performance in the same way that
explicitly calling commit() frequently can.
If you're applying atomic groups of changes and only wish to ensure
that each group is either applied or not applied, then you can prevent
the automatic commit() before and after the transaction by starting
the transaction with begin_transaction(false). However, if
cancel_transaction is called (or if commit_transaction isn't called
before the WritableDatabase object is destroyed) then any changes
which were pending before the transaction began will also be
discarded.
Transactions aren't currently supported by the InMemory backend.
Parameters:
-----------
flushed: Is this a flushed transaction? By default transactions are
"flushed", which means that committing a transaction will ensure
those changes are permanently written to the database. By contrast,
unflushed transactions only ensure that changes within the transaction
are either all applied or all aren't.
Parameters:
-----------
Xapian::UnimplementedError: will be thrown if transactions are not
available for this database type.
Xapian::InvalidOperationError: will be thrown if this is called at an
invalid time, such as when a transaction is already in progress.
"""
return _xapian.WritableDatabase_begin_transaction(self, flushed)
def commit_transaction(self):
"""
Complete the transaction currently in progress.
void Xapian::WritableDatabase::commit_transaction()
If this method completes successfully and this is a flushed
transaction, all the database modifications made during the
transaction will have been committed to the database.
If an error occurs, an exception will be thrown, and none of the
modifications made to the database during the transaction will have
been applied to the database.
In all cases the transaction will no longer be in progress.
Parameters:
-----------
Xapian::DatabaseError: will be thrown if a problem occurs while
modifying the database.
Xapian::DatabaseCorruptError: will be thrown if the database is in a
corrupt state.
Xapian::InvalidOperationError: will be thrown if a transaction is not
currently in progress.
Xapian::UnimplementedError: will be thrown if transactions are not
available for this database type.
"""
return _xapian.WritableDatabase_commit_transaction(self)
def cancel_transaction(self):
"""
Abort the transaction currently in progress, discarding the pending
modifications made to the database.
void Xapian::WritableDatabase::cancel_transaction()
If an error occurs in this method, an exception will be thrown, but
the transaction will be cancelled anyway.
Parameters:
-----------
Xapian::DatabaseError: will be thrown if a problem occurs while
modifying the database.
Xapian::DatabaseCorruptError: will be thrown if the database is in a
corrupt state.
Xapian::InvalidOperationError: will be thrown if a transaction is not
currently in progress.
Xapian::UnimplementedError: will be thrown if transactions are not
available for this database type.
"""
return _xapian.WritableDatabase_cancel_transaction(self)
def add_document(self, *args):
"""
Add a new document to the database.
Xapian::docid Xapian::WritableDatabase::add_document(const
Xapian::Document &document)
This method adds the specified document to the database, returning a
newly allocated document ID. Automatically allocated document IDs come
from a per-database monotonically increasing counter, so IDs from
deleted documents won't be reused.
If you want to specify the document ID to be used, you should call
replace_document() instead.
Note that changes to the database won't be immediately committed to
disk; see commit() for more details.
As with all database modification operations, the effect is atomic:
the document will either be fully added, or the document fails to be
added and an exception is thrown (possibly at a later time when
commit() is called or the database is closed).
Parameters:
-----------
document: The new document to be added.
The document ID of the newly added document.
Parameters:
-----------
Xapian::DatabaseError: will be thrown if a problem occurs while
writing to the database.
Xapian::DatabaseCorruptError: will be thrown if the database is in a
corrupt state.
"""
return _xapian.WritableDatabase_add_document(self, *args)
def delete_document(self, *args):
"""
Delete any documents indexed by a term from the database.
void Xapian::WritableDatabase::delete_document(const std::string
&unique_term)
This method removes any documents indexed by the specified term from
the database.
A major use is for convenience when UIDs from another system are
mapped to terms in Xapian, although this method has other uses (for
example, you could add a "deletion date" term to documents at index
time and use this method to delete all documents due for deletion on a
particular date).
Parameters:
-----------
unique_term: The term to remove references to.
Parameters:
-----------
Xapian::DatabaseError: will be thrown if a problem occurs while
writing to the database.
Xapian::DatabaseCorruptError: will be thrown if the database is in a
corrupt state.
"""
return _xapian.WritableDatabase_delete_document(self, *args)
def replace_document(self, *args):
"""
Replace any documents matching a term.
Xapian::docid Xapian::WritableDatabase::replace_document(const
std::string &unique_term, const Xapian::Document &document)
This method replaces any documents indexed by the specified term with
the specified document. If any documents are indexed by the term, the
lowest document ID will be used for the document, otherwise a new
document ID will be generated as for add_document.
One common use is to allow UIDs from another system to easily be
mapped to terms in Xapian. Note that this method doesn't automatically
add unique_term as a term, so you'll need to call
document.add_term(unique_term) first when using replace_document() in
this way.
Note that changes to the database won't be immediately committed to
disk; see commit() for more details.
As with all database modification operations, the effect is atomic:
the document(s) will either be fully replaced, or the document(s) fail
to be replaced and an exception is thrown (possibly at a later time
when commit() is called or the database is closed).
Parameters:
-----------
unique_term: The "unique" term.
document: The new document.
The document ID that document was given.
Parameters:
-----------
Xapian::DatabaseError: will be thrown if a problem occurs while
writing to the database.
Xapian::DatabaseCorruptError: will be thrown if the database is in a
corrupt state.
"""
return _xapian.WritableDatabase_replace_document(self, *args)
def add_spelling(self, *args):
"""
Add a word to the spelling dictionary.
void Xapian::WritableDatabase::add_spelling(const std::string &word,
Xapian::termcount freqinc=1) const
If the word is already present, its frequency is increased.
Parameters:
-----------
word: The word to add.
freqinc: How much to increase its frequency by (default 1).
"""
return _xapian.WritableDatabase_add_spelling(self, *args)
def remove_spelling(self, *args):
"""
Remove a word from the spelling dictionary.
void Xapian::WritableDatabase::remove_spelling(const std::string
&word, Xapian::termcount freqdec=1) const
The word's frequency is decreased, and if would become zero or less
then the word is removed completely.
Parameters:
-----------
word: The word to remove.
freqdec: How much to decrease its frequency by (default 1).
"""
return _xapian.WritableDatabase_remove_spelling(self, *args)
def add_synonym(self, *args):
"""
Add a synonym for a term.
void Xapian::WritableDatabase::add_synonym(const std::string &term,
const std::string &synonym) const
Parameters:
-----------
term: The term to add a synonym for.
synonym: The synonym to add. If this is already a synonym for term,
then no action is taken.
"""
return _xapian.WritableDatabase_add_synonym(self, *args)
def remove_synonym(self, *args):
"""
Remove a synonym for a term.
void Xapian::WritableDatabase::remove_synonym(const std::string &term,
const std::string &synonym) const
Parameters:
-----------
term: The term to remove a synonym for.
synonym: The synonym to remove. If this isn't currently a synonym for
term, then no action is taken.
"""
return _xapian.WritableDatabase_remove_synonym(self, *args)
def clear_synonyms(self, *args):
"""
Remove all synonyms for a term.
void Xapian::WritableDatabase::clear_synonyms(const std::string &term)
const
Parameters:
-----------
term: The term to remove all synonyms for. If the term has no
synonyms, no action is taken.
"""
return _xapian.WritableDatabase_clear_synonyms(self, *args)
def set_metadata(self, *args):
"""
Set the user-specified metadata associated with a given key.
void Xapian::WritableDatabase::set_metadata(const std::string &key,
const std::string &value)
This method sets the metadata value associated with a given key. If
there is already a metadata value stored in the database with the same
key, the old value is replaced. If you want to delete an existing item
of metadata, just set its value to the empty string.
User-specified metadata allows you to store arbitrary information in
the form of (key,tag) pairs.
There's no hard limit on the number of metadata items, or the size of
the metadata values. Metadata keys have a limited length, which
depends on the backend. We recommend limiting them to 200 bytes. Empty
keys are not valid, and specifying one will cause an exception.
Metadata modifications are committed to disk in the same way as
modifications to the documents in the database are: i.e.,
modifications are atomic, and won't be committed to disk immediately
(see commit() for more details). This allows metadata to be used to
link databases with versioned external resources by storing the
appropriate version number in a metadata item.
You can also use the metadata to store arbitrary extra information
associated with terms, documents, or postings by encoding the termname
and/or document id into the metadata key.
Parameters:
-----------
key: The key of the metadata item to set.
value: The value of the metadata item to set.
Parameters:
-----------
Xapian::DatabaseError: will be thrown if a problem occurs while
writing to the database.
Xapian::DatabaseCorruptError: will be thrown if the database is in a
corrupt state.
Xapian::InvalidArgumentError: will be thrown if the key supplied is
empty.
Xapian::UnimplementedError: will be thrown if the database backend in
use doesn't support user- specified metadata.
"""
return _xapian.WritableDatabase_set_metadata(self, *args)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::WritableDatabase::get_description() const
"""
return _xapian.WritableDatabase___str__(self)
WritableDatabase.commit = new_instancemethod(_xapian.WritableDatabase_commit,None,WritableDatabase)
WritableDatabase.flush = new_instancemethod(_xapian.WritableDatabase_flush,None,WritableDatabase)
WritableDatabase.begin_transaction = new_instancemethod(_xapian.WritableDatabase_begin_transaction,None,WritableDatabase)
WritableDatabase.commit_transaction = new_instancemethod(_xapian.WritableDatabase_commit_transaction,None,WritableDatabase)
WritableDatabase.cancel_transaction = new_instancemethod(_xapian.WritableDatabase_cancel_transaction,None,WritableDatabase)
WritableDatabase.add_document = new_instancemethod(_xapian.WritableDatabase_add_document,None,WritableDatabase)
WritableDatabase.delete_document = new_instancemethod(_xapian.WritableDatabase_delete_document,None,WritableDatabase)
WritableDatabase.replace_document = new_instancemethod(_xapian.WritableDatabase_replace_document,None,WritableDatabase)
WritableDatabase.add_spelling = new_instancemethod(_xapian.WritableDatabase_add_spelling,None,WritableDatabase)
WritableDatabase.remove_spelling = new_instancemethod(_xapian.WritableDatabase_remove_spelling,None,WritableDatabase)
WritableDatabase.add_synonym = new_instancemethod(_xapian.WritableDatabase_add_synonym,None,WritableDatabase)
WritableDatabase.remove_synonym = new_instancemethod(_xapian.WritableDatabase_remove_synonym,None,WritableDatabase)
WritableDatabase.clear_synonyms = new_instancemethod(_xapian.WritableDatabase_clear_synonyms,None,WritableDatabase)
WritableDatabase.set_metadata = new_instancemethod(_xapian.WritableDatabase_set_metadata,None,WritableDatabase)
WritableDatabase.__str__ = new_instancemethod(_xapian.WritableDatabase___str__,None,WritableDatabase)
WritableDatabase_swigregister = _xapian.WritableDatabase_swigregister
WritableDatabase_swigregister(WritableDatabase)
DB_CREATE_OR_OPEN = _xapian.DB_CREATE_OR_OPEN
DB_CREATE = _xapian.DB_CREATE
DB_CREATE_OR_OVERWRITE = _xapian.DB_CREATE_OR_OVERWRITE
DB_OPEN = _xapian.DB_OPEN
def open_stub(*args):
"""
Construct a WritableDatabase object for a stub database file.
WritableDatabase Xapian::Auto::open_stub(const std::string &file, int
action)
The stub database file must contain serialised parameters for exactly
one database.
Parameters:
-----------
file: pathname of the stub database file.
action: determines handling of existing/non-existing database:
Xapian::DB_CREATE fail if database already exist, otherwise create new
database.
Xapian::DB_CREATE_OR_OPEN open existing database, or create new
database if none exists.
Xapian::DB_CREATE_OR_OVERWRITE overwrite existing database, or create
new database if none exists.
Xapian::DB_OPEN open existing database, failing if none exists.
"""
return _xapian.open_stub(*args)
def brass_open(*args):
"""
Construct a Database object for update access to a Brass database.
WritableDatabase Xapian::Brass::open(const std::string &dir, int
action, int block_size=8192)
Parameters:
-----------
dir: pathname of the directory containing the database.
action: determines handling of existing/non-existing database:
Xapian::DB_CREATE fail if database already exist, otherwise create new
database.
Xapian::DB_CREATE_OR_OPEN open existing database, or create new
database if none exists.
Xapian::DB_CREATE_OR_OVERWRITE overwrite existing database, or create
new database if none exists.
Xapian::DB_OPEN open existing database, failing if none exists.
block_size: the Btree blocksize to use (in bytes), which must be a
power of two between 2048 and 65536 (inclusive). The default (also
used if an invalid value if passed) is 8192 bytes. This parameter is
ignored when opening an existing database.
"""
return _xapian.brass_open(*args)
def chert_open(*args):
"""
Construct a Database object for update access to a Chert database.
WritableDatabase Xapian::Chert::open(const std::string &dir, int
action, int block_size=8192)
Parameters:
-----------
dir: pathname of the directory containing the database.
action: determines handling of existing/non-existing database:
Xapian::DB_CREATE fail if database already exist, otherwise create new
database.
Xapian::DB_CREATE_OR_OPEN open existing database, or create new
database if none exists.
Xapian::DB_CREATE_OR_OVERWRITE overwrite existing database, or create
new database if none exists.
Xapian::DB_OPEN open existing database, failing if none exists.
block_size: the Btree blocksize to use (in bytes), which must be a
power of two between 2048 and 65536 (inclusive). The default (also
used if an invalid value if passed) is 8192 bytes. This parameter is
ignored when opening an existing database.
"""
return _xapian.chert_open(*args)
def flint_open(*args):
"""
Construct a Database object for update access to a Flint database.
WritableDatabase Xapian::Flint::open(const std::string &dir, int
action, int block_size=8192)
Parameters:
-----------
dir: pathname of the directory containing the database.
action: determines handling of existing/non-existing database:
Xapian::DB_CREATE fail if database already exist, otherwise create new
database.
Xapian::DB_CREATE_OR_OPEN open existing database, or create new
database if none exists.
Xapian::DB_CREATE_OR_OVERWRITE overwrite existing database, or create
new database if none exists.
Xapian::DB_OPEN open existing database, failing if none exists.
block_size: the Btree blocksize to use (in bytes), which must be a
power of two between 2048 and 65536 (inclusive). The default (also
used if an invalid value if passed) is 8192 bytes. This parameter is
ignored when opening an existing database.
"""
return _xapian.flint_open(*args)
def inmemory_open():
"""
Construct a WritableDatabase object for a new, empty InMemory
database.
WritableDatabase Xapian::InMemory::open()
Only a writable InMemory database can be created, since a read-only
one would always remain empty.
"""
return _xapian.inmemory_open()
def remote_open(*args):
"""
Construct a Database object for read-only access to a remote database
accessed via a program.
Database Xapian::Remote::open(const std::string &program, const
std::string &args, Xapian::timeout timeout=10000)
Access to the remote database is done by running an external program
and communicating with it on stdin/stdout.
Parameters:
-----------
program: the external program to run.
args: space-separated list of arguments to pass to program.
timeout: timeout in milliseconds. If this timeout is exceeded for any
individual operation on the remote database then
Xapian::NetworkTimeoutError is thrown. A timeout of 0 means don't
timeout. (Default is 10000ms, which is 10 seconds).
"""
return _xapian.remote_open(*args)
def remote_open_writable(*args):
"""
Construct a WritableDatabase object for update access to a remote
database accessed via a program.
WritableDatabase Xapian::Remote::open_writable(const std::string
&program, const std::string &args, Xapian::timeout timeout=0)
Access to the remote database is done by running an external program
and communicating with it on stdin/stdout.
Parameters:
-----------
program: the external program to run.
args: space-separated list of arguments to pass to program.
timeout: timeout in milliseconds. If this timeout is exceeded for any
individual operation on the remote database then
Xapian::NetworkTimeoutError is thrown. (Default is 0, which means
don't timeout).
"""
return _xapian.remote_open_writable(*args)
class Query(object):
"""
Class representing a query.
Queries are represented as a tree of objects.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
OP_AND = _xapian.Query_OP_AND
OP_OR = _xapian.Query_OP_OR
OP_AND_NOT = _xapian.Query_OP_AND_NOT
OP_XOR = _xapian.Query_OP_XOR
OP_AND_MAYBE = _xapian.Query_OP_AND_MAYBE
OP_FILTER = _xapian.Query_OP_FILTER
OP_NEAR = _xapian.Query_OP_NEAR
OP_PHRASE = _xapian.Query_OP_PHRASE
OP_VALUE_RANGE = _xapian.Query_OP_VALUE_RANGE
OP_SCALE_WEIGHT = _xapian.Query_OP_SCALE_WEIGHT
OP_ELITE_SET = _xapian.Query_OP_ELITE_SET
OP_VALUE_GE = _xapian.Query_OP_VALUE_GE
OP_VALUE_LE = _xapian.Query_OP_VALUE_LE
OP_SYNONYM = _xapian.Query_OP_SYNONYM
__swig_destroy__ = _xapian.delete_Query
def get_length(self):
"""
Get the length of the query, used by some ranking formulae.
Xapian::termcount Xapian::Query::get_length() const
This value is calculated automatically - if you want to override it
you can pass a different value to Enquire::set_query().
"""
return _xapian.Query_get_length(self)
def get_terms_begin(self):
"""
Return a Xapian::TermIterator returning all the terms in the query, in
order of termpos.
TermIterator Xapian::Query::get_terms_begin() const
If multiple terms have the same term position, their order is
unspecified. Duplicates (same term and termpos) will be removed.
"""
return _xapian.Query_get_terms_begin(self)
def get_terms_end(self):
"""
Return a Xapian::TermIterator to the end of the list of terms in the
query.
TermIterator Xapian::Query::get_terms_end() const
"""
return _xapian.Query_get_terms_end(self)
def empty(self):
"""
Test if the query is empty (i.e.
bool Xapian::Query::empty() const
was constructed using the default ctor or with an empty iterator
ctor).
"""
return _xapian.Query_empty(self)
def serialise(self):
"""
Serialise query into a string.
std::string Xapian::Query::serialise() const
The query representation may change between Xapian releases: even
between minor versions. However, it is guaranteed not to change unless
the remote database protocol has also changed between releases.
"""
return _xapian.Query_serialise(self)
unserialise = staticmethod(_xapian.Query_unserialise)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::Query::get_description() const
"""
return _xapian.Query___str__(self)
def __init__(self, *args):
"""
Construct an external source query.
Xapian::Query::Query(Xapian::PostingSource *external_source)
An attempt to clone the posting source will be made immediately, so if
the posting source supports clone(), the source supplied may be safely
deallocated after this call. If the source does not support clone(),
the caller must ensure that the posting source remains valid until the
Query is deallocated.
Parameters:
-----------
external_source: The source to use in the query.
"""
_xapian.Query_swiginit(self,_xapian.new_Query(*args))
Query.get_length = new_instancemethod(_xapian.Query_get_length,None,Query)
Query.get_terms_begin = new_instancemethod(_xapian.Query_get_terms_begin,None,Query)
Query.get_terms_end = new_instancemethod(_xapian.Query_get_terms_end,None,Query)
Query.empty = new_instancemethod(_xapian.Query_empty,None,Query)
Query.serialise = new_instancemethod(_xapian.Query_serialise,None,Query)
Query.__str__ = new_instancemethod(_xapian.Query___str__,None,Query)
Query_swigregister = _xapian.Query_swigregister
Query_swigregister(Query)
def Query_unserialise(*args):
return _xapian.Query_unserialise(*args)
Query_unserialise = _xapian.Query_unserialise
class Stopper(object):
"""
Base class for stop-word decision functor.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
__swig_destroy__ = _xapian.delete_Stopper
def __str__(self):
"""
Return a string describing this object.
virtual std::string Xapian::Stopper::get_description() const
"""
return _xapian.Stopper___str__(self)
def __init__(self):
if self.__class__ == Stopper:
_self = None
else:
_self = self
_xapian.Stopper_swiginit(self,_xapian.new_Stopper(_self, ))
def __disown__(self):
self.this.disown()
_xapian.disown_Stopper(self)
return weakref_proxy(self)
Stopper.__call__ = new_instancemethod(_xapian.Stopper___call__,None,Stopper)
Stopper.__str__ = new_instancemethod(_xapian.Stopper___str__,None,Stopper)
Stopper_swigregister = _xapian.Stopper_swigregister
Stopper_swigregister(Stopper)
class SimpleStopper(Stopper):
"""
Simple implementation of Stopper class - this will suit most users.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self):
"""
Initialise from a pair of iterators.
Xapian::SimpleStopper::SimpleStopper(Iterator begin, Iterator end)
"""
_xapian.SimpleStopper_swiginit(self,_xapian.new_SimpleStopper())
def add(self, *args):
"""
Add a single stop word.
void Xapian::SimpleStopper::add(const std::string &word)
"""
return _xapian.SimpleStopper_add(self, *args)
__swig_destroy__ = _xapian.delete_SimpleStopper
SimpleStopper.add = new_instancemethod(_xapian.SimpleStopper_add,None,SimpleStopper)
SimpleStopper_swigregister = _xapian.SimpleStopper_swigregister
SimpleStopper_swigregister(SimpleStopper)
class ValueRangeProcessor(object):
"""
Base class for value range processors.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
__swig_destroy__ = _xapian.delete_ValueRangeProcessor
def __init__(self):
if self.__class__ == ValueRangeProcessor:
_self = None
else:
_self = self
_xapian.ValueRangeProcessor_swiginit(self,_xapian.new_ValueRangeProcessor(_self, ))
def __disown__(self):
self.this.disown()
_xapian.disown_ValueRangeProcessor(self)
return weakref_proxy(self)
ValueRangeProcessor.__call__ = new_instancemethod(_xapian.ValueRangeProcessor___call__,None,ValueRangeProcessor)
ValueRangeProcessor_swigregister = _xapian.ValueRangeProcessor_swigregister
ValueRangeProcessor_swigregister(ValueRangeProcessor)
class StringValueRangeProcessor(ValueRangeProcessor):
"""
Handle a string range.
The end points can be any strings.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Constructor.
Xapian::StringValueRangeProcessor::StringValueRangeProcessor(Xapian::valueno
slot_, const std::string &str_, bool prefix_=true)
Parameters:
-----------
slot_: The value number to return from operator().
str_: A string to look for to recognise values as belonging to this
range.
prefix_: Flag specifying whether to check for str_ as a prefix or a
suffix.
"""
_xapian.StringValueRangeProcessor_swiginit(self,_xapian.new_StringValueRangeProcessor(*args))
__swig_destroy__ = _xapian.delete_StringValueRangeProcessor
StringValueRangeProcessor_swigregister = _xapian.StringValueRangeProcessor_swigregister
StringValueRangeProcessor_swigregister(StringValueRangeProcessor)
class DateValueRangeProcessor(StringValueRangeProcessor):
"""
Handle a date range.
Begin and end must be dates in a recognised format.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Constructor.
Xapian::DateValueRangeProcessor::DateValueRangeProcessor(Xapian::valueno
slot_, const char *str_, bool prefix_=true, bool prefer_mdy_=false,
int epoch_year_=1970)
This is like the previous version, but with const char * instead of
std::string - we need this overload as otherwise
DateValueRangeProcessor(1, "date:") quietly interprets the second
argument as a boolean in preference to std::string. If you want to be
compatible with 1.2.12 and earlier, then explicitly convert to
std::string, i.e.: DateValueRangeProcessor(1, std::string("date:"))
Parameters:
-----------
slot_: The value number to return from operator().
str_: A string to look for to recognise values as belonging to this
date range.
prefix_: Whether to look for the string at the start or end of the
values. If true, the string is a prefix; if false, the string is a
suffix (default: true).
prefer_mdy_: Should ambiguous dates be interpreted as month/day/year
rather than day/month/year? (default: false)
epoch_year_: Year to use as the epoch for dates with 2 digit years
(default: 1970, so 1/1/69 is 2069 while 1/1/70 is 1970).
The string supplied in str_ is used by operator() to decide whether
the pair of strings supplied to it constitute a valid range. If
prefix_ is true, the first value in a range must begin with str_ (and
the second value may optionally begin with str_); if prefix_ is false,
the second value in a range must end with str_ (and the first value
may optionally end with str_).
If str_ is empty, the setting of prefix_ is irrelevant, and no special
strings are required at the start or end of the strings defining the
range.
The remainder of both strings defining the endpoints must be valid
dates.
For example, if str_ is "created:" and prefix_ is true, and the
range processor has been added to the queryparser, the queryparser
will accept "created:1/1/2000..31/12/2001".
"""
_xapian.DateValueRangeProcessor_swiginit(self,_xapian.new_DateValueRangeProcessor(*args))
__swig_destroy__ = _xapian.delete_DateValueRangeProcessor
DateValueRangeProcessor_swigregister = _xapian.DateValueRangeProcessor_swigregister
DateValueRangeProcessor_swigregister(DateValueRangeProcessor)
class NumberValueRangeProcessor(StringValueRangeProcessor):
"""
Handle a number range.
This class must be used on values which have been encoded using
Xapian::sortable_serialise() which turns numbers into strings which
will sort in the same order as the numbers (the same values can be
used to implement a numeric sort).
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Constructor.
Xapian::NumberValueRangeProcessor::NumberValueRangeProcessor(Xapian::valueno
slot_, const std::string &str_, bool prefix_=true)
Parameters:
-----------
slot_: The value number to return from operator().
str_: A string to look for to recognise values as belonging to this
numeric range.
prefix_: Whether to look for the string at the start or end of the
values. If true, the string is a prefix; if false, the string is a
suffix (default: true).
The string supplied in str_ is used by operator() to decide whether
the pair of strings supplied to it constitute a valid range. If
prefix_ is true, the first value in a range must begin with str_ (and
the second value may optionally begin with str_); if prefix_ is false,
the second value in a range must end with str_ (and the first value
may optionally end with str_).
If str_ is empty, the setting of prefix_ is irrelevant, and no special
strings are required at the start or end of the strings defining the
range.
The remainder of both strings defining the endpoints must be valid
floating point numbers. (FIXME: define format recognised).
For example, if str_ is "$" and prefix_ is true, and the range
processor has been added to the queryparser, the queryparser will
accept "$10..50" or "$10..$50", but not "10..50" or "10..$50"
as valid ranges. If str_ is "kg" and prefix_ is false, the
queryparser will accept "10..50kg" or "10kg..50kg", but not
"10..50" or "10kg..50" as valid ranges.
"""
_xapian.NumberValueRangeProcessor_swiginit(self,_xapian.new_NumberValueRangeProcessor(*args))
__swig_destroy__ = _xapian.delete_NumberValueRangeProcessor
NumberValueRangeProcessor_swigregister = _xapian.NumberValueRangeProcessor_swigregister
NumberValueRangeProcessor_swigregister(NumberValueRangeProcessor)
class QueryParser(object):
"""
Build a Xapian::Query object from a user query string.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
FLAG_BOOLEAN = _xapian.QueryParser_FLAG_BOOLEAN
FLAG_PHRASE = _xapian.QueryParser_FLAG_PHRASE
FLAG_LOVEHATE = _xapian.QueryParser_FLAG_LOVEHATE
FLAG_BOOLEAN_ANY_CASE = _xapian.QueryParser_FLAG_BOOLEAN_ANY_CASE
FLAG_WILDCARD = _xapian.QueryParser_FLAG_WILDCARD
FLAG_PURE_NOT = _xapian.QueryParser_FLAG_PURE_NOT
FLAG_PARTIAL = _xapian.QueryParser_FLAG_PARTIAL
FLAG_SPELLING_CORRECTION = _xapian.QueryParser_FLAG_SPELLING_CORRECTION
FLAG_SYNONYM = _xapian.QueryParser_FLAG_SYNONYM
FLAG_AUTO_SYNONYMS = _xapian.QueryParser_FLAG_AUTO_SYNONYMS
FLAG_AUTO_MULTIWORD_SYNONYMS = _xapian.QueryParser_FLAG_AUTO_MULTIWORD_SYNONYMS
FLAG_DEFAULT = _xapian.QueryParser_FLAG_DEFAULT
STEM_NONE = _xapian.QueryParser_STEM_NONE
STEM_SOME = _xapian.QueryParser_STEM_SOME
STEM_ALL = _xapian.QueryParser_STEM_ALL
STEM_ALL_Z = _xapian.QueryParser_STEM_ALL_Z
def __init__(self):
"""
Default constructor.
Xapian::QueryParser::QueryParser()
"""
_xapian.QueryParser_swiginit(self,_xapian.new_QueryParser())
__swig_destroy__ = _xapian.delete_QueryParser
def set_stemmer(self, *args):
"""
Set the stemmer.
void Xapian::QueryParser::set_stemmer(const Xapian::Stem &stemmer)
This sets the stemming algorithm which will be used by the query
parser. Note that the stemming algorithm will only be used according
to the stemming strategy set by set_stemming_strategy(), which
defaults to STEM_NONE. Therefore, to use a stemming algorithm, you
will also need to call set_stemming_strategy() with a value other than
STEM_NONE.
Parameters:
-----------
stemmer: The Xapian::Stem object to set.
"""
return _xapian.QueryParser_set_stemmer(self, *args)
def set_stemming_strategy(self, *args):
"""
Set the stemming strategy.
void Xapian::QueryParser::set_stemming_strategy(stem_strategy
strategy)
This controls how the query parser will apply the stemming algorithm.
Note that the stemming algorithm is only applied to words in
probabilistic fields - boolean filter terms are never stemmed.
Parameters:
-----------
strategy: The strategy to use - possible values are: STEM_NONE: Don't
perform any stemming. (default in Xapian <= 1.3.0)
STEM_SOME: Search for stemmed forms of terms except for those which
start with a capital letter, or are followed by certain characters
(currently: (/@<>=*[{" ), or are used with operators which need
positional information. Stemmed terms are prefixed with 'Z'. (default
in Xapian >= 1.3.1)
STEM_ALL: Search for stemmed forms of all words (note: no 'Z' prefix
is added).
STEM_ALL_Z: Search for stemmed forms of all words (note: 'Z' prefix is
added). (new in Xapian 1.2.11 and 1.3.1)
"""
return _xapian.QueryParser_set_stemming_strategy(self, *args)
def set_stopper(self, stop=None):
"""
Set the stopper.
void Xapian::QueryParser::set_stopper(const Stopper *stop=NULL)
Parameters:
-----------
stop: The Stopper object to set (default NULL, which means no
stopwords).
"""
return _xapian.QueryParser_set_stopper(self, stop)
def set_default_op(self, *args):
"""
Set the default operator.
void Xapian::QueryParser::set_default_op(Query::op default_op)
Parameters:
-----------
default_op: The operator to use to combine non-filter query items
when no explicit operator is used.
The most useful values for this are OP_OR (the default) and OP_AND.
OP_NEAR and OP_PHRASE can also be useful.
So for example, 'weather forecast' is parsed as if it were 'weather OR
forecast' by default.
"""
return _xapian.QueryParser_set_default_op(self, *args)
def get_default_op(self):
"""
Get the current default operator.
Query::op Xapian::QueryParser::get_default_op() const
"""
return _xapian.QueryParser_get_default_op(self)
def set_database(self, *args):
"""
Specify the database being searched.
void Xapian::QueryParser::set_database(const Database &db)
Parameters:
-----------
db: The database to use for wildcard expansion (FLAG_WILDCARD and
FLAG_PARTIAL), spelling correction (FLAG_SPELLING_CORRECTION), and
synonyms (FLAG_SYNONYM, FLAG_AUTO_SYNONYMS, and
FLAG_AUTO_MULTIWORD_SYNONYMS).
"""
return _xapian.QueryParser_set_database(self, *args)
def set_max_wildcard_expansion(self, *args):
"""
Specify the maximum expansion of a wildcard term.
void Xapian::QueryParser::set_max_wildcard_expansion(Xapian::termcount
limit)
Note: you must also set FLAG_WILDCARD for wildcard expansion to
happen.
Parameters:
-----------
limit: The maximum number of terms each wildcard in the query can
expand to, or 0 for no limit (which is the default).
"""
return _xapian.QueryParser_set_max_wildcard_expansion(self, *args)
def parse_query(self, *args):
"""
Parse a query.
Query Xapian::QueryParser::parse_query(const std::string
&query_string, unsigned flags=FLAG_DEFAULT, const std::string
&default_prefix=std::string())
Parameters:
-----------
query_string: A free-text query as entered by a user
flags: Zero or more Query::feature_flag specifying what features the
QueryParser should support. Combine multiple values with bitwise-or
(|) (default FLAG_DEFAULT).
default_prefix: The default term prefix to use (default none). For
example, you can pass "A" when parsing an "Author" field.
Parameters:
-----------
If: the query string can't be parsed, then Xapian::QueryParserError
is thrown. You can get an English error message to report to the user
by catching it and calling get_msg() on the caught exception. The
current possible values (in case you want to translate them) are: @li
Unknown range operation @li parse error @li Syntax:
<expression> AND <expression> @li Syntax:
<expression> AND NOT <expression> @li Syntax:
<expression> NOT <expression> @li Syntax:
<expression> OR <expression> @li Syntax:
<expression> XOR <expression>
"""
return _xapian.QueryParser_parse_query(self, *args)
def add_prefix(self, *args):
"""
Add a probabilistic term prefix.
void Xapian::QueryParser::add_prefix(const std::string &field, const
std::string &prefix)
For example:
This allows the user to search for author:Orwell which will be
converted to a search for the term "Aorwell".
Multiple fields can be mapped to the same prefix. For example, you can
make title: and subject: aliases for each other.
As of 1.0.4, you can call this method multiple times with the same
value of field to allow a single field to be mapped to multiple
prefixes. Multiple terms being generated for such a field, and
combined with Xapian::Query::OP_OR.
If any prefixes are specified for the empty field name (i.e. you call
this method with an empty string as the first parameter) these
prefixes will be used for terms without a field specifier. If you do
this and also specify the default_prefix parameter to parse_query(),
then the default_prefix parameter will override.
If the prefix parameter is empty, then "field:word" will produce the
term "word" (and this can be one of several prefixes for a
particular field, or for terms without a field specifier).
If you call add_prefix() and add_boolean_prefix() for the same value
of field, a Xapian::InvalidOperationError exception will be thrown.
In 1.0.3 and earlier, subsequent calls to this method with the same
value of field had no effect.
Parameters:
-----------
field: The user visible field name
prefix: The term prefix to map this to
"""
return _xapian.QueryParser_add_prefix(self, *args)
def add_boolean_prefix(self, *args):
"""
void
Xapian::QueryParser::add_boolean_prefix(const std::string &field,
const std::string &prefix)
"""
return _xapian.QueryParser_add_boolean_prefix(self, *args)
def stoplist_begin(self):
"""
Iterate over terms omitted from the query as stopwords.
TermIterator Xapian::QueryParser::stoplist_begin() const
"""
return _xapian.QueryParser_stoplist_begin(self)
def stoplist_end(self):
"""TermIterator Xapian::QueryParser::stoplist_end() const """
return _xapian.QueryParser_stoplist_end(self)
def unstem_begin(self, *args):
"""
Iterate over unstemmed forms of the given (stemmed) term used in the
query.
TermIterator Xapian::QueryParser::unstem_begin(const std::string
&term) const
"""
return _xapian.QueryParser_unstem_begin(self, *args)
def unstem_end(self, *args):
"""
TermIterator
Xapian::QueryParser::unstem_end(const std::string &) const
"""
return _xapian.QueryParser_unstem_end(self, *args)
def add_valuerangeprocessor(self, *args):
"""
Register a ValueRangeProcessor.
void
Xapian::QueryParser::add_valuerangeprocessor(Xapian::ValueRangeProcessor
*vrproc)
"""
return _xapian.QueryParser_add_valuerangeprocessor(self, *args)
def get_corrected_query_string(self):
"""
Get the spelling-corrected query string.
std::string Xapian::QueryParser::get_corrected_query_string() const
This will only be set if FLAG_SPELLING_CORRECTION is specified when
QueryParser::parse_query() was last called.
If there were no corrections, an empty string is returned.
"""
return _xapian.QueryParser_get_corrected_query_string(self)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::QueryParser::get_description() const
"""
return _xapian.QueryParser___str__(self)
QueryParser.set_stemmer = new_instancemethod(_xapian.QueryParser_set_stemmer,None,QueryParser)
QueryParser.set_stemming_strategy = new_instancemethod(_xapian.QueryParser_set_stemming_strategy,None,QueryParser)
QueryParser.set_stopper = new_instancemethod(_xapian.QueryParser_set_stopper,None,QueryParser)
QueryParser.set_default_op = new_instancemethod(_xapian.QueryParser_set_default_op,None,QueryParser)
QueryParser.get_default_op = new_instancemethod(_xapian.QueryParser_get_default_op,None,QueryParser)
QueryParser.set_database = new_instancemethod(_xapian.QueryParser_set_database,None,QueryParser)
QueryParser.set_max_wildcard_expansion = new_instancemethod(_xapian.QueryParser_set_max_wildcard_expansion,None,QueryParser)
QueryParser.parse_query = new_instancemethod(_xapian.QueryParser_parse_query,None,QueryParser)
QueryParser.add_prefix = new_instancemethod(_xapian.QueryParser_add_prefix,None,QueryParser)
QueryParser.add_boolean_prefix = new_instancemethod(_xapian.QueryParser_add_boolean_prefix,None,QueryParser)
QueryParser.stoplist_begin = new_instancemethod(_xapian.QueryParser_stoplist_begin,None,QueryParser)
QueryParser.stoplist_end = new_instancemethod(_xapian.QueryParser_stoplist_end,None,QueryParser)
QueryParser.unstem_begin = new_instancemethod(_xapian.QueryParser_unstem_begin,None,QueryParser)
QueryParser.unstem_end = new_instancemethod(_xapian.QueryParser_unstem_end,None,QueryParser)
QueryParser.add_valuerangeprocessor = new_instancemethod(_xapian.QueryParser_add_valuerangeprocessor,None,QueryParser)
QueryParser.get_corrected_query_string = new_instancemethod(_xapian.QueryParser_get_corrected_query_string,None,QueryParser)
QueryParser.__str__ = new_instancemethod(_xapian.QueryParser___str__,None,QueryParser)
QueryParser_swigregister = _xapian.QueryParser_swigregister
QueryParser_swigregister(QueryParser)
def sortable_serialise(*args):
return _xapian.sortable_serialise(*args)
sortable_serialise = _xapian.sortable_serialise
def sortable_unserialise(*args):
return _xapian.sortable_unserialise(*args)
sortable_unserialise = _xapian.sortable_unserialise
class StemImplementation(object):
"""
Class representing a stemming algorithm implementation.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
__swig_destroy__ = _xapian.delete_StemImplementation
def __str__(self):
"""
Return a string describing this object.
virtual std::string Xapian::StemImplementation::get_description()
const =0
"""
return _xapian.StemImplementation___str__(self)
def __init__(self):
if self.__class__ == StemImplementation:
_self = None
else:
_self = self
_xapian.StemImplementation_swiginit(self,_xapian.new_StemImplementation(_self, ))
def __disown__(self):
self.this.disown()
_xapian.disown_StemImplementation(self)
return weakref_proxy(self)
StemImplementation.__call__ = new_instancemethod(_xapian.StemImplementation___call__,None,StemImplementation)
StemImplementation.__str__ = new_instancemethod(_xapian.StemImplementation___str__,None,StemImplementation)
StemImplementation_swigregister = _xapian.StemImplementation_swigregister
StemImplementation_swigregister(StemImplementation)
class Stem(object):
"""
Class representing a stemming algorithm.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct a Xapian::Stem object with a user-provided stemming
algorithm.
Xapian::Stem::Stem(StemImplementation *p)
You can subclass Xapian::StemImplementation to implement your own
stemming algorithm (or to wrap a third-party algorithm) and then wrap
your implementation in a Xapian::Stem object to pass to the Xapian
API.
Parameters:
-----------
p: The user-subclassed StemImplementation object. This is reference
counted, and so will be automatically deleted by the Xapian::Stem
wrapper when no longer required.
"""
_xapian.Stem_swiginit(self,_xapian.new_Stem(*args))
__swig_destroy__ = _xapian.delete_Stem
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::Stem::get_description() const
"""
return _xapian.Stem___str__(self)
get_available_languages = staticmethod(_xapian.Stem_get_available_languages)
Stem.__call__ = new_instancemethod(_xapian.Stem___call__,None,Stem)
Stem.__str__ = new_instancemethod(_xapian.Stem___str__,None,Stem)
Stem_swigregister = _xapian.Stem_swigregister
Stem_swigregister(Stem)
def Stem_get_available_languages():
return _xapian.Stem_get_available_languages()
Stem_get_available_languages = _xapian.Stem_get_available_languages
class TermGenerator(object):
"""
Parses a piece of text and generate terms.
This module takes a piece of text and parses it to produce words which
are then used to generate suitable terms for indexing. The terms
generated are suitable for use with Query objects produced by the
QueryParser class.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self):
"""
Default constructor.
Xapian::TermGenerator::TermGenerator()
"""
_xapian.TermGenerator_swiginit(self,_xapian.new_TermGenerator())
__swig_destroy__ = _xapian.delete_TermGenerator
def set_stemmer(self, *args):
"""
Set the Xapian::Stem object to be used for generating stemmed terms.
void Xapian::TermGenerator::set_stemmer(const Xapian::Stem &stemmer)
"""
return _xapian.TermGenerator_set_stemmer(self, *args)
def set_stopper(self, stop=None):
"""
Set the Xapian::Stopper object to be used for identifying stopwords.
void Xapian::TermGenerator::set_stopper(const Xapian::Stopper
*stop=NULL)
Stemmed forms of stopwords aren't indexed, but unstemmed forms still
are so that searches for phrases including stop words still work.
Parameters:
-----------
stop: The Stopper object to set (default NULL, which means no
stopwords).
"""
return _xapian.TermGenerator_set_stopper(self, stop)
def set_document(self, *args):
"""
Set the current document.
void Xapian::TermGenerator::set_document(const Xapian::Document &doc)
"""
return _xapian.TermGenerator_set_document(self, *args)
def get_document(self):
"""
Get the current document.
const Xapian::Document& Xapian::TermGenerator::get_document() const
"""
return _xapian.TermGenerator_get_document(self)
def set_database(self, *args):
"""
Set the database to index spelling data to.
void Xapian::TermGenerator::set_database(const
Xapian::WritableDatabase &db)
"""
return _xapian.TermGenerator_set_database(self, *args)
FLAG_SPELLING = _xapian.TermGenerator_FLAG_SPELLING
STEM_NONE = _xapian.TermGenerator_STEM_NONE
STEM_SOME = _xapian.TermGenerator_STEM_SOME
STEM_ALL = _xapian.TermGenerator_STEM_ALL
STEM_ALL_Z = _xapian.TermGenerator_STEM_ALL_Z
def set_flags(self, *args):
"""
Set flags.
flags Xapian::TermGenerator::set_flags(flags toggle, flags
mask=flags(0))
The new value of flags is: (flags & mask) ^ toggle
To just set the flags, pass the new flags in toggle and the default
value for mask.
Parameters:
-----------
toggle: Flags to XOR.
mask: Flags to AND with first.
The old flags setting.
"""
return _xapian.TermGenerator_set_flags(self, *args)
def set_stemming_strategy(self, *args):
"""
Set the stemming strategy.
void Xapian::TermGenerator::set_stemming_strategy(stem_strategy
strategy)
This method controls how the stemming algorithm is applied. It was new
in Xapian 1.3.1.
Parameters:
-----------
strategy: The strategy to use - possible values are: STEM_NONE: Don't
perform any stemming - only unstemmed terms are generated.
STEM_SOME: Generate both stemmed (with a "Z" prefix) and unstemmed
terms. This is the default strategy.
STEM_ALL: Generate only stemmed terms (but without a "Z" prefix).
STEM_ALL_Z: Generate only stemmed terms (with a "Z" prefix).
"""
return _xapian.TermGenerator_set_stemming_strategy(self, *args)
def set_max_word_length(self, *args):
"""
Set the maximum length word to index.
void Xapian::TermGenerator::set_max_word_length(unsigned
max_word_length)
The limit is on the length of a word prior to stemming and prior to
adding any term prefix.
The backends mostly impose a limit on the length of terms (often of
about 240 bytes), but it's generally useful to have a lower limit to
help prevent the index being bloated by useless junk terms from trying
to indexing things like binary data, uuencoded data, ASCII art, etc.
This method was new in Xapian 1.3.1.
Parameters:
-----------
max_word_length: The maximum length word to index, in bytes in UTF-8
representation. Default is 64.
"""
return _xapian.TermGenerator_set_max_word_length(self, *args)
def index_text(self, *args):
"""
Index some text in a std::string.
void Xapian::TermGenerator::index_text(const std::string &text,
Xapian::termcount wdf_inc=1, const std::string &prefix=std::string())
Parameters:
-----------
text: The text to index.
wdf_inc: The wdf increment (default 1).
prefix: The term prefix to use (default is no prefix).
"""
return _xapian.TermGenerator_index_text(self, *args)
def index_text_without_positions(self, *args):
"""
Index some text in a std::string without positional information.
void Xapian::TermGenerator::index_text_without_positions(const
std::string &text, Xapian::termcount wdf_inc=1, const std::string
&prefix=std::string())
Just like index_text, but no positional information is generated. This
means that the database will be significantly smaller, but that phrase
searching and NEAR won't be supported.
Parameters:
-----------
text: The text to index.
wdf_inc: The wdf increment (default 1).
prefix: The term prefix to use (default is no prefix).
"""
return _xapian.TermGenerator_index_text_without_positions(self, *args)
def increase_termpos(self, delta=100):
"""
Increase the term position used by index_text.
void Xapian::TermGenerator::increase_termpos(Xapian::termcount
delta=100)
This can be used between indexing text from different fields or other
places to prevent phrase searches from spanning between them (e.g.
between the title and body text, or between two chapters in a book).
Parameters:
-----------
delta: Amount to increase the term position by (default: 100).
"""
return _xapian.TermGenerator_increase_termpos(self, delta)
def get_termpos(self):
"""
Get the current term position.
Xapian::termcount Xapian::TermGenerator::get_termpos() const
"""
return _xapian.TermGenerator_get_termpos(self)
def set_termpos(self, *args):
"""
Set the current term position.
void Xapian::TermGenerator::set_termpos(Xapian::termcount termpos)
Parameters:
-----------
termpos: The new term position to set.
"""
return _xapian.TermGenerator_set_termpos(self, *args)
def __str__(self):
"""
Return a string describing this object.
std::string Xapian::TermGenerator::get_description() const
"""
return _xapian.TermGenerator___str__(self)
TermGenerator.set_stemmer = new_instancemethod(_xapian.TermGenerator_set_stemmer,None,TermGenerator)
TermGenerator.set_stopper = new_instancemethod(_xapian.TermGenerator_set_stopper,None,TermGenerator)
TermGenerator.set_document = new_instancemethod(_xapian.TermGenerator_set_document,None,TermGenerator)
TermGenerator.get_document = new_instancemethod(_xapian.TermGenerator_get_document,None,TermGenerator)
TermGenerator.set_database = new_instancemethod(_xapian.TermGenerator_set_database,None,TermGenerator)
TermGenerator.set_flags = new_instancemethod(_xapian.TermGenerator_set_flags,None,TermGenerator)
TermGenerator.set_stemming_strategy = new_instancemethod(_xapian.TermGenerator_set_stemming_strategy,None,TermGenerator)
TermGenerator.set_max_word_length = new_instancemethod(_xapian.TermGenerator_set_max_word_length,None,TermGenerator)
TermGenerator.index_text = new_instancemethod(_xapian.TermGenerator_index_text,None,TermGenerator)
TermGenerator.index_text_without_positions = new_instancemethod(_xapian.TermGenerator_index_text_without_positions,None,TermGenerator)
TermGenerator.increase_termpos = new_instancemethod(_xapian.TermGenerator_increase_termpos,None,TermGenerator)
TermGenerator.get_termpos = new_instancemethod(_xapian.TermGenerator_get_termpos,None,TermGenerator)
TermGenerator.set_termpos = new_instancemethod(_xapian.TermGenerator_set_termpos,None,TermGenerator)
TermGenerator.__str__ = new_instancemethod(_xapian.TermGenerator___str__,None,TermGenerator)
TermGenerator_swigregister = _xapian.TermGenerator_swigregister
TermGenerator_swigregister(TermGenerator)
class KeyMaker(object):
"""
Virtual base class for key making functors.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
__swig_destroy__ = _xapian.delete_KeyMaker
def __init__(self):
if self.__class__ == KeyMaker:
_self = None
else:
_self = self
_xapian.KeyMaker_swiginit(self,_xapian.new_KeyMaker(_self, ))
def __disown__(self):
self.this.disown()
_xapian.disown_KeyMaker(self)
return weakref_proxy(self)
KeyMaker.__call__ = new_instancemethod(_xapian.KeyMaker___call__,None,KeyMaker)
KeyMaker_swigregister = _xapian.KeyMaker_swigregister
KeyMaker_swigregister(KeyMaker)
class MultiValueKeyMaker(KeyMaker):
"""
KeyMaker subclass which combines several values.
When the result is used for sorting, results are ordered by the first
value. In the event of a tie, the second is used. If this is the same
for both, the third is used, and so on. If reverse is true for a
value, then the sort order for that value is reversed.
When used for collapsing, the documents will only be considered equal
if all the values specified match. If none of the specified values are
set then the generated key will be empty, so such documents won't be
collapsed (which is consistent with the behaviour in the "collapse on
a value" case). If you'd prefer that documents with none of the keys
set are collapsed together, then you can set reverse for at least one
of the values. Other than this, it isn't useful to set reverse for
collapsing.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self):
"""
Xapian::MultiValueKeyMaker::MultiValueKeyMaker(Iterator begin,
Iterator end)
"""
_xapian.MultiValueKeyMaker_swiginit(self,_xapian.new_MultiValueKeyMaker())
def add_value(self, *args):
"""
void
Xapian::MultiValueKeyMaker::add_value(Xapian::valueno slot, bool
reverse=false)
"""
return _xapian.MultiValueKeyMaker_add_value(self, *args)
__swig_destroy__ = _xapian.delete_MultiValueKeyMaker
MultiValueKeyMaker.add_value = new_instancemethod(_xapian.MultiValueKeyMaker_add_value,None,MultiValueKeyMaker)
MultiValueKeyMaker_swigregister = _xapian.MultiValueKeyMaker_swigregister
MultiValueKeyMaker_swigregister(MultiValueKeyMaker)
class Sorter(KeyMaker):
"""
Virtual base class for sorter functor.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
def __init__(self, *args, **kwargs): raise AttributeError("No constructor defined - class is abstract")
__repr__ = _swig_repr
__swig_destroy__ = _xapian.delete_Sorter
Sorter_swigregister = _xapian.Sorter_swigregister
Sorter_swigregister(Sorter)
class MultiValueSorter(Sorter):
"""
Sorter subclass which sorts by a several values.
Results are ordered by the first value. In the event of a tie, the
second is used. If this is the same for both, the third is used, and
so on.
Deprecated This class is deprecated - you should migrate to using
MultiValueKeyMaker instead. Note that MultiValueSorter::add() becomes
MultiValueKeyMaker::add_value(), but the sense of the direction flag
is reversed (to be consistent with Enquire::set_sort_by_value()).
So: MultiValueSorter sorter; // Primary ordering is forwards on
value 4. sorter.add(4); // Secondary ordering is reverse on value
5. sorter.add(5, false); becomes: MultiValueKeyMaker sorter; //
Primary ordering is forwards on value 4. sorter.add_value(4); //
Secondary ordering is reverse on value 5. sorter.add_value(5, true);
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self):
"""
Xapian::MultiValueSorter::MultiValueSorter(Iterator begin, Iterator
end)
"""
_xapian.MultiValueSorter_swiginit(self,_xapian.new_MultiValueSorter())
def add(self, *args):
"""
void
Xapian::MultiValueSorter::add(Xapian::valueno slot, bool forward=true)
"""
return _xapian.MultiValueSorter_add(self, *args)
__swig_destroy__ = _xapian.delete_MultiValueSorter
MultiValueSorter.add = new_instancemethod(_xapian.MultiValueSorter_add,None,MultiValueSorter)
MultiValueSorter_swigregister = _xapian.MultiValueSorter_swigregister
MultiValueSorter_swigregister(MultiValueSorter)
class ValueSetMatchDecider(MatchDecider):
"""
MatchDecider filtering results based on whether document values are in
a user- defined set.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
def __init__(self, *args):
"""
Construct a ValueSetMatchDecider.
Xapian::ValueSetMatchDecider::ValueSetMatchDecider(Xapian::valueno
slot, bool inclusive_)
Parameters:
-----------
slot: The value slot number to look in.
inclusive_: If true, match decider accepts documents which have a
value in the specified slot which is a member of the test set; if
false, match decider accepts documents which do not have a value in
the specified slot.
"""
_xapian.ValueSetMatchDecider_swiginit(self,_xapian.new_ValueSetMatchDecider(*args))
def add_value(self, *args):
"""
Add a value to the test set.
void Xapian::ValueSetMatchDecider::add_value(const std::string &value)
Parameters:
-----------
value: The value to add to the test set.
"""
return _xapian.ValueSetMatchDecider_add_value(self, *args)
def remove_value(self, *args):
"""
Remove a value from the test set.
void Xapian::ValueSetMatchDecider::remove_value(const std::string
&value)
Parameters:
-----------
value: The value to remove from the test set.
"""
return _xapian.ValueSetMatchDecider_remove_value(self, *args)
__swig_destroy__ = _xapian.delete_ValueSetMatchDecider
ValueSetMatchDecider.add_value = new_instancemethod(_xapian.ValueSetMatchDecider_add_value,None,ValueSetMatchDecider)
ValueSetMatchDecider.remove_value = new_instancemethod(_xapian.ValueSetMatchDecider_remove_value,None,ValueSetMatchDecider)
ValueSetMatchDecider_swigregister = _xapian.ValueSetMatchDecider_swigregister
ValueSetMatchDecider_swigregister(ValueSetMatchDecider)
class Compactor(object):
"""
Compact a database, or merge and compact several.
"""
thisown = _swig_property(lambda x: x.this.own(), lambda x, v: x.this.own(v), doc='The membership flag')
__repr__ = _swig_repr
STANDARD = _xapian.Compactor_STANDARD
FULL = _xapian.Compactor_FULL
FULLER = _xapian.Compactor_FULLER
def __init__(self):
"""Xapian::Compactor::Compactor() """
if self.__class__ == Compactor:
_self = None
else:
_self = self
_xapian.Compactor_swiginit(self,_xapian.new_Compactor(_self, ))
__swig_destroy__ = _xapian.delete_Compactor
def set_block_size(self, *args):
"""
Set the block size to use for tables in the output database.
void Xapian::Compactor::set_block_size(size_t block_size)
Parameters:
-----------
block_size: The block size to use. Valid block sizes are currently
powers of two between 2048 and 65536, with the default being 8192, but
the valid sizes and default may change in the future.
"""
return _xapian.Compactor_set_block_size(self, *args)
def set_renumber(self, *args):
"""
Set whether to preserve existing document id values.
void Xapian::Compactor::set_renumber(bool renumber)
Parameters:
-----------
renumber: The default is true, which means that document ids will be
renumbered - currently by applying the same offset to all the document
ids in a particular source database.
If false, then the document ids must be unique over all source
databases. Currently the ranges of document ids in each source must
not overlap either, though this restriction may be removed in the
future.
"""
return _xapian.Compactor_set_renumber(self, *args)
def set_multipass(self, *args):
"""
Set whether to merge postlists in multiple passes.
void Xapian::Compactor::set_multipass(bool multipass)
Parameters:
-----------
multipass: If true and merging more than 3 databases, merge the
postlists in multiple passes, which is generally faster but requires
more disk space for temporary files. By default we don't do this.
"""
return _xapian.Compactor_set_multipass(self, *args)
def set_compaction_level(self, *args):
"""
Set the compaction level.
void Xapian::Compactor::set_compaction_level(compaction_level
compaction)
Parameters:
-----------
compaction: Available values are: - Xapian::Compactor::STANDARD -
Don't split items unnecessarily. - Xapian::Compactor::FULL - Split
items whenever it saves space (the default). -
Xapian::Compactor::FULLER - Allow oversize items to save more space
(not recommended if you ever plan to update the compacted database).
"""
return _xapian.Compactor_set_compaction_level(self, *args)
def set_destdir(self, *args):
"""
Set where to write the output.
void Xapian::Compactor::set_destdir(const std::string &destdir)
Parameters:
-----------
destdir: Output path. This can be the same as an input if that input
is a stub database (in which case the database(s) listed in the stub
will be compacted to a new database and then the stub will be
atomically updated to point to this new database).
"""
return _xapian.Compactor_set_destdir(self, *args)
def add_source(self, *args):
"""
Add a source database.
void Xapian::Compactor::add_source(const std::string &srcdir)
Parameters:
-----------
srcdir: The path to the source database to add.
"""
return _xapian.Compactor_add_source(self, *args)
def compact(self):
"""
Perform the actual compaction/merging operation.
void Xapian::Compactor::compact()
"""
return _xapian.Compactor_compact(self)
def set_status(self, *args):
"""
Update progress.
virtual void Xapian::Compactor::set_status(const std::string &table,
const std::string &status)
Subclass this method if you want to get progress updates during
compaction. This is called for each table first with empty status, And
then one or more times with non-empty status.
The default implementation does nothing.
Parameters:
-----------
table: The table currently being compacted.
status: A status message.
"""
return _xapian.Compactor_set_status(self, *args)
def resolve_duplicate_metadata(self, *args):
"""
Resolve multiple user metadata entries with the same key.
virtual std::string
Xapian::Compactor::resolve_duplicate_metadata(const std::string &key,
size_t num_tags, const std::string tags[])
When merging, if the same user metadata key is set in more than one
input, then this method is called to allow this to be resolving in an
appropriate way.
The default implementation just returns tags[0].
For multipass this will currently get called multiple times for the
same key if there are duplicates to resolve in each pass, but this may
change in the future.
Parameters:
-----------
key: The metadata key with duplicate entries.
num_tags: How many tags there are.
tags: An array of num_tags strings containing the tags to merge.
"""
return _xapian.Compactor_resolve_duplicate_metadata(self, *args)
def __disown__(self):
self.this.disown()
_xapian.disown_Compactor(self)
return weakref_proxy(self)
Compactor.set_block_size = new_instancemethod(_xapian.Compactor_set_block_size,None,Compactor)
Compactor.set_renumber = new_instancemethod(_xapian.Compactor_set_renumber,None,Compactor)
Compactor.set_multipass = new_instancemethod(_xapian.Compactor_set_multipass,None,Compactor)
Compactor.set_compaction_level = new_instancemethod(_xapian.Compactor_set_compaction_level,None,Compactor)
Compactor.set_destdir = new_instancemethod(_xapian.Compactor_set_destdir,None,Compactor)
Compactor.add_source = new_instancemethod(_xapian.Compactor_add_source,None,Compactor)
Compactor.compact = new_instancemethod(_xapian.Compactor_compact,None,Compactor)
Compactor.set_status = new_instancemethod(_xapian.Compactor_set_status,None,Compactor)
Compactor.resolve_duplicate_metadata = new_instancemethod(_xapian.Compactor_resolve_duplicate_metadata,None,Compactor)
Compactor_swigregister = _xapian.Compactor_swigregister
Compactor_swigregister(Compactor)
# Set the documentation format - this is used by tools like "epydoc" to decide
# how to format the documentation strings.
__docformat__ = "restructuredtext en"
##################################
# Support for iteration of MSets #
##################################
class MSetItem(object):
"""An item returned from iteration of the MSet.
The item supports access to the following attributes and properties:
- `docid`: The Xapian document ID corresponding to this MSet item.
- `weight`: The weight corresponding to this MSet item.
- `rank`: The rank of this MSet item. The rank is the position in the
total set of matching documents of this item. The highest document is
given a rank of 0. If the MSet did not start at the highest matching
document, because a non-zero 'start' parameter was supplied to
get_mset(), the first document in the MSet will have a rank greater than
0 (in fact, it will be equal to the value of 'start' supplied to
get_mset()).
- `percent`: The percentage score assigned to this MSet item.
- `document`: The document for this MSet item. This can be used to access
the document data, or any other information stored in the document (such
as term lists). It is lazily evaluated.
- `collapse_key`: The value of the key which was used for collapsing.
- `collapse_count`: An estimate of the number of documents that have been
collapsed into this one.
The collapse count estimate will always be less than or equal to the actual
number of other documents satisfying the match criteria with the same
collapse key as this document. If may be 0 even though there are other
documents with the same collapse key which satisfying the match criteria.
However if this method returns non-zero, there definitely are other such
documents. So this method may be used to inform the user that there are
"at least N other matches in this group", or to control whether to offer a
"show other documents in this group" feature (but note that it may not
offer it in every case where it would show other documents).
"""
__slots__ = ('_mset', '_firstitem', 'docid', 'weight', 'rank',
'percent', 'collapse_key', 'collapse_count', '_document', )
def __init__(self, iter, mset):
self._mset = mset
self._firstitem = self._mset.get_firstitem()
self.docid = iter.get_docid()
self.weight = iter.get_weight()
self.rank = iter.get_rank()
self.percent = iter.get_percent()
self.collapse_key = iter.get_collapse_key()
self.collapse_count = iter.get_collapse_count()
self._document = None
def _get_document(self):
if self._document is None:
self._document = self._mset._get_hit_internal(self.rank - self._firstitem).get_document()
return self._document
document = property(_get_document, doc="The document object corresponding to this MSet item.")
class MSetIter(object):
"""An iterator over the items in an MSet.
The iterator will return MSetItem objects, which will be evaluated lazily
where appropriate.
"""
__slots__ = ('_iter', '_end', '_mset')
def __init__(self, mset):
self._iter = mset.begin()
self._end = mset.end()
self._mset = mset
def __iter__(self):
return self
# For Python2:
def next(self):
if self._iter == self._end:
raise StopIteration
else:
r = MSetItem(self._iter, self._mset)
self._iter.next()
return r
# For Python3:
def __next__(self):
if self._iter == self._end:
raise StopIteration
else:
r = MSetItem(self._iter, self._mset)
next(self._iter)
return r
# Modify the MSet to allow access to the python iterators, and have other
# convenience methods.
def _mset_gen_iter(self):
"""Return an iterator over the MSet.
The iterator will return MSetItem objects, which will be evaluated lazily
where appropriate.
"""
return MSetIter(self)
MSet.__iter__ = _mset_gen_iter
MSet.__len__ = lambda self: MSet.size(self)
def _mset_getitem(self, index):
"""Get an item from the MSet.
The supplied index is relative to the start of the MSet, not the absolute
rank of the item.
Returns an MSetItem.
"""
if index < 0:
index += len(self)
if index < 0 or index >= len(self):
raise IndexError("Mset index out of range")
return MSetItem(self._get_hit_internal(index), self)
MSet.__getitem__ = _mset_getitem
MSet.get_hit = _mset_getitem
##################################
# Support for iteration of ESets #
##################################
class ESetItem(object):
"""An item returned from iteration of the ESet.
The item supports access to the following attributes:
- `term`: The term corresponding to this ESet item.
- `weight`: The weight corresponding to this ESet item.
"""
__slots__ = ('term', 'weight')
def __init__(self, iter):
self.term = iter.get_term()
self.weight = iter.get_weight()
class ESetIter(object):
"""An iterator over the items in an ESet.
The iterator will return ESetItem objects.
"""
__slots__ = ('_iter', '_end')
def __init__(self, eset):
self._iter = eset.begin()
self._end = eset.end()
def __iter__(self):
return self
# For Python2:
def next(self):
if self._iter == self._end:
raise StopIteration
else:
r = ESetItem(self._iter)
self._iter.next()
return r
# For Python3:
def __next__(self):
if self._iter == self._end:
raise StopIteration
else:
r = ESetItem(self._iter)
next(self._iter)
return r
# Modify the ESet to allow access to the python iterators, and have other
# convenience methods.
def _eset_gen_iter(self):
"""Return an iterator over the ESet.
The iterator will return ESetItem objects.
"""
return ESetIter(self)
ESet.__iter__ = _eset_gen_iter
ESet.__len__ = lambda self: ESet.size(self)
#######################################
# Support for iteration of term lists #
#######################################
class TermListItem(object):
"""An item returned from iteration of a term list.
The item supports access to the following attributes and properties:
- `term`: The term corresponding to this TermListItem.
- `wdf`: The within document frequency of this term.
- `termfreq`: The number of documents in the collection which are indexed
by the term
- `positer`: An iterator over the positions which the term appears at in
the document. This is only available until the iterator which returned
this item next moves.
"""
__slots__ = ('_iter', 'term', '_wdf', '_termfreq')
def __init__(self, iter, term):
self._iter = iter
self.term = term
self._wdf = None
self._termfreq = None
if iter._has_wdf == TermIter.EAGER:
self._wdf = iter._iter.get_wdf()
if iter._has_termfreq == TermIter.EAGER:
self._termfreq = iter._iter.get_termfreq()
# Support for sequence API
sequence = ['term', 'wdf', 'termfreq', 'positer']
if iter._has_wdf == TermIter.INVALID:
sequence[1] = 0
if iter._has_termfreq == TermIter.INVALID:
sequence[2] = 0
if iter._has_positions == TermIter.INVALID:
sequence[3] = PositionIter()
def _get_wdf(self):
"""Get the within-document-frequency of the current term.
This will raise a InvalidOperationError exception if the iterator this
item came from doesn't support within-document-frequencies.
"""
if self._wdf is None:
if self._iter._has_wdf == TermIter.INVALID:
raise InvalidOperationError("Iterator does not support wdfs")
if self.term is not self._iter._lastterm:
raise InvalidOperationError("Iterator has moved, and does not support random access")
self._wdf = self._iter._iter.get_wdf()
return self._wdf
wdf = property(_get_wdf, doc=
"""The within-document-frequency of the current term (if meaningful).
This will raise a InvalidOperationError exception if the iterator
this item came from doesn't support within-document-frequencies.
""")
def _get_termfreq(self):
"""Get the term frequency.
This is the number of documents in the collection which are indexed by
the term.
This will raise a InvalidOperationError exception if the iterator this
item came from doesn't support term frequencies.
"""
if self._termfreq is None:
if self._iter._has_termfreq == TermIter.INVALID:
raise InvalidOperationError("Iterator does not support term frequencies")
if self.term is not self._iter._lastterm:
raise InvalidOperationError("Iterator has moved, and does not support random access")
self._termfreq = self._iter._iter.get_termfreq()
return self._termfreq
termfreq = property(_get_termfreq, doc=
"""The term frequency of the current term (if meaningful).
This is the number of documents in the collection which are indexed by the
term.
This will raise a InvalidOperationError exception if the iterator
this item came from doesn't support term frequencies.
""")
def _get_positer(self):
"""Get a position list iterator.
The iterator will return integers representing the positions that the
term occurs at.
This will raise a InvalidOperationError exception if the iterator this
item came from doesn't support position lists, or if the iterator has
moved on since the item was returned from it.
"""
if self._iter._has_positions == TermIter.INVALID:
raise InvalidOperationError("Iterator does not support position lists")
# Access to position lists is always lazy, so we don't need to check
# _has_positions.
if self.term is not self._iter._lastterm:
raise InvalidOperationError("Iterator has moved, and does not support random access")
return PositionIter(self._iter._iter.positionlist_begin(),
self._iter._iter.positionlist_end())
positer = property(_get_positer, doc=
"""A position iterator for the current term (if meaningful).
The iterator will return integers representing the positions that the term
occurs at.
This will raise a InvalidOperationError exception if the iterator this item
came from doesn't support position lists, or if the iterator has moved on
since the item was returned from it.
""")
class TermIter(object):
"""An iterator over a term list.
The iterator will return TermListItem objects, which will be evaluated
lazily where appropriate.
"""
__slots__ = ('_iter', '_end', '_has_termfreq', '_has_wdf',
'_has_positions', '_return_strings', '_lastterm', '_moved')
INVALID = 0
LAZY = 1
EAGER = 2
def __init__(self, start, end, has_termfreq=INVALID,
has_wdf=INVALID, has_positions=INVALID,
return_strings=False):
self._iter = start
self._end = end
self._has_termfreq = has_termfreq
self._has_wdf = has_wdf
self._has_positions = has_positions
assert(has_positions != TermIter.EAGER) # Can't do eager access to position lists
self._return_strings = return_strings
self._lastterm = None # Used to test if the iterator has moved
# _moved is True if we've moved onto the next item. This is needed so
# that the iterator doesn't have to move on until just before next() is
# called: since the iterator starts by pointing at a valid item, we
# can't just call self._iter.next() unconditionally at the start of our
# next() method.
self._moved = True
def __iter__(self):
return self
# For Python2:
def next(self):
if not self._moved:
self._iter.next()
self._moved = True
if self._iter == self._end:
self._lastterm = None
raise StopIteration
else:
self._lastterm = self._iter.get_term()
self._moved = False
if self._return_strings:
return self._lastterm
return TermListItem(self, self._lastterm)
# For Python3:
def __next__(self):
if not self._moved:
next(self._iter)
self._moved = True
if self._iter == self._end:
self._lastterm = None
raise StopIteration
else:
self._lastterm = self._iter.get_term()
self._moved = False
if self._return_strings:
return self._lastterm
return TermListItem(self, self._lastterm)
def skip_to(self, term):
"""Skip the iterator forward.
The iterator is advanced to the first term at or after the current
position which is greater than or equal to the supplied term.
If there are no such items, this will raise StopIteration.
This returns the item which the iterator is moved to. The subsequent
item will be returned the next time that next() is called (unless
skip_to() is called again first).
"""
if self._iter != self._end:
self._iter.skip_to(term)
if self._iter == self._end:
self._lastterm = None
self._moved = True
raise StopIteration
# Update self._lastterm if the iterator has moved.
# TermListItems compare a saved value of lastterm with self._lastterm
# with the object identity comparator, so it is important to ensure
# that it does not get modified if the new term compares equal.
newterm = self._iter.get_term()
if newterm != self._lastterm:
self._lastterm = newterm
self._moved = False
if self._return_strings:
return self._lastterm
return TermListItem(self, self._lastterm)
# Modify Enquire to add a "matching_terms()" method.
def _enquire_gen_iter(self, which):
"""Get an iterator over the terms which match a given match set item.
The match set item to consider is specified by the `which` parameter, which
may be a document ID, or an MSetItem object.
The iterator will return string objects.
"""
if isinstance(which, MSetItem):
which = which.docid
return TermIter(self.get_matching_terms_begin(which),
self.get_matching_terms_end(which),
return_strings=True)
Enquire.matching_terms = _enquire_gen_iter
# Modify Query to add an "__iter__()" method.
def _query_gen_iter(self):
"""Get an iterator over the terms in a query.
The iterator will return string objects.
"""
return TermIter(self.get_terms_begin(),
self.get_terms_end(),
return_strings=True)
Query.__iter__ = _query_gen_iter
# Modify Database to add an "__iter__()" method and an "allterms()" method.
def _database_gen_allterms_iter(self, prefix=None):
"""Get an iterator over all the terms in the database.
The iterator will return TermListItem objects, but these will not support
access to wdf, or position information.
Access to term frequency information is only available until the iterator
has moved on.
If prefix is supplied, only terms which start with that prefix will be
returned.
"""
if prefix is None:
return TermIter(self.allterms_begin(), self.allterms_end(),
has_termfreq=TermIter.LAZY)
else:
return TermIter(self.allterms_begin(prefix), self.allterms_end(prefix),
has_termfreq=TermIter.LAZY)
Database.__iter__ = _database_gen_allterms_iter
Database.allterms = _database_gen_allterms_iter
# Modify Database to add a "termlist()" method.
def _database_gen_termlist_iter(self, docid):
"""Get an iterator over all the terms which index a given document ID.
The iterator will return TermListItem objects.
Access to term frequency and position information is only available until
the iterator has moved on.
"""
# Note: has_termfreq is set to LAZY because most databases don't store term
# frequencies in the termlist (because this would require updating many termlist
# entries for every document update), so access to the term frequency requires a
# separate lookup.
return TermIter(self.termlist_begin(docid), self.termlist_end(docid),
has_termfreq=TermIter.LAZY,
has_wdf=TermIter.EAGER,
has_positions=TermIter.LAZY)
Database.termlist = _database_gen_termlist_iter
# Modify Database to add a "spellings()" method.
def _database_gen_spellings_iter(self):
"""Get an iterator which returns all the spelling correction targets
The iterator will return TermListItem objects. Only the term frequency is
available; wdf and positions are not meaningful.
"""
return TermIter(self.spellings_begin(), self.spellings_end(),
has_termfreq=TermIter.EAGER,
has_wdf=TermIter.INVALID,
has_positions=TermIter.INVALID)
Database.spellings = _database_gen_spellings_iter
# Modify Database to add a "synonyms()" method.
def _database_gen_synonyms_iter(self, term):
"""Get an iterator which returns all the synonyms for a given term.
The term to return synonyms for is specified by the `term` parameter.
The iterator will return string objects.
"""
return TermIter(self.synonyms_begin(term),
self.synonyms_end(term),
return_strings=True)
Database.synonyms = _database_gen_synonyms_iter
# Modify Database to add a "synonym_keys()" method.
def _database_gen_synonym_keys_iter(self, prefix=""):
"""Get an iterator which returns all the terms which have synonyms.
The iterator will return string objects.
If `prefix` is non-empty, only terms with this prefix are returned.
"""
return TermIter(self.synonym_keys_begin(prefix),
self.synonym_keys_end(prefix),
return_strings=True)
Database.synonym_keys = _database_gen_synonym_keys_iter
# Modify Database to add a "metadata_keys()" method, instead of direct access
# to metadata_keys_begin and metadata_keys_end.
def _database_gen_metadata_keys_iter(self, prefix=""):
"""Get an iterator which returns all the metadata keys.
The iterator will return string objects.
If `prefix` is non-empty, only metadata keys with this prefix are returned.
"""
return TermIter(self._metadata_keys_begin(prefix),
self._metadata_keys_end(prefix),
return_strings=True)
Database.metadata_keys = _database_gen_metadata_keys_iter
# Modify Document to add an "__iter__()" method and a "termlist()" method.
def _document_gen_termlist_iter(self):
"""Get an iterator over all the terms in a document.
The iterator will return TermListItem objects.
Access to term frequency and position information is only available until
the iterator has moved on.
Note that term frequency information is only meaningful for a document
retrieved from a database. If term frequency information is requested for
a document which was freshly created, an InvalidOperationError will be
raised.
"""
# Note: document termlist iterators may be implemented entirely in-memory
# (in which case access to all items could be allowed eagerly), but may
# also be implemented by returning a database termlist (for documents which
# are stored in a database, rather than freshly created). We choose the
# most conservative settings, to avoid doing eager access when lazy access
# would be more appropriate.
return TermIter(self.termlist_begin(), self.termlist_end(),
has_termfreq=TermIter.LAZY,
has_wdf=TermIter.EAGER,
has_positions=TermIter.LAZY)
Document.__iter__ = _document_gen_termlist_iter
Document.termlist = _document_gen_termlist_iter
# Modify QueryParser to add a "stoplist()" method.
def _queryparser_gen_stoplist_iter(self):
"""Get an iterator over all the stopped terms from the previous query.
This returns an iterator over all the terms which were omitted from the
previously parsed query due to being considered to be stopwords. Each
instance of a word omitted from the query is represented in the returned
list, in the order in which the
The iterator will return string objects.
"""
return TermIter(self.stoplist_begin(), self.stoplist_end(),
return_strings=True)
QueryParser.stoplist = _queryparser_gen_stoplist_iter
# Modify QueryParser to add an "unstemlist()" method.
def _queryparser_gen_unstemlist_iter(self, tname):
"""Get an iterator over all the unstemmed forms of a stemmed term.
This returns an iterator which returns all the unstemmed words which were
stemmed to the stemmed form specified by `tname` when parsing the previous
query. Each instance of a word which stems to `tname` is returned by the
iterator in the order in which the words appeared in the query - an
individual unstemmed word may thus occur multiple times.
The iterator will return string objects.
"""
return TermIter(self.unstem_begin(tname), self.unstem_end(tname),
return_strings=True)
QueryParser.unstemlist = _queryparser_gen_unstemlist_iter
# Modify ValueCountMatchSpy to add an "values()" method.
def wrapper():
begin = ValueCountMatchSpy.values_begin
del ValueCountMatchSpy.values_begin
end = ValueCountMatchSpy.values_end
del ValueCountMatchSpy.values_end
def values_iter(self):
"""Get an iterator over all the values in the slot.
Values will be returned in ascending alphabetical order.
The iterator will return TermListItem objects: the value can be
accessed as the `term` property, and the frequency can be accessed as
the `termfreq` property.
"""
return TermIter(begin(self), end(self), has_termfreq=TermIter.EAGER)
return values_iter
ValueCountMatchSpy.values = wrapper()
del wrapper
# Modify ValueCountMatchSpy to add an "top_values()" method.
def wrapper():
begin = ValueCountMatchSpy.top_values_begin
del ValueCountMatchSpy.top_values_begin
end = ValueCountMatchSpy.top_values_end
del ValueCountMatchSpy.top_values_end
def top_values_iter(self, maxvalues):
"""Get an iterator over the most frequent values for the slot.
Values will be returned in descending order of frequency. Values with
the same frequency will be returned in ascending alphabetical order.
The iterator will return TermListItem objects: the value can be
accessed as the `term` property, and the frequency can be accessed as
the `termfreq` property.
"""
return TermIter(begin(self, maxvalues), end(self, maxvalues),
has_termfreq=TermIter.EAGER)
return top_values_iter
ValueCountMatchSpy.top_values = wrapper()
del wrapper
# When we make a query, keep a note of postingsources involved, so they won't
# be deleted. This hack can probably be removed once xapian bug #186 is fixed.
__query_init_orig = Query.__init__
def _query_init(self, *args):
"""Make a new query object.
Many possible arguments are possible - see the documentation for details.
"""
ps = []
if len(args) == 1 and isinstance(args[0], PostingSource):
ps.append(args[0])
else:
for arg in args:
if isinstance(arg, Query):
ps.extend(getattr(arg, '_ps', []))
elif hasattr(arg, '__iter__'):
for listarg in arg:
if isinstance(listarg, Query):
ps.extend(getattr(listarg, '_ps', []))
__query_init_orig(self, *args)
self._ps = ps
Query.__init__ = _query_init
del _query_init
# When setting a query on enquire, keep a note of postingsources involved, so
# they won't be deleted. This hack can probably be removed once xapian bug #186
# is fixed.
__enquire_set_query_orig = Enquire.set_query
def _enquire_set_query(self, query, qlen=0):
self._ps = getattr(query, '_ps', [])
return __enquire_set_query_orig(self, query, qlen)
_enquire_set_query.__doc__ = __enquire_set_query_orig.__doc__
Enquire.set_query = _enquire_set_query
del _enquire_set_query
# When getting a query from enquire, keep a note of postingsources involved,
# so they won't be deleted. This hack can probably be removed once xapian bug
# #186 is fixed.
__enquire_get_query_orig = Enquire.get_query
def _enquire_get_query(self):
query = __enquire_get_query_orig(self)
query._ps = getattr(self, '_ps', [])
return query
_enquire_get_query.__doc__ = __enquire_get_query_orig.__doc__
Enquire.get_query = _enquire_get_query
del _enquire_get_query
# When we set a ValueRangeProcessor into the QueryParser, keep a python
# reference so it won't be deleted. This hack can probably be removed once
# xapian bug #186 is fixed.
__queryparser_add_valuerangeprocessor_orig = QueryParser.add_valuerangeprocessor
def _queryparser_add_valuerangeprocessor(self, vrproc):
if not hasattr(self, '_vrps'):
self._vrps = []
self._vrps.append(vrproc)
return __queryparser_add_valuerangeprocessor_orig(self, vrproc)
_queryparser_add_valuerangeprocessor.__doc__ = __queryparser_add_valuerangeprocessor_orig.__doc__
QueryParser.add_valuerangeprocessor = _queryparser_add_valuerangeprocessor
del _queryparser_add_valuerangeprocessor
# When we set a Stopper into the QueryParser, keep a python reference so it
# won't be deleted. This hack can probably be removed once xapian bug #186 is
# fixed.
__queryparser_set_stopper_orig = QueryParser.set_stopper
def _queryparser_set_stopper(self, stopper):
self._stopper = stopper
return __queryparser_set_stopper_orig(self, stopper)
_queryparser_set_stopper.__doc__ = __queryparser_set_stopper_orig.__doc__
QueryParser.set_stopper = _queryparser_set_stopper
del _queryparser_set_stopper
# When we set a Stopper into the TermGenerator, keep a python reference so it
# won't be deleted. This hack can probably be removed once xapian bug #186 is
# fixed.
__termgenerator_set_stopper_orig = TermGenerator.set_stopper
def _termgenerator_set_stopper(self, stopper):
self._stopper = stopper
return __termgenerator_set_stopper_orig(self, stopper)
_termgenerator_set_stopper.__doc__ = __termgenerator_set_stopper_orig.__doc__
TermGenerator.set_stopper = _termgenerator_set_stopper
del _termgenerator_set_stopper
def _enquire_check_deprec_args(reverse, kwargs, methodname):
"""Check the keyword arguments to one of the enquire set_sort_* methods.
"""
if reverse is not None:
if 'ascending' in kwargs:
raise TypeError('Only one of "reverse" and "ascending" may be specified')
if len(kwargs) != 0:
raise TypeError('Only keyword arguments allowed are "reverse" and "ascending"')
else:
import warnings
if 'ascending' in kwargs:
reverse = kwargs.get('ascending')
del kwargs['ascending']
warnings.warn("'ascending' as a parameter name to Enquire::" +
methodname + "() is deprecated and will be removed "
"in Xapian 1.3.0", DeprecationWarning)
else:
warnings.warn("Single argument form of Enquire::" +
methodname + "() is deprecated and will be removed "
"in Xapian 1.3.0", DeprecationWarning)
reverse = True
if len(kwargs) != 0:
raise TypeError('Only keyword arguments allowed are "reverse" and "ascending"')
return reverse
# When we set a Sorter on enquire, keep a python reference so it won't be
# deleted. This hack can probably be removed once xapian bug #186 is fixed.
__enquire_set_sort_by_key_orig = Enquire.set_sort_by_key
def _enquire_set_sort_by_key(self, sorter, reverse=None, **kwargs):
self._sorter = sorter
reverse = _enquire_check_deprec_args(reverse, kwargs, "set_sort_by_key")
return __enquire_set_sort_by_key_orig(self, sorter, reverse)
_enquire_set_sort_by_key.__doc__ = __enquire_set_sort_by_key_orig.__doc__
Enquire.set_sort_by_key = _enquire_set_sort_by_key
del _enquire_set_sort_by_key
__enquire_set_sort_by_key_then_relevance_orig = Enquire.set_sort_by_key_then_relevance
def _enquire_set_sort_by_key_then_relevance(self, sorter, reverse=None, **kwargs):
self._sorter = sorter
reverse = _enquire_check_deprec_args(reverse, kwargs, "set_sort_by_key_then_relevance")
return __enquire_set_sort_by_key_then_relevance_orig(self, sorter, reverse)
_enquire_set_sort_by_key_then_relevance.__doc__ = __enquire_set_sort_by_key_then_relevance_orig.__doc__
Enquire.set_sort_by_key_then_relevance = _enquire_set_sort_by_key_then_relevance
del _enquire_set_sort_by_key_then_relevance
__enquire_set_sort_by_relevance_then_key_orig = Enquire.set_sort_by_relevance_then_key
def _enquire_set_sort_by_relevance_then_key(self, sorter, reverse=None, **kwargs):
self._sorter = sorter
reverse = _enquire_check_deprec_args(reverse, kwargs, "set_sort_by_relevance_then_key")
return __enquire_set_sort_by_relevance_then_key_orig(self, sorter, reverse)
_enquire_set_sort_by_relevance_then_key.__doc__ = __enquire_set_sort_by_relevance_then_key_orig.__doc__
Enquire.set_sort_by_relevance_then_key = _enquire_set_sort_by_relevance_then_key
del _enquire_set_sort_by_relevance_then_key
# Add deprecation warnings about old argument names. Can be removed in 1.3.0
__enquire_set_sort_by_value_orig = Enquire.set_sort_by_value
def _enquire_set_sort_by_value(self, sort_key, reverse=None, **kwargs):
reverse = _enquire_check_deprec_args(reverse, kwargs, "set_sort_by_value")
return __enquire_set_sort_by_value_orig(self, sort_key, reverse)
_enquire_set_sort_by_value.__doc__ = __enquire_set_sort_by_value_orig.__doc__
Enquire.set_sort_by_value = _enquire_set_sort_by_value
del _enquire_set_sort_by_value
# Add deprecation warnings about old argument names. Can be removed in 1.3.0
__enquire_set_sort_by_relevance_then_value_orig = Enquire.set_sort_by_relevance_then_value
def _enquire_set_sort_by_relevance_then_value(self, sort_key, reverse=None, **kwargs):
reverse = _enquire_check_deprec_args(reverse, kwargs, "set_sort_by_relevance_then_value")
return __enquire_set_sort_by_relevance_then_value_orig(self, sort_key, reverse)
_enquire_set_sort_by_relevance_then_value.__doc__ = __enquire_set_sort_by_relevance_then_value_orig.__doc__
Enquire.set_sort_by_relevance_then_value = _enquire_set_sort_by_relevance_then_value
del _enquire_set_sort_by_relevance_then_value
# Add deprecation warnings about old argument names. Can be removed in 1.3.0
__enquire_set_sort_by_value_then_relevance_orig = Enquire.set_sort_by_value_then_relevance
def _enquire_set_sort_by_value_then_relevance(self, sort_key, reverse=None, **kwargs):
reverse = _enquire_check_deprec_args(reverse, kwargs, "set_sort_by_value_then_relevance")
return __enquire_set_sort_by_value_then_relevance_orig(self, sort_key, reverse)
_enquire_set_sort_by_value_then_relevance.__doc__ = __enquire_set_sort_by_value_then_relevance_orig.__doc__
Enquire.set_sort_by_value_then_relevance = _enquire_set_sort_by_value_then_relevance
del _enquire_set_sort_by_value_then_relevance
##########################################
# Support for iteration of posting lists #
##########################################
class PostingItem(object):
"""An item returned from iteration of a posting list.
The item supports access to the following attributes and properties:
- `docid`: The document ID corresponding to this PostingItem.
- `doclength`: The length of the document corresponding to this
PostingItem.
- `wdf`: The within document frequency of the term which the posting list
is for in the document corresponding to this PostingItem.
- `positer`: An iterator over the positions which the term corresponing to
this posting list occurs at in the document corresponding to this
PostingItem. This is only available until the iterator which returned
this item next moves.
"""
__slots__ = ('_iter', 'docid', 'doclength', 'wdf',)
def __init__(self, iter):
self._iter = iter
self.docid = iter._iter.get_docid()
self.doclength = iter._iter.get_doclength()
self.wdf = iter._iter.get_wdf()
# Support for sequence API
sequence = ['docid', 'doclength', 'wdf', 'positer']
if not iter._has_positions:
sequence[3] = PositionIter()
def _get_positer(self):
"""Get a position list iterator.
The iterator will return integers representing the positions that the
term occurs at in the document corresponding to this PostingItem.
This will raise a InvalidOperationError exception if the iterator this
item came from doesn't support position lists, or if the iterator has
moved on since the item was returned from it.
"""
if not self._iter._has_positions:
raise InvalidOperationError("Iterator does not support position lists")
if self._iter._iter == self._iter._end or \
self.docid != self._iter._iter.get_docid():
raise InvalidOperationError("Iterator has moved, and does not support random access")
return PositionIter(self._iter._iter.positionlist_begin(),
self._iter._iter.positionlist_end())
positer = property(_get_positer, doc=
"""A position iterator for the current posting (if meaningful).
The iterator will return integers representing the positions that the term
occurs at.
This will raise a InvalidOperationError exception if the iterator this item
came from doesn't support position lists, or if the iterator has moved on
since the item was returned from it.
""")
class PostingIter(object):
"""An iterator over a posting list.
The iterator will return PostingItem objects, which will be evaluated
lazily where appropriate.
"""
__slots__ = ('_iter', '_end', '_has_positions', '_moved')
def __init__(self, start, end, has_positions=False):
self._iter = start
self._end = end
self._has_positions = has_positions
# _moved is True if we've moved onto the next item. This is needed so
# that the iterator doesn't have to move on until just before next() is
# called: since the iterator starts by pointing at a valid item, we
# can't just call self._iter.next() unconditionally at the start of our
# next() method.
self._moved = True
def __iter__(self):
return self
# For Python2:
def next(self):
if not self._moved:
self._iter.next()
self._moved = True
if self._iter == self._end:
raise StopIteration
else:
self._moved = False
return PostingItem(self)
# For Python3:
def __next__(self):
if not self._moved:
next(self._iter)
self._moved = True
if self._iter == self._end:
raise StopIteration
else:
self._moved = False
return PostingItem(self)
def skip_to(self, docid):
"""Skip the iterator forward.
The iterator is advanced to the first document with a document ID
which is greater than or equal to the supplied document ID.
If there are no such items, this will raise StopIteration.
This returns the item which the iterator is moved to. The subsequent
item will be returned the next time that next() is called (unless
skip_to() is called again first).
"""
if self._iter != self._end:
self._iter.skip_to(docid)
if self._iter == self._end:
self._moved = True
raise StopIteration
self._moved = False
return PostingItem(self)
def _database_gen_postlist_iter(self, tname):
"""Get an iterator over the postings which are indexed by a given term.
If `tname` is empty, an iterator over all the documents will be returned
(this will contain one entry for each document, will always return a wdf of
1, and will not allow access to a position iterator).
"""
if len(tname) != 0:
return PostingIter(self.postlist_begin(tname), self.postlist_end(tname),
has_positions=True)
else:
return PostingIter(self.postlist_begin(tname), self.postlist_end(tname))
Database.postlist = _database_gen_postlist_iter
###########################################
# Support for iteration of position lists #
###########################################
class PositionIter(object):
"""An iterator over a position list.
The iterator will return integers, in ascending order.
"""
def __init__(self, start = 0, end = 0):
self.iter = start
self.end = end
def __iter__(self):
return self
# For Python2:
def next(self):
if self.iter==self.end:
raise StopIteration
else:
r = self.iter.get_termpos()
self.iter.next()
return r
# For Python3:
def __next__(self):
if self.iter==self.end:
raise StopIteration
else:
r = self.iter.get_termpos()
next(self.iter)
return r
# Modify Database to add a "positionlist()" method.
def _database_gen_positionlist_iter(self, docid, tname):
"""Get an iterator over all the positions in a given document of a term.
The iterator will return integers, in ascending order.
"""
return PositionIter(self.positionlist_begin(docid, tname), self.positionlist_end(docid, tname))
Database.positionlist = _database_gen_positionlist_iter
########################################
# Support for iteration of value lists #
########################################
class ValueItem(object):
"""An item returned from iteration of the values in a document.
The item supports access to the following attributes:
- `num`: The number of the value.
- `value`: The contents of the value.
"""
__slots__ = ('num', 'value', )
def __init__(self, num, value):
self.num = num
self.value = value
class ValueIter(object):
"""An iterator over all the values stored in a document.
The iterator will return ValueItem objects, in ascending order of value number.
"""
def __init__(self, start, end):
self.iter = start
self.end = end
def __iter__(self):
return self
# For Python2:
def next(self):
if self.iter==self.end:
raise StopIteration
else:
r = ValueItem(self.iter.get_valueno(), self.iter.get_value())
self.iter.next()
return r
# For Python3:
def __next__(self):
if self.iter==self.end:
raise StopIteration
else:
r = ValueItem(self.iter.get_valueno(), self.iter.get_value())
next(self.iter)
return r
# Modify Document to add a "values()" method.
def _document_gen_values_iter(self):
"""Get an iterator over all the values stored in a document.
The iterator will return ValueItem objects, in ascending order of value number.
"""
return ValueIter(self.values_begin(), self.values_end())
Document.values = _document_gen_values_iter
##########################################
# Support for iteration of value streams #
##########################################
class ValueStreamItem(object):
"""An item returned from iteration of the values in a document.
The item supports access to the following attributes:
- `docid`: The docid for the item.
- `value`: The contents of the value.
"""
__slots__ = ('docid', 'value', )
def __init__(self, docid, value):
self.docid = docid
self.value = value
class ValueStreamIter(object):
"""An iterator over all the values stored in a document.
The iterator will return ValueStreamItem objects, in ascending order of value number.
"""
def __init__(self, start, end):
self.iter = start
self.end = end
self.moved = True
def __iter__(self):
return self
# For Python2:
def next(self):
if not self.moved:
self.iter.next()
self.moved = True
if self.iter==self.end:
raise StopIteration
else:
self.moved = False
return ValueStreamItem(self.iter.get_docid(), self.iter.get_value())
# For Python3:
def __next__(self):
if not self.moved:
self.iter.next()
self.moved = True
if self.iter==self.end:
raise StopIteration
else:
self.moved = False
return ValueStreamItem(self.iter.get_docid(), self.iter.get_value())
def skip_to(self, docid):
"""Skip the iterator forward.
The iterator is advanced to the first document with a document ID
which is greater than or equal to the supplied document ID.
If there are no such items, this will raise StopIteration.
This returns the item which the iterator is moved to. The subsequent
item will be returned the next time that next() is called (unless
skip_to() is called again first).
"""
if self.iter != self.end:
self.iter.skip_to(docid)
if self.iter == self.end:
self.moved = True
raise StopIteration
self.moved = False
return ValueStreamItem(self.iter.get_docid(), self.iter.get_value())
# Modify Database to add a "valuestream()" method, and remove the
# valuestream_begin() and valuestream_end() methods.
def wrapper():
vs_begin = Database.valuestream_begin
vs_end = Database.valuestream_end
def _database_gen_valuestream_iter(self, slot):
"""Get an iterator over all the values stored in a slot in the database.
The iterator will return ValueStreamItem objects, in ascending order of
document id.
"""
return ValueStreamIter(vs_begin(self, slot), vs_end(self, slot))
return _database_gen_valuestream_iter
Database.valuestream = wrapper()
del wrapper
del Database.valuestream_begin
del Database.valuestream_end
# Fix up Enquire so that it keeps a python reference to the deciders supplied
# to it so that they won't be deleted before the Enquire object. This hack can
# probably be removed once xapian bug #186 is fixed.
_enquire_add_matchspy_orig = Enquire.add_matchspy
def _enquire_match_spy_add(self, decider):
if not hasattr(self, '_deciders'):
self._deciders = []
self._deciders.append(decider)
_enquire_add_matchspy_orig(self, decider)
_enquire_match_spy_add.__doc__ = Enquire.add_matchspy.__doc__
Enquire.add_matchspy = _enquire_match_spy_add
_enquire_clear_matchspies_orig = Enquire.clear_matchspies
def _enquire_match_spies_clear(self):
_enquire_clear_matchspies_orig(self)
if hasattr(self, '_deciders'):
del self._deciders
_enquire_match_spies_clear.__doc__ = Enquire.clear_matchspies.__doc__
Enquire.clear_matchspies = _enquire_match_spies_clear
# Fix up Stem.__init__() so that it calls __disown__() on the passed
# StemImplementation object so that Python won't delete it from under us.
_stem_init_orig = Stem.__init__
def _stem_init(self, *args):
_stem_init_orig(self, *args)
if len(args) > 0 and isinstance(args[0], StemImplementation):
args[0].__disown__()
_stem_init.__doc__ = Stem.__init__.__doc__
Stem.__init__ = _stem_init
# Remove static methods which shouldn't be in the API.
del Document_unserialise
del Query_unserialise
# Add wrappers for Query::MatchAll and Query::MatchNothing
Query.MatchAll = Query("")
Query.MatchNothing = Query()
# Require to support the non-pythonic iterators for Python 3 - these can be
# removed once support for the non-pythonic iterators is dropped in 1.3.0.
ESetIterator.__next__ = lambda self: ESetIterator.next(self)
MSetIterator.__next__ = lambda self: MSetIterator.next(self)
PostingIterator.__next__ = lambda self: PostingIterator.next(self)
PositionIterator.__next__ = lambda self: PositionIterator.next(self)
TermIterator.__next__ = lambda self: TermIterator.next(self)
ValueIterator.__next__ = lambda self: ValueIterator.next(self)
# Set the list of names which should be public.
# Note that this needs to happen at the end of xapian.py.
__all__ = []
for item in dir():
if item.startswith('_') or item.endswith('_swigregister') or item.endswith('Iterator'):
continue
__all__.append(item)
__all__ = tuple(__all__)