# -*- coding: utf-8 -*-
########################################################################
#
# License: BSD
# Created: May 26, 2003
# Author: Francesc Alted - faltet@pytables.com
#
# $Id$
#
########################################################################
"""Here is defined the AttributeSet class."""
import re
import sys
import warnings
import cPickle
import numpy
from tables import hdf5extension
from tables.utils import SizeType
from tables.registry import class_name_dict
from tables.exceptions import ClosedNodeError, PerformanceWarning
from tables.path import check_name_validity
from tables.undoredo import attr_to_shadow
from tables.filters import Filters
from tables._past import previous_api
# System attributes
SYS_ATTRS = ["CLASS", "VERSION", "TITLE", "NROWS", "EXTDIM",
"ENCODING", "PYTABLES_FORMAT_VERSION",
"FLAVOR", "FILTERS", "AUTO_INDEX",
"DIRTY", "NODE_TYPE", "NODE_TYPE_VERSION",
"PSEUDOATOM"]
# Prefixes of other system attributes
SYS_ATTRS_PREFIXES = ["FIELD_"]
# RO_ATTRS will be disabled and let the user modify them if they
# want to. The user is still not allowed to remove or rename
# system attributes. Francesc Alted 2004-12-19
# Read-only attributes:
# RO_ATTRS = ["CLASS", "FLAVOR", "VERSION", "NROWS", "EXTDIM",
# "PYTABLES_FORMAT_VERSION", "FILTERS",
# "NODE_TYPE", "NODE_TYPE_VERSION"]
# RO_ATTRS = []
# The next attributes are not meant to be copied during a Node copy process
SYS_ATTRS_NOTTOBECOPIED = ["CLASS", "VERSION", "TITLE", "NROWS", "EXTDIM",
"PYTABLES_FORMAT_VERSION", "FILTERS", "ENCODING"]
# Attributes forced to be copied during node copies
FORCE_COPY_CLASS = ['CLASS', 'VERSION']
# Regular expression for column default values.
_field_fill_re = re.compile('^FIELD_[0-9]+_FILL$')
# Regular expression for fixing old pickled filters.
_old_filters_re = re.compile(br'\(([ic])tables\.Leaf\n')
# Fixed version of the previous string.
_new_filters_sub = br'(\1tables.filters\n'
def issysattrname(name):
"Check if a name is a system attribute or not"
if (name in SYS_ATTRS or
numpy.prod([name.startswith(prefix)
for prefix in SYS_ATTRS_PREFIXES])):
return True
else:
return False
[docs]class AttributeSet(hdf5extension.AttributeSet, object):
"""Container for the HDF5 attributes of a Node.
This class provides methods to create new HDF5 node attributes,
and to get, rename or delete existing ones.
Like in Group instances (see :ref:`GroupClassDescr`), AttributeSet
instances make use of the *natural naming* convention, i.e. you can
access the attributes on disk as if they were normal Python
attributes of the AttributeSet instance.
This offers the user a very convenient way to access HDF5 node
attributes. However, for this reason and in order not to pollute the
object namespace, one can not assign *normal* attributes to
AttributeSet instances, and their members use names which start by
special prefixes as happens with Group objects.
.. rubric:: Notes on native and pickled attributes
The values of most basic types are saved as HDF5 native data in the
HDF5 file. This includes Python bool, int, float, complex and str
(but not long nor unicode) values, as well as their NumPy scalar
versions and homogeneous or *structured* NumPy arrays of them. When
read, these values are always loaded as NumPy scalar or array
objects, as needed.
For that reason, attributes in native HDF5 files will be always
mapped into NumPy objects. Specifically, a multidimensional
attribute will be mapped into a multidimensional ndarray and a
scalar will be mapped into a NumPy scalar object (for example, a
scalar H5T_NATIVE_LLONG will be read and returned as a numpy.int64
scalar).
However, other kinds of values are serialized using pickle, so you
only will be able to correctly retrieve them using a Python-aware
HDF5 library. Thus, if you want to save Python scalar values and
make sure you are able to read them with generic HDF5 tools, you
should make use of *scalar or homogeneous/structured array NumPy
objects* (for example, numpy.int64(1) or numpy.array([1, 2, 3],
dtype='int16')).
One more advice: because of the various potential difficulties in
restoring a Python object stored in an attribute, you may end up
getting a pickle string where a Python object is expected. If this
is the case, you may wish to run pickle.loads() on that string to
get an idea of where things went wrong, as shown in this example::
>>> import os, tempfile
>>> import tables
>>>
>>> class MyClass(object):
... foo = 'bar'
...
>>> myObject = MyClass() # save object of custom class in HDF5 attr
>>> h5fname = tempfile.mktemp(suffix='.h5')
>>> h5f = tables.open_file(h5fname, 'w')
>>> h5f.root._v_attrs.obj = myObject # store the object
>>> print(h5f.root._v_attrs.obj.foo) # retrieve it
bar
>>> h5f.close()
>>>
>>> del MyClass, myObject # delete class of object and reopen file
>>> h5f = tables.open_file(h5fname, 'r')
>>> print(repr(h5f.root._v_attrs.obj))
'ccopy_reg\\n_reconstructor...
>>> import pickle # let's unpickle that to see what went wrong
>>> pickle.loads(h5f.root._v_attrs.obj)
Traceback (most recent call last):
...
AttributeError: 'module' object has no attribute 'MyClass'
>>> # So the problem was not in the stored object,
... # but in the *environment* where it was restored.
... h5f.close()
>>> os.remove(h5fname)
.. rubric:: Notes on AttributeSet methods
Note that this class overrides the __getattr__(), __setattr__() and
__delattr__() special methods. This allows you to read, assign or
delete attributes on disk by just using the next constructs::
leaf.attrs.myattr = 'str attr' # set a string (native support)
leaf.attrs.myattr2 = 3 # set an integer (native support)
leaf.attrs.myattr3 = [3, (1, 2)] # a generic object (Pickled)
attrib = leaf.attrs.myattr # get the attribute ``myattr``
del leaf.attrs.myattr # delete the attribute ``myattr``
In addition, the dictionary-like __getitem__(), __setitem__() and
__delitem__() methods are available, so you may write things like
this::
for name in node._v_attrs._f_list():
print("name: %s, value: %s" % (name, node._v_attrs[name]))
Use whatever idiom you prefer to access the attributes.
If an attribute is set on a target node that already has a large
number of attributes, a PerformanceWarning will be issued.
.. rubric:: AttributeSet attributes
.. attribute:: _v_attrnames
A list with all attribute names.
.. attribute:: _v_attrnamessys
A list with system attribute names.
.. attribute:: _v_attrnamesuser
A list with user attribute names.
.. attribute:: _v_unimplemented
A list of attribute names with unimplemented native HDF5 types.
"""
def _g_getnode(self):
return self._v__nodefile._get_node(self._v__nodepath)
_v_node = property(_g_getnode, None, None,
"The :class:`Node` instance this attribute set is "
"associated with.")
def __init__(self, node):
"""Create the basic structures to keep the attribute information.
Reads all the HDF5 attributes (if any) on disk for the node "node".
Parameters
----------
node
The parent node
"""
# Refuse to create an instance of an already closed node
if not node._v_isopen:
raise ClosedNodeError("the node for attribute set is closed")
dict_ = self.__dict__
self._g_new(node)
dict_["_v__nodefile"] = node._v_file
dict_["_v__nodepath"] = node._v_pathname
dict_["_v_attrnames"] = self._g_list_attr(node)
# The list of unimplemented attribute names
dict_["_v_unimplemented"] = []
# Get the file version format. This is an optimization
# in order to avoid accessing it too much.
try:
format_version = node._v_file.format_version
except AttributeError:
parsed_version = None
else:
if format_version == 'unknown':
parsed_version = None
else:
parsed_version = tuple(map(int, format_version.split('.')))
dict_["_v__format_version"] = parsed_version
# Split the attribute list in system and user lists
dict_["_v_attrnamessys"] = []
dict_["_v_attrnamesuser"] = []
for attr in self._v_attrnames:
# put the attributes on the local dictionary to allow
# tab-completion
self.__getattr__(attr)
if issysattrname(attr):
self._v_attrnamessys.append(attr)
else:
self._v_attrnamesuser.append(attr)
# Sort the attributes
self._v_attrnames.sort()
self._v_attrnamessys.sort()
self._v_attrnamesuser.sort()
def _g_update_node_location(self, node):
"""Updates the location information about the associated `node`."""
dict_ = self.__dict__
dict_['_v__nodefile'] = node._v_file
dict_['_v__nodepath'] = node._v_pathname
# hdf5extension operations:
self._g_new(node)
_g_updateNodeLocation = previous_api(_g_update_node_location)
[docs] def _f_list(self, attrset='user'):
"""Get a list of attribute names.
The attrset string selects the attribute set to be used. A
'user' value returns only user attributes (this is the default).
A 'sys' value returns only system attributes. Finally, 'all'
returns both system and user attributes.
"""
if attrset == "user":
return self._v_attrnamesuser[:]
elif attrset == "sys":
return self._v_attrnamessys[:]
elif attrset == "all":
return self._v_attrnames[:]
def __getattr__(self, name):
"""Get the attribute named "name"."""
# If attribute does not exist, raise AttributeError
if not name in self._v_attrnames:
raise AttributeError("Attribute '%s' does not exist in node: "
"'%s'" % (name, self._v__nodepath))
# Read the attribute from disk. This is an optimization to read
# quickly system attributes that are _string_ values, but it
# takes care of other types as well as for example NROWS for
# Tables and EXTDIM for EArrays
format_version = self._v__format_version
value = self._g_getattr(self._v_node, name)
# Check whether the value is pickled
# Pickled values always seems to end with a "."
maybe_pickled = (
isinstance(value, numpy.generic) and # NumPy scalar?
value.dtype.type == numpy.bytes_ and # string type?
value.itemsize > 0 and value.endswith(b'.'))
if (maybe_pickled and value in [b"0", b"0."]):
# Workaround for a bug in many versions of Python (starting
# somewhere after Python 2.6.1). See ticket #253.
retval = value
elif (maybe_pickled and _field_fill_re.match(name)
and format_version == (1, 5)):
# This format was used during the first 1.2 releases, just
# for string defaults.
try:
retval = cPickle.loads(value)
retval = numpy.array(retval)
except ImportError:
retval = None # signal error avoiding exception
elif maybe_pickled and name == 'FILTERS' and format_version < (2, 0):
# This is a big hack, but we don't have other way to recognize
# pickled filters of PyTables 1.x files.
value = _old_filters_re.sub(_new_filters_sub, value, 1)
retval = cPickle.loads(value) # pass unpickling errors through
elif maybe_pickled:
try:
retval = cPickle.loads(value)
# except cPickle.UnpicklingError:
# It seems that pickle may raise other errors than UnpicklingError
# Perhaps it would be better just an "except:" clause?
# except (cPickle.UnpicklingError, ImportError):
# Definitely (see SF bug #1254636)
except:
# ivb (2005-09-07): It is too hard to tell
# whether the unpickling failed
# because of the string not being a pickle one at all,
# because of a malformed pickle string,
# or because of some other problem in object reconstruction,
# thus making inconvenient even the issuing of a warning here.
# The documentation contains a note on this issue,
# explaining how the user can tell where the problem was.
retval = value
# Additional check for allowing a workaround for #307
if isinstance(retval, unicode) and retval == u'':
retval = numpy.array(retval)[()]
elif name == 'FILTERS' and format_version >= (2, 0):
retval = Filters._unpack(value)
elif name == 'TITLE' and not isinstance(value, str):
if sys.version_info[0] < 3:
# unicode is OK for TITLE
retval = value
else:
retval = value.decode('utf-8')
elif (issysattrname(name) and isinstance(value, (bytes, unicode)) and
not isinstance(value, str) and not _field_fill_re.match(name)):
# system attributes should always be str
if sys.version_info[0] < 3:
retval = value.encode()
else:
# python 3, bytes and not "FIELD_[0-9]+_FILL"
retval = value.decode('utf-8')
else:
retval = value
# Put this value in local directory
self.__dict__[name] = retval
return retval
def _g__setattr(self, name, value):
"""Set a PyTables attribute.
Sets a (maybe new) PyTables attribute with the specified `name`
and `value`. If the attribute already exists, it is simply
replaced.
It does not log the change.
"""
# Save this attribute to disk
# (overwriting an existing one if needed)
stvalue = value
if issysattrname(name):
if name in ["EXTDIM", "AUTO_INDEX", "DIRTY", "NODE_TYPE_VERSION"]:
stvalue = numpy.array(value, dtype=numpy.int32)
value = stvalue[()]
elif name == "NROWS":
stvalue = numpy.array(value, dtype=SizeType)
value = stvalue[()]
elif name == "FILTERS" and self._v__format_version >= (2, 0):
stvalue = value._pack()
# value will remain as a Filters instance here
# Convert value from a Python scalar into a NumPy scalar
# (only in case it has not been converted yet)
# Fixes ticket #59
if (stvalue is value and
type(value) in (bool, bytes, int, float, complex, unicode,
numpy.unicode_)):
# Additional check for allowing a workaround for #307
if isinstance(value, unicode) and len(value) == 0:
stvalue = numpy.array(u'')
else:
stvalue = numpy.array(value)
value = stvalue[()]
self._g_setattr(self._v_node, name, stvalue)
# New attribute or value. Introduce it into the local
# directory
self.__dict__[name] = value
# Finally, add this attribute to the list if not present
attrnames = self._v_attrnames
if not name in attrnames:
attrnames.append(name)
attrnames.sort()
if issysattrname(name):
attrnamessys = self._v_attrnamessys
attrnamessys.append(name)
attrnamessys.sort()
else:
attrnamesuser = self._v_attrnamesuser
attrnamesuser.append(name)
attrnamesuser.sort()
def __setattr__(self, name, value):
"""Set a PyTables attribute.
Sets a (maybe new) PyTables attribute with the specified `name`
and `value`. If the attribute already exists, it is simply
replaced.
A ``ValueError`` is raised when the name starts with a reserved
prefix or contains a ``/``. A `NaturalNameWarning` is issued if
the name is not a valid Python identifier. A
`PerformanceWarning` is issued when the recommended maximum
number of attributes in a node is going to be exceeded.
"""
nodefile = self._v__nodefile
attrnames = self._v_attrnames
# Check for name validity
check_name_validity(name)
nodefile._check_writable()
# Check if there are too many attributes.
max_node_attrs = nodefile.params['MAX_NODE_ATTRS']
if len(attrnames) >= max_node_attrs:
warnings.warn("""\
node ``%s`` is exceeding the recommended maximum number of attributes (%d);\
be ready to see PyTables asking for *lots* of memory and possibly slow I/O"""
% (self._v__nodepath, max_node_attrs),
PerformanceWarning)
undo_enabled = nodefile.is_undo_enabled()
# Log old attribute removal (if any).
if undo_enabled and (name in attrnames):
self._g_del_and_log(name)
# Set the attribute.
self._g__setattr(name, value)
# Log new attribute addition.
if undo_enabled:
self._g_log_add(name)
def _g_log_add(self, name):
self._v__nodefile._log('ADDATTR', self._v__nodepath, name)
_g_logAdd = previous_api(_g_log_add)
def _g_del_and_log(self, name):
nodefile = self._v__nodefile
node_pathname = self._v__nodepath
# Log *before* moving to use the right shadow name.
nodefile._log('DELATTR', node_pathname, name)
attr_to_shadow(nodefile, node_pathname, name)
_g_delAndLog = previous_api(_g_del_and_log)
def _g__delattr(self, name):
"""Delete a PyTables attribute.
Deletes the specified existing PyTables attribute.
It does not log the change.
"""
# Delete the attribute from disk
self._g_remove(self._v_node, name)
# Delete the attribute from local lists
self._v_attrnames.remove(name)
if name in self._v_attrnamessys:
self._v_attrnamessys.remove(name)
else:
self._v_attrnamesuser.remove(name)
# Delete the attribute from the local directory
# closes (#1049285)
del self.__dict__[name]
def __delattr__(self, name):
"""Delete a PyTables attribute.
Deletes the specified existing PyTables attribute from the
attribute set. If a nonexistent or system attribute is
specified, an ``AttributeError`` is raised.
"""
nodefile = self._v__nodefile
# Check if attribute exists
if name not in self._v_attrnames:
raise AttributeError(
"Attribute ('%s') does not exist in node '%s'"
% (name, self._v__nodepath))
nodefile._check_writable()
# Remove the PyTables attribute or move it to shadow.
if nodefile.is_undo_enabled():
self._g_del_and_log(name)
else:
self._g__delattr(name)
def __getitem__(self, name):
"""The dictionary like interface for __getattr__()."""
try:
return self.__getattr__(name)
except AttributeError:
# Capture the AttributeError an re-raise a KeyError one
raise KeyError(
"Attribute ('%s') does not exist in node '%s'"
% (name, self._v__nodepath))
def __setitem__(self, name, value):
"""The dictionary like interface for __setattr__()."""
self.__setattr__(name, value)
def __delitem__(self, name):
"""The dictionary like interface for __delattr__()."""
try:
self.__delattr__(name)
except AttributeError:
# Capture the AttributeError an re-raise a KeyError one
raise KeyError(
"Attribute ('%s') does not exist in node '%s'"
% (name, self._v__nodepath))
[docs] def __contains__(self, name):
"""Is there an attribute with that name?
A true value is returned if the attribute set has an attribute
with the given name, false otherwise.
"""
return name in self._v_attrnames
[docs] def _f_rename(self, oldattrname, newattrname):
"""Rename an attribute from oldattrname to newattrname."""
if oldattrname == newattrname:
# Do nothing
return
# First, fetch the value of the oldattrname
attrvalue = getattr(self, oldattrname)
# Now, create the new attribute
setattr(self, newattrname, attrvalue)
# Finally, remove the old attribute
delattr(self, oldattrname)
def _g_copy(self, newset, set_attr=None, copyclass=False):
"""Copy set attributes.
Copies all user and allowed system PyTables attributes to the
given attribute set, replacing the existing ones.
You can specify a *bound* method of the destination set that
will be used to set its attributes. Else, its `_g__setattr`
method will be used.
Changes are logged depending on the chosen setting method. The
default setting method does not log anything.
.. versionchanged:: 3.0
The *newSet* parameter has been renamed into *newset*.
.. versionchanged:: 3.0
The *copyClass* parameter has been renamed into *copyclass*.
"""
copysysattrs = newset._v__nodefile.params['PYTABLES_SYS_ATTRS']
if set_attr is None:
set_attr = newset._g__setattr
for attrname in self._v_attrnamesuser:
# Do not copy the unimplemented attributes.
if attrname not in self._v_unimplemented:
set_attr(attrname, getattr(self, attrname))
# Copy the system attributes that we are allowed to.
if copysysattrs:
for attrname in self._v_attrnamessys:
if ((attrname not in SYS_ATTRS_NOTTOBECOPIED) and
# Do not copy the FIELD_ attributes in tables as this can
# be really *slow* (don't know exactly the reason).
# See #304.
not attrname.startswith("FIELD_")):
set_attr(attrname, getattr(self, attrname))
# Copy CLASS and VERSION attributes if requested
if copyclass:
for attrname in FORCE_COPY_CLASS:
if attrname in self._v_attrnamessys:
set_attr(attrname, getattr(self, attrname))
[docs] def _f_copy(self, where):
"""Copy attributes to the where node.
Copies all user and certain system attributes to the given where
node (a Node instance - see :ref:`NodeClassDescr`), replacing
the existing ones.
"""
# AttributeSet must be defined in order to define a Node.
# However, we need to know Node here.
# Using class_name_dict avoids a circular import.
if not isinstance(where, class_name_dict['Node']):
raise TypeError("destination object is not a node: %r" % (where,))
self._g_copy(where._v_attrs, where._v_attrs.__setattr__)
def _g_close(self):
# Nothing will be done here, as the existing instance is completely
# operative now.
pass
def __str__(self):
"""The string representation for this object."""
# The pathname
pathname = self._v__nodepath
# Get this class name
classname = self.__class__.__name__
# The attribute names
attrnumber = len([n for n in self._v_attrnames])
return "%s._v_attrs (%s), %s attributes" % \
(pathname, classname, attrnumber)
def __repr__(self):
"""A detailed string representation for this object."""
# print additional info only if there are attributes to show
attrnames = [n for n in self._v_attrnames]
if len(attrnames):
rep = ['%s := %r' % (attr, getattr(self, attr))
for attr in attrnames]
attrlist = '[%s]' % (',\n '.join(rep))
return "%s:\n %s" % (str(self), attrlist)
else:
return str(self)
class NotLoggedAttributeSet(AttributeSet):
def _g_log_add(self, name):
pass
_g_logAdd = previous_api(_g_log_add)
def _g_del_and_log(self, name):
self._g__delattr(name)
_g_delAndLog = previous_api(_g_del_and_log)
## Local Variables:
## mode: python
## py-indent-offset: 4
## tab-width: 4
## fill-column: 72
## End:
