Merging PR_218 openai_rev package with new streamlit chat app

This commit is contained in:
noptuno
2023-04-27 20:29:30 -04:00
parent 479b8d6d10
commit 355dee533b
8378 changed files with 2931636 additions and 3 deletions

View File

@@ -0,0 +1,18 @@
"""
Compatibility module.
This module contains duplicated code from Python itself or 3rd party
extensions, which may be included for the following reasons:
* compatibility
* we may only need a small subset of the copied library/module
"""
from . import _inspect
from . import py3k
from ._inspect import getargspec, formatargspec
from .py3k import *
__all__ = []
__all__.extend(_inspect.__all__)
__all__.extend(py3k.__all__)

View File

@@ -0,0 +1,191 @@
"""Subset of inspect module from upstream python
We use this instead of upstream because upstream inspect is slow to import, and
significantly contributes to numpy import times. Importing this copy has almost
no overhead.
"""
import types
__all__ = ['getargspec', 'formatargspec']
# ----------------------------------------------------------- type-checking
def ismethod(object):
"""Return true if the object is an instance method.
Instance method objects provide these attributes:
__doc__ documentation string
__name__ name with which this method was defined
im_class class object in which this method belongs
im_func function object containing implementation of method
im_self instance to which this method is bound, or None
"""
return isinstance(object, types.MethodType)
def isfunction(object):
"""Return true if the object is a user-defined function.
Function objects provide these attributes:
__doc__ documentation string
__name__ name with which this function was defined
func_code code object containing compiled function bytecode
func_defaults tuple of any default values for arguments
func_doc (same as __doc__)
func_globals global namespace in which this function was defined
func_name (same as __name__)
"""
return isinstance(object, types.FunctionType)
def iscode(object):
"""Return true if the object is a code object.
Code objects provide these attributes:
co_argcount number of arguments (not including * or ** args)
co_code string of raw compiled bytecode
co_consts tuple of constants used in the bytecode
co_filename name of file in which this code object was created
co_firstlineno number of first line in Python source code
co_flags bitmap: 1=optimized | 2=newlocals | 4=*arg | 8=**arg
co_lnotab encoded mapping of line numbers to bytecode indices
co_name name with which this code object was defined
co_names tuple of names of local variables
co_nlocals number of local variables
co_stacksize virtual machine stack space required
co_varnames tuple of names of arguments and local variables
"""
return isinstance(object, types.CodeType)
# ------------------------------------------------ argument list extraction
# These constants are from Python's compile.h.
CO_OPTIMIZED, CO_NEWLOCALS, CO_VARARGS, CO_VARKEYWORDS = 1, 2, 4, 8
def getargs(co):
"""Get information about the arguments accepted by a code object.
Three things are returned: (args, varargs, varkw), where 'args' is
a list of argument names (possibly containing nested lists), and
'varargs' and 'varkw' are the names of the * and ** arguments or None.
"""
if not iscode(co):
raise TypeError('arg is not a code object')
nargs = co.co_argcount
names = co.co_varnames
args = list(names[:nargs])
# The following acrobatics are for anonymous (tuple) arguments.
# Which we do not need to support, so remove to avoid importing
# the dis module.
for i in range(nargs):
if args[i][:1] in ['', '.']:
raise TypeError("tuple function arguments are not supported")
varargs = None
if co.co_flags & CO_VARARGS:
varargs = co.co_varnames[nargs]
nargs = nargs + 1
varkw = None
if co.co_flags & CO_VARKEYWORDS:
varkw = co.co_varnames[nargs]
return args, varargs, varkw
def getargspec(func):
"""Get the names and default values of a function's arguments.
A tuple of four things is returned: (args, varargs, varkw, defaults).
'args' is a list of the argument names (it may contain nested lists).
'varargs' and 'varkw' are the names of the * and ** arguments or None.
'defaults' is an n-tuple of the default values of the last n arguments.
"""
if ismethod(func):
func = func.__func__
if not isfunction(func):
raise TypeError('arg is not a Python function')
args, varargs, varkw = getargs(func.__code__)
return args, varargs, varkw, func.__defaults__
def getargvalues(frame):
"""Get information about arguments passed into a particular frame.
A tuple of four things is returned: (args, varargs, varkw, locals).
'args' is a list of the argument names (it may contain nested lists).
'varargs' and 'varkw' are the names of the * and ** arguments or None.
'locals' is the locals dictionary of the given frame.
"""
args, varargs, varkw = getargs(frame.f_code)
return args, varargs, varkw, frame.f_locals
def joinseq(seq):
if len(seq) == 1:
return '(' + seq[0] + ',)'
else:
return '(' + ', '.join(seq) + ')'
def strseq(object, convert, join=joinseq):
"""Recursively walk a sequence, stringifying each element.
"""
if type(object) in [list, tuple]:
return join([strseq(_o, convert, join) for _o in object])
else:
return convert(object)
def formatargspec(args, varargs=None, varkw=None, defaults=None,
formatarg=str,
formatvarargs=lambda name: '*' + name,
formatvarkw=lambda name: '**' + name,
formatvalue=lambda value: '=' + repr(value),
join=joinseq):
"""Format an argument spec from the 4 values returned by getargspec.
The first four arguments are (args, varargs, varkw, defaults). The
other four arguments are the corresponding optional formatting functions
that are called to turn names and values into strings. The ninth
argument is an optional function to format the sequence of arguments.
"""
specs = []
if defaults:
firstdefault = len(args) - len(defaults)
for i in range(len(args)):
spec = strseq(args[i], formatarg, join)
if defaults and i >= firstdefault:
spec = spec + formatvalue(defaults[i - firstdefault])
specs.append(spec)
if varargs is not None:
specs.append(formatvarargs(varargs))
if varkw is not None:
specs.append(formatvarkw(varkw))
return '(' + ', '.join(specs) + ')'
def formatargvalues(args, varargs, varkw, locals,
formatarg=str,
formatvarargs=lambda name: '*' + name,
formatvarkw=lambda name: '**' + name,
formatvalue=lambda value: '=' + repr(value),
join=joinseq):
"""Format an argument spec from the 4 values returned by getargvalues.
The first four arguments are (args, varargs, varkw, locals). The
next four arguments are the corresponding optional formatting functions
that are called to turn names and values into strings. The ninth
argument is an optional function to format the sequence of arguments.
"""
def convert(name, locals=locals,
formatarg=formatarg, formatvalue=formatvalue):
return formatarg(name) + formatvalue(locals[name])
specs = [strseq(arg, convert, join) for arg in args]
if varargs:
specs.append(formatvarargs(varargs) + formatvalue(locals[varargs]))
if varkw:
specs.append(formatvarkw(varkw) + formatvalue(locals[varkw]))
return '(' + ', '.join(specs) + ')'

View File

@@ -0,0 +1,487 @@
"""Utility to compare pep440 compatible version strings.
The LooseVersion and StrictVersion classes that distutils provides don't
work; they don't recognize anything like alpha/beta/rc/dev versions.
"""
# Copyright (c) Donald Stufft and individual contributors.
# All rights reserved.
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
# 1. Redistributions of source code must retain the above copyright notice,
# this list of conditions and the following disclaimer.
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
import collections
import itertools
import re
__all__ = [
"parse", "Version", "LegacyVersion", "InvalidVersion", "VERSION_PATTERN",
]
# BEGIN packaging/_structures.py
class Infinity:
def __repr__(self):
return "Infinity"
def __hash__(self):
return hash(repr(self))
def __lt__(self, other):
return False
def __le__(self, other):
return False
def __eq__(self, other):
return isinstance(other, self.__class__)
def __ne__(self, other):
return not isinstance(other, self.__class__)
def __gt__(self, other):
return True
def __ge__(self, other):
return True
def __neg__(self):
return NegativeInfinity
Infinity = Infinity()
class NegativeInfinity:
def __repr__(self):
return "-Infinity"
def __hash__(self):
return hash(repr(self))
def __lt__(self, other):
return True
def __le__(self, other):
return True
def __eq__(self, other):
return isinstance(other, self.__class__)
def __ne__(self, other):
return not isinstance(other, self.__class__)
def __gt__(self, other):
return False
def __ge__(self, other):
return False
def __neg__(self):
return Infinity
# BEGIN packaging/version.py
NegativeInfinity = NegativeInfinity()
_Version = collections.namedtuple(
"_Version",
["epoch", "release", "dev", "pre", "post", "local"],
)
def parse(version):
"""
Parse the given version string and return either a :class:`Version` object
or a :class:`LegacyVersion` object depending on if the given version is
a valid PEP 440 version or a legacy version.
"""
try:
return Version(version)
except InvalidVersion:
return LegacyVersion(version)
class InvalidVersion(ValueError):
"""
An invalid version was found, users should refer to PEP 440.
"""
class _BaseVersion:
def __hash__(self):
return hash(self._key)
def __lt__(self, other):
return self._compare(other, lambda s, o: s < o)
def __le__(self, other):
return self._compare(other, lambda s, o: s <= o)
def __eq__(self, other):
return self._compare(other, lambda s, o: s == o)
def __ge__(self, other):
return self._compare(other, lambda s, o: s >= o)
def __gt__(self, other):
return self._compare(other, lambda s, o: s > o)
def __ne__(self, other):
return self._compare(other, lambda s, o: s != o)
def _compare(self, other, method):
if not isinstance(other, _BaseVersion):
return NotImplemented
return method(self._key, other._key)
class LegacyVersion(_BaseVersion):
def __init__(self, version):
self._version = str(version)
self._key = _legacy_cmpkey(self._version)
def __str__(self):
return self._version
def __repr__(self):
return "<LegacyVersion({0})>".format(repr(str(self)))
@property
def public(self):
return self._version
@property
def base_version(self):
return self._version
@property
def local(self):
return None
@property
def is_prerelease(self):
return False
@property
def is_postrelease(self):
return False
_legacy_version_component_re = re.compile(
r"(\d+ | [a-z]+ | \.| -)", re.VERBOSE,
)
_legacy_version_replacement_map = {
"pre": "c", "preview": "c", "-": "final-", "rc": "c", "dev": "@",
}
def _parse_version_parts(s):
for part in _legacy_version_component_re.split(s):
part = _legacy_version_replacement_map.get(part, part)
if not part or part == ".":
continue
if part[:1] in "0123456789":
# pad for numeric comparison
yield part.zfill(8)
else:
yield "*" + part
# ensure that alpha/beta/candidate are before final
yield "*final"
def _legacy_cmpkey(version):
# We hardcode an epoch of -1 here. A PEP 440 version can only have an epoch
# greater than or equal to 0. This will effectively put the LegacyVersion,
# which uses the defacto standard originally implemented by setuptools,
# as before all PEP 440 versions.
epoch = -1
# This scheme is taken from pkg_resources.parse_version setuptools prior to
# its adoption of the packaging library.
parts = []
for part in _parse_version_parts(version.lower()):
if part.startswith("*"):
# remove "-" before a prerelease tag
if part < "*final":
while parts and parts[-1] == "*final-":
parts.pop()
# remove trailing zeros from each series of numeric parts
while parts and parts[-1] == "00000000":
parts.pop()
parts.append(part)
parts = tuple(parts)
return epoch, parts
# Deliberately not anchored to the start and end of the string, to make it
# easier for 3rd party code to reuse
VERSION_PATTERN = r"""
v?
(?:
(?:(?P<epoch>[0-9]+)!)? # epoch
(?P<release>[0-9]+(?:\.[0-9]+)*) # release segment
(?P<pre> # pre-release
[-_\.]?
(?P<pre_l>(a|b|c|rc|alpha|beta|pre|preview))
[-_\.]?
(?P<pre_n>[0-9]+)?
)?
(?P<post> # post release
(?:-(?P<post_n1>[0-9]+))
|
(?:
[-_\.]?
(?P<post_l>post|rev|r)
[-_\.]?
(?P<post_n2>[0-9]+)?
)
)?
(?P<dev> # dev release
[-_\.]?
(?P<dev_l>dev)
[-_\.]?
(?P<dev_n>[0-9]+)?
)?
)
(?:\+(?P<local>[a-z0-9]+(?:[-_\.][a-z0-9]+)*))? # local version
"""
class Version(_BaseVersion):
_regex = re.compile(
r"^\s*" + VERSION_PATTERN + r"\s*$",
re.VERBOSE | re.IGNORECASE,
)
def __init__(self, version):
# Validate the version and parse it into pieces
match = self._regex.search(version)
if not match:
raise InvalidVersion("Invalid version: '{0}'".format(version))
# Store the parsed out pieces of the version
self._version = _Version(
epoch=int(match.group("epoch")) if match.group("epoch") else 0,
release=tuple(int(i) for i in match.group("release").split(".")),
pre=_parse_letter_version(
match.group("pre_l"),
match.group("pre_n"),
),
post=_parse_letter_version(
match.group("post_l"),
match.group("post_n1") or match.group("post_n2"),
),
dev=_parse_letter_version(
match.group("dev_l"),
match.group("dev_n"),
),
local=_parse_local_version(match.group("local")),
)
# Generate a key which will be used for sorting
self._key = _cmpkey(
self._version.epoch,
self._version.release,
self._version.pre,
self._version.post,
self._version.dev,
self._version.local,
)
def __repr__(self):
return "<Version({0})>".format(repr(str(self)))
def __str__(self):
parts = []
# Epoch
if self._version.epoch != 0:
parts.append("{0}!".format(self._version.epoch))
# Release segment
parts.append(".".join(str(x) for x in self._version.release))
# Pre-release
if self._version.pre is not None:
parts.append("".join(str(x) for x in self._version.pre))
# Post-release
if self._version.post is not None:
parts.append(".post{0}".format(self._version.post[1]))
# Development release
if self._version.dev is not None:
parts.append(".dev{0}".format(self._version.dev[1]))
# Local version segment
if self._version.local is not None:
parts.append(
"+{0}".format(".".join(str(x) for x in self._version.local))
)
return "".join(parts)
@property
def public(self):
return str(self).split("+", 1)[0]
@property
def base_version(self):
parts = []
# Epoch
if self._version.epoch != 0:
parts.append("{0}!".format(self._version.epoch))
# Release segment
parts.append(".".join(str(x) for x in self._version.release))
return "".join(parts)
@property
def local(self):
version_string = str(self)
if "+" in version_string:
return version_string.split("+", 1)[1]
@property
def is_prerelease(self):
return bool(self._version.dev or self._version.pre)
@property
def is_postrelease(self):
return bool(self._version.post)
def _parse_letter_version(letter, number):
if letter:
# We assume there is an implicit 0 in a pre-release if there is
# no numeral associated with it.
if number is None:
number = 0
# We normalize any letters to their lower-case form
letter = letter.lower()
# We consider some words to be alternate spellings of other words and
# in those cases we want to normalize the spellings to our preferred
# spelling.
if letter == "alpha":
letter = "a"
elif letter == "beta":
letter = "b"
elif letter in ["c", "pre", "preview"]:
letter = "rc"
elif letter in ["rev", "r"]:
letter = "post"
return letter, int(number)
if not letter and number:
# We assume that if we are given a number but not given a letter,
# then this is using the implicit post release syntax (e.g., 1.0-1)
letter = "post"
return letter, int(number)
_local_version_seperators = re.compile(r"[\._-]")
def _parse_local_version(local):
"""
Takes a string like abc.1.twelve and turns it into ("abc", 1, "twelve").
"""
if local is not None:
return tuple(
part.lower() if not part.isdigit() else int(part)
for part in _local_version_seperators.split(local)
)
def _cmpkey(epoch, release, pre, post, dev, local):
# When we compare a release version, we want to compare it with all of the
# trailing zeros removed. So we'll use a reverse the list, drop all the now
# leading zeros until we come to something non-zero, then take the rest,
# re-reverse it back into the correct order, and make it a tuple and use
# that for our sorting key.
release = tuple(
reversed(list(
itertools.dropwhile(
lambda x: x == 0,
reversed(release),
)
))
)
# We need to "trick" the sorting algorithm to put 1.0.dev0 before 1.0a0.
# We'll do this by abusing the pre-segment, but we _only_ want to do this
# if there is no pre- or a post-segment. If we have one of those, then
# the normal sorting rules will handle this case correctly.
if pre is None and post is None and dev is not None:
pre = -Infinity
# Versions without a pre-release (except as noted above) should sort after
# those with one.
elif pre is None:
pre = Infinity
# Versions without a post-segment should sort before those with one.
if post is None:
post = -Infinity
# Versions without a development segment should sort after those with one.
if dev is None:
dev = Infinity
if local is None:
# Versions without a local segment should sort before those with one.
local = -Infinity
else:
# Versions with a local segment need that segment parsed to implement
# the sorting rules in PEP440.
# - Alphanumeric segments sort before numeric segments
# - Alphanumeric segments sort lexicographically
# - Numeric segments sort numerically
# - Shorter versions sort before longer versions when the prefixes
# match exactly
local = tuple(
(i, "") if isinstance(i, int) else (-Infinity, i)
for i in local
)
return epoch, release, pre, post, dev, local

View File

@@ -0,0 +1,137 @@
"""
Python 3.X compatibility tools.
While this file was originally intended for Python 2 -> 3 transition,
it is now used to create a compatibility layer between different
minor versions of Python 3.
While the active version of numpy may not support a given version of python, we
allow downstream libraries to continue to use these shims for forward
compatibility with numpy while they transition their code to newer versions of
Python.
"""
__all__ = ['bytes', 'asbytes', 'isfileobj', 'getexception', 'strchar',
'unicode', 'asunicode', 'asbytes_nested', 'asunicode_nested',
'asstr', 'open_latin1', 'long', 'basestring', 'sixu',
'integer_types', 'is_pathlib_path', 'npy_load_module', 'Path',
'pickle', 'contextlib_nullcontext', 'os_fspath', 'os_PathLike']
import sys
import os
from pathlib import Path
import io
try:
import pickle5 as pickle
except ImportError:
import pickle
long = int
integer_types = (int,)
basestring = str
unicode = str
bytes = bytes
def asunicode(s):
if isinstance(s, bytes):
return s.decode('latin1')
return str(s)
def asbytes(s):
if isinstance(s, bytes):
return s
return str(s).encode('latin1')
def asstr(s):
if isinstance(s, bytes):
return s.decode('latin1')
return str(s)
def isfileobj(f):
return isinstance(f, (io.FileIO, io.BufferedReader, io.BufferedWriter))
def open_latin1(filename, mode='r'):
return open(filename, mode=mode, encoding='iso-8859-1')
def sixu(s):
return s
strchar = 'U'
def getexception():
return sys.exc_info()[1]
def asbytes_nested(x):
if hasattr(x, '__iter__') and not isinstance(x, (bytes, unicode)):
return [asbytes_nested(y) for y in x]
else:
return asbytes(x)
def asunicode_nested(x):
if hasattr(x, '__iter__') and not isinstance(x, (bytes, unicode)):
return [asunicode_nested(y) for y in x]
else:
return asunicode(x)
def is_pathlib_path(obj):
"""
Check whether obj is a `pathlib.Path` object.
Prefer using ``isinstance(obj, os.PathLike)`` instead of this function.
"""
return isinstance(obj, Path)
# from Python 3.7
class contextlib_nullcontext:
"""Context manager that does no additional processing.
Used as a stand-in for a normal context manager, when a particular
block of code is only sometimes used with a normal context manager:
cm = optional_cm if condition else nullcontext()
with cm:
# Perform operation, using optional_cm if condition is True
.. note::
Prefer using `contextlib.nullcontext` instead of this context manager.
"""
def __init__(self, enter_result=None):
self.enter_result = enter_result
def __enter__(self):
return self.enter_result
def __exit__(self, *excinfo):
pass
def npy_load_module(name, fn, info=None):
"""
Load a module. Uses ``load_module`` which will be deprecated in python
3.12. An alternative that uses ``exec_module`` is in
numpy.distutils.misc_util.exec_mod_from_location
.. versionadded:: 1.11.2
Parameters
----------
name : str
Full module name.
fn : str
Path to module file.
info : tuple, optional
Only here for backward compatibility with Python 2.*.
Returns
-------
mod : module
"""
# Explicitly lazy import this to avoid paying the cost
# of importing importlib at startup
from importlib.machinery import SourceFileLoader
return SourceFileLoader(name, fn).load_module()
os_fspath = os.fspath
os_PathLike = os.PathLike

View File

@@ -0,0 +1,10 @@
def configuration(parent_package='',top_path=None):
from numpy.distutils.misc_util import Configuration
config = Configuration('compat', parent_package, top_path)
config.add_subpackage('tests')
return config
if __name__ == '__main__':
from numpy.distutils.core import setup
setup(configuration=configuration)

View File

@@ -0,0 +1,19 @@
from os.path import join
from numpy.compat import isfileobj
from numpy.testing import assert_
from numpy.testing import tempdir
def test_isfileobj():
with tempdir(prefix="numpy_test_compat_") as folder:
filename = join(folder, 'a.bin')
with open(filename, 'wb') as f:
assert_(isfileobj(f))
with open(filename, 'ab') as f:
assert_(isfileobj(f))
with open(filename, 'rb') as f:
assert_(isfileobj(f))