tests versuch 2

This commit is contained in:
2000-Trek 2023-07-28 23:30:45 +02:00
parent fdf385fe06
commit c88f7df83a
2363 changed files with 408191 additions and 0 deletions

View file

@ -0,0 +1,213 @@
import os
import subprocess
import contextlib
import functools
import tempfile
import shutil
import operator
@contextlib.contextmanager
def pushd(dir):
orig = os.getcwd()
os.chdir(dir)
try:
yield dir
finally:
os.chdir(orig)
@contextlib.contextmanager
def tarball_context(url, target_dir=None, runner=None, pushd=pushd):
"""
Get a tarball, extract it, change to that directory, yield, then
clean up.
`runner` is the function to invoke commands.
`pushd` is a context manager for changing the directory.
"""
if target_dir is None:
target_dir = os.path.basename(url).replace('.tar.gz', '').replace('.tgz', '')
if runner is None:
runner = functools.partial(subprocess.check_call, shell=True)
# In the tar command, use --strip-components=1 to strip the first path and
# then
# use -C to cause the files to be extracted to {target_dir}. This ensures
# that we always know where the files were extracted.
runner('mkdir {target_dir}'.format(**vars()))
try:
getter = 'wget {url} -O -'
extract = 'tar x{compression} --strip-components=1 -C {target_dir}'
cmd = ' | '.join((getter, extract))
runner(cmd.format(compression=infer_compression(url), **vars()))
with pushd(target_dir):
yield target_dir
finally:
runner('rm -Rf {target_dir}'.format(**vars()))
def infer_compression(url):
"""
Given a URL or filename, infer the compression code for tar.
"""
# cheat and just assume it's the last two characters
compression_indicator = url[-2:]
mapping = dict(gz='z', bz='j', xz='J')
# Assume 'z' (gzip) if no match
return mapping.get(compression_indicator, 'z')
@contextlib.contextmanager
def temp_dir(remover=shutil.rmtree):
"""
Create a temporary directory context. Pass a custom remover
to override the removal behavior.
"""
temp_dir = tempfile.mkdtemp()
try:
yield temp_dir
finally:
remover(temp_dir)
@contextlib.contextmanager
def repo_context(url, branch=None, quiet=True, dest_ctx=temp_dir):
"""
Check out the repo indicated by url.
If dest_ctx is supplied, it should be a context manager
to yield the target directory for the check out.
"""
exe = 'git' if 'git' in url else 'hg'
with dest_ctx() as repo_dir:
cmd = [exe, 'clone', url, repo_dir]
if branch:
cmd.extend(['--branch', branch])
devnull = open(os.path.devnull, 'w')
stdout = devnull if quiet else None
subprocess.check_call(cmd, stdout=stdout)
yield repo_dir
@contextlib.contextmanager
def null():
yield
class ExceptionTrap:
"""
A context manager that will catch certain exceptions and provide an
indication they occurred.
>>> with ExceptionTrap() as trap:
... raise Exception()
>>> bool(trap)
True
>>> with ExceptionTrap() as trap:
... pass
>>> bool(trap)
False
>>> with ExceptionTrap(ValueError) as trap:
... raise ValueError("1 + 1 is not 3")
>>> bool(trap)
True
>>> with ExceptionTrap(ValueError) as trap:
... raise Exception()
Traceback (most recent call last):
...
Exception
>>> bool(trap)
False
"""
exc_info = None, None, None
def __init__(self, exceptions=(Exception,)):
self.exceptions = exceptions
def __enter__(self):
return self
@property
def type(self):
return self.exc_info[0]
@property
def value(self):
return self.exc_info[1]
@property
def tb(self):
return self.exc_info[2]
def __exit__(self, *exc_info):
type = exc_info[0]
matches = type and issubclass(type, self.exceptions)
if matches:
self.exc_info = exc_info
return matches
def __bool__(self):
return bool(self.type)
def raises(self, func, *, _test=bool):
"""
Wrap func and replace the result with the truth
value of the trap (True if an exception occurred).
First, give the decorator an alias to support Python 3.8
Syntax.
>>> raises = ExceptionTrap(ValueError).raises
Now decorate a function that always fails.
>>> @raises
... def fail():
... raise ValueError('failed')
>>> fail()
True
"""
@functools.wraps(func)
def wrapper(*args, **kwargs):
with ExceptionTrap(self.exceptions) as trap:
func(*args, **kwargs)
return _test(trap)
return wrapper
def passes(self, func):
"""
Wrap func and replace the result with the truth
value of the trap (True if no exception).
First, give the decorator an alias to support Python 3.8
Syntax.
>>> passes = ExceptionTrap(ValueError).passes
Now decorate a function that always fails.
>>> @passes
... def fail():
... raise ValueError('failed')
>>> fail()
False
"""
return self.raises(func, _test=operator.not_)
class suppress(contextlib.suppress, contextlib.ContextDecorator):
"""
A version of contextlib.suppress with decorator support.
>>> @suppress(KeyError)
... def key_error():
... {}['']
>>> key_error()
"""

View file

@ -0,0 +1,525 @@
import functools
import time
import inspect
import collections
import types
import itertools
import setuptools.extern.more_itertools
from typing import Callable, TypeVar
CallableT = TypeVar("CallableT", bound=Callable[..., object])
def compose(*funcs):
"""
Compose any number of unary functions into a single unary function.
>>> import textwrap
>>> expected = str.strip(textwrap.dedent(compose.__doc__))
>>> strip_and_dedent = compose(str.strip, textwrap.dedent)
>>> strip_and_dedent(compose.__doc__) == expected
True
Compose also allows the innermost function to take arbitrary arguments.
>>> round_three = lambda x: round(x, ndigits=3)
>>> f = compose(round_three, int.__truediv__)
>>> [f(3*x, x+1) for x in range(1,10)]
[1.5, 2.0, 2.25, 2.4, 2.5, 2.571, 2.625, 2.667, 2.7]
"""
def compose_two(f1, f2):
return lambda *args, **kwargs: f1(f2(*args, **kwargs))
return functools.reduce(compose_two, funcs)
def method_caller(method_name, *args, **kwargs):
"""
Return a function that will call a named method on the
target object with optional positional and keyword
arguments.
>>> lower = method_caller('lower')
>>> lower('MyString')
'mystring'
"""
def call_method(target):
func = getattr(target, method_name)
return func(*args, **kwargs)
return call_method
def once(func):
"""
Decorate func so it's only ever called the first time.
This decorator can ensure that an expensive or non-idempotent function
will not be expensive on subsequent calls and is idempotent.
>>> add_three = once(lambda a: a+3)
>>> add_three(3)
6
>>> add_three(9)
6
>>> add_three('12')
6
To reset the stored value, simply clear the property ``saved_result``.
>>> del add_three.saved_result
>>> add_three(9)
12
>>> add_three(8)
12
Or invoke 'reset()' on it.
>>> add_three.reset()
>>> add_three(-3)
0
>>> add_three(0)
0
"""
@functools.wraps(func)
def wrapper(*args, **kwargs):
if not hasattr(wrapper, 'saved_result'):
wrapper.saved_result = func(*args, **kwargs)
return wrapper.saved_result
wrapper.reset = lambda: vars(wrapper).__delitem__('saved_result')
return wrapper
def method_cache(
method: CallableT,
cache_wrapper: Callable[
[CallableT], CallableT
] = functools.lru_cache(), # type: ignore[assignment]
) -> CallableT:
"""
Wrap lru_cache to support storing the cache data in the object instances.
Abstracts the common paradigm where the method explicitly saves an
underscore-prefixed protected property on first call and returns that
subsequently.
>>> class MyClass:
... calls = 0
...
... @method_cache
... def method(self, value):
... self.calls += 1
... return value
>>> a = MyClass()
>>> a.method(3)
3
>>> for x in range(75):
... res = a.method(x)
>>> a.calls
75
Note that the apparent behavior will be exactly like that of lru_cache
except that the cache is stored on each instance, so values in one
instance will not flush values from another, and when an instance is
deleted, so are the cached values for that instance.
>>> b = MyClass()
>>> for x in range(35):
... res = b.method(x)
>>> b.calls
35
>>> a.method(0)
0
>>> a.calls
75
Note that if method had been decorated with ``functools.lru_cache()``,
a.calls would have been 76 (due to the cached value of 0 having been
flushed by the 'b' instance).
Clear the cache with ``.cache_clear()``
>>> a.method.cache_clear()
Same for a method that hasn't yet been called.
>>> c = MyClass()
>>> c.method.cache_clear()
Another cache wrapper may be supplied:
>>> cache = functools.lru_cache(maxsize=2)
>>> MyClass.method2 = method_cache(lambda self: 3, cache_wrapper=cache)
>>> a = MyClass()
>>> a.method2()
3
Caution - do not subsequently wrap the method with another decorator, such
as ``@property``, which changes the semantics of the function.
See also
http://code.activestate.com/recipes/577452-a-memoize-decorator-for-instance-methods/
for another implementation and additional justification.
"""
def wrapper(self: object, *args: object, **kwargs: object) -> object:
# it's the first call, replace the method with a cached, bound method
bound_method: CallableT = types.MethodType( # type: ignore[assignment]
method, self
)
cached_method = cache_wrapper(bound_method)
setattr(self, method.__name__, cached_method)
return cached_method(*args, **kwargs)
# Support cache clear even before cache has been created.
wrapper.cache_clear = lambda: None # type: ignore[attr-defined]
return ( # type: ignore[return-value]
_special_method_cache(method, cache_wrapper) or wrapper
)
def _special_method_cache(method, cache_wrapper):
"""
Because Python treats special methods differently, it's not
possible to use instance attributes to implement the cached
methods.
Instead, install the wrapper method under a different name
and return a simple proxy to that wrapper.
https://github.com/jaraco/jaraco.functools/issues/5
"""
name = method.__name__
special_names = '__getattr__', '__getitem__'
if name not in special_names:
return
wrapper_name = '__cached' + name
def proxy(self, *args, **kwargs):
if wrapper_name not in vars(self):
bound = types.MethodType(method, self)
cache = cache_wrapper(bound)
setattr(self, wrapper_name, cache)
else:
cache = getattr(self, wrapper_name)
return cache(*args, **kwargs)
return proxy
def apply(transform):
"""
Decorate a function with a transform function that is
invoked on results returned from the decorated function.
>>> @apply(reversed)
... def get_numbers(start):
... "doc for get_numbers"
... return range(start, start+3)
>>> list(get_numbers(4))
[6, 5, 4]
>>> get_numbers.__doc__
'doc for get_numbers'
"""
def wrap(func):
return functools.wraps(func)(compose(transform, func))
return wrap
def result_invoke(action):
r"""
Decorate a function with an action function that is
invoked on the results returned from the decorated
function (for its side-effect), then return the original
result.
>>> @result_invoke(print)
... def add_two(a, b):
... return a + b
>>> x = add_two(2, 3)
5
>>> x
5
"""
def wrap(func):
@functools.wraps(func)
def wrapper(*args, **kwargs):
result = func(*args, **kwargs)
action(result)
return result
return wrapper
return wrap
def call_aside(f, *args, **kwargs):
"""
Call a function for its side effect after initialization.
>>> @call_aside
... def func(): print("called")
called
>>> func()
called
Use functools.partial to pass parameters to the initial call
>>> @functools.partial(call_aside, name='bingo')
... def func(name): print("called with", name)
called with bingo
"""
f(*args, **kwargs)
return f
class Throttler:
"""
Rate-limit a function (or other callable)
"""
def __init__(self, func, max_rate=float('Inf')):
if isinstance(func, Throttler):
func = func.func
self.func = func
self.max_rate = max_rate
self.reset()
def reset(self):
self.last_called = 0
def __call__(self, *args, **kwargs):
self._wait()
return self.func(*args, **kwargs)
def _wait(self):
"ensure at least 1/max_rate seconds from last call"
elapsed = time.time() - self.last_called
must_wait = 1 / self.max_rate - elapsed
time.sleep(max(0, must_wait))
self.last_called = time.time()
def __get__(self, obj, type=None):
return first_invoke(self._wait, functools.partial(self.func, obj))
def first_invoke(func1, func2):
"""
Return a function that when invoked will invoke func1 without
any parameters (for its side-effect) and then invoke func2
with whatever parameters were passed, returning its result.
"""
def wrapper(*args, **kwargs):
func1()
return func2(*args, **kwargs)
return wrapper
def retry_call(func, cleanup=lambda: None, retries=0, trap=()):
"""
Given a callable func, trap the indicated exceptions
for up to 'retries' times, invoking cleanup on the
exception. On the final attempt, allow any exceptions
to propagate.
"""
attempts = itertools.count() if retries == float('inf') else range(retries)
for attempt in attempts:
try:
return func()
except trap:
cleanup()
return func()
def retry(*r_args, **r_kwargs):
"""
Decorator wrapper for retry_call. Accepts arguments to retry_call
except func and then returns a decorator for the decorated function.
Ex:
>>> @retry(retries=3)
... def my_func(a, b):
... "this is my funk"
... print(a, b)
>>> my_func.__doc__
'this is my funk'
"""
def decorate(func):
@functools.wraps(func)
def wrapper(*f_args, **f_kwargs):
bound = functools.partial(func, *f_args, **f_kwargs)
return retry_call(bound, *r_args, **r_kwargs)
return wrapper
return decorate
def print_yielded(func):
"""
Convert a generator into a function that prints all yielded elements
>>> @print_yielded
... def x():
... yield 3; yield None
>>> x()
3
None
"""
print_all = functools.partial(map, print)
print_results = compose(more_itertools.consume, print_all, func)
return functools.wraps(func)(print_results)
def pass_none(func):
"""
Wrap func so it's not called if its first param is None
>>> print_text = pass_none(print)
>>> print_text('text')
text
>>> print_text(None)
"""
@functools.wraps(func)
def wrapper(param, *args, **kwargs):
if param is not None:
return func(param, *args, **kwargs)
return wrapper
def assign_params(func, namespace):
"""
Assign parameters from namespace where func solicits.
>>> def func(x, y=3):
... print(x, y)
>>> assigned = assign_params(func, dict(x=2, z=4))
>>> assigned()
2 3
The usual errors are raised if a function doesn't receive
its required parameters:
>>> assigned = assign_params(func, dict(y=3, z=4))
>>> assigned()
Traceback (most recent call last):
TypeError: func() ...argument...
It even works on methods:
>>> class Handler:
... def meth(self, arg):
... print(arg)
>>> assign_params(Handler().meth, dict(arg='crystal', foo='clear'))()
crystal
"""
sig = inspect.signature(func)
params = sig.parameters.keys()
call_ns = {k: namespace[k] for k in params if k in namespace}
return functools.partial(func, **call_ns)
def save_method_args(method):
"""
Wrap a method such that when it is called, the args and kwargs are
saved on the method.
>>> class MyClass:
... @save_method_args
... def method(self, a, b):
... print(a, b)
>>> my_ob = MyClass()
>>> my_ob.method(1, 2)
1 2
>>> my_ob._saved_method.args
(1, 2)
>>> my_ob._saved_method.kwargs
{}
>>> my_ob.method(a=3, b='foo')
3 foo
>>> my_ob._saved_method.args
()
>>> my_ob._saved_method.kwargs == dict(a=3, b='foo')
True
The arguments are stored on the instance, allowing for
different instance to save different args.
>>> your_ob = MyClass()
>>> your_ob.method({str('x'): 3}, b=[4])
{'x': 3} [4]
>>> your_ob._saved_method.args
({'x': 3},)
>>> my_ob._saved_method.args
()
"""
args_and_kwargs = collections.namedtuple('args_and_kwargs', 'args kwargs')
@functools.wraps(method)
def wrapper(self, *args, **kwargs):
attr_name = '_saved_' + method.__name__
attr = args_and_kwargs(args, kwargs)
setattr(self, attr_name, attr)
return method(self, *args, **kwargs)
return wrapper
def except_(*exceptions, replace=None, use=None):
"""
Replace the indicated exceptions, if raised, with the indicated
literal replacement or evaluated expression (if present).
>>> safe_int = except_(ValueError)(int)
>>> safe_int('five')
>>> safe_int('5')
5
Specify a literal replacement with ``replace``.
>>> safe_int_r = except_(ValueError, replace=0)(int)
>>> safe_int_r('five')
0
Provide an expression to ``use`` to pass through particular parameters.
>>> safe_int_pt = except_(ValueError, use='args[0]')(int)
>>> safe_int_pt('five')
'five'
"""
def decorate(func):
@functools.wraps(func)
def wrapper(*args, **kwargs):
try:
return func(*args, **kwargs)
except exceptions:
try:
return eval(use)
except TypeError:
return replace
return wrapper
return decorate

View file

@ -0,0 +1,599 @@
import re
import itertools
import textwrap
import functools
try:
from importlib.resources import files # type: ignore
except ImportError: # pragma: nocover
from setuptools.extern.importlib_resources import files # type: ignore
from setuptools.extern.jaraco.functools import compose, method_cache
from setuptools.extern.jaraco.context import ExceptionTrap
def substitution(old, new):
"""
Return a function that will perform a substitution on a string
"""
return lambda s: s.replace(old, new)
def multi_substitution(*substitutions):
"""
Take a sequence of pairs specifying substitutions, and create
a function that performs those substitutions.
>>> multi_substitution(('foo', 'bar'), ('bar', 'baz'))('foo')
'baz'
"""
substitutions = itertools.starmap(substitution, substitutions)
# compose function applies last function first, so reverse the
# substitutions to get the expected order.
substitutions = reversed(tuple(substitutions))
return compose(*substitutions)
class FoldedCase(str):
"""
A case insensitive string class; behaves just like str
except compares equal when the only variation is case.
>>> s = FoldedCase('hello world')
>>> s == 'Hello World'
True
>>> 'Hello World' == s
True
>>> s != 'Hello World'
False
>>> s.index('O')
4
>>> s.split('O')
['hell', ' w', 'rld']
>>> sorted(map(FoldedCase, ['GAMMA', 'alpha', 'Beta']))
['alpha', 'Beta', 'GAMMA']
Sequence membership is straightforward.
>>> "Hello World" in [s]
True
>>> s in ["Hello World"]
True
You may test for set inclusion, but candidate and elements
must both be folded.
>>> FoldedCase("Hello World") in {s}
True
>>> s in {FoldedCase("Hello World")}
True
String inclusion works as long as the FoldedCase object
is on the right.
>>> "hello" in FoldedCase("Hello World")
True
But not if the FoldedCase object is on the left:
>>> FoldedCase('hello') in 'Hello World'
False
In that case, use ``in_``:
>>> FoldedCase('hello').in_('Hello World')
True
>>> FoldedCase('hello') > FoldedCase('Hello')
False
"""
def __lt__(self, other):
return self.lower() < other.lower()
def __gt__(self, other):
return self.lower() > other.lower()
def __eq__(self, other):
return self.lower() == other.lower()
def __ne__(self, other):
return self.lower() != other.lower()
def __hash__(self):
return hash(self.lower())
def __contains__(self, other):
return super().lower().__contains__(other.lower())
def in_(self, other):
"Does self appear in other?"
return self in FoldedCase(other)
# cache lower since it's likely to be called frequently.
@method_cache
def lower(self):
return super().lower()
def index(self, sub):
return self.lower().index(sub.lower())
def split(self, splitter=' ', maxsplit=0):
pattern = re.compile(re.escape(splitter), re.I)
return pattern.split(self, maxsplit)
# Python 3.8 compatibility
_unicode_trap = ExceptionTrap(UnicodeDecodeError)
@_unicode_trap.passes
def is_decodable(value):
r"""
Return True if the supplied value is decodable (using the default
encoding).
>>> is_decodable(b'\xff')
False
>>> is_decodable(b'\x32')
True
"""
value.decode()
def is_binary(value):
r"""
Return True if the value appears to be binary (that is, it's a byte
string and isn't decodable).
>>> is_binary(b'\xff')
True
>>> is_binary('\xff')
False
"""
return isinstance(value, bytes) and not is_decodable(value)
def trim(s):
r"""
Trim something like a docstring to remove the whitespace that
is common due to indentation and formatting.
>>> trim("\n\tfoo = bar\n\t\tbar = baz\n")
'foo = bar\n\tbar = baz'
"""
return textwrap.dedent(s).strip()
def wrap(s):
"""
Wrap lines of text, retaining existing newlines as
paragraph markers.
>>> print(wrap(lorem_ipsum))
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do
eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad
minim veniam, quis nostrud exercitation ullamco laboris nisi ut
aliquip ex ea commodo consequat. Duis aute irure dolor in
reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla
pariatur. Excepteur sint occaecat cupidatat non proident, sunt in
culpa qui officia deserunt mollit anim id est laborum.
<BLANKLINE>
Curabitur pretium tincidunt lacus. Nulla gravida orci a odio. Nullam
varius, turpis et commodo pharetra, est eros bibendum elit, nec luctus
magna felis sollicitudin mauris. Integer in mauris eu nibh euismod
gravida. Duis ac tellus et risus vulputate vehicula. Donec lobortis
risus a elit. Etiam tempor. Ut ullamcorper, ligula eu tempor congue,
eros est euismod turpis, id tincidunt sapien risus a quam. Maecenas
fermentum consequat mi. Donec fermentum. Pellentesque malesuada nulla
a mi. Duis sapien sem, aliquet nec, commodo eget, consequat quis,
neque. Aliquam faucibus, elit ut dictum aliquet, felis nisl adipiscing
sapien, sed malesuada diam lacus eget erat. Cras mollis scelerisque
nunc. Nullam arcu. Aliquam consequat. Curabitur augue lorem, dapibus
quis, laoreet et, pretium ac, nisi. Aenean magna nisl, mollis quis,
molestie eu, feugiat in, orci. In hac habitasse platea dictumst.
"""
paragraphs = s.splitlines()
wrapped = ('\n'.join(textwrap.wrap(para)) for para in paragraphs)
return '\n\n'.join(wrapped)
def unwrap(s):
r"""
Given a multi-line string, return an unwrapped version.
>>> wrapped = wrap(lorem_ipsum)
>>> wrapped.count('\n')
20
>>> unwrapped = unwrap(wrapped)
>>> unwrapped.count('\n')
1
>>> print(unwrapped)
Lorem ipsum dolor sit amet, consectetur adipiscing ...
Curabitur pretium tincidunt lacus. Nulla gravida orci ...
"""
paragraphs = re.split(r'\n\n+', s)
cleaned = (para.replace('\n', ' ') for para in paragraphs)
return '\n'.join(cleaned)
class Splitter(object):
"""object that will split a string with the given arguments for each call
>>> s = Splitter(',')
>>> s('hello, world, this is your, master calling')
['hello', ' world', ' this is your', ' master calling']
"""
def __init__(self, *args):
self.args = args
def __call__(self, s):
return s.split(*self.args)
def indent(string, prefix=' ' * 4):
"""
>>> indent('foo')
' foo'
"""
return prefix + string
class WordSet(tuple):
"""
Given an identifier, return the words that identifier represents,
whether in camel case, underscore-separated, etc.
>>> WordSet.parse("camelCase")
('camel', 'Case')
>>> WordSet.parse("under_sep")
('under', 'sep')
Acronyms should be retained
>>> WordSet.parse("firstSNL")
('first', 'SNL')
>>> WordSet.parse("you_and_I")
('you', 'and', 'I')
>>> WordSet.parse("A simple test")
('A', 'simple', 'test')
Multiple caps should not interfere with the first cap of another word.
>>> WordSet.parse("myABCClass")
('my', 'ABC', 'Class')
The result is a WordSet, so you can get the form you need.
>>> WordSet.parse("myABCClass").underscore_separated()
'my_ABC_Class'
>>> WordSet.parse('a-command').camel_case()
'ACommand'
>>> WordSet.parse('someIdentifier').lowered().space_separated()
'some identifier'
Slices of the result should return another WordSet.
>>> WordSet.parse('taken-out-of-context')[1:].underscore_separated()
'out_of_context'
>>> WordSet.from_class_name(WordSet()).lowered().space_separated()
'word set'
>>> example = WordSet.parse('figured it out')
>>> example.headless_camel_case()
'figuredItOut'
>>> example.dash_separated()
'figured-it-out'
"""
_pattern = re.compile('([A-Z]?[a-z]+)|([A-Z]+(?![a-z]))')
def capitalized(self):
return WordSet(word.capitalize() for word in self)
def lowered(self):
return WordSet(word.lower() for word in self)
def camel_case(self):
return ''.join(self.capitalized())
def headless_camel_case(self):
words = iter(self)
first = next(words).lower()
new_words = itertools.chain((first,), WordSet(words).camel_case())
return ''.join(new_words)
def underscore_separated(self):
return '_'.join(self)
def dash_separated(self):
return '-'.join(self)
def space_separated(self):
return ' '.join(self)
def trim_right(self, item):
"""
Remove the item from the end of the set.
>>> WordSet.parse('foo bar').trim_right('foo')
('foo', 'bar')
>>> WordSet.parse('foo bar').trim_right('bar')
('foo',)
>>> WordSet.parse('').trim_right('bar')
()
"""
return self[:-1] if self and self[-1] == item else self
def trim_left(self, item):
"""
Remove the item from the beginning of the set.
>>> WordSet.parse('foo bar').trim_left('foo')
('bar',)
>>> WordSet.parse('foo bar').trim_left('bar')
('foo', 'bar')
>>> WordSet.parse('').trim_left('bar')
()
"""
return self[1:] if self and self[0] == item else self
def trim(self, item):
"""
>>> WordSet.parse('foo bar').trim('foo')
('bar',)
"""
return self.trim_left(item).trim_right(item)
def __getitem__(self, item):
result = super(WordSet, self).__getitem__(item)
if isinstance(item, slice):
result = WordSet(result)
return result
@classmethod
def parse(cls, identifier):
matches = cls._pattern.finditer(identifier)
return WordSet(match.group(0) for match in matches)
@classmethod
def from_class_name(cls, subject):
return cls.parse(subject.__class__.__name__)
# for backward compatibility
words = WordSet.parse
def simple_html_strip(s):
r"""
Remove HTML from the string `s`.
>>> str(simple_html_strip(''))
''
>>> print(simple_html_strip('A <bold>stormy</bold> day in paradise'))
A stormy day in paradise
>>> print(simple_html_strip('Somebody <!-- do not --> tell the truth.'))
Somebody tell the truth.
>>> print(simple_html_strip('What about<br/>\nmultiple lines?'))
What about
multiple lines?
"""
html_stripper = re.compile('(<!--.*?-->)|(<[^>]*>)|([^<]+)', re.DOTALL)
texts = (match.group(3) or '' for match in html_stripper.finditer(s))
return ''.join(texts)
class SeparatedValues(str):
"""
A string separated by a separator. Overrides __iter__ for getting
the values.
>>> list(SeparatedValues('a,b,c'))
['a', 'b', 'c']
Whitespace is stripped and empty values are discarded.
>>> list(SeparatedValues(' a, b , c, '))
['a', 'b', 'c']
"""
separator = ','
def __iter__(self):
parts = self.split(self.separator)
return filter(None, (part.strip() for part in parts))
class Stripper:
r"""
Given a series of lines, find the common prefix and strip it from them.
>>> lines = [
... 'abcdefg\n',
... 'abc\n',
... 'abcde\n',
... ]
>>> res = Stripper.strip_prefix(lines)
>>> res.prefix
'abc'
>>> list(res.lines)
['defg\n', '\n', 'de\n']
If no prefix is common, nothing should be stripped.
>>> lines = [
... 'abcd\n',
... '1234\n',
... ]
>>> res = Stripper.strip_prefix(lines)
>>> res.prefix = ''
>>> list(res.lines)
['abcd\n', '1234\n']
"""
def __init__(self, prefix, lines):
self.prefix = prefix
self.lines = map(self, lines)
@classmethod
def strip_prefix(cls, lines):
prefix_lines, lines = itertools.tee(lines)
prefix = functools.reduce(cls.common_prefix, prefix_lines)
return cls(prefix, lines)
def __call__(self, line):
if not self.prefix:
return line
null, prefix, rest = line.partition(self.prefix)
return rest
@staticmethod
def common_prefix(s1, s2):
"""
Return the common prefix of two lines.
"""
index = min(len(s1), len(s2))
while s1[:index] != s2[:index]:
index -= 1
return s1[:index]
def remove_prefix(text, prefix):
"""
Remove the prefix from the text if it exists.
>>> remove_prefix('underwhelming performance', 'underwhelming ')
'performance'
>>> remove_prefix('something special', 'sample')
'something special'
"""
null, prefix, rest = text.rpartition(prefix)
return rest
def remove_suffix(text, suffix):
"""
Remove the suffix from the text if it exists.
>>> remove_suffix('name.git', '.git')
'name'
>>> remove_suffix('something special', 'sample')
'something special'
"""
rest, suffix, null = text.partition(suffix)
return rest
def normalize_newlines(text):
r"""
Replace alternate newlines with the canonical newline.
>>> normalize_newlines('Lorem Ipsum\u2029')
'Lorem Ipsum\n'
>>> normalize_newlines('Lorem Ipsum\r\n')
'Lorem Ipsum\n'
>>> normalize_newlines('Lorem Ipsum\x85')
'Lorem Ipsum\n'
"""
newlines = ['\r\n', '\r', '\n', '\u0085', '\u2028', '\u2029']
pattern = '|'.join(newlines)
return re.sub(pattern, '\n', text)
def _nonblank(str):
return str and not str.startswith('#')
@functools.singledispatch
def yield_lines(iterable):
r"""
Yield valid lines of a string or iterable.
>>> list(yield_lines(''))
[]
>>> list(yield_lines(['foo', 'bar']))
['foo', 'bar']
>>> list(yield_lines('foo\nbar'))
['foo', 'bar']
>>> list(yield_lines('\nfoo\n#bar\nbaz #comment'))
['foo', 'baz #comment']
>>> list(yield_lines(['foo\nbar', 'baz', 'bing\n\n\n']))
['foo', 'bar', 'baz', 'bing']
"""
return itertools.chain.from_iterable(map(yield_lines, iterable))
@yield_lines.register(str)
def _(text):
return filter(_nonblank, map(str.strip, text.splitlines()))
def drop_comment(line):
"""
Drop comments.
>>> drop_comment('foo # bar')
'foo'
A hash without a space may be in a URL.
>>> drop_comment('http://example.com/foo#bar')
'http://example.com/foo#bar'
"""
return line.partition(' #')[0]
def join_continuation(lines):
r"""
Join lines continued by a trailing backslash.
>>> list(join_continuation(['foo \\', 'bar', 'baz']))
['foobar', 'baz']
>>> list(join_continuation(['foo \\', 'bar', 'baz']))
['foobar', 'baz']
>>> list(join_continuation(['foo \\', 'bar \\', 'baz']))
['foobarbaz']
Not sure why, but...
The character preceeding the backslash is also elided.
>>> list(join_continuation(['goo\\', 'dly']))
['godly']
A terrible idea, but...
If no line is available to continue, suppress the lines.
>>> list(join_continuation(['foo', 'bar\\', 'baz\\']))
['foo']
"""
lines = iter(lines)
for item in lines:
while item.endswith('\\'):
try:
item = item[:-2].strip() + next(lines)
except StopIteration:
return
yield item