add mitogen - requires ansible 2.7

This commit is contained in:
Josh Lay 2019-06-13 20:17:02 -05:00
parent eaab4634cd
commit c88082327f
136 changed files with 21264 additions and 0 deletions

View file

View file

@ -0,0 +1,593 @@
"""Utilities to support packages."""
# !mitogen: minify_safe
# NOTE: This module must remain compatible with Python 2.3, as it is shared
# by setuptools for distribution with Python 2.3 and up.
import os
import sys
import imp
import os.path
from types import ModuleType
__all__ = [
'get_importer', 'iter_importers', 'get_loader', 'find_loader',
'walk_packages', 'iter_modules', 'get_data',
'ImpImporter', 'ImpLoader', 'read_code', 'extend_path',
]
def read_code(stream):
# This helper is needed in order for the PEP 302 emulation to
# correctly handle compiled files
import marshal
magic = stream.read(4)
if magic != imp.get_magic():
return None
stream.read(4) # Skip timestamp
return marshal.load(stream)
def simplegeneric(func):
"""Make a trivial single-dispatch generic function"""
registry = {}
def wrapper(*args, **kw):
ob = args[0]
try:
cls = ob.__class__
except AttributeError:
cls = type(ob)
try:
mro = cls.__mro__
except AttributeError:
try:
class cls(cls, object):
pass
mro = cls.__mro__[1:]
except TypeError:
mro = object, # must be an ExtensionClass or some such :(
for t in mro:
if t in registry:
return registry[t](*args, **kw)
else:
return func(*args, **kw)
try:
wrapper.__name__ = func.__name__
except (TypeError, AttributeError):
pass # Python 2.3 doesn't allow functions to be renamed
def register(typ, func=None):
if func is None:
return lambda f: register(typ, f)
registry[typ] = func
return func
wrapper.__dict__ = func.__dict__
wrapper.__doc__ = func.__doc__
wrapper.register = register
return wrapper
def walk_packages(path=None, prefix='', onerror=None):
"""Yields (module_loader, name, ispkg) for all modules recursively
on path, or, if path is None, all accessible modules.
'path' should be either None or a list of paths to look for
modules in.
'prefix' is a string to output on the front of every module name
on output.
Note that this function must import all *packages* (NOT all
modules!) on the given path, in order to access the __path__
attribute to find submodules.
'onerror' is a function which gets called with one argument (the
name of the package which was being imported) if any exception
occurs while trying to import a package. If no onerror function is
supplied, ImportErrors are caught and ignored, while all other
exceptions are propagated, terminating the search.
Examples:
# list all modules python can access
walk_packages()
# list all submodules of ctypes
walk_packages(ctypes.__path__, ctypes.__name__+'.')
"""
def seen(p, m={}):
if p in m:
return True
m[p] = True
for importer, name, ispkg in iter_modules(path, prefix):
yield importer, name, ispkg
if ispkg:
try:
__import__(name)
except ImportError:
if onerror is not None:
onerror(name)
except Exception:
if onerror is not None:
onerror(name)
else:
raise
else:
path = getattr(sys.modules[name], '__path__', None) or []
# don't traverse path items we've seen before
path = [p for p in path if not seen(p)]
for item in walk_packages(path, name+'.', onerror):
yield item
def iter_modules(path=None, prefix=''):
"""Yields (module_loader, name, ispkg) for all submodules on path,
or, if path is None, all top-level modules on sys.path.
'path' should be either None or a list of paths to look for
modules in.
'prefix' is a string to output on the front of every module name
on output.
"""
if path is None:
importers = iter_importers()
else:
importers = map(get_importer, path)
yielded = {}
for i in importers:
for name, ispkg in iter_importer_modules(i, prefix):
if name not in yielded:
yielded[name] = 1
yield i, name, ispkg
#@simplegeneric
def iter_importer_modules(importer, prefix=''):
if not hasattr(importer, 'iter_modules'):
return []
return importer.iter_modules(prefix)
iter_importer_modules = simplegeneric(iter_importer_modules)
class ImpImporter:
"""PEP 302 Importer that wraps Python's "classic" import algorithm
ImpImporter(dirname) produces a PEP 302 importer that searches that
directory. ImpImporter(None) produces a PEP 302 importer that searches
the current sys.path, plus any modules that are frozen or built-in.
Note that ImpImporter does not currently support being used by placement
on sys.meta_path.
"""
def __init__(self, path=None):
self.path = path
def find_module(self, fullname, path=None):
# Note: we ignore 'path' argument since it is only used via meta_path
subname = fullname.split(".")[-1]
if subname != fullname and self.path is None:
return None
if self.path is None:
path = None
else:
path = [os.path.realpath(self.path)]
try:
file, filename, etc = imp.find_module(subname, path)
except ImportError:
return None
return ImpLoader(fullname, file, filename, etc)
def iter_modules(self, prefix=''):
if self.path is None or not os.path.isdir(self.path):
return
yielded = {}
import inspect
try:
filenames = os.listdir(self.path)
except OSError:
# ignore unreadable directories like import does
filenames = []
filenames.sort() # handle packages before same-named modules
for fn in filenames:
modname = inspect.getmodulename(fn)
if modname=='__init__' or modname in yielded:
continue
path = os.path.join(self.path, fn)
ispkg = False
if not modname and os.path.isdir(path) and '.' not in fn:
modname = fn
try:
dircontents = os.listdir(path)
except OSError:
# ignore unreadable directories like import does
dircontents = []
for fn in dircontents:
subname = inspect.getmodulename(fn)
if subname=='__init__':
ispkg = True
break
else:
continue # not a package
if modname and '.' not in modname:
yielded[modname] = 1
yield prefix + modname, ispkg
class ImpLoader:
"""PEP 302 Loader that wraps Python's "classic" import algorithm
"""
code = source = None
def __init__(self, fullname, file, filename, etc):
self.file = file
self.filename = filename
self.fullname = fullname
self.etc = etc
def load_module(self, fullname):
self._reopen()
try:
mod = imp.load_module(fullname, self.file, self.filename, self.etc)
finally:
if self.file:
self.file.close()
# Note: we don't set __loader__ because we want the module to look
# normal; i.e. this is just a wrapper for standard import machinery
return mod
def get_data(self, pathname):
return open(pathname, "rb").read()
def _reopen(self):
if self.file and self.file.closed:
mod_type = self.etc[2]
if mod_type==imp.PY_SOURCE:
self.file = open(self.filename, 'rU')
elif mod_type in (imp.PY_COMPILED, imp.C_EXTENSION):
self.file = open(self.filename, 'rb')
def _fix_name(self, fullname):
if fullname is None:
fullname = self.fullname
elif fullname != self.fullname:
raise ImportError("Loader for module %s cannot handle "
"module %s" % (self.fullname, fullname))
return fullname
def is_package(self, fullname):
fullname = self._fix_name(fullname)
return self.etc[2]==imp.PKG_DIRECTORY
def get_code(self, fullname=None):
fullname = self._fix_name(fullname)
if self.code is None:
mod_type = self.etc[2]
if mod_type==imp.PY_SOURCE:
source = self.get_source(fullname)
self.code = compile(source, self.filename, 'exec')
elif mod_type==imp.PY_COMPILED:
self._reopen()
try:
self.code = read_code(self.file)
finally:
self.file.close()
elif mod_type==imp.PKG_DIRECTORY:
self.code = self._get_delegate().get_code()
return self.code
def get_source(self, fullname=None):
fullname = self._fix_name(fullname)
if self.source is None:
mod_type = self.etc[2]
if mod_type==imp.PY_SOURCE:
self._reopen()
try:
self.source = self.file.read()
finally:
self.file.close()
elif mod_type==imp.PY_COMPILED:
if os.path.exists(self.filename[:-1]):
f = open(self.filename[:-1], 'rU')
self.source = f.read()
f.close()
elif mod_type==imp.PKG_DIRECTORY:
self.source = self._get_delegate().get_source()
return self.source
def _get_delegate(self):
return ImpImporter(self.filename).find_module('__init__')
def get_filename(self, fullname=None):
fullname = self._fix_name(fullname)
mod_type = self.etc[2]
if self.etc[2]==imp.PKG_DIRECTORY:
return self._get_delegate().get_filename()
elif self.etc[2] in (imp.PY_SOURCE, imp.PY_COMPILED, imp.C_EXTENSION):
return self.filename
return None
try:
import zipimport
from zipimport import zipimporter
def iter_zipimport_modules(importer, prefix=''):
dirlist = zipimport._zip_directory_cache[importer.archive].keys()
dirlist.sort()
_prefix = importer.prefix
plen = len(_prefix)
yielded = {}
import inspect
for fn in dirlist:
if not fn.startswith(_prefix):
continue
fn = fn[plen:].split(os.sep)
if len(fn)==2 and fn[1].startswith('__init__.py'):
if fn[0] not in yielded:
yielded[fn[0]] = 1
yield fn[0], True
if len(fn)!=1:
continue
modname = inspect.getmodulename(fn[0])
if modname=='__init__':
continue
if modname and '.' not in modname and modname not in yielded:
yielded[modname] = 1
yield prefix + modname, False
iter_importer_modules.register(zipimporter, iter_zipimport_modules)
except ImportError:
pass
def get_importer(path_item):
"""Retrieve a PEP 302 importer for the given path item
The returned importer is cached in sys.path_importer_cache
if it was newly created by a path hook.
If there is no importer, a wrapper around the basic import
machinery is returned. This wrapper is never inserted into
the importer cache (None is inserted instead).
The cache (or part of it) can be cleared manually if a
rescan of sys.path_hooks is necessary.
"""
try:
importer = sys.path_importer_cache[path_item]
except KeyError:
for path_hook in sys.path_hooks:
try:
importer = path_hook(path_item)
break
except ImportError:
pass
else:
importer = None
sys.path_importer_cache.setdefault(path_item, importer)
if importer is None:
try:
importer = ImpImporter(path_item)
except ImportError:
importer = None
return importer
def iter_importers(fullname=""):
"""Yield PEP 302 importers for the given module name
If fullname contains a '.', the importers will be for the package
containing fullname, otherwise they will be importers for sys.meta_path,
sys.path, and Python's "classic" import machinery, in that order. If
the named module is in a package, that package is imported as a side
effect of invoking this function.
Non PEP 302 mechanisms (e.g. the Windows registry) used by the
standard import machinery to find files in alternative locations
are partially supported, but are searched AFTER sys.path. Normally,
these locations are searched BEFORE sys.path, preventing sys.path
entries from shadowing them.
For this to cause a visible difference in behaviour, there must
be a module or package name that is accessible via both sys.path
and one of the non PEP 302 file system mechanisms. In this case,
the emulation will find the former version, while the builtin
import mechanism will find the latter.
Items of the following types can be affected by this discrepancy:
imp.C_EXTENSION, imp.PY_SOURCE, imp.PY_COMPILED, imp.PKG_DIRECTORY
"""
if fullname.startswith('.'):
raise ImportError("Relative module names not supported")
if '.' in fullname:
# Get the containing package's __path__
pkg = '.'.join(fullname.split('.')[:-1])
if pkg not in sys.modules:
__import__(pkg)
path = getattr(sys.modules[pkg], '__path__', None) or []
else:
for importer in sys.meta_path:
yield importer
path = sys.path
for item in path:
yield get_importer(item)
if '.' not in fullname:
yield ImpImporter()
def get_loader(module_or_name):
"""Get a PEP 302 "loader" object for module_or_name
If the module or package is accessible via the normal import
mechanism, a wrapper around the relevant part of that machinery
is returned. Returns None if the module cannot be found or imported.
If the named module is not already imported, its containing package
(if any) is imported, in order to establish the package __path__.
This function uses iter_importers(), and is thus subject to the same
limitations regarding platform-specific special import locations such
as the Windows registry.
"""
if module_or_name in sys.modules:
module_or_name = sys.modules[module_or_name]
if isinstance(module_or_name, ModuleType):
module = module_or_name
loader = getattr(module, '__loader__', None)
if loader is not None:
return loader
fullname = module.__name__
else:
fullname = module_or_name
return find_loader(fullname)
def find_loader(fullname):
"""Find a PEP 302 "loader" object for fullname
If fullname contains dots, path must be the containing package's __path__.
Returns None if the module cannot be found or imported. This function uses
iter_importers(), and is thus subject to the same limitations regarding
platform-specific special import locations such as the Windows registry.
"""
for importer in iter_importers(fullname):
loader = importer.find_module(fullname)
if loader is not None:
return loader
return None
def extend_path(path, name):
"""Extend a package's path.
Intended use is to place the following code in a package's __init__.py:
from pkgutil import extend_path
__path__ = extend_path(__path__, __name__)
This will add to the package's __path__ all subdirectories of
directories on sys.path named after the package. This is useful
if one wants to distribute different parts of a single logical
package as multiple directories.
It also looks for *.pkg files beginning where * matches the name
argument. This feature is similar to *.pth files (see site.py),
except that it doesn't special-case lines starting with 'import'.
A *.pkg file is trusted at face value: apart from checking for
duplicates, all entries found in a *.pkg file are added to the
path, regardless of whether they are exist the filesystem. (This
is a feature.)
If the input path is not a list (as is the case for frozen
packages) it is returned unchanged. The input path is not
modified; an extended copy is returned. Items are only appended
to the copy at the end.
It is assumed that sys.path is a sequence. Items of sys.path that
are not (unicode or 8-bit) strings referring to existing
directories are ignored. Unicode items of sys.path that cause
errors when used as filenames may cause this function to raise an
exception (in line with os.path.isdir() behavior).
"""
if not isinstance(path, list):
# This could happen e.g. when this is called from inside a
# frozen package. Return the path unchanged in that case.
return path
pname = os.path.join(*name.split('.')) # Reconstitute as relative path
# Just in case os.extsep != '.'
sname = os.extsep.join(name.split('.'))
sname_pkg = sname + os.extsep + "pkg"
init_py = "__init__" + os.extsep + "py"
path = path[:] # Start with a copy of the existing path
for dir in sys.path:
if not isinstance(dir, basestring) or not os.path.isdir(dir):
continue
subdir = os.path.join(dir, pname)
# XXX This may still add duplicate entries to path on
# case-insensitive filesystems
initfile = os.path.join(subdir, init_py)
if subdir not in path and os.path.isfile(initfile):
path.append(subdir)
# XXX Is this the right thing for subpackages like zope.app?
# It looks for a file named "zope.app.pkg"
pkgfile = os.path.join(dir, sname_pkg)
if os.path.isfile(pkgfile):
try:
f = open(pkgfile)
except IOError, msg:
sys.stderr.write("Can't open %s: %s\n" %
(pkgfile, msg))
else:
for line in f:
line = line.rstrip('\n')
if not line or line.startswith('#'):
continue
path.append(line) # Don't check for existence!
f.close()
return path
def get_data(package, resource):
"""Get a resource from a package.
This is a wrapper round the PEP 302 loader get_data API. The package
argument should be the name of a package, in standard module format
(foo.bar). The resource argument should be in the form of a relative
filename, using '/' as the path separator. The parent directory name '..'
is not allowed, and nor is a rooted name (starting with a '/').
The function returns a binary string, which is the contents of the
specified resource.
For packages located in the filesystem, which have already been imported,
this is the rough equivalent of
d = os.path.dirname(sys.modules[package].__file__)
data = open(os.path.join(d, resource), 'rb').read()
If the package cannot be located or loaded, or it uses a PEP 302 loader
which does not support get_data(), then None is returned.
"""
loader = get_loader(package)
if loader is None or not hasattr(loader, 'get_data'):
return None
mod = sys.modules.get(package) or loader.load_module(package)
if mod is None or not hasattr(mod, '__file__'):
return None
# Modify the resource name to be compatible with the loader.get_data
# signature - an os.path format "filename" starting with the dirname of
# the package's __file__
parts = resource.split('/')
parts.insert(0, os.path.dirname(mod.__file__))
resource_name = os.path.join(*parts)
return loader.get_data(resource_name)

View file

@ -0,0 +1,453 @@
"""Tokenization help for Python programs.
generate_tokens(readline) is a generator that breaks a stream of
text into Python tokens. It accepts a readline-like method which is called
repeatedly to get the next line of input (or "" for EOF). It generates
5-tuples with these members:
the token type (see token.py)
the token (a string)
the starting (row, column) indices of the token (a 2-tuple of ints)
the ending (row, column) indices of the token (a 2-tuple of ints)
the original line (string)
It is designed to match the working of the Python tokenizer exactly, except
that it produces COMMENT tokens for comments and gives type OP for all
operators
Older entry points
tokenize_loop(readline, tokeneater)
tokenize(readline, tokeneater=printtoken)
are the same, except instead of generating tokens, tokeneater is a callback
function to which the 5 fields described above are passed as 5 arguments,
each time a new token is found."""
# !mitogen: minify_safe
__author__ = 'Ka-Ping Yee <ping@lfw.org>'
__credits__ = ('GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, '
'Skip Montanaro, Raymond Hettinger')
from itertools import chain
import string, re
from token import *
import token
__all__ = [x for x in dir(token) if not x.startswith("_")]
__all__ += ["COMMENT", "tokenize", "generate_tokens", "NL", "untokenize"]
del token
COMMENT = N_TOKENS
tok_name[COMMENT] = 'COMMENT'
NL = N_TOKENS + 1
tok_name[NL] = 'NL'
N_TOKENS += 2
def group(*choices): return '(' + '|'.join(choices) + ')'
def any(*choices): return group(*choices) + '*'
def maybe(*choices): return group(*choices) + '?'
Whitespace = r'[ \f\t]*'
Comment = r'#[^\r\n]*'
Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment)
Name = r'[a-zA-Z_]\w*'
Hexnumber = r'0[xX][\da-fA-F]+[lL]?'
Octnumber = r'(0[oO][0-7]+)|(0[0-7]*)[lL]?'
Binnumber = r'0[bB][01]+[lL]?'
Decnumber = r'[1-9]\d*[lL]?'
Intnumber = group(Hexnumber, Binnumber, Octnumber, Decnumber)
Exponent = r'[eE][-+]?\d+'
Pointfloat = group(r'\d+\.\d*', r'\.\d+') + maybe(Exponent)
Expfloat = r'\d+' + Exponent
Floatnumber = group(Pointfloat, Expfloat)
Imagnumber = group(r'\d+[jJ]', Floatnumber + r'[jJ]')
Number = group(Imagnumber, Floatnumber, Intnumber)
# Tail end of ' string.
Single = r"[^'\\]*(?:\\.[^'\\]*)*'"
# Tail end of " string.
Double = r'[^"\\]*(?:\\.[^"\\]*)*"'
# Tail end of ''' string.
Single3 = r"[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''"
# Tail end of """ string.
Double3 = r'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""'
Triple = group("[uUbB]?[rR]?'''", '[uUbB]?[rR]?"""')
# Single-line ' or " string.
String = group(r"[uUbB]?[rR]?'[^\n'\\]*(?:\\.[^\n'\\]*)*'",
r'[uUbB]?[rR]?"[^\n"\\]*(?:\\.[^\n"\\]*)*"')
# Because of leftmost-then-longest match semantics, be sure to put the
# longest operators first (e.g., if = came before ==, == would get
# recognized as two instances of =).
Operator = group(r"\*\*=?", r">>=?", r"<<=?", r"<>", r"!=",
r"//=?",
r"[+\-*/%&|^=<>]=?",
r"~")
Bracket = '[][(){}]'
Special = group(r'\r?\n', r'[:;.,`@]')
Funny = group(Operator, Bracket, Special)
PlainToken = group(Number, Funny, String, Name)
Token = Ignore + PlainToken
# First (or only) line of ' or " string.
ContStr = group(r"[uUbB]?[rR]?'[^\n'\\]*(?:\\.[^\n'\\]*)*" +
group("'", r'\\\r?\n'),
r'[uUbB]?[rR]?"[^\n"\\]*(?:\\.[^\n"\\]*)*' +
group('"', r'\\\r?\n'))
PseudoExtras = group(r'\\\r?\n|\Z', Comment, Triple)
PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name)
tokenprog, pseudoprog, single3prog, double3prog = map(
re.compile, (Token, PseudoToken, Single3, Double3))
endprogs = {"'": re.compile(Single), '"': re.compile(Double),
"'''": single3prog, '"""': double3prog,
"r'''": single3prog, 'r"""': double3prog,
"u'''": single3prog, 'u"""': double3prog,
"ur'''": single3prog, 'ur"""': double3prog,
"R'''": single3prog, 'R"""': double3prog,
"U'''": single3prog, 'U"""': double3prog,
"uR'''": single3prog, 'uR"""': double3prog,
"Ur'''": single3prog, 'Ur"""': double3prog,
"UR'''": single3prog, 'UR"""': double3prog,
"b'''": single3prog, 'b"""': double3prog,
"br'''": single3prog, 'br"""': double3prog,
"B'''": single3prog, 'B"""': double3prog,
"bR'''": single3prog, 'bR"""': double3prog,
"Br'''": single3prog, 'Br"""': double3prog,
"BR'''": single3prog, 'BR"""': double3prog,
'r': None, 'R': None, 'u': None, 'U': None,
'b': None, 'B': None}
triple_quoted = {}
for t in ("'''", '"""',
"r'''", 'r"""', "R'''", 'R"""',
"u'''", 'u"""', "U'''", 'U"""',
"ur'''", 'ur"""', "Ur'''", 'Ur"""',
"uR'''", 'uR"""', "UR'''", 'UR"""',
"b'''", 'b"""', "B'''", 'B"""',
"br'''", 'br"""', "Br'''", 'Br"""',
"bR'''", 'bR"""', "BR'''", 'BR"""'):
triple_quoted[t] = t
single_quoted = {}
for t in ("'", '"',
"r'", 'r"', "R'", 'R"',
"u'", 'u"', "U'", 'U"',
"ur'", 'ur"', "Ur'", 'Ur"',
"uR'", 'uR"', "UR'", 'UR"',
"b'", 'b"', "B'", 'B"',
"br'", 'br"', "Br'", 'Br"',
"bR'", 'bR"', "BR'", 'BR"' ):
single_quoted[t] = t
tabsize = 8
class TokenError(Exception): pass
class StopTokenizing(Exception): pass
def printtoken(type, token, srow_scol, erow_ecol, line): # for testing
srow, scol = srow_scol
erow, ecol = erow_ecol
print("%d,%d-%d,%d:\t%s\t%s" % \
(srow, scol, erow, ecol, tok_name[type], repr(token)))
def tokenize(readline, tokeneater=printtoken):
"""
The tokenize() function accepts two parameters: one representing the
input stream, and one providing an output mechanism for tokenize().
The first parameter, readline, must be a callable object which provides
the same interface as the readline() method of built-in file objects.
Each call to the function should return one line of input as a string.
The second parameter, tokeneater, must also be a callable object. It is
called once for each token, with five arguments, corresponding to the
tuples generated by generate_tokens().
"""
try:
tokenize_loop(readline, tokeneater)
except StopTokenizing:
pass
# backwards compatible interface
def tokenize_loop(readline, tokeneater):
for token_info in generate_tokens(readline):
tokeneater(*token_info)
class Untokenizer:
def __init__(self):
self.tokens = []
self.prev_row = 1
self.prev_col = 0
def add_whitespace(self, start):
row, col = start
if row < self.prev_row or row == self.prev_row and col < self.prev_col:
raise ValueError("start ({},{}) precedes previous end ({},{})"
.format(row, col, self.prev_row, self.prev_col))
row_offset = row - self.prev_row
if row_offset:
self.tokens.append("\\\n" * row_offset)
self.prev_col = 0
col_offset = col - self.prev_col
if col_offset:
self.tokens.append(" " * col_offset)
def untokenize(self, iterable):
it = iter(iterable)
indents = []
startline = False
for t in it:
if len(t) == 2:
self.compat(t, it)
break
tok_type, token, start, end, line = t
if tok_type == ENDMARKER:
break
if tok_type == INDENT:
indents.append(token)
continue
elif tok_type == DEDENT:
indents.pop()
self.prev_row, self.prev_col = end
continue
elif tok_type in (NEWLINE, NL):
startline = True
elif startline and indents:
indent = indents[-1]
if start[1] >= len(indent):
self.tokens.append(indent)
self.prev_col = len(indent)
startline = False
self.add_whitespace(start)
self.tokens.append(token)
self.prev_row, self.prev_col = end
if tok_type in (NEWLINE, NL):
self.prev_row += 1
self.prev_col = 0
return "".join(self.tokens)
def compat(self, token, iterable):
indents = []
toks_append = self.tokens.append
startline = token[0] in (NEWLINE, NL)
prevstring = False
for tok in chain([token], iterable):
toknum, tokval = tok[:2]
if toknum in (NAME, NUMBER):
tokval += ' '
# Insert a space between two consecutive strings
if toknum == STRING:
if prevstring:
tokval = ' ' + tokval
prevstring = True
else:
prevstring = False
if toknum == INDENT:
indents.append(tokval)
continue
elif toknum == DEDENT:
indents.pop()
continue
elif toknum in (NEWLINE, NL):
startline = True
elif startline and indents:
toks_append(indents[-1])
startline = False
toks_append(tokval)
def untokenize(iterable):
"""Transform tokens back into Python source code.
Each element returned by the iterable must be a token sequence
with at least two elements, a token number and token value. If
only two tokens are passed, the resulting output is poor.
Round-trip invariant for full input:
Untokenized source will match input source exactly
Round-trip invariant for limited intput:
# Output text will tokenize the back to the input
t1 = [tok[:2] for tok in generate_tokens(f.readline)]
newcode = untokenize(t1)
readline = iter(newcode.splitlines(1)).next
t2 = [tok[:2] for tok in generate_tokens(readline)]
assert t1 == t2
"""
ut = Untokenizer()
return ut.untokenize(iterable)
def generate_tokens(readline):
"""
The generate_tokens() generator requires one argument, readline, which
must be a callable object which provides the same interface as the
readline() method of built-in file objects. Each call to the function
should return one line of input as a string. Alternately, readline
can be a callable function terminating with StopIteration:
readline = open(myfile).next # Example of alternate readline
The generator produces 5-tuples with these members: the token type; the
token string; a 2-tuple (srow, scol) of ints specifying the row and
column where the token begins in the source; a 2-tuple (erow, ecol) of
ints specifying the row and column where the token ends in the source;
and the line on which the token was found. The line passed is the
logical line; continuation lines are included.
"""
lnum = parenlev = continued = 0
namechars, numchars = string.ascii_letters + '_', '0123456789'
contstr, needcont = '', 0
contline = None
indents = [0]
while 1: # loop over lines in stream
try:
line = readline()
except StopIteration:
line = ''
lnum += 1
pos, max = 0, len(line)
if contstr: # continued string
if not line:
raise TokenError("EOF in multi-line string", strstart)
endmatch = endprog.match(line)
if endmatch:
pos = end = endmatch.end(0)
yield (STRING, contstr + line[:end],
strstart, (lnum, end), contline + line)
contstr, needcont = '', 0
contline = None
elif needcont and line[-2:] != '\\\n' and line[-3:] != '\\\r\n':
yield (ERRORTOKEN, contstr + line,
strstart, (lnum, len(line)), contline)
contstr = ''
contline = None
continue
else:
contstr = contstr + line
contline = contline + line
continue
elif parenlev == 0 and not continued: # new statement
if not line: break
column = 0
while pos < max: # measure leading whitespace
if line[pos] == ' ':
column += 1
elif line[pos] == '\t':
column = (column//tabsize + 1)*tabsize
elif line[pos] == '\f':
column = 0
else:
break
pos += 1
if pos == max:
break
if line[pos] in '#\r\n': # skip comments or blank lines
if line[pos] == '#':
comment_token = line[pos:].rstrip('\r\n')
nl_pos = pos + len(comment_token)
yield (COMMENT, comment_token,
(lnum, pos), (lnum, pos + len(comment_token)), line)
yield (NL, line[nl_pos:],
(lnum, nl_pos), (lnum, len(line)), line)
else:
yield ((NL, COMMENT)[line[pos] == '#'], line[pos:],
(lnum, pos), (lnum, len(line)), line)
continue
if column > indents[-1]: # count indents or dedents
indents.append(column)
yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
while column < indents[-1]:
if column not in indents:
raise IndentationError(
"unindent does not match any outer indentation level",
("<tokenize>", lnum, pos, line))
indents = indents[:-1]
yield (DEDENT, '', (lnum, pos), (lnum, pos), line)
else: # continued statement
if not line:
raise TokenError("EOF in multi-line statement", (lnum, 0))
continued = 0
while pos < max:
pseudomatch = pseudoprog.match(line, pos)
if pseudomatch: # scan for tokens
start, end = pseudomatch.span(1)
spos, epos, pos = (lnum, start), (lnum, end), end
if start == end:
continue
token, initial = line[start:end], line[start]
if initial in numchars or \
(initial == '.' and token != '.'): # ordinary number
yield (NUMBER, token, spos, epos, line)
elif initial in '\r\n':
if parenlev > 0:
n = NL
else:
n = NEWLINE
yield (n, token, spos, epos, line)
elif initial == '#':
assert not token.endswith("\n")
yield (COMMENT, token, spos, epos, line)
elif token in triple_quoted:
endprog = endprogs[token]
endmatch = endprog.match(line, pos)
if endmatch: # all on one line
pos = endmatch.end(0)
token = line[start:pos]
yield (STRING, token, spos, (lnum, pos), line)
else:
strstart = (lnum, start) # multiple lines
contstr = line[start:]
contline = line
break
elif initial in single_quoted or \
token[:2] in single_quoted or \
token[:3] in single_quoted:
if token[-1] == '\n': # continued string
strstart = (lnum, start)
endprog = (endprogs[initial] or endprogs[token[1]] or
endprogs[token[2]])
contstr, needcont = line[start:], 1
contline = line
break
else: # ordinary string
yield (STRING, token, spos, epos, line)
elif initial in namechars: # ordinary name
yield (NAME, token, spos, epos, line)
elif initial == '\\': # continued stmt
continued = 1
else:
if initial in '([{':
parenlev += 1
elif initial in ')]}':
parenlev -= 1
yield (OP, token, spos, epos, line)
else:
yield (ERRORTOKEN, line[pos],
(lnum, pos), (lnum, pos+1), line)
pos += 1
for indent in indents[1:]: # pop remaining indent levels
yield (DEDENT, '', (lnum, 0), (lnum, 0), '')
yield (ENDMARKER, '', (lnum, 0), (lnum, 0), '')
if __name__ == '__main__': # testing
import sys
if len(sys.argv) > 1:
tokenize(open(sys.argv[1]).readline)
else:
tokenize(sys.stdin.readline)