cpython/Lib/pprint.py

321 lines
11 KiB
Python
Raw Normal View History

# Author: Fred L. Drake, Jr.
2001-10-09 17:53:48 -03:00
# fdrake@acm.org
#
# This is a simple little module I wrote to make life easier. I didn't
# see anything quite like it in the library, though I may have overlooked
# something. I wrote this when I was trying to read some heavily nested
# tuples with fairly non-descriptive content. This is modeled very much
# after Lisp/Scheme - style pretty-printing of lists. If you find it
# useful, thank small children who sleep at night.
"""Support to pretty-print lists, tuples, & dictionaries recursively.
Very simple, but useful, especially in debugging data structures.
Classes
-------
PrettyPrinter()
Handle pretty-printing operations onto a stream using a configured
set of formatting parameters.
Functions
---------
pformat()
Format a Python object into a pretty-printed representation.
pprint()
2004-05-14 13:31:56 -03:00
Pretty-print a Python object to a stream [default is sys.stdout].
saferepr()
Generate a 'standard' repr()-like value, but protect against recursive
data structures.
"""
import sys as _sys
from cStringIO import StringIO as _StringIO
2001-02-11 22:00:42 -04:00
__all__ = ["pprint","pformat","isreadable","isrecursive","saferepr",
"PrettyPrinter"]
# cache these for faster access:
_commajoin = ", ".join
_id = id
_len = len
_type = type
def pprint(object, stream=None, indent=1, width=80, depth=None):
2004-05-14 13:31:56 -03:00
"""Pretty-print a Python object to a stream [default is sys.stdout]."""
printer = PrettyPrinter(
stream=stream, indent=indent, width=width, depth=depth)
printer.pprint(object)
def pformat(object, indent=1, width=80, depth=None):
"""Format a Python object into a pretty-printed representation."""
return PrettyPrinter(indent=indent, width=width, depth=depth).pformat(object)
def saferepr(object):
"""Version of repr() which can handle recursive data structures."""
return _safe_repr(object, {}, None, 0)[0]
def isreadable(object):
"""Determine if saferepr(object) is readable by eval()."""
return _safe_repr(object, {}, None, 0)[1]
def isrecursive(object):
"""Determine if object requires a recursive representation."""
return _safe_repr(object, {}, None, 0)[2]
class PrettyPrinter:
def __init__(self, indent=1, width=80, depth=None, stream=None):
"""Handle pretty printing operations onto a stream using a set of
configured parameters.
indent
Number of spaces to indent for each level of nesting.
width
Attempted maximum number of columns in the output.
depth
The maximum depth to print out nested structures.
stream
The desired output stream. If omitted (or false), the standard
output stream available at construction will be used.
"""
indent = int(indent)
width = int(width)
assert indent >= 0, "indent must be >= 0"
assert depth is None or depth > 0, "depth must be > 0"
assert width, "width must be != 0"
self._depth = depth
self._indent_per_level = indent
self._width = width
2002-06-01 13:07:16 -03:00
if stream is not None:
self._stream = stream
else:
self._stream = _sys.stdout
def pprint(self, object):
self._format(object, self._stream, 0, 0, {}, 0)
self._stream.write("\n")
def pformat(self, object):
sio = _StringIO()
self._format(object, sio, 0, 0, {}, 0)
return sio.getvalue()
def isrecursive(self, object):
return self.format(object, {}, 0, 0)[2]
def isreadable(self, object):
s, readable, recursive = self.format(object, {}, 0, 0)
return readable and not recursive
def _format(self, object, stream, indent, allowance, context, level):
level = level + 1
objid = _id(object)
if objid in context:
stream.write(_recursion(object))
self._recursive = True
self._readable = False
return
rep = self._repr(object, context, level - 1)
typ = _type(object)
sepLines = _len(rep) > (self._width - 1 - indent - allowance)
write = stream.write
if sepLines:
r = getattr(typ, "__repr__", None)
if issubclass(typ, dict) and r is dict.__repr__:
write('{')
if self._indent_per_level > 1:
write((self._indent_per_level - 1) * ' ')
length = _len(object)
if length:
context[objid] = 1
indent = indent + self._indent_per_level
items = object.items()
items.sort()
key, ent = items[0]
rep = self._repr(key, context, level)
write(rep)
write(': ')
self._format(ent, stream, indent + _len(rep) + 2,
allowance + 1, context, level)
if length > 1:
for key, ent in items[1:]:
rep = self._repr(key, context, level)
write(',\n%s%s: ' % (' '*indent, rep))
self._format(ent, stream, indent + _len(rep) + 2,
allowance + 1, context, level)
indent = indent - self._indent_per_level
del context[objid]
write('}')
return
if (issubclass(typ, list) and r is list.__repr__) or \
(issubclass(typ, tuple) and r is tuple.__repr__):
if issubclass(typ, list):
write('[')
endchar = ']'
else:
write('(')
endchar = ')'
if self._indent_per_level > 1:
write((self._indent_per_level - 1) * ' ')
length = _len(object)
if length:
context[objid] = 1
indent = indent + self._indent_per_level
self._format(object[0], stream, indent, allowance + 1,
context, level)
if length > 1:
for ent in object[1:]:
write(',\n' + ' '*indent)
self._format(ent, stream, indent,
allowance + 1, context, level)
indent = indent - self._indent_per_level
del context[objid]
if issubclass(typ, tuple) and length == 1:
write(',')
write(endchar)
return
write(rep)
def _repr(self, object, context, level):
repr, readable, recursive = self.format(object, context.copy(),
self._depth, level)
if not readable:
self._readable = False
if recursive:
self._recursive = True
return repr
def format(self, object, context, maxlevels, level):
"""Format object for a specific context, returning a string
and flags indicating whether the representation is 'readable'
and whether the object represents a recursive construct.
"""
return _safe_repr(object, context, maxlevels, level)
# Return triple (repr_string, isreadable, isrecursive).
def _safe_repr(object, context, maxlevels, level):
typ = _type(object)
if typ is str:
if 'locale' not in _sys.modules:
return repr(object), True, False
if "'" in object and '"' not in object:
closure = '"'
quotes = {'"': '\\"'}
else:
closure = "'"
quotes = {"'": "\\'"}
qget = quotes.get
sio = _StringIO()
write = sio.write
for char in object:
if char.isalpha():
write(char)
else:
write(qget(char, repr(char)[1:-1]))
return ("%s%s%s" % (closure, sio.getvalue(), closure)), True, False
r = getattr(typ, "__repr__", None)
if issubclass(typ, dict) and r is dict.__repr__:
if not object:
return "{}", True, False
objid = _id(object)
if maxlevels and level > maxlevels:
return "{...}", False, objid in context
if objid in context:
return _recursion(object), False, True
context[objid] = 1
readable = True
recursive = False
components = []
append = components.append
level += 1
saferepr = _safe_repr
Restructure comparison dramatically. There is no longer a default *ordering* between objects; there is only a default equality test (defined by an object being equal to itself only). Read the comment in object.c. The current implementation never uses a three-way comparison to compute a rich comparison, but it does use a rich comparison to compute a three-way comparison. I'm not quite done ripping out all the calls to PyObject_Compare/Cmp, or replacing tp_compare implementations with tp_richcompare implementations; but much of that has happened (to make most unit tests pass). The following tests still fail, because I need help deciding or understanding: test_codeop -- depends on comparing code objects test_datetime -- need Tim Peters' opinion test_marshal -- depends on comparing code objects test_mutants -- need help understanding it The problem with test_codeop and test_marshal is this: these tests compare two different code objects and expect them to be equal. Is that still a feature we'd like to support? I've temporarily removed the comparison and hash code from code objects, so they use the default (equality by pointer only) comparison. For the other two tests, run them to see for yourself. (There may be more failing test with "-u all".) A general problem with getting lots of these tests to pass is the reality that for object types that have a natural total ordering, implementing __cmp__ is much more convenient than implementing __eq__, __ne__, __lt__, and so on. Should we go back to allowing __cmp__ to provide a total ordering? Should we provide some other way to implement rich comparison with a single method override? Alex proposed a __key__() method; I've considered a __richcmp__() method. Or perhaps __cmp__() just shouldn't be killed off...
2006-08-23 21:41:19 -03:00
items = object.items()
try:
items = sorted(items)
except TypeError:
items = sorted(items, key=lambda (k, v): (str(type(k)), k, v))
for k, v in items:
krepr, kreadable, krecur = saferepr(k, context, maxlevels, level)
vrepr, vreadable, vrecur = saferepr(v, context, maxlevels, level)
append("%s: %s" % (krepr, vrepr))
readable = readable and kreadable and vreadable
if krecur or vrecur:
recursive = True
del context[objid]
return "{%s}" % _commajoin(components), readable, recursive
if (issubclass(typ, list) and r is list.__repr__) or \
(issubclass(typ, tuple) and r is tuple.__repr__):
if issubclass(typ, list):
if not object:
return "[]", True, False
format = "[%s]"
elif _len(object) == 1:
format = "(%s,)"
else:
if not object:
return "()", True, False
format = "(%s)"
objid = _id(object)
if maxlevels and level > maxlevels:
return format % "...", False, objid in context
if objid in context:
return _recursion(object), False, True
context[objid] = 1
readable = True
recursive = False
components = []
append = components.append
level += 1
for o in object:
orepr, oreadable, orecur = _safe_repr(o, context, maxlevels, level)
append(orepr)
if not oreadable:
readable = False
if orecur:
recursive = True
del context[objid]
return format % _commajoin(components), readable, recursive
2001-11-13 17:51:26 -04:00
rep = repr(object)
return rep, (rep and not rep.startswith('<')), False
def _recursion(object):
return ("<Recursion on %s with id=%s>"
% (_type(object).__name__, _id(object)))
def _perfcheck(object=None):
import time
if object is None:
object = [("string", (1, 2), [3, 4], {5: 6, 7: 8})] * 100000
p = PrettyPrinter()
t1 = time.time()
_safe_repr(object, {}, None, 0)
t2 = time.time()
p.pformat(object)
t3 = time.time()
print "_safe_repr:", t2 - t1
print "pformat:", t3 - t2
if __name__ == "__main__":
_perfcheck()