pyspider.libs.PrettyPrinter._format() - Code Metrics - Inspection of "fix typo last_modif{,i}ed" - binux/pyspider - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 39eece...c8d455 )

by Roy

created 2016-04-20 20:07 UTC

pyspider.libs.PrettyPrinter._format() F

↳ Parent: Project

Complexity

Conditions

Size

Total Lines

Duplication

Lines	0
Ratio	0 %

Metric	Value
cc	32
dl	0
loc	99
rs	2

How to fix Long Method Complexity

#  Author:      Fred L. Drake, Jr.
#               fdrake@...
#
#  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()
    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.

"""

from __future__ import print_function

import six
import sys as _sys

from io import BytesIO, StringIO

__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):
    """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]


def _sorted(iterable):
    return sorted(iterable)


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
        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 = BytesIO()
        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 self._depth and level > self._depth:
            write(rep)
            return

        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 = _sorted(object.items())
                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)
                        if sepLines:
                            write(',\n%s%s: ' % (' ' * indent, rep))
                        else:
                            write(', %s: ' % 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__) or
                (issubclass(typ, set) and r is set.__repr__) or
                (issubclass(typ, frozenset) and r is frozenset.__repr__)
        ):
            length = _len(object)
            if issubclass(typ, list):
                write('[')
                endchar = ']'
            elif issubclass(typ, set):
                if not length:
                    write('set()')
                    return
                write('set([')
                endchar = '])'
                object = _sorted(object)
                indent += 4
            elif issubclass(typ, frozenset):
                if not length:
                    write('frozenset()')
                    return
                write('frozenset([')
                endchar = '])'
                object = _sorted(object)
                indent += 10
            else:
                write('(')
                endchar = ')'
            if self._indent_per_level > 1 and sepLines:
                write((self._indent_per_level - 1) * ' ')
            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:]:
                        if sepLines:
                            write(',\n' + ' ' * indent)
                        else:
                            write(', ')
                        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:
        string = object
        string = string.replace('\n', '\\n').replace('\r', '\\r').replace('\t', '\\t')
        if 'locale' not in _sys.modules:
            return repr(object), True, False
        if "'" in object and '"' not in object:
            closure = '"'
            quotes = {'"': '\\"'}
            string = string.replace('"', '\\"')
        else:
            closure = "'"
            quotes = {"'": "\\'"}
            string = string.replace("'", "\\'")
        try:
            string.decode('utf8').encode('gbk', 'replace')
            return ("%s%s%s" % (closure, string, closure)), True, False
        except:
            pass
        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

    if typ is six.text_type:
        string = object.encode("utf8", 'replace')
        string = string.replace('\n', '\\n').replace('\r', '\\r').replace('\t', '\\t')
        if "'" in object and '"' not in object:
            closure = '"'
            quotes = {'"': '\\"'}
            string = string.replace('"', '\\"')
        else:
            closure = "'"
            quotes = {"'": "\\'"}
            string = string.replace("'", "\\'")
        return ("u%s%s%s" % (closure, string, 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
        for k, v in _sorted(object.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

    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()


1			# Author: Fred L. Drake, Jr.
2			# fdrake@...
3			#
4			# This is a simple little module I wrote to make life easier. I didn't
5			# see anything quite like it in the library, though I may have overlooked
6			# something. I wrote this when I was trying to read some heavily nested
7			# tuples with fairly non-descriptive content. This is modeled very much
8			# after Lisp/Scheme - style pretty-printing of lists. If you find it
9			# useful, thank small children who sleep at night.
10
11			"""Support to pretty-print lists, tuples, & dictionaries recursively.
12
13			Very simple, but useful, especially in debugging data structures.
14
15			Classes
16			-------
17
18			PrettyPrinter()
19			Handle pretty-printing operations onto a stream using a configured
20			set of formatting parameters.
21
22			Functions
23			---------
24
25			pformat()
26			Format a Python object into a pretty-printed representation.
27
28			pprint()
29			Pretty-print a Python object to a stream [default is sys.stdout].
30
31			saferepr()
32			Generate a 'standard' repr()-like value, but protect against recursive
33			data structures.
34
35			"""
36
37			from __future__ import print_function
38
39			import six
40			import sys as _sys
41
42			from io import BytesIO, StringIO
43
44			__all__ = ["pprint", "pformat", "isreadable", "isrecursive", "saferepr",
45			"PrettyPrinter"]
46
47			# cache these for faster access:
48			_commajoin = ", ".join
49			_id = id
50			_len = len
51			_type = type
52
53
54			def pprint(object, stream=None, indent=1, width=80, depth=None):
55			"""Pretty-print a Python object to a stream [default is sys.stdout]."""
56			printer = PrettyPrinter(
57			stream=stream, indent=indent, width=width, depth=depth)
58			printer.pprint(object)
59
60
61			def pformat(object, indent=1, width=80, depth=None):
62			"""Format a Python object into a pretty-printed representation."""
63			return PrettyPrinter(indent=indent, width=width, depth=depth).pformat(object)
64
65
66			def saferepr(object):
67			"""Version of repr() which can handle recursive data structures."""
68			return _safe_repr(object, {}, None, 0)[0]
69
70
71			def isreadable(object):
72			"""Determine if saferepr(object) is readable by eval()."""
73			return _safe_repr(object, {}, None, 0)[1]
74
75
76			def isrecursive(object):
77			"""Determine if object requires a recursive representation."""
78			return _safe_repr(object, {}, None, 0)[2]
79
80
81			def _sorted(iterable):
82			return sorted(iterable)
83
84
85			class PrettyPrinter:
86
87			def __init__(self, indent=1, width=80, depth=None, stream=None):
88			"""Handle pretty printing operations onto a stream using a set of
89			configured parameters.
90
91			indent
92			Number of spaces to indent for each level of nesting.
93
94			width
95			Attempted maximum number of columns in the output.
96
97			depth
98			The maximum depth to print out nested structures.
99
100			stream
101			The desired output stream. If omitted (or false), the standard
102			output stream available at construction will be used.
103
104			"""
105			indent = int(indent)
106			width = int(width)
107			assert indent >= 0, "indent must be >= 0"
108			assert depth is None or depth > 0, "depth must be > 0"
109			assert width, "width must be != 0"
110			self._depth = depth
111			self._indent_per_level = indent
112			self._width = width
113			if stream is not None:
114			self._stream = stream
115			else:
116			self._stream = _sys.stdout
117
118			def pprint(self, object):
119			self._format(object, self._stream, 0, 0, {}, 0)
120			self._stream.write("\n")
121
122			def pformat(self, object):
123			sio = BytesIO()
124			self._format(object, sio, 0, 0, {}, 0)
125			return sio.getvalue()
126
127			def isrecursive(self, object):
128			return self.format(object, {}, 0, 0)[2]
129
130			def isreadable(self, object):
131			s, readable, recursive = self.format(object, {}, 0, 0)
132			return readable and not recursive
133
134			def _format(self, object, stream, indent, allowance, context, level):
135			level = level + 1
136			objid = _id(object)
137			if objid in context:
138			stream.write(_recursion(object))
139			self._recursive = True
140			self._readable = False
141			return
142			rep = self._repr(object, context, level - 1)
143			typ = _type(object)
144			sepLines = _len(rep) > (self._width - 1 - indent - allowance)
145			write = stream.write
146
147			if self._depth and level > self._depth:
148			write(rep)
149			return
150
151			r = getattr(typ, "__repr__", None)
152			if issubclass(typ, dict) and r is dict.__repr__:
153			write('{')
154			if self._indent_per_level > 1:
155			write((self._indent_per_level - 1) * ' ')
156			length = _len(object)
157			if length:
158			context[objid] = 1
159			indent = indent + self._indent_per_level
160			items = _sorted(object.items())
161			key, ent = items[0]
162			rep = self._repr(key, context, level)
163			write(rep)
164			write(': ')
165			self._format(ent, stream, indent + _len(rep) + 2,
166			allowance + 1, context, level)
167			if length > 1:
168			for key, ent in items[1:]:
169			rep = self._repr(key, context, level)
170			if sepLines:
171			write(',\n%s%s: ' % (' ' * indent, rep))
172			else:
173			write(', %s: ' % rep)
174			self._format(ent, stream, indent + _len(rep) + 2,
175			allowance + 1, context, level)
176			indent = indent - self._indent_per_level
177			del context[objid]
178			write('}')
179			return
180
181			if (
182			(issubclass(typ, list) and r is list.__repr__) or
183			(issubclass(typ, tuple) and r is tuple.__repr__) or
184			(issubclass(typ, set) and r is set.__repr__) or
185			(issubclass(typ, frozenset) and r is frozenset.__repr__)
186			):
187			length = _len(object)
188			if issubclass(typ, list):
189			write('[')
190			endchar = ']'
191			elif issubclass(typ, set):
192			if not length:
193			write('set()')
194			return
195			write('set([')
196			endchar = '])'
197			object = _sorted(object)
198			indent += 4
199			elif issubclass(typ, frozenset):
200			if not length:
201			write('frozenset()')
202			return
203			write('frozenset([')
204			endchar = '])'
205			object = _sorted(object)
206			indent += 10
207			else:
208			write('(')
209			endchar = ')'
210			if self._indent_per_level > 1 and sepLines:
211			write((self._indent_per_level - 1) * ' ')
212			if length:
213			context[objid] = 1
214			indent = indent + self._indent_per_level
215			self._format(object[0], stream, indent, allowance + 1,
216			context, level)
217			if length > 1:
218			for ent in object[1:]:
219			if sepLines:
220			write(',\n' + ' ' * indent)
221			else:
222			write(', ')
223			self._format(ent, stream, indent,
224			allowance + 1, context, level)
225			indent = indent - self._indent_per_level
226			del context[objid]
227			if issubclass(typ, tuple) and length == 1:
228			write(',')
229			write(endchar)
230			return
231
232			write(rep)
233
234			def _repr(self, object, context, level):
235			repr, readable, recursive = self.format(object, context.copy(),
236			self._depth, level)
237			if not readable:
238			self._readable = False
239			if recursive:
240			self._recursive = True
241			return repr
242
243			def format(self, object, context, maxlevels, level):
244			"""Format object for a specific context, returning a string
245			and flags indicating whether the representation is 'readable'
246			and whether the object represents a recursive construct.
247			"""
248			return _safe_repr(object, context, maxlevels, level)
249
250
251			# Return triple (repr_string, isreadable, isrecursive).
252
253			def _safe_repr(object, context, maxlevels, level):
254			typ = _type(object)
255			if typ is str:
256			string = object
257			string = string.replace('\n', '\\n').replace('\r', '\\r').replace('\t', '\\t')
258			if 'locale' not in _sys.modules:
259			return repr(object), True, False
260			if "'" in object and '"' not in object:
261			closure = '"'
262			quotes = {'"': '\\"'}
263			string = string.replace('"', '\\"')
264			else:
265			closure = "'"
266			quotes = {"'": "\\'"}
267			string = string.replace("'", "\\'")
268			try:
269			string.decode('utf8').encode('gbk', 'replace')
270			return ("%s%s%s" % (closure, string, closure)), True, False
271			except:
272			pass
273			qget = quotes.get
274			sio = StringIO()
275			write = sio.write
276			for char in object:
277			if char.isalpha():
278			write(char)
279			else:
280			write(qget(char, repr(char)[1:-1]))
281			return ("%s%s%s" % (closure, sio.getvalue(), closure)), True, False
282
283			if typ is six.text_type:
284			string = object.encode("utf8", 'replace')
285			string = string.replace('\n', '\\n').replace('\r', '\\r').replace('\t', '\\t')
286			if "'" in object and '"' not in object:
287			closure = '"'
288			quotes = {'"': '\\"'}
289			string = string.replace('"', '\\"')
290			else:
291			closure = "'"
292			quotes = {"'": "\\'"}
293			string = string.replace("'", "\\'")
294			return ("u%s%s%s" % (closure, string, closure)), True, False
295
296			r = getattr(typ, "__repr__", None)
297			if issubclass(typ, dict) and r is dict.__repr__:
298			if not object:
299			return "{}", True, False
300			objid = _id(object)
301			if maxlevels and level >= maxlevels:
302			return "{...}", False, objid in context
303			if objid in context:
304			return _recursion(object), False, True
305			context[objid] = 1
306			readable = True
307			recursive = False
308			components = []
309			append = components.append
310			level += 1
311			saferepr = _safe_repr
312			for k, v in _sorted(object.items()):
313			krepr, kreadable, krecur = saferepr(k, context, maxlevels, level)
314			vrepr, vreadable, vrecur = saferepr(v, context, maxlevels, level)
315			append("%s: %s" % (krepr, vrepr))
316			readable = readable and kreadable and vreadable
317			if krecur or vrecur:
318			recursive = True
319			del context[objid]
320			return "{%s}" % _commajoin(components), readable, recursive
321
322			if (issubclass(typ, list) and r is list.__repr__) or \
323			(issubclass(typ, tuple) and r is tuple.__repr__):
324			if issubclass(typ, list):
325			if not object:
326			return "[]", True, False
327			format = "[%s]"
328			elif _len(object) == 1:
329			format = "(%s,)"
330			else:
331			if not object:
332			return "()", True, False
333			format = "(%s)"
334			objid = _id(object)
335			if maxlevels and level >= maxlevels:
336			return format % "...", False, objid in context
337			if objid in context:
338			return _recursion(object), False, True
339			context[objid] = 1
340			readable = True
341			recursive = False
342			components = []
343			append = components.append
344			level += 1
345			for o in object:
346			orepr, oreadable, orecur = _safe_repr(o, context, maxlevels, level)
347			append(orepr)
348			if not oreadable:
349			readable = False
350			if orecur:
351			recursive = True
352			del context[objid]
353			return format % _commajoin(components), readable, recursive
354
355			rep = repr(object)
356			return rep, (rep and not rep.startswith('<')), False
357
358
359			def _recursion(object):
360			return ("<Recursion on %s with id=%s>"
361			% (_type(object).__name__, _id(object)))
362
363
364			def _perfcheck(object=None):
365			import time
366			if object is None:
367			object = [("string", (1, 2), [3, 4], {5: 6, 7: 8})] * 100000
368			p = PrettyPrinter()
369			t1 = time.time()
370			_safe_repr(object, {}, None, 0)
371			t2 = time.time()
372			p.pformat(object)
373			t3 = time.time()
374			print("_safe_repr:", t2 - t1)
375			print("pformat:", t3 - t2)
376
377			if __name__ == "__main__":
378			_perfcheck()
379

binux / pyspider

Push — master ( 39eece...c8d455 )

pyspider.libs.PrettyPrinter._format() F

Complexity

Size

Duplication

How to fix Long Method Complexity

Long Method

Complexity

Duplication Side-by-Side

Filter issues like