GlobTransformBase.transform_range_ignore() - Code Metrics - Inspection of "handle complex glob groups" - ergoithz/browsepy - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — 0.5.3 ( c2ca4c...28aba1 )

by Felipe A.

created 2017-04-26 18:05 UTC

GlobTransformBase.transform_range_ignore() A

↳ Parent: GlobTransformBase

Complexity

Conditions

Size

Total Lines

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
dl	0
loc	2
rs	10
c	0
b	0
f	0
cc	1


import os
import warnings

from unicategories import categories as unicat, RangeGroup as ranges

from ..compat import re_escape, chr
from . import StateMachine


class GlobTransformBase(StateMachine):
    jumps = {
        'text': {
            '*': 'wildcard',
            '**': 'wildcard',
            '?': 'wildcard',
            '[': 'range',
            '[!': 'range',
            '[]': 'range',
            '{': 'group',
            ',': 'group',
            '}': 'group',
            '\\': 'literal',
            '/': 'sep',
            },
        'sep': {
            '': 'text',
            },
        'literal': {
            c: 'text' for c in '\\*?[{'
            },
        'wildcard': {
            '': 'text',
            },
        'range': {
            '/': 'range_sep',
            ']': 'range_close',
            '[.': 'posix_collating_symbol',
            '[:': 'posix_character_class',
            '[=': 'posix_equivalence_class',
            },
        'range_sep': {
            '': 'range',
            },
        'range_ignore': {
            '': 'range',
            },
        'range_close': {
            '': 'text',
            },
        'posix_collating_symbol': {
            '.]': 'range_ignore',
            },
        'posix_character_class': {
            ':]': 'range_ignore',
            },
        'posix_equivalence_class': {
            '=]': 'range_ignore',
            },
        'group': {
            '': 'text',
            },
        }
    character_classes = {
        'alnum': (
            # [\p{L}\p{Nl}\p{Nd}]
            unicat['L'] + unicat['Nl'] + unicat['Nd']
            ),
        'alpha': (
            # \p{L}\p{Nl}
            unicat['L'] + unicat['Nl']
            ),
        'ascii': (
            # [\x00-\x7F]
            ranges(((0, 0x7F),))
            ),
        'blank': (
            # [\p{Zs}\t]
            unicat['Zs'] + ranges(((9, 10),))
            ),
        'cntrl': (
            # \p{Cc}
            unicat['Cc']
            ),
        'digit': (
            # \p{Nd}
            unicat['Nd']
            ),
        'graph': (
            # [^\p{Z}\p{C}]
            unicat['M'] + unicat['L'] + unicat['N'] + unicat['P'] + unicat['S']
            ),
        'lower': (
            # \p{Ll}
            unicat['Ll']
            ),
        'print': (
            # \P{C}
            unicat['C']
            ),
        'punct': (
            # \p{P}
            unicat['P']
            ),
        'space': (
            # [\p{Z}\t\r\n\v\f]
            unicat['Z'] + ranges(((9, 14),))
            ),
        'upper': (
            # \p{Lu}
            unicat['Lu']
            ),
        'word': (
            # [\p{L}\p{Nl}\p{Nd}\p{Pc}]
            unicat['L'] + unicat['Nl'] + unicat['Nd'] + unicat['Pc']
            ),
        'xdigit': (
            # [0-9A-Fa-f]
            ranges(((48, 58), (65, 71), (97, 103)))
            ),
        }
    current = 'text'
    deferred = False

    def __init__(self, data, sep=os.sep, base=None):
        self.sep = sep
        self.base = base or ''
        self.deferred_data = []
        self.deep = 0
        super(GlobTransformBase, self).__init__(data)

    def transform(self, data, mark, next):
        data = super(GlobTransformBase, self).transform(data, mark, next)
        if self.deferred:
            self.deferred_data.append(data)
            data = ''
        elif self.deferred_data:
            data = ''.join(self.deferred_data) + data
            self.deferred_data[:] = ()
        return data

    def transform_posix_collating_symbol(self, data, mark, next):
        warnings.warn(
            'Posix collating symbols (like %s%s) are not supported.'
            % (data, mark))
        return None

    def transform_posix_character_class(self, data, mark, next):
        name = data[len(self.start):]
        if name not in self.character_classes:
            warnings.warn(
                'Posix character class %s is not supported.'
                % name)
            return None
        return ''.join(
            chr(start)
            if 1 == end - start else
            '%s-%s' % (chr(start), chr(end - 1))
            for start, end in self.character_classes[name]
            )

    def transform_posix_equivalence_class(self, data, mark, next):
        warnings.warn(
            'Posix equivalence class expresions (like %s%s) are not supported.'
            % (data, mark))
        return None

    def transform_wildcard(self, data, mark, next):
        if self.start == '**':
            return '.*'
        if self.start == '*':
            return '[^%s]*' % re_escape(self.sep)
        return '.'

    def transform_text(self, data, mark, next):
        return re_escape(data)

    def transform_sep(self, data, mark, next):
        return re_escape(self.sep)

    def transform_literal(self, data, mark, next):
        return data[len(self.start):]

    def transform_range(self, data, mark, next):
        self.deferred = True
        if self.start == '[!':
            return '[^%s' % data[2:]
        if self.start == '[]':
            return '[\\]%s' % data[2:]
        return data

    def transform_range_sep(self, data, mark, next):
        return re_escape(self.sep)

    def transform_range_close(self, data, mark, next):
        self.deferred = False
        if None in self.deferred_data:
            self.deferred_data[:] = ()
            return '.'
        return data

    def transform_range_ignore(self, data, mark, next):
        return ''

    def transform_group(self, data, mark, next):
        if self.start == '{':
            self.deep += 1
            return '('
        if self.start == ',' and self.deep:
            return '|'
        if self.start == '}' and self.deep:
            self.deep -= 1
            return ')'
        return data


class GlobTransform(GlobTransformBase):
    jumps = GlobTransformBase.jumps.copy()
    jumps.update({
        'start': {
            '': 'text',
            '/': 'sep',
            },
        })
    current = 'start'

    def transform_start(self, data, mark, next):
        if mark == '/':
            return '^%s' % re_escape(self.base)
        return re_escape(self.sep)

    def flush(self):
        return '%s(%s|$)' % (
            super(GlobTransformBase, self).flush(),
            re_escape(self.sep),
            )


def translate(data, sep=os.sep, base=None):
    self = GlobTransform(data, sep, base)
    return ''.join(self)


1
2			import os
3			import warnings
4
5			from unicategories import categories as unicat, RangeGroup as ranges
6
7			from ..compat import re_escape, chr
8			from . import StateMachine
9
10
11			class GlobTransformBase(StateMachine):
12			jumps = {
13			'text': {
14			'*': 'wildcard',
15			'**': 'wildcard',
16			'?': 'wildcard',
17			'[': 'range',
18			'[!': 'range',
19			'[]': 'range',
20			'{': 'group',
21			',': 'group',
22			'}': 'group',
23			'\\': 'literal',
24			'/': 'sep',
25			},
26			'sep': {
27			'': 'text',
28			},
29			'literal': {
30			c: 'text' for c in '\\*?[{'
31			},
32			'wildcard': {
33			'': 'text',
34			},
35			'range': {
36			'/': 'range_sep',
37			']': 'range_close',
38			'[.': 'posix_collating_symbol',
39			'[:': 'posix_character_class',
40			'[=': 'posix_equivalence_class',
41			},
42			'range_sep': {
43			'': 'range',
44			},
45			'range_ignore': {
46			'': 'range',
47			},
48			'range_close': {
49			'': 'text',
50			},
51			'posix_collating_symbol': {
52			'.]': 'range_ignore',
53			},
54			'posix_character_class': {
55			':]': 'range_ignore',
56			},
57			'posix_equivalence_class': {
58			'=]': 'range_ignore',
59			},
60			'group': {
61			'': 'text',
62			},
63			}
64			character_classes = {
65			'alnum': (
66			# [\p{L}\p{Nl}\p{Nd}]
67			unicat['L'] + unicat['Nl'] + unicat['Nd']
68			),
69			'alpha': (
70			# \p{L}\p{Nl}
71			unicat['L'] + unicat['Nl']
72			),
73			'ascii': (
74			# [\x00-\x7F]
75			ranges(((0, 0x7F),))
76			),
77			'blank': (
78			# [\p{Zs}\t]
79			unicat['Zs'] + ranges(((9, 10),))
80			),
81			'cntrl': (
82			# \p{Cc}
83			unicat['Cc']
84			),
85			'digit': (
86			# \p{Nd}
87			unicat['Nd']
88			),
89			'graph': (
90			# [^\p{Z}\p{C}]
91			unicat['M'] + unicat['L'] + unicat['N'] + unicat['P'] + unicat['S']
92			),
93			'lower': (
94			# \p{Ll}
95			unicat['Ll']
96			),
97			'print': (
98			# \P{C}
99			unicat['C']
100			),
101			'punct': (
102			# \p{P}
103			unicat['P']
104			),
105			'space': (
106			# [\p{Z}\t\r\n\v\f]
107			unicat['Z'] + ranges(((9, 14),))
108			),
109			'upper': (
110			# \p{Lu}
111			unicat['Lu']
112			),
113			'word': (
114			# [\p{L}\p{Nl}\p{Nd}\p{Pc}]
115			unicat['L'] + unicat['Nl'] + unicat['Nd'] + unicat['Pc']
116			),
117			'xdigit': (
118			# [0-9A-Fa-f]
119			ranges(((48, 58), (65, 71), (97, 103)))
120			),
121			}
122			current = 'text'
123			deferred = False
124
125			def __init__(self, data, sep=os.sep, base=None):
126			self.sep = sep
127			self.base = base or ''
128			self.deferred_data = []
129			self.deep = 0
130			super(GlobTransformBase, self).__init__(data)
131
132			def transform(self, data, mark, next):
133			data = super(GlobTransformBase, self).transform(data, mark, next)
134			if self.deferred:
135			self.deferred_data.append(data)
136			data = ''
137			elif self.deferred_data:
138			data = ''.join(self.deferred_data) + data
139			self.deferred_data[:] = ()
140			return data
141
142			def transform_posix_collating_symbol(self, data, mark, next):
143			warnings.warn(
144			'Posix collating symbols (like %s%s) are not supported.'
145			% (data, mark))
146			return None
147
148			def transform_posix_character_class(self, data, mark, next):
149			name = data[len(self.start):]
150			if name not in self.character_classes:
151			warnings.warn(
152			'Posix character class %s is not supported.'
153			% name)
154			return None
155			return ''.join(
156			chr(start)
157			if 1 == end - start else
158			'%s-%s' % (chr(start), chr(end - 1))
159			for start, end in self.character_classes[name]
160			)
161
162			def transform_posix_equivalence_class(self, data, mark, next):
163			warnings.warn(
164			'Posix equivalence class expresions (like %s%s) are not supported.'
165			% (data, mark))
166			return None
167
168			def transform_wildcard(self, data, mark, next):
169			if self.start == '**':
170			return '.*'
171			if self.start == '*':
172			return '[^%s]*' % re_escape(self.sep)
173			return '.'
174
175			def transform_text(self, data, mark, next):
176			return re_escape(data)
177
178			def transform_sep(self, data, mark, next):
179			return re_escape(self.sep)
180
181			def transform_literal(self, data, mark, next):
182			return data[len(self.start):]
183
184			def transform_range(self, data, mark, next):
185			self.deferred = True
186			if self.start == '[!':
187			return '[^%s' % data[2:]
188			if self.start == '[]':
189			return '[\\]%s' % data[2:]
190			return data
191
192			def transform_range_sep(self, data, mark, next):
193			return re_escape(self.sep)
194
195			def transform_range_close(self, data, mark, next):
196			self.deferred = False
197			if None in self.deferred_data:
198			self.deferred_data[:] = ()
199			return '.'
200			return data
201
202			def transform_range_ignore(self, data, mark, next):
203			return ''
204
205			def transform_group(self, data, mark, next):
206			if self.start == '{':
207			self.deep += 1
208			return '('
209			if self.start == ',' and self.deep:
210			return '\|'
211			if self.start == '}' and self.deep:
212			self.deep -= 1
213			return ')'
214			return data
215
216
217			class GlobTransform(GlobTransformBase):
218			jumps = GlobTransformBase.jumps.copy()
219			jumps.update({
220			'start': {
221			'': 'text',
222			'/': 'sep',
223			},
224			})
225			current = 'start'
226
227			def transform_start(self, data, mark, next):
228			if mark == '/':
229			return '^%s' % re_escape(self.base)
230			return re_escape(self.sep)
231
232			def flush(self):
233			return '%s(%s\|$)' % (
234			super(GlobTransformBase, self).flush(),
235			re_escape(self.sep),
236			)
237
238
239			def translate(data, sep=os.sep, base=None):
240			self = GlobTransform(data, sep, base)
241			return ''.join(self)
242

ergoithz / browsepy

Push — 0.5.3 ( c2ca4c...28aba1 )

GlobTransformBase.transform_range_ignore() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like