annotate roundup/anypy/strings.py @ 5505:2ce41b8dffaf

compared sorted lists as order can be random
author Christof Meerwald <cmeerw@cmeerw.org>
date Thu, 16 Aug 2018 21:14:07 +0100
parents 6b0c542642be
children bb7865241f8a
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
5416
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
1 # Roundup represents text internally using the native Python str type.
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
2 # In Python 3, these are Unicode strings. In Python 2, these are
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
3 # encoded using UTF-8, and the Python 2 unicode type is only used in a
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
4 # few places, generally for interacting with external modules
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
5 # requiring that type to be used.
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
6
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
7 import sys
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
8 _py3 = sys.version_info[0] > 2
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
9
5418
55f09ca366c4 Python 3 preparation: StringIO.
Joseph Myers <jsm@polyomino.org.uk>
parents: 5417
diff changeset
10 import io
55f09ca366c4 Python 3 preparation: StringIO.
Joseph Myers <jsm@polyomino.org.uk>
parents: 5417
diff changeset
11 if _py3:
55f09ca366c4 Python 3 preparation: StringIO.
Joseph Myers <jsm@polyomino.org.uk>
parents: 5417
diff changeset
12 StringIO = io.StringIO
55f09ca366c4 Python 3 preparation: StringIO.
Joseph Myers <jsm@polyomino.org.uk>
parents: 5417
diff changeset
13 else:
55f09ca366c4 Python 3 preparation: StringIO.
Joseph Myers <jsm@polyomino.org.uk>
parents: 5417
diff changeset
14 StringIO = io.BytesIO
55f09ca366c4 Python 3 preparation: StringIO.
Joseph Myers <jsm@polyomino.org.uk>
parents: 5417
diff changeset
15
5416
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
16 def b2s(b):
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
17 """Convert a UTF-8 encoded bytes object to the internal string format."""
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
18 if _py3:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
19 return b.decode('utf-8')
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
20 else:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
21 return b
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
22
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
23 def s2b(s):
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
24 """Convert a string object to UTF-8 encoded bytes."""
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
25 if _py3:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
26 return s.encode('utf-8')
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
27 else:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
28 return s
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
29
5492
6b0c542642be blobfiles now always stores/returns bytes
Christof Meerwald <cmeerw@cmeerw.org>
parents: 5418
diff changeset
30 def bs2b(s):
6b0c542642be blobfiles now always stores/returns bytes
Christof Meerwald <cmeerw@cmeerw.org>
parents: 5418
diff changeset
31 """Convert a string object or UTF-8 encoded bytes to UTF-8 encoded bytes."""
6b0c542642be blobfiles now always stores/returns bytes
Christof Meerwald <cmeerw@cmeerw.org>
parents: 5418
diff changeset
32 if _py3:
6b0c542642be blobfiles now always stores/returns bytes
Christof Meerwald <cmeerw@cmeerw.org>
parents: 5418
diff changeset
33 if isinstance(s, bytes):
6b0c542642be blobfiles now always stores/returns bytes
Christof Meerwald <cmeerw@cmeerw.org>
parents: 5418
diff changeset
34 return s
6b0c542642be blobfiles now always stores/returns bytes
Christof Meerwald <cmeerw@cmeerw.org>
parents: 5418
diff changeset
35 else:
6b0c542642be blobfiles now always stores/returns bytes
Christof Meerwald <cmeerw@cmeerw.org>
parents: 5418
diff changeset
36 return s.encode('utf-8')
6b0c542642be blobfiles now always stores/returns bytes
Christof Meerwald <cmeerw@cmeerw.org>
parents: 5418
diff changeset
37 else:
6b0c542642be blobfiles now always stores/returns bytes
Christof Meerwald <cmeerw@cmeerw.org>
parents: 5418
diff changeset
38 return s
6b0c542642be blobfiles now always stores/returns bytes
Christof Meerwald <cmeerw@cmeerw.org>
parents: 5418
diff changeset
39
5416
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
40 def s2u(s, errors='strict'):
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
41 """Convert a string object to a Unicode string."""
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
42 if _py3:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
43 return s
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
44 else:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
45 return unicode(s, 'utf-8', errors)
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
46
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
47 def u2s(u):
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
48 """Convert a Unicode string to the internal string format."""
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
49 if _py3:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
50 return u
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
51 else:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
52 return u.encode('utf-8')
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
53
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
54 def us2u(s, errors='strict'):
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
55 """Convert a string or Unicode string to a Unicode string."""
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
56 if _py3:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
57 return s
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
58 else:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
59 if isinstance(s, unicode):
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
60 return s
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
61 else:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
62 return unicode(s, 'utf-8', errors)
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
63
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
64 def us2s(u):
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
65 """Convert a string or Unicode string to the internal string format."""
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
66 if _py3:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
67 return u
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
68 else:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
69 if isinstance(u, unicode):
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
70 return u.encode('utf-8')
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
71 else:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
72 return u
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
73
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
74 def uany2s(u):
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
75 """Convert a Unicode string or other object to the internal string format.
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
76
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
77 Objects that are not Unicode strings are passed to str()."""
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
78 if _py3:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
79 return str(u)
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
80 else:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
81 if isinstance(u, unicode):
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
82 return u.encode('utf-8')
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
83 else:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
84 return str(u)
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
85
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
86 def is_us(s):
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
87 """Return whether an object is a string or Unicode string."""
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
88 if _py3:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
89 return isinstance(s, str)
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
90 else:
56c9bcdea47f Python 3 preparation: unicode.
Joseph Myers <jsm@polyomino.org.uk>
parents:
diff changeset
91 return isinstance(s, str) or isinstance(s, unicode)
5417
c749d6795bc2 Python 3 preparation: unichr.
Joseph Myers <jsm@polyomino.org.uk>
parents: 5416
diff changeset
92
c749d6795bc2 Python 3 preparation: unichr.
Joseph Myers <jsm@polyomino.org.uk>
parents: 5416
diff changeset
93 def uchr(c):
c749d6795bc2 Python 3 preparation: unichr.
Joseph Myers <jsm@polyomino.org.uk>
parents: 5416
diff changeset
94 """Return the Unicode string containing the given character."""
c749d6795bc2 Python 3 preparation: unichr.
Joseph Myers <jsm@polyomino.org.uk>
parents: 5416
diff changeset
95 if _py3:
c749d6795bc2 Python 3 preparation: unichr.
Joseph Myers <jsm@polyomino.org.uk>
parents: 5416
diff changeset
96 return chr(c)
c749d6795bc2 Python 3 preparation: unichr.
Joseph Myers <jsm@polyomino.org.uk>
parents: 5416
diff changeset
97 else:
c749d6795bc2 Python 3 preparation: unichr.
Joseph Myers <jsm@polyomino.org.uk>
parents: 5416
diff changeset
98 return unichr(c)

Roundup Issue Tracker: http://roundup-tracker.org/