root/galaxy-central/eggs/PasteScript-1.7.3-py2.6.egg/paste/script/util/string24.py

リビジョン 3, 16.5 KB (コミッタ: kohda, 14 年 前)

Install Unix tools  http://hannonlab.cshl.edu/galaxy_unix_tools/galaxy.html

行番号 
1# (c) 2005 Ian Bicking and contributors; written for Paste (http://pythonpaste.org)
2# Licensed under the MIT license: http://www.opensource.org/licenses/mit-license.php
3"""A collection of string operations (most are no longer used).
4
5Warning: most of the code you see here isn't normally used nowadays.
6Beginning with Python 1.6, many of these functions are implemented as
7methods on the standard string object. They used to be implemented by
8a built-in module called strop, but strop is now obsolete itself.
9
10Public module variables:
11
12whitespace -- a string containing all characters considered whitespace
13lowercase -- a string containing all characters considered lowercase letters
14uppercase -- a string containing all characters considered uppercase letters
15letters -- a string containing all characters considered letters
16digits -- a string containing all characters considered decimal digits
17hexdigits -- a string containing all characters considered hexadecimal digits
18octdigits -- a string containing all characters considered octal digits
19punctuation -- a string containing all characters considered punctuation
20printable -- a string containing all characters considered printable
21
22"""
23
24# Some strings for ctype-style character classification
25whitespace = ' \t\n\r\v\f'
26lowercase = 'abcdefghijklmnopqrstuvwxyz'
27uppercase = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
28letters = lowercase + uppercase
29ascii_lowercase = lowercase
30ascii_uppercase = uppercase
31ascii_letters = ascii_lowercase + ascii_uppercase
32digits = '0123456789'
33hexdigits = digits + 'abcdef' + 'ABCDEF'
34octdigits = '01234567'
35punctuation = """!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""
36printable = digits + letters + punctuation + whitespace
37
38# Case conversion helpers
39# Use str to convert Unicode literal in case of -U
40# Note that Cookie.py bogusly uses _idmap :(
41l = map(chr, xrange(256))
42_idmap = str('').join(l)
43del l
44
45# Functions which aren't available as string methods.
46
47# Capitalize the words in a string, e.g. " aBc  dEf " -> "Abc Def".
48# See also regsub.capwords().
49def capwords(s, sep=None):
50    """capwords(s, [sep]) -> string
51
52    Split the argument into words using split, capitalize each
53    word using capitalize, and join the capitalized words using
54    join. Note that this replaces runs of whitespace characters by
55    a single space.
56
57    """
58    return (sep or ' ').join([x.capitalize() for x in s.split(sep)])
59
60
61# Construct a translation string
62_idmapL = None
63def maketrans(fromstr, tostr):
64    """maketrans(frm, to) -> string
65
66    Return a translation table (a string of 256 bytes long)
67    suitable for use in string.translate.  The strings frm and to
68    must be of the same length.
69
70    """
71    if len(fromstr) != len(tostr):
72        raise ValueError, "maketrans arguments must have same length"
73    global _idmapL
74    if not _idmapL:
75        _idmapL = map(None, _idmap)
76    L = _idmapL[:]
77    fromstr = map(ord, fromstr)
78    for i in range(len(fromstr)):
79        L[fromstr[i]] = tostr[i]
80    return ''.join(L)
81
82
83
84####################################################################
85import re as _re
86
87class _multimap:
88    """Helper class for combining multiple mappings.
89
90    Used by .{safe_,}substitute() to combine the mapping and keyword
91    arguments.
92    """
93    def __init__(self, primary, secondary):
94        self._primary = primary
95        self._secondary = secondary
96
97    def __getitem__(self, key):
98        try:
99            return self._primary[key]
100        except KeyError:
101            return self._secondary[key]
102
103
104class _TemplateMetaclass(type):
105    pattern = r"""
106    %(delim)s(?:
107      (?P<escaped>%(delim)s) |   # Escape sequence of two delimiters
108      (?P<named>%(id)s)      |   # delimiter and a Python identifier
109      {(?P<braced>%(id)s)}   |   # delimiter and a braced identifier
110      (?P<invalid>)              # Other ill-formed delimiter exprs
111    )
112    """
113
114    def __init__(cls, name, bases, dct):
115        super(_TemplateMetaclass, cls).__init__(name, bases, dct)
116        if 'pattern' in dct:
117            pattern = cls.pattern
118        else:
119            pattern = _TemplateMetaclass.pattern % {
120                'delim' : _re.escape(cls.delimiter),
121                'id'    : cls.idpattern,
122                }
123        cls.pattern = _re.compile(pattern, _re.IGNORECASE | _re.VERBOSE)
124
125
126class Template:
127    """A string class for supporting $-substitutions."""
128    __metaclass__ = _TemplateMetaclass
129
130    delimiter = '$'
131    idpattern = r'[_a-z][_a-z0-9]*'
132
133    def __init__(self, template):
134        self.template = template
135
136    # Search for $$, $identifier, ${identifier}, and any bare $'s
137
138    def _invalid(self, mo):
139        i = mo.start('invalid')
140        lines = self.template[:i].splitlines(True)
141        if not lines:
142            colno = 1
143            lineno = 1
144        else:
145            colno = i - len(''.join(lines[:-1]))
146            lineno = len(lines)
147        raise ValueError('Invalid placeholder in string: line %d, col %d' %
148                         (lineno, colno))
149
150    def substitute(self, *args, **kws):
151        if len(args) > 1:
152            raise TypeError('Too many positional arguments')
153        if not args:
154            mapping = kws
155        elif kws:
156            mapping = _multimap(kws, args[0])
157        else:
158            mapping = args[0]
159        # Helper function for .sub()
160        def convert(mo):
161            # Check the most common path first.
162            named = mo.group('named') or mo.group('braced')
163            if named is not None:
164                val = mapping[named]
165                # We use this idiom instead of str() because the latter will
166                # fail if val is a Unicode containing non-ASCII characters.
167                return '%s' % val
168            if mo.group('escaped') is not None:
169                return self.delimiter
170            if mo.group('invalid') is not None:
171                self._invalid(mo)
172            raise ValueError('Unrecognized named group in pattern',
173                             self.pattern)
174        return self.pattern.sub(convert, self.template)
175
176    def safe_substitute(self, *args, **kws):
177        if len(args) > 1:
178            raise TypeError('Too many positional arguments')
179        if not args:
180            mapping = kws
181        elif kws:
182            mapping = _multimap(kws, args[0])
183        else:
184            mapping = args[0]
185        # Helper function for .sub()
186        def convert(mo):
187            named = mo.group('named')
188            if named is not None:
189                try:
190                    # We use this idiom instead of str() because the latter
191                    # will fail if val is a Unicode containing non-ASCII
192                    return '%s' % mapping[named]
193                except KeyError:
194                    return self.delimiter + named
195            braced = mo.group('braced')
196            if braced is not None:
197                try:
198                    return '%s' % mapping[braced]
199                except KeyError:
200                    return self.delimiter + '{' + braced + '}'
201            if mo.group('escaped') is not None:
202                return self.delimiter
203            if mo.group('invalid') is not None:
204                return self.delimiter
205            raise ValueError('Unrecognized named group in pattern',
206                             self.pattern)
207        return self.pattern.sub(convert, self.template)
208
209
210
211####################################################################
212# NOTE: Everything below here is deprecated.  Use string methods instead.
213# This stuff will go away in Python 3.0.
214
215# Backward compatible names for exceptions
216index_error = ValueError
217atoi_error = ValueError
218atof_error = ValueError
219atol_error = ValueError
220
221# convert UPPER CASE letters to lower case
222def lower(s):
223    """lower(s) -> string
224
225    Return a copy of the string s converted to lowercase.
226
227    """
228    return s.lower()
229
230# Convert lower case letters to UPPER CASE
231def upper(s):
232    """upper(s) -> string
233
234    Return a copy of the string s converted to uppercase.
235
236    """
237    return s.upper()
238
239# Swap lower case letters and UPPER CASE
240def swapcase(s):
241    """swapcase(s) -> string
242
243    Return a copy of the string s with upper case characters
244    converted to lowercase and vice versa.
245
246    """
247    return s.swapcase()
248
249# Strip leading and trailing tabs and spaces
250def strip(s, chars=None):
251    """strip(s [,chars]) -> string
252
253    Return a copy of the string s with leading and trailing
254    whitespace removed.
255    If chars is given and not None, remove characters in chars instead.
256    If chars is unicode, S will be converted to unicode before stripping.
257
258    """
259    return s.strip(chars)
260
261# Strip leading tabs and spaces
262def lstrip(s, chars=None):
263    """lstrip(s [,chars]) -> string
264
265    Return a copy of the string s with leading whitespace removed.
266    If chars is given and not None, remove characters in chars instead.
267
268    """
269    return s.lstrip(chars)
270
271# Strip trailing tabs and spaces
272def rstrip(s, chars=None):
273    """rstrip(s [,chars]) -> string
274
275    Return a copy of the string s with trailing whitespace removed.
276    If chars is given and not None, remove characters in chars instead.
277
278    """
279    return s.rstrip(chars)
280
281
282# Split a string into a list of space/tab-separated words
283def split(s, sep=None, maxsplit=-1):
284    """split(s [,sep [,maxsplit]]) -> list of strings
285
286    Return a list of the words in the string s, using sep as the
287    delimiter string.  If maxsplit is given, splits at no more than
288    maxsplit places (resulting in at most maxsplit+1 words).  If sep
289    is not specified or is None, any whitespace string is a separator.
290
291    (split and splitfields are synonymous)
292
293    """
294    return s.split(sep, maxsplit)
295splitfields = split
296
297# Split a string into a list of space/tab-separated words
298def rsplit(s, sep=None, maxsplit=-1):
299    """rsplit(s [,sep [,maxsplit]]) -> list of strings
300
301    Return a list of the words in the string s, using sep as the
302    delimiter string, starting at the end of the string and working
303    to the front.  If maxsplit is given, at most maxsplit splits are
304    done. If sep is not specified or is None, any whitespace string
305    is a separator.
306    """
307    return s.rsplit(sep, maxsplit)
308
309# Join fields with optional separator
310def join(words, sep = ' '):
311    """join(list [,sep]) -> string
312
313    Return a string composed of the words in list, with
314    intervening occurrences of sep.  The default separator is a
315    single space.
316
317    (joinfields and join are synonymous)
318
319    """
320    return sep.join(words)
321joinfields = join
322
323# Find substring, raise exception if not found
324def index(s, *args):
325    """index(s, sub [,start [,end]]) -> int
326
327    Like find but raises ValueError when the substring is not found.
328
329    """
330    return s.index(*args)
331
332# Find last substring, raise exception if not found
333def rindex(s, *args):
334    """rindex(s, sub [,start [,end]]) -> int
335
336    Like rfind but raises ValueError when the substring is not found.
337
338    """
339    return s.rindex(*args)
340
341# Count non-overlapping occurrences of substring
342def count(s, *args):
343    """count(s, sub[, start[,end]]) -> int
344
345    Return the number of occurrences of substring sub in string
346    s[start:end].  Optional arguments start and end are
347    interpreted as in slice notation.
348
349    """
350    return s.count(*args)
351
352# Find substring, return -1 if not found
353def find(s, *args):
354    """find(s, sub [,start [,end]]) -> in
355
356    Return the lowest index in s where substring sub is found,
357    such that sub is contained within s[start,end].  Optional
358    arguments start and end are interpreted as in slice notation.
359
360    Return -1 on failure.
361
362    """
363    return s.find(*args)
364
365# Find last substring, return -1 if not found
366def rfind(s, *args):
367    """rfind(s, sub [,start [,end]]) -> int
368
369    Return the highest index in s where substring sub is found,
370    such that sub is contained within s[start,end].  Optional
371    arguments start and end are interpreted as in slice notation.
372
373    Return -1 on failure.
374
375    """
376    return s.rfind(*args)
377
378# for a bit of speed
379_float = float
380_int = int
381_long = long
382
383# Convert string to float
384def atof(s):
385    """atof(s) -> float
386
387    Return the floating point number represented by the string s.
388
389    """
390    return _float(s)
391
392
393# Convert string to integer
394def atoi(s , base=10):
395    """atoi(s [,base]) -> int
396
397    Return the integer represented by the string s in the given
398    base, which defaults to 10.  The string s must consist of one
399    or more digits, possibly preceded by a sign.  If base is 0, it
400    is chosen from the leading characters of s, 0 for octal, 0x or
401    0X for hexadecimal.  If base is 16, a preceding 0x or 0X is
402    accepted.
403
404    """
405    return _int(s, base)
406
407
408# Convert string to long integer
409def atol(s, base=10):
410    """atol(s [,base]) -> long
411
412    Return the long integer represented by the string s in the
413    given base, which defaults to 10.  The string s must consist
414    of one or more digits, possibly preceded by a sign.  If base
415    is 0, it is chosen from the leading characters of s, 0 for
416    octal, 0x or 0X for hexadecimal.  If base is 16, a preceding
417    0x or 0X is accepted.  A trailing L or l is not accepted,
418    unless base is 0.
419
420    """
421    return _long(s, base)
422
423
424# Left-justify a string
425def ljust(s, width, *args):
426    """ljust(s, width[, fillchar]) -> string
427
428    Return a left-justified version of s, in a field of the
429    specified width, padded with spaces as needed.  The string is
430    never truncated.  If specified the fillchar is used instead of spaces.
431
432    """
433    return s.ljust(width, *args)
434
435# Right-justify a string
436def rjust(s, width, *args):
437    """rjust(s, width[, fillchar]) -> string
438
439    Return a right-justified version of s, in a field of the
440    specified width, padded with spaces as needed.  The string is
441    never truncated.  If specified the fillchar is used instead of spaces.
442
443    """
444    return s.rjust(width, *args)
445
446# Center a string
447def center(s, width, *args):
448    """center(s, width[, fillchar]) -> string
449
450    Return a center version of s, in a field of the specified
451    width. padded with spaces as needed.  The string is never
452    truncated.  If specified the fillchar is used instead of spaces.
453
454    """
455    return s.center(width, *args)
456
457# Zero-fill a number, e.g., (12, 3) --> '012' and (-3, 3) --> '-03'
458# Decadent feature: the argument may be a string or a number
459# (Use of this is deprecated; it should be a string as with ljust c.s.)
460def zfill(x, width):
461    """zfill(x, width) -> string
462
463    Pad a numeric string x with zeros on the left, to fill a field
464    of the specified width.  The string x is never truncated.
465
466    """
467    if not isinstance(x, basestring):
468        x = repr(x)
469    return x.zfill(width)
470
471# Expand tabs in a string.
472# Doesn't take non-printing chars into account, but does understand \n.
473def expandtabs(s, tabsize=8):
474    """expandtabs(s [,tabsize]) -> string
475
476    Return a copy of the string s with all tab characters replaced
477    by the appropriate number of spaces, depending on the current
478    column, and the tabsize (default 8).
479
480    """
481    return s.expandtabs(tabsize)
482
483# Character translation through look-up table.
484def translate(s, table, deletions=""):
485    """translate(s,table [,deletions]) -> string
486
487    Return a copy of the string s, where all characters occurring
488    in the optional argument deletions are removed, and the
489    remaining characters have been mapped through the given
490    translation table, which must be a string of length 256.  The
491    deletions argument is not allowed for Unicode strings.
492
493    """
494    if deletions:
495        return s.translate(table, deletions)
496    else:
497        # Add s[:0] so that if s is Unicode and table is an 8-bit string,
498        # table is converted to Unicode.  This means that table *cannot*
499        # be a dictionary -- for that feature, use u.translate() directly.
500        return s.translate(table + s[:0])
501
502# Capitalize a string, e.g. "aBc  dEf" -> "Abc  def".
503def capitalize(s):
504    """capitalize(s) -> string
505
506    Return a copy of the string s with only its first character
507    capitalized.
508
509    """
510    return s.capitalize()
511
512# Substring replacement (global)
513def replace(s, old, new, maxsplit=-1):
514    """replace (str, old, new[, maxsplit]) -> string
515
516    Return a copy of string str with all occurrences of substring
517    old replaced by new. If the optional argument maxsplit is
518    given, only the first maxsplit occurrences are replaced.
519
520    """
521    return s.replace(old, new, maxsplit)
522
523
524# Try importing optional built-in module "strop" -- if it exists,
525# it redefines some string operations that are 100-1000 times faster.
526# It also defines values for whitespace, lowercase and uppercase
527# that match <ctype.h>'s definitions.
528
529try:
530    from strop import maketrans, lowercase, uppercase, whitespace
531    letters = lowercase + uppercase
532except ImportError:
533    pass                                          # Use the original versions
Note: リポジトリブラウザについてのヘルプは TracBrowser を参照してください。