summaryrefslogtreecommitdiffstats
path: root/Lib/string.py
blob: 8c7d102b46409befa8dbade500889571c48d9aab (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
# module 'string' -- A collection of string operations

# Warning: most of the code you see here isn't normally used nowadays.
# At the end of this file most functions are replaced by built-in
# functions imported from built-in module "strop".

# Some strings for ctype-style character classification
whitespace = ' \t\n'
lowercase = 'abcdefghijklmnopqrstuvwxyz'
uppercase = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
letters = lowercase + uppercase
digits = '0123456789'
hexdigits = digits + 'abcdef' + 'ABCDEF'
octdigits = '01234567'

# Case conversion helpers
_idmap = ''
for i in range(256): _idmap = _idmap + chr(i)
_lower = _idmap[:ord('A')] + lowercase + _idmap[ord('Z')+1:]
_upper = _idmap[:ord('a')] + uppercase + _idmap[ord('z')+1:]
_swapcase = _upper[:ord('A')] + lowercase + _upper[ord('Z')+1:]
del i

# convert UPPER CASE letters to lower case
def lower(s):
	res = ''
	for c in s:
		res = res + _lower[ord(c)]
	return res

# Convert lower case letters to UPPER CASE
def upper(s):
	res = ''
	for c in s:
		res = res + _upper[ord(c)]
	return res

# Swap lower case letters and UPPER CASE
def swapcase(s):
	res = ''
	for c in s:
		res = res + _swapcase[ord(c)]
	return res

# Strip leading and trailing tabs and spaces
def strip(s):
	i, j = 0, len(s)
	while i < j and s[i] in whitespace: i = i+1
	while i < j and s[j-1] in whitespace: j = j-1
	return s[i:j]

# Split a string into a list of space/tab-separated words
# NB: split(s) is NOT the same as splitfields(s, ' ')!
def split(s):
	res = []
	i, n = 0, len(s)
	while i < n:
		while i < n and s[i] in whitespace: i = i+1
		if i == n: break
		j = i
		while j < n and s[j] not in whitespace: j = j+1
		res.append(s[i:j])
		i = j
	return res

# Split a list into fields separated by a given string
# NB: splitfields(s, ' ') is NOT the same as split(s)!
# splitfields(s, '') returns [s] (in analogy with split() in nawk)
def splitfields(s, sep):
	res = []
	nsep = len(sep)
	if nsep == 0:
		return [s]
	ns = len(s)
	i = j = 0
	while j+nsep <= ns:
		if s[j:j+nsep] == sep:
			res.append(s[i:j])
			i = j = j + nsep
		else:
			j = j + 1
	res.append(s[i:])
	return res

# Join words with spaces between them
def join(words):
	return joinfields(words, ' ')

# Join fields with separator
def joinfields(words, sep):
	res = ''
	for w in words:
		res = res + (sep + w)
	return res[len(sep):]

# Find substring, raise exception if not found
index_error = 'substring not found in string.index'
def index(s, sub, *args):
	if args:
		if len(args) > 1:
			raise TypeError, 'string.index(): too many args'
		i = args[0]
	else:
		i = 0
	n = len(sub)
	m = len(s) + 1 - n
	while i < m:
		if sub == s[i:i+n]: return i
		i = i+1
	raise index_error, (s, sub) + args

# Find substring, return -1 if not found
def find(*args):
	try:
		return apply(index, args)
	except index_error:
		return -1

# Convert string to integer
atoi_error = 'non-numeric argument to string.atoi'
def atoi(str):
	sign = ''
	s = str
	if s and s[0] in '+-':
		sign = s[0]
		s = s[1:]
	if not s: raise atoi_error, str
	while s[0] == '0' and len(s) > 1: s = s[1:]
	for c in s:
		if c not in digits: raise atoi_error, str
	return eval(sign + s)

# Left-justify a string
def ljust(s, width):
	n = width - len(s)
	if n <= 0: return s
	return s + ' '*n

# Right-justify a string
def rjust(s, width):
	n = width - len(s)
	if n <= 0: return s
	return ' '*n + s

# Center a string
def center(s, width):
	n = width - len(s)
	if n <= 0: return s
	half = n/2
	if n%2 and width%2:
		# This ensures that center(center(s, i), j) = center(s, j)
		half = half+1
	return ' '*half +  s + ' '*(n-half)

# Zero-fill a number, e.g., (12, 3) --> '012' and (-3, 3) --> '-03'
# Decadent feature: the argument may be a string or a number
# (Use of this is deprecated; it should be a string as with ljust c.s.)
def zfill(x, width):
	if type(x) == type(''): s = x
	else: s = `x`
	n = len(s)
	if n >= width: return s
	sign = ''
	if s[0] in ('-', '+'):
		sign, s = s[0], s[1:]
	return sign + '0'*(width-n) + s

# Expand tabs in a string.
# Doesn't take non-printing chars into account, but does understand \n.
def expandtabs(s, tabsize):
	res = line = ''
	for c in s:
		if c == '\t':
			c = ' '*(tabsize - len(line)%tabsize)
		line = line + c
		if c == '\n':
			res = res + line
			line = ''
	return res + line


# Try importing optional built-in module "strop" -- if it exists,
# it redefines some string operations that are 100-1000 times faster.
# The manipulation with index_error is needed for compatibility.

try:
	from strop import *
	from strop import index
	index_error = ValueError
except ImportError:
	pass # Use the original, slow versions