summaryrefslogtreecommitdiff
path: root/Lib/string.py
blob: 141204810504872ffa8198bcff2b6670bba92f63 (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
# module 'string' -- A collection of string operations

# XXX Some of these operations are incredibly slow and should be built in

# 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
_caseswap = {}
for i in range(26):
	_caseswap[lowercase[i]] = uppercase[i]
	_caseswap[uppercase[i]] = lowercase[i]
del i

# convert UPPER CASE letters to lower case
def lower(s):
	res = ''
	for c in s:
		if 'A' <= c <= 'Z': c = _caseswap[c]
		res = res + c
	return res

# Convert lower case letters to UPPER CASE
def upper(s):
	res = ''
	for c in s:
		if 'a' <= c <= 'z': c = _caseswap[c]
		res = res + c
	return res

# Swap lower case letters and UPPER CASE
def swapcase(s):
	res = ''
	for c in s:
		if 'a' <= c <= 'z' or 'A' <= c <= 'Z': c = _caseswap[c]
		res = res + 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)!
def splitfields(s, sep):
	res = []
	ns = len(s)
	nsep = len(sep)
	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):
	res = ''
	for w in words:
		res = res + (' ' + w)
	return res[1:]

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

# Find substring
index_error = 'substring not found in string.index'
def index(s, sub):
	n = len(sub)
	for i in range(len(s) + 1 - n):
		if sub == s[i:i+n]: return i
	raise index_error, (s, sub)

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

# 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