string.py revision 5aff7752eb28c6ddaa68738ee77e1947b72e1a58
1"""A collection of string operations (most are no longer used in Python 1.6). 2 3Warning: most of the code you see here isn't normally used nowadays. With 4Python 1.6, many of these functions are implemented as methods on the 5standard string object. They used to be implemented by a built-in module 6called strop, but strop is now obsolete itself. 7 8Public module variables: 9 10whitespace -- a string containing all characters considered whitespace 11lowercase -- a string containing all characters considered lowercase letters 12uppercase -- a string containing all characters considered uppercase letters 13letters -- a string containing all characters considered letters 14digits -- a string containing all characters considered decimal digits 15hexdigits -- a string containing all characters considered hexadecimal digits 16octdigits -- a string containing all characters considered octal digits 17punctuation -- a string containing all characters considered punctuation 18printable -- a string containing all characters considered printable 19 20""" 21 22# Some strings for ctype-style character classification 23whitespace = ' \t\n\r\v\f' 24lowercase = 'abcdefghijklmnopqrstuvwxyz' 25uppercase = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 26letters = lowercase + uppercase 27digits = '0123456789' 28hexdigits = digits + 'abcdef' + 'ABCDEF' 29octdigits = '01234567' 30punctuation = """!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~""" 31printable = digits + letters + punctuation + whitespace 32 33# Case conversion helpers 34_idmap = '' 35for i in range(256): _idmap = _idmap + chr(i) 36del i 37 38# Backward compatible names for exceptions 39index_error = ValueError 40atoi_error = ValueError 41atof_error = ValueError 42atol_error = ValueError 43 44# convert UPPER CASE letters to lower case 45def lower(s): 46 """lower(s) -> string 47 48 Return a copy of the string s converted to lowercase. 49 50 """ 51 return s.lower() 52 53# Convert lower case letters to UPPER CASE 54def upper(s): 55 """upper(s) -> string 56 57 Return a copy of the string s converted to uppercase. 58 59 """ 60 return s.upper() 61 62# Swap lower case letters and UPPER CASE 63def swapcase(s): 64 """swapcase(s) -> string 65 66 Return a copy of the string s with upper case characters 67 converted to lowercase and vice versa. 68 69 """ 70 return s.swapcase() 71 72# Strip leading and trailing tabs and spaces 73def strip(s): 74 """strip(s) -> string 75 76 Return a copy of the string s with leading and trailing 77 whitespace removed. 78 79 """ 80 return s.strip() 81 82# Strip leading tabs and spaces 83def lstrip(s): 84 """lstrip(s) -> string 85 86 Return a copy of the string s with leading whitespace removed. 87 88 """ 89 return s.lstrip() 90 91# Strip trailing tabs and spaces 92def rstrip(s): 93 """rstrip(s) -> string 94 95 Return a copy of the string s with trailing whitespace 96 removed. 97 98 """ 99 return s.rstrip() 100 101 102# Split a string into a list of space/tab-separated words 103# NB: split(s) is NOT the same as splitfields(s, ' ')! 104def split(s, sep=None, maxsplit=-1): 105 """split(s [,sep [,maxsplit]]) -> list of strings 106 107 Return a list of the words in the string s, using sep as the 108 delimiter string. If maxsplit is given, splits into at most 109 maxsplit words. If sep is not specified, any whitespace string 110 is a separator. 111 112 (split and splitfields are synonymous) 113 114 """ 115 return s.split(sep, maxsplit) 116splitfields = split 117 118# Join fields with optional separator 119def join(words, sep = ' '): 120 """join(list [,sep]) -> string 121 122 Return a string composed of the words in list, with 123 intervening occurrences of sep. The default separator is a 124 single space. 125 126 (joinfields and join are synonymous) 127 128 """ 129 return sep.join(words) 130joinfields = join 131 132# Find substring, raise exception if not found 133def index(s, *args): 134 """index(s, sub [,start [,end]]) -> int 135 136 Like find but raises ValueError when the substring is not found. 137 138 """ 139 return s.index(*args) 140 141# Find last substring, raise exception if not found 142def rindex(s, *args): 143 """rindex(s, sub [,start [,end]]) -> int 144 145 Like rfind but raises ValueError when the substring is not found. 146 147 """ 148 return s.rindex(*args) 149 150# Count non-overlapping occurrences of substring 151def count(s, *args): 152 """count(s, sub[, start[,end]]) -> int 153 154 Return the number of occurrences of substring sub in string 155 s[start:end]. Optional arguments start and end are 156 interpreted as in slice notation. 157 158 """ 159 return s.count(*args) 160 161# Find substring, return -1 if not found 162def find(s, *args): 163 """find(s, sub [,start [,end]]) -> in 164 165 Return the lowest index in s where substring sub is found, 166 such that sub is contained within s[start,end]. Optional 167 arguments start and end are interpreted as in slice notation. 168 169 Return -1 on failure. 170 171 """ 172 return s.find(*args) 173 174# Find last substring, return -1 if not found 175def rfind(s, *args): 176 """rfind(s, sub [,start [,end]]) -> int 177 178 Return the highest index in s where substring sub is found, 179 such that sub is contained within s[start,end]. Optional 180 arguments start and end are interpreted as in slice notation. 181 182 Return -1 on failure. 183 184 """ 185 return s.rfind(*args) 186 187# for a bit of speed 188_float = float 189_int = int 190_long = long 191_StringType = type('') 192 193# Convert string to float 194def atof(s): 195 """atof(s) -> float 196 197 Return the floating point number represented by the string s. 198 199 """ 200 return _float(s) 201 202 203# Convert string to integer 204def atoi(s , base=10): 205 """atoi(s [,base]) -> int 206 207 Return the integer represented by the string s in the given 208 base, which defaults to 10. The string s must consist of one 209 or more digits, possibly preceded by a sign. If base is 0, it 210 is chosen from the leading characters of s, 0 for octal, 0x or 211 0X for hexadecimal. If base is 16, a preceding 0x or 0X is 212 accepted. 213 214 """ 215 return _int(s, base) 216 217 218# Convert string to long integer 219def atol(s, base=10): 220 """atol(s [,base]) -> long 221 222 Return the long integer represented by the string s in the 223 given base, which defaults to 10. The string s must consist 224 of one or more digits, possibly preceded by a sign. If base 225 is 0, it is chosen from the leading characters of s, 0 for 226 octal, 0x or 0X for hexadecimal. If base is 16, a preceding 227 0x or 0X is accepted. A trailing L or l is not accepted, 228 unless base is 0. 229 230 """ 231 return _long(s, base) 232 233 234# Left-justify a string 235def ljust(s, width): 236 """ljust(s, width) -> string 237 238 Return a left-justified version of s, in a field of the 239 specified width, padded with spaces as needed. The string is 240 never truncated. 241 242 """ 243 return s.ljust(width) 244 245# Right-justify a string 246def rjust(s, width): 247 """rjust(s, width) -> string 248 249 Return a right-justified version of s, in a field of the 250 specified width, padded with spaces as needed. The string is 251 never truncated. 252 253 """ 254 return s.rjust(width) 255 256# Center a string 257def center(s, width): 258 """center(s, width) -> string 259 260 Return a center version of s, in a field of the specified 261 width. padded with spaces as needed. The string is never 262 truncated. 263 264 """ 265 return s.center(width) 266 267# Zero-fill a number, e.g., (12, 3) --> '012' and (-3, 3) --> '-03' 268# Decadent feature: the argument may be a string or a number 269# (Use of this is deprecated; it should be a string as with ljust c.s.) 270def zfill(x, width): 271 """zfill(x, width) -> string 272 273 Pad a numeric string x with zeros on the left, to fill a field 274 of the specified width. The string x is never truncated. 275 276 """ 277 if type(x) == type(''): s = x 278 else: s = `x` 279 n = len(s) 280 if n >= width: return s 281 sign = '' 282 if s[0] in ('-', '+'): 283 sign, s = s[0], s[1:] 284 return sign + '0'*(width-n) + s 285 286# Expand tabs in a string. 287# Doesn't take non-printing chars into account, but does understand \n. 288def expandtabs(s, tabsize=8): 289 """expandtabs(s [,tabsize]) -> string 290 291 Return a copy of the string s with all tab characters replaced 292 by the appropriate number of spaces, depending on the current 293 column, and the tabsize (default 8). 294 295 """ 296 return s.expandtabs(tabsize) 297 298# Character translation through look-up table. 299def translate(s, table, deletions=""): 300 """translate(s,table [,deletions]) -> string 301 302 Return a copy of the string s, where all characters occurring 303 in the optional argument deletions are removed, and the 304 remaining characters have been mapped through the given 305 translation table, which must be a string of length 256. The 306 deletions argument is not allowed for Unicode strings. 307 308 """ 309 if deletions: 310 return s.translate(table, deletions) 311 else: 312 # Add s[:0] so that if s is Unicode and table is an 8-bit string, 313 # table is converted to Unicode. This means that table *cannot* 314 # be a dictionary -- for that feature, use u.translate() directly. 315 return s.translate(table + s[:0]) 316 317# Capitalize a string, e.g. "aBc dEf" -> "Abc def". 318def capitalize(s): 319 """capitalize(s) -> string 320 321 Return a copy of the string s with only its first character 322 capitalized. 323 324 """ 325 return s.capitalize() 326 327# Capitalize the words in a string, e.g. " aBc dEf " -> "Abc Def". 328# See also regsub.capwords(). 329def capwords(s, sep=None): 330 """capwords(s, [sep]) -> string 331 332 Split the argument into words using split, capitalize each 333 word using capitalize, and join the capitalized words using 334 join. Note that this replaces runs of whitespace characters by 335 a single space. 336 337 """ 338 return join(map(capitalize, s.split(sep)), sep or ' ') 339 340# Construct a translation string 341_idmapL = None 342def maketrans(fromstr, tostr): 343 """maketrans(frm, to) -> string 344 345 Return a translation table (a string of 256 bytes long) 346 suitable for use in string.translate. The strings frm and to 347 must be of the same length. 348 349 """ 350 if len(fromstr) != len(tostr): 351 raise ValueError, "maketrans arguments must have same length" 352 global _idmapL 353 if not _idmapL: 354 _idmapL = map(None, _idmap) 355 L = _idmapL[:] 356 fromstr = map(ord, fromstr) 357 for i in range(len(fromstr)): 358 L[fromstr[i]] = tostr[i] 359 return joinfields(L, "") 360 361# Substring replacement (global) 362def replace(s, old, new, maxsplit=-1): 363 """replace (str, old, new[, maxsplit]) -> string 364 365 Return a copy of string str with all occurrences of substring 366 old replaced by new. If the optional argument maxsplit is 367 given, only the first maxsplit occurrences are replaced. 368 369 """ 370 return s.replace(old, new, maxsplit) 371 372 373# Try importing optional built-in module "strop" -- if it exists, 374# it redefines some string operations that are 100-1000 times faster. 375# It also defines values for whitespace, lowercase and uppercase 376# that match <ctype.h>'s definitions. 377 378try: 379 from strop import maketrans, lowercase, uppercase, whitespace 380 letters = lowercase + uppercase 381except ImportError: 382 pass # Use the original versions 383