Mirror
/
cpython
mirror of https://github.com/python/cpython
4
1
Fork 0
Code Issues Releases Wiki Activity

Mainlining the string_methods branch. See branch revision log 

messages for specific changes.
This commit is contained in:
Barry Warsaw 1999-10-12 19:54:53 +00:00
parent 75260275fe
commit 226ae6ca12
9 changed files with 1776 additions and 980 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
Include/floatobject.h
View File

@ -50,6 +50,7 @@ extern DL_IMPORT(PyTypeObject) PyFloat_Type;
#define PyFloat_Check(op) ((op)->ob_type == &PyFloat_Type) #define PyFloat_Check(op) ((op)->ob_type == &PyFloat_Type)
extern DL_IMPORT(PyObject *) PyFloat_FromString Py_PROTO((PyObject*, char**));
extern DL_IMPORT(PyObject *) PyFloat_FromDouble Py_PROTO((double)); extern DL_IMPORT(PyObject *) PyFloat_FromDouble Py_PROTO((double));
extern DL_IMPORT(double) PyFloat_AsDouble Py_PROTO((PyObject *)); extern DL_IMPORT(double) PyFloat_AsDouble Py_PROTO((PyObject *));

1
Include/intobject.h
View File

@ -61,6 +61,7 @@ extern DL_IMPORT(PyTypeObject) PyInt_Type;
#define PyInt_Check(op) ((op)->ob_type == &PyInt_Type) #define PyInt_Check(op) ((op)->ob_type == &PyInt_Type)
extern DL_IMPORT(PyObject *) PyInt_FromString Py_PROTO((char*, char**, int));
extern DL_IMPORT(PyObject *) PyInt_FromLong Py_PROTO((long)); extern DL_IMPORT(PyObject *) PyInt_FromLong Py_PROTO((long));
extern DL_IMPORT(long) PyInt_AsLong Py_PROTO((PyObject *)); extern DL_IMPORT(long) PyInt_AsLong Py_PROTO((PyObject *));
extern DL_IMPORT(long) PyInt_GetMax Py_PROTO((void)); extern DL_IMPORT(long) PyInt_GetMax Py_PROTO((void));

335
Lib/string.py
View File

@ -1,8 +1,9 @@
# module 'string' -- A collection of string operations # module 'string' -- A collection of string operations
# Warning: most of the code you see here isn't normally used nowadays. # Warning: most of the code you see here isn't normally used nowadays. With
# At the end of this file most functions are replaced by built-in # Python 1.6, many of these functions are implemented as methods on the
# functions imported from built-in module "strop". # standard string object. They used to be implemented by a built-in module
# called strop, but strop is now obsolete itself.
"""Common string manipulations. """Common string manipulations.
@ -30,9 +31,6 @@ octdigits = '01234567'
# Case conversion helpers # Case conversion helpers
_idmap = '' _idmap = ''
for i in range(256): _idmap = _idmap + chr(i) 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 del i
# Backward compatible names for exceptions # Backward compatible names for exceptions
@ -48,10 +46,7 @@ def lower(s):
Return a copy of the string s converted to lowercase. Return a copy of the string s converted to lowercase.
""" """
res = '' return s.lower()
for c in s:
res = res + _lower[ord(c)]
return res
# Convert lower case letters to UPPER CASE # Convert lower case letters to UPPER CASE
def upper(s): def upper(s):
@ -60,10 +55,7 @@ def upper(s):
Return a copy of the string s converted to uppercase. Return a copy of the string s converted to uppercase.
""" """
res = '' return s.upper()
for c in s:
res = res + _upper[ord(c)]
return res
# Swap lower case letters and UPPER CASE # Swap lower case letters and UPPER CASE
def swapcase(s): def swapcase(s):
@ -73,10 +65,7 @@ def swapcase(s):
converted to lowercase and vice versa. converted to lowercase and vice versa.
""" """
res = '' return s.swapcase()
for c in s:
res = res + _swapcase[ord(c)]
return res
# Strip leading and trailing tabs and spaces # Strip leading and trailing tabs and spaces
def strip(s): def strip(s):
@ -86,10 +75,7 @@ def strip(s):
whitespace removed. whitespace removed.
""" """
i, j = 0, len(s) return s.strip()
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]
# Strip leading tabs and spaces # Strip leading tabs and spaces
def lstrip(s): def lstrip(s):
@ -98,9 +84,7 @@ def lstrip(s):
Return a copy of the string s with leading whitespace removed. Return a copy of the string s with leading whitespace removed.
""" """
i, j = 0, len(s) return s.lstrip()
while i < j and s[i] in whitespace: i = i+1
return s[i:j]
# Strip trailing tabs and spaces # Strip trailing tabs and spaces
def rstrip(s): def rstrip(s):
@ -110,9 +94,7 @@ def rstrip(s):
removed. removed.
""" """
i, j = 0, len(s) return s.rstrip()
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 # Split a string into a list of space/tab-separated words
@ -128,74 +110,12 @@ def split(s, sep=None, maxsplit=0):
(split and splitfields are synonymous) (split and splitfields are synonymous)
""" """
if sep is not None: return splitfields(s, sep, maxsplit) return s.split(sep, maxsplit)
res = [] splitfields = split
i, n = 0, len(s)
if maxsplit <= 0: maxsplit = n
count = 0
while i < n:
while i < n and s[i] in whitespace: i = i+1
if i == n: break
if count >= maxsplit:
res.append(s[i:])
break
j = i
while j < n and s[j] not in whitespace: j = j+1
count = count + 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=None, maxsplit=0):
"""splitfields(str [,sep [,maxsplit]]) -> list of strings
Return a list of the words in the string s, using sep as the
delimiter string. If maxsplit is nonzero, splits into at most
maxsplit words If sep is not specified, any whitespace string
is a separator. Maxsplit defaults to 0.
(split and splitfields are synonymous)
"""
if sep is None: return split(s, None, maxsplit)
res = []
nsep = len(sep)
if nsep == 0:
return [s]
ns = len(s)
if maxsplit <= 0: maxsplit = ns
i = j = 0
count = 0
while j+nsep <= ns:
if s[j:j+nsep] == sep:
count = count + 1
res.append(s[i:j])
i = j = j + nsep
if count >= maxsplit: break
else:
j = j + 1
res.append(s[i:])
return res
# Join words with spaces between them
def join(words, sep = ' '):
"""join(list [,sep]) -> string
Return a string composed of the words in list, with
intervening occurences of sep. Sep defaults to a single
space.
(joinfields and join are synonymous)
"""
return joinfields(words, sep)
# Join fields with optional separator # Join fields with optional separator
def joinfields(words, sep = ' '): def join(words, sep = ' '):
"""joinfields(list [,sep]) -> string """join(list [,sep]) -> string
Return a string composed of the words in list, with Return a string composed of the words in list, with
intervening occurences of sep. The default separator is a intervening occurences of sep. The default separator is a
@ -204,47 +124,32 @@ def joinfields(words, sep = ' '):
(joinfields and join are synonymous) (joinfields and join are synonymous)
""" """
res = '' return sep.join(words)
for w in words: joinfields = join
res = res + (sep + w)
return res[len(sep):] # for a little bit of speed
_apply = apply
# Find substring, raise exception if not found # Find substring, raise exception if not found
def index(s, sub, i = 0, last=None): def index(s, *args):
"""index(s, sub [,start [,end]]) -> int """index(s, sub [,start [,end]]) -> int
Return the lowest index in s where substring sub is found, Like find but raises ValueError when the substring is not found.
such that sub is contained within s[start,end]. Optional
arguments start and end are interpreted as in slice notation.
Raise ValueError if not found.
""" """
if last is None: last = len(s) return _apply(s.index, args)
res = find(s, sub, i, last)
if res < 0:
raise ValueError, 'substring not found in string.index'
return res
# Find last substring, raise exception if not found # Find last substring, raise exception if not found
def rindex(s, sub, i = 0, last=None): def rindex(s, *args):
"""rindex(s, sub [,start [,end]]) -> int """rindex(s, sub [,start [,end]]) -> int
Return the highest index in s where substring sub is found, Like rfind but raises ValueError when the substring is not found.
such that sub is contained within s[start,end]. Optional
arguments start and end are interpreted as in slice notation.
Raise ValueError if not found.
""" """
if last is None: last = len(s) return _apply(s.rindex, args)
res = rfind(s, sub, i, last)
if res < 0:
raise ValueError, 'substring not found in string.index'
return res
# Count non-overlapping occurrences of substring # Count non-overlapping occurrences of substring
def count(s, sub, i = 0, last=None): def count(s, *args):
"""count(s, sub[, start[,end]]) -> int """count(s, sub[, start[,end]]) -> int
Return the number of occurrences of substring sub in string Return the number of occurrences of substring sub in string
@ -252,28 +157,10 @@ def count(s, sub, i = 0, last=None):
interpreted as in slice notation. interpreted as in slice notation.
""" """
Slen = len(s) # cache this value, for speed return _apply(s.count, args)
if last is None:
last = Slen
elif last < 0:
last = max(0, last + Slen)
elif last > Slen:
last = Slen
if i < 0: i = max(0, i + Slen)
n = len(sub)
m = last + 1 - n
if n == 0: return m-i
r = 0
while i < m:
if sub == s[i:i+n]:
r = r+1
i = i+n
else:
i = i+1
return r
# Find substring, return -1 if not found # Find substring, return -1 if not found
def find(s, sub, i = 0, last=None): def find(s, *args):
"""find(s, sub [,start [,end]]) -> in """find(s, sub [,start [,end]]) -> in
Return the lowest index in s where substring sub is found, Return the lowest index in s where substring sub is found,
@ -283,23 +170,10 @@ def find(s, sub, i = 0, last=None):
Return -1 on failure. Return -1 on failure.
""" """
Slen = len(s) # cache this value, for speed return _apply(s.find, args)
if last is None:
last = Slen
elif last < 0:
last = max(0, last + Slen)
elif last > Slen:
last = Slen
if i < 0: i = max(0, i + Slen)
n = len(sub)
m = last + 1 - n
while i < m:
if sub == s[i:i+n]: return i
i = i+1
return -1
# Find last substring, return -1 if not found # Find last substring, return -1 if not found
def rfind(s, sub, i = 0, last=None): def rfind(s, *args):
"""rfind(s, sub [,start [,end]]) -> int """rfind(s, sub [,start [,end]]) -> int
Return the highest index in s where substring sub is found, Return the highest index in s where substring sub is found,
@ -309,59 +183,29 @@ def rfind(s, sub, i = 0, last=None):
Return -1 on failure. Return -1 on failure.
""" """
Slen = len(s) # cache this value, for speed return _apply(s.rfind, args)
if last is None:
last = Slen
elif last < 0:
last = max(0, last + Slen)
elif last > Slen:
last = Slen
if i < 0: i = max(0, i + Slen)
n = len(sub)
m = last + 1 - n
r = -1
while i < m:
if sub == s[i:i+n]: r = i
i = i+1
return r
# "Safe" environment for eval() # for a bit of speed
_safe_env = {"__builtins__": {}} _float = float
_int = int
_long = long
_StringType = type('')
# Convert string to float # Convert string to float
_re = None def atof(s):
def atof(str):
"""atof(s) -> float """atof(s) -> float
Return the floating point number represented by the string s. Return the floating point number represented by the string s.
""" """
global _re if type(s) == _StringType:
if _re is None: return _float(s)
# Don't fail if re doesn't exist -- just skip the syntax check
try:
import re
except ImportError:
_re = 0
else: else:
_re = re raise TypeError('argument 1: expected string, %s found' %
sign = '' type(s).__name__)
s = strip(str)
if s and s[0] in '+-':
sign = s[0]
s = s[1:]
if not s:
raise ValueError, 'non-float argument to string.atof'
while s[0] == '0' and len(s) > 1 and s[1] in digits: s = s[1:]
if _re and not _re.match('[0-9]*(\.[0-9]*)?([eE][-+]?[0-9]+)?$', s):
raise ValueError, 'non-float argument to string.atof'
try:
return float(eval(sign + s, _safe_env))
except SyntaxError:
raise ValueError, 'non-float argument to string.atof'
# Convert string to integer # Convert string to integer
def atoi(str, base=10): def atoi(*args):
"""atoi(s [,base]) -> int """atoi(s [,base]) -> int
Return the integer represented by the string s in the given Return the integer represented by the string s in the given
@ -372,24 +216,23 @@ def atoi(str, base=10):
accepted. accepted.
""" """
if base != 10: try:
# We only get here if strop doesn't define atoi() s = args[0]
raise ValueError, "this string.atoi doesn't support base != 10" except IndexError:
sign = '' raise TypeError('function requires at least 1 argument: %d given' %
s = strip(str) len(args))
if s and s[0] in '+-': # Don't catch type error resulting from too many arguments to int(). The
sign = s[0] # error message isn't compatible but the error type is, and this function
s = s[1:] # is complicated enough already.
if not s: if type(s) == _StringType:
raise ValueError, 'non-integer argument to string.atoi' return _apply(_int, args)
while s[0] == '0' and len(s) > 1: s = s[1:] else:
for c in s: raise TypeError('argument 1: expected string, %s found' %
if c not in digits: type(s).__name__)
raise ValueError, 'non-integer argument to string.atoi'
return eval(sign + s, _safe_env)
# Convert string to long integer # Convert string to long integer
def atol(str, base=10): def atol(*args):
"""atol(s [,base]) -> long """atol(s [,base]) -> long
Return the long integer represented by the string s in the Return the long integer represented by the string s in the
@ -401,21 +244,20 @@ def atol(str, base=10):
unless base is 0. unless base is 0.
""" """
if base != 10: try:
# We only get here if strop doesn't define atol() s = args[0]
raise ValueError, "this string.atol doesn't support base != 10" except IndexError:
sign = '' raise TypeError('function requires at least 1 argument: %d given' %
s = strip(str) len(args))
if s and s[0] in '+-': # Don't catch type error resulting from too many arguments to long(). The
sign = s[0] # error message isn't compatible but the error type is, and this function
s = s[1:] # is complicated enough already.
if not s: if type(s) == _StringType:
raise ValueError, 'non-integer argument to string.atol' return _apply(_long, args)
while s[0] == '0' and len(s) > 1: s = s[1:] else:
for c in s: raise TypeError('argument 1: expected string, %s found' %
if c not in digits: type(s).__name__)
raise ValueError, 'non-integer argument to string.atol'
return eval(sign + s + 'L', _safe_env)
# Left-justify a string # Left-justify a string
def ljust(s, width): def ljust(s, width):
@ -475,7 +317,7 @@ def zfill(x, width):
n = len(s) n = len(s)
if n >= width: return s if n >= width: return s
sign = '' sign = ''
if s[:1] in ('-', '+'): if s[0] in ('-', '+'):
sign, s = s[0], s[1:] sign, s = s[0], s[1:]
return sign + '0'*(width-n) + s return sign + '0'*(width-n) + s
@ -492,7 +334,7 @@ def expandtabs(s, tabsize=8):
res = line = '' res = line = ''
for c in s: for c in s:
if c == '\t': if c == '\t':
c = ' '*(tabsize - len(line)%tabsize) c = ' '*(tabsize - len(line) % tabsize)
line = line + c line = line + c
if c == '\n': if c == '\n':
res = res + line res = res + line
@ -509,14 +351,7 @@ def translate(s, table, deletions=""):
translation table, which must be a string of length 256. translation table, which must be a string of length 256.
""" """
if type(table) != type('') or len(table) != 256: return s.translate(table, deletions)
raise TypeError, \
"translation table must be 256 characters long"
res = ""
for c in s:
if c not in deletions:
res = res + table[ord(c)]
return res
# Capitalize a string, e.g. "aBc dEf" -> "Abc def". # Capitalize a string, e.g. "aBc dEf" -> "Abc def".
def capitalize(s): def capitalize(s):
@ -526,7 +361,7 @@ def capitalize(s):
capitalized. capitalized.
""" """
return upper(s[:1]) + lower(s[1:]) return s.capitalize()
# Capitalize the words in a string, e.g. " aBc dEf " -> "Abc Def". # Capitalize the words in a string, e.g. " aBc dEf " -> "Abc Def".
# See also regsub.capwords(). # See also regsub.capwords().
@ -539,7 +374,7 @@ def capwords(s, sep=None):
a single space. a single space.
""" """
return join(map(capitalize, split(s, sep)), sep or ' ') return join(map(capitalize, s.split(sep)), sep or ' ')
# Construct a translation string # Construct a translation string
_idmapL = None _idmapL = None
@ -563,7 +398,7 @@ def maketrans(fromstr, tostr):
return joinfields(L, "") return joinfields(L, "")
# Substring replacement (global) # Substring replacement (global)
def replace(str, old, new, maxsplit=0): def replace(s, old, new, maxsplit=0):
"""replace (str, old, new[, maxsplit]) -> string """replace (str, old, new[, maxsplit]) -> string
Return a copy of string str with all occurrences of substring Return a copy of string str with all occurrences of substring
@ -571,16 +406,26 @@ def replace(str, old, new, maxsplit=0):
given, only the first maxsplit occurrences are replaced. given, only the first maxsplit occurrences are replaced.
""" """
return joinfields(splitfields(str, old, maxsplit), new) return s.replace(old, new, maxsplit)
# XXX: transitional
#
# If string objects do not have methods, then we need to use the old string.py
# library, which uses strop for many more things than just the few outlined
# below.
try:
''.upper
except AttributeError:
from stringold import *
# Try importing optional built-in module "strop" -- if it exists, # Try importing optional built-in module "strop" -- if it exists,
# it redefines some string operations that are 100-1000 times faster. # it redefines some string operations that are 100-1000 times faster.
# It also defines values for whitespace, lowercase and uppercase # It also defines values for whitespace, lowercase and uppercase
# that match <ctype.h>'s definitions. # that match <ctype.h>'s definitions.
try: try:
from strop import * from strop import maketrans, lowercase, uppercase, whitespace
letters = lowercase + uppercase letters = lowercase + uppercase
except ImportError: except ImportError:
pass # Use the original, slow versions pass # Use the original versions

333
Lib/stringold.py
View File

@ -1,8 +1,9 @@
# module 'string' -- A collection of string operations # module 'string' -- A collection of string operations
# Warning: most of the code you see here isn't normally used nowadays. # Warning: most of the code you see here isn't normally used nowadays. With
# At the end of this file most functions are replaced by built-in # Python 1.6, many of these functions are implemented as methods on the
# functions imported from built-in module "strop". # standard string object. They used to be implemented by a built-in module
# called strop, but strop is now obsolete itself.
"""Common string manipulations. """Common string manipulations.
@ -30,9 +31,6 @@ octdigits = '01234567'
# Case conversion helpers # Case conversion helpers
_idmap = '' _idmap = ''
for i in range(256): _idmap = _idmap + chr(i) 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 del i
# Backward compatible names for exceptions # Backward compatible names for exceptions
@ -48,10 +46,7 @@ def lower(s):
Return a copy of the string s converted to lowercase. Return a copy of the string s converted to lowercase.
""" """
res = '' return s.lower()
for c in s:
res = res + _lower[ord(c)]
return res
# Convert lower case letters to UPPER CASE # Convert lower case letters to UPPER CASE
def upper(s): def upper(s):
@ -60,10 +55,7 @@ def upper(s):
Return a copy of the string s converted to uppercase. Return a copy of the string s converted to uppercase.
""" """
res = '' return s.upper()
for c in s:
res = res + _upper[ord(c)]
return res
# Swap lower case letters and UPPER CASE # Swap lower case letters and UPPER CASE
def swapcase(s): def swapcase(s):
@ -73,10 +65,7 @@ def swapcase(s):
converted to lowercase and vice versa. converted to lowercase and vice versa.
""" """
res = '' return s.swapcase()
for c in s:
res = res + _swapcase[ord(c)]
return res
# Strip leading and trailing tabs and spaces # Strip leading and trailing tabs and spaces
def strip(s): def strip(s):
@ -86,10 +75,7 @@ def strip(s):
whitespace removed. whitespace removed.
""" """
i, j = 0, len(s) return s.strip()
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]
# Strip leading tabs and spaces # Strip leading tabs and spaces
def lstrip(s): def lstrip(s):
@ -98,9 +84,7 @@ def lstrip(s):
Return a copy of the string s with leading whitespace removed. Return a copy of the string s with leading whitespace removed.
""" """
i, j = 0, len(s) return s.lstrip()
while i < j and s[i] in whitespace: i = i+1
return s[i:j]
# Strip trailing tabs and spaces # Strip trailing tabs and spaces
def rstrip(s): def rstrip(s):
@ -110,9 +94,7 @@ def rstrip(s):
removed. removed.
""" """
i, j = 0, len(s) return s.rstrip()
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 # Split a string into a list of space/tab-separated words
@ -128,74 +110,12 @@ def split(s, sep=None, maxsplit=0):
(split and splitfields are synonymous) (split and splitfields are synonymous)
""" """
if sep is not None: return splitfields(s, sep, maxsplit) return s.split(sep, maxsplit)
res = [] splitfields = split
i, n = 0, len(s)
if maxsplit <= 0: maxsplit = n
count = 0
while i < n:
while i < n and s[i] in whitespace: i = i+1
if i == n: break
if count >= maxsplit:
res.append(s[i:])
break
j = i
while j < n and s[j] not in whitespace: j = j+1
count = count + 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=None, maxsplit=0):
"""splitfields(str [,sep [,maxsplit]]) -> list of strings
Return a list of the words in the string s, using sep as the
delimiter string. If maxsplit is nonzero, splits into at most
maxsplit words If sep is not specified, any whitespace string
is a separator. Maxsplit defaults to 0.
(split and splitfields are synonymous)
"""
if sep is None: return split(s, None, maxsplit)
res = []
nsep = len(sep)
if nsep == 0:
return [s]
ns = len(s)
if maxsplit <= 0: maxsplit = ns
i = j = 0
count = 0
while j+nsep <= ns:
if s[j:j+nsep] == sep:
count = count + 1
res.append(s[i:j])
i = j = j + nsep
if count >= maxsplit: break
else:
j = j + 1
res.append(s[i:])
return res
# Join words with spaces between them
def join(words, sep = ' '):
"""join(list [,sep]) -> string
Return a string composed of the words in list, with
intervening occurences of sep. Sep defaults to a single
space.
(joinfields and join are synonymous)
"""
return joinfields(words, sep)
# Join fields with optional separator # Join fields with optional separator
def joinfields(words, sep = ' '): def join(words, sep = ' '):
"""joinfields(list [,sep]) -> string """join(list [,sep]) -> string
Return a string composed of the words in list, with Return a string composed of the words in list, with
intervening occurences of sep. The default separator is a intervening occurences of sep. The default separator is a
@ -204,47 +124,32 @@ def joinfields(words, sep = ' '):
(joinfields and join are synonymous) (joinfields and join are synonymous)
""" """
res = '' return sep.join(words)
for w in words: joinfields = join
res = res + (sep + w)
return res[len(sep):] # for a little bit of speed
_apply = apply
# Find substring, raise exception if not found # Find substring, raise exception if not found
def index(s, sub, i = 0, last=None): def index(s, *args):
"""index(s, sub [,start [,end]]) -> int """index(s, sub [,start [,end]]) -> int
Return the lowest index in s where substring sub is found, Like find but raises ValueError when the substring is not found.
such that sub is contained within s[start,end]. Optional
arguments start and end are interpreted as in slice notation.
Raise ValueError if not found.
""" """
if last is None: last = len(s) return _apply(s.index, args)
res = find(s, sub, i, last)
if res < 0:
raise ValueError, 'substring not found in string.index'
return res
# Find last substring, raise exception if not found # Find last substring, raise exception if not found
def rindex(s, sub, i = 0, last=None): def rindex(s, *args):
"""rindex(s, sub [,start [,end]]) -> int """rindex(s, sub [,start [,end]]) -> int
Return the highest index in s where substring sub is found, Like rfind but raises ValueError when the substring is not found.
such that sub is contained within s[start,end]. Optional
arguments start and end are interpreted as in slice notation.
Raise ValueError if not found.
""" """
if last is None: last = len(s) return _apply(s.rindex, args)
res = rfind(s, sub, i, last)
if res < 0:
raise ValueError, 'substring not found in string.index'
return res
# Count non-overlapping occurrences of substring # Count non-overlapping occurrences of substring
def count(s, sub, i = 0, last=None): def count(s, *args):
"""count(s, sub[, start[,end]]) -> int """count(s, sub[, start[,end]]) -> int
Return the number of occurrences of substring sub in string Return the number of occurrences of substring sub in string
@ -252,28 +157,10 @@ def count(s, sub, i = 0, last=None):
interpreted as in slice notation. interpreted as in slice notation.
""" """
Slen = len(s) # cache this value, for speed return _apply(s.count, args)
if last is None:
last = Slen
elif last < 0:
last = max(0, last + Slen)
elif last > Slen:
last = Slen
if i < 0: i = max(0, i + Slen)
n = len(sub)
m = last + 1 - n
if n == 0: return m-i
r = 0
while i < m:
if sub == s[i:i+n]:
r = r+1
i = i+n
else:
i = i+1
return r
# Find substring, return -1 if not found # Find substring, return -1 if not found
def find(s, sub, i = 0, last=None): def find(s, *args):
"""find(s, sub [,start [,end]]) -> in """find(s, sub [,start [,end]]) -> in
Return the lowest index in s where substring sub is found, Return the lowest index in s where substring sub is found,
@ -283,23 +170,10 @@ def find(s, sub, i = 0, last=None):
Return -1 on failure. Return -1 on failure.
""" """
Slen = len(s) # cache this value, for speed return _apply(s.find, args)
if last is None:
last = Slen
elif last < 0:
last = max(0, last + Slen)
elif last > Slen:
last = Slen
if i < 0: i = max(0, i + Slen)
n = len(sub)
m = last + 1 - n
while i < m:
if sub == s[i:i+n]: return i
i = i+1
return -1
# Find last substring, return -1 if not found # Find last substring, return -1 if not found
def rfind(s, sub, i = 0, last=None): def rfind(s, *args):
"""rfind(s, sub [,start [,end]]) -> int """rfind(s, sub [,start [,end]]) -> int
Return the highest index in s where substring sub is found, Return the highest index in s where substring sub is found,
@ -309,59 +183,29 @@ def rfind(s, sub, i = 0, last=None):
Return -1 on failure. Return -1 on failure.
""" """
Slen = len(s) # cache this value, for speed return _apply(s.rfind, args)
if last is None:
last = Slen
elif last < 0:
last = max(0, last + Slen)
elif last > Slen:
last = Slen
if i < 0: i = max(0, i + Slen)
n = len(sub)
m = last + 1 - n
r = -1
while i < m:
if sub == s[i:i+n]: r = i
i = i+1
return r
# "Safe" environment for eval() # for a bit of speed
_safe_env = {"__builtins__": {}} _float = float
_int = int
_long = long
_StringType = type('')
# Convert string to float # Convert string to float
_re = None def atof(s):
def atof(str):
"""atof(s) -> float """atof(s) -> float
Return the floating point number represented by the string s. Return the floating point number represented by the string s.
""" """
global _re if type(s) == _StringType:
if _re is None: return _float(s)
# Don't fail if re doesn't exist -- just skip the syntax check
try:
import re
except ImportError:
_re = 0
else: else:
_re = re raise TypeError('argument 1: expected string, %s found' %
sign = '' type(s).__name__)
s = strip(str)
if s and s[0] in '+-':
sign = s[0]
s = s[1:]
if not s:
raise ValueError, 'non-float argument to string.atof'
while s[0] == '0' and len(s) > 1 and s[1] in digits: s = s[1:]
if _re and not _re.match('[0-9]*(\.[0-9]*)?([eE][-+]?[0-9]+)?$', s):
raise ValueError, 'non-float argument to string.atof'
try:
return float(eval(sign + s, _safe_env))
except SyntaxError:
raise ValueError, 'non-float argument to string.atof'
# Convert string to integer # Convert string to integer
def atoi(str, base=10): def atoi(*args):
"""atoi(s [,base]) -> int """atoi(s [,base]) -> int
Return the integer represented by the string s in the given Return the integer represented by the string s in the given
@ -372,24 +216,23 @@ def atoi(str, base=10):
accepted. accepted.
""" """
if base != 10: try:
# We only get here if strop doesn't define atoi() s = args[0]
raise ValueError, "this string.atoi doesn't support base != 10" except IndexError:
sign = '' raise TypeError('function requires at least 1 argument: %d given' %
s = strip(str) len(args))
if s and s[0] in '+-': # Don't catch type error resulting from too many arguments to int(). The
sign = s[0] # error message isn't compatible but the error type is, and this function
s = s[1:] # is complicated enough already.
if not s: if type(s) == _StringType:
raise ValueError, 'non-integer argument to string.atoi' return _apply(_int, args)
while s[0] == '0' and len(s) > 1: s = s[1:] else:
for c in s: raise TypeError('argument 1: expected string, %s found' %
if c not in digits: type(s).__name__)
raise ValueError, 'non-integer argument to string.atoi'
return eval(sign + s, _safe_env)
# Convert string to long integer # Convert string to long integer
def atol(str, base=10): def atol(*args):
"""atol(s [,base]) -> long """atol(s [,base]) -> long
Return the long integer represented by the string s in the Return the long integer represented by the string s in the
@ -401,21 +244,20 @@ def atol(str, base=10):
unless base is 0. unless base is 0.
""" """
if base != 10: try:
# We only get here if strop doesn't define atol() s = args[0]
raise ValueError, "this string.atol doesn't support base != 10" except IndexError:
sign = '' raise TypeError('function requires at least 1 argument: %d given' %
s = strip(str) len(args))
if s and s[0] in '+-': # Don't catch type error resulting from too many arguments to long(). The
sign = s[0] # error message isn't compatible but the error type is, and this function
s = s[1:] # is complicated enough already.
if not s: if type(s) == _StringType:
raise ValueError, 'non-integer argument to string.atol' return _apply(_long, args)
while s[0] == '0' and len(s) > 1: s = s[1:] else:
for c in s: raise TypeError('argument 1: expected string, %s found' %
if c not in digits: type(s).__name__)
raise ValueError, 'non-integer argument to string.atol'
return eval(sign + s + 'L', _safe_env)
# Left-justify a string # Left-justify a string
def ljust(s, width): def ljust(s, width):
@ -492,7 +334,7 @@ def expandtabs(s, tabsize=8):
res = line = '' res = line = ''
for c in s: for c in s:
if c == '\t': if c == '\t':
c = ' '*(tabsize - len(line)%tabsize) c = ' '*(tabsize - len(line) % tabsize)
line = line + c line = line + c
if c == '\n': if c == '\n':
res = res + line res = res + line
@ -509,14 +351,7 @@ def translate(s, table, deletions=""):
translation table, which must be a string of length 256. translation table, which must be a string of length 256.
""" """
if type(table) != type('') or len(table) != 256: return s.translate(table, deletions)
raise TypeError, \
"translation table must be 256 characters long"
res = ""
for c in s:
if c not in deletions:
res = res + table[ord(c)]
return res
# Capitalize a string, e.g. "aBc dEf" -> "Abc def". # Capitalize a string, e.g. "aBc dEf" -> "Abc def".
def capitalize(s): def capitalize(s):
@ -526,7 +361,7 @@ def capitalize(s):
capitalized. capitalized.
""" """
return upper(s[:1]) + lower(s[1:]) return s.capitalize()
# Capitalize the words in a string, e.g. " aBc dEf " -> "Abc Def". # Capitalize the words in a string, e.g. " aBc dEf " -> "Abc Def".
# See also regsub.capwords(). # See also regsub.capwords().
@ -539,7 +374,7 @@ def capwords(s, sep=None):
a single space. a single space.
""" """
return join(map(capitalize, split(s, sep)), sep or ' ') return join(map(capitalize, s.split(sep)), sep or ' ')
# Construct a translation string # Construct a translation string
_idmapL = None _idmapL = None
@ -563,7 +398,7 @@ def maketrans(fromstr, tostr):
return joinfields(L, "") return joinfields(L, "")
# Substring replacement (global) # Substring replacement (global)
def replace(str, old, new, maxsplit=0): def replace(s, old, new, maxsplit=0):
"""replace (str, old, new[, maxsplit]) -> string """replace (str, old, new[, maxsplit]) -> string
Return a copy of string str with all occurrences of substring Return a copy of string str with all occurrences of substring
@ -571,16 +406,26 @@ def replace(str, old, new, maxsplit=0):
given, only the first maxsplit occurrences are replaced. given, only the first maxsplit occurrences are replaced.
""" """
return joinfields(splitfields(str, old, maxsplit), new) return s.replace(old, new, maxsplit)
# XXX: transitional
#
# If string objects do not have methods, then we need to use the old string.py
# library, which uses strop for many more things than just the few outlined
# below.
try:
''.upper
except AttributeError:
from stringold import *
# Try importing optional built-in module "strop" -- if it exists, # Try importing optional built-in module "strop" -- if it exists,
# it redefines some string operations that are 100-1000 times faster. # it redefines some string operations that are 100-1000 times faster.
# It also defines values for whitespace, lowercase and uppercase # It also defines values for whitespace, lowercase and uppercase
# that match <ctype.h>'s definitions. # that match <ctype.h>'s definitions.
try: try:
from strop import * from strop import maketrans, lowercase, uppercase, whitespace
letters = lowercase + uppercase letters = lowercase + uppercase
except ImportError: except ImportError:
pass # Use the original, slow versions pass # Use the original versions

180
Objects/abstract.c
View File

@ -53,123 +53,6 @@ null_error()
return NULL; return NULL;
} }
/* Copied with modifications from stropmodule.c: atoi, atof, atol */
static PyObject *
int_from_string(v)
PyObject *v;
{
char *s, *end;
long x;
char buffer[256]; /* For errors */
s = PyString_AS_STRING(v);
while (*s && isspace(Py_CHARMASK(*s)))
s++;
errno = 0;
x = PyOS_strtol(s, &end, 10);
if (end == s || !isdigit(end[-1]))
goto bad;
while (*end && isspace(Py_CHARMASK(*end)))
end++;
if (*end != '\0') {
bad:
sprintf(buffer, "invalid literal for int(): %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
return NULL;
}
else if (end != PyString_AS_STRING(v) + PyString_GET_SIZE(v)) {
PyErr_SetString(PyExc_ValueError,
"null byte in argument for int()");
return NULL;
}
else if (errno != 0) {
sprintf(buffer, "int() literal too large: %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
return NULL;
}
return PyInt_FromLong(x);
}
static PyObject *
long_from_string(v)
PyObject *v;
{
char *s, *end;
PyObject *x;
char buffer[256]; /* For errors */
s = PyString_AS_STRING(v);
while (*s && isspace(Py_CHARMASK(*s)))
s++;
x = PyLong_FromString(s, &end, 10);
if (x == NULL) {
if (PyErr_ExceptionMatches(PyExc_ValueError))
goto bad;
return NULL;
}
while (*end && isspace(Py_CHARMASK(*end)))
end++;
if (*end != '\0') {
bad:
sprintf(buffer, "invalid literal for long(): %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
Py_XDECREF(x);
return NULL;
}
else if (end != PyString_AS_STRING(v) + PyString_GET_SIZE(v)) {
PyErr_SetString(PyExc_ValueError,
"null byte in argument for long()");
return NULL;
}
return x;
}
static PyObject *
float_from_string(v)
PyObject *v;
{
extern double strtod Py_PROTO((const char *, char **));
char *s, *last, *end;
double x;
char buffer[256]; /* For errors */
s = PyString_AS_STRING(v);
last = s + PyString_GET_SIZE(v);
while (*s && isspace(Py_CHARMASK(*s)))
s++;
if (s[0] == '\0') {
PyErr_SetString(PyExc_ValueError, "empty string for float()");
return NULL;
}
errno = 0;
PyFPE_START_PROTECT("float_from_string", return 0)
x = strtod(s, &end);
PyFPE_END_PROTECT(x)
/* Believe it or not, Solaris 2.6 can move end *beyond* the null
byte at the end of the string, when the input is inf(inity) */
if (end > last)
end = last;
while (*end && isspace(Py_CHARMASK(*end)))
end++;
if (*end != '\0') {
sprintf(buffer, "invalid literal for float(): %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
return NULL;
}
else if (end != PyString_AS_STRING(v) + PyString_GET_SIZE(v)) {
PyErr_SetString(PyExc_ValueError,
"null byte in argument for float()");
return NULL;
}
else if (errno != 0) {
sprintf(buffer, "float() literal too large: %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
return NULL;
}
return PyFloat_FromDouble(x);
}
/* Operations on any object */ /* Operations on any object */
int int
@ -713,7 +596,7 @@ PyNumber_Int(o)
if (o == NULL) if (o == NULL)
return null_error(); return null_error();
if (PyString_Check(o)) if (PyString_Check(o))
return int_from_string(o); return PyInt_FromString(PyString_AS_STRING(o), NULL, 10);
m = o->ob_type->tp_as_number; m = o->ob_type->tp_as_number;
if (m && m->nb_int) if (m && m->nb_int)
return m->nb_int(o); return m->nb_int(o);
@ -721,6 +604,61 @@ PyNumber_Int(o)
return type_error("object can't be converted to int"); return type_error("object can't be converted to int");
} }
/* There are two C API functions for converting a string to a long,
* PyNumber_Long() and PyLong_FromString(). Both are used in builtin_long,
* reachable from Python with the built-in function long().
*
* The difference is this: PyNumber_Long will raise an exception when the
* string cannot be converted to a long. The most common situation is
* where a float string is passed in; this raises a ValueError.
* PyLong_FromString does not raise an exception; it silently truncates the
* float to an integer.
*
* You can see the different behavior from Python with the following:
*
* long('9.5')
* => ValueError: invalid literal for long(): 9.5
*
* long('9.5', 10)
* => 9L
*
* The first example ends up calling PyNumber_Long(), while the second one
* calls PyLong_FromString().
*/
static PyObject *
long_from_string(v)
PyObject *v;
{
char *s, *end;
PyObject *x;
char buffer[256]; /* For errors */
s = PyString_AS_STRING(v);
while (*s && isspace(Py_CHARMASK(*s)))
s++;
x = PyLong_FromString(s, &end, 10);
if (x == NULL) {
if (PyErr_ExceptionMatches(PyExc_ValueError))
goto bad;
return NULL;
}
while (*end && isspace(Py_CHARMASK(*end)))
end++;
if (*end != '\0') {
bad:
sprintf(buffer, "invalid literal for long(): %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
Py_XDECREF(x);
return NULL;
}
else if (end != PyString_AS_STRING(v) + PyString_GET_SIZE(v)) {
PyErr_SetString(PyExc_ValueError,
"null byte in argument for long()");
return NULL;
}
return x;
}
PyObject * PyObject *
PyNumber_Long(o) PyNumber_Long(o)
PyObject *o; PyObject *o;
@ -730,6 +668,10 @@ PyNumber_Long(o)
if (o == NULL) if (o == NULL)
return null_error(); return null_error();
if (PyString_Check(o)) if (PyString_Check(o))
/* need to do extra error checking that PyLong_FromString()
* doesn't do. In particular long('9.5') must raise an
* exception, not truncate the float.
*/
return long_from_string(o); return long_from_string(o);
m = o->ob_type->tp_as_number; m = o->ob_type->tp_as_number;
if (m && m->nb_long) if (m && m->nb_long)
@ -747,7 +689,7 @@ PyNumber_Float(o)
if (o == NULL) if (o == NULL)
return null_error(); return null_error();
if (PyString_Check(o)) if (PyString_Check(o))
return float_from_string(o); return PyFloat_FromString(o, NULL);
m = o->ob_type->tp_as_number; m = o->ob_type->tp_as_number;
if (m && m->nb_float) if (m && m->nb_float)
return m->nb_float(o); return m->nb_float(o);

51
Objects/floatobject.c
View File

@ -149,6 +149,57 @@ PyFloat_FromDouble(fval)
return (PyObject *) op; return (PyObject *) op;
} }
PyObject *
PyFloat_FromString(v, pend)
PyObject *v;
char **pend;
{
extern double strtod Py_PROTO((const char *, char **));
char *s, *last, *end;
double x;
char buffer[256]; /* For errors */
if (!PyString_Check(v))
return NULL;
s = PyString_AS_STRING(v);
last = s + PyString_GET_SIZE(v);
while (*s && isspace(Py_CHARMASK(*s)))
s++;
if (s[0] == '\0') {
PyErr_SetString(PyExc_ValueError, "empty string for float()");
return NULL;
}
errno = 0;
PyFPE_START_PROTECT("PyFloat_FromString", return 0)
x = strtod(s, &end);
PyFPE_END_PROTECT(x)
/* Believe it or not, Solaris 2.6 can move end *beyond* the null
byte at the end of the string, when the input is inf(inity) */
if (end > last)
end = last;
while (*end && isspace(Py_CHARMASK(*end)))
end++;
if (*end != '\0') {
sprintf(buffer, "invalid literal for float(): %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
return NULL;
}
else if (end != PyString_AS_STRING(v) + PyString_GET_SIZE(v)) {
PyErr_SetString(PyExc_ValueError,
"null byte in argument for float()");
return NULL;
}
else if (errno != 0) {
sprintf(buffer, "float() literal too large: %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
return NULL;
}
if (pend)
*pend = end;
return PyFloat_FromDouble(x);
}
static void static void
float_dealloc(op) float_dealloc(op)
PyFloatObject *op; PyFloatObject *op;

43
Objects/intobject.c
View File

@ -32,6 +32,7 @@ PERFORMANCE OF THIS SOFTWARE.
/* Integer object implementation */ /* Integer object implementation */
#include "Python.h" #include "Python.h"
#include <ctype.h>
#ifdef HAVE_LIMITS_H #ifdef HAVE_LIMITS_H
#include <limits.h> #include <limits.h>
@ -218,6 +219,48 @@ PyInt_AsLong(op)
return val; return val;
} }
PyObject *
PyInt_FromString(s, pend, base)
char *s;
char **pend;
int base;
{
char *end;
long x;
char buffer[256]; /* For errors */
if ((base != 0 && base < 2) || base > 36) {
PyErr_SetString(PyExc_ValueError, "invalid base for int()");
return NULL;
}
while (*s && isspace(Py_CHARMASK(*s)))
s++;
errno = 0;
if (base == 0 && s[0] == '0')
x = (long) PyOS_strtoul(s, &end, base);
else
x = PyOS_strtol(s, &end, base);
if (end == s || !isalnum(end[-1]))
goto bad;
while (*end && isspace(Py_CHARMASK(*end)))
end++;
if (*end != '\0') {
bad:
sprintf(buffer, "invalid literal for int(): %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
return NULL;
}
else if (errno != 0) {
sprintf(buffer, "int() literal too large: %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
return NULL;
}
if (pend)
*pend = end;
return PyInt_FromLong(x);
}
/* Methods */ /* Methods */
/* ARGSUSED */ /* ARGSUSED */

1045
Objects/stringobject.c
View File

File diff suppressed because it is too large Load Diff

107
Python/bltinmodule.c
View File

@ -811,24 +811,6 @@ The globals and locals are dictionaries, defaulting to the current\n\
globals and locals. If only globals is given, locals defaults to it."; globals and locals. If only globals is given, locals defaults to it.";
static PyObject *
builtin_float(self, args)
PyObject *self;
PyObject *args;
{
PyObject *v;
if (!PyArg_ParseTuple(args, "O:float", &v))
return NULL;
return PyNumber_Float(v);
}
static char float_doc[] =
"float(x) -> floating point number\n\
\n\
Convert a string or number to a floating point number, if possible.";
static PyObject * static PyObject *
builtin_getattr(self, args) builtin_getattr(self, args)
PyObject *self; PyObject *self;
@ -1251,17 +1233,79 @@ builtin_int(self, args)
PyObject *args; PyObject *args;
{ {
PyObject *v; PyObject *v;
int base = -909; /* unlikely! */
if (!PyArg_ParseTuple(args, "O:int", &v)) if (!PyArg_ParseTuple(args, "O|i:int", &v, &base))
return NULL; return NULL;
if (base == -909)
return PyNumber_Int(v); return PyNumber_Int(v);
else if (!PyString_Check(v)) {
PyErr_SetString(PyExc_TypeError,
"can't convert non-string with explicit base");
return NULL;
}
return PyInt_FromString(PyString_AS_STRING(v), NULL, base);
} }
static char int_doc[] = static char int_doc[] =
"int(x) -> integer\n\ "int(x[, base]) -> integer\n\
\n\ \n\
Convert a string or number to an integer, if possible.\n\ Convert a string or number to an integer, if possible. A floating point\n\
A floating point argument will be truncated towards zero."; argument will be truncated towards zero (this does not include a string\n\
representation of a floating point number!) When converting a string, use\n\
the optional base. It is an error to supply a base when converting a\n\
non-string.";
static PyObject *
builtin_long(self, args)
PyObject *self;
PyObject *args;
{
PyObject *v;
int base = -909; /* unlikely! */
if (!PyArg_ParseTuple(args, "O|i:long", &v, &base))
return NULL;
if (base == -909)
return PyNumber_Long(v);
else if (!PyString_Check(v)) {
PyErr_SetString(PyExc_TypeError,
"can't convert non-string with explicit base");
return NULL;
}
return PyLong_FromString(PyString_AS_STRING(v), NULL, base);
}
static char long_doc[] =
"long(x) -> long integer\n\
long(x, base) -> long integer\n\
\n\
Convert a string or number to a long integer, if possible. A floating\n\
point argument will be truncated towards zero (this does not include a\n\
string representation of a floating point number!) When converting a\n\
string, use the given base. It is an error to supply a base when\n\
converting a non-string.";
static PyObject *
builtin_float(self, args)
PyObject *self;
PyObject *args;
{
PyObject *v;
if (!PyArg_ParseTuple(args, "O:float", &v))
return NULL;
if (PyString_Check(v))
return PyFloat_FromString(v, NULL);
return PyNumber_Float(v);
}
static char float_doc[] =
"float(x) -> floating point number\n\
\n\
Convert a string or number to a floating point number, if possible.";
static PyObject * static PyObject *
@ -1351,25 +1395,6 @@ static char locals_doc[] =
Return the dictionary containing the current scope's local variables."; Return the dictionary containing the current scope's local variables.";
static PyObject *
builtin_long(self, args)
PyObject *self;
PyObject *args;
{
PyObject *v;
if (!PyArg_ParseTuple(args, "O:long", &v))
return NULL;
return PyNumber_Long(v);
}
static char long_doc[] =
"long(x) -> long integer\n\
\n\
Convert a string or number to a long integer, if possible.\n\
A floating point argument will be truncated towards zero.";
static PyObject * static PyObject *
min_max(args, sign) min_max(args, sign)
PyObject *args; PyObject *args;