traverseda
/
cpython
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Convert all remaining *simple* cases of regex usage to re usage.

This commit is contained in:
Guido van Rossum 1997-10-22 21:00:49 +00:00
parent 426916e50e
commit 9694fcab53
23 changed files with 134 additions and 144 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
Lib/fmt.py
View File

@ -461,9 +461,9 @@ class StdwinBackEnd(SavingBackEnd):
self.paralist[para2].invert(d, pos1, pos2)
#
def search(self, prog):
import regex, string
import re, string
if type(prog) == type(''):
prog = regex.compile(string.lower(prog))
prog = re.compile(string.lower(prog))
if self.selection:
iold = self.selection[0][0]
else:
@ -474,8 +474,9 @@ class StdwinBackEnd(SavingBackEnd):
continue
p = self.paralist[i]
text = string.lower(p.extract())
if prog.search(text) >= 0:
a, b = prog.regs[0]
match = prog.search(text)
if match:
a, b = match.group(0)
long1 = i, a
long2 = i, b
hit = long1, long2

15
Lib/fnmatch.py
View File

@ -10,6 +10,8 @@ The function translate(PATTERN) returns a regular expression
corresponding to PATTERN. (It does not compile it.)
"""
import re
_cache = {}
def fnmatch(name, pat):
@ -42,11 +44,8 @@ def fnmatchcase(name, pat):
if not _cache.has_key(pat):
res = translate(pat)
import regex
save_syntax = regex.set_syntax(0)
_cache[pat] = regex.compile(res)
save_syntax = regex.set_syntax(save_syntax)
return _cache[pat].match(name) == len(name)
_cache[pat] = re.compile(res)
return _cache[pat].match(name) is not None
def translate(pat):
"""Translate a shell PATTERN to a regular expression.
@ -85,8 +84,6 @@ def translate(pat):
stuff = stuff[1:] + stuff[0]
stuff = '[' + stuff + ']'
res = res + stuff
elif c in '\\.+^$':
res = res + ('\\' + c)
else:
res = res + c
return res
res = res + re.escape(c)
return res + "$"

13
Lib/fpformat.py
View File

@ -11,11 +11,11 @@
# digits_behind: number of digits behind the decimal point
import regex
import re
# Compiled regular expression to "decode" a number
decoder = regex.compile( \
'^\([-+]?\)0*\([0-9]*\)\(\(\.[0-9]*\)?\)\(\([eE][-+]?[0-9]+\)?\)$')
decoder = re.compile( \
'^([-+]?)0*([0-9]*)((\.[0-9]*)?)(([eE][-+]?[0-9]+)?)$')
# \0 the whole thing
# \1 leading sign or empty
# \2 digits left of decimal point
@ -30,10 +30,9 @@ NotANumber = 'fpformat.NotANumber'
# fraction is 0 or more digits
# expo is an integer
def extract(s):
if decoder.match(s) < 0: raise NotANumber
(a1, b1), (a2, b2), (a3, b3), (a4, b4), (a5, b5) = decoder.regs[1:6]
sign, intpart, fraction, exppart = \
s[a1:b1], s[a2:b2], s[a3:b3], s[a5:b5]
m = decoder.match(s)
if not m: raise NotANumber
sign, intpart, fraction, exppart = m.group(1, 2, 3, 5)
if sign == '+': sign = ''
if fraction: fraction = fraction[1:]
if exppart: expo = eval(exppart[1:])

6
Lib/glob.py
View File

@ -2,7 +2,7 @@
import os
import fnmatch
import regex
import re
def glob(pathname):
@ -50,7 +50,7 @@ def glob1(dirname, pattern):
return result
magic_check = regex.compile('[*?[]')
magic_check = re.compile('[*?[]')
def has_magic(s):
return magic_check.search(s) >= 0
return magic_check.search(s) is not None

18
Lib/keyword.py
View File

@ -7,10 +7,7 @@
# To update the symbols in this file, 'cd' to the top directory of
# the python source tree after building the interpreter and run:
#
# PYTHONPATH=./Lib ./python Lib/keyword.py
#
# (this path allows the import of string.py and regexmodule.so
# for a site with no installation in place)
# python Lib/keyword.py
kwlist = [
#--start keywords--
@ -52,7 +49,7 @@ for keyword in kwlist:
iskeyword = kwdict.has_key
def main():
import sys, regex, string
import sys, re, string
args = sys.argv[1:]
iptfile = args and args[0] or "Python/graminit.c"
@ -61,13 +58,15 @@ def main():
# scan the source file for keywords
fp = open(iptfile)
strprog = regex.compile('"\([^"]+\)"')
strprog = re.compile('"([^"]+)"')
lines = []
while 1:
line = fp.readline()
if not line: break
if string.find(line, '{1, "') > -1 and strprog.search(line) > -1:
lines.append(" '" + strprog.group(1) + "',\n")
if string.find(line, '{1, "') > -1:
match = strprog.search(line)
if match:
lines.append(" '" + match.group(1) + "',\n")
fp.close()
lines.sort()
@ -90,4 +89,5 @@ def main():
fp.write(string.join(format, ''))
fp.close()
if __name__ == "__main__": main()
if __name__ == "__main__":
main()

9
Lib/lib-old/fmt.py
View File

@ -461,9 +461,9 @@ class StdwinBackEnd(SavingBackEnd):
self.paralist[para2].invert(d, pos1, pos2)
#
def search(self, prog):
import regex, string
import re, string
if type(prog) == type(''):
prog = regex.compile(string.lower(prog))
prog = re.compile(string.lower(prog))
if self.selection:
iold = self.selection[0][0]
else:
@ -474,8 +474,9 @@ class StdwinBackEnd(SavingBackEnd):
continue
p = self.paralist[i]
text = string.lower(p.extract())
if prog.search(text) >= 0:
a, b = prog.regs[0]
match = prog.search(text)
if match:
a, b = match.group(0)
long1 = i, a
long2 = i, b
hit = long1, long2

7
Lib/mailbox.py
View File

@ -5,7 +5,6 @@
import rfc822
import os
import regex
class _Mailbox:
def __init__(self, fp):
@ -117,12 +116,13 @@ class MmdfMailbox(_Mailbox):
class MHMailbox:
def __init__(self, dirname):
pat = regex.compile('^[0-9][0-9]*$')
import re
pat = re.compile('^[0-9][0-9]*$')
self.dirname = dirname
files = os.listdir(self.dirname)
self.boxes = []
for f in files:
if pat.match(f) == len(f):
if pat.match(f):
self.boxes.append(f)
def next(self):
@ -187,6 +187,7 @@ def _test():
if not msg:
break
msgs.append(msg)
msg.fp = None
if len(args) > 1:
num = string.atoi(args[1])
print 'Message %d body:'%num

24
Lib/mhlib.py
View File

@ -73,7 +73,7 @@ FOLDER_PROTECT = 0700
import os
import sys
from stat import ST_NLINK
import regex
import re
import string
import mimetools
import multifile
@ -236,9 +236,9 @@ class MH:
# Class representing a particular folder
numericprog = regex.compile('^[1-9][0-9]*$')
numericprog = re.compile('^[1-9][0-9]*$')
def isnumeric(str):
return numericprog.match(str) >= 0
return numericprog.match(str) is not None
class Folder:
@ -906,15 +906,12 @@ def pickline(file, key, casefold = 1):
f = open(file, 'r')
except IOError:
return None
pat = key + ':'
if casefold:
prog = regex.compile(pat, regex.casefold)
else:
prog = regex.compile(pat)
pat = re.escape(key) + ':'
prog = re.compile(pat, casefold and re.IGNORECASE)
while 1:
line = f.readline()
if not line: break
if prog.match(line) >= 0:
if prog.match(line):
text = line[len(key)+1:]
while 1:
line = f.readline()
@ -931,18 +928,15 @@ def updateline(file, key, value, casefold = 1):
f.close()
except IOError:
lines = []
pat = key + ':\(.*\)\n'
if casefold:
prog = regex.compile(pat, regex.casefold)
else:
prog = regex.compile(pat)
pat = re.escape(key) + ':(.*)\n'
prog = re.compile(pat, casefold and re.IGNORECASE)
if value is None:
newline = None
else:
newline = '%s: %s\n' % (key, value)
for i in range(len(lines)):
line = lines[i]
if prog.match(line) == len(line):
if prog.match(line):
if newline is None:
del lines[i]
else:

19
Lib/nntplib.py
View File

@ -29,7 +29,7 @@
# Imports
import regex
import re
import socket
import string
@ -313,13 +313,13 @@ class NNTP:
# - list: list of (nr, value) strings
def xhdr(self, hdr, str):
pat = re.compile('^([0-9]+) ?(.*)\n?')
resp, lines = self.longcmd('XHDR ' + hdr + ' ' + str)
for i in range(len(lines)):
line = lines[i]
n = regex.match('^[0-9]+', line)
nr = line[:n]
if n < len(line) and line[n] == ' ': n = n+1
lines[i] = (nr, line[n:])
m = pat.match(line)
if m:
lines[i] = m.group(1, 2)
return resp, lines
# Process an XOVER command (optional server extension) Arguments:
@ -354,14 +354,13 @@ class NNTP:
# - list: list of (name,title) strings
def xgtitle(self, group):
line_pat = regex.compile("^\([^ \t]+\)[ \t]+\(.*\)$")
line_pat = re.compile("^([^ \t]+)[ \t]+(.*)$")
resp, raw_lines = self.longcmd('XGTITLE ' + group)
lines = []
for raw_line in raw_lines:
if line_pat.search(string.strip(raw_line)) == 0:
lines.append(line_pat.group(1),
line_pat.group(2))
match = line_pat.search(string.strip(raw_line))
if match:
lines.append(match.group(1, 2))
return resp, lines
# Process an XPATH command (optional server extension) Arguments:

10
Lib/pipes.py
View File

@ -61,7 +61,7 @@
import sys
import regex
import re
import os
import tempfile
@ -124,10 +124,10 @@ class Template:
if self.steps <> [] and self.steps[-1][1] == SINK:
raise ValueError, \
'Template.append: already ends with SINK'
if kind[0] == 'f' and regex.search('\$IN', cmd) < 0:
if kind[0] == 'f' and not re.search('\$IN\b', cmd):
raise ValueError, \
'Template.append: missing $IN in cmd'
if kind[1] == 'f' and regex.search('\$OUT', cmd) < 0:
if kind[1] == 'f' and not re.search('\$OUT\b', cmd):
raise ValueError, \
'Template.append: missing $OUT in cmd'
self.steps.append((cmd, kind))
@ -146,10 +146,10 @@ class Template:
if self.steps <> [] and self.steps[0][1] == SOURCE:
raise ValueError, \
'Template.prepend: already begins with SOURCE'
if kind[0] == 'f' and regex.search('\$IN\>', cmd) < 0:
if kind[0] == 'f' and not re.search('\$IN\b', cmd):
raise ValueError, \
'Template.prepend: missing $IN in cmd'
if kind[1] == 'f' and regex.search('\$OUT\>', cmd) < 0:
if kind[1] == 'f' and not re.search('\$OUT\b', cmd):
raise ValueError, \
'Template.prepend: missing $OUT in cmd'
self.steps.insert(0, (cmd, kind))

11
Lib/plat-irix5/cddb.py
View File

@ -81,18 +81,17 @@ class Cddb:
self.notes = []
if not hasattr(self, 'file'):
return
import regex
reg = regex.compile('^\\([^.]*\\)\\.\\([^:]*\\):[\t ]+\\(.*\\)')
import re
reg = re.compile(r'^([^.]*)\.([^:]*):[\t ]+(.*)')
while 1:
line = f.readline()
if not line:
break
if reg.match(line) == -1:
match = reg.match(line)
if not match:
print 'syntax error in ' + file
continue
name1 = line[reg.regs[1][0]:reg.regs[1][1]]
name2 = line[reg.regs[2][0]:reg.regs[2][1]]
value = line[reg.regs[3][0]:reg.regs[3][1]]
name1, name2, value = match.group(1, 2, 3)
if name1 == 'album':
if name2 == 'artist':
self.artist = value

10
Lib/plat-irix5/cdplayer.py
View File

@ -39,8 +39,8 @@ class Cdplayer:
f = open(posix.environ['HOME'] + '/' + cdplayerrc, 'r')
except IOError:
return
import regex
reg = regex.compile('^\\([^:]*\\):\t\\(.*\\)')
import re
reg = re.compile(r'^([^:]*):\t(.*)')
s = self.id + '.'
l = len(s)
while 1:
@ -49,11 +49,11 @@ class Cdplayer:
break
if line[:l] == s:
line = line[l:]
if reg.match(line) == -1:
match = reg.match(line)
if not match:
print 'syntax error in ~/' + cdplayerrc
continue
name = line[reg.regs[1][0]:reg.regs[1][1]]
value = line[reg.regs[2][0]:reg.regs[2][1]]
name, valye = match.group(1, 2)
if name == 'title':
self.title = value
elif name == 'artist':

15
Lib/plat-irix5/flp.py
View File

@ -267,19 +267,18 @@ _parse_func = { \
# This function parses a line, and returns either
# a string or a tuple (name,value)
import regex
prog = regex.compile('^\([^:]*\): *\(.*\)')
import re
prog = re.compile('^([^:]*): *(.*)')
def _parse_line(line):
if prog.match(line) < 0:
match = prog.match(line)
if not match:
return line
a = prog.regs
name = line[:a[1][1]]
name, value = match.group(1, 2)
if name[0] == 'N':
name = string.joinfields(string.split(name),'')
name = string.join(string.split(name),'')
name = string.lower(name)
name = string.upper(name[0]) + name[1:]
value = line[a[2][0]:]
name = string.capitalize(name)
try:
pf = _parse_func[name]
except KeyError:

11
Lib/plat-irix6/cddb.py
View File

@ -81,18 +81,17 @@ class Cddb:
self.notes = []
if not hasattr(self, 'file'):
return
import regex
reg = regex.compile('^\\([^.]*\\)\\.\\([^:]*\\):[\t ]+\\(.*\\)')
import re
reg = re.compile(r'^([^.]*)\.([^:]*):[\t ]+(.*)')
while 1:
line = f.readline()
if not line:
break
if reg.match(line) == -1:
match = reg.match(line)
if not match:
print 'syntax error in ' + file
continue
name1 = line[reg.regs[1][0]:reg.regs[1][1]]
name2 = line[reg.regs[2][0]:reg.regs[2][1]]
value = line[reg.regs[3][0]:reg.regs[3][1]]
name1, name2, value = match.group(1, 2, 3)
if name1 == 'album':
if name2 == 'artist':
self.artist = value

10
Lib/plat-irix6/cdplayer.py
View File

@ -39,8 +39,8 @@ class Cdplayer:
f = open(posix.environ['HOME'] + '/' + cdplayerrc, 'r')
except IOError:
return
import regex
reg = regex.compile('^\\([^:]*\\):\t\\(.*\\)')
import re
reg = re.compile(r'^([^:]*):\t(.*)')
s = self.id + '.'
l = len(s)
while 1:
@ -49,11 +49,11 @@ class Cdplayer:
break
if line[:l] == s:
line = line[l:]
if reg.match(line) == -1:
match = reg.match(line)
if not match:
print 'syntax error in ~/' + cdplayerrc
continue
name = line[reg.regs[1][0]:reg.regs[1][1]]
value = line[reg.regs[2][0]:reg.regs[2][1]]
name, valye = match.group(1, 2)
if name == 'title':
self.title = value
elif name == 'artist':

15
Lib/plat-irix6/flp.py
View File

@ -267,19 +267,18 @@ _parse_func = { \
# This function parses a line, and returns either
# a string or a tuple (name,value)
import regex
prog = regex.compile('^\([^:]*\): *\(.*\)')
import re
prog = re.compile('^([^:]*): *(.*)')
def _parse_line(line):
if prog.match(line) < 0:
match = prog.match(line)
if not match:
return line
a = prog.regs
name = line[:a[1][1]]
name, value = match.group(1, 2)
if name[0] == 'N':
name = string.joinfields(string.split(name),'')
name = string.join(string.split(name),'')
name = string.lower(name)
name = string.upper(name[0]) + name[1:]
value = line[a[2][0]:]
name = string.capitalize(name)
try:
pf = _parse_func[name]
except KeyError:

12
Lib/posixpath.py
View File

@ -266,15 +266,15 @@ def expandvars(path):
if '$' not in path:
return path
if not _varprog:
import regex
_varprog = regex.compile('$\([a-zA-Z0-9_]+\|{[^}]*}\)')
import re
_varprog = re.compile(r'\$(\w+|\{[^}]*\})')
i = 0
while 1:
i = _varprog.search(path, i)
if i < 0:
m = _varprog.search(path, i)
if not m:
break
name = _varprog.group(1)
j = i + len(_varprog.group(0))
i, j = m.span(0)
name = m.group(1)
if name[:1] == '{' and name[-1:] == '}':
name = name[1:-1]
if os.environ.has_key(name):

4
Lib/pstats.py
View File

@ -35,7 +35,7 @@ import os
import time
import string
import marshal
import regex
import re
#**************************************************************************
# Class Stats documentation
@ -300,7 +300,7 @@ class Stats:
if type(sel) == type(""):
new_list = []
for func in list:
if 0<=regex.search(sel, func_std_string(func)):
if re.search(sel, func_std_string(func)):
new_list.append(func)
else:
count = len(list)

9
Lib/rfc822.py
View File

@ -38,7 +38,7 @@
# There are also some utility functions here.
import regex
import re
import string
import time
@ -311,7 +311,7 @@ def unquote(str):
error = 'parseaddr.error'
specials = regex.compile('[][()<>,.;:@\\" \000-\037\177-\377]')
specials = re.compile(r'[][()<>,.;:@\" \000-\037\177-\377]')
def quote(str):
return '"%s"' % string.join(
@ -408,7 +408,7 @@ def parseaddr(address):
else:
name.append(token[1])
elif token[0] == 1 and cur is addr:
if specials.search(token[1]) >= 0:
if specials.search(token[1]):
cur.append(quote(token[1]))
else:
cur.append(token[1])
@ -423,7 +423,7 @@ def parseaddr(address):
if token[0] == 2:
name.append(token[1])
elif token[0] == 1:
if specials.search(token[1]) >= 0:
if specials.search(token[1]):
addr.append(quote(token[1]))
else:
addr.append(token[1])
@ -563,4 +563,3 @@ if __name__ == '__main__':
print 'keys =', m.keys()
print 'values =', m.values()
print 'items =', m.items()

9
Lib/string.py
View File

@ -193,17 +193,20 @@ def rfind(s, sub, i = 0, last=None):
return r
# Convert string to float
re = None
def atof(str):
import regex
global re
if re is None:
import re
sign = ''
s = str
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 regex.match('[0-9]*\(\.[0-9]*\)?\([eE][-+]?[0-9]+\)?', s) != len(s):
if 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))

9
Lib/stringold.py
View File

@ -193,17 +193,20 @@ def rfind(s, sub, i = 0, last=None):
return r
# Convert string to float
re = None
def atof(str):
import regex
global re
if re is None:
import re
sign = ''
s = str
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 regex.match('[0-9]*\(\.[0-9]*\)?\([eE][-+]?[0-9]+\)?', s) != len(s):
if 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))

18
Lib/token.py
View File

@ -7,10 +7,7 @@
# To update the symbols in this file, 'cd' to the top directory of
# the python source tree after building the interpreter and run:
#
# PYTHONPATH=./Lib ./python Lib/token.py
#
# (this path allows the import of string.py and regexmodule.so
# for a site with no installation in place)
# python Lib/token.py
#--start constants--
ENDMARKER = 0
@ -73,7 +70,7 @@ def ISEOF(x):
def main():
import regex
import re
import string
import sys
args = sys.argv[1:]
@ -88,13 +85,14 @@ def main():
sys.exit(1)
lines = string.splitfields(fp.read(), "\n")
fp.close()
re = regex.compile(
"#define[ \t][ \t]*\([A-Z][A-Z_]*\)[ \t][ \t]*\([0-9][0-9]*\)",
regex.casefold)
prog = re.compile(
"#define[ \t][ \t]*([A-Z][A-Z_]*)[ \t][ \t]*([0-9][0-9]*)",
re.IGNORECASE)
tokens = {}
for line in lines:
if re.match(line) > -1:
name, val = re.group(1, 2)
match = prog.match(line)
if match:
name, val = match.group(1, 2)
val = string.atoi(val)
tokens[val] = name # reverse so we can sort them...
keys = tokens.keys()

15
Lib/tzparse.py
View File

@ -2,23 +2,22 @@
# XXX Unfinished.
# XXX Only the typical form "XXXhhYYY;ddd/hh,ddd/hh" is currently supported.
tzpat = '^\([A-Z][A-Z][A-Z]\)\([-+]?[0-9]+\)\([A-Z][A-Z][A-Z]\);' + \
'\([0-9]+\)/\([0-9]+\),\([0-9]+\)/\([0-9]+\)$'
tzpat = ('^([A-Z][A-Z][A-Z])([-+]?[0-9]+)([A-Z][A-Z][A-Z]);'
'([0-9]+)/([0-9]+),([0-9]+)/([0-9]+)$')
tzprog = None
def tzparse(tzstr):
global tzprog
if tzprog == None:
import regex
tzprog = regex.compile(tzpat)
if tzprog.match(tzstr) < 0:
import re
tzprog = re.compile(tzpat)
match = tzprog.match(tzstr)
if not match:
raise ValueError, 'not the TZ syntax I understand'
regs = tzprog.regs
subs = []
for i in range(1, 8):
a, b = regs[i]
subs.append(tzstr[a:b])
subs.append(match.group(i))
for i in (1, 3, 4, 5, 6):
subs[i] = eval(subs[i])
[tzname, delta, dstname, daystart, hourstart, dayend, hourend] = subs