FilesExpand file tree

 master

/

splitinput.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

executable file

·

91 lines (74 loc) · 3.03 KB

 master

/

splitinput.py

Copy path

Top

File metadata and controls

• Code
• Blame

executable file

·

91 lines (74 loc) · 3.03 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

#!/usr/bin/env python

# encoding: utf-8

"""

Simple utility for splitting user input.

Authors:

* Brian Granger

* Fernando Perez

"""

#-----------------------------------------------------------------------------

# Copyright (C) 2008-2009 The IPython Development Team

#

# Distributed under the terms of the BSD License. The full license is in

# the file COPYING, distributed as part of this software.

#-----------------------------------------------------------------------------

#-----------------------------------------------------------------------------

# Imports

#-----------------------------------------------------------------------------

import re

import sys

#-----------------------------------------------------------------------------

# Main function

#-----------------------------------------------------------------------------

# RegExp for splitting line contents into pre-char//first word-method//rest.

# For clarity, each group in on one line.

# WARNING: update the regexp if the escapes in interactiveshell are changed, as they

# are hardwired in.

# Although it's not solely driven by the regex, note that:

# ,;/% only trigger if they are the first character on the line

# ! and !! trigger if they are first char(s) *or* follow an indent

# ? triggers as first or last char.

# The three parts of the regex are:

# 1) pre: pre_char *or* initial whitespace

# 2) ifun: first word/method (mix of \w and '.')

# 3) the_rest: rest of line (separated from ifun by space if non-empty)

line_split = re.compile(r'^([,;/%?]|!!?|\s*)'

r'\s*([\w\.]+)'

r'(\s+.*$|$)')

# r'[\w\.]+'

# r'\s*=\s*%.*'

def split_user_input(line, pattern=None):

"""Split user input into pre-char/whitespace, function part and rest.

This is currently handles lines with '=' in them in a very inconsistent

manner.

"""

# We need to ensure that the rest of this routine deals only with unicode

if type(line)==str:

codec = sys.stdin.encoding

if codec is None:

codec = 'utf-8'

line = line.decode(codec)

if pattern is None:

pattern = line_split

match = pattern.match(line)

if not match:

# print "match failed for line '%s'" % line

try:

ifun, the_rest = line.split(None,1)

except ValueError:

# print "split failed for line '%s'" % line

ifun, the_rest = line, u''

pre = re.match('^(\s*)(.*)',line).groups()[0]

else:

pre,ifun,the_rest = match.groups()

# ifun has to be a valid python identifier, so it better encode into

# ascii. We do still make it a unicode string so that we consistently

# return unicode, but it will be one that is guaranteed to be pure ascii

try:

ifun = unicode(ifun.encode('ascii'))

except UnicodeEncodeError:

the_rest = ifun + u' ' + the_rest

ifun = u''

#print 'line:<%s>' % line # dbg

#print 'pre <%s> ifun <%s> rest <%s>' % (pre,ifun.strip(),the_rest) # dbg

return pre, ifun.strip(), the_rest.lstrip()