camelcase(ustr, maxlen=None)

Convert a unicode string into CamelCase.

>>> camelcase(u"Abc")
u'Abc'
>>> camelcase(u"abc")
u'Abc'
>>> camelcase(u"ABC")
u'Abc'

>>> camelcase(u"This is a text")
u'ThisIsAText'
>>> camelcase(u"This is a text", None)
u'ThisIsAText'

When maxlen is not None, each word is truncated to the length maxlen.

>>> camelcase(u"This is a text", 4)
u'ThisIsAText'
>>> camelcase(u"This is a text", 3)
u'ThiIsATex'
>>> camelcase(u"This is a text", 2)
u'ThIsATe'
>>> camelcase(u"This is a text", 1)
u'TIAT'
>>> camelcase(u"This is a text", 0)
u''

>>> camelcase(u"")
u''

Parameters:

ustr -

unicode string to convert

maxlen -

maximum length of each word (default: None)

escape_latex(s)

Escape a unicode string for LaTeX.

>>> s = u'\\"{}_&%a$b#\nc"\\'
>>> escape_latex(s)
u"\\textbackslash{}{''}\\{\\}\\_\\&\\%a\\$b\\#\\\\c{''}\\textbackslash{}"
>>> print s
\"{}_&%a$b#
c"\
>>> print escape_latex(s)
\textbackslash{}{''}\{\}\_\&\%a\$b\#\\c{''}\textbackslash{}

Parameters:

s -

unicode object to escape for LaTeX

Warning:

The source string must not contain empty lines such as:

• u"n..." -- empty first line
• u"...nn..." -- empty line in between
• u"...n" -- empty last line

readlines(obj, encoding=u'utf8')

Return an iterator that steps through the lines of obj.

Line endings are preserved. The iterator returns unicode objects.

>>> obj = u"Line1\nLine2\nLine3"
>>> for line in readlines(obj):
...     print repr(line)
u'Line1\n'
u'Line2\n'
u'Line3'

>>> obj = u"Line1\nLine2\nLine3\n"
>>> for line in readlines(obj):
...     print repr(line)
u'Line1\n'
u'Line2\n'
u'Line3\n'

>>> obj = "Line1\nLine2\nLine3\n"
>>> for line in readlines(obj):
...     print repr(line)
u'Line1\n'
u'Line2\n'
u'Line3\n'

>>> import os
>>> stream = os.tmpfile()
>>> stream.write("Line1\nLine2\nLine3\n")
>>> stream.seek(0)
>>> for line in readlines(obj):
...     print repr(line)
u'Line1\n'
u'Line2\n'
u'Line3\n'

Parameters:

obj -

byte string, byte stream or unicode object to read from

encoding -

encoding of obj (default: UTF-8)

split_labeled_uri(labeleduri, default=u'')

Split a labeled URI into its URI and its label.

If the labeled URI doesn't contain a label, return the default label.

>>> split_labeled_uri(u"http://www.google.com/ This is Google.")
(u'http://www.google.com/', u'This is Google.')

>>> split_labeled_uri(u"http://www.google.com/  \t surrounding spaces ")
(u'http://www.google.com/', u'surrounding spaces')

>>> split_labeled_uri(u"http://www.google.com/ given label", u"default label")
(u'http://www.google.com/', u'given label')

>>> split_labeled_uri(u"http://www.google.com/", u"default label")
(u'http://www.google.com/', u'default label')

Parameters:

labeleduri -

unicode string containing the labeled URI

default -

fallback label (default: u"")

UnicodeStream(stream, encoding=u'utf8')

Stream wrapper which automatically encodes and decodes.

Simpler interface to the codecs package.

Return a stream whose methods read(), write(), ... take and return only unicode objects. These are encoded to and decoded from the given stream using the given encoding.

>>> import sys
>>> ustream = UnicodeStream(sys.stdout)
>>> ustream.write(u"abc")
abc

>>> import os
>>> stream = os.tmpfile()
>>> stream.write("abc")
>>> stream.seek(0)
>>> ustream = UnicodeStream(stream)
>>> ustream.read()
u'abc'

Parameters:

stream -

byte stream to wrap

encoding -

encoding of stream (default: UTF-8)