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
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
|
# coding: utf-8
"""String filters.
Contains a collection of useful string manipulation filters for use in Jinja
templates.
"""
#-----------------------------------------------------------------------------
# Copyright (c) 2013, the IPython Development Team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
#-----------------------------------------------------------------------------
#-----------------------------------------------------------------------------
# Imports
#-----------------------------------------------------------------------------
import os
import re
import textwrap
from urllib2 import quote
from xml.etree import ElementTree
from IPython.core.interactiveshell import InteractiveShell
from IPython.utils import py3compat
#-----------------------------------------------------------------------------
# Functions
#-----------------------------------------------------------------------------
__all__ = [
'wrap_text',
'html2text',
'add_anchor',
'strip_dollars',
'strip_files_prefix',
'comment_lines',
'get_lines',
'ipython2python',
'posix_path',
'path2url',
]
def wrap_text(text, width=100):
"""
Intelligently wrap text.
Wrap text without breaking words if possible.
Parameters
----------
text : str
Text to wrap.
width : int, optional
Number of characters to wrap to, default 100.
"""
split_text = text.split('\n')
wrp = map(lambda x:textwrap.wrap(x,width), split_text)
wrpd = map('\n'.join, wrp)
return '\n'.join(wrpd)
def html2text(element):
"""extract inner text from html
Analog of jQuery's $(element).text()
"""
if isinstance(element, py3compat.string_types):
element = ElementTree.fromstring(element)
text = element.text or ""
for child in element:
text += html2text(child)
text += (element.tail or "")
return text
def add_anchor(html):
"""Add an anchor-link to an html header tag
For use in heading cells
"""
h = ElementTree.fromstring(py3compat.cast_bytes_py2(html, encoding='utf-8'))
link = html2text(h).replace(' ', '-')
h.set('id', link)
a = ElementTree.Element("a", {"class" : "anchor-link", "href" : "#" + link})
a.text = u'ΒΆ'
h.append(a)
# Known issue of Python3.x, ElementTree.tostring() returns a byte string
# instead of a text string. See issue http://bugs.python.org/issue10942
# Workaround is to make sure the bytes are casted to a string.
return py3compat.decode(ElementTree.tostring(h), 'utf-8')
def strip_dollars(text):
"""
Remove all dollar symbols from text
Parameters
----------
text : str
Text to remove dollars from
"""
return text.strip('$')
files_url_pattern = re.compile(r'(src|href)\=([\'"]?)files/')
def strip_files_prefix(text):
"""
Fix all fake URLs that start with `files/`,
stripping out the `files/` prefix.
Parameters
----------
text : str
Text in which to replace 'src="files/real...' with 'src="real...'
"""
return files_url_pattern.sub(r"\1=\2", text)
def comment_lines(text, prefix='# '):
"""
Build a Python comment line from input text.
Parameters
----------
text : str
Text to comment out.
prefix : str
Character to append to the start of each line.
"""
#Replace line breaks with line breaks and comment symbols.
#Also add a comment symbol at the beginning to comment out
#the first line.
return prefix + ('\n'+prefix).join(text.split('\n'))
def get_lines(text, start=None,end=None):
"""
Split the input text into separate lines and then return the
lines that the caller is interested in.
Parameters
----------
text : str
Text to parse lines from.
start : int, optional
First line to grab from.
end : int, optional
Last line to grab from.
"""
# Split the input into lines.
lines = text.split("\n")
# Return the right lines.
return "\n".join(lines[start:end]) #re-join
def ipython2python(code):
"""Transform IPython syntax to pure Python syntax
Parameters
----------
code : str
IPython code, to be transformed to pure Python
"""
shell = InteractiveShell.instance()
return shell.input_transformer_manager.transform_cell(code)
def posix_path(path):
"""Turn a path into posix-style path/to/etc
Mainly for use in latex on Windows,
where native Windows paths are not allowed.
"""
if os.path.sep != '/':
return path.replace(os.path.sep, '/')
return path
def path2url(path):
"""Turn a file path into a URL"""
parts = path.split(os.path.sep)
return '/'.join(quote(part) for part in parts)
|
