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
|
"""Read and write notebook files as XML.
Authors:
* Brian Granger
"""
#-----------------------------------------------------------------------------
# Copyright (C) 2008-2011 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
#-----------------------------------------------------------------------------
from base64 import encodestring, decodestring
import warnings
from xml.etree import ElementTree as ET
from .rwbase import NotebookReader, NotebookWriter
from .nbbase import (
new_code_cell, new_text_cell, new_worksheet, new_notebook, new_output,
new_metadata
)
#-----------------------------------------------------------------------------
# Code
#-----------------------------------------------------------------------------
def indent(elem, level=0):
i = "\n" + level*" "
if len(elem):
if not elem.text or not elem.text.strip():
elem.text = i + " "
if not elem.tail or not elem.tail.strip():
elem.tail = i
for elem in elem:
indent(elem, level+1)
if not elem.tail or not elem.tail.strip():
elem.tail = i
else:
if level and (not elem.tail or not elem.tail.strip()):
elem.tail = i
def _get_text(e, tag):
sub_e = e.find(tag)
if sub_e is None:
return None
else:
return sub_e.text
def _set_text(nbnode, attr, parent, tag):
if attr in nbnode:
e = ET.SubElement(parent, tag)
e.text = nbnode[attr]
def _get_int(e, tag):
sub_e = e.find(tag)
if sub_e is None:
return None
else:
return int(sub_e.text)
def _set_int(nbnode, attr, parent, tag):
if attr in nbnode:
e = ET.SubElement(parent, tag)
e.text = unicode(nbnode[attr])
def _get_bool(e, tag):
sub_e = e.find(tag)
if sub_e is None:
return None
else:
return bool(int(sub_e.text))
def _set_bool(nbnode, attr, parent, tag):
if attr in nbnode:
e = ET.SubElement(parent, tag)
if nbnode[attr]:
e.text = u'1'
else:
e.text = u'0'
def _get_binary(e, tag):
sub_e = e.find(tag)
if sub_e is None:
return None
else:
return decodestring(sub_e.text)
def _set_binary(nbnode, attr, parent, tag):
if attr in nbnode:
e = ET.SubElement(parent, tag)
e.text = encodestring(nbnode[attr])
class XMLReader(NotebookReader):
def reads(self, s, **kwargs):
root = ET.fromstring(s)
return self.to_notebook(root, **kwargs)
def to_notebook(self, root, **kwargs):
warnings.warn('The XML notebook format is no longer supported, '
'please convert your notebooks to JSON.', DeprecationWarning)
nbname = _get_text(root,u'name')
nbauthor = _get_text(root,u'author')
nbemail = _get_text(root,u'email')
nblicense = _get_text(root,u'license')
nbcreated = _get_text(root,u'created')
nbsaved = _get_text(root,u'saved')
worksheets = []
for ws_e in root.find(u'worksheets').getiterator(u'worksheet'):
wsname = _get_text(ws_e,u'name')
cells = []
for cell_e in ws_e.find(u'cells').getiterator():
if cell_e.tag == u'codecell':
input = _get_text(cell_e,u'input')
prompt_number = _get_int(cell_e,u'prompt_number')
collapsed = _get_bool(cell_e,u'collapsed')
language = _get_text(cell_e,u'language')
outputs = []
for output_e in cell_e.find(u'outputs').getiterator(u'output'):
output_type = _get_text(output_e,u'output_type')
output_text = _get_text(output_e,u'text')
output_png = _get_binary(output_e,u'png')
output_jpeg = _get_binary(output_e,u'jpeg')
output_svg = _get_text(output_e,u'svg')
output_html = _get_text(output_e,u'html')
output_latex = _get_text(output_e,u'latex')
output_json = _get_text(output_e,u'json')
output_javascript = _get_text(output_e,u'javascript')
out_prompt_number = _get_int(output_e,u'prompt_number')
etype = _get_text(output_e,u'etype')
evalue = _get_text(output_e,u'evalue')
traceback = []
traceback_e = output_e.find(u'traceback')
if traceback_e is not None:
for frame_e in traceback_e.getiterator(u'frame'):
traceback.append(frame_e.text)
if len(traceback) == 0:
traceback = None
output = new_output(output_type=output_type,output_png=output_png,
output_text=output_text, output_svg=output_svg,
output_html=output_html, output_latex=output_latex,
output_json=output_json, output_javascript=output_javascript,
output_jpeg=output_jpeg, prompt_number=out_prompt_number,
etype=etype, evalue=evalue, traceback=traceback
)
outputs.append(output)
cc = new_code_cell(input=input,prompt_number=prompt_number,
language=language,outputs=outputs,collapsed=collapsed)
cells.append(cc)
if cell_e.tag == u'htmlcell':
source = _get_text(cell_e,u'source')
rendered = _get_text(cell_e,u'rendered')
cells.append(new_text_cell(u'html', source=source, rendered=rendered))
if cell_e.tag == u'markdowncell':
source = _get_text(cell_e,u'source')
rendered = _get_text(cell_e,u'rendered')
cells.append(new_text_cell(u'markdown', source=source, rendered=rendered))
ws = new_worksheet(name=wsname,cells=cells)
worksheets.append(ws)
md = new_metadata(name=nbname)
nb = new_notebook(metadata=md,worksheets=worksheets)
return nb
_reader = XMLReader()
reads = _reader.reads
read = _reader.read
to_notebook = _reader.to_notebook
|
