forked from ucbds-infra/otter-grader
/
solutions.py
173 lines (129 loc) · 4.57 KB
/
solutions.py
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
"""Solution removal for Otter Assign"""
import re
import nbformat
from .utils import get_source, has_tag, is_cell_type, remove_output, remove_tag
SOLUTION_CELL_TAG = "otter_assign_solution_cell"
def has_seed(cell):
if not is_cell_type(cell, "code"):
return False
source = get_source(cell)
return source and any([l.strip().endswith('# SEED') for l in source])
solution_assignment_regex = re.compile(r"(\s*[a-zA-Z0-9_. ]*(=|<-))(.*)[ ]?#[ ]?SOLUTION")
def solution_assignment_sub(match):
"""
Substitutes the first matching group with ` ...`
"""
prefix = match.group(1)
return prefix + ' ...'
solution_line_regex = re.compile(r"(\s*)([^#\n]+)[ ]?#[ ]?SOLUTION")
def solution_line_sub(match):
"""
Substitutes the first matching group with `...`
"""
prefix = match.group(1)
return prefix + '...'
begin_solution_regex = re.compile(r"(\s*)# BEGIN SOLUTION( NO PROMPT)?")
skip_suffixes = ['# SOLUTION NO PROMPT', '# BEGIN PROMPT', '# END PROMPT', '# SEED']
SUBSTITUTIONS = [
(solution_assignment_regex, solution_assignment_sub),
(solution_line_regex, solution_line_sub),
]
# TODO: comments, docstrings
def replace_solutions(lines):
"""
Replaces solutions in ``lines``
Args:
lines (``list`` of ``str``): solutions as a list of strings
Returns:
``list`` of ``str``: stripped version of lines without solutions
"""
stripped = []
solution = False
for line in lines:
# ...
if any(line.rstrip().endswith(s) for s in skip_suffixes):
continue
# ...
if solution and not line.rstrip().endswith('# END SOLUTION'):
continue
# ...
if line.rstrip().endswith('# END SOLUTION'):
assert solution, f"END SOLUTION without BEGIN SOLUTION in {lines}"
solution = False
continue
# ...
begin_solution = begin_solution_regex.match(line)
if begin_solution:
assert not solution, f"Nested BEGIN SOLUTION in {lines}"
solution = True
if not begin_solution.group(2):
line = begin_solution.group(1) + '...'
else:
continue
for exp, sub in SUBSTITUTIONS:
m = exp.match(line)
if m:
line = sub(m)
stripped.append(line)
assert not solution, f"BEGIN SOLUTION without END SOLUTION in {lines}"
return stripped
def remove_ignored_lines(lines):
"""
Removes ignored lines in ``lines``
Args:
lines (``list`` of ``str``): cell source as a list of strings
Returns:
``list`` of ``str``: stripped version of lines without ignored lines
"""
ignore_suffix = "# IGNORE"
stripped = []
in_block = False
for line in lines:
# ...
if line.rstrip().endswith(ignore_suffix):
continue
# ...
if in_block and not line.rstrip().endswith('# END IGNORE'):
continue
# ...
if line.rstrip().endswith('# END IGNORE'):
assert in_block, f"END IGNORE without BEGIN IGNORE in {lines}"
in_block = False
continue
# ...
if re.match(r"\s*#\s*BEGIN\s*IGNORE\s*", line, flags=re.IGNORECASE):
assert not in_block, f"Nested BEGIN IGNORE in {lines}"
in_block = True
continue
stripped.append(line)
assert not in_block, f"BEGIN IGNORE without END IGNORE in {lines}"
return stripped
def strip_ignored_lines(nb):
"""
Write a notebook with ignored lines stripped
Args:
nb (``nbformat.NotebookNode``): the notebook to have ignored lines stripped
"""
for i, cell in enumerate(nb['cells']):
cell['source'] = '\n'.join(remove_ignored_lines(get_source(cell)))
return nb
def strip_solutions_and_output(nb):
"""
Write a notebook with solutions stripped and outputs cleared
Args:
nb (``nbformat.NotebookNode``): the notebook to have solutions stripped
"""
md_solutions = []
for i, cell in enumerate(nb['cells']):
if has_tag(cell, SOLUTION_CELL_TAG):
if is_cell_type(cell, "code"):
cell['source'] = '\n'.join(replace_solutions(get_source(cell)))
elif is_cell_type(cell, "markdown"):
md_solutions.append(i)
nb['cells'][i] = remove_tag(cell, SOLUTION_CELL_TAG)
md_solutions.reverse()
for i in md_solutions:
del nb['cells'][i]
# remove output from student version
remove_output(nb)
return nb