-
Notifications
You must be signed in to change notification settings - Fork 4
/
Copy pathtest_script_content_reader.py
242 lines (229 loc) · 8.76 KB
/
test_script_content_reader.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
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
from typing import Literal, Optional
import pytest
from code_embedder.script_content_reader import ScriptContentReader
from code_embedder.script_metadata import ScriptMetadata
def create_script_metadata(
path: str,
extraction_type: Literal["full", "section", "object"] = "full",
extraction_part: Optional[str] = None,
content: str = "",
) -> ScriptMetadata:
return ScriptMetadata(
path=path,
extraction_part=extraction_part,
extraction_type=extraction_type,
readme_start=0,
readme_end=0,
content=content,
)
@pytest.mark.parametrize(
"script, expected_script",
[
# Full script
(
create_script_metadata(path="tests/data/example.py"),
create_script_metadata(
path="tests/data/example.py", content='print("Hello, World! from script")\n'
),
),
# Section
(
create_script_metadata(
path="tests/data/example_section.py",
extraction_part="A",
extraction_type="section",
),
create_script_metadata(
path="tests/data/example_section.py",
extraction_part="A",
extraction_type="section",
content=(
'print("Hello, World!")\n'
"# code_embedder:A start\n"
'print("Printing only section A")\n'
"# code_embedder:A end\n"
"\n"
"# code_embedder:B start\n"
'print("Printing only section B")\n'
"# code_embedder:B end\n"
),
),
),
# Full script with python objects
(
create_script_metadata(
path="tests/data/example_python_objects.py",
),
create_script_metadata(
path="tests/data/example_python_objects.py",
content=(
"import re\n"
"\n"
"\n"
"# Function verifying an email is valid\n"
"def verify_email(email: str) -> bool:\n"
' return re.match(r"^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+'
'$", email) is not None\n'
"\n"
"\n"
"class Person:\n"
" def __init__(self, name: str, age: int):\n"
" self.name = name\n"
" self.age = age\n"
"\n"
" # String representation of the class\n"
" def __str__(self) -> str:\n"
' return f"Person(name={self.name}, age={self.age})"\n'
),
),
),
],
ids=["full_script", "section_script", "full_script_with_python_objects"],
)
def test_read_full_script(script: ScriptMetadata, expected_script: ScriptMetadata):
script_content_reader = ScriptContentReader()
assert script_content_reader._read_full_script([script]) == [expected_script]
def test_read_full_script_unknown_path() -> None:
script_content_reader = ScriptContentReader()
with pytest.raises(FileNotFoundError):
script_content_reader._read_full_script(
[create_script_metadata(path="unknown_path.py")]
)
@pytest.mark.parametrize(
"script_metadata, expected_script_metadata",
[
# Section
(
create_script_metadata(
path="tests/data/example_section.py",
extraction_part="A",
extraction_type="section",
content=(
'print("Hello, World!")\n'
"# code_embedder:A start\n"
'print("Printing only section A")\n'
"# code_embedder:A end\n"
),
),
create_script_metadata(
path="tests/data/example_section.py",
extraction_part="A",
extraction_type="section",
content='print("Printing only section A")',
),
),
# Object
(
create_script_metadata(
path="tests/data/example_python_objects.py",
extraction_part="verify_email",
extraction_type="object",
content=(
"import re\n"
"# Function verifying an email is valid\n"
"def verify_email(email: str) -> bool:\n"
' return re.match(r"^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+'
'$", email) is not None\n'
"\n"
"class Person:\n"
" def __init__(self, name: str, age: int):\n"
" self.name = name\n"
" self.age = age\n"
"\n"
" # String representation of the class\n"
" def __str__(self) -> str:\n"
' return f"Person(name={self.name}, age={self.age})"\n'
),
),
create_script_metadata(
path="tests/data/example_python_objects.py",
extraction_part="verify_email",
extraction_type="object",
content=(
"def verify_email(email: str) -> bool:\n"
' return re.match(r"^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+'
'$", email) is not None'
),
),
),
# Object class
(
create_script_metadata(
path="tests/data/example_python_objects.py",
extraction_part="Person",
extraction_type="object",
content=(
"import re\n"
"# Function verifying an email is valid\n"
"def verify_email(email: str) -> bool:\n"
' return re.match(r"^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+'
'$", email) is not None\n'
"\n"
"class Person:\n"
" def __init__(self, name: str, age: int):\n"
" self.name = name\n"
" self.age = age\n"
"\n"
" # String representation of the class\n"
" def __str__(self) -> str:\n"
' return f"Person(name={self.name}, age={self.age})"\n'
),
),
create_script_metadata(
path="tests/data/example_python_objects.py",
extraction_part="Person",
extraction_type="object",
content=(
"class Person:\n"
" def __init__(self, name: str, age: int):\n"
" self.name = name\n"
" self.age = age\n"
"\n"
" # String representation of the class\n"
" def __str__(self) -> str:\n"
' return f"Person(name={self.name}, age={self.age})"'
),
),
),
],
ids=["section", "object", "object_class"],
)
def test_read_script_section(
script_metadata: ScriptMetadata, expected_script_metadata: ScriptMetadata
):
script_content_reader = ScriptContentReader()
assert script_content_reader._update_script_content_with_extraction_part(
[script_metadata]
) == [expected_script_metadata]
@pytest.mark.parametrize(
"script_metadata, error_message",
[
# Unknown section
(
create_script_metadata(
path="tests/data/example.py",
extraction_part="no_section",
extraction_type="section",
content='print("Hello, World! from script")\n',
),
"Part no_section not found in tests/data/example.py. "
"Either start and/or end of the section is missing.",
),
# Unknown object
(
create_script_metadata(
path="tests/data/example.py",
extraction_part="no_object",
extraction_type="object",
),
"Object no_object not found in tests/data/example.py. ",
),
],
ids=["unknown_section", "unknown_object"],
)
def test_read_script_unknown_extraction_part(
script_metadata: ScriptMetadata, error_message: str
) -> None:
script_content_reader = ScriptContentReader()
with pytest.raises(ValueError, match=error_message):
script_content_reader._update_script_content_with_extraction_part([script_metadata])