IDE-Bench/util.py at main · AfterQuery/IDE-Bench · GitHub

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
from typing import Any, Dict


def parse_task_description(task_description_text: str) -> Dict[str, Any]:
    result = {}

    lines = task_description_text.strip().split("\n")

    is_yaml_format = False
    if lines and lines[0].strip().startswith("task_description:"):
        is_yaml_format = True

    if is_yaml_format:
        in_task_description = False
        task_content_lines = []
        remaining_lines = []

        for i, line in enumerate(lines):
            stripped = line.strip()

            if stripped.startswith("task_description:"):
                in_task_description = True
                continue
            elif in_task_description:
                if line.startswith("  ") or not stripped:
                    task_content_lines.append(line[2:] if line.startswith("  ") else "")
                else:
                    remaining_lines = lines[i:]
                    break

        task_content = "\n".join(task_content_lines).strip()
        task_lines = task_content.split("\n")

        objective_lines = []
        in_objective = False

        for task_line in task_lines:
            task_line = task_line.strip()
            if not task_line:
                continue

            if ":" in task_line and not in_objective:
                key, value = task_line.split(":", 1)
                key = key.strip().lower().replace(" ", "_")
                value = value.strip()

                if key == "objective" or key == "instructions":
                    in_objective = True
                    if value:
                        objective_lines.append(value)
                else:
                    result[key] = value
            elif in_objective:
                objective_lines.append(task_line)

        if objective_lines:
            result["instructions"] = "\n".join(objective_lines).strip()

        for line in remaining_lines:
            line = line.strip()
            if not line:
                continue

            if ":" in line:
                key, value = line.split(":", 1)
                key = key.strip().lower().replace(" ", "_")
                value = value.strip()

                if key == "parser_name" and value.startswith("<"):
                    result[key] = value.strip("<>")
                else:
                    result[key] = value

        result.setdefault("author_name", "System")
        result.setdefault("author_email", "system@example.com")
        result.setdefault("difficulty", "medium")
        result.setdefault("category", "Backend")
        result.setdefault("tags", ["mern"])
        result.setdefault("parser_name", "jest")

        return result

    for line in lines:
        line = line.strip()
        if not line:
            continue

        if ":" in line:
            key, value = line.split(":", 1)
            key = key.strip().lower().replace(" ", "_")
            value = value.strip()

            if key == "tags" and value.startswith("<"):
                result[key] = [tag.strip("<>") for tag in value.split()]
            elif key == "parser_name" and value.startswith("<"):
                result[key] = value.strip("<>")
            else:
                result[key] = value

    instructions_lines = []
    in_instructions = False

    for line in lines:
        line = line.strip()
        if line.startswith("Instructions:"):
            in_instructions = True
            instructions_lines.append(line.split(":", 1)[1].strip())
        elif (
            in_instructions
            and line
            and not line.startswith(
                ("author_", "difficulty:", "category:", "tags:", "parser_name:")
            )
        ):
            instructions_lines.append(line)

    if instructions_lines:
        result["instructions"] = "\n".join(instructions_lines).strip()

    return result


def test_task_description_parser():
    sample_content = """task_description |
  Task: add is_odd
  Task ID: 001

  Instructions: add is_odd and have main.py print out whether or not the random
  number is odd.

author_name: Author Name
author_email: <you@example.com>
difficulty: easy
category: Feature
tags: <python>
parser_name: <pytest>"""

    parsed = parse_task_description(sample_content)

    print("Parsed task description:")
    print(f"Task: {parsed.get('task')}")
    print(f"Task ID: {parsed.get('task_id')}")
    print(f"Instructions: {parsed.get('instructions')}")
    print(f"Author: {parsed.get('author_name')}")
    print(f"Difficulty: {parsed.get('difficulty')}")
    print(f"Tags: {parsed.get('tags')}")
    print(f"Parser: {parsed.get('parser_name')}")

    return parsed


if __name__ == "__main__":
    test_task_description_parser()