Files
daily-paper/scripts/validate_summary.py
T

145 lines
5.5 KiB
Python

import json
import sys
schema = {
"type": "object",
"required": ["arxiv_id", "title_zh", "one_line", "tags", "difficulty",
"prerequisites", "motivation", "method", "results", "improvements", "figures"],
"properties": {
"arxiv_id": {"type": "string"},
"title_zh": {"type": "string"},
"one_line": {"type": "string"},
"tags": {"type": "array", "items": {"type": "string"}},
"difficulty": {"type": "string", "enum": ["入门", "进阶", "前沿"]},
"prerequisites": {
"type": "object",
"required": ["concepts"],
"properties": {
"concepts": {"type": "array", "items": {
"type": "object",
"required": ["term", "explanation", "why_matters"],
"properties": {
"term": {"type": "string"},
"explanation": {"type": "string"},
"why_matters": {"type": "string"}
}
}}
}
},
"motivation": {
"type": "object",
"required": ["problem", "goal", "gap"],
"properties": {
"problem": {"type": "string"},
"goal": {"type": "string"},
"gap": {"type": "string"}
}
},
"method": {
"type": "object",
"required": ["overview", "key_idea", "steps", "novelty"],
"properties": {
"overview": {"type": "string"},
"key_idea": {"type": "string"},
"steps": {"type": "string"},
"novelty": {"type": "string"}
}
},
"results": {
"type": "object",
"required": ["main_findings", "benchmarks", "limitations"],
"properties": {
"main_findings": {"type": "string"},
"benchmarks": {"type": "array", "items": {
"type": "object",
"required": ["task", "metric", "this_work", "baseline", "improvement"],
"properties": {
"task": {"type": "string"},
"metric": {"type": "string"},
"this_work": {"type": "string"},
"baseline": {"type": "string"},
"improvement": {"type": "string"}
}
}},
"limitations": {"type": "string"}
}
},
"improvements": {
"type": "object",
"required": ["weaknesses", "future_work", "reproducibility"],
"properties": {
"weaknesses": {"type": "string"},
"future_work": {"type": "string"},
"reproducibility": {"type": "string"}
}
},
"figures": {
"type": "array",
"items": {
"type": "object",
"required": ["id", "caption", "description", "reason", "section"],
"properties": {
"id": {"type": "string"},
"caption": {"type": "string"},
"description": {"type": "string"},
"reason": {"type": "string"},
"section": {"type": "string", "enum": ["motivation", "method", "results", "limitations"]}
}
}
}
}
}
def validate_file(filepath):
try:
with open(filepath, 'r', encoding='utf-8') as f:
data = json.load(f)
# Check required fields
for field in schema["required"]:
if field not in data:
print(f"❌ Missing field: {field}")
return False
# Validate nested structure
for field, spec in schema["properties"].items():
if field in data:
if spec["type"] == "string":
if not isinstance(data[field], str):
print(f"❌ Field '{field}' should be string")
return False
elif spec["type"] == "array":
if not isinstance(data[field], list):
print(f"❌ Field '{field}' should be array")
return False
elif spec["type"] == "object":
if not isinstance(data[field], dict):
print(f"❌ Field '{field}' should be object")
return False
if "required" in spec:
for subfield in spec["required"]:
if subfield not in data[field]:
print(f"❌ Missing subfield: {field}.{subfield}")
return False
# Validate section enum in figures
valid_sections = ["motivation", "method", "results", "limitations"]
for fig in data.get("figures", []):
if fig["section"] not in valid_sections:
print(f"❌ Invalid section in figure: {fig['section']}")
return False
print("✅ JSON validation passed!")
return True
except json.JSONDecodeError as e:
print(f"❌ JSON decode error: {e}")
return False
except Exception as e:
print(f"❌ Validation error: {e}")
return False
if __name__ == "__main__":
filepath = sys.argv[1] if len(sys.argv) > 1 else "data/papers/2601.10592/summary.json"
validate_file(filepath)