init the project
This commit is contained in:
evyzacq
+238
@@ -0,0 +1,238 @@
|
||||
"""
|
||||
Tests for Stage 1 (Semantic Index).
|
||||
|
||||
Validates that the generated semantic_index.json meets all completeness
|
||||
and structural requirements.
|
||||
"""
|
||||
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
# Allow running from project root or tests/ directory
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent))
|
||||
import config
|
||||
|
||||
|
||||
PASS = "[PASS]"
|
||||
FAIL = "[FAIL]"
|
||||
WARN = "[WARN]"
|
||||
|
||||
|
||||
def load_inputs():
|
||||
"""Load semantic_index.json and the original parsed document."""
|
||||
try:
|
||||
si = config.load_json(config.SEMANTIC_INDEX_JSON)
|
||||
except FileNotFoundError:
|
||||
print(f"{FAIL} semantic_index.json 未找到: {config.SEMANTIC_INDEX_JSON}")
|
||||
print(" 请先运行 step1_semantic_index.py")
|
||||
sys.exit(1)
|
||||
|
||||
doc = config.load_input_document()
|
||||
return si, doc
|
||||
|
||||
|
||||
def build_image_index(doc: dict) -> dict[str, dict]:
|
||||
"""Build lookup: image rId -> image_analysis entry."""
|
||||
idx = {}
|
||||
for img in doc.get("image_analysis", []):
|
||||
rid = img.get("rid", "")
|
||||
if rid:
|
||||
idx[rid] = img
|
||||
return idx
|
||||
|
||||
|
||||
def build_logic_tree_node_index(doc: dict) -> dict[str, set[str]]:
|
||||
"""Build lookup: image rId -> set of all node IDs in that logic_tree."""
|
||||
idx = {}
|
||||
for img in doc.get("image_analysis", []):
|
||||
rid = img.get("rid", "")
|
||||
lt = img.get("logic_tree")
|
||||
if lt and rid:
|
||||
node_ids = {n["id"] for n in lt.get("nodes", [])}
|
||||
idx[rid] = node_ids
|
||||
return idx
|
||||
|
||||
|
||||
def check_unit_ids(units: list[dict]) -> list[str]:
|
||||
"""Check that every function_unit has a non-empty unit_id and name."""
|
||||
errors = []
|
||||
seen_ids = set()
|
||||
for i, fu in enumerate(units):
|
||||
uid = fu.get("unit_id", "")
|
||||
name = fu.get("name", "")
|
||||
if not uid:
|
||||
errors.append(f"function_unit[{i}]: unit_id 为空")
|
||||
elif uid in seen_ids:
|
||||
errors.append(f"function_unit[{i}]: unit_id '{uid}' 重复")
|
||||
seen_ids.add(uid)
|
||||
if not name:
|
||||
errors.append(f"function_unit[{i}] ({uid}): name 为空")
|
||||
return errors
|
||||
|
||||
|
||||
def check_sources_exist(
|
||||
units: list[dict], image_index: dict[str, dict], node_index: dict[str, set[str]]
|
||||
) -> list[str]:
|
||||
"""Check that all source references point to real content."""
|
||||
errors = []
|
||||
|
||||
for fu in units:
|
||||
uid = fu.get("unit_id", "?")
|
||||
sources = fu.get("sources", [])
|
||||
if not sources:
|
||||
errors.append(f"{uid}: sources 为空，必须至少引用一张图片或一段文字")
|
||||
continue
|
||||
|
||||
has_text = False
|
||||
has_image = False
|
||||
|
||||
for j, src in enumerate(sources):
|
||||
src_type = src.get("type", "")
|
||||
if src_type in ("table", "para"):
|
||||
has_text = True
|
||||
section = src.get("section", "")
|
||||
if not section:
|
||||
errors.append(f"{uid}.sources[{j}]: 缺少 section")
|
||||
elif src_type == "logic_tree":
|
||||
has_image = True
|
||||
image_id = src.get("image_id", "")
|
||||
if not image_id:
|
||||
errors.append(f"{uid}.sources[{j}]: logic_tree 缺少 image_id")
|
||||
continue
|
||||
|
||||
# Check image exists
|
||||
if image_id not in image_index:
|
||||
errors.append(
|
||||
f"{uid}.sources[{j}]: image_id '{image_id}' "
|
||||
f"在 image_analysis 中不存在"
|
||||
)
|
||||
continue
|
||||
|
||||
# Check logic_tree_nodes if provided
|
||||
node_ids = src.get("logic_tree_nodes", [])
|
||||
if node_ids and image_id in node_index:
|
||||
valid_nodes = node_index[image_id]
|
||||
for nid in node_ids:
|
||||
if nid not in valid_nodes:
|
||||
errors.append(
|
||||
f"{uid}.sources[{j}]: 节点 '{nid}' 在 "
|
||||
f"{image_id} 的逻辑树中不存在"
|
||||
)
|
||||
elif not node_ids:
|
||||
errors.append(
|
||||
f"{uid}.sources[{j}]: logic_tree 类型但未提供 logic_tree_nodes"
|
||||
)
|
||||
|
||||
if not has_text and not has_image:
|
||||
errors.append(f"{uid}: 必须至少引用一个文本或图片来源")
|
||||
|
||||
return errors
|
||||
|
||||
|
||||
def check_logic_tree_coverage(
|
||||
units: list[dict], node_index: dict[str, set[str]]
|
||||
) -> list[str]:
|
||||
"""Check that decision and action nodes in logic trees are covered."""
|
||||
warnings = []
|
||||
|
||||
for image_id, all_nodes in node_index.items():
|
||||
# Collect all nodes referenced across all function_units for this image
|
||||
referenced = set()
|
||||
for fu in units:
|
||||
for src in fu.get("sources", []):
|
||||
if src.get("image_id") == image_id:
|
||||
for nid in src.get("logic_tree_nodes", []):
|
||||
referenced.add(nid)
|
||||
|
||||
uncovered = all_nodes - referenced
|
||||
if uncovered:
|
||||
# Get node types from the document
|
||||
doc = config.load_input_document()
|
||||
node_types = {}
|
||||
for img in doc.get("image_analysis", []):
|
||||
if img.get("rid") == image_id:
|
||||
lt = img.get("logic_tree", {})
|
||||
for n in lt.get("nodes", []):
|
||||
node_types[n["id"]] = n.get("type", "?")
|
||||
break
|
||||
|
||||
decision_action_uncovered = [
|
||||
n for n in uncovered if node_types.get(n) in ("decision", "action")
|
||||
]
|
||||
if decision_action_uncovered:
|
||||
warnings.append(
|
||||
f"{image_id}: {len(decision_action_uncovered)} 个 "
|
||||
f"decision/action 节点未被引用: {decision_action_uncovered}"
|
||||
)
|
||||
|
||||
return warnings
|
||||
|
||||
|
||||
def run_all_tests():
|
||||
print("=" * 60)
|
||||
print("Step 1 自检测试")
|
||||
print("=" * 60)
|
||||
|
||||
si, doc = load_inputs()
|
||||
units = si.get("function_units", [])
|
||||
image_index = build_image_index(doc)
|
||||
node_index = build_logic_tree_node_index(doc)
|
||||
|
||||
all_errors = []
|
||||
all_warnings = []
|
||||
|
||||
# Test 1: unit_id and name validity
|
||||
errors = check_unit_ids(units)
|
||||
if errors:
|
||||
print(f"\n{FAIL} unit_id/name 检查: {len(errors)} 个错误")
|
||||
for e in errors:
|
||||
print(f" - {e}")
|
||||
all_errors.extend(errors)
|
||||
else:
|
||||
print(f"\n{PASS} unit_id/name 检查: 全部通过 ({len(units)} 个功能单元)")
|
||||
|
||||
# Test 2: source references exist
|
||||
errors = check_sources_exist(units, image_index, node_index)
|
||||
if errors:
|
||||
print(f"\n{FAIL} 来源引用检查: {len(errors)} 个错误")
|
||||
for e in errors:
|
||||
print(f" - {e}")
|
||||
all_errors.extend(errors)
|
||||
else:
|
||||
print(f"\n{PASS} 来源引用检查: 全部通过")
|
||||
|
||||
# Test 3: Logic tree coverage
|
||||
warnings = check_logic_tree_coverage(units, node_index)
|
||||
if warnings:
|
||||
print(f"\n{WARN} 逻辑树节点覆盖率: {len(warnings)} 个警告")
|
||||
for w in warnings:
|
||||
print(f" - {w}")
|
||||
all_warnings.extend(warnings)
|
||||
else:
|
||||
print(f"\n{PASS} 逻辑树节点覆盖率: 全部通过")
|
||||
|
||||
# Summary
|
||||
print(f"\n{'='*60}")
|
||||
total_failures = len(all_errors)
|
||||
total_warnings = len(all_warnings)
|
||||
|
||||
if total_failures == 0 and total_warnings == 0:
|
||||
print(f"{PASS} 所有测试通过!")
|
||||
elif total_failures == 0:
|
||||
print(f"{WARN} 全部通过但有 {total_warnings} 个警告")
|
||||
else:
|
||||
print(f"{FAIL} 测试失败: {total_failures} 个错误, {total_warnings} 个警告")
|
||||
print("\n请检查 LLM 输出质量，可能需要调整 Prompt 并重新运行 step1_semantic_index.py")
|
||||
|
||||
print(f"\n统计:")
|
||||
print(f" 功能单元数: {len(units)}")
|
||||
print(f" 概念数: {len(si.get('concepts', []))}")
|
||||
print(f" 逻辑树图片数: {len(node_index)}")
|
||||
|
||||
return total_failures == 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
success = run_all_tests()
|
||||
sys.exit(0 if success else 1)
|
||||
Reference in New Issue
Block a user