feat: 匠厂数据管理展示元数据规范——元数据表初始化/校验、display_order 契约、文档与测试
All checks were successful
技能自动化发布 / release (push) Successful in 5s
All checks were successful
技能自动化发布 / release (push) Successful in 5s
This commit is contained in:
248
scripts/db/display_metadata_validator.py
Normal file
248
scripts/db/display_metadata_validator.py
Normal file
@@ -0,0 +1,248 @@
|
||||
"""数据管理展示元数据校验（模板开发自检，不依赖宿主）。"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import re
|
||||
import sqlite3
|
||||
from dataclasses import dataclass, field
|
||||
|
||||
from db.display_metadata import (
|
||||
METADATA_TABLES,
|
||||
TASK_LOGS_COLUMN_METADATA,
|
||||
TASK_LOGS_TABLE,
|
||||
iter_user_tables,
|
||||
list_physical_column_names,
|
||||
)
|
||||
from util.constants import SKILL_SLUG
|
||||
|
||||
_TEMPLATE_PLACEHOLDER_SLUGS = frozenset({"your-skill-slug", "your_skill_slug"})
|
||||
_ENGLISH_PLACEHOLDER_NAME_PATTERNS = (
|
||||
re.compile(r"^my\s+skill$", re.I),
|
||||
re.compile(r"^your[-_\s]?skill", re.I),
|
||||
re.compile(r"^skill[-_\s]?template$", re.I),
|
||||
re.compile(r"^[a-z0-9_-]+$"),
|
||||
)
|
||||
_KEBAB_SLUG = re.compile(r"^[a-z0-9]+(?:-[a-z0-9]+)*$")
|
||||
_CJK_RE = re.compile(r"[\u4e00-\u9fff]")
|
||||
|
||||
|
||||
@dataclass
|
||||
class ValidationReport:
|
||||
errors: list[str] = field(default_factory=list)
|
||||
warnings: list[str] = field(default_factory=list)
|
||||
|
||||
@property
|
||||
def ok(self) -> bool:
|
||||
return not self.errors
|
||||
|
||||
|
||||
def _has_cjk(text: str) -> bool:
|
||||
return bool(_CJK_RE.search(text))
|
||||
|
||||
|
||||
def _looks_like_raw_physical_name(display_name: str, physical_name: str) -> bool:
|
||||
if not display_name.strip():
|
||||
return True
|
||||
if display_name.strip().lower() == physical_name.strip().lower():
|
||||
return True
|
||||
compact = display_name.replace(" ", "").replace("_", "").lower()
|
||||
if compact == physical_name.replace("_", "").lower():
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def _parse_frontmatter_field(text: str, field_name: str) -> str:
|
||||
parts = text.split("---", 2)
|
||||
if len(parts) < 2:
|
||||
return ""
|
||||
for line in parts[1].splitlines():
|
||||
match = re.match(rf"^{re.escape(field_name)}:\s*(.+)\s*$", line.strip())
|
||||
if match:
|
||||
return match.group(1).strip().strip("\"'")
|
||||
return ""
|
||||
|
||||
|
||||
def _parse_openclaw_slug(text: str) -> str:
|
||||
parts = text.split("---", 2)
|
||||
if len(parts) < 2:
|
||||
return ""
|
||||
lines = parts[1].splitlines()
|
||||
for index, line in enumerate(lines):
|
||||
if re.match(r"^\s+openclaw:\s*$", line):
|
||||
for inner in lines[index + 1 :]:
|
||||
if inner.strip() and inner[0] not in (" ", "\t"):
|
||||
break
|
||||
match = re.match(r"^(\s+)slug:\s*(.+)\s*$", inner)
|
||||
if match:
|
||||
return match.group(2).strip().strip("\"'")
|
||||
return ""
|
||||
|
||||
|
||||
def parse_skill_frontmatter(skill_root: str) -> dict[str, str]:
|
||||
path = os.path.join(skill_root, "SKILL.md")
|
||||
with open(path, encoding="utf-8") as f:
|
||||
text = f.read()
|
||||
return {
|
||||
"name": _parse_frontmatter_field(text, "name"),
|
||||
"slug": _parse_openclaw_slug(text),
|
||||
}
|
||||
|
||||
|
||||
def validate_skill_frontmatter(skill_root: str, *, allow_template_placeholders: bool = True) -> ValidationReport:
|
||||
report = ValidationReport()
|
||||
data = parse_skill_frontmatter(skill_root)
|
||||
name = str(data.get("name") or "").strip()
|
||||
slug = str(data.get("slug") or "").strip()
|
||||
|
||||
if not name:
|
||||
report.errors.append("SKILL.md frontmatter.name 缺失")
|
||||
elif not _has_cjk(name):
|
||||
if allow_template_placeholders and slug in _TEMPLATE_PLACEHOLDER_SLUGS:
|
||||
report.warnings.append("SKILL.md frontmatter.name 建议使用清晰的中文业务名称（模板占位可暂保留）")
|
||||
else:
|
||||
report.errors.append("SKILL.md frontmatter.name 应使用用户可见的中文业务名称")
|
||||
else:
|
||||
for pattern in _ENGLISH_PLACEHOLDER_NAME_PATTERNS:
|
||||
if pattern.fullmatch(name):
|
||||
if allow_template_placeholders and slug in _TEMPLATE_PLACEHOLDER_SLUGS:
|
||||
report.warnings.append(f"SKILL.md frontmatter.name 仍为占位风格：{name!r}")
|
||||
else:
|
||||
report.errors.append(f"SKILL.md frontmatter.name 不应为英文占位名：{name!r}")
|
||||
break
|
||||
|
||||
if not slug:
|
||||
report.errors.append("SKILL.md metadata.openclaw.slug 缺失")
|
||||
elif not _KEBAB_SLUG.fullmatch(slug):
|
||||
report.errors.append(f"metadata.openclaw.slug 必须为 kebab-case：{slug!r}")
|
||||
elif slug in _TEMPLATE_PLACEHOLDER_SLUGS and not allow_template_placeholders:
|
||||
report.errors.append(f"metadata.openclaw.slug 仍为模板占位：{slug!r}")
|
||||
|
||||
constants_slug = SKILL_SLUG.strip()
|
||||
if slug and constants_slug and slug != constants_slug:
|
||||
report.warnings.append(
|
||||
f"SKILL.md slug ({slug!r}) 与 util.constants.SKILL_SLUG ({constants_slug!r}) 不一致"
|
||||
)
|
||||
|
||||
return report
|
||||
|
||||
|
||||
def column_order_warnings(table_name: str, ordered_names: list[str]) -> list[str]:
|
||||
warnings: list[str] = []
|
||||
if "id" in ordered_names and ordered_names.index("id") != 0:
|
||||
warnings.append(f"{table_name}: 字段 id 通常应定义在 CREATE TABLE 的第一列")
|
||||
if "created_at" in ordered_names:
|
||||
idx = ordered_names.index("created_at")
|
||||
trailing = ordered_names[idx + 1 :]
|
||||
if trailing and trailing != ["updated_at"]:
|
||||
warnings.append(
|
||||
f"{table_name}: created_at 之后通常只应跟 updated_at，不应再放置其他业务字段"
|
||||
)
|
||||
if "updated_at" in ordered_names and "created_at" in ordered_names:
|
||||
if ordered_names.index("updated_at") < ordered_names.index("created_at"):
|
||||
warnings.append(f"{table_name}: updated_at 不应出现在 created_at 之前")
|
||||
return warnings
|
||||
|
||||
|
||||
def _table_exists(cursor, table_name: str) -> bool:
|
||||
cursor.execute(
|
||||
"SELECT 1 FROM sqlite_master WHERE type = 'table' AND name = ? LIMIT 1",
|
||||
(table_name,),
|
||||
)
|
||||
return cursor.fetchone() is not None
|
||||
|
||||
|
||||
def validate_display_metadata(conn: sqlite3.Connection, *, check_column_order: bool = True) -> ValidationReport:
|
||||
report = ValidationReport()
|
||||
cur = conn.cursor()
|
||||
|
||||
has_tables_meta = _table_exists(cur, "_jiangchang_tables")
|
||||
has_columns_meta = _table_exists(cur, "_jiangchang_columns")
|
||||
if not has_tables_meta:
|
||||
report.errors.append("缺少数据管理元数据表 _jiangchang_tables")
|
||||
if not has_columns_meta:
|
||||
report.errors.append("缺少数据管理元数据表 _jiangchang_columns")
|
||||
if not has_tables_meta or not has_columns_meta:
|
||||
return report
|
||||
|
||||
for table_name in iter_user_tables(cur):
|
||||
cur.execute(
|
||||
"SELECT display_name FROM _jiangchang_tables WHERE table_name = ?",
|
||||
(table_name,),
|
||||
)
|
||||
row = cur.fetchone()
|
||||
if not row or not str(row[0] or "").strip():
|
||||
report.errors.append(f"业务表 {table_name!r} 缺少 _jiangchang_tables.display_name")
|
||||
elif not _has_cjk(str(row[0])):
|
||||
report.errors.append(f"业务表 {table_name!r} 的 display_name 应使用中文业务名称")
|
||||
|
||||
physical_columns = list_physical_column_names(cur, table_name)
|
||||
if check_column_order:
|
||||
report.warnings.extend(column_order_warnings(table_name, physical_columns))
|
||||
|
||||
for column_name in physical_columns:
|
||||
cur.execute(
|
||||
"""
|
||||
SELECT display_name, visible
|
||||
FROM _jiangchang_columns
|
||||
WHERE table_name = ? AND column_name = ?
|
||||
""",
|
||||
(table_name, column_name),
|
||||
)
|
||||
col_row = cur.fetchone()
|
||||
if not col_row:
|
||||
report.errors.append(
|
||||
f"字段 {table_name}.{column_name} 缺少 _jiangchang_columns 元数据"
|
||||
)
|
||||
continue
|
||||
display_name = str(col_row[0] or "").strip()
|
||||
visible = col_row[1] is None or int(col_row[1]) != 0
|
||||
if visible and not display_name:
|
||||
report.errors.append(f"字段 {table_name}.{column_name} 的 display_name 为空")
|
||||
elif visible and _looks_like_raw_physical_name(display_name, column_name):
|
||||
report.errors.append(
|
||||
f"字段 {table_name}.{column_name} 的 display_name 不应直接等于英文物理名：{display_name!r}"
|
||||
)
|
||||
elif visible and not _has_cjk(display_name):
|
||||
report.errors.append(
|
||||
f"字段 {table_name}.{column_name} 的 display_name 应使用中文：{display_name!r}"
|
||||
)
|
||||
|
||||
cur.execute("SELECT table_name, column_name FROM _jiangchang_columns")
|
||||
for table_name, column_name in cur.fetchall():
|
||||
if table_name in METADATA_TABLES:
|
||||
continue
|
||||
cur.execute(
|
||||
"SELECT 1 FROM sqlite_master WHERE type='table' AND name = ?",
|
||||
(table_name,),
|
||||
)
|
||||
if not cur.fetchone():
|
||||
report.errors.append(f"元数据引用了不存在的表：{table_name!r}")
|
||||
continue
|
||||
physical = list_physical_column_names(cur, str(table_name))
|
||||
if str(column_name) not in physical:
|
||||
report.errors.append(f"元数据引用了不存在的字段：{table_name}.{column_name}")
|
||||
|
||||
cur.execute("SELECT table_name FROM _jiangchang_tables")
|
||||
for (table_name,) in cur.fetchall():
|
||||
if table_name in METADATA_TABLES:
|
||||
continue
|
||||
cur.execute(
|
||||
"SELECT 1 FROM sqlite_master WHERE type='table' AND name = ?",
|
||||
(table_name,),
|
||||
)
|
||||
if not cur.fetchone():
|
||||
report.errors.append(f"元数据引用了不存在的表：{table_name!r}")
|
||||
|
||||
return report
|
||||
|
||||
|
||||
def validate_template_database(conn: sqlite3.Connection) -> ValidationReport:
|
||||
report = validate_display_metadata(conn)
|
||||
physical = list_physical_column_names(conn.cursor(), TASK_LOGS_TABLE)
|
||||
expected = [str(item["column_name"]) for item in TASK_LOGS_COLUMN_METADATA]
|
||||
if physical != expected:
|
||||
report.errors.append(
|
||||
f"task_logs 物理字段顺序应为 {expected}，当前为 {physical}"
|
||||
)
|
||||
return report
|
||||
Reference in New Issue
Block a user