284 lines
11 KiB
Python
284 lines
11 KiB
Python
#!/usr/bin/env python3
|
|
"""Compare sys_dict_type / sys_dict_data across SQL snapshots."""
|
|
from __future__ import annotations
|
|
|
|
import re
|
|
from collections import defaultdict
|
|
from pathlib import Path
|
|
|
|
ROOT = Path(__file__).resolve().parents[2]
|
|
SX_SQL = ROOT / "docs/sql/sx.sql"
|
|
PORTAL_SQL = ROOT / "docs/sql/shanxia2.0.sql"
|
|
DIBANG_SQL = ROOT / "docs/sql/dibang.sql"
|
|
|
|
|
|
def parse_insert_values(line: str) -> list[str] | None:
|
|
m = re.search(r"VALUES\s*\((.*)\)\s*;?\s*$", line, re.I)
|
|
if not m:
|
|
return None
|
|
inner = m.group(1)
|
|
parts: list[str] = []
|
|
cur: list[str] = []
|
|
in_str = False
|
|
esc = False
|
|
for ch in inner:
|
|
if esc:
|
|
cur.append(ch)
|
|
esc = False
|
|
continue
|
|
if ch == "\\":
|
|
esc = True
|
|
cur.append(ch)
|
|
continue
|
|
if ch == "'":
|
|
in_str = not in_str
|
|
cur.append(ch)
|
|
continue
|
|
if ch == "," and not in_str:
|
|
parts.append("".join(cur).strip())
|
|
cur = []
|
|
continue
|
|
cur.append(ch)
|
|
if cur:
|
|
parts.append("".join(cur).strip())
|
|
return parts
|
|
|
|
|
|
def unquote(v: str) -> str:
|
|
v = v.strip()
|
|
if v.upper() == "NULL":
|
|
return ""
|
|
if v.startswith("'") and v.endswith("'"):
|
|
return v[1:-1].replace("''", "'").replace("\\'", "'")
|
|
return v
|
|
|
|
|
|
def load_sx_dicts(path: Path) -> tuple[dict[str, dict], dict[str, list[dict]]]:
|
|
types: dict[str, dict] = {}
|
|
data_by_type: dict[str, list[dict]] = defaultdict(list)
|
|
for line in path.read_text(encoding="utf-8", errors="ignore").splitlines():
|
|
if "INSERT INTO `sys_dict_type`" in line:
|
|
vals = parse_insert_values(line)
|
|
if not vals or len(vals) < 4:
|
|
continue
|
|
# dict_id, tenant_id, dict_name, dict_type, ...
|
|
dict_type = unquote(vals[3])
|
|
types[dict_type] = {
|
|
"dict_name": unquote(vals[2]),
|
|
"tenant_id": unquote(vals[1]),
|
|
"remark": unquote(vals[9]) if len(vals) > 9 else "",
|
|
}
|
|
elif "INSERT INTO `sys_dict_data`" in line:
|
|
vals = parse_insert_values(line)
|
|
if not vals or len(vals) < 6:
|
|
continue
|
|
# dict_code, tenant_id, dict_sort, dict_label, dict_value, dict_type, ...
|
|
dict_type = unquote(vals[5])
|
|
data_by_type[dict_type].append(
|
|
{
|
|
"label": unquote(vals[3]),
|
|
"value": unquote(vals[4]),
|
|
"sort": unquote(vals[2]),
|
|
"css_class": unquote(vals[6]) if len(vals) > 6 else "",
|
|
"list_class": unquote(vals[7]) if len(vals) > 7 else "",
|
|
}
|
|
)
|
|
return types, data_by_type
|
|
|
|
|
|
def load_portal_dicts(path: Path) -> tuple[dict[str, dict], dict[str, list[dict]]]:
|
|
types: dict[str, dict] = {}
|
|
data_by_type: dict[str, list[dict]] = defaultdict(list)
|
|
for line in path.read_text(encoding="utf-8", errors="ignore").splitlines():
|
|
if "INSERT INTO `sys_dict_type`" in line:
|
|
vals = parse_insert_values(line)
|
|
if not vals or len(vals) < 3:
|
|
continue
|
|
# id, dict_name, dict_type, tenant_no, ...
|
|
dict_type = unquote(vals[2])
|
|
types[dict_type] = {
|
|
"dict_name": unquote(vals[1]),
|
|
"tenant_no": unquote(vals[3]),
|
|
"remark": unquote(vals[5]) if len(vals) > 5 else "",
|
|
}
|
|
elif "INSERT INTO `sys_dict_data`" in line:
|
|
vals = parse_insert_values(line)
|
|
if not vals or len(vals) < 5:
|
|
continue
|
|
# id, dict_label, dict_value, tag_type, dict_type, tenant_no, ...
|
|
dict_type = unquote(vals[4])
|
|
data_by_type[dict_type].append(
|
|
{
|
|
"label": unquote(vals[1]),
|
|
"value": unquote(vals[2]),
|
|
"tag_type": unquote(vals[3]),
|
|
"sort": unquote(vals[6]) if len(vals) > 6 else "",
|
|
}
|
|
)
|
|
return types, data_by_type
|
|
|
|
|
|
def item_key(item: dict) -> str:
|
|
return f"{item['value']}|{item['label']}"
|
|
|
|
|
|
def compare_data(sx_items: list[dict], portal_items: list[dict]) -> dict:
|
|
sx_map = {item_key(i): i for i in sx_items}
|
|
portal_map = {item_key(i): i for i in portal_items}
|
|
sx_keys = set(sx_map)
|
|
portal_keys = set(portal_map)
|
|
return {
|
|
"only_sx": sorted(sx_keys - portal_keys),
|
|
"only_portal": sorted(portal_keys - sx_keys),
|
|
"common": sorted(sx_keys & portal_keys),
|
|
"sx_count": len(sx_items),
|
|
"portal_count": len(portal_items),
|
|
}
|
|
|
|
|
|
def main() -> None:
|
|
sx_types, sx_data = load_sx_dicts(SX_SQL)
|
|
portal_types, portal_data = load_portal_dicts(PORTAL_SQL)
|
|
|
|
sx_type_keys = set(sx_types)
|
|
portal_type_keys = set(portal_types)
|
|
|
|
only_sx_types = sorted(sx_type_keys - portal_type_keys)
|
|
only_portal_types = sorted(portal_type_keys - sx_type_keys)
|
|
common_types = sorted(sx_type_keys & portal_type_keys)
|
|
|
|
def count_by_prefix(types: set[str], prefix: str) -> int:
|
|
return sum(1 for t in types if t.startswith(prefix))
|
|
|
|
sx_data_total = sum(len(v) for v in sx_data.values())
|
|
portal_data_total = sum(len(v) for v in portal_data.values())
|
|
portal_active = sum(
|
|
1 for items in portal_data.values() for i in items
|
|
) # placeholder
|
|
|
|
print("=" * 72)
|
|
print("字典对比总览（基于 docs/sql 快照）")
|
|
print("=" * 72)
|
|
print(f"{'':28} {'sx.sql':>12} {'shanxia2.0':>12}")
|
|
print(f"{'字典类型数':28} {len(sx_type_keys):>12} {len(portal_type_keys):>12}")
|
|
print(f"{'字典项数':28} {sx_data_total:>12} {portal_data_total:>12}")
|
|
print(f"{'crm_* 类型数':28} {count_by_prefix(sx_type_keys,'crm_'):>12} {count_by_prefix(portal_type_keys,'crm_'):>12}")
|
|
print(f"{'xg_* 类型数(学工)':28} {count_by_prefix(sx_type_keys,'xg_'):>12} {count_by_prefix(portal_type_keys,'xg_'):>12}")
|
|
print(f"{'sys_* 类型数':28} {count_by_prefix(sx_type_keys,'sys_'):>12} {count_by_prefix(portal_type_keys,'sys_'):>12}")
|
|
print(f"{'pl_* 类型数(运输)':28} {count_by_prefix(sx_type_keys,'pl_'):>12} {count_by_prefix(portal_type_keys,'pl_'):>12}")
|
|
print()
|
|
|
|
# semantic alias pairs
|
|
alias_pairs = [
|
|
("sys_user_sex", "sys_sex"),
|
|
("sys_show_hide", "sys_visible"),
|
|
("sys_normal_disable", "sys_status"),
|
|
]
|
|
print("--- 语义相近但类型码不同的「别名」---")
|
|
for sx_t, portal_t in alias_pairs:
|
|
in_sx = sx_t in sx_types or portal_t in sx_types
|
|
in_portal = sx_t in portal_types or portal_t in portal_types
|
|
if in_sx or in_portal:
|
|
print(
|
|
f" sx: {sx_t} ({len(sx_data.get(sx_t,[]))}项) "
|
|
f"| portal: {portal_t} ({len(portal_data.get(portal_t,[]))}项) "
|
|
f"+ portal {sx_t} ({len(portal_data.get(sx_t,[]))}项)"
|
|
)
|
|
print()
|
|
|
|
crm_prefixes = ("crm_", "xs_", "bx_")
|
|
crm_only_sx = [t for t in only_sx_types if t.startswith(crm_prefixes) or "crm" in t or t.startswith("xs_")]
|
|
other_only_sx = [t for t in only_sx_types if t not in crm_only_sx]
|
|
|
|
print("=" * 72)
|
|
print("字典类型 (sys_dict_type) 差异明细")
|
|
print("=" * 72)
|
|
print(f"类型码相同（两边都有）: {len(common_types)}")
|
|
print(f"仅 sx 有（门户缺失）: {len(only_sx_types)}")
|
|
print(f"仅门户有（sx 无，多为 2.0 新增）: {len(only_portal_types)}")
|
|
print()
|
|
|
|
print("--- 仅门户有的字典类型（shanxia2.0 新增能力）---")
|
|
for t in only_portal_types:
|
|
print(f" {t:40} {portal_types[t]['dict_name']}")
|
|
print()
|
|
|
|
print("--- 仅 sx 有 · CRM/业务相关（建议评估是否迁入）---")
|
|
for t in crm_only_sx:
|
|
print(f" {t:40} {sx_types[t]['dict_name']} (data:{len(sx_data.get(t, []))})")
|
|
print()
|
|
|
|
print("--- 仅 sx 有 · 学工/校园 xg_*（门户一般不需要）---")
|
|
xg_only = [t for t in only_sx_types if t.startswith("xg_")]
|
|
for t in xg_only[:20]:
|
|
print(f" {t:40} {sx_types[t]['dict_name']} (data:{len(sx_data.get(t, []))})")
|
|
if len(xg_only) > 20:
|
|
print(f" ... 共 {len(xg_only)} 个 xg_* 类型")
|
|
print()
|
|
|
|
print("--- 仅 sx 有 · 若依框架 sys_*（可能与门户同名不同义）---")
|
|
sys_overlap_missing = [t for t in only_sx_types if t.startswith("sys_")]
|
|
for t in sys_overlap_missing:
|
|
print(f" {t:40} {sx_types[t]['dict_name']} (data:{len(sx_data.get(t, []))})")
|
|
print()
|
|
|
|
print("--- 仅 sx 有 · 其他 ---")
|
|
for t in other_only_sx:
|
|
if not t.startswith("xg_"):
|
|
print(f" {t:40} {sx_types[t]['dict_name']} (data:{len(sx_data.get(t, []))})")
|
|
print()
|
|
|
|
print("=" * 72)
|
|
print("同名类型下字典项 (sys_dict_data) 差异（sx ∩ 门户）")
|
|
print("=" * 72)
|
|
diff_types = []
|
|
for t in common_types:
|
|
cmp = compare_data(sx_data.get(t, []), portal_data.get(t, []))
|
|
if cmp["only_sx"] or cmp["only_portal"] or cmp["sx_count"] != cmp["portal_count"]:
|
|
diff_types.append((t, cmp))
|
|
print(f"类型码相同但字典项不完全一致: {len(diff_types)} / {len(common_types)}")
|
|
print()
|
|
for t, cmp in sorted(diff_types, key=lambda x: x[0]):
|
|
sx_name = sx_types[t]["dict_name"]
|
|
portal_name = portal_types[t]["dict_name"]
|
|
print(f"[{t}] sx:{sx_name} | portal:{portal_name}")
|
|
print(f" sx项数={cmp['sx_count']} portal项数={cmp['portal_count']}")
|
|
if cmp["only_sx"]:
|
|
print(f" 仅sx有 ({len(cmp['only_sx'])}):")
|
|
for k in cmp["only_sx"][:8]:
|
|
print(f" - {k}")
|
|
if len(cmp["only_sx"]) > 8:
|
|
print(f" ... +{len(cmp['only_sx']) - 8}")
|
|
if cmp["only_portal"]:
|
|
print(f" 仅门户有 ({len(cmp['only_portal'])}):")
|
|
for k in cmp["only_portal"][:8]:
|
|
print(f" - {k}")
|
|
if len(cmp["only_portal"]) > 8:
|
|
print(f" ... +{len(cmp['only_portal']) - 8}")
|
|
print()
|
|
|
|
print("=" * 72)
|
|
print("CRM 业务字典（sx 有、门户无）明细")
|
|
print("=" * 72)
|
|
crm_types = sorted(
|
|
t
|
|
for t in only_sx_types
|
|
if t.startswith("crm_") or t.startswith("xs_") or t in ("contract_type", "contract_nature")
|
|
)
|
|
for t in crm_types:
|
|
print(f"\n## {t} — {sx_types[t]['dict_name']}")
|
|
for item in sorted(sx_data.get(t, []), key=lambda x: (x.get("sort") or "", x["value"])):
|
|
print(f" {item['value']:20} {item['label']}")
|
|
|
|
print()
|
|
print("=" * 72)
|
|
print("地磅系统 dibang.sql")
|
|
print("=" * 72)
|
|
dibang_text = DIBANG_SQL.read_text(encoding="utf-8", errors="ignore")
|
|
has_dict = "sys_dict" in dibang_text
|
|
print("含 sys_dict 表/数据:", "是" if has_dict else "否（地磅无独立字典表，枚举多在业务字段或前端硬编码）")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|