148 lines
5.5 KiB
Python
148 lines
5.5 KiB
Python
"""内容定位:用列名 + 值找目标行/列。"""
|
||
from . import UserError
|
||
|
||
|
||
def is_formula(v) -> bool:
|
||
return isinstance(v, str) and v.startswith('=')
|
||
|
||
|
||
def detect_header_row(ws, scan=10, col_cap=200) -> int:
|
||
"""扫描前 scan 行猜表头行(只读不写,纯建议用)。
|
||
|
||
候选条件:行内非空值 ≥ 2 且全部是普通字符串(排掉单值标题行和含数字/公式的数据行),行内不重复。
|
||
取非空格数最多的最早候选行;找不到则回退 1。"""
|
||
best_row, best_cnt = 1, 0
|
||
max_c = min(ws.max_column, col_cap)
|
||
for r in range(1, min(scan, ws.max_row) + 1):
|
||
vals = []
|
||
ok = True
|
||
for c in range(1, max_c + 1):
|
||
v = ws.cell(r, c).value
|
||
if v is None or v == '':
|
||
continue
|
||
if isinstance(v, str) and not v.startswith('='):
|
||
vals.append(v.strip())
|
||
else:
|
||
ok = False
|
||
break
|
||
if not ok or len(vals) < 2 or len(set(vals)) != len(vals):
|
||
continue
|
||
if len(vals) > best_cnt:
|
||
best_row, best_cnt = r, len(vals)
|
||
return best_row
|
||
|
||
|
||
def detect_multi_level(ws, scan=10, col_cap=200):
|
||
"""检测“分组行 + 重复子列名行”相邻出现的多级表头形态,返回 (分组行, 列名行) 或 None。
|
||
|
||
判定:相邻两行均全为字符串;上行值唯一且 ≥2 个(分组标题),下行有重复且 ≥3 个、格数多于上行
|
||
(真列名在多组下重复)。只读不写,纯诊断用。"""
|
||
max_c = min(ws.max_column, col_cap)
|
||
prev = None # (row, 全字符串, 值列表)
|
||
for r in range(1, min(scan, ws.max_row) + 1):
|
||
vals = []
|
||
ok = True
|
||
for c in range(1, max_c + 1):
|
||
v = ws.cell(r, c).value
|
||
if v is None or v == '':
|
||
continue
|
||
if isinstance(v, str) and not v.startswith('='):
|
||
vals.append(v.strip())
|
||
else:
|
||
ok = False
|
||
break
|
||
if prev is not None and ok and prev[1] and prev[2]:
|
||
pu, cu = prev[2], vals
|
||
if (len(pu) >= 2 and len(set(pu)) == len(pu)
|
||
and len(cu) >= 3 and len(set(cu)) != len(cu)
|
||
and len(cu) > len(pu)):
|
||
return (prev[0], r)
|
||
prev = (r, ok, vals)
|
||
return None
|
||
|
||
|
||
def value_eq(a, b) -> bool:
|
||
if a is None and b is None:
|
||
return True
|
||
if isinstance(a, (int, float)) and isinstance(b, (int, float)):
|
||
return abs(float(a) - float(b)) < 1e-9
|
||
# 数字↔数字文本(CSV 往返后数值变文本,定位比较要能对上)
|
||
if isinstance(a, str) != isinstance(b, str):
|
||
try:
|
||
return abs(float(a) - float(b)) < 1e-9
|
||
except (TypeError, ValueError):
|
||
return False
|
||
return a == b
|
||
|
||
|
||
def build_col_map(ws, header_row: int) -> dict:
|
||
"""从表头行构建 {列名: 列号}。"""
|
||
col_map = {}
|
||
for c in range(1, ws.max_column + 1):
|
||
v = ws.cell(header_row, c).value
|
||
if v is None:
|
||
continue
|
||
name = str(v).strip()
|
||
if not name:
|
||
continue
|
||
if name in col_map:
|
||
ml = detect_multi_level(ws)
|
||
if ml:
|
||
raise UserError(
|
||
f"表头行 {header_row} 存在重复列名('{name}'),且检测到多级表头"
|
||
f"(第 {ml[0]} 行分组、第 {ml[1]} 行子列名):列名模式无法唯一定位,"
|
||
"请从 inspect 的 preview/formulas 确认目标坐标后改用 change.cells 地址模式"
|
||
)
|
||
raise UserError(f"表头行 {header_row} 存在重复列名: '{name}'")
|
||
col_map[name] = c
|
||
if not col_map:
|
||
suggest = detect_header_row(ws)
|
||
extra = f";疑似真实表头在第 {suggest} 行,请传 header_row={suggest} 重试" if suggest != header_row else ''
|
||
raise UserError(f"表头行 {header_row} 为空,无法识别列名{extra}")
|
||
if len(col_map) == 1:
|
||
# 典型现场:第 1 行是横跨全行的合并标题,单值被当成唯一列名
|
||
suggest = detect_header_row(ws)
|
||
if suggest != header_row:
|
||
raise UserError(
|
||
f"表头行 {header_row} 只解析出 1 列('{next(iter(col_map))}'),像标题行;"
|
||
f"疑似真实表头在第 {suggest} 行,请传 header_row={suggest} 重试"
|
||
)
|
||
return col_map
|
||
|
||
|
||
def find_row(ws, col_map: dict, match: dict, header_row: int) -> int:
|
||
"""用 match(列名 → 值)找唯一匹配的行号。"""
|
||
if not isinstance(match, dict) or not match:
|
||
raise UserError("match 必须是非空对象")
|
||
|
||
for k in match:
|
||
if k not in col_map:
|
||
raise UserError(
|
||
f"表头无此列: '{k}'(可用: {', '.join(col_map.keys())})"
|
||
)
|
||
|
||
hits = []
|
||
for r in range(header_row + 1, ws.max_row + 1):
|
||
ok = True
|
||
for col_name, want in match.items():
|
||
v = ws.cell(r, col_map[col_name]).value
|
||
if not value_eq(v, want):
|
||
ok = False
|
||
break
|
||
if ok:
|
||
hits.append(r)
|
||
|
||
if not hits:
|
||
raise UserError(f"找不到匹配行: {match}")
|
||
if len(hits) > 1:
|
||
raise UserError(f"匹配到 {len(hits)} 行,需增加条件: {match}")
|
||
return hits[0]
|
||
|
||
|
||
def find_col(col_map: dict, name: str) -> int:
|
||
if name not in col_map:
|
||
raise UserError(
|
||
f"表头无此列: '{name}'(可用: {', '.join(col_map.keys())})"
|
||
)
|
||
return col_map[name]
|