3218485270
71a48e4ed5
- 图源映射统一：热点采集与 Pinterest 模式均走 config.product.mark_dirs 配置，按任务序号随机抽模特图/平铺图 - 商品产地固定：统一为「中国大陆」+「产地省份=广东省」（不再读站点/字典映射） - 模板 SKU 字段检测：按建议售价同一套路检测 SKU分类/SKU数量/SKU数量单位，必填时填入单品/1/件 - 多模态分析提示词可配置：prompts/pinterest_analyze_system.md + user.md，支持国家覆盖，不丢文件回退内置 - 自定义图片模式：新增 pinterest_custom_load_node，图片数量硬校验，选品清单 ≤ 有效图片数 - 模板导出优化：写入前按货号末 3 位升序排序，不再产生空白 xlsx - 修复 v90 project review 10 项（503 致命终止、线程安全、原子写入等）
197 lines
7.7 KiB
Python
197 lines
7.7 KiB
Python
"""SPU/SKU 数据库查询 + 底图/模特图资源查找（产品图生成流水线的数据层）。
|
||
|
||
数据关系（已核实 spu_sku.db）：
|
||
- SPU.code = 款号（如 DG004）
|
||
- SKU.code = "款号-颜色编码"（如 DG004-BL01），SKU.color = 中文色名（黑/灰/...）
|
||
- basemap 目录 = basemap/<款号>/<SKU.code>/xxx.jpg
|
||
- material_library/<品类>/ 存放模特图
|
||
- SKU.img_url_2~5 = CDN 图 URL（底图/细节/模特图，仅作参考字段）
|
||
"""
|
||
import sqlite3
|
||
from pathlib import Path
|
||
from typing import Any, Dict, List, Optional
|
||
|
||
from PIL import Image
|
||
|
||
# 支持的图片格式：模特图/底图均按此识别（png/jpg 等常见格式全覆盖；AVIF/GIF/TIFF 亦支持）
|
||
IMG_EXTS = {".jpg", ".jpeg", ".png", ".webp", ".bmp", ".avif", ".gif", ".tiff", ".tif"}
|
||
|
||
|
||
def _connect(db_path) -> sqlite3.Connection:
|
||
conn = sqlite3.connect(str(db_path))
|
||
conn.row_factory = sqlite3.Row
|
||
return conn
|
||
|
||
|
||
def list_spus(db_path, country: Optional[str] = None) -> List[Dict[str, Any]]:
|
||
"""全部 SPU（可选按国家过滤）。"""
|
||
conn = _connect(db_path)
|
||
sql = "SELECT id, code, style, material, printing_type, target_audience, pattern, country, mark FROM SPU"
|
||
params: list = []
|
||
if country:
|
||
sql += " WHERE country = ?"
|
||
params.append(country)
|
||
sql += " ORDER BY code"
|
||
rows = conn.execute(sql, params).fetchall()
|
||
conn.close()
|
||
return [dict(r) for r in rows]
|
||
|
||
|
||
def list_colors(db_path, spu_code: str) -> List[Dict[str, Any]]:
|
||
"""款号 → 颜色列表（SKU.code 去重，附中文色名、CDN 底图 URL、最低价）。"""
|
||
conn = _connect(db_path)
|
||
rows = conn.execute(
|
||
"""SELECT s.code AS sku_code, s.color, s.img_url_2 AS img_url, MIN(s.price) AS price
|
||
FROM SKU s JOIN SPU p ON s.spu_id = p.id
|
||
WHERE p.code = ?
|
||
GROUP BY s.code, s.color ORDER BY s.code""", (spu_code,)).fetchall()
|
||
conn.close()
|
||
return [dict(r) for r in rows]
|
||
|
||
|
||
def _norm_name(s: str) -> str:
|
||
"""去空格（半角+全角）+ 小写，用于 SKU code 与文件夹名比较。"""
|
||
return str(s or "").replace(" ", "").replace(" ", "").strip().lower()
|
||
|
||
|
||
def find_basemap(basemap_root, spu_code: str, sku_code: str) -> Optional[Path]:
|
||
"""basemap/<款号>/<SKU.code>/ 下第一张图片；无返回 None。
|
||
|
||
SKU code 与文件夹名比较时两边都去空格（兼容 db code 或文件夹名带空格）。
|
||
"""
|
||
root = Path(basemap_root) / spu_code
|
||
if not root.exists():
|
||
return None
|
||
target = _norm_name(sku_code)
|
||
if not target:
|
||
return None
|
||
d = root / sku_code
|
||
if not (d.exists() and d.is_dir()):
|
||
d = None
|
||
for cand in sorted(root.iterdir()):
|
||
if cand.is_dir() and _norm_name(cand.name) == target:
|
||
d = cand
|
||
break
|
||
if d is None:
|
||
return None
|
||
for f in sorted(d.iterdir()):
|
||
if f.is_file() and f.suffix.lower() in IMG_EXTS:
|
||
return f
|
||
return None
|
||
|
||
|
||
def list_model_images(material_root, category: str = "T-shirt") -> List[Path]:
|
||
"""material_library/<品类>/ 下所有图片；无返回空列表。"""
|
||
d = Path(material_root) / category
|
||
if not d.exists():
|
||
return []
|
||
return [f for f in sorted(d.iterdir()) if f.is_file() and f.suffix.lower() in IMG_EXTS]
|
||
|
||
|
||
def find_first_model_folder(material_root, preferred: Optional[str] = None):
|
||
"""material_library 下「第一个有图片的子目录」及其图片列表。
|
||
|
||
- preferred（如 config 的 model_category）优先：该目录有图就直接用；
|
||
- 否则按子目录名排序，取第一个有图的目录；
|
||
- 全空返回 (None, [])。
|
||
返回 (dir_name or None, images: List[Path])。
|
||
"""
|
||
root = Path(material_root)
|
||
if not root.exists():
|
||
return None, []
|
||
candidates = []
|
||
if preferred:
|
||
d = root / preferred
|
||
if d.is_dir():
|
||
candidates.append(d)
|
||
candidates += [d for d in sorted(root.iterdir()) if d.is_dir()]
|
||
seen = set()
|
||
for d in candidates:
|
||
if d in seen:
|
||
continue
|
||
seen.add(d)
|
||
imgs = [f for f in sorted(d.iterdir()) if f.is_file() and f.suffix.lower() in IMG_EXTS]
|
||
if imgs:
|
||
return d.name, imgs
|
||
return None, []
|
||
|
||
|
||
def image_ratio_ok(path, target_ratio: float = 3 / 4, tolerance: float = 0.06) -> bool:
|
||
"""图片宽高比是否接近目标比例（默认 3:4，相对容差 6%）。
|
||
|
||
相对容差：接受 [target*(1-tol), target*(1+tol)]，对 3:4 即 0.705~0.795。
|
||
无法解析的图片（损坏/非标准）按不通过处理，避免坏图被当模特。
|
||
"""
|
||
try:
|
||
with Image.open(path) as im:
|
||
w, h = im.size
|
||
if w <= 0 or h <= 0:
|
||
return False
|
||
ratio = w / h
|
||
lo = target_ratio * (1 - tolerance)
|
||
hi = target_ratio * (1 + tolerance)
|
||
return lo <= ratio <= hi
|
||
except Exception: # noqa: BLE001
|
||
return False
|
||
|
||
|
||
def _dir_images(d: Path, ratio: float, tolerance: float) -> List[Path]:
|
||
"""返回目录内满足比例过滤(默认3:4)的图片列表；目录不存在/无图片返回空。"""
|
||
if d is None or not d.is_dir():
|
||
return []
|
||
imgs = [f for f in sorted(d.iterdir()) if f.is_file() and f.suffix.lower() in IMG_EXTS]
|
||
if not imgs:
|
||
return []
|
||
ok = [f for f in imgs if image_ratio_ok(f, ratio, tolerance)]
|
||
if len(ok) < len(imgs):
|
||
print(f"[product] 目录 {d.name}/ 过滤非 {int(ratio * 100)}:{int(ratio * 100) + 1} 比例："
|
||
f"{len(imgs)} → {len(ok)} 张")
|
||
return ok
|
||
|
||
|
||
def build_mark_sources(material_root, mark_dirs: Optional[Dict] = None,
|
||
category: str = "T-shirt", mark: str = "1",
|
||
ratio: float = 3 / 4, tolerance: float = 0.06) -> Dict[str, Any]:
|
||
"""按可配置的 mark→图源映射，返回指定 mark 的图源选择信息。
|
||
|
||
图源 = {"model": [Path...], "flat": [Path...]}（模特图 / 平铺图，各带英文键）。
|
||
从 config.product.mark_dirs 读 mark 对应的两个子目录名（model_dir/flat_dir），
|
||
在 material_library 下解析 → 过滤 3:4 → 返回「有图的文件夹」图片列表。
|
||
mark 未配置时回退 mark_dirs["1"]；完全无配置则回退 category 默认目录。
|
||
返回结构：{"model": [imgs], "flat": [imgs]}。
|
||
"""
|
||
root = Path(material_root)
|
||
result: Dict[str, Any] = {"model": [], "flat": []}
|
||
if not root.exists():
|
||
return result
|
||
mcfg = mark_dirs or {}
|
||
cfg = mcfg.get(str(mark)) or mcfg.get("1") or {} # 优先按 mark，其次回退默认 "1"
|
||
model_name = str(cfg.get("model_dir") or "").strip()
|
||
flat_name = str(cfg.get("flat_dir") or "").strip()
|
||
if model_name:
|
||
result["model"] = _dir_images(root / model_name, ratio, tolerance)
|
||
if flat_name:
|
||
result["flat"] = _dir_images(root / flat_name, ratio, tolerance)
|
||
# 回退：某类目录未配置时，使用 category 默认目录补充模特图
|
||
if not result["model"] and not result["flat"]:
|
||
d = root / category
|
||
if d.is_dir():
|
||
result["model"] = _dir_images(d, ratio, tolerance)
|
||
if not result["model"] and not result["flat"]:
|
||
for sub in sorted(root.iterdir()):
|
||
if not sub.is_dir():
|
||
continue
|
||
imgs = _dir_images(sub, ratio, tolerance)
|
||
if imgs:
|
||
result["model"] = imgs
|
||
break
|
||
return result
|
||
|
||
|
||
def first_available_sku(db_path, basemap_root, spu_code: str) -> Optional[str]:
|
||
"""返回该款号下第一个「本地有底图」的 SKU.code；无则 None。"""
|
||
for c in list_colors(db_path, spu_code):
|
||
if find_basemap(basemap_root, spu_code, c["sku_code"]) is not None:
|
||
return c["sku_code"]
|
||
return None
|