refactor(pipeline): 移除 csv_schema 等根目录中转，统一从 pipeline.csv 子包导入

- 删除 csv_schema.py、csv_header_rewrite.py、matrix_group_label.py（无引用）

- 全库改为 from pipeline.csv.schema / pipeline.csv.header_rewrite；文档字符串同步

- 与此前 jd_competitor_report 去中转同一策略

Made-with: Cursor

backend/crawler_copy/jd_pc_search/comment/jd_item_comment_export.py

@@ -16,7 +16,7 @@ from typing import Any
 _BACKEND_ROOT = Path(__file__).resolve().parents[3]
 if str(_BACKEND_ROOT) not in sys.path:
     sys.path.insert(0, str(_BACKEND_ROOT))
-from pipeline.csv_schema import COMMENT_CSV_COLUMNS, COMMENT_ROW_DICT_KEYS  # noqa: E402
+from pipeline.csv.schema import COMMENT_CSV_COLUMNS, COMMENT_ROW_DICT_KEYS  # noqa: E402
 
 
 def write_comments_flat_csv(path: Path | str, rows: list[dict[str, Any]]) -> None:

backend/crawler_copy/jd_pc_search/detail/jd_detail_buyer_extraction.py

@@ -17,7 +17,7 @@ import json
 import re
 from typing import Any
 
-from pipeline.csv_schema import strip_buyer_ranking_line_prefix
+from pipeline.csv.schema import strip_buyer_ranking_line_prefix
 
 
 def _s(x: Any) -> str:

backend/crawler_copy/jd_pc_search/jd_pipeline_export.py

@@ -12,7 +12,7 @@ from io import StringIO
 from pathlib import Path
 from typing import Any
 
-from pipeline.csv_schema import (  # noqa: E402
+from pipeline.csv.schema import (  # noqa: E402
     MERGED_CSV_COLUMNS,
     remap_merged_row_english_detail_keys_to_csv_headers,
 )
@@ -54,7 +54,7 @@ def normalize_merged_rows_for_export(rows: list[dict[str, str]]) -> None:
     整合表落盘前：搜索侧「榜单类文案」与「榜单排名」去掉 ``榜单/曝光：`` 前缀，
     与 ``strip_buyer_ranking_line_prefix`` / 入库规则一致。
     """
-    from pipeline.csv_schema import strip_buyer_ranking_line_prefix  # noqa: WPS433
+    from pipeline.csv.schema import strip_buyer_ranking_line_prefix  # noqa: WPS433
 
     hot_key = "榜单类文案"
     rank_key = "榜单排名"

backend/crawler_copy/jd_pc_search/scenario_filter.py

@@ -17,7 +17,7 @@ from typing import Any
 _BACKEND_ROOT = Path(__file__).resolve().parents[2]
 if str(_BACKEND_ROOT) not in sys.path:
     sys.path.insert(0, str(_BACKEND_ROOT))
-from pipeline.csv_schema import JD_SEARCH_CSV_HEADERS  # noqa: E402
+from pipeline.csv.schema import JD_SEARCH_CSV_HEADERS  # noqa: E402
 
 # 与 CSV 导出列名一致（jd_h5_search_requests.CSV_FIELDS 子集）
 _SCENARIO_TEXT_FIELDS: tuple[str, ...] = (

backend/crawler_copy/jd_pc_search/search/jd_h5_search_parse.py

@@ -17,7 +17,7 @@ from urllib.parse import parse_qs, urlparse
 _BACKEND_ROOT = Path(__file__).resolve().parents[3]
 if str(_BACKEND_ROOT) not in sys.path:
     sys.path.insert(0, str(_BACKEND_ROOT))
-from pipeline.csv_schema import JD_SEARCH_CSV_HEADERS as JD_EXPORT_COLUMN_HEADERS  # noqa: E402
+from pipeline.csv.schema import JD_SEARCH_CSV_HEADERS as JD_EXPORT_COLUMN_HEADERS  # noqa: E402
 
 _JD_PC_SEARCH_DIR = Path(__file__).resolve().parent
 

backend/crawler_copy/jd_pc_search/search/jd_h5_search_requests.py

@@ -65,7 +65,7 @@ _BACKEND_ROOT = Path(__file__).resolve().parents[3]
 if str(_BACKEND_ROOT) not in sys.path:
     sys.path.insert(0, str(_BACKEND_ROOT))
 from common.jd_delay_utils import parse_request_delay_range, sleep_pc_search_request_gap
-from pipeline.csv_schema import JD_SEARCH_CSV_HEADERS as JD_EXPORT_COLUMN_HEADERS  # noqa: E402
+from pipeline.csv.schema import JD_SEARCH_CSV_HEADERS as JD_EXPORT_COLUMN_HEADERS  # noqa: E402
 
 _JD_PC_SEARCH_DIR = Path(__file__).resolve().parent
 if str(_JD_PC_SEARCH_DIR) not in sys.path:

backend/pipeline/competitor_report/comment_sentiment.py

@@ -7,7 +7,7 @@ import re
 from collections import Counter
 from typing import Any
 
-from pipeline.csv_schema import MERGED_FIELD_TO_CSV_HEADER
+from pipeline.csv.schema import MERGED_FIELD_TO_CSV_HEADER
 
 from .constants import (
     _COMMENT_CSV_BODY,

backend/pipeline/competitor_report/constants.py

@@ -1,7 +1,7 @@
 """CSV 表头键、运行默认调参与关注词/场景配置（与 ``pipeline.competitor_report.jd_report`` 顶层一致）。"""
 from __future__ import annotations
 
-from pipeline.csv_schema import (
+from pipeline.csv.schema import (
     COMMENT_CSV_COLUMNS,
     JD_SEARCH_CSV_HEADERS,
     MERGED_FIELD_TO_CSV_HEADER,

backend/pipeline/competitor_report/consumer_feedback.py

@@ -1,7 +1,7 @@
 """评价与合并表按细类矩阵对齐：带前缀行、SKU→细类映射、按细类消费者反馈分组。"""
 from __future__ import annotations
 
-from pipeline.csv_schema import MERGED_FIELD_TO_CSV_HEADER
+from pipeline.csv.schema import MERGED_FIELD_TO_CSV_HEADER
 
 from .comment_sentiment import _iter_comment_text_units
 from .constants import (

backend/pipeline/competitor_report/list_mix.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 from collections import Counter
 from typing import Any
 
-from pipeline.csv_schema import JD_SEARCH_CSV_HEADERS, MERGED_FIELD_TO_CSV_HEADER
+from pipeline.csv.schema import JD_SEARCH_CSV_HEADERS, MERGED_FIELD_TO_CSV_HEADER
 
 from .constants import (
     _LEGACY_LIST_BRAND_TITLE_KEY,

backend/pipeline/competitor_report/llm_group_payloads.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 from collections import Counter
 from typing import Any
 
-from pipeline.csv_schema import JD_SEARCH_CSV_HEADERS, MERGED_FIELD_TO_CSV_HEADER
+from pipeline.csv.schema import JD_SEARCH_CSV_HEADERS, MERGED_FIELD_TO_CSV_HEADER
 
 from .comment_sentiment import _comment_keyword_hits
 from .constants import (

backend/pipeline/competitor_report/matrix_md.py

@@ -1,7 +1,7 @@
 """竞品矩阵 Markdown 行：配料格与整行管道表单元。"""
 from __future__ import annotations
 
-from pipeline.csv_schema import MERGED_FIELD_TO_CSV_HEADER, merged_csv_effective_total_sales
+from pipeline.csv.schema import MERGED_FIELD_TO_CSV_HEADER, merged_csv_effective_total_sales
 
 from .constants import (
     _COMMENT_FUZZ_KEYS,

backend/pipeline/csv_header_rewrite.py

@@ -1,3 +0,0 @@
-# -*- coding: utf-8 -*-
-"""兼容入口：实现见 ``pipeline.csv.header_rewrite``。"""
-from pipeline.csv.header_rewrite import *  # noqa: F403, F401

backend/pipeline/csv_schema.py

@@ -1,3 +0,0 @@
-# -*- coding: utf-8 -*-
-"""兼容入口：实现见 ``pipeline.csv.schema``。"""
-from pipeline.csv.schema import *  # noqa: F403, F401

backend/pipeline/dataset_nonempty.py

@@ -1,7 +1,7 @@
 """按任务扫描库内行，得到「全表至少一格非空」的列，供摘要 / 浏览 / 导出一致裁剪。"""
 from __future__ import annotations
 
-from .csv_schema import (
+from .csv.schema import (
     COMMENT_CSV_COLUMNS,
     COMMENT_CSV_TO_FIELD,
     DETAIL_CSV_COLUMNS,

backend/pipeline/demos/chapter8_text_mining_probe.py

@@ -46,7 +46,7 @@ if str(JCR_ROOT) not in sys.path:
 from pipeline.competitor_report import jd_report as jcr  # noqa: E402
 import jd_keyword_pipeline as kpl  # noqa: E402
 
-from pipeline.csv_schema import MERGED_FIELD_TO_CSV_HEADER  # noqa: E402
+from pipeline.csv.schema import MERGED_FIELD_TO_CSV_HEADER  # noqa: E402
 from pipeline.llm.generate import _call_llm  # noqa: E402 探针专用，不新增 generate 导出
 
 # 导入失败时**不得** ``sys.exit``：本模块会被 ``runner`` 在 Web 请求中 import，退出会整进程 500。

backend/pipeline/demos/run_report_llm_chapters_demo.py

@@ -40,7 +40,7 @@ if str(JCR_ROOT) not in sys.path:
 from pipeline.competitor_report import jd_report as jcr  # noqa: E402
 import jd_keyword_pipeline as kpl  # noqa: E402
 
-from pipeline.csv_schema import MERGED_FIELD_TO_CSV_HEADER  # noqa: E402
+from pipeline.csv.schema import MERGED_FIELD_TO_CSV_HEADER  # noqa: E402
 from pipeline.jd.runner import (  # noqa: E402
     get_default_report_config,
     use_chunked_group_summaries_llm,

backend/pipeline/export_job.py

@@ -9,7 +9,7 @@ from typing import Any
 from django.db.models import QuerySet
 from openpyxl import Workbook
 
-from .csv_schema import (
+from .csv.schema import (
     COMMENT_CSV_TO_FIELD,
     DETAIL_CSV_TO_FIELD,
     JD_SEARCH_CSV_HEADERS,

backend/pipeline/ingest.py

@@ -14,7 +14,7 @@ from django.conf import settings
 from django.db import transaction
 from django.utils import timezone
 
-from .csv_schema import (
+from .csv.schema import (
     COMMENT_CSV_COLUMNS,
     COMMENT_CSV_TO_FIELD,
     DETAIL_CSV_COLUMNS,

backend/pipeline/jd/detail_ware_regen.py

@@ -5,7 +5,7 @@ import csv
 import sys
 from pathlib import Path
 
-from ..csv_schema import MERGED_FIELD_TO_CSV_HEADER
+from ..csv.schema import MERGED_FIELD_TO_CSV_HEADER
 from ..ingest import FILE_DETAIL_WARE_CSV, FILE_MERGED_CSV, SKU_FIELD_MERGED
 
 

backend/pipeline/jd/merged_regen.py

@@ -1,11 +1,11 @@
-"""从 ``detail_ware_export.csv`` / ``detail/ware_*_response.json`` 补全并规范化 lean ``keyword_pipeline_merged.csv``（列序与 ``csv_schema.MERGED_CSV_COLUMNS`` 一致）。"""
+"""从 ``detail_ware_export.csv`` / ``detail/ware_*_response.json`` 补全并规范化 lean ``keyword_pipeline_merged.csv``（列序与 ``pipeline.csv.schema.MERGED_CSV_COLUMNS`` 一致）。"""
 from __future__ import annotations
 
 import csv
 import sys
 from pathlib import Path
 
-from ..csv_schema import (
+from ..csv.schema import (
     MERGED_CSV_COLUMNS,
     MERGED_FIELD_TO_CSV_HEADER,
     MERGED_LEAN_DETAIL_INTERNAL_KEYS,

backend/pipeline/jd/runner.py

@@ -12,7 +12,7 @@ from typing import Any
 
 from django.conf import settings
 
-from ..csv_schema import MERGED_FIELD_TO_CSV_HEADER
+from ..csv.schema import MERGED_FIELD_TO_CSV_HEADER
 from ..models import PipelineJob
 
 

backend/pipeline/management/commands/refresh_jd_merged_total_sales.py

@@ -9,7 +9,7 @@ from __future__ import annotations
 
 from django.core.management.base import BaseCommand
 
-from pipeline.csv_schema import (
+from pipeline.csv.schema import (
     JD_SEARCH_CSV_HEADERS,
     MERGED_FIELD_TO_CSV_HEADER,
     merged_csv_effective_total_sales,

backend/pipeline/management/commands/rewrite_pipeline_csv_headers.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 """
-将已有 run 目录下 CSV 表头重写为 ``csv_schema`` 纯中文表头（仅重命名与列序，不修改业务逻辑）。
+将已有 run 目录下 CSV 表头重写为 ``pipeline.csv.schema`` 纯中文表头（仅重命名与列序，不修改业务逻辑）。
 
 在 ``backend`` 目录::
 
@@ -16,7 +16,7 @@ from __future__ import annotations
 from django.conf import settings
 from django.core.management.base import BaseCommand, CommandError
 
-from pipeline.csv_header_rewrite import rewrite_run_dir_csv_headers
+from pipeline.csv.header_rewrite import rewrite_run_dir_csv_headers
 from pipeline.ingest import (
     FILE_COMMENTS_FLAT_CSV,
     FILE_DETAIL_WARE_CSV,
@@ -27,7 +27,7 @@ from pipeline.ingest import (
 
 
 class Command(BaseCommand):
-    help = "将 pipeline run 目录内 CSV 表头规范为 csv_schema 中的中文表头。"
+    help = "将 pipeline run 目录内 CSV 表头规范为 pipeline.csv.schema 中的中文表头。"
 
     def add_arguments(self, parser) -> None:
         parser.add_argument(

backend/pipeline/matrix_group_label.py

@@ -1,3 +0,0 @@
-# -*- coding: utf-8 -*-
-"""兼容入口：实现见 ``pipeline.jd.matrix_group_label``。"""
-from pipeline.jd.matrix_group_label import *  # noqa: F403, F401

backend/pipeline/row_serialize.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 
 from typing import Any
 
-from .csv_schema import (
+from .csv.schema import (
     COMMENT_CSV_COLUMNS,
     COMMENT_CSV_TO_FIELD,
     DETAIL_CSV_COLUMNS,

backend/pipeline/tests/test_buyer_offer_export_csv.py

@@ -7,7 +7,7 @@ from pathlib import Path
 from django.conf import settings
 from django.test import SimpleTestCase
 
-from pipeline.csv_schema import strip_buyer_ranking_line_prefix
+from pipeline.csv.schema import strip_buyer_ranking_line_prefix
 
 
 class BuyerOfferExportCsvTests(SimpleTestCase):

backend/pipeline/tests/test_competitor_brief.py

@@ -7,7 +7,7 @@ from pathlib import Path
 from django.test import SimpleTestCase
 
 from pipeline.competitor_report import jd_report as jcr
-from pipeline.csv_schema import infer_total_sales_from_sales_floor
+from pipeline.csv.schema import infer_total_sales_from_sales_floor
 from pipeline.reporting.charts import _cn_volume_int
 
 

backend/pipeline/views/product_views.py

@@ -31,7 +31,7 @@ class JdProductListView(APIView):
                 | Q(detail_brand__icontains=q)
             )
         if kw:
-            from ..csv_schema import MERGED_FIELD_TO_CSV_HEADER
+            from ..csv.schema import MERGED_FIELD_TO_CSV_HEADER
 
             h_kw = MERGED_FIELD_TO_CSV_HEADER["pipeline_keyword"]
             qs = qs.filter(