diary-news/backend/alembic/versions/0010_zhparser_chinese.py

"""搜索建议 schema 修正 — 加 zhparser 中文分词支持。

0009 跑完之后,发现:
- PG 16 + alpine 镜像没有中文分词扩展,'simple' parser 把整句中文当一个 token,词频聚合无效
- 解决:换 Debian 镜像 + 装 zhparser + 创建 chinese_zh text search config
- 修正 articles.title_zh_tsv 生成列 + refresh_search_keywords() 函数都用 chinese_zh

步骤:
  1) CREATE EXTENSION zhparser
  2) 创建 chinese_zh text search config(基于 zhparser)
  3) 重建 articles.title_zh_tsv 用 chinese_zh(先 DROP,再 ADD)
  4) CREATE OR REPLACE refresh_search_keywords() 用 chinese_zh
  5) 触发 search_keywords 立即刷新,让数据立刻可用

注意:docker-compose.yml 同步改了 postgres 用 Dockerfile.postgres
(debian bookworm + apt 装 zhparser,alpine 没现成包)

Revision ID: 0010
Revises: 0009
Create Date: 2026-06-15
"""
from __future__ import annotations

from typing import Sequence, Union

import sqlalchemy as sa
from alembic import op
from sqlalchemy.dialects.postgresql import TSVECTOR


revision: str = "0010"
down_revision: Union[str, None] = "0009"
branch_labels = None
depends_on = None


def upgrade() -> None:
    # 1) 装扩展
    op.execute("CREATE EXTENSION IF NOT EXISTS zhparser;")

    # 2) 建 text search config:中文用 zhparser,简单词(英文/数字)用 simple parser
    # zhparser 自带一个 'scwsm' 字典 + 'default' tokenizer,适合新闻类语料
    op.execute("DROP TEXT SEARCH CONFIGURATION IF EXISTS chinese_zh;")
    op.execute(
        """
        CREATE TEXT SEARCH CONFIGURATION chinese_zh (PARSER = zhparser);
        ALTER TEXT SEARCH CONFIGURATION chinese_zh
            ADD MAPPING FOR n, a, v, i, e, l, u, x
            WITH simple;
        """
    )

    # 3) 重建 articles.title_zh_tsv 列(用新 config)
    op.drop_index("ix_articles_title_zh_tsv", table_name="articles")
    op.drop_column("articles", "title_zh_tsv")
    op.add_column(
        "articles",
        sa.Column(
            "title_zh_tsv",
            TSVECTOR,
            sa.Computed(
                "to_tsvector('chinese_zh', coalesce(title_zh, ''))",
                persisted=True,
            ),
        ),
    )
    op.create_index(
        "ix_articles_title_zh_tsv",
        "articles",
        ["title_zh_tsv"],
        postgresql_using="gin",
    )

    # 4) 覆盖 refresh_search_keywords() — 用 chinese_zh + ts_stat(text) 正确签名
    op.execute("DROP FUNCTION IF EXISTS refresh_search_keywords();")
    op.execute(
        """
        CREATE OR REPLACE FUNCTION refresh_search_keywords() RETURNS void AS $func$
        BEGIN
            TRUNCATE search_keywords;

            -- ts_stat(query text) 接受 SQL 字符串,内部执行并聚合词频
            -- 'a' = 任意权重(A/B/C/D 四档,这里聚合所有)
            INSERT INTO search_keywords (keyword, source, weight, prefix_keys)
            SELECT
                word,
                'ts_stat',
                nentry::int,
                ARRAY(
                    SELECT substring(word, 1, n)
                    FROM generate_series(1, length(word)) AS n
                )
            FROM ts_stat(
                $q$
                SELECT to_tsvector('chinese_zh',
                    coalesce(title_zh, '') || ' ' ||
                    coalesce(body_zh_text, '') || ' ' ||
                    coalesce(commentary, '') || ' ' ||
                    coalesce(commentary_meituan, '')
                )
                FROM articles
                WHERE title_zh IS NOT NULL
                   OR body_zh_text IS NOT NULL
                   OR commentary IS NOT NULL
                   OR commentary_meituan IS NOT NULL
                $q$, 'a'
            )
            WHERE length(word) >= 2;
        END;
        $func$ LANGUAGE plpgsql;
        """
    )

    # 5) 立即跑一次刷新(让 worker 下次 03:00 之前就有数据可用)
    op.execute("SELECT refresh_search_keywords();")


def downgrade() -> None:
    # 1) 恢复 refresh_search_keywords() — 不强求降级数据;只恢复 schema
    op.execute("DROP FUNCTION IF EXISTS refresh_search_keywords();")
    op.execute(
        """
        CREATE OR REPLACE FUNCTION refresh_search_keywords() RETURNS void AS $func$
        BEGIN
            TRUNCATE search_keywords;

            -- 降级回 simple parser(中文会被当成一整句,词频聚合无效,仅占位)
            INSERT INTO search_keywords (keyword, source, weight, prefix_keys)
            SELECT
                word,
                'ts_stat',
                nentry::int,
                ARRAY(
                    SELECT substring(word, 1, n)
                    FROM generate_series(1, length(word)) AS n
                )
            FROM ts_stat(
                $q$
                SELECT to_tsvector('simple',
                    coalesce(title_zh, '') || ' ' ||
                    coalesce(body_zh_text, '') || ' ' ||
                    coalesce(commentary, '') || ' ' ||
                    coalesce(commentary_meituan, '')
                )
                FROM articles
                WHERE title_zh IS NOT NULL
                   OR body_zh_text IS NOT NULL
                   OR commentary IS NOT NULL
                   OR commentary_meituan IS NOT NULL
                $q$, 'a'
            )
            WHERE length(word) >= 2;
        END;
        $func$ LANGUAGE plpgsql;
        """
    )

    # 2) 恢复 title_zh_tsv 用 simple
    op.drop_index("ix_articles_title_zh_tsv", table_name="articles")
    op.drop_column("articles", "title_zh_tsv")
    op.add_column(
        "articles",
        sa.Column(
            "title_zh_tsv",
            TSVECTOR,
            sa.Computed(
                "to_tsvector('simple', coalesce(title_zh, ''))",
                persisted=True,
            ),
        ),
    )
    op.create_index(
        "ix_articles_title_zh_tsv",
        "articles",
        ["title_zh_tsv"],
        postgresql_using="gin",
    )

    # 3) 删 chinese_zh config
    op.execute("DROP TEXT SEARCH CONFIGURATION IF EXISTS chinese_zh;")

    # 4) 留 zhparser 扩展不删(其他东西可能依赖,降级时留着更安全)
    # 真要删: op.execute("DROP EXTENSION IF EXISTS zhparser;")