114 lines
7.0 KiB
SQL
114 lines
7.0 KiB
SQL
-- Author: fruit.com.cn
|
||
|
||
-- FruitShorts 短剧服务 · 印尼语（id-ID）敏感词库增量补全（PostgreSQL 18）
|
||
--
|
||
-- 续接基线：sensitive_word 已有 id 9000001~9000053（zh-CN/en-US/id-ID 三语初版）。
|
||
-- 本文件只补 id-ID 缺失/不足的分类，id 从 9000054 续接，避免与现有雪花 ID 冲突。
|
||
--
|
||
-- 分类（category）：POLITICS 政治 / PORN 色情 / ABUSE 辱骂 / AD 广告导流 / RELIGION 宗教
|
||
-- 级别（level）：
|
||
-- BLOCK 直接拒绝发布
|
||
-- REVIEW 命中转人工审核（歧义词、可能误伤的业务词放这里）
|
||
-- REPLACE 替换后放行（轻度脏话，用 replace_text 打码）
|
||
--
|
||
-- 幂等：唯一索引 uk_sensitive_word(language, word)，重复执行靠 ON CONFLICT DO NOTHING 跳过。
|
||
-- 说明：词库内容需印尼运营/合规方复核后启用，本文件仅提供开发联调可用的初始基线。
|
||
|
||
-- ============ 辱骂 / 脏话（ABUSE）· 补全 ============
|
||
INSERT INTO sensitive_word (id, word, category, level, replace_text, language, status) VALUES
|
||
(9000054, 'babi', 'ABUSE', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000055, 'brengsek', 'ABUSE', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000056, 'kampret', 'ABUSE', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000057, 'keparat', 'ABUSE', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000058, 'sundal', 'ABUSE', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000059, 'lonte', 'ABUSE', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000060, 'pelacur', 'ABUSE', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000061, 'jancok', 'ABUSE', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000062, 'asu', 'ABUSE', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000063, 'sialan', 'ABUSE', 'REPLACE', '***', 'id-ID', 1),
|
||
(9000064, 'tolol', 'ABUSE', 'REPLACE', '***', 'id-ID', 1),
|
||
(9000065, 'goblok', 'ABUSE', 'REPLACE', '***', 'id-ID', 1),
|
||
(9000066, 'bodoh', 'ABUSE', 'REPLACE', '***', 'id-ID', 1),
|
||
(9000067, 'bego', 'ABUSE', 'REPLACE', '***', 'id-ID', 1),
|
||
(9000068, 'kirik', 'ABUSE', 'REPLACE', '***', 'id-ID', 1),
|
||
(9000069, 'tai', 'ABUSE', 'REPLACE', '***', 'id-ID', 1),
|
||
(9000070, 'bejat', 'ABUSE', 'REPLACE', '***', 'id-ID', 1)
|
||
ON CONFLICT (language, word) DO NOTHING;
|
||
|
||
-- ============ 色情（PORN）· 少量补全 ============
|
||
INSERT INTO sensitive_word (id, word, category, level, replace_text, language, status) VALUES
|
||
(9000071, 'ngewe', 'PORN', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000072, 'toket', 'PORN', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000073, 'onani', 'PORN', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000074, 'perkosa', 'PORN', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000075, 'pemerkosaan', 'PORN', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000076, 'jembut', 'PORN', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000077, 'pepek', 'PORN', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000078, 'selingkuh', 'PORN', 'REVIEW', '*', 'id-ID', 1),
|
||
(9000079, 'gairah', 'PORN', 'REVIEW', '*', 'id-ID', 1)
|
||
ON CONFLICT (language, word) DO NOTHING;
|
||
|
||
-- ============ 政治（POLITICS）· 新增（基线缺失） ============
|
||
INSERT INTO sensitive_word (id, word, category, level, replace_text, language, status) VALUES
|
||
(9000080, 'PKI', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000081, 'komunis', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000082, 'Papua Merdeka', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000083, 'OPM', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000084, 'GAM', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000085, 'separatis', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000086, 'separatisme', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000087, 'teroris', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000088, 'terorisme', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000089, 'ISIS', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000090, 'jihadis', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000091, 'radikalisme', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000092, 'kudeta', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000093, 'makar', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000094, 'pemberontak', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000095, 'pemberontakan', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000096, 'kerusuhan', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000097, 'penjarahan', 'POLITICS', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000098, 'radikal', 'POLITICS', 'REVIEW', '*', 'id-ID', 1),
|
||
(9000099, 'jihad', 'POLITICS', 'REVIEW', '*', 'id-ID', 1),
|
||
(9000100, 'anti-pemerintah', 'POLITICS', 'REVIEW', '*', 'id-ID', 1),
|
||
(9000101, 'bubarkan', 'POLITICS', 'REVIEW', '*', 'id-ID', 1)
|
||
ON CONFLICT (language, word) DO NOTHING;
|
||
|
||
-- ============ 宗教（RELIGION）· 补全 ============
|
||
INSERT INTO sensitive_word (id, word, category, level, replace_text, language, status) VALUES
|
||
(9000102, 'penistaan agama', 'RELIGION', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000103, 'menghina agama', 'RELIGION', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000104, 'menghina Nabi', 'RELIGION', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000105, 'menghina Allah', 'RELIGION', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000106, 'menghina Kristen','RELIGION', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000107, 'menghina Katolik','RELIGION', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000108, 'menghina Hindu', 'RELIGION', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000109, 'menghina Buddha', 'RELIGION', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000110, 'kafir', 'RELIGION', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000111, 'murtad', 'RELIGION', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000112, 'sara', 'RELIGION', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000113, 'provokasi agama', 'RELIGION', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000114, 'konflik agama', 'RELIGION', 'REVIEW', '*', 'id-ID', 1)
|
||
ON CONFLICT (language, word) DO NOTHING;
|
||
|
||
-- ============ 广告导流 / 非法（AD）· 补全 ============
|
||
INSERT INTO sensitive_word (id, word, category, level, replace_text, language, status) VALUES
|
||
(9000115, 'judi online', 'AD', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000116, 'slot online', 'AD', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000117, 'casino', 'AD', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000118, 'poker online', 'AD', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000119, 'situs judi', 'AD', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000120, 'deposit slot', 'AD', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000121, 'link alternatif', 'AD', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000122, 'pinjol', 'AD', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000123, 'rentenir', 'AD', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000124, 'scam', 'AD', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000125, 'penipuan', 'AD', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000126, 'investasi bodong', 'AD', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000127, 'arisan berantai', 'AD', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000128, 'money game', 'AD', 'BLOCK', '*', 'id-ID', 1),
|
||
(9000129, 'pinjaman online', 'AD', 'REVIEW', '*', 'id-ID', 1),
|
||
(9000130, 'hack', 'AD', 'REVIEW', '*', 'id-ID', 1),
|
||
(9000131, 'jual akun', 'AD', 'REVIEW', '*', 'id-ID', 1)
|
||
ON CONFLICT (language, word) DO NOTHING;
|