オンデマンドのPostgreSQL匿名化

ここでは、匿名化を実現する方法を紹介します。会社の従業員の記録を含む次の表を考えてみましょう。

testdb=# create table person(id serial primary key, surname text not null, givenname text not null, midname text, address text not null, email text not null, role text not null, rank text not null);
CREATE TABLE
testdb=# insert into person(surname,givenname,address,email,role,rank) values('Singh','Kumar','2 some street, Mumbai, India','[email protected]','Seafarer','Captain');
INSERT 0 1
testdb=# insert into person(surname,givenname,address,email,role,rank) values('Mantzios','Achilleas','Agiou Titou 10, Iraklio, Crete, Greece','[email protected]','IT','DBA');
INSERT 0 1
testdb=# insert into person(surname,givenname,address,email,role,rank) values('Emanuel','Tsatsadakis','Knossou 300, Iraklio, Crete, Greece','[email protected]','IT','Developer');
INSERT 0 1
testdb=#

このテーブルは公開されており、誰でもクエリを実行でき、公開スキーマに属しています。次に、匿名化の基本的なメカニズムを作成します。これは次の要素で構成されます。

• 関連するテーブルとビューを保持するための新しいスキーマ、これを匿名と呼びましょう
• 忘れたい人のIDを含むテーブル：anonym.person_anonym
• public.personの匿名化されたバージョンを提供するビュー：anonym.person
• 新しいビューを使用するための、search_pathの設定

testdb=# create schema anonym;
CREATE SCHEMA
testdb=# create table anonym.person_anonym(id INT NOT NULL REFERENCES public.person(id));
CREATE TABLE

CREATE OR REPLACE VIEW anonym.person AS
SELECT p.id,
    CASE
        WHEN pa.id IS NULL THEN p.givenname
        ELSE '****'::character varying
    END AS givenname,
    CASE
        WHEN pa.id IS NULL THEN p.midname
        ELSE '****'::character varying
    END AS midname,
    CASE
        WHEN pa.id IS NULL THEN p.surname
        ELSE '****'::character varying
    END AS surname,
    CASE
        WHEN pa.id IS NULL THEN p.address
        ELSE '****'::text
    END AS address,
    CASE
        WHEN pa.id IS NULL THEN p.email
        ELSE '****'::character varying
    END AS email,
    role,
    rank
  FROM person p
LEFT JOIN anonym.person_anonym pa ON p.id = pa.id
;

search_pathをアプリケーションに設定しましょう：

set search_path = anonym,"$user", public;

警告 ：アプリケーションのデータソース定義でsearch_pathが正しく設定されていることが重要です。読者は、検索パスを処理するためのより高度な方法を検討することをお勧めします。より複雑で動的なロジックを処理できる関数を使用します。たとえば、データ入力ユーザー（またはロール）のセットを指定し、管理/レポートユーザーのセットを定義しながら、匿名化間隔全体でpublic.personテーブルを引き続き使用できるようにすることができます（通常のデータが表示され続けるようにするため）。 （または役割）匿名化ロジックが適用される対象。

では、人と人との関係について質問しましょう：

testdb=# select * from person;
-[ RECORD 1 ]-------------------------------------
id    | 2
givenname | Achilleas
midname   |
surname   | Mantzios
address   | Agiou Titou 10, Iraklio, Crete, Greece
email | [email protected]
role  | IT
rank  | DBA
-[ RECORD 2 ]-------------------------------------
id    | 1
givenname | Kumar
midname   |
surname   | Singh
address   | 2 some street, Mumbai, India
email | [email protected]
role  | Seafarer
rank  | Captain
-[ RECORD 3 ]-------------------------------------
id    | 3
givenname | Tsatsadakis
midname   |
surname   | Emanuel
address   | Knossou 300, Iraklio, Crete, Greece
email | [email protected]
role  | IT
rank  | Developer

testdb=#

ここで、シン氏が会社を辞め、書面による声明によって忘れられる権利を明示的に表明したとします。アプリケーションは、彼のIDを「忘れられる」IDのセットに挿入することによってこれを行います：

testdb=# insert into anonym.person_anonym (id) VALUES(1);
INSERT 0 1

前に実行した正確なクエリを繰り返しましょう：

testdb=# select * from person;
-[ RECORD 1 ]-------------------------------------
id    | 1
givenname | ****
midname   | ****
surname   | ****
address   | ****
email | ****
role  | Seafarer
rank  | Captain
-[ RECORD 2 ]-------------------------------------
id    | 2
givenname | Achilleas
midname   |
surname   | Mantzios
address   | Agiou Titou 10, Iraklio, Crete, Greece
email | [email protected]
role  | IT
rank  | DBA
-[ RECORD 3 ]-------------------------------------
id    | 3
givenname | Tsatsadakis
midname   |
surname   | Emanuel
address   | Knossou 300, Iraklio, Crete, Greece
email | [email protected]
role  | IT
rank  | Developer

testdb=#

testdb=# BEGIN ;
BEGIN
testdb=# LOCK public.person IN SHARE MODE ;
LOCK TABLE
testdb=# PREPARE TRANSACTION 'personlock';
PREPARE TRANSACTION
testdb=#

testdb=# select px.*,l0.* from pg_prepared_xacts px , pg_locks l0 where px.gid='personlock' AND l0.virtualtransaction='-1/'||px.transaction AND l0.relation='public.person'::regclass AND l0.mode='ShareLock';
-[ RECORD 1 ]------+----------------------------
transaction    | 725
gid            | personlock
prepared       | 2020-05-23 15:34:47.2155+03
owner          | postgres
database       | testdb
locktype       | relation
database       | 16384
relation       | 32829
page           |
tuple          |
virtualxid     |
transactionid  |
classid        |
objid          |
objsubid       |
virtualtransaction | -1/725
pid            |
mode           | ShareLock
granted        | t
fastpath       | f

testdb=#

CREATE OR REPLACE VIEW anonym.person AS
WITH perlockqry AS (
    SELECT 1
      FROM pg_prepared_xacts px,
        pg_locks l0
      WHERE px.gid = 'personlock'::text AND l0.virtualtransaction = ('-1/'::text || px.transaction) AND l0.relation = 'public.person'::regclass::oid AND l0.mode = 'ShareLock'::text
    )
SELECT p.id,
    CASE
        WHEN pa.id IS NULL AND NOT (EXISTS ( SELECT 1
          FROM perlockqry)) THEN p.givenname::character varying
        ELSE '****'::character varying
    END AS givenname,
    CASE
        WHEN pa.id IS NULL AND NOT (EXISTS ( SELECT 1
          FROM perlockqry)) THEN p.midname::character varying
        ELSE '****'::character varying
    END AS midname,
    CASE
        WHEN pa.id IS NULL AND NOT (EXISTS ( SELECT 1
          FROM perlockqry)) THEN p.surname::character varying
        ELSE '****'::character varying
    END AS surname,
    CASE
        WHEN pa.id IS NULL AND NOT (EXISTS ( SELECT 1
          FROM perlockqry)) THEN p.address
        ELSE '****'::text
    END AS address,
    CASE
        WHEN pa.id IS NULL AND NOT (EXISTS ( SELECT 1
          FROM perlockqry)) THEN p.email::character varying
        ELSE '****'::character varying
    END AS email,
p.role,
p.rank
  FROM public.person p
LEFT JOIN person_anonym pa ON p.id = pa.id

testdb=# select * from person;
id | givenname | midname | surname | address | email |   role   |   rank   
----+-----------+---------+---------+---------+-------+----------+-----------
  1 | ****  | **** | **** | **** | ****  | Seafarer | Captain
  2 | ****  | **** | **** | **** | ****  | IT   | DBA
  3 | ****  | **** | **** | **** | ****  | IT   | Developer
(3 rows)

testdb=#

COMMIT PREPARED 'personlock';

testdb=# select * from person;
id |  givenname  | midname | surname  |            address             |         email         |   role   |   rank   
----+-------------+---------+----------+----------------------------------------+-------------------------------+----------+-----------
  1 | ****    | **** | **** | ****                               | ****                      | Seafarer | Captain
  2 | Achilleas   |     | Mantzios | Agiou Titou 10, Iraklio, Crete, Greece | [email protected]   | IT   | DBA
  3 | Tsatsadakis |     | Emanuel  | Knossou 300, Iraklio, Crete, Greece | [email protected] | IT   | Developer
(3 rows)

testdb=#

set lock_timeout TO 1;