first commit

files/redaction_23ai.sql

@@ -0,0 +1,77 @@
+ CREATE TABLE PROCESSED_EMAILS (
+         ID NUMBER GENERATED ALWAYS AS IDENTITY,
+         DATE_SENT TIMESTAMP,
+         BOOKING VARCHAR2(100),
+         EMAIL_FROM VARCHAR2(500),
+         EMAIL_TO VARCHAR2(1000),
+         SUBJECT VARCHAR2(1000),
+         STATUS VARCHAR2(100),
+         INSERT_DATE TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+         PRIMARY KEY (ID)
+     );
+
+ ALTER TABLE PROCESSED_EMAILS ADD (
+         BRIEF_DESCRIPTION VARCHAR2(1000),
+         ALERT VARCHAR2(10),
+         THREAD_INDEX NUMERIC(10),
+         FILE_NAME VARCHAR(400)
+               );
+
+CREATE OR REPLACE VIEW PROCESSED_EMAILS_REDACTED AS
+SELECT
+----------------------------------------------------------------------
+-- EMAIL_TO: remove names, parentheses, and mask all email addresses
+----------------------------------------------------------------------
+REGEXP_REPLACE(
+    REGEXP_REPLACE(
+        REGEXP_REPLACE(
+            -- 1️⃣ Remove names and content inside parentheses before the <email>
+                                                                      EMAIL_TO,
+'([[:alpha:]][[:alpha:] .''()_-]*)<([^>]+)>',
+'<\2>'
+),
+-- 2️⃣ Mask email addresses
+'([A-Za-z])([A-Za-z0-9._%+-]*)@([A-Za-z])([A-Za-z0-9.-]*)(\.[A-Za-z]{2,}(?:\.[A-Za-z]{2,})*)',
+'\1******@\3******\5',
+1, 0, 'i'
+),
+-- 3️⃣ Normalize ";" separators
+'\s*;\s*', '; '
+) AS EMAIL_TO,
+
+----------------------------------------------------------------------
+-- EMAIL_FROM: same treatment (remove names, parentheses, mask)
+----------------------------------------------------------------------
+REGEXP_REPLACE(
+    REGEXP_REPLACE(
+        REGEXP_REPLACE(
+            EMAIL_FROM,
+            '([[:alpha:]][[:alpha:] .''()_-]*)<([^>]+)>',
+            '<\2>'
+        ),
+        '([A-Za-z])([A-Za-z0-9._%+-]*)@([A-Za-z])([A-Za-z0-9.-]*)(\.[A-Za-z]{2,}(?:\.[A-Za-z]{2,})*)',
+        '\1******@\3******\5',
+        1, 0, 'i'
+    ),
+    '\s*;\s*', '; '
+) AS EMAIL_FROM,
+
+SUBJECT,
+
+----------------------------------------------------------------------
+-- Mask BOOKING (for example, a code or sensitive text)
+----------------------------------------------------------------------
+REGEXP_REPLACE(
+    BOOKING,
+    '([A-Za-z0-9])([A-Za-z0-9 _.-]*)',
+    '***'
+) AS BOOKING,
+
+DATE_SENT,
+STATUS,
+FILE_NAME,
+THREAD_INDEX,
+INSERT_DATE,
+BRIEF_DESCRIPTION,
+ALERT
+FROM PROCESSED_EMAILS;