Two-pass PII redaction with multi-country pattern packs

Pass 1: deterministic regex with Nordic/European/ECHR/Global packs
covering fødselsnummer, Swedish personnummer, Danish/Finnish CPR,
UK NI, French INSEE, IBAN, EU phones, ECHR application numbers, DOB,
and national ID label patterns.

Pass 2: LLM semantic scan (Azure OpenAI) finds names, orgs, places
and identifying descriptions missed by regex. Runs on pre-redacted
text so no raw PII reaches the LLM.

Adds region selector (Nordic/European/ECHR/Global) to the Redact UI.
Falls back gracefully when Azure is not yet configured.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-05-07 01:27:52 +02:00
parent 2d8d1c7409
commit 9b22947eb2
5 changed files with 229 additions and 42 deletions
+5
View File
@@ -99,6 +99,11 @@ $authenticated = dbnToolsIsAuthenticated();
<span class="control-label">Mode</span>
<label><input type="radio" name="redactionMode" value="standard" checked> Standard</label>
<label><input type="radio" name="redactionMode" value="strict"> Strict</label>
<span class="control-label" style="margin-left:1.25rem">Region</span>
<label><input type="radio" name="redactionRegion" value="nordic" checked> Nordic</label>
<label><input type="radio" name="redactionRegion" value="european"> European</label>
<label><input type="radio" name="redactionRegion" value="echr"> ECHR</label>
<label><input type="radio" name="redactionRegion" value="global"> Global</label>
</div>
<label class="input-label" for="toolInput" id="inputLabel">Question</label>