diff --git a/CHANGELOG.md b/CHANGELOG.md
index a99242d..f1360a1 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,6 +11,8 @@ Version numbers follow [Semantic Versioning](https://semver.org/spec/v2.0.0.html
### Added
+- **CPR-only mode** — a new `cpr_only` scan option (sidebar toggle `#optCprOnly`, profile editor `#peOptCprOnly`) makes all three scan engines skip items that have no qualifying CPR numbers. Files whose only hits are email addresses, phone numbers, detected faces, or EXIF/GPS metadata are not flagged. The flag already detected is still shown on cards when `cpr_only=false` (default). Gated in all three engines: file scan skip condition, M365 email flagging, M365 file flagging, and Google Gmail/Drive flagging.
+
- **OCR language override** — a new `ocr_lang` scan option (sidebar select `#optOcrLang`, profile editor `#peOptOcrLang`) lets operators choose the Tesseract language pack(s) used when scanning scanned PDFs and images. Presets: `dan+eng` (default), `dan`, `eng`, `dan+eng+deu`, `dan+eng+swe`, `dan+eng+fra`. The setting flows from the UI through the profile, into all three scan engines (M365 `_scan_bytes_timeout`, M365 attachments `_scan_bytes`, M365 files `_scan_bytes`, Google `_scan_bytes` for both Gmail and Drive). The `lang` parameter is threaded through `cpr_detector._scan_bytes` → `document_scanner.scan_pdf` / `scan_image` and the spawned PDF-OCR subprocess worker. The OCR cache key already included `lang`, so per-language results are cached independently.
- **Built-in file redaction for local files** — a scissor button (`✂`) appears on cards for local DOCX, XLSX, CSV, and TXT files. Clicking it rewrites the file in-place with all detected CPR numbers replaced by `██████-████` (DOCX/XLSX) or `█`-blocks (CSV/TXT), then removes the card from the grid and logs a `"redacted"` disposition. The redaction is atomic: a temp file in the same directory is written first and then moved over the original, so a crash never leaves a half-written file. Implemented in `routes/export.py` (`POST /api/redact_item`) using the existing `document_scanner` redact functions; front-end in `results.js` (`redactItem`) with the button hidden for non-local or unsupported-extension items and for resolved/viewer-mode cards.
diff --git a/lang/da.json b/lang/da.json
index 0b95afe..6faf48d 100644
--- a/lang/da.json
+++ b/lang/da.json
@@ -577,6 +577,8 @@
"m365_badge_emails": "e-mail",
"m365_badge_phones": "tlf.",
"m365_opt_min_cpr_hint": "Filer med færre distinkte CPR-numre end denne tærskel rapporteres ikke. Sæt til 2 for at undgå falske positive, når elever har egne CPR-numre i filer.",
+ "m365_opt_cpr_only": "Kun CPR-tilstand",
+ "m365_opt_cpr_only_hint": "Flagger kun filer med CPR-numre. Filer med kun e-mailadresser, telefonnumre, ansigter eller EXIF-metadata ignoreres.",
"m365_opt_ocr_lang": "OCR-sprog",
"m365_opt_ocr_lang_hint": "Tesseract-sprogpakke(r) der bruges ved scanning af scannede PDF'er og billeder. Sprogpakker skal være installeret på serveren (f.eks. tesseract-ocr-dan). Flere pakker: dan+eng.",
"m365_filter_photo_only": "📷 Billeder / biometrisk",
diff --git a/lang/de.json b/lang/de.json
index 81b786c..6056214 100644
--- a/lang/de.json
+++ b/lang/de.json
@@ -577,6 +577,8 @@
"m365_badge_emails": "E-Mail",
"m365_badge_phones": "Tel.",
"m365_opt_min_cpr_hint": "Dateien mit weniger eindeutigen CPR-Nummern als dieser Schwellenwert werden nicht gemeldet. Auf 2 setzen, um Falsch-Positive zu vermeiden, wenn Schüler eigene CPR-Nummern in Dateien haben.",
+ "m365_opt_cpr_only": "Nur-CPR-Modus",
+ "m365_opt_cpr_only_hint": "Markiert nur Dateien mit CPR-Nummern. Dateien mit nur E-Mail-Adressen, Telefonnummern, Gesichtern oder EXIF-Metadaten werden ignoriert.",
"m365_opt_ocr_lang": "OCR-Sprache",
"m365_opt_ocr_lang_hint": "Tesseract-Sprachpaket(e) für das Scannen von gescannten PDFs und Bildern. Pakete müssen auf dem Server installiert sein (z.B. tesseract-ocr-dan). Mehrere Pakete: dan+eng.",
"m365_filter_photo_only": "📷 Fotos / biometrisch",
diff --git a/lang/en.json b/lang/en.json
index de19caa..9416b20 100644
--- a/lang/en.json
+++ b/lang/en.json
@@ -577,6 +577,8 @@
"m365_badge_emails": "email",
"m365_badge_phones": "phone",
"m365_opt_min_cpr_hint": "Files with fewer distinct CPR numbers than this threshold are not reported. Set to 2 to avoid false positives when students have their own CPR in documents.",
+ "m365_opt_cpr_only": "CPR-only mode",
+ "m365_opt_cpr_only_hint": "Only flag files that contain CPR numbers. Files with only email addresses, phone numbers, detected faces, or EXIF metadata are skipped.",
"m365_opt_ocr_lang": "OCR language",
"m365_opt_ocr_lang_hint": "Tesseract language pack(s) used when scanning scanned PDFs and images. Language packs must be installed on the server (e.g. tesseract-ocr-dan). Multiple packs: dan+eng.",
"m365_filter_photo_only": "📷 Photos / biometric",
diff --git a/scan_engine.py b/scan_engine.py
index 725906b..af5cf76 100644
--- a/scan_engine.py
+++ b/scan_engine.py
@@ -316,7 +316,7 @@ def run_file_scan(source: dict):
not skip_gps_images or bool(_exif.get("pii_fields") or _exif.get("author"))
)
- if not (_cpr_qualifies and cprs) and not _distinct_emails and not _distinct_phones and _face_count == 0 and not _exif_has_pii:
+ if not (_cpr_qualifies and cprs) and (cpr_only or (not _distinct_emails and not _distinct_phones and _face_count == 0 and not _exif_has_pii)):
continue
# Build card metadata
@@ -477,6 +477,7 @@ def run_scan(options: dict):
skip_gps_images= bool(scan_opts.get("skip_gps_images", False))
min_cpr_count = max(1, int(scan_opts.get("min_cpr_count", 1)))
ocr_lang = str(scan_opts.get("ocr_lang", "dan+eng")) or "dan+eng"
+ cpr_only = bool(scan_opts.get("cpr_only", False))
scan_emails = bool(scan_opts.get("scan_emails", False))
scan_phones = bool(scan_opts.get("scan_phones", False))
@@ -1145,7 +1146,7 @@ def run_scan(options: dict):
_distinct_emails = list(dict.fromkeys(e["formatted"] for e in all_emails))
_distinct_phones = list(dict.fromkeys(p["formatted"] for p in all_phones))
- if all_cprs or _distinct_emails or _distinct_phones:
+ if all_cprs or (not cpr_only and (_distinct_emails or _distinct_phones)):
meta["_thumb"] = _placeholder_svg(".eml", subject)
meta["_thumb_is_jpeg"] = False
meta["_attachments"] = att_results
@@ -1211,7 +1212,7 @@ def run_scan(options: dict):
)
# Flag item if CPRs/emails/phones found, faces detected, or EXIF PII found
- if (_cpr_qualifies and cprs) or _distinct_emails or _distinct_phones or _face_count > 0 or _exif_has_pii:
+ if (_cpr_qualifies and cprs) or (not cpr_only and (_distinct_emails or _distinct_phones or _face_count > 0 or _exif_has_pii)):
# Make thumbnail
if ext in {".jpg", ".jpeg", ".png"} and PIL_OK:
thumb = _make_thumb(content, name)
diff --git a/static/js/profiles.js b/static/js/profiles.js
index 91c18a9..18f9cff 100644
--- a/static/js/profiles.js
+++ b/static/js/profiles.js
@@ -142,6 +142,11 @@ function _applyProfile(profile) {
if (el) el.value = opts.ocr_lang;
}
+ if (opts.cpr_only !== undefined) {
+ const el = document.getElementById('optCprOnly');
+ if (el) el.checked = opts.cpr_only;
+ }
+
if (opts.scan_emails !== undefined) {
const el = document.getElementById('optScanEmails');
if (el) el.checked = opts.scan_emails;
@@ -432,6 +437,7 @@ function _openEditorForProfile(profile) {
${t('m365_opt_scan_photos','Søg efter ansigter i billeder')}
${t('m365_opt_skip_gps','Ignorer GPS i billeder')}
${t('m365_opt_min_cpr','Min. CPR-antal pr. fil')}
+
${t('m365_opt_cpr_only','CPR-only mode')}
${t('m365_opt_ocr_lang','OCR-sprog')}
${t('m365_opt_scan_emails','Søg efter e-mailadresser')}
${t('m365_opt_scan_phones','Søg efter telefonnumre')}