feat: extend regex parser for IT-Systemhaus service periods, contract types, and serial numbers

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-07 15:16:30 +02:00 · 2026-07-07 15:16:30 +02:00 · 3b3a2dce90
parent 0dd9916079
commit 3b3a2dce90
3 changed files with 137 additions and 4 deletions
--- a/invoice_logic.py
+++ b/invoice_logic.py
@ -140,7 +140,13 @@ def extract_invoice_items_pure_python(text):
    items = []
    lines = [line.strip() for line in text.split("\n") if line.strip()]

-    unit_pattern = re.compile(r"^(\d+(?:[\.,]\d+)?)\s*(Tag\(e\)|Std\.|Stk\.|Stunden|Stück|stk|stck|stück)$", re.IGNORECASE)
+    # IT-Systemhaus-Erweiterung: zusaetzlich Monats-/Lizenz-/Personentag-Abrechnungseinheiten,
+    # wie sie bei Managed-Services-, Cloud-Abo- und Projekthonorar-Rechnungen ueblich sind.
+    unit_pattern = re.compile(
+        r"^(\d+(?:[\.,]\d+)?)\s*(Tag\(e\)|Std\.|Stk\.|Stunden|Stück|stk|stck|stück|"
+        r"Monat\(e\)|Monate|Personentage|Personentag|PT|Lizenz\(en\)|Lizenzen|Lizenz|Wartungspauschale)$",
+        re.IGNORECASE,
+    )
    price_stop_pattern = re.compile(r"^[\d\.]+,[\d]{2}$")

    for i, line in enumerate(lines):
@ -190,10 +196,63 @@ def extract_invoice_items_pure_python(text):

 def map_unece_unit_code(unit_str):
    u = str(unit_str).lower()
+    if "monat" in u: return "MON"
+    if "personentag" in u or u == "pt": return "DAY"
    if "tag" in u or "day" in u: return "DAY"
-    elif "std" in u or "stund" in u or "hour" in u or "hur" in u: return "HUR"
+    if "std" in u or "stund" in u or "hour" in u or "hur" in u: return "HUR"
    return "C62"

+SERVICE_PERIOD_PATTERN = re.compile(
+    r"(?:Leistungszeitraum|Zeitraum|Einsatzzeitraum)\s*:?\s*"
+    r"(?:vom\s+)?(\d{1,2}[.\-]\d{1,2}[.\-]\d{4})\s*(?:bis|-|–)\s*(\d{1,2}[.\-]\d{1,2}[.\-]\d{4})",
+    re.IGNORECASE,
+)
+
+
+def extract_service_period(text):
+    """Regex-Fallback fuer den Leistungszeitraum (z.B. 'Leistungszeitraum: 01.03.2026 bis
+    31.03.2026'), falls das LLM diesen nicht extrahiert hat. Gibt (start, end) als YYYY-MM-DD
+    zurueck, oder ("", "") wenn nichts gefunden wurde."""
+    match = SERVICE_PERIOD_PATTERN.search(text)
+    if not match:
+        return "", ""
+    start = parse_to_strict_xml_date(match.group(1).replace("-", "."))
+    end = parse_to_strict_xml_date(match.group(2).replace("-", "."))
+    return start, end
+
+
+CONTRACT_TYPE_KEYWORDS = {
+    "Managed Services": re.compile(r"managed\s+services?", re.IGNORECASE),
+    "Cloud-Abonnement": re.compile(r"cloud[\s\-]?(abo(nnement)?|subscription)", re.IGNORECASE),
+    "Projekthonorar": re.compile(r"projekt(honorar|vergütung|pauschale)", re.IGNORECASE),
+}
+
+
+def detect_contract_type(text):
+    """Erkennt den IT-Systemhaus-Vertragstyp anhand von Schluesselwoertern im Rechnungstext.
+    Gibt das erste gefundene Label zurueck oder "", wenn keines passt (keine Vermutung)."""
+    for label, pattern in CONTRACT_TYPE_KEYWORDS.items():
+        if pattern.search(text):
+            return label
+    return ""
+
+
+SERIAL_NUMBER_PATTERN = re.compile(
+    r"(?:S/?N|Seriennummer|Serial(?:\s*No\.?)?)\s*:?\s*([A-Z0-9][A-Z0-9\-]{4,})",
+    re.IGNORECASE,
+)
+
+
+def extract_hardware_serial_numbers(text):
+    """Findet Hardware-Seriennummern im Rechnungstext (Muster 'S/N: ...', 'Seriennummer: ...').
+    Gibt eine Liste der gefundenen Seriennummern in Text-Reihenfolge zurueck, ohne Duplikate."""
+    found = []
+    for match in SERIAL_NUMBER_PATTERN.finditer(text):
+        serial = match.group(1).strip()
+        if serial not in found:
+            found.append(serial)
+    return found
+
 def parse_to_strict_xml_date(date_str):
    """Normalisiert ein Datum auf 'YYYY-MM-DD'. Gibt leeren String zurück, wenn das Datum
    fehlt ODER nicht geparst werden kann - NICHT still auf 'heute' fallen, damit fehlerhafte
--- a/main.py
+++ b/main.py
@ -24,6 +24,9 @@ from invoice_logic import (
    add_pdfa_output_intent,
    fix_xrechnung_xmp_conformance,
    compute_invoice_totals,
+    extract_service_period,
+    detect_contract_type,
+    extract_hardware_serial_numbers,
 )

 # ==========================================
@ -174,9 +177,20 @@ with col2:
                
                if final_data.get("recipient_email") == VERKAEUFER["email"]:
                    final_data["recipient_email"] = ""
-                
+
                final_data["items"] = extract_invoice_items_pure_python(pdf_text)
-                
+
+                # IT-Systemhaus-Regex-Fallbacks: nur ergaenzen, wenn das LLM die entsprechenden
+                # Felder nicht bereits geliefert hat.
+                if not final_data.get("service_start_date") and not final_data.get("service_end_date"):
+                    fallback_start, fallback_end = extract_service_period(pdf_text)
+                    if fallback_start and fallback_end:
+                        final_data["service_start_date"] = fallback_start
+                        final_data["service_end_date"] = fallback_end
+
+                final_data["contract_type"] = detect_contract_type(pdf_text)
+                final_data["hardware_serials"] = extract_hardware_serial_numbers(pdf_text)
+
                st.session_state.invoice_counter += 1
                st.session_state.extracted_data = final_data

@ -184,6 +198,10 @@ with col2:
        data = st.session_state.extracted_data
        
        st.caption("Mit :red[*] markierte Felder sind EN16931-Pflichtfelder und müssen für einen gültigen Export befüllt sein.")
+        if data.get("contract_type"):
+            st.caption(f"🏷️ Erkannter Vertragstyp: **{data['contract_type']}**")
+        if data.get("hardware_serials"):
+            st.caption(f"🔧 Erkannte Seriennummern: {', '.join(data['hardware_serials'])}")

        # --- BT-3 RECHNUNGSTYP DROPDOWN-MENÜ ---
        inv_type_ui = st.selectbox(
--- a/tests/test_invoice_logic.py
+++ b/tests/test_invoice_logic.py
@ -15,6 +15,9 @@ from invoice_logic import (
    aggregate_tax_subtotals,
    compute_invoice_totals,
    format_skonto_text,
+    extract_service_period,
+    detect_contract_type,
+    extract_hardware_serial_numbers,
 )


@ -96,6 +99,25 @@ def test_map_unece_unit_code_hours():
    assert map_unece_unit_code("Std.") == "HUR"


+def test_extract_invoice_items_pure_python_recognizes_person_days():
+    text = "1\nProjektarbeit\n5,00 Personentage\n800,00\n4000,00\n"
+    items = extract_invoice_items_pure_python(text)
+    assert items[0]["quantity"] == 5.0
+    assert items[0]["unit"] == "Personentage"
+
+
+def test_extract_invoice_items_pure_python_recognizes_license_months():
+    text = "1\nCloud-Lizenz\n3,00 Monat(e)\n49,00\n147,00\n"
+    items = extract_invoice_items_pure_python(text)
+    assert items[0]["unit"] == "Monat(e)"
+
+
+def test_map_unece_unit_code_extended_units():
+    assert map_unece_unit_code("Monat(e)") == "MON"
+    assert map_unece_unit_code("Personentage") == "DAY"
+    assert map_unece_unit_code("Lizenz(en)") == "C62"
+
+
 def test_parse_to_strict_xml_date_german_format():
    assert parse_to_strict_xml_date("15.01.2026") == "2026-01-15"

@ -304,3 +326,37 @@ def test_generate_compliant_xrechnung_mixed_rate_discount_emits_allowance_per_ra
    assert percents == ["19.00", "7.00"] or percents == ["7.00", "19.00"]
    total_alloc = sum(float(a.find("cbc:Amount", ns).text) for a in allowances)
    assert abs(total_alloc - 20.0) < 0.001
+
+
+def test_extract_service_period_finds_range():
+    text = "Managed Services\nLeistungszeitraum: 01.03.2026 bis 31.03.2026\n1\n..."
+    start, end = extract_service_period(text)
+    assert start == "2026-03-01"
+    assert end == "2026-03-31"
+
+
+def test_extract_service_period_returns_empty_when_absent():
+    assert extract_service_period("Keine Zeitangabe hier.") == ("", "")
+
+
+def test_detect_contract_type_managed_services():
+    assert detect_contract_type("Wartungsvertrag Managed Services Tier 2") == "Managed Services"
+
+
+def test_detect_contract_type_cloud_abo():
+    assert detect_contract_type("Ihr Cloud-Abonnement für 2026") == "Cloud-Abonnement"
+
+
+def test_detect_contract_type_returns_empty_when_no_match():
+    assert detect_contract_type("Ganz normale Rechnung ohne Vertragstyp") == ""
+
+
+def test_extract_hardware_serial_numbers_finds_sn_pattern():
+    text = "Server Dell R750\nS/N: ABCD-1234-XYZ\nSwitch Cisco\nSeriennummer: SN9988771"
+    serials = extract_hardware_serial_numbers(text)
+    assert "ABCD-1234-XYZ" in serials
+    assert "SN9988771" in serials
+
+
+def test_extract_hardware_serial_numbers_empty_when_absent():
+    assert extract_hardware_serial_numbers("Keine Seriennummern hier.") == []