Jonas Arnold Praktikum alle Files hinzugefügt

Input CSV/Normvokabular_INTERN/.~lock.NV_MASTER.ods#

@@ -1 +0,0 @@
-,jarnold,workPC,10.10.2025 09:26,file:///home/jarnold/.config/libreoffice/4;

Mapper_Makro_Alte_Versionen/mapper_macro_1.4.py

@@ -0,0 +1,469 @@
+# -*- coding: utf-8 -*-
+# mapper_macro 1.5 - LibreOffice Calc
+# Features: Kompositum-Split, Cache, Live-Vorschläge nur auf 'Objektbeschreibung', Logging
+
+import os
+import re
+import json
+import datetime
+
+# optional imports (Pandas, Spacy, RapidFuzz)
+try:
+    import pandas as pd
+    PANDAS_AVAILABLE = True
+except Exception:
+    PANDAS_AVAILABLE = False
+
+try:
+    import spacy
+    nlp = spacy.load("de_core_news_sm")
+    SPACY_AVAILABLE = True
+except Exception:
+    SPACY_AVAILABLE = False
+    nlp = None
+
+try:
+    from rapidfuzz import fuzz
+    RAPIDFUZZ_AVAILABLE = True
+except Exception:
+    RAPIDFUZZ_AVAILABLE = False
+    from difflib import SequenceMatcher
+
+# ------------------------
+# Konfiguration
+# ------------------------
+BASE_DIR = "/home/jarnold/.config/libreoffice/4/user/Scripts/python/NV Abgleich Makro"
+NV_MASTER_PATH = os.path.join(BASE_DIR, "NV_MASTER.ods")
+CACHE_FILE = os.path.join(BASE_DIR, "mapper_cache.json")
+LOG_FILE = os.path.join(BASE_DIR, "mapper_macro.log")
+
+STOPWORDS = {
+    "mit","ohne","der","die","das","ein","eine","und","zu","von","im","in","auf","an",
+    "als","bei","für","aus","dem","den","des","eines","einer"
+}
+CONF_THRESHOLD = 0.75
+
+# ------------------------
+# Logging
+# ------------------------
+def log(msg, level="INFO"):
+    ts = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+    line = f"[{ts}] [{level}] {msg}\n"
+    try:
+        os.makedirs(os.path.dirname(LOG_FILE), exist_ok=True)
+        with open(LOG_FILE, "a", encoding="utf-8") as f:
+            f.write(line)
+    except Exception:
+        pass
+
+# ------------------------
+# Cache laden
+# ------------------------
+try:
+    if os.path.exists(CACHE_FILE):
+        with open(CACHE_FILE, "r", encoding="utf-8") as f:
+            CACHE = json.load(f)
+    else:
+        CACHE = {}
+except Exception as e:
+    CACHE = {}
+    log(f"Fehler beim Laden des Caches: {e}", level="ERROR")
+
+# ------------------------
+# Textnormalisierung & Lemma
+# ------------------------
+lemma_cache = {}
+
+def normalize_text(s):
+    if not s:
+        return ""
+    s = str(s).strip().lower()
+    s = re.sub(r"[\(\)\[\]\"'\\;:\?!,\.]", "", s)
+    s = re.sub(r"\s+", " ", s)
+    return s
+
+def lemmatize_term(term):
+    term_norm = normalize_text(term)
+    if term_norm in lemma_cache:
+        return lemma_cache[term_norm]
+    if SPACY_AVAILABLE and nlp:
+        try:
+            doc = nlp(term_norm)
+            lemma = " ".join([t.lemma_ for t in doc])
+        except Exception:
+            lemma = term_norm
+    else:
+        lemma = term_norm
+    lemma_cache[term_norm] = lemma
+    return lemma
+
+# ------------------------
+# Kompositum-Splitting
+# ------------------------
+def compound_split(term):
+    if not term:
+        return []
+    parts = re.findall(r'[A-ZÄÖÜ][a-zäöü]+', term)
+    if parts:
+        return parts
+    parts = [p for p in re.split(r'[-\s]+', term) if p]
+    return parts or [term]
+
+# ------------------------
+# NV_MASTER indexieren
+# ------------------------
+def build_norm_index(nv_path):
+    norm_dict = {}
+    lemma_index = {}
+    if not PANDAS_AVAILABLE:
+        log("Pandas nicht verfügbar, NV_MASTER kann nicht gelesen.", level="ERROR")
+        return norm_dict, lemma_index
+    try:
+        sheets = pd.read_excel(nv_path, sheet_name=None, engine="odf")
+    except Exception as e:
+        log(f"Fehler beim Einlesen von NV_MASTER: {e}", level="ERROR")
+        return norm_dict, lemma_index
+
+    for sheet_name, df in sheets.items():
+        if str(sheet_name).strip().lower() == "master":
+            continue
+        df = df.fillna("")
+        cols = [str(c).strip().lower() for c in df.columns]
+        id_col = None
+        word_col = None
+        for i, c in enumerate(cols):
+            if "id" in c:
+                id_col = df.columns[i]
+            if "wort" in c or "vokabel" in c:
+                word_col = df.columns[i]
+        if word_col is None and len(df.columns) >= 1:
+            word_col = df.columns[-1]
+        if id_col is None and len(df.columns) >= 1:
+            id_col = df.columns[0]
+
+        current_parent_id = None
+        for _, row in df.iterrows():
+            id_val = str(row[id_col]).strip() if id_col in df.columns else ""
+            word_val = str(row[word_col]).strip() if word_col in df.columns else ""
+            if id_val:
+                current_parent_id = id_val
+            if not word_val:
+                continue
+            norm_name = normalize_text(word_val)
+            lemma = lemmatize_term(word_val)
+            entry = {"Name": word_val.strip(), "ID": current_parent_id or "", "Sheet": sheet_name}
+            norm_dict.setdefault(norm_name, []).append(entry)
+            lemma_index.setdefault(lemma, []).append(entry)
+
+    log(f"NV_MASTER geladen. Begriffe: {sum(len(v) for v in norm_dict.values())}")
+    return norm_dict, lemma_index
+
+# ------------------------
+# Fuzzy / Vorschläge
+# ------------------------
+def fuzzy_score(a, b):
+    if RAPIDFUZZ_AVAILABLE:
+        try:
+            return fuzz.token_set_ratio(a, b) / 100.0
+        except Exception:
+            return 0.0
+    else:
+        return SequenceMatcher(None, a.lower(), b.lower()).ratio()
+
+def get_suggestions_for_term(term_lemma, norm_dict, lemma_index, threshold=CONF_THRESHOLD):
+    candidates = []
+    for key_lemma, entries in lemma_index.items():
+        score = fuzzy_score(term_lemma, key_lemma)
+        if key_lemma.startswith(term_lemma):
+            score = min(score + 0.1, 1.0)
+        if score >= threshold:
+            for e in entries:
+                candidates.append((score, e["Name"], e["ID"]))
+    for norm_key, entries in norm_dict.items():
+        score = fuzzy_score(term_lemma, norm_key)
+        if norm_key.startswith(term_lemma):
+            score = min(score + 0.1, 1.0)
+        if score >= threshold:
+            for e in entries:
+                candidates.append((score, e["Name"], e["ID"]))
+    candidates.sort(key=lambda t: t[0], reverse=True)
+    seen = set()
+    results = []
+    for score, name, id_ in candidates:
+        key = (name, id_)
+        if key in seen:
+            continue
+        seen.add(key)
+        results.append({"score": score, "name": name, "id": id_})
+    return [f'{r["name"]} ({r["id"]})' if r["id"] else r["name"] for r in results]
+
+# ------------------------
+# Mapping eines Terms (mit Cache)
+# ------------------------
+def map_term_with_indexes(term, norm_dict, lemma_index):
+    term_norm = normalize_text(term)
+    term_lemma = lemmatize_term(term)
+    if term_lemma in CACHE:
+        c = CACHE[term_lemma]
+        return c.get("hits", []), c.get("suggestions", []), c.get("ids", [])
+
+    hits = []
+    suggestions = []
+    ids = []
+
+    if term_norm in norm_dict:
+        for e in norm_dict[term_norm]:
+            hits.append(e["Name"])
+            if e["ID"]:
+                ids.append(e["ID"])
+    if not hits and term_lemma in lemma_index:
+        for e in lemma_index[term_lemma]:
+            hits.append(e["Name"])
+            if e["ID"]:
+                ids.append(e["ID"])
+    suggestions = get_suggestions_for_term(term_lemma, norm_dict, lemma_index)
+
+    if not hits:
+        tokens = compound_split(term)
+        for t in tokens:
+            t_lemma = lemmatize_term(t)
+            if t_lemma in lemma_index:
+                for e in lemma_index[t_lemma]:
+                    hits.append(e["Name"])
+                    if e["ID"]:
+                        ids.append(e["ID"])
+            else:
+                suggestions.extend(get_suggestions_for_term(t_lemma, norm_dict, lemma_index))
+
+    def uniq(seq):
+        seen = set()
+        out = []
+        for x in seq:
+            if x not in seen:
+                seen.add(x)
+                out.append(x)
+        return out
+
+    hits = uniq(hits)
+    suggestions = uniq(suggestions)
+    ids = uniq(ids)
+
+    CACHE[term_lemma] = {"hits": hits, "suggestions": suggestions, "ids": ids}
+    return hits, suggestions, ids
+
+# ------------------------
+# Header + Spalten
+# ------------------------
+def find_header_and_cols(sheet):
+    try:
+        cursor = sheet.createCursor()
+        cursor.gotoStartOfUsedArea(False)
+        cursor.gotoEndOfUsedArea(True)
+        dr = cursor.getRangeAddress()
+    except Exception:
+        return None, None, None
+    header_row = None
+    objekt_col = None
+    for r in range(0, min(5, dr.EndRow + 1)):
+        for c in range(0, dr.EndColumn + 1):
+            try:
+                val = str(sheet.getCellByPosition(c, r).String).strip().lower()
+            except Exception:
+                val = ""
+            if val == "objektbeschreibung":
+                header_row = r
+                objekt_col = c
+                break
+        if objekt_col is not None:
+            break
+
+    if header_row is None:
+        return None, None, dr
+    existing = {}
+    for c in range(0, dr.EndColumn + 1):
+        try:
+            h = str(sheet.getCellByPosition(c, header_row).String).strip()
+        except Exception:
+            h = ""
+        if h == "Norm_Treffer":
+            existing["Norm_Treffer"] = c
+        if h == "Norm_Vorschlag":
+            existing["Norm_Vorschlag"] = c
+        if h == "Norm_ID":
+            existing["Norm_ID"] = c
+    return header_row, objekt_col, dr, existing
+
+# ------------------------
+# Optimierter Live-Handler (nur Objektbeschreibung)
+# ------------------------
+def on_objektbeschreibung_change(oEvent=None):
+    try:
+        doc = XSCRIPTCONTEXT.getDocument()
+        sheet = doc.CurrentController.ActiveSheet
+    except Exception as e:
+        log(f"Dokumentzugriff fehlgeschlagen: {e}", level="ERROR")
+        return
+
+    cell = None
+    try:
+        if oEvent and hasattr(oEvent, "Range") and oEvent.Range is not None:
+            cell = oEvent.Range
+        elif oEvent and hasattr(oEvent, "Source") and oEvent.Source is not None:
+            cell = oEvent.Source
+    except Exception:
+        cell = None
+    if cell is None:
+        try:
+            sel = doc.CurrentSelection
+            if hasattr(sel, "getCellByPosition"):
+                cell = sel
+            else:
+                cell = sel.getCellByPosition(0, 0)
+        except Exception as e:
+            log(f"Keine Selektion: {e}", level="ERROR")
+            return
+
+    try:
+        row_index = cell.CellAddress.Row
+        col_index = cell.CellAddress.Column
+    except Exception:
+        return
+
+    try:
+        header_row, objekt_col, dr, existing = find_header_and_cols(sheet)
+        if header_row is None or col_index != objekt_col:
+            return  # nur die Objektbeschreibung-Spalte bearbeiten
+        last_col = dr.EndColumn
+        if "Norm_Vorschlag" not in existing:
+            last_col += 1
+            existing["Norm_Vorschlag"] = last_col
+            sheet.getCellByPosition(last_col, header_row).String = "Norm_Vorschlag"
+        norm_sug_col = existing["Norm_Vorschlag"]
+    except Exception as e:
+        log(f"Fehler Spaltenbestimmung: {e}", level="ERROR")
+        return
+
+    try:
+        txt = str(cell.String).strip()
+        if not txt:
+            sheet.getCellByPosition(norm_sug_col, row_index).String = ""
+            return
+        norm_dict, lemma_index = build_norm_index(NV_MASTER_PATH)
+        suggestions_acc = []
+        clauses = [c.strip() for c in re.split(r",", txt) if c.strip()]
+        for cl in clauses:
+            parts = [p.strip() for p in re.split(r"\s+", cl) if p.strip()]
+            for p in parts:
+                if p.lower() in STOPWORDS or re.fullmatch(r"\d+", p):
+                    continue
+                for sp in compound_split(p):
+                    _, sugs, _ = map_term_with_indexes(sp, norm_dict, lemma_index)
+                    suggestions_acc.extend(sugs)
+
+        seen = set()
+        ordered = []
+        for s in suggestions_acc:
+            if s not in seen:
+                seen.add(s)
+                ordered.append(s)
+        sheet.getCellByPosition(norm_sug_col, row_index).String = " | ".join(ordered)
+
+        with open(CACHE_FILE, "w", encoding="utf-8") as f:
+            json.dump(CACHE, f, ensure_ascii=False, indent=2)
+
+    except Exception as e:
+        log(f"Fehler im Live-Handler: {e}", level="ERROR")
+
+# ------------------------
+# Batch-Durchlauf
+# ------------------------
+def run_mapper_macro():
+    log("=== mapper_macro 1.5 gestartet ===", level="INFO")
+    try:
+        doc = XSCRIPTCONTEXT.getDocument()
+        sheet = doc.CurrentController.ActiveSheet
+        cursor = sheet.createCursor()
+        cursor.gotoStartOfUsedArea(False)
+        cursor.gotoEndOfUsedArea(True)
+        dr = cursor.getRangeAddress()
+    except Exception as e:
+        log(f"Dokumentzugriff fehlgeschlagen: {e}", level="ERROR")
+        return
+
+    header_row, objekt_col, dr, existing = find_header_and_cols(sheet)
+    if objekt_col is None:
+        log("Spalte 'Objektbeschreibung' nicht gefunden.", level="ERROR")
+        return
+    if "Norm_Treffer" not in existing:
+        last_col = dr.EndColumn + 1
+        existing["Norm_Treffer"] = last_col
+        sheet.getCellByPosition(last_col, header_row).String = "Norm_Treffer"
+    if "Norm_Vorschlag" not in existing:
+        last_col = dr.EndColumn + 2
+        existing["Norm_Vorschlag"] = last_col
+        sheet.getCellByPosition(last_col, header_row).String = "Norm_Vorschlag"
+    if "Norm_ID" not in existing:
+        last_col = dr.EndColumn + 3
+        existing["Norm_ID"] = last_col
+        sheet.getCellByPosition(last_col, header_row).String = "Norm_ID"
+
+    norm_dict, lemma_index = build_norm_index(NV_MASTER_PATH)
+    GREEN, YELLOW, RED = 0xADFF2F, 0xFFA500, 0xCC0000
+
+    for r in range(header_row + 1, dr.EndRow + 1):
+        try:
+            cell = sheet.getCellByPosition(objekt_col, r)
+            txt = str(cell.String).strip()
+            if not txt:
+                continue
+            clauses = [c.strip() for c in re.split(r",", txt) if c.strip()]
+            terms = []
+            for cl in clauses:
+                for p in [p.strip() for p in re.split(r"\s+", cl) if p.strip()]:
+                    if p.lower() in STOPWORDS or re.fullmatch(r"\d+", p):
+                        continue
+                    terms.extend([sp.strip() for sp in compound_split(p) if sp.strip()])
+
+            row_hits, row_sugs, row_ids = [], [], []
+            any_unmapped = False
+            for term in terms:
+                hits, sugs, ids = map_term_with_indexes(term, norm_dict, lemma_index)
+                row_hits.extend(hits)
+                row_sugs.extend(sugs)
+                row_ids.extend(ids)
+                if not hits and not sugs:
+                    any_unmapped = True
+
+            def uniq(seq):
+                seen = set()
+                out = []
+                for x in seq:
+                    if x not in seen:
+                        seen.add(x)
+                        out.append(x)
+                return out
+
+            row_hits, row_sugs, row_ids = map(uniq, [row_hits, row_sugs, row_ids])
+            sheet.getCellByPosition(existing["Norm_Treffer"], r).String = " | ".join(row_hits)
+            sheet.getCellByPosition(existing["Norm_Vorschlag"], r).String = " | ".join(row_sugs)
+            sheet.getCellByPosition(existing["Norm_ID"], r).String = " | ".join(row_ids)
+
+            cell.CellBackColor = RED if any_unmapped else 0xFFFFFF
+            sheet.getCellByPosition(existing["Norm_Treffer"], r).CellBackColor = GREEN if row_hits and not any_unmapped else 0xFFFFFF
+            sheet.getCellByPosition(existing["Norm_Vorschlag"], r).CellBackColor = YELLOW if row_sugs else 0xFFFFFF
+
+        except Exception as e:
+            log(f"Fehler in Zeile {r}: {e}", level="ERROR")
+            continue
+
+    with open(CACHE_FILE, "w", encoding="utf-8") as f:
+        json.dump(CACHE, f, ensure_ascii=False, indent=2)
+    log("=== mapper_macro 1.5 fertig ===", level="INFO")
+
+# ------------------------
+# Export
+# ------------------------
+g_exportedScripts = (
+    run_mapper_macro,
+    on_objektbeschreibung_change
+)

Mapper_Makro_Alte_Versionen/mapper_macro_1.5.py

@@ -0,0 +1,508 @@
+# -*- coding: utf-8 -*-
+# mapper_macro 1.5 - korrigiert: Logging im Dokumentverzeichnis, stabile Button-Erstellung,
+# keine Listener, optimiertes Mapping (ohne Listener-Teil)
+
+import os
+import re
+import json
+import datetime
+
+# optionale Module (Pandas, Spacy, RapidFuzz)
+try:
+    import pandas as pd
+    PANDAS_AVAILABLE = True
+except Exception:
+    PANDAS_AVAILABLE = False
+
+try:
+    import spacy
+    nlp = spacy.load("de_core_news_sm")
+    SPACY_AVAILABLE = True
+except Exception:
+    SPACY_AVAILABLE = False
+    nlp = None
+
+try:
+    from rapidfuzz import fuzz
+    RAPIDFUZZ_AVAILABLE = True
+except Exception:
+    RAPIDFUZZ_AVAILABLE = False
+
+from difflib import SequenceMatcher
+
+# UNO (für Button/Paths)
+try:
+    import uno
+except Exception:
+    uno = None
+
+# ------------------------
+# Konfiguration (Fallback-BASE_DIR)
+# ------------------------
+BASE_DIR = os.path.expanduser("~/.config/libreoffice/4/user/Scripts/python/Vokabular_Abgleich_Makro")
+NV_MASTER_FILENAME = "NV_MASTER.ods"
+CACHE_FILENAME = "mapper_cache.json"
+LOG_FILENAME = "mapper_macro.log"
+
+STOPWORDS = {
+    "mit", "ohne", "der", "die", "das", "ein", "eine", "und", "zu", "von", "im", "in", "auf", "an",
+    "als", "bei", "für", "aus", "dem", "den", "des", "eines", "einer"
+}
+CONF_THRESHOLD = 0.82
+FUZZY_CUTOFF = 0.88
+
+# Per-document paths (initialized by set_paths_from_doc)
+DOC_DIR = BASE_DIR
+NV_MASTER_PATH = os.path.join(DOC_DIR, NV_MASTER_FILENAME)
+CACHE_FILE = os.path.join(DOC_DIR, CACHE_FILENAME)
+LOG_FILE = os.path.join(DOC_DIR, LOG_FILENAME)
+
+# in-memory cache
+try:
+    if os.path.exists(CACHE_FILE):
+        with open(CACHE_FILE, "r", encoding="utf-8") as f:
+            CACHE = json.load(f)
+    else:
+        CACHE = {}
+except Exception:
+    CACHE = {}
+
+# ------------------------
+# Pfade im Dokument setzen
+# ------------------------
+def set_paths_from_doc(doc):
+    global DOC_DIR, NV_MASTER_PATH, CACHE_FILE, LOG_FILE
+    try:
+        url = getattr(doc, "URL", "")
+        if url and url.strip():
+            # UNO liefert file:///...
+            try:
+                system_path = uno.fileUrlToSystemPath(url)
+            except Exception:
+                # fallback: try simple unquote
+                from urllib.parse import unquote, urlparse
+                parsed = urlparse(url)
+                if parsed.scheme == "file":
+                    system_path = unquote(parsed.path)
+                else:
+                    system_path = ""
+            if system_path:
+                d = os.path.dirname(system_path)
+                if os.path.isdir(d):
+                    DOC_DIR = d
+    except Exception:
+        DOC_DIR = BASE_DIR
+    NV_MASTER_PATH = os.path.join(DOC_DIR, NV_MASTER_FILENAME)
+    CACHE_FILE = os.path.join(DOC_DIR, CACHE_FILENAME)
+    LOG_FILE = os.path.join(DOC_DIR, LOG_FILENAME)
+
+# ------------------------
+# Logging (Dokumentdir, robust)
+# ------------------------
+def log(msg, level="INFO"):
+    ts = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+    line = f"[{ts}] [{level}] {msg}\n"
+    try:
+        # ensure directory exists
+        os.makedirs(os.path.dirname(LOG_FILE), exist_ok=True)
+        with open(LOG_FILE, "a", encoding="utf-8") as f:
+            f.write(line)
+    except Exception:
+        # absolute fallback: try writing into BASE_DIR
+        try:
+            fallback = os.path.join(BASE_DIR, LOG_FILENAME)
+            os.makedirs(os.path.dirname(fallback), exist_ok=True)
+            with open(fallback, "a", encoding="utf-8") as f:
+                f.write(line)
+        except Exception:
+            # last resort: silent
+            pass
+
+# ------------------------
+# Textvorbereitung & Helpers
+# ------------------------
+lemma_cache = {}
+
+def normalize_text(s):
+    if not s:
+        return ""
+    s = str(s).strip().lower()
+    s = re.sub(r"[\(\)\[\]\"'\\;:\?!,\.]", "", s)
+    s = re.sub(r"\s+", " ", s)
+    return s
+
+def lemmatize_term(term):
+    term_norm = normalize_text(term)
+    if term_norm in lemma_cache:
+        return lemma_cache[term_norm]
+    if SPACY_AVAILABLE and nlp:
+        try:
+            doc = nlp(term_norm)
+            lemma = " ".join([t.lemma_ for t in doc])
+        except Exception:
+            lemma = term_norm
+    else:
+        lemma = term_norm
+    lemma_cache[term_norm] = lemma
+    return lemma
+
+def compound_split(term):
+    if not term:
+        return []
+    parts = re.findall(r'[A-ZÄÖÜ][a-zäöü]+', term)
+    if parts:
+        return parts
+    parts = [p for p in re.split(r'[-\s]+', term) if p]
+    return parts or [term]
+
+# ------------------------
+# NV_MASTER indexieren
+# ------------------------
+def build_norm_index(nv_path):
+    norm_dict = {}
+    lemma_index = {}
+    if not PANDAS_AVAILABLE:
+        log("Pandas nicht verfügbar, NV_MASTER kann nicht gelesen.", level="ERROR")
+        return norm_dict, lemma_index
+    try:
+        sheets = pd.read_excel(nv_path, sheet_name=None, engine="odf")
+    except Exception as e:
+        log(f"Fehler beim Einlesen von NV_MASTER: {e}", level="ERROR")
+        return norm_dict, lemma_index
+
+    for sheet_name, df in sheets.items():
+        if str(sheet_name).strip().lower() == "master":
+            continue
+        df = df.fillna("")
+        cols = [str(c).strip().lower() for c in df.columns]
+        # find id/word columns with fallback
+        id_col = None
+        word_col = None
+        for i, c in enumerate(cols):
+            if "id" in c:
+                id_col = df.columns[i]
+            if "wort" in c or "vokabel" in c:
+                word_col = df.columns[i]
+        if word_col is None and len(df.columns) >= 1:
+            word_col = df.columns[-1]
+        if id_col is None and len(df.columns) >= 1:
+            id_col = df.columns[0]
+
+        current_parent_id = None
+        for _, row in df.iterrows():
+            id_val = str(row[id_col]).strip() if id_col in df.columns else ""
+            word_val = str(row[word_col]).strip() if word_col in df.columns else ""
+            if id_val:
+                current_parent_id = id_val
+            if not word_val:
+                continue
+            norm_name = normalize_text(word_val)
+            lemma = lemmatize_term(word_val)
+            entry = {"Name": word_val.strip(), "ID": current_parent_id or "", "Sheet": sheet_name}
+            norm_dict.setdefault(norm_name, []).append(entry)
+            lemma_index.setdefault(lemma, []).append(entry)
+
+    log(f"NV_MASTER geladen. Begriffe: {sum(len(v) for v in norm_dict.values())}", level="INFO")
+    return norm_dict, lemma_index
+
+# ------------------------
+# Fuzzy Matching
+# ------------------------
+def fuzzy_score(a, b):
+    a = (a or "").lower()
+    b = (b or "").lower()
+    if RAPIDFUZZ_AVAILABLE:
+        try:
+            return fuzz.token_sort_ratio(a, b) / 100.0
+        except Exception:
+            return 0.0
+    else:
+        return SequenceMatcher(None, a, b).ratio()
+
+def get_suggestions(term_lemma, norm_dict, lemma_index, threshold=FUZZY_CUTOFF, max_sugs=6):
+    candidates = []
+    term_norm = term_lemma or ""
+    for key_lemma, entries in lemma_index.items():
+        if not key_lemma:
+            continue
+        score = fuzzy_score(term_norm, key_lemma)
+        if key_lemma.startswith(term_norm):
+            score = min(score + 0.08, 1.0)
+        if score >= threshold:
+            for e in entries:
+                candidates.append((score, e["Name"], e["ID"]))
+    # also check normalized names
+    for norm_key, entries in norm_dict.items():
+        score = fuzzy_score(term_norm, norm_key)
+        if norm_key.startswith(term_norm):
+            score = min(score + 0.08, 1.0)
+        if score >= threshold:
+            for e in entries:
+                candidates.append((score, e["Name"], e["ID"]))
+    # sort & dedupe
+    candidates.sort(key=lambda t: t[0], reverse=True)
+    seen = set()
+    out = []
+    for score, name, id_ in candidates:
+        key = (name, id_)
+        if key in seen:
+            continue
+        seen.add(key)
+        if id_:
+            out.append(f"{name} ({id_})")
+        else:
+            out.append(name)
+        if len(out) >= max_sugs:
+            break
+    return out
+
+# ------------------------
+# Mapping mit Cache
+# ------------------------
+def map_term(term, norm_dict, lemma_index):
+    term_norm = normalize_text(term)
+    term_lemma = lemmatize_term(term)
+    if term_lemma in CACHE:
+        return CACHE[term_lemma]
+
+    hits = []
+    suggestions = []
+    ids = []
+
+    # exact
+    if term_norm in norm_dict:
+        for e in norm_dict[term_norm]:
+            hits.append(e["Name"])
+            if e["ID"]:
+                ids.append(e["ID"])
+
+    # lemma
+    if not hits and term_lemma in lemma_index:
+        for e in lemma_index[term_lemma]:
+            hits.append(e["Name"])
+            if e["ID"]:
+                ids.append(e["ID"])
+
+    # suggestions only if no hit
+    if not hits:
+        suggestions = get_suggestions(term_lemma, norm_dict, lemma_index)
+
+    # remove suggestions that are equal/contain hits
+    suggestions = [s for s in suggestions if not any(h.lower() in s.lower() for h in hits)]
+
+    result = {"hits": hits, "suggestions": suggestions, "ids": ids}
+    CACHE[term_lemma] = result
+    return result
+
+# ------------------------
+# Button erstellen (sicher)
+# ------------------------
+def add_macro_button(sheet):
+    try:
+        doc = XSCRIPTCONTEXT.getDocument()
+    except Exception:
+        log("add_macro_button: kein Dokument-Kontext", level="WARN")
+        return
+    try:
+        draw_page = sheet.DrawPage
+        # avoid duplicate
+        for shape in draw_page:
+            try:
+                if getattr(shape, "Name", "") == "MapperStartButton":
+                    return
+            except Exception:
+                continue
+
+        # create shape and button model
+        shape = doc.createInstance("com.sun.star.drawing.ControlShape")
+        shape.Name = "MapperStartButton"
+        shape.Position = uno.createUnoStruct("com.sun.star.awt.Point")
+        shape.Position.X = 1000
+        shape.Position.Y = 200
+        shape.Size = uno.createUnoStruct("com.sun.star.awt.Size")
+        shape.Size.Width = 3000
+        shape.Size.Height = 1000
+
+        button_model = doc.createInstance("com.sun.star.form.component.CommandButton")
+        button_model.Label = "Start Mapping"
+        button_model.HelpText = "Startet das Mapping (run_mapper_macro)"
+        # assign macro via ActionCommand is not enough; user must link in UI; we add the control and label
+
+        shape.Control = button_model
+        draw_page.add(shape)
+        log("Button 'MapperStartButton' erstellt.", level="INFO")
+    except Exception as e:
+        log(f"add_macro_button Fehler: {e}", level="ERROR")
+
+# ------------------------
+# Hauptlauf (ohne Listener)
+# ------------------------
+def run_mapper_macro():
+    try:
+        doc = XSCRIPTCONTEXT.getDocument()
+        set_paths_from_doc(doc)
+        log("=== mapper_macro gestartet ===", level="INFO")
+        sheet = doc.CurrentController.ActiveSheet
+        add_macro_button(sheet)
+
+        # used area
+        cursor = sheet.createCursor()
+        cursor.gotoStartOfUsedArea(False)
+        cursor.gotoEndOfUsedArea(True)
+        dr = cursor.getRangeAddress()
+
+        # find header and objekt col
+        header_row = None
+        objekt_col = None
+        for r in range(0, min(10, dr.EndRow + 1)):
+            for c in range(0, dr.EndColumn + 1):
+                try:
+                    val = str(sheet.getCellByPosition(c, r).String).strip().lower()
+                except Exception:
+                    val = ""
+                if val == "Objektbeschreibung":
+                    header_row = r
+                    objekt_col = c
+                    break
+            if objekt_col is not None:
+                break
+
+        if objekt_col is None:
+            log("run_mapper_macro: 'Objektbeschreibung' Header nicht gefunden.", level="ERROR")
+            return
+
+        # ensure result cols
+        existing = {}
+        last_col = dr.EndColumn
+        for c in range(0, dr.EndColumn + 1):
+            try:
+                h = str(sheet.getCellByPosition(c, header_row).String).strip()
+            except Exception:
+                h = ""
+            if h == "Norm_Treffer":
+                existing["Norm_Treffer"] = c
+            if h == "Norm_Vorschlag":
+                existing["Norm_Vorschlag"] = c
+            if h == "Norm_ID":
+                existing["Norm_ID"] = c
+
+        if "Norm_Treffer" not in existing:
+            last_col += 1
+            existing["Norm_Treffer"] = last_col
+            sheet.getCellByPosition(last_col, header_row).String = "Norm_Treffer"
+        if "Norm_Vorschlag" not in existing:
+            last_col += 1
+            existing["Norm_Vorschlag"] = last_col
+            sheet.getCellByPosition(last_col, header_row).String = "Norm_Vorschlag"
+        if "Norm_ID" not in existing:
+            last_col += 1
+            existing["Norm_ID"] = last_col
+            sheet.getCellByPosition(last_col, header_row).String = "Norm_ID"
+
+        norm_tr_col = existing["Norm_Treffer"]
+        norm_sug_col = existing["Norm_Vorschlag"]
+        norm_id_col = existing["Norm_ID"]
+
+        # build index
+        norm_dict, lemma_index = build_norm_index(NV_MASTER_PATH)
+        if not norm_dict and not lemma_index:
+            log("run_mapper_macro: NV_MASTER leer oder nicht lesbar.", level="ERROR")
+            return
+
+        GREEN, YELLOW, RED = 0xADFF2F, 0xFFFF66, 0xFF9999
+        rows_processed = 0
+
+        for r in range(header_row + 1, dr.EndRow + 1):
+            try:
+                cell = sheet.getCellByPosition(objekt_col, r)
+                txt = str(cell.String).strip()
+                if not txt:
+                    continue
+
+                # phrase-first: try entire cleaned phrase (remove stopwords)
+                tokens = [t.strip() for t in re.split(r'\s+', normalize_text(txt)) if t and t not in STOPWORDS]
+                phrase = " ".join(tokens).strip()
+                terms = []
+                if phrase:
+                    # first try phrase as whole
+                    mapped_phrase = map_term(phrase, norm_dict, lemma_index)
+                    if mapped_phrase["hits"] or mapped_phrase["suggestions"]:
+                        # use phrase result (flatten hits+suggestions for output)
+                        row_hits = mapped_phrase["hits"]
+                        row_sugs = mapped_phrase["suggestions"]
+                        row_ids = mapped_phrase["ids"]
+                        any_unmapped = False if (row_hits or row_sugs) else True
+                    else:
+                        # fallback to token/compound processing
+                        for p in [p for p in re.split(r'[,\s]+', txt) if p.strip()]:
+                            if p.lower() in STOPWORDS or re.fullmatch(r'\d+', p):
+                                continue
+                            for sp in compound_split(p):
+                                if sp and sp.strip():
+                                    terms.append(sp.strip())
+                        row_hits = []
+                        row_sugs = []
+                        row_ids = []
+                        any_unmapped = False
+                        for term in terms:
+                            mapped = map_term(term, norm_dict, lemma_index)
+                            hits, sugs, ids = mapped["hits"], mapped["suggestions"], mapped["ids"]
+                            if hits:
+                                row_hits.extend(hits)
+                            if sugs:
+                                row_sugs.extend(sugs)
+                            if ids:
+                                row_ids.extend(ids)
+                            if not hits and not sugs:
+                                any_unmapped = True
+                else:
+                    row_hits, row_sugs, row_ids = [], [], []
+                    any_unmapped = True
+
+                # dedupe preserving order
+                def uniq(seq):
+                    seen = set()
+                    out = []
+                    for x in seq:
+                        if x not in seen:
+                            seen.add(x)
+                            out.append(x)
+                    return out
+
+                row_hits = uniq(row_hits)
+                row_sugs = uniq(row_sugs)
+                row_ids = uniq(row_ids)
+
+                # write
+                sheet.getCellByPosition(norm_tr_col, r).String = " | ".join(row_hits)
+                sheet.getCellByPosition(norm_sug_col, r).String = " | ".join(row_sugs)
+                sheet.getCellByPosition(norm_id_col, r).String = " | ".join(row_ids)
+
+                cell.CellBackColor = RED if any_unmapped else 0xFFFFFF
+                sheet.getCellByPosition(norm_tr_col, r).CellBackColor = GREEN if row_hits else 0xFFFFFF
+                sheet.getCellByPosition(norm_sug_col, r).CellBackColor = YELLOW if row_sugs else 0xFFFFFF
+
+                rows_processed += 1
+            except Exception as e:
+                log(f"Fehler in Zeile {r}: {e}", level="ERROR")
+                continue
+
+        # persist cache file to DOC_DIR
+        try:
+            with open(CACHE_FILE, "w", encoding="utf-8") as f:
+                json.dump(CACHE, f, ensure_ascii=False, indent=2)
+        except Exception as e:
+            log(f"Cache speichern fehlgeschlagen: {e}", level="WARN")
+
+        log(f"=== mapper_macro fertig. Zeilen verarbeitet: {rows_processed} ===", level="INFO")
+    except Exception as e:
+        # top-level safety
+        try:
+            log(f"run_mapper_macro: Unhandled exception: {e}", level="ERROR")
+        except Exception:
+            pass
+
+# ------------------------
+# Export
+# ------------------------
+g_exportedScripts = (run_mapper_macro,)

Mapper_Makro_Alte_Versionen/mapper_macro_2.0.py

@@ -0,0 +1,343 @@
+# -*- coding: utf-8 -*-
+"""
+LibreOffice Calc Makro: NV_MASTER-Abgleich (verbessertes semantisches Matching)
+Speicherort: /home/jarnold/.config/libreoffice/4/user/Scripts/python/NV Abgleich Makro/mapper_macro.py
+"""
+
+import os
+import re
+import json
+import traceback
+
+# ------------------------------------------------------------
+# LIBRARIES & MODELS
+# ------------------------------------------------------------
+try:
+    import pandas as pd
+    PANDAS_AVAILABLE = True
+except Exception:
+    PANDAS_AVAILABLE = False
+
+try:
+    import spacy
+    # Verwende das mittlere Modell für semantische Ähnlichkeit
+    nlp = spacy.load("de_core_news_md")
+    SPACY_AVAILABLE = True
+except Exception:
+    SPACY_AVAILABLE = False
+    nlp = None
+
+try:
+    from rapidfuzz import fuzz
+    RAPIDFUZZ_AVAILABLE = True
+except Exception:
+    RAPIDFUZZ_AVAILABLE = False
+    from difflib import SequenceMatcher
+
+# ------------------------------------------------------------
+# KONFIGURATION
+# ------------------------------------------------------------
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+NV_MASTER_PATH = os.path.join(BASE_DIR, "NV_MASTER.ods")
+LOG_FILE = os.path.join(BASE_DIR, "mapper_macro.log")
+CACHE_FILE = os.path.join(BASE_DIR, "mapper_cache.json")
+
+STOPWORDS = {"mit","ohne","der","die","das","ein","eine","und","zu","von","im","in","auf","an","als","bei","für","aus","dem","den","des","eines","einer"}
+CONF_THRESHOLD = 0.70  # etwas großzügiger für semantisches Matching
+
+# ------------------------------------------------------------
+# LOGGING
+# ------------------------------------------------------------
+def log(msg):
+    """Schreibt technische Logs ins Makroverzeichnis."""
+    try:
+        with open(LOG_FILE, "a", encoding="utf-8") as f:
+            f.write(msg.strip() + "\n")
+    except Exception:
+        pass
+
+log("Makro gestartet")
+
+# ------------------------------------------------------------
+# CACHE
+# ------------------------------------------------------------
+try:
+    if os.path.exists(CACHE_FILE):
+        with open(CACHE_FILE, "r", encoding="utf-8") as f:
+            CACHE = json.load(f)
+    else:
+        CACHE = {}
+except Exception:
+    CACHE = {}
+
+# ------------------------------------------------------------
+# TEXTNORMALISIERUNG & LEMMATISIERUNG
+# ------------------------------------------------------------
+def normalize_text(s):
+    if not s:
+        return ""
+    s = str(s).strip().lower()
+    s = re.sub(r"[\(\)\[\]\"'\\;:\?!,\.]", "", s)
+    s = re.sub(r"\s+", " ", s)
+    return s
+
+lemma_cache = {}
+def lemmatize_term(term):
+    t = normalize_text(term)
+    if t in lemma_cache:
+        return lemma_cache[t]
+    if SPACY_AVAILABLE and nlp:
+        try:
+            doc = nlp(t)
+            lemma = " ".join([token.lemma_ for token in doc])
+        except Exception:
+            lemma = t
+    else:
+        lemma = t
+    lemma_cache[t] = lemma
+    return lemma
+
+# ------------------------------------------------------------
+# NV_MASTER LADEN
+# ------------------------------------------------------------
+def build_norm_index(nv_path):
+    norm_dict = {}
+    lemma_index = {}
+
+    if not PANDAS_AVAILABLE:
+        log("Pandas nicht verfügbar – NV_MASTER kann nicht geladen werden.")
+        return norm_dict, lemma_index
+
+    try:
+        sheets = pd.read_excel(nv_path, sheet_name=None, engine="odf")
+    except Exception as e:
+        log(f"Fehler beim Laden von NV_MASTER: {e}")
+        return norm_dict, lemma_index
+
+    for sheet_name, df in sheets.items():
+        if str(sheet_name).strip().lower() == "master":
+            continue
+        df = df.fillna("")
+        cols = [str(c).strip().lower() for c in df.columns]
+        id_col = next((df.columns[i] for i, c in enumerate(cols) if "id" in c), df.columns[0])
+        word_col = next((df.columns[i] for i, c in enumerate(cols) if "wort" in c or "vokabel" in c), df.columns[-1])
+
+        current_parent_id = None
+        for _, row in df.iterrows():
+            id_val = str(row[id_col]).strip()
+            word_val = str(row[word_col]).strip()
+            if id_val:
+                current_parent_id = id_val
+            if not word_val:
+                continue
+            norm_name = normalize_text(word_val)
+            lemma = lemmatize_term(word_val)
+            entry = {"Name": word_val, "ID": current_parent_id or "", "Sheet": sheet_name}
+            norm_dict.setdefault(norm_name, []).append(entry)
+            lemma_index.setdefault(lemma, []).append(entry)
+
+    log(f"NV_MASTER geladen: {sum(len(v) for v in norm_dict.values())} Begriffe.")
+    return norm_dict, lemma_index
+
+# ------------------------------------------------------------
+# SCORING: FUZZY + SEMANTISCH
+# ------------------------------------------------------------
+def fuzzy_score(a, b):
+    if RAPIDFUZZ_AVAILABLE:
+        try:
+            return fuzz.token_set_ratio(a, b) / 100.0
+        except Exception:
+            return 0.0
+    else:
+        return SequenceMatcher(None, a.lower(), b.lower()).ratio()
+
+def semantic_similarity(a, b):
+    if not SPACY_AVAILABLE or not hasattr(nlp.vocab, "vectors"):
+        return 0.0
+    try:
+        doc_a, doc_b = nlp(a), nlp(b)
+        if doc_a.vector_norm and doc_b.vector_norm:
+            return float(doc_a.similarity(doc_b))
+        return 0.0
+    except Exception:
+        return 0.0
+
+def combined_score(a, b):
+    sf = fuzzy_score(a, b)
+    ss = semantic_similarity(a, b)
+    return max(sf, ss)
+
+# ------------------------------------------------------------
+# MATCHING & VORSCHLÄGE
+# ------------------------------------------------------------
+def get_suggestions_for_term(term_lemma, norm_dict, lemma_index, top_n=3, threshold=CONF_THRESHOLD):
+    candidates = []
+    for key_lemma, entries in lemma_index.items():
+        score = combined_score(term_lemma, key_lemma)
+        if key_lemma.startswith(term_lemma):
+            score = min(score + 0.05, 1.0)
+        if score >= threshold:
+            for e in entries:
+                candidates.append((score, e["Name"], e["ID"]))
+    for norm_key, entries in norm_dict.items():
+        score = combined_score(term_lemma, norm_key)
+        if norm_key.startswith(term_lemma):
+            score = min(score + 0.05, 1.0)
+        if score >= threshold:
+            for e in entries:
+                candidates.append((score, e["Name"], e["ID"]))
+    candidates.sort(key=lambda x: x[0], reverse=True)
+    seen, results = set(), []
+    for score, name, id_ in candidates:
+        key = (name.lower(), id_.lower() if id_ else "")
+        if key in seen:
+            continue
+        seen.add(key)
+        results.append({"score": score, "name": name, "id": id_})
+        if len(results) >= top_n:
+            break
+    return [f'{r["name"]} ({r["id"]})' if r["id"] else r["name"] for r in results]
+
+def map_term_with_indexes(term, norm_dict, lemma_index):
+    term_norm = normalize_text(term)
+    term_lemma = lemmatize_term(term)
+
+    if term_lemma in CACHE:
+        return CACHE[term_lemma]["hits"], CACHE[term_lemma]["suggestions"], CACHE[term_lemma]["ids"]
+
+    hits, suggestions, ids = [], [], []
+
+    if term_norm in norm_dict:
+        for e in norm_dict[term_norm]:
+            hits.append(e["Name"])
+            if e["ID"]:
+                ids.append(e["ID"])
+
+    if not hits and term_lemma in lemma_index:
+        for e in lemma_index[term_lemma]:
+            hits.append(e["Name"])
+            if e["ID"]:
+                ids.append(e["ID"])
+
+    suggs = get_suggestions_for_term(term_lemma, norm_dict, lemma_index, top_n=3, threshold=CONF_THRESHOLD)
+    filtered_suggs = []
+    for s in suggs:
+        s_clean = normalize_text(s.split(" (")[0])
+        if s_clean not in [normalize_text(h) for h in hits]:
+            filtered_suggs.append(s)
+    suggestions = filtered_suggs
+
+    def uniq(seq):
+        seen = set()
+        out = []
+        for x in seq:
+            if x not in seen:
+                seen.add(x)
+                out.append(x)
+        return out
+
+    hits, suggestions, ids = uniq(hits), uniq(suggestions), uniq(ids)
+    CACHE[term_lemma] = {"hits": hits, "suggestions": suggestions, "ids": ids}
+
+    log(f"TERM: {term} | HITS: {hits} | SUGGS: {suggestions}")
+    return hits, suggestions, ids
+
+# ------------------------------------------------------------
+# HAUPTMAKRO
+# ------------------------------------------------------------
+def run_mapper_macro():
+    try:
+        doc = XSCRIPTCONTEXT.getDocument()
+        sheet = doc.CurrentController.ActiveSheet
+    except Exception as e:
+        log(f"Fehler beim Zugriff auf Dokument: {e}")
+        return
+
+    norm_dict, lemma_index = build_norm_index(NV_MASTER_PATH)
+    if not norm_dict:
+        log("Fehler: NV_MASTER leer oder nicht gefunden.")
+        return
+
+    try:
+        cursor = sheet.createCursor()
+        cursor.gotoStartOfUsedArea(False)
+        cursor.gotoEndOfUsedArea(True)
+        used = cursor.getRangeAddress()
+    except Exception as e:
+        log(f"Cursor-Fehler: {e}")
+        return
+
+    header_row = 0
+    objekt_col = None
+    for c in range(0, used.EndColumn + 1):
+        val = str(sheet.getCellByPosition(c, header_row).String).strip().lower()
+        if val == "objektbeschreibung":
+            objekt_col = c
+            break
+    if objekt_col is None:
+        log("Keine Spalte 'Objektbeschreibung' gefunden.")
+        return
+
+    existing = {}
+    for c in range(0, used.EndColumn + 1):
+        h = str(sheet.getCellByPosition(c, header_row).String).strip()
+        if h == "Norm_Treffer": existing["Norm_Treffer"] = c
+        if h == "Norm_Vorschlag": existing["Norm_Vorschlag"] = c
+        if h == "Norm_ID": existing["Norm_ID"] = c
+
+    last_col = used.EndColumn
+    for name in ["Norm_Treffer", "Norm_Vorschlag", "Norm_ID"]:
+        if name not in existing:
+            last_col += 1
+            existing[name] = last_col
+            sheet.getCellByPosition(last_col, header_row).String = name
+
+    GREEN, YELLOW, RED = 0xADFF2F, 0xFFD700, 0xCC0000
+    norm_tr_col, norm_sug_col, norm_id_col = existing["Norm_Treffer"], existing["Norm_Vorschlag"], existing["Norm_ID"]
+
+    rows = 0
+    for r in range(header_row + 1, used.EndRow + 1):
+        txt = str(sheet.getCellByPosition(objekt_col, r).String).strip()
+        if not txt:
+            continue
+        terms = [t.strip() for t in re.split(r",|\s+", txt) if t.strip() and t.lower() not in STOPWORDS]
+        row_hits, row_sugs, row_ids, any_unmapped = [], [], [], False
+        for term in terms:
+            hits, sugs, ids = map_term_with_indexes(term, norm_dict, lemma_index)
+            if hits: row_hits.extend(hits)
+            if sugs: row_sugs.extend(sugs)
+            if ids: row_ids.extend(ids)
+            if not hits and not sugs: any_unmapped = True
+
+        def uniq(seq):
+            seen = set()
+            out = []
+            for x in seq:
+                if x not in seen:
+                    seen.add(x)
+                    out.append(x)
+            return out
+
+        row_hits, row_sugs, row_ids = uniq(row_hits), uniq(row_sugs), uniq(row_ids)
+        sheet.getCellByPosition(norm_tr_col, r).String = " | ".join(row_hits)
+        sheet.getCellByPosition(norm_sug_col, r).String = " | ".join(row_sugs)
+        sheet.getCellByPosition(norm_id_col, r).String = " | ".join(row_ids)
+
+        obj_cell = sheet.getCellByPosition(objekt_col, r)
+        sug_cell = sheet.getCellByPosition(norm_sug_col, r)
+        tr_cell = sheet.getCellByPosition(norm_tr_col, r)
+
+        if any_unmapped:
+            obj_cell.CellBackColor = RED
+        elif row_hits:
+            tr_cell.CellBackColor = GREEN
+        if row_sugs:
+            sug_cell.CellBackColor = YELLOW
+
+        rows += 1
+
+    with open(CACHE_FILE, "w", encoding="utf-8") as f:
+        json.dump(CACHE, f, ensure_ascii=False, indent=2)
+    log(f"Makro abgeschlossen, {rows} Zeilen verarbeitet.")
+
+g_exportedScripts = (run_mapper_macro,)

Mapper_Makro_Alte_Versionen/mapper_macro_2.1.py

@@ -1,7 +1,6 @@
 # -*- coding: utf-8 -*-
 # LibreOffice Calc macro: NV_MASTER-Abgleich, Pandas+odf, Cache, Farben
-# Pfade: BASE_DIR muss auf das Verzeichnis zeigen, in dem NV_MASTER.ods + Makro liegen.
+# Speicherort: /home/jarnold/.config/libreoffice/4/user/Scripts/python/Vokabular_Abgleich_Makro/mapper_macro_2.1.py
-# Speichern: /home/jarnold/.config/libreoffice/4/user/Scripts/python/NV Abgleich Makro/mapper_macro.py
 
 import os
 import re
@@ -9,7 +8,6 @@ import json
 import traceback
 
 # UNO-Context wird zur Laufzeit zur Verfügung gestellt (XSCRIPTCONTEXT)
-# Third-party libs: pandas, odfpy, optional: spacy, rapidfuzz
 try:
     import pandas as pd
     PANDAS_AVAILABLE = True
@@ -34,10 +32,10 @@ except Exception:
 # ------------------------
 # Konfiguration
 # ------------------------
-BASE_DIR = "/home/jarnold/.config/libreoffice/4/user/Scripts/python/NV Abgleich Makro"
+BASE_DIR = "/home/jarnold/.config/libreoffice/4/user/Scripts/python/Vokabular_Abgleich_Makro"
 NV_MASTER_PATH = os.path.join(BASE_DIR, "NV_MASTER.ods")
-LOG_FILE = os.path.join(BASE_DIR, "mapper_macro.log")
+LOG_FILE = os.path.join(BASE_DIR, "mapper_macro_2.1.log")
-CACHE_FILE = os.path.join(BASE_DIR, "mapper_cache.json")
+CACHE_FILE = os.path.join(BASE_DIR, "mapper_cache_2.1.json")
 
 STOPWORDS = {"mit","ohne","der","die","das","ein","eine","und","zu","von","im","in","auf","an","als","bei","für","aus","dem","den","des","eines","einer"}
 CONF_THRESHOLD = 0.75  # Basis-Schwelle für Vorschläge
@@ -110,10 +108,8 @@ def build_norm_index(nv_path):
     for sheet_name, df in sheets.items():
         if str(sheet_name).strip().lower() == "master":
             continue
-        # normalize columns names to find ID and Wort columns
+        df = df.fillna("")
-        df = df.fillna("")  # leere Zellen als ""
         cols = [str(c).strip().lower() for c in df.columns]
-        # try to find columns
         id_col = None
         word_col = None
         for i, c in enumerate(cols):
@@ -121,7 +117,6 @@ def build_norm_index(nv_path):
                 id_col = df.columns[i]
             if "wort" in c or "vokabel" in c:
                 word_col = df.columns[i]
-        # fallback: if not found, try first/last
         if word_col is None and len(df.columns) >= 1:
             word_col = df.columns[-1]
         if id_col is None and len(df.columns) >= 1:
@@ -131,18 +126,14 @@ def build_norm_index(nv_path):
         for _, row in df.iterrows():
             id_val = str(row[id_col]).strip() if id_col in df.columns else ""
             word_val = str(row[word_col]).strip() if word_col in df.columns else ""
-            # if row defines an ID, set as current parent
             if id_val:
                 current_parent_id = id_val
-            # skip empty word cells
             if not word_val:
                 continue
             norm_name = normalize_text(word_val)
             lemma = lemmatize_term(word_val)
             entry = {"Name": word_val.strip(), "ID": current_parent_id or "", "Sheet": sheet_name}
-            # add to norm_dict by normalized name (exact matching)
             norm_dict.setdefault(norm_name, []).append(entry)
-            # add to lemma_index
             lemma_index.setdefault(lemma, []).append(entry)
 
     log(f"NV_MASTER geladen ({NV_MASTER_PATH}). Begriffe: {sum(len(v) for v in norm_dict.values())}")
@@ -163,10 +154,8 @@ def fuzzy_score(a, b):
         except Exception:
             return 0.0
 
-def get_suggestions_for_term(term_lemma, norm_dict, lemma_index, top_n=None, threshold=CONF_THRESHOLD):
+def get_suggestions_for_term(term_lemma, norm_dict, lemma_index, threshold=CONF_THRESHOLD):
-    # collect candidates from lemma_index keys and norm_dict keys
     candidates = []
-    # iterate over lemma_index keys for candidate names
     for key_lemma, entries in lemma_index.items():
         score = fuzzy_score(term_lemma, key_lemma)
         if key_lemma.startswith(term_lemma):
@@ -174,7 +163,6 @@ def get_suggestions_for_term(term_lemma, norm_dict, lemma_index, top_n=None, thr
         if score >= threshold:
             for e in entries:
                 candidates.append((score, e["Name"], e["ID"]))
-    # also check norm_dict keys (exact-normalized names) as additional candidates
     for norm_key, entries in norm_dict.items():
         score = fuzzy_score(term_lemma, norm_key)
         if norm_key.startswith(term_lemma):
@@ -182,9 +170,7 @@ def get_suggestions_for_term(term_lemma, norm_dict, lemma_index, top_n=None, thr
         if score >= threshold:
             for e in entries:
                 candidates.append((score, e["Name"], e["ID"]))
-    # sort by score descending
     candidates.sort(key=lambda t: t[0], reverse=True)
-    # unique by (Name, ID) preserve score order
     seen = set()
     results = []
     for score, name, id_ in candidates:
@@ -193,40 +179,28 @@ def get_suggestions_for_term(term_lemma, norm_dict, lemma_index, top_n=None, thr
             continue
         seen.add(key)
         results.append({"score": score, "name": name, "id": id_})
-    # return all candidates (no limit) as "Name (ID)"
     return [f'{r["name"]} ({r["id"]})' if r["id"] else r["name"] for r in results]
 
 def map_term_with_indexes(term, norm_dict, lemma_index):
     term_norm = normalize_text(term)
     term_lemma = lemmatize_term(term)
-    # cache lookup
     if term_lemma in CACHE:
-        return CACHE[term_lemma]["hits"], CACHE[term_lemma]["suggestions"], CACHE[term_lemma]["ids"]
+        return CACHE[term_lemma]["hits"], CACHE[term_lemma]["suggestions"]
 
     hits = []
     suggestions = []
-    ids = []
 
-    # 1) exact normalized name match
     if term_norm in norm_dict:
         for e in norm_dict[term_norm]:
-            hits.append(e["Name"])
+            hits.append(f'{e["Name"]} ({e["ID"]})' if e["ID"] else e["Name"])
-            if e["ID"]:
-                ids.append(e["ID"])
 
-    # 2) lemma match (if not already hits)
     if not hits and term_lemma in lemma_index:
         for e in lemma_index[term_lemma]:
-            hits.append(e["Name"])
+            hits.append(f'{e["Name"]} ({e["ID"]})' if e["ID"] else e["Name"])
-            if e["ID"]:
-                ids.append(e["ID"])
 
-    # 3) suggestions via fuzzy (always compute even if hits exist, but suggestions empty if exact)
+    if not hits:
-    suggs = get_suggestions_for_term(term_lemma, norm_dict, lemma_index, top_n=None, threshold=CONF_THRESHOLD)
+        suggestions = get_suggestions_for_term(term_lemma, norm_dict, lemma_index)
-    # If there are exact hits, we still may present suggestions (user wanted unlimited), but suggestions are secondary
-    suggestions = suggs
 
-    # deduplicate lists preserving order
     def unique_preserve(seq):
         seen = set()
         out = []
@@ -238,18 +212,15 @@ def map_term_with_indexes(term, norm_dict, lemma_index):
 
     hits = unique_preserve(hits)
     suggestions = unique_preserve(suggestions)
-    ids = unique_preserve(ids)
 
-    # cache result
+    CACHE[term_lemma] = {"hits": hits, "suggestions": suggestions}
-    CACHE[term_lemma] = {"hits": hits, "suggestions": suggestions, "ids": ids}
+    return hits, suggestions
-    return hits, suggestions, ids
 
 # ------------------------
 # Haupt-Makro
 # ------------------------
 def run_mapper_macro():
     try:
-        # UNO doc/sheet
         doc = XSCRIPTCONTEXT.getDocument()
         sheet = doc.CurrentController.ActiveSheet
         cursor = sheet.createCursor()
@@ -260,7 +231,6 @@ def run_mapper_macro():
         log("Fehler: konnte Dokument/Sheet nicht öffnen: " + str(e))
         return
 
-    # find header row and Objektbeschreibung column (search first 5 rows)
     header_row = None
     objekt_col = None
     max_col = data_range.EndColumn
@@ -281,7 +251,7 @@ def run_mapper_macro():
         log("Spalte 'Objektbeschreibung' nicht gefunden. Abbruch.")
         return
 
-    # determine or create result columns: search if exist anywhere; otherwise append at right end
+    # Prüfen/Anlegen der Ergebnis-Spalten
     existing = {}
     for c in range(0, data_range.EndColumn+1):
         try:
@@ -292,59 +262,38 @@ def run_mapper_macro():
             existing["Norm_Treffer"] = c
         if h == "Norm_Vorschlag":
             existing["Norm_Vorschlag"] = c
-        if h == "Norm_ID":
-            existing["Norm_ID"] = c
 
-    # append columns at right end if missing
     last_col = data_range.EndColumn
     if "Norm_Treffer" not in existing:
         last_col += 1
         existing["Norm_Treffer"] = last_col
-        try:
         sheet.getCellByPosition(last_col, header_row).String = "Norm_Treffer"
-        except Exception:
-            pass
     if "Norm_Vorschlag" not in existing:
         last_col += 1
         existing["Norm_Vorschlag"] = last_col
-        try:
         sheet.getCellByPosition(last_col, header_row).String = "Norm_Vorschlag"
-        except Exception:
-            pass
-    if "Norm_ID" not in existing:
-        last_col += 1
-        existing["Norm_ID"] = last_col
-        try:
-            sheet.getCellByPosition(last_col, header_row).String = "Norm_ID"
-        except Exception:
-            pass
 
     norm_tr_col = existing["Norm_Treffer"]
     norm_sug_col = existing["Norm_Vorschlag"]
-    norm_id_col = existing["Norm_ID"]
 
-    # Build norm indexes
     norm_dict, lemma_index = build_norm_index(NV_MASTER_PATH)
     if not norm_dict and not lemma_index:
         log("NV_MASTER leer oder nicht lesbar. Abbruch.")
         return
 
-    # colors
     GREEN = 0xADFF2F
     YELLOW = 0xFFA500
     RED = 0xCC0000
+    WHITE = 0xFFFFFF
 
-    # iterate rows
     rows_processed = 0
     for r in range(header_row + 1, data_range.EndRow + 1):
         try:
             cell = sheet.getCellByPosition(objekt_col, r)
             txt = str(cell.String).strip()
             if not txt:
-                # clear any previous outputs? keep existing per spec; skip empty
                 continue
 
-            # tokenize: split by commas first, then whitespace; filter stopwords and pure numbers
             clauses = [c.strip() for c in re.split(r",", txt) if c.strip()]
             terms = []
             for cl in clauses:
@@ -356,24 +305,19 @@ def run_mapper_macro():
                         continue
                     terms.append(p)
 
-            # for each term, get hits/suggestions/ids
             row_hits = []
             row_sugs = []
-            row_ids = []
+            unmapped_terms = []
-            any_unmapped = False  # at least one term without hit and without suggestion
+
-            # We will record for each term
             for term in terms:
-                hits, sugs, ids = map_term_with_indexes(term, norm_dict, lemma_index)
+                hits, sugs = map_term_with_indexes(term, norm_dict, lemma_index)
                 if hits:
                     row_hits.extend(hits)
+                else:
+                    unmapped_terms.append(term)
                     if sugs:
                         row_sugs.extend(sugs)
-                if ids:
-                    row_ids.extend(ids)
-                if (not hits) and (not sugs):
-                    any_unmapped = True
 
-            # deduplicate preserving order
             def uniq(seq):
                 seen = set()
                 out = []
@@ -385,57 +329,30 @@ def run_mapper_macro():
 
             row_hits = uniq(row_hits)
             row_sugs = uniq(row_sugs)
-            row_ids = uniq(row_ids)
 
-            # write outputs (unlimited lists, joined with " | ")
+            # Farb-Logik für Objektbeschreibung
-            try:
+            if terms and not unmapped_terms and row_hits:
-                sheet.getCellByPosition(norm_tr_col, r).String = " | ".join(row_hits)
+                cell.CellBackColor = GREEN
-                sheet.getCellByPosition(norm_sug_col, r).String = " | ".join(row_sugs)
+                row_sugs = []
-                sheet.getCellByPosition(norm_id_col, r).String = " | ".join(row_ids)
+            elif row_hits:
-            except Exception:
+                cell.CellBackColor = YELLOW
-                pass
+            else:
-
-            # Coloring rules per new spec:
-            # - Objektbeschreibung cell: RED if any_unmapped else no change (we do not color green/yellow here)
-            # - Norm_Treffer cell: GREEN if all terms matched (i.e., terms non-empty and no term unmapped and at least one hit per term)
-            # - Norm_Vorschlag cell: YELLOW if at least one suggestion exists
-            # Determine "all matched": terms non-empty and every term has at least one hit (we approximated by checking any_unmapped and hits length)
-            all_matched = False
-            if terms:
-                # all_matched if no term without hit and there is at least one hit overall
-                if (not any_unmapped) and row_hits:
-                    all_matched = True
-
-            # apply colors
-            try:
-                if any_unmapped:
                 cell.CellBackColor = RED
-                else:
+
-                    # clear red if previously set? We'll leave unchanged if not set. Optionally set to default 16777215 (white)
+            # Ergebniszellen
-                    pass
-                # Norm_Treffer coloring
             tr_cell = sheet.getCellByPosition(norm_tr_col, r)
-                if all_matched:
+            tr_cell.String = " | ".join(row_hits)
-                    tr_cell.CellBackColor = GREEN
+            tr_cell.CellBackColor = GREEN if row_hits else WHITE
-                else:
+
-                    # clear color if needed -> set to white
-                    tr_cell.CellBackColor = 0xFFFFFF
-                # Norm_Vorschlag coloring
             sug_cell = sheet.getCellByPosition(norm_sug_col, r)
-                if row_sugs:
+            sug_cell.String = " | ".join(row_sugs)
-                    sug_cell.CellBackColor = YELLOW
+            sug_cell.CellBackColor = YELLOW if row_sugs else WHITE
-                else:
-                    sug_cell.CellBackColor = 0xFFFFFF
-            except Exception:
-                pass
 
             rows_processed += 1
 
         except Exception as e:
-            # continue processing other rows; log once
+            log(f"Fehler in Zeile {r}: {e}\n{traceback.format_exc()}")
-            log(f"Fehler in Zeile {r}: {e}")
 
-    # persist cache
     try:
         with open(CACHE_FILE, "w", encoding="utf-8") as f:
             json.dump(CACHE, f, ensure_ascii=False, indent=2)
@@ -444,5 +361,5 @@ def run_mapper_macro():
 
     log(f"run_mapper_macro fertig. Zeilen verarbeitet: {rows_processed}")
 
-# Export for LO
+# Export für LibreOffice
 g_exportedScripts = (run_mapper_macro,)

Mapper_Makro_Alte_Versionen/mapper_macro_2.2.py

@@ -0,0 +1,455 @@
+# -*- coding: utf-8 -*-
+"""
+LibreOffice/Excel Macro: NV_MASTER-Abgleich
+Version: 2.3
+Pfad: libreoffice/4/user/Scripts/python/Vokabular_Abgleich_Makro/mapper_macro_2.3.py
+
+Beschreibung:
+-------------
+Dieses Python-Makro für LibreOffice/Excel führt einen Abgleich von Begriffen
+aus einem aktiven Sheet gegen ein zentral gepflegtes NV_MASTER-Vokabular durch.
+Es erstellt Treffer, Vorschläge und markiert die Zellen farblich. 
+
+Hauptfunktionen:
+----------------
+1. Text-Normalisierung und Lemma-Bestimmung
+2. Laden des NV_MASTER-Vokabulars und Aufbau von Norm-Index + Lemma-Index
+3. Fuzzy Matching (RapidFuzz oder difflib) für Begriffe
+4. Treffer- und Vorschlagsbestimmung
+5. Mapping auf Sheet:
+   - Norm_Treffer (grün)
+   - Norm_Vorschlag (gelb)
+   - Kein_Treffer (rot)
+6. Caching zur Vermeidung mehrfacher Berechnungen
+7. Logging in externe Datei
+
+Externe Abhängigkeiten:
+-----------------------
+- pandas (für ODS/Excel-Leseoperationen)
+- spacy (für deutsche Lemma-Bestimmung)
+- rapidfuzz (optional für schnellere Fuzzy-String-Matches)
+
+UNO-spezifische Objekte:
+------------------------
+- XSCRIPTCONTEXT: Bereitgestellt durch LibreOffice zur Laufzeit
+
+Schwachstellen / Optimierungsansätze:
+-------------------------------------
+- Fehlerbehandlung ist robust, aber teilweise sehr still (z.B. Cache-Fehler, Pandas-Fehler).
+- Schleifen über Zellen sind bei großen Sheets langsam (potenziell durch pandas vollständig ersetzen).
+- Lemma-Berechnung könnte nur einmal für NV_MASTER und einmal für Sheet durchgeführt werden.
+- RapidFuzz optional; fallback auf SequenceMatcher ist deutlich langsamer.
+- Cache wird nur am Ende geschrieben; Absturz vor Ende verliert bisherige Ergebnisse.
+- Farbwerte sind fest codiert; parametrisieren könnte Flexibilität erhöhen.
+- Stopwords sind hart codiert; konfigurierbar wäre effizienter.
+- Es werden keine parallelen Abfragen / Batch-Operationen verwendet.
+- Logging nur in Datei; LibreOffice-eigene Meldungen oder Fortschrittsanzeige fehlen.
+"""
+
+import os
+import re
+import json
+import traceback
+
+# UNO-Context wird zur Laufzeit von LibreOffice bereitgestellt
+try:
+    import pandas as pd
+    PANDAS_AVAILABLE = True
+except Exception:
+    PANDAS_AVAILABLE = False
+
+try:
+    import spacy
+    nlp = spacy.load("de_core_news_sm")
+    SPACY_AVAILABLE = True
+except Exception:
+    SPACY_AVAILABLE = False
+    nlp = None
+
+try:
+    from rapidfuzz import fuzz
+    RAPIDFUZZ_AVAILABLE = True
+except Exception:
+    RAPIDFUZZ_AVAILABLE = False
+    from difflib import SequenceMatcher
+
+# ------------------------
+# Konfiguration
+# ------------------------
+BASE_DIR = "/home/jarnold/.config/libreoffice/4/user/Scripts/python/Vokabular_Abgleich_Makro"
+NV_MASTER_PATH = os.path.join(BASE_DIR, "NV_MASTER.ods")
+LOG_FILE = os.path.join(BASE_DIR, "mapper_macro_2.3.log")
+CACHE_FILE = os.path.join(BASE_DIR, "mapper_cache_2.3.json")
+
+STOPWORDS = {"mit","ohne","der","die","das","ein","eine","und","zu","von","im","in","auf","an","als","bei","für","aus","dem","den","des","eines","einer"}
+CONF_THRESHOLD = 0.75  # Basis-Schwelle für Vorschläge
+
+# ------------------------
+# Logging-Funktion
+# ------------------------
+def log(msg):
+    """Schreibt Nachricht in LOG_FILE. Fehler werden ignoriert."""
+    try:
+        with open(LOG_FILE, "a", encoding="utf-8") as f:
+            f.write(msg + "\n")
+    except Exception:
+        pass
+
+# ------------------------
+# Cache laden
+# ------------------------
+try:
+    if os.path.exists(CACHE_FILE):
+        with open(CACHE_FILE, "r", encoding="utf-8") as f:
+            CACHE = json.load(f)
+    else:
+        CACHE = {}
+except Exception:
+    CACHE = {}
+
+# ------------------------
+# Text-Normalisierung & Lemma
+# ------------------------
+def normalize_text(s):
+    """Entfernt Sonderzeichen, multiple Whitespaces, wandelt in lowercase."""
+    if not s:
+        return ""
+    s = str(s).strip().lower()
+    s = re.sub(r"[\(\)\[\]\"'\\;:\?!,\.]", "", s)
+    s = re.sub(r"\s+", " ", s)
+    return s
+
+lemma_cache = {}
+def lemmatize_term(term):
+    """Lemmatisiert einen Begriff mit SpaCy. Falls nicht verfügbar, Rückgabe Normalized String."""
+    term_norm = normalize_text(term)
+    if term_norm in lemma_cache:
+        return lemma_cache[term_norm]
+    if SPACY_AVAILABLE and nlp:
+        try:
+            doc = nlp(term_norm)
+            lemma = " ".join([token.lemma_ for token in doc])
+        except Exception:
+            lemma = term_norm
+    else:
+        lemma = term_norm
+    lemma_cache[term_norm] = lemma
+    return lemma
+
+# ------------------------
+# NV_MASTER laden
+# ------------------------
+def build_norm_index(nv_path):
+    """
+    Liest NV_MASTER ein und erstellt:
+    - norm_dict: Normalisierte Begriffe -> Einträge mit Name, ID, Sheet
+    - lemma_index: Lemma -> Einträge
+    """
+    norm_dict = {}
+    lemma_index = {}
+    if not PANDAS_AVAILABLE:
+        log("Pandas nicht verfügbar. NV_MASTER kann nicht gelesen werden.")
+        return norm_dict, lemma_index
+    try:
+        sheets = pd.read_excel(nv_path, sheet_name=None, engine="odf")
+    except Exception as e:
+        log(f"Fehler beim Einlesen NV_MASTER: {e}")
+        return norm_dict, lemma_index
+
+    for sheet_name, df in sheets.items():
+        if str(sheet_name).strip().lower() == "master":
+            continue
+        df = df.fillna("")
+        cols = [str(c).strip().lower() for c in df.columns]
+        id_col = None
+        word_col = None
+        for i, c in enumerate(cols):
+            if "id" in c:
+                id_col = df.columns[i]
+            if "wort" in c or "vokabel" in c:
+                word_col = df.columns[i]
+        if word_col is None and len(df.columns) >= 1:
+            word_col = df.columns[-1]
+        if id_col is None and len(df.columns) >= 1:
+            id_col = df.columns[0]
+
+        current_parent_id = None
+        for _, row in df.iterrows():
+            id_val = str(row[id_col]).strip() if id_col in df.columns else ""
+            word_val = str(row[word_col]).strip() if word_col in df.columns else ""
+            if id_val:
+                current_parent_id = id_val
+            if not word_val:
+                continue
+            norm_name = normalize_text(word_val)
+            lemma = lemmatize_term(word_val)
+            entry = {"Name": word_val.strip(), "ID": current_parent_id or "", "Sheet": sheet_name}
+            norm_dict.setdefault(norm_name, []).append(entry)
+            lemma_index.setdefault(lemma, []).append(entry)
+    log(f"NV_MASTER geladen ({NV_MASTER_PATH}). Begriffe: {sum(len(v) for v in norm_dict.values())}")
+    return norm_dict, lemma_index
+
+# ------------------------
+# Matching-Funktionen
+# ------------------------
+def fuzzy_score(a, b):
+    """Berechnet Fuzzy-Score zwischen zwei Strings. RapidFuzz oder fallback SequenceMatcher."""
+    if RAPIDFUZZ_AVAILABLE:
+        try:
+            return fuzz.token_set_ratio(a, b) / 100.0
+        except Exception:
+            return 0.0
+    else:
+        try:
+            return SequenceMatcher(None, a.lower(), b.lower()).ratio()
+        except Exception:
+            return 0.0
+
+def get_suggestions_for_term(term_lemma, norm_dict, lemma_index, threshold=CONF_THRESHOLD):
+    """
+    Liefert Vorschläge für ein Lemma, wenn kein exakter Treffer existiert.
+    Score-basierte Sortierung, Duplikate werden entfernt.
+    """
+    candidates = []
+    for key_lemma, entries in lemma_index.items():
+        score = fuzzy_score(term_lemma, key_lemma)
+        if key_lemma.startswith(term_lemma):
+            score = min(score + 0.1, 1.0)
+        if score >= threshold:
+            for e in entries:
+                candidates.append((score, e["Name"], e["ID"]))
+    for norm_key, entries in norm_dict.items():
+        score = fuzzy_score(term_lemma, norm_key)
+        if norm_key.startswith(term_lemma):
+            score = min(score + 0.1, 1.0)
+        if score >= threshold:
+            for e in entries:
+                candidates.append((score, e["Name"], e["ID"]))
+    candidates.sort(key=lambda t: t[0], reverse=True)
+    seen = set()
+    results = []
+    for score, name, id_ in candidates:
+        key = (name, id_)
+        if key in seen:
+            continue
+        seen.add(key)
+        results.append({"score": score, "name": name, "id": id_})
+    return [f'{r["name"]} ({r["id"]})' if r["id"] else r["name"] for r in results]
+
+def map_term_with_indexes(term, norm_dict, lemma_index):
+    """
+    Mappt einen Term auf NV_MASTER:
+    - Treffer
+    - Vorschläge
+    - IDs
+    Nutzt Cache, um Wiederholungen zu vermeiden.
+    """
+    term_norm = normalize_text(term)
+    term_lemma = lemmatize_term(term)
+    if term_lemma in CACHE:
+        cached = CACHE[term_lemma]
+        return cached.get("hits", []), cached.get("suggestions", []), cached.get("ids", [])
+    hits = []
+    suggestions = []
+    ids = []
+    if term_norm in norm_dict:
+        for e in norm_dict[term_norm]:
+            hits.append(e["Name"])
+            if e["ID"]:
+                ids.append(e["ID"])
+    if not hits and term_lemma in lemma_index:
+        for e in lemma_index[term_lemma]:
+            hits.append(e["Name"])
+            if e["ID"]:
+                ids.append(e["ID"])
+    if not hits:
+        suggestions = get_suggestions_for_term(term_lemma, norm_dict, lemma_index, threshold=CONF_THRESHOLD)
+
+    # Duplikate entfernen
+    def unique_preserve(seq):
+        seen = set()
+        out = []
+        for x in seq:
+            if x not in seen:
+                seen.add(x)
+                out.append(x)
+        return out
+
+    hits = unique_preserve(hits)
+    suggestions = unique_preserve(suggestions)
+    ids = unique_preserve(ids)
+    CACHE[term_lemma] = {"hits": hits, "suggestions": suggestions, "ids": ids}
+    return hits, suggestions, ids
+
+# ------------------------
+# Haupt-Makro
+# ------------------------
+def run_mapper_macro():
+    """
+    Haupt-Makro für LibreOffice:
+    1. Bestimmt Header + Spalten
+    2. Fügt Spalten für Norm_Treffer, Norm_Vorschlag, Kein_Treffer hinzu
+    3. Liest NV_MASTER und baut Indizes
+    4. Iteriert über Zeilen und Terms
+    5. Markiert Zellen farblich (grün/gelb/rot)
+    6. Schreibt Cache am Ende
+    """
+    try:
+        doc = XSCRIPTCONTEXT.getDocument()
+        sheet = doc.CurrentController.ActiveSheet
+        cursor = sheet.createCursor()
+        cursor.gotoStartOfUsedArea(False)
+        cursor.gotoEndOfUsedArea(True)
+        data_range = cursor.getRangeAddress()
+    except Exception as e:
+        log("Fehler: konnte Dokument/Sheet nicht öffnen: " + str(e))
+        return
+
+    # Header finden
+    header_row = None
+    objekt_col = None
+    max_col = data_range.EndColumn
+    for r in range(0, min(5, data_range.EndRow+1)):
+        for c in range(0, max_col+1):
+            try:
+                val = str(sheet.getCellByPosition(c, r).String).strip().lower()
+            except Exception:
+                val = ""
+            if val == "objektbeschreibung":
+                header_row = r
+                objekt_col = c
+                break
+        if objekt_col is not None:
+            break
+    if objekt_col is None:
+        log("Spalte 'Objektbeschreibung' nicht gefunden. Abbruch.")
+        return
+
+    # Spalten anlegen, falls nicht vorhanden
+    existing = {}
+    for c in range(0, data_range.EndColumn+1):
+        try:
+            h = str(sheet.getCellByPosition(c, header_row).String).strip()
+        except Exception:
+            h = ""
+        if h == "Norm_Treffer":
+            existing["Norm_Treffer"] = c
+        if h == "Norm_Vorschlag":
+            existing["Norm_Vorschlag"] = c
+    last_col = data_range.EndColumn
+    if "Norm_Treffer" not in existing:
+        last_col += 1
+        existing["Norm_Treffer"] = last_col
+        sheet.getCellByPosition(last_col, header_row).String = "Norm_Treffer"
+    if "Norm_Vorschlag" not in existing:
+        last_col += 1
+        existing["Norm_Vorschlag"] = last_col
+        sheet.getCellByPosition(last_col, header_row).String = "Norm_Vorschlag"
+    if "Kein_Treffer" not in existing:
+        last_col += 1
+        existing["Kein_Treffer"] = last_col
+        sheet.getCellByPosition(last_col, header_row).String = "Kein_Treffer"
+
+    norm_tr_col = existing["Norm_Treffer"]
+    norm_sug_col = existing["Norm_Vorschlag"]
+    kein_tr_col = existing["Kein_Treffer"]
+
+    # NV_MASTER laden
+    norm_dict, lemma_index = build_norm_index(NV_MASTER_PATH)
+    if not norm_dict and not lemma_index:
+        log("NV_MASTER leer oder nicht lesbar. Abbruch.")
+        return
+
+    # Farben
+    GREEN = 0xADFF2F
+    YELLOW = 0xFFA500
+    RED = 0xCC0000
+    WHITE = 0xFFFFFF
+
+    rows_processed = 0
+    for r in range(header_row + 1, data_range.EndRow + 1):
+        try:
+            cell = sheet.getCellByPosition(objekt_col, r)
+            txt = str(cell.String).strip()
+            if not txt:
+                continue
+
+            # Term-Extraktion
+            clauses = [c.strip() for c in re.split(r",", txt) if c.strip()]
+            terms = []
+            for cl in clauses:
+                parts = [p.strip() for p in re.split(r"\s+", cl) if p.strip()]
+                for p in parts:
+                    if p.lower() in STOPWORDS:
+                        continue
+                    if re.fullmatch(r"\d+", p):
+                        continue
+                    terms.append(p)
+
+            row_hits = []
+            row_sugs = []
+            row_ids = []
+            unmapped_terms = []
+
+            for term in terms:
+                hits, sugs, ids = map_term_with_indexes(term, norm_dict, lemma_index)
+                if hits:
+                    row_hits.extend([f"{h} ({id_})" if id_ else h for h,id_ in zip(hits, ids + [""]*len(hits))])
+                else:
+                    unmapped_terms.append(term)
+                    if sugs:
+                        row_sugs.extend([f"{s}" for s in sugs])
+                if ids:
+                    row_ids.extend(ids)
+
+            def uniq(seq):
+                seen = set()
+                out = []
+                for x in seq:
+                    if x not in seen:
+                        seen.add(x)
+                        out.append(x)
+                return out
+
+            row_hits = uniq(row_hits)
+            row_sugs = uniq(row_sugs)
+            unmapped_terms = uniq(unmapped_terms)
+
+            # Farb-Logik
+            if terms and not unmapped_terms and row_hits:
+                cell.CellBackColor = GREEN
+                row_sugs = []  # keine Vorschläge wenn alles Treffer
+            elif row_hits:
+                cell.CellBackColor = YELLOW
+            else:
+                cell.CellBackColor = RED
+
+            # Ergebnisse schreiben
+            tr_cell = sheet.getCellByPosition(norm_tr_col, r)
+            tr_cell.String = " | ".join(row_hits)
+            tr_cell.CellBackColor = GREEN if row_hits else WHITE
+
+            sug_cell = sheet.getCellByPosition(norm_sug_col, r)
+            sug_cell.String = " | ".join(row_sugs)
+            sug_cell.CellBackColor = YELLOW if row_sugs else WHITE
+
+            kt_cell = sheet.getCellByPosition(kein_tr_col, r)
+            kt_cell.String = " | ".join(unmapped_terms)
+            kt_cell.CellBackColor = RED if unmapped_terms else WHITE
+
+            rows_processed += 1
+
+        except Exception as e:
+            log(f"Fehler in Zeile {r}: {e}\n{traceback.format_exc()}")
+
+    # Cache speichern
+    try:
+        with open(CACHE_FILE, "w", encoding="utf-8") as f:
+            json.dump(CACHE, f, ensure_ascii=False, indent=2)
+    except Exception:
+        pass
+
+    log(f"run_mapper_macro fertig. Zeilen verarbeitet: {rows_processed}")
+
+# Export für LibreOffice
+g_exportedScripts = (run_mapper_macro,)

NV_Master_EditorFAIL.py

@@ -1,171 +0,0 @@
-import os
-import re
-import logging
-import datetime
-import pandas as pd
-from openpyxl.utils import get_column_letter
-from openpyxl.styles import Alignment
-import ezodf
-
-# ----------------- KONFIGURATION -----------------
-INPUT_FILE = r"/home/jarnold/projects/GND-Skript Test/Input CSV/Normvokabular_INTERN/NV_MASTER.ods"
-MASTER_SHEET_NAME = "Masterstruktur"
-today = datetime.datetime.today().strftime("%y.%m.%d")
-base, ext = os.path.splitext(INPUT_FILE)
-OUTPUT_FILE = f"{base}_Updated_{today}{ext}"
-
-logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
-
-# ----------------- HILFSFUNKTIONEN -----------------
-
-def load_file(input_file):
-    """
-    Prüft Dateiformat und gibt für Excel: pd.ExcelFile + Engine zurück,
-    für ODS: None + "odf" (da ODS direkt über ezodf gelesen wird).
-    """
-    ext = os.path.splitext(input_file)[1].lower()
-    if ext in [".xlsx", ".xls"]:
-        engine = "openpyxl"
-        xls = pd.ExcelFile(input_file, engine=engine)
-    elif ext == ".ods":
-        engine = "odf"
-        xls = None  # ODS wird direkt über ezodf gelesen
-    else:
-        raise ValueError(f"Nicht unterstütztes Dateiformat: {ext}")
-    logging.info(f"Lade Datei {input_file} mit Engine '{engine}'")
-    return xls, engine
-
-def read_ods_sheet(filename, sheet_name):
-    """Liests ODS Sheet sauber ein, inklusive Header."""
-    doc = ezodf.opendoc(filename)
-    sheet = doc.sheets[sheet_name]
-    data = []
-    headers = [str(sheet[0, col].value).strip() for col in range(sheet.ncols())]
-    for row_idx in range(1, sheet.nrows()):
-        row = {}
-        empty_row = True
-        for col_idx, col_name in enumerate(headers):
-            cell_val = sheet[row_idx, col_idx].value
-            val = "" if cell_val is None else str(cell_val).strip()
-            row[col_name] = val
-            if val:
-                empty_row = False
-        if not empty_row:
-            data.append(row)
-    df = pd.DataFrame(data, columns=headers)
-    return df
-
-def process_category_sheet(df):
-    """Erstellt die treppenartige Hierarchie."""
-    df = df.copy()
-    for col in ["ID","Unterkategorie","Unterunterkategorie","Wort/Vokabel"]:
-        if col not in df.columns:
-            df[col] = ""
-    rows = []
-    current_id = ""
-    current_uuk = ""
-    for _, r in df.iterrows():
-        id_val = str(r.get("ID","")).strip()
-        uuk_val = str(r.get("Unterunterkategorie","")).strip()
-        word_val = str(r.get("Wort/Vokabel","")).strip()
-
-        if id_val:  # Kategoriezeile
-            current_id = id_val
-            current_uuk = uuk_val or word_val
-            rows.append({"ID": current_id, "Unterkategorie": "", "Unterunterkategorie": current_uuk, "Wort/Vokabel": ""})
-            continue
-        if uuk_val:  # Unterunterkategorie
-            current_uuk = uuk_val
-            rows.append({"ID": "", "Unterkategorie": "", "Unterunterkategorie": current_uuk, "Wort/Vokabel": ""})
-            continue
-        if word_val:  # Vokabel
-            rows.append({"ID": "", "Unterkategorie": "", "Unterunterkategorie": "", "Wort/Vokabel": word_val})
-            continue
-    return pd.DataFrame(rows, columns=["ID","Unterkategorie","Unterunterkategorie","Wort/Vokabel"])
-
-def remove_empty_vocabulary_rows(df):
-    """Entfernt Zeilen, die nur leere Wort/Vokabel-Spalte haben."""
-    return df[df["Wort/Vokabel"].astype(str).str.strip() != ""].copy().reset_index(drop=True)
-
-def sync_master_and_sheets(master_df, category_dfs):
-    """Synchronisiert Kategorien nach Master, Vokabeln bleiben erhalten."""
-    master_df = master_df.copy()
-    master_df["ID"] = master_df["ID"].astype(str).str.strip()
-    master_dict = dict(zip(master_df["ID"], master_df["Kategorie"]))
-    updated_dfs = {}
-    summary = {}
-
-    for sheet_name, df in category_dfs.items():
-        rows_out = []
-        changes = {"removed":0}
-        for _, row in df.iterrows():
-            id_val = str(row.get("ID","")).strip()
-            if id_val and id_val not in master_dict:
-                changes["removed"] +=1
-                continue
-            rows_out.append(row.to_dict())
-        updated_dfs[sheet_name] = pd.DataFrame(rows_out, columns=df.columns)
-        summary[sheet_name] = changes
-
-    new_master = pd.DataFrame([{"ID":k,"Kategorie":v} for k,v in sorted(master_dict.items())])
-    return new_master, updated_dfs, summary
-
-def save_excel(processed_sheets, output_file):
-    from openpyxl import Workbook
-    with pd.ExcelWriter(output_file, engine="openpyxl") as writer:
-        for sheet_name, df in processed_sheets.items():
-            df.to_excel(writer, sheet_name=sheet_name, index=False)
-            ws = writer.sheets[sheet_name]
-            for col_idx, col in enumerate(df.columns,1):
-                max_len = max(df[col].astype(str).map(len).max() if len(df)>0 else 0,len(col))+2
-                ws.column_dimensions[get_column_letter(col_idx)].width = max_len
-                for row_idx in range(1,len(df)+2):
-                    ws.cell(row=row_idx,column=col_idx).alignment = Alignment(horizontal='left')
-
-def save_ods(processed_sheets, output_file):
-    doc = ezodf.newdoc(doctype="ods", filename=output_file)
-    for name, df in processed_sheets.items():
-        sheet = ezodf.Sheet(name, size=(len(df)+1,len(df.columns)))
-        doc.sheets += sheet
-        for col_idx, col_name in enumerate(df.columns):
-            sheet[0,col_idx].set_value(col_name)
-        for row_idx,row in enumerate(df.itertuples(index=False),start=1):
-            for col_idx,value in enumerate(row):
-                sheet[row_idx,col_idx].set_value("" if pd.isna(value) else value)
-    doc.save()
-
-# ----------------- HAUPTPROGRAMM -----------------
-def main():
-    xls, engine = load_file(INPUT_FILE)
-    if engine == "odf":
-        doc = ezodf.opendoc(INPUT_FILE)
-        sheet_names = [s.name for s in doc.sheets if s.name != MASTER_SHEET_NAME]
-        category_dfs = {name: process_category_sheet(read_ods_sheet(INPUT_FILE,name)) for name in sheet_names}
-        master_df = read_ods_sheet(INPUT_FILE, MASTER_SHEET_NAME)
-    else:
-        sheet_names = [s for s in xls.sheet_names if s != MASTER_SHEET_NAME]
-        category_dfs = {}
-        for sheet_name in sheet_names:
-            df = pd.read_excel(xls, sheet_name=sheet_name, engine=engine)
-            df.columns = [str(c).strip() for c in df.columns]
-            category_dfs[sheet_name] = process_category_sheet(df)
-        master_df = pd.read_excel(xls, sheet_name=MASTER_SHEET_NAME, engine=engine)
-        master_df.columns = [str(c).strip() for c in master_df.columns]
-
-    new_master, updated_dfs, summary = sync_master_and_sheets(master_df, category_dfs)
-    processed_sheets = {MASTER_SHEET_NAME:new_master}
-    processed_sheets.update({k:remove_empty_vocabulary_rows(v) for k,v in updated_dfs.items()})
-
-    ext_out = os.path.splitext(OUTPUT_FILE)[1].lower()
-    if ext_out in [".xlsx",".xls"]:
-        save_excel(processed_sheets, OUTPUT_FILE)
-    else:
-        save_ods(processed_sheets, OUTPUT_FILE)
-
-    logging.info(f"Datei gespeichert: {OUTPUT_FILE}")
-    logging.info("===== SYNC SUMMARY =====")
-    for sheet, info in summary.items():
-        logging.info(f"{sheet}: {info}")
-
-if __name__ == "__main__":
-    main()

NV_Master_to_SPOT.py

@@ -1,3 +1,32 @@
+"""
+===============================================================================
+Skriptname: NV_SPOT_Export.py
+Beschreibung:
+    Dieses Skript soll hierarchische Normvokabular-Tabellen
+    (ODS/XLSX-Format) in eine JSON-basierte SPOT-Struktur (Strukturierter
+    Positionsbaum) konvertieren. Es ermöglicht das Exportieren in Excel und ODS, sowie
+    das nachträgliche Ergänzen von Kategorien, Unterkategorien und Wörtern.
+
+    //NOCH NICHT GETESTET//
+
+Hauptfunktionen:
+    - Node:                Klasse zur Repräsentation von Baumknoten.
+    - load_excel_or_ods:   Lädt Tabellen aus ODS/XLSX-Dateien.
+    - process_sheet_to_tree: Erzeugt eine Baumstruktur aus einem Sheet.
+    - save_spot_json:      Speichert den SPOT-Baum als JSON.
+    - load_spot_json:      Lädt SPOT-Daten aus JSON-Dateien.
+    - export_spot_to_excel: Exportiert den SPOT-Baum nach Excel.
+    - export_spot_to_ods:   Exportiert den SPOT-Baum nach ODS.
+    - add_category/subcategory/word: Fügt Elemente im Baum hinzu.
+    - main:                Steuert den Workflow.
+
+Abhängigkeiten:
+    Python 3.x, pandas, openpyxl, ezodf, json, logging, datetime
+
+Stand: 2025-10-01
+===============================================================================
+"""
+
 import os
 import json
 import datetime
@@ -12,6 +41,20 @@ logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(
 
 # ---------------- SPOT-Baumstruktur ----------------
 class Node:
+    """
+    Repräsentiert einen Knoten in der SPOT-Baumstruktur.
+
+    Attribute:
+        name (str): Anzeigename des Knotens.
+        id (str): Optionale ID (nur für Kategorien).
+        type (str): Knotentyp ("category", "subcategory", "word").
+        children (list[Node]): Unterknoten.
+
+    Methoden:
+        add_child(child): Fügt einen Unterknoten hinzu.
+        to_dict(): Serialisiert den Knoten in ein Dictionary/JSON-kompatibles Format.
+        from_dict(d): Rekonstruiert den Baum aus einem Dictionary.
+    """
     def __init__(self, name, node_type="category", id=None):
         self.name = name
         self.id = id
@@ -19,9 +62,11 @@ class Node:
         self.children = []
 
     def add_child(self, child):
+        """Fügt dem aktuellen Knoten einen Unterknoten hinzu."""
         self.children.append(child)
 
     def to_dict(self):
+        """Wandelt den Knoten (rekursiv) in ein Dictionary um."""
         if self.type == "word":
             return self.name
         return {
@@ -33,14 +78,26 @@ class Node:
 
     @staticmethod
     def from_dict(d):
+        """Erzeugt aus einem Dictionary ein Node-Objekt (rekursiv)."""
         if isinstance(d, str):
             return Node(d, "word")
         node = Node(d["name"], d.get("type", "category"), d.get("id"))
         node.children = [Node.from_dict(c) for c in d.get("children", [])]
         return node
 
+
 # ---------------- Funktionen zum Laden ----------------
 def load_excel_or_ods(input_file, master_sheet="Masterstruktur"):
+    """
+    Lädt ODS oder Excel-Datei und gibt Master- sowie Kategorien-DataFrames zurück.
+
+    Parameter:
+        input_file (str): Pfad zur Quelldatei.
+        master_sheet (str): Name des Masterblattes.
+
+    Rückgabe:
+        (master_df, dfs): Master-DataFrame und Dictionary mit anderen Sheets.
+    """
     ext = os.path.splitext(input_file)[1].lower()
     engine = "openpyxl" if ext in [".xlsx", ".xls"] else "odf"
     xls = pd.ExcelFile(input_file, engine=engine)
@@ -49,26 +106,44 @@ def load_excel_or_ods(input_file, master_sheet="Masterstruktur"):
     master_df = pd.read_excel(xls, sheet_name=master_sheet, engine=engine)
     return master_df, dfs
 
+
 # ---------------- Baum aus Sheet erstellen ----------------
 def process_sheet_to_tree(df):
+    """
+    Wandelt ein Kategoriensheet in eine hierarchische Baumstruktur (Liste von Nodes) um.
+
+    Struktur:
+        Kategorie → Unterkategorie → Wort
+
+    Parameter:
+        df (pd.DataFrame): Eingabedaten mit Spalten ["ID", "Unterkategorie",
+                            "Unterunterkategorie", "Wort/Vokabel"].
+
+    Rückgabe:
+        list[Node]: Liste von Baumknoten der obersten Ebene.
+    """
     df = df.fillna("").astype(str)
     tree_nodes = []
     current_cat = None
     current_sub = None
+
     for idx, row in df.iterrows():
         id_val = row.get("ID", "").strip()
         uk_val = row.get("Unterkategorie", "").strip()
         uuk_val = row.get("Unterunterkategorie", "").strip()
         word_val = row.get("Wort/Vokabel", "").strip()
 
+        # Neue Kategorieebene
         if id_val:
             current_cat = Node(uk_val or word_val, "category", id=id_val)
             tree_nodes.append(current_cat)
             current_sub = None
+        # Unterkategorie
         elif uuk_val:
             current_sub = Node(uuk_val, "subcategory")
             if current_cat:
                 current_cat.add_child(current_sub)
+        # Wortebene
         elif word_val:
             word_node = Node(word_val, "word")
             if current_sub:
@@ -77,28 +152,60 @@ def process_sheet_to_tree(df):
                 current_cat.add_child(word_node)
     return tree_nodes
 
+
 # ---------------- SPOT laden/speichern ----------------
 def save_spot_json(tree_nodes, file_path):
+    """
+    Speichert den SPOT-Baum als JSON-Datei.
+
+    Parameter:
+        tree_nodes (list[Node]): Wurzelknoten der Baumstruktur.
+        file_path (str): Zielpfad.
+    """
     with open(file_path, "w", encoding="utf-8") as f:
         json.dump([n.to_dict() for n in tree_nodes], f, indent=2, ensure_ascii=False)
     logging.info(f"SPOT gespeichert: {file_path}")
 
+
 def load_spot_json(file_path):
+    """
+    Lädt SPOT-JSON-Datei und rekonstruiert den Baum.
+
+    Parameter:
+        file_path (str): Pfad zur JSON-Datei.
+
+    Rückgabe:
+        list[Node]: Liste oberster Knoten.
+    """
     with open(file_path, "r", encoding="utf-8") as f:
         data = json.load(f)
     return [Node.from_dict(n) for n in data]
 
+
 # ---------------- Export in Excel ----------------
 def export_spot_to_excel(tree_nodes, output_file):
+    """
+    Exportiert den SPOT-Baum in eine Excel-Datei.
+
+    Struktur:
+        Spalten A–D: ID, Kategorie, Unterkategorie, Wort.
+
+    Parameter:
+        tree_nodes (list[Node]): Baumstruktur.
+        output_file (str): Zielpfad der Excel-Datei.
+    """
     wb = Workbook()
     wb.remove(wb.active)
+
     for node in tree_nodes:
         ws = wb.create_sheet(title=node.name[:31])
         row_idx = 1
-        # Kategorie
+
+        # Kategoriezeile
         ws.cell(row=row_idx, column=1, value=node.id)
         ws.cell(row=row_idx, column=2, value=node.name)
         row_idx += 1
+
         for sub in node.children:
             if sub.type == "subcategory":
                 ws.cell(row=row_idx, column=3, value=sub.name)
@@ -109,28 +216,44 @@ def export_spot_to_excel(tree_nodes, output_file):
             elif sub.type == "word":
                 ws.cell(row=row_idx, column=4, value=sub.name)
                 row_idx += 1
-        # Spaltenbreiten anpassen
+
+        # Spaltenbreiten und Ausrichtung
         for col_idx, col_letter in enumerate(["A", "B", "C", "D"], 1):
             ws.column_dimensions[col_letter].width = 20
             for r in range(1, row_idx):
                 ws.cell(r, col_idx).alignment = Alignment(horizontal='left')
+
     wb.save(output_file)
     logging.info(f"Excel exportiert: {output_file}")
 
+
 # ---------------- Export in ODS ----------------
 def export_spot_to_ods(tree_nodes, output_file):
+    """
+    Exportiert den SPOT-Baum in eine ODS-Datei.
+
+    Struktur analog zum Excel-Export.
+
+    Parameter:
+        tree_nodes (list[Node]): Baumstruktur.
+        output_file (str): Zielpfad der ODS-Datei.
+    """
     doc = ezodf.newdoc(doctype="ods", filename=output_file)
+
     for node in tree_nodes:
         sheet = ezodf.Sheet(node.name[:31], size=(len(node.children) + 10, 4))
         doc.sheets += sheet
+
         sheet[0, 0].set_value("ID")
         sheet[0, 1].set_value("Unterkategorie")
         sheet[0, 2].set_value("Unterunterkategorie")
         sheet[0, 3].set_value("Wort/Vokabel")
+
         row_idx = 1
         sheet[row_idx, 0].set_value(node.id)
         sheet[row_idx, 1].set_value(node.name)
         row_idx += 1
+
         for sub in node.children:
             if sub.type == "subcategory":
                 sheet[row_idx, 2].set_value(sub.name)
@@ -141,22 +264,51 @@ def export_spot_to_ods(tree_nodes, output_file):
             elif sub.type == "word":
                 sheet[row_idx, 3].set_value(sub.name)
                 row_idx += 1
+
     doc.save()
     logging.info(f"ODS exportiert: {output_file}")
 
+
 # ---------------- CLI-Funktionen zum Editieren ----------------
 def add_category(tree_nodes, cat_id, cat_name):
+    """
+    Fügt eine neue Kategorie zum SPOT-Baum hinzu.
+
+    Parameter:
+        tree_nodes (list[Node]): Liste der obersten Knoten.
+        cat_id (str): ID der Kategorie.
+        cat_name (str): Name der Kategorie.
+    """
     tree_nodes.append(Node(cat_name, "category", id=cat_id))
     logging.info(f"Kategorie hinzugefügt: {cat_id} {cat_name}")
 
+
 def add_subcategory(tree_nodes, cat_id, sub_name):
+    """
+    Fügt einer vorhandenen Kategorie eine Unterkategorie hinzu.
+
+    Parameter:
+        tree_nodes (list[Node]): Wurzelknoten.
+        cat_id (str): Zielkategorie-ID.
+        sub_name (str): Name der Unterkategorie.
+    """
     for cat in tree_nodes:
         if cat.id == cat_id:
             cat.add_child(Node(sub_name, "subcategory"))
             logging.info(f"Unterkategorie hinzugefügt: {sub_name} in {cat_id}")
             return
 
+
 def add_word(tree_nodes, cat_id, sub_name, word_name):
+    """
+    Fügt einem Unterknoten ein Wort hinzu.
+
+    Parameter:
+        tree_nodes (list[Node]): Wurzelknoten.
+        cat_id (str): ID der Kategorie.
+        sub_name (str): Name der Unterkategorie.
+        word_name (str): Neues Wort.
+    """
     for cat in tree_nodes:
         if cat.id == cat_id:
             for sub in cat.children:
@@ -165,9 +317,18 @@ def add_word(tree_nodes, cat_id, sub_name, word_name):
                     logging.info(f"Wort hinzugefügt: {word_name} unter {sub_name}")
                     return
 
+
 # ---------------- HAUPTPROGRAMM ----------------
 def main():
-    INPUT_FILE = "NV_MASTER.ods"   # Beispielpfad
+    """
+    Ablauf:
+      1. Liest Masterdatei (ODS oder XLSX).
+      2. Wandelt Kategorienblätter in SPOT-Struktur um.
+      3. Speichert SPOT als JSON.
+      4. Exportiert SPOT nach Excel und ODS.
+      5. Optional: Bearbeiten des Baums über CLI-Funktionen.
+    """
+    INPUT_FILE = "NV_MASTER.ods"
     OUTPUT_SPOT = "nv_spot.json"
     today = datetime.datetime.today().strftime("%y.%m.%d")
     OUTPUT_EXCEL = f"NV_MASTER_SPOT_{today}.xlsx"
@@ -177,9 +338,10 @@ def main():
     spot_tree = []
     for sheet, df in dfs.items():
         spot_tree.extend(process_sheet_to_tree(df))
+
     save_spot_json(spot_tree, OUTPUT_SPOT)
 
-    # Beispiel: Editieren
+    # Beispielhafte Nutzung der Editierfunktionen:
     # add_category(spot_tree, "10.1", "Neue Kategorie")
     # add_subcategory(spot_tree, "10.1", "Neue Unterunterkategorie")
     # add_word(spot_tree, "10.1", "Neue Unterunterkategorie", "Neues Wort")
@@ -188,5 +350,6 @@ def main():
     export_spot_to_ods(spot_tree, OUTPUT_ODS)
     logging.info("SPOT-Workflow abgeschlossen.")
 
+
 if __name__ == "__main__":
     main()

NormVokabular_Mapper_1.4.py

@@ -1,13 +1,10 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 """
-NormVokabular Mapper – Version 1.4.1
+NormVokabular Mapper – Version 1.4.2
-- Detailliertes (DEBUG) Batch-Logging: gepufferte Logs werden periodisch in Konsole + Datei geschrieben
+
-- Getty AAT (SPARQL via requests) – API-polite, timeout/retries/backoff
+Dieses Skript normalisiert und mappt Begriffe aus Input-Dateien auf ein zentrales Normvokabular
-- Fehlertoleranz: API-Ausfälle führen nicht zum Totalabsturz
+und führt optional API-Abgleiche mit GND und Wikidata durch. Ergebnisse werden in Excel/ODS gespeichert.
-- Fehlende Begriffe -> separate Datei (gleiches Format wie Output)
-- Bestehende Normalisierung/Lemmatisierung/Stemming wird weiterverwendet
-- Batch-Logging-Modus (konfigurierbar)
 """
 
 from __future__ import annotations
@@ -25,50 +22,52 @@ from collections import defaultdict
 from difflib import SequenceMatcher
 from datetime import datetime
 
-# Optional libs
+# Optional Libraries
 try:
-    from rapidfuzz import fuzz
+    from rapidfuzz import fuzz  # für schnellere String-Similarity
     RAPIDFUZZ_AVAILABLE = True
 except Exception:
     RAPIDFUZZ_AVAILABLE = False
 
 try:
     import spacy
-    nlp = spacy.load("de_core_news_sm")
+    nlp = spacy.load("de_core_news_sm")  # deutsche Lemmatization
     SPACY_AVAILABLE = True
 except Exception:
     SPACY_AVAILABLE = False
     nlp = None
 
 # =========================
-# Config & Pfade
+# Konfiguration & Pfade
 # =========================
-INPUT_DIR = Path("Input CSV")
+INPUT_DIR = Path("Input CSV")                # Eingabeverzeichnis
-OUTPUT_DIR = Path("Auswertung Ergebnisse")
+OUTPUT_DIR = Path("Auswertung Ergebnisse")  # Ausgabeordner
-OUTPUT_DIR.mkdir(exist_ok=True)
+OUTPUT_DIR.mkdir(exist_ok=True)             # Verzeichnis erstellen, falls nicht vorhanden
-NORMVOC_FILE = Path("Input CSV/Normvokabular_INTERN/NV_MASTER.ods")
+NORMVOC_FILE = Path("Input CSV/Normvokabular_INTERN/NV_MASTER.ods")  # Normvokabular-Datei
-CACHE_FILE = "api_cache.json"
+CACHE_FILE = "api_cache.json"               # Cache für API-Antworten
 STOPWORDS = {"mit","ohne","der","die","das","ein","eine","und","zu","von","im","in","auf","an","als","bei","für","aus","dem","den","des","eines","einer"}
-CONF_THRESHOLD = 0.75
+CONF_THRESHOLD = 0.75                       # Threshold für Vorschläge
 TIMEOUT_DEFAULT = 5
 MAX_RETRIES_DEFAULT = 3
 BACKOFF_FACTOR_DEFAULT = 2
 HEADERS = {"User-Agent": "VLG_API_multi/1.0 (projekt@example.com)"}
-API_ACTIVE = {"gnd": True, "wikidata": True, "aat": True}
+API_ACTIVE = {"gnd": True, "wikidata": True}  # API-Verfügbarkeit
-FAIL_COUNTER = {"gnd": 0, "wikidata": 0, "aat": 0}
+FAIL_COUNTER = {"gnd": 0, "wikidata": 0}
 
-# Logging file
+# Logging-Parameter
 LOG_FILE = OUTPUT_DIR / "mapper_log.txt"
-
+LOG_BATCH_SIZE = 100        # Anzahl Logs vor Flush
-# Batch logging parameters
+LOG_FLUSH_INTERVAL = 5.0    # Sekunden zwischen Flushes
-LOG_BATCH_SIZE = 100        # flush wenn >= Einträge
+LOG_LEVEL = "DEBUG"          # Logging-Level
-LOG_FLUSH_INTERVAL = 5.0   # Sekunden zwischen Flushes (Batch-Logging)
-LOG_LEVEL = "DEBUG"        # ausführlich gewünscht
 
 # =========================
-# Buffered/Batched Logger
+# Batch/Buffered Logger
 # =========================
 class BatchLogger:
+    """
+    Buffered Logger: Speichert Logs in einem Queue-Buffer und schreibt sie periodisch in Datei und Konsole.
+    Reduziert I/O-Aufwand bei vielen Logs.
+    """
     def __init__(self, logfile: Path, flush_interval: float = 5.0, batch_size: int = 100, level: str = "DEBUG"):
         self.logfile = logfile
         self.flush_interval = flush_interval
@@ -77,7 +76,7 @@ class BatchLogger:
         self.q = queue.Queue()
         self._stop_event = threading.Event()
         self._thread = threading.Thread(target=self._worker, daemon=True, name="BatchLoggerThread")
-        # Ensure logfile exists
+        # Sicherstellen, dass die Log-Datei existiert
         try:
             logfile.parent.mkdir(parents=True, exist_ok=True)
             logfile.touch(exist_ok=True)
@@ -86,35 +85,33 @@ class BatchLogger:
         self._thread.start()
 
     def _format(self, level: str, msg: str) -> str:
+        """Formatiert Logeinträge mit Timestamp"""
         ts = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
         return f"{ts} - {level} - {msg}"
 
     def log(self, level: str, msg: str):
+        """Fügt Log dem Queue hinzu und löst Flush aus, falls Batchgröße erreicht"""
         if self._stop_event.is_set():
             return
         formatted = self._format(level, msg)
         self.q.put((level, formatted))
-        # If queue too big, trigger immediate flush by putting a special token
         if self.q.qsize() >= self.batch_size:
             self.q.put(("__FLUSH__", "__FLUSH__"))
 
     def debug(self, msg: str):
         if LOG_LEVEL in ("DEBUG",):
             self.log("DEBUG", msg)
-
     def info(self, msg: str):
         self.log("INFO", msg)
-
     def warning(self, msg: str):
         self.log("WARNING", msg)
-
     def error(self, msg: str):
         self.log("ERROR", msg)
-
     def exception(self, msg: str):
         self.log("EXCEPTION", msg)
 
     def _worker(self):
+        """Hintergrund-Thread: verarbeitet Queue, schreibt Logs periodisch"""
         buffer = []
         last_flush = time.time()
         while not self._stop_event.is_set() or not self.q.empty():
@@ -123,7 +120,6 @@ class BatchLogger:
                 try:
                     item = self.q.get(timeout=self.flush_interval)
                 except queue.Empty:
-                    # time-based flush
                     if buffer:
                         self._flush_buffer(buffer)
                         buffer = []
@@ -141,36 +137,30 @@ class BatchLogger:
                     continue
                 buffer.append((level, formatted))
 
-                # flush conditions
                 if len(buffer) >= self.batch_size or (time.time() - last_flush) >= self.flush_interval:
                     self._flush_buffer(buffer)
                     buffer = []
                     last_flush = time.time()
             except Exception as e:
-                # As a last resort, write error immediately to stderr
                 try:
                     sys.stderr.write(f"BatchLogger worker error: {e}\n")
                 except Exception:
                     pass
                 time.sleep(0.5)
-        # final flush
         if buffer:
             self._flush_buffer(buffer)
 
     def _flush_buffer(self, buffer):
+        """Schreibt Puffer in Datei und Konsole"""
         if not buffer:
             return
-        # write to console and file
         try:
-            # console
             out_lines = [f"{line}\n" for _, line in buffer]
-            # write to stdout
             try:
                 sys.stdout.writelines(out_lines)
                 sys.stdout.flush()
             except Exception:
                 pass
-            # append to file
             try:
                 with open(self.logfile, "a", encoding="utf-8") as f:
                     f.writelines(out_lines)
@@ -183,17 +173,17 @@ class BatchLogger:
             pass
 
     def stop(self):
+        """Stoppt Logger-Thread"""
         self._stop_event.set()
-        # put sentinel to wake worker
         try:
             self.q.put(("__FLUSH__", "__FLUSH__"))
         except Exception:
             pass
         self._thread.join(timeout=5.0)
 
-# Instantiate logger
+# Logger-Instanz erstellen
 logger = BatchLogger(LOG_FILE, flush_interval=LOG_FLUSH_INTERVAL, batch_size=LOG_BATCH_SIZE, level=LOG_LEVEL)
-logger.info("Starte NormVokabular Mapper v1.4.1 (Batch-Logging aktiv)")
+logger.info("Starte NormVokabular Mapper v1.4.2 (Batch-Logging aktiv)")
 
 # =========================
 # Cache laden/speichern
@@ -210,6 +200,7 @@ else:
     CACHE = {}
 
 def save_cache():
+    """Speichert aktuellen Cache in JSON"""
     try:
         with open(CACHE_FILE,"w",encoding="utf-8") as f:
             json.dump(CACHE, f, indent=2, ensure_ascii=False)
@@ -221,6 +212,7 @@ def save_cache():
 # Normalisierung / Lemma / Tokenization
 # =========================
 def normalize_text(s):
+    """Text in Kleinbuchstaben, Sonderzeichen entfernen, Trim"""
     if not s:
         return ""
     s = str(s).lower().strip()
@@ -229,8 +221,8 @@ def normalize_text(s):
     return s
 
 lemma_cache = {}
-
 def lemmatize_term(term):
+    """Lemmatize mit spaCy, Cache für Performance"""
     term_norm = normalize_text(term)
     if term_norm in lemma_cache:
         return lemma_cache[term_norm]
@@ -246,6 +238,7 @@ def lemmatize_term(term):
     return lemma
 
 def compound_split(term):
+    """Splittet Komposita nach -, _, / oder Leerzeichen"""
     if not term:
         return []
     parts = [p for p in re.split(r"[\s\-_/]+", term) if p]
@@ -255,24 +248,29 @@ def compound_split(term):
 # Normvokabular laden & Index
 # =========================
 def load_normvokabular(file_path):
+    """Lädt Normvokabular aus Excel/ODS, erstellt Dictionarys für Mapping"""
     try:
         sheets = pd.read_excel(file_path, sheet_name=None, engine="odf" if file_path.suffix.lower()==".ods" else None)
     except Exception as e:
         logger.error(f"Normvokabular konnte nicht geladen werden: {e}")
         raise
+
     norm_dict = {}
     stem_index = defaultdict(list)
     lemma_norm_map = {}
 
     for sheet_name, df in sheets.items():
         if sheet_name.lower() in ["master", "übersicht"]:
-            continue
+            continue  # Übersichtsblätter ignorieren
         df = df.dropna(how="all", axis=1)
         df.columns = [str(c).strip() for c in df.columns]
+
+        # ID- und Wort-Spalte finden
         id_col = next((c for c in df.columns if "ID" in c), None)
         word_col = next((c for c in df.columns if "Wort" in c or "Vokabel" in c or "Begriff" in c), None)
         if not id_col or not word_col:
             continue
+
         current_parent_id = None
         for _, row in df.iterrows():
             row_id = str(row[id_col]).strip() if pd.notna(row[id_col]) else None
@@ -296,6 +294,10 @@ def load_normvokabular(file_path):
 # Mapping & Vorschläge
 # =========================
 def map_to_norm(term, norm_dict, stem_index, lemma_norm_map, top_n=3):
+    """
+    Mappt einen Begriff auf Normvokabular.
+    Prüft exakte Treffer, Lemma-Treffer, Komposita und generiert Vorschläge.
+    """
     term_norm = normalize_text(term)
     term_lemma = lemmatize_term(term)
 
@@ -329,6 +331,7 @@ def map_to_norm(term, norm_dict, stem_index, lemma_norm_map, top_n=3):
         return "KEIN TREFFER", "", combined_suggestions
 
 def get_suggestions(term_lemma, lemma_norm_map, top_n=3, threshold=CONF_THRESHOLD):
+    """Ermittelt Vorschläge basierend auf Similarity"""
     candidates = []
     for key_lemma, entry in lemma_norm_map.items():
         if RAPIDFUZZ_AVAILABLE:
@@ -346,10 +349,14 @@ def get_suggestions(term_lemma, lemma_norm_map, top_n=3, threshold=CONF_THRESHOL
 # Generic request with retries & caching
 # =========================
 def request_with_retries_generic(api_name, url, params=None, headers=None, timeout=TIMEOUT_DEFAULT, max_retries=MAX_RETRIES_DEFAULT, backoff=BACKOFF_FACTOR_DEFAULT):
+    """
+    Sendet GET-Requests mit Retry-Logik, Backoff und Caching
+    """
     cache_key = url + (json.dumps(params, sort_keys=True, ensure_ascii=False) if params else "")
     if cache_key in CACHE:
         logger.debug(f"[Cache] {api_name}: {cache_key}")
         return CACHE[cache_key]
+
     retries = 0
     while retries < max_retries:
         try:
@@ -378,9 +385,10 @@ def request_with_retries_generic(api_name, url, params=None, headers=None, timeo
     return None
 
 # =========================
-# GND / Wikidata (bestehend)
+# GND / Wikidata Batch Queries
 # =========================
 def batch_query_gnd(terms):
+    """Batch-Abfrage der Begriffe bei GND"""
     results = {}
     if not API_ACTIVE.get("gnd", False):
         for t in terms: results[t] = ""
@@ -409,6 +417,7 @@ def batch_query_gnd(terms):
     return results
 
 def batch_query_wikidata(terms):
+    """Batch-Abfrage der Begriffe bei Wikidata"""
     results = {}
     if not API_ACTIVE.get("wikidata", False):
         for t in terms: results[t] = ""
@@ -423,10 +432,13 @@ def batch_query_wikidata(terms):
         top = ""
         try:
             if data and "search" in data:
+                # Ermittlung der Kandidaten mit Ähnlichkeitsbewertung
                 cands = [(e.get("label",""), SequenceMatcher(None, t.lower(), e.get("label","").lower()).ratio())
                          for e in data["search"] if e.get("label","")]
+                # Filterung nach Mindestähnlichkeit (0.70)
                 cands = [c for c in cands if c[1] >= 0.70]
                 if cands:
+                    # Bestes Ergebnis nach Ähnlichkeit auswählen
                     top = sorted(cands, key=lambda x: x[1], reverse=True)[0][0]
         except Exception as e:
             logger.debug(f"[WD] Fehler bei Verarbeitung für '{t}': {e}")
@@ -435,93 +447,14 @@ def batch_query_wikidata(terms):
     logger.info(f"[WD] Fertig. Dauer: {elapsed:.1f}s")
     return results
 
-# =========================
-# Getty AAT Abfrage – robust & API-polite (requests)
-# =========================
-def batch_query_getty_aat(terms):
-    results = {}
-    if not API_ACTIVE.get("aat", False):
-        for t in terms: results[t] = ""
-        return results
-
-    endpoint = "https://vocab.getty.edu/sparql"
-    headers = {"Accept": "application/sparql-results+json", "User-Agent": HEADERS.get("User-Agent")}
-    TIMEOUT = 8
-    MAX_RETRIES = 3
-    BACKOFF_FACTOR = 2
-    FAIL_LIMIT = 5
-    fail_counter_local = 0
-
-    logger.info(f"[AAT] Starte Getty AAT-Abgleich für {len(terms)} Terme")
-    start_all = time.time()
-    for idx, term in enumerate(terms, start=1):
-        term_norm = lemmatize_term(normalize_text(term))
-        tokens = compound_split(term_norm)
-        logger.debug(f"[AAT] ({idx}/{len(terms)}) Begriff '{term}' -> Tokens: {tokens}")
-
-        query_fragments = []
-        for tkn in tokens:
-            t_escaped = tkn.replace('"', '\\"')
-            qf = f"""
-                ?concept skos:prefLabel ?label .
-                FILTER(lang(?label)='de' && CONTAINS(LCASE(?label), LCASE("{t_escaped}")))
-            """
-            query_fragments.append(f"{{ {qf} }}")
-        query_body = " UNION ".join(query_fragments) if query_fragments else ""
-        query = f"PREFIX skos: <http://www.w3.org/2004/02/skos/core#> SELECT ?label ?concept WHERE {{ {query_body} }} LIMIT 10"
-
-        retries = 0
-        success = False
-        start_term = time.time()
-        while retries < MAX_RETRIES and not success:
-            try:
-                logger.debug(f"[AAT] Anfrage (Retry {retries}) für '{term}'")
-                r = requests.get(endpoint, params={"query": query}, headers=headers, timeout=TIMEOUT)
-                if r.status_code != 200:
-                    raise ValueError(f"HTTP {r.status_code}")
-                ret = r.json()
-                candidates = [(b['label']['value'], b['concept']['value']) for b in ret.get("results", {}).get("bindings", [])]
-                if candidates:
-                    scored = [
-                        (c[0], c[1], SequenceMatcher(None, term_norm, lemmatize_term(normalize_text(c[0]))).ratio())
-                        for c in candidates
-                    ]
-                    top = max(scored, key=lambda x: x[2])
-                    results[term] = top[0]
-                    logger.debug(f"[AAT] Treffer für '{term}': {results[term]} (Score: {top[2]:.3f})")
-                else:
-                    results[term] = ""
-                    logger.debug(f"[AAT] Kein Treffer für '{term}'")
-                success = True
-            except Exception as e:
-                retries += 1
-                wait = BACKOFF_FACTOR ** retries
-                logger.warning(f"[AAT] Fehler ({retries}/{MAX_RETRIES}) für '{term}': {e} – warte {wait}s")
-                time.sleep(wait)
-                if retries == MAX_RETRIES:
-                    results[term] = ""
-                    fail_counter_local += 1
-            # polite delay
-            time.sleep(1.0)
-        elapsed_term = time.time() - start_term
-        logger.debug(f"[AAT] Dauer für '{term}': {elapsed_term:.2f}s")
-
-        if fail_counter_local >= FAIL_LIMIT:
-            logger.error("[AAT] Zu viele Fehler lokal - breche AAT-Abfragen ab.")
-            for t_rem in terms[idx:]:
-                results[t_rem] = ""
-            FAIL_COUNTER["aat"] += fail_counter_local
-            API_ACTIVE["aat"] = False
-            break
-
-    elapsed_all = time.time() - start_all
-    logger.info(f"[AAT] Getty AAT-Abgleich abgeschlossen. Dauer: {elapsed_all:.1f}s")
-    return results
-
 # =========================
 # Markierung / Export (Excel/ODS)
 # =========================
 def mark_norm_hits(file_path):
+    """
+    Markiert Treffer in Excel/ODS farblich:
+    Grün = Treffer, Rot = KEIN TREFFER
+    """
     ext = file_path.suffix.lower()
     try:
         if ext in [".xlsx", ".xls"]:
@@ -529,12 +462,14 @@ def mark_norm_hits(file_path):
             from openpyxl.styles import PatternFill
             wb = load_workbook(file_path)
             ws = wb.active
+            # Spaltenmapping anhand der Kopfzeile
             col_map = {cell.value: idx+1 for idx, cell in enumerate(ws[1])}
             norm_col = col_map.get("Norm_Treffer", None)
             if not norm_col:
                 logger.debug("Spalte 'Norm_Treffer' nicht gefunden (mark_norm_hits).")
                 wb.save(file_path)
                 return
+            # Farben definieren
             green_fill = PatternFill(start_color="C6EFCE", end_color="C6EFCE", fill_type="solid")
             red_fill   = PatternFill(start_color="FFC7CE", end_color="FFC7CE", fill_type="solid")
             for row in ws.iter_rows(min_row=2, min_col=norm_col, max_col=norm_col):
@@ -545,6 +480,7 @@ def mark_norm_hits(file_path):
                     cell.fill = red_fill
             wb.save(file_path)
         elif ext == ".ods":
+            # ODS: kein Zell-Fill, stattdessen Status-Spalte
             df = pd.read_excel(file_path, engine="odf")
             df["Norm_Status"] = df["Norm_Treffer"].apply(lambda x: "Treffer" if pd.notna(x) and str(x).strip() and x != "KEIN TREFFER" else "Kein Treffer")
             df.to_excel(file_path, index=False, engine="odf")
@@ -555,6 +491,9 @@ def mark_norm_hits(file_path):
 # Fehlende Begriffe -> separate Datei
 # =========================
 def export_missing_terms(out_df, output_file):
+    """
+    Speichert Begriffe ohne Treffer oder Vorschläge in separater Datei
+    """
     missing_df = out_df[
         (out_df["Norm_Treffer"] == "KEIN TREFFER") &
         (out_df["Norm_Vorschlag"].isna() | (out_df["Norm_Vorschlag"].str.strip() == ""))
@@ -562,7 +501,6 @@ def export_missing_terms(out_df, output_file):
 
     count_missing = len(missing_df)
     logger.info(f"Anzahl Begriffe ohne Treffer und Vorschläge: {count_missing}")
-
     if count_missing == 0:
         return
 
@@ -589,8 +527,10 @@ def export_missing_terms(out_df, output_file):
 # Haupt-Loop: Verarbeitung Input-Dateien
 # =========================
 def process_files():
+    """Verarbeitet alle Dateien im Input-Ordner, mappt Begriffe und speichert Ergebnisse"""
     overall_start = time.time()
     try:
+        # Normvokabular laden
         norm_dict, stem_index, lemma_norm_map = load_normvokabular(NORMVOC_FILE)
     except Exception as e:
         logger.error("Normvokabular konnte nicht geladen werden. Beende.")
@@ -626,6 +566,7 @@ def process_files():
         df = df.dropna(how="all")
         df.columns = [str(c).strip() for c in df.columns]
 
+        # Spalten identifizieren
         besch_col = next((c for c in df.columns if "Objektbeschreibung" in c), None)
         box_col = next((c for c in df.columns if "Objekt/Ebene" in c), None)
         urh_col = next((c for c in df.columns if "Urheber" in c), None)
@@ -633,6 +574,7 @@ def process_files():
             logger.warning(f"Spalte 'Objektbeschreibung' nicht gefunden in {file_path.name}. Datei übersprungen.")
             continue
 
+        # Begriffe extrahieren
         row_terms_map = []
         for r_idx, row in enumerate(df.itertuples(index=False), start=1):
             try:
@@ -657,9 +599,11 @@ def process_files():
             if (r_idx % 200) == 0:
                 logger.debug(f"[{file_path.name}] Zeile {r_idx} verarbeitet")
 
+        # Alle einzigartigen Terme für API-Abfragen
         all_terms = list({t for _,_,terms in row_terms_map for t in terms})
         logger.info(f"[{file_path.name}] Gefundene unique Terme: {len(all_terms)}")
         total_unique_terms = len(all_terms)
+
         # API-Abfragen
         t0 = time.time()
         gnd_results = batch_query_gnd(all_terms)
@@ -668,9 +612,6 @@ def process_files():
         wd_results = batch_query_wikidata(all_terms)
         t2 = time.time()
         logger.info(f"[{file_path.name}] Wikidata-Abfragen Dauer: {t2-t1:.1f}s")
-        aat_results = batch_query_getty_aat(all_terms) if API_ACTIVE.get("aat", False) else {t:"" for t in all_terms}
-        t3 = time.time()
-        logger.info(f"[{file_path.name}] AAT-Abfragen Dauer: {t3-t2:.1f}s")
 
         # Build output rows
         output_rows = []
@@ -690,58 +631,30 @@ def process_files():
                     "Norm_ID": norm_id,
                     "Norm_Vorschlag": ", ".join(suggestions) if suggestions else "",
                     "GND_Top1": gnd_results.get(term,""),
-                    "WD_Top1": wd_results.get(term,""),
+                    "WD_Top1": wd_results.get(term,"")
-                    "AAT_Top1": aat_results.get(term,"")
                 }
                 output_rows.append(out_row)
                 processed_count += 1
                 if (processed_count % 200) == 0:
                     logger.debug(f"[{file_path.name}] {processed_count}/{total_unique_terms} Terme verarbeitet")
 
+        # Save output
         out_df = pd.DataFrame(output_rows)
-        output_file = OUTPUT_DIR / f"Auswertung_{file_path.stem}{file_path.suffix}"
+        out_file = OUTPUT_DIR / f"{file_path.stem}_mapped.xlsx"
-        version = 1
-        while output_file.exists():
-            output_file = OUTPUT_DIR / f"Auswertung_{file_path.stem}_({version}){file_path.suffix}"
-            version += 1
-        engine = "odf" if output_file.suffix.lower()==".ods" else None
-
         try:
-            out_df.to_excel(output_file, index=False, engine=engine)
+            out_df.to_excel(out_file, index=False, engine="openpyxl")
-            logger.info(f"[{file_path.name}] Auswertung gespeichert: {output_file}")
+            logger.info(f"Ergebnisse gespeichert: {out_file}")
+            mark_norm_hits(out_file)
+            export_missing_terms(out_df, out_file)
         except Exception as e:
-            logger.error(f"[{file_path.name}] Fehler beim Speichern der Auswertung {output_file}: {e}")
+            logger.error(f"Fehler beim Speichern der Ergebnisse für {file_path.name}: {e}")
-            continue
 
-        export_missing_terms(out_df, output_file)
+    elapsed_total = time.time() - overall_start
-        mark_norm_hits(output_file)
+    logger.info(f"Verarbeitung abgeschlossen. Gesamtzeit: {elapsed_total:.1f}s")
+    logger.info(f"Gesamtterme: {total_terms}, Treffer: {total_hits}, Trefferquote: {total_hits/total_terms:.2%}" if total_terms else "")
 
-        file_elapsed = time.time() - file_start
-        logger.info(f"[Datei {file_idx}/{len(files)}] Fertig ({file_elapsed:.1f}s)")
-
-    overall_elapsed = time.time() - overall_start
-    logger.info(f"Fertig. Gesamt: {total_terms} Begriffe, {total_hits} Treffer im Normvokabular. Gesamtzeit: {overall_elapsed:.1f}s")
-
-# =========================
-# Main
-# =========================
-if __name__ == "__main__":
-    try:
-        process_files()
-    except KeyboardInterrupt:
-        logger.warning("Abbruch durch Benutzer (KeyboardInterrupt).")
-    except SystemExit:
-        logger.warning("SystemExit aufgetreten.")
-    except Exception as e:
-        logger.exception(f"Ungefangener Fehler: {e}")
-    finally:
-        # Stop logger (flush remaining logs)
-        try:
     save_cache()
-        except Exception:
-            pass
-        try:
-            logger.info("Beende.")
     logger.stop()
-        except Exception:
+
-            pass
+if __name__ == "__main__":
+    process_files()

NormVokabular_Mapper_Wrapper.py

@@ -1,46 +0,0 @@
-import subprocess
-import json
-import sys
-from pathlib import Path
-
-def run_mapper(term):
-    """
-    Ruft das bestehende mapper script auf und liefert Vorschläge zurück.
-    Erwartet, dass das mapper script eine JSON-Ausgabe liefert:
-    {
-        "term": "Begriff",
-        "norm_name": "Normierter Treffer oder KEIN TREFFER",
-        "norm_id": "ID",
-        "suggestions": ["Vorschlag1", "Vorschlag2", "Vorschlag3"]
-    }
-    """
-    mapper_script = Path("/home/jarnold/projects/GND-Skript Test/NormVokabular_Mapper_1.2.py")  # dein bestehendes Mapper-Skript
-    if not mapper_script.exists():
-        raise FileNotFoundError(f"{mapper_script} nicht gefunden")
-
-    # Übergabe als JSON-String
-    input_json = json.dumps({"term": term})
-
-    # Aufruf via subprocess
-    result = subprocess.run(
-        [sys.executable, str(mapper_script), input_json],
-        capture_output=True,
-        text=True
-    )
-
-    if result.returncode != 0:
-        raise RuntimeError(f"Mapper Fehler: {result.stderr}")
-
-    try:
-        output = json.loads(result.stdout)
-    except Exception as e:
-        raise ValueError(f"Ungültige Ausgabe vom Mapper: {e}")
-
-    return output
-
-
-if __name__ == "__main__":
-    if len(sys.argv) > 1:
-        term = sys.argv[1]
-        output = run_mapper(term)
-        print(json.dumps(output, ensure_ascii=False))

Tryout/NVTest.py

@@ -1,101 +0,0 @@
-import pandas as pd
-import requests
-import time
-import os
-
-def match_gnd(token, delay=0.3):
-    """GND-Abfrage für ein Schlagwort, gibt erstes Ergebnis zurück"""
-    url = f"https://lobid.org/gnd/search?q={token}&format=json"
-    try:
-        resp = requests.get(url, timeout=5)
-        if resp.status_code == 200:
-            data = resp.json()
-            if 'member' in data and data['member']:
-                first = data['member'][0]
-                return first.get('preferredName'), first.get('gndIdentifier')
-    except Exception as e:
-        print(f"Fehler bei GND-Abfrage für '{token}': {e}")
-    time.sleep(delay)
-    return None, None
-
-def load_exlibris_refs(path):
-    """CSV einlesen, Scan-Zuordnung, Platzhalter-Inventarnummer, GND-Abgleich"""
-    df = pd.read_csv(path, dtype=str, header=0)
-    # erste Spalte leer? → "Kürzel"
-    if df.columns[0].strip() == '':
-        df.rename(columns={df.columns[0]: 'Kürzel'}, inplace=True)
-    df.fillna('', inplace=True)
-
-    # Scan-Level-Spalten
-    level_cols = [c for c in df.columns if c.strip() in ['0','1','2','3','4']]
-
-    obj_list = []
-    current_obj = None
-    placeholder_counter = 1
-
-    for _, row in df.iterrows():
-        has_0 = row['0'].strip() if '0' in df.columns else ''
-        row_refs = []
-        for c in level_cols:
-            val = row[c].strip()
-            if val:
-                row_refs.append({'level': c, 'scan_ref': val})
-
-        if has_0:
-            if current_obj:
-                obj_list.append(current_obj)
-            core_data = {col: row[col] for col in df.columns if col not in level_cols}
-            # Inventarnummer prüfen
-            inv = core_data.get('Inventarnummer','').strip()
-            if not inv:
-                core_data['Inventarnummer'] = f'PL-{placeholder_counter:04d}'
-                placeholder_counter += 1
-            # GND-Abgleich
-            obj_descr = core_data.get('Objektbeschreibung','')
-            gnd_name, gnd_id = None, None
-            if obj_descr:
-                tokens = [t.strip() for t in obj_descr.split(',') if t.strip()]
-                for t in tokens:
-                    name, gid = match_gnd(t)
-                    if gid:
-                        gnd_name = name
-                        gnd_id = gid
-                        break
-            core_data['GND_Name'] = gnd_name
-            core_data['GND_ID'] = gnd_id
-            current_obj = core_data
-            current_obj['ScanReferenzen'] = row_refs
-        else:
-            if current_obj:
-                current_obj['ScanReferenzen'].extend(row_refs)
-
-    if current_obj:
-        obj_list.append(current_obj)
-
-    out_df = pd.DataFrame(obj_list)
-    core_fields = ['Kürzel','Inventarnummer','Standort','Jahr','Urheber','Eigner',
-                   'Objektbeschreibung','Material','Maße (in cm)',
-                   'Objekttyp','Inschrift','Anmerkungen','ScanReferenzen',
-                   'GND_Name','GND_ID']
-    available = [c for c in core_fields if c in out_df.columns]
-    return out_df[available]
-
-# ====================
-# Hauptteil
-# ====================
-if __name__ == "__main__":
-    # CSV im gleichen Ordner suchen
-    csv_files = [f for f in os.listdir('.') if f.lower().endswith('.csv')]
-    if not csv_files:
-        print("Keine CSV-Datei im aktuellen Ordner gefunden.")
-        exit(1)
-    # nimm die erste gefundene CSV
-    input_csv = csv_files[0]
-    print(f"Verwende CSV-Datei: {input_csv}")
-
-    df = load_exlibris_refs(input_csv)
-
-    # Ergebnis als Testergebnis.csv speichern
-    output_file = "Testergebnis.csv"
-    df.to_csv(output_file, index=False)
-    print(f"Aufbereitete Daten gespeichert als {output_file}")

VLG.py

@@ -1,190 +0,0 @@
-#!/usr/bin/env python3
-"""
-VLG_AAT.py Gruppierung, Auflösung "Objektbeschreibung"
-NOCH OHNE AAT-ABGLEICH
-
-- Prüft ezodf in aktueller Umgebung
-- Liest ODS aus "Input CSV/"
-- Extrahiert Begriffe aus "Objektbeschreibung"
-- Lemmatisierung (Spacy) + Stopwortfilter
-- Subtokenisierung komplexer Phrasen
-- Zählt Häufigkeiten
-- Ausgabe ODS / CSV-Fallback in "Auswertung Ergebnisse"
-"""
-
-import os
-import sys
-import logging
-from collections import Counter
-import pandas as pd
-import spacy
-
-# ---------------------------
-# Logging
-# ---------------------------
-logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
-
-# ---------------------------
-# ezodf prüfen
-# ---------------------------
-try:
-    import ezodf
-    EZODF_AVAILABLE = True
-    logging.info(f"ezodf erkannt")
-except ImportError:
-    EZODF_AVAILABLE = False
-    logging.error("ezodf konnte nicht importiert werden!")
-    logging.error("Möglicherweise nutzen Sie nicht die Python-Umgebung, in der ezodf installiert ist.")
-    logging.error(f"Aktuelle Python-Executable: {sys.executable}")
-    logging.error("Bitte prüfen Sie Ihre venv oder installieren Sie ezodf in dieser Umgebung:")
-    logging.error("    python -m pip install ezodf")
-    sys.exit(1)
-
-# ---------------------------
-# Spacy laden
-# ---------------------------
-try:
-    nlp = spacy.load("de_core_news_sm")
-    logging.info("Spacy-Modell geladen.")
-except Exception as e:
-    logging.error(f"Spacy-Modell konnte nicht geladen werden: {e}")
-    sys.exit(1)
-
-# ---------------------------
-# Konfiguration
-# ---------------------------
-INPUT_FOLDER = "Input CSV"
-OUTPUT_FOLDER = "Auswertung Ergebnisse"
-INPUT_FILENAME = None
-TARGET_COLUMN = "Objektbeschreibung"
-STOPWORDS = {"mit", "auf", "von", "und", "der", "die", "das"}  # erweiterbar
-MAPPING = {  # Projektinterne Sonderfälle
-    "exlibris": "exlibris",
-    "wappen": "wappen"
-}
-
-# ---------------------------
-# Funktionen
-# ---------------------------
-def find_input_file(folder: str, filename_hint: str = None):
-    if not os.path.isdir(folder):
-        raise FileNotFoundError(f"Input-Ordner '{folder}' existiert nicht.")
-    files = [f for f in os.listdir(folder) if f.lower().endswith(".ods")]
-    if filename_hint:
-        for f in files:
-            if f == filename_hint or filename_hint in f:
-                return os.path.join(folder, f)
-    if not files:
-        raise FileNotFoundError(f"Keine .ods-Dateien in '{folder}' gefunden.")
-    return os.path.join(folder, files[0])
-
-def read_ods_first_sheet(path: str) -> pd.DataFrame:
-    """Lädt ODS, erkennt automatisch Header-Zeile."""
-    try:
-        df = pd.read_excel(path, engine="odf", header=None)
-        logging.info("ODS mit pandas + odfpy geladen.")
-    except Exception as e1:
-        logging.warning(f"pandas + odfpy konnte ODS nicht lesen ({e1}).")
-        if not EZODF_AVAILABLE:
-            raise RuntimeError("ezodf nicht installiert und pandas + odfpy fehlgeschlagen.")
-        doc = ezodf.opendoc(path)
-        sheet = doc.sheets[0]
-        data = []
-        for row in sheet.rows():
-            values = [c.value if hasattr(c, "value") else "" for c in row]
-            data.append(values)
-        df = pd.DataFrame(data)
-        logging.info("ODS mit ezodf geladen.")
-
-    # Header-Zeile automatisch finden
-    header_row_index = None
-    for i, row in df.iterrows():
-        row_str = row.fillna("").astype(str).str.lower()
-        if any("objektbeschreibung" in str(cell) for cell in row_str):
-            header_row_index = i
-            break
-    if header_row_index is None:
-        raise KeyError("Keine Header-Zeile mit 'Objektbeschreibung' gefunden.")
-
-    df.columns = df.iloc[header_row_index]
-    df = df.iloc[header_row_index + 1:].reset_index(drop=True)
-    return df
-
-def tokenize_and_lemmatize(series: pd.Series) -> list:
-    """Tokenisiert, entfernt Stopwords, wendet Mapping + Spacy-Lemmatisierung an."""
-    series = series.fillna("").astype(str).str.strip().str.lower()
-    all_terms = []
-    for text in series:
-        if not text:
-            continue
-        # Komma-Split
-        for part in [p.strip() for p in text.split(",") if p.strip()]:
-            # Subtokenisierung via Spacy
-            doc = nlp(part)
-            for token in doc:
-                lemma = token.lemma_.lower()
-                if lemma in STOPWORDS:
-                    continue
-                lemma = MAPPING.get(lemma, lemma)
-                if lemma:
-                    all_terms.append(lemma)
-    return all_terms
-
-def write_output(rows: list, outpath: str):
-    if EZODF_AVAILABLE:
-        if not rows:
-            logging.warning("Keine Daten zum Schreiben.")
-            return
-        keys = list(rows[0].keys())
-        doc = ezodf.newdoc(doctype="ods", filename=outpath)
-        sheet = ezodf.Sheet("Auswertung", size=(len(rows)+1, len(keys)))
-        doc.sheets += sheet
-        for ci, k in enumerate(keys):
-            sheet[0, ci].set_value(k)
-        for ri, row in enumerate(rows, start=1):
-            for ci, k in enumerate(keys):
-                sheet[ri, ci].set_value(row.get(k, ""))
-        doc.save()
-        logging.info(f"ODS geschrieben: {outpath}")
-    else:
-        csv_path = os.path.splitext(outpath)[0] + ".csv"
-        df = pd.DataFrame(rows)
-        df.to_csv(csv_path, index=False, sep=";", encoding="utf-8")
-        logging.info(f"CSV-Fallback geschrieben: {csv_path}")
-
-# ---------------------------
-# Hauptfunktion
-# ---------------------------
-def main(input_folder=INPUT_FOLDER, input_filename=INPUT_FILENAME):
-    input_path = find_input_file(input_folder, filename_hint=input_filename)
-    input_basename = os.path.splitext(os.path.basename(input_path))[0]
-    logging.info(f"Verarbeite Datei: {input_path}")
-
-    df = read_ods_first_sheet(input_path)
-    logging.info(f"Geladene Spalten: {list(df.columns)}")
-
-    if TARGET_COLUMN.lower() not in [str(c).lower() for c in df.columns]:
-        raise KeyError(f"Spalte '{TARGET_COLUMN}' nicht gefunden.")
-
-    terms = tokenize_and_lemmatize(df[TARGET_COLUMN])
-    logging.info(f"Gefundene Begriffe: {len(terms)}")
-
-    counts = Counter(terms)
-    sorted_terms = sorted(counts.items(), key=lambda kv: kv[1], reverse=True)
-    rows = [{"Begriff": term, "Anzahl": freq} for term, freq in sorted_terms]
-
-    os.makedirs(OUTPUT_FOLDER, exist_ok=True)
-    out_name = f"{input_basename} Auswertung.ods"
-    out_path = os.path.join(OUTPUT_FOLDER, out_name)
-    write_output(rows, out_path)
-    logging.info("Fertig.")
-
-if __name__ == "__main__":
-    argv = sys.argv[1:]
-    folder = INPUT_FOLDER
-    fname = INPUT_FILENAME
-    if len(argv) >= 1:
-        folder = argv[0]
-    if len(argv) >= 2:
-        fname = argv[1]
-    main(input_folder=folder, input_filename=fname)

VLG_API_multi.py

@@ -1,262 +0,0 @@
-import os
-import sys
-import time
-import json
-import requests
-import pandas as pd
-from pathlib import Path
-from difflib import SequenceMatcher
-import argparse
-
-# =========================
-# Argumente / Dry-Run
-# =========================
-parser = argparse.ArgumentParser()
-parser.add_argument('--dry-run', action='store_true', help='API-Abfragen simulieren')
-args = parser.parse_args()
-DRY_RUN = args.dry_run
-
-# =========================
-# Konfiguration
-# =========================
-INPUT_DIR = Path("Input CSV")
-OUTPUT_DIR = Path("Auswertung Ergebnisse")
-OUTPUT_DIR.mkdir(exist_ok=True)
-
-TIMEOUT = 5
-MAX_RETRIES = 3
-BACKOFF_FACTOR = 2
-MAX_CONSECUTIVE_FAILURES = 10
-
-CACHE_FILE = "api_cache.json"
-if os.path.exists(CACHE_FILE):
-    with open(CACHE_FILE, "r", encoding="utf-8") as f:
-        CACHE = json.load(f)
-else:
-    CACHE = {}
-
-API_ACTIVE = {"gnd": True, "wikidata": True}
-FAIL_COUNTER = {"gnd": 0, "wikidata": 0}
-
-HEADERS = {"User-Agent": "VLG_API_multi/1.0 (projekt@example.com)"}
-
-# =========================
-# Logging
-# =========================
-def log(level, msg):
-    print(f"[{level}] {msg}")
-
-# =========================
-# Cache speichern
-# =========================
-def save_cache():
-    with open(CACHE_FILE, "w", encoding="utf-8") as f:
-        json.dump(CACHE, f, indent=2, ensure_ascii=False)
-
-# =========================
-# Request mit Retry & Backoff
-# =========================
-def request_with_retries(api_name, url, params=None):
-    if DRY_RUN:
-        return {"dummy": True}
-    if not API_ACTIVE[api_name]:
-        return None
-
-    cache_key = url + (str(params) if params else "")
-    if cache_key in CACHE:
-        return CACHE[cache_key]
-
-    retries = 0
-    while retries < MAX_RETRIES:
-        try:
-            r = requests.get(url, params=params, timeout=TIMEOUT, headers=HEADERS)
-            if r.status_code == 200:
-                try:
-                    data = r.json()
-                except:
-                    data = r.text
-                CACHE[cache_key] = data
-                save_cache()
-                FAIL_COUNTER[api_name] = 0
-                return data
-            elif r.status_code in [403, 429]:
-                log("ERROR", f"{api_name.upper()} HTTP {r.status_code} – Stopschalter aktiviert")
-                API_ACTIVE[api_name] = False
-                return None
-            else:
-                log("ERROR", f"{api_name.upper()} HTTP {r.status_code}")
-        except requests.exceptions.Timeout:
-            log("ERROR", f"Timeout bei {api_name.upper()}")
-        except Exception as e:
-            log("ERROR", f"Fehler bei {api_name.upper()}: {e}")
-
-        retries += 1
-        sleep_time = min(BACKOFF_FACTOR ** retries, 30)
-        time.sleep(sleep_time)
-
-    FAIL_COUNTER[api_name] += 1
-    if FAIL_COUNTER[api_name] >= MAX_CONSECUTIVE_FAILURES:
-        log("CRITICAL", f"{MAX_CONSECUTIVE_FAILURES} Fehler bei {api_name.upper()} – Stopschalter aktiviert")
-        API_ACTIVE[api_name] = False
-    return None
-
-# =========================
-# API-Abfragen mit Confidence
-# =========================
-def query_gnd(term, min_conf=0.6):
-    if DRY_RUN or not API_ACTIVE["gnd"]:
-        return "TEST_GND", 1.0
-
-    url = f"https://lobid.org/gnd/search?q={term}&format=json"
-    data = request_with_retries("gnd", url)
-    if not data:
-        return "API nicht erreichbar", 0.0
-
-    results = []
-    scores = []
-    for doc in data.get("member", []):
-        name = doc.get("preferredName", "")
-        conf = SequenceMatcher(None, term.lower(), name.lower()).ratio()
-        if conf >= min_conf:
-            results.append(name)
-            scores.append(conf)
-    if results:
-        return ", ".join(results), max(scores)
-    return "ohne Ergebnis", 0.0
-
-def query_wikidata(term, min_conf=0.5):
-    if DRY_RUN or not API_ACTIVE["wikidata"]:
-        return "TEST_WD", 1.0
-
-    url = "https://www.wikidata.org/w/api.php"
-    params = {"action": "wbsearchentities", "search": term, "language": "de", "format": "json"}
-    data = request_with_retries("wikidata", url, params)
-    if not data:
-        return "API nicht erreichbar", 0.0
-
-    results = []
-    scores = []
-    for entry in data.get("search", []):
-        match_info = entry.get("match", {})
-        score = match_info.get("score", 0.0)
-        if score >= min_conf:
-            results.append(entry["label"])
-            scores.append(score)
-    if results:
-        return ", ".join(results), max(scores)
-    return "ohne Ergebnis", 0.0
-
-# =========================
-# Input laden
-# =========================
-def load_input_file(file_path):
-    try:
-        if file_path.suffix.lower() == ".ods":
-            df = pd.read_excel(file_path, engine="odf", header=None)
-        elif file_path.suffix.lower() == ".xlsx":
-            df = pd.read_excel(file_path, engine="openpyxl", header=None)
-        elif file_path.suffix.lower() == ".csv":
-            df = pd.read_csv(file_path, header=None)
-        else:
-            log("WARNING", f"Unbekanntes Dateiformat: {file_path.name}")
-            return None
-        return df
-    except Exception as e:
-        log("ERROR", f"Fehler beim Laden von {file_path.name}: {e}")
-        return None
-
-# =========================
-# Header-Zeile suchen
-# =========================
-def find_header_row(df, keywords=["objektbeschreibung", "objekt/ebene"]):
-    for i, row in df.iterrows():
-        row_lower = [str(cell).lower() if pd.notna(cell) else "" for cell in row]
-        if any(kw in cell for kw in keywords for cell in row_lower):
-            return i, row_lower
-    return None, None
-
-# =========================
-# Verarbeitung
-# =========================
-def process_files():
-    all_terms = []
-    output_rows = []
-
-    for file_path in INPUT_DIR.glob("*"):
-        if not file_path.suffix.lower() in [".csv", ".xlsx", ".ods"]:
-            continue
-        log("INFO", f"Verarbeite {file_path.name}")
-        df = load_input_file(file_path)
-        if df is None:
-            continue
-
-        header_idx, header_row = find_header_row(df)
-        if header_idx is None:
-            log("WARNING", f"Keine Header-Zeile gefunden in {file_path.name}")
-            continue
-        df.columns = header_row
-        df = df.iloc[header_idx+1:].reset_index(drop=True)
-
-        col_objdesc = next((col for col in df.columns if "objektbeschreibung" in str(col).lower()), None)
-        col_objlevel = next((col for col in df.columns if "objekt/ebene" in str(col).lower()), None)
-        if not col_objdesc:
-            log("WARNING", f"Keine Spalte 'Objektbeschreibung' in {file_path.name}")
-            continue
-
-        term_list = []
-        obj_level_list = []
-        for _, row in df.iterrows():
-            terms = str(row[col_objdesc]) if pd.notna(row[col_objdesc]) else ""
-            if not terms:
-                continue
-            for term in [t.strip() for t in terms.split(",") if t.strip()]:
-                term_list.append(term)
-                obj_level_list.append(row[col_objlevel] if col_objlevel and pd.notna(row[col_objlevel]) else "")
-
-        # API-Abfragen
-        gnd_results = []
-        gnd_scores = []
-        wikidata_results = []
-        wikidata_scores = []
-
-        for term in term_list:
-            gnd_res, gnd_conf = query_gnd(term)
-            wikidata_res, wd_conf = query_wikidata(term)
-            gnd_results.append(gnd_res)
-            gnd_scores.append(gnd_conf)
-            wikidata_results.append(wikidata_res)
-            wikidata_scores.append(wd_conf)
-
-        for idx, term in enumerate(term_list):
-            output_rows.append({
-                "Begriff": term,
-                "Quelle": file_path.name,
-                "Objekt/Ebene": obj_level_list[idx],
-                "GND": gnd_results[idx],
-                "GND_Confidence": gnd_scores[idx],
-                "Wikidata": wikidata_results[idx],
-                "Wikidata_Confidence": wikidata_scores[idx]
-            })
-        all_terms.extend(term_list)
-
-    # Hauptoutput
-    out_df = pd.DataFrame(output_rows)
-    out_file = OUTPUT_DIR / "Auswertung_gesamt.ods"
-    out_df.to_excel(out_file, index=False, engine="odf")
-    log("INFO", f"Hauptauswertung gespeichert: {out_file}")
-
-    # Rohdatei
-    raw_terms = pd.Series(all_terms).value_counts().reset_index()
-    raw_terms.columns = ["Begriff", "Häufigkeit"]
-    raw_file = OUTPUT_DIR / "Rohbegriffe.ods"
-    raw_terms.to_excel(raw_file, index=False, engine="odf")
-    log("INFO", f"Rohbegriffe gespeichert: {raw_file}")
-
-# =========================
-# Main
-# =========================
-if __name__ == "__main__":
-    if not INPUT_DIR.exists():
-        log("CRITICAL", f"Eingabeordner {INPUT_DIR} fehlt!")
-        sys.exit(1)
-    process_files()

Vorschlag_Ersetzen/Vorschlag_Ersetzen_Makro

@@ -0,0 +1,2 @@
+Makro für die Erfassungstabelle, mit dem Vorschläge für Begriffe per Klick angenommen und ersetzt werden sollen. 
+Funktioniert nicht in LibreOffice, müsste in excel aber laufen.

Wiki_Anleitungen/.~lock.Anleitung Arbeiten mit Flachscanner Exlibris.odt#

@@ -0,0 +1 @@
+,jarnold,workPC,16.10.2025 13:04,file:///home/jarnold/.config/libreoffice/4;

Wiki_Anleitungen/Benutzungsanleitung - NV_MASTER_Abgleich_Makro_wikimarkup

@@ -0,0 +1,125 @@
+= Benutzungsanleitung - NV_MASTER Abgleich Makro =
+'''(mapper_macro_2.x.py)'''
+
+== 1. Was das Makro macht ==
+Dieses Makro hilft dir dabei, Begriffe in der Auswertungstabelle zu vereinheitlichen.
+Es vergleicht automatisch die Inhalte aus der Spalte „Objektbeschreibung“ mit einer
+Normvokabular-Referenzdatei namens „NV_MASTER.ods“.
+So findest du heraus, welche Begriffe schon genormt sind, wo es passende Vorschläge gibt
+und wo etwas gar nicht erkannt wurde.
+Das Makro markiert in der Auswertungstabelle jede Zeile unter „Objektbeschreibung“
+farbig:
+
+* <span style="color:green;">Grün</span>: Alles passt, alle Begriffe gefunden
+* <span style="color:yellow;">Gelb</span>: Einige Begriffe wurden erkannt, andere nicht
+* <span style="color:red;">Rot</span>: Kein einziger Begriff erkannt
+
+Beispiel:
+
+{| class="wikitable"
+|+ Tabelle 1
+|-
+! Objektbeschreibung !! Norm_Treffer !! Norm_Vorschlag !! Kein_Treffer
+|-
+| (leer) || || || 
+|}
+
+Die Spalten „Norm_Treffer“, „Norm_Vorschlag“ und „Kein_Treffer“ legt das Makro
+automatisch an, wenn sie fehlen.
+
+! Tipps zur Nutzung !
+* Wenn du die NV_MASTER-Datei änderst, starte das Makro neu – es liest sie bei
+jedem Lauf neu ein.
+* Erstelle ein Backup der Auswertungstabelle, bevor du das Makro ausführst.
+* Schaue ab und zu in die Logdatei, um zu prüfen, ob alles korrekt läuft.
+* Wenn ein Begriff rot markiert wird, aber deiner Meinung nach sinnvoll und zutreffend
+für das beschriebene Objekt ist, schreibe den Begriff auf und sprich mit deinen
+Vorgesetzten ab, ob er in das Normvokabular aufgenommen werden sollte.
+
+== 2. Wo die Dateien des Makros liegen müssen ==
+'''Unter Linux:'''
+<pre>
+/home/&lt;dein-benutzername&gt;/.config/libreoffice/4/user/Scripts/python/Vokabular_Abgleich_Makro/
+</pre>
+
+'''Unter Windows:'''
+<pre>
+C:\Users\<dein-benutzername>\AppData\Roaming\LibreOffice\4\user\Scripts\python\Vokabular_Abgleich_Makro\
+</pre>
+
+In diesem Ordner müssen liegen:  
+* mapper_macro_2.x.py (das Makro)  
+* NV_MASTER.ods (die Referenzdatei)  
+* optional: mapper_macro_2.x.log (wird automatisch erstellt)
+
+== 3. Wie du das Makro startest ==
+# Öffne deine Calc-Datei mit den Begriffen
+# Gehe im Menü auf Extras → Makros → Makros ausführen...
+# Wähle: Meine Makros → mapper_macro_2.x.py → run_mapper_macro
+# Klicke auf Ausführen
+
+Das Makro startet sofort. Je nach Tabellenumfang dauert der Abgleich ein paar Sekunden bis Minuten.  
+Wenn nichts passiert, liegt ein Fehler vor. In diesem Fall schaue in die .log-Datei, die das Makro bei jedem Durchlauf erstellt. Sie liegt im selben Ordner wie das Makro.
+
+== 4. Wie du das Ergebnis liest ==
+Nach dem Lauf schreibt das Makro die Treffer und Vorschläge direkt in deine Tabelle und markiert sie:
+
+{| class="wikitable"
+|+ Tabelle 2
+|-
+! Objektbeschreibung !! Norm_Treffer !! Norm_Vorschlag !! Kein_Treffer
+|-
+| Harfe, Noten, Bäume, Geldbeutel, Landschaft, Gewässer || Harfe (2.1) | Noten (3.4) | Landschaft (7.2) Gewässer (9.1) || Baum || Geldbeutel
+|}
+
+Farben:  
+* 🟩 <span style="color:green;">Grün</span>: Alle Begriffe wurden direkt erkannt → Perfekt!  
+* 🟨 <span style="color:yellow;">Gelb</span>: Einige Begriffe wurden erkannt, aber andere nur teilweise oder gar nicht → Vorschläge unter der Spalte „Norm_Vorschlag“ prüfen  
+* 🟥 <span style="color:red;">Rot</span>: Kein Begriff wurde gefunden → Objektbeschreibung anpassen, ggf. neue Begriffe in das Normvokabular aufnehmen
+
+== 5. Wo das Protokoll liegt (Logdatei) ==
+Das Makro schreibt alles, was passiert, in eine Logdatei:
+
+'''Linux:''' /home/<dein-benutzername>/.config/libreoffice/4/user/Scripts/python/Vokabular_Abgleich_Makro/mapper_macro_2.x.log  
+'''Windows:''' C:\Users\<dein-benutzername>\AppData\Roaming\LibreOffice\4\user\Scripts\python\Vokabular_Abgleich_Makro\mapper_macro_2.x.log  
+
+Dort siehst du:  
+* wann das Makro gestartet wurde  
+* wie viele Zeilen verarbeitet wurden  
+* und ob Fehler aufgetreten sind
+
+{| class="wikitable"
+|+ Tabelle 3
+|-
+! Problem !! Ursache !! Lösung
+|-
+| Das Makro taucht nicht auf || Falscher Speicherort || Prüfe, ob das Skript wirklich im Ordner Scripts/python liegt
+|-
+| Fehlermeldung „Module not found“ || Python-Bibliotheken fehlen || Installiere pandas, odfpy, spacy, rapidfuzz
+|-
+| NV_MASTER wird nicht gelesen || Datei fehlt oder ist kaputt || Prüfe Name und Speicherort
+|-
+| LibreOffice stürzt ab || Sehr große Datei oder fehlerhafte NV_MASTER || Teste mit kleinerer Datei oder neuem NV_MASTER
+|}
+
+== 6. Was das Makro benötigt, um einwandfrei zu laufen ==
+Alle folgenden Pakete sind für das Makro notwendig, egal ob LibreOffice oder Excel:
+
+{| class="wikitable"
+|+ Tabelle 4
+|-
+! Paket !! Zweck
+|-
+| pandas || Einlesen der Referenzdatei (NV_MASTER.ods)
+|-
+| odfpy || Ermöglicht Lesen von .ods-Dateien (für pandas.read_excel(..., engine="odf"))
+|-
+| spacy || Lemmatisierung (optional, aber empfohlen)
+|-
+| rapidfuzz || Schnelles Fuzzy-Matching (Alternativ zu difflib)
+|-
+| openpyxl || Wird benötigt, falls .xlsx genutzt wird
+|-
+| python-dateutil || Wird automatisch von pandas gebraucht
+|}
+

Wiki_Anleitungen/Digitalisierung_Workflow_141025.drawio

@@ -0,0 +1,622 @@
+<mxfile host="app.diagrams.net" agent="Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:143.0) Gecko/20100101 Firefox/143.0" version="28.2.5">
+  <diagram name="Page-1" id="aLmyRVYCle99qeRE2JvP">
+    <mxGraphModel dx="1301" dy="1900" grid="1" gridSize="10" guides="1" tooltips="1" connect="1" arrows="1" fold="1" page="1" pageScale="1" pageWidth="850" pageHeight="1100" math="0" shadow="0">
+      <root>
+        <mxCell id="0" />
+        <mxCell id="1" parent="0" />
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-3" value="" style="group" parent="1" vertex="1" connectable="0">
+          <mxGeometry x="85" y="932" width="310" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-2" value="Scan- und Erfassungsprozess" style="text;html=1;align=center;verticalAlign=middle;whiteSpace=wrap;rounded=0;" parent="WA2_J1DCvVjPXciXSW-M-3" vertex="1">
+          <mxGeometry x="60" y="-900" width="210" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-13" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=0;exitY=1;exitDx=0;exitDy=0;entryX=0.5;entryY=0;entryDx=0;entryDy=0;" parent="1" source="WA2_J1DCvVjPXciXSW-M-4" target="WA2_J1DCvVjPXciXSW-M-6" edge="1">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-14" value="Makro gibt Vorschläge aus NV zurück" style="edgeLabel;html=1;align=center;verticalAlign=middle;resizable=0;points=[];" parent="WA2_J1DCvVjPXciXSW-M-13" vertex="1" connectable="0">
+          <mxGeometry x="0.2678" y="-1" relative="1" as="geometry">
+            <mxPoint as="offset" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-4" value="&lt;div&gt;Makro (mapper_macro_2.x.py)&lt;/div&gt;" style="ellipse;whiteSpace=wrap;html=1;fillColor=#FFFF66;" parent="1" vertex="1">
+          <mxGeometry x="575" y="52" width="200" height="100" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-5" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=0.367;exitY=0.988;exitDx=0;exitDy=0;exitPerimeter=0;" parent="1" source="WA2_J1DCvVjPXciXSW-M-1" target="WA2_J1DCvVjPXciXSW-M-4" edge="1">
+          <mxGeometry relative="1" as="geometry">
+            <mxPoint x="405" y="97" as="sourcePoint" />
+            <Array as="points">
+              <mxPoint x="235" y="91" />
+              <mxPoint x="235" y="117" />
+            </Array>
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-12" value="Wird vom Makro gelesen und mit NV abgeglichen" style="edgeLabel;html=1;align=center;verticalAlign=middle;resizable=0;points=[];" parent="WA2_J1DCvVjPXciXSW-M-5" vertex="1" connectable="0">
+          <mxGeometry x="0.0228" y="4" relative="1" as="geometry">
+            <mxPoint as="offset" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-6" value="Anpassung der Erfassungstabelle anhand der Vorschläge" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#B3FF66;" parent="1" vertex="1">
+          <mxGeometry x="80" y="212" width="320" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-10" value="" style="endArrow=none;dashed=1;html=1;rounded=0;" parent="1" edge="1">
+          <mxGeometry width="50" height="50" relative="1" as="geometry">
+            <mxPoint x="515" y="972" as="sourcePoint" />
+            <mxPoint x="515" y="12" as="targetPoint" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-11" value="&lt;h1 style=&quot;margin-top: 0px;&quot;&gt;Workflow Digitalisierung -&lt;/h1&gt;&lt;h1 style=&quot;margin-top: 0px;&quot;&gt;&lt;u&gt;&lt;font style=&quot;font-size: 20px;&quot;&gt;Objekterfassung und Pflege des Normvokabulars&lt;/font&gt;&lt;/u&gt;&lt;/h1&gt;&lt;div&gt;&lt;font style=&quot;font-size: 14px;&quot;&gt;- Erfassung und Verschlagwortung von Bildobjekten&lt;/font&gt;&lt;/div&gt;&lt;div&gt;&lt;font style=&quot;font-size: 14px;&quot;&gt;- Abgleich mit internem Normvokabular&lt;/font&gt;&lt;/div&gt;&lt;div&gt;&lt;font style=&quot;font-size: 14px;&quot;&gt;- API-Abgleich mit getty und GND&lt;/font&gt;&lt;/div&gt;&lt;div&gt;&lt;font style=&quot;font-size: 14px;&quot;&gt;- Pflege und Erweiterung des Normvokabulars&lt;/font&gt;&lt;/div&gt;" style="text;html=1;whiteSpace=wrap;overflow=hidden;rounded=0;" parent="1" vertex="1">
+          <mxGeometry x="30" y="-1070" width="455" height="220" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-1" value="&lt;div&gt;Scan und Erfassen der Objekte, Erfassung in Tabellen, Spalte &quot;Objektbeschreibung&quot;&lt;/div&gt;" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#B3FF66;" parent="1" vertex="1">
+          <mxGeometry x="85" y="32" width="310" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-16" value="Makro 2 (Übernahme von Vorschlägen aus NV per Klick)" style="rounded=1;whiteSpace=wrap;html=1;fillColor=#FF6666;" parent="1" vertex="1">
+          <mxGeometry x="575" y="292" width="190" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-20" value="" style="html=1;shadow=0;dashed=0;align=center;verticalAlign=middle;shape=mxgraph.arrows2.arrow;dy=0.6;dx=40;notch=0;fillColor=#FF6666;" parent="1" vertex="1">
+          <mxGeometry x="460" y="312" width="90" height="20" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-23" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.071;entryY=0.25;entryDx=0;entryDy=0;entryPerimeter=0;exitX=0.5;exitY=1;exitDx=0;exitDy=0;dashed=1;" parent="1" edge="1">
+          <mxGeometry relative="1" as="geometry">
+            <mxPoint x="592.495" y="462" as="targetPoint" />
+            <mxPoint x="232.5700000000001" y="432" as="sourcePoint" />
+            <Array as="points">
+              <mxPoint x="233" y="462" />
+            </Array>
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-34" value="Gleiche Funktion wie Makro 1 + API-Abgleich" style="edgeLabel;html=1;align=center;verticalAlign=middle;resizable=0;points=[];" parent="WA2_J1DCvVjPXciXSW-M-23" vertex="1" connectable="0">
+          <mxGeometry x="-0.4298" relative="1" as="geometry">
+            <mxPoint x="53" as="offset" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="ey7EfLCcf-ExpX1qzLUj-15" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=0.25;exitY=1;exitDx=0;exitDy=0;" edge="1" parent="1" source="WA2_J1DCvVjPXciXSW-M-21">
+          <mxGeometry relative="1" as="geometry">
+            <mxPoint x="165.20000000000005" y="510" as="targetPoint" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-21" value="Bereinigte Erfassungstabelle" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#99CCFF;" parent="1" vertex="1">
+          <mxGeometry x="85" y="362" width="320" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-37" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.452;entryY=-0.007;entryDx=0;entryDy=0;entryPerimeter=0;dashed=1;" parent="1" source="WA2_J1DCvVjPXciXSW-M-24" target="WA2_J1DCvVjPXciXSW-M-33" edge="1">
+          <mxGeometry relative="1" as="geometry">
+            <Array as="points">
+              <mxPoint x="232" y="480" />
+            </Array>
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-60" value="gibt aus" style="edgeLabel;html=1;align=center;verticalAlign=middle;resizable=0;points=[];" parent="WA2_J1DCvVjPXciXSW-M-37" vertex="1" connectable="0">
+          <mxGeometry x="-0.0997" y="-1" relative="1" as="geometry">
+            <mxPoint as="offset" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-24" value="NormVokabular_Mapper.py" style="ellipse;whiteSpace=wrap;html=1;fillColor=#FFFF66;" parent="1" vertex="1">
+          <mxGeometry x="592.5" y="432" width="175" height="80" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-27" value="&lt;u&gt;&lt;b&gt;WHK/Manuell&lt;/b&gt;&lt;/u&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=0;points=[];autosize=1;strokeColor=none;fillColor=none;" parent="1" vertex="1">
+          <mxGeometry x="145" width="100" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-28" value="&lt;b&gt;&lt;u&gt;Programm/automatisiert&lt;/u&gt;&lt;/b&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=0;points=[];autosize=1;strokeColor=none;fillColor=none;" parent="1" vertex="1">
+          <mxGeometry x="590" width="160" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-29" value="&lt;div&gt;Mögliche Optimierung, funktioniert aber nicht in LO&lt;/div&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=0;points=[];autosize=1;strokeColor=none;fillColor=none;fontSize=8;" parent="1" vertex="1">
+          <mxGeometry x="570" y="362" width="200" height="20" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-32" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.484;entryY=0;entryDx=0;entryDy=0;entryPerimeter=0;" parent="1" source="WA2_J1DCvVjPXciXSW-M-6" target="WA2_J1DCvVjPXciXSW-M-21" edge="1">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="ey7EfLCcf-ExpX1qzLUj-17" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;" edge="1" parent="1" source="WA2_J1DCvVjPXciXSW-M-33">
+          <mxGeometry relative="1" as="geometry">
+            <mxPoint x="247.5" y="720" as="targetPoint" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-33" value="Bereinigte Erfassungstabelle" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#99CCFF;" parent="1" vertex="1">
+          <mxGeometry x="85" y="512" width="325" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-35" value="&lt;ul&gt;&lt;li&gt;Liest Spalte Objektbeschreibung aus, filtert Stopwords und Zahlen raus&lt;/li&gt;&lt;li&gt;Normalisierung, Lemmatisierung, Stemming der Wörter für höhere Trefferwahrscheinlichkeit&lt;/li&gt;&lt;li&gt;Liest das Normvokabular, Berücksichtigt ID-Hierarchie, erstellt Index für gestemmte Begriffe&lt;/li&gt;&lt;li&gt;Abgleich mit Normvokabular, generiert Vorschläge wenn kein Treffer vorliegt&lt;/li&gt;&lt;li&gt;API-Abgleich (aktuell GND und wikidata, Top1-Treffer)&lt;/li&gt;&lt;li&gt;Erstellt eine Auswertungsdatei, markiert Begriffe entsprechend ihres Status)&lt;/li&gt;&lt;/ul&gt;" style="text;strokeColor=none;fillColor=none;html=1;whiteSpace=wrap;verticalAlign=middle;overflow=hidden;fontSize=10;align=left;" parent="1" vertex="1">
+          <mxGeometry x="520" y="532" width="300" height="160" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-93" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=0.5;exitY=1;exitDx=0;exitDy=0;entryX=0.5;entryY=0;entryDx=0;entryDy=0;" parent="1" source="WA2_J1DCvVjPXciXSW-M-39" target="WA2_J1DCvVjPXciXSW-M-45" edge="1">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-39" value="Aufnahme ins Normvokabular oder Verwerfen des Begriffs" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#B3FF66;" parent="1" vertex="1">
+          <mxGeometry x="85" y="722" width="330" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-43" value="" style="endArrow=none;dashed=1;html=1;rounded=0;" parent="1" edge="1">
+          <mxGeometry width="50" height="50" relative="1" as="geometry">
+            <mxPoint x="515" y="1192" as="sourcePoint" />
+            <mxPoint x="515" y="962" as="targetPoint" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-94" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0;entryY=0.5;entryDx=0;entryDy=0;dashed=1;" parent="1" source="WA2_J1DCvVjPXciXSW-M-45" target="WA2_J1DCvVjPXciXSW-M-46" edge="1">
+          <mxGeometry relative="1" as="geometry">
+            <mxPoint x="615" y="832" as="targetPoint" />
+            <Array as="points">
+              <mxPoint x="475" y="822" />
+              <mxPoint x="475" y="822" />
+            </Array>
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="ey7EfLCcf-ExpX1qzLUj-16" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=0.25;exitY=1;exitDx=0;exitDy=0;" edge="1" parent="1" source="WA2_J1DCvVjPXciXSW-M-45">
+          <mxGeometry relative="1" as="geometry">
+            <mxPoint x="167.66666666666674" y="980" as="targetPoint" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-45" value="Manuelle Anpassung der Normvokabular-Masterfile" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#99CCFF;" parent="1" vertex="1">
+          <mxGeometry x="85" y="802" width="330" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-92" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;dashed=1;" parent="1" source="WA2_J1DCvVjPXciXSW-M-46" target="WA2_J1DCvVjPXciXSW-M-52" edge="1">
+          <mxGeometry relative="1" as="geometry">
+            <Array as="points">
+              <mxPoint x="695" y="912" />
+              <mxPoint x="198" y="912" />
+            </Array>
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-220" value="gibt aus" style="edgeLabel;html=1;align=center;verticalAlign=middle;resizable=0;points=[];" parent="WA2_J1DCvVjPXciXSW-M-92" vertex="1" connectable="0">
+          <mxGeometry x="0.3024" y="-2" relative="1" as="geometry">
+            <mxPoint as="offset" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-46" value="Masterfile_Editor.py" style="ellipse;whiteSpace=wrap;html=1;fillColor=#FFFF66;" parent="1" vertex="1">
+          <mxGeometry x="635" y="782" width="120" height="80" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-49" value="liest und bereinigt Normvokabular" style="text;html=1;align=center;verticalAlign=middle;resizable=0;points=[];autosize=1;strokeColor=none;fillColor=none;" parent="1" vertex="1">
+          <mxGeometry x="427.5" y="817" width="200" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-58" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.5;entryY=0;entryDx=0;entryDy=0;" parent="1" source="WA2_J1DCvVjPXciXSW-M-52" target="WA2_J1DCvVjPXciXSW-M-57" edge="1">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-221" value="" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;" parent="1" source="WA2_J1DCvVjPXciXSW-M-52" target="WA2_J1DCvVjPXciXSW-M-57" edge="1">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-222" value="=" style="edgeLabel;html=1;align=center;verticalAlign=middle;resizable=0;points=[];" parent="WA2_J1DCvVjPXciXSW-M-221" vertex="1" connectable="0">
+          <mxGeometry x="-0.3079" y="1" relative="1" as="geometry">
+            <mxPoint as="offset" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-52" value="Aktualisierte Masterfile, mit allen Änderungen und in der richtigen Struktur" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#99CCFF;" parent="1" vertex="1">
+          <mxGeometry x="85" y="980" width="225" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-59" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=0;exitY=0.5;exitDx=0;exitDy=0;" parent="1" source="WA2_J1DCvVjPXciXSW-M-57" edge="1">
+          <mxGeometry relative="1" as="geometry">
+            <mxPoint x="70" y="242" as="targetPoint" />
+            <Array as="points">
+              <mxPoint x="40" y="1130" />
+              <mxPoint x="40" y="242" />
+            </Array>
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-57" value="Masterfile Normvokabular Updated" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#99CCFF;" parent="1" vertex="1">
+          <mxGeometry x="117.5" y="1100" width="160" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-64" value="" style="html=1;shadow=0;dashed=0;align=center;verticalAlign=middle;shape=mxgraph.arrows2.arrow;dy=0.6;dx=40;notch=0;fillColor=#FF6666;" parent="1" vertex="1">
+          <mxGeometry x="410" y="1107.5" width="90" height="20" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-200" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=0.5;exitY=1;exitDx=0;exitDy=0;" parent="1" source="WA2_J1DCvVjPXciXSW-M-65" edge="1">
+          <mxGeometry relative="1" as="geometry">
+            <mxPoint x="40" y="1140" as="targetPoint" />
+            <Array as="points">
+              <mxPoint x="680" y="1180" />
+              <mxPoint x="40" y="1180" />
+            </Array>
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-65" value="&lt;div&gt;Normvokabular-Masterfile muss&amp;nbsp;&lt;/div&gt;&lt;div&gt;&lt;b&gt;zentral&lt;/b&gt; als &lt;b&gt;SPOT&lt;/b&gt; vorliegen und gepflegt werden können&lt;/div&gt;" style="ellipse;whiteSpace=wrap;html=1;fillColor=#FF6666;" parent="1" vertex="1">
+          <mxGeometry x="575" y="1075" width="210" height="85" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-66" value="" style="whiteSpace=wrap;html=1;aspect=fixed;fillColor=#99CCFF;" parent="1" vertex="1">
+          <mxGeometry x="485" y="-1046" width="20" height="20" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-67" value="" style="whiteSpace=wrap;html=1;aspect=fixed;fillColor=#FF6666;" parent="1" vertex="1">
+          <mxGeometry x="485" y="-1006" width="20" height="20" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-68" value="" style="whiteSpace=wrap;html=1;aspect=fixed;fillColor=#B3FF66;" parent="1" vertex="1">
+          <mxGeometry x="485" y="-966" width="20" height="20" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-69" value="" style="whiteSpace=wrap;html=1;aspect=fixed;fillColor=#FFFF66;" parent="1" vertex="1">
+          <mxGeometry x="485" y="-926" width="20" height="20" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-70" value="&lt;b&gt;Datei&lt;/b&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=0;points=[];autosize=1;strokeColor=none;fillColor=none;" parent="1" vertex="1">
+          <mxGeometry x="518" y="-1050" width="50" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-71" value="&lt;b&gt;Fehlender Schritt/Optimierungsmöglichkeit&lt;/b&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=0;points=[];autosize=1;strokeColor=none;fillColor=none;" parent="1" vertex="1">
+          <mxGeometry x="510" y="-1011" width="270" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-72" value="&lt;b&gt;Vorgang, WHK&lt;/b&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=0;points=[];autosize=1;strokeColor=none;fillColor=none;" parent="1" vertex="1">
+          <mxGeometry x="515" y="-971" width="110" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-73" value="&lt;b&gt;Programm&lt;/b&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=0;points=[];autosize=1;strokeColor=none;fillColor=none;" parent="1" vertex="1">
+          <mxGeometry x="520" y="-931" width="80" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-74" value="" style="endArrow=none;html=1;rounded=0;" parent="1" edge="1">
+          <mxGeometry width="50" height="50" relative="1" as="geometry">
+            <mxPoint x="35" y="-850" as="sourcePoint" />
+            <mxPoint x="805" y="-850" as="targetPoint" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-75" value="&lt;div align=&quot;left&quot;&gt;&lt;font style=&quot;font-size: 13px;&quot;&gt;&lt;b&gt;&lt;u&gt;&lt;font&gt;Probleme/Noch zu klären:&lt;/font&gt;&lt;/u&gt;&lt;/b&gt;&lt;/font&gt;&lt;ul&gt;&lt;li&gt;&lt;font style=&quot;font-size: 13px;&quot;&gt;&lt;b&gt;Makro 1 und NormVokabular-Mapper&lt;/b&gt; redundant, eine Methode festlegen (Makro benutzerfreundlicher, Treffer/Vorschläge direkt in Erfassung sichtbar, Mapper genauer, API-Abgleich, Auswertungsdatei übersichtlicher)&lt;/font&gt;&lt;/li&gt;&lt;li&gt;&lt;font style=&quot;font-size: 13px;&quot;&gt;&lt;b&gt;Makro 2&lt;/b&gt; (Vorschläge aus Normvokabular können automatisch per Klick in die Erfassungstabelle übernommen werden)&lt;/font&gt;&lt;/li&gt;&lt;li&gt;&lt;font style=&quot;font-size: 13px;&quot;&gt;&lt;b&gt;Normvokabular&lt;/b&gt;: Eine zentrale .json als SPOT etablieren und zentral in alle Prozesse einbinden&lt;/font&gt;&lt;/li&gt;&lt;li&gt;&lt;font style=&quot;font-size: 13px;&quot;&gt;&lt;b&gt;Mapper&lt;/b&gt;&amp;nbsp;oder &lt;b&gt;Makro&lt;/b&gt; benötigt Funktion, Wörter ohne Treffer und Vorschlag in &lt;br&gt;eigene Liste zu übernehmen und auszugeben -&amp;gt; manuelle Prüfung&lt;/font&gt;&lt;/li&gt;&lt;li&gt;&lt;font style=&quot;font-size: 13px;&quot;&gt;&lt;b&gt;Normvokabular&lt;/b&gt;: Regeln, ID-Struktur, Kategorien müssen auf Qualität und Nutzbarkeit geprüft werden; danach Anpassung aller Programme, die sich auf Normvokabular stützen&lt;/font&gt;&lt;/li&gt;&lt;/ul&gt;&lt;font style=&quot;font-size: 13px;&quot;&gt;&lt;br&gt;&lt;/font&gt;&lt;/div&gt;" style="rounded=0;whiteSpace=wrap;html=1;align=left;spacing=2;spacingRight=0;" parent="1" vertex="1">
+          <mxGeometry x="40" y="1232" width="770" height="190" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-80" value="&lt;ul&gt;&lt;li&gt;Liest Spalte Objektbeschreibung aus, filtert Stopwords und Zahlen raus&lt;/li&gt;&lt;li&gt;Normalisierung, Lemmatisierung, Stemming der Wörter für höhere Trefferwahrscheinlichkeit&lt;/li&gt;&lt;li&gt;Liest das Normvokabular, Berücksichtigt ID-Hierarchie, erstellt Index für gestemmte Begriffe, cache und log&lt;/li&gt;&lt;li&gt;Abgleich mit Normvokabular, generiert Vorschläge wenn kein Treffer vorliegt&lt;/li&gt;&lt;li&gt;Markiert Treffer, Vorschläge und Keine Treffer&lt;/li&gt;&lt;/ul&gt;" style="text;strokeColor=none;fillColor=none;html=1;whiteSpace=wrap;verticalAlign=middle;overflow=hidden;fontSize=10;align=left;" parent="1" vertex="1">
+          <mxGeometry x="525" y="132" width="300" height="160" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-81" value="" style="endArrow=none;dashed=1;html=1;dashPattern=1 3;strokeWidth=2;rounded=0;" parent="1" edge="1">
+          <mxGeometry width="50" height="50" relative="1" as="geometry">
+            <mxPoint x="245" y="322" as="sourcePoint" />
+            <mxPoint x="455" y="322" as="targetPoint" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-83" value="" style="endArrow=none;dashed=1;html=1;dashPattern=1 3;strokeWidth=2;rounded=0;entryX=0.055;entryY=0.48;entryDx=0;entryDy=0;entryPerimeter=0;" parent="1" target="WA2_J1DCvVjPXciXSW-M-64" edge="1">
+          <mxGeometry width="50" height="50" relative="1" as="geometry">
+            <mxPoint x="281" y="1117" as="sourcePoint" />
+            <mxPoint x="365" y="1002" as="targetPoint" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-91" value="&lt;ul&gt;&lt;li&gt;Automatische Spaltenerkennung (ID, Name/Wort/Vokabel)&lt;/li&gt;&lt;li&gt;Aufbau einer hierarchischen Struktur (Ober-, Unter-, Unterunterkategorien)&lt;/li&gt;&lt;li&gt;Erstellung eines Mastersheets mit eindeutigen IDs&lt;/li&gt;&lt;li&gt;Sortierte Ausgabe nach vordefinierter Sheet-Reihenfolge&lt;/li&gt;&lt;li&gt;Protokollierung im Terminal (Zeilenanzahl, Warnungen, ID-Zählung)&lt;/li&gt;&lt;li&gt;Speicherung einer neuen, synchronisierten Output-Datei ohne Änderung der Originaldatei&lt;/li&gt;&lt;/ul&gt;" style="text;strokeColor=none;fillColor=none;html=1;whiteSpace=wrap;verticalAlign=middle;overflow=hidden;fontSize=10;" parent="1" vertex="1">
+          <mxGeometry x="510" y="902" width="310" height="160" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-96" value="" style="endArrow=none;html=1;rounded=0;" parent="1" edge="1">
+          <mxGeometry width="50" height="50" relative="1" as="geometry">
+            <mxPoint x="15" y="1460" as="sourcePoint" />
+            <mxPoint x="815" y="1460" as="targetPoint" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-192" value="&lt;font style=&quot;font-size: 19px;&quot;&gt;&lt;b&gt;&lt;u&gt;3. Aktuelle Struktur des Normvokabulars (Stand 10/25)&lt;/u&gt;&lt;/b&gt;&lt;/font&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=0;points=[];autosize=1;strokeColor=none;fillColor=none;" parent="1" vertex="1">
+          <mxGeometry x="35" y="1480" width="510" height="40" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-195" value="" style="group" parent="1" vertex="1" connectable="0">
+          <mxGeometry x="90" y="1740" width="580" height="380" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-97" value="Assets" style="childLayout=tableLayout;recursiveResize=0;strokeColor=#98bf21;fillColor=#A7C942;shadow=1;" parent="WA2_J1DCvVjPXciXSW-M-195" vertex="1">
+          <mxGeometry x="50" y="40" width="550" height="330" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-98" style="shape=tableRow;horizontal=0;startSize=0;swimlaneHead=0;swimlaneBody=0;top=0;left=0;bottom=0;right=0;dropTarget=0;collapsible=0;recursiveResize=0;expand=0;fontStyle=0;strokeColor=inherit;fillColor=#ffffff;" parent="WA2_J1DCvVjPXciXSW-M-97" vertex="1">
+          <mxGeometry width="550" height="43" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-99" value="ID" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#A7C942;align=center;fontStyle=1;fontColor=#FFFFFF;html=1;" parent="WA2_J1DCvVjPXciXSW-M-98" vertex="1">
+          <mxGeometry width="117" height="43" as="geometry">
+            <mxRectangle width="117" height="43" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-100" value="Unterkategorie" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#A7C942;align=center;fontStyle=1;fontColor=#FFFFFF;html=1;" parent="WA2_J1DCvVjPXciXSW-M-98" vertex="1">
+          <mxGeometry x="117" width="159" height="43" as="geometry">
+            <mxRectangle width="159" height="43" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-101" value="Unterunterkategorie" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#A7C942;align=center;fontStyle=1;fontColor=#FFFFFF;html=1;" parent="WA2_J1DCvVjPXciXSW-M-98" vertex="1">
+          <mxGeometry x="276" width="137" height="43" as="geometry">
+            <mxRectangle width="137" height="43" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-165" value="Wort/Vokabel" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#A7C942;align=center;fontStyle=1;fontColor=#FFFFFF;html=1;" parent="WA2_J1DCvVjPXciXSW-M-98" vertex="1">
+          <mxGeometry x="413" width="137" height="43" as="geometry">
+            <mxRectangle width="137" height="43" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-102" value="" style="shape=tableRow;horizontal=0;startSize=0;swimlaneHead=0;swimlaneBody=0;top=0;left=0;bottom=0;right=0;dropTarget=0;collapsible=0;recursiveResize=0;expand=0;fontStyle=0;strokeColor=inherit;fillColor=#ffffff;" parent="WA2_J1DCvVjPXciXSW-M-97" vertex="1">
+          <mxGeometry y="43" width="550" height="42" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-103" value="7.1.1" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;align=center;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-102" vertex="1">
+          <mxGeometry width="117" height="42" as="geometry">
+            <mxRectangle width="117" height="42" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-104" value="Außenarchitektur" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;align=center;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-102" vertex="1">
+          <mxGeometry x="117" width="159" height="42" as="geometry">
+            <mxRectangle width="159" height="42" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-105" value="Außenarchitektur allgemein" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;align=center;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-102" vertex="1">
+          <mxGeometry x="276" width="137" height="42" as="geometry">
+            <mxRectangle width="137" height="42" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-166" value="Außenarchitektur allgemein" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;align=center;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-102" vertex="1">
+          <mxGeometry x="413" width="137" height="42" as="geometry">
+            <mxRectangle width="137" height="42" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-187" style="shape=tableRow;horizontal=0;startSize=0;swimlaneHead=0;swimlaneBody=0;top=0;left=0;bottom=0;right=0;dropTarget=0;collapsible=0;recursiveResize=0;expand=0;fontStyle=0;strokeColor=inherit;fillColor=#ffffff;" parent="WA2_J1DCvVjPXciXSW-M-97" vertex="1">
+          <mxGeometry y="85" width="550" height="41" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-188" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=inherit;align=center;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-187" vertex="1">
+          <mxGeometry width="117" height="41" as="geometry">
+            <mxRectangle width="117" height="41" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-189" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=inherit;align=center;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-187" vertex="1">
+          <mxGeometry x="117" width="159" height="41" as="geometry">
+            <mxRectangle width="159" height="41" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-190" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=inherit;align=center;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-187" vertex="1">
+          <mxGeometry x="276" width="137" height="41" as="geometry">
+            <mxRectangle width="137" height="41" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-191" value="Hof" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=inherit;align=center;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-187" vertex="1">
+          <mxGeometry x="413" width="137" height="41" as="geometry">
+            <mxRectangle width="137" height="41" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-106" value="" style="shape=tableRow;horizontal=0;startSize=0;swimlaneHead=0;swimlaneBody=0;top=0;left=0;bottom=0;right=0;dropTarget=0;collapsible=0;recursiveResize=0;expand=0;fontStyle=1;strokeColor=inherit;fillColor=#EAF2D3;" parent="WA2_J1DCvVjPXciXSW-M-97" vertex="1">
+          <mxGeometry y="126" width="550" height="41" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-107" value="7.1.2" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-106" vertex="1">
+          <mxGeometry width="117" height="41" as="geometry">
+            <mxRectangle width="117" height="41" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-108" value="Außenarchitektur" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-106" vertex="1">
+          <mxGeometry x="117" width="159" height="41" as="geometry">
+            <mxRectangle width="159" height="41" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-109" value="Gebäudetypen" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-106" vertex="1">
+          <mxGeometry x="276" width="137" height="41" as="geometry">
+            <mxRectangle width="137" height="41" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-167" value="Gebäudetypen" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-106" vertex="1">
+          <mxGeometry x="413" width="137" height="41" as="geometry">
+            <mxRectangle width="137" height="41" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-110" value="" style="shape=tableRow;horizontal=0;startSize=0;swimlaneHead=0;swimlaneBody=0;top=0;left=0;bottom=0;right=0;dropTarget=0;collapsible=0;recursiveResize=0;expand=0;fontStyle=0;strokeColor=inherit;fillColor=#ffffff;" parent="WA2_J1DCvVjPXciXSW-M-97" vertex="1">
+          <mxGeometry y="167" width="550" height="44" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-111" value="" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=inherit;fontStyle=0;align=center;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-110" vertex="1">
+          <mxGeometry width="117" height="44" as="geometry">
+            <mxRectangle width="117" height="44" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-112" value="" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=inherit;fontStyle=0;align=center;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-110" vertex="1">
+          <mxGeometry x="117" width="159" height="44" as="geometry">
+            <mxRectangle width="159" height="44" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-113" value="" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=inherit;fontStyle=0;align=center;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-110" vertex="1">
+          <mxGeometry x="276" width="137" height="44" as="geometry">
+            <mxRectangle width="137" height="44" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-168" value="Haus" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=inherit;fontStyle=0;align=center;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-110" vertex="1">
+          <mxGeometry x="413" width="137" height="44" as="geometry">
+            <mxRectangle width="137" height="44" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-114" value="" style="shape=tableRow;horizontal=0;startSize=0;swimlaneHead=0;swimlaneBody=0;top=0;left=0;bottom=0;right=0;dropTarget=0;collapsible=0;recursiveResize=0;expand=0;fontStyle=1;strokeColor=inherit;fillColor=#EAF2D3;" parent="WA2_J1DCvVjPXciXSW-M-97" vertex="1">
+          <mxGeometry y="211" width="550" height="39" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-115" value="7.2" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-114" vertex="1">
+          <mxGeometry width="117" height="39" as="geometry">
+            <mxRectangle width="117" height="39" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-116" value="Innenarchitektur" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-114" vertex="1">
+          <mxGeometry x="117" width="159" height="39" as="geometry">
+            <mxRectangle width="159" height="39" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-117" value="" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-114" vertex="1">
+          <mxGeometry x="276" width="137" height="39" as="geometry">
+            <mxRectangle width="137" height="39" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-169" value="Innenarchitektur" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-114" vertex="1">
+          <mxGeometry x="413" width="137" height="39" as="geometry">
+            <mxRectangle width="137" height="39" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-175" style="shape=tableRow;horizontal=0;startSize=0;swimlaneHead=0;swimlaneBody=0;top=0;left=0;bottom=0;right=0;dropTarget=0;collapsible=0;recursiveResize=0;expand=0;fontStyle=1;strokeColor=inherit;fillColor=#FFFFFF;" parent="WA2_J1DCvVjPXciXSW-M-97" vertex="1">
+          <mxGeometry y="250" width="550" height="40" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-176" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=inherit;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-175" vertex="1">
+          <mxGeometry width="117" height="40" as="geometry">
+            <mxRectangle width="117" height="40" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-177" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=inherit;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-175" vertex="1">
+          <mxGeometry x="117" width="159" height="40" as="geometry">
+            <mxRectangle width="159" height="40" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-178" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=inherit;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-175" vertex="1">
+          <mxGeometry x="276" width="137" height="40" as="geometry">
+            <mxRectangle width="137" height="40" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-179" value="Zimmer" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=inherit;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-175" vertex="1">
+          <mxGeometry x="413" width="137" height="40" as="geometry">
+            <mxRectangle width="137" height="40" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-170" style="shape=tableRow;horizontal=0;startSize=0;swimlaneHead=0;swimlaneBody=0;top=0;left=0;bottom=0;right=0;dropTarget=0;collapsible=0;recursiveResize=0;expand=0;fontStyle=1;strokeColor=inherit;fillColor=#EAF2D3;" parent="WA2_J1DCvVjPXciXSW-M-97" vertex="1">
+          <mxGeometry y="290" width="550" height="40" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-171" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-170" vertex="1">
+          <mxGeometry width="117" height="40" as="geometry">
+            <mxRectangle width="117" height="40" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-172" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-170" vertex="1">
+          <mxGeometry x="117" width="159" height="40" as="geometry">
+            <mxRectangle width="159" height="40" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-173" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-170" vertex="1">
+          <mxGeometry x="276" width="137" height="40" as="geometry">
+            <mxRectangle width="137" height="40" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-174" value="Fußboden" style="connectable=0;recursiveResize=0;strokeColor=inherit;fillColor=#E6FFCC;whiteSpace=wrap;html=1;" parent="WA2_J1DCvVjPXciXSW-M-170" vertex="1">
+          <mxGeometry x="413" width="137" height="40" as="geometry">
+            <mxRectangle width="137" height="40" as="alternateBounds" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-323" value="&lt;b&gt;&lt;u&gt;b) Beispiel&lt;/u&gt;&lt;/b&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=0;points=[];autosize=1;strokeColor=none;fillColor=none;" parent="WA2_J1DCvVjPXciXSW-M-195" vertex="1">
+          <mxGeometry x="-30" width="80" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-197" value="" style="endArrow=none;html=1;rounded=0;" parent="1" edge="1">
+          <mxGeometry width="50" height="50" relative="1" as="geometry">
+            <mxPoint x="45" y="-110" as="sourcePoint" />
+            <mxPoint x="815" y="-110" as="targetPoint" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-198" value="&lt;font style=&quot;font-size: 21px;&quot;&gt;&lt;b&gt;&lt;u&gt;2. Normvokabular-Abgleich&lt;/u&gt;&lt;/b&gt;&lt;/font&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=0;points=[];autosize=1;strokeColor=none;fillColor=none;" parent="1" vertex="1">
+          <mxGeometry x="45" y="-70" width="290" height="40" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-199" value="" style="endArrow=none;dashed=1;html=1;dashPattern=1 3;strokeWidth=2;rounded=0;entryX=0;entryY=0.5;entryDx=0;entryDy=0;exitX=1;exitY=0.5;exitDx=0;exitDy=0;exitPerimeter=0;" parent="1" source="WA2_J1DCvVjPXciXSW-M-64" target="WA2_J1DCvVjPXciXSW-M-65" edge="1">
+          <mxGeometry width="50" height="50" relative="1" as="geometry">
+            <mxPoint x="440" y="1110" as="sourcePoint" />
+            <mxPoint x="534" y="1110" as="targetPoint" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-202" value="Scanvorgang" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#B3FF66;" parent="1" vertex="1">
+          <mxGeometry x="70" y="-670" width="200" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-203" value="Erfassen" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#B3FF66;" parent="1" vertex="1">
+          <mxGeometry x="240" y="-400" width="200" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-207" value="Ebenenstruktur festlegen" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#B3FF66;" parent="1" vertex="1">
+          <mxGeometry x="180" y="-490" width="200" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-209" value="Erfassungstabelle" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#99CCFF;" parent="1" vertex="1">
+          <mxGeometry x="370" y="-200" width="247.5" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-210" value="&lt;ul&gt;&lt;li&gt;Durchgehen einer Box von vorne bis hinten&lt;/li&gt;&lt;li&gt;Auflegen des Objekts, Ausrichtung der Farbkarte&lt;/li&gt;&lt;li&gt;Manuelles Festlegen des Scanbereichs&lt;/li&gt;&lt;li&gt;Scan der gesamten Box&lt;/li&gt;&lt;/ul&gt;" style="text;strokeColor=none;fillColor=none;html=1;whiteSpace=wrap;verticalAlign=middle;overflow=hidden;" parent="1" vertex="1">
+          <mxGeometry x="255" y="-690" width="320" height="80" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-211" value="&lt;ul&gt;&lt;li&gt;Durchgehen der exportierten Scans im Bildviewer&lt;/li&gt;&lt;li&gt;Festlegung der Scanebenen (Umschlag, Vorderseite, Rückseite, etc.)&lt;/li&gt;&lt;/ul&gt;" style="text;strokeColor=none;fillColor=none;html=1;whiteSpace=wrap;verticalAlign=middle;overflow=hidden;" parent="1" vertex="1">
+          <mxGeometry x="367.5" y="-500" width="320" height="80" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-212" value="&lt;ul&gt;&lt;li&gt;Durchgehen der Scans&lt;/li&gt;&lt;li&gt;Erfassen: Datum, Urheber, Eigner, Material&lt;/li&gt;&lt;li&gt;Vermessen des Objekts&lt;/li&gt;&lt;li&gt;Objektbeschreibung: Verschlagwortung des Bildinhalts&lt;/li&gt;&lt;li&gt;Erfassen etwaiger Inschriften und Anmerkungen&lt;/li&gt;&lt;/ul&gt;" style="text;strokeColor=none;fillColor=none;html=1;whiteSpace=wrap;verticalAlign=middle;overflow=hidden;" parent="1" vertex="1">
+          <mxGeometry x="438" y="-440" width="300" height="140" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-216" value="&lt;font style=&quot;font-size: 21px;&quot;&gt;&lt;b&gt;&lt;u&gt;1. Ablauf des Scan- und Erfassungsprozesses&lt;/u&gt;&lt;/b&gt;&lt;/font&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=0;points=[];autosize=1;strokeColor=none;fillColor=none;" parent="1" vertex="1">
+          <mxGeometry x="35" y="-840" width="490" height="40" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-217" value="Vorbereitung" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#B3FF66;" parent="1" vertex="1">
+          <mxGeometry x="30" y="-760" width="200" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-218" value="&lt;ul&gt;&lt;li&gt;PC hochfahren&lt;/li&gt;&lt;li&gt;Scanner starten/Kamera und Beleuchtung vorbereiten, Farbkarte platzieren&lt;/li&gt;&lt;li&gt;Software starten, Scanauftrag wählen&lt;/li&gt;&lt;li&gt;Erfassungstabelle öffnen&lt;/li&gt;&lt;li&gt;Passende Box wählen&lt;/li&gt;&lt;/ul&gt;" style="text;strokeColor=none;fillColor=none;html=1;whiteSpace=wrap;verticalAlign=middle;overflow=hidden;" parent="1" vertex="1">
+          <mxGeometry x="212.5" y="-790" width="555" height="110" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-236" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=0.25;exitY=1;exitDx=0;exitDy=0;entryX=0;entryY=0.5;entryDx=0;entryDy=0;" parent="1" source="WA2_J1DCvVjPXciXSW-M-226" target="WA2_J1DCvVjPXciXSW-M-228" edge="1">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-318" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=1;exitY=0.5;exitDx=0;exitDy=0;" parent="1" source="WA2_J1DCvVjPXciXSW-M-226" edge="1">
+          <mxGeometry relative="1" as="geometry">
+            <mxPoint x="350" y="1573" as="targetPoint" />
+            <Array as="points">
+              <mxPoint x="340" y="1573" />
+              <mxPoint x="360" y="1573" />
+            </Array>
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-226" value="Kategorie" style="rounded=0;whiteSpace=wrap;html=1;" parent="1" vertex="1">
+          <mxGeometry x="170" y="1562.5" width="150" height="20" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-237" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=0.25;exitY=1;exitDx=0;exitDy=0;entryX=0;entryY=0.5;entryDx=0;entryDy=0;" parent="1" source="WA2_J1DCvVjPXciXSW-M-228" target="WA2_J1DCvVjPXciXSW-M-229" edge="1">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-228" value="Unterkategorie" style="rounded=0;whiteSpace=wrap;html=1;" parent="1" vertex="1">
+          <mxGeometry x="290" y="1605" width="150" height="20" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-238" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=0.232;exitY=1.005;exitDx=0;exitDy=0;entryX=0;entryY=0.5;entryDx=0;entryDy=0;exitPerimeter=0;" parent="1" source="WA2_J1DCvVjPXciXSW-M-229" target="WA2_J1DCvVjPXciXSW-M-230" edge="1">
+          <mxGeometry relative="1" as="geometry">
+            <mxPoint x="407.5" y="1652.5" as="sourcePoint" />
+            <mxPoint x="440" y="1687.5" as="targetPoint" />
+            <Array as="points">
+              <mxPoint x="440" y="1700" />
+            </Array>
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-320" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=1;exitY=0.5;exitDx=0;exitDy=0;" parent="1" source="WA2_J1DCvVjPXciXSW-M-229" edge="1">
+          <mxGeometry relative="1" as="geometry">
+            <mxPoint x="590" y="1660" as="targetPoint" />
+            <Array as="points">
+              <mxPoint x="580" y="1660" />
+              <mxPoint x="580" y="1660" />
+            </Array>
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-229" value="Unterunterkategorie" style="rounded=0;whiteSpace=wrap;html=1;" parent="1" vertex="1">
+          <mxGeometry x="405" y="1650" width="150" height="20" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-230" value="Wort/Vokabel" style="rounded=0;whiteSpace=wrap;html=1;" parent="1" vertex="1">
+          <mxGeometry x="513" y="1690" width="150" height="20" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-313" value="&lt;font style=&quot;font-size: 10px;&quot;&gt;1&lt;/font&gt;" style="ellipse;whiteSpace=wrap;html=1;rounded=0;" parent="1" vertex="1">
+          <mxGeometry x="352.5" y="1560" width="25" height="25" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-315" value="&lt;font style=&quot;font-size: 10px;&quot;&gt;1.1&lt;/font&gt;" style="ellipse;whiteSpace=wrap;html=1;rounded=0;" parent="1" vertex="1">
+          <mxGeometry x="475" y="1602.5" width="25" height="25" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-316" value="&lt;font style=&quot;font-size: 10px;&quot;&gt;1.1.1&lt;/font&gt;" style="ellipse;whiteSpace=wrap;html=1;rounded=0;" parent="1" vertex="1">
+          <mxGeometry x="592.5" y="1647.5" width="25" height="25" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-319" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=1;exitY=0.5;exitDx=0;exitDy=0;" parent="1" source="WA2_J1DCvVjPXciXSW-M-228" edge="1">
+          <mxGeometry relative="1" as="geometry">
+            <mxPoint x="470" y="1615" as="targetPoint" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-321" value="" style="endArrow=none;dashed=1;html=1;dashPattern=1 3;strokeWidth=2;rounded=0;" parent="1" edge="1">
+          <mxGeometry width="50" height="50" relative="1" as="geometry">
+            <mxPoint x="50" y="1740" as="sourcePoint" />
+            <mxPoint x="800" y="1740" as="targetPoint" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-322" value="&lt;b&gt;&lt;u&gt;a) Hierarchie und ID-Struktur&lt;/u&gt;&lt;/b&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=0;points=[];autosize=1;strokeColor=none;fillColor=none;" parent="1" vertex="1">
+          <mxGeometry x="40" y="1530" width="190" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="WA2_J1DCvVjPXciXSW-M-193" value="Blatt 7 - Architektur" style="rounded=0;whiteSpace=wrap;html=1;" parent="1" vertex="1">
+          <mxGeometry x="140" y="2110" width="165" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="B-3lv8s0GtbLfT8x5DVe-1" value="Scan exportieren" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#B3FF66;" parent="1" vertex="1">
+          <mxGeometry x="122.5" y="-580" width="200" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="B-3lv8s0GtbLfT8x5DVe-2" value="&lt;ul&gt;&lt;li&gt;Export der gesamten Scans einer Box in einen Ordner&lt;/li&gt;&lt;li&gt;Reihenfolge der Scans checken&lt;/li&gt;&lt;/ul&gt;" style="text;strokeColor=none;fillColor=none;html=1;whiteSpace=wrap;verticalAlign=middle;overflow=hidden;" parent="1" vertex="1">
+          <mxGeometry x="307.5" y="-590" width="320" height="80" as="geometry" />
+        </mxCell>
+        <mxCell id="ey7EfLCcf-ExpX1qzLUj-1" value="Erfassung prüfen" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#B3FF66;" vertex="1" parent="1">
+          <mxGeometry x="310" y="-300" width="200" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="ey7EfLCcf-ExpX1qzLUj-2" value="&lt;ul&gt;&lt;li&gt;Durchgehen der Scans, Vergleich der Nummern mit dem Inhalt der Erfassung&lt;/li&gt;&lt;li&gt;Makro laufen lassen: Prüft Begriffe unter &quot;Objektbschreibung&quot; auf Treffer im Normvokabular (siehe Anleitung)&lt;/li&gt;&lt;/ul&gt;" style="text;strokeColor=none;fillColor=none;html=1;whiteSpace=wrap;verticalAlign=middle;overflow=hidden;" vertex="1" parent="1">
+          <mxGeometry x="490" y="-310" width="320" height="90" as="geometry" />
+        </mxCell>
+        <mxCell id="ey7EfLCcf-ExpX1qzLUj-3" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.3;entryY=0;entryDx=0;entryDy=0;entryPerimeter=0;" edge="1" parent="1" source="WA2_J1DCvVjPXciXSW-M-217" target="WA2_J1DCvVjPXciXSW-M-202">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="ey7EfLCcf-ExpX1qzLUj-4" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.238;entryY=0;entryDx=0;entryDy=0;entryPerimeter=0;" edge="1" parent="1" source="WA2_J1DCvVjPXciXSW-M-202" target="B-3lv8s0GtbLfT8x5DVe-1">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="ey7EfLCcf-ExpX1qzLUj-6" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.213;entryY=0;entryDx=0;entryDy=0;entryPerimeter=0;" edge="1" parent="1" source="B-3lv8s0GtbLfT8x5DVe-1" target="WA2_J1DCvVjPXciXSW-M-207">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="ey7EfLCcf-ExpX1qzLUj-7" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.2;entryY=0;entryDx=0;entryDy=0;entryPerimeter=0;" edge="1" parent="1" source="WA2_J1DCvVjPXciXSW-M-207" target="WA2_J1DCvVjPXciXSW-M-203">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="ey7EfLCcf-ExpX1qzLUj-8" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;exitX=0.5;exitY=1;exitDx=0;exitDy=0;entryX=0.148;entryY=-0.056;entryDx=0;entryDy=0;entryPerimeter=0;" edge="1" parent="1" source="WA2_J1DCvVjPXciXSW-M-203" target="ey7EfLCcf-ExpX1qzLUj-1">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="ey7EfLCcf-ExpX1qzLUj-10" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.161;entryY=-0.039;entryDx=0;entryDy=0;entryPerimeter=0;" edge="1" parent="1" source="ey7EfLCcf-ExpX1qzLUj-1" target="WA2_J1DCvVjPXciXSW-M-209">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="ey7EfLCcf-ExpX1qzLUj-11" value="&lt;font style=&quot;font-size: 15px;&quot;&gt;&lt;b&gt;Stand: 14.10.25&lt;/b&gt;&lt;/font&gt;" style="text;html=1;align=center;verticalAlign=middle;whiteSpace=wrap;rounded=0;" vertex="1" parent="1">
+          <mxGeometry x="745" y="-1090" width="105" height="50" as="geometry" />
+        </mxCell>
+        <mxCell id="ey7EfLCcf-ExpX1qzLUj-12" value="" style="endArrow=none;dashed=1;html=1;dashPattern=1 3;strokeWidth=2;rounded=0;" edge="1" parent="1">
+          <mxGeometry width="50" height="50" relative="1" as="geometry">
+            <mxPoint x="470" y="-880" as="sourcePoint" />
+            <mxPoint x="520" y="-880" as="targetPoint" />
+          </mxGeometry>
+        </mxCell>
+        <mxCell id="ey7EfLCcf-ExpX1qzLUj-13" value="&lt;b&gt;Optional/Optimierungsmöglichkeit&lt;/b&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=0;points=[];autosize=1;strokeColor=none;fillColor=none;" vertex="1" parent="1">
+          <mxGeometry x="530" y="-896" width="220" height="30" as="geometry" />
+        </mxCell>
+      </root>
+    </mxGraphModel>
+  </diagram>
+</mxfile>

Wiki_Anleitungen/ExLibris_Scannen_und_Erfassen_Leitfaden_wikimarkup

@@ -0,0 +1,97 @@
+= ExLibris Scannen und Erfassen – Leitfaden =
+
+Die Digitalisierung von Exlibris-Objekten ist in zwei Hauptschritte gegliedert: **Scannen** und **Erfassen** der Objekte.  
+Jedes Objekt ist Teil einer Box, jede Box ist Teil eines Oktavs (°).  
+Eine Box wird vollständig gescannt, bevor die Erfassung beginnt – das vermeidet Fehler, wenn sich z. B. die Reihenfolge der Scans durch nachträgliches Hinzufügen oder Löschen ändert.
+
+== 1. Vorbereitung ==
+
+=== a) Hardware vorbereiten ===
+* PC starten  
+* Lichter anschalten  
+* Kameraabdeckung entfernen  
+* Kamera einschalten  
+
+=== b) Software vorbereiten ===
+* MultiDotScan by Walter Nagel starten  
+* Scanauftrag auswählen → '''WELCHEN SCANAUFTRAG'''
+
+== 2. Scanvorgang ==
+* Objekt auf Unterlage legen, rechtwinklig zum Bildausschnitt in der Software  
+* Farbkarte anlegen – je nach Format des Objekts rechts oder unten  
+* Bildausschnitt an Objekt anpassen (Rand ca. 10–20 mm)  
+* Kamera mit dem Pedal auslösen → '''Scan'''  
+* Wenn ein Scan fehlt oder neu gemacht werden muss: in der Software an die richtige Stelle ziehen → Scans werden beim Export automatisch in der korrekten Reihenfolge angeordnet  
+
+== 3. Scans exportieren ==
+* Nach dem Scan der gesamten Box den Scanauftrag exportieren → landet unter '''DATEIPFAD'''
+
+== 4. Erfassen ==
+
+* Erfasste Scans unter '''DATEIPFAD''' öffnen  
+  (im Bildexplorer, '''nicht''' in der Scansoftware – sonst kann sich die Reihenfolge der Scans ändern, was zu Fehlern in der Erfassungstabelle führt)
+* Jede Box (= jeder Scanauftrag) beginnt numerisch bei 1; jeder Scan ist fortlaufend nummeriert  
+* Scannummern in die Erfassungstabelle eintragen, dabei Ebenenstruktur berücksichtigen:
+
+=== Ebenenstruktur ===
+* Standard: Vorderseite → Ebene 0, Rückseite → Ebene 1  
+* Wenn das Exlibris einen Umschlag hat oder mehrere Exlibris in einem Briefumschlag liegen:
+  * Umschlag = Ebene 0  
+  * Vorderseite = Ebene 1  
+  * Rückseite = Ebene 2  
+  * Rückseite Umschlag = Ebene 3  
+  → So ist klar erkennbar, wo ein Umschlag beginnt und endet.
+
+=== Erfassen der Metadaten ===
+* Jahr – steht eine Jahreszahl auf Vorder- oder Rückseite?  
+* Urheber – Künstler  
+* Eigner – wem gehört das Exlibris?  
+* Objektbeschreibung – was ist zu sehen? Verschlagwortung des Bildinhalts  
+
+==== Beachten ====
+* Beschreibung von '''grob → genau'''  
+  * Beispiel: „Baum“ statt „Schwarzeiche“  
+  * „Helm“ statt „Topfhelm 15. Jahrhundert“  
+* '''Singularformen''' bevorzugen – auch bei mehreren Objekten  
+  * z. B. „Buch“ statt „Bücher“, „Figur, weiblich“ statt „Frauengruppe“  
+* '''Aktivitäten im Infinitiv''' angeben: „sitzen“, „lesen“, „fahren“ statt „sitzt“, „lesend“, „fährt“  
+* '''Verbindungswörter vermeiden''' („Stopwords“):  
+  <nowiki>mit, ohne, der, die, das, ein, eine, und, zu, von, im, in, auf, an, als, bei, für, aus, dem, den, des, eines, einer</nowiki>  
+  (werden vom Mapper-Makro ohnehin herausgefiltert)
+
+* Material – meist Papier  
+* Maße – Höhe × Breite in cm (bei geraden cm-Zahlen „,0“ anfügen, z. B. 14,3 × 7,0 cm statt 14,3 × 7)  
+* Objekttyp – Exlibris, Rückseite, Umschlag, Zettel  
+* Inschrift – z. B. Wappen mit Spruchband  
+* Anmerkungen – sonstige Notizen oder Hinweise (Bleistifteinträge etc.)  
+* AUX – irrelevant  
+
+== 5. Erfassung überprüfen ==
+* Stimmt die Nummerierung der Scans mit der entsprechenden Zeile in der Erfassungstabelle überein?  
+* Makro über die Tabelle laufen lassen:  
+  Es existiert ein Makro für den Abgleich der Spalte „Objektbeschreibung“ mit dem internen Normvokabular, das die Verschlagwortung vereinheitlicht.  
+
+Dieses Makro kann direkt in LibreOffice Calc über das Menü gestartet werden:
+
+<pre>
+Extras → Makros → Makros verwalten → Python → 
+Meine Makros → Vokabular_Abgleich_Makro → mapper_macro_2.x → run_mapper_macro → Ausführen
+</pre>
+
+'''Hinweis:'''  
+Für die Benutzung des Makros liegt eine ausführliche Anleitung unter '''DATEIPFAD'''.
+
+== 6. Abschluss ==
+* Vordruck ausfüllen:  
+  * Name  
+  * Datum  
+  * Welche Box  
+  * Bis wohin wurde gescannt/erfasst  
+  * Gibt es etwas zu beachten?
+
+== 7. Best Practices ==
+* Lieber zu viel als zu wenig scannen (Rückseiten, Umschläge usw.)  
+* Lieber zu viel als zu wenig beschreiben (alles, was nachvollziehbar erkennbar ist, kann verschlagwortet werden)  
+* Notizen oder Beschriftungen auf Exlibris oder Rückseiten vollständig erfassen  
+* Bei Unsicherheiten: nachfragen  
+

config.json

@@ -1,9 +0,0 @@
-{
-  "normvokabular_path": "/home/jarnold/projects/GND-Skript Test/Input CSV/Normvokabular_INTERN/NV_MASTER.ods",
-  "max_suggestions": 3,
-  "color_hit": "#C6EFCE",
-  "color_miss": "#FFC7CE",
-  "use_rapidfuzz": false,
-  "use_spacy": false,
-  "autosave": false
-}

mapper.py

@@ -1,371 +0,0 @@
-import os
-import sys
-import re
-import time
-import json
-import pandas as pd
-import requests
-from pathlib import Path
-from collections import defaultdict
-from difflib import SequenceMatcher
-
-# RapidFuzz für Token-basierte Fuzzy-Suche
-try:
-    from rapidfuzz import fuzz
-    RAPIDFUZZ_AVAILABLE = True
-    print("RapidFuzz verfügbar")
-except ImportError:
-    RAPIDFUZZ_AVAILABLE = False
-    print("RapidFuzz nicht verfügbar – nutze SequenceMatcher")
-
-# Spacy Lemmatizer
-try:
-    import spacy
-    nlp = spacy.load("de_core_news_sm")
-    SPACY_AVAILABLE = True
-    print("Spacy Lemmatizer aktiviert")
-except:
-    SPACY_AVAILABLE = False
-    nlp = None
-    print("Spacy nicht verfügbar – nutze naive Stemmer")
-
-# =========================
-# Pfade & Config
-# =========================
-INPUT_DIR = Path("Input CSV")
-OUTPUT_DIR = Path("Auswertung Ergebnisse")
-OUTPUT_DIR.mkdir(exist_ok=True)
-NORMVOC_FILE = Path("Input CSV/Normvokabular_INTERN/NV_MASTER.ods")
-CACHE_FILE = "api_cache.json"
-STOPWORDS = {"mit","ohne","der","die","das","ein","eine","und","zu","von","im","in","auf","an","als","bei","für","aus","dem","den","des","eines","einer"}
-CONF_THRESHOLD = 0.75
-TIMEOUT = 5
-MAX_RETRIES = 3
-BACKOFF_FACTOR = 2
-HEADERS = {"User-Agent": "VLG_API_multi/1.0 (projekt@example.com)"}
-API_ACTIVE = {"gnd": True, "wikidata": True}
-FAIL_COUNTER = {"gnd": 0, "wikidata": 0}
-
-# Cache
-if os.path.exists(CACHE_FILE):
-    with open(CACHE_FILE,"r",encoding="utf-8") as f:
-        CACHE = json.load(f)
-else:
-    CACHE = {}
-
-def save_cache():
-    with open(CACHE_FILE,"w",encoding="utf-8") as f:
-        json.dump(CACHE, f, indent=2, ensure_ascii=False)
-
-# =========================
-# Normalisierung / Lemma
-# =========================
-def normalize_text(s):
-    if not s:
-        return ""
-    s = str(s).lower().strip()
-    s = re.sub(r"[\(\)\[\]\"'\\.,;:\?!]", "", s)
-    s = re.sub(r"\s+"," ",s)
-    return s
-
-# Lemma-Cache
-lemma_cache = {}
-
-def lemmatize_term(term):
-    term_norm = normalize_text(term)
-    if term_norm in lemma_cache:
-        return lemma_cache[term_norm]
-    if SPACY_AVAILABLE and nlp:
-        doc = nlp(term_norm)
-        lemma = " ".join([token.lemma_ for token in doc])
-    else:
-        lemma = term_norm
-    lemma_cache[term_norm] = lemma
-    return lemma
-
-# =========================
-# Kompositum-Zerlegung (einfacher Ansatz)
-# =========================
-def compound_split(term):
-    parts = re.findall(r'[A-ZÄÖÜ][a-zäöü]+', term)
-    return parts if parts else [term]
-
-# =========================
-# Normvokabular laden & Lemma vorbereiten
-# =========================
-def load_normvokabular(file_path):
-    sheets = pd.read_excel(file_path, sheet_name=None, engine="odf" if file_path.suffix.lower()==".ods" else None)
-    norm_dict = {}
-    stem_index = defaultdict(list)
-    lemma_norm_map = {}  # für RapidFuzz preprocessed
-
-    for sheet_name, df in sheets.items():
-        if sheet_name.lower() in ["master", "übersicht"]:
-            continue
-        df = df.dropna(how="all", axis=1)
-        df.columns = [str(c).strip() for c in df.columns]
-        id_col = next((c for c in df.columns if "ID" in c), None)
-        word_col = next((c for c in df.columns if "Wort" in c or "Vokabel" in c), None)
-        if not id_col or not word_col:
-            continue
-
-        current_parent_id = None
-        for _, row in df.iterrows():
-            row_id = str(row[id_col]).strip() if pd.notna(row[id_col]) else None
-            row_word = str(row[word_col]).strip() if pd.notna(row[word_col]) else None
-            if row_id:
-                current_parent_id = row_id
-            if not row_word:
-                continue
-            assigned_parent_id = current_parent_id
-            entry = {
-                "Name": row_word,
-                "ID": assigned_parent_id,   # Parent-ID
-                "Sheet": sheet_name,
-                "Own_ID": row_id or ""      # eigene ID, falls vorhanden
-            }
-            key = normalize_text(row_word)
-            norm_dict[key] = entry
-            lemma = lemmatize_term(key)
-            stem_index[lemma].append(entry)
-            if lemma not in lemma_norm_map:
-                lemma_norm_map[lemma] = entry
-    return norm_dict, stem_index, lemma_norm_map
-
-# =========================
-# Mapping & Vorschläge
-# =========================
-def map_to_norm(term, norm_dict, stem_index, lemma_norm_map, top_n=3):
-    term_norm = normalize_text(term)
-    term_lemma = lemmatize_term(term)
-
-    # Exakter Treffer
-    if term_norm in norm_dict:
-        e = norm_dict[term_norm]
-        return e["Name"], e["ID"], []
-
-    # Lemma-Treffer
-    if term_lemma in stem_index:
-        e = stem_index[term_lemma][0]
-        return e["Name"], e["ID"], []
-
-    # KEIN TREFFER → Kompositum-Split
-    tokens = compound_split(term)
-    if len(tokens) == 1:
-        suggestions = get_suggestions(term_lemma, lemma_norm_map, top_n)
-        return "KEIN TREFFER", "", suggestions
-    else:
-        token_matches = []
-        for t in tokens:
-            t_lemma = lemmatize_term(t)
-            if t_lemma in stem_index:
-                e = stem_index[t_lemma][0]
-                token_matches.append((t, e["Name"], e["ID"]))
-            else:
-                sugg = get_suggestions(t_lemma, lemma_norm_map, top_n)
-                token_matches.append((t, "KEIN TREFFER", "", sugg))
-        combined_suggestions = [f"{m[1]} ({m[2]})" for m in token_matches if m[1] != "KEIN TREFFER"]
-        return "KEIN TREFFER", "", combined_suggestions
-
-def get_suggestions(term_lemma, lemma_norm_map, top_n=3, threshold=CONF_THRESHOLD):
-    candidates = []
-    for key_lemma, entry in lemma_norm_map.items():
-        if RAPIDFUZZ_AVAILABLE:
-            score = fuzz.token_set_ratio(term_lemma, key_lemma)/100
-        else:
-            score = SequenceMatcher(None, term_lemma.lower(), key_lemma.lower()).ratio()
-        if key_lemma.lower().startswith(term_lemma.lower()):
-            score = min(score + 0.1, 1.0)
-        if score >= threshold:
-            candidates.append((score, entry["Name"], entry["ID"]))
-    candidates.sort(reverse=True)
-    return [f"{name} ({id_})" for _, name, id_ in candidates[:top_n]]
-
-# =========================
-# API-Abfragen
-# =========================
-def request_with_retries(api_name,url,params=None):
-    cache_key = url + str(params)
-    if cache_key in CACHE:
-        return CACHE[cache_key]
-    retries = 0
-    while retries < MAX_RETRIES:
-        try:
-            r = requests.get(url, params=params, timeout=TIMEOUT, headers=HEADERS)
-            if r.status_code == 200:
-                try: data = r.json()
-                except: data = r.text
-                CACHE[cache_key] = data
-                FAIL_COUNTER[api_name] = 0
-                return data
-        except:
-            pass
-        retries += 1
-        time.sleep(min(BACKOFF_FACTOR**retries,30))
-    FAIL_COUNTER[api_name] += 1
-    if FAIL_COUNTER[api_name] >= 10:
-        API_ACTIVE[api_name] = False
-    return None
-
-def batch_query_gnd(terms):
-    results={}
-    if not API_ACTIVE.get("gnd", False):
-        for t in terms: results[t] = ""
-        return results
-    for t in terms:
-        url="https://lobid.org/gnd/search"
-        params={"q":t,"format":"json"}
-        data = request_with_retries("gnd", url, params)
-        top = ""
-        if data and "member" in data:
-            cands = [(doc.get("preferredName","") or doc.get("name",""), SequenceMatcher(None,t.lower(),(doc.get("preferredName","") or doc.get("name","")).lower()).ratio()) for doc in data["member"] if doc.get("preferredName","") or doc.get("name","")]
-            cands = [c for c in cands if c[1]>=0.75]
-            if cands:
-                top = sorted(cands,key=lambda x:x[1],reverse=True)[0][0]
-        results[t] = top
-    return results
-
-def batch_query_wikidata(terms):
-    results={}
-    if not API_ACTIVE.get("wikidata", False):
-        for t in terms: results[t] = ""
-        return results
-    for t in terms:
-        url="https://www.wikidata.org/w/api.php"
-        params={"action":"wbsearchentities","search":t,"language":"de","format":"json"}
-        data = request_with_retries("wikidata", url, params)
-        top = ""
-        if data and "search" in data:
-            cands = [(e.get("label",""), SequenceMatcher(None,t.lower(),e.get("label","").lower()).ratio()) for e in data["search"] if e.get("label","")]
-            cands = [c for c in cands if c[1]>=0.70]
-            if cands:
-                top = sorted(cands,key=lambda x:x[1],reverse=True)[0][0]
-        results[t] = top
-    return results
-
-# =========================
-# Markierung / Export
-# =========================
-def mark_norm_hits(file_path):
-    ext = file_path.suffix.lower()
-    if ext in [".xlsx", ".xls"]:
-        from openpyxl import load_workbook
-        from openpyxl.styles import PatternFill
-        wb = load_workbook(file_path)
-        ws = wb.active
-        green_fill = PatternFill(start_color="C6EFCE", end_color="C6EFCE", fill_type="solid")
-        red_fill   = PatternFill(start_color="FFC7CE", end_color="FFC7CE", fill_type="solid")
-        col_map = {cell.value: idx+1 for idx, cell in enumerate(ws[1])}
-        norm_col = col_map.get("Norm_Treffer", None)
-        if not norm_col:
-            print("Spalte 'Norm_Treffer' nicht gefunden")
-            return
-        for row in ws.iter_rows(min_row=2, min_col=norm_col, max_col=norm_col):
-            cell = row[0]
-            if cell.value and cell.value != "KEIN TREFFER":
-                cell.fill = green_fill
-            else:
-                cell.fill = red_fill
-        wb.save(file_path)
-    elif ext==".ods":
-        df = pd.read_excel(file_path, engine="odf")
-        df["Norm_Status"] = df["Norm_Treffer"].apply(lambda x: "Treffer" if pd.notna(x) and str(x).strip() and x!="KEIN TREFFER" else "Kein Treffer")
-        df.to_excel(file_path, index=False, engine="odf")
-
-# =========================
-# Verarbeitung Input-Dateien
-# =========================
-def process_files():
-    norm_dict, stem_index, lemma_norm_map = load_normvokabular(NORMVOC_FILE)
-    total_terms = 0
-    total_hits = 0
-
-    if not INPUT_DIR.exists():
-        print(f"Eingabeordner {INPUT_DIR} fehlt")
-        sys.exit(1)
-    files = list(INPUT_DIR.glob("*"))
-    if not files:
-        print("Keine Dateien gefunden")
-        return
-
-    for file_path in files:
-        if not file_path.suffix.lower() in [".csv",".ods",".xls",".xlsx"]:
-            continue
-        print(f"Verarbeite Datei: {file_path.name}")
-        try:
-            if file_path.suffix.lower() == ".csv":
-                df = pd.read_csv(file_path)
-            else:
-                df = pd.read_excel(file_path, engine="odf" if file_path.suffix.lower()==".ods" else None)
-        except Exception as e:
-            print(f"Fehler beim Lesen von {file_path.name}: {e}")
-            continue
-
-        df = df.dropna(how="all")
-        df.columns = [str(c).strip() for c in df.columns]
-
-        besch_col = next((c for c in df.columns if "Objektbeschreibung" in c), None)
-        box_col = next((c for c in df.columns if "Objekt/Ebene" in c), None)
-        urh_col = next((c for c in df.columns if "Urheber" in c), None)
-        if not besch_col: continue
-
-        row_terms_map = []
-        for _, row in df.iterrows():
-            besch = str(row[besch_col]).strip() if pd.notna(row[besch_col]) else ""
-            if not besch: continue
-            obj_box = row[box_col] if box_col else ""
-            urheber = row[urh_col] if urh_col else ""
-            clauses = [c.strip() for c in re.split(r",", besch) if c.strip()]
-            terms = []
-            for clause in clauses:
-                parts = [p.strip() for p in re.split(r"\s+", clause) if p.strip()]
-                for p in parts:
-                    if p.lower() in STOPWORDS: continue
-                    if re.fullmatch(r"\d+", p): continue
-                    terms.append(p)
-            row_terms_map.append((obj_box, urheber, terms))
-
-        all_terms = list({t for _,_,terms in row_terms_map for t in terms})
-        gnd_results = batch_query_gnd(all_terms)
-        wd_results = batch_query_wikidata(all_terms)
-
-        output_rows = []
-        for obj_box, urheber, terms in row_terms_map:
-            for term in terms:
-                norm_name, norm_id, suggestions = map_to_norm(term, norm_dict, stem_index, lemma_norm_map)
-                total_terms += 1
-                if norm_name != "KEIN TREFFER":
-                    total_hits += 1
-                out_row = {
-                    "Box": obj_box,
-                    "Objekt/Ebene": obj_box,
-                    "Urheber": urheber,
-                    "Begriff": term,
-                    "Norm_Treffer": norm_name,
-                    "Norm_ID": norm_id,
-                    "Norm_Vorschlag": ", ".join(suggestions) if suggestions else "",
-                    "GND_Top1": gnd_results.get(term,""),
-                    "WD_Top1": wd_results.get(term,"")
-                }
-                output_rows.append(out_row)
-
-        out_df = pd.DataFrame(output_rows)
-        output_file = OUTPUT_DIR / f"Auswertung_{file_path.stem}{file_path.suffix}"
-        version = 1
-        while output_file.exists():
-            output_file = OUTPUT_DIR / f"Auswertung_{file_path.stem}_({version}){file_path.suffix}"
-            version += 1
-        engine = "odf" if output_file.suffix.lower()==".ods" else None
-        out_df.to_excel(output_file, index=False, engine=engine)
-        mark_norm_hits(output_file)
-        print(f"Auswertung gespeichert: {output_file}")
-
-    save_cache()
-    print(f"Gesamt: {total_terms} Begriffe, {total_hits} Treffer im Normvokabular")
-
-# =========================
-# Main
-# =========================
-if __name__ == "__main__":
-    process_files()
-    print("Fertig")

mapper_macro.py

@@ -1,237 +0,0 @@
-import uno
-import os
-import re
-import traceback
-import json
-
-# Optional für Lemmatizer
-try:
-    import spacy
-    nlp = spacy.load("de_core_news_sm")
-    SPACY_AVAILABLE = True
-except:
-    SPACY_AVAILABLE = False
-    nlp = None
-
-# Optional für Fuzzy Matching
-try:
-    from rapidfuzz import fuzz
-    RAPIDFUZZ_AVAILABLE = True
-except:
-    from difflib import SequenceMatcher
-    RAPIDFUZZ_AVAILABLE = False
-
-import odf.opendocument
-import odf.table
-import odf.text
-
-# ------------------------
-# Konfiguration absolute Pfade
-# ------------------------
-BASE_DIR = "/home/jarnold/.config/libreoffice/4/user/Scripts/python/NV Abgleich Makro"
-NV_MASTER_PATH = os.path.join(BASE_DIR, "NV_MASTER.ods")
-LOG_FILE = os.path.join(BASE_DIR, "mapper_macro.log")
-CACHE_FILE = os.path.join(BASE_DIR, "mapper_cache.json")
-
-STOPWORDS = {"mit","ohne","der","die","das","ein","eine","und","zu","von","im","in","auf","an","als","bei","für","aus","dem","den","des","eines","einer"}
-CONF_THRESHOLD = 0.75
-
-# ------------------------
-# Logging
-# ------------------------
-def log(msg):
-    with open(LOG_FILE, "a", encoding="utf-8") as f:
-        f.write(msg + "\n")
-
-# ------------------------
-# Cache laden
-# ------------------------
-if os.path.exists(CACHE_FILE):
-    with open(CACHE_FILE, "r", encoding="utf-8") as f:
-        CACHE = json.load(f)
-else:
-    CACHE = {}
-
-# ------------------------
-# Normalisierung / Lemma
-# ------------------------
-def normalize_text(s):
-    if not s:
-        return ""
-    s = str(s).lower().strip()
-    s = re.sub(r"[\(\)\[\]\"'\\.,;:\?!]", "", s)
-    s = re.sub(r"\s+"," ",s)
-    return s
-
-lemma_cache = {}
-def lemmatize_term(term):
-    term_norm = normalize_text(term)
-    if term_norm in lemma_cache:
-        return lemma_cache[term_norm]
-    if SPACY_AVAILABLE and nlp:
-        doc = nlp(term_norm)
-        lemma = " ".join([token.lemma_ for token in doc])
-    else:
-        lemma = term_norm
-    lemma_cache[term_norm] = lemma
-    return lemma
-
-# ------------------------
-# NV_MASTER einlesen
-# ------------------------
-def load_nv_master(path):
-    norm_dict = {}
-    try:
-        doc = odf.opendocument.load(path)
-    except Exception as e:
-        log(f"Fehler beim Laden von NV_MASTER: {e}")
-        return norm_dict
-
-    for sheet in doc.spreadsheet.getElementsByType(odf.table.Table):
-        sheet_name = sheet.getAttribute("name")
-        if sheet_name.lower() == "master":
-            continue
-
-        current_parent_id = None
-        for row in sheet.getElementsByType(odf.table.TableRow):
-            cells = row.getElementsByType(odf.table.TableCell)
-            cell_values = []
-            for cell in cells:
-                texts = cell.getElementsByType(odf.text.P)
-                if texts and texts[0].firstChild:
-                    cell_values.append(str(texts[0].firstChild.data).strip())
-                else:
-                    cell_values.append("")
-            if not cell_values or len(cell_values)<4:
-                continue
-            id_val, unterk, unterunterk, word = cell_values[:4]
-            if id_val:
-                current_parent_id = id_val.strip()
-            if not word:
-                continue
-            key = lemmatize_term(word)
-            norm_dict[key] = {
-                "Name": word.strip(),
-                "ID": current_parent_id,
-                "Sheet": sheet_name,
-                "Unterkategorie": unterk.strip(),
-                "Unterunterkategorie": unterunterk.strip()
-            }
-    log(f"NV_MASTER geladen: {len(norm_dict)} Begriffe")
-    return norm_dict
-
-# ------------------------
-# Matching
-# ------------------------
-def get_suggestions(term_lemma, norm_dict, top_n=3, threshold=CONF_THRESHOLD):
-    candidates = []
-    for key, entry in norm_dict.items():
-        if RAPIDFUZZ_AVAILABLE:
-            score = fuzz.token_set_ratio(term_lemma, key)/100
-        else:
-            score = SequenceMatcher(None, term_lemma.lower(), key.lower()).ratio()
-        if key.lower().startswith(term_lemma.lower()):
-            score = min(score + 0.1, 1.0)
-        if score >= threshold:
-            candidates.append((score, entry["Name"], entry["ID"]))
-    candidates.sort(reverse=True)
-    return [f"{name} ({id_})" for _, name, id_ in candidates[:top_n]]
-
-def map_word(word, norm_dict):
-    key = lemmatize_term(word)
-    if key in CACHE:
-        cached = CACHE[key]
-        return cached["Norm"], cached["Suggestion"], cached["ID"]
-
-    if key in norm_dict:
-        entry = norm_dict[key]
-        tr, sug, wid = entry["Name"], "", entry["ID"]
-    else:
-        suggestions = get_suggestions(term_lemma=key, norm_dict=norm_dict)
-        if suggestions:
-            tr, sug, wid = "KEIN TREFFER", ", ".join(suggestions), ""
-        else:
-            tr, sug, wid = "KEIN TREFFER", "", ""
-
-    CACHE[key] = {"Norm": tr, "Suggestion": sug, "ID": wid}
-    return tr, sug, wid
-
-# ------------------------
-# Makro-Hauptfunktion
-# ------------------------
-def run_mapper_macro():
-    try:
-        doc = XSCRIPTCONTEXT.getDocument()
-        sheets = doc.getSheets()
-        sheet = sheets.getByIndex(0)
-        cursor = sheet.createCursor()
-        cursor.gotoStartOfUsedArea(False)
-        cursor.gotoEndOfUsedArea(True)
-        data_range = cursor.getRangeAddress()
-
-        header_row = 0
-        objekt_col = None
-
-        # Header prüfen
-        for col in range(data_range.EndColumn+1):
-            val = sheet.getCellByPosition(col, header_row).String.strip().lower()
-            if val == "objektbeschreibung":
-                objekt_col = col
-                break
-
-        if objekt_col is None:
-            log("Spalte 'Objektbeschreibung' nicht gefunden")
-            return
-
-        # Neue Spalten am rechten Tabellenende erstellen
-        max_col = data_range.EndColumn
-        norm_tr_col = max_col + 1
-        norm_sug_col = max_col + 2
-        norm_id_col = max_col + 3
-
-        sheet.getCellByPosition(norm_tr_col, header_row).String = "Norm_Treffer"
-        sheet.getCellByPosition(norm_sug_col, header_row).String = "Norm_Vorschlag"
-        sheet.getCellByPosition(norm_id_col, header_row).String = "Norm_ID"
-
-        norm_dict = load_nv_master(NV_MASTER_PATH)
-
-        # Farben
-        GREEN = 0xC6EFCE
-        YELLOW = 0xFFEB9C
-        RED = 0xFFC7CE
-
-        for row in range(1, data_range.EndRow+1):
-            cell = sheet.getCellByPosition(objekt_col, row)
-            val = cell.String.strip()
-            if not val:
-                continue
-            words = [w.strip() for w in re.split(r"\s+", val) if w.strip() and w.lower() not in STOPWORDS]
-            tr_list, sug_list, id_list = [], [], []
-            for w in words:
-                tr, sug, wid = map_word(w, norm_dict)
-                if tr != "KEIN TREFFER":
-                    tr_list.append(tr)
-                if sug:
-                    sug_list.append(sug)
-                if wid:
-                    id_list.append(wid)
-            sheet.getCellByPosition(norm_tr_col, row).String = ", ".join(tr_list)
-            sheet.getCellByPosition(norm_sug_col, row).String = ", ".join(sug_list)
-            sheet.getCellByPosition(norm_id_col, row).String = ", ".join(id_list)
-            # Farbmarkierung
-            if tr_list:
-                cell.CellBackColor = GREEN
-            elif sug_list:
-                cell.CellBackColor = YELLOW
-            else:
-                cell.CellBackColor = RED
-
-        # Cache speichern
-        with open(CACHE_FILE, "w", encoding="utf-8") as f:
-            json.dump(CACHE, f, ensure_ascii=False, indent=2)
-
-        log("Makro erfolgreich ausgeführt")
-
-    except Exception as e:
-        log("Fehler in run_mapper_macro:")
-        log(traceback.format_exc())

mapper_macro_1.2.py

@@ -1,297 +0,0 @@
-# -*- coding: utf-8 -*-
-import os
-import uno
-import unohelper
-import re
-import json
-import pandas as pd
-from pathlib import Path
-from difflib import SequenceMatcher
-
-# RapidFuzz für Fuzzy-Suche
-try:
-    from rapidfuzz import fuzz
-    RAPIDFUZZ_AVAILABLE = True
-except ImportError:
-    RAPIDFUZZ_AVAILABLE = False
-
-# Spacy Lemmatizer
-try:
-    import spacy
-    nlp = spacy.load("de_core_news_sm")
-    SPACY_AVAILABLE = True
-except:
-    SPACY_AVAILABLE = False
-    nlp = None
-
-# =========================
-# Pfade & Config
-# =========================
-SCRIPT_DIR = Path("/home/jarnold/.config/libreoffice/4/user/Scripts/python/NV Abgleich Makro")
-NV_MASTER_FILE = SCRIPT_DIR / "NV_MASTER.ods"
-CACHE_FILE = SCRIPT_DIR / "mapper_cache.json"
-LOG_FILE = SCRIPT_DIR / "mapper_log.txt"
-STOPWORDS = {"mit","ohne","der","die","das","ein","eine","und","zu","von","im","in","auf","an","als","bei","für","aus","dem","den","des","eines","einer"}
-
-# =========================
-# Cache & Logging
-# =========================
-if CACHE_FILE.exists():
-    with open(CACHE_FILE,"r",encoding="utf-8") as f:
-        CACHE = json.load(f)
-else:
-    CACHE = {}
-
-def save_cache():
-    with open(CACHE_FILE,"w",encoding="utf-8") as f:
-        json.dump(CACHE, f, indent=2, ensure_ascii=False)
-
-def log(msg):
-    with open(LOG_FILE,"a",encoding="utf-8") as f:
-        f.write(msg + "\n")
-
-# =========================
-# Textverarbeitung
-# =========================
-def normalize_text(s):
-    if not s: return ""
-    s = str(s).lower().strip()
-    s = re.sub(r"[\(\)\[\]\"'\\.,;:\?!]", "", s)
-    s = re.sub(r"\s+"," ",s)
-    return s
-
-lemma_cache = {}
-def lemmatize_term(term):
-    term_norm = normalize_text(term)
-    if term_norm in lemma_cache:
-        return lemma_cache[term_norm]
-    if SPACY_AVAILABLE and nlp:
-        doc = nlp(term_norm)
-        lemma = " ".join([token.lemma_ for token in doc])
-    else:
-        lemma = term_norm
-    lemma_cache[term_norm] = lemma
-    return lemma
-
-def compound_split(term):
-    parts = re.findall(r'[A-ZÄÖÜa-zäöü]+', term)
-    return parts if parts else [term]
-
-# =========================
-# NV_MASTER laden
-# =========================
-def load_normvokabular(file_path):
-    sheets = pd.read_excel(file_path, sheet_name=None, engine="odf")
-    norm_dict = {}
-    for sheet_name, df in sheets.items():
-        df = df.dropna(how="all", axis=1)
-        df.columns = [str(c).strip() for c in df.columns]
-        if "ID" not in df.columns or "Wort/Vokabel" not in df.columns:
-            continue
-        current_parent_id = None
-        for _, row in df.iterrows():
-            row_id = str(row["ID"]).strip() if pd.notna(row["ID"]) else None
-            row_word = str(row["Wort/Vokabel"]).strip() if pd.notna(row["Wort/Vokabel"]) else None
-            if row_id: current_parent_id = row_id
-            if not row_word: continue
-            norm_dict[normalize_text(row_word)] = {
-                "ID": current_parent_id,
-                "Wort/Vokabel": row_word
-            }
-    return norm_dict
-
-# =========================
-# Mapping
-# =========================
-def map_term_with_indexes(term, norm_dict):
-    term_norm = normalize_text(term)
-    term_lemma = lemmatize_term(term_norm)
-
-    # Cache prüfen
-    if term_lemma in CACHE:
-        cached = CACHE[term_lemma]
-        if isinstance(cached, dict) and all(k in cached for k in ("hits","suggestions","ids")):
-            return cached["hits"], cached["suggestions"], cached["ids"]
-        else:
-            CACHE.pop(term_lemma, None)
-
-    hits = []
-    suggestions = []
-    ids = []
-
-    # Exakte Treffer
-    if term_norm in norm_dict:
-        e = norm_dict[term_norm]
-        hits.append(e["Wort/Vokabel"])
-        ids.append(e["ID"])
-    elif term_lemma in norm_dict:
-        e = norm_dict[term_lemma]
-        hits.append(e["Wort/Vokabel"])
-        ids.append(e["ID"])
-    else:
-        # Fuzzy Matching
-        for key, e in norm_dict.items():
-            score = fuzz.token_sort_ratio(term_lemma, key)/100.0 if RAPIDFUZZ_AVAILABLE else SequenceMatcher(None, term_lemma, key).ratio()
-            if score >= 0.75:
-                suggestions.append(e["Wort/Vokabel"])
-                ids.append(e["ID"])
-
-    CACHE[term_lemma] = {"hits": hits, "suggestions": suggestions, "ids": ids}
-    return hits, suggestions, ids
-
-# =========================
-# LibreOffice Dialog (ListBox + Checkbox)
-# =========================
-def apply_proposals_dialog():
-    ctx = uno.getComponentContext()
-    smgr = ctx.ServiceManager
-    desktop = smgr.createInstanceWithContext("com.sun.star.frame.Desktop", ctx)
-    doc = desktop.getCurrentComponent()
-    if not doc.supportsService("com.sun.star.sheet.SpreadsheetDocument"):
-        log("Kein Calc-Dokument aktiv")
-        return
-    selection = doc.CurrentSelection
-    sheet = doc.CurrentController.ActiveSheet
-
-    # Prüfen ob eine Zelle ausgewählt ist
-    if selection is None or not hasattr(selection, "getCellAddress"):
-        log("Keine Zelle ausgewählt")
-        return
-    cell = selection
-
-    # Spalte überprüfen
-    header_row = sheet.getCellRangeByPosition(0,0,sheet.Columns.Count-1,0)
-    objekt_col = None
-    norm_vorschlag_col = None
-    for col_idx in range(sheet.Columns.Count):
-        val = sheet.getCellByPosition(col_idx,0).String
-        if val.strip().lower() == "objektbeschreibung":
-            objekt_col = col_idx
-        elif val.strip().lower() == "norm_vorschlag":
-            norm_vorschlag_col = col_idx
-    if norm_vorschlag_col is None or objekt_col is None:
-        log("Spalte 'Norm_Vorschlag' oder 'Objektbeschreibung' nicht gefunden")
-        return
-
-    # Vorschläge auslesen
-    proposals_str = sheet.getCellByPosition(norm_vorschlag_col, cell.RangeAddress.StartRow).String
-    if not proposals_str.strip():
-        log("Keine Vorschläge in der ausgewählten Zelle")
-        return
-    proposals = [p.strip() for p in proposals_str.split(";") if p.strip()]
-
-    # Dialog erstellen
-    toolkit = smgr.createInstanceWithContext("com.sun.star.awt.Toolkit", ctx)
-    dialog_model = smgr.createInstanceWithContext("com.sun.star.awt.UnoControlDialogModel", ctx)
-    dialog_model.Width = 180
-    dialog_model.Height = 150
-    dialog_model.Title = "Vorschläge übernehmen"
-
-    # ListBox
-    lb_model = dialog_model.createInstance("com.sun.star.awt.UnoControlListBoxModel")
-    lb_model.Name = "ProposalList"
-    lb_model.PositionX = 10
-    lb_model.PositionY = 10
-    lb_model.Width = 160
-    lb_model.Height = 80
-    lb_model.StringItemList = tuple(proposals)
-    dialog_model.insertByName("ProposalList", lb_model)
-
-    # Checkbox
-    cb_model = dialog_model.createInstance("com.sun.star.awt.UnoControlCheckBoxModel")
-    cb_model.Name = "AllCheck"
-    cb_model.PositionX = 10
-    cb_model.PositionY = 95
-    cb_model.Width = 160
-    cb_model.Height = 15
-    cb_model.Label = "Alle Vorschläge übernehmen"
-    dialog_model.insertByName("AllCheck", cb_model)
-
-    # OK-Button
-    btn_model = dialog_model.createInstance("com.sun.star.awt.UnoControlButtonModel")
-    btn_model.Name = "OKButton"
-    btn_model.PositionX = 10
-    btn_model.PositionY = 115
-    btn_model.Width = 80
-    btn_model.Height = 20
-    btn_model.Label = "OK"
-    dialog_model.insertByName("OKButton", btn_model)
-
-    # Abbrechen-Button
-    cancel_model = dialog_model.createInstance("com.sun.star.awt.UnoControlButtonModel")
-    cancel_model.Name = "CancelButton"
-    cancel_model.PositionX = 100
-    cancel_model.PositionY = 115
-    cancel_model.Width = 80
-    cancel_model.Height = 20
-    cancel_model.Label = "Abbrechen"
-    dialog_model.insertByName("CancelButton", cancel_model)
-
-    # Control Dialog
-    dialog = smgr.createInstanceWithContext("com.sun.star.awt.UnoControlDialog", ctx)
-    dialog.setModel(dialog_model)
-    dialog.setVisible(True)
-    toolkit.createPeer(dialog, None)
-
-    # Warten auf OK
-    while True:
-        import time
-        time.sleep(0.1)
-        # Prüfen auf Klick
-        if dialog.getControl("OKButton").Pressed:
-            all_flag = dialog.getControl("AllCheck").State == 1
-            selected_idx = dialog.getControl("ProposalList").SelectedItems
-            if selected_idx:
-                selected_proposal = proposals[selected_idx[0]]
-            else:
-                selected_proposal = None
-            break
-        elif dialog.getControl("CancelButton").Pressed:
-            dialog.endExecute()
-            return
-
-    # Anwenden
-    obj_cell = sheet.getCellByPosition(objekt_col, cell.RangeAddress.StartRow)
-    obj_text = obj_cell.String
-    if all_flag:
-        for prop in proposals:
-            idx = obj_text.lower().find(prop.lower())
-            if idx != -1:
-                obj_text = obj_text[:idx] + prop + obj_text[idx+len(prop):]
-    else:
-        if selected_proposal:
-            idx = obj_text.lower().find(selected_proposal.lower())
-            if idx != -1:
-                obj_text = obj_text[:idx] + selected_proposal + obj_text[idx+len(selected_proposal):]
-
-    obj_cell.String = obj_text
-    obj_cell.CellBackColor = 0x00FF00  # grün
-    dialog.endExecute()
-    save_cache()
-    log(f"Vorschlag übernommen: {obj_text}")
-
-# =========================
-# Automatische Button-Registrierung
-# =========================
-def register_toolbar_button():
-    ctx = uno.getComponentContext()
-    smgr = ctx.ServiceManager
-    desktop = smgr.createInstanceWithContext("com.sun.star.frame.Desktop", ctx)
-    doc = desktop.getCurrentComponent()
-    frame = doc.CurrentController.Frame
-    # Button kann manuell über Makro-Menü an Toolbar gebunden werden
-    # Hier wird nur das Makro selbst registriert
-    # Symbolleiste muss in LO einmalig erstellt werden
-
-# =========================
-# Hauptmakro
-# =========================
-def run_mapper_macro():
-    try:
-        norm_dict = load_normvokabular(NV_MASTER_FILE)
-        log(f"NV_MASTER geladen ({len(norm_dict)} Begriffe)")
-
-        apply_proposals_dialog()
-
-    except Exception as e:
-        log(f"Fehler in run_mapper_macro: {e}")

mapper_macro_2.3.py

@@ -0,0 +1,379 @@
+# -*- coding: utf-8 -*-
+# LibreOffice/Excel Macro: NV_MASTER-Abgleich, Pandas+odf, Cache, Farben
+# Version 2.3 – mit "Kein_Treffer" Spalte
+# Speicherort: libreoffice/4/user/Scripts/python/Vokabular_Abgleich_Makro/mapper_macro_2.3.py
+
+import os
+import re
+import json
+import traceback
+
+# UNO-Context wird zur Laufzeit zur Verfügung gestellt (XSCRIPTCONTEXT)
+try:
+    import pandas as pd
+    PANDAS_AVAILABLE = True
+except Exception:
+    PANDAS_AVAILABLE = False
+
+try:
+    import spacy
+    nlp = spacy.load("de_core_news_sm")
+    SPACY_AVAILABLE = True
+except Exception:
+    SPACY_AVAILABLE = False
+    nlp = None
+
+try:
+    from rapidfuzz import fuzz
+    RAPIDFUZZ_AVAILABLE = True
+except Exception:
+    RAPIDFUZZ_AVAILABLE = False
+    from difflib import SequenceMatcher
+
+# ------------------------
+# Konfiguration
+# ------------------------
+BASE_DIR = "/home/jarnold/.config/libreoffice/4/user/Scripts/python/Vokabular_Abgleich_Makro"
+NV_MASTER_PATH = os.path.join(BASE_DIR, "NV_MASTER.ods")
+LOG_FILE = os.path.join(BASE_DIR, "mapper_macro_2.3.log")
+CACHE_FILE = os.path.join(BASE_DIR, "mapper_cache_2.3.json")
+
+STOPWORDS = {"mit","ohne","der","die","das","ein","eine","und","zu","von","im","in","auf","an","als","bei","für","aus","dem","den","des","eines","einer"}
+CONF_THRESHOLD = 0.75  # Basis-Schwelle für Vorschläge
+
+# ------------------------
+# Logging
+# ------------------------
+def log(msg):
+    try:
+        with open(LOG_FILE, "a", encoding="utf-8") as f:
+            f.write(msg + "\n")
+    except Exception:
+        pass
+
+# ------------------------
+# Cache laden
+# ------------------------
+try:
+    if os.path.exists(CACHE_FILE):
+        with open(CACHE_FILE, "r", encoding="utf-8") as f:
+            CACHE = json.load(f)
+    else:
+        CACHE = {}
+except Exception:
+    CACHE = {}
+
+# ------------------------
+# Text-Normalisierung & Lemma
+# ------------------------
+def normalize_text(s):
+    if not s:
+        return ""
+    s = str(s).strip().lower()
+    s = re.sub(r"[\(\)\[\]\"'\\;:\?!,\.]", "", s)
+    s = re.sub(r"\s+", " ", s)
+    return s
+
+lemma_cache = {}
+def lemmatize_term(term):
+    term_norm = normalize_text(term)
+    if term_norm in lemma_cache:
+        return lemma_cache[term_norm]
+    if SPACY_AVAILABLE and nlp:
+        try:
+            doc = nlp(term_norm)
+            lemma = " ".join([token.lemma_ for token in doc])
+        except Exception:
+            lemma = term_norm
+    else:
+        lemma = term_norm
+    lemma_cache[term_norm] = lemma
+    return lemma
+
+# ------------------------
+# NV_MASTER laden
+# ------------------------
+def build_norm_index(nv_path):
+    norm_dict = {}
+    lemma_index = {}
+    if not PANDAS_AVAILABLE:
+        log("Pandas nicht verfügbar. NV_MASTER kann nicht gelesen werden.")
+        return norm_dict, lemma_index
+    try:
+        sheets = pd.read_excel(nv_path, sheet_name=None, engine="odf")
+    except Exception as e:
+        log(f"Fehler beim Einlesen NV_MASTER: {e}")
+        return norm_dict, lemma_index
+    for sheet_name, df in sheets.items():
+        if str(sheet_name).strip().lower() == "master":
+            continue
+        df = df.fillna("")
+        cols = [str(c).strip().lower() for c in df.columns]
+        id_col = None
+        word_col = None
+        for i, c in enumerate(cols):
+            if "id" in c:
+                id_col = df.columns[i]
+            if "wort" in c or "vokabel" in c:
+                word_col = df.columns[i]
+        if word_col is None and len(df.columns) >= 1:
+            word_col = df.columns[-1]
+        if id_col is None and len(df.columns) >= 1:
+            id_col = df.columns[0]
+        current_parent_id = None
+        for _, row in df.iterrows():
+            id_val = str(row[id_col]).strip() if id_col in df.columns else ""
+            word_val = str(row[word_col]).strip() if word_col in df.columns else ""
+            if id_val:
+                current_parent_id = id_val
+            if not word_val:
+                continue
+            norm_name = normalize_text(word_val)
+            lemma = lemmatize_term(word_val)
+            entry = {"Name": word_val.strip(), "ID": current_parent_id or "", "Sheet": sheet_name}
+            norm_dict.setdefault(norm_name, []).append(entry)
+            lemma_index.setdefault(lemma, []).append(entry)
+    log(f"NV_MASTER geladen ({NV_MASTER_PATH}). Begriffe: {sum(len(v) for v in norm_dict.values())}")
+    return norm_dict, lemma_index
+
+# ------------------------
+# Matching
+# ------------------------
+def fuzzy_score(a, b):
+    if RAPIDFUZZ_AVAILABLE:
+        try:
+            return fuzz.token_set_ratio(a, b) / 100.0
+        except Exception:
+            return 0.0
+    else:
+        try:
+            return SequenceMatcher(None, a.lower(), b.lower()).ratio()
+        except Exception:
+            return 0.0
+
+def get_suggestions_for_term(term_lemma, norm_dict, lemma_index, threshold=CONF_THRESHOLD):
+    candidates = []
+    for key_lemma, entries in lemma_index.items():
+        score = fuzzy_score(term_lemma, key_lemma)
+        if key_lemma.startswith(term_lemma):
+            score = min(score + 0.1, 1.0)
+        if score >= threshold:
+            for e in entries:
+                candidates.append((score, e["Name"], e["ID"]))
+    for norm_key, entries in norm_dict.items():
+        score = fuzzy_score(term_lemma, norm_key)
+        if norm_key.startswith(term_lemma):
+            score = min(score + 0.1, 1.0)
+        if score >= threshold:
+            for e in entries:
+                candidates.append((score, e["Name"], e["ID"]))
+    candidates.sort(key=lambda t: t[0], reverse=True)
+    seen = set()
+    results = []
+    for score, name, id_ in candidates:
+        key = (name, id_)
+        if key in seen:
+            continue
+        seen.add(key)
+        results.append({"score": score, "name": name, "id": id_})
+    return [f'{r["name"]} ({r["id"]})' if r["id"] else r["name"] for r in results]
+
+def map_term_with_indexes(term, norm_dict, lemma_index):
+    term_norm = normalize_text(term)
+    term_lemma = lemmatize_term(term)
+    if term_lemma in CACHE:
+        cached = CACHE[term_lemma]
+        return cached.get("hits", []), cached.get("suggestions", []), cached.get("ids", [])
+    hits = []
+    suggestions = []
+    ids = []
+    if term_norm in norm_dict:
+        for e in norm_dict[term_norm]:
+            hits.append(e["Name"])
+            if e["ID"]:
+                ids.append(e["ID"])
+    if not hits and term_lemma in lemma_index:
+        for e in lemma_index[term_lemma]:
+            hits.append(e["Name"])
+            if e["ID"]:
+                ids.append(e["ID"])
+    if not hits:
+        suggestions = get_suggestions_for_term(term_lemma, norm_dict, lemma_index, threshold=CONF_THRESHOLD)
+    def unique_preserve(seq):
+        seen = set()
+        out = []
+        for x in seq:
+            if x not in seen:
+                seen.add(x)
+                out.append(x)
+        return out
+    hits = unique_preserve(hits)
+    suggestions = unique_preserve(suggestions)
+    ids = unique_preserve(ids)
+    CACHE[term_lemma] = {"hits": hits, "suggestions": suggestions, "ids": ids}
+    return hits, suggestions, ids
+
+# ------------------------
+# Haupt-Makro
+# ------------------------
+def run_mapper_macro():
+    try:
+        doc = XSCRIPTCONTEXT.getDocument()
+        sheet = doc.CurrentController.ActiveSheet
+        cursor = sheet.createCursor()
+        cursor.gotoStartOfUsedArea(False)
+        cursor.gotoEndOfUsedArea(True)
+        data_range = cursor.getRangeAddress()
+    except Exception as e:
+        log("Fehler: konnte Dokument/Sheet nicht öffnen: " + str(e))
+        return
+
+    # Header finden
+    header_row = None
+    objekt_col = None
+    max_col = data_range.EndColumn
+    for r in range(0, min(5, data_range.EndRow+1)):
+        for c in range(0, max_col+1):
+            try:
+                val = str(sheet.getCellByPosition(c, r).String).strip().lower()
+            except Exception:
+                val = ""
+            if val == "objektbeschreibung":
+                header_row = r
+                objekt_col = c
+                break
+        if objekt_col is not None:
+            break
+    if objekt_col is None:
+        log("Spalte 'Objektbeschreibung' nicht gefunden. Abbruch.")
+        return
+
+    # Spalten anlegen
+    existing = {}
+    for c in range(0, data_range.EndColumn+1):
+        try:
+            h = str(sheet.getCellByPosition(c, header_row).String).strip()
+        except Exception:
+            h = ""
+        if h == "Norm_Treffer":
+            existing["Norm_Treffer"] = c
+        if h == "Norm_Vorschlag":
+            existing["Norm_Vorschlag"] = c
+
+    last_col = data_range.EndColumn
+    if "Norm_Treffer" not in existing:
+        last_col += 1
+        existing["Norm_Treffer"] = last_col
+        sheet.getCellByPosition(last_col, header_row).String = "Norm_Treffer"
+    if "Norm_Vorschlag" not in existing:
+        last_col += 1
+        existing["Norm_Vorschlag"] = last_col
+        sheet.getCellByPosition(last_col, header_row).String = "Norm_Vorschlag"
+
+    # Neue Spalte "Kein_Treffer"
+    if "Kein_Treffer" not in existing:
+        last_col += 1
+        existing["Kein_Treffer"] = last_col
+        sheet.getCellByPosition(last_col, header_row).String = "Kein_Treffer"
+
+    norm_tr_col = existing["Norm_Treffer"]
+    norm_sug_col = existing["Norm_Vorschlag"]
+    kein_tr_col = existing["Kein_Treffer"]
+
+    norm_dict, lemma_index = build_norm_index(NV_MASTER_PATH)
+    if not norm_dict and not lemma_index:
+        log("NV_MASTER leer oder nicht lesbar. Abbruch.")
+        return
+
+    GREEN = 0xADFF2F
+    YELLOW = 0xFFA500
+    RED = 0xCC0000
+    WHITE = 0xFFFFFF
+
+    rows_processed = 0
+    for r in range(header_row + 1, data_range.EndRow + 1):
+        try:
+            cell = sheet.getCellByPosition(objekt_col, r)
+            txt = str(cell.String).strip()
+            if not txt:
+                continue
+
+            clauses = [c.strip() for c in re.split(r",", txt) if c.strip()]
+            terms = []
+            for cl in clauses:
+                parts = [p.strip() for p in re.split(r"\s+", cl) if p.strip()]
+                for p in parts:
+                    if p.lower() in STOPWORDS:
+                        continue
+                    if re.fullmatch(r"\d+", p):
+                        continue
+                    terms.append(p)
+
+            row_hits = []
+            row_sugs = []
+            row_ids = []
+            unmapped_terms = []
+
+            for term in terms:
+                hits, sugs, ids = map_term_with_indexes(term, norm_dict, lemma_index)
+                if hits:
+                    row_hits.extend([f"{h} ({id_})" if id_ else h for h,id_ in zip(hits, ids + [""]*len(hits))])
+                else:
+                    unmapped_terms.append(term)
+                    if sugs:
+                        row_sugs.extend([f"{s}" for s in sugs])
+                if ids:
+                    row_ids.extend(ids)
+
+            def uniq(seq):
+                seen = set()
+                out = []
+                for x in seq:
+                    if x not in seen:
+                        seen.add(x)
+                        out.append(x)
+                return out
+
+            row_hits = uniq(row_hits)
+            row_sugs = uniq(row_sugs)
+            unmapped_terms = uniq(unmapped_terms)
+
+            # Farb-Logik Objektbeschreibung
+            if terms and not unmapped_terms and row_hits:
+                cell.CellBackColor = GREEN
+                row_sugs = []  # keine Vorschläge wenn alles Treffer
+            elif row_hits:
+                cell.CellBackColor = YELLOW
+            else:
+                cell.CellBackColor = RED
+
+            # Norm_Treffer
+            tr_cell = sheet.getCellByPosition(norm_tr_col, r)
+            tr_cell.String = " | ".join(row_hits)
+            tr_cell.CellBackColor = GREEN if row_hits else WHITE
+
+            # Norm_Vorschlag
+            sug_cell = sheet.getCellByPosition(norm_sug_col, r)
+            sug_cell.String = " | ".join(row_sugs)
+            sug_cell.CellBackColor = YELLOW if row_sugs else WHITE
+
+            # Kein_Treffer
+            kt_cell = sheet.getCellByPosition(kein_tr_col, r)
+            kt_cell.String = " | ".join(unmapped_terms)
+            kt_cell.CellBackColor = RED if unmapped_terms else WHITE
+
+            rows_processed += 1
+
+        except Exception as e:
+            log(f"Fehler in Zeile {r}: {e}\n{traceback.format_exc()}")
+
+    try:
+        with open(CACHE_FILE, "w", encoding="utf-8") as f:
+            json.dump(CACHE, f, ensure_ascii=False, indent=2)
+    except Exception:
+        pass
+
+    log(f"run_mapper_macro fertig. Zeilen verarbeitet: {rows_processed}")
+
+# Export für LibreOffice
+g_exportedScripts = (run_mapper_macro,)

normmapper_macro.py

@@ -1,121 +0,0 @@
-import uno
-import json
-import subprocess
-from pathlib import Path
-from com.sun.star.awt import XActionListener
-
-# Farbwerte (BGR)
-GREEN = 0xC6EFCE
-RED = 0xFFC7CE
-YELLOW = 0xFFEB9C
-
-def get_objektbeschreibung_column(sheet):
-    """Findet die Spalte 'Objektbeschreibung'."""
-    for row in range(sheet.Rows.Count):
-        for col in range(sheet.Columns.Count):
-            cell = sheet.getCellByPosition(col, row)
-            if cell.String.strip().lower() == "objektbeschreibung":
-                return col
-    return None
-
-def update_cell_color(cell, status):
-    """Färbt die Zelle."""
-    if status == "grün":
-        cell.CellBackColor = GREEN
-    elif status == "gelb":
-        cell.CellBackColor = YELLOW
-    else:
-        cell.CellBackColor = RED
-
-def call_mapper(term):
-    """Ruft den lokalen Wrapper auf."""
-    wrapper = Path("/home/jarnold/projects/GND-Skript Test/NormVokabular_Mapper_Wrapper.py")
-    if not wrapper.exists():
-        return {"term": term, "norm_name": "KEIN TREFFER", "norm_id": "", "suggestions": []}
-
-    result = subprocess.run(
-        ["python3", str(wrapper), term],
-        capture_output=True,
-        text=True
-    )
-    try:
-        output = json.loads(result.stdout)
-    except:
-        output = {"term": term, "norm_name": "KEIN TREFFER", "norm_id": "", "suggestions": []}
-    return output
-
-class SuggestionListener(XActionListener):
-    """Listener für Klick auf Vorschlag-Button."""
-    def __init__(self, cell, suggestion, dialog):
-        self.cell = cell
-        self.suggestion = suggestion
-        self.dialog = dialog
-
-    def actionPerformed(self, event):
-        self.cell.String = self.suggestion
-        update_cell_color(self.cell, "grün")
-        self.dialog.endExecute()  # schließt das Dialogfenster
-
-    def disposing(self, event):
-        pass
-
-def show_suggestion_dialog(cell, term, suggestions):
-    """Zeigt ein Dialog-Fenster mit klickbaren Vorschlägen."""
-    ctx = XSCRIPTCONTEXT.getComponentContext()
-    smgr = ctx.getServiceManager()
-    toolkit = smgr.createInstance("com.sun.star.awt.Toolkit")
-    dialog_model = smgr.createInstance("com.sun.star.awt.UnoControlDialogModel")
-    dialog_model.PositionX = 100
-    dialog_model.PositionY = 100
-    dialog_model.Width = 200
-    dialog_model.Height = 30 + 25*len(suggestions)
-    dialog_model.Title = f"Vorschläge für '{term}'"
-
-    for i, sugg in enumerate(suggestions[:3]):
-        btn_model = dialog_model.createInstance("com.sun.star.awt.UnoControlButtonModel")
-        btn_model.Name = f"btn_{i}"
-        btn_model.Label = sugg
-        btn_model.PositionX = 10
-        btn_model.PositionY = 10 + i*25
-        btn_model.Width = 180
-        btn_model.Height = 20
-        dialog_model.insertByName(btn_model.Name, btn_model)
-
-    dialog = smgr.createInstance("com.sun.star.awt.UnoControlDialog")
-    dialog.setModel(dialog_model)
-    dialog.setVisible(True)
-
-    for i, sugg in enumerate(suggestions[:3]):
-        btn = dialog.getControl(f"btn_{i}")
-        listener = SuggestionListener(cell, sugg, dialog)
-        btn.addActionListener(listener)
-
-    toolkit.createDialog(dialog).execute()
-
-def mapper_process_column():
-    """Verarbeitet alle Zellen unter 'Objektbeschreibung' in der aktiven Tabelle."""
-    doc = XSCRIPTCONTEXT.getDocument()
-    sheet = doc.CurrentController.ActiveSheet
-    col_index = get_objektbeschreibung_column(sheet)
-    if col_index is None:
-        return
-
-    for row in range(sheet.Rows.Count):
-        cell = sheet.getCellByPosition(col_index, row)
-        if not cell.String.strip():
-            continue  # leere Zelle ignorieren
-        term = cell.String.strip()
-        result = call_mapper(term)
-
-        if result["norm_name"] != "KEIN TREFFER":
-            cell.String = result["norm_name"]
-            update_cell_color(cell, "grün")
-        elif result["suggestions"]:
-            update_cell_color(cell, "gelb")
-            show_suggestion_dialog(cell, term, result["suggestions"])
-        else:
-            update_cell_color(cell, "rot")
-            show_suggestion_dialog(cell, term, [])
-
-# Export
-g_exportedScripts = mapper_process_column,