diff --git a/prototypes/arc2_prototype/.python-version b/prototypes/arc2_prototype/.python-version new file mode 100644 index 0000000..b6d8b76 --- /dev/null +++ b/prototypes/arc2_prototype/.python-version @@ -0,0 +1 @@ +3.11.8 diff --git a/prototypes/arc2_prototype/README.md b/prototypes/arc2_prototype/README.md index b060066..133975f 100644 --- a/prototypes/arc2_prototype/README.md +++ b/prototypes/arc2_prototype/README.md @@ -2,7 +2,8 @@ ### 1. Create and activate a virtual environment -
python3 -m venv .venv
+pyenv shell 3.11.8
+python -m venv .venv
source .venv/bin/activate
diff --git a/prototypes/arc2_prototype/app.py b/prototypes/arc2_prototype/app.py
index d478ddd..243e841 100644
--- a/prototypes/arc2_prototype/app.py
+++ b/prototypes/arc2_prototype/app.py
@@ -3,6 +3,8 @@ import os
import json
from ocr_pdf_service.ocr_runner import run_ocr_and_extract
from exxeta_service.exxetaGPT_api import extract_with_exxeta
+from spacy_service.spacy import extract_with_spacy
+from merge_validate_service.merge_validate import merge_and_validate_entities
app = Flask(__name__)
UPLOAD_FOLDER = "pitchbooks"
@@ -31,11 +33,13 @@ def upload():
pitchbook_pages = json.load(f)
extract_with_exxeta(pitchbook_pages)
+ extract_with_spacy(pitchbook_pages)
+ merge_and_validate_entities()
except Exception as e:
return jsonify({"error": str(e)}), 500
- return "status: complete"
+ return "status: complete\n"
if __name__ == "__main__":
app.run(debug=True)
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/exxeta_service/output/exxeta-results.json b/prototypes/arc2_prototype/exxeta_service/output/exxeta-results.json
index 64c9dc9..c93c677 100644
--- a/prototypes/arc2_prototype/exxeta_service/output/exxeta-results.json
+++ b/prototypes/arc2_prototype/exxeta_service/output/exxeta-results.json
@@ -6,7 +6,7 @@
},
{
"label": "RISIKOPROFIL",
- "entity": "Core, core+, value-added",
+ "entity": "core, core+, value-added",
"page": 7
},
{
@@ -72,6 +72,11 @@
{
"label": "RISIKOPROFIL",
"entity": "Core",
+ "page": 15
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core/Core+",
"page": 19
},
{
@@ -87,11 +92,11 @@
{
"label": "RISIKOPROFIL",
"entity": "Core",
- "page": 26
+ "page": 28
},
{
"label": "RISIKOPROFIL",
- "entity": "Value-added",
+ "entity": "Core",
"page": 26
},
{
@@ -101,19 +106,19 @@
},
{
"label": "RISIKOPROFIL",
- "entity": "Core Offices, quality Retail asset",
- "page": 27
- },
- {
- "label": "RISIKOPROFIL",
- "entity": "Core + assets",
- "page": 27
+ "entity": "Core, Core+",
+ "page": 33
},
{
"label": "RISIKOPROFIL",
"entity": "Core, Core+",
"page": 33
},
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Value-added",
+ "page": 33
+ },
{
"label": "RISIKOPROFIL",
"entity": "Core",
@@ -138,5 +143,20 @@
"label": "RISIKOPROFIL",
"entity": "Core",
"page": 37
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 37
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 38
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 38
}
]
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/merge_validate_service/merge_validate.py b/prototypes/arc2_prototype/merge_validate_service/merge_validate.py
new file mode 100644
index 0000000..9dd75f1
--- /dev/null
+++ b/prototypes/arc2_prototype/merge_validate_service/merge_validate.py
@@ -0,0 +1,71 @@
+import json
+from pathlib import Path
+
+def normalize_entity(entity_str):
+ if not entity_str:
+ return ""
+ normalized = entity_str.replace('\n', ' ')
+ normalized = ''.join(normalized.lower().split())
+ return normalized
+
+def merge_and_validate_entities():
+ base_dir = Path(__file__).resolve().parent
+ spacy_results_path = base_dir / ".." / "spacy_service" / "output" / "spacy-results.json"
+ exxeta_results_path = base_dir / ".." / "exxeta_service" / "output" / "exxeta-results.json"
+ output_path = base_dir / "output" / "merged-results.json"
+
+ with open(spacy_results_path, "r", encoding="utf-8") as f:
+ spacy_data = json.load(f)
+ with open(exxeta_results_path, "r", encoding="utf-8") as f:
+ exxeta_data = json.load(f)
+
+ merged = []
+ seen = set()
+
+ for s in spacy_data:
+ s_entity_norm = normalize_entity(s["entity"])
+ s_page = s["page"]
+
+ found = False
+ for e in exxeta_data:
+ e_entity_norm = normalize_entity(e["entity"])
+ e_page = e["page"]
+
+ if (s["label"] == e["label"] and
+ s_entity_norm == e_entity_norm and
+ s_page == e_page):
+
+ merged.append({
+ "label": s["label"],
+ "entity": s["entity"],
+ "page": s_page,
+ "status": "validated"
+ })
+ seen.add((e["entity"], e_page))
+ found = True
+ break
+
+ if not found:
+ merged.append({
+ "label": s["label"],
+ "entity": s["entity"],
+ "page": s_page,
+ "status": "single-source",
+ "source": "spacy"
+ })
+
+ for e in exxeta_data:
+ if (e["entity"], e["page"]) not in seen:
+ merged.append({
+ "label": e["label"],
+ "entity": e["entity"],
+ "page": e["page"],
+ "status": "single-source",
+ "source": "exxeta"
+ })
+
+ output_path.parent.mkdir(parents=True, exist_ok=True)
+ with open(output_path, "w", encoding="utf-8") as f:
+ json.dump(merged, f, indent=2, ensure_ascii=False)
+
+ return merged
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/merge_validate_service/output/merged-results.json b/prototypes/arc2_prototype/merge_validate_service/output/merged-results.json
new file mode 100644
index 0000000..060fe46
--- /dev/null
+++ b/prototypes/arc2_prototype/merge_validate_service/output/merged-results.json
@@ -0,0 +1,447 @@
+[
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core and Core+",
+ "page": 4,
+ "status": "validated"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core, core+, value-added",
+ "page": 7,
+ "status": "validated"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core/Core+",
+ "page": 10,
+ "status": "validated"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core/core+",
+ "page": 10,
+ "status": "validated"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core/Core+",
+ "page": 10,
+ "status": "validated"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "UK, DE, BE, NL, LU,",
+ "page": 10,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core / Core +",
+ "page": 12,
+ "status": "validated"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core\n/ core+",
+ "page": 12,
+ "status": "validated"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core\n",
+ "page": 12,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Term / core+",
+ "page": 12,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core/core+",
+ "page": 12,
+ "status": "validated"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "6,4 6,4",
+ "page": 13,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Country /",
+ "page": 14,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core Excellent",
+ "page": 14,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core 40",
+ "page": 14,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core 400m",
+ "page": 14,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core 99m-102",
+ "page": 14,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core 85m-90m",
+ "page": 14,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core 50",
+ "page": 14,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Country /",
+ "page": 15,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core Good New",
+ "page": 15,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core 44m-46m",
+ "page": 15,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core Good New",
+ "page": 15,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core CBD New",
+ "page": 15,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core Good New",
+ "page": 15,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "countries, giving",
+ "page": 18,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core/core+",
+ "page": 20,
+ "status": "validated"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core/core+",
+ "page": 20,
+ "status": "validated"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "D, and",
+ "page": 21,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "UK, DE, BE, NL, LU,",
+ "page": 26,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core or",
+ "page": 27,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core +",
+ "page": 27,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "kgCO,e",
+ "page": 30,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "C,\n",
+ "page": 32,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "KfW, Dwp",
+ "page": 35,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Bank,",
+ "page": 35,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "HSBC, RTE",
+ "page": 37,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core WALB (",
+ "page": 37,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core WALB (",
+ "page": 37,
+ "status": "single-source",
+ "source": "spacy"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 9,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 14,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 14,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 14,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 14,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 14,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 15,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 15,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 15,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 15,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 15,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core/Core+",
+ "page": 19,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 28,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 26,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core Offices, Core + assets",
+ "page": 27,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core, Core+",
+ "page": 33,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core, Core+",
+ "page": 33,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Value-added",
+ "page": 33,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 35,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 35,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core Parking",
+ "page": 36,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core Parking",
+ "page": 36,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 37,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 37,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 38,
+ "status": "single-source",
+ "source": "exxeta"
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core",
+ "page": 38,
+ "status": "single-source",
+ "source": "exxeta"
+ }
+]
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/ocr_pdf_service/output/pitchbook-OCR.pdf b/prototypes/arc2_prototype/ocr_pdf_service/output/pitchbook-OCR.pdf
index 8a5677d..9b16efd 100644
Binary files a/prototypes/arc2_prototype/ocr_pdf_service/output/pitchbook-OCR.pdf and b/prototypes/arc2_prototype/ocr_pdf_service/output/pitchbook-OCR.pdf differ
diff --git a/prototypes/arc2_prototype/pitchbooks/Pitchbook 1.pdf b/prototypes/arc2_prototype/pitchbooks/Pitchbook 1.pdf
new file mode 100644
index 0000000..a3b5538
Binary files /dev/null and b/prototypes/arc2_prototype/pitchbooks/Pitchbook 1.pdf differ
diff --git a/prototypes/arc2_prototype/pitchbooks/Pitchbook 3.pdf b/prototypes/arc2_prototype/pitchbooks/Pitchbook 3.pdf
new file mode 100644
index 0000000..ea60f84
Binary files /dev/null and b/prototypes/arc2_prototype/pitchbooks/Pitchbook 3.pdf differ
diff --git a/prototypes/arc2_prototype/requirements.txt b/prototypes/arc2_prototype/requirements.txt
index d727943..be1ab0b 100644
--- a/prototypes/arc2_prototype/requirements.txt
+++ b/prototypes/arc2_prototype/requirements.txt
@@ -1,4 +1,74 @@
-flask
-pdfplumber
-ocrmypdf
-requests
\ No newline at end of file
+annotated-types==0.7.0
+blinker==1.9.0
+blis==0.7.11
+catalogue==2.0.10
+certifi==2025.4.26
+cffi==1.17.1
+charset-normalizer==3.4.1
+click==8.1.8
+cloudpathlib==0.16.0
+confection==0.1.5
+cryptography==44.0.2
+cymem==2.0.11
+Deprecated==1.2.18
+deprecation==2.1.0
+filelock==3.18.0
+Flask==3.1.0
+fsspec==2025.3.2
+huggingface-hub==0.30.2
+idna==3.10
+img2pdf==0.6.1
+itsdangerous==2.2.0
+Jinja2==3.1.6
+langcodes==3.5.0
+language_data==1.3.0
+lxml==5.4.0
+marisa-trie==1.2.1
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+mdurl==0.1.2
+mpmath==1.3.0
+murmurhash==1.0.12
+networkx==3.4.2
+numpy==1.26.4
+ocrmypdf==16.10.1
+packaging==25.0
+pdfminer.six==20250327
+pdfplumber==0.11.6
+pi_heif==0.22.0
+pikepdf==9.7.0
+pillow==11.2.1
+pluggy==1.5.0
+preshed==3.0.9
+pycparser==2.22
+pydantic==2.11.3
+pydantic_core==2.33.1
+Pygments==2.19.1
+PyMuPDF==1.25.5
+pypdfium2==4.30.1
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.3
+rich==14.0.0
+safetensors==0.5.3
+smart-open==6.4.0
+spacy==3.7.2
+spacy-alignments==0.9.1
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+spacy-transformers==1.3.3
+srsly==2.5.1
+sympy==1.14.0
+thinc==8.2.5
+tokenizers==0.15.2
+torch==2.1.0
+tqdm==4.67.1
+transformers==4.35.2
+typer==0.9.4
+typing-inspection==0.4.0
+typing_extensions==4.13.2
+urllib3==2.4.0
+wasabi==1.1.3
+weasel==0.3.4
+Werkzeug==3.1.3
+wrapt==1.17.2
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/config.cfg b/prototypes/arc2_prototype/spacy_service/models/model-best/config.cfg
new file mode 100644
index 0000000..1cf80c4
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-best/config.cfg
@@ -0,0 +1,145 @@
+[paths]
+train = "./data/train.spacy"
+dev = "./data/train.spacy"
+vectors = null
+init_tok2vec = null
+
+[system]
+gpu_allocator = null
+seed = 0
+
+[nlp]
+lang = "de"
+pipeline = ["tok2vec","ner"]
+batch_size = 1000
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+vectors = {"@vectors":"spacy.Vectors.v1"}
+
+[components]
+
+[components.ner]
+factory = "ner"
+incorrect_spans_key = null
+moves = null
+scorer = {"@scorers":"spacy.ner_scorer.v1"}
+update_with_oracle_cut_size = 100
+
+[components.ner.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "ner"
+extra_state_tokens = false
+hidden_width = 64
+maxout_pieces = 2
+use_upper = true
+nO = null
+
+[components.ner.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+upstream = "*"
+
+[components.tok2vec]
+factory = "tok2vec"
+
+[components.tok2vec.model]
+@architectures = "spacy.Tok2Vec.v2"
+
+[components.tok2vec.model.embed]
+@architectures = "spacy.MultiHashEmbed.v2"
+width = ${components.tok2vec.model.encode.width}
+attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
+rows = [5000,1000,2500,2500]
+include_static_vectors = false
+
+[components.tok2vec.model.encode]
+@architectures = "spacy.MaxoutWindowEncoder.v2"
+width = 96
+depth = 4
+window_size = 1
+maxout_pieces = 3
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[training]
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+accumulate_gradient = 1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_components = []
+before_to_disk = null
+before_update = null
+
+[training.batcher]
+@batchers = "spacy.batch_by_words.v1"
+discard_oversize = false
+tolerance = 0.2
+get_length = null
+
+[training.batcher.size]
+@schedules = "compounding.v1"
+start = 100
+stop = 1000
+compound = 1.001
+t = 0.0
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+[training.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = false
+eps = 0.00000001
+learn_rate = 0.001
+
+[training.score_weights]
+ents_f = 1.0
+ents_p = 0.0
+ents_r = 0.0
+ents_per_type = null
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.tokenizer]
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/meta.json b/prototypes/arc2_prototype/spacy_service/models/model-best/meta.json
new file mode 100644
index 0000000..daabc76
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-best/meta.json
@@ -0,0 +1,52 @@
+{
+ "lang":"de",
+ "name":"pipeline",
+ "version":"0.0.0",
+ "spacy_version":">=3.7.2,<3.8.0",
+ "description":"",
+ "author":"",
+ "email":"",
+ "url":"",
+ "license":"",
+ "spacy_git_version":"a89eae928",
+ "vectors":{
+ "width":0,
+ "vectors":0,
+ "keys":0,
+ "name":null,
+ "mode":"default"
+ },
+ "labels":{
+ "tok2vec":[
+
+ ],
+ "ner":[
+ "RISIKOPROFIL"
+ ]
+ },
+ "pipeline":[
+ "tok2vec",
+ "ner"
+ ],
+ "components":[
+ "tok2vec",
+ "ner"
+ ],
+ "disabled":[
+
+ ],
+ "performance":{
+ "ents_f":1.0,
+ "ents_p":1.0,
+ "ents_r":1.0,
+ "ents_per_type":{
+ "RISIKOPROFIL":{
+ "p":1.0,
+ "r":1.0,
+ "f":1.0
+ }
+ },
+ "tok2vec_loss":0.000000029,
+ "ner_loss":0.0000000614
+ }
+}
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/ner/cfg b/prototypes/arc2_prototype/spacy_service/models/model-best/ner/cfg
new file mode 100644
index 0000000..6cd11cf
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-best/ner/cfg
@@ -0,0 +1,13 @@
+{
+ "moves":null,
+ "update_with_oracle_cut_size":100,
+ "multitasks":[
+
+ ],
+ "min_action_freq":1,
+ "learn_tokens":false,
+ "beam_width":1,
+ "beam_density":0.0,
+ "beam_update_prob":0.0,
+ "incorrect_spans_key":null
+}
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/ner/model b/prototypes/arc2_prototype/spacy_service/models/model-best/ner/model
new file mode 100644
index 0000000..8a0c5ae
Binary files /dev/null and b/prototypes/arc2_prototype/spacy_service/models/model-best/ner/model differ
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/ner/moves b/prototypes/arc2_prototype/spacy_service/models/model-best/ner/moves
new file mode 100644
index 0000000..e72ba15
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-best/ner/moves
@@ -0,0 +1 @@
+movesx{"0":{},"1":{"RISIKOPROFIL":45},"2":{"RISIKOPROFIL":45},"3":{"RISIKOPROFIL":45},"4":{"RISIKOPROFIL":45,"":1},"5":{"":1}}cfgneg_key
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/tok2vec/cfg b/prototypes/arc2_prototype/spacy_service/models/model-best/tok2vec/cfg
new file mode 100644
index 0000000..0e0dcd2
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-best/tok2vec/cfg
@@ -0,0 +1,3 @@
+{
+
+}
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/tok2vec/model b/prototypes/arc2_prototype/spacy_service/models/model-best/tok2vec/model
new file mode 100644
index 0000000..1cfa6a5
Binary files /dev/null and b/prototypes/arc2_prototype/spacy_service/models/model-best/tok2vec/model differ
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/tokenizer b/prototypes/arc2_prototype/spacy_service/models/model-best/tokenizer
new file mode 100644
index 0000000..9cdc922
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-best/tokenizer
@@ -0,0 +1,3 @@
+prefix_search^``|^§|^%|^=|^—|^–|^\+(?![0-9])|^…|^……|^,|^:|^;|^\!|^\?|^¿|^؟|^¡|^\(|^\)|^\[|^\]|^\{|^\}|^<|^>|^_|^#|^\*|^&|^。|^?|^!|^,|^、|^;|^:|^~|^·|^।|^،|^۔|^؛|^٪|^\.\.+|^…|^\'|^"|^”|^“|^`|^‘|^´|^’|^‚|^,|^„|^»|^«|^「|^」|^『|^』|^(|^)|^〔|^〕|^【|^】|^《|^》|^〈|^〉|^〈|^〉|^⟦|^⟧|^\$|^£|^€|^¥|^฿|^US\$|^C\$|^A\$|^₽|^﷼|^₴|^₠|^₡|^₢|^₣|^₤|^₥|^₦|^₧|^₨|^₩|^₪|^₫|^€|^₭|^₮|^₯|^₰|^₱|^₲|^₳|^₴|^₵|^₶|^₷|^₸|^₹|^₺|^₻|^₼|^₽|^₾|^₿|^[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]suffix_search2''$|/$|…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|?$|!$|,$|、$|;$|:$|~$|·$|।$|،$|۔$|؛$|٪$|\.\.+$|…$|\'$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|($|)$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|〈$|〉$|⟦$|⟧$|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]$|(?<=[0-9])\+$|(?<=°[FfCcKk])\.$|(?<=[0-9])(?:\$|£|€|¥|฿|US\$|C\$|A\$|₽|﷼|₴|₠|₡|₢|₣|₤|₥|₦|₧|₨|₩|₪|₫|€|₭|₮|₯|₰|₱|₲|₳|₴|₵|₶|₷|₸|₹|₺|₻|₼|₽|₾|₿)$|(?<=[0-9])(?:km|km²|km³|m|m²|m³|dm|dm²|dm³|cm|cm²|cm³|mm|mm²|mm³|ha|µm|nm|yd|in|ft|kg|g|mg|µg|t|lb|oz|m/s|km/h|kmh|mph|hPa|Pa|mbar|mb|MB|kb|KB|gb|GB|tb|TB|T|G|M|K|%|км|км²|км³|м|м²|м³|дм|дм²|дм³|см|см²|см³|мм|мм²|мм³|нм|кг|г|мг|м/с|км/ч|кПа|Па|мбар|Кб|КБ|кб|Мб|МБ|мб|Гб|ГБ|гб|Тб|ТБ|тбكم|كم²|كم³|م|م²|م³|سم|سم²|سم³|مم|مم²|مم³|كم|غرام|جرام|جم|كغ|ملغ|كوب|اكواب)$|(?<=[a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F%²\-\+…|……|,|:|;|\!|\?|¿|؟|¡|\(|\)|\[|\]|\{|\}|<|>|_|#|\*|&|。|?|!|,|、|;|:|~|·|।|،|۔|؛|٪(?:\'"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉〈〉⟦⟧)])\.$|(?<=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F][A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\.$infix_finditerZ\.\.+|…|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]|(?<=[a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\.(?=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])[,!?](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])[:<>=](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F]),(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[0-9A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\/(?=[0-9A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])([\"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉〈〉⟦⟧\)\]\(\[])(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])--(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[0-9])-(?=[0-9])token_matchurl_match
(?u)^(?:(?:[\w\+\-\.]{2,})://)?(?:\S+(?::\S*)?@)?(?:(?!(?:10|127)(?:\.\d{1,3}){3})(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[A-Za-z0-9\u00a1-\uffff][A-Za-z0-9\u00a1-\uffff_-]{0,62})?[A-Za-z0-9\u00a1-\uffff]\.)+(?:[a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F]{2,63}))(?::\d{2,5})?(?:[/?#]\S*)?$exceptions A
+A
+ A 'A'''A'''SA'SC's'nA'nCein'neA'neCeine'nemA'nemCeinem'nenA'nenCeinen'sA'sC's(*_*)A(*_*)(-8A(-8(-:A(-:(-;A(-;(-_-)A(-_-)(._.)A(._.)(:A(:(;A(;(=A(=(>_<)A(>_<)(^_^)A(^_^)(o:A(o:(¬_¬)A(¬_¬)(ಠ_ಠ)A(ಠ_ಠ)(╯°□°)╯︵┻━┻A(╯°□°)╯︵┻━┻)-:A)-:):A):-_-A-_--__-A-__-._.A._.0.0A0.00.oA0.o0_0A0_00_oA0_o8)A8)8-)A8-)8-DA8-D8DA8D:'(A:'(:')A:'):'-(A:'-(:'-)A:'-):(A:(:((A:((:(((A:(((:()A:():)A:):))A:)):)))A:))):*A:*:-(A:-(:-((A:-((:-(((A:-(((:-)A:-):-))A:-)):-)))A:-))):-*A:-*:-/A:-/:-0A:-0:-3A:-3:->A:->:-DA:-D:-OA:-O:-PA:-P:-XA:-X:-]A:-]:-oA:-o:-pA:-p:-xA:-x:-|A:-|:-}A:-}:/A:/:0A:0:1A:1:3A:3:>A:>:DA:D:OA:O:PA:P:XA:X:]A:]:oA:o:o)A:o):pA:p:xA:x:|A:|:}A:}:’(A:’(:’)A:’):’-(A:’-(:’-)A:’-);)A;);-)A;-);-DA;-D;DA;D;_;A;_;<.A=(A=(=)A=)=/A=/=3A=3=DA=D=[A=[=]A=]=|A=|>..<>.>A>.>>:(A>:(>:oA>:o><(((*>A><(((*>@_@A@_@A.C.AA.C.A.D.AA.D.A.G.AA.G.Abb.AAbb.CAbbildungAbk.AAbk.CAbkürzungAbs.AAbs.Abt.AAbt.CAbteilungApr.AApr.CAprilAug.AAug.CAugustB.A.AB.A.B.Sc.AB.Sc.Bd.ABd.CBandBetr.ABetr.CBetreffBf.ABf.CBahnhofBhf.ABhf.CBahnhofBiol.ABiol.Bsp.ABsp.CBeispielC++AC++CDU/CSUACDU/CSUChr.AChr.Cie.ACie.Co.ACo.D.C.AD.C.Dez.ADez.CDezemberDi.ADi.CDienstagDipl.ADipl.Dipl.-Ing.ADipl.-Ing.Do.ADo.CDonnerstagDr.ADr.Fa.AFa.CFirmaFam.AFam.CFamilieFeb.AFeb.CFebruarFr.AFr.CFrauFrl.AFrl.CFräuleinG.m.b.H.AG.m.b.H.Gebr.AGebr.Hbf.AHbf.CHauptbahnhofHg.AHg.Hr.AHr.CHerrHrn.AHrn.CHerrnHrsg.AHrsg.I.AI.II.AII.III.AIII.IV.AIV.Inc.AInc.Ing.AIng.Jan.AJan.CJanuarJh.AJh.CJahrhundertJhd.AJhd.CJahrhundertJr.AJr.Jul.AJul.CJuliJun.AJun.CJuniK.O.AK.O.L'AL'L.A.AL.A.L’AL’M.A.AM.A.M.Sc.AM.Sc.Mi.AMi.CMittwochMio.AMio.CMillionMo.AMo.CMontagMr.AMr.Mrd.AMrd.CMilliardeMrz.AMrz.CMärzMwSt.AMwSt.CMehrwertsteuerMär.AMär.CMärzN.Y.AN.Y.N.Y.C.AN.Y.C.Nov.ANov.CNovemberNr.ANr.CNummerO.K.AO.K.O.OAO.OO.oAO.oO_OAO_OO_oAO_oOkt.AOkt.COktoberOrig.AOrig.COriginalP.S.AP.S.Pkt.APkt.CPunktProf.AProf.CProfessorR.I.P.AR.I.P.Red.ARed.CRedaktionS'AS'C'sSa.ASa.CSamstagSep.ASep.CSeptemberSept.ASept.CSeptemberSo.ASo.CSonntagSt.ASt.Std.AStd.CStundeStr.AStr.CStraßeS’AS’C'sTel.ATel.CTelefonTsd.ATsd.CTausendU.S.AU.S.U.S.A.AU.S.A.U.S.S.AU.S.S.Univ.AUniv.CUniversitätV.VAV.VV_VAV_VVol.AVol.XDAXDXDDAXDD[-:A[-:[:A[:[=A[=\")A\")\nA\n\tA\t]=A]=^_^A^_^^__^A^__^^___^A^___^``A``a.Aa.a.D.Aa.D.a.M.Aa.M.a.Z.Aa.Z.abzgl.Aabzgl.Cabzüglichadv.Aadv.al.Aal.allg.Aallg.Callgemeinauf'mAaufA'mCdemauf’mAaufA’mCdemb.Ab.betr.Abetr.biol.Abiol.bspw.Abspw.Cbeispielsweisebzgl.Abzgl.Cbezüglichbzw.Abzw.Cbeziehungsweisec.Ac.c/oAc/oca.Aca.co.Aco.d'Ad'd.Ad.d.h.Ad.h.dgl.Adgl.Cdergleichendu'sAduA'sCesdu’sAduA’sCesd’Ad’e.Ae.e.V.Ae.V.e.g.Ae.g.ebd.Aebd.Cebendaehem.Aehem.eigtl.Aeigtl.Ceigentlichengl.Aengl.Cenglischentspr.Aentspr.er'sAerA'sCeserm.Aerm.er’sAerA’sCesetc.Aetc.ev.Aev.evtl.Aevtl.Ceventuellf.Af.frz.Afrz.Cfranzösischg.Ag.geb.Ageb.gegr.Agegr.Cgegründetgem.Agem.ggf.Aggf.Cgegebenenfallsggfs.Aggfs.Cgegebenenfallsggü.Aggü.Cgegenüberh.Ah.h.c.Ah.c.hinter'mAhinterA'mCdemhinter’mAhinterA’mCdemhrsg.Ahrsg.i.Ai.i.A.Ai.A.i.G.Ai.G.i.O.Ai.O.i.Tr.Ai.Tr.i.V.Ai.V.i.d.R.Ai.d.R.i.e.Ai.e.ich'sAichA'sCesich’sAichA’sCesihr'sAihrA'sCesihr’sAihrA’sCesincl.Aincl.Cinklusiveinkl.Ainkl.Cinklusiveinsb.Ainsb.Cinsbesonderej.Aj.jr.Ajr.jun.Ajun.jur.Ajur.k.Ak.kath.Akath.Ckatholischl.Al.lat.Alat.lt.Alt.Clautm.Am.m.E.Am.E.m.M.Am.M.max.Amax.Cmaximalmin.Amin.Cminimalmind.Amind.Cmindestensmtl.Amtl.Cmonatlichn.An.n.Chr.An.Chr.nat.Anat.o.Ao.o.0Ao.0o.OAo.Oo.a.Ao.a.o.g.Ao.g.o.k.Ao.k.o.oAo.oo.ä.Ao.ä.o_0Ao_0o_OAo_Oo_oAo_oorig.Aorig.Coriginalp.Ap.p.a.Ap.a.p.s.Ap.s.pers.Apers.phil.Aphil.q.Aq.q.e.d.Aq.e.d.r.Ar.rer.Arer.röm.Aröm.Crömischs'As'C'ss.As.s.o.As.o.sen.Asen.sie'sAsieA'sCessie’sAsieA’sCessog.Asog.std.Astd.stellv.Astellv.s’As’C'st.At.tägl.Atägl.Ctäglichu.Au.u.U.Au.U.u.a.Au.a.u.s.w.Au.s.w.u.v.m.Au.v.m.unter'mAunterA'mCdemunter’mAunterA’mCdemusf.Ausf.usw.Ausw.uvm.Auvm.v.Av.v.Chr.Av.Chr.v.a.Av.a.v.l.n.r.Av.l.n.r.v.vAv.vv_vAv_vvgl.Avgl.Cvergleichevllt.Avllt.Cvielleichtvlt.Avlt.Cvielleichtvor'mAvorA'mCdemvor’mAvorA’mCdemvs.Avs.w.Aw.wir'sAwirA'sCeswir’sAwirA’sCeswiss.Awiss.x.Ax.xDAxDxDDAxDDy.Ay.z.Az.z.B.Az.B.z.Bsp.Az.Bsp.z.T.Az.T.z.Z.Az.Z.z.Zt.Az.Zt.z.b.Az.b.zzgl.Azzgl. A C ¯\(ツ)/¯A¯\(ツ)/¯°C.A°ACA.°F.A°AFA.°K.A°AKA.°c.A°AcA.°f.A°AfA.°k.A°AkA.ä.Aä.ö.Aö.österr.Aösterr.Cösterreichischü.Aü.über'mAüberA'mCdemüber’mAüberA’mCdemಠ_ಠAಠ_ಠಠ︵ಠAಠ︵ಠ—A—’A’’SA’SC's’nA’nCein’neA’neCeine’nemA’nemCeinem’nenA’nenCeinen’sA’sC's’’A’’faster_heuristics
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/key2row b/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/key2row
new file mode 100644
index 0000000..5416677
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/key2row
@@ -0,0 +1 @@
+
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/lookups.bin b/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/lookups.bin
new file mode 100644
index 0000000..5416677
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/lookups.bin
@@ -0,0 +1 @@
+
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/strings.json b/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/strings.json
new file mode 100644
index 0000000..7569f1d
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/strings.json
@@ -0,0 +1,1585 @@
+[
+ "\t",
+ "\n",
+ " ",
+ " ",
+ "\"",
+ "$",
+ "%",
+ "'",
+ "''",
+ "'-(",
+ "'-)",
+ "'S",
+ "'X",
+ "'m",
+ "'n",
+ "'ne",
+ "'nem",
+ "'nen",
+ "'s",
+ "'x",
+ "'xx",
+ "'xxx",
+ "(",
+ "(((",
+ "(*>",
+ "(*_*)",
+ "(-8",
+ "(-:",
+ "(-;",
+ "(-_-)",
+ "(-d",
+ "(._.)",
+ "(:",
+ "(;",
+ "(=",
+ "(>_<)",
+ "(^_^)",
+ "(o:",
+ "(x:",
+ "(x_x)",
+ "(\u00ac_\u00ac)",
+ "(\u0ca0_\u0ca0)",
+ "(\u256f\u00b0\u25a1\u00b0\uff09\u256f\ufe35\u253b\u2501\u253b",
+ ")",
+ ")))",
+ ")-:",
+ ")/\u00af",
+ "):",
+ "*",
+ "+",
+ ",",
+ "-",
+ "-((",
+ "-))",
+ "-0",
+ "-3",
+ "-8",
+ "-D",
+ "-O",
+ "-P",
+ "-X",
+ "-_-",
+ "-__-",
+ "-d",
+ "-o",
+ "-p",
+ "-x",
+ "-|",
+ ".",
+ ".A.",
+ ".B.",
+ ".C.",
+ ".D.",
+ ".E.",
+ ".G.",
+ ".H.",
+ ".K.",
+ ".M.",
+ ".O.",
+ ".P.",
+ ".R.",
+ ".S.",
+ ".Sc",
+ ".T.",
+ ".U.",
+ ".V.",
+ ".Y.",
+ ".Z.",
+ "._.",
+ ".a.",
+ ".b.",
+ ".c.",
+ ".d.",
+ ".e.",
+ ".g.",
+ ".h.",
+ ".k.",
+ ".m.",
+ ".o.",
+ ".r.",
+ ".s.",
+ ".w.",
+ ".\u00e4.",
+ "/",
+ "/3",
+ "/Core+",
+ "/Xxxx+",
+ "/core+",
+ "/d",
+ "/xxxx+",
+ "0",
+ "0%+",
+ "0.0",
+ "0.o",
+ "022",
+ "032",
+ "034",
+ "0_0",
+ "0_o",
+ "1",
+ "1.",
+ "10",
+ "12",
+ "2",
+ "2.",
+ "20",
+ "2022",
+ "2032",
+ "2034",
+ "250",
+ "3",
+ "3.",
+ "33",
+ "333",
+ "35",
+ "5",
+ "50",
+ "7",
+ "7,50%+",
+ "8",
+ "8)",
+ "8-",
+ "8-)",
+ "8-D",
+ "8-d",
+ "8D",
+ "8d",
+ ":",
+ ":'(",
+ ":')",
+ ":'-(",
+ ":'-)",
+ ":(",
+ ":((",
+ ":(((",
+ ":()",
+ ":)",
+ ":))",
+ ":)))",
+ ":*",
+ ":-(",
+ ":-((",
+ ":-(((",
+ ":-)",
+ ":-))",
+ ":-)))",
+ ":-*",
+ ":-/",
+ ":-0",
+ ":-3",
+ ":->",
+ ":-D",
+ ":-O",
+ ":-P",
+ ":-X",
+ ":-]",
+ ":-d",
+ ":-o",
+ ":-p",
+ ":-x",
+ ":-|",
+ ":-}",
+ ":/",
+ ":0",
+ ":1",
+ ":3",
+ ":>",
+ ":D",
+ ":O",
+ ":P",
+ ":X",
+ ":]",
+ ":d",
+ ":o",
+ ":o)",
+ ":p",
+ ":x",
+ ":x)",
+ ":|",
+ ":}",
+ ":\u2019(",
+ ":\u2019)",
+ ":\u2019-(",
+ ":\u2019-)",
+ ";",
+ ";)",
+ ";-)",
+ ";-D",
+ ";-X",
+ ";-d",
+ ";D",
+ ";X",
+ ";_;",
+ ";d",
+ "<",
+ "<.<",
+ "3",
+ "",
+ "",
+ "=",
+ "=(",
+ "=)",
+ "=/",
+ "=3",
+ "=D",
+ "=X",
+ "=[",
+ "=]",
+ "=d",
+ "=|",
+ ">",
+ ">.<",
+ ">.>",
+ ">:(",
+ ">:o",
+ ">:x",
+ "><(((*>",
+ "@",
+ "@_@",
+ "A",
+ "A.",
+ "A.C.",
+ "A.D.",
+ "A.G.",
+ "Abb",
+ "Abb.",
+ "Abbildung",
+ "Abk",
+ "Abk.",
+ "Abk\u00fcrzung",
+ "Abs",
+ "Abs.",
+ "Abt",
+ "Abt.",
+ "Abteilung",
+ "Add",
+ "Aktueller",
+ "Allgemeine",
+ "Amsterdam",
+ "Anlagestrategien",
+ "Anlagevehikels",
+ "Ansprechpartners",
+ "Antagevehikels",
+ "Apr",
+ "Apr.",
+ "April",
+ "Art",
+ "Assets",
+ "Aufl\u00f6sung",
+ "Aufwertung",
+ "Aug",
+ "Aug.",
+ "August",
+ "B",
+ "B.",
+ "B.A.",
+ "B.Sc",
+ "B.Sc.",
+ "Bahnhof",
+ "Band",
+ "Bd",
+ "Bd.",
+ "Beispiel",
+ "Berlin",
+ "Bestandsentwicklungen",
+ "Betr",
+ "Betr.",
+ "Betreff",
+ "Bf",
+ "Bf.",
+ "Bhf",
+ "Bhf.",
+ "Biol",
+ "Biol.",
+ "Bsp",
+ "Bsp.",
+ "C",
+ "C++",
+ "C.",
+ "CDU",
+ "CDU/CSU",
+ "CSU",
+ "Chr",
+ "Chr.",
+ "Cie",
+ "Cie.",
+ "Cities",
+ "Closings",
+ "Co",
+ "Co.",
+ "Core",
+ "Core+",
+ "Core+/Value",
+ "D",
+ "D.",
+ "D.C.",
+ "Deutschland",
+ "Deutschlands",
+ "Dez",
+ "Dez.",
+ "Dezember",
+ "Di",
+ "Di.",
+ "Dienstag",
+ "Different",
+ "Dipl",
+ "Dipl.",
+ "Dipl.-Ing",
+ "Dipl.-Ing.",
+ "Do",
+ "Do.",
+ "Donnerstag",
+ "Dr",
+ "Dr.",
+ "D\u00e4nemark",
+ "E",
+ "E-Mail",
+ "E.",
+ "Einw",
+ "Europe",
+ "European",
+ "Exit",
+ "F",
+ "F.",
+ "FIL",
+ "Fa",
+ "Fa.",
+ "Fam",
+ "Fam.",
+ "Familie",
+ "Feb",
+ "Feb.",
+ "Februar",
+ "Firma",
+ "Fond",
+ "Fonds",
+ "Fr",
+ "Fr.",
+ "Frankreich",
+ "Frau",
+ "Frl",
+ "Frl.",
+ "Fr\u00e4ulein",
+ "Fu\u0308hrende",
+ "G",
+ "G.",
+ "G.m.b",
+ "G.m.b.H.",
+ "Gateway",
+ "Gebr",
+ "Gebr.",
+ "Geplantes",
+ "Gesamtrendite",
+ "H",
+ "H.",
+ "Halten",
+ "Halten-Strategie",
+ "Hauptbahnhof",
+ "Hbf",
+ "Hbf.",
+ "Herr",
+ "Herrn",
+ "Hg",
+ "Hg.",
+ "Hr",
+ "Hr.",
+ "Hrn",
+ "Hrn.",
+ "Hrsg",
+ "Hrsg.",
+ "I",
+ "I.",
+ "II",
+ "II.",
+ "III",
+ "III.",
+ "INREV",
+ "IRR",
+ "IV",
+ "IV.",
+ "Immobilien",
+ "Immobilien-Spezialfonds",
+ "Inc",
+ "Inc.",
+ "Informationen",
+ "Ing",
+ "Ing.",
+ "Investmentmanagers",
+ "J",
+ "Jahr",
+ "Jahre",
+ "Jahrhundert",
+ "Jan",
+ "Jan.",
+ "Januar",
+ "Jh",
+ "Jh.",
+ "Jhd",
+ "Jhd.",
+ "Jr",
+ "Jr.",
+ "Jul",
+ "Jul.",
+ "Juli",
+ "Jun",
+ "Jun.",
+ "Juni",
+ "K",
+ "K.",
+ "K.O.",
+ "Kaufen",
+ "Key",
+ "L",
+ "L'",
+ "L.A.",
+ "LTV",
+ "LTY",
+ "Laufzeit",
+ "London",
+ "L\u00e4nderallokation",
+ "L\u2019",
+ "M",
+ "M.",
+ "M.A.",
+ "M.Sc",
+ "M.Sc.",
+ "Manager",
+ "Maximaler",
+ "Mehrwertsteuer",
+ "Metropolregionen",
+ "Mi",
+ "Mi.",
+ "Milliarde",
+ "Million",
+ "Mio",
+ "Mio.",
+ "Mittwoch",
+ "Mo",
+ "Mo.",
+ "Montag",
+ "Mr",
+ "Mr.",
+ "Mrd",
+ "Mrd.",
+ "Mrz",
+ "Mrz.",
+ "MwSt",
+ "MwSt.",
+ "M\u00e4r",
+ "M\u00e4r.",
+ "M\u00e4rz",
+ "N",
+ "N.Y.",
+ "N.Y.C.",
+ "Nachvermietungsstrategie",
+ "Name",
+ "Niederlande",
+ "Nov",
+ "Nov.",
+ "November",
+ "Nr",
+ "Nr.",
+ "Nummer",
+ "O",
+ "O.",
+ "O.K.",
+ "O.O",
+ "O.o",
+ "O_O",
+ "O_o",
+ "Offen",
+ "Offener",
+ "Okt",
+ "Okt.",
+ "Oktober",
+ "OpCo",
+ "Orig",
+ "Orig.",
+ "Original",
+ "P",
+ "P.S.",
+ "Paris",
+ "Pkt",
+ "Pkt.",
+ "Prof",
+ "Prof.",
+ "Professor",
+ "Punkt",
+ "R",
+ "R.",
+ "R.I.P.",
+ "RE",
+ "REV",
+ "RISIKOPROFIL",
+ "ROOT",
+ "Rechtsform",
+ "Red",
+ "Red.",
+ "Redaktion",
+ "Risikoprofil",
+ "Risk",
+ "S",
+ "S'",
+ "Sa",
+ "Sa.",
+ "Samstag",
+ "Sc.",
+ "Schweden",
+ "Sep",
+ "Sep.",
+ "Sept",
+ "Sept.",
+ "September",
+ "Sitz",
+ "Skandinavien",
+ "So",
+ "So.",
+ "Sonntag",
+ "St",
+ "St.",
+ "Standortaufwertungsstrategie",
+ "Standorte",
+ "Std",
+ "Std.",
+ "Stil",
+ "Str",
+ "Str.",
+ "Strategie",
+ "Stra\u00dfe",
+ "Struktur",
+ "Stunde",
+ "S\u2019",
+ "T",
+ "T.",
+ "Tausend",
+ "Tel",
+ "Tel.",
+ "Telefon",
+ "Telefonnummer",
+ "The",
+ "Tr",
+ "Tr.",
+ "Tsd",
+ "Tsd.",
+ "U",
+ "U.",
+ "U.S.",
+ "U.S.A.",
+ "U.S.S.",
+ "Univ",
+ "Univ.",
+ "Universit\u00e4t",
+ "V",
+ "V.",
+ "V.V",
+ "V_V",
+ "Value",
+ "Vol",
+ "Vol.",
+ "W",
+ "Wertstabile",
+ "Wohnimmobilien",
+ "X'",
+ "X++",
+ "X-Xxxx",
+ "X.",
+ "X.X",
+ "X.X.",
+ "X.X.X.",
+ "X.Xx",
+ "X.Xx.",
+ "X.x",
+ "X.x.x",
+ "X.x.x.X.",
+ "XD",
+ "XDD",
+ "XX",
+ "XX.",
+ "XXX",
+ "XXX.",
+ "XXX/XXX",
+ "XXXX",
+ "X_X",
+ "X_x",
+ "Xx",
+ "Xx.",
+ "XxXx",
+ "XxXx.",
+ "Xxx",
+ "Xxx.",
+ "Xxxx",
+ "Xxxx+",
+ "Xxxx+/Xxxxx",
+ "Xxxx-XXX",
+ "Xxxx-Xxxxx-XXX",
+ "Xxxx.",
+ "Xxxx.-Xxx",
+ "Xxxx.-Xxx.",
+ "Xxxxx",
+ "Xxxxx)/Xxxx",
+ "Xxxxx-Xxxxx",
+ "Xx\u0308xxxx",
+ "X\u2019",
+ "Z",
+ "Z.",
+ "Ziel-LTY",
+ "Ziel-Netto-IRR",
+ "Zielanlagestrategie",
+ "Zielregionfen)/Jand",
+ "Zielsektoren",
+ "Zielvolumen",
+ "Ziirraiaein",
+ "Zt",
+ "Zt.",
+ "[",
+ "[-:",
+ "[:",
+ "[=",
+ "\\",
+ "\\\")",
+ "\\n",
+ "\\t",
+ "\\x",
+ "]",
+ "]=",
+ "^",
+ "^_^",
+ "^__^",
+ "^___^",
+ "_*)",
+ "_-)",
+ "_.)",
+ "_<)",
+ "_^)",
+ "__-",
+ "__^",
+ "_\u00ac)",
+ "_\u0ca0)",
+ "`",
+ "``",
+ "a",
+ "a.",
+ "a.D.",
+ "a.M.",
+ "a.Z.",
+ "a.c.",
+ "a.d.",
+ "a.g.",
+ "a.m.",
+ "a.z.",
+ "abb",
+ "abb.",
+ "abk",
+ "abk.",
+ "abs",
+ "abs.",
+ "abt",
+ "abt.",
+ "abzgl",
+ "abzgl.",
+ "abz\u00fcglich",
+ "ace",
+ "add",
+ "adv",
+ "adv.",
+ "ahr",
+ "ail",
+ "aiming",
+ "aktueller",
+ "al",
+ "al.",
+ "allg",
+ "allg.",
+ "allgemein",
+ "allgemeine",
+ "am.",
+ "ame",
+ "amsterdam",
+ "an.",
+ "and",
+ "anlagestrategien",
+ "anlagevehikels",
+ "ansprechpartners",
+ "antagevehikels",
+ "apr",
+ "apr.",
+ "ark",
+ "art",
+ "asset",
+ "assets",
+ "at",
+ "at.",
+ "ath",
+ "auf",
+ "aufl\u00f6sung",
+ "aufwertung",
+ "auf\u2019m",
+ "aug",
+ "aug.",
+ "ausgew\u00e4hlte",
+ "ax.",
+ "b",
+ "b.",
+ "b.a.",
+ "b.sc",
+ "b.sc.",
+ "bb.",
+ "bd",
+ "bd.",
+ "beispielsweise",
+ "ber",
+ "berlin",
+ "bestandsentwicklungen",
+ "betr",
+ "betr.",
+ "beziehungsweise",
+ "bez\u00fcglich",
+ "bf",
+ "bf.",
+ "bhf",
+ "bhf.",
+ "biol",
+ "biol.",
+ "bk.",
+ "br.",
+ "bs.",
+ "bsp",
+ "bsp.",
+ "bspw",
+ "bspw.",
+ "bt.",
+ "bzgl",
+ "bzgl.",
+ "bzw",
+ "bzw.",
+ "c",
+ "c++",
+ "c.",
+ "c/o",
+ "ca",
+ "ca.",
+ "cal",
+ "cdu",
+ "cdu/csu",
+ "ce>",
+ "chr",
+ "chr.",
+ "cht",
+ "cie",
+ "cie.",
+ "cities",
+ "cl.",
+ "closings",
+ "co",
+ "co.",
+ "core",
+ "core+",
+ "core+/value",
+ "csu",
+ "cts",
+ "d",
+ "d'",
+ "d)",
+ "d,dd%+",
+ "d-",
+ "d-)",
+ "d-X",
+ "d.",
+ "d.c.",
+ "d.d",
+ "d.h",
+ "d.h.",
+ "d.x",
+ "dX",
+ "d_d",
+ "d_x",
+ "dam",
+ "dd",
+ "ddd",
+ "dddd",
+ "de",
+ "ded",
+ "dem",
+ "den",
+ "der",
+ "dergleichen",
+ "des",
+ "deutschland",
+ "deutschlands",
+ "development",
+ "dez",
+ "dez.",
+ "dgl",
+ "dgl.",
+ "di",
+ "di.",
+ "different",
+ "dipl",
+ "dipl.",
+ "dipl.-ing",
+ "dipl.-ing.",
+ "do",
+ "do.",
+ "don",
+ "dr",
+ "dr.",
+ "du",
+ "du\u2019s",
+ "dv.",
+ "d\u00e4nemark",
+ "d\u2019",
+ "e",
+ "e-mail",
+ "e.",
+ "e.V.",
+ "e.d",
+ "e.g",
+ "e.g.",
+ "e.v.",
+ "ean",
+ "eb.",
+ "ebd",
+ "ebd.",
+ "ebenda",
+ "ebr",
+ "ed.",
+ "egr",
+ "egy",
+ "ehem",
+ "ehem.",
+ "eigentlich",
+ "eigtl",
+ "eigtl.",
+ "ein",
+ "eine",
+ "einem",
+ "einen",
+ "einw",
+ "eit",
+ "el.",
+ "els",
+ "em.",
+ "en.",
+ "engl",
+ "engl.",
+ "englisch",
+ "enhancing",
+ "ent",
+ "entspr",
+ "entspr.",
+ "ep.",
+ "ept",
+ "er",
+ "er.",
+ "erm",
+ "erm.",
+ "err",
+ "ers",
+ "ersten",
+ "er\u2019s",
+ "es",
+ "etc",
+ "etc.",
+ "etr",
+ "ets",
+ "europe",
+ "european",
+ "ev",
+ "ev.",
+ "eventuell",
+ "evtl",
+ "evtl.",
+ "exit",
+ "expertise",
+ "exposure",
+ "ez.",
+ "e\u2019s",
+ "f",
+ "f.",
+ "fa",
+ "fa.",
+ "fam",
+ "fam.",
+ "feb",
+ "feb.",
+ "fen",
+ "festgelegter",
+ "fil",
+ "fond",
+ "fonds",
+ "fr",
+ "fr.",
+ "frankreich",
+ "franz\u00f6sisch",
+ "frl",
+ "frl.",
+ "frz",
+ "frz.",
+ "fs.",
+ "fund",
+ "fu\u0308hrende",
+ "f\u2019m",
+ "g",
+ "g.",
+ "g.m.b",
+ "g.m.b.h.",
+ "gateway",
+ "geb",
+ "geb.",
+ "gebr",
+ "gebr.",
+ "gegebenenfalls",
+ "gegen\u00fcber",
+ "gegr",
+ "gegr.",
+ "gegr\u00fcndet",
+ "gem",
+ "gem.",
+ "gen",
+ "geplantes",
+ "ger",
+ "gesamtrendite",
+ "gf.",
+ "gfs",
+ "ggf",
+ "ggf.",
+ "ggfs",
+ "ggfs.",
+ "gg\u00fc",
+ "gg\u00fc.",
+ "gie",
+ "gl.",
+ "good",
+ "gr.",
+ "gtl",
+ "g\u00fc.",
+ "h",
+ "h.",
+ "h.c",
+ "h.c.",
+ "halten",
+ "halten-strategie",
+ "hbf",
+ "hbf.",
+ "hd.",
+ "hed",
+ "hem",
+ "hf.",
+ "hg",
+ "hg.",
+ "hil",
+ "hinter",
+ "hinter\u2019m",
+ "hotels",
+ "hr",
+ "hr.",
+ "hre",
+ "hrn",
+ "hrn.",
+ "hrsg",
+ "hrsg.",
+ "h\u2019s",
+ "i",
+ "i.",
+ "i.A.",
+ "i.G.",
+ "i.O.",
+ "i.Tr.",
+ "i.V.",
+ "i.a.",
+ "i.d",
+ "i.d.R.",
+ "i.d.r.",
+ "i.e",
+ "i.e.",
+ "i.g.",
+ "i.o.",
+ "i.tr.",
+ "i.v.",
+ "ich",
+ "ich\u2019s",
+ "ie.",
+ "ien",
+ "ies",
+ "ig.",
+ "ihr",
+ "ihr\u2019s",
+ "ii",
+ "ii.",
+ "iii",
+ "iii.",
+ "il.",
+ "ile",
+ "illustration",
+ "ime",
+ "immobilien",
+ "immobilien-spezialfonds",
+ "in",
+ "in.",
+ "inc",
+ "inc.",
+ "incl",
+ "incl.",
+ "ind",
+ "ine",
+ "informationen",
+ "ing",
+ "ing.",
+ "initiatives",
+ "inkl",
+ "inkl.",
+ "inklusive",
+ "inrev",
+ "insb",
+ "insb.",
+ "insbesondere",
+ "investmentmanagers",
+ "investments",
+ "inw",
+ "io.",
+ "iol",
+ "ion",
+ "ipl",
+ "irr",
+ "is",
+ "ise",
+ "isk",
+ "iss",
+ "ite",
+ "ith",
+ "ity",
+ "itz",
+ "ium",
+ "iv",
+ "iv.",
+ "j",
+ "j.",
+ "jahr",
+ "jahre",
+ "jan",
+ "jan.",
+ "jh",
+ "jh.",
+ "jhd",
+ "jhd.",
+ "jr",
+ "jr.",
+ "jul",
+ "jul.",
+ "jun",
+ "jun.",
+ "jur",
+ "jur.",
+ "k",
+ "k.",
+ "k.o.",
+ "kath",
+ "kath.",
+ "katholisch",
+ "kaufen",
+ "ket",
+ "key",
+ "kl.",
+ "kt.",
+ "l",
+ "l'",
+ "l.",
+ "l.a.",
+ "langfristig",
+ "lat",
+ "lat.",
+ "laufzeit",
+ "laut",
+ "le.g",
+ "ler",
+ "level",
+ "lg.",
+ "lin",
+ "lio",
+ "llg",
+ "llt",
+ "llv",
+ "london",
+ "lt",
+ "lt.",
+ "lte",
+ "ltv",
+ "lty",
+ "lue",
+ "lv.",
+ "l\u00e4nderallokation",
+ "l\u2019",
+ "m",
+ "m.",
+ "m.E.",
+ "m.M.",
+ "m.a.",
+ "m.b",
+ "m.e.",
+ "m.m.",
+ "m.sc",
+ "m.sc.",
+ "mal",
+ "management",
+ "manager",
+ "market",
+ "max",
+ "max.",
+ "maximal",
+ "maximaler",
+ "men",
+ "mer",
+ "metropolregionen",
+ "mi",
+ "mi.",
+ "million",
+ "min",
+ "min.",
+ "mind",
+ "mind.",
+ "mindestens",
+ "minimal",
+ "minor",
+ "mio",
+ "mio.",
+ "mit",
+ "mo",
+ "mo.",
+ "monatlich",
+ "mr",
+ "mr.",
+ "mrd",
+ "mrd.",
+ "mrz",
+ "mrz.",
+ "mtl",
+ "mtl.",
+ "mwst",
+ "mwst.",
+ "m\u00e4r",
+ "m\u00e4r.",
+ "n",
+ "n.",
+ "n.Chr.",
+ "n.chr.",
+ "n.r",
+ "n.y.",
+ "n.y.c.",
+ "nachvermietungsstrategie",
+ "name",
+ "nat",
+ "nat.",
+ "nc.",
+ "ncl",
+ "nd.",
+ "nde",
+ "nds",
+ "ne",
+ "nem",
+ "nen",
+ "ner",
+ "ng.",
+ "ngl",
+ "ngs",
+ "niederlande",
+ "niv",
+ "nkl",
+ "nor",
+ "nov",
+ "nov.",
+ "nr",
+ "nr.",
+ "nsb",
+ "nts",
+ "o",
+ "o.",
+ "o.0",
+ "o.O",
+ "o.a",
+ "o.a.",
+ "o.g",
+ "o.g.",
+ "o.k",
+ "o.k.",
+ "o.o",
+ "o.\u00e4",
+ "o.\u00e4.",
+ "o_0",
+ "o_O",
+ "o_o",
+ "of",
+ "of.",
+ "offen",
+ "offener",
+ "og.",
+ "okt",
+ "okt.",
+ "ol.",
+ "ond",
+ "ood",
+ "opco",
+ "ope",
+ "ore",
+ "orig",
+ "orig.",
+ "original",
+ "orm",
+ "ov.",
+ "over",
+ "p",
+ "p.",
+ "p.a",
+ "p.a.",
+ "p.s",
+ "p.s.",
+ "pCo",
+ "paris",
+ "pco",
+ "pers",
+ "pers.",
+ "phil",
+ "phil.",
+ "pkt",
+ "pkt.",
+ "pl.",
+ "portfolio",
+ "pr.",
+ "premium",
+ "prof",
+ "prof.",
+ "profile",
+ "projects",
+ "pt.",
+ "pw.",
+ "q",
+ "q.",
+ "q.e.d",
+ "q.e.d.",
+ "quality",
+ "r",
+ "r.",
+ "r.i.p.",
+ "rd.",
+ "re",
+ "re+",
+ "rechtsform",
+ "red",
+ "red.",
+ "ren",
+ "rer",
+ "rer.",
+ "rev",
+ "rig",
+ "ris",
+ "risikoprofil",
+ "risk",
+ "rl.",
+ "rm.",
+ "rn.",
+ "rof",
+ "rr.",
+ "rs.",
+ "rsg",
+ "rte",
+ "rz.",
+ "r\u00f6m",
+ "r\u00f6m.",
+ "r\u00f6misch",
+ "r\u2019m",
+ "r\u2019s",
+ "s",
+ "s'",
+ "s.",
+ "s.o",
+ "s.o.",
+ "s.w",
+ "sa",
+ "sa.",
+ "sb.",
+ "schweden",
+ "sd.",
+ "sen",
+ "sen.",
+ "sep",
+ "sep.",
+ "sept",
+ "sept.",
+ "set",
+ "sf.",
+ "sg.",
+ "sie",
+ "sie\u2019s",
+ "sitz",
+ "skandinavien",
+ "so",
+ "so.",
+ "sog",
+ "sog.",
+ "sp.",
+ "space",
+ "spr",
+ "spw",
+ "ss.",
+ "st",
+ "st.",
+ "standortaufwertungsstrategie",
+ "standorte",
+ "std",
+ "std.",
+ "stellv",
+ "stellv.",
+ "stil",
+ "str",
+ "str.",
+ "strategie",
+ "strategy",
+ "struktur",
+ "sw.",
+ "s\u2019",
+ "t",
+ "t.",
+ "tactical",
+ "tc.",
+ "td.",
+ "tel",
+ "tel.",
+ "telefonnummer",
+ "ten",
+ "ter",
+ "tes",
+ "th.",
+ "the",
+ "tig",
+ "til",
+ "time",
+ "tl.",
+ "to",
+ "tr",
+ "tr.",
+ "tsd",
+ "tsd.",
+ "tur",
+ "t\u00e4gl",
+ "t\u00e4gl.",
+ "t\u00e4glich",
+ "u",
+ "u.",
+ "u.U.",
+ "u.a",
+ "u.a.",
+ "u.s.",
+ "u.s.a.",
+ "u.s.s.",
+ "u.s.w",
+ "u.s.w.",
+ "u.u.",
+ "u.v.m",
+ "u.v.m.",
+ "ug.",
+ "ul.",
+ "un.",
+ "und",
+ "ung",
+ "univ",
+ "univ.",
+ "unter",
+ "unter\u2019m",
+ "ur.",
+ "ure",
+ "usf",
+ "usf.",
+ "usw",
+ "usw.",
+ "uvm",
+ "uvm.",
+ "u\u2019s",
+ "v",
+ "v.",
+ "v.Chr.",
+ "v.a",
+ "v.a.",
+ "v.chr.",
+ "v.l.n.r",
+ "v.l.n.r.",
+ "v.m",
+ "v.v",
+ "v_v",
+ "value",
+ "value-added",
+ "vel",
+ "ver",
+ "vergleiche",
+ "ves",
+ "vgl",
+ "vgl.",
+ "vielleicht",
+ "vllt",
+ "vllt.",
+ "vlt",
+ "vlt.",
+ "vm.",
+ "vol",
+ "vol.",
+ "vom",
+ "vor",
+ "vor\u2019m",
+ "vs",
+ "vs.",
+ "vtl",
+ "w",
+ "w.",
+ "wSt",
+ "way",
+ "well-established",
+ "wertstabile",
+ "wir",
+ "wir\u2019s",
+ "wiss",
+ "wiss.",
+ "with",
+ "wohnimmobilien",
+ "x",
+ "x'",
+ "x-xxxx",
+ "x.",
+ "x.X",
+ "x.X.",
+ "x.Xx.",
+ "x.Xxx.",
+ "x.d",
+ "x.x",
+ "x.x.",
+ "x.x.X.",
+ "x.x.x",
+ "x.x.x.",
+ "x.x.x.x",
+ "x.x.x.x.",
+ "x/x",
+ "xD",
+ "xDD",
+ "xX",
+ "xXX",
+ "x_X",
+ "x_d",
+ "x_x",
+ "xd",
+ "xdd",
+ "xit",
+ "xx",
+ "xx.",
+ "xx.x",
+ "xxx",
+ "xxx.",
+ "xxxx",
+ "xxxx)/xxxx",
+ "xxxx+",
+ "xxxx+/xxxx",
+ "xxxx-xxx",
+ "xxxx-xxxx",
+ "xxxx-xxxx-xxx",
+ "xxxx.",
+ "xxxx\u2019x",
+ "xxx\u2019x",
+ "xx\u0308xxxx",
+ "xx\u2019x",
+ "x\u2019",
+ "x\ufe35x",
+ "y",
+ "y.",
+ "z",
+ "z.",
+ "z.B.",
+ "z.Bsp.",
+ "z.T.",
+ "z.Z.",
+ "z.Zt.",
+ "z.b",
+ "z.b.",
+ "z.bsp.",
+ "z.t.",
+ "z.z.",
+ "z.zt.",
+ "zgl",
+ "ziel-lty",
+ "ziel-netto-irr",
+ "zielanlagestrategie",
+ "zielregionfen)/jand",
+ "zielsektoren",
+ "zielvolumen",
+ "ziirraiaein",
+ "zt",
+ "zw.",
+ "zzgl",
+ "zzgl.",
+ "|",
+ "}",
+ "\u00a0",
+ "\u00ac",
+ "\u00ac_\u00ac",
+ "\u00af",
+ "\u00af\\(x)/\u00af",
+ "\u00af\\(\u30c4)/\u00af",
+ "\u00b0",
+ "\u00b0C.",
+ "\u00b0F.",
+ "\u00b0K.",
+ "\u00b0X.",
+ "\u00b0c.",
+ "\u00b0f.",
+ "\u00b0k.",
+ "\u00b0x.",
+ "\u00dc",
+ "\u00dcbersicht",
+ "\u00e4",
+ "\u00e4.",
+ "\u00e4gl",
+ "\u00e4r.",
+ "\u00f6",
+ "\u00f6.",
+ "\u00f6m.",
+ "\u00f6sterr",
+ "\u00f6sterr.",
+ "\u00f6sterreichisch",
+ "\u00fc",
+ "\u00fc.",
+ "\u00fcber",
+ "\u00fcbersicht",
+ "\u00fcber\u2019m",
+ "\u0ca0",
+ "\u0ca0_\u0ca0",
+ "\u0ca0\ufe35\u0ca0",
+ "\u2014",
+ "\u2019",
+ "\u2019-(",
+ "\u2019-)",
+ "\u2019S",
+ "\u2019X",
+ "\u2019m",
+ "\u2019n",
+ "\u2019ne",
+ "\u2019nem",
+ "\u2019nen",
+ "\u2019s",
+ "\u2019x",
+ "\u2019xx",
+ "\u2019xxx",
+ "\u2019\u2019",
+ "\u201a",
+ "\u20ac",
+ "\u2501",
+ "\u253b",
+ "\u253b\u2501\u253b",
+ "\u256f",
+ "\u25a1",
+ "\ufe35",
+ "\uff09"
+]
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/vectors b/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/vectors
new file mode 100644
index 0000000..ebadaa5
Binary files /dev/null and b/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/vectors differ
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/vectors.cfg b/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/vectors.cfg
new file mode 100644
index 0000000..32c800a
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/vectors.cfg
@@ -0,0 +1,3 @@
+{
+ "mode":"default"
+}
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/config.cfg b/prototypes/arc2_prototype/spacy_service/models/model-last/config.cfg
new file mode 100644
index 0000000..1cf80c4
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-last/config.cfg
@@ -0,0 +1,145 @@
+[paths]
+train = "./data/train.spacy"
+dev = "./data/train.spacy"
+vectors = null
+init_tok2vec = null
+
+[system]
+gpu_allocator = null
+seed = 0
+
+[nlp]
+lang = "de"
+pipeline = ["tok2vec","ner"]
+batch_size = 1000
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+vectors = {"@vectors":"spacy.Vectors.v1"}
+
+[components]
+
+[components.ner]
+factory = "ner"
+incorrect_spans_key = null
+moves = null
+scorer = {"@scorers":"spacy.ner_scorer.v1"}
+update_with_oracle_cut_size = 100
+
+[components.ner.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "ner"
+extra_state_tokens = false
+hidden_width = 64
+maxout_pieces = 2
+use_upper = true
+nO = null
+
+[components.ner.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+upstream = "*"
+
+[components.tok2vec]
+factory = "tok2vec"
+
+[components.tok2vec.model]
+@architectures = "spacy.Tok2Vec.v2"
+
+[components.tok2vec.model.embed]
+@architectures = "spacy.MultiHashEmbed.v2"
+width = ${components.tok2vec.model.encode.width}
+attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
+rows = [5000,1000,2500,2500]
+include_static_vectors = false
+
+[components.tok2vec.model.encode]
+@architectures = "spacy.MaxoutWindowEncoder.v2"
+width = 96
+depth = 4
+window_size = 1
+maxout_pieces = 3
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[training]
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+accumulate_gradient = 1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_components = []
+before_to_disk = null
+before_update = null
+
+[training.batcher]
+@batchers = "spacy.batch_by_words.v1"
+discard_oversize = false
+tolerance = 0.2
+get_length = null
+
+[training.batcher.size]
+@schedules = "compounding.v1"
+start = 100
+stop = 1000
+compound = 1.001
+t = 0.0
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+[training.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = false
+eps = 0.00000001
+learn_rate = 0.001
+
+[training.score_weights]
+ents_f = 1.0
+ents_p = 0.0
+ents_r = 0.0
+ents_per_type = null
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.tokenizer]
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/meta.json b/prototypes/arc2_prototype/spacy_service/models/model-last/meta.json
new file mode 100644
index 0000000..daabc76
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-last/meta.json
@@ -0,0 +1,52 @@
+{
+ "lang":"de",
+ "name":"pipeline",
+ "version":"0.0.0",
+ "spacy_version":">=3.7.2,<3.8.0",
+ "description":"",
+ "author":"",
+ "email":"",
+ "url":"",
+ "license":"",
+ "spacy_git_version":"a89eae928",
+ "vectors":{
+ "width":0,
+ "vectors":0,
+ "keys":0,
+ "name":null,
+ "mode":"default"
+ },
+ "labels":{
+ "tok2vec":[
+
+ ],
+ "ner":[
+ "RISIKOPROFIL"
+ ]
+ },
+ "pipeline":[
+ "tok2vec",
+ "ner"
+ ],
+ "components":[
+ "tok2vec",
+ "ner"
+ ],
+ "disabled":[
+
+ ],
+ "performance":{
+ "ents_f":1.0,
+ "ents_p":1.0,
+ "ents_r":1.0,
+ "ents_per_type":{
+ "RISIKOPROFIL":{
+ "p":1.0,
+ "r":1.0,
+ "f":1.0
+ }
+ },
+ "tok2vec_loss":0.000000029,
+ "ner_loss":0.0000000614
+ }
+}
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/ner/cfg b/prototypes/arc2_prototype/spacy_service/models/model-last/ner/cfg
new file mode 100644
index 0000000..6cd11cf
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-last/ner/cfg
@@ -0,0 +1,13 @@
+{
+ "moves":null,
+ "update_with_oracle_cut_size":100,
+ "multitasks":[
+
+ ],
+ "min_action_freq":1,
+ "learn_tokens":false,
+ "beam_width":1,
+ "beam_density":0.0,
+ "beam_update_prob":0.0,
+ "incorrect_spans_key":null
+}
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/ner/model b/prototypes/arc2_prototype/spacy_service/models/model-last/ner/model
new file mode 100644
index 0000000..8a0c5ae
Binary files /dev/null and b/prototypes/arc2_prototype/spacy_service/models/model-last/ner/model differ
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/ner/moves b/prototypes/arc2_prototype/spacy_service/models/model-last/ner/moves
new file mode 100644
index 0000000..e72ba15
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-last/ner/moves
@@ -0,0 +1 @@
+movesx{"0":{},"1":{"RISIKOPROFIL":45},"2":{"RISIKOPROFIL":45},"3":{"RISIKOPROFIL":45},"4":{"RISIKOPROFIL":45,"":1},"5":{"":1}}cfgneg_key
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/tok2vec/cfg b/prototypes/arc2_prototype/spacy_service/models/model-last/tok2vec/cfg
new file mode 100644
index 0000000..0e0dcd2
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-last/tok2vec/cfg
@@ -0,0 +1,3 @@
+{
+
+}
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/tok2vec/model b/prototypes/arc2_prototype/spacy_service/models/model-last/tok2vec/model
new file mode 100644
index 0000000..1cfa6a5
Binary files /dev/null and b/prototypes/arc2_prototype/spacy_service/models/model-last/tok2vec/model differ
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/tokenizer b/prototypes/arc2_prototype/spacy_service/models/model-last/tokenizer
new file mode 100644
index 0000000..9cdc922
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-last/tokenizer
@@ -0,0 +1,3 @@
+prefix_search^``|^§|^%|^=|^—|^–|^\+(?![0-9])|^…|^……|^,|^:|^;|^\!|^\?|^¿|^؟|^¡|^\(|^\)|^\[|^\]|^\{|^\}|^<|^>|^_|^#|^\*|^&|^。|^?|^!|^,|^、|^;|^:|^~|^·|^।|^،|^۔|^؛|^٪|^\.\.+|^…|^\'|^"|^”|^“|^`|^‘|^´|^’|^‚|^,|^„|^»|^«|^「|^」|^『|^』|^(|^)|^〔|^〕|^【|^】|^《|^》|^〈|^〉|^〈|^〉|^⟦|^⟧|^\$|^£|^€|^¥|^฿|^US\$|^C\$|^A\$|^₽|^﷼|^₴|^₠|^₡|^₢|^₣|^₤|^₥|^₦|^₧|^₨|^₩|^₪|^₫|^€|^₭|^₮|^₯|^₰|^₱|^₲|^₳|^₴|^₵|^₶|^₷|^₸|^₹|^₺|^₻|^₼|^₽|^₾|^₿|^[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]suffix_search2''$|/$|…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|?$|!$|,$|、$|;$|:$|~$|·$|।$|،$|۔$|؛$|٪$|\.\.+$|…$|\'$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|($|)$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|〈$|〉$|⟦$|⟧$|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]$|(?<=[0-9])\+$|(?<=°[FfCcKk])\.$|(?<=[0-9])(?:\$|£|€|¥|฿|US\$|C\$|A\$|₽|﷼|₴|₠|₡|₢|₣|₤|₥|₦|₧|₨|₩|₪|₫|€|₭|₮|₯|₰|₱|₲|₳|₴|₵|₶|₷|₸|₹|₺|₻|₼|₽|₾|₿)$|(?<=[0-9])(?:km|km²|km³|m|m²|m³|dm|dm²|dm³|cm|cm²|cm³|mm|mm²|mm³|ha|µm|nm|yd|in|ft|kg|g|mg|µg|t|lb|oz|m/s|km/h|kmh|mph|hPa|Pa|mbar|mb|MB|kb|KB|gb|GB|tb|TB|T|G|M|K|%|км|км²|км³|м|м²|м³|дм|дм²|дм³|см|см²|см³|мм|мм²|мм³|нм|кг|г|мг|м/с|км/ч|кПа|Па|мбар|Кб|КБ|кб|Мб|МБ|мб|Гб|ГБ|гб|Тб|ТБ|тбكم|كم²|كم³|م|م²|م³|سم|سم²|سم³|مم|مم²|مم³|كم|غرام|جرام|جم|كغ|ملغ|كوب|اكواب)$|(?<=[a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F%²\-\+…|……|,|:|;|\!|\?|¿|؟|¡|\(|\)|\[|\]|\{|\}|<|>|_|#|\*|&|。|?|!|,|、|;|:|~|·|।|،|۔|؛|٪(?:\'"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉〈〉⟦⟧)])\.$|(?<=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F][A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\.$infix_finditerZ\.\.+|…|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]|(?<=[a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\.(?=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])[,!?](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])[:<>=](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F]),(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[0-9A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\/(?=[0-9A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])([\"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉〈〉⟦⟧\)\]\(\[])(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])--(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[0-9])-(?=[0-9])token_matchurl_match
(?u)^(?:(?:[\w\+\-\.]{2,})://)?(?:\S+(?::\S*)?@)?(?:(?!(?:10|127)(?:\.\d{1,3}){3})(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[A-Za-z0-9\u00a1-\uffff][A-Za-z0-9\u00a1-\uffff_-]{0,62})?[A-Za-z0-9\u00a1-\uffff]\.)+(?:[a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F]{2,63}))(?::\d{2,5})?(?:[/?#]\S*)?$exceptions A
+A
+ A 'A'''A'''SA'SC's'nA'nCein'neA'neCeine'nemA'nemCeinem'nenA'nenCeinen'sA'sC's(*_*)A(*_*)(-8A(-8(-:A(-:(-;A(-;(-_-)A(-_-)(._.)A(._.)(:A(:(;A(;(=A(=(>_<)A(>_<)(^_^)A(^_^)(o:A(o:(¬_¬)A(¬_¬)(ಠ_ಠ)A(ಠ_ಠ)(╯°□°)╯︵┻━┻A(╯°□°)╯︵┻━┻)-:A)-:):A):-_-A-_--__-A-__-._.A._.0.0A0.00.oA0.o0_0A0_00_oA0_o8)A8)8-)A8-)8-DA8-D8DA8D:'(A:'(:')A:'):'-(A:'-(:'-)A:'-):(A:(:((A:((:(((A:(((:()A:():)A:):))A:)):)))A:))):*A:*:-(A:-(:-((A:-((:-(((A:-(((:-)A:-):-))A:-)):-)))A:-))):-*A:-*:-/A:-/:-0A:-0:-3A:-3:->A:->:-DA:-D:-OA:-O:-PA:-P:-XA:-X:-]A:-]:-oA:-o:-pA:-p:-xA:-x:-|A:-|:-}A:-}:/A:/:0A:0:1A:1:3A:3:>A:>:DA:D:OA:O:PA:P:XA:X:]A:]:oA:o:o)A:o):pA:p:xA:x:|A:|:}A:}:’(A:’(:’)A:’):’-(A:’-(:’-)A:’-);)A;);-)A;-);-DA;-D;DA;D;_;A;_;<.A=(A=(=)A=)=/A=/=3A=3=DA=D=[A=[=]A=]=|A=|>..<>.>A>.>>:(A>:(>:oA>:o><(((*>A><(((*>@_@A@_@A.C.AA.C.A.D.AA.D.A.G.AA.G.Abb.AAbb.CAbbildungAbk.AAbk.CAbkürzungAbs.AAbs.Abt.AAbt.CAbteilungApr.AApr.CAprilAug.AAug.CAugustB.A.AB.A.B.Sc.AB.Sc.Bd.ABd.CBandBetr.ABetr.CBetreffBf.ABf.CBahnhofBhf.ABhf.CBahnhofBiol.ABiol.Bsp.ABsp.CBeispielC++AC++CDU/CSUACDU/CSUChr.AChr.Cie.ACie.Co.ACo.D.C.AD.C.Dez.ADez.CDezemberDi.ADi.CDienstagDipl.ADipl.Dipl.-Ing.ADipl.-Ing.Do.ADo.CDonnerstagDr.ADr.Fa.AFa.CFirmaFam.AFam.CFamilieFeb.AFeb.CFebruarFr.AFr.CFrauFrl.AFrl.CFräuleinG.m.b.H.AG.m.b.H.Gebr.AGebr.Hbf.AHbf.CHauptbahnhofHg.AHg.Hr.AHr.CHerrHrn.AHrn.CHerrnHrsg.AHrsg.I.AI.II.AII.III.AIII.IV.AIV.Inc.AInc.Ing.AIng.Jan.AJan.CJanuarJh.AJh.CJahrhundertJhd.AJhd.CJahrhundertJr.AJr.Jul.AJul.CJuliJun.AJun.CJuniK.O.AK.O.L'AL'L.A.AL.A.L’AL’M.A.AM.A.M.Sc.AM.Sc.Mi.AMi.CMittwochMio.AMio.CMillionMo.AMo.CMontagMr.AMr.Mrd.AMrd.CMilliardeMrz.AMrz.CMärzMwSt.AMwSt.CMehrwertsteuerMär.AMär.CMärzN.Y.AN.Y.N.Y.C.AN.Y.C.Nov.ANov.CNovemberNr.ANr.CNummerO.K.AO.K.O.OAO.OO.oAO.oO_OAO_OO_oAO_oOkt.AOkt.COktoberOrig.AOrig.COriginalP.S.AP.S.Pkt.APkt.CPunktProf.AProf.CProfessorR.I.P.AR.I.P.Red.ARed.CRedaktionS'AS'C'sSa.ASa.CSamstagSep.ASep.CSeptemberSept.ASept.CSeptemberSo.ASo.CSonntagSt.ASt.Std.AStd.CStundeStr.AStr.CStraßeS’AS’C'sTel.ATel.CTelefonTsd.ATsd.CTausendU.S.AU.S.U.S.A.AU.S.A.U.S.S.AU.S.S.Univ.AUniv.CUniversitätV.VAV.VV_VAV_VVol.AVol.XDAXDXDDAXDD[-:A[-:[:A[:[=A[=\")A\")\nA\n\tA\t]=A]=^_^A^_^^__^A^__^^___^A^___^``A``a.Aa.a.D.Aa.D.a.M.Aa.M.a.Z.Aa.Z.abzgl.Aabzgl.Cabzüglichadv.Aadv.al.Aal.allg.Aallg.Callgemeinauf'mAaufA'mCdemauf’mAaufA’mCdemb.Ab.betr.Abetr.biol.Abiol.bspw.Abspw.Cbeispielsweisebzgl.Abzgl.Cbezüglichbzw.Abzw.Cbeziehungsweisec.Ac.c/oAc/oca.Aca.co.Aco.d'Ad'd.Ad.d.h.Ad.h.dgl.Adgl.Cdergleichendu'sAduA'sCesdu’sAduA’sCesd’Ad’e.Ae.e.V.Ae.V.e.g.Ae.g.ebd.Aebd.Cebendaehem.Aehem.eigtl.Aeigtl.Ceigentlichengl.Aengl.Cenglischentspr.Aentspr.er'sAerA'sCeserm.Aerm.er’sAerA’sCesetc.Aetc.ev.Aev.evtl.Aevtl.Ceventuellf.Af.frz.Afrz.Cfranzösischg.Ag.geb.Ageb.gegr.Agegr.Cgegründetgem.Agem.ggf.Aggf.Cgegebenenfallsggfs.Aggfs.Cgegebenenfallsggü.Aggü.Cgegenüberh.Ah.h.c.Ah.c.hinter'mAhinterA'mCdemhinter’mAhinterA’mCdemhrsg.Ahrsg.i.Ai.i.A.Ai.A.i.G.Ai.G.i.O.Ai.O.i.Tr.Ai.Tr.i.V.Ai.V.i.d.R.Ai.d.R.i.e.Ai.e.ich'sAichA'sCesich’sAichA’sCesihr'sAihrA'sCesihr’sAihrA’sCesincl.Aincl.Cinklusiveinkl.Ainkl.Cinklusiveinsb.Ainsb.Cinsbesonderej.Aj.jr.Ajr.jun.Ajun.jur.Ajur.k.Ak.kath.Akath.Ckatholischl.Al.lat.Alat.lt.Alt.Clautm.Am.m.E.Am.E.m.M.Am.M.max.Amax.Cmaximalmin.Amin.Cminimalmind.Amind.Cmindestensmtl.Amtl.Cmonatlichn.An.n.Chr.An.Chr.nat.Anat.o.Ao.o.0Ao.0o.OAo.Oo.a.Ao.a.o.g.Ao.g.o.k.Ao.k.o.oAo.oo.ä.Ao.ä.o_0Ao_0o_OAo_Oo_oAo_oorig.Aorig.Coriginalp.Ap.p.a.Ap.a.p.s.Ap.s.pers.Apers.phil.Aphil.q.Aq.q.e.d.Aq.e.d.r.Ar.rer.Arer.röm.Aröm.Crömischs'As'C'ss.As.s.o.As.o.sen.Asen.sie'sAsieA'sCessie’sAsieA’sCessog.Asog.std.Astd.stellv.Astellv.s’As’C'st.At.tägl.Atägl.Ctäglichu.Au.u.U.Au.U.u.a.Au.a.u.s.w.Au.s.w.u.v.m.Au.v.m.unter'mAunterA'mCdemunter’mAunterA’mCdemusf.Ausf.usw.Ausw.uvm.Auvm.v.Av.v.Chr.Av.Chr.v.a.Av.a.v.l.n.r.Av.l.n.r.v.vAv.vv_vAv_vvgl.Avgl.Cvergleichevllt.Avllt.Cvielleichtvlt.Avlt.Cvielleichtvor'mAvorA'mCdemvor’mAvorA’mCdemvs.Avs.w.Aw.wir'sAwirA'sCeswir’sAwirA’sCeswiss.Awiss.x.Ax.xDAxDxDDAxDDy.Ay.z.Az.z.B.Az.B.z.Bsp.Az.Bsp.z.T.Az.T.z.Z.Az.Z.z.Zt.Az.Zt.z.b.Az.b.zzgl.Azzgl. A C ¯\(ツ)/¯A¯\(ツ)/¯°C.A°ACA.°F.A°AFA.°K.A°AKA.°c.A°AcA.°f.A°AfA.°k.A°AkA.ä.Aä.ö.Aö.österr.Aösterr.Cösterreichischü.Aü.über'mAüberA'mCdemüber’mAüberA’mCdemಠ_ಠAಠ_ಠಠ︵ಠAಠ︵ಠ—A—’A’’SA’SC's’nA’nCein’neA’neCeine’nemA’nemCeinem’nenA’nenCeinen’sA’sC's’’A’’faster_heuristics
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/key2row b/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/key2row
new file mode 100644
index 0000000..5416677
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/key2row
@@ -0,0 +1 @@
+
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/lookups.bin b/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/lookups.bin
new file mode 100644
index 0000000..5416677
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/lookups.bin
@@ -0,0 +1 @@
+
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/strings.json b/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/strings.json
new file mode 100644
index 0000000..7569f1d
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/strings.json
@@ -0,0 +1,1585 @@
+[
+ "\t",
+ "\n",
+ " ",
+ " ",
+ "\"",
+ "$",
+ "%",
+ "'",
+ "''",
+ "'-(",
+ "'-)",
+ "'S",
+ "'X",
+ "'m",
+ "'n",
+ "'ne",
+ "'nem",
+ "'nen",
+ "'s",
+ "'x",
+ "'xx",
+ "'xxx",
+ "(",
+ "(((",
+ "(*>",
+ "(*_*)",
+ "(-8",
+ "(-:",
+ "(-;",
+ "(-_-)",
+ "(-d",
+ "(._.)",
+ "(:",
+ "(;",
+ "(=",
+ "(>_<)",
+ "(^_^)",
+ "(o:",
+ "(x:",
+ "(x_x)",
+ "(\u00ac_\u00ac)",
+ "(\u0ca0_\u0ca0)",
+ "(\u256f\u00b0\u25a1\u00b0\uff09\u256f\ufe35\u253b\u2501\u253b",
+ ")",
+ ")))",
+ ")-:",
+ ")/\u00af",
+ "):",
+ "*",
+ "+",
+ ",",
+ "-",
+ "-((",
+ "-))",
+ "-0",
+ "-3",
+ "-8",
+ "-D",
+ "-O",
+ "-P",
+ "-X",
+ "-_-",
+ "-__-",
+ "-d",
+ "-o",
+ "-p",
+ "-x",
+ "-|",
+ ".",
+ ".A.",
+ ".B.",
+ ".C.",
+ ".D.",
+ ".E.",
+ ".G.",
+ ".H.",
+ ".K.",
+ ".M.",
+ ".O.",
+ ".P.",
+ ".R.",
+ ".S.",
+ ".Sc",
+ ".T.",
+ ".U.",
+ ".V.",
+ ".Y.",
+ ".Z.",
+ "._.",
+ ".a.",
+ ".b.",
+ ".c.",
+ ".d.",
+ ".e.",
+ ".g.",
+ ".h.",
+ ".k.",
+ ".m.",
+ ".o.",
+ ".r.",
+ ".s.",
+ ".w.",
+ ".\u00e4.",
+ "/",
+ "/3",
+ "/Core+",
+ "/Xxxx+",
+ "/core+",
+ "/d",
+ "/xxxx+",
+ "0",
+ "0%+",
+ "0.0",
+ "0.o",
+ "022",
+ "032",
+ "034",
+ "0_0",
+ "0_o",
+ "1",
+ "1.",
+ "10",
+ "12",
+ "2",
+ "2.",
+ "20",
+ "2022",
+ "2032",
+ "2034",
+ "250",
+ "3",
+ "3.",
+ "33",
+ "333",
+ "35",
+ "5",
+ "50",
+ "7",
+ "7,50%+",
+ "8",
+ "8)",
+ "8-",
+ "8-)",
+ "8-D",
+ "8-d",
+ "8D",
+ "8d",
+ ":",
+ ":'(",
+ ":')",
+ ":'-(",
+ ":'-)",
+ ":(",
+ ":((",
+ ":(((",
+ ":()",
+ ":)",
+ ":))",
+ ":)))",
+ ":*",
+ ":-(",
+ ":-((",
+ ":-(((",
+ ":-)",
+ ":-))",
+ ":-)))",
+ ":-*",
+ ":-/",
+ ":-0",
+ ":-3",
+ ":->",
+ ":-D",
+ ":-O",
+ ":-P",
+ ":-X",
+ ":-]",
+ ":-d",
+ ":-o",
+ ":-p",
+ ":-x",
+ ":-|",
+ ":-}",
+ ":/",
+ ":0",
+ ":1",
+ ":3",
+ ":>",
+ ":D",
+ ":O",
+ ":P",
+ ":X",
+ ":]",
+ ":d",
+ ":o",
+ ":o)",
+ ":p",
+ ":x",
+ ":x)",
+ ":|",
+ ":}",
+ ":\u2019(",
+ ":\u2019)",
+ ":\u2019-(",
+ ":\u2019-)",
+ ";",
+ ";)",
+ ";-)",
+ ";-D",
+ ";-X",
+ ";-d",
+ ";D",
+ ";X",
+ ";_;",
+ ";d",
+ "<",
+ "<.<",
+ "3",
+ "",
+ "",
+ "=",
+ "=(",
+ "=)",
+ "=/",
+ "=3",
+ "=D",
+ "=X",
+ "=[",
+ "=]",
+ "=d",
+ "=|",
+ ">",
+ ">.<",
+ ">.>",
+ ">:(",
+ ">:o",
+ ">:x",
+ "><(((*>",
+ "@",
+ "@_@",
+ "A",
+ "A.",
+ "A.C.",
+ "A.D.",
+ "A.G.",
+ "Abb",
+ "Abb.",
+ "Abbildung",
+ "Abk",
+ "Abk.",
+ "Abk\u00fcrzung",
+ "Abs",
+ "Abs.",
+ "Abt",
+ "Abt.",
+ "Abteilung",
+ "Add",
+ "Aktueller",
+ "Allgemeine",
+ "Amsterdam",
+ "Anlagestrategien",
+ "Anlagevehikels",
+ "Ansprechpartners",
+ "Antagevehikels",
+ "Apr",
+ "Apr.",
+ "April",
+ "Art",
+ "Assets",
+ "Aufl\u00f6sung",
+ "Aufwertung",
+ "Aug",
+ "Aug.",
+ "August",
+ "B",
+ "B.",
+ "B.A.",
+ "B.Sc",
+ "B.Sc.",
+ "Bahnhof",
+ "Band",
+ "Bd",
+ "Bd.",
+ "Beispiel",
+ "Berlin",
+ "Bestandsentwicklungen",
+ "Betr",
+ "Betr.",
+ "Betreff",
+ "Bf",
+ "Bf.",
+ "Bhf",
+ "Bhf.",
+ "Biol",
+ "Biol.",
+ "Bsp",
+ "Bsp.",
+ "C",
+ "C++",
+ "C.",
+ "CDU",
+ "CDU/CSU",
+ "CSU",
+ "Chr",
+ "Chr.",
+ "Cie",
+ "Cie.",
+ "Cities",
+ "Closings",
+ "Co",
+ "Co.",
+ "Core",
+ "Core+",
+ "Core+/Value",
+ "D",
+ "D.",
+ "D.C.",
+ "Deutschland",
+ "Deutschlands",
+ "Dez",
+ "Dez.",
+ "Dezember",
+ "Di",
+ "Di.",
+ "Dienstag",
+ "Different",
+ "Dipl",
+ "Dipl.",
+ "Dipl.-Ing",
+ "Dipl.-Ing.",
+ "Do",
+ "Do.",
+ "Donnerstag",
+ "Dr",
+ "Dr.",
+ "D\u00e4nemark",
+ "E",
+ "E-Mail",
+ "E.",
+ "Einw",
+ "Europe",
+ "European",
+ "Exit",
+ "F",
+ "F.",
+ "FIL",
+ "Fa",
+ "Fa.",
+ "Fam",
+ "Fam.",
+ "Familie",
+ "Feb",
+ "Feb.",
+ "Februar",
+ "Firma",
+ "Fond",
+ "Fonds",
+ "Fr",
+ "Fr.",
+ "Frankreich",
+ "Frau",
+ "Frl",
+ "Frl.",
+ "Fr\u00e4ulein",
+ "Fu\u0308hrende",
+ "G",
+ "G.",
+ "G.m.b",
+ "G.m.b.H.",
+ "Gateway",
+ "Gebr",
+ "Gebr.",
+ "Geplantes",
+ "Gesamtrendite",
+ "H",
+ "H.",
+ "Halten",
+ "Halten-Strategie",
+ "Hauptbahnhof",
+ "Hbf",
+ "Hbf.",
+ "Herr",
+ "Herrn",
+ "Hg",
+ "Hg.",
+ "Hr",
+ "Hr.",
+ "Hrn",
+ "Hrn.",
+ "Hrsg",
+ "Hrsg.",
+ "I",
+ "I.",
+ "II",
+ "II.",
+ "III",
+ "III.",
+ "INREV",
+ "IRR",
+ "IV",
+ "IV.",
+ "Immobilien",
+ "Immobilien-Spezialfonds",
+ "Inc",
+ "Inc.",
+ "Informationen",
+ "Ing",
+ "Ing.",
+ "Investmentmanagers",
+ "J",
+ "Jahr",
+ "Jahre",
+ "Jahrhundert",
+ "Jan",
+ "Jan.",
+ "Januar",
+ "Jh",
+ "Jh.",
+ "Jhd",
+ "Jhd.",
+ "Jr",
+ "Jr.",
+ "Jul",
+ "Jul.",
+ "Juli",
+ "Jun",
+ "Jun.",
+ "Juni",
+ "K",
+ "K.",
+ "K.O.",
+ "Kaufen",
+ "Key",
+ "L",
+ "L'",
+ "L.A.",
+ "LTV",
+ "LTY",
+ "Laufzeit",
+ "London",
+ "L\u00e4nderallokation",
+ "L\u2019",
+ "M",
+ "M.",
+ "M.A.",
+ "M.Sc",
+ "M.Sc.",
+ "Manager",
+ "Maximaler",
+ "Mehrwertsteuer",
+ "Metropolregionen",
+ "Mi",
+ "Mi.",
+ "Milliarde",
+ "Million",
+ "Mio",
+ "Mio.",
+ "Mittwoch",
+ "Mo",
+ "Mo.",
+ "Montag",
+ "Mr",
+ "Mr.",
+ "Mrd",
+ "Mrd.",
+ "Mrz",
+ "Mrz.",
+ "MwSt",
+ "MwSt.",
+ "M\u00e4r",
+ "M\u00e4r.",
+ "M\u00e4rz",
+ "N",
+ "N.Y.",
+ "N.Y.C.",
+ "Nachvermietungsstrategie",
+ "Name",
+ "Niederlande",
+ "Nov",
+ "Nov.",
+ "November",
+ "Nr",
+ "Nr.",
+ "Nummer",
+ "O",
+ "O.",
+ "O.K.",
+ "O.O",
+ "O.o",
+ "O_O",
+ "O_o",
+ "Offen",
+ "Offener",
+ "Okt",
+ "Okt.",
+ "Oktober",
+ "OpCo",
+ "Orig",
+ "Orig.",
+ "Original",
+ "P",
+ "P.S.",
+ "Paris",
+ "Pkt",
+ "Pkt.",
+ "Prof",
+ "Prof.",
+ "Professor",
+ "Punkt",
+ "R",
+ "R.",
+ "R.I.P.",
+ "RE",
+ "REV",
+ "RISIKOPROFIL",
+ "ROOT",
+ "Rechtsform",
+ "Red",
+ "Red.",
+ "Redaktion",
+ "Risikoprofil",
+ "Risk",
+ "S",
+ "S'",
+ "Sa",
+ "Sa.",
+ "Samstag",
+ "Sc.",
+ "Schweden",
+ "Sep",
+ "Sep.",
+ "Sept",
+ "Sept.",
+ "September",
+ "Sitz",
+ "Skandinavien",
+ "So",
+ "So.",
+ "Sonntag",
+ "St",
+ "St.",
+ "Standortaufwertungsstrategie",
+ "Standorte",
+ "Std",
+ "Std.",
+ "Stil",
+ "Str",
+ "Str.",
+ "Strategie",
+ "Stra\u00dfe",
+ "Struktur",
+ "Stunde",
+ "S\u2019",
+ "T",
+ "T.",
+ "Tausend",
+ "Tel",
+ "Tel.",
+ "Telefon",
+ "Telefonnummer",
+ "The",
+ "Tr",
+ "Tr.",
+ "Tsd",
+ "Tsd.",
+ "U",
+ "U.",
+ "U.S.",
+ "U.S.A.",
+ "U.S.S.",
+ "Univ",
+ "Univ.",
+ "Universit\u00e4t",
+ "V",
+ "V.",
+ "V.V",
+ "V_V",
+ "Value",
+ "Vol",
+ "Vol.",
+ "W",
+ "Wertstabile",
+ "Wohnimmobilien",
+ "X'",
+ "X++",
+ "X-Xxxx",
+ "X.",
+ "X.X",
+ "X.X.",
+ "X.X.X.",
+ "X.Xx",
+ "X.Xx.",
+ "X.x",
+ "X.x.x",
+ "X.x.x.X.",
+ "XD",
+ "XDD",
+ "XX",
+ "XX.",
+ "XXX",
+ "XXX.",
+ "XXX/XXX",
+ "XXXX",
+ "X_X",
+ "X_x",
+ "Xx",
+ "Xx.",
+ "XxXx",
+ "XxXx.",
+ "Xxx",
+ "Xxx.",
+ "Xxxx",
+ "Xxxx+",
+ "Xxxx+/Xxxxx",
+ "Xxxx-XXX",
+ "Xxxx-Xxxxx-XXX",
+ "Xxxx.",
+ "Xxxx.-Xxx",
+ "Xxxx.-Xxx.",
+ "Xxxxx",
+ "Xxxxx)/Xxxx",
+ "Xxxxx-Xxxxx",
+ "Xx\u0308xxxx",
+ "X\u2019",
+ "Z",
+ "Z.",
+ "Ziel-LTY",
+ "Ziel-Netto-IRR",
+ "Zielanlagestrategie",
+ "Zielregionfen)/Jand",
+ "Zielsektoren",
+ "Zielvolumen",
+ "Ziirraiaein",
+ "Zt",
+ "Zt.",
+ "[",
+ "[-:",
+ "[:",
+ "[=",
+ "\\",
+ "\\\")",
+ "\\n",
+ "\\t",
+ "\\x",
+ "]",
+ "]=",
+ "^",
+ "^_^",
+ "^__^",
+ "^___^",
+ "_*)",
+ "_-)",
+ "_.)",
+ "_<)",
+ "_^)",
+ "__-",
+ "__^",
+ "_\u00ac)",
+ "_\u0ca0)",
+ "`",
+ "``",
+ "a",
+ "a.",
+ "a.D.",
+ "a.M.",
+ "a.Z.",
+ "a.c.",
+ "a.d.",
+ "a.g.",
+ "a.m.",
+ "a.z.",
+ "abb",
+ "abb.",
+ "abk",
+ "abk.",
+ "abs",
+ "abs.",
+ "abt",
+ "abt.",
+ "abzgl",
+ "abzgl.",
+ "abz\u00fcglich",
+ "ace",
+ "add",
+ "adv",
+ "adv.",
+ "ahr",
+ "ail",
+ "aiming",
+ "aktueller",
+ "al",
+ "al.",
+ "allg",
+ "allg.",
+ "allgemein",
+ "allgemeine",
+ "am.",
+ "ame",
+ "amsterdam",
+ "an.",
+ "and",
+ "anlagestrategien",
+ "anlagevehikels",
+ "ansprechpartners",
+ "antagevehikels",
+ "apr",
+ "apr.",
+ "ark",
+ "art",
+ "asset",
+ "assets",
+ "at",
+ "at.",
+ "ath",
+ "auf",
+ "aufl\u00f6sung",
+ "aufwertung",
+ "auf\u2019m",
+ "aug",
+ "aug.",
+ "ausgew\u00e4hlte",
+ "ax.",
+ "b",
+ "b.",
+ "b.a.",
+ "b.sc",
+ "b.sc.",
+ "bb.",
+ "bd",
+ "bd.",
+ "beispielsweise",
+ "ber",
+ "berlin",
+ "bestandsentwicklungen",
+ "betr",
+ "betr.",
+ "beziehungsweise",
+ "bez\u00fcglich",
+ "bf",
+ "bf.",
+ "bhf",
+ "bhf.",
+ "biol",
+ "biol.",
+ "bk.",
+ "br.",
+ "bs.",
+ "bsp",
+ "bsp.",
+ "bspw",
+ "bspw.",
+ "bt.",
+ "bzgl",
+ "bzgl.",
+ "bzw",
+ "bzw.",
+ "c",
+ "c++",
+ "c.",
+ "c/o",
+ "ca",
+ "ca.",
+ "cal",
+ "cdu",
+ "cdu/csu",
+ "ce>",
+ "chr",
+ "chr.",
+ "cht",
+ "cie",
+ "cie.",
+ "cities",
+ "cl.",
+ "closings",
+ "co",
+ "co.",
+ "core",
+ "core+",
+ "core+/value",
+ "csu",
+ "cts",
+ "d",
+ "d'",
+ "d)",
+ "d,dd%+",
+ "d-",
+ "d-)",
+ "d-X",
+ "d.",
+ "d.c.",
+ "d.d",
+ "d.h",
+ "d.h.",
+ "d.x",
+ "dX",
+ "d_d",
+ "d_x",
+ "dam",
+ "dd",
+ "ddd",
+ "dddd",
+ "de",
+ "ded",
+ "dem",
+ "den",
+ "der",
+ "dergleichen",
+ "des",
+ "deutschland",
+ "deutschlands",
+ "development",
+ "dez",
+ "dez.",
+ "dgl",
+ "dgl.",
+ "di",
+ "di.",
+ "different",
+ "dipl",
+ "dipl.",
+ "dipl.-ing",
+ "dipl.-ing.",
+ "do",
+ "do.",
+ "don",
+ "dr",
+ "dr.",
+ "du",
+ "du\u2019s",
+ "dv.",
+ "d\u00e4nemark",
+ "d\u2019",
+ "e",
+ "e-mail",
+ "e.",
+ "e.V.",
+ "e.d",
+ "e.g",
+ "e.g.",
+ "e.v.",
+ "ean",
+ "eb.",
+ "ebd",
+ "ebd.",
+ "ebenda",
+ "ebr",
+ "ed.",
+ "egr",
+ "egy",
+ "ehem",
+ "ehem.",
+ "eigentlich",
+ "eigtl",
+ "eigtl.",
+ "ein",
+ "eine",
+ "einem",
+ "einen",
+ "einw",
+ "eit",
+ "el.",
+ "els",
+ "em.",
+ "en.",
+ "engl",
+ "engl.",
+ "englisch",
+ "enhancing",
+ "ent",
+ "entspr",
+ "entspr.",
+ "ep.",
+ "ept",
+ "er",
+ "er.",
+ "erm",
+ "erm.",
+ "err",
+ "ers",
+ "ersten",
+ "er\u2019s",
+ "es",
+ "etc",
+ "etc.",
+ "etr",
+ "ets",
+ "europe",
+ "european",
+ "ev",
+ "ev.",
+ "eventuell",
+ "evtl",
+ "evtl.",
+ "exit",
+ "expertise",
+ "exposure",
+ "ez.",
+ "e\u2019s",
+ "f",
+ "f.",
+ "fa",
+ "fa.",
+ "fam",
+ "fam.",
+ "feb",
+ "feb.",
+ "fen",
+ "festgelegter",
+ "fil",
+ "fond",
+ "fonds",
+ "fr",
+ "fr.",
+ "frankreich",
+ "franz\u00f6sisch",
+ "frl",
+ "frl.",
+ "frz",
+ "frz.",
+ "fs.",
+ "fund",
+ "fu\u0308hrende",
+ "f\u2019m",
+ "g",
+ "g.",
+ "g.m.b",
+ "g.m.b.h.",
+ "gateway",
+ "geb",
+ "geb.",
+ "gebr",
+ "gebr.",
+ "gegebenenfalls",
+ "gegen\u00fcber",
+ "gegr",
+ "gegr.",
+ "gegr\u00fcndet",
+ "gem",
+ "gem.",
+ "gen",
+ "geplantes",
+ "ger",
+ "gesamtrendite",
+ "gf.",
+ "gfs",
+ "ggf",
+ "ggf.",
+ "ggfs",
+ "ggfs.",
+ "gg\u00fc",
+ "gg\u00fc.",
+ "gie",
+ "gl.",
+ "good",
+ "gr.",
+ "gtl",
+ "g\u00fc.",
+ "h",
+ "h.",
+ "h.c",
+ "h.c.",
+ "halten",
+ "halten-strategie",
+ "hbf",
+ "hbf.",
+ "hd.",
+ "hed",
+ "hem",
+ "hf.",
+ "hg",
+ "hg.",
+ "hil",
+ "hinter",
+ "hinter\u2019m",
+ "hotels",
+ "hr",
+ "hr.",
+ "hre",
+ "hrn",
+ "hrn.",
+ "hrsg",
+ "hrsg.",
+ "h\u2019s",
+ "i",
+ "i.",
+ "i.A.",
+ "i.G.",
+ "i.O.",
+ "i.Tr.",
+ "i.V.",
+ "i.a.",
+ "i.d",
+ "i.d.R.",
+ "i.d.r.",
+ "i.e",
+ "i.e.",
+ "i.g.",
+ "i.o.",
+ "i.tr.",
+ "i.v.",
+ "ich",
+ "ich\u2019s",
+ "ie.",
+ "ien",
+ "ies",
+ "ig.",
+ "ihr",
+ "ihr\u2019s",
+ "ii",
+ "ii.",
+ "iii",
+ "iii.",
+ "il.",
+ "ile",
+ "illustration",
+ "ime",
+ "immobilien",
+ "immobilien-spezialfonds",
+ "in",
+ "in.",
+ "inc",
+ "inc.",
+ "incl",
+ "incl.",
+ "ind",
+ "ine",
+ "informationen",
+ "ing",
+ "ing.",
+ "initiatives",
+ "inkl",
+ "inkl.",
+ "inklusive",
+ "inrev",
+ "insb",
+ "insb.",
+ "insbesondere",
+ "investmentmanagers",
+ "investments",
+ "inw",
+ "io.",
+ "iol",
+ "ion",
+ "ipl",
+ "irr",
+ "is",
+ "ise",
+ "isk",
+ "iss",
+ "ite",
+ "ith",
+ "ity",
+ "itz",
+ "ium",
+ "iv",
+ "iv.",
+ "j",
+ "j.",
+ "jahr",
+ "jahre",
+ "jan",
+ "jan.",
+ "jh",
+ "jh.",
+ "jhd",
+ "jhd.",
+ "jr",
+ "jr.",
+ "jul",
+ "jul.",
+ "jun",
+ "jun.",
+ "jur",
+ "jur.",
+ "k",
+ "k.",
+ "k.o.",
+ "kath",
+ "kath.",
+ "katholisch",
+ "kaufen",
+ "ket",
+ "key",
+ "kl.",
+ "kt.",
+ "l",
+ "l'",
+ "l.",
+ "l.a.",
+ "langfristig",
+ "lat",
+ "lat.",
+ "laufzeit",
+ "laut",
+ "le.g",
+ "ler",
+ "level",
+ "lg.",
+ "lin",
+ "lio",
+ "llg",
+ "llt",
+ "llv",
+ "london",
+ "lt",
+ "lt.",
+ "lte",
+ "ltv",
+ "lty",
+ "lue",
+ "lv.",
+ "l\u00e4nderallokation",
+ "l\u2019",
+ "m",
+ "m.",
+ "m.E.",
+ "m.M.",
+ "m.a.",
+ "m.b",
+ "m.e.",
+ "m.m.",
+ "m.sc",
+ "m.sc.",
+ "mal",
+ "management",
+ "manager",
+ "market",
+ "max",
+ "max.",
+ "maximal",
+ "maximaler",
+ "men",
+ "mer",
+ "metropolregionen",
+ "mi",
+ "mi.",
+ "million",
+ "min",
+ "min.",
+ "mind",
+ "mind.",
+ "mindestens",
+ "minimal",
+ "minor",
+ "mio",
+ "mio.",
+ "mit",
+ "mo",
+ "mo.",
+ "monatlich",
+ "mr",
+ "mr.",
+ "mrd",
+ "mrd.",
+ "mrz",
+ "mrz.",
+ "mtl",
+ "mtl.",
+ "mwst",
+ "mwst.",
+ "m\u00e4r",
+ "m\u00e4r.",
+ "n",
+ "n.",
+ "n.Chr.",
+ "n.chr.",
+ "n.r",
+ "n.y.",
+ "n.y.c.",
+ "nachvermietungsstrategie",
+ "name",
+ "nat",
+ "nat.",
+ "nc.",
+ "ncl",
+ "nd.",
+ "nde",
+ "nds",
+ "ne",
+ "nem",
+ "nen",
+ "ner",
+ "ng.",
+ "ngl",
+ "ngs",
+ "niederlande",
+ "niv",
+ "nkl",
+ "nor",
+ "nov",
+ "nov.",
+ "nr",
+ "nr.",
+ "nsb",
+ "nts",
+ "o",
+ "o.",
+ "o.0",
+ "o.O",
+ "o.a",
+ "o.a.",
+ "o.g",
+ "o.g.",
+ "o.k",
+ "o.k.",
+ "o.o",
+ "o.\u00e4",
+ "o.\u00e4.",
+ "o_0",
+ "o_O",
+ "o_o",
+ "of",
+ "of.",
+ "offen",
+ "offener",
+ "og.",
+ "okt",
+ "okt.",
+ "ol.",
+ "ond",
+ "ood",
+ "opco",
+ "ope",
+ "ore",
+ "orig",
+ "orig.",
+ "original",
+ "orm",
+ "ov.",
+ "over",
+ "p",
+ "p.",
+ "p.a",
+ "p.a.",
+ "p.s",
+ "p.s.",
+ "pCo",
+ "paris",
+ "pco",
+ "pers",
+ "pers.",
+ "phil",
+ "phil.",
+ "pkt",
+ "pkt.",
+ "pl.",
+ "portfolio",
+ "pr.",
+ "premium",
+ "prof",
+ "prof.",
+ "profile",
+ "projects",
+ "pt.",
+ "pw.",
+ "q",
+ "q.",
+ "q.e.d",
+ "q.e.d.",
+ "quality",
+ "r",
+ "r.",
+ "r.i.p.",
+ "rd.",
+ "re",
+ "re+",
+ "rechtsform",
+ "red",
+ "red.",
+ "ren",
+ "rer",
+ "rer.",
+ "rev",
+ "rig",
+ "ris",
+ "risikoprofil",
+ "risk",
+ "rl.",
+ "rm.",
+ "rn.",
+ "rof",
+ "rr.",
+ "rs.",
+ "rsg",
+ "rte",
+ "rz.",
+ "r\u00f6m",
+ "r\u00f6m.",
+ "r\u00f6misch",
+ "r\u2019m",
+ "r\u2019s",
+ "s",
+ "s'",
+ "s.",
+ "s.o",
+ "s.o.",
+ "s.w",
+ "sa",
+ "sa.",
+ "sb.",
+ "schweden",
+ "sd.",
+ "sen",
+ "sen.",
+ "sep",
+ "sep.",
+ "sept",
+ "sept.",
+ "set",
+ "sf.",
+ "sg.",
+ "sie",
+ "sie\u2019s",
+ "sitz",
+ "skandinavien",
+ "so",
+ "so.",
+ "sog",
+ "sog.",
+ "sp.",
+ "space",
+ "spr",
+ "spw",
+ "ss.",
+ "st",
+ "st.",
+ "standortaufwertungsstrategie",
+ "standorte",
+ "std",
+ "std.",
+ "stellv",
+ "stellv.",
+ "stil",
+ "str",
+ "str.",
+ "strategie",
+ "strategy",
+ "struktur",
+ "sw.",
+ "s\u2019",
+ "t",
+ "t.",
+ "tactical",
+ "tc.",
+ "td.",
+ "tel",
+ "tel.",
+ "telefonnummer",
+ "ten",
+ "ter",
+ "tes",
+ "th.",
+ "the",
+ "tig",
+ "til",
+ "time",
+ "tl.",
+ "to",
+ "tr",
+ "tr.",
+ "tsd",
+ "tsd.",
+ "tur",
+ "t\u00e4gl",
+ "t\u00e4gl.",
+ "t\u00e4glich",
+ "u",
+ "u.",
+ "u.U.",
+ "u.a",
+ "u.a.",
+ "u.s.",
+ "u.s.a.",
+ "u.s.s.",
+ "u.s.w",
+ "u.s.w.",
+ "u.u.",
+ "u.v.m",
+ "u.v.m.",
+ "ug.",
+ "ul.",
+ "un.",
+ "und",
+ "ung",
+ "univ",
+ "univ.",
+ "unter",
+ "unter\u2019m",
+ "ur.",
+ "ure",
+ "usf",
+ "usf.",
+ "usw",
+ "usw.",
+ "uvm",
+ "uvm.",
+ "u\u2019s",
+ "v",
+ "v.",
+ "v.Chr.",
+ "v.a",
+ "v.a.",
+ "v.chr.",
+ "v.l.n.r",
+ "v.l.n.r.",
+ "v.m",
+ "v.v",
+ "v_v",
+ "value",
+ "value-added",
+ "vel",
+ "ver",
+ "vergleiche",
+ "ves",
+ "vgl",
+ "vgl.",
+ "vielleicht",
+ "vllt",
+ "vllt.",
+ "vlt",
+ "vlt.",
+ "vm.",
+ "vol",
+ "vol.",
+ "vom",
+ "vor",
+ "vor\u2019m",
+ "vs",
+ "vs.",
+ "vtl",
+ "w",
+ "w.",
+ "wSt",
+ "way",
+ "well-established",
+ "wertstabile",
+ "wir",
+ "wir\u2019s",
+ "wiss",
+ "wiss.",
+ "with",
+ "wohnimmobilien",
+ "x",
+ "x'",
+ "x-xxxx",
+ "x.",
+ "x.X",
+ "x.X.",
+ "x.Xx.",
+ "x.Xxx.",
+ "x.d",
+ "x.x",
+ "x.x.",
+ "x.x.X.",
+ "x.x.x",
+ "x.x.x.",
+ "x.x.x.x",
+ "x.x.x.x.",
+ "x/x",
+ "xD",
+ "xDD",
+ "xX",
+ "xXX",
+ "x_X",
+ "x_d",
+ "x_x",
+ "xd",
+ "xdd",
+ "xit",
+ "xx",
+ "xx.",
+ "xx.x",
+ "xxx",
+ "xxx.",
+ "xxxx",
+ "xxxx)/xxxx",
+ "xxxx+",
+ "xxxx+/xxxx",
+ "xxxx-xxx",
+ "xxxx-xxxx",
+ "xxxx-xxxx-xxx",
+ "xxxx.",
+ "xxxx\u2019x",
+ "xxx\u2019x",
+ "xx\u0308xxxx",
+ "xx\u2019x",
+ "x\u2019",
+ "x\ufe35x",
+ "y",
+ "y.",
+ "z",
+ "z.",
+ "z.B.",
+ "z.Bsp.",
+ "z.T.",
+ "z.Z.",
+ "z.Zt.",
+ "z.b",
+ "z.b.",
+ "z.bsp.",
+ "z.t.",
+ "z.z.",
+ "z.zt.",
+ "zgl",
+ "ziel-lty",
+ "ziel-netto-irr",
+ "zielanlagestrategie",
+ "zielregionfen)/jand",
+ "zielsektoren",
+ "zielvolumen",
+ "ziirraiaein",
+ "zt",
+ "zw.",
+ "zzgl",
+ "zzgl.",
+ "|",
+ "}",
+ "\u00a0",
+ "\u00ac",
+ "\u00ac_\u00ac",
+ "\u00af",
+ "\u00af\\(x)/\u00af",
+ "\u00af\\(\u30c4)/\u00af",
+ "\u00b0",
+ "\u00b0C.",
+ "\u00b0F.",
+ "\u00b0K.",
+ "\u00b0X.",
+ "\u00b0c.",
+ "\u00b0f.",
+ "\u00b0k.",
+ "\u00b0x.",
+ "\u00dc",
+ "\u00dcbersicht",
+ "\u00e4",
+ "\u00e4.",
+ "\u00e4gl",
+ "\u00e4r.",
+ "\u00f6",
+ "\u00f6.",
+ "\u00f6m.",
+ "\u00f6sterr",
+ "\u00f6sterr.",
+ "\u00f6sterreichisch",
+ "\u00fc",
+ "\u00fc.",
+ "\u00fcber",
+ "\u00fcbersicht",
+ "\u00fcber\u2019m",
+ "\u0ca0",
+ "\u0ca0_\u0ca0",
+ "\u0ca0\ufe35\u0ca0",
+ "\u2014",
+ "\u2019",
+ "\u2019-(",
+ "\u2019-)",
+ "\u2019S",
+ "\u2019X",
+ "\u2019m",
+ "\u2019n",
+ "\u2019ne",
+ "\u2019nem",
+ "\u2019nen",
+ "\u2019s",
+ "\u2019x",
+ "\u2019xx",
+ "\u2019xxx",
+ "\u2019\u2019",
+ "\u201a",
+ "\u20ac",
+ "\u2501",
+ "\u253b",
+ "\u253b\u2501\u253b",
+ "\u256f",
+ "\u25a1",
+ "\ufe35",
+ "\uff09"
+]
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/vectors b/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/vectors
new file mode 100644
index 0000000..ebadaa5
Binary files /dev/null and b/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/vectors differ
diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/vectors.cfg b/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/vectors.cfg
new file mode 100644
index 0000000..32c800a
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/vectors.cfg
@@ -0,0 +1,3 @@
+{
+ "mode":"default"
+}
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/output/spacy-results.json b/prototypes/arc2_prototype/spacy_service/output/spacy-results.json
new file mode 100644
index 0000000..d68242e
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/output/spacy-results.json
@@ -0,0 +1,197 @@
+[
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core and Core+",
+ "page": 4
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core, core+, value-added",
+ "page": 7
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core/Core+",
+ "page": 10
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core/core+",
+ "page": 10
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core/Core+",
+ "page": 10
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "UK, DE, BE, NL, LU,",
+ "page": 10
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core / Core +",
+ "page": 12
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core\n/ core+",
+ "page": 12
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core\n",
+ "page": 12
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Term / core+",
+ "page": 12
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core/core+",
+ "page": 12
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "6,4 6,4",
+ "page": 13
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Country /",
+ "page": 14
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core Excellent",
+ "page": 14
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core 40",
+ "page": 14
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core 400m",
+ "page": 14
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core 99m-102",
+ "page": 14
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core 85m-90m",
+ "page": 14
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core 50",
+ "page": 14
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Country /",
+ "page": 15
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core Good New",
+ "page": 15
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core 44m-46m",
+ "page": 15
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core Good New",
+ "page": 15
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core CBD New",
+ "page": 15
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core Good New",
+ "page": 15
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "countries, giving",
+ "page": 18
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core/core+",
+ "page": 20
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core/core+",
+ "page": 20
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "D, and",
+ "page": 21
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "UK, DE, BE, NL, LU,",
+ "page": 26
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "core or",
+ "page": 27
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core +",
+ "page": 27
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "kgCO,e",
+ "page": 30
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "C,\n",
+ "page": 32
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "KfW, Dwp",
+ "page": 35
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Bank,",
+ "page": 35
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "HSBC, RTE",
+ "page": 37
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core WALB (",
+ "page": 37
+ },
+ {
+ "label": "RISIKOPROFIL",
+ "entity": "Core WALB (",
+ "page": 37
+ }
+]
\ No newline at end of file
diff --git a/prototypes/arc2_prototype/spacy_service/spacy.py b/prototypes/arc2_prototype/spacy_service/spacy.py
new file mode 100644
index 0000000..28d5a34
--- /dev/null
+++ b/prototypes/arc2_prototype/spacy_service/spacy.py
@@ -0,0 +1,39 @@
+import spacy
+from pathlib import Path
+import json
+import os
+import fitz
+
+OUTPUT_FOLDER = Path(__file__).resolve().parent / "output"
+OUTPUT_FOLDER.mkdir(parents=True, exist_ok=True)
+
+model_path = os.path.join(os.path.dirname(__file__), "models", "model-last")
+nlp = spacy.load(model_path)
+input_pdf_path = Path(__file__).resolve().parent / ".." / "ocr_pdf_service" / "output" / "pitchbook-OCR.pdf"
+input_pdf = Path(input_pdf_path)
+doc = fitz.open(input_pdf)
+
+
+def extract_with_spacy(pages_json):
+ results = []
+
+ for page in pages_json:
+ text = page.get("text", "").strip()
+ page_num = page.get("page")
+
+ if not text:
+ continue
+
+ doc = nlp(text)
+ for ent in doc.ents:
+ results.append({
+ "label": ent.label_,
+ "entity": ent.text,
+ "page": page_num
+ })
+
+ output_path = OUTPUT_FOLDER / f"spacy-results.json"
+ with open(output_path, "w", encoding="utf-8") as f:
+ json.dump(results, f, indent=2, ensure_ascii=False)
+
+ return results
\ No newline at end of file