Floke/Brancheneinstufung2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: robust metric extraction with confidence score and proof snippets

Browse Source 
- fixed Year-Prefix Bug in MetricParser
- added metric_confidence and metric_proof_text to database
- added Entity-Check and Annual-Priority to LLM prompt
- improved UI: added confidence traffic light and mouse-over proof tooltip
- restored missing API endpoints (create, bulk, wiki-override)
This commit is contained in:
Floke
2026-01-23 21:16:07 +00:00
parent cec6724fe9
commit d1c79439a0
7006 changed files with 1367435 additions and 201 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
company-explorer/backend/lib/core_utils.py
View File

@@ -126,55 +126,16 @@ def extract_numeric_value(raw_value: str, is_umsatz: bool = False) -> str:
Returns string representation of the number or 'k.A.'.
Handles German number formatting (1.000 = 1000, 1,5 = 1.5).
"""
if not raw_value:
from .metric_parser import MetricParser
val = MetricParser.extract_numeric_value(raw_value, is_revenue=is_umsatz)
if val is None:
return "k.A."
raw_value = str(raw_value).strip().lower()
if raw_value in ["k.a.", "nan", "none"]:
return "k.A."
multiplier = 1.0
if 'mrd' in raw_value or 'billion' in raw_value or 'bn' in raw_value:
multiplier = 1000.0
if not is_umsatz: multiplier = 1000000000.0
elif 'mio' in raw_value or 'million' in raw_value or 'mn' in raw_value:
multiplier = 1.0
if not is_umsatz: multiplier = 1000000.0
elif 'tsd' in raw_value or 'thousand' in raw_value:
multiplier = 0.001
if not is_umsatz: multiplier = 1000.0
matches = re.findall(r'(\d+[\.,]?\d*[\.,]?\d*)', raw_value)
if not matches:
return "k.A."
try:
num_str = matches[0]
if '.' in num_str and ',' in num_str:
if num_str.rfind(',') > num_str.rfind('.'):
num_str = num_str.replace('.', '').replace(',', '.')
else:
num_str = num_str.replace(',', '')
elif '.' in num_str:
parts = num_str.split('.')
if len(parts) > 1 and len(parts[-1]) == 3 and not is_umsatz:
num_str = num_str.replace('.', '')
elif is_umsatz and len(parts) > 1 and len(parts[-1]) == 3:
if num_str.count('.') > 1:
num_str = num_str.replace('.', '')
elif ',' in num_str:
num_str = num_str.replace(',', '.')
val = float(num_str) * multiplier
if is_umsatz:
return f"{val:.2f}".rstrip('0').rstrip('.')
else:
return str(int(val))
except ValueError:
return "k.A."
if is_umsatz:
return f"{val:.2f}".rstrip('0').rstrip('.')
else:
return str(int(val))
def fuzzy_similarity(str1: str, str2: str) -> float:
"""Returns fuzzy similarity between two strings (0.0 to 1.0)."""