AI-Cognitive-Leap/agnes-the-ai-analyst
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix: strip HTML from table and column descriptions in OpenMetadata enricher

Browse source 
Imports strip_html from transformer and applies it to both table-level
and column-level descriptions parsed from the OpenMetadata API response.
This commit is contained in:
ZdenekSrotyr 2026-04-09 18:42:37 +02:00
parent 30987eef16
commit 49cb940729
1 changed files with 3 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
connectors/openmetadata/enricher.py
View file

@ -17,6 +17,7 @@ from typing import Dict, List, Optional, Any
from dataclasses import dataclass as _dataclass from dataclasses import dataclass as _dataclass
from .client import OpenMetadataClient from .client import OpenMetadataClient
from .transformer import strip_html
@_dataclass @_dataclass
@ -207,13 +208,13 @@ class CatalogEnricher:
CatalogTableData or None if parsing fails CatalogTableData or None if parsing fails
""" """
try: try:
description = raw.get("description", "") or "" description = strip_html(raw.get("description", "") or "")
# Parse columns # Parse columns
columns = {} columns = {}
for col in raw.get("columns", []): for col in raw.get("columns", []):
col_name = col.get("name", "").lower() col_name = col.get("name", "").lower()
col_description = col.get("description", "") or "" col_description = strip_html(col.get("description", "") or "")
col_type = col.get("dataType", "") col_type = col.get("dataType", "")
columns[col_name] = CatalogColumnData( columns[col_name] = CatalogColumnData(