Add checks for BOM encoding in files

src/corelibs/file_handling/file_bom_encoding.py

@@ -0,0 +1,75 @@
+"""
+File check if BOM encoded, needed for CSV load
+"""
+
+from pathlib import Path
+from typing import TypedDict
+
+
+class BomEncodingInfo(TypedDict):
+    """BOM encoding info"""
+    has_bom: bool
+    bom_type: str | None
+    encoding: str | None
+    bom_length: int
+    bom_pattern: bytes | None
+
+
+def is_bom_encoded(file_path: Path) -> bool:
+    """
+    Detect if a file is BOM encoded
+
+    Args:
+        file_path (str): Path to the file to check
+
+    Returns:
+        bool: True if file has BOM, False otherwise
+    """
+    return is_bom_encoded_info(file_path)['has_bom']
+
+
+def is_bom_encoded_info(file_path: Path) -> BomEncodingInfo:
+    """
+    Enhanced BOM detection with additional file analysis
+
+    Args:
+        file_path (str): Path to the file to check
+
+    Returns:
+        dict: Comprehensive BOM and encoding information
+    """
+    try:
+        # Read first 1024 bytes for analysis
+        with open(file_path, 'rb') as f:
+            header = f.read(4)
+
+        bom_patterns = {
+            b'\xef\xbb\xbf': ('UTF-8', 'utf-8', 3),
+            b'\xff\xfe\x00\x00': ('UTF-32 LE', 'utf-32-le', 4),
+            b'\x00\x00\xfe\xff': ('UTF-32 BE', 'utf-32-be', 4),
+            b'\xff\xfe': ('UTF-16 LE', 'utf-16-le', 2),
+            b'\xfe\xff': ('UTF-16 BE', 'utf-16-be', 2),
+        }
+
+        for bom_pattern, (encoding_name, encoding, length) in bom_patterns.items():
+            if header.startswith(bom_pattern):
+                return {
+                    'has_bom': True,
+                    'bom_type': encoding_name,
+                    'encoding': encoding,
+                    'bom_length': length,
+                    'bom_pattern': bom_pattern
+                }
+
+        return {
+            'has_bom': False,
+            'bom_type': None,
+            'encoding': None,
+            'bom_length': 0,
+            'bom_pattern': None
+        }
+    except Exception as e:
+        raise ValueError(f"Error checking BOM encoding: {e}") from e
+
+
+# __END__