robertwb commented on code in PR #31455:
URL: https://github.com/apache/beam/pull/31455#discussion_r1624895474
##########
sdks/python/apache_beam/yaml/yaml_mapping.py:
##########
@@ -65,9 +72,85 @@ def normalize_mapping(spec):
config = spec.get('config')
if isinstance(config.get('drop'), str):
config['drop'] = [config['drop']]
+ for field, value in list(config.get('fields', {}).items()):
+ if isinstance(value, (str, int, float)):
+ config['fields'][field] = {'expression': str(value)}
+
+ elif spec['type'] in _str_expression_fields:
+ param = _str_expression_fields[spec['type']]
+ config = spec.get('config', {})
+ if isinstance(config.get(param), (str, int, float)):
+ config[param] = {'expression': str(config.get(param))}
+
return spec
+def is_literal(expr: str) -> bool:
+ # Some languages have limited integer literal ranges.
+ if re.fullmatch(r'-?\d+?', expr) and -1 << 31 < int(expr) < 1 << 31:
+ return True
+ elif re.fullmatch(r'-?\d+\.\d*', expr):
+ return True
+ elif re.fullmatch(r'"[^\\"]*"', expr):
+ return True
+ else:
+ return False
+
+
+def validate_generic_expression(
+ expr_dict: dict,
+ input_fields: Collection[str],
+ allow_cmp: bool,
+ error_field: str) -> None:
+ if not isinstance(expr_dict, dict):
+ raise ValueError(
+ f"Ambiguous expression type (perhaps missing quoting?): {expr_dict}")
+ if len(expr_dict) != 1 or 'expression' not in expr_dict:
+ raise ValueError(
+ "Missing language specification. "
+ "Must specify a language when using a map with custom logic for %s" %
+ error_field)
+ expr = str(expr_dict['expression'])
+
+ def is_atomic(expr: str):
+ return is_literal(expr) or expr in input_fields
+
+ if is_atomic(expr):
+ return
+
+ if allow_cmp:
+ maybe_cmp = re.fullmatch('(.*)([<>=!]+)(.*)', expr)
+ if maybe_cmp:
+ left, cmp, right = maybe_cmp.groups()
+ if (is_atomic(left.strip()) and is_atomic(right.strip()) and
+ cmp in {'==', '<=', '>=', '<', '>', '!='}):
+ return
+
+ raise ValueError(
+ f"Missing language specification or unknown input fields: {expr}")
Review Comment:
Fixed. I kept the "unkown input fields" as a missing/typo input name is
still a quite likely error here we should point to.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
