Feat add json validation checks #616
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
|
|
@@ -1747,6 +1747,117 @@ def apply(df: DataFrame) -> DataFrame: | |||||
| return condition, apply | ||||||
|
|
||||||
|
|
||||||
| @register_rule("row") | ||||||
| def is_valid_json(column: str | Column) -> Column: | ||||||
| """ | ||||||
| Checks whether the values in the input column is a valid JSON string. | ||||||
|
|
||||||
| Args: | ||||||
| column: Column name (str) or Column expression to check for valid JSON. | ||||||
|
|
||||||
| Returns: | ||||||
| A Spark Column representing the condition for invalid JSON strings. | ||||||
| """ | ||||||
| col_str_norm, col_expr_str, col_expr = _get_normalized_column_and_expr(column) | ||||||
| return make_condition( | ||||||
| ~F.when(F.col(col_expr_str).isNotNull(), F.try_parse_json(col_expr_str).isNotNull()), | ||||||
ghanse marked this conversation as resolved.
Show resolved
Hide resolved
|
||||||
| F.concat_ws( | ||||||
| "", | ||||||
| F.lit("Value '"), | ||||||
| col_expr.cast("string"), | ||||||
| F.lit(f"' in Column '{col_expr_str}' is not a valid JSON string"), | ||||||
| ), | ||||||
| f"{col_str_norm}_is_not_valid_json", | ||||||
| ) | ||||||
|
|
||||||
|
|
||||||
| @register_rule("row") | ||||||
| def has_json_keys(column: str | Column, keys: list[str], require_all: bool = True) -> Column: | ||||||
| """ | ||||||
| Checks whether the values in the input column contain specific JSON keys. | ||||||
|
|
||||||
| Args: | ||||||
| column: The name of the column or the column expression to check for JSON keys. | ||||||
| keys: The list of JSON keys to check for. | ||||||
| require_all: If True, all specified keys must be present. If False, at least one key must be present. | ||||||
|
|
||||||
| Returns: | ||||||
| Column: A Spark Column representing the condition for missing JSON keys. | ||||||
| """ | ||||||
| if not keys: | ||||||
| raise InvalidParameterError("The 'keys' parameter must be a non-empty list of strings.") | ||||||
| if any(not isinstance(k, str) for k in keys): | ||||||
| raise InvalidParameterError("All keys must be of type string.") | ||||||
|
|
||||||
| col_str_norm, col_expr_str, col_expr = _get_normalized_column_and_expr(column) | ||||||
| json_keys_array = F.json_object_keys(col_expr) | ||||||
|
There was a problem hiding this comment. pyspark.sql.functions does not expose json_object_keys; this will raise AttributeError at runtime. Use F.expr to call the SQL function or derive keys via from_json + map_keys. For example: json_keys_array = F.expr(f"json_object_keys({col_expr_str})").
Suggested change
There was a problem hiding this comment. Interestingly, |
||||||
| required_keys = F.array_distinct(F.array(*[F.lit(k) for k in keys])) | ||||||
|
|
||||||
| json_validation_error = is_valid_json(col_str_norm) | ||||||
| is_invalid_json = json_validation_error.isNotNull() | ||||||
|
|
||||||
| has_json_keys_msg = F.concat_ws( | ||||||
| "", | ||||||
| F.lit("Value '"), | ||||||
| F.when(col_expr.isNull(), F.lit("null")).otherwise(col_expr.cast("string")), | ||||||
| F.lit(f"' in Column '{col_expr_str}' is missing keys in the list: ["), | ||||||
| F.concat_ws(", ", F.lit(keys)), | ||||||
| F.lit("]"), | ||||||
| ) | ||||||
| message = F.when(is_invalid_json, json_validation_error).otherwise(has_json_keys_msg) | ||||||
|
|
||||||
| if require_all: | ||||||
| missing = F.array_except(required_keys, json_keys_array) | ||||||
| condition_when_valid = F.size(missing) == 0 | ||||||
| else: | ||||||
| condition_when_valid = F.arrays_overlap(json_keys_array, required_keys) | ||||||
|
|
||||||
| condition = F.when(~is_invalid_json, condition_when_valid).otherwise(F.lit(False)) | ||||||
|
|
||||||
| return make_condition( | ||||||
| ~condition, | ||||||
| message, | ||||||
| f"{col_str_norm}_does_not_have_json_keys", | ||||||
| ) | ||||||
|
|
||||||
|
|
||||||
| @register_rule("row") | ||||||
| def has_valid_json_schema(column: str | Column, schema: str | types.StructType) -> Column: | ||||||
| """ | ||||||
| Checks whether the values in the input column conform to a specified JSON schema. | ||||||
|
|
||||||
| Args: | ||||||
| column: The name of the column or the column expression to check for JSON schema conformity. | ||||||
| schema: The expected JSON schema as a DDL string (e.g., "id INT, name STRING") or StructType object. | ||||||
|
|
||||||
| Returns: | ||||||
| Column: A Spark Column representing the condition for JSON schema violations. | ||||||
| """ | ||||||
| _expected_schema = _get_schema(schema) | ||||||
|
|
||||||
| col_str_norm, col_expr_str, col_expr = _get_normalized_column_and_expr(column) | ||||||
|
|
||||||
| json_validation_error = is_valid_json(col_str_norm) | ||||||
| is_invalid_json = json_validation_error.isNotNull() | ||||||
| parsed_column = F.from_json(col_expr, _expected_schema) | ||||||
|
|
||||||
| condition = F.when(~is_invalid_json & parsed_column.isNotNull(), F.lit(True)).otherwise(F.lit(False)) | ||||||
|
|
||||||
| has_json_schema_msg = F.concat_ws( | ||||||
| "", | ||||||
| F.lit("Value '"), | ||||||
| F.when(col_expr.isNull(), F.lit("null")).otherwise(col_expr.cast("string")), | ||||||
| F.lit(f"' in Column '{col_expr_str}' does not conform to the expected JSON schema: "), | ||||||
| F.lit(_expected_schema.simpleString()), | ||||||
| ) | ||||||
|
|
||||||
| return make_condition( | ||||||
| ~condition, | ||||||
| F.when(is_invalid_json, json_validation_error).otherwise(has_json_schema_msg), | ||||||
| f"{col_str_norm}_has_invalid_json_schema", | ||||||
| ) | ||||||
|
|
||||||
|
|
||||||
| def _get_schema(input_schema: str | types.StructType, columns: list[str] | None = None) -> types.StructType: | ||||||
| """ | ||||||
| Normalize the input schema into a Spark StructType schema. | ||||||
|
|
||||||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
pls group examples for
has_json_keysandis_valid_jsontogether