avrotize 3.0.1__py3-none-any.whl → 3.1.0__py3-none-any.whl

avrotize/commands.json

@@ -997,6 +997,471 @@
     "suggested_output_file_path": "{input_file_name}.sql",
     "prompts": []
   },
+  {
+    "command": "sql2a",
+    "description": "Convert SQL schema to Avrotize schema (connects to live database)",
+    "group": "5_SQL",
+    "function": {
+      "name": "avrotize.sqltoavro.convert_sql_to_avro",
+      "args": {
+        "connection_string": "args.connection_string",
+        "database": "args.database",
+        "table_name": "args.table_name",
+        "avro_namespace": "args.namespace",
+        "avro_schema_file": "output_file_path",
+        "dialect": "args.dialect",
+        "emit_cloudevents": "args.emit_cloudevents",
+        "emit_cloudevents_xregistry": "args.emit_xregistry",
+        "sample_size": "args.sample_size",
+        "infer_json_schema": "args.infer_json",
+        "infer_xml_schema": "args.infer_xml",
+        "username": "args.username",
+        "password": "args.password"
+      }
+    },
+    "extensions": [],
+    "args": [
+      {
+        "name": "input",
+        "type": "str",
+        "nargs": "?",
+        "help": "Not used (database connection is live)",
+        "required": false
+      },
+      {
+        "name": "--out",
+        "type": "str",
+        "help": "Path to the Avrotize schema file",
+        "required": false
+      },
+      {
+        "name": "--connection-string",
+        "type": "str",
+        "help": "Database connection string. Examples: postgresql://host:port/db (credentials via --username/--password), postgresql://user:pass@host:port/db?sslmode=require (PostgreSQL with SSL), mysql://user:pass@host/db?ssl=true (MySQL with SSL), mssql://@host/db (SQL Server with Windows Auth)",
+        "required": true
+      },
+      {
+        "name": "--username",
+        "type": "str",
+        "help": "Database username (overrides credentials in connection string, avoids credentials in command history)",
+        "required": false
+      },
+      {
+        "name": "--password",
+        "type": "str",
+        "help": "Database password (overrides credentials in connection string, avoids credentials in command history)",
+        "required": false
+      },
+      {
+        "name": "--database",
+        "type": "str",
+        "help": "Database name (if not in connection string)",
+        "required": false
+      },
+      {
+        "name": "--table-name",
+        "type": "str",
+        "help": "Specific table name (omit for all tables)",
+        "required": false
+      },
+      {
+        "name": "--namespace",
+        "type": "str",
+        "help": "Namespace for the Avrotize schema",
+        "required": false
+      },
+      {
+        "name": "--dialect",
+        "type": "str",
+        "help": "SQL dialect",
+        "choices": [
+          "postgres",
+          "mysql",
+          "sqlserver",
+          "oracle",
+          "sqlite"
+        ],
+        "default": "postgres",
+        "required": false
+      },
+      {
+        "name": "--emit-cloudevents",
+        "type": "bool",
+        "help": "Emit CloudEvents declarations for tables with type/source/data/id columns",
+        "required": false
+      },
+      {
+        "name": "--emit-xregistry",
+        "type": "bool",
+        "help": "Emit an xRegistry manifest instead of a single Avrotize schema",
+        "required": false
+      },
+      {
+        "name": "--sample-size",
+        "type": "int",
+        "help": "Number of rows to sample for JSON/XML inference",
+        "default": 100,
+        "required": false
+      },
+      {
+        "name": "--infer-json",
+        "type": "bool",
+        "help": "Infer schema for JSON/JSONB columns",
+        "default": true,
+        "required": false
+      },
+      {
+        "name": "--infer-xml",
+        "type": "bool",
+        "help": "Infer schema for XML columns",
+        "default": true,
+        "required": false
+      }
+    ],
+    "suggested_output_file_path": "{database}.avsc",
+    "prompts": [
+      {
+        "name": "--namespace",
+        "message": "Enter the namespace for the Avro schema",
+        "type": "str",
+        "required": false
+      },
+      {
+        "name": "--dialect",
+        "message": "Select the SQL dialect",
+        "choices": [
+          "postgres",
+          "mysql",
+          "sqlserver",
+          "oracle",
+          "sqlite"
+        ],
+        "default": "postgres",
+        "required": true
+      }
+    ]
+  },
+  {
+    "command": "json2a",
+    "description": "Infer Avro schema from JSON files",
+    "group": "6_Inference",
+    "skip_input_file_handling": true,
+    "function": {
+      "name": "avrotize.jsontoschema.convert_json_to_avro",
+      "args": {
+        "input_files": "args.input",
+        "avro_schema_file": "output_file_path",
+        "type_name": "args.type_name",
+        "avro_namespace": "args.namespace",
+        "sample_size": "args.sample_size"
+      }
+    },
+    "extensions": [".json", ".jsonl", ".ndjson"],
+    "args": [
+      {
+        "name": "input",
+        "type": "str",
+        "nargs": "+",
+        "help": "JSON file(s) to analyze for schema inference",
+        "required": true
+      },
+      {
+        "name": "--out",
+        "type": "str",
+        "help": "Path to the output Avro schema file",
+        "required": false
+      },
+      {
+        "name": "--type-name",
+        "type": "str",
+        "help": "Name for the root type",
+        "default": "Document",
+        "required": false
+      },
+      {
+        "name": "--namespace",
+        "type": "str",
+        "help": "Namespace for the Avro schema",
+        "required": false
+      },
+      {
+        "name": "--sample-size",
+        "type": "int",
+        "help": "Maximum number of records to sample (0 = all)",
+        "default": 0,
+        "required": false
+      }
+    ],
+    "suggested_output_file_path": "{input_file_name}.avsc",
+    "prompts": [
+      {
+        "name": "--type-name",
+        "message": "Enter the name for the root type",
+        "type": "str",
+        "default": "Document",
+        "required": false
+      },
+      {
+        "name": "--namespace",
+        "message": "Enter the namespace for the Avro schema",
+        "type": "str",
+        "required": false
+      }
+    ]
+  },
+  {
+    "command": "json2s",
+    "description": "Infer JSON Structure schema from JSON files",
+    "group": "6_Inference",
+    "skip_input_file_handling": true,
+    "function": {
+      "name": "avrotize.jsontoschema.convert_json_to_jstruct",
+      "args": {
+        "input_files": "args.input",
+        "jstruct_schema_file": "output_file_path",
+        "type_name": "args.type_name",
+        "base_id": "args.base_id",
+        "sample_size": "args.sample_size"
+      }
+    },
+    "extensions": [".json", ".jsonl", ".ndjson"],
+    "args": [
+      {
+        "name": "input",
+        "type": "str",
+        "nargs": "+",
+        "help": "JSON file(s) to analyze for schema inference",
+        "required": true
+      },
+      {
+        "name": "--out",
+        "type": "str",
+        "help": "Path to the output JSON Structure schema file",
+        "required": false
+      },
+      {
+        "name": "--type-name",
+        "type": "str",
+        "help": "Name for the root type",
+        "default": "Document",
+        "required": false
+      },
+      {
+        "name": "--base-id",
+        "type": "str",
+        "help": "Base URI for $id generation",
+        "default": "https://example.com/",
+        "required": false
+      },
+      {
+        "name": "--sample-size",
+        "type": "int",
+        "help": "Maximum number of records to sample (0 = all)",
+        "default": 0,
+        "required": false
+      }
+    ],
+    "suggested_output_file_path": "{input_file_name}.jstruct.json",
+    "prompts": [
+      {
+        "name": "--type-name",
+        "message": "Enter the name for the root type",
+        "type": "str",
+        "default": "Document",
+        "required": false
+      },
+      {
+        "name": "--base-id",
+        "message": "Enter the base URI for $id generation",
+        "type": "str",
+        "default": "https://example.com/",
+        "required": false
+      }
+    ]
+  },
+  {
+    "command": "xml2a",
+    "description": "Infer Avro schema from XML files",
+    "group": "6_Inference",
+    "skip_input_file_handling": true,
+    "function": {
+      "name": "avrotize.xmltoschema.convert_xml_to_avro",
+      "args": {
+        "input_files": "args.input",
+        "avro_schema_file": "output_file_path",
+        "type_name": "args.type_name",
+        "avro_namespace": "args.namespace",
+        "sample_size": "args.sample_size"
+      }
+    },
+    "extensions": [".xml"],
+    "args": [
+      {
+        "name": "input",
+        "type": "str",
+        "nargs": "+",
+        "help": "XML file(s) to analyze for schema inference",
+        "required": true
+      },
+      {
+        "name": "--out",
+        "type": "str",
+        "help": "Path to the output Avro schema file",
+        "required": false
+      },
+      {
+        "name": "--type-name",
+        "type": "str",
+        "help": "Name for the root type",
+        "default": "Document",
+        "required": false
+      },
+      {
+        "name": "--namespace",
+        "type": "str",
+        "help": "Namespace for the Avro schema",
+        "required": false
+      },
+      {
+        "name": "--sample-size",
+        "type": "int",
+        "help": "Maximum number of documents to sample (0 = all)",
+        "default": 0,
+        "required": false
+      }
+    ],
+    "suggested_output_file_path": "{input_file_name}.avsc",
+    "prompts": [
+      {
+        "name": "--type-name",
+        "message": "Enter the name for the root type",
+        "type": "str",
+        "default": "Document",
+        "required": false
+      },
+      {
+        "name": "--namespace",
+        "message": "Enter the namespace for the Avro schema",
+        "type": "str",
+        "required": false
+      }
+    ]
+  },
+  {
+    "command": "xml2s",
+    "description": "Infer JSON Structure schema from XML files",
+    "group": "6_Inference",
+    "skip_input_file_handling": true,
+    "function": {
+      "name": "avrotize.xmltoschema.convert_xml_to_jstruct",
+      "args": {
+        "input_files": "args.input",
+        "jstruct_schema_file": "output_file_path",
+        "type_name": "args.type_name",
+        "base_id": "args.base_id",
+        "sample_size": "args.sample_size"
+      }
+    },
+    "extensions": [".xml"],
+    "args": [
+      {
+        "name": "input",
+        "type": "str",
+        "nargs": "+",
+        "help": "XML file(s) to analyze for schema inference",
+        "required": true
+      },
+      {
+        "name": "--out",
+        "type": "str",
+        "help": "Path to the output JSON Structure schema file",
+        "required": false
+      },
+      {
+        "name": "--type-name",
+        "type": "str",
+        "help": "Name for the root type",
+        "default": "Document",
+        "required": false
+      },
+      {
+        "name": "--base-id",
+        "type": "str",
+        "help": "Base URI for $id generation",
+        "default": "https://example.com/",
+        "required": false
+      },
+      {
+        "name": "--sample-size",
+        "type": "int",
+        "help": "Maximum number of documents to sample (0 = all)",
+        "default": 0,
+        "required": false
+      }
+    ],
+    "suggested_output_file_path": "{input_file_name}.jstruct.json",
+    "prompts": [
+      {
+        "name": "--type-name",
+        "message": "Enter the name for the root type",
+        "type": "str",
+        "default": "Document",
+        "required": false
+      },
+      {
+        "name": "--base-id",
+        "message": "Enter the base URI for $id generation",
+        "type": "str",
+        "default": "https://example.com/",
+        "required": false
+      }
+    ]
+  },
+  {
+    "command": "validate",
+    "description": "Validate JSON instances against Avro or JSON Structure schemas",
+    "group": "6_Inference",
+    "skip_input_file_handling": true,
+    "function": {
+      "name": "avrotize.validate.validate",
+      "args": {
+        "input": "args.input",
+        "schema": "args.schema",
+        "schema_type": "args.schema_type",
+        "quiet": "args.quiet"
+      }
+    },
+    "extensions": [".json", ".jsonl"],
+    "args": [
+      {
+        "name": "input",
+        "type": "str",
+        "nargs": "+",
+        "help": "JSON file(s) to validate",
+        "required": true
+      },
+      {
+        "name": "--schema",
+        "type": "str",
+        "help": "Path to schema file (.avsc for Avro, .jstruct.json for JSON Structure)",
+        "required": true
+      },
+      {
+        "name": "--schema-type",
+        "type": "str",
+        "help": "Schema type: 'avro' or 'jstruct'. Auto-detected from file extension if omitted.",
+        "required": false
+      },
+      {
+        "name": "--quiet",
+        "type": "bool",
+        "help": "Suppress output. Exit code 0 if valid, 1 if invalid.",
+        "default": false,
+        "required": false
+      }
+    ],
+    "prompts": []
+  },
   {
     "command": "a2mongo",
     "description": "Convert Avrotize schema to MongoDB schema",
@@ -1115,7 +1580,8 @@
         "avro_schema_path": "input_file_path",
         "output_path": "output_file_path",
         "avro_record_type": "args.record_type",
-        "emit_cloudevents_columns": "args.emit_cloudevents_columns"
+        "emit_cloudevents_columns": "args.emit_cloudevents_columns",
+        "output_format": "args.format"
       }
     },
     "extensions": [
@@ -1147,6 +1613,14 @@
         "help": "Add CloudEvents columns to the Iceberg schema",
         "default": false,
         "required": false
+      },
+      {
+        "name": "--format",
+        "type": "str",
+        "help": "Output format: 'arrow' for binary Arrow IPC (default), 'schema' for JSON",
+        "choices": ["schema", "arrow"],
+        "default": "arrow",
+        "required": false
       }
     ],
     "suggested_output_file_path": "{input_file_name}.iceberg",
@@ -1169,7 +1643,8 @@
         "structure_schema_path": "input_file_path",
         "output_path": "output_file_path",
         "structure_record_type": "args.record_type",
-        "emit_cloudevents_columns": "args.emit_cloudevents_columns"
+        "emit_cloudevents_columns": "args.emit_cloudevents_columns",
+        "output_format": "args.format"
       }
     },
     "extensions": [
@@ -1202,6 +1677,14 @@
         "help": "Add CloudEvents columns to the Iceberg schema",
         "default": false,
         "required": false
+      },
+      {
+        "name": "--format",
+        "type": "str",
+        "help": "Output format: 'arrow' for binary Arrow IPC (default), 'schema' for JSON",
+        "choices": ["schema", "arrow"],
+        "default": "arrow",
+        "required": false
       }
     ],
     "suggested_output_file_path": "{input_file_name}.iceberg",

avrotize/dependencies/cs/net90/dependencies.csproj

@@ -14,17 +14,17 @@
     <ItemGroup>
         <PackageReference Include="Apache.Avro" Version="1.12.0" />
         <PackageReference Include="Newtonsoft.Json" Version="13.0.4" />
-        <PackageReference Include="System.Text.Json" Version="9.0.3" />
+        <PackageReference Include="System.Text.Json" Version="10.0.1" />
         <PackageReference Include="System.Memory.Data" Version="9.0.3" />
-        <PackageReference Include="protobuf-net" Version="3.2.30" />
+        <PackageReference Include="protobuf-net" Version="3.2.56" />
         <PackageReference Include="MessagePack" Version="3.1.4" />
-        <PackageReference Include="Dahomey.Cbor" Version="1.25.1" />
+        <PackageReference Include="Dahomey.Cbor" Version="1.26.0" />
     </ItemGroup>
 
     <!-- Testing -->
     <ItemGroup>
         <PackageReference Include="NUnit" Version="4.4.0" />
-        <PackageReference Include="NUnit3TestAdapter" Version="5.2.0" />
+        <PackageReference Include="NUnit3TestAdapter" Version="6.1.0" />
         <PackageReference Include="Microsoft.NET.Test.Sdk" Version="18.0.1" />
     </ItemGroup>
 </Project>

avrotize/dependencies/java/jdk21/pom.xml

@@ -36,7 +36,7 @@
         <dependency>
             <groupId>com.fasterxml.jackson</groupId>
             <artifactId>jackson-bom</artifactId>
-            <version>2.20.1</version>
+            <version>2.18.2</version>
             <type>pom</type>
             <scope>import</scope>
         </dependency>
@@ -48,31 +48,31 @@
         <dependency>
             <groupId>com.fasterxml.jackson.core</groupId>
             <artifactId>jackson-databind</artifactId>
-            <version>2.20.1</version>
+            <version>2.18.2</version>
         </dependency>
         <dependency>
             <groupId>com.fasterxml.jackson.core</groupId>
             <artifactId>jackson-annotations</artifactId>
-            <version>2.20</version>
+            <version>2.18.2</version>
         </dependency>
 
         <!-- Testing - JUnit 5 -->
         <dependency>
             <groupId>org.junit.jupiter</groupId>
             <artifactId>junit-jupiter</artifactId>
-            <version>6.0.1</version>
+            <version>6.0.2</version>
             <scope>test</scope>
         </dependency>
         <dependency>
             <groupId>org.junit.jupiter</groupId>
             <artifactId>junit-jupiter-api</artifactId>
-            <version>6.0.1</version>
+            <version>6.0.2</version>
             <scope>test</scope>
         </dependency>
         <dependency>
             <groupId>org.junit.jupiter</groupId>
             <artifactId>junit-jupiter-engine</artifactId>
-            <version>6.0.1</version>
+            <version>6.0.2</version>
             <scope>test</scope>
         </dependency>
 

avrotize/dependencies/typescript/node22/package.json

@@ -8,7 +8,7 @@
     "kafkajs": "^2.2.4"
   },
   "devDependencies": {
-    "@types/node": "^24.10.1",
+    "@types/node": "^25.0.3",
     "typescript": "^5.7.2",
     "jest": "^30.2.0",
     "@types/jest": "^30.0.0"