[avro-schema] fix enum logic (sanitize) (#19549)

bin/configs/avro-schema-enums.yaml

@@ -0,0 +1,4 @@
+generatorName: avro-schema
+outputDir: samples/openapi3/schema/valid-enums/avro-schema-enum
+inputSpec: modules/openapi-generator/src/test/resources/3_0/avro-schema/valid-enums.yaml
+templateDir: modules/openapi-generator/src/main/resources/avro-schema

modules/openapi-generator/src/main/java/org/openapitools/codegen/languages/AvroSchemaCodegen.java

@@ -25,12 +25,20 @@ import org.openapitools.codegen.model.ModelsMap;
 
 import java.io.File;
 import java.util.Arrays;
+import java.util.Collections;
 import java.util.EnumSet;
 import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.stream.Collectors;
 
 import static org.openapitools.codegen.utils.StringUtils.camelize;
 
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
 public class AvroSchemaCodegen extends DefaultCodegen implements CodegenConfig {
+    private final Logger LOGGER = LoggerFactory.getLogger(AvroSchemaCodegen.class);
     private static final String AVRO = "avro-schema";
     protected String packageName = "model";
 
@@ -148,4 +156,44 @@ public class AvroSchemaCodegen extends DefaultCodegen implements CodegenConfig {
         return input;
     }
 
+    @Override
+    protected List<Map<String, Object>> buildEnumVars(List<Object> values, String dataType) {
+        List<Object> sanitizedValues = values.stream().map(Object::toString).map(this::sanitizeEnumValue)
+                .collect(Collectors.toList());
+        removeEnumValueCollisions(sanitizedValues);
+        return super.buildEnumVars(sanitizedValues, dataType);
+    }
+
+    /**
+     * Valid enums in Avro need to adhere to [A-Za-z_][A-Za-z0-9_]*
+     * See https://avro.apache.org/docs/1.12.0/specification/#enums
+     */
+    private String sanitizeEnumValue(String value) {
+        // Replace any non-alphanumeric characters with an underscore
+        String sanitizedValue = value.replaceAll("[^A-Za-z0-9_]", "_");
+        // If the enum starts with a number, prefix it with an underscore
+        sanitizedValue = sanitizedValue.replaceAll("^([0-9])", "_$1");
+        return sanitizedValue;
+    }
+
+    private void removeEnumValueCollisions(List<Object> values) {
+        Collections.reverse(values);
+        for (int i = 0; i < values.size(); i++) {
+            final String value = values.get(i).toString();
+            long count = values.stream().filter(v1 -> v1.equals(value)).count();
+            if (count > 1) {
+                String uniqueEnumValue = getUniqueEnumValue(value.toString(), values);
+                LOGGER.debug("Changing duplicate enumeration value from " + value + " to " + uniqueEnumValue);
+                values.set(i, uniqueEnumValue);
+            }
+        }
+        Collections.reverse(values);
+    }
+
+    private String getUniqueEnumValue(String value, List<Object> values) {
+        long count = values.stream().filter(v -> v.equals(value)).count();
+        return count > 1
+                ? getUniqueEnumValue(value + count, values)
+                : value;
+    }
 }

modules/openapi-generator/src/test/resources/3_0/avro-schema/valid-enums.yaml

@@ -0,0 +1,30 @@
+openapi: 3.0.0
+info:
+  version: 1.0.0
+  title: Test for valid enums
+paths:
+  /test:
+    get:
+      responses:
+        '200':
+          description: OK
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Sample'
+components:
+  schemas:
+    Sample:
+      properties:
+        type:
+          enum:
+            - 'a'
+            - 'b'
+            # This enum is invalid for Avro schemas, as it contains a `-`
+            - 'uh-oh'
+            # This next one starts with a number, which is invalid for Avro schemas
+            - '0h_oh'
+            # The next two is to make sure collisions are resolved properly
+            - 'coll-ision'
+            - 'coll_ision'
+          type: 'string'

samples/openapi3/schema/valid-enums/avro-schema-enum/.openapi-generator-ignore

@@ -0,0 +1,23 @@
+# OpenAPI Generator Ignore
+# Generated by openapi-generator https://github.com/openapitools/openapi-generator
+
+# Use this file to prevent files from being overwritten by the generator.
+# The patterns follow closely to .gitignore or .dockerignore.
+
+# As an example, the C# client generator defines ApiClient.cs.
+# You can make changes and tell OpenAPI Generator to ignore just this file by uncommenting the following line:
+#ApiClient.cs
+
+# You can match any string of characters against a directory, file or extension with a single asterisk (*):
+#foo/*/qux
+# The above matches foo/bar/qux and foo/baz/qux, but not foo/bar/baz/qux
+
+# You can recursively match patterns against a directory, file or extension with a double asterisk (**):
+#foo/**/qux
+# This matches foo/bar/qux, foo/baz/qux, and foo/bar/baz/qux
+
+# You can also negate patterns with an exclamation (!).
+# For example, you can ignore all files in a docs folder with the file extension .md:
+#docs/*.md
+# Then explicitly reverse the ignore rule for a single file:
+#!docs/README.md

samples/openapi3/schema/valid-enums/avro-schema-enum/.openapi-generator/FILES

@@ -0,0 +1 @@
+Sample.avsc

samples/openapi3/schema/valid-enums/avro-schema-enum/.openapi-generator/VERSION

@@ -0,0 +1 @@
+7.9.0-SNAPSHOT

samples/openapi3/schema/valid-enums/avro-schema-enum/Sample.avsc

@@ -0,0 +1,26 @@
+{
+  "namespace": "model",
+  "type": "record",
+  "doc": "",
+  "name": "Sample",
+  "fields": [
+    {
+      "name": "type",
+      "type": ["null", {
+        "type": "enum",
+        "name": "Sample_type",
+        "symbols": [
+          "a",
+          "b",
+          "uh_oh",
+          "_0h_oh",
+          "coll_ision",
+          "coll_ision2"
+        ]
+      }],
+      "doc": "",
+      "default": null
+    }
+  ]
+
+}