Add charset support for Python file reading to improve encoding flexibility and configuration

Author: maksymuimanov

common/python-executor-common/src/main/java/io/maksymuimanov/python/file/PythonFileReader.java

@@ -32,7 +32,7 @@ public interface PythonFileReader {
     PythonScript readScript(PythonScript pythonScript);
 
     /**
-     * Returns an {@link InputStream} object representing the input stream of the given script.
+     * Returns an {@link InputStream} object representing the input reader of the given script.
      *
      * @param path non-{@code null} file system path
      * @return non-{@code null} {@link InputStream} instance pointing to the script

core/python-executor-autoconfigure/src/main/java/io/maksymuimanov/python/autoconfigure/PythonFileProperties.java

@@ -35,4 +35,8 @@ public class PythonFileProperties {
      * Base directory path where Python scripts are stored or loaded from.
      */
     private String path = "/python/";
+    /**
+     * Charset used to read Python script files.
+     */
+    private String charset = "UTF-8";
 }

core/python-executor-autoconfigure/src/main/java/io/maksymuimanov/python/autoconfigure/PythonFileReaderAutoConfiguration.java

@@ -7,6 +7,8 @@
 import org.springframework.boot.context.properties.EnableConfigurationProperties;
 import org.springframework.context.annotation.Bean;
 
+import java.nio.charset.Charset;
+
 /**
  * Spring Boot autoconfiguration for {@link PythonFileReader} beans.
  *
@@ -34,6 +36,6 @@ public class PythonFileReaderAutoConfiguration {
     @Bean
     @ConditionalOnMissingBean(PythonFileReader.class)
     public PythonFileReader basicPythonFileHandler(PythonFileProperties fileProperties) {
-        return new BasicPythonFileReader(fileProperties.getPath());
+        return new BasicPythonFileReader(fileProperties.getPath(), Charset.forName(fileProperties.getCharset()));
     }
 }

core/python-executor-autoconfigure/src/main/resources/META-INF/additional-spring-configuration-metadata.json

@@ -21,6 +21,13 @@
       "type": "java.lang.String",
       "sourceType": "io.maksymuimanov.python.autoconfigure.PythonFileProperties"
     },
+    {
+      "name": "spring.python.file.charset",
+      "description": "Charset used to read Python script files.",
+      "defaultValue": "UTF-8",
+      "type": "java.lang.String",
+      "sourceType": "io.maksymuimanov.python.autoconfigure.PythonFileProperties"
+    },
     {
       "name": "spring.python.pip.command",
       "description": "Command used to invoke pip for managing Python packages. Typically 'python -m pip', but can point to an interpreter inside a virtual environment or a Windows launcher.",

core/python-executor-core/src/main/java/io/maksymuimanov/python/file/BasicPythonFileReader.java

@@ -5,24 +5,18 @@
 import lombok.RequiredArgsConstructor;
 import org.springframework.core.io.ClassPathResource;
 
-import java.io.BufferedReader;
 import java.io.IOException;
 import java.io.InputStream;
-import java.io.InputStreamReader;
+import java.nio.charset.Charset;
 import java.util.Map;
 import java.util.concurrent.ConcurrentHashMap;
-import java.util.stream.Collectors;
 
 /**
  * Implementation of the {@link PythonFileReader} interface providing
  * reading file operations for Python scripts.
  * <p>
- * This class supports reading from Python script files and resolving script paths
- * based on configured {@link BasicPythonFileReader#rootPath}.
- * </p>
- * <p>
- * The class assumes script files are encoded in the platform default charset.
- * The returned script content preserves line breaks as newline characters.
+ * This class supports reading from Python script files and creating script input
+ * stream based on configured {@link BasicPythonFileReader#rootPath}.
  * </p>
  *
  * @see PythonFileReader
@@ -33,9 +27,10 @@
 public class BasicPythonFileReader implements PythonFileReader {
     private final Map<String, String> fileCache;
     private final String rootPath;
+    private final Charset charset;
 
-    public BasicPythonFileReader(String rootPath) {
-        this(new ConcurrentHashMap<>(), rootPath);
+    public BasicPythonFileReader(String rootPath, Charset charset) {
+        this(new ConcurrentHashMap<>(), rootPath, charset);
     }
 
     /**
@@ -50,8 +45,9 @@ public PythonScript readScript(PythonScript script) {
         try {
             String source = script.getSource();
             String body = this.fileCache.computeIfAbsent(source, path -> {
-                try (BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(this.getInputStream(path)))) {
-                    return bufferedReader.lines().collect(Collectors.joining("\n"));
+                try (InputStream inputStream = this.getInputStream(path)) {
+                    byte[] bytes = inputStream.readAllBytes();
+                    return new String(bytes, this.charset);
                 } catch (Exception e) {
                     throw new PythonFileException(e);
                 }
@@ -63,19 +59,11 @@ public PythonScript readScript(PythonScript script) {
         }
     }
 
-    /**
-     * Resolves the {@link InputStream} for the script file by appending the given relative path
-     * to the base path configured in {@link BasicPythonFileReader#rootPath}.
-     *
-     * @param path the relative path string of the script file, must be non-null
-     * @return the resolved {@link InputStream} to the script file
-     * @throws PythonFileException if the resource cannot be resolved
-     */
     @Override
     public InputStream getInputStream(String path) {
         try {
-            ClassPathResource classPathResource = new ClassPathResource(this.rootPath + path);
-            return classPathResource.getInputStream();
+            ClassPathResource resource = new ClassPathResource(this.rootPath + path);
+            return resource.getInputStream();
         } catch (IOException e) {
             throw new PythonFileException(e);
         }

core/python-executor-core/src/test/java/io/maksymuimanov/python/file/BasicPythonFileReaderTests.java

@@ -4,10 +4,12 @@
 import org.junit.jupiter.api.Assertions;
 import org.junit.jupiter.api.Test;
 
+import java.nio.charset.StandardCharsets;
+
 import static io.maksymuimanov.python.constant.TestConstants.FILE_SCRIPT;
 
 class BasicPythonFileReaderTests {
-    private static final PythonFileReader FILE_READER = new BasicPythonFileReader("/");
+    private static final PythonFileReader FILE_READER = new BasicPythonFileReader("/", StandardCharsets.UTF_8);
 
     @Test
     void testReadScript() {