[GitHub] [carbondata] xubo245 commented on a change in pull request #3819: [CARBONDATA-3855]support carbon SDK to load data from different files

[GitBox]

xubo245 commented on a change in pull request #3819:
URL: https://github.com/apache/carbondata/pull/3819#discussion_r464178115



##########
File path: sdk/sdk/src/main/java/org/apache/carbondata/sdk/file/CarbonWriterBuilder.java
##########
@@ -594,6 +614,428 @@ public CarbonWriterBuilder withJsonInput(Schema carbonSchema) {
     return this;
   }
 
+  private void validateCsvFiles() throws IOException {
+    File[] dataFiles = this.extractDataFiles();
+    for (File dataFile : dataFiles) {
+      try {
+        CsvParser csvParser = SDKUtil.buildCsvParser();
+        csvParser.beginParsing(dataFile);
+      } catch (IllegalArgumentException ex) {
+        if (ex.getCause() instanceof FileNotFoundException) {
+          throw new FileNotFoundException("File " + dataFile +
+              " not found to build carbon writer.");
+        }
+        throw ex;
+      }
+    }
+    this.dataFiles = dataFiles;
+  }
+
+  /**
+   * to build a {@link CarbonWriter}, which accepts loading CSV files.
+   *
+   * @param filePath absolute path under which files should be loaded.
+   * @return CarbonWriterBuilder
+   */
+  public CarbonWriterBuilder withCsvPath(String filePath) throws IOException {
+    if (filePath.length() == 0) {
+      throw new IllegalArgumentException("filePath can not be empty");
+    }
+    this.filePath = filePath;
+    this.isDirectory = new File(filePath).isDirectory();
+    this.withCsvInput();
+    this.validateCsvFiles();
+    return this;
+  }
+
+  /**
+   * to build a {@link CarbonWriter}, which accepts CSV files directory and
+   * list of file which has to be loaded.
+   *
+   * @param filePath directory where the CSV file exists.
+   * @param fileList list of files which has to be loaded.
+   * @return CarbonWriterBuilder
+   */
+  public CarbonWriterBuilder withCsvPath(String filePath, List<String> fileList)
+      throws IOException {
+    this.fileList = fileList;
+    this.withCsvPath(filePath);
+    return this;
+  }
+
+  private void validateJsonFiles() throws IOException {
+    File[] dataFiles = this.extractDataFiles();
+    for (File dataFile : dataFiles) {
+      try {
+        new JSONParser().parse(SDKUtil.buildJsonReader(dataFile));
+      } catch (FileNotFoundException ex) {
+        throw new FileNotFoundException("File " + dataFile + " not found to build carbon writer.");
+      } catch (ParseException ex) {
+        throw new RuntimeException("File " + dataFile + " is not in json format.");
+      }
+    }
+    this.dataFiles = dataFiles;
+  }
+
+  /**
+   * to build a {@link CarbonWriter}, which accepts loading JSON files.
+   *
+   * @param filePath absolute path under which files should be loaded.
+   * @return CarbonWriterBuilder
+   */
+  public CarbonWriterBuilder withJsonPath(String filePath) throws IOException {
+    if (filePath.length() == 0) {
+      throw new IllegalArgumentException("filePath can not be empty");
+    }
+    this.filePath = filePath;
+    this.isDirectory = new File(filePath).isDirectory();
+    this.withJsonInput();
+    this.validateJsonFiles();
+    return this;
+  }
+
+  /**
+   * to build a {@link CarbonWriter}, which accepts JSON file directory and
+   * list of file which has to be loaded.
+   *
+   * @param filePath directory where the json file exists.
+   * @param fileList list of files which has to be loaded.
+   * @return CarbonWriterBuilder
+   * @throws IOException
+   */
+  public CarbonWriterBuilder withJsonPath(String filePath, List<String> fileList)
+      throws IOException {
+    this.fileList = fileList;
+    this.withJsonPath(filePath);
+    return this;
+  }
+
+  /**
+   * to build a {@link CarbonWriter}, which accepts loading Parquet files.
+   *
+   * @param filePath absolute path under which files should be loaded.
+   * @return CarbonWriterBuilder
+   */
+  public CarbonWriterBuilder withParquetPath(String filePath) throws IOException {
+    if (filePath.length() == 0) {

Review comment:
       it will NPE when filePath is null




----------------------------------------------------------------
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.

For queries about this service, please contact Infrastructure at:
[hidden email]