exceptionfactory commented on code in PR #10013: URL: https://github.com/apache/nifi/pull/10013#discussion_r2222946299
########## nifi-extension-bundles/nifi-parquet-bundle/nifi-parquet-content-viewer/src/main/java/org/apache/parquet/web/controller/ParquetContentViewerController.java: ########## @@ -0,0 +1,167 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.parquet.web.controller; + +import com.google.gson.Gson; +import com.google.gson.GsonBuilder; +import com.google.gson.JsonParser; +import jakarta.servlet.ServletContext; +import jakarta.servlet.http.HttpServlet; +import jakarta.servlet.http.HttpServletRequest; +import jakarta.servlet.http.HttpServletResponse; +import org.apache.avro.generic.GenericRecord; +import org.apache.hadoop.conf.Configuration; +import org.apache.nifi.authorization.AccessDeniedException; +import org.apache.nifi.web.ContentAccess; +import org.apache.nifi.web.ContentRequestContext; +import org.apache.nifi.web.DownloadableContent; +import org.apache.nifi.web.HttpServletContentRequestContext; +import org.apache.nifi.web.ResourceNotFoundException; +import org.apache.parquet.avro.AvroParquetReader; +import org.apache.parquet.hadoop.ParquetReader; +import org.apache.parquet.io.InputFile; +import org.apache.nifi.parquet.shared.NifiParquetInputFile; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; +import java.io.ByteArrayInputStream; +import java.io.IOException; +import java.io.InputStream; +import java.net.HttpURLConnection; +import java.util.ArrayList; +import java.util.List; + +public class ParquetContentViewerController extends HttpServlet { + private static final Logger logger = LoggerFactory.getLogger(ParquetContentViewerController.class); + + @Override + public void doGet(final HttpServletRequest request, final HttpServletResponse response) throws IOException { + final ContentRequestContext requestContext = new HttpServletContentRequestContext(request); + + final ServletContext servletContext = request.getServletContext(); + final ContentAccess contentAccess = (ContentAccess) servletContext.getAttribute("nifi-content-access"); + // get the content + final DownloadableContent downloadableContent; + try { + downloadableContent = contentAccess.getContent(requestContext); + } catch (final ResourceNotFoundException e) { + logger.warn("Content not found", e); + response.sendError(HttpURLConnection.HTTP_NOT_FOUND, "Content not found"); + return; + } catch (final AccessDeniedException e) { + logger.warn("Content access denied", e); + response.sendError(HttpURLConnection.HTTP_FORBIDDEN, "Content access denied"); + return; + } catch (final Exception e) { + logger.warn("Content retrieval failed", e); + response.sendError(HttpURLConnection.HTTP_INTERNAL_ERROR, "Content retrieval failed"); + return; + } + + response.setStatus(HttpServletResponse.SC_OK); + + final boolean formatted = Boolean.parseBoolean(request.getParameter("formatted")); + if (!formatted) { + final InputStream contentStream = downloadableContent.getContent(); + contentStream.transferTo(response.getOutputStream()); + return; + } + + // allow the user to drive the data type but fall back to the content type if necessary + String displayName = request.getParameter("mimeTypeDisplayName"); + if (displayName == null) { + displayName = downloadableContent.getType(); + } + + if (displayName == null || !(displayName.equals("parquet") || displayName.equals("application/vnd.apache.parquet"))) { + response.sendError(HttpURLConnection.HTTP_BAD_REQUEST, "Unknown content type"); + return; + } + + try { + //Convert InputStream to a seekable InputStream + long maxBytes = 1024 * 1024 * 2; //10MB + byte[] data = getInputStreamBytes(downloadableContent.getContent(), maxBytes); + + if (data.length < 1) { + response.getOutputStream().write("Content size is too large to display.".getBytes()); + return; + } + + Configuration conf = new Configuration(); + conf.setBoolean("parquet.avro.readInt96AsFixed", true); + + final InputFile inputFile = new NifiParquetInputFile(new ByteArrayInputStream(data), data.length); + final ParquetReader<GenericRecord> reader = AvroParquetReader.<GenericRecord>builder(inputFile) + .withConf(conf) + .build(); + + //Get each column per record and save it to corresponding column list + GenericRecord record; + Gson gson = new GsonBuilder().setPrettyPrinting().create(); + boolean firstRecord = true; + + while ((record = reader.read()) != null) { + if (firstRecord) { + firstRecord = false; + } else { + response.getOutputStream().write(",\n".getBytes()); + } + + response.getOutputStream().write(gson.toJson(JsonParser.parseString(record.toString())).getBytes()); Review Comment: It should be possible to write directly to the output stream, instead of creating a string and then writing it to the stream. ########## nifi-extension-bundles/nifi-parquet-bundle/nifi-parquet-content-viewer/src/main/java/org/apache/parquet/web/controller/ParquetContentViewerController.java: ########## @@ -0,0 +1,167 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.parquet.web.controller; + +import com.google.gson.Gson; +import com.google.gson.GsonBuilder; +import com.google.gson.JsonParser; +import jakarta.servlet.ServletContext; +import jakarta.servlet.http.HttpServlet; +import jakarta.servlet.http.HttpServletRequest; +import jakarta.servlet.http.HttpServletResponse; +import org.apache.avro.generic.GenericRecord; +import org.apache.hadoop.conf.Configuration; +import org.apache.nifi.authorization.AccessDeniedException; +import org.apache.nifi.web.ContentAccess; +import org.apache.nifi.web.ContentRequestContext; +import org.apache.nifi.web.DownloadableContent; +import org.apache.nifi.web.HttpServletContentRequestContext; +import org.apache.nifi.web.ResourceNotFoundException; +import org.apache.parquet.avro.AvroParquetReader; +import org.apache.parquet.hadoop.ParquetReader; +import org.apache.parquet.io.InputFile; +import org.apache.nifi.parquet.shared.NifiParquetInputFile; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; +import java.io.ByteArrayInputStream; +import java.io.IOException; +import java.io.InputStream; +import java.net.HttpURLConnection; +import java.util.ArrayList; +import java.util.List; + +public class ParquetContentViewerController extends HttpServlet { + private static final Logger logger = LoggerFactory.getLogger(ParquetContentViewerController.class); + + @Override + public void doGet(final HttpServletRequest request, final HttpServletResponse response) throws IOException { + final ContentRequestContext requestContext = new HttpServletContentRequestContext(request); + + final ServletContext servletContext = request.getServletContext(); + final ContentAccess contentAccess = (ContentAccess) servletContext.getAttribute("nifi-content-access"); + // get the content + final DownloadableContent downloadableContent; + try { + downloadableContent = contentAccess.getContent(requestContext); + } catch (final ResourceNotFoundException e) { + logger.warn("Content not found", e); + response.sendError(HttpURLConnection.HTTP_NOT_FOUND, "Content not found"); + return; + } catch (final AccessDeniedException e) { + logger.warn("Content access denied", e); + response.sendError(HttpURLConnection.HTTP_FORBIDDEN, "Content access denied"); + return; + } catch (final Exception e) { + logger.warn("Content retrieval failed", e); + response.sendError(HttpURLConnection.HTTP_INTERNAL_ERROR, "Content retrieval failed"); + return; + } + + response.setStatus(HttpServletResponse.SC_OK); + + final boolean formatted = Boolean.parseBoolean(request.getParameter("formatted")); + if (!formatted) { + final InputStream contentStream = downloadableContent.getContent(); + contentStream.transferTo(response.getOutputStream()); + return; + } + + // allow the user to drive the data type but fall back to the content type if necessary + String displayName = request.getParameter("mimeTypeDisplayName"); + if (displayName == null) { + displayName = downloadableContent.getType(); + } + + if (displayName == null || !(displayName.equals("parquet") || displayName.equals("application/vnd.apache.parquet"))) { + response.sendError(HttpURLConnection.HTTP_BAD_REQUEST, "Unknown content type"); + return; + } + + try { + //Convert InputStream to a seekable InputStream + long maxBytes = 1024 * 1024 * 2; //10MB + byte[] data = getInputStreamBytes(downloadableContent.getContent(), maxBytes); + + if (data.length < 1) { + response.getOutputStream().write("Content size is too large to display.".getBytes()); + return; + } + + Configuration conf = new Configuration(); + conf.setBoolean("parquet.avro.readInt96AsFixed", true); + + final InputFile inputFile = new NifiParquetInputFile(new ByteArrayInputStream(data), data.length); + final ParquetReader<GenericRecord> reader = AvroParquetReader.<GenericRecord>builder(inputFile) + .withConf(conf) + .build(); + + //Get each column per record and save it to corresponding column list + GenericRecord record; + Gson gson = new GsonBuilder().setPrettyPrinting().create(); Review Comment: Gson should be avoided in general, and Jackson is preferred. ########## nifi-extension-bundles/nifi-parquet-bundle/nifi-parquet-content-viewer/src/main/java/org/apache/parquet/web/controller/ParquetContentViewerController.java: ########## @@ -0,0 +1,167 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.parquet.web.controller; + +import com.google.gson.Gson; +import com.google.gson.GsonBuilder; +import com.google.gson.JsonParser; +import jakarta.servlet.ServletContext; +import jakarta.servlet.http.HttpServlet; +import jakarta.servlet.http.HttpServletRequest; +import jakarta.servlet.http.HttpServletResponse; +import org.apache.avro.generic.GenericRecord; +import org.apache.hadoop.conf.Configuration; +import org.apache.nifi.authorization.AccessDeniedException; +import org.apache.nifi.web.ContentAccess; +import org.apache.nifi.web.ContentRequestContext; +import org.apache.nifi.web.DownloadableContent; +import org.apache.nifi.web.HttpServletContentRequestContext; +import org.apache.nifi.web.ResourceNotFoundException; +import org.apache.parquet.avro.AvroParquetReader; +import org.apache.parquet.hadoop.ParquetReader; +import org.apache.parquet.io.InputFile; +import org.apache.nifi.parquet.shared.NifiParquetInputFile; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; +import java.io.ByteArrayInputStream; +import java.io.IOException; +import java.io.InputStream; +import java.net.HttpURLConnection; +import java.util.ArrayList; +import java.util.List; + +public class ParquetContentViewerController extends HttpServlet { + private static final Logger logger = LoggerFactory.getLogger(ParquetContentViewerController.class); + + @Override + public void doGet(final HttpServletRequest request, final HttpServletResponse response) throws IOException { + final ContentRequestContext requestContext = new HttpServletContentRequestContext(request); + + final ServletContext servletContext = request.getServletContext(); + final ContentAccess contentAccess = (ContentAccess) servletContext.getAttribute("nifi-content-access"); + // get the content + final DownloadableContent downloadableContent; + try { + downloadableContent = contentAccess.getContent(requestContext); + } catch (final ResourceNotFoundException e) { + logger.warn("Content not found", e); + response.sendError(HttpURLConnection.HTTP_NOT_FOUND, "Content not found"); + return; + } catch (final AccessDeniedException e) { + logger.warn("Content access denied", e); + response.sendError(HttpURLConnection.HTTP_FORBIDDEN, "Content access denied"); + return; + } catch (final Exception e) { + logger.warn("Content retrieval failed", e); + response.sendError(HttpURLConnection.HTTP_INTERNAL_ERROR, "Content retrieval failed"); + return; + } + + response.setStatus(HttpServletResponse.SC_OK); + + final boolean formatted = Boolean.parseBoolean(request.getParameter("formatted")); + if (!formatted) { + final InputStream contentStream = downloadableContent.getContent(); + contentStream.transferTo(response.getOutputStream()); + return; + } + + // allow the user to drive the data type but fall back to the content type if necessary + String displayName = request.getParameter("mimeTypeDisplayName"); + if (displayName == null) { + displayName = downloadableContent.getType(); + } + + if (displayName == null || !(displayName.equals("parquet") || displayName.equals("application/vnd.apache.parquet"))) { + response.sendError(HttpURLConnection.HTTP_BAD_REQUEST, "Unknown content type"); + return; + } + + try { + //Convert InputStream to a seekable InputStream + long maxBytes = 1024 * 1024 * 2; //10MB Review Comment: This can be declared as a static variable. ########## nifi-extension-bundles/nifi-parquet-bundle/nifi-parquet-content-viewer/src/main/java/org/apache/parquet/web/controller/ParquetContentViewerController.java: ########## @@ -0,0 +1,167 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.parquet.web.controller; + +import com.google.gson.Gson; +import com.google.gson.GsonBuilder; +import com.google.gson.JsonParser; +import jakarta.servlet.ServletContext; +import jakarta.servlet.http.HttpServlet; +import jakarta.servlet.http.HttpServletRequest; +import jakarta.servlet.http.HttpServletResponse; +import org.apache.avro.generic.GenericRecord; +import org.apache.hadoop.conf.Configuration; +import org.apache.nifi.authorization.AccessDeniedException; +import org.apache.nifi.web.ContentAccess; +import org.apache.nifi.web.ContentRequestContext; +import org.apache.nifi.web.DownloadableContent; +import org.apache.nifi.web.HttpServletContentRequestContext; +import org.apache.nifi.web.ResourceNotFoundException; +import org.apache.parquet.avro.AvroParquetReader; +import org.apache.parquet.hadoop.ParquetReader; +import org.apache.parquet.io.InputFile; +import org.apache.nifi.parquet.shared.NifiParquetInputFile; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; +import java.io.ByteArrayInputStream; +import java.io.IOException; +import java.io.InputStream; +import java.net.HttpURLConnection; +import java.util.ArrayList; +import java.util.List; + +public class ParquetContentViewerController extends HttpServlet { + private static final Logger logger = LoggerFactory.getLogger(ParquetContentViewerController.class); + + @Override + public void doGet(final HttpServletRequest request, final HttpServletResponse response) throws IOException { + final ContentRequestContext requestContext = new HttpServletContentRequestContext(request); + + final ServletContext servletContext = request.getServletContext(); + final ContentAccess contentAccess = (ContentAccess) servletContext.getAttribute("nifi-content-access"); + // get the content + final DownloadableContent downloadableContent; + try { + downloadableContent = contentAccess.getContent(requestContext); + } catch (final ResourceNotFoundException e) { + logger.warn("Content not found", e); + response.sendError(HttpURLConnection.HTTP_NOT_FOUND, "Content not found"); + return; + } catch (final AccessDeniedException e) { + logger.warn("Content access denied", e); + response.sendError(HttpURLConnection.HTTP_FORBIDDEN, "Content access denied"); + return; + } catch (final Exception e) { + logger.warn("Content retrieval failed", e); + response.sendError(HttpURLConnection.HTTP_INTERNAL_ERROR, "Content retrieval failed"); + return; + } + + response.setStatus(HttpServletResponse.SC_OK); + + final boolean formatted = Boolean.parseBoolean(request.getParameter("formatted")); + if (!formatted) { + final InputStream contentStream = downloadableContent.getContent(); + contentStream.transferTo(response.getOutputStream()); + return; + } + + // allow the user to drive the data type but fall back to the content type if necessary + String displayName = request.getParameter("mimeTypeDisplayName"); + if (displayName == null) { + displayName = downloadableContent.getType(); + } + + if (displayName == null || !(displayName.equals("parquet") || displayName.equals("application/vnd.apache.parquet"))) { + response.sendError(HttpURLConnection.HTTP_BAD_REQUEST, "Unknown content type"); + return; + } + + try { + //Convert InputStream to a seekable InputStream + long maxBytes = 1024 * 1024 * 2; //10MB + byte[] data = getInputStreamBytes(downloadableContent.getContent(), maxBytes); + + if (data.length < 1) { + response.getOutputStream().write("Content size is too large to display.".getBytes()); + return; + } + + Configuration conf = new Configuration(); + conf.setBoolean("parquet.avro.readInt96AsFixed", true); Review Comment: Is there a reason for this property setting? It should be commented if needed as to the reason. ########## nifi-extension-bundles/nifi-parquet-bundle/nifi-parquet-content-viewer/src/main/java/org/apache/parquet/web/controller/ParquetContentViewerController.java: ########## @@ -0,0 +1,167 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.parquet.web.controller; + +import com.google.gson.Gson; +import com.google.gson.GsonBuilder; +import com.google.gson.JsonParser; +import jakarta.servlet.ServletContext; +import jakarta.servlet.http.HttpServlet; +import jakarta.servlet.http.HttpServletRequest; +import jakarta.servlet.http.HttpServletResponse; +import org.apache.avro.generic.GenericRecord; +import org.apache.hadoop.conf.Configuration; +import org.apache.nifi.authorization.AccessDeniedException; +import org.apache.nifi.web.ContentAccess; +import org.apache.nifi.web.ContentRequestContext; +import org.apache.nifi.web.DownloadableContent; +import org.apache.nifi.web.HttpServletContentRequestContext; +import org.apache.nifi.web.ResourceNotFoundException; +import org.apache.parquet.avro.AvroParquetReader; +import org.apache.parquet.hadoop.ParquetReader; +import org.apache.parquet.io.InputFile; +import org.apache.nifi.parquet.shared.NifiParquetInputFile; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; +import java.io.ByteArrayInputStream; +import java.io.IOException; +import java.io.InputStream; +import java.net.HttpURLConnection; +import java.util.ArrayList; +import java.util.List; + +public class ParquetContentViewerController extends HttpServlet { + private static final Logger logger = LoggerFactory.getLogger(ParquetContentViewerController.class); + + @Override + public void doGet(final HttpServletRequest request, final HttpServletResponse response) throws IOException { + final ContentRequestContext requestContext = new HttpServletContentRequestContext(request); + + final ServletContext servletContext = request.getServletContext(); + final ContentAccess contentAccess = (ContentAccess) servletContext.getAttribute("nifi-content-access"); + // get the content + final DownloadableContent downloadableContent; + try { + downloadableContent = contentAccess.getContent(requestContext); + } catch (final ResourceNotFoundException e) { + logger.warn("Content not found", e); + response.sendError(HttpURLConnection.HTTP_NOT_FOUND, "Content not found"); + return; + } catch (final AccessDeniedException e) { + logger.warn("Content access denied", e); + response.sendError(HttpURLConnection.HTTP_FORBIDDEN, "Content access denied"); + return; + } catch (final Exception e) { + logger.warn("Content retrieval failed", e); + response.sendError(HttpURLConnection.HTTP_INTERNAL_ERROR, "Content retrieval failed"); + return; + } + + response.setStatus(HttpServletResponse.SC_OK); + + final boolean formatted = Boolean.parseBoolean(request.getParameter("formatted")); + if (!formatted) { + final InputStream contentStream = downloadableContent.getContent(); + contentStream.transferTo(response.getOutputStream()); + return; + } + + // allow the user to drive the data type but fall back to the content type if necessary + String displayName = request.getParameter("mimeTypeDisplayName"); + if (displayName == null) { + displayName = downloadableContent.getType(); + } + + if (displayName == null || !(displayName.equals("parquet") || displayName.equals("application/vnd.apache.parquet"))) { + response.sendError(HttpURLConnection.HTTP_BAD_REQUEST, "Unknown content type"); + return; + } + + try { + //Convert InputStream to a seekable InputStream + long maxBytes = 1024 * 1024 * 2; //10MB + byte[] data = getInputStreamBytes(downloadableContent.getContent(), maxBytes); + + if (data.length < 1) { + response.getOutputStream().write("Content size is too large to display.".getBytes()); + return; + } + + Configuration conf = new Configuration(); + conf.setBoolean("parquet.avro.readInt96AsFixed", true); + + final InputFile inputFile = new NifiParquetInputFile(new ByteArrayInputStream(data), data.length); + final ParquetReader<GenericRecord> reader = AvroParquetReader.<GenericRecord>builder(inputFile) + .withConf(conf) + .build(); + + //Get each column per record and save it to corresponding column list + GenericRecord record; + Gson gson = new GsonBuilder().setPrettyPrinting().create(); + boolean firstRecord = true; + + while ((record = reader.read()) != null) { + if (firstRecord) { + firstRecord = false; + } else { + response.getOutputStream().write(",\n".getBytes()); + } + + response.getOutputStream().write(gson.toJson(JsonParser.parseString(record.toString())).getBytes()); + } + } catch (final Throwable t) { + logger.warn("Unable to format FlowFile content", t); + response.sendError(HttpURLConnection.HTTP_INTERNAL_ERROR, "Unable to format FlowFile content"); + } + } + + private byte[] getInputStreamBytes(final InputStream inputStream, long maxBytes) throws IOException { Review Comment: This method can be refactored to use a ByteArrayOutputStream and transferTo, avoiding the intermediate List of byte arrays. ########## nifi-extension-bundles/nifi-parquet-bundle/nifi-parquet-content-viewer/src/main/java/org/apache/parquet/web/controller/ParquetContentViewerController.java: ########## @@ -0,0 +1,167 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.parquet.web.controller; + +import com.google.gson.Gson; +import com.google.gson.GsonBuilder; +import com.google.gson.JsonParser; +import jakarta.servlet.ServletContext; +import jakarta.servlet.http.HttpServlet; +import jakarta.servlet.http.HttpServletRequest; +import jakarta.servlet.http.HttpServletResponse; +import org.apache.avro.generic.GenericRecord; +import org.apache.hadoop.conf.Configuration; +import org.apache.nifi.authorization.AccessDeniedException; +import org.apache.nifi.web.ContentAccess; +import org.apache.nifi.web.ContentRequestContext; +import org.apache.nifi.web.DownloadableContent; +import org.apache.nifi.web.HttpServletContentRequestContext; +import org.apache.nifi.web.ResourceNotFoundException; +import org.apache.parquet.avro.AvroParquetReader; +import org.apache.parquet.hadoop.ParquetReader; +import org.apache.parquet.io.InputFile; +import org.apache.nifi.parquet.shared.NifiParquetInputFile; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; +import java.io.ByteArrayInputStream; +import java.io.IOException; +import java.io.InputStream; +import java.net.HttpURLConnection; +import java.util.ArrayList; +import java.util.List; + +public class ParquetContentViewerController extends HttpServlet { + private static final Logger logger = LoggerFactory.getLogger(ParquetContentViewerController.class); + + @Override + public void doGet(final HttpServletRequest request, final HttpServletResponse response) throws IOException { + final ContentRequestContext requestContext = new HttpServletContentRequestContext(request); + + final ServletContext servletContext = request.getServletContext(); + final ContentAccess contentAccess = (ContentAccess) servletContext.getAttribute("nifi-content-access"); + // get the content + final DownloadableContent downloadableContent; + try { + downloadableContent = contentAccess.getContent(requestContext); + } catch (final ResourceNotFoundException e) { + logger.warn("Content not found", e); + response.sendError(HttpURLConnection.HTTP_NOT_FOUND, "Content not found"); + return; + } catch (final AccessDeniedException e) { + logger.warn("Content access denied", e); + response.sendError(HttpURLConnection.HTTP_FORBIDDEN, "Content access denied"); + return; + } catch (final Exception e) { + logger.warn("Content retrieval failed", e); + response.sendError(HttpURLConnection.HTTP_INTERNAL_ERROR, "Content retrieval failed"); + return; + } + + response.setStatus(HttpServletResponse.SC_OK); + + final boolean formatted = Boolean.parseBoolean(request.getParameter("formatted")); + if (!formatted) { + final InputStream contentStream = downloadableContent.getContent(); + contentStream.transferTo(response.getOutputStream()); + return; + } + + // allow the user to drive the data type but fall back to the content type if necessary + String displayName = request.getParameter("mimeTypeDisplayName"); + if (displayName == null) { + displayName = downloadableContent.getType(); + } + + if (displayName == null || !(displayName.equals("parquet") || displayName.equals("application/vnd.apache.parquet"))) { + response.sendError(HttpURLConnection.HTTP_BAD_REQUEST, "Unknown content type"); + return; + } + + try { + //Convert InputStream to a seekable InputStream + long maxBytes = 1024 * 1024 * 2; //10MB + byte[] data = getInputStreamBytes(downloadableContent.getContent(), maxBytes); + + if (data.length < 1) { Review Comment: This can be simplified: ```suggestion if (data.length == 0) { ``` ########## nifi-extension-bundles/nifi-parquet-bundle/nifi-parquet-content-viewer/src/main/java/org/apache/parquet/web/controller/ParquetContentViewerController.java: ########## @@ -0,0 +1,167 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.parquet.web.controller; + +import com.google.gson.Gson; +import com.google.gson.GsonBuilder; +import com.google.gson.JsonParser; +import jakarta.servlet.ServletContext; +import jakarta.servlet.http.HttpServlet; +import jakarta.servlet.http.HttpServletRequest; +import jakarta.servlet.http.HttpServletResponse; +import org.apache.avro.generic.GenericRecord; +import org.apache.hadoop.conf.Configuration; +import org.apache.nifi.authorization.AccessDeniedException; +import org.apache.nifi.web.ContentAccess; +import org.apache.nifi.web.ContentRequestContext; +import org.apache.nifi.web.DownloadableContent; +import org.apache.nifi.web.HttpServletContentRequestContext; +import org.apache.nifi.web.ResourceNotFoundException; +import org.apache.parquet.avro.AvroParquetReader; +import org.apache.parquet.hadoop.ParquetReader; +import org.apache.parquet.io.InputFile; +import org.apache.nifi.parquet.shared.NifiParquetInputFile; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; +import java.io.ByteArrayInputStream; +import java.io.IOException; +import java.io.InputStream; +import java.net.HttpURLConnection; +import java.util.ArrayList; +import java.util.List; + +public class ParquetContentViewerController extends HttpServlet { + private static final Logger logger = LoggerFactory.getLogger(ParquetContentViewerController.class); + + @Override + public void doGet(final HttpServletRequest request, final HttpServletResponse response) throws IOException { + final ContentRequestContext requestContext = new HttpServletContentRequestContext(request); + + final ServletContext servletContext = request.getServletContext(); + final ContentAccess contentAccess = (ContentAccess) servletContext.getAttribute("nifi-content-access"); + // get the content + final DownloadableContent downloadableContent; + try { + downloadableContent = contentAccess.getContent(requestContext); + } catch (final ResourceNotFoundException e) { + logger.warn("Content not found", e); + response.sendError(HttpURLConnection.HTTP_NOT_FOUND, "Content not found"); + return; + } catch (final AccessDeniedException e) { + logger.warn("Content access denied", e); + response.sendError(HttpURLConnection.HTTP_FORBIDDEN, "Content access denied"); + return; + } catch (final Exception e) { + logger.warn("Content retrieval failed", e); + response.sendError(HttpURLConnection.HTTP_INTERNAL_ERROR, "Content retrieval failed"); + return; + } + + response.setStatus(HttpServletResponse.SC_OK); + + final boolean formatted = Boolean.parseBoolean(request.getParameter("formatted")); + if (!formatted) { + final InputStream contentStream = downloadableContent.getContent(); + contentStream.transferTo(response.getOutputStream()); + return; + } + + // allow the user to drive the data type but fall back to the content type if necessary + String displayName = request.getParameter("mimeTypeDisplayName"); + if (displayName == null) { + displayName = downloadableContent.getType(); + } + + if (displayName == null || !(displayName.equals("parquet") || displayName.equals("application/vnd.apache.parquet"))) { + response.sendError(HttpURLConnection.HTTP_BAD_REQUEST, "Unknown content type"); + return; + } + + try { + //Convert InputStream to a seekable InputStream + long maxBytes = 1024 * 1024 * 2; //10MB + byte[] data = getInputStreamBytes(downloadableContent.getContent(), maxBytes); + + if (data.length < 1) { + response.getOutputStream().write("Content size is too large to display.".getBytes()); + return; + } + + Configuration conf = new Configuration(); + conf.setBoolean("parquet.avro.readInt96AsFixed", true); + + final InputFile inputFile = new NifiParquetInputFile(new ByteArrayInputStream(data), data.length); + final ParquetReader<GenericRecord> reader = AvroParquetReader.<GenericRecord>builder(inputFile) + .withConf(conf) + .build(); + + //Get each column per record and save it to corresponding column list + GenericRecord record; + Gson gson = new GsonBuilder().setPrettyPrinting().create(); + boolean firstRecord = true; + + while ((record = reader.read()) != null) { + if (firstRecord) { + firstRecord = false; + } else { + response.getOutputStream().write(",\n".getBytes()); + } + + response.getOutputStream().write(gson.toJson(JsonParser.parseString(record.toString())).getBytes()); + } + } catch (final Throwable t) { + logger.warn("Unable to format FlowFile content", t); + response.sendError(HttpURLConnection.HTTP_INTERNAL_ERROR, "Unable to format FlowFile content"); + } + } + + private byte[] getInputStreamBytes(final InputStream inputStream, long maxBytes) throws IOException { + final int bufferSize = 8 * 1024; //8KB Review Comment: This can be set to a static variable. -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
