نشر الموصِّل

/**
 * Main entry point for the connector. Creates and starts an indexing
 * application using the {@code ListingConnector} template and the sample's
 * custom {@code Repository} implementation.
 *
 * @param args program command line arguments
 * @throws InterruptedException thrown if an abort is issued during initialization
 */
public static void main(String[] args) throws InterruptedException {
  Repository repository = new GithubRepository();
  IndexingConnector connector = new ListingConnector(repository);
  IndexingApplication application = new IndexingApplication.Builder(connector, args)
      .build();
  application.start();
}

/**
 * Gets all of the existing item IDs from the data repository. While
 * multiple repositories are supported, only one repository is traversed
 * per call. The remaining repositories are saved in the checkpoint
 * are traversed on subsequent calls. This minimizes the amount of
 * data that needs to be reindex in the event of an error.
 *
 * <p>This method is called by {@link ListingConnector#traverse()} during
 * <em>full traversals</em>. Every document ID and metadata hash value in
 * the <em>repository</em> is pushed to the Cloud Search queue. Each pushed
 * document is later polled and processed in the {@link #getDoc(Item)} method.
 * <p>
 * The metadata hash values are pushed to aid document change detection. The
 * queue sets the document status depending on the hash comparison. If the
 * pushed ID doesn't yet exist in Cloud Search, the document's status is
 * set to <em>new</em>. If the ID exists but has a mismatched hash value,
 * its status is set to <em>modified</em>. If the ID exists and matches
 * the hash value, its status is unchanged.
 *
 * <p>In every case, the pushed content hash value is only used for
 * comparison. The hash value is only set in the queue during an
 * update (see {@link #getDoc(Item)}).
 *
 * @param checkpoint value defined and maintained by this connector
 * @return this is typically a {@link PushItems} instance
 */
@Override
public CheckpointCloseableIterable<ApiOperation> getIds(byte[] checkpoint)
    throws RepositoryException {
  List<String> repositories;
  // Decode the checkpoint if present to get the list of remaining
  // repositories to index.
  if (checkpoint != null) {
    try {
      FullTraversalCheckpoint decodedCheckpoint = FullTraversalCheckpoint
          .fromBytes(checkpoint);
      repositories = decodedCheckpoint.getRemainingRepositories();
    } catch (IOException e) {
      throw new RepositoryException.Builder()
          .setErrorMessage("Unable to deserialize checkpoint")
          .setCause(e)
          .build();
    }
  } else {
    // No previous checkpoint, scan for repositories to index
    // based on the connector configuration.
    try {
      repositories = scanRepositories();
    } catch (IOException e) {
      throw toRepositoryError(e, Optional.of("Unable to scan repositories"));
    }
  }

  if (repositories.isEmpty()) {
    // Nothing left to index. Reset the checkpoint to null so the
    // next full traversal starts from the beginning
    Collection<ApiOperation> empty = Collections.emptyList();
    return new CheckpointCloseableIterableImpl.Builder<>(empty)
        .setCheckpoint((byte[]) null)
        .setHasMore(false)
        .build();
  }

  // Still have more repositories to index. Pop the next repository to
  // index off the list. The remaining repositories make up the next
  // checkpoint.
  String repositoryToIndex = repositories.get(0);
  repositories = repositories.subList(1, repositories.size());

  try {
    log.info(() -> String.format("Traversing repository %s", repositoryToIndex));
    Collection<ApiOperation> items = collectRepositoryItems(repositoryToIndex);
    FullTraversalCheckpoint newCheckpoint = new FullTraversalCheckpoint(repositories);
    return new CheckpointCloseableIterableImpl.Builder<>(items)
        .setHasMore(true)
        .setCheckpoint(newCheckpoint.toBytes())
        .build();
  } catch (IOException e) {
    String errorMessage = String.format("Unable to traverse repo: %s",
        repositoryToIndex);
    throw toRepositoryError(e, Optional.of(errorMessage));
  }
}

/**
 * Fetch IDs to  push in to the queue for all items in the repository.
 * Currently captures issues & content in the master branch.
 *
 * @param name Name of repository to index
 * @return Items to push into the queue for later indexing
 * @throws IOException if error reading issues
 */
private Collection<ApiOperation> collectRepositoryItems(String name)
    throws IOException {
  List<ApiOperation> operations = new ArrayList<>();
  GHRepository repo = github.getRepository(name);

  // Add the repository as an item to be indexed
  String metadataHash = repo.getUpdatedAt().toString();
  String resourceName = repo.getHtmlUrl().getPath();
  PushItem repositoryPushItem = new PushItem()
      .setMetadataHash(metadataHash);
  PushItems items = new PushItems.Builder()
      .addPushItem(resourceName, repositoryPushItem)
      .build();

  operations.add(items);
  // Add issues/pull requests & files
  operations.add(collectIssues(repo));
  operations.add(collectContent(repo));
  return operations;
}

/**
 * Gets a single data repository item and indexes it if required.
 *
 * <p>This method is called by the {@link ListingConnector} during a poll
 * of the Cloud Search queue. Each queued item is processed
 * individually depending on its state in the data repository.
 *
 * @param item the data repository item to retrieve
 * @return the item's state determines which type of
 * {@link ApiOperation} is returned:
 * {@link RepositoryDoc}, {@link DeleteItem}, or {@link PushItem}
 */
@Override
public ApiOperation getDoc(Item item) throws RepositoryException {
  log.info(() -> String.format("Processing item: %s ", item.getName()));
  Object githubObject;
  try {
    // Retrieve the item from GitHub
    githubObject = getGithubObject(item.getName());
    if (githubObject instanceof GHRepository) {
      return indexItem((GHRepository) githubObject, item);
    } else if (githubObject instanceof GHPullRequest) {
      return indexItem((GHPullRequest) githubObject, item);
    } else if (githubObject instanceof GHIssue) {
      return indexItem((GHIssue) githubObject, item);
    } else if (githubObject instanceof GHContent) {
      return indexItem((GHContent) githubObject, item);
    } else {
      String errorMessage = String.format("Unexpected item received: %s",
          item.getName());
      throw new RepositoryException.Builder()
          .setErrorMessage(errorMessage)
          .setErrorType(RepositoryException.ErrorType.UNKNOWN)
          .build();
    }
  } catch (FileNotFoundException e) {
    log.info(() -> String.format("Deleting item: %s ", item.getName()));
    return ApiOperations.deleteItem(item.getName());
  } catch (IOException e) {
    String errorMessage = String.format("Unable to retrieve item: %s",
        item.getName());
    throw toRepositoryError(e, Optional.of(errorMessage));
  }
}

/**
 * Build the ApiOperation to index a content item (file).
 *
 * @param content      Content item to index
 * @param previousItem Previous item state in the index
 * @return ApiOperation (RepositoryDoc if indexing,  PushItem if not modified)
 * @throws IOException if unable to create operation
 */
private ApiOperation indexItem(GHContent content, Item previousItem)
    throws IOException {
  String metadataHash = content.getSha();

  // If previously indexed and unchanged, just requeue as unmodified
  if (canSkipIndexing(previousItem, metadataHash)) {
    return notModified(previousItem.getName());
  }

  String resourceName = new URL(content.getHtmlUrl()).getPath();
  FieldOrValue<String> title = FieldOrValue.withValue(content.getName());
  FieldOrValue<String> url = FieldOrValue.withValue(content.getHtmlUrl());

  String containerName = content.getOwner().getHtmlUrl().getPath();
  String programmingLanguage = FileExtensions.getLanguageForFile(content.getName());

  // Structured data based on the schema
  Multimap<String, Object> structuredData = ArrayListMultimap.create();
  structuredData.put("organization", content.getOwner().getOwnerName());
  structuredData.put("repository", content.getOwner().getName());
  structuredData.put("path", content.getPath());
  structuredData.put("language", programmingLanguage);

  Item item = IndexingItemBuilder.fromConfiguration(resourceName)
      .setTitle(title)
      .setContainerName(containerName)
      .setSourceRepositoryUrl(url)
      .setItemType(IndexingItemBuilder.ItemType.CONTAINER_ITEM)
      .setObjectType("file")
      .setValues(structuredData)
      .setVersion(Longs.toByteArray(System.currentTimeMillis()))
      .setHash(content.getSha())
      .build();

  // Index the file content too
  String mimeType = FileTypeMap.getDefaultFileTypeMap()
      .getContentType(content.getName());
  AbstractInputStreamContent fileContent = new InputStreamContent(
      mimeType, content.read())
      .setLength(content.getSize())
      .setCloseInputStream(true);
  return new RepositoryDoc.Builder()
      .setItem(item)
      .setContent(fileContent, IndexingService.ContentFormat.RAW)
      .setRequestMode(IndexingService.RequestMode.SYNCHRONOUS)
      .build();
}