3b1bf154144ca1c637471605384c5a438ee6f659,deeplearning/clgen/corpuses/corpuses.py,Corpus,Create,#Corpus#,200

Before Change

    // Nothing to do for already-encoded databases.
    // TODO(github.com/ChrisCummins/clgen/issues/130): Refactor this after
    // splitting out Corpus class.
    if self.config.HasField("pre_encoded_corpus_url"):
      return

    preprocessed_lock_path = pathlib.Path(
        self.preprocessed.url[len("sqlite:///"):]).parent / "LOCK"
    with lockfile.LockFile(preprocessed_lock_path):
      self.preprocessed.Create(self.config)

After Change

      config_to_store.ClearField("contentfiles")
      corpus = session.GetOrAdd(
          dashboard_db.Corpus,
          config_proto_sha1=crypto.sha1(config_to_store.SerializeToString()),
          config_proto=str(config_to_store),
          preprocessed_url=self.preprocessed.url,
          encoded_url=self.encoded.url,
          summary=self.GetShortSummary(),
      )
      session.flush()
      self._dashboard_db_id = corpus.id

  @property
  def dashboard_db_id(self) -> int:
    if not self._created:

Instances