Build a step for generating cache DB file. If self.db_path exists and not overwritting, build an empty step. Overwise, build a step as follows. Pipe original reader to the _DatasetWriter, so that dataset field blobs are populated. Then sav
(self, overwrite=False)
| 91 | return self.original_reader._schema |
| 92 | |
| 93 | def build_cache_step(self, overwrite=False): |
| 94 | """Build a step for generating cache DB file. |
| 95 | |
| 96 | If self.db_path exists and not overwritting, build an empty step. |
| 97 | Overwise, build a step as follows. |
| 98 | Pipe original reader to the _DatasetWriter, |
| 99 | so that dataset field blobs are populated. |
| 100 | Then save these blobs into a file. |
| 101 | |
| 102 | Args: |
| 103 | overwrite: bool. If true, ignore the existing file |
| 104 | and build a new one overwritting the existing one anyway. |
| 105 | |
| 106 | Returns: |
| 107 | build_cache_step: ExecutionStep. |
| 108 | The step to be run for building a cache DB file. |
| 109 | """ |
| 110 | if os.path.exists(self.db_path) and not overwrite: |
| 111 | # cache already exists, no need to rebuild it |
| 112 | return core.execution_step('build_step', []) |
| 113 | |
| 114 | init_net = core.Net('init') |
| 115 | self._init_field_blobs_as_empty(init_net) |
| 116 | with Cluster(), core.NameScope(self.name), TaskGroup() as copy_tg: |
| 117 | pipe(self.original_reader, self.ds.writer(), num_threads=16) |
| 118 | copy_step = copy_tg.to_task().get_step() |
| 119 | save_net = core.Net('save') |
| 120 | self._save_field_blobs_to_db_file(save_net) |
| 121 | |
| 122 | return core.execution_step('build_cache', [init_net, copy_step, save_net]) |
| 123 | |
| 124 | def _save_field_blobs_to_db_file(self, net): |
| 125 | """Save dataset field blobs to a DB file at db_path""" |