cognite-extractor-utils 7.1.4__py3-none-any.whl → 7.1.6__py3-none-any.whl

cognite/extractorutils/__init__.py

@@ -16,5 +16,5 @@
 Cognite extractor utils is a Python package that simplifies the development of new extractors.
 """
 
-__version__ = "7.1.4"
+__version__ = "7.1.6"
 from .base import Extractor

cognite/extractorutils/uploader/files.py

@@ -251,70 +251,72 @@ class IOFileUploadQueue(AbstractUploadQueue):
             max_delay=RETRY_MAX_DELAY,
             backoff=RETRY_BACKOFF_FACTOR,
         )
-        def _upload_single(read_file: Callable[[], BinaryIO], file_meta: FileMetadata) -> None:
+        def upload_file(read_file: Callable[[], BinaryIO], file_meta: FileMetadata) -> None:
+            with read_file() as file:
+                size = super_len(file)
+                if size == 0:
+                    # upload just the file metadata witout data
+                    file_meta, _url = self.cdf_client.files.create(
+                        file_metadata=file_meta, overwrite=self.overwrite_existing
+                    )
+                elif size >= self.max_single_chunk_file_size:
+                    # The minimum chunk size is 4000MiB.
+                    chunks = ChunkedStream(file, self.max_file_chunk_size, size)
+                    self.logger.debug(
+                        f"File {file_meta.external_id} is larger than 5GiB ({size})"
+                        f", uploading in {chunks.chunk_count} chunks"
+                    )
+                    with self.cdf_client.files.multipart_upload_session(
+                        file_meta.name if file_meta.name is not None else "",
+                        parts=chunks.chunk_count,
+                        overwrite=self.overwrite_existing,
+                        external_id=file_meta.external_id,
+                        source=file_meta.source,
+                        mime_type=file_meta.mime_type,
+                        metadata=file_meta.metadata,
+                        directory=file_meta.directory,
+                        asset_ids=file_meta.asset_ids,
+                        data_set_id=file_meta.data_set_id,
+                        labels=file_meta.labels,
+                        geo_location=file_meta.geo_location,
+                        source_created_time=file_meta.source_created_time,
+                        source_modified_time=file_meta.source_modified_time,
+                        security_categories=file_meta.security_categories,
+                    ) as session:
+                        while chunks.next_chunk():
+                            session.upload_part(chunks.current_chunk, chunks)
+                        file_meta = session.file_metadata
+                else:
+                    file_meta = self.cdf_client.files.upload_bytes(
+                        file,
+                        file_meta.name if file_meta.name is not None else "",
+                        overwrite=self.overwrite_existing,
+                        external_id=file_meta.external_id,
+                        source=file_meta.source,
+                        mime_type=file_meta.mime_type,
+                        metadata=file_meta.metadata,
+                        directory=file_meta.directory,
+                        asset_ids=file_meta.asset_ids,
+                        data_set_id=file_meta.data_set_id,
+                        labels=file_meta.labels,
+                        geo_location=file_meta.geo_location,
+                        source_created_time=file_meta.source_created_time,
+                        source_modified_time=file_meta.source_modified_time,
+                        security_categories=file_meta.security_categories,
+                    )
+
+            if self.post_upload_function:
+                try:
+                    self.post_upload_function([file_meta])
+                except Exception as e:
+                    self.logger.error("Error in upload callback: %s", str(e))
+
+        def wrapped_upload(read_file: Callable[[], BinaryIO], file_meta: FileMetadata) -> None:
             try:
-                # Upload file
-                with read_file() as file:
-                    size = super_len(file)
-                    if size == 0:
-                        # upload just the file metadata witout data
-                        file_meta, _url = self.cdf_client.files.create(
-                            file_metadata=file_meta, overwrite=self.overwrite_existing
-                        )
-                    elif size >= self.max_single_chunk_file_size:
-                        # The minimum chunk size is 4000MiB.
-                        chunks = ChunkedStream(file, self.max_file_chunk_size, size)
-                        self.logger.debug(
-                            f"File {file_meta.external_id} is larger than 5GiB ({size})"
-                            f", uploading in {chunks.chunk_count} chunks"
-                        )
-                        with self.cdf_client.files.multipart_upload_session(
-                            file_meta.name if file_meta.name is not None else "",
-                            parts=chunks.chunk_count,
-                            overwrite=self.overwrite_existing,
-                            external_id=file_meta.external_id,
-                            source=file_meta.source,
-                            mime_type=file_meta.mime_type,
-                            metadata=file_meta.metadata,
-                            directory=file_meta.directory,
-                            asset_ids=file_meta.asset_ids,
-                            data_set_id=file_meta.data_set_id,
-                            labels=file_meta.labels,
-                            geo_location=file_meta.geo_location,
-                            source_created_time=file_meta.source_created_time,
-                            source_modified_time=file_meta.source_modified_time,
-                            security_categories=file_meta.security_categories,
-                        ) as session:
-                            while chunks.next_chunk():
-                                session.upload_part(chunks.current_chunk, chunks)
-                            file_meta = session.file_metadata
-                    else:
-                        file_meta = self.cdf_client.files.upload_bytes(
-                            file,
-                            file_meta.name if file_meta.name is not None else "",
-                            overwrite=self.overwrite_existing,
-                            external_id=file_meta.external_id,
-                            source=file_meta.source,
-                            mime_type=file_meta.mime_type,
-                            metadata=file_meta.metadata,
-                            directory=file_meta.directory,
-                            asset_ids=file_meta.asset_ids,
-                            data_set_id=file_meta.data_set_id,
-                            labels=file_meta.labels,
-                            geo_location=file_meta.geo_location,
-                            source_created_time=file_meta.source_created_time,
-                            source_modified_time=file_meta.source_modified_time,
-                            security_categories=file_meta.security_categories,
-                        )
-
-                if self.post_upload_function:
-                    try:
-                        self.post_upload_function([file_meta])
-                    except Exception as e:
-                        self.logger.error("Error in upload callback: %s", str(e))
+                upload_file(read_file, file_meta)
 
             except Exception as e:
-                self.logger.exception("Unexpected error while uploading file")
+                self.logger.exception(f"Unexpected error while uploading file: {file_meta.external_id}")
                 self.errors.append(e)
 
             finally:
@@ -331,7 +333,7 @@ class IOFileUploadQueue(AbstractUploadQueue):
                     pass
 
         with self.lock:
-            self.upload_queue.append(self._pool.submit(_upload_single, read_file, file_meta))
+            self.upload_queue.append(self._pool.submit(wrapped_upload, read_file, file_meta))
             self.upload_queue_size += 1
             self.files_queued.inc()
             self.queue_size.set(self.upload_queue_size)

{cognite_extractor_utils-7.1.4.dist-info → cognite_extractor_utils-7.1.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cognite-extractor-utils
-Version: 7.1.4
+Version: 7.1.6
 Summary: Utilities for easier development of extractors for CDF
 Home-page: https://github.com/cognitedata/python-extractor-utils
 License: Apache-2.0
@@ -18,7 +18,7 @@ Provides-Extra: experimental
 Requires-Dist: arrow (>=1.0.0,<2.0.0)
 Requires-Dist: azure-identity (>=1.14.0,<2.0.0)
 Requires-Dist: azure-keyvault-secrets (>=4.7.0,<5.0.0)
-Requires-Dist: cognite-sdk (>=7.41.0,<8.0.0)
+Requires-Dist: cognite-sdk (>=7.43.3,<8.0.0)
 Requires-Dist: dacite (>=1.6.0,<2.0.0)
 Requires-Dist: decorator (>=5.1.1,<6.0.0)
 Requires-Dist: more-itertools (>=10.0.0,<11.0.0)

{cognite_extractor_utils-7.1.4.dist-info → cognite_extractor_utils-7.1.6.dist-info}/RECORD

@@ -1,4 +1,4 @@
-cognite/extractorutils/__init__.py,sha256=SEjG_txXBnbsMe3Fr5VxS1poP4XYsm6RM7d-g-_s81U,739
+cognite/extractorutils/__init__.py,sha256=rJAstzCVQ53u8dhEY1mpXwfauLJj4Apwuc4T0SywH-Y,739
 cognite/extractorutils/_inner_util.py,sha256=gmz6aqS7jDNsg8z4RHgJjMFohDLOMiaU4gMWBhg3xcE,1558
 cognite/extractorutils/base.py,sha256=q6NU2bPec3WOasVnnIFoh-aUJudVZWZ2R6emz3IRj8Q,16391
 cognite/extractorutils/configtools/__init__.py,sha256=L-daaqInIsmHcjb2forJeY0fW8tz1mlteOUo7IsWnrU,3059
@@ -15,13 +15,13 @@ cognite/extractorutils/uploader/_base.py,sha256=wktbV8dpb8zBOsNaECZkBNoJSpOz437N
 cognite/extractorutils/uploader/_metrics.py,sha256=J2LJXb19L_SLSJ_voNIQHYLp0pjxUKevpH1q_xKX6Hk,3247
 cognite/extractorutils/uploader/assets.py,sha256=2E90N1kxsaA6Ah4h0_r_dTVhDYY_68ItRWrHYkkltJw,5628
 cognite/extractorutils/uploader/events.py,sha256=NZP2tMoU_rh_rb-EZiUBsOT5KdNABHN4c9Oddk0OsdE,5680
-cognite/extractorutils/uploader/files.py,sha256=-yskmzcS9FcAsT2wmu3G4pd9cHJeiNqxmrERoRC72Dg,18417
+cognite/extractorutils/uploader/files.py,sha256=31kPS4fwz8ZSXWss-CKmYTM6ZLVx9LtsDe7LHT7Wy98,18329
 cognite/extractorutils/uploader/raw.py,sha256=wFjF90PFTjmByOWx_Y4_YfDJ2w2jl0EQJ2Tjx2MP2PM,6738
 cognite/extractorutils/uploader/time_series.py,sha256=WAtEQy7k5IjG-sw1oWwCujIM6PjHZYl4LKa4wy2tBPw,26817
 cognite/extractorutils/uploader_extractor.py,sha256=E-mpVvbPg_Tk90U4S9JybV0duptJ2SXE88HB6npE3zI,7732
 cognite/extractorutils/uploader_types.py,sha256=wxfrsiKPTzG5lmoYtQsxt8Xyj-s5HnaLl8WDzJNrazg,1020
 cognite/extractorutils/util.py,sha256=p7AGEgeIU0bNjuFJcFR3V5ZYr6QDj_ZC3zGxRJTf4yk,17198
-cognite_extractor_utils-7.1.4.dist-info/LICENSE,sha256=psuoW8kuDP96RQsdhzwOqi6fyWv0ct8CR6Jr7He_P_k,10173
-cognite_extractor_utils-7.1.4.dist-info/METADATA,sha256=2kFFLglmkRQH5oVko9iD3BZWELQrHbOdUQ2KH-QBJhI,5446
-cognite_extractor_utils-7.1.4.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-cognite_extractor_utils-7.1.4.dist-info/RECORD,,
+cognite_extractor_utils-7.1.6.dist-info/LICENSE,sha256=psuoW8kuDP96RQsdhzwOqi6fyWv0ct8CR6Jr7He_P_k,10173
+cognite_extractor_utils-7.1.6.dist-info/METADATA,sha256=lKPIa6knFqkRfZNTIff9JyC-dTnBYKLVbGmgASboGLs,5446
+cognite_extractor_utils-7.1.6.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+cognite_extractor_utils-7.1.6.dist-info/RECORD,,