🎉Source File: Add datatime format parsing support for csv files (airb…

…ytehq#25445)

* Add datatime format parsing support

* Updated subject in docs

* Bump file secure

* PR number bumped

* Fix typo

* auto-bump connector version

---------

Co-authored-by: Octavia Squidington III <octavia-squidington-iii@users.noreply.github.com>

airbyte-config-oss/init-oss/src/main/resources/seed/oss_catalog.json

@@ -12862,7 +12862,7 @@
     "sourceDefinitionId": "778daa7c-feaf-4db6-96f3-70fd645acc77",
     "name": "File (CSV, JSON, Excel, Feather, Parquet)",
     "dockerRepository": "airbyte/source-file",
-    "dockerImageTag": "0.2.38",
+    "dockerImageTag": "0.3.0",
     "documentationUrl": "https://docs.airbyte.com/integrations/sources/file",
     "icon": "file.svg",
     "sourceType": "file",

airbyte-config-oss/init-oss/src/main/resources/seed/source_definitions.yaml

@@ -637,7 +637,7 @@
 - name: File (CSV, JSON, Excel, Feather, Parquet)
   sourceDefinitionId: 778daa7c-feaf-4db6-96f3-70fd645acc77
   dockerRepository: airbyte/source-file
-  dockerImageTag: 0.2.38
+  dockerImageTag: 0.3.0
   documentationUrl: https://docs.airbyte.com/integrations/sources/file
   icon: file.svg
   sourceType: file

airbyte-config-oss/init-oss/src/main/resources/seed/source_specs.yaml

@@ -4555,7 +4555,7 @@
     supportsNormalization: false
     supportsDBT: false
     supported_destination_sync_modes: []
-- dockerImage: "airbyte/source-file:0.2.38"
+- dockerImage: "airbyte/source-file:0.3.0"
   spec:
     documentationUrl: "https://docs.airbyte.com/integrations/sources/file"
     connectionSpecification:

airbyte-integrations/connectors/source-file-secure/Dockerfile

@@ -9,5 +9,5 @@ RUN pip install .
 ENV AIRBYTE_ENTRYPOINT "python /airbyte/integration_code/main.py"
 ENTRYPOINT ["python", "/airbyte/integration_code/main.py"]
 
-LABEL io.airbyte.version=0.2.38
+LABEL io.airbyte.version=0.3.0
 LABEL io.airbyte.name=airbyte/source-file-secure

airbyte-integrations/connectors/source-file/Dockerfile

@@ -17,5 +17,5 @@ COPY source_file ./source_file
 ENV AIRBYTE_ENTRYPOINT "python /airbyte/integration_code/main.py"
 ENTRYPOINT ["python", "/airbyte/integration_code/main.py"]
 
-LABEL io.airbyte.version=0.2.38
+LABEL io.airbyte.version=0.3.0
 LABEL io.airbyte.name=airbyte/source-file

airbyte-integrations/connectors/source-file/source_file/client.py

@@ -364,6 +364,8 @@ def dtype_to_json_type(current_type: str, dtype) -> str:
             return "number"
         if dtype == "bool" and (not current_type or current_type == "boolean"):
             return "boolean"
+        if dtype == "datetime64[ns]":
+            return "datetime"
         return "string"
 
     @property
@@ -419,8 +421,14 @@ def _stream_properties(self, fp, empty_schema: bool = False, read_sample_chunk:
             for col in df.columns:
                 # if data type of the same column differs in dataframes, we choose the broadest one
                 prev_frame_column_type = fields.get(col)
-                fields[col] = self.dtype_to_json_type(prev_frame_column_type, df[col].dtype)
-        return {field: {"type": [fields[field], "null"]} for field in fields}
+                df_type = df[col].dtype
+                fields[col] = self.dtype_to_json_type(prev_frame_column_type, df_type)
+        return {
+            field: (
+                {"type": ["string", "null"], "format": "datetime"} if fields[field] == "datetime" else {"type": [fields[field], "null"]}
+            )
+            for field in fields
+        }
 
     def streams(self, empty_schema: bool = False) -> Iterable:
         """Discovers available streams"""

airbyte-integrations/connectors/source-file/unit_tests/test_client.py

@@ -93,6 +93,7 @@ def test_load_nested_json(client, absolute_path, test_files):
         ("boolean", "bool", "boolean"),
         ("number", "int64", "number"),
         ("number", "float64", "number"),
+        ("number", "datetime64[ns]", "datetime"),
     ],
 )
 def test_dtype_to_json_type(client, current_type, dtype, expected):

airbyte-integrations/connectors/source-file/unit_tests/test_source.py

@@ -42,7 +42,7 @@ def test_csv_with_utf16_encoding(absolute_path, test_files):
     config_local_csv_utf16 = {
         "dataset_name": "AAA",
         "format": "csv",
-        "reader_options": '{"encoding":"utf_16"}',
+        "reader_options": '{"encoding":"utf_16", "parse_dates": [\"header5\"]}',
         "url": f"{absolute_path}/{test_files}/test_utf16.csv",
         "provider": {"storage": "local"},
     }
@@ -53,6 +53,7 @@ def test_csv_with_utf16_encoding(absolute_path, test_files):
             "header2": {"type": ["number", "null"]},
             "header3": {"type": ["number", "null"]},
             "header4": {"type": ["boolean", "null"]},
+            "header5": {"type": ["string", "null"], "format": "datetime"},
         },
         "type": "object",
     }

connectors.md

@@ -75,7 +75,7 @@
 | **Facebook Pages** | <img alt="Facebook Pages icon" src="https://raw.githubusercontent.com/airbytehq/airbyte /master/airbyte-config-oss/init-oss/src/main/resources/icons/facebook.svg" height="30" height="30"/> | Source | airbyte/source-facebook-pages:0.2.4 | beta | [docs](https://docs.airbyte.com/integrations/sources/facebook-pages) | [connectors/source/facebook-pages](https://github.com/airbytehq/airbyte/issues?q=is:open+is:issue+label:connectors/source/facebook-pages) | [source-facebook-pages](https://github.com/airbytehq/airbyte/tree/master/airbyte-integrations/connectors/source-facebook-pages) | <small>`010eb12f-837b-4685-892d-0a39f76a98f5`</small> |
 | **Fastbill** | <img alt="Fastbill icon" src="https://raw.githubusercontent.com/airbytehq/airbyte /master/airbyte-config-oss/init-oss/src/main/resources/icons/fastbill.svg" height="30" height="30"/> | Source | airbyte/source-fastbill:0.1.0 | alpha | [docs](https://docs.airbyte.com/integrations/sources/fastbill) | [connectors/source/fastbill](https://github.com/airbytehq/airbyte/issues?q=is:open+is:issue+label:connectors/source/fastbill) | [source-fastbill](https://github.com/airbytehq/airbyte/tree/master/airbyte-integrations/connectors/source-fastbill) | <small>`eb3e9c1c-0467-4eb7-a172-5265e04ccd0a`</small> |
 | **Fauna** | <img alt="Fauna icon" src="https://raw.githubusercontent.com/airbytehq/airbyte /master/airbyte-config-oss/init-oss/src/main/resources/icons/fauna.svg" height="30" height="30"/> | Source | airbyte/source-fauna:0.1.1 | alpha | [docs](https://docs.airbyte.com/integrations/sources/fauna) | [connectors/source/fauna](https://github.com/airbytehq/airbyte/issues?q=is:open+is:issue+label:connectors/source/fauna) | [source-fauna](https://github.com/airbytehq/airbyte/tree/master/airbyte-integrations/connectors/source-fauna) | <small>`3825db3e-c94b-42ac-bd53-b5a9507ace2b`</small> |
-| **File (CSV, JSON, Excel, Feather, Parquet)** | <img alt="File (CSV, JSON, Excel, Feather, Parquet) icon" src="https://raw.githubusercontent.com/airbytehq/airbyte /master/airbyte-config-oss/init-oss/src/main/resources/icons/file.svg" height="30" height="30"/> | Source | airbyte/source-file:0.2.38 | generally_available | [docs](https://docs.airbyte.com/integrations/sources/file) | [connectors/source/file](https://github.com/airbytehq/airbyte/issues?q=is:open+is:issue+label:connectors/source/file) | [source-file](https://github.com/airbytehq/airbyte/tree/master/airbyte-integrations/connectors/source-file) | <small>`778daa7c-feaf-4db6-96f3-70fd645acc77`</small> |
+| **File (CSV, JSON, Excel, Feather, Parquet)** | <img alt="File (CSV, JSON, Excel, Feather, Parquet) icon" src="https://raw.githubusercontent.com/airbytehq/airbyte /master/airbyte-config-oss/init-oss/src/main/resources/icons/file.svg" height="30" height="30"/> | Source | airbyte/source-file:0.3.0 | generally_available | [docs](https://docs.airbyte.com/integrations/sources/file) | [connectors/source/file](https://github.com/airbytehq/airbyte/issues?q=is:open+is:issue+label:connectors/source/file) | [source-file](https://github.com/airbytehq/airbyte/tree/master/airbyte-integrations/connectors/source-file) | <small>`778daa7c-feaf-4db6-96f3-70fd645acc77`</small> |
 | **Firebase Realtime Database** | x | Source | airbyte/source-firebase-realtime-database:0.1.0 | alpha | [docs](https://docs.airbyte.io/integrations/sources/firebase-realtime-database) | [connectors/source/firebase-realtime-database](https://github.com/airbytehq/airbyte/issues?q=is:open+is:issue+label:connectors/source/firebase-realtime-database) | [source-firebase-realtime-database](https://github.com/airbytehq/airbyte/tree/master/airbyte-integrations/connectors/source-firebase-realtime-database) | <small>`acb5f973-a565-441e-992f-4946f3e65662`</small> |
 | **Firebolt** | <img alt="Firebolt icon" src="https://raw.githubusercontent.com/airbytehq/airbyte /master/airbyte-config-oss/init-oss/src/main/resources/icons/firebolt.svg" height="30" height="30"/> | Source | airbyte/source-firebolt:0.2.0 | alpha | [docs](https://docs.airbyte.com/integrations/sources/firebolt) | [connectors/source/firebolt](https://github.com/airbytehq/airbyte/issues?q=is:open+is:issue+label:connectors/source/firebolt) | [source-firebolt](https://github.com/airbytehq/airbyte/tree/master/airbyte-integrations/connectors/source-firebolt) | <small>`6f2ac653-8623-43c4-8950-19218c7caf3d`</small> |
 | **Flexport** | x | Source | airbyte/source-flexport:0.1.0 | alpha | [docs](https://docs.airbyte.com/integrations/sources/flexport) | [connectors/source/flexport](https://github.com/airbytehq/airbyte/issues?q=is:open+is:issue+label:connectors/source/flexport) | [source-flexport](https://github.com/airbytehq/airbyte/tree/master/airbyte-integrations/connectors/source-flexport) | <small>`f95337f1-2ad1-4baf-922f-2ca9152de630`</small> |

docs/integrations/sources/file.md

@@ -79,12 +79,13 @@ For example, if the format `CSV` is selected, then options from the [read_csv](h
 
 - It is therefore possible to customize the `delimiter` (or `sep`) to in case of tab separated files.
 - Header line can be ignored with `header=0` and customized with `names`
+- Parse dates for in specified columns 
 - etc
 
 We would therefore provide in the `reader_options` the following json:
 
 ```
-{ "sep" : "\t", "header" : 0, "names": ["column1", "column2"]}
+{ "sep" : "\t", "header" : 0, "names": ["column1", "column2"], "parse_dates": ["column2"]}
 ```
 
 In case you select `JSON` format, then options from the [read_json](https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html#io-json-reader) reader are available.
@@ -190,17 +191,18 @@ In order to read large files from a remote location, this connector uses the [sm
 
 | Version | Date       | Pull Request                                             | Subject                                                                                                 |
 |:--------|:-----------|:---------------------------------------------------------|:--------------------------------------------------------------------------------------------------------|
+| 0.3.0   | 2023-04-24 | [25445](https://github.com/airbytehq/airbyte/pull/25445) | Add datatime format parsing support for csv files                                                       |
 | 0.2.38  | 2023-04-12 | [23759](https://github.com/airbytehq/airbyte/pull/23759) | Fix column data types for numerical values                                                              |
 | 0.2.37  | 2023-04-06 | [24525](https://github.com/airbytehq/airbyte/pull/24525) | Fix examples in spec                                                                                    |
 | 0.2.36  | 2023-03-27 | [24588](https://github.com/airbytehq/airbyte/pull/24588) | Remove traceback from user messages.                                                                    |
 | 0.2.35  | 2023-03-03 | [24278](https://github.com/airbytehq/airbyte/pull/24278) | Read only file header when checking connectivity; read only a single chunk when discovering the schema. |
-| 0.2.34  | 2023-03-03 | [23723](https://github.com/airbytehq/airbyte/pull/23723) | Update description in spec, make user-friendly error messages and docs.                            |
+| 0.2.34  | 2023-03-03 | [23723](https://github.com/airbytehq/airbyte/pull/23723) | Update description in spec, make user-friendly error messages and docs.                                 |
 | 0.2.33  | 2023-01-04 | [21012](https://github.com/airbytehq/airbyte/pull/21012) | Fix special characters bug                                                                              |
 | 0.2.32  | 2022-12-21 | [20740](https://github.com/airbytehq/airbyte/pull/20740) | Source File: increase SSH timeout to 60s                                                                |
 | 0.2.31  | 2022-11-17 | [19567](https://github.com/airbytehq/airbyte/pull/19567) | Source File: bump 0.2.31                                                                                |
 | 0.2.30  | 2022-11-10 | [19222](https://github.com/airbytehq/airbyte/pull/19222) | Use AirbyteConnectionStatus for "check" command                                                         |
 | 0.2.29  | 2022-11-08 | [18587](https://github.com/airbytehq/airbyte/pull/18587) | Fix pandas read_csv header none issue.                                                                  |
-| 0.2.28  | 2022-10-27 | [18428](https://github.com/airbytehq/airbyte/pull/18428) | Added retry logic for `Connection reset error - 104`                                                    |
+| 0.2.28  | 2022-10-27 | [18428](https://github.com/airbytehq/airbyte/pull/18428) | Add retry logic for `Connection reset error - 104`                                                      |
 | 0.2.27  | 2022-10-26 | [18481](https://github.com/airbytehq/airbyte/pull/18481) | Fix check for wrong format                                                                              |
 | 0.2.26  | 2022-10-18 | [18116](https://github.com/airbytehq/airbyte/pull/18116) | Transform Dropbox shared link                                                                           |
 | 0.2.25  | 2022-10-14 | [17994](https://github.com/airbytehq/airbyte/pull/17994) | Handle `UnicodeDecodeError` during discover step.                                                       |
@@ -212,7 +214,7 @@ In order to read large files from a remote location, this connector uses the [sm
 | 0.2.19  | 2022-08-19 | [15768](https://github.com/airbytehq/airbyte/pull/15768) | Convert 'nan' to 'null'                                                                                 |
 | 0.2.18  | 2022-08-16 | [15698](https://github.com/airbytehq/airbyte/pull/15698) | Cache binary stream to file for discover                                                                |
 | 0.2.17  | 2022-08-11 | [15501](https://github.com/airbytehq/airbyte/pull/15501) | Cache binary stream to file                                                                             |
-| 0.2.16  | 2022-08-10 | [15293](https://github.com/airbytehq/airbyte/pull/15293) | added support for encoding reader option                                                                |
+| 0.2.16  | 2022-08-10 | [15293](https://github.com/airbytehq/airbyte/pull/15293) | Add support for encoding reader option                                                                  |
 | 0.2.15  | 2022-08-05 | [15269](https://github.com/airbytehq/airbyte/pull/15269) | Bump `smart-open` version to 6.0.0                                                                      |
 | 0.2.12  | 2022-07-12 | [14535](https://github.com/airbytehq/airbyte/pull/14535) | Fix invalid schema generation for JSON files                                                            |
 | 0.2.11  | 2022-07-12 | [9974](https://github.com/airbytehq/airbyte/pull/14588)  | Add support to YAML format                                                                              |