✨feat(source google drive): make file-trasfer (#51585)

Implement file-transfer feature for source-google-drive

airbyte-integrations/connectors/source-google-drive/acceptance-test-config.yml

@@ -41,4 +41,7 @@ acceptance_tests:
   spec:
     tests:
       - spec_path: integration_tests/spec.json
+        # changed from "Document File Type Format (Experimental)" to "Unstructured Document Format".
+        backward_compatibility_tests_config:
+          disable_for_version: "0.1.0-rc.1"
 connector_image: airbyte/source-google-drive:dev

airbyte-integrations/connectors/source-google-drive/integration_tests/spec.json

@@ -272,7 +272,7 @@
                   "required": ["filetype"]
                 },
                 {
-                  "title": "Document File Type Format (Experimental)",
+                  "title": "Unstructured Document Format",
                   "type": "object",
                   "properties": {
                     "filetype": {
@@ -325,6 +325,19 @@
                   },
                   "description": "Extract text from document formats (.pdf, .docx, .md, .pptx) and emit as one record per file.",
                   "required": ["filetype"]
+                },
+                {
+                  "title": "Excel Format",
+                  "type": "object",
+                  "properties": {
+                    "filetype": {
+                      "title": "Filetype",
+                      "default": "excel",
+                      "const": "excel",
+                      "type": "string"
+                    }
+                  },
+                  "required": ["filetype"]
                 }
               ]
             },
@@ -333,11 +346,63 @@
               "description": "When enabled, syncs will not validate or structure records against the stream's schema.",
               "default": false,
               "type": "boolean"
+            },
+            "recent_n_files_to_read_for_schema_discovery": {
+              "title": "Files To Read For Schema Discover",
+              "description": "The number of resent files which will be used to discover the schema for this stream.",
+              "exclusiveMinimum": 0,
+              "type": "integer"
             }
           },
           "required": ["name", "format"]
         }
       },
+      "delivery_method": {
+        "title": "Delivery Method",
+        "default": "use_records_transfer",
+        "type": "object",
+        "order": 1,
+        "display_type": "radio",
+        "group": "advanced",
+        "oneOf": [
+          {
+            "title": "Replicate Records",
+            "type": "object",
+            "properties": {
+              "delivery_type": {
+                "title": "Delivery Type",
+                "default": "use_records_transfer",
+                "const": "use_records_transfer",
+                "enum": ["use_records_transfer"],
+                "type": "string"
+              }
+            },
+            "description": "Recommended - Extract and load structured records into your destination of choice. This is the classic method of moving data in Airbyte. It allows for blocking and hashing individual fields or files from a structured schema. Data can be flattened, typed and deduped depending on the destination.",
+            "required": ["delivery_type"]
+          },
+          {
+            "title": "Copy Raw Files",
+            "type": "object",
+            "properties": {
+              "delivery_type": {
+                "title": "Delivery Type",
+                "default": "use_file_transfer",
+                "const": "use_file_transfer",
+                "enum": ["use_file_transfer"],
+                "type": "string"
+              },
+              "preserve_directory_structure": {
+                "title": "Preserve Sub-Directories in File Paths",
+                "description": "If enabled, sends subdirectory folder structure along with source file names to the destination. Otherwise, files will be synced by their names only. This option is ignored when file-based replication is not enabled.",
+                "default": true,
+                "type": "boolean"
+              }
+            },
+            "description": "Copy raw files without parsing their contents. Bits are copied into the destination exactly as they appeared in the source. Recommended for use with unstructured text data, non-text and compressed files.",
+            "required": ["delivery_type"]
+          }
+        ]
+      },
       "folder_url": {
         "title": "Folder Url",
         "description": "URL for the folder you want to sync. Using individual streams and glob patterns, it's possible to only sync a subset of all files located in the folder.",

airbyte-integrations/connectors/source-google-drive/metadata.yaml

@@ -3,11 +3,11 @@ data:
     hosts:
       - "www.googleapis.com"
   connectorBuildOptions:
-    baseImage: docker.io/airbyte/python-connector-base:1.2.2@sha256:57703de3b4c4204bd68a7b13c9300f8e03c0189bffddaffc796f1da25d2dbea0
+    baseImage: docker.io/airbyte/python-connector-base:3.0.0@sha256:1a0845ff2b30eafa793c6eee4e8f4283c2e52e1bbd44eed6cb9e9abd5d34d844
   connectorSubtype: file
   connectorType: source
   definitionId: 9f8dda77-1048-4368-815b-269bf54ee9b8
-  dockerImageTag: 0.0.12
+  dockerImageTag: 0.1.0-rc.1
   dockerRepository: airbyte/source-google-drive
   githubIssueLabel: source-google-drive
   icon: google-drive.svg
@@ -23,6 +23,9 @@ data:
     oss:
       enabled: true
   releaseStage: alpha
+  releases:
+    rolloutConfiguration:
+      enableProgressiveRollout: true
   documentationUrl: https://docs.airbyte.com/integrations/sources/google-drive
   tags:
     - language:python