🎉 BigQuery destination mlp (#11238)

* fix bug with anyOf and allOf json blocks * updated spec and documentation * rollback last changes * updated spec * updated spec * updated bigquery permissions in doc * updated spec * updated spec * updated spec * updated tests * fixed remarks * updated tests * updated tests * added new bigquery version * updated spec * updated version * updated definitions
airbytehq · Mar 23, 2022 · 8771ba9 · 8771ba9
1 parent 656ccd5
commit 8771ba9
Show file tree

Hide file tree

Showing 5 changed files with 153 additions and 85 deletions.
diff --git a/airbyte-config/init/src/main/resources/seed/destination_definitions.yaml b/airbyte-config/init/src/main/resources/seed/destination_definitions.yaml
@@ -19,7 +19,7 @@
 - name: BigQuery
   destinationDefinitionId: 22f6c74f-5699-40ff-833c-4a879ea40133
   dockerRepository: airbyte/destination-bigquery
-  dockerImageTag: 0.6.12
+  dockerImageTag: 1.0.0
   documentationUrl: https://docs.airbyte.io/integrations/destinations/bigquery
   icon: bigquery.svg
   resourceRequirements:

diff --git a/airbyte-config/init/src/main/resources/seed/destination_specs.yaml b/airbyte-config/init/src/main/resources/seed/destination_specs.yaml
@@ -188,7 +188,7 @@
     supportsDBT: false
     supported_destination_sync_modes:
     - "append"
-- dockerImage: "airbyte/destination-bigquery:0.6.12"
+- dockerImage: "airbyte/destination-bigquery:1.0.0"
   spec:
     documentationUrl: "https://docs.airbyte.io/integrations/destinations/bigquery"
     connectionSpecification:
@@ -201,14 +201,13 @@
       additionalProperties: true
       properties:
         big_query_client_buffer_size_mb:
-          title: "Google BigQuery client chunk size"
-          description: "Google BigQuery client's chunk(buffer) size (MIN=1, MAX =\
+          title: "Google BigQuery Client Chunk Size (Optional)"
+          description: "Google BigQuery client's chunk (buffer) size (MIN=1, MAX =\
             \ 15) for each table. The size that will be written by a single RPC. Written\
             \ data will be buffered and only flushed upon reaching this size or closing\
-            \ the channel. The default 15MiB value is used if not set explicitly.\
-            \ It's recommended to decrease value for big data sets migration for less\
-            \ HEAP memory consumption and avoiding crashes. For more details refer\
-            \ to https://googleapis.dev/python/bigquery/latest/generated/google.cloud.bigquery.client.Client.html"
+            \ the channel. The default 15MB value is used if not set explicitly. Read\
+            \ more <a href=\"https://googleapis.dev/python/bigquery/latest/generated/google.cloud.bigquery.client.Client.html\"\
+            >here</a>."
           type: "integer"
           minimum: 1
           maximum: 15
@@ -218,18 +217,22 @@
         project_id:
           type: "string"
           description: "The GCP project ID for the project containing the target BigQuery\
-            \ dataset."
+            \ dataset. Read more <a href=\"https://cloud.google.com/iam/docs/creating-managing-service-accounts#creating\"\
+            >here</a>."
           title: "Project ID"
         dataset_id:
           type: "string"
-          description: "Default BigQuery Dataset ID tables are replicated to if the\
-            \ source does not specify a namespace."
+          description: "The default BigQuery Dataset ID that tables are replicated\
+            \ to if the source does not specify a namespace. Read more <a href=\"\
+            https://cloud.google.com/bigquery/docs/datasets#create-dataset\">here</a>."
           title: "Default Dataset ID"
         dataset_location:
           type: "string"
           description: "The location of the dataset. Warning: Changes made after creation\
-            \ will not be applied."
-          title: "Dataset Location"
+            \ will not be applied. The default \"US\" value is used if not set explicitly.\
+            \ Read more <a href=\"https://cloud.google.com/bigquery/docs/locations\"\
+            >here</a>."
+          title: "Dataset Location (Optional)"
           default: "US"
           enum:
           - "US"
@@ -266,20 +269,22 @@
         credentials_json:
           type: "string"
           description: "The contents of the JSON service account key. Check out the\
-            \ <a href=\"https://docs.airbyte.io/integrations/destinations/bigquery\"\
+            \ <a href=\"https://docs.airbyte.com/integrations/destinations/bigquery#service-account-key\"\
             >docs</a> if you need help generating this key. Default credentials will\
             \ be used if this field is left empty."
-          title: "Credentials JSON"
+          title: "Credentials JSON (Optional)"
           airbyte_secret: true
         transformation_priority:
           type: "string"
           description: "Interactive run type means that the query is executed as soon\
             \ as possible, and these queries count towards concurrent rate limit and\
-            \ daily limit. Batch queries are queued and started as soon as idle resources\
+            \ daily limit. Read more about interactive run type <a href=\"https://cloud.google.com/bigquery/docs/running-queries#queries\"\
+            >here</a>. Batch queries are queued and started as soon as idle resources\
             \ are available in the BigQuery shared resource pool, which usually occurs\
             \ within a few minutes. Batch queries don’t count towards your concurrent\
-            \ rate limit."
-          title: "Transformation Query Run Type"
+            \ rate limit. Read more about batch queries <a href=\"https://cloud.google.com/bigquery/docs/running-queries#batch\"\
+            >here</a>. The default \"interactive\" value is used if not set explicitly."
+          title: "Transformation Query Run Type (Optional)"
           default: "interactive"
           enum:
           - "interactive"
@@ -288,11 +293,17 @@
           type: "object"
           title: "Loading Method"
           description: "Loading method used to send select the way data will be uploaded\
-            \ to BigQuery."
+            \ to BigQuery. <br><b>Standard Inserts</b> - Direct uploading using SQL\
+            \ INSERT statements. This method is extremely inefficient and provided\
+            \ only for quick testing. In almost all cases, you should use staging.\
+            \ <br><b>GCS Staging</b> - Writes large batches of records to a file,\
+            \ uploads the file to GCS, then uses <b>COPY INTO table</b> to upload\
+            \ the file. Recommended for most workloads for better speed and scalability.\
+            \ Read more about GCS Staging <a href=\"https://docs.airbyte.com/integrations/destinations/bigquery#gcs-staging\"\
+            >here</a>."
           oneOf:
           - title: "Standard Inserts"
             additionalProperties: false
-            description: "Direct uploading using streams."
             required:
             - "method"
             properties:
@@ -301,9 +312,6 @@
                 const: "Standard"
           - title: "GCS Staging"
             additionalProperties: false
-            description: "Writes large batches of records to a file, uploads the file\
-              \ to GCS, then uses <pre>COPY INTO table</pre> to upload the file. Recommended\
-              \ for large production workloads for better speed and scalability."
             required:
             - "method"
             - "gcs_bucket_name"
@@ -316,16 +324,18 @@
               gcs_bucket_name:
                 title: "GCS Bucket Name"
                 type: "string"
-                description: "The name of the GCS bucket."
+                description: "The name of the GCS bucket. Read more <a href=\"https://cloud.google.com/storage/docs/naming-buckets\"\
+                  >here</a>."
                 examples:
                 - "airbyte_sync"
               gcs_bucket_path:
+                title: "GCS Bucket Path"
                 description: "Directory under the GCS bucket where data will be written."
                 type: "string"
                 examples:
                 - "data_sync/test"
               part_size_mb:
-                title: "Block Size (MB) for GCS multipart upload"
+                title: "Block Size (MB) for GCS Multipart Upload (Optional)"
                 description: "This is the size of a \"Part\" being buffered in memory.\
                   \ It limits the memory usage when writing. Larger values will allow\
                   \ to upload a bigger files and improve the speed, but consumes more\
@@ -340,14 +350,19 @@
                 type: "string"
                 description: "This upload method is supposed to temporary store records\
                   \ in GCS bucket. What do you want to do with data in GCS bucket\
-                  \ when migration has finished?"
-                title: "GCS tmp files afterward processing"
+                  \ when migration has finished? The default \"Delete all tmp files\
+                  \ from GCS\" value is used if not set explicitly."
+                title: "GCS Tmp Files Afterward Processing (Optional)"
                 default: "Delete all tmp files from GCS"
                 enum:
                 - "Delete all tmp files from GCS"
                 - "Keep all tmp files in GCS"
               credential:
                 title: "Credential"
+                description: "An HMAC key is a type of credential and can be associated\
+                  \ with a service account or a user account in Cloud Storage. Read\
+                  \ more <a href=\"https://cloud.google.com/storage/docs/authentication/hmackeys\"\
+                  >here</a>."
                 type: "object"
                 oneOf:
                 - title: "HMAC key"

diff --git a/airbyte-integrations/connectors/destination-bigquery/Dockerfile b/airbyte-integrations/connectors/destination-bigquery/Dockerfile
@@ -17,5 +17,5 @@ ENV ENABLE_SENTRY true
 
 COPY --from=build /airbyte /airbyte
 
-LABEL io.airbyte.version=0.6.12
+LABEL io.airbyte.version=1.0.0
 LABEL io.airbyte.name=airbyte/destination-bigquery
diff --git a/airbyte-integrations/connectors/destination-bigquery/src/main/resources/spec.json b/airbyte-integrations/connectors/destination-bigquery/src/main/resources/spec.json
@@ -12,8 +12,8 @@
     "additionalProperties": true,
     "properties": {
       "big_query_client_buffer_size_mb": {
-        "title": "Google BigQuery client chunk size",
-        "description": "Google BigQuery client's chunk(buffer) size (MIN=1, MAX = 15) for each table. The size that will be written by a single RPC. Written data will be buffered and only flushed upon reaching this size or closing the channel. The default 15MiB value is used if not set explicitly. It's recommended to decrease value for big data sets migration for less HEAP memory consumption and avoiding crashes. For more details refer to https://googleapis.dev/python/bigquery/latest/generated/google.cloud.bigquery.client.Client.html",
+        "title": "Google BigQuery Client Chunk Size (Optional)",
+        "description": "Google BigQuery client's chunk (buffer) size (MIN=1, MAX = 15) for each table. The size that will be written by a single RPC. Written data will be buffered and only flushed upon reaching this size or closing the channel. The default 15MB value is used if not set explicitly. Read more <a href=\"https://googleapis.dev/python/bigquery/latest/generated/google.cloud.bigquery.client.Client.html\">here</a>.",
         "type": "integer",
         "minimum": 1,
         "maximum": 15,
@@ -22,18 +22,18 @@
       },
       "project_id": {
         "type": "string",
-        "description": "The GCP project ID for the project containing the target BigQuery dataset.",
+        "description": "The GCP project ID for the project containing the target BigQuery dataset. Read more <a href=\"https://cloud.google.com/iam/docs/creating-managing-service-accounts#creating\">here</a>.",
         "title": "Project ID"
       },
       "dataset_id": {
         "type": "string",
-        "description": "Default BigQuery Dataset ID tables are replicated to if the source does not specify a namespace.",
+        "description": "The default BigQuery Dataset ID that tables are replicated to if the source does not specify a namespace. Read more <a href=\"https://cloud.google.com/bigquery/docs/datasets#create-dataset\">here</a>.",
         "title": "Default Dataset ID"
       },
       "dataset_location": {
         "type": "string",
-        "description": "The location of the dataset. Warning: Changes made after creation will not be applied.",
-        "title": "Dataset Location",
+        "description": "The location of the dataset. Warning: Changes made after creation will not be applied. The default \"US\" value is used if not set explicitly. Read more <a href=\"https://cloud.google.com/bigquery/docs/locations\">here</a>.",
+        "title": "Dataset Location (Optional)",
         "default": "US",
         "enum": [
           "US",
@@ -71,26 +71,25 @@
       },
       "credentials_json": {
         "type": "string",
-        "description": "The contents of the JSON service account key. Check out the <a href=\"https://docs.airbyte.io/integrations/destinations/bigquery\">docs</a> if you need help generating this key. Default credentials will be used if this field is left empty.",
-        "title": "Credentials JSON",
+        "description": "The contents of the JSON service account key. Check out the <a href=\"https://docs.airbyte.com/integrations/destinations/bigquery#service-account-key\">docs</a> if you need help generating this key. Default credentials will be used if this field is left empty.",
+        "title": "Credentials JSON (Optional)",
         "airbyte_secret": true
       },
       "transformation_priority": {
         "type": "string",
-        "description": "Interactive run type means that the query is executed as soon as possible, and these queries count towards concurrent rate limit and daily limit. Batch queries are queued and started as soon as idle resources are available in the BigQuery shared resource pool, which usually occurs within a few minutes. Batch queries don’t count towards your concurrent rate limit.",
-        "title": "Transformation Query Run Type",
+        "description": "Interactive run type means that the query is executed as soon as possible, and these queries count towards concurrent rate limit and daily limit. Read more about interactive run type <a href=\"https://cloud.google.com/bigquery/docs/running-queries#queries\">here</a>. Batch queries are queued and started as soon as idle resources are available in the BigQuery shared resource pool, which usually occurs within a few minutes. Batch queries don’t count towards your concurrent rate limit. Read more about batch queries <a href=\"https://cloud.google.com/bigquery/docs/running-queries#batch\">here</a>. The default \"interactive\" value is used if not set explicitly.",
+        "title": "Transformation Query Run Type (Optional)",
         "default": "interactive",
         "enum": ["interactive", "batch"]
       },
       "loading_method": {
         "type": "object",
         "title": "Loading Method",
-        "description": "Loading method used to send select the way data will be uploaded to BigQuery.",
+        "description": "Loading method used to send select the way data will be uploaded to BigQuery. <br><b>Standard Inserts</b> - Direct uploading using SQL INSERT statements. This method is extremely inefficient and provided only for quick testing. In almost all cases, you should use staging. <br><b>GCS Staging</b> - Writes large batches of records to a file, uploads the file to GCS, then uses <b>COPY INTO table</b> to upload the file. Recommended for most workloads for better speed and scalability. Read more about GCS Staging <a href=\"https://docs.airbyte.com/integrations/destinations/bigquery#gcs-staging\">here</a>.",
         "oneOf": [
           {
             "title": "Standard Inserts",
             "additionalProperties": false,
-            "description": "Direct uploading using streams.",
             "required": ["method"],
             "properties": {
               "method": {
@@ -102,7 +101,6 @@
           {
             "title": "GCS Staging",
             "additionalProperties": false,
-            "description": "Writes large batches of records to a file, uploads the file to GCS, then uses <pre>COPY INTO table</pre> to upload the file. Recommended for large production workloads for better speed and scalability.",
             "required": [
               "method",
               "gcs_bucket_name",
@@ -117,16 +115,17 @@
               "gcs_bucket_name": {
                 "title": "GCS Bucket Name",
                 "type": "string",
-                "description": "The name of the GCS bucket.",
+                "description": "The name of the GCS bucket. Read more <a href=\"https://cloud.google.com/storage/docs/naming-buckets\">here</a>.",
                 "examples": ["airbyte_sync"]
               },
               "gcs_bucket_path": {
+                "title": "GCS Bucket Path",
                 "description": "Directory under the GCS bucket where data will be written.",
                 "type": "string",
                 "examples": ["data_sync/test"]
               },
               "part_size_mb": {
-                "title": "Block Size (MB) for GCS multipart upload",
+                "title": "Block Size (MB) for GCS Multipart Upload (Optional)",
                 "description": "This is the size of a \"Part\" being buffered in memory. It limits the memory usage when writing. Larger values will allow to upload a bigger files and improve the speed, but consumes more memory. Allowed values: min=5MB, max=525MB Default: 5MB.",
                 "type": "integer",
                 "default": 5,
@@ -136,8 +135,8 @@
               },
               "keep_files_in_gcs-bucket": {
                 "type": "string",
-                "description": "This upload method is supposed to temporary store records in GCS bucket. What do you want to do with data in GCS bucket when migration has finished?",
-                "title": "GCS tmp files afterward processing",
+                "description": "This upload method is supposed to temporary store records in GCS bucket. What do you want to do with data in GCS bucket when migration has finished? The default \"Delete all tmp files from GCS\" value is used if not set explicitly.",
+                "title": "GCS Tmp Files Afterward Processing (Optional)",
                 "default": "Delete all tmp files from GCS",
                 "enum": [
                   "Delete all tmp files from GCS",
@@ -146,6 +145,7 @@
               },
               "credential": {
                 "title": "Credential",
+                "description": "An HMAC key is a type of credential and can be associated with a service account or a user account in Cloud Storage. Read more <a href=\"https://cloud.google.com/storage/docs/authentication/hmackeys\">here</a>.",
                 "type": "object",
                 "oneOf": [
                   {