Tutorial and documentation for config-based connectors

airbyte-cdk/python/airbyte_cdk/sources/declarative/auth/token.py

@@ -83,7 +83,7 @@ def token(self) -> str:
 @dataclass
 class BasicHttpAuthenticator(AbstractHeaderAuthenticator):
     """
-    Builds auth based off the basic authentication scheme as defined by RFC 7617, which transmits credentials as USER ID/password pairs, encoded using bas64
+    Builds auth based off the basic authentication scheme as defined by RFC 7617, which transmits credentials as USER ID/password pairs, encoded using base64
     https://developer.mozilla.org/en-US/docs/Web/HTTP/Authentication#basic_authentication_scheme
 
     The header is of the form

airbyte-cdk/python/airbyte_cdk/sources/declarative/parsers/class_types_registry.py

@@ -4,6 +4,7 @@
 
 from typing import Mapping, Type
 
+from airbyte_cdk.sources.declarative.auth.oauth import DeclarativeOauth2Authenticator
 from airbyte_cdk.sources.declarative.auth.token import ApiKeyAuthenticator, BasicHttpAuthenticator, BearerAuthenticator
 from airbyte_cdk.sources.declarative.datetime.min_max_datetime import MinMaxDatetime
 from airbyte_cdk.sources.declarative.declarative_stream import DeclarativeStream
@@ -56,6 +57,7 @@
     "ListStreamSlicer": ListStreamSlicer,
     "MinMaxDatetime": MinMaxDatetime,
     "NoPagination": NoPagination,
+    "OAuthAuthenticator": DeclarativeOauth2Authenticator,
     "OffsetIncrement": OffsetIncrement,
     "RecordSelector": RecordSelector,
     "RemoveFields": RemoveFields,

airbyte-cdk/python/airbyte_cdk/sources/declarative/parsers/factory.py

@@ -52,7 +52,7 @@ class DeclarativeComponentFactory:
     If the component definition is a mapping with neither a "class_name" nor a "type" field,
     the factory will do a best-effort attempt at inferring the component type by looking up the parent object's constructor type hints.
     If the type hint is an interface present in `DEFAULT_IMPLEMENTATIONS_REGISTRY`,
-    then the factory will create an object of it's default implementation.
+    then the factory will create an object of its default implementation.
 
     If the component definition is a list, then the factory will iterate over the elements of the list,
     instantiate its subcomponents, and return a list of instantiated objects.

airbyte-cdk/python/airbyte_cdk/sources/declarative/parsers/yaml_parser.py

@@ -15,7 +15,7 @@ class YamlParser(ConnectionDefinitionParser):
     """
     Parses a Yaml string to a ConnectionDefinition
 
-    In addition to standard Yaml parsing, the input_string can contain refererences to values previously defined.
+    In addition to standard Yaml parsing, the input_string can contain references to values previously defined.
     This parser will dereference these values to produce a complete ConnectionDefinition.
 
     References can be defined using a *ref(<arg>) string.

airbyte-cdk/python/unit_tests/sources/declarative/extractors/test_dpath_extractor.py

@@ -20,6 +20,7 @@
     [
         ("test_extract_from_array", ["data"], {"data": [{"id": 1}, {"id": 2}]}, [{"id": 1}, {"id": 2}]),
         ("test_extract_single_record", ["data"], {"data": {"id": 1}}, [{"id": 1}]),
+        ("test_extract_single_record_from_root", [], {"id": 1}, [{"id": 1}]),
         ("test_extract_from_root_array", [], [{"id": 1}, {"id": 2}], [{"id": 1}, {"id": 2}]),
         ("test_nested_field", ["data", "records"], {"data": {"records": [{"id": 1}, {"id": 2}]}}, [{"id": 1}, {"id": 2}]),
         ("test_field_in_config", ["{{ config['field'] }}"], {"record_array": [{"id": 1}, {"id": 2}]}, [{"id": 1}, {"id": 2}]),

docs/connector-development/config-based/authentication.md

@@ -0,0 +1,73 @@
+# Authentication
+
+The `Authenticator` defines how to configure outgoing HTTP requests to authenticate on the API source.
+
+## Authenticators
+
+### ApiKeyAuthenticator
+
+The `ApiKeyAuthenticator` sets an HTTP header on outgoing requests.
+The following definition will set the header "Authorization" with a value "Bearer hello":
+
+```yaml
+authenticator:
+  type: "ApiKeyAuthenticator"
+  header: "Authorization"
+  token: "Bearer hello"
+```
+
+### BearerAuthenticator
+
+The `BearerAuthenticator` is a specialized `ApiKeyAuthenticator` that always sets the header "Authorization" with the value "Bearer {token}".
+The following definition will set the header "Authorization" with a value "Bearer hello"
+
+```yaml
+authenticator:
+  type: "BearerAuthenticator"
+  token: "hello"
+```
+
+More information on bearer authentication can be found [here](https://swagger.io/docs/specification/authentication/bearer-authentication/)
+
+### BasicHttpAuthenticator
+
+The `BasicHttpAuthenticator` set the "Authorization" header with a (USER ID/password) pair, encoded using base64 as per [RFC 7617](https://developer.mozilla.org/en-US/docs/Web/HTTP/Authentication#basic_authentication_scheme).
+The following definition will set the header "Authorization" with a value "Basic {encoded credentials}"
+
+```yaml
+authenticator:
+  type: "BasicHttpAuthenticator"
+  username: "hello"
+  password: "world"
+```
+
+The password is optional. Authenticating with APIs using Basic HTTP and a single API key can be done as:
+
+```yaml
+authenticator:
+  type: "BasicHttpAuthenticator"
+  username: "hello"
+```
+
+### OAuth
+
+OAuth authentication is supported through the `OAuthAuthenticator`, which requires the following parameters:
+
+- token_refresh_endpoint: The endpoint to refresh the access token
+- client_id: The client id
+- client_secret: The client secret
+- refresh_token: The token used to refresh the access token
+- scopes (Optional): The scopes to request. Default: Empty list
+- token_expiry_date (Optional): The access token expiration date formatted as RFC-3339 ("%Y-%m-%dT%H:%M:%S.%f%z")
+- access_token_name (Optional): The field to extract access token from in the response. Default: "access_token".
+- expires_in_name (Optional): The field to extract expires_in from in the response. Default: "expires_in"
+- refresh_request_body (Optional): The request body to send in the refresh request. Default: None
+
+```yaml
+authenticator:
+  type: "OAuthAuthenticator"
+  token_refresh_endpoint: "https://api.searchmetrics.com/v4/token"
+  client_id: "{{ config['api_key'] }}"
+  client_secret: "{{ config['client_secret'] }}"
+  refresh_token: ""
+```

docs/connector-development/config-based/error-handling.md

@@ -0,0 +1,177 @@
+# Error handling
+
+By default, only server errors (HTTP 5XX) and too many requests (HTTP 429) will be retried up to 5 times with exponential backoff.
+Other HTTP errors will result in a failed read.
+
+Other behaviors can be configured through the `Requester`'s `error_handler` field.
+
+## Defining errors
+
+### From status code
+
+Response filters can be used to define how to handle requests resulting in responses with a specific HTTP status code.
+For instance, this example will configure the handler to also retry responses with 404 error:
+
+```yaml
+requester:
+  <...>
+  error_handler:
+    response_filters:
+        - http_codes: [ 404 ]
+          action: RETRY
+```
+
+Response filters can be used to specify HTTP errors to ignore.
+For instance, this example will configure the handler to ignore responses with 404 error:
+
+```yaml
+requester:
+  <...>
+  error_handler:
+    response_filters:
+        - http_codes: [ 404 ]
+          action: IGNORE
+```
+
+### From error message
+
+Errors can also be defined by parsing the error message.
+For instance, this error handler will ignores responses if the error message contains the string "ignorethisresponse"
+
+```yaml
+requester:
+  <...>
+  error_handler:
+    response_filters:
+        - error_message_contain: "ignorethisresponse"
+          action: IGNORE
+```
+
+This can also be done through a more generic string interpolation strategy with the following parameters:
+
+- response: the decoded response
+
+This example ignores errors where the response contains a "code" field:
+
+```yaml
+requester:
+  <...>
+  error_handler:
+    response_filters:
+        - predicate: "{{ 'code' in response }}"
+          action: IGNORE
+```
+
+The error handler can have multiple response filters.
+The following example is configured to ignore 404 errors, and retry 429 errors:
+
+```yaml
+requester:
+  <...>
+  error_handler:
+    response_filters:
+        - http_codes: [ 404 ]
+          action: IGNORE
+          - http_codes: [ 429 ]
+            action: RETRY
+```
+
+## Backoff Strategies
+
+The error handler supports a few backoff strategies, which are described in the following sections.
+
+### Exponential backoff
+
+This is the default backoff strategy. The requester will backoff with an exponential backoff interval
+
+### Constant Backoff
+
+When using the `ConstantBackoffStrategy`, the requester will backoff with a constant interval.
+
+### Wait time defined in header
+
+When using the `WaitTimeFromHeaderBackoffStrategy`, the requester will backoff by an interval specified in the response header.
+In this example, the requester will backoff by the response's "wait_time" header value:
+
+```yaml
+requester:
+  <...>
+  error_handler:
+    <...>
+    backoff_strategies:
+        - type: "WaitTimeFromHeaderBackoffStrategy"
+          header: "wait_time"
+```
+
+Optionally, a regular expression can be configured to extract the wait time from the header value.
+
+```yaml
+requester:
+  <...>
+  error_handler:
+    <...>
+    backoff_strategies:
+        - type: "WaitTimeFromHeaderBackoffStrategy"
+          header: "wait_time"
+          regex: "[-+]?\d+"
+```
+
+### Wait until time defined in header
+
+When using the `WaitUntilTimeFromHeaderBackoffStrategy`, the requester will backoff until the time specified in the response header.
+In this example, the requester will wait until the time specified in the "wait_until" header value:
+
+```yaml
+requester:
+  <...>
+  error_handler:
+    <...>
+    backoff_strategies:
+        - type: "WaitUntilTimeFromHeaderBackoffStrategy"
+          header: "wait_until"
+          regex: "[-+]?\d+"
+          min_wait: 5
+```
+
+The strategy accepts an optional regular expression to extract the time from the header value, and a minimum time to wait.
+
+## Advanced error handling
+
+The error handler can have multiple backoff strategies, allowing it to fallback if a strategy cannot be evaluated.
+For instance, the following defines an error handler that will read the backoff time from a header, and default to a constant backoff if the wait time could not be extracted from the response:
+
+```yaml
+requester:
+  <...>
+  error_handler:
+    <...>
+    backoff_strategies:
+        - type: "WaitTimeFromHeaderBackoffStrategy"
+          header: "wait_time"
+          - type: "ConstantBackoffStrategy"
+            backoff_time_in_seconds: 5
+
+```
+
+The `requester` can be configured to use a `CompositeErrorHandler`, which sequentially iterates over a list of error handlers, enabling different retry mechanisms for different types of errors.
+
+In this example, a constant backoff of 5 seconds, will be applied if the response contains a "code" field, and an exponential backoff will be applied if the error code is 403:
+
+```yaml
+requester:
+  <...>
+  error_handler:
+    type: "CompositeErrorHandler"
+    error_handlers:
+      - response_filters:
+          - predicate: "{{ 'code' in response }}"
+            action: RETRY
+        backoff_strategies:
+          - type: "ConstantBackoffStrategy"
+            backoff_time_in_seconds: 5
+      - response_filters:
+          - http_codes: [ 403 ]
+            action: RETRY
+        backoff_strategies:
+          - type: "ExponentialBackoffStrategy"
+```

docs/connector-development/config-based/index.md

@@ -0,0 +1,26 @@
+# Index
+
+## From scratch
+
+- [Overview](overview.md)
+- [Yaml structure](overview.md)
+- [Reference docs](https://airbyte-cdk.readthedocs.io/en/latest/api/airbyte_cdk.sources.declarative.html)
+
+## Concepts
+
+- [Authentication](authentication.md)
+- [Error handling](error-handling.md)
+- [Pagination](pagination.md)
+- [Record selection](record-selector.md)
+- [Request options](request-options.md)
+- [Stream slicers](stream-slicers.md)
+
+## Tutorial
+
+0. [Getting started](tutorial/0-getting-started.md)
+1. [Creating a source](tutorial/1-create-source.md)
+2. [Installing dependencies](tutorial/2-install-dependencies.md)
+3. [Connecting to the API](tutorial/3-connecting-to-the-API-source.md)
+4. [Reading data](tutorial/4-reading-data.md)
+5. [Incremental reads](tutorial/5-incremental-reads.md)
+6. [Testing](tutorial/6-testing.md)