Merge remote-tracking branch 'origin/main' into baz/cdk/test-read-ref…

…actor

airbyte_cdk/sources/declarative/declarative_component_schema.yaml

@@ -40,6 +40,8 @@ properties:
     "$ref": "#/definitions/Spec"
   concurrency_level:
     "$ref": "#/definitions/ConcurrencyLevel"
+  api_budget:
+    "$ref": "#/definitions/HTTPAPIBudget"
   metadata:
     type: object
     description: For internal Airbyte use only - DO NOT modify manually. Used by consumers of declarative manifests for storing related metadata.
@@ -794,7 +796,7 @@ definitions:
         description: This option is used to adjust the upper and lower boundaries of each datetime window to beginning and end of the provided target period (day, week, month)
         type: object
         required:
-        - target
+          - target
         properties:
           target:
             title: Target
@@ -1365,6 +1367,170 @@ definitions:
       $parameters:
         type: object
         additional_properties: true
+  HTTPAPIBudget:
+    title: HTTP API Budget
+    description: >
+      Defines how many requests can be made to the API in a given time frame. `HTTPAPIBudget` extracts the remaining
+      call count and the reset time from HTTP response headers using the header names provided by
+      `ratelimit_remaining_header` and `ratelimit_reset_header`. Only requests using `HttpRequester`
+      are rate-limited; custom components that bypass `HttpRequester` are not covered by this budget.
+    type: object
+    required:
+      - type
+      - policies
+    properties:
+      type:
+        type: string
+        enum: [HTTPAPIBudget]
+      policies:
+        title: Policies
+        description: List of call rate policies that define how many calls are allowed.
+        type: array
+        items:
+          anyOf:
+            - "$ref": "#/definitions/FixedWindowCallRatePolicy"
+            - "$ref": "#/definitions/MovingWindowCallRatePolicy"
+            - "$ref": "#/definitions/UnlimitedCallRatePolicy"
+      ratelimit_reset_header:
+        title: Rate Limit Reset Header
+        description: The HTTP response header name that indicates when the rate limit resets.
+        type: string
+        default: "ratelimit-reset"
+      ratelimit_remaining_header:
+        title: Rate Limit Remaining Header
+        description: The HTTP response header name that indicates the number of remaining allowed calls.
+        type: string
+        default: "ratelimit-remaining"
+      status_codes_for_ratelimit_hit:
+        title: Status Codes for Rate Limit Hit
+        description: List of HTTP status codes that indicate a rate limit has been hit.
+        type: array
+        items:
+          type: integer
+        default: [429]
+    additionalProperties: true
+  FixedWindowCallRatePolicy:
+    title: Fixed Window Call Rate Policy
+    description: A policy that allows a fixed number of calls within a specific time window.
+    type: object
+    required:
+      - type
+      - period
+      - call_limit
+      - matchers
+    properties:
+      type:
+        type: string
+        enum: [FixedWindowCallRatePolicy]
+      period:
+        title: Period
+        description: The time interval for the rate limit window.
+        type: string
+      call_limit:
+        title: Call Limit
+        description: The maximum number of calls allowed within the period.
+        type: integer
+      matchers:
+        title: Matchers
+        description: List of matchers that define which requests this policy applies to.
+        type: array
+        items:
+          "$ref": "#/definitions/HttpRequestRegexMatcher"
+    additionalProperties: true
+  MovingWindowCallRatePolicy:
+    title: Moving Window Call Rate Policy
+    description: A policy that allows a fixed number of calls within a moving time window.
+    type: object
+    required:
+      - type
+      - rates
+      - matchers
+    properties:
+      type:
+        type: string
+        enum: [MovingWindowCallRatePolicy]
+      rates:
+        title: Rates
+        description: List of rates that define the call limits for different time intervals.
+        type: array
+        items:
+          "$ref": "#/definitions/Rate"
+      matchers:
+        title: Matchers
+        description: List of matchers that define which requests this policy applies to.
+        type: array
+        items:
+          "$ref": "#/definitions/HttpRequestRegexMatcher"
+    additionalProperties: true
+  UnlimitedCallRatePolicy:
+    title: Unlimited Call Rate Policy
+    description: A policy that allows unlimited calls for specific requests.
+    type: object
+    required:
+      - type
+      - matchers
+    properties:
+      type:
+        type: string
+        enum: [UnlimitedCallRatePolicy]
+      matchers:
+        title: Matchers
+        description: List of matchers that define which requests this policy applies to.
+        type: array
+        items:
+          "$ref": "#/definitions/HttpRequestRegexMatcher"
+    additionalProperties: true
+  Rate:
+    title: Rate
+    description: Defines a rate limit with a specific number of calls allowed within a time interval.
+    type: object
+    required:
+      - limit
+      - interval
+    properties:
+      limit:
+        title: Limit
+        description: The maximum number of calls allowed within the interval.
+        type: integer
+      interval:
+        title: Interval
+        description: The time interval for the rate limit.
+        type: string
+        examples:
+          - "PT1H"
+          - "P1D"
+    additionalProperties: true
+  HttpRequestRegexMatcher:
+    title: HTTP Request Matcher
+    description: >
+      Matches HTTP requests based on method, base URL, URL path pattern, query parameters, and headers.
+      Use `url_base` to specify the scheme and host (without trailing slash) and
+      `url_path_pattern` to apply a regex to the request path.
+    type: object
+    properties:
+      method:
+        title: Method
+        description: The HTTP method to match (e.g., GET, POST).
+        type: string
+      url_base:
+        title: URL Base
+        description: The base URL (scheme and host, e.g. "https://api.example.com") to match.
+        type: string
+      url_path_pattern:
+        title: URL Path Pattern
+        description: A regular expression pattern to match the URL path.
+        type: string
+      params:
+        title: Parameters
+        description: The query parameters to match.
+        type: object
+        additionalProperties: true
+      headers:
+        title: Headers
+        description: The headers to match.
+        type: object
+        additionalProperties: true
+    additionalProperties: true
   DefaultErrorHandler:
     title: Default Error Handler
     description: Component defining how to handle errors. Default behavior includes only retrying server errors (HTTP 5XX) and too many requests (HTTP 429) with an exponential backoff.
@@ -1549,7 +1715,6 @@ definitions:
         anyOf:
           - "$ref": "#/definitions/JsonDecoder"
           - "$ref": "#/definitions/XmlDecoder"
-          - "$ref": "#/definitions/CompositeRawDecoder"
       $parameters:
         type: object
         additionalProperties: true
@@ -2133,43 +2298,26 @@ definitions:
       $parameters:
         type: object
         additionalProperties: true
-  GzipJsonDecoder:
-    title: GzipJson Decoder
-    description: Use this if the response is Gzip compressed Json.
-    type: object
-    additionalProperties: true
-    required:
-      - type
-    properties:
-      type:
-        type: string
-        enum: [GzipJsonDecoder]
-      encoding:
-        type: string
-        default: utf-8
-      $parameters:
-        type: object
-        additionalProperties: true
   ZipfileDecoder:
     title: Zipfile Decoder
     description: Decoder for response data that is returned as zipfile(s).
     type: object
     additionalProperties: true
     required:
       - type
-      - parser
+      - decoder
     properties:
       type:
         type: string
         enum: [ZipfileDecoder]
-      parser:
+      decoder:
         title: Parser
         description: Parser to parse the decompressed data from the zipfile(s).
         anyOf:
-          - "$ref": "#/definitions/GzipParser"
-          - "$ref": "#/definitions/JsonParser"
-          - "$ref": "#/definitions/JsonLineParser"
-          - "$ref": "#/definitions/CsvParser"
+          - "$ref": "#/definitions/CsvDecoder"
+          - "$ref": "#/definitions/GzipDecoder"
+          - "$ref": "#/definitions/JsonDecoder"
+          - "$ref": "#/definitions/JsonlDecoder"
   ListPartitionRouter:
     title: List Partition Router
     description: A Partition router that specifies a list of attributes where each attribute describes a portion of the complete data set for a stream. During a sync, each value is iterated over and can be used as input to outbound API requests.
@@ -3002,79 +3150,39 @@ definitions:
         description: Component decoding the response so records can be extracted.
         anyOf:
           - "$ref": "#/definitions/CustomDecoder"
+          - "$ref": "#/definitions/CsvDecoder"
+          - "$ref": "#/definitions/GzipDecoder"
           - "$ref": "#/definitions/JsonDecoder"
           - "$ref": "#/definitions/JsonlDecoder"
           - "$ref": "#/definitions/IterableDecoder"
           - "$ref": "#/definitions/XmlDecoder"
-          - "$ref": "#/definitions/GzipJsonDecoder"
-          - "$ref": "#/definitions/CompositeRawDecoder"
           - "$ref": "#/definitions/ZipfileDecoder"
       $parameters:
         type: object
         additionalProperties: true
-  CompositeRawDecoder:
-    description: "(This is experimental, use at your own risk)"
-    type: object
-    required:
-      - type
-      - parser
-    properties:
-      type:
-        type: string
-        enum: [CompositeRawDecoder]
-      parser:
-        anyOf:
-          - "$ref": "#/definitions/GzipParser"
-          - "$ref": "#/definitions/JsonParser"
-          - "$ref": "#/definitions/JsonLineParser"
-          - "$ref": "#/definitions/CsvParser"
-  #    PARSERS
-  GzipParser:
+  GzipDecoder:
     type: object
     required:
       - type
-      - inner_parser
+      - decoder
     properties:
       type:
         type: string
-        enum: [GzipParser]
-      inner_parser:
+        enum: [GzipDecoder]
+      decoder:
         anyOf:
-          - "$ref": "#/definitions/JsonLineParser"
-          - "$ref": "#/definitions/CsvParser"
-          - "$ref": "#/definitions/JsonParser"
-  JsonParser:
-    title: JsonParser
-    description: Parser used for parsing str, bytes, or bytearray data and returning data in a dictionary format.
-    type: object
-    required:
-      - type
-    properties:
-      type:
-        type: string
-        enum: [JsonParser]
-      encoding:
-        type: string
-        default: utf-8
-  JsonLineParser:
-    type: object
-    required:
-      - type
-    properties:
-      type:
-        type: string
-        enum: [JsonLineParser]
-      encoding:
-        type: string
-        default: utf-8
-  CsvParser:
+          - "$ref": "#/definitions/CsvDecoder"
+          - "$ref": "#/definitions/GzipDecoder"
+          - "$ref": "#/definitions/JsonDecoder"
+          - "$ref": "#/definitions/JsonlDecoder"
+  CsvDecoder:
     type: object
     required:
       - type
     properties:
       type:
         type: string
-        enum: [CsvParser]
+        enum: [CsvDecoder]
       encoding:
         type: string
         default: utf-8
@@ -3202,24 +3310,24 @@ definitions:
         description: Component decoding the response so records can be extracted.
         anyOf:
           - "$ref": "#/definitions/CustomDecoder"
+          - "$ref": "#/definitions/CsvDecoder"
+          - "$ref": "#/definitions/GzipDecoder"
           - "$ref": "#/definitions/JsonDecoder"
           - "$ref": "#/definitions/JsonlDecoder"
           - "$ref": "#/definitions/IterableDecoder"
           - "$ref": "#/definitions/XmlDecoder"
-          - "$ref": "#/definitions/GzipJsonDecoder"
-          - "$ref": "#/definitions/CompositeRawDecoder"
           - "$ref": "#/definitions/ZipfileDecoder"
       download_decoder:
         title: Download Decoder
         description: Component decoding the download response so records can be extracted.
         anyOf:
           - "$ref": "#/definitions/CustomDecoder"
+          - "$ref": "#/definitions/CsvDecoder"
+          - "$ref": "#/definitions/GzipDecoder"
           - "$ref": "#/definitions/JsonDecoder"
           - "$ref": "#/definitions/JsonlDecoder"
           - "$ref": "#/definitions/IterableDecoder"
           - "$ref": "#/definitions/XmlDecoder"
-          - "$ref": "#/definitions/GzipJsonDecoder"
-          - "$ref": "#/definitions/CompositeRawDecoder"
           - "$ref": "#/definitions/ZipfileDecoder"
       $parameters:
         type: object

airbyte_cdk/sources/declarative/decoders/__init__.py

@@ -10,10 +10,8 @@
 )
 from airbyte_cdk.sources.declarative.decoders.decoder import Decoder
 from airbyte_cdk.sources.declarative.decoders.json_decoder import (
-    GzipJsonDecoder,
     IterableDecoder,
     JsonDecoder,
-    JsonlDecoder,
 )
 from airbyte_cdk.sources.declarative.decoders.noop_decoder import NoopDecoder
 from airbyte_cdk.sources.declarative.decoders.pagination_decoder_decorator import (
@@ -27,9 +25,7 @@
     "CompositeRawDecoder",
     "JsonDecoder",
     "JsonParser",
-    "JsonlDecoder",
     "IterableDecoder",
-    "GzipJsonDecoder",
     "NoopDecoder",
     "PaginationDecoderDecorator",
     "XmlDecoder",