airbyte-cdk 7.3.7.post3.dev18576192478__tar.gz → 7.3.9__tar.gz

{airbyte_cdk-7.3.7.post3.dev18576192478 → airbyte_cdk-7.3.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: airbyte-cdk
-Version: 7.3.7.post3.dev18576192478
+Version: 7.3.9
 Summary: A framework for writing Airbyte Connectors.
 Home-page: https://airbyte.com
 License: MIT
@@ -35,7 +35,7 @@ Requires-Dist: click (>=8.1.8,<9.0.0)
 Requires-Dist: cohere (>=4.21,<6.0.0) ; extra == "vector-db-based"
 Requires-Dist: cryptography (>=44.0.0,<45.0.0)
 Requires-Dist: dateparser (>=1.2.2,<2.0.0)
-Requires-Dist: ddtrace (>=3.12.0,<4.0.0) ; extra == "manifest-server"
+Requires-Dist: ddtrace (>=3,<4) ; extra == "manifest-server"
 Requires-Dist: dpath (>=2.1.6,<3.0.0)
 Requires-Dist: dunamai (>=1.22.0,<2.0.0)
 Requires-Dist: fastapi (>=0.116.1) ; extra == "manifest-server"
@@ -45,11 +45,10 @@ Requires-Dist: google-cloud-secret-manager (>=2.17.0,<3.0.0)
 Requires-Dist: isodate (>=0.6.1,<0.7.0)
 Requires-Dist: jsonref (>=1,<2)
 Requires-Dist: jsonschema (>=4.17.3,<5.0)
-Requires-Dist: langchain (>=0.1.16,<1.0.0) ; extra == "vector-db-based"
-Requires-Dist: langchain_core (>=0.1.42,<1.0.0)
+Requires-Dist: langchain (==0.1.16) ; extra == "vector-db-based"
+Requires-Dist: langchain_core (==0.1.42)
 Requires-Dist: markdown ; extra == "file-based"
 Requires-Dist: nltk (==3.9.1)
-Requires-Dist: numpy (>=2.0.0,<3.0.0)
 Requires-Dist: openai[embeddings] (==0.27.9) ; extra == "vector-db-based"
 Requires-Dist: orjson (>=3.10.7,<4.0.0)
 Requires-Dist: packaging

{airbyte_cdk-7.3.7.post3.dev18576192478 → airbyte_cdk-7.3.9}/airbyte_cdk/sources/declarative/extractors/response_to_file_extractor.py

@@ -7,11 +7,11 @@ import uuid
 import zlib
 from contextlib import closing
 from dataclasses import InitVar, dataclass
+from math import nan
 from typing import Any, Dict, Iterable, Mapping, Optional, Tuple
 
 import pandas as pd
 import requests
-from numpy import nan
 
 from airbyte_cdk.sources.declarative.extractors.record_extractor import RecordExtractor
 

{airbyte_cdk-7.3.7.post3.dev18576192478 → airbyte_cdk-7.3.9}/airbyte_cdk/sources/file_based/exceptions.py

@@ -157,3 +157,7 @@ class CustomFileBasedException(AirbyteTracedException):
 
 class FileSizeLimitError(CustomFileBasedException):
     pass
+
+
+class EmptyFileSchemaInferenceError(AirbyteTracedException):
+    pass

{airbyte_cdk-7.3.7.post3.dev18576192478 → airbyte_cdk-7.3.9}/airbyte_cdk/sources/file_based/file_types/csv_parser.py

@@ -22,7 +22,11 @@ from airbyte_cdk.sources.file_based.config.csv_format import (
     InferenceType,
 )
 from airbyte_cdk.sources.file_based.config.file_based_stream_config import FileBasedStreamConfig
-from airbyte_cdk.sources.file_based.exceptions import FileBasedSourceError, RecordParseError
+from airbyte_cdk.sources.file_based.exceptions import (
+    EmptyFileSchemaInferenceError,
+    FileBasedSourceError,
+    RecordParseError,
+)
 from airbyte_cdk.sources.file_based.file_based_stream_reader import (
     AbstractFileBasedStreamReader,
     FileReadMode,
@@ -203,7 +207,7 @@ class CsvParser(FileTypeParser):
                 break
 
         if not type_inferrer_by_field:
-            raise AirbyteTracedException(
+            raise EmptyFileSchemaInferenceError(
                 message=f"Could not infer schema as there are no rows in {file.uri}. If having an empty CSV file is expected, ignore this. "
                 f"Else, please contact Airbyte.",
                 failure_type=FailureType.config_error,

{airbyte_cdk-7.3.7.post3.dev18576192478 → airbyte_cdk-7.3.9}/airbyte_cdk/sources/file_based/file_types/excel_parser.py

@@ -9,8 +9,6 @@ from typing import Any, Dict, Iterable, Mapping, Optional, Tuple, Union
 
 import orjson
 import pandas as pd
-from numpy import datetime64, issubdtype
-from numpy import dtype as dtype_
 from pydantic.v1 import BaseModel
 
 from airbyte_cdk.sources.file_based.config.file_based_stream_config import (
@@ -141,7 +139,7 @@ class ExcelParser(FileTypeParser):
     @staticmethod
     def dtype_to_json_type(
         current_type: Optional[str],
-        dtype: dtype_,  # type: ignore [type-arg]
+        dtype: Any,  # Type object from pandas DataFrame
     ) -> str:
         """
         Convert Pandas DataFrame types to Airbyte Types.
@@ -163,7 +161,7 @@ class ExcelParser(FileTypeParser):
             return "number"
         if dtype == "bool" and (not current_type or current_type == "boolean"):
             return "boolean"
-        if issubdtype(dtype, datetime64):
+        if pd.api.types.is_datetime64_any_dtype(dtype):
             return "date-time"
         return "string"
 

{airbyte_cdk-7.3.7.post3.dev18576192478 → airbyte_cdk-7.3.9}/airbyte_cdk/sources/file_based/stream/default_file_based_stream.py

@@ -9,13 +9,26 @@ from collections import defaultdict
 from copy import deepcopy
 from functools import cache
 from os import path
-from typing import Any, Dict, Iterable, List, Mapping, MutableMapping, Optional, Set, Tuple, Union
+from typing import (
+    Any,
+    Dict,
+    Iterable,
+    List,
+    Mapping,
+    MutableMapping,
+    NoReturn,
+    Optional,
+    Set,
+    Tuple,
+    Union,
+)
 
 from airbyte_cdk.models import AirbyteLogMessage, AirbyteMessage, AirbyteStream, FailureType, Level
 from airbyte_cdk.models import Type as MessageType
 from airbyte_cdk.sources.file_based.config.file_based_stream_config import PrimaryKeyType
 from airbyte_cdk.sources.file_based.exceptions import (
     DuplicatedFilesError,
+    EmptyFileSchemaInferenceError,
     FileBasedSourceError,
     InvalidSchemaError,
     MissingSchemaError,
@@ -230,7 +243,7 @@ class DefaultFileBasedStream(AbstractFileBasedStream, IncrementalMixin):
         return self.ab_last_mod_col
 
     @cache
-    def get_json_schema(self) -> JsonSchema:
+    def get_json_schema(self) -> JsonSchema:  # type: ignore
         if self.use_file_transfer:
             return file_transfer_schema
         extra_fields = {
@@ -246,12 +259,12 @@ class DefaultFileBasedStream(AbstractFileBasedStream, IncrementalMixin):
                 exception=AirbyteTracedException(exception=config_exception),
                 failure_type=FailureType.config_error,
             )
+        except EmptyFileSchemaInferenceError as exc:
+            self._raise_schema_inference_error(exc)
         except AirbyteTracedException as ate:
             raise ate
         except Exception as exc:
-            raise SchemaInferenceError(
-                FileBasedSourceError.SCHEMA_INFERENCE_ERROR, stream=self.name
-            ) from exc
+            self._raise_schema_inference_error(exc)
         else:
             return {"type": "object", "properties": {**extra_fields, **schema["properties"]}}
 
@@ -380,17 +393,24 @@ class DefaultFileBasedStream(AbstractFileBasedStream, IncrementalMixin):
 
         return base_schema
 
-    async def _infer_file_schema(self, file: RemoteFile) -> SchemaType:
+    async def _infer_file_schema(self, file: RemoteFile) -> SchemaType:  # type: ignore
         try:
             return await self.get_parser().infer_schema(
                 self.config, file, self.stream_reader, self.logger
             )
+        except EmptyFileSchemaInferenceError as exc:
+            self._raise_schema_inference_error(exc, file)
         except AirbyteTracedException as ate:
             raise ate
         except Exception as exc:
-            raise SchemaInferenceError(
-                FileBasedSourceError.SCHEMA_INFERENCE_ERROR,
-                file=file.uri,
-                format=str(self.config.format),
-                stream=self.name,
-            ) from exc
+            self._raise_schema_inference_error(exc, file)
+
+    def _raise_schema_inference_error(
+        self, exc: Exception, file: Optional[RemoteFile] = None
+    ) -> NoReturn:
+        raise SchemaInferenceError(
+            FileBasedSourceError.SCHEMA_INFERENCE_ERROR,
+            file=file.uri if file else None,
+            format=str(self.config.format) if self.config.format else None,
+            stream=self.name,
+        ) from exc

{airbyte_cdk-7.3.7.post3.dev18576192478 → airbyte_cdk-7.3.9}/pyproject.toml

@@ -23,7 +23,7 @@ classifiers = [
 keywords = ["airbyte", "connector-development-kit", "cdk"]
 
 # Python CDK uses dynamic versioning: https://github.com/mtkennerly/poetry-dynamic-versioning
-version = "7.3.7.post3.dev18576192478"  # Version will be calculated dynamically.
+version = "7.3.9"  # Version will be calculated dynamically.
 
 [tool.poetry-dynamic-versioning]
 enable = false
@@ -64,8 +64,8 @@ wcmatch = "10.0"
 avro = { version = ">=1.11.2,<1.13.0", optional = true }  # TODO: Move into dev dependencies if only used in tests
 cohere = { version = ">=4.21,<6.0.0", optional = true }
 fastavro = { version = ">=1.11.0,<2.0.0", optional = true }
-langchain = { version = ">=0.1.16,<1.0.0", optional = true }
-langchain_core = { version = ">=0.1.42,<1.0.0", optional = true }
+langchain = { version = "0.1.16", optional = true }
+langchain_core = { version = "0.1.42", optional = true }
 markdown = { version = "*", optional = true }  # TODO: Remove if unused
 openai = { version = "0.27.9", extras = ["embeddings"], optional = true }  # Used indirectly by langchain library
 pdf2image = { version = "1.16.3", optional = true }
@@ -76,7 +76,6 @@ python-calamine = { version = "0.2.3", optional = true }  # TODO: Remove if unus
 python-snappy = { version = "0.7.3", optional = true }  # TODO: remove if unused
 tiktoken = { version = "0.8.0", optional = true }
 nltk = { version = "3.9.1", optional = true }
-numpy = "^2.0.0"
 unstructured = { version = "0.10.27", extras = ["docx", "pptx"], optional = true }
 "unstructured.pytesseract" = { version = ">=0.3.12", optional = true }
 pyjwt = "^2.8.0"
@@ -88,7 +87,7 @@ serpyco-rs = "^1.10.2"
 sqlalchemy = {version = "^2.0,!=2.0.36", optional = true }
 fastapi = { version = ">=0.116.1", optional = true }
 uvicorn = { version = ">=0.35.0", optional = true}
-ddtrace = { version = "^3.12.0", optional = true }
+ddtrace = { version = "^3", optional = true }
 xmltodict = ">=0.13,<0.15"
 anyascii = "^0.3.2"
 whenever = ">=0.7.3,<0.9.0"