Source File: Fix special characters bug (#21012)

* Source File: Fix special characters bug * Source File: bump version; update docs * Source File: update SSH credentials in unit tests * Source File: bump version (secure) * Source File: update resources manually

Author: artem1205

airbyte-config/init/src/main/resources/seed/source_definitions.yaml

@@ -489,7 +489,7 @@
 - name: File
  sourceDefinitionId: 778daa7c-feaf-4db6-96f3-70fd645acc77
  dockerRepository: airbyte/source-file
- dockerImageTag: 0.2.32
+ dockerImageTag: 0.2.33
  documentationUrl: https://docs.airbyte.com/integrations/sources/file
  icon: file.svg
  sourceType: file

airbyte-config/init/src/main/resources/seed/source_specs.yaml

@@ -4041,7 +4041,7 @@
  supportsNormalization: false
  supportsDBT: false
  supported_destination_sync_modes: []
-- dockerImage: "airbyte/source-file:0.2.32"
+- dockerImage: "airbyte/source-file:0.2.33"
  spec:
  documentationUrl: "https://docs.airbyte.com/integrations/sources/file"
  connectionSpecification:

airbyte-integrations/connectors/source-file-secure/Dockerfile

@@ -9,5 +9,5 @@ RUN pip install .
 ENV AIRBYTE_ENTRYPOINT "python /airbyte/integration_code/main.py"
 ENTRYPOINT ["python", "/airbyte/integration_code/main.py"]
 
-LABEL io.airbyte.version=0.2.32
+LABEL io.airbyte.version=0.2.33
 LABEL io.airbyte.name=airbyte/source-file-secure

airbyte-integrations/connectors/source-file/Dockerfile

@@ -17,5 +17,5 @@ COPY source_file ./source_file
 ENV AIRBYTE_ENTRYPOINT "python /airbyte/integration_code/main.py"
 ENTRYPOINT ["python", "/airbyte/integration_code/main.py"]
 
-LABEL io.airbyte.version=0.2.32
+LABEL io.airbyte.version=0.2.33
 LABEL io.airbyte.name=airbyte/source-file

airbyte-integrations/connectors/source-file/integration_tests/conftest.py

@@ -73,7 +73,7 @@ def is_ssh_ready(ip, port):
  ip,
  port=port,
  username="user1",
- password="pass1",
+ password="abc123@456#",
  )
  return True
  except (SSHException, socket.error):
@@ -93,9 +93,9 @@ def ssh_service(docker_ip, docker_services):
 def provider_config(ssh_service):
  def lookup(name):
  providers = {
- "ssh": dict(storage="SSH", host=ssh_service, user="user1", password="pass1", port=2222),
- "scp": dict(storage="SCP", host=ssh_service, user="user1", password="pass1", port=2222),
- "sftp": dict(storage="SFTP", host=ssh_service, user="user1", password="pass1", port=100),
+ "ssh": dict(storage="SSH", host=ssh_service, user="user1", password="abc123@456#", port=2222),
+ "scp": dict(storage="SCP", host=ssh_service, user="user1", password="abc123@456#", port=2222),
+ "sftp": dict(storage="SFTP", host=ssh_service, user="user1", password="abc123@456#", port=100),
  "gcs": dict(storage="GCS"),
  "s3": dict(storage="S3"),
  "azure": dict(storage="AzBlob"),

airbyte-integrations/connectors/source-file/integration_tests/docker-compose.yml

@@ -6,4 +6,4 @@ services:
  - "2222:22"
  volumes:
  - ./sample_files:/home/user1/files
- command: user1:pass1:1001
+ command: user1:abc123@456#:1001

airbyte-integrations/connectors/source-file/source_file/client.py

@@ -6,6 +6,7 @@
 import json
 import tempfile
 import traceback
+import urllib
 from os import environ
 from typing import Iterable
 from urllib.parse import urlparse
@@ -108,8 +109,11 @@ def _open(self):
  port = self._provider["port"]
  return smart_open.open(f"webhdfs://{host}:{port}/{url}", **self.args)
  elif storage in ("ssh://", "scp://", "sftp://"):
- user = self._provider["user"]
- host = self._provider["host"]
+ # We need to quote parameters to deal with special characters
+ # https://bugs.python.org/issue18140
+ user = urllib.parse.quote(self._provider["user"])
+ host = urllib.parse.quote(self._provider["host"])
+ url = urllib.parse.quote(url)
  # TODO: Remove int casting when https://github.com/airbytehq/airbyte/issues/4952 is addressed
  # TODO: The "port" field in spec.json must also be changed
  _port_value = self._provider.get("port", 22)
@@ -120,7 +124,7 @@ def _open(self):
  # Explicitly turn off ssh keys stored in ~/.ssh
  transport_params = {"connect_kwargs": {"look_for_keys": False}, "timeout": SSH_TIMEOUT}
  if "password" in self._provider:
- password = self._provider["password"]
+ password = urllib.parse.quote(self._provider["password"])
  uri = f"{storage}{user}:{password}@{host}:{port}/{url}"
  else:
  uri = f"{storage}{user}@{host}:{port}/{url}"

docs/integrations/sources/file.md

@@ -138,7 +138,8 @@ In order to read large files from a remote location, this connector uses the [sm
 ## Changelog
 
 | Version | Date | Pull Request | Subject |
-|:--------|:-----------| :------------------------------------------------------- |:---------------------------------------------------------|
+|:--------|:-----------|:---------------------------------------------------------|:---------------------------------------------------------|
+| 0.2.33 | 2023-01-04 | [21012](https://github.com/airbytehq/airbyte/pull/21012) | Fix special characters bug |
 | 0.2.32 | 2022-12-21 | [20740](https://github.com/airbytehq/airbyte/pull/20740) | Source File: increase SSH timeout to 60s |
 | 0.2.31 | 2022-11-17 | [19567](https://github.com/airbytehq/airbyte/pull/19567) | Source File: bump 0.2.31 |
 | 0.2.30 | 2022-11-10 | [19222](https://github.com/airbytehq/airbyte/pull/19222) | Use AirbyteConnectionStatus for "check" command |