Merge branch 'main' into 484-feat-support-integer-types-other-than-bi…

…gint

.github/workflows/constraints.txt

@@ -1,2 +1,2 @@
-meltano==3.6.0b2
+meltano==3.6.0
 tox==4.23.2

.github/workflows/release_workflow.yml

@@ -37,4 +37,4 @@ jobs:
         tag: ${{ github.ref }}
         overwrite: true
         file_glob: true
-    - uses: pypa/gh-action-pypi-publish@v1.11.0
+    - uses: pypa/gh-action-pypi-publish@v1.12.3

.pre-commit-config.yaml

@@ -18,7 +18,7 @@ repos:
   - id: trailing-whitespace
 
 - repo: https://github.com/astral-sh/ruff-pre-commit
-  rev: v0.7.2
+  rev: v0.8.6
   hooks:
   - id: ruff
     args: [--fix]

pyproject.toml

@@ -33,14 +33,14 @@ packages = [
 
 [tool.poetry.dependencies]
 python = ">=3.9"
-faker = {version = "~=30.0", optional = true}
+faker = {version = "~=33.1", optional = true}
 psycopg = {extras = ["binary"], version = "3.2.3"}
 psycopg2-binary = "2.9.10"
 sqlalchemy = "~=2.0"
 sshtunnel = "0.4.0"
 
 [tool.poetry.dependencies.singer-sdk]
-version = "~=0.42.0b1"
+version = "~=0.43.0"
 
 [tool.poetry.extras]
 faker = ["faker"]

target_postgres/connector.py

@@ -120,6 +120,15 @@ def interpret_content_encoding(self) -> bool:
         """
         return self.config.get("interpret_content_encoding", False)
 
+    @cached_property
+    def sanitize_null_text_characters(self) -> bool:
+        """Whether to sanitize null text characters.
+
+        Returns:
+            True if the feature is enabled, False otherwise.
+        """
+        return self.config.get("sanitize_null_text_characters", False)
+
     def prepare_table(  # type: ignore[override]  # noqa: PLR0913
         self,
         full_table_name: str | FullyQualifiedName,

target_postgres/sinks.py

@@ -119,6 +119,27 @@ def generate_temp_table_name(self):
         # in postgres, used a guid just in case we are using the same session
         return f"{str(uuid.uuid4()).replace('-', '_')}"
 
+    def sanitize_null_text_characters(self, data):
+        """Sanitizes null characters by replacing \u0000 with \ufffd."""
+
+        def replace_null_character(d):
+            return d.replace("\u0000", "\ufffd")
+
+        if isinstance(data, str):
+            data = replace_null_character(data)
+
+        elif isinstance(data, dict):
+            for k in data:
+                if isinstance(data[k], str):
+                    data[k] = replace_null_character(data[k])
+
+        elif isinstance(data, list):
+            for i in range(0, len(data)):
+                if isinstance(data[i], str):
+                    data[i] = replace_null_character(data[i])
+
+        return data
+
     def generate_copy_statement(
         self,
         full_table_name: str | FullyQualifiedName,
@@ -204,7 +225,12 @@ def bulk_insert_records(  # type: ignore[override]
             unique_records: dict[tuple, dict] = {}  # pk tuple: values
             for record in records:
                 insert_record = {
-                    column.name: record.get(column.name) for column in columns
+                    column.name: (
+                        self.sanitize_null_text_characters(record.get(column.name))
+                        if self.connector.sanitize_null_text_characters
+                        else record.get(column.name)
+                    )
+                    for column in columns
                 }
                 # No need to check for a KeyError here because the SDK already
                 # guarantees that all key properties exist in the record.
@@ -214,7 +240,12 @@ def bulk_insert_records(  # type: ignore[override]
         else:
             for record in records:
                 insert_record = {
-                    column.name: record.get(column.name) for column in columns
+                    column.name: (
+                        self.sanitize_null_text_characters(record.get(column.name))
+                        if self.connector.sanitize_null_text_characters
+                        else record.get(column.name)
+                    )
+                    for column in columns
                 }
                 data.append(insert_record)
 

target_postgres/target.py

@@ -218,6 +218,17 @@ def __init__(
                 "in an error if the data is not encoded as expected."
             ),
         ),
+        th.Property(
+            "sanitize_null_text_characters",
+            th.BooleanType,
+            default=False,
+            description=(
+                "If set to true, the target will sanitize null characters in "
+                "char/text/varchar fields, as they are not supported by Postgres. "
+                "See [postgres documentation](https://www.postgresql.org/docs/current/functions-string.html) "  # noqa: E501
+                "for more information about chr(0) not being supported."
+            ),
+        ),
         th.Property(
             "ssl_enable",
             th.BooleanType,