python-databases 2.0.0__tar.gz → 2.2.0__tar.gz

{python_databases-2.0.0/python_databases.egg-info → python_databases-2.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-databases
-Version: 2.0.0
+Version: 2.2.0
 Summary: A Python library for managing and interacting with multiple databases seamlessly.
 Author: Avi Zaguri
 License: MIT
@@ -16,11 +16,10 @@ Classifier: Topic :: System :: Logging
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: custom-python-logger>=4.0.2
-Requires-Dist: elasticsearch<9
-Requires-Dist: pandas>=2.3.3
-Requires-Dist: psycopg2-binary>=2.9.11
-Requires-Dist: python-dotenv>=1.2.1
+Requires-Dist: custom-python-logger>=4.2.0
+Requires-Dist: elasticsearch<9,>=8.19.3
+Requires-Dist: psycopg2-binary>=2.9.13
+Requires-Dist: python-dotenv>=1.2.4
 Requires-Dist: retrying>=1.4.2
 Dynamic: license-file
 

{python_databases-2.0.0 → python_databases-2.2.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "python-databases"
-version = "2.0.0"
+version = "2.2.0"
 description = "A Python library for managing and interacting with multiple databases seamlessly."
 readme = "README.md"
 requires-python = ">=3.12"
@@ -21,20 +21,17 @@ classifiers = [
 ]
 
 dependencies = [
-    "custom-python-logger>=4.0.2",
-    "elasticsearch<9",
-    "pandas>=2.3.3",
-    "psycopg2-binary>=2.9.11",
-    "python-dotenv>=1.2.1",
+    "custom-python-logger>=4.2.0",
+    "elasticsearch>=8.19.3,<9",
+    "psycopg2-binary>=2.9.13",
+    "python-dotenv>=1.2.4",
     "retrying>=1.4.2",
 ]
 
 [dependency-groups]
 dev = [
-    "pre-commit>=4.6.2",
-    "pytest>=9.0.2",
-    "setuptools>=84.0.0",
-    "wheel>=0.48.0",
+    "pre-commit>=4.7.0",
+    "pytest>=9.2.0",
 ]
 
 [project.urls]

{python_databases-2.0.0 → python_databases-2.2.0}/python_databases/elasticsearch_infrastructure/elasticsearch.py

@@ -6,7 +6,6 @@ from datetime import UTC, datetime
 from enum import Enum
 from typing import Any
 
-import pandas as pd
 from custom_python_logger import get_logger
 from elasticsearch import Elasticsearch, helpers
 from retrying import retry
@@ -38,10 +37,10 @@ class ElasticSearch(ABC):
         self.password = password
 
         self.elasticsearch_port = elasticsearch_port
-        if not self.elasticsearch_port:
-            self.elasticsearch_url = f"{self.protocol.value}://{self.elk_hostname}"
-        else:
+        if self.elasticsearch_port:
             self.elasticsearch_url = f"{self.protocol.value}://{self.elk_hostname}:{self.elasticsearch_port}"
+        else:
+            self.elasticsearch_url = f"{self.protocol.value}://{self.elk_hostname}"
         self.kibana_port = kibana_port
 
         self.elk_client = None
@@ -67,7 +66,7 @@ class ElasticSearch(ABC):
         ):
             for item in failed_response:
                 if item[1]["index"]["status"] != 201 or item[1]["index"]["_shards"]["failed"] > 0:
-                    self.logger.debug(f"Failed document: \n{item}")
+                    self.logger.error(f"Failed document: \n{item}")
                     failed_response_list.append(item)
         if raise_on_error and failed_response_list:
             raise Exception(f"Failed to report {len(failed_response_list)} documents to Elasticsearch")
@@ -89,7 +88,9 @@ class ElasticSearch(ABC):
 
         if quick:
             self._set_list_of_docs_quick(
-                list_of_docs=list_of_docs, request_timeout=request_timeout, raise_on_error=raise_on_error
+                list_of_docs=list_of_docs,
+                request_timeout=request_timeout,
+                raise_on_error=raise_on_error,
             )
         else:
             self._set_list_of_docs_safe(list_of_docs=list_of_docs)
@@ -97,23 +98,15 @@ class ElasticSearch(ABC):
 
     @staticmethod
     def _get_doc_with_basic_info() -> dict:
-        doc = {}
-
         timestamp = datetime.now(tz=UTC)
         date_and_time_str = timestamp.isoformat()
-        date = date_and_time_str.split("T")[0]
-        time_part = date_and_time_str.split("T")[1].split("+")[0]
-
-        doc.update(
-            {
-                "doc_id": timestamp.strftime("%Y%m%dT%H%M%S%f"),
-                "upload_timestamp": timestamp,
-                "date_and_time_str": date_and_time_str,
-                "date_str": date,
-                "time_str": time_part,
-            }
-        )
-        return doc
+        return {
+            "doc_id": timestamp.strftime("%Y%m%dT%H%M%S%f"),
+            "upload_timestamp": timestamp,
+            "date_and_time_str": date_and_time_str,
+            "date_str": date_and_time_str.split("T")[0],
+            "time_str": date_and_time_str.split("T")[1].split("+")[0],
+        }
 
     @staticmethod
     def _add_list_values_as_str(doc: dict, column: str, value: Any) -> None:
@@ -218,19 +211,6 @@ class ElasticSearch(ABC):
         except Exception as e:
             raise Exception(f"Failed to get documents from index '{index}': {str(e)}") from e
 
-    def convert_dataframes_to_list_of_docs(
-        self,
-        dataframe: pd.DataFrame,
-        log_progress: bool = False,
-    ) -> list:
-        data = []
-        dataframe_values = dataframe.values.tolist()
-        for index, value in enumerate(dataframe_values):
-            if log_progress:
-                self.logger.debug(f"index: {index}/{len(dataframe_values)}")
-            data.append(value)
-        return data
-
 
 class ElasticSearchOnPrem(ElasticSearch):
     def __init__(

{python_databases-2.0.0 → python_databases-2.2.0/python_databases.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-databases
-Version: 2.0.0
+Version: 2.2.0
 Summary: A Python library for managing and interacting with multiple databases seamlessly.
 Author: Avi Zaguri
 License: MIT
@@ -16,11 +16,10 @@ Classifier: Topic :: System :: Logging
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: custom-python-logger>=4.0.2
-Requires-Dist: elasticsearch<9
-Requires-Dist: pandas>=2.3.3
-Requires-Dist: psycopg2-binary>=2.9.11
-Requires-Dist: python-dotenv>=1.2.1
+Requires-Dist: custom-python-logger>=4.2.0
+Requires-Dist: elasticsearch<9,>=8.19.3
+Requires-Dist: psycopg2-binary>=2.9.13
+Requires-Dist: python-dotenv>=1.2.4
 Requires-Dist: retrying>=1.4.2
 Dynamic: license-file
 

python_databases-2.2.0/python_databases.egg-info/requires.txt

@@ -0,0 +1,5 @@
+custom-python-logger>=4.2.0
+elasticsearch<9,>=8.19.3
+psycopg2-binary>=2.9.13
+python-dotenv>=1.2.4
+retrying>=1.4.2

{python_databases-2.0.0 → python_databases-2.2.0}/tests/test_elasticsearch.py

@@ -10,7 +10,6 @@ from collections.abc import Iterator
 from datetime import datetime
 from unittest.mock import MagicMock, call, patch
 
-import pandas as pd
 import pytest
 from elasticsearch.helpers import BulkIndexError
 
@@ -421,31 +420,6 @@ def test_get_documents_wraps_and_chains_client_error(  # pylint: disable=redefin
     assert exc_info.value.__cause__ is original, "original error not chained"
 
 
-# --------------------------------------------------------------------------- #
-# convert_dataframes_to_list_of_docs
-# --------------------------------------------------------------------------- #
-def test_convert_dataframes_returns_one_entry_per_row(  # pylint: disable=redefined-outer-name
-    es: _FakeElasticSearch,
-) -> None:
-    df = pd.DataFrame({"a": [1, 2], "b": [3, 4]})
-    result = es.convert_dataframes_to_list_of_docs(dataframe=df)
-    assert len(result) == 2, f"expected one entry per row, got {result}"
-
-
-@pytest.mark.xfail(
-    strict=True,
-    reason="BUG: convert_dataframes_to_list_of_docs returns bare value lists (df.values.tolist()), "
-    "dropping column names. Its output is not consumable by fill_elk_index_as_bulk / _build_document, "
-    "which iterate row.items().",
-)
-def test_convert_dataframes_output_is_keyed_by_column(  # pylint: disable=redefined-outer-name
-    es: _FakeElasticSearch,
-) -> None:
-    df = pd.DataFrame({"a": [1, 2], "b": [3, 4]})
-    result = es.convert_dataframes_to_list_of_docs(dataframe=df)
-    assert result == [{"a": 1, "b": 3}, {"a": 2, "b": 4}], f"column names lost: {result}"
-
-
 # --------------------------------------------------------------------------- #
 # Concrete connect implementations
 # --------------------------------------------------------------------------- #

python_databases-2.0.0/python_databases.egg-info/requires.txt

@@ -1,6 +0,0 @@
-custom-python-logger>=4.0.2
-elasticsearch<9
-pandas>=2.3.3
-psycopg2-binary>=2.9.11
-python-dotenv>=1.2.1
-retrying>=1.4.2