dbworkload 0.6.1__tar.gz → 0.6.3__tar.gz

dbworkload-0.6.3/PKG-INFO

@@ -0,0 +1,54 @@
+Metadata-Version: 2.1
+Name: dbworkload
+Version: 0.6.3
+Summary: Workload framework
+Home-page: https://dbworkload.github.io/dbworkload/
+License: GPLv3+
+Author: Fabio Ghirardello
+Requires-Python: >=3.8,<4.0
+Classifier: License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)
+Classifier: License :: Other/Proprietary License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Provides-Extra: all
+Provides-Extra: cassandra
+Provides-Extra: mariadb
+Provides-Extra: mongo
+Provides-Extra: mysql
+Provides-Extra: odbc
+Provides-Extra: oracle
+Provides-Extra: postgres
+Provides-Extra: spanner
+Requires-Dist: cassandra-driver ; extra == "all" or extra == "cassandra"
+Requires-Dist: google-cloud-spanner ; extra == "all" or extra == "spanner"
+Requires-Dist: jinja2
+Requires-Dist: mariadb ; extra == "all" or extra == "mariadb"
+Requires-Dist: mysql-connector-python ; extra == "all" or extra == "mysql"
+Requires-Dist: numpy
+Requires-Dist: oracledb ; extra == "all" or extra == "oracle"
+Requires-Dist: pandas
+Requires-Dist: plotext
+Requires-Dist: plotly
+Requires-Dist: prometheus-client
+Requires-Dist: psycopg ; extra == "all" or extra == "postgres"
+Requires-Dist: psycopg-binary ; extra == "all" or extra == "postgres"
+Requires-Dist: pymongo ; extra == "all" or extra == "mongo"
+Requires-Dist: pyodbc ; extra == "all" or extra == "odbc"
+Requires-Dist: pytdigest
+Requires-Dist: pyyaml
+Requires-Dist: sqlparse
+Requires-Dist: tabulate
+Requires-Dist: typer[all]
+Project-URL: Repository, https://github.com/dbworkload/dbworkload
+Description-Content-Type: text/markdown
+
+# dbworkload - DBMS workload utility
+
+Visit the [online documentation](https://dbworkload.github.io/dbworkload/).
+

{dbworkload-0.6.1 → dbworkload-0.6.3}/dbworkload/cli/main.py

@@ -4,7 +4,6 @@ from .. import __version__
 from dbworkload.cli.dep import Param, EPILOG, ConnInfo
 from enum import Enum
 from pathlib import Path
-from typer.main import get_command
 from typing import Optional
 from urllib.parse import urlparse
 import dbworkload.cli.util
@@ -298,5 +297,6 @@ def version_option(
 ) -> None:
     pass
 
+
 # this is only needed for mkdocs-click
-click_app = get_command(app)
+click_app = typer.main.get_command(app)

{dbworkload-0.6.1 → dbworkload-0.6.3}/dbworkload/utils/simplefaker.py

@@ -7,6 +7,7 @@ import pandas as pd
 import uuid
 import random
 import builtins
+from .common import import_class_at_runtime
 
 logger = logging.getLogger("dbworkload")
 
@@ -584,6 +585,9 @@ class SimpleFaker:
             return [SimpleFaker.Bit(seed=s, **args) for s in seeds]
         elif obj_type == "bytes":
             return [SimpleFaker.Bytes(seed=s, **args) for s in seeds]
+        elif obj_type == "custom":
+            custom_gen = import_class_at_runtime(args.pop("path"))
+            return [custom_gen(seed=s, **args) for s in seeds]
         else:
             raise ValueError(
                 f"SimpleFaker type not implemented or recognized: '{obj_type}'"
@@ -610,47 +614,57 @@ class SimpleFaker:
             separator (str): the field delimiter in the CSV file
             compression (str): the compression format (gzip, zip, None..)
         """
+
+        def gen_to_csv(iters: int):
+            # create individual Series and then concat them together
+            df = pd.concat(
+                [pd.Series([next(gen) for _ in range(iters)]) for gen in generators],
+                axis=1,
+                keys=col_names,
+            )
+
+            # get a list of the colums that are not to be sorted by
+            remaining = list(set(col_names) - set(sort_by))
+
+            # create a dataframe by concatenating:
+            # 1 - the df subset with the sort_by columns sorted by the sort_by columns
+            # 2 - the df subset with the remaining columns
+            # finally order the columns by the original col_names
+            # then save to csv
+            pd.concat(
+                [
+                    df[sort_by].sort_values(sort_by).reset_index(drop=True),
+                    df[remaining],
+                ],
+                axis=1,
+            )[col_names].to_csv(
+                basename + "_" + str(counter) + suffix,
+                quoting=csv.QUOTE_MINIMAL,
+                sep=separator,
+                header=False,
+                index=False,
+                compression=compression,
+            )
+
         logger.debug("SimpleFaker worker created")
         if iterations > self.csv_max_rows:
-            count = int(iterations / self.csv_max_rows)
+            count = iterations // self.csv_max_rows
             rem = iterations % self.csv_max_rows
             iterations = self.csv_max_rows
         else:
             count = 1
             rem = 0
 
-        if separator == "\t":
-            suffix = ".tsv"
-        else:
-            suffix = ".csv"
-
-        if compression == "gzip":
-            suffix += ".gz"
-        elif compression == "zip":
-            suffix += ".zip"
-        elif compression == "bz2":
-            suffix += ".bz2"
-        elif compression == "xz":
-            suffix += ".xz"
-
-        for x in range(count):
+        suffix = ".tsv" if separator == "\t" else ".csv"
+
+        if compression:
+            suffix += "." + {
+                "gzip": "gz",
+            }.get(compression, compression)
+
+        for counter in range(count):
             try:
-                pd.DataFrame(
-                    [
-                        row
-                        for row in [
-                            [next(x) for x in generators] for _ in range(iterations)
-                        ]
-                    ],
-                    columns=col_names,
-                ).sort_values(by=sort_by).to_csv(
-                    basename + "_" + str(x) + suffix,
-                    quoting=csv.QUOTE_MINIMAL,
-                    sep=separator,
-                    header=False,
-                    index=False,
-                    compression=compression,
-                )
+                gen_to_csv(iterations)
             except csv.Error as e:
                 logger.error(e)
                 if e.args[0] == "need to escape, but no escapechar set":
@@ -658,20 +672,11 @@ class SimpleFaker:
                         f"You cannot use the selected delimiter '{separator}'. Consider using another char or the the tab key."
                     )
 
-            logger.debug(f"Saved file '{basename + '_' + str(x) + suffix}'")
+            logger.debug(f"Saved file '{basename + '_' + str(counter) + suffix}'")
 
         # remaining rows, if any
         if rem > 0:
-            pd.DataFrame(
-                [row for row in [[next(x) for x in generators] for _ in range(rem)]],
-                columns=col_names,
-            ).sort_values(by=sort_by).to_csv(
-                basename + "_" + str(count) + suffix,
-                quoting=csv.QUOTE_MINIMAL,
-                sep=separator,
-                header=False,
-                index=False,
-                compression=compression,
-            )
+            counter = count
+            gen_to_csv(rem)
 
-            logger.debug(f"Saved file '{basename + '_' + str(x) + suffix}'")
+            logger.debug(f"Saved file '{basename + '_' + str(counter) + suffix}'")

{dbworkload-0.6.1 → dbworkload-0.6.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "dbworkload"
-version = "0.6.1"
+version = "0.6.3"
 description = "Workload framework"
 authors = ["Fabio Ghirardello"]
 license = "GPLv3+"
@@ -18,26 +18,26 @@ dbworkload = 'dbworkload.cli.main:app'
 
 [tool.poetry.dependencies]
 python = "^3.8"
-pandas = "^1.5.2"
-tabulate = "^0.9.0"
-numpy = "^1.23.5"
-prometheus-client = "^0.15.0"
-pyyaml = "^6.0"
-typer = {extras = ["all"], version = "^0.7.0"}
-cassandra-driver = {version = "^3.29.1", optional = true}
-mysql-connector-python = {version = "^8.4.0", optional = true}
-oracledb = {version = "^2.2.0", optional = true}
-psycopg = {version = "^3.1.19", optional = true}
-psycopg-binary = {version = "^3.1.19", optional = true}
-pymongo = {version = "^4.7.2", optional = true}
-pyodbc = {version = "^5.1.0", optional = true}
-mariadb = {version = "^1.1.10", optional = true}
-google-cloud-spanner = {version = "^3.49.1", optional = true}
-pytdigest = "^0.1.4"
-plotext = "^5.2.8"
-plotly = "^5.24.0"
-jinja2 = "^3.1.4"
-sqlparse = "^0.5.1"
+pandas = "*"
+tabulate = "*"
+numpy = "*"
+prometheus-client = "*"
+pyyaml = "*"
+typer = {extras = ["all"], version = "*"}
+cassandra-driver = {version = "*", optional = true}
+mysql-connector-python = {version = "*", optional = true}
+oracledb = {version = "*", optional = true}
+psycopg = {version = "*", optional = true}
+psycopg-binary = {version = "*", optional = true}
+pymongo = {version = "*", optional = true}
+pyodbc = {version = "*", optional = true}
+mariadb = {version = "*", optional = true}
+google-cloud-spanner = {version = "*", optional = true}
+pytdigest = "*"
+plotext = "*"
+plotly = "*"
+jinja2 = "*"
+sqlparse = "*"
 
 [tool.poetry.extras]
 all =  ["psycopg", "psycopg-binary", "mysql-connector-python", "mariadb", "oracledb", "pyodbc", "pymongo", "cassandra-driver", "google-cloud-spanner"]

dbworkload-0.6.1/PKG-INFO

@@ -1,53 +0,0 @@
-Metadata-Version: 2.1
-Name: dbworkload
-Version: 0.6.1
-Summary: Workload framework
-Home-page: https://dbworkload.github.io/dbworkload/
-License: GPLv3+
-Author: Fabio Ghirardello
-Requires-Python: >=3.8,<4.0
-Classifier: License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)
-Classifier: License :: Other/Proprietary License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Provides-Extra: all
-Provides-Extra: cassandra
-Provides-Extra: mariadb
-Provides-Extra: mongo
-Provides-Extra: mysql
-Provides-Extra: odbc
-Provides-Extra: oracle
-Provides-Extra: postgres
-Provides-Extra: spanner
-Requires-Dist: cassandra-driver (>=3.29.1,<4.0.0) ; extra == "all" or extra == "cassandra"
-Requires-Dist: google-cloud-spanner (>=3.49.1,<4.0.0) ; extra == "all" or extra == "spanner"
-Requires-Dist: jinja2 (>=3.1.4,<4.0.0)
-Requires-Dist: mariadb (>=1.1.10,<2.0.0) ; extra == "all" or extra == "mariadb"
-Requires-Dist: mysql-connector-python (>=8.4.0,<9.0.0) ; extra == "all" or extra == "mysql"
-Requires-Dist: numpy (>=1.23.5,<2.0.0)
-Requires-Dist: oracledb (>=2.2.0,<3.0.0) ; extra == "all" or extra == "oracle"
-Requires-Dist: pandas (>=1.5.2,<2.0.0)
-Requires-Dist: plotext (>=5.2.8,<6.0.0)
-Requires-Dist: plotly (>=5.24.0,<6.0.0)
-Requires-Dist: prometheus-client (>=0.15.0,<0.16.0)
-Requires-Dist: psycopg (>=3.1.19,<4.0.0) ; extra == "all" or extra == "postgres"
-Requires-Dist: psycopg-binary (>=3.1.19,<4.0.0) ; extra == "all" or extra == "postgres"
-Requires-Dist: pymongo (>=4.7.2,<5.0.0) ; extra == "all" or extra == "mongo"
-Requires-Dist: pyodbc (>=5.1.0,<6.0.0) ; extra == "all" or extra == "odbc"
-Requires-Dist: pytdigest (>=0.1.4,<0.2.0)
-Requires-Dist: pyyaml (>=6.0,<7.0)
-Requires-Dist: sqlparse (>=0.5.1,<0.6.0)
-Requires-Dist: tabulate (>=0.9.0,<0.10.0)
-Requires-Dist: typer[all] (>=0.7.0,<0.8.0)
-Project-URL: Repository, https://github.com/dbworkload/dbworkload
-Description-Content-Type: text/markdown
-
-# dbworkload - DBMS workload utility
-
-Visit the [online documentation](https://dbworkload.github.io/dbworkload/).
-