sqlite2duckdb 0.3.0__tar.gz

sqlite2duckdb-0.3.0/.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

sqlite2duckdb-0.3.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 sacha schutz
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

sqlite2duckdb-0.3.0/Makefile

@@ -0,0 +1,12 @@
+
+run:
+	python -m sqlite2duckdb 
+	
+build:
+	rm -Rf dist/ ; python -m build
+
+test:
+	python -m pytest
+
+publish:
+	python -m twine upload  dist/*

sqlite2duckdb-0.3.0/PKG-INFO

@@ -0,0 +1,74 @@
+Metadata-Version: 2.3
+Name: sqlite2duckdb
+Version: 0.3.0
+Summary: A tool to convert sqlite database to duckdb database
+Project-URL: Homepage, https://github.com/dridk/sqlite2duckdb
+Project-URL: Issues, https://github.com/dridk/sqlite2duckdb/issues
+Author-email: Sacha Schutz <sacha.schutz@pm.me>
+License-File: LICENSE
+Keywords: database,duckdb,olap,oltp,sqlite
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Dist: duckdb>=0.10.0
+Description-Content-Type: text/markdown
+
+# sqlite2duckdb
+
+![PyPI - Python Version](https://img.shields.io/pypi/pyversions/sqlite2duckdb)
+![PyPI - Downloads](https://img.shields.io/pypi/dm/cutevariant)
+
+A tool for converting a [sqlite](https://www.sqlite.org/) database into a [duckdb](https://duckdb.org/) database
+
+
+## Description 
+
+Sqlite is an embedded online database designed for transactional reading and writing.
+Duckdb is also an embedded database, but column-oriented, designed for analytical process with a very high reading efficiency.
+See [https://towardsdatascience.com/forget-about-sqlite-use-duckdb-instead-and-thank-me-later-df76ee9bb777](https://towardsdatascience.com/forget-about-sqlite-use-duckdb-instead-and-thank-me-later-df76ee9bb777)
+
+
+## Installation 
+
+```
+pip install sqlite2duckdb
+```
+
+## Usage 
+
+### As a command line 
+
+```
+
+usage: sqlite2duckdb <sqlite_path> <duckdb_path>
+
+Convert Sqlite database to Duckdb database
+
+positional arguments:
+  sqlite_path    sqlite file path
+  duckdb_path    duckdb file path
+
+options:
+  -h, --help     show this help message and exit
+  -v, --version  show program's version number and exit
+
+
+```
+
+### Examples 
+
+```bash
+sqlite2duckdb source.db target.db
+```
+
+### From python 
+
+```python
+
+from sqlite2duckdb  import sqlite_to_duckdb
+sqlite_to_duckdb("source.sqlite", "target.duckdb")
+
+```
+
+
+

sqlite2duckdb-0.3.0/README.md

@@ -0,0 +1,59 @@
+# sqlite2duckdb
+
+![PyPI - Python Version](https://img.shields.io/pypi/pyversions/sqlite2duckdb)
+![PyPI - Downloads](https://img.shields.io/pypi/dm/cutevariant)
+
+A tool for converting a [sqlite](https://www.sqlite.org/) database into a [duckdb](https://duckdb.org/) database
+
+
+## Description 
+
+Sqlite is an embedded online database designed for transactional reading and writing.
+Duckdb is also an embedded database, but column-oriented, designed for analytical process with a very high reading efficiency.
+See [https://towardsdatascience.com/forget-about-sqlite-use-duckdb-instead-and-thank-me-later-df76ee9bb777](https://towardsdatascience.com/forget-about-sqlite-use-duckdb-instead-and-thank-me-later-df76ee9bb777)
+
+
+## Installation 
+
+```
+pip install sqlite2duckdb
+```
+
+## Usage 
+
+### As a command line 
+
+```
+
+usage: sqlite2duckdb <sqlite_path> <duckdb_path>
+
+Convert Sqlite database to Duckdb database
+
+positional arguments:
+  sqlite_path    sqlite file path
+  duckdb_path    duckdb file path
+
+options:
+  -h, --help     show this help message and exit
+  -v, --version  show program's version number and exit
+
+
+```
+
+### Examples 
+
+```bash
+sqlite2duckdb source.db target.db
+```
+
+### From python 
+
+```python
+
+from sqlite2duckdb  import sqlite_to_duckdb
+sqlite_to_duckdb("source.sqlite", "target.duckdb")
+
+```
+
+
+

sqlite2duckdb-0.3.0/pyproject.toml

@@ -0,0 +1,29 @@
+[build-system]
+requires = ["hatchling", "build", "twine"]
+build-backend = "hatchling.build"
+
+
+[project]
+name = "sqlite2duckdb"
+version = "0.3.0"
+authors = [{name="Sacha Schutz", email="sacha.schutz@pm.me"}]
+description = "A tool to convert sqlite database to duckdb database"
+readme = "README.md"
+requres-python = ">=3.8"
+keywords = ["sqlite", "duckdb", "database", "olap", "oltp"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    'duckdb >= 0.10.0'
+]
+
+
+[project.urls]
+Homepage = "https://github.com/dridk/sqlite2duckdb"
+Issues = "https://github.com/dridk/sqlite2duckdb/issues"
+
+[project.scripts]
+sqlite2duckdb = "sqlite2duckdb.__main__:main_cli"

sqlite2duckdb-0.3.0/requirements.txt

@@ -0,0 +1 @@
+duckdb

sqlite2duckdb-0.3.0/sqlite2duckdb/__init__.py

@@ -0,0 +1,4 @@
+import importlib.metadata
+from sqlite2duckdb.sqlite_to_duckdb import sqlite_to_duckdb
+
+__VERSION__ = importlib.metadata.version("sqlite2duckdb")

sqlite2duckdb-0.3.0/sqlite2duckdb/__main__.py

@@ -0,0 +1,38 @@
+import duckdb
+import argparse
+import os
+from sqlite2duckdb import sqlite_to_duckdb, __VERSION__
+
+
+def main_cli():
+    parser = argparse.ArgumentParser(
+        description="Convert Sqlite database to Duckdb database",
+        usage="sqlite2duckdb <sqlite_path> <duckdb_path>",
+    )
+
+    parser.add_argument("sqlite_path", type=str, help="sqlite file path")
+    parser.add_argument("duckdb_path", type=str, help="duckdb file path")
+    parser.add_argument(
+        "-v", "--version", action="version", version=f"sqlite2duckdb {__VERSION__}"
+    )
+
+    # Analyser les arguments
+    args = parser.parse_args()
+
+    if os.path.exists(args.duckdb_path):
+        delete_input = (
+            input(
+                f"{args.duckdb_path} already exists. do you want to delete this file ? (yes/no): "
+            )
+            .strip()
+            .lower()
+        )
+        if delete_input in ("yes", "y"):
+            os.remove(args.duckdb_path)
+        else:
+            exit(1)
+    sqlite_to_duckdb(args.sqlite_path, args.duckdb_path)
+
+
+if __name__ == "__main__":
+    main_cli()

sqlite2duckdb-0.3.0/sqlite2duckdb/sqlite_to_duckdb.py

@@ -0,0 +1,47 @@
+import duckdb
+import os
+import sqlite3
+import time
+
+
+def sqlite_to_duckdb(sqlite_db: str, duck_db: str):
+    print(f"Create {duck_db} databases")
+
+    if not os.path.exists(sqlite_db):
+        raise Exception(f"File {sqlite_db} doesn't exists")
+
+    # Remove target db if exists
+    if os.path.exists(duck_db):
+        raise Exception(f"Database {duck_db} already exists")
+
+    # Create databases
+
+    start_time = time.perf_counter()
+    conn = duckdb.connect(duck_db)
+    db_name = conn.sql("SELECT database_name FROM duckdb_databases").fetchone()[0]
+
+    ## Install sqlite
+    conn.sql(
+        f"""
+    INSTALL sqlite;
+    LOAD sqlite;
+    ATTACH '{sqlite_db}' as __other;
+    """
+    )
+
+    ## Get sqlite Names
+    conn.sql("USE __other")
+    tables = [i[0] for i in conn.sql("SHOW tables").fetchall()]
+    print(f"{len(tables)} tables found(s)")
+    conn.sql(f"USE {db_name}")
+
+    # Create tables
+    for table in tables:
+        print(f"Create duckdb table {table}")
+        conn.sql(f"CREATE TABLE {table} AS select * FROM __other.{table}")
+
+    conn.sql(f"DETACH __other")
+    conn.close()
+    end_time = time.perf_counter()
+    execution_time = (end_time - start_time) * 1000
+    print(f"Done in {execution_time:.2f} ms !")

sqlite2duckdb-0.3.0/tests/test_convert.py

@@ -0,0 +1,20 @@
+import sqlite3 
+import duckdb 
+from tests import utils
+import os 
+
+from sqlite2duckdb.__main__ import sqlite_to_duckdb
+
+def test_conversion():
+
+	duckdb_path = utils.generate_fake_duckdb()
+	sqlite_path = utils.generate_fake_sqlite()
+
+	sqlite_to_duckdb(sqlite_path, duckdb_path)
+
+	
+	
+
+	
+	
+	

sqlite2duckdb-0.3.0/tests/utils.py

@@ -0,0 +1,68 @@
+
+import sqlite3
+import random
+import datetime
+import tempfile
+from faker import Faker
+import os 
+
+def generate_fake_duckdb():
+	filename =  tempfile.mkstemp(prefix="sqlite2duckdb_duck", suffix=".duckdb")[1]
+	if os.path.exists(filename):
+		os.remove(filename)
+
+	return filename
+
+def generate_fake_sqlite():
+	
+	temp_file_path = tempfile.mkstemp(prefix="sqlite2duckdb", suffix=".sqlite")[1]
+	print(f"Create temp sqlite db at {temp_file_path}")
+	fake = Faker()
+
+	conn = sqlite3.connect(temp_file_path)
+	cursor = conn.cursor()
+
+	# Create sqlite database 
+	cursor.execute('''
+	    CREATE TABLE IF NOT EXISTS data (
+	        id INTEGER PRIMARY KEY,
+	        integer_col INTEGER,
+	        real_col REAL,
+	        text_col TEXT,
+	        boolean_col BOOLEAN,
+	        date_col DATE,
+	        time_col TIME,
+	        datetime_col DATETIME,
+	        blob_col BLOB,
+	        numeric_col NUMERIC,
+	        null_col NULL
+	    )
+	''')
+
+	# Generate fake data 
+	def generate_fake_data():
+	    integer_col = random.randint(1, 1000)
+	    real_col = random.uniform(1.0, 1000.0)
+	    text_col = fake.text(max_nb_chars=20)
+	    boolean_col = random.choice([True, False])
+	    date_col = fake.date()
+	    time_col = fake.date_time()
+	    datetime_col = fake.date_time()
+	    blob_col = fake.binary(length=10)
+	    numeric_col = random.choice([integer_col, real_col])
+	    null_col = None
+	    return (integer_col, real_col, text_col, boolean_col, date_col, time_col, datetime_col, blob_col, numeric_col, null_col)
+
+
+	for _ in range(1000):
+
+	    cursor.execute('''
+	        INSERT INTO data (integer_col, real_col, text_col, boolean_col, date_col, time_col, datetime_col, blob_col, numeric_col, null_col)
+	        VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+	    ''', generate_fake_data())
+
+	# Sauvegarde (commit) des changements et fermeture de la connexion
+	conn.commit()
+	conn.close()
+
+	return temp_file_path