sqlframe 0.1.dev3__tar.gz → 1.1.0__tar.gz

sqlframe-1.1.0/.github/CODEOWNERS

@@ -0,0 +1 @@
+*       @eakmanrq

sqlframe-1.1.0/.github/workflows/main.workflow.yaml

@@ -0,0 +1,42 @@
+name: SQLFrame
+on:
+  push:
+    branches:
+    - main
+    paths:
+      - 'sqlframe/**'
+      - 'tests/**'
+      - 'Makefile'
+      - 'setup.py'
+  pull_request:
+    types:
+    - synchronize
+    - opened
+    paths:
+    - 'sqlframe/**'
+    - 'tests/**'
+    - 'Makefile'
+    - 'setup.py'
+jobs:
+  run-tests:
+    runs-on: ubuntu-latest
+    env:
+      PYTEST_XDIST_AUTO_NUM_WORKERS: 4
+    strategy:
+      matrix:
+        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+    - name: Install Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: make install-dev
+    - name: Run Style
+      run: make style
+    - name: Setup Postgres
+      uses: ikalnytskyi/action-setup-postgres@v6
+    - name: Run tests
+      run: make local-test

sqlframe-1.1.0/.github/workflows/publish.workflow.yaml

@@ -0,0 +1,27 @@
+name: Publish
+on:
+  push:
+    tags:
+      - 'v[0-9]+.[0-9]+.[0-9]+'
+permissions:
+  contents: write
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    env:
+      TWINE_USERNAME: ${{ secrets.TWINE_USERNAME }}
+      TWINE_PASSWORD: ${{ secrets.TWINE_PASSWORD }}
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+    - name: Publish
+      run: make publish
+    - name: Create release
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        tag: ${{ github.ref_name }}
+      run: |
+        gh release create "$tag" \
+            --repo="$GITHUB_REPOSITORY" \
+            --title="SQLFrame ${tag#v}" \
+            --generate-notes

sqlframe-1.1.0/.readthedocs.yaml

@@ -0,0 +1,13 @@
+version: 2
+
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.8"
+
+mkdocs:
+  configuration: mkdocs.yml
+
+python:
+   install:
+   - requirements: docs/requirements.txt

{sqlframe-0.1.dev3 → sqlframe-1.1.0}/Makefile

@@ -1,5 +1,5 @@
 install-dev:
-	pip install -e ".[dev]"
+	pip install -e ".[dev,duckdb,postgres,redshift,bigquery,snowflake,spark]"
 
 install-pre-commit:
 	pre-commit install
@@ -8,10 +8,10 @@ slow-test:
 	pytest -n auto tests
 
 fast-test:
-	pytest -n auto tests/unit
+	pytest -n auto -m "fast"
 
 local-test:
-	pytest -n auto -m "local"
+	pytest -n auto -m "fast or local"
 
 bigquery-test:
 	pytest -n auto -m "bigquery"

{sqlframe-0.1.dev3 → sqlframe-1.1.0}/PKG-INFO

@@ -1,11 +1,12 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 0.1.dev3
-Summary: PySpark Dataframe API Compatible SQL Generator
+Version: 1.1.0
+Summary: Taking the Spark out of PySpark by converting to SQL
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman
 Author-email: eakmanrq@gmail.com
 License: MIT
+Platform: UNKNOWN
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
@@ -15,61 +16,30 @@ Classifier: Programming Language :: SQL
 Classifier: Programming Language :: Python :: 3 :: Only
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: prettytable
-Requires-Dist: sqlglot
 Provides-Extra: bigquery
-Requires-Dist: google-cloud-bigquery[pandas]; extra == "bigquery"
-Requires-Dist: google-cloud-bigquery-storage; extra == "bigquery"
 Provides-Extra: dev
-Requires-Dist: duckdb; extra == "dev"
-Requires-Dist: mkdocs==1.4.2; extra == "dev"
-Requires-Dist: mkdocs-include-markdown-plugin==4.0.3; extra == "dev"
-Requires-Dist: mkdocs-material==9.0.5; extra == "dev"
-Requires-Dist: mkdocs-material-extensions==1.1.1; extra == "dev"
-Requires-Dist: mypy; extra == "dev"
-Requires-Dist: pandas; extra == "dev"
-Requires-Dist: pymdown-extensions; extra == "dev"
-Requires-Dist: psycopg; extra == "dev"
-Requires-Dist: pyarrow; extra == "dev"
-Requires-Dist: pyspark; extra == "dev"
-Requires-Dist: pytest; extra == "dev"
-Requires-Dist: pytest-postgresql; extra == "dev"
-Requires-Dist: pytest-xdist; extra == "dev"
-Requires-Dist: pre-commit; extra == "dev"
-Requires-Dist: ruff; extra == "dev"
-Requires-Dist: typing_extensions; extra == "dev"
-Requires-Dist: types-psycopg2; extra == "dev"
+Provides-Extra: docs
 Provides-Extra: duckdb
-Requires-Dist: duckdb; extra == "duckdb"
-Requires-Dist: pandas; extra == "duckdb"
 Provides-Extra: postgres
-Requires-Dist: psycopg2; extra == "postgres"
 Provides-Extra: redshift
-Requires-Dist: redshift_connector; extra == "redshift"
 Provides-Extra: snowflake
-Requires-Dist: snowflake-connector-python[pandas,secure-local-storage]; extra == "snowflake"
 Provides-Extra: spark
-Requires-Dist: pyspark; extra == "spark"
+License-File: LICENSE
 
 <div align="center">
-  <img src="docs/images/sqlframe_logo.png" alt="SQLFrame Logo" width="400"/>
+  <img src="https://sqlframe.readthedocs.io/en/latest/docs/images/sqlframe_logo.png" alt="SQLFrame Logo" width="400"/>
 </div>
 
-![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)
-
 SQLFrame implements the PySpark DataFrame API in order to enable running transformation pipelines directly on database engines - no Spark clusters or dependencies required.
 
-![SQLFrame Diagram](docs/images/sqlframe_diagram.png)
+SQLFrame currently supports the following engines (many more in development):
 
-SQLFrame currently supports the following engines:
-
-* [BigQuery](docs/bigquery.md)
-* [DuckDB](docs/duckdb.md)
-* [Postgres](docs/postgres.md)
+* [BigQuery](https://sqlframe.readthedocs.io/en/latest/bigquery/)
+* [DuckDB](https://sqlframe.readthedocs.io/en/latest/duckdb)
+* [Postgres](https://sqlframe.readthedocs.io/en/latest/postgres)
 
 SQLFrame also has a "Standalone" session that be used to generate SQL without any connection to a database engine.
-* [Standalone](docs/standalone.md)
+* [Standalone](https://sqlframe.readthedocs.io/en/latest/standalone)
 
 SQLFrame is great for:
 
@@ -101,7 +71,7 @@ from sqlframe.bigquery import Window
 
 session = BigQuerySession()
 table_path = "bigquery-public-data.samples.natality"
-# Get the top 5 years with the greatest year-over-year % change in new families with a single child
+# Top 5 years with the greatest year-over-year % change in new families with single child
 df = (
     session.table(table_path)
     .where(F.col("ever_born") == 1)
@@ -118,17 +88,15 @@ df = (
     )
     .orderBy(F.abs(F.col("percent_change")).desc())
     .select(
-        F.col("year").alias("Year"),
-        F.format_number("num_single_child_families", 0).alias("number of new families single child"),
+        F.col("year").alias("year"),
+        F.format_number("num_single_child_families", 0).alias("new families single child"),
         F.format_number(F.col("percent_change") * 100, 2).alias("percent change"),
     )
     .limit(5)
 )
 ```
 ```python
-df.sql()
-```
-```sql
+>>> df.sql()
 WITH `t94228` AS (
   SELECT
     `natality`.`year` AS `year`,
@@ -147,7 +115,7 @@ WITH `t94228` AS (
 )
 SELECT
   `t39093`.`year` AS `year`,
-  FORMAT('%\'.0f', ROUND(CAST(`t39093`.`num_single_child_families` AS FLOAT64), 0)) AS `number of new families single child`,
+  FORMAT('%\'.0f', ROUND(CAST(`t39093`.`num_single_child_families` AS FLOAT64), 0)) AS `new families single child`,
   FORMAT('%\'.2f', ROUND(CAST((((`t39093`.`num_single_child_families` - `t39093`.`last_year_num_single_child_families`) / `t39093`.`last_year_num_single_child_families`) * 100) AS FLOAT64), 2)) AS `percent change`
 FROM `t39093` AS `t39093`
 ORDER BY
@@ -155,16 +123,16 @@ ORDER BY
 LIMIT 5
 ```
 ```python
-df.show()
-```
-```
-+------+-------------------------------------+----------------+
-| year | number of new families single child | percent change |
-+------+-------------------------------------+----------------+
-| 1989 |              1,650,246              |     25.02      |
-| 1974 |               783,448               |     14.49      |
-| 1977 |              1,057,379              |     11.38      |
-| 1985 |              1,308,476              |     11.15      |
-| 1975 |               868,985               |     10.92      |
-+------+-------------------------------------+----------------+
+>>> df.show()
++------+---------------------------+----------------+
+| year | new families single child | percent change |
++------+---------------------------+----------------+
+| 1989 |         1,650,246         |     25.02      |
+| 1974 |          783,448          |     14.49      |
+| 1977 |         1,057,379         |     11.38      |
+| 1985 |         1,308,476         |     11.15      |
+| 1975 |          868,985          |     10.92      |
++------+---------------------------+----------------+
 ```
+
+

{sqlframe-0.1.dev3 → sqlframe-1.1.0}/README.md

@@ -1,21 +1,17 @@
 <div align="center">
-  <img src="docs/images/sqlframe_logo.png" alt="SQLFrame Logo" width="400"/>
+  <img src="https://sqlframe.readthedocs.io/en/latest/docs/images/sqlframe_logo.png" alt="SQLFrame Logo" width="400"/>
 </div>
 
-![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)
-
 SQLFrame implements the PySpark DataFrame API in order to enable running transformation pipelines directly on database engines - no Spark clusters or dependencies required.
 
-![SQLFrame Diagram](docs/images/sqlframe_diagram.png)
-
-SQLFrame currently supports the following engines:
+SQLFrame currently supports the following engines (many more in development):
 
-* [BigQuery](docs/bigquery.md)
-* [DuckDB](docs/duckdb.md)
-* [Postgres](docs/postgres.md)
+* [BigQuery](https://sqlframe.readthedocs.io/en/latest/bigquery/)
+* [DuckDB](https://sqlframe.readthedocs.io/en/latest/duckdb)
+* [Postgres](https://sqlframe.readthedocs.io/en/latest/postgres)
 
 SQLFrame also has a "Standalone" session that be used to generate SQL without any connection to a database engine.
-* [Standalone](docs/standalone.md)
+* [Standalone](https://sqlframe.readthedocs.io/en/latest/standalone)
 
 SQLFrame is great for:
 
@@ -47,7 +43,7 @@ from sqlframe.bigquery import Window
 
 session = BigQuerySession()
 table_path = "bigquery-public-data.samples.natality"
-# Get the top 5 years with the greatest year-over-year % change in new families with a single child
+# Top 5 years with the greatest year-over-year % change in new families with single child
 df = (
     session.table(table_path)
     .where(F.col("ever_born") == 1)
@@ -64,17 +60,15 @@ df = (
     )
     .orderBy(F.abs(F.col("percent_change")).desc())
     .select(
-        F.col("year").alias("Year"),
-        F.format_number("num_single_child_families", 0).alias("number of new families single child"),
+        F.col("year").alias("year"),
+        F.format_number("num_single_child_families", 0).alias("new families single child"),
         F.format_number(F.col("percent_change") * 100, 2).alias("percent change"),
     )
     .limit(5)
 )
 ```
 ```python
-df.sql()
-```
-```sql
+>>> df.sql()
 WITH `t94228` AS (
   SELECT
     `natality`.`year` AS `year`,
@@ -93,7 +87,7 @@ WITH `t94228` AS (
 )
 SELECT
   `t39093`.`year` AS `year`,
-  FORMAT('%\'.0f', ROUND(CAST(`t39093`.`num_single_child_families` AS FLOAT64), 0)) AS `number of new families single child`,
+  FORMAT('%\'.0f', ROUND(CAST(`t39093`.`num_single_child_families` AS FLOAT64), 0)) AS `new families single child`,
   FORMAT('%\'.2f', ROUND(CAST((((`t39093`.`num_single_child_families` - `t39093`.`last_year_num_single_child_families`) / `t39093`.`last_year_num_single_child_families`) * 100) AS FLOAT64), 2)) AS `percent change`
 FROM `t39093` AS `t39093`
 ORDER BY
@@ -101,16 +95,14 @@ ORDER BY
 LIMIT 5
 ```
 ```python
-df.show()
-```
-```
-+------+-------------------------------------+----------------+
-| year | number of new families single child | percent change |
-+------+-------------------------------------+----------------+
-| 1989 |              1,650,246              |     25.02      |
-| 1974 |               783,448               |     14.49      |
-| 1977 |              1,057,379              |     11.38      |
-| 1985 |              1,308,476              |     11.15      |
-| 1975 |               868,985               |     10.92      |
-+------+-------------------------------------+----------------+
+>>> df.show()
++------+---------------------------+----------------+
+| year | new families single child | percent change |
++------+---------------------------+----------------+
+| 1989 |         1,650,246         |     25.02      |
+| 1974 |          783,448          |     14.49      |
+| 1977 |         1,057,379         |     11.38      |
+| 1985 |         1,308,476         |     11.15      |
+| 1975 |          868,985          |     10.92      |
++------+---------------------------+----------------+
 ```

{sqlframe-0.1.dev3 → sqlframe-1.1.0}/blogs/sqlframe_universal_dataframe_api.md

@@ -9,7 +9,8 @@ SQL is the universal language that unites all data professionals, and it enables
 Despite its strengths, SQL often seems ill-suited for maintaining data pipelines.
 The language lacks support for abstracting common operations or unit testing specific segments of code, leading many to use Jinja as a makeshift solution. 
 Jinja SQL is to SQL what Pig Latin is to English - can be fun in small doses but impossible to understand at scale. 
-Moreover, SQL's repetitive nature, requiring columns to be repeated across operations, leads to fatigue and many data practitioners responding to the siren song of `SELECT *` and later found drowning in the sea of non-determinism.
+Furthermore, the repetitive nature of SQL, where columns must be specified repeatedly across operations, often leads to fatigue among data professionals. 
+This results in data professionals responding to the siren song of `SELECT *`, only to be later found drowning in the sea of non-determinism.
 
 This has put data professionals in a tough spot: Do you write your pipelines in SQL to favor accessibility or Python to favor maintainability? 
 Well, starting today, you no longer have to choose. 
@@ -25,7 +26,7 @@ You can finally have your cake and eat it too.
   <img src="../docs/images/sqlframe_logo.png" alt="SQLFrame Logo" width="800"/>
 </div>
 
-SQLFrame revolutionizes how data professionals interact with SQL and PySpark DataFrames. 
+[SQLFrame](https://github.com/eakmanrq/sqlframe) revolutionizes how data professionals interact with SQL and PySpark DataFrames. 
 Unlike traditional PySpark, SQLFrame converts DataFrame operations directly into SQL, enabling real-time SQL script generation during development. 
 Here's how it works:
 
@@ -133,7 +134,7 @@ Therefore not only does SQLFrame make your DataFrame pipeline more accessible, i
   <img src="images/you_get_pyspark_api.gif" alt="There is more" width="800"/>
 </div>
 
-SQLFrame currently supports BigQuery, DuckDB, and PostgreSQL, with Redshift, Snowflake, Spark, and Trino in development. 
-For those interested in experimenting with SQL generation for other engines, the "StandaloneSession" provides a flexible testing ground.
+SQLFrame currently supports [BigQuery](https://sqlframe.readthedocs.io/en/stable/bigquery/), [DuckDB](https://sqlframe.readthedocs.io/en/stable/duckdb/), and [Postgres](https://sqlframe.readthedocs.io/en/stable/postgres/), with Redshift, Snowflake, Spark, and Trino in development. 
+For those interested in experimenting with SQL generation for other engines, the [StandaloneSession](https://sqlframe.readthedocs.io/en/stable/standalone/) provides a flexible testing ground.
 
-Follow the simple setup guide to begin integrating SQLFrame into your projects today!
+Checkout the [README](https://github.com/eakmanrq/sqlframe) for more information on how to get started with SQLFrame!

{sqlframe-0.1.dev3/docs → sqlframe-1.1.0}/docs/bigquery.md

@@ -60,27 +60,34 @@ print(session.catalog.listColumns(table_path))
     .where(F.col("ever_born") == 1)
     .groupBy("year")
     .agg(F.count("*").alias("num_single_child_families"))
-    .withColumn("last_year_num_single_child_families", F.lag(F.col("num_single_child_families"), 1).over(Window.orderBy("year")))
-    .withColumn("percent_change", (F.col("num_single_child_families") - F.col("last_year_num_single_child_families")) / F.col("last_year_num_single_child_families"))
+    .withColumn(
+      "last_year_num_single_child_families", 
+      F.lag(F.col("num_single_child_families"), 1).over(Window.orderBy("year"))
+    )
+    .withColumn(
+      "percent_change", 
+      (F.col("num_single_child_families") - F.col("last_year_num_single_child_families")) 
+      / F.col("last_year_num_single_child_families")
+    )
     .orderBy(F.abs(F.col("percent_change")).desc())
     .select(
-        F.col("year").alias("Year"),
-        F.format_number("num_single_child_families", 0).alias("number of new families single child"),
+        F.col("year").alias("year"),
+        F.format_number("num_single_child_families", 0).alias("new families single child"),
         F.format_number(F.col("percent_change") * 100, 2).alias("percent change"),
     )
     .limit(5)
     .show()
 )
 """
-+------+-------------------------------------+----------------+
-| year | number of new families single child | percent change |
-+------+-------------------------------------+----------------+
-| 1989 |              1,650,246              |     25.02      |
-| 1974 |               783,448               |     14.49      |
-| 1977 |              1,057,379              |     11.38      |
-| 1985 |              1,308,476              |     11.15      |
-| 1975 |               868,985               |     10.92      |
-+------+-------------------------------------+----------------+
++------+---------------------------+----------------+
+| year | new families single child | percent change |
++------+---------------------------+----------------+
+| 1989 |         1,650,246         |     25.02      |
+| 1974 |          783,448          |     14.49      |
+| 1977 |         1,057,379         |     11.38      |
+| 1985 |         1,308,476         |     11.15      |
+| 1975 |          868,985          |     10.92      |
++------+---------------------------+----------------+
 """
 ```
 

sqlframe-1.1.0/docs/requirements.txt

@@ -0,0 +1,6 @@
+mkdocs==1.4.2
+mkdocs-include-markdown-plugin==4.0.3
+mkdocs-material==9.0.5
+mkdocs-material-extensions==1.1.1
+mkdocs-glightbox==0.3.7
+pymdown-extensions

{sqlframe-0.1.dev3 → sqlframe-1.1.0}/mkdocs.yml

@@ -32,6 +32,8 @@ theme:
     - navigation.tracking
     - navigation.tabs
     - navigation.sections
+    - toc.integrate
+    - toc.follow
 plugins:
   - include-markdown
   - search

sqlframe-1.1.0/pytest.ini

@@ -0,0 +1,7 @@
+[pytest]
+markers =
+    bigquery: test for BigQuery
+    duckdb: test for DuckDB
+    local: test that don't rely on external connections
+    postgres: test for Postgres
+addopts = -n 0 --dist=loadgroup

sqlframe-1.1.0/renovate.json

@@ -0,0 +1,17 @@
+{
+  "$schema": "https://docs.renovatebot.com/renovate-schema.json",
+  "rangeStrategy": "widen",
+  "extends": [
+    "config:recommended"
+  ],
+  "ignoreDeps": [
+    "mkdocs-include-markdown-plugin",
+    "mkdocs",
+    "mkdocs-material",
+    "mkdocs-material-extensions",
+    "mkdocs-include-markdown-plugin"
+  ],
+  "ignorePaths": [
+    "docs/**"
+  ]
+}

{sqlframe-0.1.dev3 → sqlframe-1.1.0}/setup.py

@@ -2,7 +2,7 @@ from setuptools import find_packages, setup
 
 setup(
     name="sqlframe",
-    description="PySpark Dataframe API Compatible SQL Generator",
+    description="Taking the Spark out of PySpark by converting to SQL",
     long_description=open("README.md").read(),
     long_description_content_type="text/markdown",
     url="https://github.com/eakmanrq/sqlframe",
@@ -19,49 +19,57 @@ setup(
     setup_requires=["setuptools_scm"],
     python_requires=">=3.8",
     install_requires=[
-        "prettytable",
-        "sqlglot",
+        "prettytable<3.11.0",
+        "sqlglot>=24.0.0,<24.1",
     ],
     extras_require={
         "bigquery": [
-            "google-cloud-bigquery[pandas]",
-            "google-cloud-bigquery-storage",
+            "google-cloud-bigquery[pandas]>=3,<4",
+            "google-cloud-bigquery-storage>=2,<3",
+            "pandas>=2,<3",
         ],
         "dev": [
-            "duckdb",
+            "duckdb>=0.9,<0.11",
+            "mypy>=1.10.0,<1.11",
+            "pandas>=2,<3",
+            "pandas-stubs>=2,<3",
+            "psycopg>=3.1,<4",
+            "pyarrow>=10,<17",
+            "pyspark>=2,<3.6",
+            "pytest>=8.2.0,<8.3",
+            "pytest-postgresql>=6,<7",
+            "pytest-xdist>=3.6,<3.7",
+            "pre-commit>=3.5;python_version=='3.8'",
+            "pre-commit>=3.7,<3.8;python_version>='3.9'",
+            "ruff>=0.4.4,<0.5",
+            "typing_extensions>=4.11,<5",
+            "types-psycopg2>=2.9,<3",
+        ],
+        "docs": [
             "mkdocs==1.4.2",
             "mkdocs-include-markdown-plugin==4.0.3",
             "mkdocs-material==9.0.5",
             "mkdocs-material-extensions==1.1.1",
-            "mypy",
-            "pandas",
             "pymdown-extensions",
-            "psycopg",
-            "pyarrow",
-            "pyspark",
-            "pytest",
-            "pytest-postgresql",
-            "pytest-xdist",
-            "pre-commit",
-            "ruff",
-            "typing_extensions",
-            "types-psycopg2",
         ],
         "duckdb": [
-            "duckdb",
-            "pandas",
+            "duckdb>=0.9,<0.11",
+            "pandas>=2,<3",
         ],
         "postgres": [
-            "psycopg2",
+            "pandas>=2,<3",
+            "psycopg2>=2.8,<3",
         ],
         "redshift": [
-            "redshift_connector",
+            "pandas>=2,<3",
+            "redshift_connector>=2.1.1,<2.2.0",
         ],
         "snowflake": [
-            "snowflake-connector-python[pandas,secure-local-storage]",
+            "pandas>=2,<3",
+            "snowflake-connector-python[pandas,secure-local-storage]>=3.10.0,<3.11",
         ],
         "spark": [
-            "pyspark",
+            "pyspark>=2,<3.6",
         ],
     },
     classifiers=[

{sqlframe-0.1.dev3 → sqlframe-1.1.0}/sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.1.dev3'
-__version_tuple__ = version_tuple = (0, 1, 'dev3')
+__version__ = version = '1.1.0'
+__version_tuple__ = version_tuple = (1, 1, 0)

{sqlframe-0.1.dev3 → sqlframe-1.1.0}/sqlframe/base/catalog.py

@@ -8,7 +8,7 @@ from sqlglot import MappingSchema, exp
 
 from sqlframe.base.decorators import normalize
 from sqlframe.base.exceptions import TableSchemaError
-from sqlframe.base.util import to_schema
+from sqlframe.base.util import ensure_column_mapping, to_schema
 
 if t.TYPE_CHECKING:
     from sqlglot.schema import ColumnMapping
@@ -82,6 +82,7 @@ class _BaseCatalog(t.Generic[SESSION, DF]):
                 raise TableSchemaError(
                     "This session does not have access to a catalog that can lookup column information. See docs for explicitly defining columns or using a session that can automatically determine this."
                 )
+        column_mapping = ensure_column_mapping(column_mapping)  # type: ignore
         self._schema.add_table(table, column_mapping, dialect=self.session.input_dialect)
 
     @normalize(["dbName"])

{sqlframe-0.1.dev3 → sqlframe-1.1.0}/sqlframe/base/dataframe.py

@@ -417,7 +417,7 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         from sqlframe.base.session import _BaseSession
 
         value = expression.sql(dialect=_BaseSession().input_dialect).encode("utf-8")
-        hash = f"t{zlib.crc32(value)}"[:6]
+        hash = f"t{zlib.crc32(value)}"[:9]
         return self.session._normalize_string(hash)
 
     def _get_select_expressions(
@@ -606,8 +606,11 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         return df._convert_leaf_to_cte(sequence_id=new_sequence_id)
 
     @operation(Operation.WHERE)
-    def where(self, column: t.Union[Column, bool], **kwargs) -> Self:
-        col = self._ensure_and_normalize_col(column)
+    def where(self, column: t.Union[Column, str, bool], **kwargs) -> Self:
+        if isinstance(column, str):
+            col = sqlglot.parse_one(column, dialect=self.session.input_dialect)
+        else:
+            col = self._ensure_and_normalize_col(column)
         return self.copy(expression=self.expression.where(col.expression))
 
     filter = where
@@ -662,7 +665,7 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         | 16|  Bob|    85|
         +---+-----+------+
         """
-        return self.join.__wrapped__(self, other, how="cross")
+        return self.join.__wrapped__(self, other, how="cross")  # type: ignore
 
     @operation(Operation.FROM)
     def join(
@@ -769,7 +772,7 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         new_df = self.copy(expression=join_expression)
         new_df.pending_join_hints.extend(self.pending_join_hints)
         new_df.pending_hints.extend(other_df.pending_hints)
-        new_df = new_df.select.__wrapped__(new_df, *select_column_names)
+        new_df = new_df.select.__wrapped__(new_df, *select_column_names)  # type: ignore
         return new_df
 
     @operation(Operation.ORDER_BY)
@@ -1094,7 +1097,7 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         )
         if existing_col_index:
             expression = self.expression.copy()
-            expression.expressions[existing_col_index] = col.expression
+            expression.expressions[existing_col_index] = col.alias(colName).expression
             return self.copy(expression=expression)
         return self.copy().select(col.alias(colName), append=True)