laketower 0.6.1__tar.gz → 0.6.3__tar.gz

{laketower-0.6.1 → laketower-0.6.3}/.github/workflows/ci-cd.yml

@@ -18,7 +18,7 @@ jobs:
     steps:
       - uses: actions/checkout@v5
       - name: Install uv
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: ${{ matrix.python-version }}
           enable-cache: true
@@ -52,7 +52,7 @@ jobs:
           ref: main
       - uses: actions/checkout@v5
       - name: Install uv
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: "3.13"
           enable-cache: true
@@ -126,7 +126,7 @@ jobs:
     steps:
       - uses: actions/checkout@v5
       - name: Install uv
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: '3.13'
           enable-cache: true
@@ -187,7 +187,7 @@ jobs:
       - name: Publish package distributions to PyPI
         uses: pypa/gh-action-pypi-publish@release/v1
       - name: Install uv
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
       - name: Validate package is available with uvx
         run: uvx laketower --version
 
@@ -209,7 +209,7 @@ jobs:
           name: build
           path: dist/
       - name: Install uv
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: '3.13'
           enable-cache: true

{laketower-0.6.1 → laketower-0.6.3}/.gitignore

@@ -14,4 +14,7 @@ node_modules/
 .venv
 
 # IDEs
-.vscode
+.vscode
+
+# OS
+.DS_Store

{laketower-0.6.1 → laketower-0.6.3}/CHANGELOG.md

@@ -7,6 +7,24 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.6.3] - 2025-10-19
+Patch release removing unnecessary `pandas` dependency and updating the displayed
+application name in the web application.
+
+### Fixed
+- web: update application name
+- web: move application details to about modal window
+
+### Misc
+- replace usage of `pandas.DataFrame` with `pyarrow.Table`
+
+## [0.6.2] - 2025-09-28
+Patch release fixing a bug when registering Arrow Datasets as tables instead of
+views with DuckDB query engine, leading to performance degradation on larger tables.
+
+### Fixed
+- map arrow datasets as views with DuckDB query engine
+
 ## [0.6.1] - 2025-09-11
 Patch release with minor enhancements (SQL syntax highlighting, query parameters,
 predefined query Markdown description) and quality of life improvements
@@ -130,7 +148,9 @@ Initial release of `laketower`.
     - View a given table with simple query builder
     - Query all registered tables with DuckDB SQL dialect
 
-[Unreleased]: https://github.com/datalpia/laketower/compare/0.6.1...HEAD
+[Unreleased]: https://github.com/datalpia/laketower/compare/0.6.3...HEAD
+[0.6.3]: https://github.com/datalpia/laketower/compare/0.6.2...0.6.3
+[0.6.2]: https://github.com/datalpia/laketower/compare/0.6.1...0.6.2
 [0.6.1]: https://github.com/datalpia/laketower/compare/0.6.0...0.6.1
 [0.6.0]: https://github.com/datalpia/laketower/compare/0.5.1...0.6.0
 [0.5.1]: https://github.com/datalpia/laketower/compare/0.5.0...0.5.1

{laketower-0.6.1 → laketower-0.6.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: laketower
-Version: 0.6.1
+Version: 0.6.3
 Summary: Oversee your lakehouse
 Project-URL: Repository, https://github.com/datalpia/laketower
 Project-URL: Issues, https://github.com/datalpia/laketower/issues
@@ -28,7 +28,6 @@ Requires-Dist: duckdb
 Requires-Dist: fastapi
 Requires-Dist: jinja2!=3.1.5,>=3
 Requires-Dist: markdown
-Requires-Dist: pandas
 Requires-Dist: pyarrow!=19.0.0
 Requires-Dist: pydantic-settings>=2
 Requires-Dist: pydantic>=2
@@ -39,7 +38,7 @@ Requires-Dist: sqlglot
 Requires-Dist: uvicorn
 Description-Content-Type: text/markdown
 
-# Laketower
+# 🗼 Laketower
 
 > Oversee your lakehouse
 
@@ -614,4 +613,4 @@ $ laketower -c demo/laketower.yml queries view daily_avg_temperature_params -p s
 
 Licensed under [Apache License 2.0](LICENSE)
 
-Copyright (c) 2025 - present Romain Clement
+Copyright (c) 2025 - present Romain Clement / Datalpia

{laketower-0.6.1 → laketower-0.6.3}/README.md

@@ -1,4 +1,4 @@
-# Laketower
+# 🗼 Laketower
 
 > Oversee your lakehouse
 
@@ -573,4 +573,4 @@ $ laketower -c demo/laketower.yml queries view daily_avg_temperature_params -p s
 
 Licensed under [Apache License 2.0](LICENSE)
 
-Copyright (c) 2025 - present Romain Clement
+Copyright (c) 2025 - present Romain Clement / Datalpia

laketower-0.6.3/laketower/__about__.py

@@ -0,0 +1 @@
+__version__ = "0.6.3"

{laketower-0.6.1 → laketower-0.6.3}/laketower/cli.py

@@ -8,6 +8,7 @@ import rich.table
 import rich.text
 import rich.tree
 import uvicorn
+import pyarrow.csv as pacsv
 
 from laketower.__about__ import __version__
 from laketower.config import load_yaml_config
@@ -135,11 +136,10 @@ def table_statistics(
         results = execute_query({table_name: table_dataset}, sql_query)
 
         out = rich.table.Table()
-        for column in results.columns:
+        for column in results.column_names:
             out.add_column(column)
-        for value_list in results.to_numpy().tolist():
-            row = [str(x) for x in value_list]
-            out.add_row(*row)
+        for row_dict in results.to_pylist():
+            out.add_row(*[str(row_dict[col]) for col in results.column_names])
     except Exception as e:
         out = rich.panel.Panel.fit(f"[red]{e}")
 
@@ -168,11 +168,10 @@ def view_table(
         results = execute_query({table_name: table_dataset}, sql_query)
 
         out = rich.table.Table()
-        for column in results.columns:
+        for column in results.column_names:
             out.add_column(column)
-        for value_list in results.to_numpy().tolist():
-            row = [str(x) for x in value_list]
-            out.add_row(*row)
+        for row_dict in results.to_pylist():
+            out.add_row(*[str(row_dict[col]) for col in results.column_names])
     except Exception as e:
         out = rich.panel.Panel.fit(f"[red]{e}")
 
@@ -198,15 +197,16 @@ def query_table(
         results = execute_query(tables_dataset, sql_query, sql_params=query_params)
 
         out = rich.table.Table()
-        for column in results.columns:
+        for column in results.column_names:
             out.add_column(column)
-        for value_list in results.values.tolist():
-            row = [str(x) for x in value_list]
-            out.add_row(*row)
+        for row_dict in results.to_pylist():
+            out.add_row(*[str(row_dict[col]) for col in results.column_names])
 
         if output_path is not None:
-            results.to_csv(
-                output_path, header=True, index=False, sep=",", encoding="utf-8"
+            pacsv.write_csv(
+                results,
+                output_path,
+                pacsv.WriteOptions(include_header=True, delimiter=","),
             )
             out = rich.text.Text(f"Query results written to: {output_path}")
     except ValueError as e:
@@ -271,11 +271,10 @@ def view_query(
         results = execute_query(tables_dataset, sql_query, sql_params=sql_params)
 
         out = rich.table.Table()
-        for column in results.columns:
+        for column in results.column_names:
             out.add_column(column)
-        for value_list in results.values.tolist():
-            row = [str(x) for x in value_list]
-            out.add_row(*row)
+        for row_dict in results.to_pylist():
+            out.add_row(*[str(row_dict[col]) for col in results.column_names])
     except ValueError as e:
         out = rich.panel.Panel.fit(f"[red]{e}")
 

{laketower-0.6.1 → laketower-0.6.3}/laketower/tables.py

@@ -4,8 +4,8 @@ from typing import Any, BinaryIO, Protocol, TextIO
 
 import deltalake
 import duckdb
-import pandas as pd
 import pyarrow as pa
+import pyarrow.csv as csv
 import pyarrow.dataset as padataset
 import pydantic
 import sqlglot
@@ -61,7 +61,7 @@ class TableProtocol(Protocol):  # pragma: no cover
     def history(self) -> TableHistory: ...
     def dataset(self, version: int | str | None = None) -> padataset.Dataset: ...
     def import_data(
-        self, data: pd.DataFrame, mode: ImportModeEnum = ImportModeEnum.append
+        self, data: pa.Table, mode: ImportModeEnum = ImportModeEnum.append
     ) -> None: ...
 
 
@@ -202,7 +202,7 @@ class DeltaTable:
         return self._impl.to_pyarrow_dataset()
 
     def import_data(
-        self, data: pd.DataFrame, mode: ImportModeEnum = ImportModeEnum.append
+        self, data: pa.Table, mode: ImportModeEnum = ImportModeEnum.append
     ) -> None:
         deltalake.write_deltalake(
             self.table_config.uri, data, mode=mode.value, schema_mode="merge"
@@ -274,7 +274,7 @@ def execute_query(
     tables_datasets: dict[str, padataset.Dataset],
     sql_query: str,
     sql_params: dict[str, str] = {},
-) -> pd.DataFrame:
+) -> pa.Table:
     if not sql_query:
         raise ValueError("Error: Cannot execute empty SQL query")
 
@@ -288,8 +288,8 @@ def execute_query(
 
             view_name = f"{table_name}_view"
             conn.register(view_name, table_dataset)
-            conn.execute(f'create table "{table_name}" as select * from "{view_name}"')  # nosec B608
-        return conn.execute(sql_query, parameters=sql_params).df()
+            conn.execute(f'create view "{table_name}" as select * from "{view_name}"')  # nosec B608
+        return conn.execute(sql_query, parameters=sql_params).fetch_arrow_table()
     except duckdb.Error as e:
         raise ValueError(str(e)) from e
 
@@ -303,7 +303,11 @@ def import_file_to_table(
     encoding: str = "utf-8",
 ) -> int:
     file_format_handler = {
-        ImportFileFormatEnum.csv: lambda f, d, e: pd.read_csv(f, sep=d, encoding=e)
+        ImportFileFormatEnum.csv: lambda f, d, e: csv.read_csv(
+            f,
+            read_options=csv.ReadOptions(encoding=e),
+            parse_options=csv.ParseOptions(delimiter=d),
+        )
     }
     table = load_table(table_config)
     df = file_format_handler[file_format](file_path, delimiter, encoding)

{laketower-0.6.1 → laketower-0.6.3}/laketower/templates/_base.html

@@ -68,14 +68,12 @@
         </ul>
 
         <div class="mt-auto pt-3 border-top flex-shrink-0">
-          <small class="text-muted px-3 d-block">
-            <a href="https://github.com/datalpia/laketower/releases/tag/{{ app_metadata.app_version }}"
-               target="_blank"
-               class="text-muted text-decoration-none">
-              v{{ app_metadata.app_version }}
-              <i class="bi-box-arrow-up-right ms-1" style="font-size: 0.7em;"></i>
-            </a>
-          </small>
+          <div class="px-3 d-block">
+            <button type="button" class="btn btn-link btn-sm text-muted text-decoration-none p-0" data-bs-toggle="modal" data-bs-target="#creditsModal">
+              <i class="bi-info-circle me-1"></i>
+              About
+            </button>
+          </div>
         </div>
       </div>
     </nav>
@@ -99,6 +97,72 @@
     </div>
   </main>
 
+  <div class="modal fade" id="creditsModal" tabindex="-1" aria-labelledby="creditsModalLabel" aria-hidden="true">
+    <div class="modal-dialog modal-dialog-centered">
+      <div class="modal-content">
+        <div class="modal-header">
+          <h5 class="modal-title" id="creditsModalLabel">About</h5>
+          <button type="button" class="btn-close" data-bs-dismiss="modal" aria-label="Close"></button>
+        </div>
+        <div class="modal-body">
+          <div class="text-center mb-3">
+            <h4>{{ app_metadata.app_name }}</h4>
+            <p class="text-muted mb-0">Oversee your lakehouse</p>
+          </div>
+
+          <dl class="row mb-3">
+            <dt class="col-sm-4">Version</dt>
+            <dd class="col-sm-8">
+              <a href="https://github.com/datalpia/laketower/releases/tag/{{ app_metadata.app_version }}"
+                 target="_blank"
+                 class="text-decoration-none">
+                {{ app_metadata.app_version }}
+                <i class="bi-box-arrow-up-right ms-1" style="font-size: 0.8em;"></i>
+              </a>
+            </dd>
+
+            <dt class="col-sm-4">Repository</dt>
+            <dd class="col-sm-8">
+              <a href="https://github.com/datalpia/laketower"
+                 target="_blank"
+                 class="text-decoration-none">
+                github.com/datalpia/laketower
+                <i class="bi-box-arrow-up-right ms-1" style="font-size: 0.8em;"></i>
+              </a>
+            </dd>
+
+            <dt class="col-sm-4">Issue Tracker</dt>
+            <dd class="col-sm-8">
+              <a href="https://github.com/datalpia/laketower/issues"
+                 target="_blank"
+                 class="text-decoration-none">
+                Report an issue
+                <i class="bi-box-arrow-up-right ms-1" style="font-size: 0.8em;"></i>
+              </a>
+            </dd>
+
+            <dt class="col-sm-4">License</dt>
+            <dd class="col-sm-8">
+              <a href="https://github.com/datalpia/laketower/blob/main/LICENSE"
+                 target="_blank"
+                 class="text-decoration-none">
+                Apache License 2.0
+                <i class="bi-box-arrow-up-right ms-1" style="font-size: 0.8em;"></i>
+              </a>
+            </dd>
+          </dl>
+
+          <div class="text-center text-muted">
+            <small>Copyright © 2025 Romain Clement / Datalpia</small>
+          </div>
+        </div>
+        <div class="modal-footer">
+          <button type="button" class="btn btn-secondary" data-bs-dismiss="modal">Close</button>
+        </div>
+      </div>
+    </div>
+  </div>
+
   <script src="{{ url_for('static', path='/vendor/bootstrap/bootstrap.bundle.min.js') }}"></script>
   {% block extra_scripts %}{% endblock %}
 </body>

{laketower-0.6.1 → laketower-0.6.3}/laketower/templates/queries/view.html

@@ -58,16 +58,16 @@
       <table class="table table-sm table-bordered table-striped table-hover">
         <thead>
           <tr>
-            {% for column in query_results.columns %}
+            {% for column in query_results.column_names %}
             <th>{{ column }}</th>
             {% endfor %}
           </tr>
         </thead>
         <tbody class="table-group-divider">
-          {% for row in query_results.to_numpy().tolist() %}
+          {% for row in query_results.to_pylist() %}
           <tr>
-            {% for col in row %}
-            <td>{{ col }}</td>
+            {% for column in query_results.column_names %}
+            <td>{{ row[column] }}</td>
             {% endfor %}
           </tr>
           {% endfor %}

{laketower-0.6.1 → laketower-0.6.3}/laketower/templates/tables/query.html

@@ -47,16 +47,16 @@
       <table class="table table-sm table-bordered table-striped table-hover">
         <thead>
           <tr>
-            {% for column in table_results.columns %}
+            {% for column in table_results.column_names %}
             <th>{{ column }}</th>
             {% endfor %}
           </tr>
         </thead>
         <tbody class="table-group-divider">
-          {% for row in table_results.to_numpy().tolist() %}
+          {% for row in table_results.to_pylist() %}
           <tr>
-            {% for col in row %}
-            <td>{{ col }}</td>
+            {% for column in table_results.column_names %}
+            <td>{{ row[column] }}</td>
             {% endfor %}
           </tr>
           {% endfor %}

{laketower-0.6.1 → laketower-0.6.3}/laketower/templates/tables/statistics.html

@@ -15,16 +15,16 @@
       <table class="table table-sm table-bordered table-striped table-hover">
         <thead>
           <tr>
-            {% for column in table_results.columns %}
+            {% for column in table_results.column_names %}
             <th>{{ column }}</th>
             {% endfor %}
           </tr>
         </thead>
         <tbody class="table-group-divider">
-          {% for row in table_results.to_numpy().tolist() %}
+          {% for row in table_results.to_pylist() %}
           <tr>
-            {% for col in row %}
-            <td>{{ col }}</td>
+            {% for column in table_results.column_names %}
+            <td>{{ row[column] }}</td>
             {% endfor %}
           </tr>
           {% endfor %}

{laketower-0.6.1 → laketower-0.6.3}/laketower/templates/tables/view.html

@@ -15,7 +15,7 @@
       <table class="table table-sm table-bordered table-striped table-hover">
         <thead>
           <tr>
-            {% for column in table_results.columns %}
+            {% for column in table_results.column_names %}
             <th>
               {{ column }}
               {% if column == request.query_params.sort_asc %}
@@ -44,10 +44,10 @@
           </tr>
         </thead>
         <tbody class="table-group-divider">
-          {% for row in table_results.to_numpy().tolist() %}
+          {% for row in table_results.to_pylist() %}
           <tr>
-            {% for col in row %}
-            <td>{{ col }}</td>
+            {% for column in table_results.column_names %}
+            <td>{{ row[column] }}</td>
             {% endfor %}
           </tr>
           {% endfor %}

{laketower-0.6.1 → laketower-0.6.3}/laketower/web.py

@@ -1,3 +1,4 @@
+import io
 import urllib.parse
 from dataclasses import dataclass
 from pathlib import Path
@@ -5,6 +6,7 @@ from typing import Annotated
 
 import bleach
 import markdown
+import pyarrow.csv as pacsv
 import pydantic_settings
 from fastapi import APIRouter, FastAPI, File, Form, Query, Request, UploadFile
 from fastapi.responses import HTMLResponse, RedirectResponse, Response
@@ -119,10 +121,13 @@ def export_tables_query_csv(request: Request, sql: str) -> Response:
     tables_dataset = load_datasets(config.tables)
 
     results = execute_query(tables_dataset, sql)
-    csv_content = results.to_csv(header=True, index=False, sep=",")
+    csv_content = io.BytesIO()
+    pacsv.write_csv(
+        results, csv_content, pacsv.WriteOptions(include_header=True, delimiter=",")
+    )
 
     return Response(
-        content=csv_content,
+        content=csv_content.getvalue(),
         media_type="text/csv",
         headers={"Content-Disposition": "attachment; filename=query_results.csv"},
     )
@@ -415,7 +420,7 @@ def create_app() -> FastAPI:
     )
     app.include_router(router)
     app.state.app_metadata = AppMetadata(
-        app_name="Laketower", app_version=__about__.__version__
+        app_name="🗼 Laketower", app_version=__about__.__version__
     )
     app.state.config = config
 

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

@@ -14,7 +14,6 @@ dependencies = [
     "fastapi",
     "jinja2>=3,!=3.1.5",
     "markdown",
-    "pandas",
     "pyarrow!=19.0.0",
     "pydantic>=2",
     "pydantic-settings>=2",
@@ -56,19 +55,20 @@ build-backend = "hatchling.build"
 [dependency-groups]
 dev = [
     "bandit==1.8.6",
-    "beautifulsoup4==4.13.5",
+    "beautifulsoup4==4.14.2",
     "httpx==0.28.1",
-    "invoke==2.2.0",
-    "mypy==1.17.1",
-    "pandas-stubs==2.3.2.250827",
+    "invoke==2.2.1",
+    "mypy==1.18.2",
+    "pandas==2.3.3",
+    "pandas-stubs==2.3.2.250926",
     "pip-audit==2.9.0",
-    "pyarrow-stubs==20.0.0.20250825",
+    "pyarrow-stubs==20.0.0.20250928",
     "pytest==8.4.2",
     "pytest-cov==7.0.0",
-    "ruff==0.13.0",
+    "ruff==0.14.1",
     "types-bleach==6.2.0.20250809",
     "types-markdown==3.9.0.20250906",
-    "types-pyyaml==6.0.12.20250822",
+    "types-pyyaml==6.0.12.20250915",
     "watchdog==6.0.0",
 ]
 

{laketower-0.6.1 → laketower-0.6.3}/tasks.py

@@ -18,7 +18,11 @@ def format(ctx: Context) -> None:
 
 @task
 def audit(ctx: Context) -> None:
-    ctx.run("pip-audit", echo=True, pty=True)
+    ignored_vulns = [
+        "GHSA-4xh5-x5gv-qwph",  # pip<=25.2 affected, no resolution yet
+    ]
+    options = [f"--ignore-vuln {vuln}" for vuln in ignored_vulns]
+    ctx.run(f"pip-audit {' '.join(options)}", echo=True, pty=True)
 
 
 @task

{laketower-0.6.1 → laketower-0.6.3}/tests/test_cli.py

@@ -6,6 +6,7 @@ from typing import Any
 import deltalake
 import pandas as pd
 import pyarrow as pa
+import pyarrow.csv as pacsv
 import pytest
 import yaml
 
@@ -744,7 +745,7 @@ def test_tables_query_output_csv(
     delta_table: deltalake.DeltaTable,
 ) -> None:
     selected_column = delta_table.schema().fields[0].name
-    selected_limit = 1
+    selected_limit = 3
 
     output_csv_path = tmp_path / "output.csv"
 
@@ -774,8 +775,12 @@ def test_tables_query_output_csv(
     df = delta_table.to_pandas()
     expected_output = df[[selected_column]][0:selected_limit]
     expected_csv_path = tmp_path / "expected.csv"
-    expected_output.to_csv(
-        expected_csv_path, header=True, index=False, sep=",", encoding="utf-8"
+
+    expected_table = pa.Table.from_pandas(expected_output)
+    pacsv.write_csv(
+        expected_table,
+        expected_csv_path,
+        pacsv.WriteOptions(include_header=True, delimiter=","),
     )
     assert output_csv_path.read_text() == expected_csv_path.read_text()