Merge branch 'main' into main

kraina-ai · Sep 25, 2024 · 9d3fed6 · 9d3fed6
2 parents 4d5a3b3 + 3689a4d
commit 9d3fed6
Show file tree

Hide file tree

Showing 17 changed files with 280 additions and 147 deletions.
diff --git a/.github/workflows/ci-dev.yml b/.github/workflows/ci-dev.yml
@@ -88,7 +88,7 @@ jobs:
           key: mkdocs-osm-dev-cache-${{ runner.os }}
       - name: Prepare DuckDB dependency
         run: |
-          wget https://github.com/duckdb/duckdb/releases/download/v0.10.2/duckdb_cli-linux-amd64.zip
+          wget https://github.com/duckdb/duckdb/releases/download/v1.1.0/duckdb_cli-linux-amd64.zip
           unzip duckdb_cli-linux-amd64.zip
           chmod a+x ./duckdb
       - name: Test required commands

diff --git a/.github/workflows/ci-prod.yml b/.github/workflows/ci-prod.yml
@@ -79,7 +79,7 @@ jobs:
           key: mkdocs-osm-dev-cache-${{ runner.os }}
       - name: Prepare DuckDB dependency
         run: |
-          wget https://github.com/duckdb/duckdb/releases/download/v0.10.2/duckdb_cli-linux-amd64.zip
+          wget https://github.com/duckdb/duckdb/releases/download/v1.1.0/duckdb_cli-linux-amd64.zip
           unzip duckdb_cli-linux-amd64.zip
           chmod a+x ./duckdb
       - name: Test required commands

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -11,6 +11,27 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Option to export to DuckDB database [#94](https://github.com/kraina-ai/quackosm/issues/119)
 
+## [0.11.0] - 2024-09-24
+
+### Changed
+
+- Bumped minimal DuckDB version to `1.1.0`
+- Refactored geoparquet operations for compatibility with new DuckDB version
+- Excluded `conftest.py` file from the final library build
+- Replaced `unary_union` calls with `union_all()` on all GeoDataFrames
+- Silenced `pooch` library warnings regarding empty SHA hash
+
+## [0.10.0] - 2024-09-23
+
+### Changed
+
+- **BREAKING** Changed required minimal number of points in polygon from 3 to 4
+- Added removal of repeated points in linestrings
+
+### Fixed
+
+- Removed support for yanked polars version `1.7.0`
+
 ## [0.9.4] - 2024-09-11
 
 ### Changed
@@ -366,7 +387,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Created QuackOSM repository
 - Implemented PbfFileReader
 
-[Unreleased]: https://github.com/kraina-ai/quackosm/compare/0.9.4...HEAD
+[Unreleased]: https://github.com/kraina-ai/quackosm/compare/0.11.0...HEAD
+
+[0.11.0]: https://github.com/kraina-ai/quackosm/compare/0.10.0...0.11.0
+
+[0.10.0]: https://github.com/kraina-ai/quackosm/compare/0.9.4...0.10.0
 
 [0.9.4]: https://github.com/kraina-ai/quackosm/compare/0.9.3...0.9.4
 

diff --git a/README.md b/README.md
@@ -70,7 +70,7 @@ QuackOSM supports **Python >= 3.9**
 
 Required:
 
-- `duckdb (>=0.10.2, <1.1.0)`: For all DuckDB operations on PBF files
+- `duckdb (>=1.1.0)`: For all DuckDB operations on PBF files
 
 - `pyarrow (>=16.0.0)`: For parquet files wrangling
 
@@ -148,9 +148,7 @@ way/993121275      {'building': 'yes', 'name': ...  POLYGON ((7.43214 43.7481...
 ```python
 >>> import duckdb
 >>> duckdb.load_extension('spatial')
->>> duckdb.read_parquet(str(gpq_path)).project(
-...     "* REPLACE (ST_GeomFromWKB(geometry) AS geometry)"
-... ).order("feature_id")
+>>> duckdb.read_parquet(str(gpq_path)).order("feature_id")
 ┌──────────────────┬──────────────────────┬──────────────────────────────────────────────┐
 │    feature_id    │         tags         │                   geometry                   │
 │     varchar      │ map(varchar, varch…  │                   geometry                   │
@@ -270,9 +268,7 @@ way/998561139     {'barrier': 'bollard', 'bicyc...  LINESTRING (12.45828 41.9...
 ```python
 >>> import duckdb
 >>> duckdb.load_extension('spatial')
->>> duckdb.read_parquet(str(gpq_path)).project(
-...     "* REPLACE (ST_GeomFromWKB(geometry) AS geometry)"
-... ).order("feature_id")
+>>> duckdb.read_parquet(str(gpq_path)).order("feature_id")
 ┌──────────────────┬──────────────────────┬──────────────────────────────────────────────┐
 │    feature_id    │         tags         │                   geometry                   │
 │     varchar      │ map(varchar, varch…  │                   geometry                   │
@@ -388,9 +384,7 @@ relation/3256168   {'building': 'yes', 'type': ...  POLYGON ((12.46061 41.907...
 ```python
 >>> import duckdb
 >>> duckdb.load_extension('spatial')
->>> duckdb.read_parquet(str(gpq_path)).project(
-...     "* REPLACE (ST_GeomFromWKB(geometry) AS geometry)"
-... ).order("feature_id")
+>>> duckdb.read_parquet(str(gpq_path)).order("feature_id")
 ┌──────────────────┬────────────────────────────┬──────────────────────────────┐
 │    feature_id    │            tags            │           geometry           │
 │     varchar      │   map(varchar, varchar)    │           geometry           │

diff --git a/examples/pbf_file_reader.ipynb b/examples/pbf_file_reader.ipynb
@@ -102,9 +102,7 @@
     "connection.load_extension(\"parquet\")\n",
     "connection.load_extension(\"spatial\")\n",
     "\n",
-    "features_relation = connection.read_parquet(str(reykjavik_buildings_gpq)).project(\n",
-    "    \"* REPLACE (ST_GeomFromWKB(geometry) AS geometry)\"\n",
-    ")\n",
+    "features_relation = connection.read_parquet(str(reykjavik_buildings_gpq))\n",
     "features_relation"
    ]
   },
@@ -190,9 +188,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "features_relation = connection.read_parquet(str(estonia_features_gpq)).project(\n",
-    "    \"* REPLACE (ST_GeomFromWKB(geometry) AS geometry)\"\n",
-    ")\n",
+    "features_relation = connection.read_parquet(str(estonia_features_gpq))\n",
     "features_relation"
    ]
   },
@@ -294,9 +290,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "features_relation = connection.read_parquet(str(liechtenstein_features_gpq)).project(\n",
-    "    \"* REPLACE (ST_GeomFromWKB(geometry) AS geometry)\"\n",
-    ")\n",
+    "features_relation = connection.read_parquet(str(liechtenstein_features_gpq))\n",
     "features_relation"
    ]
   },

diff --git a/pdm.lock b/pdm.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -1,13 +1,13 @@
 [project]
 name = "QuackOSM"
-version = "0.9.4"
+version = "0.11.0"
 description = "An open-source tool for reading OpenStreetMap PBF files using DuckDB"
 authors = [{ name = "Kamil Raczycki", email = "[email protected]" }]
 dependencies = [
     "geopandas>=0.6",
     "shapely>=2",
     "pyarrow>=16.0.0",
-    "duckdb>=0.10.2,<1.1.0",
+    "duckdb>=1.1.0",
     "geoarrow-pyarrow>=0.1.2",
     "geoarrow-pandas>=0.1.1",
     "typeguard>=3.0.0",
@@ -16,7 +16,7 @@ dependencies = [
     "tqdm>=4.42.0",
     "beautifulsoup4",
     "requests",
-    "polars>=0.19.4",
+    "polars>=0.19.4,!=1.7.0",
     "rich>=12.0.0",
     "geopy>=2.0.0",
     "numpy>=1.26.0",
@@ -109,6 +109,9 @@ cli-dev = ["ipywidgets", "folium", "matplotlib>=3.2.0", "mapclassify"]
 [tool.pdm.scripts]
 post_install = "pre-commit install"
 
+[tool.pdm.build]
+excludes = ["quackosm/conftest.py"]
+
 [tool.black]
 line-length = 100
 target-version = ["py39", "py310", "py311", "py312"]
@@ -170,7 +173,7 @@ close-quotes-on-newline = true
 wrap-one-line = true
 
 [tool.bumpver]
-current_version = "0.9.4"
+current_version = "0.11.0"
 version_pattern = "MAJOR.MINOR.PATCH[PYTAGNUM]"
 commit_message = "chore(CI/CD): bump version {old_version} -> {new_version}"
 commit = true

diff --git a/quackosm/__init__.py b/quackosm/__init__.py
@@ -21,7 +21,7 @@
 from quackosm.pbf_file_reader import PbfFileReader
 
 __app_name__ = "QuackOSM"
-__version__ = "0.9.4"
+__version__ = "0.11.0"
 
 __all__ = [
     "PbfFileReader",

diff --git a/quackosm/_geopandas_api_version.py b/quackosm/_geopandas_api_version.py
@@ -0,0 +1,4 @@
+import geopandas as gpd
+from packaging import version
+
+GEOPANDAS_NEW_API = version.parse(gpd.__version__) >= version.parse("1.0.0")