Merge pull request #808 from UXARRAY/rajeeja/io_shapefile

Implement `Grid.open_file` method support non xarray formats including Shapefile/Geojson
UXARRAY · Sep 19, 2024 · 6862950 · 6862950
2 parents 2b60860 + 610e029
commit 6862950
Show file tree

Hide file tree

Showing 30 changed files with 1,065 additions and 1,445 deletions.
diff --git a/ci/asv.yml b/ci/asv.yml
@@ -24,6 +24,7 @@ dependencies:
   - scipy
   - shapely
   - spatialpandas
+  - geopandas
   - xarray
   - asv
   - pip:

diff --git a/ci/docs.yml b/ci/docs.yml
@@ -33,6 +33,7 @@ dependencies:
     - pandas
     - geocat-datafiles
     - spatialpandas
+    - geopandas
     - pip:
       - antimeridian
       - git+https://github.com/philipc2/pyfma.git # fix until https://github.com/nschloe/pyfma/pull/17 is merged
diff --git a/ci/environment.yml b/ci/environment.yml
@@ -28,6 +28,7 @@ dependencies:
   - scipy
   - shapely
   - spatialpandas
+  - geopandas
   - xarray
   - asv
   - pip:

diff --git a/ci/install-upstream.sh b/ci/install-upstream.sh
@@ -33,6 +33,7 @@ python -m pip install \
     pandas \
     scikit-learn \
     scipy \
+    geopandas \
     xarray
 
 # install rest from source

diff --git a/docs/internal_api/index.rst b/docs/internal_api/index.rst
@@ -286,12 +286,17 @@ SCRIP
    io._scrip._encode_scrip
 
 
-Shapefile
+GeoPandas
 ---------
 .. autosummary::
    :toctree: generated/
 
-   io._shapefile._read_shpfile
+   io._geopandas._read_geodataframe
+   io._geopandas._read_geopandas
+   io._geopandas._encode_geopandas
+   io._geopandas._standardize_geopandas
+   io._geopandas._is_geopandas
+   io._geopandas._validate_minimum_geopandas
 
 Vertices
 --------

diff --git a/pyproject.toml b/pyproject.toml
@@ -42,6 +42,7 @@ dependencies = [
   "scipy",
   "shapely",
   "spatialpandas",
+  "geopandas",
   "xarray",
 ]
 # minimal dependencies end

diff --git a/test/meshfiles/geojson/README.md b/test/meshfiles/geojson/README.md
@@ -0,0 +1,15 @@
+GeoJSON is a format for encoding a variety of geographic data structures, including points, lines, and polygons.
+
+This repository contains "sample_chicago_buildings" GeoJSON file featuring a selection of buildings in Chicago. The file includes:
+
+        Number of polygons: 10
+        Polygon 1: 26 sides
+        Polygon 2: 36 sides
+        Polygon 3: 29 sides
+        Polygon 4: 10 sides
+        Polygon 5: 30 sides
+        Polygon 6: 8 sides
+        Polygon 7: 7 sides
+        Polygon 8: 9 sides
+        Polygon 9: 7 sides
+        Polygon 10: 19 sides
diff --git a/test/meshfiles/geojson/sample_chicago_buildings.geojson b/test/meshfiles/geojson/sample_chicago_buildings.geojson
diff --git a/test/meshfiles/shp/5poly/5poly.cpg b/test/meshfiles/shp/5poly/5poly.cpg
@@ -0,0 +1 @@
+ISO-8859-1
diff --git a/test/meshfiles/shp/5poly/5poly.dbf b/test/meshfiles/shp/5poly/5poly.dbf
diff --git a/test/meshfiles/shp/5poly/5poly.shp b/test/meshfiles/shp/5poly/5poly.shp
diff --git a/test/meshfiles/shp/5poly/5poly.shx b/test/meshfiles/shp/5poly/5poly.shx
diff --git a/test/meshfiles/shp/README.md b/test/meshfiles/shp/README.md
@@ -0,0 +1,15 @@
+### There are 3 sub folders each containing different shapefile examples
+
+1. **5poly** : A very simple file containing only 5 polygons with different number of sides
+2. **cb_2018_us_national_20m**: Real word shapefile containing the 2018 Census Bureau US map at 20m resolution
+3. **multipoly**: Test file containing multipolygons.
+
+### Files Included in the Shapefile Dataset
+
+1. **.shp** - **Shape Format**: Contains the geometric data (polygons) for the features in the dataset. The first 100 bytes contain metadata about the file.
+
+2. **.shx** - **Shape Index Format**: Contains the index data for the .shp file, allowing for quick access to the geometric data.
+
+3. **.dbf** - **Attribute Format**: Contains attribute data for the features in the .shp file. This is a dBase file that stores information in a tabular format, where each row corresponds to a feature in the .shp file.
+
+4. **.cpg** - **Code Page Format**: Contains character encoding information for the .dbf file, ensuring that text data is correctly interpreted. Eg. ISO-8859-1
diff --git a/test/meshfiles/shp/cb_2018_us_nation_20m/cb_2018_us_nation_20m.cpg b/test/meshfiles/shp/cb_2018_us_nation_20m/cb_2018_us_nation_20m.cpg
@@ -0,0 +1 @@
+UTF-8
diff --git a/test/meshfiles/shp/cb_2018_us_nation_20m/cb_2018_us_nation_20m.dbf b/test/meshfiles/shp/cb_2018_us_nation_20m/cb_2018_us_nation_20m.dbf
diff --git a/test/meshfiles/shp/cb_2018_us_nation_20m/cb_2018_us_nation_20m.prj b/test/meshfiles/shp/cb_2018_us_nation_20m/cb_2018_us_nation_20m.prj
@@ -0,0 +1 @@
+GEOGCS["GCS_North_American_1983",DATUM["D_North_American_1983",SPHEROID["GRS_1980",6378137,298.257222101]],PRIMEM["Greenwich",0],UNIT["Degree",0.017453292519943295]]
diff --git a/test/meshfiles/shp/cb_2018_us_nation_20m/cb_2018_us_nation_20m.shp b/test/meshfiles/shp/cb_2018_us_nation_20m/cb_2018_us_nation_20m.shp
diff --git a/test/meshfiles/shp/cb_2018_us_nation_20m/cb_2018_us_nation_20m.shp.ea.iso.xml b/test/meshfiles/shp/cb_2018_us_nation_20m/cb_2018_us_nation_20m.shp.ea.iso.xml
@@ -0,0 +1,119 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--This file contains all the Entity and Attribute Information--><gfc:FC_FeatureCatalogue xmlns:gmx="http://www.isotc211.org/2005/gmx"
+                         xmlns:gco="http://www.isotc211.org/2005/gco"
+                         xmlns:gmd="http://www.isotc211.org/2005/gmd"
+                         xmlns:xlink="http://www.w3.org/1999/xlink"
+                         xmlns:gml="http://www.opengis.net/gml/3.2"
+                         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+                         xmlns:gfc="http://www.isotc211.org/2005/gfc"
+                         xsi:schemaLocation="https://www.ngdc.noaa.gov/metadata/published/xsd/schema/gfc/featureCataloging.xsd http://www.isotc211.org/2005/gfc">
+   <gmx:name>
+      <gco:CharacterString>Feature Catalog for the 2018 United States 1:20,000,000 Cartographic Boundary File</gco:CharacterString>
+   </gmx:name>
+   <gmx:scope>
+      <gco:CharacterString>The United States at a scale of 1:20,000,000</gco:CharacterString>
+   </gmx:scope>
+   <gmx:versionNumber>
+      <gco:CharacterString>cb_2018_nation_20m</gco:CharacterString>
+   </gmx:versionNumber>
+   <gmx:versionDate>
+      <gco:Date>2019-05</gco:Date>
+   </gmx:versionDate>
+   <gmx:language>
+      <gco:CharacterString>eng</gco:CharacterString>
+   </gmx:language>
+   <gmx:characterSet>
+      <gmd:MD_CharacterSetCode codeList="http://www.isotc211.org/2005/resources/Codelist/gmxCodelists.xml#MD_CharacterSetCode"
+                               codeListValue="utf8"
+                               codeSpace="004">utf8
+            </gmd:MD_CharacterSetCode>
+   </gmx:characterSet>
+   <gfc:producer xlink:href="https://www.ngdc.noaa.gov/docucomp/1df27e57-4768-42de-909b-52f530601fba"
+                 xlink:title="U.S Department of Commerce, U.S Census Bureau, Geographic Customer Services Branch"/>
+   <gfc:featureType>
+      <gfc:FC_FeatureType>
+         <gfc:typeName>
+            <gco:LocalName>cb_2018_us_nation_20m.shp</gco:LocalName>
+         </gfc:typeName>
+         <gfc:definition>
+            <gco:CharacterString>Current Nation (national)</gco:CharacterString>
+         </gfc:definition>
+         <gfc:isAbstract>
+            <gco:Boolean>false</gco:Boolean>
+         </gfc:isAbstract>
+         <gfc:featureCatalogue uuidref="2018_nation_20m.ea.iso.xml"/>
+         <gfc:carrierOfCharacteristics>
+            <gfc:FC_FeatureAttribute>
+               <gfc:memberName>
+                  <gco:LocalName>AFFGEOID</gco:LocalName>
+               </gfc:memberName>
+               <gfc:definition>
+                  <gco:CharacterString>American FactFinder summary level code + geovariant code + '00US'</gco:CharacterString>
+               </gfc:definition>
+               <gfc:cardinality gco:nilReason="unknown"/>
+               <gfc:definitionReference xlink:title="U.S. Census Bureau"
+                                        xlink:href="http://www.ngdc.noaa.gov/docucomp/eb139e38-ee29-4d59-b157-5e874d4420c4"/>
+               <gfc:listedValue>
+                  <gfc:FC_ListedValue>
+                     <gfc:label>
+                        <gco:CharacterString>American FactFinder geographic identifier</gco:CharacterString>
+                     </gfc:label>
+                     <gfc:definitionReference xlink:title="U.S. Census Bureau"
+                                              xlink:href="http://www.ngdc.noaa.gov/docucomp/eb139e38-ee29-4d59-b157-5e874d4420c4"/>
+                  </gfc:FC_ListedValue>
+               </gfc:listedValue>
+            </gfc:FC_FeatureAttribute>
+         </gfc:carrierOfCharacteristics>
+         <gfc:carrierOfCharacteristics>
+            <gfc:FC_FeatureAttribute>
+               <gfc:memberName>
+                  <gco:LocalName>GEOID</gco:LocalName>
+               </gfc:memberName>
+               <gfc:definition>
+                  <gco:CharacterString>Nation identifier</gco:CharacterString>
+               </gfc:definition>
+               <gfc:cardinality gco:nilReason="unknown"/>
+               <gfc:definitionReference xlink:title="U.S. Census Bureau"
+                                        xlink:href="http://www.ngdc.noaa.gov/docucomp/eb139e38-ee29-4d59-b157-5e874d4420c4"/>
+               <gfc:listedValue>
+                  <gfc:FC_ListedValue>
+                     <gfc:label>
+                        <gco:CharacterString>US</gco:CharacterString>
+                     </gfc:label>
+                     <gfc:definition>
+                        <gco:CharacterString>United States</gco:CharacterString>
+                     </gfc:definition>
+                     <gfc:definitionReference xlink:title="U.S. Census Bureau"
+                                              xlink:href="http://www.ngdc.noaa.gov/docucomp/eb139e38-ee29-4d59-b157-5e874d4420c4"/>
+                  </gfc:FC_ListedValue>
+               </gfc:listedValue>
+            </gfc:FC_FeatureAttribute>
+         </gfc:carrierOfCharacteristics>
+         <gfc:carrierOfCharacteristics>
+            <gfc:FC_FeatureAttribute>
+               <gfc:memberName>
+                  <gco:LocalName>NAME</gco:LocalName>
+               </gfc:memberName>
+               <gfc:definition>
+                  <gco:CharacterString>Nation name</gco:CharacterString>
+               </gfc:definition>
+               <gfc:cardinality gco:nilReason="unknown"/>
+               <gfc:definitionReference xlink:title="U.S. Census Bureau"
+                                        xlink:href="http://www.ngdc.noaa.gov/docucomp/eb139e38-ee29-4d59-b157-5e874d4420c4"/>
+               <gfc:listedValue>
+                  <gfc:FC_ListedValue>
+                     <gfc:label>
+                        <gco:CharacterString>United States</gco:CharacterString>
+                     </gfc:label>
+                     <gfc:definition>
+                        <gco:CharacterString>Nation</gco:CharacterString>
+                     </gfc:definition>
+                     <gfc:definitionReference xlink:title="U.S. Census Bureau"
+                                              xlink:href="http://www.ngdc.noaa.gov/docucomp/eb139e38-ee29-4d59-b157-5e874d4420c4"/>
+                  </gfc:FC_ListedValue>
+               </gfc:listedValue>
+            </gfc:FC_FeatureAttribute>
+         </gfc:carrierOfCharacteristics>
+      </gfc:FC_FeatureType>
+   </gfc:featureType>
+</gfc:FC_FeatureCatalogue>