Add script to import geometries

scripts/2024-10-01_import-new-geometries/.gitignore

@@ -0,0 +1,165 @@
+*.sql
+*.gpkg
+
+# 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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/

scripts/2024-10-01_import-new-geometries/README.md

@@ -0,0 +1,14 @@
+# Script to import new Geometries into the assets database
+
+The script takes a geopackage file as input and creates two files:
+
+- a file `sgsids.txt` which contains all sgsids whose geometries are to be updated
+- a SQL Script `import_geometries.sql` which, for each asset with a relevant sgsid, deletes the existing geometries and inserts the new ones
+
+Getting started:
+
+- Install Python 3.12
+- Install requirements.txt
+- Adjust the parameters in at the top of `main.py`
+- Run `main.py`
+- Run the resulting SQL Script directly in the database. In case of a large number of geometries, consider running the script in smaller transaction blocks. Tools like Datagrip can do this directly.

scripts/2024-10-01_import-new-geometries/main.py

@@ -0,0 +1,68 @@
+from typing import TextIO
+
+import geopandas as gpd
+import numpy as np
+from geopandas import GeoDataFrame
+import os
+
+# The following parameters need to be adjusted to the correct values:
+filedir = ''
+filename = 'geometries.gpkg'
+output_filename = 'import_geometries.sql'
+output_sgsids_filename = 'sgsids.txt'
+
+# The following sgsids are not in the database, they were manually translated to the probably correct sgsid:
+sgsid_translation_dict = {}
+
+# Only use entries with Bemerkung equal to one of the following:
+allowed_bemerkung = ['erraten', 'erraten_B', 'neu', 'neu (?)', 'unsich kein B']
+
+def read_gdf(file: str, layer: str, allowed_bemerkung: list, translation_dict: dict):
+    '''Read a geopandas dataframe from a file and layer, filter out entries with Bemerkung not in allowed_bemerkung and translate the sgsid according to translationDict.'''
+    gdf = gpd.read_file(file, layer=layer)
+    print(gdf['Bemerkung'].value_counts())
+    gdf = gdf[(gdf['Bemerkung'].isin(allowed_bemerkung))]
+    gdf.replace({'IDSGS_neu': translation_dict}, inplace=True)
+    return gdf
+
+def write_insert_statements(f: TextIO, gdf: GeoDataFrame, geom_type: str):
+    for i, row in gdf.iterrows():
+        f.write(
+            f"INSERT INTO study_{geom_type} (asset_id, geom_quality_item_code, geom) VALUES ((SELECT asset_id FROM asset WHERE sgs_id = {row['IDSGS_neu']}), 'revised', ST_GeomFromText('{row['geometry'].wkt}', 2056));\n")
+
+def main():
+    path = os.path.join(filedir, filename)
+    gdf_points = read_gdf(file=path, layer='backup_20240829__points', allowed_bemerkung=allowed_bemerkung, translation_dict=sgsid_translation_dict)
+    gdf_lines = read_gdf(file=path, layer='backup_20240829__lines', allowed_bemerkung=allowed_bemerkung, translation_dict=sgsid_translation_dict)
+    gdf_polygons = read_gdf(file=path, layer='backup_20240829__polygons', allowed_bemerkung=allowed_bemerkung, translation_dict=sgsid_translation_dict)
+    gdf_lines = gdf_lines.explode() # explode multi-linestrings to linestrings
+    gdf_polygons = gdf_polygons.explode() # explode multi-polygons to polygons
+    gdf_points = gdf_points[~gdf_points['geometry'].is_empty] # remove empty geometries
+
+    sgs_ids = np.unique(np.concatenate(
+        [gdf_lines['IDSGS_neu'].unique(),
+         gdf_points['IDSGS_neu'].unique(),
+         gdf_polygons['IDSGS_neu'].unique()]))
+
+    np.savetxt(os.path.join(filedir, output_sgsids_filename), sgs_ids.astype(int), fmt='%d', delimiter=',')
+
+    # for each sgsid write a sql delete statement to delete all entries with this sgsid. Commit the commands every 1000 rows.
+    with open(os.path.join(filedir, output_filename), 'w') as f:
+        for i, sgsid in enumerate(sgs_ids):
+            f.write(
+                f"DELETE FROM study_location WHERE asset_id = (SELECT asset_id FROM asset WHERE sgs_id = {sgsid});\n")
+            f.write(f"DELETE FROM study_trace WHERE asset_id = (SELECT asset_id FROM asset WHERE sgs_id = {sgsid});\n")
+            f.write(f"DELETE FROM study_area WHERE asset_id = (SELECT asset_id FROM asset WHERE sgs_id = {sgsid});\n")
+
+        f.write('SELECT \'Finished deleting previous studies.\';\n\n')
+
+        # write the insert statements for the points
+        f.write('SELECT \'Creating locations.\';\n')
+        write_insert_statements(f, gdf_points, 'location')
+        f.write('\nSELECT \'Creating trace.\';\n')
+        write_insert_statements(f, gdf_lines, 'trace')
+        f.write('\nSELECT \'Creating area.\';\n')
+        write_insert_statements(f, gdf_polygons, 'area')
+
+if __name__ == '__main__':
+    main()

scripts/2024-10-01_import-new-geometries/requirements.txt

@@ -0,0 +1,2 @@
+geopandas
+numpy