HDXDSYS-2123 Catch munge_url exception in HDX Python API

.pre-commit-config.yaml

@@ -1,5 +1,5 @@
 default_language_version:
-    python: python3.12
+    python: python3.13
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v5.0.0

hatch.toml

@@ -24,7 +24,7 @@ version_scheme = "python-simplified-semver"
 features = ["test"]
 
 [[envs.hatch-test.matrix]]
-python = ["3.12"]
+python = ["3.13"]
 
 [envs.hatch-test.scripts]
 run = """

pyproject.toml

@@ -37,8 +37,8 @@ dependencies = [
     "ckanapi>=4.8",
     "defopt>=6.4.0",
     "email_validator",
-    "hdx-python-country>=3.9.3",
-    "hdx-python-utilities>=3.8.6",
+    "hdx-python-country>=3.9.4",
+    "hdx-python-utilities>=3.8.7",
     "libhxl>=5.2.2",
     "makefun",
     "quantulum3",

requirements.txt

@@ -34,8 +34,6 @@ colorama==0.4.6
     # via mkdocs-material
 coverage==7.8.0
     # via pytest-cov
-cydifflib==1.2.0
-    # via hdx-python-utilities
 defopt==6.4.0
     # via hdx-python-api (pyproject.toml)
 distlib==0.3.9
@@ -64,11 +62,11 @@ google-auth==2.40.1
     #   gspread
 google-auth-oauthlib==1.2.2
     # via gspread
-gspread==6.2.0
+gspread==6.2.1
     # via hdx-python-api (pyproject.toml)
-hdx-python-country==3.9.3
+hdx-python-country==3.9.4
     # via hdx-python-api (pyproject.toml)
-hdx-python-utilities==3.8.6
+hdx-python-utilities==3.8.7
     # via
     #   hdx-python-api (pyproject.toml)
     #   hdx-python-country
@@ -80,7 +78,7 @@ idna==3.10
     # via
     #   email-validator
     #   requests
-ijson==3.3.0
+ijson==3.4.0
     # via hdx-python-utilities
 inflect==7.5.0
     # via quantulum3
@@ -110,7 +108,7 @@ libhxl==5.2.2
     #   hdx-python-country
 loguru==0.7.3
     # via hdx-python-utilities
-makefun==1.15.6
+makefun==1.16.0
     # via hdx-python-api (pyproject.toml)
 markdown==3.8
     # via
@@ -131,15 +129,15 @@ mergedeep==1.3.4
     # via
     #   mkdocs
     #   mkdocs-get-deps
-mkapi==4.3.2
+mkapi==4.4.0
     # via hdx-python-api (pyproject.toml)
 mkdocs==1.6.1
     # via
     #   mkapi
     #   mkdocs-material
 mkdocs-get-deps==0.2.0
     # via mkdocs
-mkdocs-material==9.6.12
+mkdocs-material==9.6.14
     # via mkapi
 mkdocs-material-extensions==1.3.1
     # via mkdocs-material
@@ -167,7 +165,7 @@ platformdirs==4.3.8
     # via
     #   mkdocs-get-deps
     #   virtualenv
-pluggy==1.5.0
+pluggy==1.6.0
     # via pytest
 ply==3.11
     # via
@@ -225,7 +223,7 @@ pyyaml==6.0.2
     #   pymdown-extensions
     #   pyyaml-env-tag
     #   tableschema-to-template
-pyyaml-env-tag==0.1
+pyyaml-env-tag==1.1
     # via mkdocs
 quantulum3==0.9.2
     # via hdx-python-api (pyproject.toml)
@@ -252,17 +250,15 @@ rfc3986==2.0.0
     # via frictionless
 rich==14.0.0
     # via typer
-rpds-py==0.24.0
+rpds-py==0.25.0
     # via
     #   jsonschema
     #   referencing
 rsa==4.9.1
     # via google-auth
 ruamel-yaml==0.18.10
     # via hdx-python-utilities
-ruamel-yaml-clib==0.2.12
-    # via ruamel-yaml
-setuptools==80.3.1
+setuptools==80.7.1
     # via ckanapi
 shellingham==1.5.4
     # via typer
@@ -290,14 +286,13 @@ text-unidecode==1.3
     # via python-slugify
 typeguard==4.4.2
     # via inflect
-typer==0.15.3
+typer==0.15.4
     # via frictionless
 typing-extensions==4.13.2
     # via
     #   frictionless
     #   pydantic
     #   pydantic-core
-    #   referencing
     #   typeguard
     #   typer
     #   typing-inspection
@@ -313,7 +308,7 @@ urllib3==2.4.0
     #   requests
 validators==0.35.0
     # via frictionless
-virtualenv==20.31.1
+virtualenv==20.31.2
     # via pre-commit
 watchdog==6.0.0
     # via mkdocs

src/hdx/data/dataset.py

@@ -20,7 +20,7 @@
     Union,
 )
 
-from hxl.input import InputOptions, munge_url
+from hxl.input import HXLIOException, InputOptions, munge_url
 
 import hdx.data.organization as org_module
 import hdx.data.resource as res_module
@@ -220,7 +220,10 @@ def save_to_json(self, path: str, follow_urls: bool = False):
         dataset_dict = self.get_dataset_dict()
         if follow_urls:
             for resource in dataset_dict.get("resources", tuple()):
-                resource["url"] = munge_url(resource["url"], InputOptions())
+                try:
+                    resource["url"] = munge_url(resource["url"], InputOptions())
+                except HXLIOException:
+                    pass
         save_json(dataset_dict, path)
 
     @staticmethod

tests/hdx/api/test_ckan.py

@@ -37,6 +37,8 @@ def configuration(self):
         )
         Locations._validlocations = None
         Country.countriesdata(use_live=False)
+        Vocabulary._approved_vocabulary = None
+        Vocabulary._tags_dict = None
 
     @pytest.fixture(scope="function")
     def datasetmetadata(self):