New Release

.github/workflows/test.yml

@@ -20,18 +20,21 @@ jobs:
     # needs: lint
     strategy:
       matrix:
-        ckan-version: [2.9]
+        ckan-base-version: [2.9]
+        ckan-version: [py3.9]
+        solr-version: [solr8]
       fail-fast: false
 
-    name: CKAN ${{ matrix.ckan-version }}
+    name: CKAN ${{ matrix.ckan-base-version }}
     runs-on: ubuntu-latest
     container:
-      image: openknowledge/ckan-dev:${{ matrix.ckan-version }}
+      image: ckan/ckan-dev:${{ matrix.ckan-base-version }}-${{ matrix.ckan-version }}
+      options: --user root
     services:
       solr:
-        image: ckan/ckan-solr:${{ matrix.ckan-version }}-solr9
+        image: ckan/ckan-solr:${{ matrix.ckan-base-version }}-${{ matrix.solr-version }}
       postgres:
-        image: ckan/ckan-postgres-dev:${{ matrix.ckan-version }}
+        image: ckan/ckan-postgres-dev:${{ matrix.ckan-base-version }}
         env:
           POSTGRES_USER: postgres
           POSTGRES_PASSWORD: postgres
@@ -48,6 +51,8 @@ jobs:
 
     steps:
     - uses: actions/checkout@v2
+    - name: Install CURL
+      run: apt install curl -y
     - name: Install requirements
       run: |
         pip install -r dev-requirements.txt
@@ -66,8 +71,8 @@ jobs:
         ckan -c test.ini db init
     - name: Run tests
       run: pytest --ckan-ini=test.ini --cov=ckanext.datasetsnippets --cov-report=xml --cov-append --disable-warnings ckanext/datasetsnippets/tests
-    - name: Upload coverage report to codecov
-      uses: codecov/codecov-action@v1
-      with:
-        file: ./coverage.xml
-        token: ${{secrets.CODECOV_TOKEN}}
+    - name: Upload coverage reports to Codecov
+      run: |
+        curl -Os https://uploader.codecov.io/latest/linux/codecov
+        chmod +x codecov
+        ./codecov

CHANGELOG.md

@@ -2,6 +2,12 @@
 
 ## Development
 
+## [0.1.10](https://github.com/berlinonline/ckanext-datasetsnippets/releases/tag/0.1.10)
+
+_(2024-09-02)_
+
+- Sanitize user input & handle author_string/author
+
 ## [0.1.9](https://github.com/berlinonline/ckanext-datasetsnippets/releases/tag/0.1.9)
 
 _(2024-08-29)_

README.md

@@ -86,7 +86,7 @@ datasetsnippets.datenportal_title = 'Berlin Open Data'
 
 ## License
 
-This material is copyright © [BerlinOnline Stadtportal GmbH](https://www.berlinonline.net/).
+This material is copyright © [BerlinOnline GmbH](https://www.berlinonline.net/).
 
 This extension is open and licensed under the GNU Affero General Public License (AGPL) v3.0.
 Its full text may be found at:

ckanext/datasetsnippets/VERSION

@@ -1 +1 @@
-0.1.9
+0.1.10

ckanext/datasetsnippets/blueprints/feeds.py

@@ -363,15 +363,23 @@ def custom():
     fields = request.params.get(u'fields', u'')
     fq = u''
     search_params = {}
+    # some facets are not with the name used in CKAN
+    changed_facets = {'author_string': 'author'}
+
     for (param, value) in request.params.items():
         if param not in [u'q', u'page', u'sort'] \
                 and len(value) and not param.startswith(u'_'):
             if param == 'fq':
                 value_tmp = value.split('&')
                 result_dict = dict(pair.split('=') for pair in value_tmp)
                 for res in result_dict:
-                    search_params[res] = result_dict[res]
-                    fq += u' +%s:%s' % (res, result_dict[res])
+                    if res in changed_facets.keys():
+                        res_tmp = changed_facets[res]
+                        search_params[res] = result_dict[res]
+                        fq += u' +%s:%s' % (res_tmp, result_dict[res])
+                    else:
+                        search_params[res] = result_dict[res]
+                        fq += u' +%s:%s' % (res, result_dict[res])
             else:
                 search_params[param] = value
                 fq += u' %s:%s' % (param, value)
@@ -508,7 +516,7 @@ def _create_rss_id(resource_path, authority_name=None, date_string=None):
 
     # Construct the GUID as a full URL
     if authority_name:
-        return f"http://{authority_name}{resource_path}"
+        return f"https://{authority_name}{resource_path}"
     else:
         # Fallback to just the resource path if authority_name is not available
         return resource_path

ckanext/datasetsnippets/blueprints/snippet_blueprint.py

@@ -14,6 +14,7 @@
 import ckan.plugins as plugins
 from ckan.plugins import toolkit
 from ckan.common import _, c, request, config
+from six.moves.urllib.parse import unquote
 
 from ckanext.datasetsnippets.blueprints import feeds
 
@@ -156,7 +157,8 @@ def search_dataset():
                         if k != 'root_breadcrumb']
 
     # unicode format (decoded from utf8)
-    q = c.q = request.params.get('q', u'')
+    q = request.params.get('q', u'')
+    c.q = unquote(q)
     c.query_error = False
     page = h.get_page_number(request.params)
 

publiccode.yml

@@ -0,0 +1,144 @@
+# This repository adheres to the publiccode.yml standard by including this 
+# metadata file that makes public software easily discoverable.
+# More info at https://github.com/italia/publiccode.yml
+
+publiccodeYmlVersion: '0.2'
+name: ckanext-datasetsnippets
+url: 'https://github.com/berlinonline/ckanext-datasetsnippets'
+releaseDate: '2022-02-22'
+softwareVersion: 0.1.11
+developmentStatus: stable
+softwareType: addon
+categories:
+  - it-development
+  - knowledge-management
+maintenance:
+  type: internal
+  contacts:
+    - name: Dr. Knud Möller
+      email: [email protected]
+legal:
+  license: AGPL-3.0-only
+  mainCopyrightOwner: BerlinOnline GmbH
+  repoOwner: BerlinOnline GmbH
+localisation:
+  localisationReady: false
+description:
+  it:
+    genericName: ckanext-datasetsnippets
+    documentation: >-
+      https://github.com/berlinonline/ckanext-datasetsnippets?tab=readme-ov-file#ckanext-datasetsnippets
+    apiDocumentation: >-
+      https://github.com/berlinonline/ckanext-datasetsnippets?tab=readme-ov-file#api
+    shortDescription: >-
+      ckanext-datasetsnippets provides markup snippets for dataset pages and
+      dataset search. These snippets can be loaded from the data portal's public
+      CMS 
+    longDescription: >
+      This plugin belongs to a set of plugins for the _Datenregister_ – the
+      non-public [CKAN](https://ckan.org/) instance that is part of Berlin's
+      open data portal [daten.berlin.de](https://daten.berlin.de/).
+      _ckanext-datasetsnippets_ provides markup snippets for dataset pages and
+      dataset search. These snippets can be loaded from the data portal's public
+      CMS to handle all requests for datasets.
+
+
+      The plugin implements the following CKAN interfaces:
+
+
+      -
+      [ITemplateHelpers](http://docs.ckan.org/en/latest/extensions/plugin-interfaces.html#ckan.plugins.interfaces.ITemplateHelpers)
+
+      -
+      [IBlueprint](http://docs.ckan.org/en/latest/extensions/plugin-interfaces.html#ckan.plugins.interfaces.IBlueprint)
+
+      -
+      [IAuthFunctions](http://docs.ckan.org/en/latest/extensions/plugin-interfaces.html#ckan.plugins.interfaces.IAuthFunctions)
+
+
+      ## Requirements
+
+
+      This plugin has been tested with CKAN 2.9.9 (which requires Python 3).
+
+
+      ## API
+
+
+      The Snippet API has the following two endpoints:
+
+
+      ### `/snippet/dataset`
+
+
+      This is the search endpoint of the snippet API, which is equivalent to
+      `/dataset` in the regular CKAN UI. Without additional parameters, this
+      returns markup for the paginated list of all datasets. Parameters (search
+      facets, ordering etc.) can be use to restrict the result. The parameters
+      are identical to the regular CKAN search parameters.
+
+
+      ### `/snippet/dataset/<id>`
+
+
+      This is the dataset detail endpoint of the snippet API, which is
+      equivalent to `/dataset/<id>` in the regular CKAN UI. `<id>` is the name
+      or id of a dataset.
+
+
+      ### Parameters
+
+
+      Both endpoints allow a `root\_breadcrumb` parameter to set the root
+      element of the breadcrumb returned in the snippets. The
+      `root\_breadcrumb`-URL-parameter takes precedence over the
+      `datasetsnippets.default\_root\_breadcrumb` config (see below).
+
+
+      ## Configuration
+
+
+      The plugin introduces the following configuration options:
+
+
+      ### datasetsnippets.path
+
+
+      Defines the path component that is prefixed to links that the snippets
+      contain. In the regular CKAN UI, this would be `dataset`, but the site
+      calling the snippet API might require a different path.
+
+          datasetsnippets.path = 'datensaetze'
+
+      ### datasetsnippets.datasets\_per\_page
+
+
+      Defines how many datasets are shown per result page in pagination. The
+      option is equivalent to
+      [ckan.datasets\_per\_page](https://docs.ckan.org/en/2.9/maintaining/configuration.html#ckan-datasets-per-page),
+      but only applies to the snippets and leaves the regular CKAN UI untouched.
+
+          datasetsnippets.datasets\_per\_page = 10
+
+      ### datasetsnippets.default\_root\_breadcrumb
+
+
+      Defines the string that is used as the root element for the breadcrumb
+      that is part of the returned snippets.
+
+          datasetsnippets.default\_root\_breadcrumb = 'Berlin Open Data'
+
+      ### datasetsnippets.datenportal\_url
+
+
+      Defines the url to the datenportal. The url will then be used for
+      generating the feeds using the provided url.
+
+          datasetsnippets.datenportal\_url = link\_to\_portal
+
+      ### datasetsnippets.datenportal\_title
+
+
+      Defines a string that will be used as a title in the feeds.
+
+          datasetsnippets.datenportal\_title = 'Berlin Open Data'