Update versions of dependencies

.github/dependabot.yml

@@ -0,0 +1,26 @@
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    groups:
+      dev-deps:
+        dependency-type: "development"
+      prod-deps:
+        dependency-type: "production"
+    open-pull-requests-limit: 5
+    commit-message:
+      prefix: "deps"
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    groups:
+      actions-deps:
+        patterns:
+          - "*"
+    open-pull-requests-limit: 5
+    commit-message:
+      prefix: "ci"
+

.github/workflows/ci.yml

@@ -9,13 +9,14 @@ on:
 
 jobs:
   test:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     strategy:
       matrix:
+        python-version: ["3.9", "3.11"]
         tox_env: [python] #, precommit]
     services:
       postgres:
-        image: postgres:9.6
+        image: postgres:11.1
         env:
           POSTGRES_PASSWORD: postgres
           POSTGRES_DB: bsync_validator
@@ -28,16 +29,15 @@ jobs:
         ports:
           - 5432:5432
     steps:
-      - uses: actions/checkout@v3
-      - uses: actions/setup-python@v3
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
-          python-version: "3.6.7"
+          python-version: ${{ matrix.python-version }}
       - name: Display system info
         run: python -c "import sys; print(sys.version)"
       - name: Setup Python
         run: |
-          apt-get update && apt-get install python-enchant -y
-          pip install tox
+          sudo apt-get update && sudo apt-get install python3-enchant -y
           pip install --upgrade pip
           pip install tox coveralls
       - name: Run tox

.pre-commit-config.yaml

@@ -11,53 +11,43 @@ exclude: |
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v5.0.0
     hooks:
-      - id: trailing-whitespace
-      - id: check-added-large-files
-        args: ["--maxkb=5000"]
       - id: check-ast
+      - id: check-added-large-files
+        # Reduced max file size from 5000KB to 2000KB to prevent large files from being added.
+        args: ["--maxkb=2000"]
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+      - id: check-toml
+      - id: check-yaml
       - id: check-json
+      - id: name-tests-test
+        args: ["--pytest-test-first"]
+      - id: fix-byte-order-marker
+      - id: check-case-conflict
+      - id: check-docstring-first
+      - id: check-executables-have-shebangs
       - id: check-merge-conflict
       - id: check-xml
-      - id: check-yaml
-        exclude: .*/templates
       - id: debug-statements
-      - id: end-of-file-fixer
-        exclude: seed/static/seed/locales/
       - id: mixed-line-ending
-        exclude: seed/static/seed/locales/
       - id: pretty-format-json
         args: ["--autofix", "--no-sort-keys"]
-  - repo: https://github.com/pre-commit/mirrors-isort
-    rev: v5.10.1
-    hooks:
-      - id: isort
-        args:
-          [
-            -m=VERTICAL_HANGING_INDENT,
-            --skip=seed/models/__init__.py,
-            --filter-files,
-          ]
-  - repo: https://github.com/PyCQA/autoflake
-    rev: v2.2.1
-    hooks:
-      - id: autoflake
-        args:
-          [
-            "--in-place",
-            "--recursive",
-            "--remove-all-unused-imports",
-            "--remove-unused-variable",
-          ]
-  - repo: https://github.com/PyCQA/flake8
-    rev: 6.1.0
-    hooks:
-      - id: flake8
-        args: ["--ignore=F401,E402,E501,E731,W503,W504"]
-  - repo: https://github.com/pre-commit/mirrors-prettier
+        files: \.(json|template)$
+    - repo: https://github.com/pre-commit/mirrors-prettier
     rev: v3.0.3
     hooks:
       - id: prettier
         # for now ignoring html, javascript
         types_or: [yaml, markdown, css, scss]
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.11.7
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix, --output-format=full]
+        types_or: [python, pyi, jupyter]
+      - id: ruff-format
+        types_or: [python, pyi, jupyter]
+
+

bsyncviewer/lib/bedes/bedes_parser.py

@@ -1,6 +1,7 @@
 import json
 import os
-from collections import Mapping, OrderedDict, defaultdict
+from collections import OrderedDict, defaultdict
+from collections.abc import Mapping
 
 import xmltodict
 

bsyncviewer/lib/schema_parser.py

@@ -199,7 +199,7 @@ def check_all_type_definitions(self):
 
     def _read_schema(self, root_element):
         full_schema = BuildingSyncSchemaRoot()
-        for child in root_element.getchildren():
+        for child in root_element:
 
             if child.tag.endswith('element'):
                 if 'name' in child.attrib:
@@ -230,7 +230,7 @@ def _read_ref_element(self, parent_object):
 
         ref_element.ref_type = parent_object.attrib['ref']
 
-        for child in parent_object.getchildren():
+        for child in parent_object:
             if child.tag.endswith('attribute'):
                 ref_element.attributes.append(self._read_attribute(child))
             elif child.tag.endswith('annotation'):
@@ -251,7 +251,7 @@ def _read_named_element(self, parent_object):
             named_element.min_occurs = parent_object.attrib['minOccurs']
         if 'maxOccurs' in parent_object.attrib:
             named_element.max_occurs = parent_object.attrib['maxOccurs']
-        for child in parent_object.getchildren():
+        for child in parent_object:
             if child.tag.endswith('annotation'):
                 named_element.annotations.append(self._read_annotation(child))
             elif child.tag.endswith('complexType'):
@@ -270,7 +270,7 @@ def _read_named_element(self, parent_object):
     @staticmethod
     def _read_annotation(parent_object):
         annotation = AnnotationElement()
-        for child in parent_object.getchildren():
+        for child in parent_object:
             if child.tag.endswith('documentation'):
                 annotation.documentation = child.text
             else:
@@ -279,7 +279,7 @@ def _read_annotation(parent_object):
 
     def _read_attribute(self, parent_object):
         attribute = AttributeElement()
-        for child in parent_object.getchildren():
+        for child in parent_object:
             if child.tag.endswith('simpleType'):
                 attribute.simple_types.append(self._read_simple_type(child))
             elif child.tag.endswith('annotation'):
@@ -290,7 +290,7 @@ def _read_attribute(self, parent_object):
 
     def _read_complex_type(self, parent_object):
         this_complex_type = ComplexTypeElement()
-        for child in parent_object.getchildren():
+        for child in parent_object:
             if child.tag.endswith('sequence'):
                 this_complex_type.sequences.append(self._read_sequence(child))
             elif child.tag.endswith('simpleContent'):
@@ -312,7 +312,7 @@ def _read_complex_type(self, parent_object):
 
     def _read_sequence(self, parent_object):
         this_sequence = SequenceElement()
-        for child in parent_object.getchildren():
+        for child in parent_object:
             if child.tag.endswith('element'):
                 if 'name' in child.attrib:
                     this_sequence.named_elements.append(self._read_named_element(child))
@@ -329,7 +329,7 @@ def _read_sequence(self, parent_object):
 
     def _read_simple_content(self, parent_object):
         this_simple_content = SimpleContentElement()
-        for child in parent_object.getchildren():
+        for child in parent_object:
             if child.tag.endswith('extension'):
                 this_simple_content.extensions.append(self._read_extension(child))
             else:
@@ -340,7 +340,7 @@ def _read_extension(self, parent_object):
         this_extension = ExtensionElement()
         if 'base' in parent_object.attrib:
             this_extension.base_type = parent_object.attrib['base']
-        for child in parent_object.getchildren():
+        for child in parent_object:
             if child.tag.endswith('attribute'):
                 this_extension.attributes.append(self._read_attribute(child))
             else:
@@ -361,7 +361,7 @@ def _read_simple_type(self, parent_object):
         if parent_object.attrib and parent_object.attrib['name']:
             this_simple_content.name = parent_object.attrib['name']
 
-        for child in parent_object.getchildren():
+        for child in parent_object:
             if child.tag.endswith('restriction'):
                 this_simple_content.restrictions.append(self._read_restriction(child))
             elif child.tag.endswith('annotation'):
@@ -378,7 +378,7 @@ def _read_simple_type(self, parent_object):
     @staticmethod
     def _read_restriction(parent_object):
         this_restriction = RestrictionElement()
-        for child in parent_object.getchildren():
+        for child in parent_object:
             if child.tag.endswith('enumeration'):
                 this_restriction.enumerations.append(child.attrib['value'])
             elif child.tag.endswith('minInclusive'):
@@ -394,7 +394,7 @@ def _read_restriction(parent_object):
 
     def _read_choice(self, parent_object):
         this_choice = ChoiceElement()
-        for child in parent_object.getchildren():
+        for child in parent_object:
             if child.tag.endswith('element'):
                 if 'name' in child.attrib:
                     this_choice.named_elements.append(self._read_named_element(child))

bsyncviewer/management/commands/bedes.py

@@ -89,7 +89,10 @@ def parse(self, bedes_version, schema_version):
             bsync_term = self.manual_mapping(attribute.name, manual_mappings)
 
             for bt in bedes.terms:
-                distance = jellyfish.jaro_winkler(bsync_term.lower(), bt['Term'].lower())
+                # Skip if bt['Term'] is None or not a string
+                if not bt.get('Term') or not isinstance(bt['Term'], str):
+                    continue
+                distance = jellyfish.jaro_winkler_similarity(bsync_term.lower(), bt['Term'].lower())
 
                 if distance >= 0.98:
                     results[attribute.id].append({
@@ -106,7 +109,7 @@ def parse(self, bedes_version, schema_version):
             if not results[attribute.id]:
                 for be in bedes.enumerations:
                     # .lower() function used to neutralize upper/lower case discrepancies (there are many in enumerations/list options)
-                    distance = jellyfish.jaro_winkler(bsync_term.lower(), be['List-Option'].lower())
+                    distance = jellyfish.jaro_winkler_similarity(bsync_term.lower(), be['List-Option'].lower())
 
                     if distance >= 0.98:
                         results[attribute.id].append({
@@ -162,7 +165,7 @@ def parse(self, bedes_version, schema_version):
                             for word_group in word_groups.keys():
 
                                 for bt in bedes.terms:
-                                    distance = jellyfish.jaro_winkler(word_group.lower(), bt['Term'].lower())
+                                    distance = jellyfish.jaro_winkler_similarity(word_group.lower(), bt['Term'].lower())
 
                                     if distance >= 0.98:
 
@@ -183,7 +186,7 @@ def parse(self, bedes_version, schema_version):
                                     # if no matches found in BEDES terms, check list options
                                     for be in bedes.enumerations:
 
-                                        distance = jellyfish.jaro_winkler(word_group.lower(), be['List-Option'].lower())
+                                        distance = jellyfish.jaro_winkler_similarity(word_group.lower(), be['List-Option'].lower())
 
                                         if distance >= 0.98:
                                             for i in range(word_groups[word_group], word_groups[word_group] + number_of_words):
@@ -367,7 +370,10 @@ def parse(self, bedes_version, schema_version):
             print(associated_attrs)
 
             for be in bedes.enumerations:
-                distance = jellyfish.jaro_winkler(enumeration.name, be['List-Option'])
+                # Skip if be['List-Option'] is None or not a string
+                if not be.get('List-Option') or not isinstance(be['List-Option'], str):
+                    continue
+                distance = jellyfish.jaro_winkler_similarity(enumeration.name, be['List-Option'])
 
                 if distance >= 0.95:
                     results[enumeration.id].append({

requirements-test.txt

@@ -3,4 +3,5 @@
 autopep8==1.4.4
 coveralls==2.2.0
 coverage==5.0.1
+pre-commit==3.5.0
 tox==3.14.1

requirements.txt

@@ -2,19 +2,20 @@ Django==2.2.28
 django-bootstrap4==2.3.1
 djangorestframework==3.11.2
 djangorestframework-xml==1.0.1
-# Version of lxml has to match what is in testsuite
-lxml==4.9.1
-psycopg2==2.8.6
+
+psycopg2-binary==2.9.7
+
 semantic-version==2.10.0
 stopit==1.1.2
 xmlschema==1.0.15
 xmltodict==0.12.0
 
 # string matching
-jellyfish==0.7.1
+jellyfish==1.2.0
 
 # schematron runner from TestSuite repo
-testsuite==0.1.3
+# This also sets the version of lxml to use
+testsuite==0.1.5
 
 # production deployment
-uWSGI==2.0.22
+uWSGI==2.0.26

tox.ini

@@ -13,9 +13,6 @@ envlist =
 passenv=
     DJANGO_LOG_LEVEL
     DJANGO_SETTINGS_MODULE
-    TRAVIS
-    TRAVIS_JOB_ID
-    TRAVIS_BRANCH
 commands = coverage run manage.py test
 deps = -r{toxinidir}/requirements-test.txt