Merge branch 'release/0.8.0'

UUDigitalHumanitieslab · Jan 31, 2024 · 91de0ef · 91de0ef
2 parents fcb2d94 + 2c08355
commit 91de0ef
Show file tree

Hide file tree

Showing 57 changed files with 5,246 additions and 6,175 deletions.
diff --git a/README.md b/README.md
@@ -3,7 +3,7 @@
 [![Build Status](https://travis-ci.org/UUDigitalHumanitieslab/sasta.svg?branch=develop)](https://travis-ci.org/UUDigitalHumanitieslab/sasta)
 
 > SASTA: **S**emi-automatische **A**nalyse van **S**pontane **Ta**al
- 
+
 Annotate and analyze transcripts
 
 
@@ -60,7 +60,7 @@ Running the application in [development mode][8] (hit ctrl-C to stop):
 $ yarn start
 ```
 
-This will run the backend and frontend applications, as well as their unittests, and watch all source files for changes. You can visit the frontend on http://localhost:5000/, the browsable backend API on http://localhost:5000/api/ and the backend admin on http://localhost:5000/admin/. On every change, unittests rerun, frontend code rebuilds and open browser tabs refresh automatically (livereload).
+This will run the backend and frontend applications, as well as their unittests, and watch all source files for changes. You can visit the frontend on http://localhost:8000/, the browsable backend API on http://localhost:8000/api/ and the backend admin on http://localhost:8000/admin/. On every change, unittests rerun, frontend code rebuilds and open browser tabs refresh automatically (livereload).
 
 [8]: #development-mode-vs-production-mode
 
@@ -188,7 +188,7 @@ The purpose of development mode is to facilitate live development, as the name i
 dimension  |  Development mode  |  Production mode
 -----------|--------------------|-----------------
 command  |  `yarn start`  |  `yarn start-p`
-base address  |  http://localhost:5000  |  http://localhost:4200
+base address  |  http://localhost:8000  |  http://localhost:4200
 backend server (Django)  |  in charge of everything  |  serves backend only
 
 frontend server (angular-cli)  |  serves  |  watch and build

diff --git a/backend/README.md b/backend/README.md
@@ -68,10 +68,10 @@ $ python manage.py runserver
 Once you see this line:
 
 ```console
-Starting development server at http://127.0.0.1:5000/
+Starting development server at http://127.0.0.1:8000/
 ```
 
-you can visit http://localhost:5000/admin/ and http://localhost:5000/api/ in your browser of choice. If you attached an external frontend application, its main page will be at http://localhost:5000/.
+you can visit http://localhost:8000/admin/ and http://localhost:8000/api/ in your browser of choice. If you attached an external frontend application, its main page will be at http://localhost:8000/.
 
 ### Enabling livereload
 

diff --git a/backend/analysis/annotations/safreader.py b/backend/analysis/annotations/safreader.py
@@ -140,22 +140,28 @@ def parse_word(self, utt_id, word_id, colname, word_data, wordposmap):
                 if not split_labels:
                     self.errors.append((utt_id, word_id, text, level, label))
 
-                for label in split_labels:
-                    mapped = item2queryid(label, level, self.item_mapping)
-                    if mapped:
-                        query_id, fase = mapped
-                        instance.annotations.append(SAFAnnotation(
-                            level, label, fase, query_id))
-                        self.document.exactresults[query_id].append((utt_id, word_id))
-
-                    else:
-                        logger.warning(
-                            'Cannot resolve query_id for (%s, %s)', level, label)
-                        self.errors.append((utt_id, word_id, text, level, label))
+                self.map_labels(split_labels, instance,
+                                level, utt_id, word_id, text)
 
         # read comments
         comment_data = data.loc[data.level == SAF_COMMENT_LEVEL.lower()].dropna()
         if not comment_data.empty:
             instance.comment = str(comment_data[colname].iloc[0])
 
         return instance
+
+    def map_labels(self, split_labels: List[str], saf_word: SAFWord, level: str, utt_id, word_id, text):
+        for label in split_labels:
+            mapped = item2queryid(label, level, self.item_mapping)
+            if mapped:
+                query_id, fase = mapped
+                saf_word.annotations.append(SAFAnnotation(
+                    level, label, fase, query_id))
+                self.document.exactresults[query_id].append(
+                    (utt_id, word_id))
+
+            else:
+                logger.warning(
+                    'Cannot resolve query_id for (%s, %s)', level, label)
+                self.errors.append(
+                    (utt_id, word_id, text, level, label))
diff --git a/backend/analysis/management/commands/set_default_methods.py b/backend/analysis/management/commands/set_default_methods.py
@@ -1,5 +1,5 @@
 from analysis.models import Corpus, MethodCategory
-from django.core.management.base import BaseCommand, CommandError
+from django.core.management.base import BaseCommand
 
 
 class Command(BaseCommand):
@@ -11,7 +11,7 @@ def handle(self, *args, **options) -> None:
             for category in MethodCategory.objects.all():
                 print(f'Setting new defaults for category {category.name}')
                 self.handle_category(category)
-        except Exception as e:
+        except Exception:
             pass
         finally:
             print('Setting new default methods complete')
@@ -28,7 +28,7 @@ def handle_category(self, category: MethodCategory):
                 corpus.save()
                 print(
                     f'Updated corpus {corpus.name} from {old_method.name if old_method else "None"} to {new_method.name}')
-        except Exception as e:
+        except Exception:
             pass
         finally:
             print('Setting new default methods complete')
diff --git a/backend/manage.py b/backend/manage.py
@@ -16,7 +16,7 @@ def main():
         ) from exc
 
     from django.core.management.commands.runserver import Command as runserver
-    runserver.default_port = "5000"
+    runserver.default_port = "8000"
 
     execute_from_command_line(sys.argv)
 

diff --git a/backend/requirements.txt b/backend/requirements.txt
@@ -31,7 +31,7 @@ celery==5.2.7
     # via
     #   -r requirements.in
     #   django-celery-results
-certifi==2022.12.7
+certifi==2023.7.22
     # via requests
 cffi==1.15.1
     # via cryptography
@@ -57,7 +57,7 @@ click-repl==0.2.0
     # via celery
 corpus2alpino==0.3.10
     # via -r requirements.in
-cryptography==39.0.1
+cryptography==41.0.6
     # via pyjwt
 cymem==2.0.6
     # via
@@ -115,7 +115,7 @@ lxml==4.9.1
     #   python-docx
     #   sastadev
     #   tei-reader
-markupsafe==2.1.1
+markupsafe==2.0.1
     # via jinja2
 murmurhash==1.0.7
     # via
@@ -257,7 +257,7 @@ typing-extensions==4.1.1
     # via
     #   pydantic
     #   sastadev
-urllib3==1.26.10
+urllib3==1.26.18
     # via
     #   django-revproxy
     #   requests

diff --git a/backend/sasta/common_settings.py b/backend/sasta/common_settings.py
@@ -0,0 +1,116 @@
+'''
+Common settings between development and production environments.
+Values here should be imported in settings.py
+'''
+# Application settings
+INSTALLED_APPS = [
+    'django.contrib.admin',
+    'django.contrib.auth',
+    'django.contrib.contenttypes',
+    'django.contrib.sessions',
+    'django.contrib.messages',
+    'django.contrib.sites',
+    'livereload',
+    'django.contrib.staticfiles',
+    'django_celery_results',
+    'rest_framework',
+    'rest_framework.authtoken',
+    'allauth',
+    'allauth.account',
+    'allauth.socialaccount',
+    'rest_auth',
+    'rest_auth.registration',
+    'revproxy',
+    'analysis',
+    'authentication',
+    'parse',
+    'convert',
+    'sastadev'
+]
+
+MIDDLEWARE = [
+    'django.middleware.security.SecurityMiddleware',
+    'django.contrib.sessions.middleware.SessionMiddleware',
+    'django.middleware.common.CommonMiddleware',
+    'django.middleware.csrf.CsrfViewMiddleware',
+    'django.contrib.auth.middleware.AuthenticationMiddleware',
+    'django.contrib.messages.middleware.MessageMiddleware',
+    'django.middleware.clickjacking.XFrameOptionsMiddleware',
+
+]
+
+TEMPLATES = [
+    {
+        'BACKEND': 'django.template.backends.django.DjangoTemplates',
+        'DIRS': [],
+        'APP_DIRS': True,
+        'OPTIONS': {
+            'context_processors': [
+                'django.template.context_processors.debug',
+                'django.template.context_processors.request',
+                'django.contrib.auth.context_processors.auth',
+                'django.contrib.messages.context_processors.messages',
+            ],
+        },
+    },
+]
+
+DEFAULT_AUTO_FIELD = 'django.db.models.AutoField'
+PROXY_FRONTEND = None
+
+# Password validation
+# https://docs.djangoproject.com/en/3.0/ref/settings/#auth-password-validators
+
+AUTH_PASSWORD_VALIDATORS = [
+    {
+        'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
+    },
+]
+
+# Internationalization
+# https://docs.djangoproject.com/en/3.0/topics/i18n/
+LANGUAGE_CODE = 'en-us'
+
+TIME_ZONE = 'Europe/Amsterdam'
+
+USE_I18N = True
+
+USE_L10N = True
+
+USE_TZ = True
+
+# Static files (CSS, JavaScript, Images)
+# https://docs.djangoproject.com/en/3.0/howto/static-files/
+STATIC_URL = '/static/'
+MEDIA_URL = '/media/'
+
+# DRF
+REST_FRAMEWORK = {
+    'DEFAULT_PERMISSION_CLASSES': [
+        'rest_framework.permissions.IsAuthenticated',
+    ],
+    'DEFAULT_AUTHENTICATION_CLASSES': [
+        'rest_framework.authentication.TokenAuthentication',
+        'sasta.authentication.CsrfExemptSessionAuthentication',
+    ]
+}
+
+# Authentication
+SITE_ID = 1
+ACCOUNT_EMAIL_REQUIRED = True
+ACCOUNT_EMAIL_VERIFICATION = 'mandatory'
+ACCOUNT_AUTHENTICATION_METHOD = 'username_email'
+
+# Celery
+CELERY_RESULT_BACKEND = 'django-db'
+CELERY_IGNORE_RESULT = False
+CELERY_TIMEZONE = TIME_ZONE