rename fields and classes in (collection_)models.py; adjust tests

collection_models.py

@@ -7,19 +7,18 @@
 from models import UserInfo, Metadata, RecursiveRelatedCollection
 
 
-class CollectionName(BaseModel):  # todo: change to CollectionLabel
-    name: str = Field(title='label from a collection')  # todo: change to label
-    namehash: str = Field(title='namehash of the name')  # todo: remove namehash (also from the collections code)
+class CollectionLabel(BaseModel):
+    label: str = Field(title='label from a collection')
 
 
 class Collection(BaseModel):
     collection_id: str = Field(title='id of the collection')
     title: str = Field(title='title of the collection')
     owner: str = Field(title='ETH address of the collection owner')
-    number_of_names: int = Field(title='total number of names in the collection')
+    number_of_labels: int = Field(title='total number of labels in the collection')
     last_updated_timestamp: int = Field(title='timestamp in milliseconds of last collection update')
-    top_names: list[CollectionName] = Field(
-        title='top names stored in the collection (limited by `limit_names`)', description='can not be greater than 10')
+    top_labels: list[CollectionLabel] = Field(
+        title='top labels stored in the collection (limited by `limit_labels`)', description='can not be greater than 10')
     types: list[str] = Field(title='list of types to which the collection belongs',
                              description='example of type is `human`')
     avatar_emoji: str = Field(title='avatar emoji associated with this collection')
@@ -50,7 +49,7 @@ class BaseCollectionRequest(BaseModel):
 
 
 class BaseCollectionSearchLimitOffsetSort(BaseCollectionRequest):
-    limit_names: int = Field(10, ge=0, le=10, title='the number of names returned in each collection',
+    limit_labels: int = Field(10, ge=0, le=10, title='the number of labels returned in each collection',
                              description='can not be greater than 10')
     offset: int = Field(0,
                         title='offset of the first collection to return (used for pagination)',
@@ -66,8 +65,8 @@ class BaseCollectionSearch(BaseCollectionSearchLimitOffsetSort):
                                         description='* set to null if you want to disable the penalization\n'
                                                     '* if the penalization algorithm is turned on then 3 times more results (than max_related_collections) are retrieved from Elasticsearch')
     name_diversity_ratio: Optional[float] = Field(None, examples=[0.5], ge=0.0, le=1.0,
-        title='similarity value used for adding penalty to collections with similar names to other collections',
-        description='* if more than name_diversity_ratio % of the names have already been used, penalize the collection\n'
+        title='similarity value used for adding penalty to collections with similar labels to other collections',
+        description='* if more than name_diversity_ratio % of the labels have already been used, penalize the collection\n'
                     '* set to null if you want disable the penalization\n'
                     '* if the penalization algorithm is turned on then 3 times more results (than `max_related_collections`) '
                     'are retrieved from Elasticsearch'
@@ -135,16 +134,16 @@ class CollectionCountByStringRequest(BaseCollectionRequest):
 
 # ======== Collection Membership ========
 
-class CollectionsContainingNameCountRequest(BaseCollectionRequest):
+class CollectionsContainingLabelCountRequest(BaseCollectionRequest):
     label: str = Field(title='label for which collection membership will be checked', examples=['zeus'])
 
 
-class CollectionsContainingNameCountResponse(BaseCollectionQueryResponse):
+class CollectionsContainingLabelCountResponse(BaseCollectionQueryResponse):
     count: Union[int, str] = Field(
         title='count of collections containing input label or `1000+` if more than 1000 results')
 
 
-class CollectionsContainingNameRequest(BaseCollectionSearchLimitOffsetSort):
+class CollectionsContainingLabelRequest(BaseCollectionSearchLimitOffsetSort):
     label: str = Field(title='label for which membership will be checked for each collection', examples=['zeus'])
     mode: str = Field('instant', title='request mode: instant, domain_detail', pattern=r'^(instant|domain_detail)$')
     max_results: int = Field(3, ge=0, title='max number of collections to return (for each page)',
@@ -154,7 +153,8 @@ class CollectionsContainingNameRequest(BaseCollectionSearchLimitOffsetSort):
                                     '* if AI - use intelligent endpoint-specific ranking\n'
                                     '* if Relevance - use relevance ranking')
 
-class CollectionsContainingNameResponse(BaseCollectionQueryResponse):
+
+class CollectionsContainingLabelResponse(BaseCollectionQueryResponse):
     collections: list[Collection] = Field(title='list of public collections the provided label is a member of')
 
 
@@ -165,7 +165,7 @@ class GetCollectionByIdRequest(BaseCollectionRequest):
 # ======== Suggestions from collections ========
 
 class SuggestionFromCollection(BaseModel):
-    name: str = Field(title="label from a collection")  # todo: change to label
+    label: str = Field(title="label from a collection")
     tokenized_label: list[str] = Field(title="suggested tokenization of label")
     metadata: Optional[Metadata] = Field(None, title="information how suggestion was generated",
                                          description="if metadata=False this key is absent")
@@ -193,7 +193,7 @@ class SampleCollectionMembers(BaseModel):
 
 class Top10CollectionMembersRequest(BaseModel):
     user_info: Optional[UserInfo] = Field(None, title='information about user making request')
-    collection_id: str = Field(title='id of the collection to fetch names from', examples=['ri2QqxnAqZT7'])
+    collection_id: str = Field(title='id of the collection to fetch labels from', examples=['ri2QqxnAqZT7'])
     metadata: bool = Field(True, title='return all the metadata in response')
     max_recursive_related_collections: int = Field(3, ge=0, le=10,
                                                    title='Set to 0 to disable the "recursive related collection search". '
@@ -209,7 +209,7 @@ class ScrambleCollectionTokens(BaseModel):
     metadata: bool = Field(True, title='return all the metadata in response')
     method: Literal['left-right-shuffle', 'left-right-shuffle-with-unigrams', 'full-shuffle'] = \
         Field('left-right-shuffle-with-unigrams', title='method used to scramble tokens and generate new suggestions',
-  description='* left-right-shuffle - tokenize names as bigrams and shuffle the right-side tokens (do not use unigrams)'
+  description='* left-right-shuffle - tokenize labels as bigrams and shuffle the right-side tokens (do not use unigrams)'
               '\n* left-right-shuffle-with-unigrams - same as above, but with some tokens swapped with unigrams'
               '\n* full-shuffle - shuffle all tokens from bigrams and unigrams and create random bigrams')
     n_top_members: int = Field(25, title='number of collection\'s top members to include in scrambling', ge=1)
@@ -235,10 +235,3 @@ class FetchCollectionMembersRequest(BaseModel):
     metadata: bool = Field(
         True, title='return all the metadata in response'
     )
-
-
-# refactor models plan:
-#  [x] apply easy renamings
-#  [x] separate request forming functions
-#  3. adjust collection models and their request forming functions
-#  4. check josiah renamings

models.py

@@ -32,23 +32,23 @@ class Metadata(BaseModel):
                                              description='list of interpretation tags based on which the '
                                                          'suggestion has been generated')
     cached_status: str = Field(title='cached status',
-                               description='name\'s status cached at the time of application startup')
+                               description='label\'s status cached at the time of application startup')
     categories: list[str] = Field(title='domain category',
                                   description='can be either available, taken, recently released or on sale')
     cached_interesting_score: Optional[float] = Field(title='cached interesting score',
-                                                      description='name\'s interesting score cached at the time of '
+                                                      description='label\'s interesting score cached at the time of '
                                                                   'application startup')
     applied_strategies: list[list[str]] = Field(
         title="sequence of steps performed in every pipeline that generated the suggestion"
     )
     collection_title: Optional[str] = Field(
         title='name of the collection',
-        description='if name has been generated using a collection, '
+        description='if label has been generated using a collection, '
                     'then this field would contains its name, else it is null'
     )
     collection_id: Optional[str] = Field(
         title='id of the collection',
-        description='if name has been generated using a collection, '
+        description='if label has been generated using a collection, '
                     'then this field would contains its id, else it is null'
     )
     grouping_category: Optional[str] = Field(title='grouping category to which this suggestion belongs')
@@ -153,7 +153,7 @@ class CategoriesParams(BaseModel):
     model_config = ConfigDict(frozen=True)
 
 
-class GroupedNameRequest(BaseModel):
+class GroupedLabelRequest(BaseModel):
     label: str = Field(title='input label', pattern='^[^.]*$', examples=['zeus'],
                        description='* cannot contain dots (.)'
                                    '\n* if enclosed in double quotes assuming label is pre-tokenized')
@@ -169,7 +169,7 @@ class GroupedNameRequest(BaseModel):
         title='controls the results of other categories than related (except for "Other Names")')
 
 
-class NameRequest(BaseModel):
+class LabelRequest(BaseModel):
     label: str = Field(title='input label', description='cannot contain dots (.)',
                        pattern='^[^.]*$', examples=['zeus'])
     metadata: bool = Field(True, title='return all the metadata in response')
@@ -188,8 +188,8 @@ class NameRequest(BaseModel):
 
 
 class Suggestion(BaseModel):
-    name: str = Field(title="suggested similar label")  # todo: change to label
-    tokenized_label: list[str] = Field(title="original tokenization of suggested name's label")
+    label: str = Field(title="suggested similar label")
+    tokenized_label: list[str] = Field(title="suggested tokenization of label")
     metadata: Optional[Metadata] = Field(None, title="information how suggestion was generated",
                                          description="if metadata=False this key is absent")
 

tests/test_collections_api.py

@@ -92,7 +92,7 @@ def test_collection_api_metadata(self, test_test_client):
         es_time = response_json['metadata'].get('elasticsearch_processing_time_ms', 0)
         assert es_time <= response_json['metadata']['processing_time_ms'] <= (t1 - t0) * 1000
 
-    @mark.skip(reason='we return only names, without the root name')
+    @mark.skip(reason='we return only labels, without the root name')
     @mark.integration_test
     def test_collection_api_eth_suffix(self, test_test_client):
         response = test_test_client.post("/find_collections_by_string", json={
@@ -109,9 +109,9 @@ def test_collection_api_eth_suffix(self, test_test_client):
         response_json = response.json()
 
         assert len(response_json['related_collections'] + response_json['other_collections']) <= 5
-        assert all([member_name['name'].endswith('.eth')
+        assert all([member_name['label'].endswith('.eth')
                     for collection in response_json['related_collections'] + response_json['other_collections']
-                    for member_name in collection['top_names']])
+                    for member_name in collection['top_labels']])
 
     @mark.integration_test
     def test_collection_api_avatar_emojis_and_images(self, test_test_client):
@@ -153,7 +153,7 @@ def test_collection_api_instant_search(self, test_test_client):
             "max_total_collections": 15,
             "name_diversity_ratio": 0.5,
             "max_per_type": 3,
-            "limit_names": 10,
+            "limit_labels": 10,
         })
 
         assert response.status_code == 200
@@ -172,7 +172,7 @@ def test_collection_api_domain_details(self, test_test_client):
             "max_total_collections": 6,
             "name_diversity_ratio": 0.5,
             "max_per_type": 3,
-            "limit_names": 10,
+            "limit_labels": 10,
         })
 
         assert response.status_code == 200
@@ -190,7 +190,7 @@ def test_collection_api_domain_details_pagination_by_string(self, test_test_clie
             "max_total_collections": 100,
             "name_diversity_ratio": None,  # no diversity
             "max_per_type": None,
-            "limit_names": 10,
+            "limit_labels": 10,
             "sort_order": 'Z-A',  # sort
             "offset": 0,  # page 1
             "max_related_collections": 100,
@@ -207,7 +207,7 @@ def test_collection_api_domain_details_pagination_by_string(self, test_test_clie
             "max_total_collections": 100,
             "name_diversity_ratio": None,  # no diversity
             "max_per_type": None,
-            "limit_names": 10,
+            "limit_labels": 10,
             "sort_order": 'Z-A',  # sort
             "offset": 100,  # page 2
             "max_related_collections": 100,
@@ -269,7 +269,7 @@ def test_collection_api_find_collections_by_member_list_az(self, test_test_clien
         response = test_test_client.post("/find_collections_by_member", json={
             "label": "australia",
             "sort_order": "A-Z",
-            "limit_names": lim,
+            "limit_labels": lim,
             "mode": 'domain_detail',
             "offset": 10,
             'max_results': 30
@@ -279,8 +279,8 @@ def test_collection_api_find_collections_by_member_list_az(self, test_test_clien
         response_json = response.json()
         collection_list = response_json['collections']
 
-        # test limit names
-        assert all([len(c['top_names']) <= lim for c in collection_list])
+        # test limit labels
+        assert all([len(c['top_labels']) <= lim for c in collection_list])
 
         # test A-Z sort
         titles = [c['title'] for c in collection_list]
@@ -308,7 +308,7 @@ def test_collection_api_find_collections_by_member_page_out_of_bounds(self, test
         response = test_test_client.post("/find_collections_by_member", json={
             "label": "softmachine",
             "mode": "domain_detail",
-            "limit_names": 10,
+            "limit_labels": 10,
             "sort_order": 'AI',  # sort
             "offset": 20,  # page out of bounds (offset >= n_matched_collections)
             "max_related_collections": 100,
@@ -331,7 +331,7 @@ def test_collection_api_find_collections_by_collection(self, test_test_client):
             "max_total_collections": 10,
             "name_diversity_ratio": 0.5,
             "max_per_type": 3,
-            "limit_names": 10,
+            "limit_labels": 10,
             "sort_order": 'Relevance'
         })
 
@@ -351,7 +351,7 @@ def test_collection_api_find_collections_by_collection_az(self, test_test_client
             "min_other_collections": 0,
             "max_other_collections": 4,
             "max_total_collections": 10,
-            "limit_names": 6,
+            "limit_labels": 6,
             "offset": 8,
             "sort_order": 'A-Z'
         })
@@ -362,8 +362,8 @@ def test_collection_api_find_collections_by_collection_az(self, test_test_client
 
         collection_list = response_json['related_collections']
 
-        # test limit names
-        assert all([len(c['top_names']) <= 6 for c in collection_list])
+        # test limit labels
+        assert all([len(c['top_labels']) <= 6 for c in collection_list])
 
         # test A-Z sort
         titles = [c['title'] for c in collection_list]
@@ -383,7 +383,7 @@ def test_collection_api_find_collections_by_collection_not_found(self, test_test
             "max_total_collections": 6,
             "name_diversity_ratio": 0.5,
             "max_per_type": 3,
-            "limit_names": 10,
+            "limit_labels": 10,
         })
         assert response.status_code == 404
 
@@ -402,10 +402,10 @@ def test_collection_api_member_dot(self, test_test_client):
         assert response.status_code == 422
 
     @mark.integration_test
-    def test_collection_api_instant_search_limit_names_gt_10(self, test_test_client):
+    def test_collection_api_instant_search_limit_labels_gt_10(self, test_test_client):
         response = test_test_client.post("/find_collections_by_string", json={
             "query": "australia",
-            "limit_names": 11,
+            "limit_labels": 11,
         })
         assert response.status_code == 422
 
@@ -568,8 +568,8 @@ def test_fetch_collection_members_pagination(self, test_test_client):
         response2_json = response2.json()
 
         # Verify different pages return different members
-        first_page_names = [s['name'] for s in response_json['suggestions']]
-        second_page_names = [s['name'] for s in response2_json['suggestions']]
+        first_page_names = [s['label'] for s in response_json['suggestions']]
+        second_page_names = [s['label'] for s in response2_json['suggestions']]
         assert not set(first_page_names).intersection(second_page_names)
 
     @mark.integration_test
@@ -600,7 +600,7 @@ def test_fetch_collection_members_high_offset(self, test_test_client):
 
     @mark.integration_test
     def test_fetch_collection_members_tokenized_names(self, test_test_client):
-        name2labeltokens = {
+        label2tokens = {
             "dualipa": ("dua", "lipa"),
             "thebeatles": ("the", "beatles"),
             "davidbowie": ("david", "bowie")
@@ -615,9 +615,9 @@ def test_fetch_collection_members_tokenized_names(self, test_test_client):
         assert response.status_code == 200
         response_json = response.json()
         for item in response_json['suggestions']:
-            assert ''.join(item['tokenized_label']) == item['name']
-            if item['name'] in name2labeltokens:
-                assert tuple(item['tokenized_label']) == name2labeltokens[item['name']]
+            assert ''.join(item['tokenized_label']) == item['label']
+            if item['label'] in label2tokens:
+                assert tuple(item['tokenized_label']) == label2tokens[item['label']]
 
     @mark.integration_test
     def test_get_collection_by_id(self, test_test_client):
@@ -630,9 +630,10 @@ def test_get_collection_by_id(self, test_test_client):
         assert collection['collection_id'] == "ri2QqxnAqZT7"
         assert 'title' in collection
         assert 'owner' in collection
-        assert 'number_of_names' in collection
+        assert 'number_of_labels' in collection
         assert 'last_updated_timestamp' in collection
-        assert 'top_names' in collection
+        assert 'top_labels' in collection
+        assert all([tuple(label.keys()) == ('label',) for label in collection['top_labels']])
         assert 'types' in collection
         assert 'avatar_emoji' in collection
         assert 'avatar_image' in collection
@@ -677,7 +678,7 @@ def test_collection_api_unavailability_find_collections_by_collection(self, test
             "min_other_collections": 0,
             "max_other_collections": 2,
             "max_total_collections": 10,
-            "limit_names": 6,
+            "limit_labels": 6,
             "offset": 8,
             "sort_order": 'A-Z'
         })