Skip to content

Commit

Permalink
chore: use snapshot tests
Browse files Browse the repository at this point in the history 
Uses `syrupy` to handle snapshotting of text outputs. To update the
snapshot files, run `pytest --snapshot-update` or `just test-update`.
  • Loading branch information
@JamesGuthrie
JamesGuthrie committed Nov 15, 2024
1 parent 2b330a4 commit 51550bd
Show file tree
Hide file tree
Showing 18 changed files with 786 additions and 759 deletions.
7 changes: 7 additions & 0 deletions projects/extension/build.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@
- clean-sql removes sql file artifacts from the sql dir
- clean-py removes python build artifacts from the extension src dir
- test runs the tests in the docker container
- test-update runs the tests in the docker container and updates snapshots
- test-server runs the test http server in the docker container
- lint-sql runs pgspot against the `ai--<this_version>.sql` file
- lint-py runs ruff linter against the python source files
Expand Down Expand Up @@ -605,6 +606,10 @@ def test() -> None:
subprocess.run("pytest", shell=True, check=True, env=os.environ, cwd=tests_dir())


def test_update() -> None:
subprocess.run("pytest --snapshot-update", shell=True, check=True, env=os.environ, cwd=tests_dir())


def lint_sql() -> None:
sql = sql_dir().joinpath(f"ai--{this_version()}.sql")
cmd = " ".join(
Expand Down Expand Up @@ -721,6 +726,8 @@ def run() -> None:
test_server()
elif action == "test":
test()
elif action == "test-update":
test_update()
elif action == "lint-sql":
lint_sql()
elif action == "lint-py":
Expand Down
3 changes: 3 additions & 0 deletions projects/extension/justfile
View file
Original file line number Diff line number Diff line change
Expand Up @@ -67,6 +67,9 @@ test-server:
test:
@./build.py test

test-update:
@./build.py test-update

lint-sql:
@./build.py lint-sql

Expand Down
1 change: 1 addition & 0 deletions projects/extension/requirements-test.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -7,3 +7,4 @@ python-dotenv==1.0.1
fastapi==0.112.0
fastapi-cli==0.0.5
psycopg[binary]==3.2.1
syrupy==4.7.2
238 changes: 238 additions & 0 deletions projects/extension/tests/contents/__snapshots__/test_contents.ambr
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,238 @@
# serializer version: 1
# name: test_contents
'''
DROP DATABASE
CREATE DATABASE
You are now connected to database "toc" as user "postgres".
CREATE EXTENSION
Objects in extension "ai"
Object description
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
event trigger _vectorizer_handle_drops
function ai.anthropic_generate(text,jsonb,integer,text,text,text,double precision,integer,text,text,text[],double precision,jsonb,jsonb,integer,double precision)
function ai.chunking_character_text_splitter(name,integer,integer,text,boolean)
function ai.chunking_recursive_character_text_splitter(name,integer,integer,text[],boolean)
function ai.cohere_chat_complete(text,text,text,text,text,jsonb,text,text,jsonb,boolean,jsonb,text,double precision,integer,integer,integer,double precision,integer,text[],double precision,double precision,jsonb,jsonb,boolean)
function ai.cohere_classify_simple(text,text[],text,text,jsonb,text)
function ai.cohere_classify(text,text[],text,text,jsonb,text)
function ai.cohere_detokenize(text,integer[],text,text)
function ai.cohere_embed(text,text,text,text,text,text)
function ai.cohere_list_models(text,text,text,boolean)
function ai.cohere_rerank_simple(text,text,jsonb,text,text,integer,integer)
function ai.cohere_rerank(text,text,jsonb,text,text,integer,text[],boolean,integer)
function ai.cohere_tokenize(text,text,text,text)
function ai.create_vectorizer(regclass,name,jsonb,jsonb,jsonb,jsonb,jsonb,jsonb,name,name,name,name,name,name,name[],boolean)
function ai.disable_vectorizer_schedule(integer)
function ai.drop_vectorizer(integer,boolean)
function ai.embedding_openai(text,integer,text,text)
function ai.enable_vectorizer_schedule(integer)
function ai.execute_vectorizer(integer)
function ai.formatting_python_template(text)
function ai.grant_ai_usage(name,boolean)
function ai.grant_secret(text,text)
function ai.grant_to()
function ai.grant_to(name[])
function ai.indexing_default()
function ai.indexing_diskann(integer,text,integer,integer,double precision,integer,integer,boolean)
function ai.indexing_hnsw(integer,text,integer,integer,boolean)
function ai.indexing_none()
function ai.ollama_chat_complete(text,jsonb,text,double precision,jsonb)
function ai.ollama_embed(text,text,text,double precision,jsonb)
function ai.ollama_generate(text,text,text,bytea[],double precision,jsonb,text,text,integer[])
function ai.ollama_list_models(text)
function ai.ollama_ps(text)
function ai.openai_chat_complete_simple(text,text,text)
function ai.openai_chat_complete(text,jsonb,text,text,text,double precision,jsonb,boolean,integer,integer,integer,double precision,jsonb,integer,text,double precision,double precision,jsonb,jsonb,text)
function ai.openai_detokenize(text,integer[])
function ai.openai_embed(text,integer[],text,text,text,integer,text)
function ai.openai_embed(text,text,text,text,text,integer,text)
function ai.openai_embed(text,text[],text,text,text,integer,text)
function ai.openai_list_models(text,text,text)
function ai.openai_moderate(text,text,text,text,text)
function ai.openai_tokenize(text,text)
function ai.processing_default(integer,integer)
function ai._resolve_indexing_default()
function ai._resolve_scheduling_default()
function ai.reveal_secret(text,boolean)
function ai.revoke_secret(text,text)
function ai.scheduling_default()
function ai.scheduling_none()
function ai.scheduling_timescaledb(interval,timestamp with time zone,boolean,text)
function ai._validate_chunking(jsonb,name,name)
function ai._validate_embedding(jsonb)
function ai._validate_formatting(jsonb,name,name)
function ai._validate_formatting_python_template(jsonb,name,name)
function ai._validate_indexing_diskann(jsonb)
function ai._validate_indexing_hnsw(jsonb)
function ai._validate_indexing(jsonb)
function ai._validate_processing(jsonb)
function ai._validate_scheduling(jsonb)
function ai._vectorizer_create_queue_table(name,name,jsonb,name[])
function ai._vectorizer_create_source_trigger(name,name,name,name,name,jsonb)
function ai._vectorizer_create_target_table(name,name,jsonb,name,name,integer,name[])
function ai._vectorizer_create_vector_index(name,name,jsonb)
function ai._vectorizer_create_view(name,name,name,name,jsonb,name,name,name[])
function ai._vectorizer_grant_to_source(name,name,name[])
function ai._vectorizer_grant_to_vectorizer(name[])
function ai._vectorizer_handle_drops()
function ai._vectorizer_job(integer,jsonb)
function ai.vectorizer_queue_pending(integer,boolean)
function ai._vectorizer_schedule_job(integer,jsonb)
function ai._vectorizer_should_create_vector_index(ai.vectorizer)
function ai._vectorizer_source_pk(regclass)
function ai._vectorizer_vector_index_exists(name,name,jsonb)
sequence ai.vectorizer_id_seq
table ai.feature_flag
table ai.migration
table ai._secret_permissions
table ai.vectorizer
table ai.vectorizer_errors
view ai.secret_permissions
view ai.vectorizer_status
(81 rows)

Table "ai._secret_permissions"
Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description
--------+------+-----------+----------+---------+----------+-------------+--------------+-------------
name | text | | not null | | extended | | |
role | text | | not null | | extended | | |
Indexes:
"_secret_permissions_pkey" PRIMARY KEY, btree (name, role)
Check constraints:
"_secret_permissions_name_check" CHECK (name = '*'::text OR name ~ '^[A-Za-z0-9_.]+$'::text)
Access method: heap

Index "ai._secret_permissions_pkey"
Column | Type | Key? | Definition | Storage | Stats target
--------+------+------+------------+----------+--------------
name | text | yes | name | extended |
role | text | yes | role | extended |
primary key, btree, for table "ai._secret_permissions"

Table "ai.feature_flag"
Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description
--------------------+--------------------------+-----------+----------+-------------------+----------+-------------+--------------+-------------
name | text | | not null | | extended | | |
applied_at_version | text | | not null | | extended | | |
applied_at | timestamp with time zone | | not null | clock_timestamp() | plain | | |
Indexes:
"feature_flag_pkey" PRIMARY KEY, btree (name)
Access method: heap

Index "ai.feature_flag_pkey"
Column | Type | Key? | Definition | Storage | Stats target
--------+------+------+------------+----------+--------------
name | text | yes | name | extended |
primary key, btree, for table "ai.feature_flag"

Table "ai.migration"
Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description
--------------------+--------------------------+-----------+----------+-------------------+----------+-------------+--------------+-------------
name | text | | not null | | extended | | |
applied_at_version | text | | not null | | extended | | |
applied_at | timestamp with time zone | | not null | clock_timestamp() | plain | | |
body | text | | not null | | extended | | |
Indexes:
"migration_pkey" PRIMARY KEY, btree (name)
Access method: heap

Index "ai.migration_pkey"
Column | Type | Key? | Definition | Storage | Stats target
--------+------+------+------------+----------+--------------
name | text | yes | name | extended |
primary key, btree, for table "ai.migration"

View "ai.secret_permissions"
Column | Type | Collation | Nullable | Default | Storage | Description
--------+------+-----------+----------+---------+----------+-------------
name | text | | | | extended |
role | text | | | | extended |
View definition:
SELECT name,
role
FROM ai._secret_permissions
WHERE to_regrole(role) IS NOT NULL AND pg_has_role(CURRENT_USER, role::name, 'member'::text);

Table "ai.vectorizer"
Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description
---------------+---------+-----------+----------+----------------------------------+----------+-------------+--------------+-------------
id | integer | | not null | generated by default as identity | plain | | |
source_schema | name | | not null | | plain | | |
source_table | name | | not null | | plain | | |
source_pk | jsonb | | not null | | extended | | |
target_schema | name | | not null | | plain | | |
target_table | name | | not null | | plain | | |
view_schema | name | | not null | | plain | | |
view_name | name | | not null | | plain | | |
trigger_name | name | | not null | | plain | | |
queue_schema | name | | | | plain | | |
queue_table | name | | | | plain | | |
config | jsonb | | not null | | extended | | |
Indexes:
"vectorizer_pkey" PRIMARY KEY, btree (id)
"vectorizer_target_schema_target_table_key" UNIQUE CONSTRAINT, btree (target_schema, target_table)
Referenced by:
TABLE "ai.vectorizer_errors" CONSTRAINT "vectorizer_errors_id_fkey" FOREIGN KEY (id) REFERENCES ai.vectorizer(id) ON DELETE CASCADE
Access method: heap

Table "ai.vectorizer_errors"
Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description
----------+--------------------------+-----------+----------+---------+----------+-------------+--------------+-------------
id | integer | | not null | | plain | | |
message | text | | | | extended | | |
details | jsonb | | | | extended | | |
recorded | timestamp with time zone | | not null | now() | plain | | |
Indexes:
"vectorizer_errors_id_recorded_idx" btree (id, recorded)
Foreign-key constraints:
"vectorizer_errors_id_fkey" FOREIGN KEY (id) REFERENCES ai.vectorizer(id) ON DELETE CASCADE
Access method: heap

Index "ai.vectorizer_errors_id_recorded_idx"
Column | Type | Key? | Definition | Storage | Stats target
----------+--------------------------+------+------------+---------+--------------
id | integer | yes | id | plain |
recorded | timestamp with time zone | yes | recorded | plain |
btree, for table "ai.vectorizer_errors"

Sequence "ai.vectorizer_id_seq"
Type | Start | Minimum | Maximum | Increment | Cycles? | Cache
---------+-------+---------+------------+-----------+---------+-------
integer | 1 | 1 | 2147483647 | 1 | no | 1
Sequence for identity column: ai.vectorizer.id

Index "ai.vectorizer_pkey"
Column | Type | Key? | Definition | Storage | Stats target
--------+---------+------+------------+---------+--------------
id | integer | yes | id | plain |
primary key, btree, for table "ai.vectorizer"

View "ai.vectorizer_status"
Column | Type | Collation | Nullable | Default | Storage | Description
---------------+---------+-----------+----------+---------+----------+-------------
id | integer | | | | plain |
source_table | text | C | | | extended |
target_table | text | C | | | extended |
view | text | C | | | extended |
pending_items | bigint | | | | plain |
View definition:
SELECT id,
format('%I.%I'::text, source_schema, source_table) AS source_table,
format('%I.%I'::text, target_schema, target_table) AS target_table,
format('%I.%I'::text, view_schema, view_name) AS view,
CASE
WHEN queue_table IS NOT NULL AND has_table_privilege(CURRENT_USER, format('%I.%I'::text, queue_schema, queue_table), 'select'::text) THEN ai.vectorizer_queue_pending(id)
ELSE NULL::bigint
END AS pending_items
FROM ai.vectorizer v;

Index "ai.vectorizer_target_schema_target_table_key"
Column | Type | Key? | Definition | Storage | Stats target
---------------+---------+------+---------------+---------+--------------
target_schema | cstring | yes | target_schema | plain |
target_table | cstring | yes | target_table | plain |
unique, btree, for table "ai.vectorizer"


'''
# ---
Loading

0 comments on commit 51550bd

Please sign in to comment.