New format handling CSV NDJSON

meilisearch/_httprequests.py

@@ -13,23 +13,33 @@ def __init__(self, config: Config) -> None:
         self.config = config
         self.headers = {
             'X-Meili-Api-Key': self.config.api_key,
-            'Content-Type': 'application/json'
         }
 
     def send_request(
         self,
         http_method: Callable,
         path: str,
-        body: Optional[Union[Dict[str, Any], List[Dict[str, Any]], List[str]]] = None,
+        body: Optional[Union[Dict[str, Any], List[Dict[str, Any]], List[str], str]] = None,
+        content_type: Optional[str] = None,
     ) -> Any:
+        if content_type:
+            self.headers['Content-Type'] = content_type
         try:
             request_path = self.config.url + '/' + path
-            request = http_method(
-                request_path,
-                timeout=self.config.timeout,
-                headers=self.headers,
-                data=json.dumps(body) if body else "null"
-            )
+            if isinstance(body, bytes):
+                request = http_method(
+                    request_path,
+                    timeout=self.config.timeout,
+                    headers=self.headers,
+                    data=body
+                )
+            else:
+                request = http_method(
+                    request_path,
+                    timeout=self.config.timeout,
+                    headers=self.headers,
+                    data=json.dumps(body) if body else "null"
+                )
             return self.__validate(request)
 
         except requests.exceptions.Timeout as err:
@@ -45,16 +55,18 @@ def get(
     def post(
         self,
         path: str,
-        body: Optional[Union[Dict[str, Any], List[Dict[str, Any]], List[str]]] = None,
+        body: Optional[Union[Dict[str, Any], List[Dict[str, Any]], List[str], str]] = None,
+        content_type: Optional[str] = 'application/json',
     ) -> Any:
-        return self.send_request(requests.post, path, body)
+        return self.send_request(requests.post, path, body, content_type)
 
     def put(
         self,
         path: str,
         body: Optional[Union[Dict[str, Any], List[Dict[str, Any]], List[str]]] = None,
+        content_type: Optional[str] = 'application/json',
     ) -> Any:
-        return self.send_request(requests.put, path, body)
+        return self.send_request(requests.put, path, body, content_type)
 
     def delete(
         self,

meilisearch/index.py

@@ -316,7 +316,6 @@ def get_documents(self, parameters: Optional[Dict[str, Any]] = None) -> List[Dic
         """
         if parameters is None:
             parameters = {}
-
         return self.http.get(
             f'{self.config.paths.index}/{self.uid}/{self.config.paths.document}?{urllib.parse.urlencode(parameters)}'
         )
@@ -346,11 +345,7 @@ def add_documents(
         MeiliSearchApiError
             An error containing details about why MeiliSearch can't process your request. MeiliSearch error codes are described here: https://docs.meilisearch.com/errors/#meilisearch-errors
         """
-        if primary_key is None:
-            url = f'{self.config.paths.index}/{self.uid}/{self.config.paths.document}'
-        else:
-            primary_key = urllib.parse.urlencode({'primaryKey': primary_key})
-            url = f'{self.config.paths.index}/{self.uid}/{self.config.paths.document}?{primary_key}'
+        url = self._build_url(primary_key)
         return self.http.post(url, documents)
 
     def add_documents_in_batches(
@@ -391,6 +386,118 @@ def add_documents_in_batches(
 
         return update_ids
 
+    def add_documents_json(
+        self,
+        str_documents: str,
+        primary_key: Optional[str] = None,
+    ) -> Dict[str, int]:
+        """Add string documents from JSON file to the index.
+
+        Parameters
+        ----------
+        str_documents:
+            String of document from a JSON file.
+        primary_key (optional):
+            The primary-key used in index. Ignored if already set up.
+
+        Returns
+        -------
+        update:
+            Dictionary containing an update id to track the action:
+            https://docs.meilisearch.com/reference/api/updates.html#get-an-update-status
+
+        Raises
+        ------
+        MeiliSearchApiError
+            An error containing details about why MeiliSearch can't process your request. MeiliSearch error codes are described here: https://docs.meilisearch.com/errors/#meilisearch-errors
+        """
+        return self.add_documents_raw(str_documents, primary_key, 'application/json')
+
+    def add_documents_csv(
+        self,
+        str_documents: str,
+        primary_key: Optional[str] = None,
+    ) -> Dict[str, int]:
+        """Add string documents from a CSV file to the index.
+
+        Parameters
+        ----------
+        str_documents:
+            String of document from a CSV file.
+        primary_key (optional):
+            The primary-key used in index. Ignored if already set up.
+
+        Returns
+        -------
+        update:
+            Dictionary containing an update id to track the action:
+            https://docs.meilisearch.com/reference/api/updates.html#get-an-update-status
+
+        Raises
+        ------
+        MeiliSearchApiError
+            An error containing details about why MeiliSearch can't process your request. MeiliSearch error codes are described here: https://docs.meilisearch.com/errors/#meilisearch-errors
+        """
+        return self.add_documents_raw(str_documents, primary_key, 'text/csv')
+
+    def add_documents_ndjson(
+        self,
+        str_documents: str,
+        primary_key: Optional[str] = None,
+    ) -> Dict[str, int]:
+        """Add string documents from a NDJSON file to the index.
+
+        Parameters
+        ----------
+        str_documents:
+            String of document from a NDJSON file.
+        primary_key (optional):
+            The primary-key used in index. Ignored if already set up.
+
+        Returns
+        -------
+        update:
+            Dictionary containing an update id to track the action:
+            https://docs.meilisearch.com/reference/api/updates.html#get-an-update-status
+
+        Raises
+        ------
+        MeiliSearchApiError
+            An error containing details about why MeiliSearch can't process your request. MeiliSearch error codes are described here: https://docs.meilisearch.com/errors/#meilisearch-errors
+        """
+        return self.add_documents_raw(str_documents, primary_key, 'application/x-ndjson')
+
+    def add_documents_raw(
+        self,
+        str_documents: str,
+        primary_key: Optional[str] = None,
+        content_type: Optional[str] = None,
+    ) -> Dict[str, int]:
+        """Add string documents to the index.
+
+        Parameters
+        ----------
+        str_documents:
+            String of document.
+        primary_key (optional):
+            The primary-key used in index. Ignored if already set up.
+        type:
+            The type of document. Type available: 'csv', 'json', 'jsonl'
+
+        Returns
+        -------
+        update:
+            Dictionary containing an update id to track the action:
+            https://docs.meilisearch.com/reference/api/updates.html#get-an-update-status
+
+        Raises
+        ------
+        MeiliSearchApiError
+            An error containing details about why MeiliSearch can't process your request. MeiliSearch error codes are described here: https://docs.meilisearch.com/errors/#meilisearch-errors
+        """
+        url = self._build_url(primary_key)
+        return self.http.post(url, str_documents, content_type)
+
     def update_documents(
         self,
         documents: List[Dict[str, Any]],
@@ -416,11 +523,7 @@ def update_documents(
         MeiliSearchApiError
             An error containing details about why MeiliSearch can't process your request. MeiliSearch error codes are described here: https://docs.meilisearch.com/errors/#meilisearch-errors
         """
-        if primary_key is None:
-            url = f'{self.config.paths.index}/{self.uid}/{self.config.paths.document}'
-        else:
-            primary_key = urllib.parse.urlencode({'primaryKey': primary_key})
-            url = f'{self.config.paths.index}/{self.uid}/{self.config.paths.document}?{primary_key}'
+        url = self._build_url(primary_key)
         return self.http.put(url, documents)
 
     def update_documents_in_batches(
@@ -1134,3 +1237,12 @@ def _iso_to_date_time(iso_date: Optional[Union[datetime, str]]) -> Optional[date
 
     def __settings_url_for(self, sub_route: str) -> str:
         return f'{self.config.paths.index}/{self.uid}/{self.config.paths.setting}/{sub_route}'
+
+    def _build_url(
+        self,
+        primary_key: Optional[str] = None,
+    ) -> str:
+        if primary_key is None:
+            return f'{self.config.paths.index}/{self.uid}/{self.config.paths.document}'
+        primary_key = urllib.parse.urlencode({'primaryKey': primary_key})
+        return f'{self.config.paths.index}/{self.uid}/{self.config.paths.document}?{primary_key}'

meilisearch/tests/conftest.py

@@ -35,9 +35,33 @@ def small_movies():
     """
     Runs once per session. Provides the content of small_movies.json.
     """
-    with open('./datasets/small_movies.json', 'r', encoding="utf8") as movie_file:
+    with open('./datasets/small_movies.json', 'r', encoding='utf-8') as movie_file:
         yield json.loads(movie_file.read())
 
+@fixture(scope='session')
+def small_movies_json_file():
+    """
+    Runs once per session. Provides the content of small_movies.json from read.
+    """
+    with open('./datasets/small_movies.json', 'r', encoding='utf-8') as movie_json_file:
+        return movie_json_file.read().encode('utf-8')
+
+@fixture(scope='session')
+def songs_csv():
+    """
+    Runs once per session. Provides the content of songs.csv from read..
+    """
+    with open('./datasets/songs.csv', 'r', encoding='utf-8') as song_csv_file:
+        return song_csv_file.read().encode('utf-8')
+
+@fixture(scope='session')
+def songs_ndjson():
+    """
+    Runs once per session. Provides the content of songs.ndjson from read..
+    """
+    with open('./datasets/songs.ndjson', 'r', encoding='utf-8') as song_ndjson_file:
+        return song_ndjson_file.read().encode('utf-8')
+
 @fixture(scope='function')
 def empty_index(client):
     def index_maker(index_name=common.INDEX_UID):

meilisearch/tests/index/test_index_document_meilisearch.py

@@ -144,3 +144,36 @@ def test_delete_all_documents(index_with_documents):
     response = index.get_documents()
     assert isinstance(response, list)
     assert response == []
+
+def test_add_documents_csv(empty_index, songs_csv):
+    """Tests adding new documents to a clean index."""
+    index = empty_index()
+    response = index.add_documents_csv(songs_csv)
+    assert isinstance(response, dict)
+    assert 'updateId' in response
+    update = index.wait_for_pending_update(response['updateId'])
+    assert update['status'] == 'processed'
+    assert update['type']['number'] != 0
+    assert index.get_primary_key() == 'id'
+
+def test_add_documents_json(empty_index, small_movies_json_file):
+    """Tests adding new documents to a clean index."""
+    index = empty_index()
+    response = index.add_documents_json(small_movies_json_file)
+    assert isinstance(response, dict)
+    assert 'updateId' in response
+    update = index.wait_for_pending_update(response['updateId'])
+    assert update['status'] == 'processed'
+    assert update['type']['number'] != 0
+    assert index.get_primary_key() == 'id'
+
+def test_add_documents_ndjson(empty_index, songs_ndjson):
+    """Tests adding new documents to a clean index."""
+    index = empty_index()
+    response = index.add_documents_ndjson(songs_ndjson)
+    assert isinstance(response, dict)
+    assert 'updateId' in response
+    update = index.wait_for_pending_update(response['updateId'])
+    assert update['status'] == 'processed'
+    assert update['type']['number'] != 0
+    assert index.get_primary_key() == 'id'