Skip to content

Commit f297d60

Browse files
mattgotteinermattgotteiner
committed
update
1 parent 0c91e8b commit f297d60

File tree

3 files changed

+171
-11
lines changed

3 files changed

+171
-11
lines changed

‎Quickstart-ACL/requirements.txt‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,4 +6,4 @@ requests
66
msgraph-sdk
77

88
--extra-index-url https://pkgs.dev.azure.com/azure-sdk/public/_packaging/azure-sdk-for-python/pypi/simple/
9-
azure-search-documents==11.6.0a20250505003
9+
azure-search-documents==11.6.0a20250507002

‎Quickstart-Document-Permissions/document-permissions.ipynb‎

Lines changed: 168 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -8,9 +8,17 @@
88
"## Document Permissions in Azure AI Search"
99
]
1010
},
11+
{
12+
"cell_type": "markdown",
13+
"id": "f445040a",
14+
"metadata": {},
15+
"source": [
16+
"## 1. Load Connections"
17+
]
18+
},
1119
{
1220
"cell_type": "code",
13-
"execution_count": 10,
21+
"execution_count": 33,
1422
"id": "0b40bb5b",
1523
"metadata": {},
1624
"outputs": [],
@@ -30,12 +38,21 @@
3038
"adls_gen2_account_name = os.getenv(\"AZURE_STORAGE_ACCOUNT_NAME\", \"documentpermissionssample\")\n",
3139
"adls_gen2_container_name = os.getenv(\"AZURE_STORAGE_CONTAINER_NAME\", \"documentpermissionssample\")\n",
3240
"adls_gen2_connection_string = os.environ[\"AZURE_STORAGE_CONNECTION_STRING\"]\n",
41+
"adls_gen2_resource_id = os.environ[\"AZURE_STORAGE_RESOURCE_ID\"]\n",
3342
"token_provider = get_bearer_token_provider(credential, \"https://search.azure.com/.default\")"
3443
]
3544
},
45+
{
46+
"cell_type": "markdown",
47+
"id": "2d46b940",
48+
"metadata": {},
49+
"source": [
50+
"## 2. Create Index"
51+
]
52+
},
3653
{
3754
"cell_type": "code",
38-
"execution_count": 2,
55+
"execution_count": 34,
3956
"id": "2f981cad",
4057
"metadata": {},
4158
"outputs": [
@@ -56,8 +73,9 @@
5673
" name=index_name,\n",
5774
" fields=[\n",
5875
" SearchField(name=\"id\", type=\"Edm.String\", key=True, filterable=True, sortable=True),\n",
59-
" SearchField(name=\"oid\", type=\"Collection(Edm.String)\", filterable=True, permission_filter=PermissionFilter.USER_IDS),\n",
60-
" SearchField(name=\"group\", type=\"Collection(Edm.String)\", filterable=True, permission_filter=PermissionFilter.GROUP_IDS),\n",
76+
" SearchField(name=\"content\", type=\"Edm.String\", searchable=True, filterable=False, sortable=False),\n",
77+
" SearchField(name=\"oids\", type=\"Collection(Edm.String)\", filterable=True, permission_filter=PermissionFilter.USER_IDS),\n",
78+
" SearchField(name=\"groups\", type=\"Collection(Edm.String)\", filterable=True, permission_filter=PermissionFilter.GROUP_IDS),\n",
6179
" SearchField(name=\"metadata_storage_path\", type=\"Edm.String\", searchable=True),\n",
6280
" SearchField(name=\"metadata_storage_name\", type=\"Edm.String\", searchable=True)\n",
6381
" ],\n",
@@ -68,9 +86,17 @@
6886
"print(f\"Index '{index_name}' created with permission filter option enabled.\")"
6987
]
7088
},
89+
{
90+
"cell_type": "markdown",
91+
"id": "2b8945a2",
92+
"metadata": {},
93+
"source": [
94+
"## 3. Create data source"
95+
]
96+
},
7197
{
7298
"cell_type": "code",
73-
"execution_count": 11,
99+
"execution_count": 35,
74100
"id": "b25aaf7b",
75101
"metadata": {},
76102
"outputs": [
@@ -89,7 +115,7 @@
89115
"datasource = SearchIndexerDataSourceConnection(\n",
90116
" name=datasource_name,\n",
91117
" type=SearchIndexerDataSourceType.ADLS_GEN2,\n",
92-
" connection_string=adls_gen2_connection_string,\n",
118+
" connection_string=f\"ResourceId={adls_gen2_resource_id};\",\n",
93119
" container=SearchIndexerDataContainer(name=adls_gen2_container_name),\n",
94120
" indexer_permission_options=[IndexerPermissionOption.GROUP_IDS]\n",
95121
")\n",
@@ -98,9 +124,80 @@
98124
"print(f\"Datasource '{datasource_name}' created with permission filter option enabled.\")"
99125
]
100126
},
127+
{
128+
"cell_type": "markdown",
129+
"id": "ff5b912d",
130+
"metadata": {},
131+
"source": [
132+
"## 4. Get group id"
133+
]
134+
},
135+
{
136+
"cell_type": "code",
137+
"execution_count": 36,
138+
"id": "329fe160",
139+
"metadata": {},
140+
"outputs": [],
141+
"source": [
142+
"from msgraph import GraphServiceClient\n",
143+
"client = GraphServiceClient(credentials=credential, scopes=[\"https://graph.microsoft.com/.default\"])\n",
144+
"\n",
145+
"groups = await client.me.member_of.get()\n",
146+
"group_id = groups.value[0].id "
147+
]
148+
},
149+
{
150+
"cell_type": "markdown",
151+
"id": "20588dc3",
152+
"metadata": {},
153+
"source": [
154+
"## 5. Upload sample directory and file"
155+
]
156+
},
157+
{
158+
"cell_type": "code",
159+
"execution_count": 37,
160+
"id": "acd28b29",
161+
"metadata": {},
162+
"outputs": [
163+
{
164+
"data": {
165+
"text/plain": [
166+
"{'counters': {'directories_successful': 2, 'files_successful': 1, 'failure_count': 0}, 'continuation': None}"
167+
]
168+
},
169+
"execution_count": 37,
170+
"metadata": {},
171+
"output_type": "execute_result"
172+
}
173+
],
174+
"source": [
175+
"from azure.storage.filedatalake import DataLakeServiceClient\n",
176+
"\n",
177+
"service = DataLakeServiceClient.from_connection_string(adls_gen2_connection_string, credential=credential)\n",
178+
"container = service.get_file_system_client(adls_gen2_container_name)\n",
179+
"if not container.exists():\n",
180+
" container.create_file_system()\n",
181+
"data_dir_client = container.get_directory_client(\"data\")\n",
182+
"data_dir_client.create_directory()\n",
183+
"file_client = data_dir_client.create_file(\"sample.txt\")\n",
184+
"file_client.upload_data(\"This is a sample file.\", overwrite=True)\n",
185+
"\n",
186+
"root_dir_client = container.get_directory_client(\"/\")\n",
187+
"root_dir_client.update_access_control_recursive(f\"group:{group_id}:rwx\")\n"
188+
]
189+
},
190+
{
191+
"cell_type": "markdown",
192+
"id": "ca6de2ad",
193+
"metadata": {},
194+
"source": [
195+
"## 6. Run indexer"
196+
]
197+
},
101198
{
102199
"cell_type": "code",
103-
"execution_count": 15,
200+
"execution_count": 39,
104201
"id": "2ce7eb5e",
105202
"metadata": {},
106203
"outputs": [
@@ -120,14 +217,76 @@
120217
" target_index_name=index_name,\n",
121218
" data_source_name=datasource_name,\n",
122219
" field_mappings=[\n",
123-
" FieldMapping(source_field_name=\"metadata_group_ids\", target_field_name=\"group\"),\n",
124-
" FieldMapping(source_field_name=\"metadata_user_ids\", target_field_name=\"oid\"),\n",
220+
" FieldMapping(source_field_name=\"metadata_group_ids\", target_field_name=\"groups\"),\n",
221+
" FieldMapping(source_field_name=\"metadata_user_ids\", target_field_name=\"oids\"),\n",
125222
" ]\n",
126223
")\n",
127224
"\n",
128225
"indexer_client.create_or_update_indexer(indexer)\n",
129226
"print(f\"Indexer '{indexer_name}' created\")\n"
130227
]
228+
},
229+
{
230+
"cell_type": "markdown",
231+
"id": "987dd496",
232+
"metadata": {},
233+
"source": [
234+
"## 7. Search sample data using x-ms-query-source-authorization "
235+
]
236+
},
237+
{
238+
"cell_type": "code",
239+
"execution_count": 43,
240+
"id": "7a899da1",
241+
"metadata": {},
242+
"outputs": [
243+
{
244+
"name": "stdout",
245+
"output_type": "stream",
246+
"text": [
247+
"Path: https://magotteiadlsgen2.blob.core.windows.net/documentpermissionssample/data/sample.txt, OID: ['none'], Group: ['ec5aece9-33fc-4b2e-abe1-aedf771357a3']\n"
248+
]
249+
}
250+
],
251+
"source": [
252+
"from azure.search.documents import SearchClient\n",
253+
"search_client = SearchClient(endpoint=endpoint, index_name=index_name, credential=credential)\n",
254+
"\n",
255+
"results = search_client.search(search_text=\"*\", x_ms_query_source_authorization=token_provider(), select=\"metadata_storage_path,oids,groups\", order_by=\"id asc\")\n",
256+
"for result in results:\n",
257+
" print(f\"Path: {result['metadata_storage_path']}, OID: {result['oids']}, Group: {result['groups']}\")"
258+
]
259+
},
260+
{
261+
"cell_type": "markdown",
262+
"id": "c712ab8c",
263+
"metadata": {},
264+
"source": [
265+
"## 8. Search sample data without x-ms-query-source-authorization "
266+
]
267+
},
268+
{
269+
"cell_type": "code",
270+
"execution_count": 44,
271+
"id": "72d203f0",
272+
"metadata": {},
273+
"outputs": [
274+
{
275+
"name": "stdout",
276+
"output_type": "stream",
277+
"text": [
278+
"Path: https://magotteiadlsgen2.blob.core.windows.net/documentpermissionssample/data/sample.txt, OID: ['none'], Group: ['ec5aece9-33fc-4b2e-abe1-aedf771357a3']\n"
279+
]
280+
}
281+
],
282+
"source": [
283+
"from azure.search.documents import SearchClient\n",
284+
"search_client = SearchClient(endpoint=endpoint, index_name=index_name, credential=credential)\n",
285+
"\n",
286+
"results = search_client.search(search_text=\"*\", x_ms_query_source_authorization=None, select=\"metadata_storage_path,oids,groups\", order_by=\"id asc\")\n",
287+
"for result in results:\n",
288+
" print(f\"Path: {result['metadata_storage_path']}, OID: {result['oids']}, Group: {result['groups']}\")"
289+
]
131290
}
132291
],
133292
"metadata": {

‎Quickstart-Document-Permissions/requirements.txt‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,7 @@ ipykernel
44
dotenv
55
requests
66
msgraph-sdk
7+
azure-storage-file-datalake
78

89
--extra-index-url https://pkgs.dev.azure.com/azure-sdk/public/_packaging/azure-sdk-for-python/pypi/simple/
9-
azure-search-documents==11.6.0a20250505003
10+
azure-search-documents==11.6.0a20250507002

0 commit comments

Comments
 (0)