chore: import upstream snapshot with attribution

sdk/python/test/test_frontend_api/common.py

@@ -0,0 +1,115 @@
+#
+#  Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+
+import os
+
+import requests
+
+HOST_ADDRESS = os.getenv("HOST_ADDRESS", "http://127.0.0.1:9380")
+API_VERSION = "v1"
+DATASETS_API_URL = f"/api/{API_VERSION}/datasets"
+
+DATASET_NAME_LIMIT = 128
+
+
+def create_dataset(auth, payload=None):
+    url = f"{HOST_ADDRESS}{DATASETS_API_URL}"
+    res = requests.post(url=url, headers={"Content-Type": "application/json"}, auth=auth, json=payload)
+    return res.json()
+
+
+def list_dataset(auth, params=None):
+    url = f"{HOST_ADDRESS}{DATASETS_API_URL}"
+    res = requests.get(url=url, headers={"Content-Type": "application/json"}, auth=auth, params=params)
+    return res.json()
+
+
+def rm_dataset(auth, dataset_ids):
+    url = f"{HOST_ADDRESS}{DATASETS_API_URL}"
+    res = requests.delete(url=url, headers={"Content-Type": "application/json"}, auth=auth, json={"ids": dataset_ids})
+    return res.json()
+
+
+def update_dataset(auth, dataset_id, payload=None):
+    url = f"{HOST_ADDRESS}{DATASETS_API_URL}/{dataset_id}"
+    res = requests.put(url=url, headers={"Content-Type": "application/json"}, auth=auth, json=payload)
+    return res.json()
+
+
+def upload_file(auth, dataset_id, path):
+    authorization = {"Authorization": auth}
+    url = f"{HOST_ADDRESS}/v1/document/upload"
+    json_req = {
+        "kb_id": dataset_id,
+    }
+
+    file = {"file": open(f"{path}", "rb")}
+
+    res = requests.post(url=url, headers=authorization, files=file, data=json_req)
+    return res.json()
+
+
+def list_document(auth, dataset_id):
+    authorization = {"Authorization": auth}
+    url = f"{HOST_ADDRESS}/v1/document/list?id={dataset_id}"
+    json = {}
+    res = requests.post(url=url, headers=authorization, json=json)
+    return res.json()
+
+
+def get_docs_info(auth, dataset_id, doc_ids=None, doc_id=None):
+    """
+    Get document information by IDs.
+
+    Args:
+        auth: Authorization header
+        dataset_id: Dataset ID
+        doc_ids: List of document IDs (use for multiple) - exclusive with doc_id
+        doc_id: Single document ID (use for one) - exclusive with doc_ids
+
+    Raises:
+        ValueError: If both doc_id and doc_ids are provided
+    """
+    # Validate that id and ids are not used together
+    if doc_id and doc_ids:
+        raise ValueError("Cannot use both 'id' and 'ids' parameters at the same time.")
+
+    authorization = {"Authorization": auth}
+    params = {}
+    if doc_ids:
+        # Multiple IDs
+        for id in doc_ids:
+            params.append(("ids", id))
+    elif doc_id:
+        # Single ID
+        params["id"] = doc_id
+
+    # Use /api/v1 prefix for dataset API
+    url = f"{HOST_ADDRESS}/api/v1/datasets/{dataset_id}/documents"
+    res = requests.get(url=url, headers=authorization, params=params)
+    return res.json()
+
+
+def parse_docs(auth, doc_ids):
+    authorization = {"Authorization": auth}
+    json_req = {"doc_ids": doc_ids, "run": 1}
+    url = f"{HOST_ADDRESS}/api/v1/documents/ingest"
+    res = requests.post(url=url, headers=authorization, json=json_req)
+    return res.json()
+
+
+def parse_file(auth, document_id):
+    pass

sdk/python/test/test_frontend_api/get_email.py

@@ -0,0 +1,20 @@
+#
+#  Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+
+
+def test_get_email(get_email):
+    print("\nEmail account:", flush=True)
+    print(f"{get_email}\n", flush=True)

sdk/python/test/test_frontend_api/test_chunk.py

@@ -0,0 +1,74 @@
+#
+#  Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+from common import create_dataset, list_dataset, rm_dataset, upload_file
+from common import list_document, get_docs_info, parse_docs
+from time import sleep
+from timeit import default_timer as timer
+
+
+def test_parse_txt_document(get_auth):
+    # create dataset
+    res = create_dataset(get_auth, {"name": "test_parse_txt_document"})
+    assert res.get("code") == 0, f"{res.get('message')}"
+
+    # list dataset
+    page_number = 1
+    dataset_list = []
+    dataset_id = None
+    while True:
+        res = list_dataset(get_auth, {"page": page_number, "page_size": 150})
+        data = res.get("data")
+        if isinstance(data, dict):
+            data = data.get("kbs", [])
+        for item in data:
+            dataset_id = item.get("id")
+            dataset_list.append(dataset_id)
+        if len(dataset_list) < page_number * 150:
+            break
+        page_number += 1
+
+    filename = "ragflow_test.txt"
+    res = upload_file(get_auth, dataset_id, f"../test_sdk_api/test_data/{filename}")
+    assert res.get("code") == 0, f"{res.get('message')}"
+
+    res = list_document(get_auth, dataset_id)
+
+    doc_id_list = []
+    for doc in res["data"]["docs"]:
+        doc_id_list.append(doc["id"])
+
+    res = get_docs_info(get_auth, dataset_id, doc_ids=doc_id_list)
+    print(doc_id_list)
+    doc_count = len(doc_id_list)
+    res = parse_docs(get_auth, doc_id_list)
+
+    start_ts = timer()
+    while True:
+        res = get_docs_info(get_auth, dataset_id, doc_ids=doc_id_list)
+        finished_count = 0
+        for doc_info in res["data"]:
+            if doc_info["progress"] == 1:
+                finished_count += 1
+        if finished_count == doc_count:
+            break
+        sleep(1)
+    print("time cost {:.1f}s".format(timer() - start_ts))
+
+    # delete dataset
+    if dataset_list:
+        res = rm_dataset(get_auth, dataset_list)
+        assert res.get("code") == 0, f"{res.get('message')}"
+    print(f"{len(dataset_list)} datasets are deleted")

sdk/python/test/test_frontend_api/test_dataset.py

@@ -0,0 +1,198 @@
+#
+#  Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+
+from common import create_dataset, list_dataset, rm_dataset, update_dataset, DATASET_NAME_LIMIT
+import re
+import random
+import string
+
+
+def test_dataset(get_auth):
+    # create dataset
+    res = create_dataset(get_auth, {"name": "test_create_dataset"})
+    assert res.get("code") == 0, f"{res.get('message')}"
+
+    # list dataset
+    page_number = 1
+    dataset_list = []
+    while True:
+        res = list_dataset(get_auth, {"page": page_number, "page_size": 150})
+        data = res.get("data")
+        if isinstance(data, dict):
+            data = data.get("kbs", [])
+        for item in data:
+            dataset_id = item.get("id")
+            dataset_list.append(dataset_id)
+        if len(dataset_list) < page_number * 150:
+            break
+        page_number += 1
+
+    print(f"found {len(dataset_list)} datasets")
+    # delete dataset
+    if dataset_list:
+        res = rm_dataset(get_auth, dataset_list)
+        assert res.get("code") == 0, f"{res.get('message')}"
+    print(f"{len(dataset_list)} datasets are deleted")
+
+
+def test_dataset_1k_dataset(get_auth):
+    # create dataset
+    for i in range(1000):
+        res = create_dataset(get_auth, {"name": f"test_create_dataset_{i}"})
+        assert res.get("code") == 0, f"{res.get('message')}"
+
+    # list dataset
+    page_number = 1
+    dataset_list = []
+    while True:
+        res = list_dataset(get_auth, {"page": page_number, "page_size": 150})
+        data = res.get("data")
+        if isinstance(data, dict):
+            data = data.get("kbs", [])
+        for item in data:
+            dataset_id = item.get("id")
+            dataset_list.append(dataset_id)
+        if len(dataset_list) < page_number * 150:
+            break
+        page_number += 1
+
+    print(f"found {len(dataset_list)} datasets")
+    # delete dataset
+    if dataset_list:
+        res = rm_dataset(get_auth, dataset_list)
+        assert res.get("code") == 0, f"{res.get('message')}"
+    print(f"{len(dataset_list)} datasets are deleted")
+
+
+def test_duplicated_name_dataset(get_auth):
+    # create dataset
+    for i in range(20):
+        res = create_dataset(get_auth, {"name": "test_create_dataset"})
+        assert res.get("code") == 0, f"{res.get('message')}"
+
+    # list dataset
+    res = list_dataset(get_auth, {"page": 1})
+    data = res.get("data")
+    if isinstance(data, dict):
+        data = data.get("kbs", [])
+    dataset_list = []
+    pattern = r"^test_create_dataset.*"
+    for item in data:
+        dataset_name = item.get("name")
+        dataset_id = item.get("id")
+        dataset_list.append(dataset_id)
+        match = re.match(pattern, dataset_name)
+        assert match is not None
+
+    if dataset_list:
+        res = rm_dataset(get_auth, dataset_list)
+        assert res.get("code") == 0, f"{res.get('message')}"
+    print(f"{len(dataset_list)} datasets are deleted")
+
+
+def test_invalid_name_dataset(get_auth):
+    # create dataset
+    res = create_dataset(get_auth, {"name": 0})
+    assert res["code"] != 0
+
+    res = create_dataset(get_auth, {"name": ""})
+    assert res["code"] != 0
+
+    long_string = ""
+
+    while len(long_string.encode("utf-8")) <= DATASET_NAME_LIMIT:
+        long_string += random.choice(string.ascii_letters + string.digits)
+
+    res = create_dataset(get_auth, {"name": long_string})
+    assert res["code"] != 0
+    print(res)
+
+
+def test_update_different_params_dataset_success(get_auth):
+    # create dataset
+    res = create_dataset(get_auth, {"name": "test_create_dataset"})
+    assert res.get("code") == 0, f"{res.get('message')}"
+
+    # list dataset
+    page_number = 1
+    dataset_list = []
+    while True:
+        res = list_dataset(get_auth, {"page": page_number, "page_size": 150})
+        data = res.get("data")
+        if isinstance(data, dict):
+            data = data.get("kbs", [])
+        for item in data:
+            dataset_id = item.get("id")
+            dataset_list.append(dataset_id)
+        if len(dataset_list) < page_number * 150:
+            break
+        page_number += 1
+
+    print(f"found {len(dataset_list)} datasets")
+    dataset_id = dataset_list[0]
+
+    res = update_dataset(
+        get_auth,
+        dataset_id,
+        {
+            "name": "test_update_dataset",
+            "description": "test",
+            "permission": "me",
+            "chunk_method": "presentation",
+            "language": "spanish",
+        },
+    )
+    assert res.get("code") == 0, f"{res.get('message')}"
+
+    # delete dataset
+    if dataset_list:
+        res = rm_dataset(get_auth, dataset_list)
+        assert res.get("code") == 0, f"{res.get('message')}"
+    print(f"{len(dataset_list)} datasets are deleted")
+
+
+# update dataset with different parameters
+def test_update_different_params_dataset_fail(get_auth):
+    # create dataset
+    res = create_dataset(get_auth, {"name": "test_create_dataset"})
+    assert res.get("code") == 0, f"{res.get('message')}"
+
+    # list dataset
+    page_number = 1
+    dataset_list = []
+    while True:
+        res = list_dataset(get_auth, {"page": page_number, "page_size": 150})
+        data = res.get("data")
+        if isinstance(data, dict):
+            data = data.get("kbs", [])
+        for item in data:
+            dataset_id = item.get("id")
+            dataset_list.append(dataset_id)
+        if len(dataset_list) < page_number * 150:
+            break
+        page_number += 1
+
+    print(f"found {len(dataset_list)} datasets")
+    dataset_id = dataset_list[0]
+
+    res = update_dataset(get_auth, dataset_id, {"id": "xxx"})
+    assert res.get("code") == 101
+
+    # delete dataset
+    if dataset_list:
+        res = rm_dataset(get_auth, dataset_list)
+        assert res.get("code") == 0, f"{res.get('message')}"
+    print(f"{len(dataset_list)} datasets are deleted")