16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367 | class SharePointReader(BaseReader):
"""SharePoint reader.
Reads folders from the SharePoint site from a folder under documents.
"""
def __init__(
self,
client_id: str,
client_secret: str,
tenant_id: str,
) -> None:
"""
Initializes an instance of SharePoint reader.
Args:
client_id: The Application ID for the app registered in Microsoft Azure Portal.
The application must also be configured with MS Graph permissions "Files.ReadAll", "Sites.ReadAll" and BrowserSiteLists.Read.All.
client_secret: The application secret for the app registered in Azure.
tenant_id: Unique identifier of the Azure Active Directory Instance.
"""
self.client_id = (client_id,)
self.client_secret = (client_secret,)
self.tenant_id = tenant_id
self._authorization_headers = None
def _get_access_token(self) -> str:
"""
Gets the access_token for accessing file from SharePoint.
Returns:
str: The access_token for accessing the file.
Raises:
ValueError: If there is an error in obtaining the access_token.
"""
authority = f"https://login.microsoftonline.com/{self.tenant_id}/oauth2/token"
payload = {
"grant_type": "client_credentials",
"client_id": self.client_id,
"client_secret": self.client_secret,
"resource": "https://graph.microsoft.com/",
}
response = requests.post(
url=authority,
data=payload,
)
if response.status_code == 200 and "access_token" in response.json():
return response.json()["access_token"]
else:
logger.error(response.json()["error"])
raise ValueError(response.json()["error_description"])
def _get_site_id_with_host_name(self, access_token, sharepoint_site_name) -> str:
"""
Retrieves the site ID of a SharePoint site using the provided site name.
Args:
sharepoint_site_name (str): The name of the SharePoint site.
Returns:
str: The ID of the SharePoint site.
Raises:
Exception: If the specified SharePoint site is not found.
"""
site_information_endpoint = (
f"https://graph.microsoft.com/v1.0/sites?search={sharepoint_site_name}"
)
self._authorization_headers = {"Authorization": f"Bearer {access_token}"}
response = requests.get(
url=site_information_endpoint,
headers=self._authorization_headers,
)
if response.status_code == 200 and "value" in response.json():
if (
len(response.json()["value"]) > 0
and "id" in response.json()["value"][0]
):
return response.json()["value"][0]["id"]
else:
raise ValueError(
f"The specified sharepoint site {sharepoint_site_name} is not found."
)
else:
if "error_description" in response.json():
logger.error(response.json()["error"])
raise ValueError(response.json()["error_description"])
raise ValueError(response.json()["error"])
def _get_drive_id(self) -> str:
"""
Retrieves the drive ID of the SharePoint site.
Returns:
str: The ID of the SharePoint site drive.
Raises:
ValueError: If there is an error in obtaining the drive ID.
"""
self._drive_id_endpoint = f"https://graph.microsoft.com/v1.0/sites/{self._site_id_with_host_name}/drives"
response = requests.get(
url=self._drive_id_endpoint,
headers=self._authorization_headers,
)
if response.status_code == 200 and "value" in response.json():
if (
len(response.json()["value"]) > 0
and "id" in response.json()["value"][0]
):
return response.json()["value"][0]["id"]
else:
raise ValueError(
"Error occurred while fetching the drives for the sharepoint site."
)
else:
logger.error(response.json()["error"])
raise ValueError(response.json()["error_description"])
def _get_sharepoint_folder_id(self, folder_path: str) -> str:
"""
Retrieves the folder ID of the SharePoint site.
Args:
folder_path (str): The path of the folder in the SharePoint site.
Returns:
str: The ID of the SharePoint site folder.
"""
folder_id_endpoint = (
f"{self._drive_id_endpoint}/{self._drive_id}/root:/{folder_path}"
)
response = requests.get(
url=folder_id_endpoint,
headers=self._authorization_headers,
)
if response.status_code == 200 and "id" in response.json():
return response.json()["id"]
else:
raise ValueError(response.json()["error"])
def _download_files_and_extract_metadata(
self,
folder_id: str,
download_dir: str,
include_subfolders: bool = False,
) -> Dict[str, str]:
"""
Downloads files from the specified folder ID and extracts metadata.
Args:
folder_id (str): The ID of the folder from which the files should be downloaded.
download_dir (str): The directory where the files should be downloaded.
include_subfolders (bool): If True, files from all subfolders are downloaded.
Returns:
Dict[str, str]: A dictionary containing the metadata of the downloaded files.
Raises:
ValueError: If there is an error in downloading the files.
"""
folder_info_endpoint = (
f"{self._drive_id_endpoint}/{self._drive_id}/items/{folder_id}/children"
)
response = requests.get(
url=folder_info_endpoint,
headers=self._authorization_headers,
)
if response.status_code == 200:
data = response.json()
metadata = {}
for item in data["value"]:
if include_subfolders and "folder" in item:
sub_folder_download_dir = os.path.join(download_dir, item["name"])
subfolder_metadata = self._download_files_and_extract_metadata(
folder_id=item["id"],
download_dir=sub_folder_download_dir,
include_subfolders=include_subfolders,
)
metadata.update(subfolder_metadata)
elif "file" in item:
file_metadata = self._download_file(item, download_dir)
metadata.update(file_metadata)
return metadata
else:
logger.error(response.json()["error"])
raise ValueError(response.json()["error"])
def _download_file_by_url(self, item: Dict[str, Any], download_dir: str) -> str:
"""
Downloads the file from the provided URL.
Args:
item (Dict[str, Any]): Dictionary containing file metadata.
download_dir (str): The directory where the files should be downloaded.
Returns:
str: The path of the downloaded file in the temporary directory.
"""
# Get the download URL for the file.
file_download_url = item["@microsoft.graph.downloadUrl"]
file_name = item["name"]
response = requests.get(file_download_url)
# Create the directory if it does not exist and save the file.
if not os.path.exists(download_dir):
os.makedirs(download_dir)
file_path = os.path.join(download_dir, file_name)
with open(file_path, "wb") as f:
f.write(response.content)
return file_path
def _extract_metadata_for_file(self, item: Dict[str, Any]) -> Dict[str, str]:
"""
Extracts metadata related to the file.
Parameters:
- item (Dict[str, str]): Dictionary containing file metadata.
Returns:
- Dict[str, str]: A dictionary containing the extracted metadata.
"""
# Extract the required metadata for file.
return {
"file_id": item.get("id"),
"file_name": item.get("name"),
"url": item.get("webUrl"),
}
def _download_file(
self,
item: Dict[str, Any],
download_dir: str,
):
metadata = {}
file_path = self._download_file_by_url(item, download_dir)
metadata[file_path] = self._extract_metadata_for_file(item)
return metadata
def _download_files_from_sharepoint(
self,
download_dir: str,
sharepoint_site_name: str,
sharepoint_folder_path: str,
recursive: bool,
) -> Dict[str, str]:
"""
Downloads files from the specified folder and returns the metadata for the downloaded files.
Args:
download_dir (str): The directory where the files should be downloaded.
sharepoint_site_name (str): The name of the SharePoint site.
sharepoint_folder_path (str): The path of the folder in the SharePoint site.
recursive (bool): If True, files from all subfolders are downloaded.
Returns:
Dict[str, str]: A dictionary containing the metadata of the downloaded files.
"""
access_token = self._get_access_token()
self._site_id_with_host_name = self._get_site_id_with_host_name(
access_token, sharepoint_site_name
)
self._drive_id = self._get_drive_id()
self.sharepoint_folder_id = self._get_sharepoint_folder_id(
sharepoint_folder_path
)
return self._download_files_and_extract_metadata(
self.sharepoint_folder_id, download_dir, recursive
)
def _load_documents_with_metadata(
self,
files_metadata: Dict[str, Any],
download_dir: str,
recursive: bool,
) -> List[Document]:
"""
Loads the documents from the downloaded files.
Args:
files_metadata (Dict[str,Any]): A dictionary containing the metadata of the downloaded files.
download_dir (str): The directory where the files should be downloaded.
recursive (bool): If True, files from all subfolders are downloaded.
Returns:
List[Document]: A list containing the documents with metadata.
"""
def get_metadata(filename: str) -> Any:
return files_metadata[filename]
simple_loader = SimpleDirectoryReader(
download_dir, file_metadata=get_metadata, recursive=recursive
)
return simple_loader.load_data()
def load_data(
self,
sharepoint_site_name: str,
sharepoint_folder_path: str,
recursive: bool = False,
) -> List[Document]:
"""
Loads the files from the specified folder in the SharePoint site.
Args:
sharepoint_site_name (str): The name of the SharePoint site.
sharepoint_folder_path (str): The path of the folder in the SharePoint site.
recursive (bool): If True, files from all subfolders are downloaded.
Returns:
List[Document]: A list containing the documents with metadata.
Raises:
Exception: If an error occurs while accessing SharePoint site.
"""
try:
with tempfile.TemporaryDirectory() as temp_dir:
files_metadata = self._download_files_from_sharepoint(
temp_dir, sharepoint_site_name, sharepoint_folder_path, recursive
)
# return self.files_metadata
return self._load_documents_with_metadata(
files_metadata, temp_dir, recursive
)
except Exception as exp:
logger.error("An error occurred while accessing SharePoint: %s", exp)
|