Spaces:
Running
on
Zero
Running
on
Zero
File size: 14,124 Bytes
d864d45 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 |
import os
from typing import List, Type
import boto3
import pandas as pd
from tools.config import (
AWS_REGION,
DOCUMENT_REDACTION_BUCKET,
RUN_AWS_FUNCTIONS,
S3_OUTPUTS_BUCKET,
SAVE_LOGS_TO_CSV,
)
from tools.secure_path_utils import secure_join
PandasDataFrame = Type[pd.DataFrame]
def get_assumed_role_info():
sts_endpoint = "https://sts." + AWS_REGION + ".amazonaws.com"
sts = boto3.client("sts", region_name=AWS_REGION, endpoint_url=sts_endpoint)
response = sts.get_caller_identity()
# Extract ARN of the assumed role
assumed_role_arn = response["Arn"]
# Extract the name of the assumed role from the ARN
assumed_role_name = assumed_role_arn.split("/")[-1]
return assumed_role_arn, assumed_role_name
if RUN_AWS_FUNCTIONS:
try:
session = boto3.Session(region_name=AWS_REGION)
except Exception as e:
print("Could not start boto3 session:", e)
try:
assumed_role_arn, assumed_role_name = get_assumed_role_info()
print("Successfully assumed ARN role")
# print("Assumed Role ARN:", assumed_role_arn)
# print("Assumed Role Name:", assumed_role_name)
except Exception as e:
print("Could not get assumed role from STS:", e)
# Download direct from S3 - requires login credentials
def download_file_from_s3(
bucket_name: str,
key: str,
local_file_path_and_name: str,
RUN_AWS_FUNCTIONS: bool = RUN_AWS_FUNCTIONS,
):
if RUN_AWS_FUNCTIONS:
try:
# Ensure the local directory exists
os.makedirs(os.path.dirname(local_file_path_and_name), exist_ok=True)
s3 = boto3.client("s3", region_name=AWS_REGION)
s3.download_file(bucket_name, key, local_file_path_and_name)
print(
f"File downloaded from s3://{bucket_name}/{key} to {local_file_path_and_name}"
)
except Exception as e:
print("Could not download file:", key, "from s3 due to", e)
def download_folder_from_s3(
bucket_name: str,
s3_folder: str,
local_folder: str,
RUN_AWS_FUNCTIONS: bool = RUN_AWS_FUNCTIONS,
):
"""
Download all files from an S3 folder to a local folder.
"""
if RUN_AWS_FUNCTIONS:
if bucket_name and s3_folder and local_folder:
s3 = boto3.client("s3", region_name=AWS_REGION)
# List objects in the specified S3 folder
response = s3.list_objects_v2(Bucket=bucket_name, Prefix=s3_folder)
# Download each object
for obj in response.get("Contents", []):
# Extract object key and construct local file path
object_key = obj["Key"]
local_file_path = secure_join(
local_folder, os.path.relpath(object_key, s3_folder)
)
# Create directories if necessary
os.makedirs(os.path.dirname(local_file_path), exist_ok=True)
# Download the object
try:
s3.download_file(bucket_name, object_key, local_file_path)
print(
f"Downloaded 's3://{bucket_name}/{object_key}' to '{local_file_path}'"
)
except Exception as e:
print(f"Error downloading 's3://{bucket_name}/{object_key}':", e)
else:
print(
"One or more required variables are empty, could not download from S3"
)
def download_files_from_s3(
bucket_name: str,
s3_folder: str,
local_folder: str,
filenames: List[str],
RUN_AWS_FUNCTIONS: bool = RUN_AWS_FUNCTIONS,
):
"""
Download specific files from an S3 folder to a local folder.
"""
if RUN_AWS_FUNCTIONS:
if bucket_name and s3_folder and local_folder and filenames:
s3 = boto3.client("s3", region_name=AWS_REGION)
print("Trying to download file: ", filenames)
if filenames == "*":
# List all objects in the S3 folder
print("Trying to download all files in AWS folder: ", s3_folder)
response = s3.list_objects_v2(Bucket=bucket_name, Prefix=s3_folder)
print("Found files in AWS folder: ", response.get("Contents", []))
filenames = [
obj["Key"].split("/")[-1] for obj in response.get("Contents", [])
]
print("Found filenames in AWS folder: ", filenames)
for filename in filenames:
object_key = secure_join(s3_folder, filename)
local_file_path = secure_join(local_folder, filename)
# Create directories if necessary
os.makedirs(os.path.dirname(local_file_path), exist_ok=True)
# Download the object
try:
s3.download_file(bucket_name, object_key, local_file_path)
print(
f"Downloaded 's3://{bucket_name}/{object_key}' to '{local_file_path}'"
)
except Exception as e:
print(f"Error downloading 's3://{bucket_name}/{object_key}':", e)
else:
print(
"One or more required variables are empty, could not download from S3"
)
def upload_file_to_s3(
local_file_paths: List[str],
s3_key: str,
s3_bucket: str = DOCUMENT_REDACTION_BUCKET,
RUN_AWS_FUNCTIONS: bool = RUN_AWS_FUNCTIONS,
):
"""
Uploads a file from local machine to Amazon S3.
Args:
- local_file_path: Local file path(s) of the file(s) to upload.
- s3_key: Key (path) to the file in the S3 bucket.
- s3_bucket: Name of the S3 bucket.
Returns:
- Message as variable/printed to console
"""
final_out_message = list()
final_out_message_str = ""
if RUN_AWS_FUNCTIONS:
try:
if s3_bucket and s3_key and local_file_paths:
s3_client = boto3.client("s3", region_name=AWS_REGION)
if isinstance(local_file_paths, str):
local_file_paths = [local_file_paths]
for file in local_file_paths:
if s3_client:
# print(s3_client)
try:
# Get file name off file path
file_name = os.path.basename(file)
s3_key_full = s3_key + file_name
# print("S3 key: ", s3_bucket, "/", s3_key_full, sep="")
s3_client.upload_file(file, s3_bucket, s3_key_full)
out_message = (
"File " + file_name + " uploaded successfully!"
)
except Exception as e:
out_message = f"Error uploading file(s): {e}"
print(out_message)
final_out_message.append(out_message)
final_out_message_str = "\n".join(final_out_message)
else:
final_out_message_str = "Could not connect to AWS."
else:
final_out_message_str = (
"At least one essential variable is empty, could not upload to S3"
)
except Exception as e:
final_out_message_str = "Could not upload files to S3 due to: " + str(e)
print(final_out_message_str)
else:
final_out_message_str = "App not set to run AWS functions"
return final_out_message_str
def upload_log_file_to_s3(
local_file_paths: List[str],
s3_key: str,
s3_bucket: str = DOCUMENT_REDACTION_BUCKET,
RUN_AWS_FUNCTIONS: bool = RUN_AWS_FUNCTIONS,
SAVE_LOGS_TO_CSV: bool = SAVE_LOGS_TO_CSV,
):
"""
Uploads a log file from local machine to Amazon S3.
Args:
- local_file_path: Local file path(s) of the file(s) to upload.
- s3_key: Key (path) to the file in the S3 bucket.
- s3_bucket: Name of the S3 bucket.
Returns:
- Message as variable/printed to console
"""
final_out_message = list()
final_out_message_str = ""
if RUN_AWS_FUNCTIONS and SAVE_LOGS_TO_CSV:
try:
if s3_bucket and s3_key and local_file_paths:
s3_client = boto3.client("s3", region_name=AWS_REGION)
if isinstance(local_file_paths, str):
local_file_paths = [local_file_paths]
for file in local_file_paths:
if s3_client:
# print(s3_client)
try:
# Get file name off file path
file_name = os.path.basename(file)
s3_key_full = s3_key + file_name
s3_client.upload_file(file, s3_bucket, s3_key_full)
out_message = (
"File " + file_name + " uploaded successfully!"
)
# print(out_message)
except Exception as e:
out_message = f"Error uploading file(s): {e}"
print(out_message)
final_out_message.append(out_message)
final_out_message_str = "\n".join(final_out_message)
else:
final_out_message_str = "Could not connect to AWS."
else:
final_out_message_str = (
"At least one essential variable is empty, could not upload to S3"
)
except Exception as e:
final_out_message_str = "Could not upload files to S3 due to: " + str(e)
print(final_out_message_str)
else:
final_out_message_str = "App not set to run AWS functions"
return final_out_message_str
# Helper to upload outputs to S3 when enabled in config.
def export_outputs_to_s3(
file_list_state,
s3_output_folder_state_value: str,
save_outputs_to_s3_flag: bool,
base_file_state=None,
s3_bucket: str = S3_OUTPUTS_BUCKET,
):
"""
Upload a list of local output files to the configured S3 outputs folder.
- file_list_state: Gradio dropdown state that holds a list of file paths or a
single path/string. If blank/empty, no action is taken.
- s3_output_folder_state_value: Final S3 key prefix (including any session hash)
to use as the destination folder for uploads.
- s3_bucket: Name of the S3 bucket.
"""
try:
# Respect the runtime toggle as well as environment configuration
if not save_outputs_to_s3_flag:
return
if not s3_output_folder_state_value:
# No configured S3 outputs folder – nothing to do
return
# Normalise input to a Python list of strings
file_paths = file_list_state
if not file_paths:
return
# Gradio dropdown may return a single string or a list
if isinstance(file_paths, str):
file_paths = [file_paths]
# Filter out any non-truthy values
file_paths = [p for p in file_paths if p]
if not file_paths:
return
# Derive a base file stem (name without extension) from the original
# file(s) being analysed, if provided. This is used to create an
# additional subfolder layer so that outputs are grouped under the
# analysed file name rather than under each output file name.
base_stem = None
if base_file_state:
base_path = None
# Gradio File components typically provide a list of objects with a `.name` attribute
if isinstance(base_file_state, str):
base_path = base_file_state
elif isinstance(base_file_state, list) and base_file_state:
first_item = base_file_state[0]
base_path = getattr(first_item, "name", None) or str(first_item)
else:
base_path = getattr(base_file_state, "name", None) or str(
base_file_state
)
if base_path:
base_name = os.path.basename(base_path)
base_stem, _ = os.path.splitext(base_name)
# Ensure base S3 prefix (session/date) ends with a trailing slash
base_prefix = s3_output_folder_state_value
if not base_prefix.endswith("/"):
base_prefix = base_prefix + "/"
# For each file, append a subfolder. If we have a derived base_stem
# from the input being analysed, use that; otherwise, fall back to
# the individual output file name stem. Final pattern:
# <session_output_folder>/<date>/<base_file_stem>/<file_name>
# or, if base_file_stem is not available:
# <session_output_folder>/<date>/<output_file_stem>/<file_name>
for file in file_paths:
file_name = os.path.basename(file)
if base_stem:
folder_stem = base_stem
else:
folder_stem, _ = os.path.splitext(file_name)
per_file_prefix = base_prefix + folder_stem + "/"
out_message = upload_file_to_s3(
local_file_paths=[file],
s3_key=per_file_prefix,
s3_bucket=s3_bucket,
)
# Log any issues to console so failures are visible in logs/stdout
if (
"Error uploading file" in out_message
or "could not upload" in out_message.lower()
):
print("export_outputs_to_s3 encountered issues:", out_message)
print("Successfully uploaded outputs to S3")
except Exception as e:
# Do not break the app flow if S3 upload fails – just report to console
print(f"export_outputs_to_s3 failed with error: {e}")
# No GUI outputs to update
return
|