Spaces:
Runtime error
Runtime error
Roland Ding commited on
Commit ·
e8f5f18
1
Parent(s): ddc46db
8.7.20.54 added terminal print out function as a decorator to wrap up function and provide a terminal view for the code it executed.
Browse files- cloud_db.py +5 -0
- cloud_storage.py +7 -1
- supplier.py +10 -3
- utility.py +64 -0
cloud_db.py
CHANGED
|
@@ -15,6 +15,7 @@ dynamodb data operations
|
|
| 15 |
'''
|
| 16 |
|
| 17 |
# get the list of articles from articles table in dynamodb
|
|
|
|
| 18 |
def get_table(table_name:str):
|
| 19 |
result = db_client.scan(TableName = table_name)#,AttributesToGet = data_structure[table_name]["fields"])
|
| 20 |
return [db_map_to_py_dict(r) for r in result["Items"]]
|
|
@@ -31,6 +32,7 @@ def post_item(table_name:str,item:dict):
|
|
| 31 |
return res
|
| 32 |
|
| 33 |
# update an article in table articles in dynamodb, return error if failed
|
|
|
|
| 34 |
def put_item(table_name:str,item:dict):
|
| 35 |
try:
|
| 36 |
res = db_client.put_item(
|
|
@@ -42,6 +44,7 @@ def put_item(table_name:str,item:dict):
|
|
| 42 |
return res
|
| 43 |
|
| 44 |
# delete an article in table articles in dynamodb, return error if not found.
|
|
|
|
| 45 |
def delete_item(table_name:str,key:dict):
|
| 46 |
try:
|
| 47 |
res = db_client.delete_item(
|
|
@@ -55,6 +58,7 @@ def delete_item(table_name:str,key:dict):
|
|
| 55 |
|
| 56 |
'''
|
| 57 |
'''
|
|
|
|
| 58 |
def get_item(table_name:str,key:dict):
|
| 59 |
try:
|
| 60 |
res = db_client.get_item(
|
|
@@ -68,6 +72,7 @@ def get_item(table_name:str,key:dict):
|
|
| 68 |
'''
|
| 69 |
dynamodb structure management
|
| 70 |
'''
|
|
|
|
| 71 |
def get_structure(table_name:str):
|
| 72 |
result = db_client.describe_table(TableName = table_name)
|
| 73 |
return result["Table"]["AttributeDefinitions"]
|
|
|
|
| 15 |
'''
|
| 16 |
|
| 17 |
# get the list of articles from articles table in dynamodb
|
| 18 |
+
@terminal_print
|
| 19 |
def get_table(table_name:str):
|
| 20 |
result = db_client.scan(TableName = table_name)#,AttributesToGet = data_structure[table_name]["fields"])
|
| 21 |
return [db_map_to_py_dict(r) for r in result["Items"]]
|
|
|
|
| 32 |
return res
|
| 33 |
|
| 34 |
# update an article in table articles in dynamodb, return error if failed
|
| 35 |
+
@terminal_print
|
| 36 |
def put_item(table_name:str,item:dict):
|
| 37 |
try:
|
| 38 |
res = db_client.put_item(
|
|
|
|
| 44 |
return res
|
| 45 |
|
| 46 |
# delete an article in table articles in dynamodb, return error if not found.
|
| 47 |
+
@terminal_print
|
| 48 |
def delete_item(table_name:str,key:dict):
|
| 49 |
try:
|
| 50 |
res = db_client.delete_item(
|
|
|
|
| 58 |
|
| 59 |
'''
|
| 60 |
'''
|
| 61 |
+
@terminal_print
|
| 62 |
def get_item(table_name:str,key:dict):
|
| 63 |
try:
|
| 64 |
res = db_client.get_item(
|
|
|
|
| 72 |
'''
|
| 73 |
dynamodb structure management
|
| 74 |
'''
|
| 75 |
+
@terminal_print
|
| 76 |
def get_structure(table_name:str):
|
| 77 |
result = db_client.describe_table(TableName = table_name)
|
| 78 |
return result["Table"]["AttributeDefinitions"]
|
cloud_storage.py
CHANGED
|
@@ -2,7 +2,7 @@ import boto3
|
|
| 2 |
import os
|
| 3 |
import tempfile
|
| 4 |
|
| 5 |
-
from utility import aws_access_key_id, aws_secret_access_key
|
| 6 |
|
| 7 |
s3 = boto3.client(
|
| 8 |
's3',
|
|
@@ -11,6 +11,7 @@ s3 = boto3.client(
|
|
| 11 |
)
|
| 12 |
|
| 13 |
# post or update a file to s3
|
|
|
|
| 14 |
def upload_file(path, bucket, object_name=None):
|
| 15 |
"""Upload a file to an S3 bucket
|
| 16 |
|
|
@@ -33,6 +34,7 @@ def upload_file(path, bucket, object_name=None):
|
|
| 33 |
return False
|
| 34 |
return res
|
| 35 |
|
|
|
|
| 36 |
def upload_fileobj(file_obj, bucket, object_name=None):
|
| 37 |
'''
|
| 38 |
Upload a file object to an S3 bucket
|
|
@@ -55,6 +57,7 @@ def upload_fileobj(file_obj, bucket, object_name=None):
|
|
| 55 |
return res
|
| 56 |
|
| 57 |
# get a file from s3
|
|
|
|
| 58 |
def download_file(bucket, object_name, file_name=None):
|
| 59 |
"""Download a file from an S3 bucket
|
| 60 |
|
|
@@ -75,6 +78,7 @@ def download_file(bucket, object_name, file_name=None):
|
|
| 75 |
return True
|
| 76 |
|
| 77 |
# download a file object from s3
|
|
|
|
| 78 |
def download_fileobj(bucket, object_name, temp_obj=None):
|
| 79 |
'''
|
| 80 |
Download a file object from an S3 bucket
|
|
@@ -97,6 +101,7 @@ def download_fileobj(bucket, object_name, temp_obj=None):
|
|
| 97 |
return temp_obj
|
| 98 |
|
| 99 |
# delete a file from s3
|
|
|
|
| 100 |
def delete_file(bucket, object_name):
|
| 101 |
"""Delete a file from an S3 bucket
|
| 102 |
|
|
@@ -112,6 +117,7 @@ def delete_file(bucket, object_name):
|
|
| 112 |
return response
|
| 113 |
|
| 114 |
# list all files in a bucket
|
|
|
|
| 115 |
def list_files(bucket):
|
| 116 |
"""List files in a bucket
|
| 117 |
|
|
|
|
| 2 |
import os
|
| 3 |
import tempfile
|
| 4 |
|
| 5 |
+
from utility import aws_access_key_id, aws_secret_access_key,terminal_print
|
| 6 |
|
| 7 |
s3 = boto3.client(
|
| 8 |
's3',
|
|
|
|
| 11 |
)
|
| 12 |
|
| 13 |
# post or update a file to s3
|
| 14 |
+
@terminal_print
|
| 15 |
def upload_file(path, bucket, object_name=None):
|
| 16 |
"""Upload a file to an S3 bucket
|
| 17 |
|
|
|
|
| 34 |
return False
|
| 35 |
return res
|
| 36 |
|
| 37 |
+
@terminal_print
|
| 38 |
def upload_fileobj(file_obj, bucket, object_name=None):
|
| 39 |
'''
|
| 40 |
Upload a file object to an S3 bucket
|
|
|
|
| 57 |
return res
|
| 58 |
|
| 59 |
# get a file from s3
|
| 60 |
+
@terminal_print
|
| 61 |
def download_file(bucket, object_name, file_name=None):
|
| 62 |
"""Download a file from an S3 bucket
|
| 63 |
|
|
|
|
| 78 |
return True
|
| 79 |
|
| 80 |
# download a file object from s3
|
| 81 |
+
@terminal_print
|
| 82 |
def download_fileobj(bucket, object_name, temp_obj=None):
|
| 83 |
'''
|
| 84 |
Download a file object from an S3 bucket
|
|
|
|
| 101 |
return temp_obj
|
| 102 |
|
| 103 |
# delete a file from s3
|
| 104 |
+
@terminal_print
|
| 105 |
def delete_file(bucket, object_name):
|
| 106 |
"""Delete a file from an S3 bucket
|
| 107 |
|
|
|
|
| 117 |
return response
|
| 118 |
|
| 119 |
# list all files in a bucket
|
| 120 |
+
@terminal_print
|
| 121 |
def list_files(bucket):
|
| 122 |
"""List files in a bucket
|
| 123 |
|
supplier.py
CHANGED
|
@@ -2,11 +2,12 @@ import openai
|
|
| 2 |
import tiktoken
|
| 3 |
|
| 4 |
from application import *
|
|
|
|
| 5 |
|
| 6 |
openai.api_key = openai_api_key
|
| 7 |
token_encoder = tiktoken.get_encoding("cl100k_base")
|
| 8 |
|
| 9 |
-
|
| 10 |
def execute_prompt(prompt):
|
| 11 |
'''
|
| 12 |
execute_prompt function takes two arguments: text and prompt
|
|
@@ -28,22 +29,28 @@ def execute_prompt(prompt):
|
|
| 28 |
)
|
| 29 |
return res.choices[0]["text"] if res.choices else "<error> failed to generate text</error>"
|
| 30 |
|
|
|
|
| 31 |
def format(**kwargs):
|
| 32 |
if "format" in kwargs:
|
| 33 |
return kwargs["format"]
|
| 34 |
return kwargs
|
| 35 |
|
| 36 |
|
|
|
|
| 37 |
def execute_instruction(article, instruction,model="gpt-3.5-turbo-16k",format="markdown"):
|
| 38 |
'''
|
| 39 |
execute_instruction function takes three arguments: article, instruction and model
|
| 40 |
|
|
|
|
|
|
|
| 41 |
article: the raw text from the article source
|
| 42 |
instruction: the instruction for the rational execution it needs to complete
|
| 43 |
-
model: the model
|
| 44 |
-
format: the format of the table
|
| 45 |
|
| 46 |
return: a string, the result of the rational execution
|
|
|
|
|
|
|
| 47 |
'''
|
| 48 |
msg_stream = [
|
| 49 |
{
|
|
|
|
| 2 |
import tiktoken
|
| 3 |
|
| 4 |
from application import *
|
| 5 |
+
from utility import terminal_print
|
| 6 |
|
| 7 |
openai.api_key = openai_api_key
|
| 8 |
token_encoder = tiktoken.get_encoding("cl100k_base")
|
| 9 |
|
| 10 |
+
@terminal_print
|
| 11 |
def execute_prompt(prompt):
|
| 12 |
'''
|
| 13 |
execute_prompt function takes two arguments: text and prompt
|
|
|
|
| 29 |
)
|
| 30 |
return res.choices[0]["text"] if res.choices else "<error> failed to generate text</error>"
|
| 31 |
|
| 32 |
+
@terminal_print
|
| 33 |
def format(**kwargs):
|
| 34 |
if "format" in kwargs:
|
| 35 |
return kwargs["format"]
|
| 36 |
return kwargs
|
| 37 |
|
| 38 |
|
| 39 |
+
@terminal_print
|
| 40 |
def execute_instruction(article, instruction,model="gpt-3.5-turbo-16k",format="markdown"):
|
| 41 |
'''
|
| 42 |
execute_instruction function takes three arguments: article, instruction and model
|
| 43 |
|
| 44 |
+
Parameters
|
| 45 |
+
----------
|
| 46 |
article: the raw text from the article source
|
| 47 |
instruction: the instruction for the rational execution it needs to complete
|
| 48 |
+
model: the model to use for the rational execution
|
| 49 |
+
format: the format of the table to be formatted
|
| 50 |
|
| 51 |
return: a string, the result of the rational execution
|
| 52 |
+
|
| 53 |
+
|
| 54 |
'''
|
| 55 |
msg_stream = [
|
| 56 |
{
|
utility.py
CHANGED
|
@@ -6,6 +6,26 @@ from pdfminer.high_level import extract_text
|
|
| 6 |
from pdfminer.pdfparser import PDFParser
|
| 7 |
from pdfminer.pdfdocument import PDFDocument
|
| 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
|
| 10 |
'''
|
| 11 |
following functions are for file manipulation
|
|
@@ -15,6 +35,7 @@ keyword_search = lambda kw, text: kw.lower() in text.lower()
|
|
| 15 |
list_or = lambda l: sum(l)>0
|
| 16 |
list_and = lambda l: sum(l)==len(l)
|
| 17 |
|
|
|
|
| 18 |
def read_pdf(file_path):
|
| 19 |
'''
|
| 20 |
this function read the pdf file and return the text
|
|
@@ -86,6 +107,7 @@ def format_response(code,data):
|
|
| 86 |
following functions are for string manipulation
|
| 87 |
'''
|
| 88 |
|
|
|
|
| 89 |
def format_text(text,remove_char_ls = ["\\n--\\n","\\n\\n","\n"]):
|
| 90 |
'''
|
| 91 |
this function format the text output by removing excessive characters
|
|
@@ -105,6 +127,7 @@ def format_text(text,remove_char_ls = ["\\n--\\n","\\n\\n","\n"]):
|
|
| 105 |
|
| 106 |
return text
|
| 107 |
|
|
|
|
| 108 |
def remove_symbols(text):
|
| 109 |
'''
|
| 110 |
this function remove symbols that are not in unicode
|
|
@@ -123,6 +146,7 @@ def remove_symbols(text):
|
|
| 123 |
text = text.replace('-\n', '')
|
| 124 |
return text
|
| 125 |
|
|
|
|
| 126 |
def remove_citation(text):
|
| 127 |
'''
|
| 128 |
this function remove citation pattern in the text
|
|
@@ -155,6 +179,7 @@ def str_to_tuple(s):
|
|
| 155 |
'''
|
| 156 |
return tuple(s.replace("(","").replace(")","").split(","))
|
| 157 |
|
|
|
|
| 158 |
def replace_symbols(s):
|
| 159 |
'''
|
| 160 |
this function replace symbols in the string to comply with file names
|
|
@@ -186,6 +211,7 @@ def replace_symbols(s):
|
|
| 186 |
following functions are for dynamodb data manipulation
|
| 187 |
'''
|
| 188 |
|
|
|
|
| 189 |
def db_map_to_py_dict(db_map):
|
| 190 |
'''
|
| 191 |
this function convert dynamodb map data structure to python dictionary
|
|
@@ -222,6 +248,7 @@ def db_map_to_py_dict(db_map):
|
|
| 222 |
|
| 223 |
return py_dict
|
| 224 |
|
|
|
|
| 225 |
def py_dict_to_db_map(py_dict):
|
| 226 |
'''
|
| 227 |
this function convert python dictionary to dynamodb map data structure
|
|
@@ -255,6 +282,7 @@ def py_dict_to_db_map(py_dict):
|
|
| 255 |
db_map[key] = {"NULL":True}
|
| 256 |
return db_map
|
| 257 |
|
|
|
|
| 258 |
def db_list_to_py_list(db_list):
|
| 259 |
'''
|
| 260 |
this function convert dynamodb list data structure to python list
|
|
@@ -283,6 +311,7 @@ def db_list_to_py_list(db_list):
|
|
| 283 |
|
| 284 |
return py_list
|
| 285 |
|
|
|
|
| 286 |
def py_list_to_db_list(py_list):
|
| 287 |
'''
|
| 288 |
this function convert python list to dynamodb list data structure
|
|
@@ -321,10 +350,45 @@ def py_list_to_db_list(py_list):
|
|
| 321 |
|
| 322 |
return db_list
|
| 323 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 324 |
'''
|
| 325 |
following functions are used for business logic. (to be moved to business logic layer)
|
| 326 |
'''
|
| 327 |
|
|
|
|
| 328 |
def est_cost(n_tokens,rate):
|
| 329 |
'''
|
| 330 |
this function calculate the estimated cost of the translation
|
|
|
|
| 6 |
from pdfminer.pdfparser import PDFParser
|
| 7 |
from pdfminer.pdfdocument import PDFDocument
|
| 8 |
|
| 9 |
+
'''
|
| 10 |
+
universal system functions
|
| 11 |
+
'''
|
| 12 |
+
|
| 13 |
+
def terminal_print(func):
|
| 14 |
+
from datetime import datetime
|
| 15 |
+
# import os
|
| 16 |
+
def wrapper(*args, **kwargs):
|
| 17 |
+
start = datetime.now()
|
| 18 |
+
print(f"{start.strftime('%y-%m-%d %H:%M:%S')} - executing: {func.__name__}")
|
| 19 |
+
|
| 20 |
+
result = func(*args, **kwargs)
|
| 21 |
+
|
| 22 |
+
end = datetime.now()
|
| 23 |
+
print(f"{end.strftime('%y-%m-%d %H:%M:%S')} - completed: {func.__name__}, runtime: {end-start} seconds")
|
| 24 |
+
|
| 25 |
+
return result
|
| 26 |
+
|
| 27 |
+
return wrapper
|
| 28 |
+
|
| 29 |
|
| 30 |
'''
|
| 31 |
following functions are for file manipulation
|
|
|
|
| 35 |
list_or = lambda l: sum(l)>0
|
| 36 |
list_and = lambda l: sum(l)==len(l)
|
| 37 |
|
| 38 |
+
@terminal_print
|
| 39 |
def read_pdf(file_path):
|
| 40 |
'''
|
| 41 |
this function read the pdf file and return the text
|
|
|
|
| 107 |
following functions are for string manipulation
|
| 108 |
'''
|
| 109 |
|
| 110 |
+
@terminal_print
|
| 111 |
def format_text(text,remove_char_ls = ["\\n--\\n","\\n\\n","\n"]):
|
| 112 |
'''
|
| 113 |
this function format the text output by removing excessive characters
|
|
|
|
| 127 |
|
| 128 |
return text
|
| 129 |
|
| 130 |
+
@terminal_print
|
| 131 |
def remove_symbols(text):
|
| 132 |
'''
|
| 133 |
this function remove symbols that are not in unicode
|
|
|
|
| 146 |
text = text.replace('-\n', '')
|
| 147 |
return text
|
| 148 |
|
| 149 |
+
@terminal_print
|
| 150 |
def remove_citation(text):
|
| 151 |
'''
|
| 152 |
this function remove citation pattern in the text
|
|
|
|
| 179 |
'''
|
| 180 |
return tuple(s.replace("(","").replace(")","").split(","))
|
| 181 |
|
| 182 |
+
@terminal_print
|
| 183 |
def replace_symbols(s):
|
| 184 |
'''
|
| 185 |
this function replace symbols in the string to comply with file names
|
|
|
|
| 211 |
following functions are for dynamodb data manipulation
|
| 212 |
'''
|
| 213 |
|
| 214 |
+
@terminal_print
|
| 215 |
def db_map_to_py_dict(db_map):
|
| 216 |
'''
|
| 217 |
this function convert dynamodb map data structure to python dictionary
|
|
|
|
| 248 |
|
| 249 |
return py_dict
|
| 250 |
|
| 251 |
+
@terminal_print
|
| 252 |
def py_dict_to_db_map(py_dict):
|
| 253 |
'''
|
| 254 |
this function convert python dictionary to dynamodb map data structure
|
|
|
|
| 282 |
db_map[key] = {"NULL":True}
|
| 283 |
return db_map
|
| 284 |
|
| 285 |
+
@terminal_print
|
| 286 |
def db_list_to_py_list(db_list):
|
| 287 |
'''
|
| 288 |
this function convert dynamodb list data structure to python list
|
|
|
|
| 311 |
|
| 312 |
return py_list
|
| 313 |
|
| 314 |
+
@terminal_print
|
| 315 |
def py_list_to_db_list(py_list):
|
| 316 |
'''
|
| 317 |
this function convert python list to dynamodb list data structure
|
|
|
|
| 350 |
|
| 351 |
return db_list
|
| 352 |
|
| 353 |
+
'''
|
| 354 |
+
following functions are for markdown table creation
|
| 355 |
+
'''
|
| 356 |
+
|
| 357 |
+
@terminal_print
|
| 358 |
+
def create_md_table(array):
|
| 359 |
+
'''
|
| 360 |
+
create markdown tables for an array.
|
| 361 |
+
|
| 362 |
+
Parameters
|
| 363 |
+
----------
|
| 364 |
+
array: list
|
| 365 |
+
a table in the form of a list of lists
|
| 366 |
+
|
| 367 |
+
Returns
|
| 368 |
+
-------
|
| 369 |
+
md_table: str
|
| 370 |
+
'''
|
| 371 |
+
md_table = ""
|
| 372 |
+
|
| 373 |
+
for i,row in enumerate(array):
|
| 374 |
+
md_row = ""
|
| 375 |
+
for item in row:
|
| 376 |
+
md_item = f"| {item} "
|
| 377 |
+
md_row += md_item
|
| 378 |
+
|
| 379 |
+
md_row += " |\n"
|
| 380 |
+
md_table += md_row
|
| 381 |
+
|
| 382 |
+
if i == 0:
|
| 383 |
+
md_table += f"| {'|'.join(['---' for _ in range(len(row))])} |\n"
|
| 384 |
+
|
| 385 |
+
return md_table
|
| 386 |
+
|
| 387 |
'''
|
| 388 |
following functions are used for business logic. (to be moved to business logic layer)
|
| 389 |
'''
|
| 390 |
|
| 391 |
+
@terminal_print
|
| 392 |
def est_cost(n_tokens,rate):
|
| 393 |
'''
|
| 394 |
this function calculate the estimated cost of the translation
|