polly-python 1.6.0__tar.gz → 1.7.0__tar.gz

{polly_python-1.6.0/polly_python.egg-info → polly_python-1.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: polly_python
-Version: 1.6.0
+Version: 1.7.0
 Summary: Polly SDK
 Home-page: https://github.com/ElucidataInc/polly-python
 Project-URL: Documentation, https://docs.elucidata.io

polly_python-1.7.0/polly/__init__.py

@@ -0,0 +1 @@
+__version__ = "1.7.0"

{polly_python-1.6.0 → polly_python-1.7.0}/polly/omixatlas.py

@@ -1537,6 +1537,24 @@ class OmixAtlas:
         except Exception as err:
             raise err
 
+    @Track.track_decorator
+    def download_linked_reports(self, repo_key: str, dataset_id: str, folder_path: str):
+        """Downloads Linked Reports to the repo
+
+        Args:
+            repo_key (str): repo_name/repo_id of the repository for which to fetch the report
+            dataset_id (str): dataset_id of the dataset which to fetch the reports.
+            folder_path (str): local folder path where the files need to be downloaded
+
+        Returns:
+            Downloads the datasets in the passed folder path
+        """
+        try:
+            report_obj = Reporting()
+            report_obj.download_linked_reports(self, repo_key, dataset_id, folder_path)
+        except Exception as err:
+            raise err
+
     @Track.track_decorator
     def delete_linked_report(
         self, repo_key: str, dataset_id: str, report_id: str

{polly_python-1.6.0 → polly_python-1.7.0/polly_python.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: polly_python
-Version: 1.6.0
+Version: 1.7.0
 Summary: Polly SDK
 Home-page: https://github.com/ElucidataInc/polly-python
 Project-URL: Documentation, https://docs.elucidata.io

{polly_python-1.6.0 → polly_python-1.7.0}/polly_services/reporting/reporting.py

@@ -1,12 +1,19 @@
+import os
 from polly_interfaces.IReporting import IReporting
 from polly.errors import error_handler, InvalidParameterException
 import json
+import urllib.parse
 import pandas as pd
 from polly import helpers
 from datetime import datetime
 from urllib.parse import urlparse
 from polly_services import polly_services_hlpr
 from polly_services.reporting import reporting_hlpr
+from polly.errors import (
+    InvalidParameterException,
+    error_handler,
+    InvalidDirectoryPath,
+)
 
 
 class Reporting(IReporting):
@@ -268,6 +275,100 @@ class Reporting(IReporting):
                 pd.set_option("display.max_colwidth", None)
                 return df
 
+    def download_linked_reports(
+        self, polly_session, repo_key: str, dataset_id: str, local_folder_path: str
+    ):
+        """Download linked reports to the local path
+
+        Args:
+            polly_session : polly_session variable
+            repo_key (str): repo_key for the omixatlas
+            dataset_id (str): dataset_id for the repo
+            local_folder_path (str): _description_
+        """
+        # sanity check of variables
+        if not (repo_key and isinstance(repo_key, str)):
+            raise InvalidParameterException("repo_key")
+        if not (dataset_id and isinstance(dataset_id, str)):
+            raise InvalidParameterException("dataset_id")
+
+        isExists = os.path.isdir(local_folder_path)
+        if not isExists:
+            raise InvalidDirectoryPath(local_folder_path)
+
+        # get the resultant dataframe from fetch_linked_reports function
+        df = self.fetch_linked_reports(polly_session, repo_key, dataset_id)
+
+        if df is None:
+            print("No reports to download")
+            return
+
+        urls_list = []
+        # iterate on the DF and get the report_ids
+        for index, row in df.iterrows():
+            # print(row)
+            urls_list.append(row["URL"])
+
+        files_signed_urls_list = []
+
+        file_id_list = []
+
+        for url in urls_list:
+            parsed_url = urllib.parse.urlparse(url)
+
+            # Extract the query string parameters
+            query_params = urllib.parse.parse_qs(parsed_url.query)
+
+            # Get the value of the 'id' parameter
+            # id will be list here
+            file_id = query_params.get("id")
+
+            # Print the extracted ID
+            if file_id:
+                # Assuming 'id' exists and has only one value
+                file_id_list.append(file_id[0])
+            else:
+                print(f"ID not found in the file URL: {url}")
+
+        # call the API on the report_id to get list of all signed urls
+        for file_id in file_id_list:
+            params = {"action": "file_download"}
+            url = f"{polly_session.base_url}/shared-files/{file_id}"
+
+            response = polly_session.session.get(url, params=params)
+            error_handler(response)
+            response_json = response.json()
+
+            # structure of response
+            """
+                {
+                    "data":{
+                        "type":"file",
+                        "id":"15374/renamed - another.xlsx",
+                        "attributes":{
+                            "s3_key":"15374/renamed - another.xlsx",
+                            "last_modified":"2024-04-11 04:28:35.000000",
+                            "size":"8.94 KB",
+                            "file_name":""
+                        },
+                        "links":{
+                            "self":"/projects/15374/files/renamed%20-%20another.xlsx",
+                            "signed_url": "<signed_url>"
+                        }
+                    }
+                }
+            """
+            signed_url_val = response_json.get("data").get("links").get("signed_url")
+            files_signed_urls_list.append(signed_url_val)
+
+        try:
+            # iterate over signed urls and download it in the provided local file path
+            reporting_hlpr.download_from_s3_signedUrls(
+                files_signed_urls_list, local_folder_path
+            )
+        except Exception as err:
+            raise err
+
     def delete_linked_report(
         self, polly_session, repo_key: str, dataset_id: str, report_id: str
     ):

{polly_python-1.6.0 → polly_python-1.7.0}/polly_services/reporting/reporting_hlpr.py

@@ -1,10 +1,13 @@
 import json
+import os
 import urllib
 from polly import helpers
 from cloudpathlib import S3Client
 from polly.errors import error_handler
 from urllib.parse import quote
 from polly.errors import paramException, AccessDeniedError
+from tqdm import tqdm
+import requests
 
 
 def verify_workspace_path(cloud_path: str, credentials: dict) -> tuple:
@@ -232,3 +235,52 @@ def split_workspace_path(absolute_path: str) -> tuple:
     for item in range(2, len(contents)):
         workspace_path = helpers.make_path(workspace_path, contents[item])
     return workspace_id, workspace_path
+
+
+def download_from_s3_signedUrls(urls: str, local_folder: str):
+    """
+    Downloads files from a list of AWS signed URLs to a local folder.
+
+    Args:
+        urls: A list of strings containing the AWS signed URLs.
+        local_folder: The path to the local folder where files will be downloaded.
+    """
+    # Create directory if it doesn't exist
+    os.makedirs(local_folder, exist_ok=True)
+
+    for url in urls:
+        parsed_url = urllib.parse.urlparse(url)
+        path = parsed_url.path
+        filename = os.path.basename(path)
+        # print(filename)
+        print(f"Starting report download {filename}")
+        local_path = os.path.join(local_folder, filename)
+
+        try:
+            response = requests.get(url, stream=True)
+            error_handler(response)
+
+            # tqdm implement
+            with open(local_path, "wb") as f:
+                chunk_size = 4096
+                total_size = int(response.headers.get('Content-Length', 0))
+
+                # Create a progress bar with total size (if available)
+                pbar = tqdm(
+                    total=total_size,
+                    unit='B',
+                    unit_scale=True,
+                    unit_divisor=4096
+                )
+
+                for chunk in response.iter_content(chunk_size=chunk_size):
+                    if chunk:  # Filter out keep-alive new chunks
+                        f.write(chunk)
+                        pbar.update(len(chunk))  # Update progress bar with downloaded chunk size
+
+                pbar.close()  # Close the progress bar after download
+                print()
+        
+
+        except requests.exceptions.RequestException as e:
+            print(f"Error downloading {filename} from s3: {e}")

polly_python-1.6.0/polly/__init__.py

@@ -1 +0,0 @@
-__version__ = "1.6.0"