cloudos-cli 2.48.0__tar.gz → 2.49.0__tar.gz

{cloudos_cli-2.48.0 → cloudos_cli-2.49.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cloudos_cli
-Version: 2.48.0
+Version: 2.49.0
 Summary: Python package for interacting with CloudOS
 Home-page: https://github.com/lifebit-ai/cloudos-cli
 Author: David Piñeyro
@@ -775,16 +775,15 @@ This file can later be used when running a job with `cloudos job run --job-confi
 > [!NOTE]
 > Job details can only be retrieved for a single user, cannot see other user's job details.
 
-#### Get a list of your jobs from a CloudOS workspace
+#### Get a list of workspace jobs from a CloudOS
 
-You can get a summary of your last 30 submitted jobs (or your selected number of last jobs using `--last-n-jobs n`
-parameter) in two different formats:
+You can get a summary of the workspace's last 30 submitted jobs (or a selected number of last jobs using `--last-n-jobs n` parameter) in two different formats:
 
 - CSV: this is a table with a minimum predefined set of columns by default, or all the
 available columns using the `--all-fields` argument.
-- JSON: all the available information from your jobs, in JSON format.
+- JSON: all the available information from the workspace jobs, in JSON format (`--all-fields` is always enabled for this format).
 
-To get a list with your last 30 submitted jobs to a given workspace, in CSV format, use
+To get a list with the workspace's last 30 submitted jobs, in CSV format, use
 the following command:
 
 ```bash
@@ -806,7 +805,7 @@ Executing list...
 
 In addition, a file named `joblist.csv` is created.
 
-To get the same information, but for all your jobs and in JSON format, use the following command:
+To get the same information, but for all the workspace's jobs and in JSON format, use the following command:
 
 ```bash
 cloudos job list \

{cloudos_cli-2.48.0 → cloudos_cli-2.49.0}/README.md

@@ -740,16 +740,15 @@ This file can later be used when running a job with `cloudos job run --job-confi
 > [!NOTE]
 > Job details can only be retrieved for a single user, cannot see other user's job details.
 
-#### Get a list of your jobs from a CloudOS workspace
+#### Get a list of workspace jobs from a CloudOS
 
-You can get a summary of your last 30 submitted jobs (or your selected number of last jobs using `--last-n-jobs n`
-parameter) in two different formats:
+You can get a summary of the workspace's last 30 submitted jobs (or a selected number of last jobs using `--last-n-jobs n` parameter) in two different formats:
 
 - CSV: this is a table with a minimum predefined set of columns by default, or all the
 available columns using the `--all-fields` argument.
-- JSON: all the available information from your jobs, in JSON format.
+- JSON: all the available information from the workspace jobs, in JSON format (`--all-fields` is always enabled for this format).
 
-To get a list with your last 30 submitted jobs to a given workspace, in CSV format, use
+To get a list with the workspace's last 30 submitted jobs, in CSV format, use
 the following command:
 
 ```bash
@@ -771,7 +770,7 @@ Executing list...
 
 In addition, a file named `joblist.csv` is created.
 
-To get the same information, but for all your jobs and in JSON format, use the following command:
+To get the same information, but for all the workspace's jobs and in JSON format, use the following command:
 
 ```bash
 cloudos job list \

{cloudos_cli-2.48.0 → cloudos_cli-2.49.0}/cloudos_cli/__main__.py

@@ -1176,17 +1176,17 @@ def job_details(ctx,
               default='joblist',
               required=False)
 @click.option('--output-format',
-              help='The desired file format (file extension) for the output. Default=csv.',
+              help='The desired file format (file extension) for the output. For json option --all-fields will be automatically set to True. Default=csv.',
               type=click.Choice(['csv', 'json'], case_sensitive=False),
               default='csv')
 @click.option('--all-fields',
               help=('Whether to collect all available fields from jobs or ' +
                     'just the preconfigured selected fields. Only applicable ' +
-                    'when --output-format=csv'),
+                    'when --output-format=csv. Automatically enabled for json output.'),
               is_flag=True)
 @click.option('--last-n-jobs',
-              help=("The number of last user's jobs to retrieve. You can use 'all' to " +
-                    "retrieve all user's jobs. Default=30."),
+              help=("The number of last workspace jobs to retrieve. You can use 'all' to " +
+                    "retrieve all workspace jobs. Default=30."),
               default='30')
 @click.option('--page',
               help=('Response page to retrieve. If --last-n-jobs is set, then --page ' +
@@ -1221,7 +1221,7 @@ def list_jobs(ctx,
               disable_ssl_verification,
               ssl_cert,
               profile):
-    """Collect all your jobs from a CloudOS workspace in CSV format."""
+    """Collect workspace jobs from a CloudOS workspace in CSV or JSON format."""
     profile = profile or ctx.default_map['job']['list']['profile']
     # Create a dictionary with required and non-required params
     required_dict = {
@@ -1270,6 +1270,7 @@ def list_jobs(ctx,
         except ValueError:
             print("[ERROR] last-n-jobs value was not valid. Please use a positive int or 'all'")
             raise
+
     my_jobs_r = cl.get_job_list(workspace_id, last_n_jobs, page, archived, verify_ssl)
     if len(my_jobs_r) == 0:
         if ctx.get_parameter_source('page') == click.core.ParameterSource.DEFAULT:
@@ -1281,15 +1282,14 @@ def list_jobs(ctx,
                   'using --page parameter.')
     elif output_format == 'csv':
         my_jobs = cl.process_job_list(my_jobs_r, all_fields)
-        my_jobs.to_csv(outfile, index=False)
-        print(f'\tJob list collected with a total of {my_jobs.shape[0]} jobs.')
+        cl.save_job_list_to_csv(my_jobs, outfile)
     elif output_format == 'json':
         with open(outfile, 'w') as o:
             o.write(json.dumps(my_jobs_r))
         print(f'\tJob list collected with a total of {len(my_jobs_r)} jobs.')
+        print(f'\tJob list saved to {outfile}')
     else:
         raise ValueError('Unrecognised output format. Please use one of [csv|json]')
-    print(f'\tJob list saved to {outfile}')
 
 
 @job.command('abort')

cloudos_cli-2.49.0/cloudos_cli/_version.py

@@ -0,0 +1 @@
+__version__ = '2.49.0'

{cloudos_cli-2.48.0 → cloudos_cli-2.49.0}/cloudos_cli/clos.py

@@ -11,6 +11,8 @@ from cloudos_cli.utils.errors import BadRequestException, JoBNotCompletedExcepti
 from cloudos_cli.utils.requests import retry_requests_get, retry_requests_post, retry_requests_put
 import pandas as pd
 from cloudos_cli.utils.last_wf import youngest_workflow_id_by_name
+from datetime import datetime
+
 
 # GLOBAL VARS
 JOB_COMPLETED = 'completed'
@@ -430,28 +432,27 @@ class Cloudos:
         df : pandas.DataFrame
             A DataFrame with the requested columns from the jobs.
         """
-        COLUMNS = ['_id',
-                   'team',
+        COLUMNS = ['status',
                    'name',
-                   'parameters',
-                   'status',
+                   'project.name',
+                   'user.name',
+                   'user.surname',
+                   'workflow.name',
+                   '_id',
                    'startTime',
                    'endTime',
                    'createdAt',
                    'updatedAt',
-                   'computeCostSpent',
-                   'masterInstanceStorageCost',
-                   'user.id',
-                   'workflow._id',
-                   'workflow.name',
-                   'workflow.description',
-                   'workflow.createdAt',
-                   'workflow.updatedAt',
-                   'workflow.workflowType',
-                   'project._id',
-                   'project.name',
-                   'project.createdAt',
-                   'project.updatedAt'
+                   'revision.commit',
+                   'realInstancesExecutionCost',
+                   'masterInstance.usedInstance.type',
+                   'storageMode',
+                   'workflow.repository.url',
+                   'nextflowVersion',
+                   'batch.enabled',
+                   'storageSizeInGb',
+                   'batch.jobQueue.id',
+                   'usesFusionFileSystem'
                    ]
         df_full = pd.json_normalize(r)
         if df_full.empty:
@@ -462,6 +463,156 @@ class Cloudos:
             df = df_full.loc[:, COLUMNS]
         return df
 
+    def reorder_job_list(self, my_jobs_df, filename='my_jobs.csv'):
+        """Save a job list DataFrame to a CSV file with renamed and ordered columns.
+
+        Parameters
+        ----------
+        my_jobs_df : pandas.DataFrame
+            A DataFrame containing job information from process_job_list.
+        filename : str
+            The name of the file to save the DataFrame to. Default is 'my_jobs.csv'.
+
+        Returns
+        -------
+        None
+            Saves the DataFrame to a CSV file with renamed and ordered columns.
+        """
+        # Handle empty DataFrame
+        if my_jobs_df.empty:
+            print("Warning: DataFrame is empty. Creating empty CSV file.")
+            empty_df = pd.DataFrame()
+            empty_df.to_csv(filename, index=False)
+            return
+
+        # Create a copy to avoid modifying the original DataFrame
+        jobs_df = my_jobs_df.copy()
+
+        # 1. Fusion user.name and user.surname into user
+        if 'user.name' in jobs_df.columns and 'user.surname' in jobs_df.columns:
+            jobs_df['user'] = jobs_df.apply(
+                lambda row: f"{row.get('user.name', '')} {row.get('user.surname', '')}".strip()
+                if pd.notna(row.get('user.name')) or pd.notna(row.get('user.surname'))
+                else None, axis=1
+            )
+            # Remove original columns
+            jobs_df = jobs_df.drop(columns=['user.name', 'user.surname'], errors='ignore')
+
+        # 2. Convert time fields to human-readable format
+        time_columns = ['startTime', 'endTime', 'createdAt', 'updatedAt']
+        for col in time_columns:
+            if col in jobs_df.columns:
+                def format_time(x):
+                    if pd.notna(x) and isinstance(x, str) and x:
+                        try:
+                            return datetime.fromisoformat(x.replace('Z', '+00:00')).strftime('%Y-%m-%d %H:%M:%S UTC')
+                        except (ValueError, TypeError):
+                            return x  # Return original value if parsing fails
+                    return None
+                jobs_df[col] = jobs_df[col].apply(format_time)
+
+        # 3. Format realInstancesExecutionCost (divide by 100, show 4 decimals)
+        if 'realInstancesExecutionCost' in jobs_df.columns:
+            def format_cost(x):
+                if pd.notna(x) and x != '' and x is not None:
+                    try:
+                        return f"{float(x) / 100:.4f}"
+                    except (ValueError, TypeError):
+                        return x  # Return original value if conversion fails
+                return None
+            jobs_df['realInstancesExecutionCost'] = jobs_df['realInstancesExecutionCost'].apply(format_cost)
+
+        # 4. Calculate Run time (endTime - startTime)
+        if 'startTime' in jobs_df.columns and 'endTime' in jobs_df.columns:
+            def calculate_runtime(row):
+                start_time = row.get('startTime')
+                end_time = row.get('endTime')
+                if pd.notna(start_time) and pd.notna(end_time) and start_time and end_time:
+                    # Use original times from the original DataFrame for calculation
+                    original_start = my_jobs_df.iloc[row.name].get('startTime') if row.name < len(my_jobs_df) else start_time
+                    original_end = my_jobs_df.iloc[row.name].get('endTime') if row.name < len(my_jobs_df) else end_time
+                    if pd.notna(original_start) and pd.notna(original_end) and original_start and original_end:
+                        try:
+                            start_dt = datetime.fromisoformat(str(original_start).replace('Z', '+00:00'))
+                            end_dt = datetime.fromisoformat(str(original_end).replace('Z', '+00:00'))
+                            duration = end_dt - start_dt
+                            # Format duration as hours:minutes:seconds
+                            total_seconds = int(duration.total_seconds())
+                            hours = total_seconds // 3600
+                            minutes = (total_seconds % 3600) // 60
+                            seconds = total_seconds % 60
+                            if hours > 0:
+                                return f"{hours}h {minutes}m {seconds}s"
+                            elif minutes > 0:
+                                return f"{minutes}m {seconds}s"
+                            else:
+                                return f"{seconds}s"
+                        except (ValueError, TypeError):
+                            return None
+                return None
+
+            jobs_df['Run time'] = jobs_df.apply(calculate_runtime, axis=1)
+
+        # 5. Format batch.enabled (True -> "Batch", else "N/A")
+        if 'batch.enabled' in jobs_df.columns:
+            jobs_df['batch.enabled'] = jobs_df['batch.enabled'].apply(
+                lambda x: "Batch" if x is True else "N/A"
+            )
+
+        # 6. Rename columns using the provided dictionary
+        column_name_mapping = {
+            "status": "Status",
+            "name": "Name",
+            "project.name": "Project",
+            "user": "Owner",
+            "workflow.name": "Pipeline",
+            "_id": "ID",
+            "createdAt": "Submit time",
+            "updatedAt": "End time",
+            "revision.commit": "Commit",
+            "realInstancesExecutionCost": "Cost",
+            "masterInstance.usedInstance.type": "Resources",
+            "storageMode": "Storage type",
+            "workflow.repository.url": "Pipeline url",
+            "nextflowVersion": "Nextflow version",
+            "batch.enabled": "Executor",
+            "storageSizeInGb": "Storage size",
+            "batch.jobQueue.id": "Job queue ID",
+            "usesFusionFileSystem": "Accelerated file staging"
+        }
+
+        # Rename columns that exist in the DataFrame
+        jobs_df = jobs_df.rename(columns=column_name_mapping)
+
+        # Remove the original startTime and endTime columns since we now have Submit time, End time, and Run time
+        jobs_df = jobs_df.drop(columns=['startTime', 'endTime'], errors='ignore')
+
+        # 7. Define the desired order of columns
+        desired_order = [
+            "Status", "Name", "Project", "Owner", "Pipeline", "ID",
+            "Submit time", "End time", "Run time", "Commit", "Cost",
+            "Resources", "Storage type", "Pipeline url",
+            "Nextflow version", "Executor", "Storage size", "Job queue ID",
+            "Accelerated file staging"
+        ]
+
+        # Reorder columns - only include columns that exist in the DataFrame
+        available_columns = [col for col in desired_order if col in jobs_df.columns]
+        # Add any remaining columns that aren't in the desired order
+        remaining_columns = [col for col in jobs_df.columns if col not in desired_order]
+        final_column_order = available_columns + remaining_columns
+
+        # Reorder the DataFrame
+        jobs_df = jobs_df[final_column_order]
+        return jobs_df
+
+    def save_job_list_to_csv(self, my_jobs_df, filename='my_jobs.csv'):
+        # Save to CSV
+        jobs_df = self.reorder_job_list(my_jobs_df, filename)
+        jobs_df.to_csv(filename, index=False)
+        print(f'\tJob list collected with a total of {len(jobs_df)} jobs.')
+        print(f'\tJob list saved to {filename}')
+
     def get_workflow_list(self, workspace_id, verify=True, get_all=True,
                           page=1, page_size=10, max_page_size=100,
                           archived_status=False):

{cloudos_cli-2.48.0 → cloudos_cli-2.49.0}/cloudos_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cloudos_cli
-Version: 2.48.0
+Version: 2.49.0
 Summary: Python package for interacting with CloudOS
 Home-page: https://github.com/lifebit-ai/cloudos-cli
 Author: David Piñeyro
@@ -775,16 +775,15 @@ This file can later be used when running a job with `cloudos job run --job-confi
 > [!NOTE]
 > Job details can only be retrieved for a single user, cannot see other user's job details.
 
-#### Get a list of your jobs from a CloudOS workspace
+#### Get a list of workspace jobs from a CloudOS
 
-You can get a summary of your last 30 submitted jobs (or your selected number of last jobs using `--last-n-jobs n`
-parameter) in two different formats:
+You can get a summary of the workspace's last 30 submitted jobs (or a selected number of last jobs using `--last-n-jobs n` parameter) in two different formats:
 
 - CSV: this is a table with a minimum predefined set of columns by default, or all the
 available columns using the `--all-fields` argument.
-- JSON: all the available information from your jobs, in JSON format.
+- JSON: all the available information from the workspace jobs, in JSON format (`--all-fields` is always enabled for this format).
 
-To get a list with your last 30 submitted jobs to a given workspace, in CSV format, use
+To get a list with the workspace's last 30 submitted jobs, in CSV format, use
 the following command:
 
 ```bash
@@ -806,7 +805,7 @@ Executing list...
 
 In addition, a file named `joblist.csv` is created.
 
-To get the same information, but for all your jobs and in JSON format, use the following command:
+To get the same information, but for all the workspace's jobs and in JSON format, use the following command:
 
 ```bash
 cloudos job list \

cloudos_cli-2.48.0/cloudos_cli/_version.py

@@ -1 +0,0 @@
-__version__ = '2.48.0'