Loading computing/hadoop/HadoopShell.ipynb +0 −0 Original line number Diff line number Diff line computing/hadoop/hadoop_utils.py +1 −86 Original line number Diff line number Diff line from datetime import datetime from os import environ, popen import queue import re import subprocess import threading import time import ipywidgets as widgets Loading Loading @@ -106,88 +104,5 @@ def kinit(): display(widget_layout) # Function to read output continuously from stdout and stderr def read_output(stream, output_queue): for line in iter(stream.readline, ''): output_queue.put(line) stream.close() class BeelineCLI: def __init__(self): # Start the beeline CLI as a subprocess self.beeline_process = subprocess.Popen( ['beeline'], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, bufsize=1 ) # Queues to hold stdout and stderr lines self.stdout_queue = queue.Queue() self.stderr_queue = queue.Queue() # Threads to read from stdout and stderr self.stdout_thread = threading.Thread( target=read_output, args=( self.beeline_process.stdout, self.stdout_queue ), daemon=True ) self.stderr_thread = threading.Thread( target=read_output, args=( self.beeline_process.stderr, self.stderr_queue ), daemon=True ) self.stdout_thread.start() self.stderr_thread.start() self.print_outputs() def run(self, command, wait_s=1): """Send a query to the beeline process and print the output.""" # Write the query to beeline's stdin self.beeline_process.stdin.write(command + '\n') self.beeline_process.stdin.flush() self.print_outputs(wait_s=wait_s) def print_outputs(self, wait_s=1): last_output_handled = datetime.now() while True: output_handled = False try: while not self.stderr_queue.empty(): print(self.stderr_queue.get_nowait(), end='') output_handled = True last_output_handled = datetime.now() while not self.stdout_queue.empty(): print(self.stdout_queue.get_nowait(), end='') output_handled = True last_output_handled = datetime.now() except queue.Empty: continue # Break the loop if no new output is being handled last_handling_s = (datetime.now() - last_output_handled).seconds if (not output_handled) and (last_handling_s > wait_s): break def terminate(self): # Stop the beeline process after use self.run('!quit') self.beeline_process.terminate() self.stdout_thread.join() self.stderr_thread.join() set_hadoop_env() kinit() No newline at end of file ui/NotebookCLI.ipynb 0 → 100644 +110 −0 Original line number Diff line number Diff line %% Cell type:code id:69b71081-968d-4e98-995f-057d28b6fa6a tags: ``` python %load_ext autoreload ``` %% Cell type:code id:9b51aabc-bbe9-4a8f-af43-f1d2de1cdd45 tags: ``` python %autoreload 1 ``` %% Cell type:code id:8942713d-49f7-408a-a2ff-242914455da0 tags: ``` python %aimport ui_utils ``` %% Cell type:markdown id:69c2975e-a7af-4fa1-a423-f4604e275d2f tags: # Running a CLI application from a notebook <p style="font-size:36px; color:red; font-weight:bold">Hack alert</p> This has been done for demostrative purposes but it is not really convenient and safe. Only use this as the last option!! This notebook and the realted library contains some code to be able to interact with CLI utilities from a notebook %% Cell type:code id:9727ec1a-96de-4172-b93d-9f05aa858d8d tags: ``` python cli = ui_utils.CLI(['/bin/sqlite3'], 1) ``` %% Cell type:code id:636487b8-4825-4ccb-a2d3-37bce3a31970 tags: ``` python cli.run('.help') ``` %% Output .archive ... Manage SQL archives .auth ON|OFF Show authorizer callbacks .backup ?DB? FILE Backup DB (default "main") to FILE .bail on|off Stop after hitting an error. Default OFF .binary on|off Turn binary output on or off. Default OFF .cd DIRECTORY Change the working directory to DIRECTORY .changes on|off Show number of rows changed by SQL .check GLOB Fail if output since .testcase does not match .clone NEWDB Clone data into NEWDB from the existing database .databases List names and files of attached databases .dbconfig ?op? ?val? List or change sqlite3_db_config() options .dbinfo ?DB? Show status information about the database .dump ?TABLE? Render database content as SQL .echo on|off Turn command echo on or off .eqp on|off|full|... Enable or disable automatic EXPLAIN QUERY PLAN .excel Display the output of next command in spreadsheet .exit ?CODE? Exit this program with return-code CODE .expert EXPERIMENTAL. Suggest indexes for queries .explain ?on|off|auto? Change the EXPLAIN formatting mode. Default: auto .filectrl CMD ... Run various sqlite3_file_control() operations .fullschema ?--indent? Show schema and the content of sqlite_stat tables .headers on|off Turn display of headers on or off .help ?-all? ?PATTERN? Show help text for PATTERN .import FILE TABLE Import data from FILE into TABLE .imposter INDEX TABLE Create imposter table TABLE on index INDEX .indexes ?TABLE? Show names of indexes .limit ?LIMIT? ?VAL? Display or change the value of an SQLITE_LIMIT .lint OPTIONS Report potential schema issues. .load FILE ?ENTRY? Load an extension library .log FILE|off Turn logging on or off. FILE can be stderr/stdout .mode MODE ?TABLE? Set output mode .nullvalue STRING Use STRING in place of NULL values .once ?OPTIONS? ?FILE? Output for the next SQL command only to FILE .open ?OPTIONS? ?FILE? Close existing database and reopen FILE .output ?FILE? Send output to FILE or stdout if FILE is omitted .parameter CMD ... Manage SQL parameter bindings .print STRING... Print literal STRING .progress N Invoke progress handler after every N opcodes .prompt MAIN CONTINUE Replace the standard prompts .quit Exit this program .read FILE Read input from FILE .recover Recover as much data as possible from corrupt db. .restore ?DB? FILE Restore content of DB (default "main") from FILE .save FILE Write in-memory database into FILE .scanstats on|off Turn sqlite3_stmt_scanstatus() metrics on or off .schema ?PATTERN? Show the CREATE statements matching PATTERN .selftest ?OPTIONS? Run tests defined in the SELFTEST table .separator COL ?ROW? Change the column and row separators .sha3sum ... Compute a SHA3 hash of database content .shell CMD ARGS... Run CMD ARGS... in a system shell .show Show the current values for various settings .stats ?on|off? Show stats or turn stats on or off .system CMD ARGS... Run CMD ARGS... in a system shell .tables ?TABLE? List names of tables matching LIKE pattern TABLE .testcase NAME Begin redirecting output to 'testcase-out.txt' .testctrl CMD ... Run various sqlite3_test_control() operations .timeout MS Try opening locked tables for MS milliseconds .timer on|off Turn SQL timer on or off .trace ?OPTIONS? Output each SQL statement as it is run .vfsinfo ?AUX? Information about the top-level VFS .vfslist List all available VFSes .vfsname ?AUX? Print the name of the VFS stack .width NUM1 NUM2 ... Set minimum column widths for columnar output %% Cell type:code id:597f8500-6dd7-42af-ac29-c2b5ba57a16e tags: ``` python ``` ui/ui_utils.py 0 → 100644 +83 −0 Original line number Diff line number Diff line from datetime import datetime import queue import subprocess import threading # Function to read output continuously from stdout and stderr def read_output(stream, output_queue): for line in iter(stream.readline, ''): output_queue.put(line) stream.close() class CLI: def __init__(self, cmd, init_wait_s=1): # Start the CLI as a subprocess self.cli_process = subprocess.Popen( cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, bufsize=1 ) # Queues to hold stdout and stderr lines self.stdout_queue = queue.Queue() self.stderr_queue = queue.Queue() # Threads to read from stdout and stderr self.stdout_thread = threading.Thread( target=read_output, args=( self.cli_process.stdout, self.stdout_queue ), daemon=True ) self.stderr_thread = threading.Thread( target=read_output, args=( self.cli_process.stderr, self.stderr_queue ), daemon=True ) self.stdout_thread.start() self.stderr_thread.start() self.print_outputs(wait_s=init_wait_s) def run(self, command, wait_s=1): """Send a command to the process and print the output.""" self.cli_process.stdin.write(command + '\n') self.cli_process.stdin.flush() self.print_outputs(wait_s=wait_s) def print_outputs(self, wait_s=1): last_output_handled = datetime.now() while True: output_handled = False try: while not self.stderr_queue.empty(): print(self.stderr_queue.get_nowait(), end='') output_handled = True last_output_handled = datetime.now() while not self.stdout_queue.empty(): print(self.stdout_queue.get_nowait(), end='') output_handled = True last_output_handled = datetime.now() except queue.Empty: continue # Break the loop if no new output is being handled last_handling_s = (datetime.now() - last_output_handled).seconds if (not output_handled) and (last_handling_s > wait_s): break def terminate(self, command=None): if not command is None: self.run(command) self.cli_process.terminate() self.stdout_thread.join() self.stderr_thread.join() No newline at end of file Loading
computing/hadoop/hadoop_utils.py +1 −86 Original line number Diff line number Diff line from datetime import datetime from os import environ, popen import queue import re import subprocess import threading import time import ipywidgets as widgets Loading Loading @@ -106,88 +104,5 @@ def kinit(): display(widget_layout) # Function to read output continuously from stdout and stderr def read_output(stream, output_queue): for line in iter(stream.readline, ''): output_queue.put(line) stream.close() class BeelineCLI: def __init__(self): # Start the beeline CLI as a subprocess self.beeline_process = subprocess.Popen( ['beeline'], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, bufsize=1 ) # Queues to hold stdout and stderr lines self.stdout_queue = queue.Queue() self.stderr_queue = queue.Queue() # Threads to read from stdout and stderr self.stdout_thread = threading.Thread( target=read_output, args=( self.beeline_process.stdout, self.stdout_queue ), daemon=True ) self.stderr_thread = threading.Thread( target=read_output, args=( self.beeline_process.stderr, self.stderr_queue ), daemon=True ) self.stdout_thread.start() self.stderr_thread.start() self.print_outputs() def run(self, command, wait_s=1): """Send a query to the beeline process and print the output.""" # Write the query to beeline's stdin self.beeline_process.stdin.write(command + '\n') self.beeline_process.stdin.flush() self.print_outputs(wait_s=wait_s) def print_outputs(self, wait_s=1): last_output_handled = datetime.now() while True: output_handled = False try: while not self.stderr_queue.empty(): print(self.stderr_queue.get_nowait(), end='') output_handled = True last_output_handled = datetime.now() while not self.stdout_queue.empty(): print(self.stdout_queue.get_nowait(), end='') output_handled = True last_output_handled = datetime.now() except queue.Empty: continue # Break the loop if no new output is being handled last_handling_s = (datetime.now() - last_output_handled).seconds if (not output_handled) and (last_handling_s > wait_s): break def terminate(self): # Stop the beeline process after use self.run('!quit') self.beeline_process.terminate() self.stdout_thread.join() self.stderr_thread.join() set_hadoop_env() kinit() No newline at end of file
ui/NotebookCLI.ipynb 0 → 100644 +110 −0 Original line number Diff line number Diff line %% Cell type:code id:69b71081-968d-4e98-995f-057d28b6fa6a tags: ``` python %load_ext autoreload ``` %% Cell type:code id:9b51aabc-bbe9-4a8f-af43-f1d2de1cdd45 tags: ``` python %autoreload 1 ``` %% Cell type:code id:8942713d-49f7-408a-a2ff-242914455da0 tags: ``` python %aimport ui_utils ``` %% Cell type:markdown id:69c2975e-a7af-4fa1-a423-f4604e275d2f tags: # Running a CLI application from a notebook <p style="font-size:36px; color:red; font-weight:bold">Hack alert</p> This has been done for demostrative purposes but it is not really convenient and safe. Only use this as the last option!! This notebook and the realted library contains some code to be able to interact with CLI utilities from a notebook %% Cell type:code id:9727ec1a-96de-4172-b93d-9f05aa858d8d tags: ``` python cli = ui_utils.CLI(['/bin/sqlite3'], 1) ``` %% Cell type:code id:636487b8-4825-4ccb-a2d3-37bce3a31970 tags: ``` python cli.run('.help') ``` %% Output .archive ... Manage SQL archives .auth ON|OFF Show authorizer callbacks .backup ?DB? FILE Backup DB (default "main") to FILE .bail on|off Stop after hitting an error. Default OFF .binary on|off Turn binary output on or off. Default OFF .cd DIRECTORY Change the working directory to DIRECTORY .changes on|off Show number of rows changed by SQL .check GLOB Fail if output since .testcase does not match .clone NEWDB Clone data into NEWDB from the existing database .databases List names and files of attached databases .dbconfig ?op? ?val? List or change sqlite3_db_config() options .dbinfo ?DB? Show status information about the database .dump ?TABLE? Render database content as SQL .echo on|off Turn command echo on or off .eqp on|off|full|... Enable or disable automatic EXPLAIN QUERY PLAN .excel Display the output of next command in spreadsheet .exit ?CODE? Exit this program with return-code CODE .expert EXPERIMENTAL. Suggest indexes for queries .explain ?on|off|auto? Change the EXPLAIN formatting mode. Default: auto .filectrl CMD ... Run various sqlite3_file_control() operations .fullschema ?--indent? Show schema and the content of sqlite_stat tables .headers on|off Turn display of headers on or off .help ?-all? ?PATTERN? Show help text for PATTERN .import FILE TABLE Import data from FILE into TABLE .imposter INDEX TABLE Create imposter table TABLE on index INDEX .indexes ?TABLE? Show names of indexes .limit ?LIMIT? ?VAL? Display or change the value of an SQLITE_LIMIT .lint OPTIONS Report potential schema issues. .load FILE ?ENTRY? Load an extension library .log FILE|off Turn logging on or off. FILE can be stderr/stdout .mode MODE ?TABLE? Set output mode .nullvalue STRING Use STRING in place of NULL values .once ?OPTIONS? ?FILE? Output for the next SQL command only to FILE .open ?OPTIONS? ?FILE? Close existing database and reopen FILE .output ?FILE? Send output to FILE or stdout if FILE is omitted .parameter CMD ... Manage SQL parameter bindings .print STRING... Print literal STRING .progress N Invoke progress handler after every N opcodes .prompt MAIN CONTINUE Replace the standard prompts .quit Exit this program .read FILE Read input from FILE .recover Recover as much data as possible from corrupt db. .restore ?DB? FILE Restore content of DB (default "main") from FILE .save FILE Write in-memory database into FILE .scanstats on|off Turn sqlite3_stmt_scanstatus() metrics on or off .schema ?PATTERN? Show the CREATE statements matching PATTERN .selftest ?OPTIONS? Run tests defined in the SELFTEST table .separator COL ?ROW? Change the column and row separators .sha3sum ... Compute a SHA3 hash of database content .shell CMD ARGS... Run CMD ARGS... in a system shell .show Show the current values for various settings .stats ?on|off? Show stats or turn stats on or off .system CMD ARGS... Run CMD ARGS... in a system shell .tables ?TABLE? List names of tables matching LIKE pattern TABLE .testcase NAME Begin redirecting output to 'testcase-out.txt' .testctrl CMD ... Run various sqlite3_test_control() operations .timeout MS Try opening locked tables for MS milliseconds .timer on|off Turn SQL timer on or off .trace ?OPTIONS? Output each SQL statement as it is run .vfsinfo ?AUX? Information about the top-level VFS .vfslist List all available VFSes .vfsname ?AUX? Print the name of the VFS stack .width NUM1 NUM2 ... Set minimum column widths for columnar output %% Cell type:code id:597f8500-6dd7-42af-ac29-c2b5ba57a16e tags: ``` python ```
ui/ui_utils.py 0 → 100644 +83 −0 Original line number Diff line number Diff line from datetime import datetime import queue import subprocess import threading # Function to read output continuously from stdout and stderr def read_output(stream, output_queue): for line in iter(stream.readline, ''): output_queue.put(line) stream.close() class CLI: def __init__(self, cmd, init_wait_s=1): # Start the CLI as a subprocess self.cli_process = subprocess.Popen( cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, bufsize=1 ) # Queues to hold stdout and stderr lines self.stdout_queue = queue.Queue() self.stderr_queue = queue.Queue() # Threads to read from stdout and stderr self.stdout_thread = threading.Thread( target=read_output, args=( self.cli_process.stdout, self.stdout_queue ), daemon=True ) self.stderr_thread = threading.Thread( target=read_output, args=( self.cli_process.stderr, self.stderr_queue ), daemon=True ) self.stdout_thread.start() self.stderr_thread.start() self.print_outputs(wait_s=init_wait_s) def run(self, command, wait_s=1): """Send a command to the process and print the output.""" self.cli_process.stdin.write(command + '\n') self.cli_process.stdin.flush() self.print_outputs(wait_s=wait_s) def print_outputs(self, wait_s=1): last_output_handled = datetime.now() while True: output_handled = False try: while not self.stderr_queue.empty(): print(self.stderr_queue.get_nowait(), end='') output_handled = True last_output_handled = datetime.now() while not self.stdout_queue.empty(): print(self.stdout_queue.get_nowait(), end='') output_handled = True last_output_handled = datetime.now() except queue.Empty: continue # Break the loop if no new output is being handled last_handling_s = (datetime.now() - last_output_handled).seconds if (not output_handled) and (last_handling_s > wait_s): break def terminate(self, command=None): if not command is None: self.run(command) self.cli_process.terminate() self.stdout_thread.join() self.stderr_thread.join() No newline at end of file