[rocpd] Adding merge and package submodules for rocpd (#164)

* adding ROCpd database merge

* adding ROCpd database merge concatenating all tables

* update merge script

  - copy all tables from files

* fix merge format

* Add package submodule, initial POC.  Need to refine

* Minor fixes and clean up duplicated code in package.py

* Revamp metadata layout, add wildcard and .rpdb parsing

* Add auto merge & package when > 5 DBs, add examples, don't use auto_merge when using sub-commands merge & package

* - Extend package/yaml inputs to all rocpd modules
- Improve handling more corner cases for bad input files when parsing input parameters (bad yaml files, bad .rpdb folder, folders as input)
- Changed to use UUID in merged filename instead of the time, in auto-merge algorithm

* Minor text fixes for consistancy between modules

* Add more wildcard support and add package, merge tests

* Make changes based on review suggestions

* Move parsing packages into importer.py, simplified adding required params to a function

* fix package test by flattening input list before processing

* Integrate merge.py changes from Jonathan to add name-collision checks, recreating indexes, foreign key check (disabled for now, due to processing time)

* Rework rocpd.<submodule>.{add_args,process_args}

- add_args function returns a functor which accepts input and args
- time_window functor returned from add_args automatically applies time windowing of input

* change merge&package limit to 1, merge should create data views

* Move files by default instead of making copies

- copying can be enabled by passing "copy=True" or --copy cmdline argument

* refactor package to make the logic cleaner, set merge limit back to 5

* Allow automerge-limit param to override limit, change default back to 1.  Tests updated to use query, much quicker

* Update --help instructions for package

---------

Co-authored-by: acanadas <acanadas@amd.com>
Co-authored-by: a-canadasruiz <Araceli.CanadasRuiz@amd.com>
Co-authored-by: Young Hui <young.hui@amd.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
This commit is contained in:
systems-assistant[bot]
2025-11-12 17:07:12 -05:00
committed by GitHub
vanhempi f58393108f
commit 061948a5ec
13 muutettua tiedostoa jossa 1512 lisäystä ja 330 poistoa
@@ -32,7 +32,15 @@ from datetime import datetime
from . import output_config
from . import libpyrocpd
from .importer import RocpdImportData
from .time_window import apply_time_window
__all__ = [
"export_sqlite_query",
"send_report_email",
"zip_files",
"add_args",
"execute",
"main",
]
def export_sqlite_query(
@@ -439,34 +447,18 @@ def add_args(parser):
"--template-path", help="Path to a Jinja2 HTML template for the dashboard"
)
return [
"query",
"script",
"email_to",
"email_from",
"email_subject",
"smtp_server",
"smtp_port",
"smtp_user",
"smtp_password",
"inline_preview",
"zip_attachments",
"format",
"template_path",
]
def process_args(input, args):
ret = {}
return ret
return process_args
def process_args(args, valid_args):
# do not add any of the arguments to the output config dict
ret = {}
return ret
def execute(input, args, config=None, **kwargs):
def execute(input, args, config=None, window_args=None, **kwargs):
importData = RocpdImportData(input)
apply_time_window(importData, **window_args)
importData = RocpdImportData(
input, automerge_limit=getattr(args, "automerge_limit", None)
)
config = (
output_config.output_config(**kwargs)
@@ -524,11 +516,8 @@ def execute(input, args, config=None, window_args=None, **kwargs):
def main(argv=None):
import argparse
from .time_window import add_args as add_args_time_window
from .time_window import process_args as process_args_time_window
from .output_config import add_args as add_args_output_config
from .output_config import process_args as process_args_output_config
from .output_config import add_generic_args, process_generic_args
from . import time_window
from . import output_config
parser = argparse.ArgumentParser(
description="Generate report for rocpd query", allow_abbrev=False
@@ -545,17 +534,19 @@ def main(argv=None):
help="Input path and filename to one or more database(s), separated by spaces",
)
valid_out_config_args = add_args_output_config(parser)
valid_generic_args = add_generic_args(parser)
valid_time_window_args = add_args_time_window(parser)
valid_query_args = add_args(parser)
process_out_config_args = output_config.add_args(parser)
process_generic_args = output_config.add_generic_args(parser)
process_time_window_args = time_window.add_args(parser)
process_query_args = add_args(parser)
args = parser.parse_args(argv)
out_cfg_args = process_args_output_config(args, valid_out_config_args)
generic_out_cfg_args = process_generic_args(args, valid_generic_args)
window_args = process_args_time_window(args, valid_time_window_args)
query_args = process_args(args, valid_query_args)
input = RocpdImportData(args.input)
out_cfg_args = process_out_config_args(input, args)
generic_out_cfg_args = process_generic_args(input, args)
query_args = process_query_args(input, args)
process_time_window_args(input, args)
all_args = {
**query_args,
@@ -564,9 +555,8 @@ def main(argv=None):
}
execute(
args.input,
input,
args,
window_args=window_args,
**all_args,
)