1
0
mirror of https://github.com/kellyjonbrazil/jc.git synced 2025-06-17 00:07:37 +02:00
Files
jc/jc/parsers/rsync.py

341 lines
12 KiB
Python
Raw Normal View History

2022-01-28 14:08:43 -08:00
"""jc - JSON CLI output utility `rsync` command output parser
2022-01-31 11:13:23 -08:00
Supports the following options with all levels of verbosity:
- `-i` or `--itemize-changes`
- `--log-file`
2022-01-28 14:08:43 -08:00
Usage (cli):
$ rsync -i -a source/ dest | jc --rsync
or
$ jc rsync -i -a source/ dest
Usage (module):
import jc
result = jc.parse('rsync', rsync_command_output)
or
import jc.parsers.rsync
result = jc.parsers.rsync.parse(rsync_command_output)
Schema:
[
{
"summary": {
"date": string,
"time": string,
"process": integer, # need to convert
"sent": integer, # need to convert
"received": integer, # need to convert
2022-01-31 11:13:23 -08:00
"total_size": integer, # need to convert
"matches": integer, # need to convert
"hash_hits": integer, # need to convert
"false_alarms": integer, # need to convert
"data": integer?, # need to convert
"bytes_sec": float, # need to convert
"speedup": float # need to convert
},
"files": [
"filename": string,
"metadata": string,
"update_type": string/null,
"file_type": string/null,
"checksum_or_value_different": bool/null,
"size_different": bool/null,
"modification_time_different": bool/null,
"permissions_different": bool/null,
"owner_different": bool/null,
"group_different": bool/null,
"future": null,
"acl_different": bool/null,
2022-01-31 11:13:23 -08:00
"extended_attribute_different": bool/null
]
2022-01-28 14:08:43 -08:00
}
]
Examples:
$ rsync | jc --rsync -p
[]
$ rsync | jc --rsync -p -r
[]
"""
import re
2022-01-30 16:21:03 -08:00
from copy import deepcopy
2022-01-28 14:08:43 -08:00
from typing import List, Dict
import jc.utils
class info():
"""Provides parser metadata (version, author, etc.)"""
version = '1.0'
description = '`rsync` command parser'
author = 'Kelly Brazil'
author_email = 'kellyjonbrazil@gmail.com'
compatible = ['linux', 'darwin', 'cygwin', 'freebsd']
magic_commands = ['rsync -i', 'rsync --itemize-changes']
__version__ = info.version
def _process(proc_data: List[Dict]) -> List[Dict]:
"""
Final processing to conform to the schema.
Parameters:
proc_data: (List of Dictionaries) raw structured data to process
Returns:
List of Dictionaries. Structured to conform to the schema.
"""
2022-01-31 11:13:23 -08:00
int_list = ['process', 'sent', 'received', 'total_size', 'matches', 'has_hits', 'false_alarms', 'data']
float_list = ['bytes_sec', 'speedup']
for item in proc_data:
for key in item['summary']:
if key in int_list:
item['summary'][key] = jc.utils.convert_to_int(item['summary'][key])
if key in float_list:
item['summary'][key] = jc.utils.convert_to_float(item['summary'][key])
2022-01-28 15:00:05 -08:00
2022-01-28 14:08:43 -08:00
return proc_data
def parse(
data: str,
raw: bool = False,
quiet: bool = False
) -> List[Dict]:
"""
Main text parsing function
Parameters:
data: (string) text data to parse
raw: (boolean) unprocessed output if True
quiet: (boolean) suppress warning messages if True
Returns:
List of Dictionaries. Raw or processed structured data.
"""
jc.utils.compatibility(__name__, info.compatible, quiet)
jc.utils.input_type_check(data)
raw_output: List = []
2022-01-30 16:21:03 -08:00
rsync_run_new: Dict = {
'summary': {},
'files': []
2022-01-30 16:21:03 -08:00
}
rsync_run = deepcopy(rsync_run_new)
last_process = ''
2022-01-28 14:08:43 -08:00
update_type = {
'<': 'file sent',
'>': 'file received',
'c': 'local change or creation',
'h': 'hard link',
'.': 'not updated',
'*': 'message',
'+': None
}
file_type = {
'f': 'file',
'd': 'directory',
'L': 'symlink',
'D': 'device',
'S': 'special file',
'+': None
}
checksum_or_value_different = {
'c': True,
'.': False,
'+': None
}
size_different = {
's': True,
'.': False,
'+': None
}
modification_time_different = {
't': True,
'.': False,
'+': None
}
permissions_different = {
'p': True,
'.': False,
'+': None
}
owner_different = {
'o': True,
'.': False,
'+': None
}
group_different = {
'g': True,
'.': False,
'+': None
}
acl_different = {
'a': True,
'.': False,
'+': None
}
extended_attribute_different = {
'x': True,
'.': False,
'+': None
}
if jc.utils.has_data(data):
file_line_re = re.compile(r'(?P<meta>[<>ch.*][fdlDS][c.+][s.+][t.+][p.+][o.+][g.+][u.+][a.+][x.+]) (?P<name>.+)')
2022-01-28 14:45:01 -08:00
stat1_line_re = re.compile(r'(sent)\s+(?P<sent>[0-9,]+)\s+(bytes)\s+(received)\s+(?P<received>[0-9,]+)\s+(bytes)\s+(?P<bytes_sec>[0-9,.]+)\s+(bytes/sec)')
stat2_line_re = re.compile(r'(total size is)\s+(?P<total_size>[0-9,]+)\s+(speedup is)\s+(?P<speedup>[0-9,.]+)')
2022-01-28 14:08:43 -08:00
file_line_log_re = re.compile(r'(?P<date>\d\d\d\d/\d\d/\d\d)\s+(?P<time>\d\d:\d\d:\d\d)\s+\[(?P<process>\d+)\]\s+(?P<meta>[<>ch.*][fdlDS][c.+][s.+][t.+][p.+][o.+][g.+][u.+][a.+][x.+])\s+(?P<name>.+)')
stat_line_log_re = re.compile(r'(?P<date>\d\d\d\d/\d\d/\d\d)\s+(?P<time>\d\d:\d\d:\d\d)\s+\[(?P<process>\d+)\]\s+sent\s+(?P<sent>[\d,]+)\s+bytes\s+received\s+(?P<received>[\d,]+)\s+bytes\s+total\s+size\s+(?P<total_size>[\d,]+)')
stat1_line_log_v_re = re.compile(r'(?P<date>\d\d\d\d/\d\d/\d\d)\s+(?P<time>\d\d:\d\d:\d\d)\s+\[(?P<process>\d+)]\s+total:\s+matches=(?P<matches>[\d,]+)\s+hash_hits=(?P<hash_hits>[\d,]+)\s+false_alarms=(?P<false_alarms>[\d,]+)\s+data=(?P<data>[\d,]+)')
stat2_line_log_v_re = re.compile(r'(?P<date>\d\d\d\d/\d\d/\d\d)\s+(?P<time>\d\d:\d\d:\d\d)\s+\[(?P<process>\d+)\]\s+sent\s+(?P<sent>[\d,]+)\s+bytes\s+received\s+(?P<received>[\d,]+)\s+bytes\s+(?P<bytes_sec>[\d,.]+)\s+bytes/sec')
stat3_line_log_v_re = re.compile(r'(?P<date>\d\d\d\d/\d\d/\d\d)\s+(?P<time>\d\d:\d\d:\d\d)\s+\[(?P<process>\d+)]\s+total\s+size\s+is\s+(?P<total_size>[\d,]+)\s+speedup\s+is\s+(?P<speedup>[\d,.]+)')
2022-01-28 14:08:43 -08:00
for line in filter(None, data.splitlines()):
file_line = file_line_re.match(line)
2022-01-28 14:08:43 -08:00
if file_line:
filename = file_line.group('name')
meta = file_line.group('meta')
2022-01-28 14:08:43 -08:00
output_line = {
'filename': filename,
'metadata': meta,
'update_type': update_type[meta[0]],
'file_type': file_type[meta[1]],
'checksum_or_value_different': checksum_or_value_different[meta[2]],
'size_different': size_different[meta[3]],
'modification_time_different': modification_time_different[meta[4]],
'permissions_different': permissions_different[meta[5]],
'owner_different': owner_different[meta[6]],
'group_different': group_different[meta[7]],
'acl_different': acl_different[meta[9]],
'extended_attribute_different': extended_attribute_different[meta[10]]
}
rsync_run['files'].append(output_line)
2022-01-28 14:45:01 -08:00
continue
file_line_log = file_line_log_re.match(line)
if file_line_log:
filename = file_line_log.group('name')
date = file_line_log.group('date')
time = file_line_log.group('time')
process = file_line_log.group('process')
meta = file_line_log.group('meta')
if process != last_process:
2022-01-30 16:21:03 -08:00
raw_output.append(rsync_run)
rsync_run = deepcopy(rsync_run_new)
last_process = process
output_line = {
'filename': filename,
'date': date,
'time': time,
'process': process,
'metadata': meta,
'update_type': update_type[meta[0]],
'file_type': file_type[meta[1]],
'checksum_or_value_different': checksum_or_value_different[meta[2]],
'size_different': size_different[meta[3]],
'modification_time_different': modification_time_different[meta[4]],
'permissions_different': permissions_different[meta[5]],
'owner_different': owner_different[meta[6]],
'group_different': group_different[meta[7]],
'acl_different': acl_different[meta[9]],
'extended_attribute_different': extended_attribute_different[meta[10]]
}
rsync_run['files'].append(output_line)
continue
stat1_line = stat1_line_re.match(line)
2022-01-28 14:45:01 -08:00
if stat1_line:
rsync_run['summary'] = {
2022-01-28 14:45:01 -08:00
'sent': stat1_line.group('sent'),
'received': stat1_line.group('received'),
'bytes_sec': stat1_line.group('bytes_sec')
}
continue
stat2_line = stat2_line_re.match(line)
2022-01-28 14:45:01 -08:00
if stat2_line:
rsync_run['summary']['total_size'] = stat2_line.group('total_size')
rsync_run['summary']['speedup'] = stat2_line.group('speedup')
2022-01-28 14:45:01 -08:00
continue
2022-01-28 14:08:43 -08:00
stat_line_log = stat_line_log_re.match(line)
if stat_line_log:
rsync_run['summary'] = {
'date': stat_line_log.group('date'),
'time': stat_line_log.group('time'),
'process': stat_line_log.group('process'),
'sent': stat_line_log.group('sent'),
'received': stat_line_log.group('received'),
'total_size': stat_line_log.group('total_size')
}
continue
2022-01-30 16:21:03 -08:00
stat1_line_log_v = stat1_line_log_v_re.match(line)
if stat1_line_log_v:
rsync_run['summary'] = {
'date': stat1_line_log_v.group('date'),
'time': stat1_line_log_v.group('time'),
'process': stat1_line_log_v.group('process'),
'matches': stat1_line_log_v.group('matches'),
'hash_hits': stat1_line_log_v.group('hash_hits'),
'false_alarms': stat1_line_log_v.group('false_alarms'),
'data': stat1_line_log_v.group('data')
}
continue
stat2_line_log_v = stat2_line_log_v_re.match(line)
if stat2_line_log_v:
rsync_run['summary']['sent'] = stat2_line_log_v.group('sent')
rsync_run['summary']['received'] = stat2_line_log_v.group('received')
rsync_run['summary']['bytes_sec'] = stat2_line_log_v.group('bytes_sec')
continue
stat3_line_log_v = stat3_line_log_v_re.match(line)
if stat3_line_log_v:
rsync_run['summary']['total_size'] = stat3_line_log_v.group('total_size')
rsync_run['summary']['speedup'] = stat3_line_log_v.group('speedup')
continue
raw_output.append(rsync_run)
# cleanup blank entries
raw_output = [run for run in raw_output if run != rsync_run_new]
2022-01-28 14:08:43 -08:00
return raw_output if raw else _process(raw_output)