python/jc
1
0
Fork 0
mirror of https://github.com/kellyjonbrazil/jc.git synced 2025-08-10 22:41:51 +02:00
Code Issues Releases Activity

add multi-archive support

Browse Source
This commit is contained in:
Kelly Brazil
2021-12-21 11:11:44 -08:00
parent ff78a46c48
commit 51d2f316f3
1 changed files with 88 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

151
jc/parsers/zipinfo.py
View File

@@ -19,30 +19,31 @@ Usage (module):
result = jc.parsers.zipinfo.parse(zipinfo_command_output) result = jc.parsers.zipinfo.parse(zipinfo_command_output)
Schema: Schema:
[
{ {
"archive": string, "archive": string,
"size": integer, "size": integer,
"size_unit": string, "size_unit": string,
"number_entries": integer, "number_entries": integer,
"number_files": integer, "number_files": integer,
"bytes_uncompressed": integer, "bytes_uncompressed": integer,
"bytes_compressed": integer, "bytes_compressed": integer,
"percent_compressed": float, "percent_compressed": float,
"files": [ "files": [
{ {
"flags": string, "flags": string,
"zipversion": string, "zipversion": string,
"zipunder": string "zipunder": string
"filesize": integer, "filesize": integer,
"type": string, "type": string,
"method": string, "method": string,
"date": string, "date": string,
"time": string, "time": string,
"filename": string "filename": string
} }
] ]
} }
]
Examples: Examples:
@@ -103,17 +104,20 @@ def _process(proc_data):
""" """
for entry in proc_data: for entry in proc_data:
int_list = ['bytes_compressed', 'bytes_uncompressed', 'number_entries', 'number_files', 'size'] int_list = ['bytes_compressed', 'bytes_uncompressed', 'number_entries',
'number_files', 'size', 'filesize']
float_list = ['percent_compressed']
for key in entry: for key in entry:
if key in int_list: if key in int_list:
entry[key] = jc.utils.convert_to_int(entry[key]) entry[key] = jc.utils.convert_to_int(entry[key])
if key in float_list:
entry[key] = jc.utils.convert_to_float(entry[key])
if key in "files": if 'files' in key:
for d in entry[key]: for item in entry['files']:
for key in d: for key in item:
if key in "filesize": if key in int_list:
d[key] = jc.utils.convert_to_int(d[key]) item[key] = jc.utils.convert_to_int(item[key])
return proc_data return proc_data
@@ -134,47 +138,68 @@ def parse(data, raw=False, quiet=False):
jc.utils.compatibility(__name__, info.compatible, quiet) jc.utils.compatibility(__name__, info.compatible, quiet)
jc.utils.input_type_check(data) jc.utils.input_type_check(data)
raw_output = {} raw_output = []
archives = []
datalines = data.splitlines()
datalist = list(filter(None, datalines))
if jc.utils.has_data(data): if jc.utils.has_data(data):
datalines = data.splitlines()
archive_info = [] # remove last line of multi-archive output since it is not needed
if datalines[-1].endswith('archives were successfully processed.'):
datalines.pop(-1)
# 1st line # extract each archive into its own list of lines.
# Archive: log4j-core-2.16.0.jar # archives are separated by a blank line
line = datalist.pop(0) this_archive = []
_, archive = line.split() for row in datalines:
if row == '':
archives.append(this_archive)
this_archive = []
continue
# 2nd line this_archive.append(row)
# Zip file size: 1789565 bytes, number of entries: 1218
line = datalist.pop(0)
_, _, _, size, size_unit, _, _, _, number_entries = line.split()
size_unit = size_unit.rstrip(',')
# last line if this_archive:
# 1218 files, 3974141 bytes uncompressed, 1515455 bytes compressed: 61.9% archives.append(this_archive)
line = datalist.pop(-1)
number_files, _, bytes_uncompressed, _, _, bytes_compressed, _, _, percent_compressed = line.split()
percent_compressed = float(percent_compressed.rstrip("%"))
# Add header row for parsing # iterate through list of archives and parse
datalist[:0] = ['flags zipversion zipunder filesize type method date time filename'] for archive_item in archives:
archive_info = {}
file_list = jc.parsers.universal.simple_table_parse(datalist) # 1st line
# Archive: log4j-core-2.16.0.jar
line = archive_item.pop(0)
_, archive = line.split()
archive_info.append({'archive': archive, # 2nd line
'size': size, # Zip file size: 1789565 bytes, number of entries: 1218
'size_unit': size_unit, line = archive_item.pop(0)
'number_entries': number_entries, _, _, _, size, size_unit, *_, number_entries = line.split()
'number_files': number_files, size_unit = size_unit.rstrip(',')
'bytes_uncompressed': bytes_uncompressed,
'bytes_compressed': bytes_compressed,
'percent_compressed': percent_compressed,
'files': file_list})
raw_output = archive_info # last line
# 1218 files, 3974141 bytes uncompressed, 1515455 bytes compressed: 61.9%
line = archive_item.pop(-1)
number_files, _, bytes_uncompressed, _, _, bytes_compressed, *_, percent_compressed = line.split()
percent_compressed = percent_compressed.rstrip("%")
# Add header row for parsing
archive_item[:0] = ['flags zipversion zipunder filesize type method date time filename']
file_list = jc.parsers.universal.simple_table_parse(archive_item)
archive_info = {
'archive': archive,
'size': size,
'size_unit': size_unit,
'number_entries': number_entries,
'number_files': number_files,
'bytes_uncompressed': bytes_uncompressed,
'bytes_compressed': bytes_compressed,
'percent_compressed': percent_compressed,
'files': file_list
}
raw_output.append(archive_info)
return raw_output if raw else _process(raw_output) return raw_output if raw else _process(raw_output)