diff options
Diffstat (limited to 'tools/glusterfind/src/utils.py')
| -rw-r--r-- | tools/glusterfind/src/utils.py | 63 |
1 files changed, 51 insertions, 12 deletions
diff --git a/tools/glusterfind/src/utils.py b/tools/glusterfind/src/utils.py index cda5ea6378e..906ebd8f252 100644 --- a/tools/glusterfind/src/utils.py +++ b/tools/glusterfind/src/utils.py @@ -1,4 +1,4 @@ -#!/usr/bin/env python +# -*- coding: utf-8 -*- # Copyright (c) 2015 Red Hat, Inc. <http://www.redhat.com/> # This file is part of GlusterFS. @@ -15,10 +15,12 @@ import xml.etree.cElementTree as etree import logging import os from datetime import datetime -import urllib ROOT_GFID = "00000000-0000-0000-0000-000000000001" DEFAULT_CHANGELOG_INTERVAL = 15 +SPACE_ESCAPE_CHAR = "%20" +NEWLINE_ESCAPE_CHAR = "%0A" +PERCENTAGE_ESCAPE_CHAR = "%25" ParseError = etree.ParseError if hasattr(etree, 'ParseError') else SyntaxError cache_data = {} @@ -34,10 +36,10 @@ class RecordType(object): def cache_output(func): def wrapper(*args, **kwargs): global cache_data - if cache_data.get(func.func_name, None) is None: - cache_data[func.func_name] = func(*args, **kwargs) + if cache_data.get(func.__name__, None) is None: + cache_data[func.__name__] = func(*args, **kwargs) - return cache_data[func.func_name] + return cache_data[func.__name__] return wrapper @@ -56,12 +58,13 @@ def find(path, callback_func=lambda x: True, filter_func=lambda x: True, # Capture filter_func output and pass it to callback function filter_result = filter_func(path) if filter_result is not None: - callback_func(path, filter_result) + callback_func(path, filter_result, os.path.isdir(path)) for p in os.listdir(path): full_path = os.path.join(path, p) - if os.path.isdir(full_path): + is_dir = os.path.isdir(full_path) + if is_dir: if subdirs_crawl: find(full_path, callback_func, filter_func, ignore_dirs) else: @@ -71,10 +74,11 @@ def find(path, callback_func=lambda x: True, filter_func=lambda x: True, else: filter_result = filter_func(full_path) if filter_result is not None: - callback_func(full_path, filter_result) + callback_func(full_path, filter_result, is_dir) -def output_write(f, path, prefix=".", encode=False): +def output_write(f, path, prefix=".", encode=False, tag="", + field_separator=" "): if path == "": return @@ -82,9 +86,12 @@ def output_write(f, path, prefix=".", encode=False): path = os.path.join(prefix, path) if encode: - path = urllib.quote_plus(path) + path = quote_plus_space_newline(path) - f.write("%s\n" % path) + # set the field separator + FS = "" if tag == "" else field_separator + + f.write("%s%s%s\n" % (tag.strip(), FS, path)) def human_time(ts): @@ -223,6 +230,38 @@ def get_changelog_rollover_time(volumename): try: tree = etree.fromstring(out) - return int(tree.find('volGetopts/Value').text) + val = tree.find('volGetopts/Opt/Value').text + if val is not None: + # Filter the value by split, as it may be 'X (DEFAULT)' + # and we only need 'X' + return int(val.split(' ', 1)[0]) except ParseError: return DEFAULT_CHANGELOG_INTERVAL + + +def output_path_prepare(path, args): + """ + If Prefix is set, joins to Path, removes ending slash + and encodes it. + """ + if args.output_prefix != ".": + path = os.path.join(args.output_prefix, path) + if path.endswith("/"): + path = path[0:len(path)-1] + + if args.no_encode: + return path + else: + return quote_plus_space_newline(path) + + +def unquote_plus_space_newline(s): + return s.replace(SPACE_ESCAPE_CHAR, " ")\ + .replace(NEWLINE_ESCAPE_CHAR, "\n")\ + .replace(PERCENTAGE_ESCAPE_CHAR, "%") + + +def quote_plus_space_newline(s): + return s.replace("%", PERCENTAGE_ESCAPE_CHAR)\ + .replace(" ", SPACE_ESCAPE_CHAR)\ + .replace("\n", NEWLINE_ESCAPE_CHAR) |