Mercurial > p > roundup > code
view scripts/spam-remover @ 5525:bb7865241f8a
Make CSV import/export compatible across Python versions (also RDBMS journals) (issue 2550976, issue 2550975).
The roundup-admin export and import commands are used for migrating
between different database backends. It is desirable that they should
be usable also for migrations between Python 2 and Python 3, and in
some cases (e.g. with the anydbm backend) this may be required.
To be usable for such migrations, the format of the generated CSV
files needs to be stable, meaning the same as currently used with
Python 2. The export process uses repr() to produce the fields in the
CSV files and eval() to convert them back to Python data structures.
repr() of strings with non-ASCII characters produces different results
for Python 2 and Python 3.
This patch adds repr_export and eval_import functions to
roundup/anypy/strings.py which provide the required operations that
are just repr() and eval() in Python 2, but are more complicated in
Python 3 to use data representations compatible with Python 2. These
functions are then used in the required places for export and import.
repr() and eval() are also used in storing the dict of changed values
in the journal for the RDBMS backends. It is similarly desirable that
the database be compatible between Python 2 and Python 3, so that
export and import do not need to be used for a migration between
Python versions for non-anydbm back ends. Thus, this patch changes
rdbms_common.py in the places involved in storing journals in the
database, not just in those involved in import/export.
Given this patch, import/export with non-ASCII characters appear based
on some limited testing to work across Python versions, and an
instance using the sqlite backend appears to be compatible between
Python versions without needing import/export, *if* the sessions/otks
databases (which use anydbm) are deleted when changing Python version.
| author | Joseph Myers <jsm@polyomino.org.uk> |
|---|---|
| date | Sun, 02 Sep 2018 23:48:04 +0000 |
| parents | c75defc1c2f0 |
| children | 9c3ec0a5c7fc |
line wrap: on
line source
#! /usr/bin/env python # Copyright (C) 2012 Dr. Ralf Schlatterbeck Open Source Consulting. # Reichergasse 131, A-3411 Weidling. # Web: http://www.runtux.com Email: rsc@runtux.com # All rights reserved # # Permission is hereby granted, free of charge, to any person obtaining a copy # of this software and associated documentation files (the "Software"), to deal # in the Software without restriction, including without limitation the rights # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell # copies of the Software, and to permit persons to whom the Software is # furnished to do so, subject to the following conditions: # # The above copyright notice and this permission notice shall be included in # all copies or substantial portions of the Software. # # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE # SOFTWARE. from __future__ import print_function _doc = ''' %prog [options] Remove file attachment spam from a tracker: - Edit the journal of the given issue(s) and remove the links to the spam-files - Set the contents of the spam-files involved to zero length WARNING: This is a dangerous operation as it will edit the history *and* remove data that is not in the journal (the contents of files). Be careful with the file pattern (start of filename) you specify! ''' import sys from optparse import OptionParser from roundup import instance, hyperdb def main(): cmd = OptionParser(usage=_doc) cmd.add_option \ ( "-i", "--instance" , help = "Instance home" , default = "." ) cmd.add_option \ ( "-d", "--designator" , dest = "designators" , help = "Item designator for issue(s), to remove files from,\n" "e.g. issue4711" , action = "append" , default = [] ) cmd.add_option \ ( "-f", "--filename" , dest = "filenames" , help = "Exact spam-filename to remove from issue(s)" , action = "append" , default = [] ) cmd.add_option \ ( "-a", "--action", "--no-dry-run" , dest = "doit" , help = "Don't perform any action by default unless specified" , action = "store_true" ) cmd.add_option \ ( "-s", "--file-start-pattern" , dest = "file_pattern" , help = "Start of spam-filename to remove from issue(s)" , action = "append" , default = [] ) cmd.add_option \ ( "-u", "--spam-user" , dest = "users" , help = "Username that created the spam-files to remove" , action = "append" , default = [] ) cmd.add_option \ ( "-q", "--quiet" , dest = "quiet" , help = "Be quiet about what we're doing" , action = "store_true" ) opt, args = cmd.parse_args() # open the instance if len(args): print("This command doesn't take arguments", file=sys.stderr) cmd.show_help() tracker = instance.open(opt.instance) db = tracker.open('admin') db.tx_Source = "cli" users = dict.fromkeys (db.user.lookup(u) for u in opt.users) files_to_remove = {} for fn in opt.filenames: for fid in db.file.filter(None,dict(name=fn)): if db.file.get(fid,'name') == fn: files_to_remove[fid] = True for fn in opt.file_pattern: for fid in db.file.filter(None,dict(name=fn)): if db.file.get(fid,'name').startswith(fn): files_to_remove[fid] = True files_found = {} for d in opt.designators: clsname, id = hyperdb.splitDesignator(d) cls = db.getclass(clsname) issuefiles = dict.fromkeys(cls.get (id, 'files')) for fid in list(issuefiles.keys()): f = db.file.getnode(fid) if fid in files_to_remove or f.creator in users: files_to_remove[fid] = True files_found[fid] = True if not opt.quiet: print("deleting file %s from issue" % f) del issuefiles[fid] if opt.doit: cls.set(id, files=list(issuefiles.keys())) journal = oldjournal = db.getjournal(clsname, id) # do this twice, we may have file-removals *before* file # additions for files to delete and may discover mid-journal # that there are new files to remove for x in range(2): newjournal = [] for j in journal: if j[3] == 'set' and 'files' in j[4]: if j[4]['files'][0][0] not in ('-', '+') : newjournal.append(j) continue changes = dict(j[4]['files']) # only consider file additions by this user if j[2] in users and '+' in changes: f = dict.fromkeys(changes['+']) files_found.update(f) files_to_remove.update(f) del changes['+'] # change dict in-place for k, v in list(changes.items()): new_f = [] for f in v: if f in files_to_remove: files_found[f] = True else: new_f.append(f) if new_f : changes[k] = new_f else: del changes[k] msg = [] if not opt.quiet: msg.append ("Old journal entry: %s" % str(j)) if changes: j[4]['files'] = tuple(changes.items()) else: del j[4]['files'] if j[4]: newjournal.append(j) if not opt.quiet: msg.append ("New journal entry: %s" % str(j)) elif not opt.quiet: msg.append ("deleted") if len(msg) == 2 and msg[0][4:] != msg[1][4:]: for m in msg: print(m) else: newjournal.append(j) journal = newjournal if newjournal != oldjournal and opt.doit: db.setjournal(clsname, id, newjournal) if opt.doit: for f in files_found: db.file.set(f, content=' ') db.commit() else: print("Database not changed") if __name__ == '__main__': main()
