Mercurial > kallithea
view scripts/i18n @ 8908:8993d401575b stable
files: fix raw download of repo files with names with unicode points above 256 in name
Raw download had apparently only been tested with non-ascii characters that
were latin1. That was apparently a (too) simple case that worked without
crashing.
Files with unicode code points above 256 in their name would fail to download,
when Waitress failed like this, trying to get a real byte string by encoding
WSGI headers to latin1:
UnicodeEncodeError: 'latin-1' codec can't encode characters in position 84-85: ordinal not in range(256)
HTTP headers are of course byte strings on the network, but Python3 WSGI does
unfortunately neither expose it as bytes nor as unicode strings to be encoded
as utf-8. Instead, it uses unicode strings with byte values encoded as code
points 0-255. That is achieved by decoding the utf-8 encoded bytes as latin1.
For raw downloads, the recommended download filename is provided in the
Content-Disposition header. The problem is that it was provided as a real
unicode string.
Fixed by applying the "proper" latin1-decoding of a utf8-encoding.
author | Mads Kiilerich <mads@kiilerich.com> |
---|---|
date | Mon, 07 Feb 2022 19:07:08 +0100 |
parents | 68eee0e7f4f5 |
children |
line wrap: on
line source
#!/usr/bin/env python3 # -*- coding: utf-8 -*- # This program is free software: you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation, either version 3 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see <http://www.gnu.org/licenses/>. import os import shutil import sys import click import i18n_utils """ Tool for maintenance of .po and .pot files Normally, the i18n-related files contain for each translatable string a reference to all the source code locations where this string is found. This meta data is useful for translators to assess how strings are used, but is not relevant for normal development nor for running Kallithea. Such meta data, or derived data like kallithea.pot, will inherently be outdated, and create unnecessary churn and repository growth, making it harder to spot actual and important changes. """ @click.group() @click.option('--debug/--no-debug', default=False) def cli(debug): if (debug): i18n_utils.do_debug = True pass @cli.command() @click.argument('po_files', nargs=-1) @click.option('--merge-pot-file', default=None) @click.option('--strip/--no-strip', default=False) def normalize_po_files(po_files, merge_pot_file, strip): """Normalize the specified .po and .pot files. By default, only actual translations and essential headers will be preserved, just as we want it in the main branches with minimal noise. If a .pot file is specified, the po files will instead be updated by running GNU msgmerge with this .pot file, thus updating source code references and preserving comments and outdated translations. """ for po_file in po_files: i18n_utils._normalize_po_file(po_file, merge_pot_file=merge_pot_file, strip=strip) @cli.command() @click.argument('local') @click.argument('base') @click.argument('other') @click.argument('output') @click.option('--merge-pot-file', default=None) @click.option('--strip/--no-strip', default=False) def normalized_merge(local, base, other, output, merge_pot_file, strip): """Merge tool for use with 'hg merge/rebase/graft --tool' i18n files are partially manually editored original source of content, and partially automatically generated and updated. That create a lot of churn and often cause a lot of merge conflicts. To avoid that, this merge tool wrapper will normalize .po content before running the merge tool. By default, only actual translations and essential headers will be preserved, just as we want it in the main branches with minimal noise. If a .pot file is specified, the po files will instead be updated by running GNU msgmerge with this .pot file, thus updating source code references and preserving comments and outdated translations. Add the following to your user or repository-specific .hgrc file to use it: [merge-tools] i18n.executable = /path/to/scripts/i18n i18n.args = normalized-merge $local $base $other $output and then invoke merge/rebase/graft with the additional argument '--tool i18n'. """ from mercurial import context, simplemerge from mercurial import ui as uimod print('i18n normalized-merge: normalizing and merging %s' % output) i18n_utils._normalize_po_file(local, merge_pot_file=merge_pot_file, strip=strip) i18n_utils._normalize_po_file(base, merge_pot_file=merge_pot_file, strip=strip) i18n_utils._normalize_po_file(other, merge_pot_file=merge_pot_file, strip=strip) i18n_utils._normalize_po_file(output, merge_pot_file=merge_pot_file, strip=strip) # simplemerge will write markers to 'local' if it fails, keep a copy without markers localkeep = local + '.keep' shutil.copyfile(local, localkeep) ret = simplemerge.simplemerge(uimod.ui.load(), context.arbitraryfilectx(local.encode('utf-8')), context.arbitraryfilectx(base.encode('utf-8')), context.arbitraryfilectx(other.encode('utf-8')), label=[b'local', b'other', b'base'], mode='merge', ) shutil.copyfile(local, output) # simplemerge wrote to local - either resolved or with conflict markers if ret: shutil.copyfile(localkeep, local) basekeep = base + '.keep' otherkeep = other + '.keep' shutil.copyfile(base, basekeep) shutil.copyfile(other, otherkeep) sys.stderr.write("Error: simple merge failed and %s is left with conflict markers. Resolve the conflicts, then use 'hg resolve -m'.\n" % output) sys.stderr.write('Resolve with e.g.: kdiff3 %s %s %s -o %s\n' % (basekeep, localkeep, otherkeep, output)) sys.exit(ret) os.remove(localkeep) @cli.command() @click.argument('file1') @click.argument('file2') @click.option('--merge-pot-file', default=None) @click.option('--strip/--no-strip', default=False) def normalized_diff(file1, file2, merge_pot_file, strip): """Compare two files while transparently normalizing them.""" sys.exit(i18n_utils._normalized_diff(file1, file2, merge_pot_file=merge_pot_file, strip=strip)) if __name__ == '__main__': cli()