notmuch/devel/nmbug/notmuch-report
Daniel Kahn Gillmor 6a833a6e83 Use https instead of http where possible
Many of the external links found in the notmuch source can be resolved
using https instead of http.  This changeset addresses as many as i
could find, without touching the e-mail corpus or expected outputs
found in tests.
2016-06-05 08:32:17 -03:00

440 lines
14 KiB
Python
Executable file

#!/usr/bin/python
#
# Copyright (c) 2011-2012 David Bremner <david@tethera.net>
#
# dependencies
# - python 2.6 for json
# - argparse; either python 2.7, or install separately
#
# 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 https://www.gnu.org/licenses/ .
"""Generate text and/or HTML for one or more notmuch searches.
Messages matching each search are grouped by thread. Each message
that contains both a subject and message-id will have the displayed
subject link to an archive view of the message (defaulting to Gmane).
"""
from __future__ import print_function
from __future__ import unicode_literals
import codecs
import collections
import datetime
import email.utils
try: # Python 3
from urllib.parse import quote
except ImportError: # Python 2
from urllib import quote
import json
import argparse
import os
import re
import sys
import subprocess
import xml.sax.saxutils
_ENCODING = 'UTF-8'
_PAGES = {}
if not hasattr(collections, 'OrderedDict'): # Python 2.6 or earlier
class _OrderedDict (dict):
"Just enough of a stub to get through Page._get_threads"
def __init__(self, *args, **kwargs):
super(_OrderedDict, self).__init__(*args, **kwargs)
self._keys = [] # record key order
def __setitem__(self, key, value):
super(_OrderedDict, self).__setitem__(key, value)
self._keys.append(key)
def values(self):
for key in self._keys:
yield self[key]
collections.OrderedDict = _OrderedDict
class ConfigError (Exception):
"""Errors with config file usage
"""
pass
def read_config(path=None, encoding=None):
"Read config from json file"
if not encoding:
encoding = _ENCODING
if path:
try:
with open(path, 'rb') as f:
config_bytes = f.read()
except IOError as e:
raise ConfigError('Could not read config from {}'.format(path))
else:
nmbhome = os.getenv('NMBGIT', os.path.expanduser('~/.nmbug'))
branch = 'config'
filename = 'notmuch-report.json'
# read only the first line from the pipe
sha1_bytes = subprocess.Popen(
['git', '--git-dir', nmbhome, 'show-ref', '-s', '--heads', branch],
stdout=subprocess.PIPE).stdout.readline()
sha1 = sha1_bytes.decode(encoding).rstrip()
if not sha1:
raise ConfigError(
("No local branch '{branch}' in {nmbgit}. "
'Checkout a local {branch} branch or explicitly set --config.'
).format(branch=branch, nmbgit=nmbhome))
p = subprocess.Popen(
['git', '--git-dir', nmbhome, 'cat-file', 'blob',
'{}:{}'.format(sha1, filename)],
stdout=subprocess.PIPE)
config_bytes, err = p.communicate()
status = p.wait()
if status != 0:
raise ConfigError(
("Missing {filename} in branch '{branch}' of {nmbgit}. "
'Add the file or explicitly set --config.'
).format(filename=filename, branch=branch, nmbgit=nmbhome))
config_json = config_bytes.decode(encoding)
try:
return json.loads(config_json)
except ValueError as e:
if not path:
path = "{} in branch '{}' of {}".format(
filename, branch, nmbhome)
raise ConfigError(
'Could not parse JSON from the config file {}:\n{}'.format(
path, e))
class Thread (list):
def __init__(self):
self.running_data = {}
class Page (object):
def __init__(self, header=None, footer=None):
self.header = header
self.footer = footer
def write(self, database, views, stream=None):
if not stream:
try: # Python 3
byte_stream = sys.stdout.buffer
except AttributeError: # Python 2
byte_stream = sys.stdout
stream = codecs.getwriter(encoding=_ENCODING)(stream=byte_stream)
self._write_header(views=views, stream=stream)
for view in views:
self._write_view(database=database, view=view, stream=stream)
self._write_footer(views=views, stream=stream)
def _write_header(self, views, stream):
if self.header:
stream.write(self.header)
def _write_footer(self, views, stream):
if self.footer:
stream.write(self.footer)
def _write_view(self, database, view, stream):
# sort order, default to oldest-first
sort_key = view.get('sort', 'oldest-first')
# dynamically accept all values in Query.SORT
sort_attribute = sort_key.upper().replace('-', '_')
try:
sort = getattr(notmuch.Query.SORT, sort_attribute)
except AttributeError:
raise ConfigError('Invalid sort setting for {}: {!r}'.format(
view['title'], sort_key))
if 'query-string' not in view:
query = view['query']
view['query-string'] = ' and '.join(
'( {} )'.format(q) for q in query)
q = notmuch.Query(database, view['query-string'])
q.set_sort(sort)
threads = self._get_threads(messages=q.search_messages())
self._write_view_header(view=view, stream=stream)
self._write_threads(threads=threads, stream=stream)
def _get_threads(self, messages):
threads = collections.OrderedDict()
for message in messages:
thread_id = message.get_thread_id()
if thread_id in threads:
thread = threads[thread_id]
else:
thread = Thread()
threads[thread_id] = thread
thread.running_data, display_data = self._message_display_data(
running_data=thread.running_data, message=message)
thread.append(display_data)
return list(threads.values())
def _write_view_header(self, view, stream):
pass
def _write_threads(self, threads, stream):
for thread in threads:
for message_display_data in thread:
stream.write(
('{date:10.10s} {from:20.20s} {subject:40.40s}\n'
'{message-id-term:>72}\n'
).format(**message_display_data))
if thread != threads[-1]:
stream.write('\n')
def _message_display_data(self, running_data, message):
headers = ('thread-id', 'message-id', 'date', 'from', 'subject')
data = {}
for header in headers:
if header == 'thread-id':
value = message.get_thread_id()
elif header == 'message-id':
value = message.get_message_id()
data['message-id-term'] = 'id:"{0}"'.format(value)
elif header == 'date':
value = str(datetime.datetime.utcfromtimestamp(
message.get_date()).date())
else:
value = message.get_header(header)
if header == 'from':
(value, addr) = email.utils.parseaddr(value)
if not value:
value = addr.split('@')[0]
data[header] = value
next_running_data = data.copy()
for header, value in data.items():
if header in ['message-id', 'subject']:
continue
if value == running_data.get(header, None):
data[header] = ''
return (next_running_data, data)
class HtmlPage (Page):
_slug_regexp = re.compile('\W+')
def __init__(self, message_url_template, **kwargs):
self.message_url_template = message_url_template
super(HtmlPage, self).__init__(**kwargs)
def _write_header(self, views, stream):
super(HtmlPage, self)._write_header(views=views, stream=stream)
stream.write('<ul>\n')
for view in views:
if 'id' not in view:
view['id'] = self._slug(view['title'])
stream.write(
'<li><a href="#{id}">{title}</a></li>\n'.format(**view))
stream.write('</ul>\n')
def _write_view_header(self, view, stream):
stream.write('<h3 id="{id}">{title}</h3>\n'.format(**view))
stream.write('<p>\n')
if 'comment' in view:
stream.write(view['comment'])
stream.write('\n')
for line in [
'The view is generated from the following query:',
'</p>',
'<p>',
' <code>',
view['query-string'],
' </code>',
'</p>',
]:
stream.write(line)
stream.write('\n')
def _write_threads(self, threads, stream):
if not threads:
return
stream.write('<table>\n')
for thread in threads:
stream.write(' <tbody>\n')
for message_display_data in thread:
stream.write((
' <tr class="message-first">\n'
' <td>{date}</td>\n'
' <td><code>{message-id-term}</code></td>\n'
' </tr>\n'
' <tr class="message-last">\n'
' <td>{from}</td>\n'
' <td>{subject}</td>\n'
' </tr>\n'
).format(**message_display_data))
stream.write(' </tbody>\n')
if thread != threads[-1]:
stream.write(
' <tbody><tr><td colspan="2"><br /></td></tr></tbody>\n')
stream.write('</table>\n')
def _message_display_data(self, *args, **kwargs):
running_data, display_data = super(
HtmlPage, self)._message_display_data(
*args, **kwargs)
if 'subject' in display_data and 'message-id' in display_data:
d = {
'message-id': quote(display_data['message-id']),
'subject': xml.sax.saxutils.escape(display_data['subject']),
}
d['url'] = self.message_url_template.format(**d)
display_data['subject'] = (
'<a href="{url}">{subject}</a>'
).format(**d)
for key in ['message-id', 'from']:
if key in display_data:
display_data[key] = xml.sax.saxutils.escape(display_data[key])
return (running_data, display_data)
def _slug(self, string):
return self._slug_regexp.sub('-', string)
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument(
'--text', action='store_true', help='output plain text format')
parser.add_argument(
'--config', metavar='PATH',
help='load config from given file. '
'The format is described in notmuch-report.json(5).')
parser.add_argument(
'--list-views', action='store_true', help='list views')
parser.add_argument(
'--get-query', metavar='VIEW', help='get query for view')
args = parser.parse_args()
try:
config = read_config(path=args.config)
except ConfigError as e:
print(e, file=sys.stderr)
sys.exit(1)
header_template = config['meta'].get('header', '''<!DOCTYPE html>
<html lang="en">
<head>
<meta http-equiv="Content-Type" content="text/html; charset={encoding}" />
<title>{title}</title>
<style media="screen" type="text/css">
h1 {{
font-size: 1.5em;
}}
h2 {{
font-size: 1.17em;
}}
h3 {{
font-size: 100%;
}}
table {{
border-spacing: 0;
}}
tr.message-first td {{
padding-top: {inter_message_padding};
}}
tr.message-last td {{
padding-bottom: {inter_message_padding};
}}
td {{
padding-left: {border_radius};
padding-right: {border_radius};
}}
tr:first-child td:first-child {{
border-top-left-radius: {border_radius};
}}
tr:first-child td:last-child {{
border-top-right-radius: {border_radius};
}}
tr:last-child td:first-child {{
border-bottom-left-radius: {border_radius};
}}
tr:last-child td:last-child {{
border-bottom-right-radius: {border_radius};
}}
tbody:nth-child(4n+1) tr td {{
background-color: #ffd96e;
}}
tbody:nth-child(4n+3) tr td {{
background-color: #bce;
}}
hr {{
border: 0;
height: 1px;
color: #ccc;
background-color: #ccc;
}}
</style>
</head>
<body>
<h1>{title}</h1>
<p>
{blurb}
</p>
<h2>Views</h2>
''')
footer_template = config['meta'].get('footer', '''
<hr>
<p>Generated: {datetime}</p>
</body>
</html>
''')
now = datetime.datetime.utcnow()
context = {
'date': now,
'datetime': now.strftime('%Y-%m-%d %H:%M:%SZ'),
'title': config['meta']['title'],
'blurb': config['meta']['blurb'],
'encoding': _ENCODING,
'inter_message_padding': '0.25em',
'border_radius': '0.5em',
}
_PAGES['text'] = Page()
_PAGES['html'] = HtmlPage(
header=header_template.format(**context),
footer=footer_template.format(**context),
message_url_template=config['meta'].get(
'message-url', 'http://mid.gmane.org/{message-id}'),
)
if args.list_views:
for view in config['views']:
print(view['title'])
sys.exit(0)
elif args.get_query != None:
for view in config['views']:
if args.get_query == view['title']:
print(' and '.join('( {} )'.format(q) for q in view['query']))
sys.exit(0)
else:
# only import notmuch if needed
import notmuch
if args.text:
page = _PAGES['text']
else:
page = _PAGES['html']
db = notmuch.Database(mode=notmuch.Database.MODE.READ_ONLY)
page.write(database=db, views=config['views'])