nmbug-status: Add Page and HtmlPage for modular rendering

I was having trouble understanding the logic of the longish print_view
function, so I refactored the output generation into modular bits.
The basic text rendering is handled by Page, which has enough hooks
that HtmlPage can borrow the logic and slot-in HTML generators.

By modularizing the logic it should also be easier to build other
renderers if folks want to customize the layout for other projects.

Timezones
=========

This commit has not effect on the output, except that some dates have
been converted from the sender's timezone to UTC due to:

  -            val = m.get_header(header)
  -            ...
  -            if header == 'date':
  -                val = str.join(' ', val.split(None)[1:4])
  -                val = str(datetime.datetime.strptime(val, '%d %b %Y').date())
  ...
  +                value = str(datetime.datetime.utcfromtimestamp(
  +                    message.get_date()).date())

I also tweaked the HTML header date to be utcnow instead of the local
now() to make all times independent of the generator's local time.
This matches Gmane, which converts all Date headers to UTC (although
they use a 'GMT' suffix).  Notmuch uses
g_mime_utils_header_decode_date to calculate the UTC timestamps, but
uses a NULL tz_offset which drops the information we'd need to get
back to the sender's local time [1].  With the generator's local time
arbitrarily different from the sender's and viewer's local time,
sticking with UTC seems the best bet.

[1]: https://developer.gnome.org/gmime/stable/gmime-gmime-utils.html#g-mime-utils-header-decode-date

1 files changed, 171 insertions, 121 deletions

diff --git a/devel/nmbug/nmbug-status b/devel/nmbug/nmbug-status
index 22b6b104..6aa25832 100755
--- a/devel/nmbug/nmbug-status
+++ b/devel/nmbug/nmbug-status
@@ -5,10 +5,13 @@
 # dependencies
 #       - python 2.6 for json
 #       - argparse; either python 2.7, or install separately
+#       - collections.OrderedDict; python 2.7
 
 from __future__ import print_function
+from __future__ import unicode_literals
 
 import codecs
+import collections
 import datetime
 import email.utils
 import locale
@@ -24,6 +27,7 @@ import subprocess
 
 
 _ENCODING = locale.getpreferredencoding() or sys.getdefaultencoding()
+_PAGES = {}
 
 
 def read_config(path=None, encoding=None):
@@ -50,104 +54,175 @@ def read_config(path=None, encoding=None):
     return json.load(fp)
 
 
-class Thread:
-    def __init__(self, last, lines):
-        self.last = last
-        self.lines = lines
-
-    def join_utf8_with_newlines(self):
-        return '\n'.join( (line.encode('utf-8') for line in self.lines) )
-
-
-def output_with_separator(threadlist, sep):
-    outputs = (thread.join_utf8_with_newlines() for thread in threadlist)
-    print(sep.join(outputs))
-
-
-def print_view(database, title, query, comment,
-               headers=('date', 'from', 'subject')):
-
-    query_string = ' and '.join(query)
-    q_new = notmuch.Query(database, query_string)
-    q_new.set_sort(notmuch.Query.SORT.OLDEST_FIRST)
-
-    last_thread_id = ''
-    threads = {}
-    threadlist = []
-    out = {}
-    last = None
-    lines = None
-
-    if output_format == 'html':
-        print('<h3><a name="%s" />%s</h3>' % (title, title))
-        print(comment)
-        print('The view is generated from the following query:')
-        print('<blockquote>')
-        print(query_string)
-        print('</blockquote>')
-        print('<table>\n')
-
-    for m in q_new.search_messages():
-
-        thread_id = m.get_thread_id()
-
-        if thread_id != last_thread_id:
-            if threads.has_key(thread_id):
-                last = threads[thread_id].last
-                lines = threads[thread_id].lines
+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='UTF-8')(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):
+        if 'query-string' not in view:
+            query = view['query']
+            view['query-string'] = ' and '.join(query)
+        q = notmuch.Query(database, view['query-string'])
+        q.set_sort(notmuch.Query.SORT.OLDEST_FIRST)
+        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:
-                last = {}
-                lines = []
-                thread = Thread(last, lines)
+                thread = Thread()
                 threads[thread_id] = thread
-                for h in headers:
-                    last[h] = ''
-                threadlist.append(thread)
-            last_thread_id = thread_id
-
+            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:
-            val = m.get_header(header)
-
-            if header == 'date':
-                val = str.join(' ', val.split(None)[1:4])
-                val = str(datetime.datetime.strptime(val, '%d %b %Y').date())
-            elif header == 'from':
-                (val, addr) = email.utils.parseaddr(val)
-                if val == '':
-                    val = addr.split('@')[0]
-
-            if header != 'subject' and last[header] == val:
-                out[header] = ''
+            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:
-                out[header] = val
-                last[header] = val
-
-        mid = m.get_message_id()
-        out['id'] = 'id:"%s"' % mid
-
-        if output_format == 'html':
-
-            out['subject'] = '<a href="http://mid.gmane.org/%s">%s</a>' % (
-                quote(mid), out['subject'])
-
-            lines.append(' <tr><td>%s' % out['date'])
-            lines.append('</td><td>%s' % out['id'])
-            lines.append('</td></tr>')
-            lines.append(' <tr><td>%s' % out['from'])
-            lines.append('</td><td>%s' % out['subject'])
-            lines.append('</td></tr>')
-        else:
-            lines.append('%(date)-10.10s %(from)-20.20s %(subject)-40.40s\n%(id)72s' % out)
-
-    if output_format == 'html':
-        output_with_separator(threadlist,
-                              '\n<tr><td colspan="2"><br /></td></tr>\n')
-        print('</table>')
-    else:
-        output_with_separator(threadlist, '\n\n')
-
+                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):
+    def _write_header(self, views, stream):
+        super(HtmlPage, self)._write_header(views=views, stream=stream)
+        stream.write('<ul>\n')
+        for view in views:
+            stream.write(
+                '<li><a href="#{title}">{title}</a></li>\n'.format(**view))
+        stream.write('</ul>\n')
+
+    def _write_view_header(self, view, stream):
+        stream.write('<h3><a name="{title}" />{title}</h3>\n'.format(**view))
+        if 'comment' in view:
+            stream.write(view['comment'])
+            stream.write('\n')
+        for line in [
+                'The view is generated from the following query:',
+                '<blockquote>',
+                view['query-string'],
+                '</blockquote>',
+                ]:
+            stream.write(line)
+            stream.write('\n')
+
+    def _write_threads(self, threads, stream):
+        if not threads:
+            return
+        stream.write('<table>\n')
+        for thread in threads:
+            for message_display_data in thread:
+                stream.write((
+                    '<tr><td>{date}\n'
+                    '</td><td>{message-id-term}\n'
+                    '</td></tr>\n'
+                    '<tr><td>{from}\n'
+                    '</td><td>{subject}\n'
+                    '</td></tr>\n'
+                    ).format(**message_display_data))
+            if thread != threads[-1]:
+                stream.write('<tr><td colspan="2"><br /></td></tr>\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': display_data['subject'],
+                }
+            display_data['subject'] = (
+                '<a href="http://mid.gmane.org/{message-id}">{subject}</a>'
+                ).format(**d)
+        return (running_data, display_data)
+
+
+_PAGES['text'] = Page()
+_PAGES['html'] = HtmlPage(
+    header='''<?xml version="1.0" encoding="utf-8" ?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+<head>
+<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+<title>Notmuch Patches</title>
+</head>
+<body>
+<h2>Notmuch Patches</h2>
+Generated: {date}<br />
+For more infomation see <a href="http://notmuchmail.org/nmbug">nmbug</a>
+<h3>Views</h3>
+'''.format(date=datetime.datetime.utcnow().date()),
+    footer='</body>\n</html>\n',
+    )
 
-# parse command line arguments
 
 parser = argparse.ArgumentParser()
 parser.add_argument('--text', help='output plain text format',
@@ -177,34 +252,9 @@ else:
     import notmuch
 
 if args.text:
-    output_format = 'text'
+    page = _PAGES['text']
 else:
-    output_format = 'html'
-
-# main program
+    page = _PAGES['html']
 
 db = notmuch.Database(mode=notmuch.Database.MODE.READ_ONLY)
-
-if output_format == 'html':
-    print('''<?xml version="1.0" encoding="utf-8" ?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
-<head>
-<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-<title>Notmuch Patches</title>
-</head>
-<body>
-<h2>Notmuch Patches</h2>
-Generated: {date}<br />
-For more infomation see <a href="http://notmuchmail.org/nmbug">nmbug</a>
-<h3>Views</h3>
-<ul>'''.format(date=datetime.datetime.utcnow().date()))
-    for view in config['views']:
-        print('<li><a href="#%(title)s">%(title)s</a></li>' % view)
-    print('</ul>')
-
-for view in config['views']:
-    print_view(database=db, **view)
-
-if output_format == 'html':
-    print('</body>\n</html>')
+page.write(database=db, views=config['views'])