Add support for naming bases.

apachedex/__init__.py

@@ -664,14 +664,31 @@ class AggregateSiteUrl(argparse.Action):
   }
   def __call__(self, parser, namespace, values, option_string=None):
     action = base_action = self.__argument_to_aggregator[option_string]
-    dest = getattr(namespace, self.dest)
-    for value in values:
+    site_list, site_caption_dict = getattr(namespace, self.dest)
+    next_value = iter(values).next
+    while True:
+      try:
+        value = next_value()
+      except StopIteration:
+        break
+      if value in site_caption_dict:
+        raise ValueError('Duplicate base: %r' % value)
+      if action is not None and value[0] == '+':
+        caption = value[1:]
+        try:
+          value = next_value()
+        except StopIteration:
+          raise ValueError('No base follows caption %r' % value)
+      else:
+        caption = value
+      site_caption_dict[value] = caption
+      caption = None
       match = re.compile(value).match
       if base_action is not None:
         match_suffix = re.compile(value + '(?P<suffix>.*)').match
         action = partial(base_action,
           suffix=lambda x: match_suffix(x).group('suffix'))
-      dest.append((value, match, action))
+      site_list.append((value, match, action))
 
 def _asMonthString(timestamp):
   dt, _ = timestamp.split(' ')
@@ -778,7 +795,7 @@ period_parser = {
 unquoteToHtml = lambda x, encoding: escape(unquote(x).decode(encoding))
 
 def asHTML(out, encoding, per_site, args, default_site, period_parameter_dict,
-    stats):
+    stats, site_caption_dict):
   period = period_parameter_dict['period']
   decimator = period_parameter_dict['decimator']
   date_format = period_parameter_dict['date_format']
@@ -821,10 +838,9 @@ def asHTML(out, encoding, per_site, args, default_site, period_parameter_dict,
   for date, hit in sorted(hit_per_day.iteritems(), key=ITEMGETTER0):
     out.write('<tr><td>%s</td><td>%s</td></tr>' % (date, hit))
   out.write('</table>')
-  for site_id, data in per_site.iteritems():
-    if site_id is None:
-      site_id = default_site
-    out.write('<h1>Site: %s</h1>' % unquoteToHtml(site_id, encoding))
+  for site_id, data in sorted(per_site.iteritems(), key=ITEMGETTER0):
+    out.write('<h1>Site: %s</h1>' % unquoteToHtml(site_caption_dict.get(
+      site_id, site_id), encoding))
     apdex_data = data.getApdexData()
     if apdex_data:
       out.write(
@@ -942,10 +958,14 @@ def main():
     'Arguments (except for -d/--default) are interpreted as Python regexes. '
     'Literal values are expected urlencoded. For example: '
     '--base "/%E6%96%87%E5%AD%97%E5%8C%96%E3%81%91(/|$|\\?)" matches '
-    '"/\xe6\x96\x87\xe5\xad\x97\xe5\x8c\x96\xe3\x81\x91" ("mojibake").')
+    '"/\xe6\x96\x87\xe5\xad\x97\xe5\x8c\x96\xe3\x81\x91" ("mojibake").'
+    'You can name matched entries by providing a name before the regex,'
+    'prefixed by "+". For example: --base +foo "/foo(/|$|\\?)" '
+    '"/bar(/|$|\\?)" "+baz boo" "/baz(/|$|\\?)" will defines 3 bases, named'
+    '"foo", "/bar(/|$|\\?)" and "baz boo" respectively.')
   group.add_argument('-d', '--default',
     help='Caption for lines matching no prefix, or skip them if not provided.')
-  group.add_argument('--base', dest='path', default=[], nargs='+',
+  group.add_argument('--base', dest='path', default=([], {}), nargs='+',
     action=AggregateSiteUrl,
     help='Absolute base url(s) of some part of a site.')
   group.add_argument('--erp5-base', dest='path', nargs='+',
@@ -1014,7 +1034,7 @@ def main():
     period = args.period
   asDate, decimator, graph_period, date_format, placeholder_delta, \
     round_date = period_parser[period]
-  site_list = args.path
+  site_list, site_caption_dict = args.path
   default_site = args.default
   if default_site is None:
     default_action = None
@@ -1024,6 +1044,7 @@ def main():
       sys.exit(1)
   else:
     default_action = partial(GenericSiteStats, suffix=lambda x: x)
+    site_caption_dict[None] = default_site
   infile_list = args.logfile
   quiet = args.quiet
   threshold = args.apdex
@@ -1168,7 +1189,9 @@ def main():
         'no_url_lines': no_url_lines,
         'skipped_lines': skipped_lines,
         'skipped_user_agent': skipped_user_agent,
-    })
+      },
+      site_caption_dict,
+    )
 
 if __name__ == '__main__':
   main()