New script to generate all_id2.txt

- Legacy-Id: 2202

changelog

@@ -1,3 +1,10 @@
+ietfdb (2.49)
+
+  * New script to generate all_id2.txt. This should be called in
+    www6s/scripts/datatracker-updater: run "python -m
+    ietf.idindex.generate_all_id2_txt" and place its output
+    in $ID/all_id2.txt.
+
 ietfdb (2.48)
 
   From Pasi:

ietf/idindex/generate_all_id2_txt.py

@@ -0,0 +1,38 @@
+# Portions Copyright (C) 2009-2010 Nokia Corporation and/or its subsidiary(-ies).
+# All rights reserved. Contact: Pasi Eronen <pasi.eronen@nokia.com>
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+#
+#  * Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+#
+#  * Redistributions in binary form must reproduce the above
+#    copyright notice, this list of conditions and the following
+#    disclaimer in the documentation and/or other materials provided
+#    with the distribution.
+#
+#  * Neither the name of the Nokia Corporation and/or its
+#    subsidiary(-ies) nor the names of its contributors may be used
+#    to endorse or promote products derived from this software
+#    without specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+from ietf import settings
+from django.core import management
+management.setup_environ(settings)
+
+from ietf.idindex.views import all_id2_txt
+print all_id2_txt().encode('utf-8'),

ietf/idindex/testurl.list

@@ -14,5 +14,7 @@
 301	/drafts/all_id.html
 301	/drafts/		
 200,heavy	/drafts/_test/all_id.txt
+# this takes 3 minutes, so disabled by default
+#200,heavy	/drafts/_test/all_id2.txt
 200,heavy	/drafts/_test/id_index.txt
 200,heavy	/drafts/_test/id_abstracts.txt

ietf/idindex/urls.py

@@ -20,6 +20,7 @@ urlpatterns = patterns('',
 if settings.SERVER_MODE != 'production':
     urlpatterns += patterns('',
         (r'^_test/all_id.txt$', views.test_all_id_txt),                        
+        (r'^_test/all_id2.txt$', views.test_all_id2_txt),
         (r'^_test/id_index.txt$', views.test_id_index_txt), 
         (r'^_test/id_abstracts.txt$', views.test_id_abstracts_txt)   
     )

ietf/idindex/views.py

@@ -35,7 +35,9 @@
 from django.http import HttpResponse, HttpResponsePermanentRedirect
 from django.template import loader
 from django.shortcuts import get_object_or_404
-from ietf.idtracker.models import Acronym, IETFWG, InternetDraft, IDInternal
+from ietf.idtracker.models import Acronym, IETFWG, InternetDraft, IDInternal,PersonOrOrgInfo
+from ietf.idtracker.templatetags.ietf_filters import clean_whitespace
+import re
 
 def all_id_txt():
     all_ids = InternetDraft.objects.order_by('filename')
@@ -58,6 +60,81 @@ def all_id_txt():
                                      'withdrawn_ietf':withdrawn_ietf,
                                      'replaced':replaced})
 
+def all_id2_entry(id):
+    fields = []
+    # 0
+    fields.append(id.filename+"-"+id.revision_display())
+    # 1
+    fields.append(id.id_document_tag)
+    # 2
+    status = id.status.status
+    fields.append(status)
+    # 3
+    iesgstate = id.idstate() if status=="Active" else ""
+    fields.append(iesgstate)
+    # 4
+    fields.append(id.rfc_number if status=="RFC" else "")
+    # 5
+    if status == "Replaced":
+        try:
+            fields.append(id.replaced_by.filename)
+        except InternetDraft.DoesNotExist:
+            fields.append("")
+    else:
+        fields.append("")
+    # 6
+    fields.append(id.revision_date)
+    # 7
+    group_acronym = id.group.acronym
+    if group_acronym == "none":
+        group_acronym = ""
+    fields.append(group_acronym)
+
+    # 8
+    area = ""
+    if id.idinternal:
+        area = id.idinternal.area_acronym
+    elif not group_acronym:
+        pass
+    else:
+        wgs = id.group.ietfwg_set.all()
+        if len(wgs) > 0:
+            area = wgs[0].area_acronym() or ""
+    fields.append(area)
+    # 9
+    fields.append(id.idinternal.job_owner if id.idinternal else "")
+    # 10
+    if id.intended_status and id.intended_status.intended_status not in ("None","Request"):
+        fields.append(id.intended_status.intended_status)
+    else:
+        fields.append("")
+    # 11
+    if (iesgstate=="In Last Call") or iesgstate.startswith("In Last Call::"):
+        fields.append(id.lc_expiration_date)
+    else:
+        fields.append("")
+    # 12
+    fields.append(id.file_type if status=="Active" else "")
+    # 13
+    fields.append(clean_whitespace(id.title))
+    # 14
+    authors = []
+    for author in sorted(id.authors.all(), key=lambda x: x.final_author_order()):
+        try:
+            realname = unicode(author.person)
+            email = author.email() or ""
+            name = re.sub(u"[<>@,]", u"", realname) + u" <"+re.sub(u"[<>,]", u"", email).strip()+u">"
+            authors.append(clean_whitespace(name))
+        except PersonOrOrgInfo.DoesNotExist:
+            pass
+    fields.append(u", ".join(authors))
+    return "\t".join([unicode(x) for x in fields])
+    
+def all_id2_txt():
+    all_ids = InternetDraft.objects.order_by('filename').select_related('status__status','group__acronym','intended_status__intended_status')
+    data = "\n".join([all_id2_entry(id) for id in all_ids])
+    return loader.render_to_string("idindex/all_id2.txt",{'data':data})
+
 def id_index_txt():
     groups = IETFWG.objects.all()
     return loader.render_to_string("idindex/id_index.txt", {'groups':groups})
@@ -68,6 +145,8 @@ def id_abstracts_txt():
 
 def test_all_id_txt(request):
     return HttpResponse(all_id_txt(), mimetype='text/plain')
+def test_all_id2_txt(request):
+    return HttpResponse(all_id2_txt(), mimetype='text/plain')
 def test_id_index_txt(request):
     return HttpResponse(id_index_txt(), mimetype='text/plain')
 def test_id_abstracts_txt(request):

ietf/templates/idindex/all_id2.txt

@@ -0,0 +1,33 @@
+{% autoescape off %}#
+# Index of all Internet-Drafts
+# generated: {% now "Y-m-d H:i:s T" %}
+#
+# Description of fields:
+# 0   draft name and latest revision
+# 1   id_document_tag (internal database identifier; avoid using
+#     unless you really need it)
+# 2   one of "Active", "Expired", "RFC", "Withdrawn by Submitter",
+#     "Replaced", or "Withdrawn by IETF"
+# 3   if #2 is "Active", the IESG state for the document (such as
+#     "In Last Call", "AD Evaluation::Revised ID Needed", or "I-D Exists");
+#     otherwise empty
+# 4   if #2 is "RFC", the RFC number (otherwise empty)
+# 5   if #2 is "Replaced", the replacing draft name (otherwise empty)
+# 6   revision date (YYYY-MM-DD)
+# 7   group acronym (or empty if no group/not known)
+# 8   area acronym (or empty if not known; not necessarily accurate
+#     for older drafts)
+# 9   responsible AD name (or empty if not known)
+# 10  intended maturity level (or empty if not known)
+# 11  if #3 is "In Last Call" (with any substate), the last call
+#     end date (YYYY-MM-DD); otherwise empty
+# 12  if #2 is "Active", list of file types; otherwise empty
+# 13  draft title
+# 14  draft authors (often quite inaccurate, especially the email
+#     addresses...)
+#
+# new fields can be added to the end in the future, so remember to
+# ignore those in your code
+#
+{{ data }}
+# end{% endautoescape %}