# HG changeset patch
# User Paul Boddie <paul@boddie.org.uk>
# Date 1374168286 -7200
# Node ID db03adb5f2e3c4066606a1da5c0e0a81f5d8c681
# Parent  e425db7daf2380bb73cc35735bd55278dd1b6d84
Added tools to acquire user details from Confluence and to add users to MoinMoin.

diff -r e425db7daf23 -r db03adb5f2e3 README.txt
--- a/README.txt	Wed Jul 17 18:07:43 2013 +0200
+++ b/README.txt	Thu Jul 18 19:24:46 2013 +0200
@@ -136,6 +136,31 @@
 or it should be placed in a different location and the MAPPING_ID_TO_PAGE
 variable changed in the script to refer to this different location.
 
+Identifying and Migrating Users
+-------------------------------
+
+Confluence export archives do not contain user profile information, but page
+versions are marked with user identifiers. Therefore, a list of user
+identifiers can be obtained by running a script extracting these identifiers.
+The following command writes to standard output the users involved with
+editing the wiki in four different spaces (exported to four directories):
+
+tools/users.sh COM DEV DOC SEC
+
+This output can be edited and then passed to a special user administration
+program as follows:
+
+tools/users.sh COM DEV DOC SEC > users.txt # for editing
+cat users.txt | tools/addusers.py wiki http://wiki.list.org/
+
+If no users are to be removed in migration, the following command could be
+issued:
+
+tools/users.sh COM DEV DOC SEC | tools/addusers.py wiki http://wiki.list.org/
+
+The addusers.py program needs to be told the directory containing the wiki
+configuration as well as the URL of the original Confluence site.
+
 Output Structure
 ----------------
 
diff -r e425db7daf23 -r db03adb5f2e3 tools/addusers.py
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/addusers.py	Thu Jul 18 19:24:46 2013 +0200
@@ -0,0 +1,62 @@
+#!/usr/bin/env python
+
+"""
+Add users to a MoinMoin wiki, fetching the profile of each user from a
+Confluence site in order to obtain name and e-mail details.
+
+User details are written to standard output in a tab-separated sequence using
+the following format:
+
+USERNAME FULLNAME EMAIL IMAGE-URL PASSWORD
+"""
+
+from time import sleep
+from os.path import split
+from subprocess import call
+import random, string
+import sys
+
+this_dir = split(sys.argv[0])[0]
+sys.path.append(this_dir)
+
+from get_profile import get_profile
+
+def randompass():
+    return "".join(random.sample(string.ascii_letters, 10))
+
+def add_user(wiki, username, fullname, email, password):
+    cmd = ["moin", "--config-dir=%s" % wiki, "account", "create",
+        "--name=%s" % username,
+        "--email=%s" % email,
+        "--password=%s" % password] + \
+        (fullname and ["--alias=%s" % fullname] or [])
+    call(cmd)
+
+def main():
+    progname = split(sys.argv[0])[-1]
+
+    try:
+        wiki = sys.argv[1]
+        url = sys.argv[2]
+        delay = int((sys.argv[3:4] or ["1"])[0])
+    except (IndexError, ValueError):
+        print >>sys.stderr, "%s <wiki configuration directory> <wiki URL> [ <retrieval delay> ]" % progname
+        print >>sys.stderr
+        print >>sys.stderr, "Example: %s wiki http://wiki.list.org/" % progname
+        sys.exit(1)
+
+    line = sys.stdin.readline()
+    while line:
+        username = line.strip()
+        username, fullname, email, image = get_profile(url, username)
+        password = randompass()
+        add_user(wiki, username, fullname, email, password)
+        print "\t".join([username, fullname, email, image, password])
+
+        sleep(delay)
+        line = sys.stdin.readline()
+
+if __name__ == "__main__":
+    main()
+
+# vim: tabstop=4 expandtab shiftwidth=4
diff -r e425db7daf23 -r db03adb5f2e3 tools/get_profile.py
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/get_profile.py	Thu Jul 18 19:24:46 2013 +0200
@@ -0,0 +1,48 @@
+#!/usr/bin/env python
+
+"""
+Fetch the profile of a user from a Confluence site, printing their profile
+details in a tab-separated sequence using the following format:
+
+USERNAME FULLNAME EMAIL IMAGE-URL
+"""
+
+from os.path import split
+from urllib import basejoin
+import libxml2dom, sys
+
+def get_profile(url, username):
+    try:
+        d = libxml2dom.parseURI("%s/display/~%s" % (url.rstrip("/"), username), html=True)
+
+        fullname = d.xpath("//span[@id='fullName']")
+        fullname = fullname and fullname[0].textContent or ""
+        email = d.xpath("//span[@id='email']")
+        email = email and email[0].textContent.replace(" at ", "@").replace(" dot ", ".") or ""
+        image = d.xpath("//img[contains(@class, 'userLogo')]/@src")
+        image = image and image[0].textContent or ""
+
+        return [username, fullname, email, image and basejoin(url, image) or ""]
+
+    except libxml2dom.LSException:
+        return [username, "", username, ""]
+
+def main():
+    progname = split(sys.argv[0])[-1]
+
+    try:
+        url = sys.argv[1]
+        username = sys.argv[2]
+    except IndexError:
+        print >>sys.stderr, "%s <wiki URL> <username>" % progname
+        print >>sys.stderr
+        print >>sys.stderr, "Example: %s http://wiki.list.org/ <username>" % progname
+        sys.exit(1)
+
+    details = get_profile(url, username)
+    print "\t".join(details)
+
+if __name__ == "__main__":
+    main()
+
+# vim: tabstop=4 expandtab shiftwidth=4