Columbia LDAP lookup

README

Install pyldap (per requirements.py).

Example Usage:

    Chris-retina:ldap chmullig$ cat members_head.csv 
    email
    clm2186@columbia.edu
    ashutosh.nanda@columbia.edu
    Chris-retina:ldap chmullig$ python2.7 ldap_lookup.py members_head.csv 
    1 []
    1 [('uni=an2655,ou=People,o=Columbia University,c=US', {'givenName;x-role-2': ['Ashutosh'], 'cn': ['Ashutosh Nanda'], 'title': ['Student, FU FOUNDATN SCHL OF ENGINEERING & APPLIED SCIENCE:UGRAD'], 'cn;x-role-2': ['Ashutosh Nanda'], 'title;x-role-2': ['Teaching Assistant III'], 'ou;x-role-2': ['Department of Statistics'], 'sn': ['Nanda'], 'uni': ['an2655'], 'sn;x-role-2': ['Nanda'], 'ou': ['Computer Science'], 'givenName': ['Ashutosh']})]
    Chris-retina:ldap chmullig$ cat members_head.luldap.csv 
    email,results,sn,givenName,cn,ou,title,uni
    clm2186@columbia.edu,0
    ashutosh.nanda@columbia.edu,1,Nanda,Ashutosh,Ashutosh Nanda,Computer Science,"Student, FU FOUNDATN SCHL OF ENGINEERING & APPLIED SCIENCE:UGRAD",an2655
    Chris-retina:ldap chmullig$ 

ldap_lookup.py

#ldapsearch -h ldap.columbia.edu -s sub -x -t -b "o=Columbia University,c=US" -LLL "ou=Computer Science"

from paged_search_ext_s import MyLDAPObject
import ldap
import sys
import random
import csv

try:
    f = csv.reader(open(sys.argv[1], 'rb'))
    head = f.next()
except (KeyError, IOError):
    print 'ERROR call with a file to read'
    sys.exit(1)

outfn = sys.argv[1][:-4]+'.luldap.csv'

output = csv.writer(open(outfn, "w"))

con = MyLDAPObject("ldap://ldap.columbia.edu")
con.start_tls_s()
dn = "o=Columbia University,c=US"
con.bind_s("", "", ldap.AUTH_SIMPLE)
con.page_size=10

keys = ["sn", "givenName", "cn", "ou", "title", "uni",]
output.writerow(['email', 'results'] + keys)

for (email,) in f:
    results_pages, results = con.paged_search_ext_s(
        dn,
        ldap.SCOPE_SUBTREE,
        "(mail=%s)" % (email),
        ["sn", "givenName", "cn", "ou", "title", "uni",])
    print results_pages, results
    try:
        outrow = [results[0][1].get(key, ['',])[0] for key in keys]
        output.writerow([email, len(results)] + outrow)
    except:
        output.writerow([email, len(results)])

members_head.csv

email
clm2186@columbia.edu
ashutosh.nanda@columbia.edu

members_head.luldap.csv

email,results,sn,givenName,cn,ou,title,uni
clm2186@columbia.edu,0
ashutosh.nanda@columbia.edu,1,Nanda,Ashutosh,Ashutosh Nanda,Computer Science,"Student, FU FOUNDATN SCHL OF ENGINEERING & APPLIED SCIENCE:UGRAD",an2655

paged_search_ext_s.py

import ldap
from ldap.controls import SimplePagedResultsControl
from ldap.ldapobject import LDAPObject

class PagedResultsSearchObject:
  page_size = 10

  def paged_search_ext_s(self,base,scope,filterstr='(objectClass=*)',attrlist=None,attrsonly=0,serverctrls=None,clientctrls=None,timeout=-1,sizelimit=0):
    """
    Behaves exactly like LDAPObject.search_ext_s() but internally uses the
    simple paged results control to retrieve search results in chunks.
    
    This is non-sense for really large results sets which you would like
    to process one-by-one
    """
    req_ctrl = SimplePagedResultsControl(True,size=self.page_size,cookie='')

    # Send first search request
    msgid = self.search_ext(
      base,
      ldap.SCOPE_SUBTREE,
      filterstr,
      attrlist=attrlist,
      serverctrls=(serverctrls or [])+[req_ctrl]
    )

    result_pages = 0
    all_results = []
    
    while True:
      rtype, rdata, rmsgid, rctrls = self.result3(msgid)
      all_results.extend(rdata)
      result_pages += 1
      # Extract the simple paged results response control
      pctrls = [
        c
        for c in rctrls
        if c.controlType == SimplePagedResultsControl.controlType
      ]
      if pctrls:
        if pctrls[0].cookie:
            # Copy cookie from response control to request control
            req_ctrl.cookie = pctrls[0].cookie
            msgid = self.search_ext(
              base,
              ldap.SCOPE_SUBTREE,
              filterstr,
              attrlist=attrlist,
              serverctrls=(serverctrls or [])+[req_ctrl]
            )
        else:
            break
    return result_pages,all_results


class MyLDAPObject(LDAPObject,PagedResultsSearchObject):
  pass


### Jaraco's example
# ldap.set_option(ldap.OPT_REFERRALS, 0)
# l = MyLDAPObject(url,trace_level=2)
# l.protocol_version = 3
# l.simple_bind_s("", "")
# l.page_size=10

# # Send search request
# result_pages,all_results = l.paged_search_ext_s(
#   base,
#   ldap.SCOPE_SUBTREE,
#   search_flt,
#   attrlist=searchreq_attrlist,
#   serverctrls=None
# )

# l.unbind_s()

requirements.py

pyldap