added dumpcsv command

etherdump/commands/dumpcsv.py

@@ -0,0 +1,65 @@
+#!/usr/bin/env python
+from __future__ import print_function
+from argparse import ArgumentParser
+import sys, json, re
+from datetime import datetime
+from urllib import urlencode
+from urllib2 import urlopen, HTTPError, URLError
+from csv import writer 
+
+"""
+Dumps a CSV of all pads with columns
+padid, groupid, revisions, lastedited, author_ids
+
+    padids have their group name trimmed
+    groupid is without (g.  $)
+    revisions is an integral number of edits
+    lastedited is ISO8601 formatted
+    author_ids is a space delimited list of internal author IDs 
+"""
+
+groupnamepat = re.compile(r"^g\.(\w+)\$")
+
+out = writer(sys.stdout)
+
+def jsonload (url):
+    f = urlopen(url)
+    data = f.read()
+    f.close()
+    return json.loads(data)
+
+def main (args):
+    p = ArgumentParser("")
+    p.add_argument("--padinfo", default="padinfo.json", help="padinfo, default: padinfo.json")
+    p.add_argument("--format", default="csv", help="output format: csv (default), json")
+    args = p.parse_args(args)
+
+    with open(args.padinfo) as f:
+        info = json.load(f)
+    apiurl =  "{0[protocol]}://{0[hostname]}:{0[port]}{0[apiurl]}{0[apiversion]}/".format(info)
+    data = {}
+    data['apikey'] = info['apikey']
+    requesturl = apiurl+'listAllPads?'+urlencode(data)
+
+    results = jsonload(requesturl)['data']['padIDs']
+    results.sort()
+    out.writerow(("padid", "groupid", "lastedited", "revisions", "author_ids"))
+    for padid in results:
+        print (u"{0}".format(padid), file=sys.stderr)
+        m = groupnamepat.match(padid)
+        if m:
+            groupname = m.group(1)
+            padidnogroup = padid[m.end():]
+        else:
+            groupname = u""
+            padidnogroup = padid
+
+        data['padID'] = padid.encode("utf-8")
+        revisions = jsonload(apiurl+'getRevisionsCount?'+urlencode(data))['data']['revisions']
+        lastedited_raw = jsonload(apiurl+'getLastEdited?'+urlencode(data))['data']['lastEdited']
+        lastedited_iso = datetime.fromtimestamp(int(lastedited_raw)/1000).isoformat()
+        author_ids = jsonload(apiurl+'listAuthorsOfPad?'+urlencode(data))['data']['authorIDs']
+        author_ids = u" ".join(author_ids).encode("utf-8")
+        out.writerow((padidnogroup.encode("utf-8"), groupname.encode("utf-8"), revisions, lastedited_iso, author_ids))
+
+