How to import CSV/TSV data to Couch DB?

How to import CSV/TSV data to Couch开发者_运维问答 DB?

Its pretty easy with python.

 #!/usr/bin/env python

from couchdbkit import Server, Database
from couchdbkit.loaders import FileSystemDocsLoader
from csv import DictReader
import sys, subprocess, math, os



def parseDoc(doc):
    for k,v in doc.items():
        if (isinstance(v,str)):
            #print k, v, v.isdigit()
            # #see if this string is really an int or a float
            if v.isdigit()==True: #int
                doc[k] = int(v)
            else: #try a float
                try:
                    if math.isnan(float(v))==False:
                        doc[k] = float(v) 
                except:
                    pass            
    return doc


def upload(db, docs):
    db.bulk_save(docs)
    del docs
    return list()


def uploadFile(fname, uri, dbname):


  print 'Upload contents of %s to %s/%s' % (fname, uri, dbname)

  # #connect to the db
  theServer = Server(uri)
  db = theServer.get_or_create_db(dbname)

  #loop on file for upload
  reader = DictReader(open(fname, 'rU'), dialect = 'excel')  #see the python csv module 
         #for other options, such as using the tab delimeter. The first line in your csv 
         #file should contain all of the "key" and all subsequent lines hold the values 
         #for those keys.

  #used for bulk uploading
  docs = list()
  checkpoint = 100

  for doc in reader:
    newdoc = parseDoc(doc) #this just converts strings that are really numbers into ints and floats

    #Here I check to see if the doc is already on the database. If it is, then I assign
    #the _rev key so that it updates the doc on the db.

    if db.doc_exist(newdoc.get('_id')):
      newdoc['_rev'] = db.get_rev(newdoc.get('_id'))

    docs.append(newdoc)

    if len(docs)%checkpoint==0:
      docs = upload(db,docs)

  #don't forget the last batch        
  docs = upload(db,docs)



if __name__=='__main__':
  filename = sys.argv[1]
  uri = sys.argv[2]
  dbname = sys.argv[3]

  uploadFile(filename, uri, dbname)

Apache CouchDB only stores JSON documents. Therefore, to import CSV you must convert to individual JSON documents and then POST them normally.

You will probably have to write a program to loop through each line. Convert the CSV line (a sequence of values) into the JSON document (a sequence of key:value pairs). Then simply send it to CouchDB using HTTP.

I use this here: https://github/glynnbird/couchimport. If your CSV is reasonably simple it will just boil down to setting a DB name and piping the CSV to couchimport.

Just wrote a script in Ruby: csv2couchdb

Hello i create this simple snippet and he is very fast and powerful.

import csv
import couchdb #install this library with pip

couch = couchdb.Server('http://user:password@localhost:port') #change user, password and localhost with yours

dbname = #insert a name of the db
db = couch.create(dbname) #create the database
db = couch[dbname]


with open(r'INSERT FILE PATH') as csv_file: #in the '' insert your file path 
    csv_reader = csv.reader(csv_file, delimiter=',')
    keys = next(csv_reader)
    line_count = 0
    for values in csv_reader:
        db.save(dict(zip(keys,values)))