AWS Lambda Chat Bot Hackthonに参加して画像検索用のChat Botを作成してみました。 ref: http://qiita.com/GushiSnow/items/3000fd4fc5a94b3e9e72

file0.py

query = "curl -XGET {your elasticsearch endpoint}:9200/_all/_search?pretty -d\'"

file1.txt

command_text = event['text'].replace("bot_lambda_out ", "")

file10.txt

python execute_wiki_pedia_xml_to_json.py -xml enwiki-20080312-abstract.xml -img True

file11.txt

python execute_wiki_pedia_xml_to_json.py -xml enwiki-20080312-abstract.xml -img True

file12.txt

parallel --linebuffer -j 40-100 :::: jobs.txt

file13.txt

gzip {your git clone folder}/Data/wiki_image/*.json

file14.txt

vagrant up

file15.txt

[vagrant]
{あなたが設定したVagrantのipアドレス（デフォルトは192.168.33.25に設定しています。）} ansible_ssh_private_key_file=.vagrant/machines/default/virtualbox/private_key ansible_ssh_user=vagrant

file16.txt

cd {your git clone folder}/ansible_setting
ansible-playbook -i vagrant_host vagrant_lambda_docker.yml

file17.txt

vagrant reload
vagrant ssh
cd /home/vagrant/AWS_Lambda_Chatbot/docker
make test-elasticsearch-english

file18.txt

docker tag {docker elasticsearch image} elasticsearch_english
docker login
docker tag elasticsearch_english:latest {your docker repository name}:{tag name}
docker push {your docker repository name}:{tag name}

file19.txt

cd {your git clone folder}/ansible_setting
ansible-playbook -i aws_lambda_chatbot_host aws_lambda_chatbot.yml

file2.txt

## convert HTML POST data or HTTP GET query string to JSON

## get the raw post data from the AWS built-in variable and give it a nicer name
#if ($context.httpMethod == "POST")
 #set($rawAPIData = $input.path('$'))
#elseif ($context.httpMethod == "GET")
 #set($rawAPIData = $input.params().querystring)
 #set($rawAPIData = $rawAPIData.toString())
 #set($rawAPIDataLength = $rawAPIData.length() - 1)
 #set($rawAPIData = $rawAPIData.substring(1, $rawAPIDataLength))
 #set($rawAPIData = $rawAPIData.replace(", ", "&"))
#else
 #set($rawAPIData = "")
#end

## first we get the number of "&" in the string, this tells us if there is more than one key value pair
#set($countAmpersands = $rawAPIData.length() - $rawAPIData.replace("&", "").length())

## if there are no "&" at all then we have only one key value pair.
## we append an ampersand to the string so that we can tokenise it the same way as multiple kv pairs.
## the "empty" kv pair to the right of the ampersand will be ignored anyway.
#if ($countAmpersands == 0)
 #set($rawPostData = $rawAPIData + "&")
#end

## now we tokenise using the ampersand(s)
#set($tokenisedAmpersand = $rawAPIData.split("&"))

## we set up a variable to hold the valid key value pairs
#set($tokenisedEquals = [])

## now we set up a loop to find the valid key value pairs, which must contain only one "="
#foreach( $kvPair in $tokenisedAmpersand )
 #set($countEquals = $kvPair.length() - $kvPair.replace("=", "").length())
 #if ($countEquals == 1)
  #set($kvTokenised = $kvPair.split("="))
  #if ($kvTokenised[0].length() > 0)
   ## we found a valid key value pair. add it to the list.
   #set($devNull = $tokenisedEquals.add($kvPair))
  #end
 #end
#end

## next we set up our loop inside the output structure "{" and "}"
{
#foreach( $kvPair in $tokenisedEquals )
  ## finally we output the JSON for this pair and append a comma if this isn't the last pair
  #set($kvTokenised = $kvPair.split("="))
 "$util.urlDecode($kvTokenised[0])" : #if($kvTokenised[1].length() > 0)"$util.urlDecode($kvTokenised[1])"#{else}""#end#if( $foreach.hasNext ),#end
#end
}

file20.txt

ssh -i {your key} ubuntu@{your ip address}

file21.txt

docker login
docker pull {your docker repository name}:{tag name}

file22.txt

git clone https://github.com/SnowMasaya/AWS_Lambda_ChatBot.git
cd {your git clone folder}/Question_Answer
sh elastic_start_english.sh 1 5 True elasticsearch_english

file23.txt

sh elastic_start_english.sh [PIPE_NUMBER] [PARALLEL_NUMBER] [IMAGE_FLAG (True or False)] [ELS_IMAGE_NAME]

file24.py

query = "curl -XGET {your elasticsearch endpoint}:9200/_all/_search?pretty -d\'"

file3.txt

TYPE=InnoDB;

file4.sql

1: create database enwiki
2: use enwiki
2: source enwiki-20080312-imagelinks.sql

file5.py

for extract_data in doc:
    if extract_data.tag in self.extract_dict_array:
        # replace method for title extract
        if extract_data.text is not None:
            self.index_json.update({ "index" : { "_index" : "wikipedia", "_type" : "contents", "_id" : str(index_count) } })
            replace_text = extract_data.text.replace("Wikipedia: ", "")
            self.json_data.update({extract_data.tag: replace_text})
            if extract_data.tag == "title" and self.image_Flag is True and len(replace_text) > 1:
                self.__get_image(replace_text)
        else:
            self.index_json.update({ "index" : { "_index" : "wikipedia", "_type" : "contents", "_id" : str(index_count)  } })
self.json_data.update({extract_data.tag: extract_data.text})

file6.txt

            if extract_data.tag == "title" and self.image_Flag is True and len(replace_text) > 1:
                self.__get_image(replace_text)

file7.py

SELECT DISTINCT il_to from imagelinks WHERE (il_to LIKE " + "'" + search_word  + "%" + ".jpg')" + "OR" + \
"(il_to LIKE " + "'" + search_word + "%" + ".JPG')" + "order by (il_to = '" + search_word + "') desc"

file8.txt

http://〇〇.jpg

file9.txt

{"index": {"_id": "20", "_index": "wikipedia_image", "_type": "contents"}}      
   42 {"abstract": "(Arabic)The Pledge", "image": "https://upload.wikimedia.org/wikipedia/commons/d/d4/Algeria%2C_Ottawa.JPG", "title": "Algeria", "url": "http://en.wikipedia.org/wiki/Algeria"}