Continue cleanup (#339)

docs/quick-start.md

@@ -36,14 +36,14 @@ The second command will download and run a prebuilt AsterixDB docker container f
 After it finishes, you should see the messages as shown in the following screenshot:
 ![docker][docker]
 
-**Step 4**: Run the following command to ingest sample tweets (about 324K) and US population data into AsterixDB.
+**Step 4**: Run the following command to ingest sample tweets (about 47K) and US population data into AsterixDB.
 
 
 ```
 ~/cloudberry> ./script/ingestAllTwitterToLocalCluster.sh
 ```
 
-This step is downloading about 70MB of data, and it may take 5 minutes, again, depending on your network speed. You should see the messages as shown in the following screenshot:
+When it finishes you should see the messages as shown in the following screenshot:
 ![ingestion][ingestion]
 
 **Step 5**: Compile and run the Cloudberry server.
@@ -80,17 +80,24 @@ The instructions above assume that we use an AsterixDB instance in a Docker cont
 
 **Step 8**: Follow the instructions on the [AsterixDB Installation Guide](https://ci.apache.org/projects/asterixdb/index.html) to install an AsterixDB cluster.  Select your preferred installation option. 
 
-**Step 9**: Ingest twitter data.
+**Step 9**: Ingest twitter data to AsterixDB
 
-**Step 10**: Change the Cloudberry middleware configuration to connect to this new AsterixDB cluster. You can modify the AsterixDB hostname in the configuration file `neo/conf/application.conf` and change the `asterixdb.url` value to the AsterixDB hostname.
+You need to give the RESTFul API link of the AsterixDB cluster and one of its NC names to the ingestion script as following:
+
+```
+~/cloudberry> ./script/ingestAllTwitterToLocalCluster.sh http://YourAsterixDBServerIP:19002/aql ONE_OF_NC_NAMES
+```
+
+**Step 10**: Change the Cloudberry middleware configuration to connect to this new AsterixDB cluster. 
+You can modify the AsterixDB hostname in the configuration file `neo/conf/application.conf` by changing the `asterixdb.url` value.
 
 ```
 asterixdb.url = "http://YourAsterixDBHostName:19002/query/service"
 ```
 
 ## Build your own application
 
-For more information about Cloudberry, please read its [documentation](/documentation).
+TwitterMap is one example of how to use Cloudberry. To develop your own application, please find more information in [documentation](/documentation).
 
 [architecture]: /img/quick-start-architecture.png
 {: width="800px"}

script/dockerClean.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 #clean up the existing images
-docker stop -f cc nc1
+docker stop cc nc1
 docker rm -f cc nc1
 docker volume rm dbstore
 # remove the local image to fetch the newest remote version

script/fileFeed.sh

@@ -1,3 +1,7 @@
 #!/usr/bin/env bash
+link=${1-"localhost"}
+host=$(basename $(dirname $link))
+host=${host%%:*}
+port=${2-"10001"}
 sbt "project noah" --error "run-main edu.uci.ics.cloudberry.noah.feed.FileFeedDriver \
--u localhost -p ${1:-10001}"
+-u $host -p $port"

script/ingestAllTwitterToLocalCluster.sh

@@ -18,10 +18,11 @@
 #===============================================================================
 
 host=${1:-'http://localhost:19002/aql'}
+nc=${2:-"nc1"}
 echo "Ingesting sample tweets..."
-./script/ingestTwitterToLocalCluster.sh $host
+./script/ingestTwitterToLocalCluster.sh $host $nc
 
 echo "Ingesting population data..."
-./script/ingestPopulationToLocalCluster.sh $host
+./script/ingestPopulationToLocalCluster.sh $host $nc
 
 echo "Data ingestion completed!"

script/ingestPopulationToLocalCluster.sh

@@ -20,8 +20,9 @@
 set -o nounset                              # Treat unset variables as an error
 
 host=${1:-'http://localhost:19002/aql'}
+nc=${2:-"nc1"}
 # ddl to register the twitter dataset
-cat <<'EOF' | curl -XPOST --data-binary @- $host
+cat <<EOF | curl -XPOST --data-binary @- $host
 use dataverse twitter;
 create type typeStatePopulation if not exists as open{
     name:string,
@@ -52,7 +53,7 @@ create dataset dsCityPopulation(typeCityPopulation) if not exists primary key ci
 
 create feed StatePopulationFeed using socket_adapter
 (
-    ("sockets"="nc1:10002"),
+    ("sockets"="$nc:10002"),
     ("address-type"="nc"),
     ("type-name"="typeStatePopulation"),
     ("format"="adm")
@@ -62,7 +63,7 @@ start feed StatePopulationFeed;
 
 create feed CountyPopulationFeed using socket_adapter
 (
-    ("sockets"="nc1:10003"),
+    ("sockets"="$nc:10003"),
     ("address-type"="nc"),
     ("type-name"="typeCountyPopulation"),
     ("format"="adm")
@@ -72,7 +73,7 @@ start feed CountyPopulationFeed;
 
 create feed CityPopulationFeed using socket_adapter
 (
-    ("sockets"="nc1:10004"),
+    ("sockets"="$nc:10004"),
     ("address-type"="nc"),
     ("type-name"="typeCityPopulation"),
     ("format"="adm")
@@ -83,13 +84,13 @@ EOF
 
 echo 'Created population datasets in AsterixDB.'
 #Serve socket feed using local file
-cat ./noah/src/main/resources/population/adm/allStatePopulation.adm | ./script/fileFeed.sh 10002
+cat ./noah/src/main/resources/population/adm/allStatePopulation.adm | ./script/fileFeed.sh $host 10002
 echo 'Ingested state population dataset.'
 
-cat ./noah/src/main/resources/population/adm/allCountyPopulation.adm | ./script/fileFeed.sh 10003
+cat ./noah/src/main/resources/population/adm/allCountyPopulation.adm | ./script/fileFeed.sh $host 10003
 echo 'Ingested county population dataset.'
 
-cat ./noah/src/main/resources/population/adm/allCityPopulation.adm | ./script/fileFeed.sh 10004
+cat ./noah/src/main/resources/population/adm/allCityPopulation.adm | ./script/fileFeed.sh $host 10004
 echo 'Ingested city population dataset.'
 
 cat <<'EOF' | curl -XPOST --data-binary @- $host

script/ingestTwitterToLocalCluster.sh

@@ -20,8 +20,9 @@
 set -o nounset                              # Treat unset variables as an error
 
 # ddl to register the twitter dataset
-host=${1:-'http://localhost:19002/aql'}
-cat <<'EOF' | curl -XPOST --data-binary @- $host
+host=${1:-"http://localhost:19002/aql"}
+nc=${2:-"nc1"}
+cat <<EOF | curl -XPOST --data-binary @- $host
 drop dataverse twitter if exists;
 create dataverse twitter if not exists;
 use dataverse twitter
@@ -84,7 +85,7 @@ create index text_idx if not exists on ds_tweet("text") type fulltext;
 
 create feed TweetFeed using socket_adapter
 (
-    ("sockets"="nc1:10001"),
+    ("sockets"="$nc:10001"),
     ("address-type"="nc"),
     ("type-name"="typeTweet"),
     ("format"="adm")
@@ -94,11 +95,9 @@ start feed TweetFeed;
 EOF
 
 
-[ -f ./script/sample.adm.gz ] || { echo "Downloading the data...";  ./script/getSampleTweetsFromGDrive.sh; }
-#Serve socket feed using local file
-#git lfs fetch
+#[ -f ./script/sample.adm.gz ] || { echo "Downloading the data...";  ./script/getSampleTweetsFromGDrive.sh; }
 
 echo "Start ingestion ..." 
-gunzip -c ./script/sample.adm.gz | ./script/fileFeed.sh
+gunzip -c ./script/sample.adm.gz | ./script/fileFeed.sh $host 10001
 echo "Ingested sample tweets."