hw2: done ex1, ex2a, ex2b

Assignment2_part1/convert.sh

@@ -0,0 +1,30 @@
+#!/bin/sh
+set -e
+
+SCRIPT_DIR=$(cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd)
+
+input="$SCRIPT_DIR/data/restaurants.csv"
+output="$SCRIPT_DIR/data/restaurants.jsonl"
+
+
+# In order:
+# - Convert CSV to JSON
+# - Convert JSON array in JSON lines notation
+# - Remove last line (which is all `null`)
+cat "$input" | jq -s --raw-input --raw-output \
+  'split("\n") | .[1:-1] | map(split(",")) |
+    map({
+      "id": .[0],
+      "name": .[1],
+      "city": .[2],
+      "location": {
+          "lon": .[8] | sub("^\"\\["; "") | sub("\\s*"; "") | tonumber,
+          "lat": .[9] | sub("\\]\"$"; "") | sub("\\s*"; "") | tonumber,
+      },
+      "averageCostForTwo": .[3],
+      "aggregateRating": .[4],
+      "ratingText": .[5],
+      "votes": .[6],
+      "date": .[7]
+    })' "$input" | \
+        jq -c '.[]' > "$output"

Assignment2_part1/mappings.json

@@ -0,0 +1,50 @@
+{
+  "properties": {
+    "id": {
+      "type": "long"
+    },
+    "name": {
+      "type": "text",
+      "fields": {
+        "keyword": {
+          "type": "keyword",
+          "ignore_above": 256
+        }
+      }
+    },
+    "city": {
+      "type": "text",
+      "fields": {
+        "keyword": {
+          "type": "keyword",
+          "ignore_above": 256
+        }
+      }
+    },
+    "location": {
+      "type": "geo_point"
+    },
+    "averageCostForTwo": {
+      "type": "float"
+    },
+    "aggregateRating": {
+      "type": "float"
+    },
+    "ratingText": {
+      "type": "text",
+      "fields": {
+        "keyword": {
+          "type": "keyword",
+          "ignore_above": 256
+        }
+      }
+    },
+    "votes": {
+      "type": "float"
+    },
+    "date": {
+      "type": "date",
+      "format": "date_optional_time"
+    }
+  }
+}

Assignment2_part1/queries/query2a.http

@@ -0,0 +1,17 @@
+GET /restaurants/_search
+{
+  "query": {
+    "bool": {
+      "must": [
+        { "match": { "name": "pizza" } }
+      ],
+      "should": [
+        { "match": { "ratingText": "Very Good" } },
+        { "match": { "ratingText": "Excellent" } }
+      ],
+      "must_not": [
+        { "match": { "name": "pasta" } }
+      ]
+    }
+  }
+}

Assignment2_part1/queries/query2b.http

@@ -0,0 +1,31 @@
+GET /restaurants/_search
+{
+  "from" : 0,
+  "size" : 5,
+  "sort" : [
+    { "averageCostForTwo" : "desc" }
+  ],
+  "query": {
+    "bool": {
+      "must": [
+        {
+          "range": {
+            "date": {
+              "gte": "2018-01-01",
+              "lte": "2018-12-31"
+            }
+          }
+        },
+        {
+          "geo_distance": {
+            "distance": "20km",
+            "location": {
+              "lat": 33.9259,
+              "lon": -83.3389
+            }
+          }
+        }
+      ]
+    }
+  }
+}

Assignment2_part1/upload.sh

@@ -0,0 +1,32 @@
+#!/bin/bash
+
+set -e
+
+SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+
+elastic_dir="$HOME/bin/elasticsearch-8.6.2"
+elastic_url="https://localhost:9200"
+crt="$elastic_dir/config/certs/http_ca.crt"
+
+input="$SCRIPT_DIR/data/restaurants.jsonl"
+password="GZH*wqNTvQ0WRdrPrpHm"
+
+# Create index
+curl --cacert "$crt" -u "elastic:$password" \
+    -X DELETE "$elastic_url/restaurants" | jq . || true
+curl --cacert "$crt" -u "elastic:$password" \
+    -X PUT "$elastic_url/restaurants" | jq .
+
+# Upload mappings
+cat mappings.json | curl --cacert "$crt" -u "elastic:$password" -X POST \
+    --data-binary @- "$elastic_url/restaurants/_mappings/" \
+    -H "Content-Type: application/json" | jq .
+
+# Upload documents one by one
+while IFS= read -r line
+do
+    id=$(echo "$line" | jq '.id | tonumber')
+    echo $line | curl -k --cacert "$crt" -u "elastic:$password" -X PUT \
+        --data-binary @- "$elastic_url/restaurants/_doc/$id" \
+        -H "Content-Type: application/json" | jq ._id &
+done < "$input"