Adicione abreviações postais dos EUA à sua pesquisa do Atlas em 5 minutos

1
“Avenue”: 
2
3
{
4
5
"mappingType":"equivalent",
6
7
"synonyms":["AVENUE","AV","AVEN","AVENU","AVN","AVNUE","AVE"]
8
9
}

1
git clone https://github.com/mongodb-developer/Postal-Abbreviations-Synonyms-Atlas-Search-Tutorial/ 
2
3
cd Postal-Abbreviations-Synonyms-Atlas-Search-Tutorial
4
5
python3 main.py

1
import json
2
3
import requests
4
5
from bs4 import BeautifulSoup
6
7
import pandas as pd
8
9
import re

1
# Create a URL object
2
3
streetsUrl = 'https://pe.usps.com/text/pub28/28apc_002.htm'
4
5
# Create object page
6
7
headers = {
8
9
    "User-Agent": 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.96 Mobile Safari/537.36'}
10
11
streetsPage = requests.get(streetsUrl, headers=headers)

1
# Obtain page's information
2
3
streetsSoup = BeautifulSoup(streetsPage.text, 'html.parser')

1
# Get the table by its id
2
3
streetsTable = streetsSoup.find('table', {'id': 'ep533076'})

1
# Transform the table into a list of dataframes
2
3
streetsDf = pd.read_html(str(streetsTable))

1
# Group together all "Commonly Used Street Suffix or Abbreviation" entries
2
3
streetsGroup = streetsDf[0].groupby(0)[1].apply(list)

1
for x in range(streetsGroup.size):
2
3
4
    dictionary = {
5
6
        "mappingType": "equivalent",
7
8
        "synonyms": streetsGroup[x]
9
10
    }
11
12
13
    # export the JSON into a file
14
15
    with open(streetsGroup.index.values[x] + ".json", "w") as outfile:
16
17
        json.dump(dictionary, outfile)

1
# Create a URL object
2
3
unitsUrl = 'https://pe.usps.com/text/pub28/28apc_003.htm'
4
5
6
unitsPage = requests.get(unitsUrl, headers=headers)
7
8
9
# Obtain page's information
10
11
unitsSoup = BeautifulSoup(unitsPage.text, 'html.parser')
12
13
14
# Get the table by its id
15
16
unitsTable = unitsSoup.find('table', {'id': 'ep538257'})
17
18
19
# Transform the table into a list of dataframes
20
21
unitsDf = pd.read_html(str(unitsTable))

1
unitsDf[0] = unitsDf[0].dropna()

1
# Create a 2D list that we will use for our synonyms
2
3
unitsList = unitsDf[0][[0, 2]].values.tolist()

1
# Remove all non-alphanumeric characters
2
3
unitsList = [[re.sub("[^ \w]"," ",x).strip().lower() for x in y] for y in unitsList]

1
# Restrict the range to only retrieve the results we want
2
3
for x in range(1, len(unitsList) - 1):
4
5
6
    dictionary = {
7
8
        "mappingType": "equivalent",
9
10
        "synonyms": unitsList[x]
11
12
    }
13
14
15
    # export the JSON into a file
16
17
    with open(unitsList[x][0] + ".json", "w") as outfile:
18
19
        json.dump(dictionary, outfile)

1
mongosh "mongodb+srv://cluster0.XXXXX.mongodb.net/sample_restaurant" --apiVersion 1 --username <USERNAME>

1
use('sample_restaurants')
2
3
db.createCollection("postal_synonyms", { validator: { $jsonSchema: { "bsonType": "object", "required": ["mappingType", "synonyms"], "properties": { "mappingType": { "type": "string", "enum": ["equivalent", "explicit"], "description": "must be a either equivalent or explicit" }, "synonyms": { "bsonType": "array", "items": { "type": "string" }, "description": "must be an Array with each item a string and is required" }, "input": { "type": "array", "items": { "type": "string" }, "description": "must be an Array and is each item is a string" } }, "anyOf": [{ "not": { "properties": { "mappingType": { "enum": ["explicit"] } }, "required": ["mappingType"] } }, { "required": ["input"] }] } } })

1
cat *.json | mongoimport --uri 'mongodb+srv://<USERNAME>:<PASSWORD>@cluster0.pwh9dzy.mongodb.net/sample_restaurants?retryWrites=true&w=majority' --collection='postal_synonyms'

1
{
2
3
  "mappings": {
4
5
    "dynamic": true
6
7
  },
8
9
  "synonyms": [
10
11
    {
12
13
      "analyzer": "lucene.standard",
14
15
      "name": "synonym_mapping",
16
17
      "source": {
18
19
        "collection": "postal_synonyms"
20
21
      }
22
23
    }
24
25
    ]
26
27
}

1
{
2
3
  index: 'default',
4
5
  text: {
6
7
    query: 'boulevard',
8
9
    path: 'address.street'
10
11
  }
12
13
}

1
{
2
3
  index: 'default',
4
5
  text: {
6
7
    query: blvd,
8
9
    path: 'address.street'
10
11
  }
12
13
}

1
{
2
3
  index: 'default',
4
5
  text: {
6
7
    query: 'blvd',
8
9
    path: 'address.street',
10
11
    synonyms:'synonym_mapping'
12
13
  }
14
15
}