Difference between revisions of "RegEx Pattern Matching"

Revision as of 19:41, 15 July 2015

#ENCODING
import io
import sys
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-16')
#MONGO
from pymongo import MongoClient
client = MongoClient()
client.progzoo.authenticate('scott','tiger')
db = client['progzoo']
#PRETTY
import pprint
pp = pprint.PrettyPrinter(indent=4)

Pattern Matching String

This tutorial uses RegEx to check names. We will be using find() on the collection world.

You can use '$regex':"^B" to get all the countries that start with B.

Find the countries that start with Y

pp.pprint(list(
    db.world.find({"name":{'$regex':"^F"}},{"name":1,"_id":0})
))

pp.pprint(list(db.world.find({"name":{'$regex':"^Y"}},{"name":1,"_id":0})))

You can use '$regex':"a$" to get all the countries that end with a.

Find the countries that end with Y

pp.pprint(list(
    db.world.find({"name":{'$regex':"l$"}},{"name":1,"_id":0})
))

pp.pprint(list(db.world.find({"name":{'$regex':"y$"}},{"name":1,"_id":0})))

Luxembourg has an x, so does one other country, list them both

Find the countries that contain the letter x

pp.pprint(list(
    db.world.find({"name":{'$regex':"ana"}},{"name":1,"_id":0})
))

pp.pprint(list(db.world.find({"name":{'$regex':"x"}},{"name":1,"_id":0})))

Iceland and Switzerland end with land but where are the others?

Find the countries that end with land

pp.pprint(list(
    db.world.find({"name":{'$regex':"stan$"}},{"name":1,"_id":0})
))

pp.pprint(list(db.world.find({"name":{'$regex':"land$"}},{"name":1,"_id":0})))

Columbia starts with a C and ends with ia - there are two other countries like this.
You can use .* to match any character except newlines.

Find the countries that start with C and end with ia

pp.pprint(list(
    db.world.find({"name":{'$regex':"^A.*n$"}},{"name":1,"_id":0})
))

pp.pprint(list(db.world.find({"name":{'$regex':"^C.*ia$"}},{"name":1,"_id":0})))

Greece has a double e, who has a double o

Find the countty that has oo in its name

pp.pprint(list(
    db.world.find({"name":{'$regex':"ee"}},{"name":1,"_id":0})
))

pp.pprint(list(db.world.find({"name":{'$regex':"oo"}},{"name":1,"_id":0})))

Bahamas has three a, who else?

Find the countty that has oo in its name

pp.pprint(list(
    db.world.find({"name":{'$regex':"^T"}},{"name":1,"_id":0})
))

pp.pprint(list(db.world.find({"name":{'$regex':"(.*[aA].*){3}"},{"name":1,"_id":0})))

@@ Line 106: / Line 106: @@
 </pre>
 <div class=ans>
-pp.pprint(list(db.world.find({"name":{'$regex':"a.*a.*a.*"}},{"name":1,"_id":0})))
+pp.pprint(list(db.world.find({"name":{'$regex':"(.*[aA].*){3}"},{"name":1,"_id":0})))
 </div>
 </div>