Difference between revisions of "RegEx Pattern Matching"
| Line 136: | Line 136: | ||
</div> | </div> | ||
</div> | </div> | ||
| + | |||
| + | <div class=q data-lang="py3"> | ||
| + | Cuba and Togo have four character names. | ||
| + | <p class=strong>Find the countries that have exactly four characters</p> | ||
| + | <pre class=def> | ||
| + | pp.pprint(list( | ||
| + | db.world.find({"name":{'$regex':"^Cu.*$"}},{"name":1,"_id":0}) | ||
| + | )) | ||
| + | </pre> | ||
| + | <div class=ans> | ||
| + | pp.pprint(list(db.world.find({"name":{'$regex':"^.{4}$"}},{"name":1,"_id":0}))) | ||
| + | </div> | ||
| + | </div> | ||
| + | ==Harder Questions== | ||
Revision as of 20:25, 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":{'$regex':"oo"}},{"name":1,"_id":0})))
Bahamas has three a, who else?
Find the country that has three or more a in the name
pp.pprint(list(
db.world.find({"name":{'$regex':"^T"}},{"name":1,"_id":0})
))
pp.pprint(list(db.world.find({"name":{'$regex':"(.*[aA].*){3}"}},{"name":1,"_id":0})))
India and Angola have n as their second character.
.* Indicates one or more characters, . indicates just one.
Find the countries that have "t" as the second character.
pp.pprint(list(
db.world.find({"name":{'$regex':"^.n"}},{"name":1,"_id":0})
))
pp.pprint(list(db.world.find({"name":{'$regex':"^.t"}},{"name":1,"_id":0})))
Lesotho and Moldova both have two o characters seperated by two other characters.
Find the countries that have two "o" characters separated by two others.
pp.pprint(list(
db.world.find({"name":{'$regex':"o.o"}},{"name":1,"_id":0})
))
pp.pprint(list(db.world.find({"name":{'$regex':"o..o"}},{"name":1,"_id":0})))
Cuba and Togo have four character names.
Find the countries that have exactly four characters
pp.pprint(list(
db.world.find({"name":{'$regex':"^Cu.*$"}},{"name":1,"_id":0})
))
pp.pprint(list(db.world.find({"name":{'$regex':"^.{4}$"}},{"name":1,"_id":0})))