Skip to content

Commit 53d87d2

Browse files
gregmalcolmgregmalcolm
committed
2 parents bfdebc5 + bb0cb4b commit 53d87d2

File tree

3 files changed

+272
-0
lines changed

3 files changed

+272
-0
lines changed

‎python 2/koans/about_regex.py

Lines changed: 238 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,238 @@
1+
#!/usr/bin/env python
2+
# -*- coding: utf-8 -*-
3+
4+
from runner.koan import *
5+
import re
6+
class AboutRegex(Koan):
7+
"""
8+
This koans are based on the Ben's book: Regular Expressions in 10 minutes.
9+
I found this books very useful so I decided to write a koans in order to practice everything I had learned from it.
10+
http://www.forta.com/books/0672325667/
11+
"""
12+
13+
def test_matching_literal_text(self):
14+
"""
15+
Lesson 1 Matching Literal String
16+
"""
17+
string = "Hello, my name is Felix and this koans are based on the Ben's book: Regular Expressions in 10 minutes."
18+
m = re.search(__, string)
19+
self.assertTrue(m and m.group(0) and m.group(0)== 'Felix', "I want my name")
20+
21+
def test_matching_literal_text_how_many(self):
22+
"""
23+
Lesson 1 How many matches?
24+
25+
The default behaviour of most regular extression engines is to return just the first match.
26+
In python you have the next options:
27+
28+
match() --> Determine if the RE matches at the beginning of the string.
29+
search() --> Scan through a string, looking for any location where this RE matches.
30+
findall() --> Find all substrings where the RE matches, and returns them as a list.
31+
finditer() --> Find all substrings where the RE matches, and returns them as an iterator.
32+
33+
"""
34+
string = "Hello, my name is Felix and this koans are based on the Ben's book: Regular Expressions in 10 minutes. Repeat My name is Felix"
35+
m = re.match('Felix', string) #TIP: Maybe match it's not the best option
36+
self.assertEqual(len(m),2, "I want to know how many times appears my name")
37+
38+
def test_matching_literal_text_not_case_sensitivity(self):
39+
"""
40+
Lesson 1 Matching Literal String non case sensitivity.
41+
Most regex implementations also support matches that are not case sensitive. In python you can use re.IGNORECASE, in
42+
Javascript you can specify the optional i flag.
43+
In Ben's book you can see more languages.
44+
45+
"""
46+
string = "Hello, my name is Felix or felix and this koans are based on the Ben's book: Regular Expressions in 10 minutes."
47+
self.assertEqual(len(re.findall("felix", string,__)),2, "I want my name")
48+
49+
def test_matching_any_character(self):
50+
"""
51+
Lesson 1 Matching any character
52+
53+
. matches any character, alphabetic characters, digits and .
54+
"""
55+
string = "pecks.xlx\n" \
56+
+ "orders1.xls\n" \
57+
+ "apec1.xls\n" \
58+
+ "na1.xls\n" \
59+
+ "na2.xls\n" \
60+
+ "sa1.xls"
61+
62+
#TIP: remember the issue of this lesson
63+
self.assertEquals(len(re.findall(__, string)),3, "I want to find all files for North America(na) or South America(sa)")
64+
65+
def test_matching_special_character(self):
66+
"""
67+
Lesson 1 Matching special character
68+
69+
Uses \ if you want to match special character
70+
"""
71+
string = "sales.xlx\n" \
72+
+ "sales1.xls\n" \
73+
+ "orders1.xls\n" \
74+
+ "apac1.xls\n" \
75+
+ "sales2.xls\n" \
76+
+ "na1.xls\n" \
77+
+ "na2.xls\n" \
78+
+ "sa1.xls"
79+
#TIP you can use the pattern .a. which matches in above test but in this case matches more than you want
80+
self.assertEquals(len(re.findall(__, string)),3, "I want to find all files for North America(na) or South America(sa)")
81+
82+
def test_matching_set_character(self):
83+
"""
84+
Lesson 2 Matching sets of characters
85+
86+
A set of characters is defined using the metacharacters [ and ]. Everything between them is part of the set and
87+
any one of the set members must match (but not all).
88+
"""
89+
string = "sales.xlx\n" \
90+
+ "sales1.xls\n" \
91+
+ "orders3.xls\n" \
92+
+ "apac1.xls\n" \
93+
+ "sales2.xls\n" \
94+
+ "na1.xls\n" \
95+
+ "na2.xls\n" \
96+
+ "sa1.xls\n" \
97+
+ "ca1.xls"
98+
#TIP you can use the pattern .a. which matches in above test but in this case matches more than you want
99+
self.assertEquals(len(re.findall(__, string)),3, "I want to find all files for North America(na) or South America(sa), but not (ca)")
100+
101+
def test_using_character_set_ranges(self):
102+
"""
103+
Lesson 2 Using character set ranges
104+
105+
The previous pattern could be [ns]a.\.xls and if a in the list had a file name sam.xls would be matched because the . matches all
106+
characters, not just digits. This can be solved with Character sets.
107+
You can use this pattern [ns]a[0123456789]\.xls but to simplify you can use a special metacharacter: - (hyphen). i.e [0-9]
108+
109+
- is only a metacharacter when used between [].
110+
111+
"""
112+
string = "sales.xlx\n" \
113+
+ "sales1.xls\n" \
114+
+ "orders3.xls\n" \
115+
+ "apac1.xls\n" \
116+
+ "sales2.xls\n" \
117+
+ "na1.xls\n" \
118+
+ "na2.xls\n" \
119+
+ "sa1.xls\n" \
120+
+ "sam.xls\n" \
121+
+ "ca1.xls"
122+
self.assertEquals(len(re.findall(__, string)),3, "I want to find all files for North America(na) or South America(sa), but not (ca)")
123+
124+
def test_using_multiple_ranges(self):
125+
"""
126+
Lesson 2 Using character set ranges
127+
128+
The following are valid ranges:
129+
A-Z matches all uppercase characters from A to Z
130+
a-z matches all uppercase characters from a to z
131+
A-F matches all uppercase characters from A to F
132+
A-z matches all uppercase characters from A to z. This pattern also includes characters such as [ and ^
133+
Any two ASCII characters may be specified as the range start and end.
134+
135+
"""
136+
string = '<BODY BGCOLOR="#336633" TEXT="#FFFFFF" MARGINWIDTH="0" MARGINHEIGHT="0" TOPMARGIN="0" LEFTMARGIN="0">'
137+
self.assertEquals(len(re.findall(__, string)),2, "I want to find all the colors in RGB")
138+
139+
140+
def test_anything_but_matching(self):
141+
"""
142+
Lesson 2 Using character set ranges
143+
Occsionally, you'll want a list of characters that you don't want to match.
144+
Character sets can be negated using the ^ metacharacter.
145+
146+
"""
147+
string = "sales.xlx\n" \
148+
+ "sales1.xls\n" \
149+
+ "orders3.xls\n" \
150+
+ "apac1.xls\n" \
151+
+ "sales2.xls\n" \
152+
+ "sales3.xls\n" \
153+
+ "europe2.xls\n" \
154+
+ "sam.xls\n" \
155+
+ "na1.xls\n" \
156+
+ "na2.xls\n" \
157+
+ "sa1.xls\n" \
158+
+ "ca1.xls"
159+
m = re.search(__, string)
160+
self.assertTrue(m and m.group(0) and m.group(0)== 'sam.xls', "I want to find the name sam")
161+
162+
def using_metacharacters_escaping(self):
163+
"""
164+
Lesson 3 Using metacharacters
165+
166+
Metacharacters are characters that have special meaning within regular expressions.
167+
168+
Metacharacters can be escaped by preceding them with a backslash, therefore \. matches .
169+
"""
170+
string = "var myArray = new Array();\n" \
171+
+ "if (myArray[0]) { \n" \
172+
+ "}"
173+
m = re.search("myArray[0]", string) #TIP: This pattern matches "myArray0" because [ and ] are metacharacters
174+
self.assertTrue(m and m.group(0) and m.group(0)== 'myArray[0]', "I want to find myArray[0]")
175+
176+
def using_metacharacters_matching_white_spaces(self):
177+
"""
178+
Lesson 3 Matching whitespace character
179+
180+
Sometimes you'll have to match nonprinting whitespace characters embedded in your text. For example tab characters
181+
or line breaks .
182+
In this cases you can use these special metacharacters:
183+
[\b] Backspace
184+
\f Form feed
185+
\n Line feed
186+
\r Carriage return
187+
\t Tab
188+
\v Vertical tab
189+
190+
"""
191+
f = open('koans/regex_cvs', 'r')
192+
string = f.read()
193+
#This text contains a series of records in comma-delimited format (cvs). Before processing the records, you need
194+
# to remove any blank lines in the data.
195+
m = re.search("", string)
196+
self.assertTrue(m and m.group(0) and m.group(0)== '\n\n', "I want to find the blank lines")
197+
198+
def using_metacharacters_matching_digits(self):
199+
"""
200+
Lesson 3 Using metacharacters
201+
202+
As you have seen in Lesson 2, [0-9] is a shorcut for [0123456789] and is used to match any digit.
203+
To match anything other than a digit, the set can be negated as [^0-9].
204+
With the next metacharacters you can do the same:
205+
\d match any digit (same as [0-9])
206+
\D match any nondigit (same as [0-9])
207+
"""
208+
string = "var myArray = new Array();\n" \
209+
+ "if (myArray[0]) { \n" \
210+
+ " alert('Learning regex'); \n" \
211+
+ "} \n" \
212+
+ "if (myArray[1]) { \n" \
213+
+ " alert('With this great book');\n" \
214+
+ "} \n"
215+
216+
self.assertEquals( len(re.findall(__, string)), 2, "I want to find all uses of myArray")
217+
218+
219+
def using_metacharacters_matching_alphanumeric_characters(self):
220+
"""
221+
Lesson 3 Using metacharacters
222+
223+
Like with the digits you have special characters for alphanumeric characters:
224+
\w Any alphanumeric character in uppercase or lowercase and underscore: [a-zA-Z0-9_]
225+
\W Any nonalphanumeric or underscore character: [^a-zA-Z0-9_]
226+
227+
Here you have a list of IDs made of 3 characters/digits/underscores, 1 hyphen and 3 characters/digits/underscores:
228+
A1A-B_A or BA_-2e3 or 1_2-34R
229+
"""
230+
string = "A_1-DRA\n" \
231+
+"A01-2ER\n" \
232+
+"A01-(4d\n" \
233+
+"B11=223\n" \
234+
+"A1A-B_A\n" \
235+
+"1_2-34R\n" \
236+
+"BA_-2e3"
237+
238+
self.assertEquals( len(re.findall(__, string)), 5, "I want to find the ids")

‎python 2/koans/regex_cvs

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
1+
"101", "Ben", "Forta
2+
"102", "Felix", "Lopez"
3+
4+
"103", "Roberta", "Robertson"
5+
"104", "Bob", "Bobson"
6+

‎python 2/koans/regex_solutions.txt

Lines changed: 28 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,28 @@
1+
test_matching_literal_text:
2+
Felix
3+
test_matching_literal_text_how_many:
4+
findall
5+
test_matching_literal_text_not_case_sensitivity:
6+
re.findall("felix", string, re.IGNORECASE)
7+
test_matching_any_character:
8+
.a OR .a.
9+
test_matching_special_character:
10+
.a.\.
11+
test_matching_set_character:
12+
[ns]a.\. Actually this pattern is not quite right either. If a file named usa1.xls existed, it would match.
13+
The solution to this problem involves matching, which will be covered later, in "Position Matching.
14+
test_using_character_set_ranges:
15+
[ns]a[0-9]\.xls
16+
test_using_multiple_ranges:
17+
#[0-9A-Fa-f][0-9A-Fa-f][0-9A-Fa-f][0-9A-Fa-f][0-9A-Fa-f][0-9A-Fa-f] OR #[0-9A-Fa-f]{6} but the latter will be seen later
18+
test_anything_but_matching:
19+
[ns]a[^0-9]\.xls
20+
using_metacharacters_escaping:
21+
myArray\[0\]
22+
using_metacharacters_macthing_white_spaces:
23+
\n\n
24+
IMPORTANT: Windows uses a carriage return line fedd combination used as an end-of-line marker, so you need to use \r\n.
25+
using_metacharacters_matching_digits:
26+
myArray\[\d\]
27+
using_metacharacters_matching_alphanumeric_characters:
28+
\w\w\w-\w\w\w

0 commit comments

Comments
 (0)