This commit is contained in:
IgnBys
commit
6cc8ddc5b7
349
README.md
349
README.md
|
|
@ -1,6 +1,11 @@
|
|||
|
||||
## Zajęcia 1
|
||||
|
||||
Copyright AMU Poznan
|
||||
|
||||
Made by multiple people
|
||||
|
||||
|
||||
### Informacje na temat przedmiotu
|
||||
|
||||
Prowadzący: Jacek Kałużny
|
||||
|
|
@ -18,347 +23,3 @@ W ten sposób będziemy aktualizować zadania co zajęcia.
|
|||
Zadania robimy do końca soboty poprzedzającej zajęcia
|
||||
|
||||
Rozwiązanie zapisujemy w pliku run.py
|
||||
|
||||
|
||||
## Zajęcia 2 Wyrażenia regularne
|
||||
|
||||
Dokumentacja wyrażeń regularnych w python3: https://docs.python.org/3/library/re.html
|
||||
|
||||
### Podstawowe funkcje
|
||||
|
||||
search - zwraca pierwsze dopasowanie w napisie
|
||||
|
||||
findall - zwraca listę wszystkich dopasowań (nienakładających się na siebie)
|
||||
|
||||
match - zwraca dopasowanie od początku string
|
||||
|
||||
To tylko podstawowe funkcje, z których będziemy korzystać. W dokumentacji opisane są wszystkie.
|
||||
|
||||
### Obiekt match
|
||||
|
||||
```
|
||||
import re
|
||||
answer = re.search('na','banan')
|
||||
print(answer)
|
||||
print(answer.start())
|
||||
print(answer.end())
|
||||
print(answer.group())
|
||||
|
||||
answer = re.search('na','kabanos')
|
||||
print(answer)
|
||||
type(answer)
|
||||
|
||||
if answer:
|
||||
print(answer.group())
|
||||
else:
|
||||
pass
|
||||
```
|
||||
|
||||
### Metaznaki
|
||||
|
||||
|
||||
- [] - zbiór znaków
|
||||
- . - jakikolwiek znak
|
||||
|
||||
- ^ - początek napisu
|
||||
- $ - koniec napisu
|
||||
|
||||
- ? - znak występuje lub nie występuje
|
||||
- \* - zero albo więcej pojawień się
|
||||
- \+ - jeden albo więcej pojawień się
|
||||
- {} - dokładnie tyle pojawień się
|
||||
|
||||
- | - lub
|
||||
- () - grupa
|
||||
- \ -znak ucieczki
|
||||
|
||||
- \d digit
|
||||
- \D nie digit
|
||||
- \s whitespace
|
||||
- \S niewhitespace
|
||||
|
||||
|
||||
### Flagi
|
||||
|
||||
Można użyć specjalnych flag, np:
|
||||
`re.search('ma', 'AlA Ma KoTa', re.IGNORECASE)`.
|
||||
|
||||
### Przykłady (objaśnienia na laboratoriach)
|
||||
|
||||
Do nauki lepiej użyć pythona w wersji interaktywnej, a najlepiej ipython.
|
||||
|
||||
```
|
||||
import re
|
||||
|
||||
text = 'Ala ma kota i hamak, oraz 150 bananów.'
|
||||
|
||||
re.search('ma',text)
|
||||
re.match('ma',text)
|
||||
re.match('Ala ma',text)
|
||||
re.findall('ma',text)
|
||||
|
||||
re.findall('[mn]a',text)
|
||||
re.findall('[0-9]',text)
|
||||
re.findall('[0-9abc]',text)
|
||||
re.findall('[a-z][a-z]ma[a-z]',text)
|
||||
re.findall('[a-zA-Z][a-zA-Z]ma[a-zA-z0-9]',text)
|
||||
re.findall('\d',text)
|
||||
|
||||
re.search('[0-9][0-9][0-9]',text)
|
||||
re.search('[\d][\d][\d]',text)
|
||||
|
||||
re.search('\d{2}',text)
|
||||
re.search('\d{3}',text)
|
||||
|
||||
re.search('\d+',text)
|
||||
|
||||
re.search('\d+ bananów',text)
|
||||
re.search('\d* bananów','Ala ma dużo bananów')
|
||||
re.search('\d* bananów',text)
|
||||
re.search('ma \d? bananów','Ala ma 5 bananów')
|
||||
re.search('ma ?\d? bananów','Ala ma bananów')
|
||||
re.search('ma( \d)? bananów','Ala ma bananów')
|
||||
|
||||
re.search('\d+ bananów','Ala ma 10 bananów albo 20 bananów')
|
||||
re.search('\d+ bananów$','Ala ma 10 bananów albo 20 bananów')
|
||||
|
||||
text = 'Ala ma kota i hamak, oraz 150 bananów.'
|
||||
|
||||
re.search('\d+ bananów',text)
|
||||
|
||||
re.search('\d+\sbananów',text)
|
||||
|
||||
re.search('kota . hamak',text)
|
||||
|
||||
re.search('kota . hamak','Ala ma kota z hamakiem')
|
||||
|
||||
re.search('kota .* hamak','Ala ma kota lub hamak')
|
||||
|
||||
re.search('\.',text)
|
||||
|
||||
re.search('kota|psa','Ala ma kota lub hamak')
|
||||
|
||||
re.findall('kota|psa','Ala ma kota lub psa')
|
||||
|
||||
re.search('kota (i|lub) psa','Ala ma kota lub psa')
|
||||
|
||||
re.search('mam (kota).*(kota|psa)','Ja mam kota. Ala ma psa.').group(0)
|
||||
|
||||
re.search('mam (kota).*(kota|psa)','Ja mam kota. Ala ma psa.').group(1)
|
||||
|
||||
re.search('mam (kota).*(kota|psa)','Ja mam kota. Ala ma psa.').group(2)
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
### Przykłady wyrażenia regularne 2 (objaśnienia na laboratoriach)
|
||||
|
||||
#### ^
|
||||
```
|
||||
re.search('[0-9]+', '123-456-789')
|
||||
re.search('[^0-9][0-9]+[^0-9]', '123-456-789')
|
||||
```
|
||||
|
||||
#### cudzysłów
|
||||
'' oraz "" - oznaczają to samo w pythonie
|
||||
|
||||
' ala ma psa o imieniu "Burek"'
|
||||
|
||||
" ala ma psa o imieniu 'Burek' "
|
||||
|
||||
' ala ma psa o imieniu \'Burek\' '
|
||||
|
||||
" ala ma psa o imieniu \"Burek\" "
|
||||
|
||||
#### multiline string
|
||||
|
||||
#### raw string
|
||||
|
||||
przy raw string znaki \ traktowane są jako zwykłe znaki \
|
||||
|
||||
chociaż nawet w raw string nadal są escapowane (ale wtedy \ pozostają również w stringu bez zmian)
|
||||
|
||||
https://docs.python.org/3/reference/lexical_analysis.html
|
||||
|
||||
dobra praktyka - wszędzie escapować
|
||||
|
||||
```
|
||||
'\\'
|
||||
print('\\')
|
||||
|
||||
r'\\'
|
||||
print(r'\\')
|
||||
|
||||
|
||||
print("abcd")
|
||||
print("ab\cd")
|
||||
print(r"ab\cd")
|
||||
|
||||
print("ab\nd")
|
||||
print(r"ab\nd")
|
||||
|
||||
|
||||
print("\"")
|
||||
print(r"\"")
|
||||
|
||||
print("\")
|
||||
print(r"\")
|
||||
|
||||
re.search('\\', r'a\bc')
|
||||
re.search(r'\\', r'a\bc')
|
||||
re.search('\\\\', r'a\bc')
|
||||
```
|
||||
|
||||
#### RE SUB
|
||||
```
|
||||
re.sub(pattern, replacement, string)
|
||||
|
||||
re.sub('a','b', 'ala ma kota')
|
||||
```
|
||||
|
||||
#### backreferencje:
|
||||
|
||||
```
|
||||
|
||||
re.search(r' \d+ \d+', 'ala ma 41 41 kota')
|
||||
re.search(r' \d+ \d+', 'ala ma 41 123 kota')
|
||||
re.search(r' (\d+) \1', 'ala ma 41 41 kota')
|
||||
re.search(r' (\d+) \1', 'ala ma 41 123 kota')
|
||||
```
|
||||
|
||||
#### lookahead ( to sa takie assercje):
|
||||
```
|
||||
re.search(r'ma kot', 'ala ma kot')
|
||||
re.search(r'ma kot(?=[ay])', 'ala ma kot')
|
||||
re.search(r'ma kot(?=[ay])', 'ala ma kotka')
|
||||
re.search(r'ma kot(?=[ay])', 'ala ma koty')
|
||||
re.search(r'ma kot(?=[ay])', 'ala ma kota')
|
||||
|
||||
re.search(r'ma kot(?![ay])', 'ala ma kot')
|
||||
re.search(r'ma kot(?![ay])', 'ala ma kotka')
|
||||
re.search(r'ma kot(?![ay])', 'ala ma koty')
|
||||
re.search(r'ma kot(?![ay])', 'ala ma kota')
|
||||
```
|
||||
|
||||
#### named groups
|
||||
```
|
||||
r = re.search(r'ma (?P<ilepsow>\d+) kotow i (?P<ilekotow>\d+) psow', 'ala ma 100 kotow i 200 psow')
|
||||
r.groups()
|
||||
r.groups('ilepsow')
|
||||
r.groups('ilekotow')
|
||||
```
|
||||
|
||||
#### re.split
|
||||
```
|
||||
('a,b.c,d').split(',')
|
||||
('a,b.c,d').split(',')
|
||||
('a,b.c,d').split(',.')
|
||||
re.split(r',', 'a,b.c,d')
|
||||
re.split(r'[.,]', 'a,b.c,d')
|
||||
```
|
||||
#### \w word character
|
||||
```
|
||||
\w - matchuje Unicod word character , jeżeli flaga ASCII to [a-zA-Z0-9_]
|
||||
\w - odwrotne do \W, jezeli flaga ASCI to [^a-zA-Z0-9_]
|
||||
|
||||
re.findall(r'\w+', 'ala ma 3 koty.')
|
||||
re.findall(r'\W+', 'ala ma 3 koty.')
|
||||
```
|
||||
#### początek albo koniec słowa | word boundary
|
||||
```
|
||||
re.search(r'\bkot\b', 'Ala ma kota')
|
||||
re.search(r'\bkot\b', 'Ala ma kot')
|
||||
re.search(r'\bkot\b', 'Ala ma kot.')
|
||||
re.search(r'\bkot\b', 'Ala ma kot ')
|
||||
|
||||
re.search(r'\Bot\B', 'Ala ma kot ')
|
||||
re.search(r'\Bot\B', 'Ala ma kota ')
|
||||
```
|
||||
#### MULTILINE
|
||||
```
|
||||
re.findall(r'^Ma', 'Ma kota Ala\nMa psa Jacek')
|
||||
re.findall(r'^Ma', 'Ma kota Ala\nMa psa Jacek', re.MULTILINE)
|
||||
```
|
||||
#### RE.COMPILE
|
||||
|
||||
|
||||
|
||||
|
||||
## zajęcia 6
|
||||
|
||||
instalacja https://pypi.org/project/google-re2/
|
||||
|
||||
### DFA i NDFA
|
||||
|
||||
```
|
||||
import re2 as re
|
||||
n = 50
|
||||
regexp = "a?"*n+"a"*n
|
||||
s = "a"*n
|
||||
re.match(regexp, s)
|
||||
```
|
||||
|
||||
```
|
||||
re.match(r"(\d)abc\1", "3abc3") # re2 nie obsługuje backreferencji
|
||||
```
|
||||
|
||||
|
||||
re2 max memory - podniesienie limitu
|
||||
time # mierzenie czasu działania
|
||||
|
||||
|
||||
gdyby ktoś chciał poczytać więcej:
|
||||
https://swtch.com/~rsc/regexp/regexp1.html
|
||||
|
||||
### UTF-8
|
||||
```
|
||||
c = "ℋ"
|
||||
ord(c)
|
||||
chr(8459)
|
||||
8* 16**2 + 0 * 16**(1) + 0*16**(0)
|
||||
15*16**3 + 15* 16**2 + 15 * 16**(1) + 15*16**(0)
|
||||
```
|
||||
|
||||
```
|
||||
xxd -b file
|
||||
xxd file
|
||||
```
|
||||
|
||||
termin oddawania zadań - 15. listopada
|
||||
|
||||
|
||||
## Zajęcia 7
|
||||
https://www.openfst.org/twiki/bin/view/GRM/Thrax
|
||||
|
||||
https://www.cs.jhu.edu/~jason/465/hw-ofst/hw-ofst.pdf
|
||||
|
||||
Wszystkie zadania proszę robić na wzór `TaskH00`. Proszę umieszczać gramatykę w pliku `grammar.grm` oraz
|
||||
opisywać finalną regułę nazwą `FinalRule`.
|
||||
|
||||
|
||||
|
||||
## KOLOKWIUM
|
||||
Operatory, obowiązujące na kolokwium
|
||||
====================================
|
||||
|
||||
* kwantyfikatory `-` `*` `+` `?` `{n}` `{n,}` `{n, m}`
|
||||
* alternatywa — `|`
|
||||
* klasy znaków — `[...]`
|
||||
* zanegowane klasy znaków — `[^...]`
|
||||
* dowolny znak — `.`
|
||||
* unieważnianie znaków specjalnych — \
|
||||
* operatory zakotwiczające — `^` `$`
|
||||
|
||||
|
||||
Na kolokwium do każdego z 4 pytań będą 3 podpunkty. Na każdy podpunkt odpowiadamy TAK/NIE. Czas trwania to 15 minut.
|
||||
|
||||
- zawsze daszek i dolar
|
||||
- nie bierzemy pod uwagę capturing (jeżeli są pytania o równoważne)
|
||||
- proponuję wydrukować cały test w wersji bez opdowiedzi i sprawdzać
|
||||
|
||||
|
||||
Do zaliczenia należy zdobyć conajmniej 10 punktów.
|
||||
|
|
|
|||
|
|
@ -0,0 +1,8 @@
|
|||
Read a description of a deterministic finite-state automaton in the AT&T format
|
||||
(without weights) from the file in the first argument.
|
||||
|
||||
Read strings from the standard input.
|
||||
If a string is accepted by the
|
||||
automaton, write YES, otherwise- write NO.
|
||||
|
||||
The program is invoked like this: ./run.py fsa_description.arg < test1.in > test1.out
|
||||
|
|
@ -0,0 +1,16 @@
|
|||
0 1 x
|
||||
1 2 y
|
||||
2 3 z
|
||||
0 4 y
|
||||
0 4 z
|
||||
1 4 x
|
||||
1 4 z
|
||||
2 4 x
|
||||
2 4 y
|
||||
3 4 x
|
||||
3 4 y
|
||||
3 4 z
|
||||
4 4 x
|
||||
4 4 y
|
||||
4 4 z
|
||||
3
|
||||
|
|
@ -0,0 +1,9 @@
|
|||
NO
|
||||
YES
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
|
|
@ -0,0 +1,9 @@
|
|||
xxyz
|
||||
xyz
|
||||
xy
|
||||
zz
|
||||
xxy
|
||||
yzx
|
||||
|
||||
x
|
||||
xyzz
|
||||
|
|
@ -0,0 +1,10 @@
|
|||
Use a deterministic finite-state automaton (FSA) engine from the TaskE00.
|
||||
Create your own FSA description to check whether the string starts with "01" and ends with "01.
|
||||
Save it to fsa_description.arg file.
|
||||
|
||||
The alphabet is "0", "1".
|
||||
|
||||
Read strings from the standard input.
|
||||
If a string is accepted by the
|
||||
automaton, write YES, otherwise- write NO.
|
||||
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
YES
|
||||
NO
|
||||
YES
|
||||
NO
|
||||
YES
|
||||
NO
|
||||
NO
|
||||
YES
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
01
|
||||
10
|
||||
0101
|
||||
1010
|
||||
011101
|
||||
101010
|
||||
100010
|
||||
0100001
|
||||
|
||||
00110
|
||||
0000
|
||||
10101
|
||||
0
|
||||
1
|
||||
|
|
@ -0,0 +1,9 @@
|
|||
Use a deterministic finite-state automaton (FSA) engine from the TaskE00.
|
||||
Create your own FSA description to check whether the string starts with "10" and ends with "10.
|
||||
Save it to fsa_description.arg file.
|
||||
|
||||
The alphabet is "0", "1".
|
||||
|
||||
Read strings from the standard input.
|
||||
If a string is accepted by the
|
||||
automaton, write YES, otherwise- write NO.
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
NO
|
||||
YES
|
||||
NO
|
||||
YES
|
||||
NO
|
||||
YES
|
||||
YES
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
01
|
||||
10
|
||||
0101
|
||||
1010
|
||||
011101
|
||||
101010
|
||||
100010
|
||||
0100001
|
||||
|
||||
00110
|
||||
0000
|
||||
10101
|
||||
0
|
||||
1
|
||||
|
|
@ -0,0 +1,11 @@
|
|||
Use a deterministic finite-state automaton (FSA) engine from the TaskE00.
|
||||
Create your own FSA description to check whether the string contains "0"
|
||||
even number of times.
|
||||
Save it to fsa_description.arg file.
|
||||
|
||||
The alphabet is "0", "1".
|
||||
|
||||
Read strings from the standard input.
|
||||
If a string is accepted by the
|
||||
automaton, write YES, otherwise- write NO.
|
||||
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
NO
|
||||
NO
|
||||
YES
|
||||
YES
|
||||
YES
|
||||
NO
|
||||
YES
|
||||
NO
|
||||
YES
|
||||
NO
|
||||
YES
|
||||
YES
|
||||
NO
|
||||
YES
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
01
|
||||
10
|
||||
0101
|
||||
1010
|
||||
011101
|
||||
101010
|
||||
100010
|
||||
0100001
|
||||
|
||||
00110
|
||||
0000
|
||||
10101
|
||||
0
|
||||
1
|
||||
|
|
@ -0,0 +1,11 @@
|
|||
Use a deterministic finite-state automaton (FSA) engine from the TaskE00.
|
||||
Create your own FSA description to check whether the string contains "0"
|
||||
odd number of times.
|
||||
Save it to fsa_description.arg file.
|
||||
|
||||
The alphabet is "0", "1".
|
||||
|
||||
Read strings from the standard input.
|
||||
If a string is accepted by the
|
||||
automaton, write YES, otherwise- write NO.
|
||||
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
YES
|
||||
YES
|
||||
NO
|
||||
NO
|
||||
NO
|
||||
YES
|
||||
NO
|
||||
YES
|
||||
NO
|
||||
YES
|
||||
NO
|
||||
NO
|
||||
YES
|
||||
NO
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
01
|
||||
10
|
||||
0101
|
||||
1010
|
||||
011101
|
||||
101010
|
||||
100010
|
||||
0100001
|
||||
|
||||
00110
|
||||
0000
|
||||
10101
|
||||
0
|
||||
1
|
||||
|
|
@ -0,0 +1,10 @@
|
|||
Use a deterministic finite-state automaton (FSA) engine from the TaskB00.
|
||||
Create your own FSA description to check whether the line contains string '19DD', where D is a digit.
|
||||
Save it to fsa_description.arg file.
|
||||
|
||||
FSA alphabet is '0123456789x'.
|
||||
|
||||
Read strings from the standard input.
|
||||
If a string is accepted by the
|
||||
automaton, write YES, otherwise- write NO.
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because one or more lines are too long
|
|
@ -0,0 +1,6 @@
|
|||
NO
|
||||
YES
|
||||
NO
|
||||
NO
|
||||
YES
|
||||
YES
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
3214545443
|
||||
1910
|
||||
19
|
||||
xxx2190x
|
||||
xxx21905x
|
||||
1905x54545
|
||||
|
|
@ -0,0 +1,9 @@
|
|||
Use a deterministic finite-state automaton (FSA) engine from the previous task.
|
||||
Create your own FSA description to check whether the word "hamlet" is in the given line.
|
||||
Save it to fsa_description.arg file.
|
||||
|
||||
FSA alphabet is 'abcdefghijklmnopqrstuvwxyz '.
|
||||
|
||||
Read strings from the standard input.
|
||||
If a string is accepted by the
|
||||
automaton, write YES, otherwise- write NO.
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,3 @@
|
|||
NO
|
||||
YES
|
||||
YES
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
haml
|
||||
hamlet
|
||||
aaahamletbbb
|
||||
|
|
@ -0,0 +1,10 @@
|
|||
Use a deterministic finite-state automaton (FSA) engine from the previous task.
|
||||
Create your own FSA description to check whether the word "ophelia" is in the given line.
|
||||
Save it to fsa_description.arg file.
|
||||
|
||||
FSA alphabet is 'abcdefghijklmnopqrstuvwxyz '.
|
||||
|
||||
Read strings from the standard input.
|
||||
If a string is accepted by the
|
||||
automaton, write YES, otherwise- write NO.
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,3 @@
|
|||
NO
|
||||
YES
|
||||
YES
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
oph
|
||||
ophelia
|
||||
xfdfdopheliafff
|
||||
|
|
@ -0,0 +1,10 @@
|
|||
Use a deterministic finite-state automaton (FSA) engine from the previous task.
|
||||
Create your own FSA description to check whether the word "juliet" is in the given line.
|
||||
Save it to fsa_description.arg file.
|
||||
|
||||
FSA alphabet is 'abcdefghijklmnopqrstuvwxyz '.
|
||||
|
||||
Read strings from the standard input.
|
||||
If a string is accepted by the
|
||||
automaton, write YES, otherwise- write NO.
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,3 @@
|
|||
NO
|
||||
YES
|
||||
YES
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
juli
|
||||
juliet
|
||||
dgfdgjulietaaa
|
||||
|
|
@ -0,0 +1,10 @@
|
|||
Use a deterministic finite-state automaton (FSA) engine from the previous task.
|
||||
Create your own FSA description to check whether the word "macbeth" is in the given line.
|
||||
Save it to fsa_description.arg file.
|
||||
|
||||
FSA alphabet is 'abcdefghijklmnopqrstuvwxyz '.
|
||||
|
||||
Read strings from the standard input.
|
||||
If a string is accepted by the
|
||||
automaton, write YES, otherwise- write NO.
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,3 @@
|
|||
NO
|
||||
YES
|
||||
YES
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
macb
|
||||
macbeth
|
||||
xadadamacbethrff
|
||||
Loading…
Reference in New Issue