Compare commits
No commits in common. "b8ff9bedad288930c5347708a07c9da847ddf0c1" and "e067a250ead643e08ca2461b4277d0f6c10ced3b" have entirely different histories.
b8ff9bedad
...
e067a250ea
@ -1,25 +0,0 @@
|
||||
import re
|
||||
|
||||
def substitute_digits(input_string):
|
||||
def replace_digit(match):
|
||||
digits = match.group()
|
||||
replaced_digits = ''
|
||||
for digit in digits:
|
||||
if '0' <= digit <= '9':
|
||||
replaced_digits += chr(ord('a') + int(digit))
|
||||
else:
|
||||
replaced_digits += digit
|
||||
return replaced_digits
|
||||
|
||||
pattern = re.compile(r'\d{4}')
|
||||
substituted_string = pattern.sub(replace_digit, input_string)
|
||||
|
||||
return substituted_string
|
||||
|
||||
|
||||
file_path = 'simple.in'
|
||||
with open(file_path, 'r', encoding = 'utf-8') as file:
|
||||
for line in file:
|
||||
line = line.rstrip('\n')
|
||||
result = substitute_digits(line)
|
||||
print(result)
|
@ -18,3 +18,5 @@ letter to lower. In this task word means the string of "\w" metacharacters,
|
||||
lower case letter is [a-ząćęłńóśźż] class,
|
||||
capital case letter is [A-ZĄĆĘŁŃÓŚŹŻ] class.
|
||||
|
||||
POINTS: 2
|
||||
DEADLINE: 2020-12-18 23:59:59
|
||||
|
@ -1,10 +0,0 @@
|
||||
import re
|
||||
|
||||
def process_file(file_path):
|
||||
with open(file_path, 'r',encoding='utf-8') as file:
|
||||
for line in file:
|
||||
modified_line = re.sub(r'\b(?:[A-Z]+\w*[a-z]+\w*|[a-z]+\w*[A-Z]+\w*)\b', lambda match: match.group(0).swapcase(), line)
|
||||
print(modified_line, end='')
|
||||
|
||||
file_path = 'polish_wiki_excerpt.exp'
|
||||
process_file(file_path)
|
@ -1,23 +0,0 @@
|
||||
import re
|
||||
|
||||
def analyze_line(line):
|
||||
result = re.findall(r'([a-ząćęłńóśźż])|([A-ZĄĆĘŁŃÓŚŹŻ])|(\d)|(\s)', line, flags=re.UNICODE)
|
||||
|
||||
lower_case_letters = [match[0] for match in result if match[0]]
|
||||
upper_case_letters = [match[1] for match in result if match[1]]
|
||||
digits = [match[2] for match in result if match[2]]
|
||||
special_characters = [match[3] for match in result if match[3]]
|
||||
|
||||
result = f"{len(lower_case_letters)} {len(upper_case_letters)} {len(digits)} {len(special_characters)}"
|
||||
return result
|
||||
|
||||
def process_file(file_path):
|
||||
with open(file_path, 'r', encoding='utf-8') as file:
|
||||
for line in file:
|
||||
line = line.rstrip('\n')
|
||||
if line:
|
||||
result = analyze_line(line)
|
||||
print(result)
|
||||
|
||||
file_path = 'simple.in'
|
||||
process_file(file_path)
|
@ -19,3 +19,6 @@ In this task word means a string of "\w" metacharacters,
|
||||
lower case letter is [a-ząćęłńóśźż] class,
|
||||
capital case letter is [A-ZĄĆĘŁŃÓŚŹŻ] class capital case letter is [A-ZĄĆĘŁŃÓŚŹŻ] class.
|
||||
|
||||
|
||||
POINTS: 1
|
||||
DEADLINE: 2020-12-18 23:59:59
|
||||
|
@ -1,13 +0,0 @@
|
||||
import re
|
||||
|
||||
def process_line(line):
|
||||
words = re.findall(r'\b(?:[a-ząćęłńóśźż]+\w*|[A-ZĄĆĘŁŃÓŚŹŻ]+\w*)\b', line, flags=re.UNICODE)
|
||||
lowercase_words = [word for word in words if word[0].islower()]
|
||||
uppercase_words = [word for word in words if word[0].isupper()]
|
||||
return f"{len(lowercase_words)} {len(uppercase_words)}"
|
||||
|
||||
file_path = 'simple.in'
|
||||
with open(file_path, 'r', encoding='utf-8') as file:
|
||||
for line in file:
|
||||
result = process_line(line.strip())
|
||||
print(result)
|
@ -16,3 +16,5 @@ Write the input line with the second digits string deleted.
|
||||
Digit is a [0-9] class.
|
||||
|
||||
|
||||
POINTS: 1
|
||||
DEADLINE: 2020-12-18 23:59:59
|
||||
|
@ -1,22 +0,0 @@
|
||||
import re
|
||||
|
||||
def delete_second_digits(input_line):
|
||||
regex = r'\b(\d+)\b'
|
||||
numbers = re.findall(regex, input_line)
|
||||
|
||||
if len(numbers) > 1:
|
||||
second_number = numbers[1]
|
||||
input_line = re.sub(re.escape(second_number), '', input_line, 1)
|
||||
|
||||
return input_line
|
||||
|
||||
file_path = 'simple.in'
|
||||
output_lines = []
|
||||
|
||||
with open(file_path, 'r', encoding='utf-8') as file:
|
||||
for line in file:
|
||||
modified_line = delete_second_digits(line)
|
||||
output_lines.append(modified_line)
|
||||
|
||||
for line in output_lines:
|
||||
print(line, end='')
|
@ -1,6 +1,3 @@
|
||||
Mam 2 jabłka i 35 banananów.
|
||||
Mam 2 jabłka i 35 banananów oraz 20 gruszek.
|
||||
Widziałem 2 bociany.
|
||||
2 35 209
|
||||
12 34
|
||||
532 234 234 324
|
@ -17,3 +17,6 @@ The number of "x" in the "xxx" string should be the same as the
|
||||
the number of characters in the input string.
|
||||
In this task, a word means a string of "\w" metacharacters.
|
||||
|
||||
|
||||
POINTS: 2
|
||||
DEADLINE: 2020-12-18 23:59:59
|
||||
|
@ -1,15 +0,0 @@
|
||||
import re
|
||||
|
||||
def process_line(line):
|
||||
words = re.findall(r'\w+', line)
|
||||
if len(words) >= 3:
|
||||
third_word = words[2]
|
||||
replacement = 'x' * len(third_word)
|
||||
line = re.sub(r'\b' + re.escape(third_word) + r'\b', replacement, line)
|
||||
|
||||
return line
|
||||
|
||||
with open('simple.in', 'r', encoding='utf-8') as file:
|
||||
for line in file:
|
||||
processed_line = process_line(line)
|
||||
print(processed_line, end='')
|
@ -1,20 +0,0 @@
|
||||
Use regular expressions to extract lines containing polish surnames.
|
||||
|
||||
Download list of polish male and female surnames from here:
|
||||
|
||||
|
||||
* https://dane.gov.pl/pl/dataset/1681,nazwiska-osob-zyjacych-wystepujace-w-rejestrze-pesel/resource/35279/table?page=1&per_page=20&q=&sort=
|
||||
* https://dane.gov.pl/pl/dataset/1681,nazwiska-osob-zyjacych-wystepujace-w-rejestrze-pesel/resource/22817/table?page=1&per_page=20&q=&sort=
|
||||
|
||||
|
||||
Extract lines from stdin containing any of the surnames.
|
||||
Look only for surnames in lowercase.
|
||||
The surname does not have to be surrounded by space or any other special characters.
|
||||
Don't search for declined forms of surnames.
|
||||
|
||||
Check either NFA (e.g. re python library) and DFA (google re2) and compare run speed.
|
||||
|
||||
Submit solution based on DFA library.
|
||||
|
||||
NOTE: You could extract the polish surnames list, save it to a file, then commit the file to your repository.
|
||||
NOTE: You may set max_mem to a higher value than the default in re2 library.
|
File diff suppressed because one or more lines are too long
@ -1,41 +0,0 @@
|
||||
Use regular expressions to mark Polish first-person masculine forms.
|
||||
|
||||
You should handle the following types of expressions:
|
||||
|
||||
* first-person masculine past forms of verbs ("zrobiłem", "pisałem", etc.),
|
||||
* first-person singular masculine forms of the verb "być" ("be") combined
|
||||
with singular masculine nominative forms of adjectives ("wysoki", "sprytny", etc.),
|
||||
assuming that the form of the verb "być" is to the left of the adjective, not
|
||||
more than 3 other words,
|
||||
* the verb "będę" combined with the past participle (i.e. 3rd person
|
||||
masculine imperfect form, e.g. "robił", pisał"), assuming
|
||||
that "będę" is to the left of the adjective, not
|
||||
more than 3 other words to the left of the participle OR directly
|
||||
to the right of the participle ("robił będę").
|
||||
|
||||
The first-person masculine forms should be marked with curly brackets.
|
||||
You should mark only the masculine form. Do not mark the form of "być"
|
||||
(unless it clearly a masculine form, i.e. for "byłem").
|
||||
|
||||
The match should be case-insensitive.
|
||||
|
||||
The PoliMorf dictionary of inflected forms should be applied:
|
||||
http://zil.ipipan.waw.pl/PoliMorf?action=AttachFile&do=get&target=PoliMorf-0.6.7.tab.gz
|
||||
|
||||
Suggested steps:
|
||||
|
||||
1. Extract all the needed forms from the PoliMorf dictionary:
|
||||
|
||||
* 1st person masculine past forms of verbs, unfortunately
|
||||
this form is not directly present in the lexicon, you need
|
||||
to add "em" to the 3rd person masculine form ("zrobił" => "zrobiłem")
|
||||
* singular masculine nominative forms of adjectives
|
||||
* masculine past participle (3rd person masculine imperfect forms of verbs)
|
||||
|
||||
You could do this using grep/cut commands — to obtain a simple text files
|
||||
with a word in each line. You can do this once and commit the 3 files to your repository.
|
||||
|
||||
2. In your `run` script/program, read the 3 files and create a large
|
||||
expression with alternatives. Use a regexp library based on DFAs (determintistic
|
||||
finite-automatons).
|
||||
|
@ -1,25 +0,0 @@
|
||||
Tu nic nie ma.
|
||||
Wczoraj {ugotowałem} ziemniaki.
|
||||
{Jechałem}, {jechałem} i {jechałem}, a potem się {zatrzymałem}.
|
||||
{Umyłem} się mydłem.
|
||||
Jestem {wysoki}.
|
||||
Jest wysoki.
|
||||
Mówią, że jestem od zawsze niezwykle {sprytny}.
|
||||
aaaa {byłem} aaa {zielony} ddd
|
||||
aaaa {byłem} aaa bbb {zielony} ddd
|
||||
aaaa {byłem} aaa bbb ccc {zielony} ddd
|
||||
aaaa {byłem} aaa bbb ccc ddd zielony ddd
|
||||
aaaa był aaa bbb zielony ddd
|
||||
aaaa byłam aaa bbb zielony ddd
|
||||
aaaa byłam aaa bbb zielona ddd
|
||||
teraz będę {pisał} książkę
|
||||
będę teraz {pisał} książkę
|
||||
będę teraz dla ciebie {pisał} książkę
|
||||
teraz dla ciebie {pisał} będę księżkę
|
||||
będę i on napisał książkę
|
||||
aaa będę {śpiewał} bbb
|
||||
aaa będę ccc {śpiewał} bbb
|
||||
aaa będę ccc ddd {śpiewał} bbb
|
||||
aaa będę ccc ddd eee {śpiewał} bbb
|
||||
aaa będę ccc ddd eee fff śpiewał bbb
|
||||
{pływałem} i {biegałem}
|
@ -1,25 +0,0 @@
|
||||
Tu nic nie ma.
|
||||
Wczoraj ugotowałem ziemniaki.
|
||||
Jechałem, jechałem i jechałem, a potem się zatrzymałem.
|
||||
Umyłem się mydłem.
|
||||
Jestem wysoki.
|
||||
Jest wysoki.
|
||||
Mówią, że jestem od zawsze niezwykle sprytny.
|
||||
aaaa byłem aaa zielony ddd
|
||||
aaaa byłem aaa bbb zielony ddd
|
||||
aaaa byłem aaa bbb ccc zielony ddd
|
||||
aaaa byłem aaa bbb ccc ddd zielony ddd
|
||||
aaaa był aaa bbb zielony ddd
|
||||
aaaa byłam aaa bbb zielony ddd
|
||||
aaaa byłam aaa bbb zielona ddd
|
||||
teraz będę pisał książkę
|
||||
będę teraz pisał książkę
|
||||
będę teraz dla ciebie pisał książkę
|
||||
teraz dla ciebie pisał będę księżkę
|
||||
będę i on napisał książkę
|
||||
aaa będę śpiewał bbb
|
||||
aaa będę ccc śpiewał bbb
|
||||
aaa będę ccc ddd śpiewał bbb
|
||||
aaa będę ccc ddd eee śpiewał bbb
|
||||
aaa będę ccc ddd eee fff śpiewał bbb
|
||||
pływałem i biegałem
|
@ -1,40 +0,0 @@
|
||||
Use regular expressions to mark Polish first-person feminine forms.
|
||||
|
||||
You should handle the following types of expressions:
|
||||
|
||||
* first-person feminine past forms of verbs ("zrobiłam", "pisałam", etc.),
|
||||
* first-person singular feminine forms of the verb "być" ("be") combined
|
||||
with singular feminine nominative forms of adjectives ("wysoka", "sprytna", etc.),
|
||||
assuming that the form of the verb "być" is to the left of the adjective, not
|
||||
more than 3 other words,
|
||||
* the verb "będę" combined with the past participle (i.e. 3rd person
|
||||
feminine imperfect form, e.g. "robiła", pisała"), assuming
|
||||
that "będę" is to the left of the adjective, not
|
||||
more than 3 other words to the left of the participle OR directly
|
||||
to the right of the participle ("robiła będę").
|
||||
|
||||
The first-person feminine forms should be marked with curly brackets.
|
||||
You should mark only the feminine form. Do not mark the form of "być"
|
||||
(unless it clearly a feminine form, i.e. for "byłam").
|
||||
|
||||
The match should be case-insensitive.
|
||||
|
||||
The PoliMorf dictionary of inflected forms should be applied:
|
||||
http://zil.ipipan.waw.pl/PoliMorf?action=AttachFile&do=get&target=PoliMorf-0.6.7.tab.gz
|
||||
|
||||
Suggested steps:
|
||||
|
||||
1. Extract all the needed forms from the PoliMorf dictionary:
|
||||
|
||||
* 1st person feminine past forms of verbs, unfortunately
|
||||
this form is not directly present in the lexicon, you need
|
||||
to add "m" to the 3rd person feminine form ("zrobiła" => "zrobiłam")
|
||||
* singular feminine nominative forms of adjectives
|
||||
* feminine past participle (3rd person feminine imperfect forms of verbs)
|
||||
|
||||
You could do this using grep/cut commands — to obtain a simple text files
|
||||
with a word in each line. You can do this once and commit the 3 files to your repository.
|
||||
|
||||
2. In your `run` script/program, read the 3 files and create a large
|
||||
expression with alternatives. Use a regexp library based on DFAs (determintistic
|
||||
finite-automatons).
|
@ -1,25 +0,0 @@
|
||||
Tu nic nie ma.
|
||||
Wczoraj {ugotowałam} ziemniaki.
|
||||
{Jechałam}, {jechałam} i {jechałam}, a potem się {zatrzymałam}.
|
||||
{Umyłam} się mydłem i bam, złam się.
|
||||
Jestem {wysoka}.
|
||||
Jest {wysoka}.
|
||||
Mówią, że jestem od zawsze niezwykle {sprytna}.
|
||||
aaaa {byłam} aaa {zielona} ddd
|
||||
aaaa {byłam} aaa bbb {zielona} ddd
|
||||
aaaa {byłam} aaa bbb ccc {zielona} ddd
|
||||
aaaa {byłam} aaa bbb ccc ddd zielona ddd
|
||||
aaaa była aaa bbb zielona ddd
|
||||
aaaa byłem aaa bbb zielona ddd
|
||||
aaaa byłem aaa bbb zielony ddd
|
||||
teraz będę {pisała} książkę
|
||||
będę teraz {pisała} książkę
|
||||
będę teraz dla ciebie {pisała} książkę
|
||||
teraz dla ciebie {pisała} będę księżkę
|
||||
będę i ona napisała książkę
|
||||
aaa będę {śpiewała} bbb
|
||||
aaa będę ccc {śpiewała} bbb
|
||||
aaa będę ccc ddd {śpiewała} bbb
|
||||
aaa będę ccc ddd eee {śpiewała} bbb
|
||||
aaa będę ccc ddd eee fff śpiewała bbb
|
||||
{pływałam} i {biegałam}
|
@ -1,25 +0,0 @@
|
||||
Tu nic nie ma.
|
||||
Wczoraj ugotowałam ziemniaki.
|
||||
Jechałam, jechałam i jechałam, a potem się zatrzymałam.
|
||||
Umyłam się mydłem i bam, złam się.
|
||||
Jestem wysoka.
|
||||
Jest wysoka.
|
||||
Mówią, że jestem od zawsze niezwykle sprytna.
|
||||
aaaa byłam aaa zielona ddd
|
||||
aaaa byłam aaa bbb zielona ddd
|
||||
aaaa byłam aaa bbb ccc zielona ddd
|
||||
aaaa byłam aaa bbb ccc ddd zielona ddd
|
||||
aaaa była aaa bbb zielona ddd
|
||||
aaaa byłem aaa bbb zielona ddd
|
||||
aaaa byłem aaa bbb zielony ddd
|
||||
teraz będę pisała książkę
|
||||
będę teraz pisała książkę
|
||||
będę teraz dla ciebie pisała książkę
|
||||
teraz dla ciebie pisała będę księżkę
|
||||
będę i ona napisała książkę
|
||||
aaa będę śpiewała bbb
|
||||
aaa będę ccc śpiewała bbb
|
||||
aaa będę ccc ddd śpiewała bbb
|
||||
aaa będę ccc ddd eee śpiewała bbb
|
||||
aaa będę ccc ddd eee fff śpiewała bbb
|
||||
pływałam i biegałam
|
@ -1,20 +0,0 @@
|
||||
Use regular expressions to extract lines containing polish surnames. CASE INSENSITIVE
|
||||
|
||||
Download list of polish male and female surnames from here:
|
||||
|
||||
|
||||
* https://dane.gov.pl/pl/dataset/1681,nazwiska-osob-zyjacych-wystepujace-w-rejestrze-pesel/resource/35279/table?page=1&per_page=20&q=&sort=
|
||||
* https://dane.gov.pl/pl/dataset/1681,nazwiska-osob-zyjacych-wystepujace-w-rejestrze-pesel/resource/22817/table?page=1&per_page=20&q=&sort=
|
||||
|
||||
|
||||
Extract lines from stdin containing any of the surnames.
|
||||
Look only for surnames no matter casing (case insensitive).
|
||||
The surname does not have to be surrounded by space or any other special characters.
|
||||
Don't search for declined forms of surnames.
|
||||
|
||||
Check either NFA (e.g. re python library) and DFA (google re2) and compare them.
|
||||
|
||||
Submit solution based on a better method.
|
||||
|
||||
NOTE: You could extract the polish surnames list, save it to a file, then commit the file to your repository.
|
||||
NOTE: You may set max_mem to a higher value than the default in re2 library.
|
File diff suppressed because one or more lines are too long
Loading…
Reference in New Issue
Block a user