Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Implemented parsing Roman Numerals #63

Open
wants to merge 11 commits into
base: master
Choose a base branch
from
Open

Implemented parsing Roman Numerals #63

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
386fdd9
Implemented parsing Roman Numerals
AmPhIbIaN26 Apr 10, 2021
81ed627
Revert "Implemented parsing Roman Numerals"
AmPhIbIaN26 Apr 14, 2021
6658bc4
Implemented parsing Roman Numerals
AmPhIbIaN26 Apr 14, 2021
ff64b93
Revert "Implemented parsing Roman Numerals"
AmPhIbIaN26 May 3, 2021
c6285cb
Revert "Revert "Implemented parsing Roman Numerals""
AmPhIbIaN26 May 3, 2021
ce81365
Revert "Implemented parsing Roman Numerals"
AmPhIbIaN26 May 3, 2021
b36483e
Update __init__.py
AmPhIbIaN26 May 3, 2021
be5d4e3
Revert "Update __init__.py"
AmPhIbIaN26 May 3, 2021
8e28343
Revert "Revert "Implemented parsing Roman Numerals""
AmPhIbIaN26 May 3, 2021
9a6fb48
Revert "Revert "Revert "Implemented parsing Roman Numerals"""
AmPhIbIaN26 May 3, 2021
4c127ec
Revert "Revert "Implemented parsing Roman Numerals""
AmPhIbIaN26 May 3, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
44 changes: 44 additions & 0 deletions number_parser/data/rom.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,44 @@
info = {
"UNIT_NUMBERS": {
"i": 1,
"ii": 2,
"iii": 3,
"iv": 5,
"vi": 6,
"vii": 7,
"viii": 8,
"ix": 9
},
"DIRECT_NUMBERS": {
"x": 10,

},
"TENS": {
"xx": 20,
"xxx": 30,
"xl": 40,
"l": 50,
"lx": 60,
"lxx": 70,
"lxxx": 80,
"xc": 90
},
"HUNDREDS": {
"c": 100,
"cc": 200,
"ccc": 300,
"cd": 400,
"d": 500,
"dc": 600,
"dcc": 700,
"dccc": 800,
"cm": 900
},
"BIG_POWERS_OF_TEN": {
"m": 1000,
"mm": 2000,
"mmm": 3000
},
"SKIP_TOKENS": [],
"USE_LONG_SCALE": False
}
12 changes: 11 additions & 1 deletion number_parser/parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
from importlib import import_module
import unicodedata
SENTENCE_SEPARATORS = [".", ","]
SUPPORTED_LANGUAGES = ['en', 'es', 'hi', 'ru']
SUPPORTED_LANGUAGES = ['en', 'es', 'hi', 'ru', 'rom']
RE_BUG_LANGUAGES = ['hi']


Expand Down Expand Up @@ -141,6 +141,8 @@ def _build_number(token_list, lang_data):

def _tokenize(input_string, language):
"""Breaks string on any non-word character."""
if language == 'rom':
return re.split("^(m{0,3})(cm|cd|d?c{0,3})(xc|xl|l?x{0,3})(ix|iv|v?i{0,3})$", input_string.lower())
input_string = input_string.replace('\xad', '')
if language in RE_BUG_LANGUAGES:
return re.split(r'(\s+)', input_string)
Expand Down Expand Up @@ -310,6 +312,14 @@ def parse(input_string, language=None):

tokens = _tokenize(input_string, language)

if language == 'rom':
tokens = _tokenize(input_string, language=None)
for token in tokens:
if re.search("^(m{0,3})(cm|cd|d?c{0,3})(xc|xl|l?x{0,3})(ix|iv|v?i{0,3})$", token.lower()):
tokens[tokens.index(token)] = str(parse_number(token, language='rom'))
final_sentance = ''.join(tokens)
return final_sentance

final_sentence = []
current_sentence = []
tokens_taken = []
Expand Down