mathparse 0.2.3__tar.gz → 0.2.4__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {mathparse-0.2.3 → mathparse-0.2.4}/PKG-INFO +1 -1
- {mathparse-0.2.3 → mathparse-0.2.4}/mathparse/__init__.py +1 -1
- {mathparse-0.2.3 → mathparse-0.2.4}/mathparse/mathparse.py +51 -3
- mathparse-0.2.4/mathparse/mathwords.py +1723 -0
- {mathparse-0.2.3 → mathparse-0.2.4}/mathparse.egg-info/PKG-INFO +1 -1
- {mathparse-0.2.3 → mathparse-0.2.4}/tests/test_binary_operations.py +53 -0
- {mathparse-0.2.3 → mathparse-0.2.4}/tests/test_complex_statements.py +14 -0
- mathparse-0.2.4/tests/test_unary_operations.py +138 -0
- {mathparse-0.2.3 → mathparse-0.2.4}/tests/test_utils.py +3 -0
- mathparse-0.2.3/mathparse/mathwords.py +0 -839
- mathparse-0.2.3/tests/test_unary_operations.py +0 -43
- {mathparse-0.2.3 → mathparse-0.2.4}/LICENSE +0 -0
- {mathparse-0.2.3 → mathparse-0.2.4}/README.md +0 -0
- {mathparse-0.2.3 → mathparse-0.2.4}/mathparse.egg-info/SOURCES.txt +0 -0
- {mathparse-0.2.3 → mathparse-0.2.4}/mathparse.egg-info/dependency_links.txt +0 -0
- {mathparse-0.2.3 → mathparse-0.2.4}/mathparse.egg-info/requires.txt +0 -0
- {mathparse-0.2.3 → mathparse-0.2.4}/mathparse.egg-info/top_level.txt +0 -0
- {mathparse-0.2.3 → mathparse-0.2.4}/pyproject.toml +0 -0
- {mathparse-0.2.3 → mathparse-0.2.4}/setup.cfg +0 -0
- {mathparse-0.2.3 → mathparse-0.2.4}/tests/test_language_support.py +0 -0
- {mathparse-0.2.3 → mathparse-0.2.4}/tests/test_replace_word_tokens.py +0 -0
- {mathparse-0.2.3 → mathparse-0.2.4}/tests/test_simplified_chinese.py +0 -0
|
@@ -79,6 +79,41 @@ def is_word(word: str, language: str) -> bool:
|
|
|
79
79
|
return word in words
|
|
80
80
|
|
|
81
81
|
|
|
82
|
+
def create_unicode_word_boundary_pattern(word: str) -> str:
|
|
83
|
+
"""
|
|
84
|
+
Create a regex pattern with Unicode-aware word boundaries.
|
|
85
|
+
|
|
86
|
+
Standard regex \\b word boundaries don't work with non-ASCII characters
|
|
87
|
+
(e.g., Devanagari, Arabic, Hebrew, Chinese, Thai, etc.). This function
|
|
88
|
+
creates a pattern that works across all Unicode scripts.
|
|
89
|
+
|
|
90
|
+
Args:
|
|
91
|
+
word (str): The word to create a boundary pattern for
|
|
92
|
+
|
|
93
|
+
Returns:
|
|
94
|
+
str: A regex pattern string with proper Unicode boundaries
|
|
95
|
+
|
|
96
|
+
Examples:
|
|
97
|
+
>>> create_unicode_word_boundary_pattern("two")
|
|
98
|
+
'(?<![\\w])two(?![\\w])'
|
|
99
|
+
>>> create_unicode_word_boundary_pattern("दो") # Hindi "two"
|
|
100
|
+
'(?:^|(?<=[\\s+\\-*/^()]))दो(?:$|(?=[\\s+\\-*/^()]))'
|
|
101
|
+
"""
|
|
102
|
+
# Check if word contains only ASCII alphanumeric characters
|
|
103
|
+
if word.isascii() and word.replace('-', '').replace("'", '').isalnum():
|
|
104
|
+
# For ASCII words, use standard word boundaries
|
|
105
|
+
return r'\b' + re.escape(word) + r'\b'
|
|
106
|
+
else:
|
|
107
|
+
# For non-ASCII (Unicode) words, use space/operator boundaries
|
|
108
|
+
# This pattern matches the word when it's:
|
|
109
|
+
# - At the start of string OR preceded by whitespace/operator
|
|
110
|
+
# - At the end of string OR followed by whitespace/operator
|
|
111
|
+
escaped_word = re.escape(word)
|
|
112
|
+
# Boundary characters: whitespace, operators, parentheses
|
|
113
|
+
boundary = r'[\s+\-*/^()]'
|
|
114
|
+
return f'(?:^|(?<={boundary})){escaped_word}(?:$|(?={boundary}))'
|
|
115
|
+
|
|
116
|
+
|
|
82
117
|
def find_word_groups(string: str, words: list) -> list:
|
|
83
118
|
"""
|
|
84
119
|
Find matches for words in the format "3 thousand 6 hundred 2".
|
|
@@ -302,9 +337,10 @@ def replace_word_tokens(
|
|
|
302
337
|
|
|
303
338
|
# Replace number words with numeric values
|
|
304
339
|
for number in frozenset(numbers.keys()):
|
|
305
|
-
# Use word boundaries to prevent partial matches
|
|
306
|
-
# (e.g., "nine" in "nineteen")
|
|
307
|
-
|
|
340
|
+
# Use Unicode-aware word boundaries to prevent partial matches
|
|
341
|
+
# (e.g., "nine" in "nineteen") and support non-ASCII scripts
|
|
342
|
+
# (e.g., Devanagari, Arabic, Hebrew, Chinese, etc.)
|
|
343
|
+
pattern = create_unicode_word_boundary_pattern(number)
|
|
308
344
|
if re.search(pattern, string):
|
|
309
345
|
string = re.sub(pattern, str(numbers[number]), string)
|
|
310
346
|
|
|
@@ -403,6 +439,7 @@ def to_postfix(tokens: list) -> list:
|
|
|
403
439
|
Convert a list of evaluatable tokens to postfix format.
|
|
404
440
|
"""
|
|
405
441
|
precedence = {
|
|
442
|
+
'.': 5,
|
|
406
443
|
'/': 4,
|
|
407
444
|
'*': 4,
|
|
408
445
|
'+': 3,
|
|
@@ -499,6 +536,17 @@ def evaluate_postfix(tokens: list) -> Union[int, float, str, Decimal]:
|
|
|
499
536
|
total = 'undefined'
|
|
500
537
|
else:
|
|
501
538
|
total = Decimal(str(a)) / Decimal(str(b))
|
|
539
|
+
elif token == '.':
|
|
540
|
+
# Treat decimal points as a binary operator that combines the
|
|
541
|
+
# integer and fractional part of two numbers
|
|
542
|
+
# Example: 53 . 25 = 53.25
|
|
543
|
+
if b == 0:
|
|
544
|
+
total = Decimal(a)
|
|
545
|
+
else:
|
|
546
|
+
# Count the digits in b to determine the divisor
|
|
547
|
+
digits = len(str(int(b)))
|
|
548
|
+
divisor = 10 ** digits
|
|
549
|
+
total = a + (b / divisor)
|
|
502
550
|
else:
|
|
503
551
|
raise PostfixTokenEvaluationException(
|
|
504
552
|
'Unknown token "{}"'.format(token)
|