),
),
),
(
"dollars",
(
re.compile(r"\$[0-9]{1,}\.?[0-9]{0,}[mbkMBK]?"),
lambda m: dollars_to_string(m.group()),
),
),
("percent", (re.compile(r"\%"), lambda m: " percent")),
(
"fractions",
(
re.compile(r"\b[0-9]\s?\/\s?[0-9]\b"),
lambda m: fraction_to_string(m.group()),
),
),
(
"plural_numbers",
(
re.compile(r"\b[0-9]{1,}s\b"),
lambda m: plural_numbers_to_string(m.group()),
),
),
(
"numbers",
(
re.compile(r"[0-9\.]{1,}"),
lambda m: " " + digits_to_string(m.group()) + " ",
),
)
),
("acronyms", (re.compile(r"\b(([A-Z]){1,}[.]?){2,}\b"), lambda m: " ".join(m.group().lower().replace(".", "")))),
("dashes", (re.compile(r"\-[0-9]\b"), lambda m: "negative " + m.group()[1:])),
("negatives", (re.compile(r" \- "), lambda m: "")),
("positives", (re.compile(r"\+"), lambda m: " plus ")),
("ordinals", (re.compile(r"[0-9]{1,}(st|nd|rd|th)"), lambda m: ordinal_to_string(m.group()))),
(
"many_dollars", (
re.compile(r"\$([0-9]{1,}\.?[0-9]{0,})\s(billion|million|trillion)"),
lambda m: " ".join([digits_to_string(m.groups()[0]), m.groups()[1], "dollars"])
)
),
("dollars", (re.compile(r"\$[0-9]{1,}\.?[0-9]{0,}[mbMB]?"), lambda m: dollars_to_string(m.group()))),
("percent", (re.compile(r"\%"), lambda m: " percent")),
("fractions", (re.compile(r"\b[0-9]\s?\/\s[0-9]\b"), lambda m: fraction_to_string(m.group()))),
("plural_numbers", (re.compile(r"\b[0-9]{1,}s\b"), lambda m: plural_numbers_to_string(m.group()))),
("numbers", (re.compile(r"[0-9\.]{1,}"), lambda m: " " + digits_to_string(m.group()) + " ")),
("apostrophes", (re.compile(r"\'"), lambda m: " \'")),
]
)
def remove_special_chars(line, chars_to_replace):
"remove a set of special chars"
for char_to_replace in chars_to_replace:
line = line.replace(char_to_replace, ' ')
return line
def remove_double_spaces(line):