Unicode General Categories
Match a Unicode General Category.
ugc_cased_letter(lo, hi, char_class = TRUE) ugc_close_punctuation(lo, hi, char_class = TRUE) ugc_connector_punctuation(lo, hi, char_class = TRUE) ugc_control(lo, hi, char_class = TRUE) ugc_currency_symbol(lo, hi, char_class = TRUE) ugc_dash_punctuation(lo, hi, char_class = TRUE) ugc_decimal_number(lo, hi, char_class = TRUE) ugc_enclosing_mark(lo, hi, char_class = TRUE) ugc_final_punctuation(lo, hi, char_class = TRUE) ugc_format_control(lo, hi, char_class = TRUE) ugc_initial_punctuation(lo, hi, char_class = TRUE) ugc_letter(lo, hi, char_class = TRUE) ugc_letter_number(lo, hi, char_class = TRUE) ugc_line_separator(lo, hi, char_class = TRUE) ugc_lowercase_letter(lo, hi, char_class = TRUE) ugc_mark(lo, hi, char_class = TRUE) ugc_math_symbol(lo, hi, char_class = TRUE) ugc_modifier_letter(lo, hi, char_class = TRUE) ugc_modifier_symbol(lo, hi, char_class = TRUE) ugc_nonspacing_mark(lo, hi, char_class = TRUE) ugc_number(lo, hi, char_class = TRUE) ugc_open_punctuation(lo, hi, char_class = TRUE) ugc_other(lo, hi, char_class = TRUE) ugc_other_letter(lo, hi, char_class = TRUE) ugc_other_number(lo, hi, char_class = TRUE) ugc_other_punctuation(lo, hi, char_class = TRUE) ugc_other_symbol(lo, hi, char_class = TRUE) ugc_paragraph_separator(lo, hi, char_class = TRUE) ugc_private_use_control(lo, hi, char_class = TRUE) ugc_punctuation(lo, hi, char_class = TRUE) ugc_separator(lo, hi, char_class = TRUE) ugc_space_separator(lo, hi, char_class = TRUE) ugc_spacing_mark(lo, hi, char_class = TRUE) ugc_surrogate_control(lo, hi, char_class = TRUE) ugc_symbol(lo, hi, char_class = TRUE) ugc_titlecase_letter(lo, hi, char_class = TRUE) ugc_unassigned_control(lo, hi, char_class = TRUE) ugc_uppercase_letter(lo, hi, char_class = TRUE) UGC_UPPERCASE_LETTER UGC_LOWERCASE_LETTER UGC_TITLECASE_LETTER UGC_CASED_LETTER UGC_MODIFIER_LETTER UGC_OTHER_LETTER UGC_LETTER UGC_NONSPACING_MARK UGC_SPACING_MARK UGC_ENCLOSING_MARK UGC_MARK UGC_DECIMAL_NUMBER UGC_LETTER_NUMBER UGC_OTHER_NUMBER UGC_NUMBER UGC_CONNECTOR_PUNCTUATION UGC_DASH_PUNCTUATION UGC_OPEN_PUNCTUATION UGC_CLOSE_PUNCTUATION UGC_INITIAL_PUNCTUATION UGC_FINAL_PUNCTUATION UGC_OTHER_PUNCTUATION UGC_PUNCTUATION UGC_MATH_SYMBOL UGC_CURRENCY_SYMBOL UGC_MODIFIER_SYMBOL UGC_OTHER_SYMBOL UGC_SYMBOL UGC_SPACE_SEPARATOR UGC_LINE_SEPARATOR UGC_PARAGRAPH_SEPARATOR UGC_SEPARATOR UGC_CONTROL UGC_FORMAT_CONTROL UGC_SURROGATE_CONTROL UGC_PRIVATE_USE_CONTROL UGC_UNASSIGNED_CONTROL UGC_OTHER
lo |
A non-negative integer. Minimum number of repeats, when grouped. |
hi |
positive integer. Maximum number of repeats, when grouped. |
char_class |
|
An object of class regex (inherits from character) of length 1.
A character vector representing part or all of a regular expression.
Table 12 of the Unicode Standard Annex #44 defines the Unicode General Categories. http://www.unicode.org/reports/tr44
You can see which characters are contained in a category by visiting, e.g., http://www.fileformat.info/info/unicode/category/Nd/list.htm
# Classes
ugc_lowercase_letter()
ugc_decimal_number()
ugc_paragraph_separator()
ugc_currency_symbol()
# With repetition
ugc_nonspacing_mark(3, 6)
ugc_separator(1, Inf)
ugc_dash_punctuation(0, Inf)
# Without a class wrapper
ugc_titlecase_letter(char_class = FALSE)
# Constants
UGC_UPPERCASE_LETTER
UGC_LETTER_NUMBER
UGC_MATH_SYMBOL
UGC_FORMAT_CONTROL
## Not run:
# All the Unicode general categories.
# Not run, since it generates lots of output
ls("package:rebus.unicode", pattern = "^ugc")
## End(Not run)
# Usage
library(rebus.base)
x <- "I exchanged $1000 for \u20ac665.41 and \u00a3243.13."
(rx <- capture(ugc_currency_symbol()) %R%
capture(
ugc_decimal_number(1, Inf) %R%
optional(group("." %R% ugc_decimal_number(2)))
)
)
stringi::stri_match_all_regex(x, rx)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.