Feature #11735 ยป 0001-Introduce-String-squish-and-String-squish.patch
| string.c | ||
|---|---|---|
|
return str;
|
||
|
}
|
||
|
/*
|
||
|
* call-seq:
|
||
|
* str.squish! -> str
|
||
|
*
|
||
|
* Performs a destructive squish. See String#squish.
|
||
|
*
|
||
|
* str = " foo bar \n \t boo"
|
||
|
* str.squish! # => "foo bar boo"
|
||
|
* str # => "foo bar boo"
|
||
|
*/
|
||
|
static VALUE
|
||
|
rb_str_squish_bang(VALUE str)
|
||
|
{
|
||
|
static const char before_regex_source[] = "\\A[[:space:]]+";
|
||
|
static const char after_regex_source[] = "[[:space:]]+\\z";
|
||
|
static const char between_regex_source[] = "[[:space:]]+";
|
||
|
VALUE before_argv[] = {
|
||
|
rb_reg_new(before_regex_source, sizeof before_regex_source - 1, 0),
|
||
|
rb_str_new_cstr("")
|
||
|
};
|
||
|
VALUE after_argv[] = {
|
||
|
rb_reg_new(after_regex_source, sizeof after_regex_source - 1, 0),
|
||
|
rb_str_new_cstr("")
|
||
|
};
|
||
|
VALUE between_argv[] = {
|
||
|
rb_reg_new(between_regex_source, sizeof between_regex_source - 1, 0),
|
||
|
rb_str_new_cstr(" ")
|
||
|
};
|
||
|
rb_str_gsub_bang(2, before_argv, str);
|
||
|
rb_str_gsub_bang(2, after_argv, str);
|
||
|
rb_str_gsub_bang(2, between_argv, str);
|
||
|
return str;
|
||
|
}
|
||
|
/*
|
||
|
* call-seq:
|
||
|
* str.squish -> str
|
||
|
*
|
||
|
* Returns the string, first removing all whitespace on both ends of the
|
||
|
* string, and then changing remaining consecutive whitespace groups into one
|
||
|
* space each.
|
||
|
*
|
||
|
* Note that it handles both ASCII and Unicode whitespace.
|
||
|
*
|
||
|
* %{ Multi-line
|
||
|
* string }.squish # => "Multi-line string"
|
||
|
* " foo bar \n \t boo".squish # => "foo bar boo"
|
||
|
*/
|
||
|
static VALUE
|
||
|
rb_str_squish(VALUE str)
|
||
|
{
|
||
|
str = rb_str_dup(str);
|
||
|
return rb_str_squish_bang(str);
|
||
|
}
|
||
|
/**********************************************************************
|
||
|
* Document-class: Symbol
|
||
|
*
|
||
| ... | ... | |
|
rb_define_method(rb_cString, "strip", rb_str_strip, 0);
|
||
|
rb_define_method(rb_cString, "lstrip", rb_str_lstrip, 0);
|
||
|
rb_define_method(rb_cString, "rstrip", rb_str_rstrip, 0);
|
||
|
rb_define_method(rb_cString, "squish", rb_str_squish, 0);
|
||
|
rb_define_method(rb_cString, "sub!", rb_str_sub_bang, -1);
|
||
|
rb_define_method(rb_cString, "gsub!", rb_str_gsub_bang, -1);
|
||
| ... | ... | |
|
rb_define_method(rb_cString, "strip!", rb_str_strip_bang, 0);
|
||
|
rb_define_method(rb_cString, "lstrip!", rb_str_lstrip_bang, 0);
|
||
|
rb_define_method(rb_cString, "rstrip!", rb_str_rstrip_bang, 0);
|
||
|
rb_define_method(rb_cString, "squish!", rb_str_squish_bang, 0);
|
||
|
rb_define_method(rb_cString, "tr", rb_str_tr, 2);
|
||
|
rb_define_method(rb_cString, "tr_s", rb_str_tr_s, 2);
|
||
| test/ruby/test_string.rb | ||
|---|---|---|
|
end;
|
||
|
end if [0].pack("l!").bytesize < [nil].pack("p").bytesize
|
||
|
# enable only when string size range is smaller than memory space
|
||
|
def test_string_squish
|
||
|
original = %{\u205f\u3000 A string surrounded by various unicode spaces,
|
||
|
with tabs(\t\t), newlines(\n\n), unicode nextlines(\u0085\u0085) and many spaces( ). \u00a0\u2007}
|
||
|
expected = "A string surrounded by various unicode spaces, " +
|
||
|
"with tabs( ), newlines( ), unicode nextlines( ) and many spaces( )."
|
||
|
# Make sure squish returns what we expect:
|
||
|
assert_equal expected, original.squish
|
||
|
# But doesn't modify the original string:
|
||
|
assert_not_equal expected, original
|
||
|
# Make sure squish! returns what we expect:
|
||
|
assert_equal expected, original.squish!
|
||
|
# And changes the original string:
|
||
|
assert_equal expected, original
|
||
|
end
|
||
|
end
|
||
|
class TestString2 < TestString
|
||