procyberian/emacs
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

'[:graph:]' now excludes whitespace, not just ' '

Browse source 
* doc/lispref/searching.texi (Char Classes):
* lisp/emacs-lisp/rx.el (rx): Document [:graph:] to be [:print:]
sans whitespace (not sans space).
* src/character.c (graphicp): Exclude all Unicode whitespace chars,
not just space.
* src/regex.c (ISGRAPH): Exclude U+00A0 (NO-BREAK SPACE).
This commit is contained in:
Paul Eggert 2015-04-15 23:45:08 -07:00
parent 5161c9ca6a
commit 3074a9fad1
4 changed files with 21 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
doc/lispref/searching.texi
View file

@ -558,7 +558,7 @@ This matches any @acronym{ASCII} control character.
This matches @samp{0} through @samp{9}. Thus, @samp{[-+[:digit:]]}
matches any digit, as well as @samp{+} and @samp{-}.
@item [:graph:]
This matches graphic characters---everything except space,
This matches graphic characters---everything except whitespace,
@acronym{ASCII} and non-@acronym{ASCII} control characters,
surrogates, and codepoints unassigned by Unicode, as indicated by the
Unicode @samp{general-category} property (@pxref{Character
@ -572,7 +572,7 @@ This matches any multibyte character (@pxref{Text Representations}).
@item [:nonascii:]
This matches any non-@acronym{ASCII} character.
@item [:print:]
This matches any printing character---either space, or a graphic
This matches any printing character---either whitespace, or a graphic
character matched by @samp{[:graph:]}.
@item [:punct:]
This matches any punctuation character. (At present, for multibyte

4
lisp/emacs-lisp/rx.el
View file

@ -965,12 +965,12 @@ CHAR
matches space and tab only.
`graphic', `graph'
matches graphic characters--everything except space, ASCII
matches graphic characters--everything except whitespace, ASCII
and non-ASCII control characters, surrogates, and codepoints
unassigned by Unicode.
`printing', `print'
matches space and graphic characters.
matches whitespace and graphic characters.
`alphanumeric', `alnum'
matches alphabetic characters and digits. (For multibyte characters,

25
src/character.c
View file

@ -984,8 +984,7 @@ character is not ASCII nor 8-bit character, an error is signaled. */)
#ifdef emacs
/* Return 'true' if C is an alphabetic character as defined by its
Unicode properties. */
/* Return true if C is an alphabetic character. */
bool
alphabeticp (int c)
{
@ -1008,8 +1007,7 @@ alphabeticp (int c)
|| gen_cat == UNICODE_CATEGORY_Nl);
}
/* Return 'true' if C is an decimal-number character as defined by its
Unicode properties. */
/* Return true if C is a decimal-number character. */
bool
decimalnump (int c)
{
@ -1022,16 +1020,25 @@ decimalnump (int c)
return gen_cat == UNICODE_CATEGORY_Nd;
}
/* Return 'true' if C is a graphic character as defined by its
Unicode properties. */
/* Return true if C is a graphic character. */
bool
graphicp (int c)
{
return c == ' ' || printablep (c);
Lisp_Object category = CHAR_TABLE_REF (Vunicode_category_table, c);
if (! INTEGERP (category))
return false;
EMACS_INT gen_cat = XINT (category);
/* See UTS #18. */
return (!(gen_cat == UNICODE_CATEGORY_Zs /* space separator */
|| gen_cat == UNICODE_CATEGORY_Zl /* line separator */
|| gen_cat == UNICODE_CATEGORY_Zp /* paragraph separator */
|| gen_cat == UNICODE_CATEGORY_Cc /* control */
|| gen_cat == UNICODE_CATEGORY_Cs /* surrogate */
|| gen_cat == UNICODE_CATEGORY_Cn)); /* unassigned */
}
/* Return 'true' if C is a printable character as defined by its
Unicode properties. */
/* Return true if C is a printable character. */
bool
printablep (int c)
{

2
src/regex.c
View file

@ -313,7 +313,7 @@ enum syntaxcode { Swhitespace = 0, Sword = 1, Ssymbol = 2 };
/* The rest must handle multibyte characters. */
# define ISGRAPH(c) (SINGLE_BYTE_CHAR_P (c) \
? (c) > ' ' && !((c) >= 0177 && (c) <= 0237) \
? (c) > ' ' && !((c) >= 0177 && (c) <= 0240) \
: graphicp (c))
# define ISPRINT(c) (SINGLE_BYTE_CHAR_P (c) \