Change 31455 by [EMAIL PROTECTED] on 2007/06/24 15:46:40
s/\bunicode\b/Unicode/; # For everything not dual life
Affected files ...
... //depot/perl/dump.c#269 edit
... //depot/perl/ext/Data/Dumper/Dumper.pm#48 edit
... //depot/perl/pod/perlapi.pod#297 edit
... //depot/perl/pod/perldiag.pod#473 edit
... //depot/perl/pod/perlhack.pod#129 edit
... //depot/perl/pod/perlpacktut.pod#15 edit
... //depot/perl/pod/perlre.pod#131 edit
... //depot/perl/pod/perlretut.pod#42 edit
... //depot/perl/pod/perlunicode.pod#140 edit
... //depot/perl/regcomp.c#595 edit
... //depot/perl/regcomp.h#127 edit
... //depot/perl/regexec.c#543 edit
... //depot/perl/utf8.c#301 edit
... //depot/perl/vms/vms.c#201 edit
Differences ...
==== //depot/perl/dump.c#269 (text) ====
Index: perl/dump.c
--- perl/dump.c#268~31412~ 2007-06-18 01:27:59.000000000 -0700
+++ perl/dump.c 2007-06-24 08:46:40.000000000 -0700
@@ -175,9 +175,9 @@
Normally the SV will be cleared before the escaped string is prepared,
but when PERL_PV_ESCAPE_NOCLEAR is set this will not occur.
-If PERL_PV_ESCAPE_UNI is set then the input string is treated as unicode,
+If PERL_PV_ESCAPE_UNI is set then the input string is treated as Unicode,
if PERL_PV_ESCAPE_UNI_DETECT is set then the input string is scanned
-using C<is_utf8_string()> to determine if it is unicode.
+using C<is_utf8_string()> to determine if it is Unicode.
If PERL_PV_ESCAPE_ALL is set then all input chars will be output
using C<\x01F1> style escapes, otherwise only chars above 255 will be
@@ -214,7 +214,7 @@
STRLEN wrote = 0; /* chars written so far */
STRLEN chsize = 0; /* size of data to be written */
STRLEN readsize = 1; /* size of data just read */
- bool isuni= flags & PERL_PV_ESCAPE_UNI ? 1 : 0; /* is this unicode */
+ bool isuni= flags & PERL_PV_ESCAPE_UNI ? 1 : 0; /* is this Unicode */
const char *pv = str;
const char * const end = pv + count; /* end of string */
octbuf[0] = esc;
==== //depot/perl/ext/Data/Dumper/Dumper.pm#48 (text) ====
Index: perl/ext/Data/Dumper/Dumper.pm
--- perl/ext/Data/Dumper/Dumper.pm#47~30656~ 2007-03-21 03:24:52.000000000
-0700
+++ perl/ext/Data/Dumper/Dumper.pm 2007-06-24 08:46:40.000000000 -0700
@@ -9,7 +9,7 @@
package Data::Dumper;
-$VERSION = '2.121_12';
+$VERSION = '2.121_13';
#$| = 1;
@@ -498,7 +498,7 @@
}
else { # string
if ($s->{useqq} or $val =~ tr/\0-\377//c) {
- # Fall back to qq if there's unicode
+ # Fall back to qq if there's Unicode
$out .= qquote($val, $s->{useqq});
}
else {
==== //depot/perl/pod/perlapi.pod#297 (text+w) ====
Index: perl/pod/perlapi.pod
--- perl/pod/perlapi.pod#296~31409~ 2007-06-18 00:39:35.000000000 -0700
+++ perl/pod/perlapi.pod 2007-06-24 08:46:40.000000000 -0700
@@ -848,9 +848,9 @@
Normally the SV will be cleared before the escaped string is prepared,
but when PERL_PV_ESCAPE_NOCLEAR is set this will not occur.
-If PERL_PV_ESCAPE_UNI is set then the input string is treated as unicode,
+If PERL_PV_ESCAPE_UNI is set then the input string is treated as Unicode,
if PERL_PV_ESCAPE_UNI_DETECT is set then the input string is scanned
-using C<is_utf8_string()> to determine if it is unicode.
+using C<is_utf8_string()> to determine if it is Unicode.
If PERL_PV_ESCAPE_ALL is set then all input chars will be output
using C<\x01F1> style escapes, otherwise only chars above 255 will be
@@ -6771,7 +6771,7 @@
X<utf8n_to_uvuni>
Bottom level UTF-8 decode routine.
-Returns the unicode code point value of the first character in the string C<s>
+Returns the Unicode code point value of the first character in the string C<s>
which is assumed to be in UTF-8 encoding and no longer than C<curlen>;
C<retlen> will be set to the length, in bytes, of that character.
==== //depot/perl/pod/perldiag.pod#473 (text) ====
Index: perl/pod/perldiag.pod
--- perl/pod/perldiag.pod#472~31333~ 2007-06-05 03:10:33.000000000 -0700
+++ perl/pod/perldiag.pod 2007-06-24 08:46:40.000000000 -0700
@@ -1881,7 +1881,7 @@
=item Ignoring %s in character class in regex; marked by <-- HERE in m/%s/
-(W) Named unicode character escapes (\N{...}) may return multi-char
+(W) Named Unicode character escapes (\N{...}) may return multi-char
or zero length sequences. When such an escape is used in a character class
its behaviour is not well defined. Check that the correct escape has
been used, and the correct charname handler is in scope.
==== //depot/perl/pod/perlhack.pod#129 (text) ====
Index: perl/pod/perlhack.pod
--- perl/pod/perlhack.pod#128~31433~ 2007-06-21 01:12:09.000000000 -0700
+++ perl/pod/perlhack.pod 2007-06-24 08:46:40.000000000 -0700
@@ -1925,7 +1925,7 @@
explanation of is() and other testing functions).
is( "1.20.300.4000", sprintf "%vd", pack("U*",1,20,300,4000),
- "U* produces unicode" );
+ "U* produces Unicode" );
Now we'll test that we got that space-at-the-beginning business right:
@@ -1936,7 +1936,7 @@
the first active format:
isnt( v1.20.300.4000, sprintf "%vd", pack("C0U*",1,20,300,4000),
- "U* not first isn't unicode" );
+ "U* not first isn't Unicode" );
Mustn't forget to change the number of tests which appears at the top,
or else the automated tester will get confused. This will either look
==== //depot/perl/pod/perlpacktut.pod#15 (text) ====
Index: perl/pod/perlpacktut.pod
--- perl/pod/perlpacktut.pod#14~30688~ 2007-03-22 07:45:36.000000000 -0700
+++ perl/pod/perlpacktut.pod 2007-06-24 08:46:40.000000000 -0700
@@ -660,7 +660,7 @@
Please note: in the general case, you're better off using
Encode::decode_utf8 to decode a UTF-8 encoded byte string to a Perl
-unicode string, and Encode::encode_utf8 to encode a Perl unicode string
+Unicode string, and Encode::encode_utf8 to encode a Perl Unicode string
to UTF-8 bytes. These functions provide means of handling invalid byte
sequences and generally have a friendlier interface.
==== //depot/perl/pod/perlre.pod#131 (text) ====
Index: perl/pod/perlre.pod
--- perl/pod/perlre.pod#130~31325~ 2007-06-01 02:14:24.000000000 -0700
+++ perl/pod/perlre.pod 2007-06-24 08:46:40.000000000 -0700
@@ -261,7 +261,7 @@
optionally be wrapped in curly brackets for safer parsing.
\g{name} Named backreference
\k<name> Named backreference
- \N{name} Named unicode character, or unicode escape
+ \N{name} Named Unicode character, or Unicode escape
\x12 Hexadecimal escape sequence
\x{1234} Long hexadecimal escape sequence
\K Keep the stuff left of the \K, don't include it in $&
==== //depot/perl/pod/perlretut.pod#42 (text) ====
Index: perl/pod/perlretut.pod
--- perl/pod/perlretut.pod#41~30493~ 2007-03-07 05:23:23.000000000 -0800
+++ perl/pod/perlretut.pod 2007-06-24 08:46:40.000000000 -0700
@@ -1841,7 +1841,7 @@
With the advent of 5.6.0, Perl regexps can handle more than just the
standard ASCII character set. Perl now supports I<Unicode>, a standard
for representing the alphabets from virtually all of the world's written
-languages, and a host of symbols. Perl's text strings are unicode strings, so
+languages, and a host of symbols. Perl's text strings are Unicode strings, so
they can contain characters with a value (codepoint or character number) higher
than 255
@@ -1890,7 +1890,7 @@
lib/perl5/X.X.X/unicore directory (where X.X.X is the perl
version number as it is installed on your system).
-The answer to requirement 2), as of 5.6.0, is that a regexp uses unicode
+The answer to requirement 2), as of 5.6.0, is that a regexp uses Unicode
characters. Internally, this is encoded to bytes using either UTF-8 or a
native 8 bit encoding, depending on the history of the string, but
conceptually it is a sequence of characters, not bytes. See
==== //depot/perl/pod/perlunicode.pod#140 (text) ====
Index: perl/pod/perlunicode.pod
--- perl/pod/perlunicode.pod#139~30493~ 2007-03-07 05:23:23.000000000 -0800
+++ perl/pod/perlunicode.pod 2007-06-24 08:46:40.000000000 -0700
@@ -53,7 +53,7 @@
=item C<use encoding> needed to upgrade non-Latin-1 byte strings
-By default, there is a fundamental asymmetry in Perl's unicode model:
+By default, there is a fundamental asymmetry in Perl's Unicode model:
implicit upgrading from byte strings to Unicode strings assumes that
they were encoded in I<ISO 8859-1 (Latin-1)>, but Unicode strings are
downgraded with UTF-8 encoding. This happens because the first 256
==== //depot/perl/regcomp.c#595 (text) ====
Index: perl/regcomp.c
--- perl/regcomp.c#594~31352~ 2007-06-07 09:09:54.000000000 -0700
+++ perl/regcomp.c 2007-06-24 08:46:40.000000000 -0700
@@ -1356,7 +1356,7 @@
have unique chars.
We use an array of integers to represent the character codes 0..255
- (trie->charmap) and we use a an HV* to store unicode characters. We use
the
+ (trie->charmap) and we use a an HV* to store Unicode characters. We use
the
native representation of the character value as the key and IV's for the
coded index.
@@ -4185,7 +4185,7 @@
return(NULL);
}
if (RExC_utf8 && !RExC_orig_utf8) {
- /* It's possible to write a regexp in ascii that represents unicode
+ /* It's possible to write a regexp in ascii that represents Unicode
codepoints outside of the byte range, such as via \x{100}. If we
detect such a sequence we have to convert the entire pattern to utf8
and then recompile, as our sizing calculation will have been based
@@ -6438,7 +6438,7 @@
/* RExC_parse points at the beginning brace,
endbrace points at the last */
if ( name[0]=='U' && name[1]=='+' ) {
- /* its a "unicode hex" notation {U+89AB} */
+ /* its a "Unicode hex" notation {U+89AB} */
I32 fl = PERL_SCAN_ALLOW_UNDERSCORES
| PERL_SCAN_DISALLOW_PREFIX
| (SIZE_ONLY ? PERL_SCAN_SILENT_ILLDIGIT : 0);
@@ -7147,7 +7147,7 @@
case 'h': case 'H': /* HORIZWS */
case 'k': case 'K': /* named backref, keep marker */
case 'N': /* named char sequence */
- case 'p': case 'P': /* unicode property */
+ case 'p': case 'P': /* Unicode property */
case 'R': /* LNBREAK */
case 's': case 'S': /* space class */
case 'v': case 'V': /* VERTWS */
==== //depot/perl/regcomp.h#127 (text) ====
Index: perl/regcomp.h
--- perl/regcomp.h#126~31341~ 2007-06-06 07:42:01.000000000 -0700
+++ perl/regcomp.h 2007-06-24 08:46:40.000000000 -0700
@@ -492,7 +492,7 @@
* n - Root of op tree for (?{EVAL}) item
* o - Start op for (?{EVAL}) item
* p - Pad for (?{EVAL}) item
- * s - swash for unicode-style character class, and the multicharacter
+ * s - swash for Unicode-style character class, and the multicharacter
* strings resulting from casefolding the single-character entries
* in the character class
* t - trie struct
==== //depot/perl/regexec.c#543 (text) ====
Index: perl/regexec.c
--- perl/regexec.c#542~31417~ 2007-06-18 08:10:32.000000000 -0700
+++ perl/regexec.c 2007-06-24 08:46:40.000000000 -0700
@@ -1481,8 +1481,8 @@
U8 **points; /* map of where we were in the input string
when reading a given char. For ASCII this
is unnecessary overhead as the relationship
- is always 1:1, but for unicode, especially
- case folded unicode this is not true. */
+ is always 1:1, but for Unicode, especially
+ case folded Unicode this is not true. */
U8 foldbuf[ UTF8_MAXBYTES_CASE + 1 ];
U8 *bitmap=NULL;
==== //depot/perl/utf8.c#301 (text) ====
Index: perl/utf8.c
--- perl/utf8.c#300~31252~ 2007-05-21 12:57:24.000000000 -0700
+++ perl/utf8.c 2007-06-24 08:46:40.000000000 -0700
@@ -378,7 +378,7 @@
=for apidoc A|UV|utf8n_to_uvuni|const U8 *s|STRLEN curlen|STRLEN *retlen|U32
flags
Bottom level UTF-8 decode routine.
-Returns the unicode code point value of the first character in the string C<s>
+Returns the Unicode code point value of the first character in the string C<s>
which is assumed to be in UTF-8 encoding and no longer than C<curlen>;
C<retlen> will be set to the length, in bytes, of that character.
==== //depot/perl/vms/vms.c#201 (text) ====
Index: perl/vms/vms.c
--- perl/vms/vms.c#200~31421~ 2007-06-19 05:29:32.000000000 -0700
+++ perl/vms/vms.c 2007-06-24 08:46:40.000000000 -0700
@@ -419,7 +419,7 @@
}
}
- /* High bit set, but not a unicode character! */
+ /* High bit set, but not a Unicode character! */
/* Non printing DECMCS or ISO Latin-1 character? */
if (*inspec <= 0x9F) {
@@ -6110,7 +6110,7 @@
}
if ((*cp2 == '^')) {
/* EFS file escape, pass the next character as is */
- /* Fix me: HEX encoding for UNICODE not implemented */
+ /* Fix me: HEX encoding for Unicode not implemented */
cp2++;
}
else if ( *cp2 == '.') {
@@ -6125,7 +6125,7 @@
for (; cp2 <= dirend; cp2++) {
if ((*cp2 == '^')) {
/* EFS file escape, pass the next character as is */
- /* Fix me: HEX encoding for UNICODE not implemented */
+ /* Fix me: HEX encoding for Unicode not implemented */
*(cp1++) = *(++cp2);
/* An escaped dot stays as is -- don't convert to slash */
if (*cp2 == '.') cp2++;
@@ -9021,7 +9021,7 @@
if (dd->flags & PERL_VMSDIR_M_UNIXSPECS) {
/* Translate the encoded characters. */
- /* Fixme: unicode handling could result in embedded 0 characters */
+ /* Fixme: Unicode handling could result in embedded 0 characters */
if (strchr(dd->entry.d_name, '^') != NULL) {
char new_name[256];
char * q;
@@ -9035,7 +9035,7 @@
/* fix-me */
/* if outchars_added > 1, then this is a wide file
specification */
/* Wide file specifications need to be passed in Perl */
- /* counted strings apparently with a unicode flag */
+ /* counted strings apparently with a Unicode flag */
}
*q = 0;
strcpy(dd->entry.d_name, new_name);
@@ -12408,7 +12408,7 @@
vms_debug_on_exception = 0;
}
- /* Create VTF-7 filenames from UNICODE instead of UTF-8 */
+ /* Create VTF-7 filenames from Unicode instead of UTF-8 */
vms_vtf7_filenames = 0;
status = sys_trnlnm("PERL_VMS_VTF7_FILENAMES", val_str, sizeof(val_str));
if ($VMS_STATUS_SUCCESS(status)) {
End of Patch.
