From: Gisle Aas <gisle@aas.no>
Date: Tue, 27 Mar 2001 11:30:24 +0000 (-0800)
Subject: Re: perl@9359 breaks HTML::Parser
X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=d5ce4a7cd9d16a6d235e1b45a0768034bbdac1f0;p=p5sagit%2Fp5-mst-13.2.git

Re: perl@9359 breaks HTML::Parser
Message-ID: <lrr8zjxb5b.fsf@caliper.ActiveState.com>

Clarify the UTF-8 issues of the API docs.
(Slightly reworded and expanded.)

p4raw-id: //depot/perl@9386
---

diff --git a/pod/perlapi.pod b/pod/perlapi.pod
index aaa9e90..711db4d 100644
--- a/pod/perlapi.pod
+++ b/pod/perlapi.pod
@@ -2179,6 +2179,7 @@ Found in file sv.h
 =item SvPOK_only
 
 Tells an SV that it is a string and disables all other OK bits.
+Will also turn off the UTF8 status.
 
 	void	SvPOK_only(SV* sv)
 
@@ -2187,8 +2188,8 @@ Found in file sv.h
 
 =item SvPOK_only_UTF8
 
-Tells an SV that it is a UTF8 string (do not use frivolously)
-and disables all other OK bits.
+Tells an SV that it is a string and disables all other OK bits,
+and leaves the UTF8 status as it was.
   
 	void	SvPOK_only_UTF8(SV* sv)
 
@@ -2494,7 +2495,8 @@ Found in file sv.h
 
 =item SvUTF8_on
 
-Tells an SV that it is a string and encoded in UTF8.  Do not use frivolously.
+Turn on the UTF8 status of an SV (the data is not changed, just the flag).
+Do not use frivolously.
 
 	void	SvUTF8_on(SV *sv)
 
@@ -2544,7 +2546,8 @@ Found in file sv.c
 =item sv_catpv
 
 Concatenates the string onto the end of the string which is in the SV.
-Handles 'get' magic, but not 'set' magic.  See C<sv_catpv_mg>.
+If the SV has the UTF8 status set, then the bytes appended should be
+valid UTF8.  Handles 'get' magic, but not 'set' magic.  See C<sv_catpv_mg>.
 
 	void	sv_catpv(SV* sv, const char* ptr)
 
@@ -2553,9 +2556,13 @@ Found in file sv.c
 
 =item sv_catpvf
 
-Processes its arguments like C<sprintf> and appends the formatted output
-to an SV.  Handles 'get' magic, but not 'set' magic.  C<SvSETMAGIC()> must
-typically be called after calling this function to handle 'set' magic.
+Processes its arguments like C<sprintf> and appends the formatted
+output to an SV.  If the appended data contains "wide" characters
+(including, but not limited to, SVs with a UTF-8 PV formatted with %s,
+and characters >255 formatted with %c), the original SV might get
+upgraded to UTF-8.  Handles 'get' magic, but not 'set' magic.
+C<SvSETMAGIC()> must typically be called after calling this function
+to handle 'set' magic.
 
 	void	sv_catpvf(SV* sv, const char* pat, ...)
 
@@ -2574,8 +2581,9 @@ Found in file sv.c
 =item sv_catpvn
 
 Concatenates the string onto the end of the string which is in the SV.  The
-C<len> indicates number of bytes to copy.  Handles 'get' magic, but not
-'set' magic.  See C<sv_catpvn_mg>.
+C<len> indicates number of bytes to copy.  If the SV has the UTF8
+status set, then the bytes appended should be valid UTF8.
+Handles 'get' magic, but not 'set' magic.  See C<sv_catpvn_mg>.
 
 	void	sv_catpvn(SV* sv, const char* ptr, STRLEN len)
 
diff --git a/sv.c b/sv.c
index 75b35a8..7e98be6 100644
--- a/sv.c
+++ b/sv.c
@@ -3817,8 +3817,9 @@ Perl_sv_chop(pTHX_ register SV *sv, register char *ptr)	/* like set but assuming
 =for apidoc sv_catpvn
 
 Concatenates the string onto the end of the string which is in the SV.  The
-C<len> indicates number of bytes to copy.  Handles 'get' magic, but not
-'set' magic.  See C<sv_catpvn_mg>.
+C<len> indicates number of bytes to copy.  If the SV has the UTF8
+status set, then the bytes appended should be valid UTF8.
+Handles 'get' magic, but not 'set' magic.  See C<sv_catpvn_mg>.
 
 =cut
 */
@@ -3916,10 +3917,10 @@ Perl_sv_catsv_mg(pTHX_ SV *dsv, register SV *ssv)
 =for apidoc sv_catpv
 
 Concatenates the string onto the end of the string which is in the SV.
-Handles 'get' magic, but not 'set' magic.  See C<sv_catpv_mg>.
+If the SV has the UTF8 status set, then the bytes appended should be
+valid UTF8.  Handles 'get' magic, but not 'set' magic.  See C<sv_catpv_mg>.
 
-=cut
-*/
+=cut */
 
 void
 Perl_sv_catpv(pTHX_ register SV *sv, register const char *ptr)
@@ -6760,12 +6761,15 @@ Perl_sv_catpvf_mg_nocontext(SV *sv, const char* pat, ...)
 /*
 =for apidoc sv_catpvf
 
-Processes its arguments like C<sprintf> and appends the formatted output
-to an SV.  Handles 'get' magic, but not 'set' magic.  C<SvSETMAGIC()> must
-typically be called after calling this function to handle 'set' magic.
+Processes its arguments like C<sprintf> and appends the formatted
+output to an SV.  If the appended data contains "wide" characters
+(including, but not limited to, SVs with a UTF-8 PV formatted with %s,
+and characters >255 formatted with %c), the original SV might get
+upgraded to UTF-8.  Handles 'get' magic, but not 'set' magic.
+C<SvSETMAGIC()> must typically be called after calling this function
+to handle 'set' magic.
 
-=cut
-*/
+=cut */
 
 void
 Perl_sv_catpvf(pTHX_ SV *sv, const char* pat, ...)
diff --git a/sv.h b/sv.h
index 2785f14..ab04b05 100644
--- a/sv.h
+++ b/sv.h
@@ -478,6 +478,7 @@ Unsets the PV status of an SV.
 
 =for apidoc Am|void|SvPOK_only|SV* sv
 Tells an SV that it is a string and disables all other OK bits.
+Will also turn off the UTF8 status.
 
 =for apidoc Am|bool|SvOOK|SV* sv
 Returns a boolean indicating whether the SvIVX is a valid offset value for
@@ -584,14 +585,15 @@ Set the length of the string which is in the SV.  See C<SvCUR>.
 Returns a boolean indicating whether the SV contains UTF-8 encoded data.
 
 =for apidoc Am|void|SvUTF8_on|SV *sv
-Tells an SV that it is a string and encoded in UTF8.  Do not use frivolously.
+Turn on the UTF8 status of an SV (the data is not changed, just the flag).
+Do not use frivolously.
 
 =for apidoc Am|void|SvUTF8_off|SV *sv
 Unsets the UTF8 status of an SV.
 
 =for apidoc Am|void|SvPOK_only_UTF8|SV* sv
-Tells an SV that it is a UTF8 string (do not use frivolously)
-and disables all other OK bits.
+Tells an SV that it is a string and disables all other OK bits,
+and leaves the UTF8 status as it was.
   
 =cut
  */