cvsuser 01/11/12 20:35:46
Modified: docs strings.pod
include/parrot exceptions.h string.h
t/op string.t
Log:
core.ops - Added ord operator, documentation
string.c - Added string_ord, _string_index (_string_index is a static helper)
Patched string_concat to handle null strings properly.
docs/strings.pod - Description of string_ord
include/parrot/exceptions.h - Added ORD_OUT_OF_STRING exception
include/parrot/string.h - Added string_ord()
t/op/string.t - Added full set of test for ord_i_(s|sc)(_(i|ic))?
string.c contains a bit of documentation explaining the logic behind
_string_index, primarily having to do with multiple encoding formats.
Revision Changes Path
1.6 +13 -0 parrot/docs/strings.pod
Index: strings.pod
===================================================================
RCS file: /cvs/public/parrot/docs/strings.pod,v
retrieving revision 1.5
retrieving revision 1.6
diff -u -w -r1.5 -r1.6
--- strings.pod 2001/10/10 18:21:04 1.5
+++ strings.pod 2001/11/13 04:35:46 1.6
@@ -89,6 +89,19 @@
C<*dest> is a null pointer, a new string structure is created with the
same encoding as C<src>.)
+To retrieve a single character of the string, call
+
+ INTVAL string_ord(STRING* s, INTVAL n)
+
+The result will be returned from the function. It checks for the existence of
+C<s>, and tests for C<n> being out of range. Currently it applies the method
+that perl uses on arrays to handle negative indices. That is to say, negative
+values count backwards from the end of the string. For example, index -1 is
+the last character in the string, -2 is the next-to-last, and so on.
+
+If C<s> is null or C<s> is zero-length, it throws an exception. If C<n> is out
+of range, it also throws an exception.
+
To compare two strings, use:
INTVAL string_compare(STRING* s1, STRING* s2)
1.5 +2 -1 parrot/include/parrot/exceptions.h
Index: exceptions.h
===================================================================
RCS file: /cvs/public/parrot/include/parrot/exceptions.h,v
retrieving revision 1.4
retrieving revision 1.5
diff -u -w -r1.4 -r1.5
--- exceptions.h 2001/10/31 22:51:32 1.4
+++ exceptions.h 2001/11/13 04:35:46 1.5
@@ -1,7 +1,7 @@
/* exceptions.h
* Copyright: (When this is determined...it will go here)
* CVS Info
- * $Id: exceptions.h,v 1.4 2001/10/31 22:51:32 tom Exp $
+ * $Id: exceptions.h,v 1.5 2001/11/13 04:35:46 jgoff Exp $
* Overview:
* define the internal interpreter exceptions
* Data Structure and Algorithms:
@@ -17,6 +17,7 @@
#define NO_REG_FRAMES 1
#define SUBSTR_OUT_OF_STRING 1
+#define ORD_OUT_OF_STRING 1
#define MALFORMED_UTF8 1
#define MALFORMED_UTF16 1
#define MALFORMED_UTF32 1
1.10 +3 -1 parrot/include/parrot/string.h
Index: string.h
===================================================================
RCS file: /cvs/public/parrot/include/parrot/string.h,v
retrieving revision 1.9
retrieving revision 1.10
diff -u -w -r1.9 -r1.10
--- string.h 2001/10/31 22:51:32 1.9
+++ string.h 2001/11/13 04:35:46 1.10
@@ -1,7 +1,7 @@
/* string.h
* Copyright: (When this is determined...it will go here)
* CVS Info
- * $Id: string.h,v 1.9 2001/10/31 22:51:32 tom Exp $
+ * $Id: string.h,v 1.10 2001/11/13 04:35:46 jgoff Exp $
* Overview:
* This is the api header for the string subsystem
* Data Structure and Algorithms:
@@ -45,6 +45,8 @@
/* Declarations of other functions */
INTVAL
string_length(STRING*);
+INTVAL
+string_ord(STRING* s, INTVAL index);
void
string_grow(STRING* s, INTVAL newsize);
void
1.13 +125 -1 parrot/t/op/string.t
Index: string.t
===================================================================
RCS file: /cvs/public/parrot/t/op/string.t,v
retrieving revision 1.12
retrieving revision 1.13
diff -u -w -r1.12 -r1.13
--- string.t 2001/10/16 18:35:04 1.12
+++ string.t 2001/11/13 04:35:46 1.13
@@ -1,6 +1,6 @@
#! perl -w
-use Parrot::Test tests => 24;
+use Parrot::Test tests => 43;
output_is( <<'CODE', <<OUTPUT, "set_s_sc" );
set S4, "JAPH\n"
@@ -127,7 +127,30 @@
length 21
OUTPUT
+output_is( <<'CODE', '', "2-param concat, null onto null" );
+ concat S0,S0
+ end
+CODE
+
+output_is( <<'CODE', <<OUTPUT, '2-param concat, "foo1" onto null' );
+ concat S0,"foo1"
+ print S0
+ print "\n"
+ end
+CODE
+foo1
+OUTPUT
+output_is( <<'CODE', <<OUTPUT, '2-param concat, "foo2" onto null' );
+ set S1,"foo2"
+ concat S0,S1
+ print S0
+ print "\n"
+ end
+CODE
+foo2
+OUTPUT
+
output_is( <<'CODE', <<OUTPUT, "concat" );
set S1, "fish"
set S2, "bone"
@@ -140,6 +163,7 @@
fishbone
OUTPUT
+
output_is(<<"CODE", <<'OUTPUT', "clears");
@{[ set_str_regs( sub {"BOO $_[0]\\n"} ) ]}
clears
@@ -309,7 +333,107 @@
foo
OUTPUT
+output_is(<<'CODE','Cannot get character of empty string','2-param ord, empty
string');
+ ord I0,""
+ print I0
+ end
+CODE
+
+output_is(<<'CODE','Cannot get character of empty string','2-param ord, empty
string register');
+ ord I0,S0
+ print I0
+ end
+CODE
+output_is(<<'CODE','Cannot get character of empty string','3-param ord, empty
string');
+ ord I0,"",0
+ print I0
+ end
+CODE
+
+output_is(<<'CODE','Cannot get character of empty string','3-param ord, empty
string register');
+ ord I0,S0,0
+ print I0
+ end
+CODE
+
+output_is(<<'CODE',ord('a'),'2-param ord, one-character string');
+ ord I0,"a"
+ print I0
+ end
+CODE
+
+output_is(<<'CODE',ord('a'),'2-param ord, one-character string register');
+ set S0,"a"
+ ord I0,S0
+ print I0
+ end
+CODE
+
+output_is(<<'CODE',ord('a'),'3-param ord, one-character string');
+ ord I0,"a",0
+ print I0
+ end
+CODE
+
+output_is(<<'CODE',ord('a'),'3-param ord, one-character string register');
+ set S0,"a"
+ ord I0,S0,0
+ print I0
+ end
+CODE
+
+output_is(<<'CODE',ord('b'),'3-param ord, multi-character string');
+ ord I0,"ab",1
+ print I0
+ end
+CODE
+
+output_is(<<'CODE',ord('b'),'3-param ord, multi-character string register');
+ set S0,"ab"
+ ord I0,S0,1
+ print I0
+ end
+CODE
+
+output_is(<<'CODE', 'Cannot get character past end of string','3-param ord,
multi-character string');
+ ord I0,"ab",2
+ print I0
+ end
+CODE
+
+output_is(<<'CODE', 'Cannot get character past end of string','3-param ord,
multi-character string');
+ set S0,"ab"
+ ord I0,S0,2
+ print I0
+ end
+CODE
+
+output_is(<<'CODE',ord('a'),'3-param ord, one-character string, from end');
+ ord I0,"a",-1
+ print I0
+ end
+CODE
+
+output_is(<<'CODE',ord('a'),'3-param ord, one-character string register, from end');
+ set S0,"a"
+ ord I0,S0,-1
+ print I0
+ end
+CODE
+
+output_is(<<'CODE',ord('b'),'3-param ord, multi-character string, from end');
+ ord I0,"ab",-1
+ print I0
+ end
+CODE
+
+output_is(<<'CODE',ord('b'),'3-param ord, multi-character string register, from
end');
+ set S0,"ab"
+ ord I0,S0,-1
+ print I0
+ end
+CODE
# Set all string registers to values given by &$_[0](reg num)
sub set_str_regs {
