Change 16556: EBCDIC: make t/op/pat #242 and 243 finally succeed.

[Jarkko Hietaniemi]

Change 16556 by jhi@alpha on 2002/05/12 15:29:36

        EBCDIC: make t/op/pat #242 and 243 finally succeed.

Affected files ...

.... //depot/perl/pod/perlebcdic.pod#17 edit
.... //depot/perl/regcomp.c#305 edit

Differences ...

==== //depot/perl/pod/perlebcdic.pod#17 (text) ====
Index: perl/pod/perlebcdic.pod
--- perl/pod/perlebcdic.pod#16~15317~   Tue Mar 19 05:56:27 2002
+++ perl/pod/perlebcdic.pod     Sun May 12 08:29:36 2002
@@ -837,7 +837,11 @@
 [A-Z] and [a-z] have been especially coded to not pick up gap 
 characters.  For example, characters such as E<ocirc> C<o WITH CIRCUMFLEX> 
 that lie between I and J would not be matched by the 
-regular expression range C</[H-K]/>.  
+regular expression range C</[H-K]/>.  This works in
+the other direction, too, if either of the range end points is
+explicitly numeric: C<[\x89-\x91]> will match C<\x8e>, even
+though C<\x89> is C<i> and C<\x91 > is C<j>, and C<\x8e>
+is a gap character from the alphabetic viewpoint.
 
 If you do want to match the alphabet gap characters in a single octet 
 regular expression try matching the hex or octal code such 

==== //depot/perl/regcomp.c#305 (text) ====
Index: perl/regcomp.c
--- perl/regcomp.c#304~16231~   Sat Apr 27 14:56:22 2002
+++ perl/regcomp.c      Sun May 12 08:29:36 2002
@@ -3523,6 +3523,9 @@
     UV n;
     bool optimize_invert   = TRUE;
     AV* unicode_alternate  = 0;
+#ifdef EBCDIC
+    UV literal_endpoint = 0;
+#endif
 
     ret = reganode(pRExC_state, ANYOF, 0);
 
@@ -3685,6 +3688,10 @@
                break;
            }
        } /* end of \blah */
+#ifdef EBCDIC
+       else
+           literal_endpoint++;
+#endif
 
        if (namedclass > OOB_NAMEDCLASS) { /* this is a named class \blah */
 
@@ -4087,8 +4094,11 @@
                IV ceilvalue = value < 256 ? value : 255;
 
 #ifdef EBCDIC
-               if ((isLOWER(prevvalue) && isLOWER(ceilvalue)) ||
-                   (isUPPER(prevvalue) && isUPPER(ceilvalue)))
+               /* In EBCDIC [\x89-\x91] should include
+                * the \x8e but [i-j] should not. */
+               if (literal_endpoint == 2 &&
+                   ((isLOWER(prevvalue) && isLOWER(ceilvalue)) ||
+                    (isUPPER(prevvalue) && isUPPER(ceilvalue))))
                {
                    if (isLOWER(prevvalue)) {
                        for (i = prevvalue; i <= ceilvalue; i++)
@@ -4168,6 +4178,9 @@
                    }
                }
            }
+#ifdef EBCDIC
+           literal_endpoint = 0;
+#endif
         }
 
        range = 0; /* this range (if it was one) is done now */
End of Patch.