[9fans] Fix sam regexp bug with metacharacters in classes

[adr <adr@SDF.ORG>]

The code assumes runes are 16 bits long, not 21, creating faulting
code parsing classes. I.e. '/[\-]' will not match '-'.

This is the same fix already in 9front.

http://adr.freeshell.org/plan9/patches/sam_fix_metachars_on_classes.diff

--- /sys/src/cmd/sam/regexp.c   Tue Apr 23 19:06:01 2013
+++ regexp.c    Tue Nov 23 15:01:18 2021
@@ -53,8 +53,8 @@
  /*
   * Actions and Tokens
   *
- *     0x100xx are operators, value == precedence
- *     0x200xx are tokens, i.e. operands for operators
+ *     0x2000xx are operators, value == precedence
+ *     0x3000xx are tokens, i.e. operands for operators
   */
  enum {
        OPERATOR = Runemask+1,  /* Bitmask of all operators */
@@ -462,7 +462,8 @@
                        exprp++;
                        return '\n';
                }
-               return *exprp++|(Runemax+1);
+               /* add a flag so metacharacters aren't interpreted */
+               return *exprp++|(Runemask+1);
        }
        return *exprp++;
  }
@@ -498,11 +499,12 @@
                        if((c2 = nextrec()) == ']')
                                goto Error;
                        classp[n+0] = Runemax;
-                       classp[n+1] = c1;
-                       classp[n+2] = c2;
+                       /* remove possible flag from nextrec() */
+                       classp[n+1] = c1 & Runemask;
+                       classp[n+2] = c2 & Runemask;
                        n += 3;
                }else
-                       classp[n++] = c1;
+                       classp[n++] = c1 & Runemask;
        }
        classp[n] = 0;
        if(nclass == Nclass){


------------------------------------------
9fans: 9fans
Permalink: https://9fans.topicbox.com/groups/9fans/Tccbdb20b670003a1-M5d4e6bea6c6908b388e51f0c
Delivery options: https://9fans.topicbox.com/groups/9fans/subscription