pcre2test: tighten \x{...} parsing in subject

Eventhough it is documented that invalid escapes will be reported,
the code would fallback in that case and result in a NUL being
generated whenever an incompete \x{ escape was being parsed.

Refactor the code to report the error instead and fix the logic used
for overlong numbers so that the truncation doesn't result in an
unexpected value being used.

There was an old (from PCRE 4.0) test that was affected but which is
no longer relevant, because it could only be triggered with invalid
UTF (which isn't supported), and that was therefore removed as a
result.

Additionally, it was found that the same syntax error was affecting
perltest so correct that as well by reporting syntax errors in the
subject lines.

While at it update related documentation for Perl's compatibility.

doc/pcre2compat.3

@@ -226,9 +226,15 @@ handled by PCRE2, either by the interpreter or the JIT. An example is
 /(?:|(?0)abcd)(?(R)|\ez)/, which matches a sequence of any number of repeated
 "abcd" substrings at the end of the subject.
 .P
-23. From release 10.45, PCRE2 gives an error if \ex is not followed by a 
-hexadecimal digit or a curly bracket. It used to interpret this as the NUL 
-character. Perl still generates NUL, but warns in its warning mode.
+23. Both PCRE2 and Perl error when \ex{ escapes are invalid, but Perl tries to
+recover and prints a warning if the problem was that an invalid hexadecimal
+digit was found, since PCRE2 doesn't have warnings it returns an error instead.
+Additionally, Perl accepts \ex{} and generates NUL unlike PCRE2.
+.P
+24. From release 10.45, PCRE2 gives an error if \ex is not followed by a
+hexadecimal digit or a curly bracket. It used to interpret this as the NUL
+character. Perl still generates NUL, but warns when in warning mode in most
+cases.
 .
 .
 .SH AUTHOR

doc/pcre2test.1

@@ -516,7 +516,7 @@ this makes it possible to construct invalid UTF-8 sequences for testing
 purposes. On the other hand, \ex{hh} is interpreted as a UTF-8 character in
 UTF-8 mode, generating more than one byte if the value is greater than 127.
 When testing the 8-bit library not in UTF-8 mode, \ex{hh} generates one byte
-for values less than 256, and causes an error for greater values.
+for values that could fit on it, and causes an error for greater values.
 .P
 In UTF-16 mode, all 4-digit \ex{hhhh} values are accepted. This makes it
 possible to construct invalid UTF-16 sequences for testing purposes.

perltest.sh

@@ -314,7 +314,13 @@ for (;;)
       }
     else
       {
-      $x = eval "\"$_\"";   # To get escapes processed
+      s/(?<!\\)\\$//;     # Remove pcre2test specific trailing backslash
+      $x = eval "\"$_\""; # To get escapes processed
+      if ($interact && $@)
+        {
+        print STDERR "$@";
+        redo;
+        }
       }
 
     # Empty array for holding results, ensure $REGERROR and $REGMARK are

src/pcre2test.c

@@ -7174,10 +7174,10 @@ while ((c = *p++) != 0)
     break;
 
     case 'x':
+    c = 0;
     if (*p == '{')
       {
       uint8_t *pt = p;
-      c = 0;
 
       /* We used to have "while (isxdigit(*(++pt)))" here, but it fails
       when isxdigit() is a macro that refers to its argument more than
@@ -7187,36 +7187,41 @@ while ((c = *p++) != 0)
       for (pt++; isxdigit(*pt); pt++)
         {
         if (++i == 9)
+          {
           fprintf(outfile, "** Too many hex digits in \\x{...} item; "
                            "using only the first eight.\n");
-        else c = c * 16 + (tolower(*pt) - ((isdigit(*pt))? '0' : 'a' - 10));
+          while (isxdigit(*pt)) pt++;
+          break;
+          }
+        else c = c * 16 + (tolower(*pt) - (isdigit(*pt)? '0' : 'a' - 10));
         }
-      if (*pt == '}')
+      if (i == 0 || *pt != '}')
         {
-        p = pt + 1;
-        break;
+        fprintf(outfile, "** Malformed \\x{ escape\n");
+        return PR_OK;
         }
-      /* Not correct form for \x{...}; fall through */
+      else p = pt + 1;
       }
-
-    /* \x without {} always defines just one byte in 8-bit mode. This
-    allows UTF-8 characters to be constructed byte by byte, and also allows
-    invalid UTF-8 sequences to be made. Just copy the byte in UTF-8 mode.
-    Otherwise, pass it down as data. */
-
-    c = 0;
-    while (i++ < 2 && isxdigit(*p))
+    else
       {
-      c = c * 16 + (tolower(*p) - ((isdigit(*p))? '0' : 'a' - 10));
-      p++;
-      }
+      /* \x without {} always defines just one byte in 8-bit mode. This
+      allows UTF-8 characters to be constructed byte by byte, and also allows
+      invalid UTF-8 sequences to be made. Just copy the byte in UTF-8 mode.
+      Otherwise, pass it down as data. */
+
+      while (i++ < 2 && isxdigit(*p))
+        {
+        c = c * 16 + (tolower(*p) - (isdigit(*p)? '0' : 'a' - 10));
+        p++;
+        }
 #if defined SUPPORT_PCRE2_8
-    if (utf && (test_mode == PCRE8_MODE))
-      {
-      *q8++ = c;
-      continue;
-      }
+      if (utf && (test_mode == PCRE8_MODE))
+        {
+        *q8++ = c;
+        continue;
+        }
 #endif
+      }
     break;
 
     case 0:     /* \ followed by EOF allows for an empty line */
@@ -7309,10 +7314,7 @@ while ((c = *p++) != 0)
     }
 #endif
 #ifdef SUPPORT_PCRE2_32
-  if (test_mode == PCRE32_MODE)
-    {
-    *q32++ = c;
-    }
+  if (test_mode == PCRE32_MODE) *q32++ = c;
 #endif
   }
 

testdata/testinput10

@@ -187,9 +187,6 @@
     \x{c0}
     \x{f0}
 
-/Ā{3,4}/IB,utf
-  \x{100}\x{100}\x{100}\x{100\x{100}
-
 /(\x{100}+|x)/IB,utf
 
 /(\x{100}*a|x)/IB,utf

testdata/testinput12

@@ -56,9 +56,6 @@
     \x{c0}
     \x{f0}
 
-/Ā{3,4}/IB,utf
-  \x{100}\x{100}\x{100}\x{100\x{100}
-
 /(\x{100}+|x)/IB,utf
 
 /(\x{100}*a|x)/IB,utf

testdata/testoutput10

@@ -492,22 +492,6 @@ No match
     \x{f0}
 No match
 
-/Ā{3,4}/IB,utf
-------------------------------------------------------------------
-        Bra
-        \x{100}{3}
-        \x{100}?+
-        Ket
-        End
-------------------------------------------------------------------
-Capture group count = 0
-Options: utf
-First code unit = \xc4
-Last code unit = \x80
-Subject length lower bound = 3
-  \x{100}\x{100}\x{100}\x{100\x{100}
- 0: \x{100}\x{100}\x{100}
-
 /(\x{100}+|x)/IB,utf
 ------------------------------------------------------------------
         Bra

testdata/testoutput12-16

@@ -273,22 +273,6 @@ No match
     \x{f0}
 No match
 
-/Ā{3,4}/IB,utf
-------------------------------------------------------------------
-        Bra
-        \x{100}{3}
-        \x{100}?+
-        Ket
-        End
-------------------------------------------------------------------
-Capture group count = 0
-Options: utf
-First code unit = \x{100}
-Last code unit = \x{100}
-Subject length lower bound = 3
-  \x{100}\x{100}\x{100}\x{100\x{100}
- 0: \x{100}\x{100}\x{100}
-
 /(\x{100}+|x)/IB,utf
 ------------------------------------------------------------------
         Bra

testdata/testoutput12-32

@@ -268,22 +268,6 @@ No match
     \x{f0}
 No match
 
-/Ā{3,4}/IB,utf
-------------------------------------------------------------------
-        Bra
-        \x{100}{3}
-        \x{100}?+
-        Ket
-        End
-------------------------------------------------------------------
-Capture group count = 0
-Options: utf
-First code unit = \x{100}
-Last code unit = \x{100}
-Subject length lower bound = 3
-  \x{100}\x{100}\x{100}\x{100\x{100}
- 0: \x{100}\x{100}\x{100}
-
 /(\x{100}+|x)/IB,utf
 ------------------------------------------------------------------
         Bra