pcre2test: improve binmode

Report parameters for OP_[V]REVERSE, avoid ambiguous back references,
simplify code and update related documentation.

Author: carenas

doc/pcre2pattern.3

@@ -3184,8 +3184,8 @@ For example:
   (?(VERSION>=10.4)yes|no)
 .sp
 This pattern matches "yes" if the PCRE2 version is greater or equal to 10.4, or
-"no" otherwise. The fractional part of the version number may not contain more
-than two digits.
+"no" otherwise. The fractional part of the version number could be ommited and
+may not contain more than two digits.
 .
 .
 .SS "Assertion conditions"

doc/pcre2syntax.3

@@ -627,22 +627,26 @@ following ways:
   (?(condition)yes-pattern)
   (?(condition)yes-pattern|no-pattern)
 .sp
-  (?(n)               absolute reference condition
-  (?(+n)              relative reference condition (PCRE2 extension)
-  (?(-n)              relative reference condition (PCRE2 extension)
-  (?(<name>)          named reference condition (Perl)
-  (?('name')          named reference condition (Perl)
-  (?(name)            named reference condition (PCRE2, deprecated)
-  (?(R)               overall recursion condition
-  (?(Rn)              specific numbered group recursion condition
-  (?(R&name)          specific named group recursion condition
-  (?(DEFINE)          define groups for reference
-  (?(VERSION[>]=n.m)  test PCRE2 version
-  (?(assert)          assertion condition
+  (?(n)                absolute reference condition
+  (?(+n)               relative reference condition (PCRE2 extension)
+  (?(-n)               relative reference condition (PCRE2 extension)
+  (?(<name>)           named reference condition (Perl)
+  (?('name')           named reference condition (Perl)
+  (?(name)             named reference condition (PCRE2, deprecated)
+  (?(R)                overall recursion condition
+  (?(Rn)               specific numbered group recursion condition
+  (?(R&name)           specific named group recursion condition
+  (?(DEFINE)           define groups for reference
+  (?(VERSION[>]=n[.m]) test PCRE2 version
+  (?(assert)           assertion condition
 .sp
 Note the ambiguity of (?(R) and (?(Rn) which might be named reference
 conditions or recursion tests. Such a condition is interpreted as a reference
 condition if the relevant named group exists.
+.sp
+The parts within brackets for the VERSION conditional syntax could be ommited.
+The fractional part of the version number defaults to 0, and can be up to two
+digits long.
 .
 .
 .SH "BACKTRACKING CONTROL"
@@ -708,16 +712,16 @@ there is additional interpretation:
 1. Backslash is an escape character, and the forms described in "ESCAPED
 CHARACTERS" above are recognized. Also:
 .sp
-  \eQ...\eE   can be used to suppress interpretation
-  \el        force the next character to lower case
-  \eu        force the next character to upper case
-  \eL        force subsequent characters to lower case
-  \eU        force subsequent characters to upper case
-  \eu\eL      force next character to upper case, then all lower
-  \el\eU      force next character to lower case, then all upper
-  \eE        end \eL or \eU case forcing
-  \eb        backspace character (note: as in character class in pattern)
-  \ev        vertical tab character (note: not the same as in a pattern)
+  \eQ...\eE can be used to suppress interpretation
+  \el      force the next character to lower case
+  \eu      force the next character to upper case
+  \eL      force subsequent characters to lower case
+  \eU      force subsequent characters to upper case
+  \eu\eL    force next character to upper case, then all lower
+  \el\eU    force next character to lower case, then all upper
+  \eE      end \eL or \eU case forcing
+  \eb      backspace character (note: as in character class in pattern)
+  \ev      vertical tab character (note: not the same as in a pattern)
 .sp
 2. The Python form \eg<n>, where the angle brackets are part of the syntax and
 \fIn\fP is either a group name or a number, is recognized as an alternative way

src/pcre2_internal.h

@@ -1988,7 +1988,8 @@ some cases doesn't actually use these names at all). */
   "Cond",                                                         \
   "SBra", "SBraPos", "SCBra", "SCBraPos",                         \
   "SCond",                                                        \
-  "Capture ref", "Capture dnref", "Cond rec", "Cond dnrec",       \
+  "Capture ref", "Capture ref <",                                 \
+  "Cond recurse", "Cond recurse <",                               \
   "Cond false", "Cond true",                                      \
   "Brazero", "Braminzero", "Braposzero",                          \
   "*MARK", "*PRUNE", "*PRUNE", "*SKIP", "*SKIP",                  \

src/pcre2_printint_inc.h

@@ -734,31 +734,22 @@ for(;;)
     fprintf(f, "%s", OP_names[*code]);
     break;
 
-    case OP_REVERSE:
-    if (print_lengths) fprintf(f, "%3d ", GET2(code, 1));
-      else fprintf(f, "    ");
-    fprintf(f, "%s", OP_names[*code]);
-    break;
-
-    case OP_VREVERSE:
-    if (print_lengths) fprintf(f, "%3d %d ", GET2(code, 1),
-      GET2(code, 1 + IMM2_SIZE));
-    else fprintf(f, "    ");
-    fprintf(f, "%s", OP_names[*code]);
-    break;
-
     case OP_CLOSE:
     fprintf(f, "    %s %d", OP_names[*code], GET2(code, 1));
     break;
 
     case OP_CREF:
-    fprintf(f, "%3d %s", GET2(code,1), OP_names[*code]);
+    case OP_REVERSE:
+    case OP_VREVERSE:
+    fprintf(f, "%3d %s", GET2(code, 1), OP_names[*code]);
+    if (*code == OP_VREVERSE) fprintf(f, " %d", GET2(code, 1 + IMM2_SIZE));
     break;
 
     case OP_DNCREF:
+    case OP_DNRREF:
       {
       PCRE2_SPTR entry = nametable + (GET2(code, 1) * nesize) + IMM2_SIZE;
-      fprintf(f, " %s Capture ref <", flag);
+      fprintf(f, " %s %s", flag, OP_names[*code]);
       print_custring(f, entry);
       fprintf(f, ">%d", GET2(code, 1 + IMM2_SIZE));
       }
@@ -767,26 +758,9 @@ for(;;)
     case OP_RREF:
     c = GET2(code, 1);
     if (c == RREF_ANY)
-      fprintf(f, "    Cond recurse any");
+      fprintf(f, "    %s any", OP_names[*code]);
     else
-      fprintf(f, "    Cond recurse %d", c);
-    break;
-
-    case OP_DNRREF:
-      {
-      PCRE2_SPTR entry = nametable + (GET2(code, 1) * nesize) + IMM2_SIZE;
-      fprintf(f, " %s Cond recurse <", flag);
-      print_custring(f, entry);
-      fprintf(f, ">%d", GET2(code, 1 + IMM2_SIZE));
-      }
-    break;
-
-    case OP_FALSE:
-    fprintf(f, "    Cond false");
-    break;
-
-    case OP_TRUE:
-    fprintf(f, "    Cond true");
+      fprintf(f, "    %s %d", OP_names[*code], c);
     break;
 
     case OP_STARI:
@@ -936,7 +910,7 @@ for(;;)
     flag = "/i";
     /* Fall through */
     case OP_REF:
-    fprintf(f, " %s \\%d", flag, GET2(code,1));
+    fprintf(f, " %s \\g{%d}", flag, GET2(code, 1));
     i = (*code == OP_REFI)? code[1 + IMM2_SIZE] : 0;
     if (i != 0) fprintf(f, " 0x%02x", i);
     ccode = code + OP_lengths[*code];
@@ -1104,10 +1078,6 @@ for(;;)
     extra += code[1];
     break;
 
-    case OP_THEN:
-    fprintf(f, "    %s", OP_names[*code]);
-    break;
-
     case OP_CIRCM:
     case OP_DOLLM:
     flag = "/m";
@@ -1121,7 +1091,7 @@ for(;;)
     }
 
   code += OP_lengths[*code] + extra;
-  fprintf(f, "\n");
+  putc('\n', f);
   }
 }
 

testdata/testinput2

@@ -6146,6 +6146,8 @@ a)"xI
 
 /(?(VERSION=10.3)b)((?<=b).*)/B
 
+/(?(VERSION>=10.3)b)((?<=b).*)/B
+
 /[aA]b[cC]/IB
 
 /[cc]abcd/I