Add short synonyms for Bidi_Control and Bidi_Class

doc/html/pcre2pattern.html

@@ -783,7 +783,7 @@ escape sequences are:
   \P{<i>xx</i>}   a character without the <i>xx</i> property
   \X       a Unicode extended grapheme cluster
 </pre>
-The property names represented by <i>xx</i> above are not case-sensitive, and in 
+The property names represented by <i>xx</i> above are not case-sensitive, and in
 accordance with Unicode's "loose matching" rules, spaces, hyphens, and
 underscores are ignored. There is support for Unicode script names, Unicode
 general category properties, "Any", which matches any character (including
@@ -1072,10 +1072,13 @@ PCRE2_UCP option or by starting the pattern with (*UCP).
 Bi-directional properties for \p and \P
 </b><br>
 <P>
-Two properties relating to bi-directional text are supported:
+Two properties relating to bi-directional text (each with a shorter synonym)
+are supported:
 <pre>
   \p{Bidi_Control}         matches a Bidi control character
+  \p{Bidi_C}               matches a Bidi control character
   \p{Bidi_Class:&#60;class&#62;}   matches a character with the given class
+  \p{BC:&#60;class&#62;}           matches a character with the given class
 </pre>
 The recognized classes are:
 <pre>
@@ -1088,7 +1091,7 @@ The recognized classes are:
   ES          European separator
   ET          European terminator
   FSI         first strong isolate
-  L           left-to-right            
+  L           left-to-right
   LRE         left-to-right embedding
   LRI         left-to-right isolate
   LRO         left-to-right override
@@ -1101,11 +1104,10 @@ The recognized classes are:
   RLI         right-to-left isolate
   RLO         right-to-left override
   S           segment separator
-  WS          which space             
+  WS          which space
 </pre>
-For Bidi_Class, an equals sign may be used instead of a colon. The class names 
+For Bidi_Class, an equals sign may be used instead of a colon. The class names
-are case-insensitive. As for other properties, only the short names are 
+are case-insensitive; only the short names listed above are recognized.
-recognized.
 </P>
 <br><b>
 Extended grapheme clusters
@@ -3902,7 +3904,7 @@ Cambridge, England.
 </P>
 <br><a name="SEC32" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 08 December 2021
+Last updated: 10 December 2021
 <br>
 Copyright &copy; 1997-2021 University of Cambridge.
 <br>

doc/html/pcre2syntax.html

@@ -137,6 +137,11 @@ happening, \s and \w may also match characters with code points in the range
 sequences is changed to use Unicode properties and they match many more
 characters.
 </P>
+<P>
+Property descriptions in \p and \P are matched caselessly; hyphens,
+underscores, and white space are ignored, in accordance with Unicode's "loose
+matching" rules.
+</P>
 <br><a name="SEC5" href="#TOC1">GENERAL CATEGORY PROPERTIES FOR \p and \P</a><br>
 <P>
 <pre>
@@ -367,7 +372,9 @@ Zanabazar_Square.
 <P>
 <pre>
   \p{Bidi_Control}         matches a Bidi control character
+  \p{Bidi_C}               matches a Bidi control character
   \p{Bidi_Class:&#60;class&#62;}   matches a character with the given class
+  \p{BC:&#60;class&#62;}           matches a character with the given class
 </pre>
 The recognized classes are:
 <pre>
@@ -731,7 +738,7 @@ Cambridge, England.
 </P>
 <br><a name="SEC30" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 08 December 2021
+Last updated: 10 December 2021
 <br>
 Copyright &copy; 1997-2021 University of Cambridge.
 <br>

doc/pcre2pattern.3

@@ -1,4 +1,4 @@
-.TH PCRE2PATTERN 3 "08 December 2021" "PCRE2 10.40"
+.TH PCRE2PATTERN 3 "10 December 2021" "PCRE2 10.40"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "PCRE2 REGULAR EXPRESSION DETAILS"
@@ -779,7 +779,7 @@ escape sequences are:
   \eP{\fIxx\fP}   a character without the \fIxx\fP property
   \eX       a Unicode extended grapheme cluster
 .sp
-The property names represented by \fIxx\fP above are not case-sensitive, and in 
+The property names represented by \fIxx\fP above are not case-sensitive, and in
 accordance with Unicode's "loose matching" rules, spaces, hyphens, and
 underscores are ignored. There is support for Unicode script names, Unicode
 general category properties, "Any", which matches any character (including
@@ -1064,10 +1064,13 @@ PCRE2_UCP option or by starting the pattern with (*UCP).
 .SS "Bi-directional properties for \ep and \eP"
 .rs
 .sp
-Two properties relating to bi-directional text are supported:
+Two properties relating to bi-directional text (each with a shorter synonym)
+are supported:
 .sp
   \ep{Bidi_Control}         matches a Bidi control character
+  \ep{Bidi_C}               matches a Bidi control character
   \ep{Bidi_Class:<class>}   matches a character with the given class
+  \ep{BC:<class>}           matches a character with the given class
 .sp
 The recognized classes are:
 .sp
@@ -1080,7 +1083,7 @@ The recognized classes are:
   ES          European separator
   ET          European terminator
   FSI         first strong isolate
-  L           left-to-right            
+  L           left-to-right
   LRE         left-to-right embedding
   LRI         left-to-right isolate
   LRO         left-to-right override
@@ -1093,11 +1096,10 @@ The recognized classes are:
   RLI         right-to-left isolate
   RLO         right-to-left override
   S           segment separator
-  WS          which space             
+  WS          which space
 .sp
-For Bidi_Class, an equals sign may be used instead of a colon. The class names 
+For Bidi_Class, an equals sign may be used instead of a colon. The class names
-are case-insensitive. As for other properties, only the short names are 
+are case-insensitive; only the short names listed above are recognized.
-recognized.
 .
 .
 .SS Extended grapheme clusters
@@ -3950,6 +3952,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 08 December 2021
+Last updated: 10 December 2021
 Copyright (c) 1997-2021 University of Cambridge.
 .fi

doc/pcre2syntax.3

@@ -1,4 +1,4 @@
-.TH PCRE2SYNTAX 3 "08 December 2021" "PCRE2 10.40"
+.TH PCRE2SYNTAX 3 "10 December 2021" "PCRE2 10.40"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "PCRE2 REGULAR EXPRESSION SYNTAX SUMMARY"
@@ -102,6 +102,10 @@ happening, \es and \ew may also match characters with code points in the range
 128-255. If the PCRE2_UCP option is set, the behaviour of these escape
 sequences is changed to use Unicode properties and they match many more
 characters.
+.P
+Property descriptions in \ep and \eP are matched caselessly; hyphens,
+underscores, and white space are ignored, in accordance with Unicode's "loose
+matching" rules.
 .
 .
 .SH "GENERAL CATEGORY PROPERTIES FOR \ep and \eP"
@@ -337,7 +341,9 @@ Zanabazar_Square.
 .rs
 .sp
   \ep{Bidi_Control}         matches a Bidi control character
+  \ep{Bidi_C}               matches a Bidi control character
   \ep{Bidi_Class:<class>}   matches a character with the given class
+  \ep{BC:<class>}           matches a character with the given class
 .sp
 The recognized classes are:
 .sp
@@ -717,6 +723,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 08 December 2021
+Last updated: 10 December 2021
 Copyright (c) 1997-2021 University of Cambridge.
 .fi

src/pcre2_compile.c

@@ -688,6 +688,15 @@ static uint32_t chartypeoffset[] = {
   OP_STAR - OP_STAR,    OP_STARI - OP_STAR,
   OP_NOTSTAR - OP_STAR, OP_NOTSTARI - OP_STAR };
 
+/* Table of synonyms for Unicode properties. Each pair has the synonym first,
+followed by the name that's in the UCD table (lower case, no hyphens,
+underscores, or spaces). */
+
+static const char *prop_synonyms[] = {
+  "bc",       "bidiclass",
+  "bidic",    "bidicontrol"
+};
+
 /* Tables of names of POSIX character classes and their lengths. The names are
 now all in a single string, to reduce the number of relocations when a shared
 library is dynamically loaded. The list of lengths is terminated by a zero
@@ -2101,11 +2110,13 @@ negation. */
 if (c == CHAR_LEFT_CURLY_BRACKET)
   {
   if (ptr >= cb->end_pattern) goto ERROR_RETURN;
+
   if (*ptr == CHAR_CIRCUMFLEX_ACCENT)
     {
     *negptr = TRUE;
     ptr++;
     }
+
   for (i = 0; i < (int)(sizeof(name) / sizeof(PCRE2_UCHAR)) - 1; i++)
     {
     if (ptr >= cb->end_pattern) goto ERROR_RETURN;
@@ -2118,10 +2129,39 @@ if (c == CHAR_LEFT_CURLY_BRACKET)
     }
   if (c != CHAR_RIGHT_CURLY_BRACKET) goto ERROR_RETURN;
   name[i] = 0;
+
+  /* Implement a general synonym feature for class names. */
+
+  if (vptr != NULL) *vptr = 0;   /* Terminate class name */
+
+  bot = 0;
+  top = sizeof(prop_synonyms)/sizeof(char *);
+
+  while (top != bot)
+    {
+    size_t mid = ((top + bot)/2) & (-2);
+    int cf = PRIV(strcmp_c8)(name, prop_synonyms[mid]);
+    if (cf == 0)
+      {
+      const char *s = prop_synonyms[mid+1];
+      size_t slen = strlen(s);
+      if (vptr != NULL)
+        {
+        size_t vlen = name + i - vptr;
+        memmove(name + slen + 1, vptr + 1, (vlen + 1) * sizeof(PCRE2_UCHAR));
+        vptr = name + slen;
+        i = slen + vlen + 1;
+        }
+      for (size_t k = 0; k <= slen; k++) name[k] = s[k];
+      break;
+      }
+
+    if (cf > 0) bot = mid + 2; else top = mid;
+    }
   }
 
-/* Otherwise there is just one following character, which must be an ASCII
+/* If { doesn't follow \p or \P there is just one following character, which
-letter. */
+must be an ASCII letter. */
 
 else if (MAX_255(c) && (cb->ctypes[c] & ctype_letter) != 0)
   {
@@ -2138,7 +2178,6 @@ property names are "bidi<name>". */
 
 if (vptr != NULL)
   {
-  *vptr = 0;   /* Terminate class name */
   if (PRIV(strcmp_c8)(name, "bidiclass") != 0)
     {
     *errorcodeptr = ERR47;

testdata/testinput4

@@ -2507,15 +2507,15 @@
     -->\x{061c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}<--
     -->\x{2066}\x{2067}\x{2068}\x{2069}<--
 
-/\p{bidicontrol}+?/utf
+/\p{bidic}+?/utf
     -->\x{061c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}<--
     -->\x{2066}\x{2067}\x{2068}\x{2069}<--
 
-/\p{bidicontrol}++/utf
+/\p{bidi_control}++/utf
     -->\x{061c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}<--
     -->\x{2066}\x{2067}\x{2068}\x{2069}<--
 
-/[\p{bidi_control}]/utf
+/[\p{bidi_c}]/utf
     -->\x{202c}<--
 
 /[\p{bidicontrol}]+/utf
@@ -2545,7 +2545,7 @@
 /\p{bidi class = al}/utf
     -->\x{061D}<--
 
-/\p{bidi class = al}+/utf
+/\p{bc = al}+/utf
     -->\x{061D}\x{061e}\x{061f}<--
 
 /\p{bidi_class : AL}+?/utf
@@ -2554,7 +2554,7 @@
 /\p{Bidi_Class : AL}++/utf
     -->\x{061D}\x{061e}\x{061f}<--
 
-/\p{bidi class = aN}+/utf
+/\p{b_c = aN}+/utf
     -->\x{061D}\x{0602}\x{0604}\x{061f}<--
 
 /\p{bidi class = B}+/utf

testdata/testoutput4

@@ -4047,19 +4047,19 @@ No match
     -->\x{2066}\x{2067}\x{2068}\x{2069}<--
  0: \x{2066}\x{2067}\x{2068}\x{2069}
 
-/\p{bidicontrol}+?/utf
+/\p{bidic}+?/utf
     -->\x{061c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}<--
  0: \x{61c}
     -->\x{2066}\x{2067}\x{2068}\x{2069}<--
  0: \x{2066}
 
-/\p{bidicontrol}++/utf
+/\p{bidi_control}++/utf
     -->\x{061c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}<--
  0: \x{61c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}
     -->\x{2066}\x{2067}\x{2068}\x{2069}<--
  0: \x{2066}\x{2067}\x{2068}\x{2069}
 
-/[\p{bidi_control}]/utf
+/[\p{bidi_c}]/utf
     -->\x{202c}<--
  0: \x{202c}
 
@@ -4107,7 +4107,7 @@ No match
     -->\x{061D}<--
  0: \x{61d}
 
-/\p{bidi class = al}+/utf
+/\p{bc = al}+/utf
     -->\x{061D}\x{061e}\x{061f}<--
  0: \x{61d}\x{61e}\x{61f}
 
@@ -4119,7 +4119,7 @@ No match
     -->\x{061D}\x{061e}\x{061f}<--
  0: \x{61d}\x{61e}\x{61f}
 
-/\p{bidi class = aN}+/utf
+/\p{b_c = aN}+/utf
     -->\x{061D}\x{0602}\x{0604}\x{061f}<--
  0: \x{602}\x{604}