/\p{InFoo} should only match blocks, or be user-defined

For a property \p{Block=Foo}, we allow the synonym  \p{InFoo} as
documented variously, including perluniprops, even though this usage is
discouraged, as a new Unicode release used in a new version of Perl
could cause the synonym to no longer work.

Prior to this commit, we erroneously allowed the synonym for other
properties, such as \p{InKana} or \p{InS}.

diff --git a/charclass_invlists.h b/charclass_invlists.h
index 566d22f..2028430 100644 (file)
--- a/charclass_invlists.h
+++ b/charclass_invlists.h
@@ -395301,7 +395301,7 @@ static const U8 WB_table[23][23] = {
  * 78e2600e24fa7d5ab62117de50b382f8b31b08401c37a0782c38dacb340b64e7 lib/unicore/extracted/DLineBreak.txt
  * 1bde4ad73e271c6349fbd1972e54f38bba5cc1900c28f678e79b9e8909b31793 lib/unicore/extracted/DNumType.txt
  * 6278722699123f3890e4b1cc42011e96d8960e4958a3b93484361530983d2611 lib/unicore/extracted/DNumValues.txt
- * b3d90fc23817ea4e33e9a90107c0a6c7b23314efd5712905ed172624d5524693 lib/unicore/mktables
+ * a53648677d262457dda0b22efba8820d2a45ca6ebae01f8c73d30db380eb83b5 lib/unicore/mktables
  * a712c758275b460d18fa77a26ed3589689bb3f69dcc1ea99b913e32db92a5cd2 lib/unicore/version
  * 2680b9254eb236c5c090f11b149605043e8c8433661b96efc4a42fb4709342a5 regen/charset_translations.pl
  * 03e51b0f07beebd5da62ab943899aa4934eee1f792fa27c1fb638c33bf4ac6ea regen/mk_PL_charclass.pl

diff --git a/lib/unicore/mktables b/lib/unicore/mktables
index 9860bf7..368794d 100644 (file)
--- a/lib/unicore/mktables
+++ b/lib/unicore/mktables
@@ -19133,6 +19133,7 @@ Test_GCB("1100 $nobreak 1161");  # Bug #70940
 Expect(0, 0x2028, '\p{Print}', ""); # Bug # 71722
 Expect(0, 0x2029, '\p{Print}', ""); # Bug # 71722
 Expect(1, 0xFF10, '\p{XDigit}', ""); # Bug # 71726
+Error('\p{InKana}');    # 'Kana' is not a block so InKana shouldn't compile
 
 # Make sure this gets tested; it was not part of the official test suite at
 # the time this was added.  Note that this is as it would appear in the

diff --git a/lib/unicore/uni_keywords.pl b/lib/unicore/uni_keywords.pl
index 22fd8c6..5c2f2a9 100644 (file)
--- a/lib/unicore/uni_keywords.pl
+++ b/lib/unicore/uni_keywords.pl
@@ -1261,7 +1261,7 @@
 # 78e2600e24fa7d5ab62117de50b382f8b31b08401c37a0782c38dacb340b64e7 lib/unicore/extracted/DLineBreak.txt
 # 1bde4ad73e271c6349fbd1972e54f38bba5cc1900c28f678e79b9e8909b31793 lib/unicore/extracted/DNumType.txt
 # 6278722699123f3890e4b1cc42011e96d8960e4958a3b93484361530983d2611 lib/unicore/extracted/DNumValues.txt
-# b3d90fc23817ea4e33e9a90107c0a6c7b23314efd5712905ed172624d5524693 lib/unicore/mktables
+# a53648677d262457dda0b22efba8820d2a45ca6ebae01f8c73d30db380eb83b5 lib/unicore/mktables
 # a712c758275b460d18fa77a26ed3589689bb3f69dcc1ea99b913e32db92a5cd2 lib/unicore/version
 # 2680b9254eb236c5c090f11b149605043e8c8433661b96efc4a42fb4709342a5 regen/charset_translations.pl
 # 03e51b0f07beebd5da62ab943899aa4934eee1f792fa27c1fb638c33bf4ac6ea regen/mk_PL_charclass.pl

diff --git a/regcharclass.h b/regcharclass.h
index 39d3a4b..cf25342 100644 (file)
--- a/regcharclass.h
+++ b/regcharclass.h
@@ -1901,7 +1901,7 @@
  * 78e2600e24fa7d5ab62117de50b382f8b31b08401c37a0782c38dacb340b64e7 lib/unicore/extracted/DLineBreak.txt
  * 1bde4ad73e271c6349fbd1972e54f38bba5cc1900c28f678e79b9e8909b31793 lib/unicore/extracted/DNumType.txt
  * 6278722699123f3890e4b1cc42011e96d8960e4958a3b93484361530983d2611 lib/unicore/extracted/DNumValues.txt
- * b3d90fc23817ea4e33e9a90107c0a6c7b23314efd5712905ed172624d5524693 lib/unicore/mktables
+ * a53648677d262457dda0b22efba8820d2a45ca6ebae01f8c73d30db380eb83b5 lib/unicore/mktables
  * a712c758275b460d18fa77a26ed3589689bb3f69dcc1ea99b913e32db92a5cd2 lib/unicore/version
  * 2680b9254eb236c5c090f11b149605043e8c8433661b96efc4a42fb4709342a5 regen/charset_translations.pl
  * 830144f6afdd047b009754ffa06134397268f6638837fe85283483eb0cfdd558 regen/regcharclass.pl

diff --git a/regcomp.c b/regcomp.c
index 8125ce0..5068a0a 100644 (file)
--- a/regcomp.c
+++ b/regcomp.c
@@ -22574,8 +22574,7 @@ Perl_parse_uniprop_string(pTHX_
     int slash_pos  = -1;    /* Where the '/' is found, or negative if none */
     int table_index = 0;    /* The entry number for this property in the table
                                of all Unicode property names */
-    bool starts_with_In_or_Is = FALSE;  /* ? Does the name start with 'In' or
-                                             'Is' */
+    bool starts_with_Is = FALSE;  /* ? Does the name start with 'Is' */
     Size_t lookup_offset = 0;   /* Used to ignore the first few characters of
                                    the normalized name in certain situations */
     Size_t non_pkg_begin = 0;   /* Offset of first byte in 'name' that isn't
@@ -23053,7 +23052,11 @@ Perl_parse_uniprop_string(pTHX_
         &&  name[non_pkg_begin+0] == 'I'
         && (name[non_pkg_begin+1] == 'n' || name[non_pkg_begin+1] == 's'))
     {
-        starts_with_In_or_Is = TRUE;
+        /* Names that start with In have different characterstics than those
+         * that start with Is */
+        if (name[non_pkg_begin+1] == 's') {
+            starts_with_Is = TRUE;
+        }
     }
     else {
         could_be_user_defined = FALSE;
@@ -23392,8 +23395,11 @@ Perl_parse_uniprop_string(pTHX_
     /* If it didn't find the property ... */
     if (table_index == 0) {
 
-        /* Try again stripping off any initial 'In' or 'Is' */
-        if (starts_with_In_or_Is) {
+        /* Try again stripping off any initial 'Is'.  This is because we
+         * promise that an initial Is is optional.  The same isn't true of
+         * names that start with 'In'.  Those can match only blocks, and the
+         * lookup table already has those accounted for. */
+        if (starts_with_Is) {
             lookup_name += 2;
             lookup_len -= 2;
             equals_pos -= 2;

diff --git a/uni_keywords.h b/uni_keywords.h
index 6eebad3..d0d20e0 100644 (file)
--- a/uni_keywords.h
+++ b/uni_keywords.h
@@ -7284,7 +7284,7 @@ MPH_VALt match_uniprop( const unsigned char * const key, const U16 key_len ) {
  * 78e2600e24fa7d5ab62117de50b382f8b31b08401c37a0782c38dacb340b64e7 lib/unicore/extracted/DLineBreak.txt
  * 1bde4ad73e271c6349fbd1972e54f38bba5cc1900c28f678e79b9e8909b31793 lib/unicore/extracted/DNumType.txt
  * 6278722699123f3890e4b1cc42011e96d8960e4958a3b93484361530983d2611 lib/unicore/extracted/DNumValues.txt
- * b3d90fc23817ea4e33e9a90107c0a6c7b23314efd5712905ed172624d5524693 lib/unicore/mktables
+ * a53648677d262457dda0b22efba8820d2a45ca6ebae01f8c73d30db380eb83b5 lib/unicore/mktables
  * a712c758275b460d18fa77a26ed3589689bb3f69dcc1ea99b913e32db92a5cd2 lib/unicore/version
  * 2680b9254eb236c5c090f11b149605043e8c8433661b96efc4a42fb4709342a5 regen/charset_translations.pl
  * 03e51b0f07beebd5da62ab943899aa4934eee1f792fa27c1fb638c33bf4ac6ea regen/mk_PL_charclass.pl