mktables: Don't output anything above IV_MAX

This is in preparation for later commits to restrict Unicode code points
to IV_MAX.  No tables are currently output that go this high, so this
change has no current effect.

diff --git a/charclass_invlists.h b/charclass_invlists.h
index ed7bf46..1ae9812 100644 (file)
--- a/charclass_invlists.h
+++ b/charclass_invlists.h
@@ -97454,7 +97454,7 @@ static const U8 WB_table[24][24] = {
  * be0f129691d479aa38646e4ca0ec1ee576ae7f75b0300a5624a7fa862fa8abba lib/unicore/extracted/DLineBreak.txt
  * 92449d354d9f6b6f2f97a292ebb59f6344ffdeb83d120d7d23e569c43ba67cd5 lib/unicore/extracted/DNumType.txt
  * e3a319527153b0c6c0c549b40fc6f3a01a7a0dcd6620784391db25901df3b154 lib/unicore/extracted/DNumValues.txt
- * fd5dda65f76b9209787c5d0bb99f4cde8708c0bf86bcefe344d2d474a0306e28 lib/unicore/mktables
+ * 409910af8e9ad2cba213c70f936a6c716494029a8346e8b55dd44275cc51d35d lib/unicore/mktables
  * 21653d2744fdd071f9ef138c805393901bb9547cf3e777ebf50215a191f986ea lib/unicore/version
  * 913d2f93f3cb6cdf1664db888bf840bc4eb074eef824e082fceda24a9445e60c regen/charset_translations.pl
  * 48418cbf454eb9ef35c73468ed5ef72ad8603490eabe74181ce4fae42ec72579 regen/mk_invlists.pl

diff --git a/lib/unicore/mktables b/lib/unicore/mktables
index 0c8c83c..1386735 100644 (file)
--- a/lib/unicore/mktables
+++ b/lib/unicore/mktables
@@ -1140,17 +1140,16 @@ my $MAX_UNICODE_CODEPOINT_STRING = ($v_version ge v2.0.0)
 my $MAX_UNICODE_CODEPOINT = hex $MAX_UNICODE_CODEPOINT_STRING;
 my $MAX_UNICODE_CODEPOINTS = $MAX_UNICODE_CODEPOINT + 1;
 
-# We work with above-Unicode code points, up to UV_MAX.   But when you get
-# that high, above IV_MAX, some operations don't work, and you can easily get
-# overflow.  Therefore for internal use, we use a much smaller number,
-# translating it to UV_MAX only for output.  The exact number is immaterial
-# (all Unicode code points are treated exactly the same), but the algorithm
-# requires it to be at least 2 * $MAX_UNICODE_CODEPOINTS + 1;
+# We work with above-Unicode code points, up to IV_MAX, but we may want to use
+# sentinels above that number.  Therefore for internal use, we use a much
+# smaller number, translating it to IV_MAX only for output.  The exact number
+# is immaterial (all Unicode code points are treated exactly the same), but
+# the algorithm requires it to be at least 2 * $MAX_UNICODE_CODEPOINTS + 1;
 my $MAX_WORKING_CODEPOINTS= $MAX_UNICODE_CODEPOINT * 8;
 my $MAX_WORKING_CODEPOINT = $MAX_WORKING_CODEPOINTS - 1;
 my $MAX_WORKING_CODEPOINT_STRING = sprintf("%X", $MAX_WORKING_CODEPOINT);
 
-my $MAX_PLATFORM_CODEPOINT = ~0;
+my $MAX_PLATFORM_CODEPOINT = ~0 >> 1;
 
 # Matches legal code point.  4-6 hex numbers, If there are 6, the first
 # two must be 10; if there are 5, the first must not be a 0.  Written this way

diff --git a/regcharclass.h b/regcharclass.h
index 17812c5..6b3e846 100644 (file)
--- a/regcharclass.h
+++ b/regcharclass.h
@@ -1898,7 +1898,7 @@
  * be0f129691d479aa38646e4ca0ec1ee576ae7f75b0300a5624a7fa862fa8abba lib/unicore/extracted/DLineBreak.txt
  * 92449d354d9f6b6f2f97a292ebb59f6344ffdeb83d120d7d23e569c43ba67cd5 lib/unicore/extracted/DNumType.txt
  * e3a319527153b0c6c0c549b40fc6f3a01a7a0dcd6620784391db25901df3b154 lib/unicore/extracted/DNumValues.txt
- * fd5dda65f76b9209787c5d0bb99f4cde8708c0bf86bcefe344d2d474a0306e28 lib/unicore/mktables
+ * 409910af8e9ad2cba213c70f936a6c716494029a8346e8b55dd44275cc51d35d lib/unicore/mktables
  * 21653d2744fdd071f9ef138c805393901bb9547cf3e777ebf50215a191f986ea lib/unicore/version
  * 913d2f93f3cb6cdf1664db888bf840bc4eb074eef824e082fceda24a9445e60c regen/charset_translations.pl
  * 9ea6338945a7d70e5ea4b31ac7856c0b521df96be002e94b4b3b7d31debbf3ab regen/regcharclass.pl