Move data for PL_InBitmap to charclass_invlists.h

khwilliamson · khwilliamson · commit ffffbf0d2b86 · 2019-11-29T12:01:03.000-07:00
This makes it consistent with the other inversion lists for this sort of thing, and finishes the fix for GH #17154
diff --git a/charclass_invlists.h b/charclass_invlists.h
@@ -6,6 +6,22 @@
 
 /* See the generating file for comments */
 
+/* This gives the number of code points that can be in the bitmap of an ANYOF
+ * node.  The shift number must currently be one of: 8..12.  It can't be less
+ * than 8 (256) because some code relies on it being at least that.  Above 12
+ * (4096), and you start running into warnings that some data structure widths
+ * have been exceeded, though the test suite as of this writing still passes
+ * for up through 16, which is as high as anyone would ever want to go,
+ * encompassing all of the Unicode BMP, and thus including all the economically
+ * important world scripts.  At 12 most of them are: including Arabic,
+ * Cyrillic, Greek, Hebrew, Indian subcontinent, Latin, and Thai; but not Han,
+ * Japanese, nor Korean.  (The regarglen structure in regnodes.h is a U8, and
+ * the trie types TRIEC and AHOCORASICKC are larger than U8 for shift values
+ * above 12.)  Be sure to benchmark before changing, as larger sizes do
+ * significantly slow down the test suite */
+
+#define NUM_ANYOF_CODE_POINTS   (1 << 8)
+
 
 #if (defined(PERL_IN_REGCOMP_C) && ! defined(PERL_IN_XSUB_RE))
 
@@ -29368,6 +29384,15 @@ static const GCB_enum _Perl_GCB_invmap[] = {  /* for EBCDIC 037 */
 
 #if (defined(PERL_IN_REGCOMP_C) && ! defined(PERL_IN_XSUB_RE))
 
+static const UV _Perl_InBitmap_invlist[] = {  /* for all charsets */
+	2,	/* Number of elements */
+	148565664, /* Version and data structure type */
+	0,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0x0,
+	0x100
+};
+
 #  if 'A' == 65 /* ASCII/Latin1 */
 
 static const UV _Perl_IVCF_invlist[] = {  /* for ASCII/Latin1 */
@@ -395305,5 +395330,5 @@ static const U8 WB_table[23][23] = {
  * a712c758275b460d18fa77a26ed3589689bb3f69dcc1ea99b913e32db92a5cd2 lib/unicore/version
  * 2680b9254eb236c5c090f11b149605043e8c8433661b96efc4a42fb4709342a5 regen/charset_translations.pl
  * 03e51b0f07beebd5da62ab943899aa4934eee1f792fa27c1fb638c33bf4ac6ea regen/mk_PL_charclass.pl
- * 61ea8132bb9ea5c637609e2d026b0b85ce17d6bec544c2f08ce411e6f65e8386 regen/mk_invlists.pl
+ * eeb419293bc4fed3c653e3f41c9b7a889019e2134dc892b7bf669ccdcbeb869b regen/mk_invlists.pl
  * ex: set ro: */
diff --git a/lib/unicore/uni_keywords.pl b/lib/unicore/uni_keywords.pl
@@ -1265,5 +1265,5 @@
 # a712c758275b460d18fa77a26ed3589689bb3f69dcc1ea99b913e32db92a5cd2 lib/unicore/version
 # 2680b9254eb236c5c090f11b149605043e8c8433661b96efc4a42fb4709342a5 regen/charset_translations.pl
 # 03e51b0f07beebd5da62ab943899aa4934eee1f792fa27c1fb638c33bf4ac6ea regen/mk_PL_charclass.pl
-# 61ea8132bb9ea5c637609e2d026b0b85ce17d6bec544c2f08ce411e6f65e8386 regen/mk_invlists.pl
+# eeb419293bc4fed3c653e3f41c9b7a889019e2134dc892b7bf669ccdcbeb869b regen/mk_invlists.pl
 # ex: set ro:
diff --git a/regcomp.c b/regcomp.c
@@ -7368,28 +7368,6 @@ Perl_re_op_compile(pTHX_ SV ** const patternp, int pat_count,
 
     DEBUG_r(if (!PL_colorset) reginitcolors());
 
-    /* Initialize these here instead of as-needed, as is quick and avoids
-     * having to test them each time otherwise */
-    if (! PL_InBitmap) {
-#ifdef DEBUGGING
-        char * dump_len_string;
-#endif
-
-        /* This is calculated here, because the Perl program that generates the
-         * static global ones doesn't currently have access to
-         * NUM_ANYOF_CODE_POINTS */
-	PL_InBitmap = _new_invlist(2);
-	PL_InBitmap = _add_range_to_invlist(PL_InBitmap, 0,
-                                                    NUM_ANYOF_CODE_POINTS - 1);
-#ifdef DEBUGGING
-        dump_len_string = PerlEnv_getenv("PERL_DUMP_RE_MAX_LEN");
-        if (   ! dump_len_string
-            || ! grok_atoUV(dump_len_string, (UV *)&PL_dump_re_max_len, NULL))
-        {
-            PL_dump_re_max_len = 60;    /* A reasonable default */
-        }
-#endif
-    }
 
     pRExC_state->warn_text = NULL;
     pRExC_state->unlexed_names = NULL;
@@ -22020,6 +21998,17 @@ Perl_init_uniprops(pTHX)
 {
     dVAR;
 
+#ifdef DEBUGGING
+    char * dump_len_string;
+
+    dump_len_string = PerlEnv_getenv("PERL_DUMP_RE_MAX_LEN");
+    if (   ! dump_len_string
+        || ! grok_atoUV(dump_len_string, (UV *)&PL_dump_re_max_len, NULL))
+    {
+        PL_dump_re_max_len = 60;    /* A reasonable default */
+    }
+#endif
+
     PL_user_def_props = newHV();
 
 #ifdef USE_ITHREADS
@@ -22071,6 +22060,7 @@ Perl_init_uniprops(pTHX)
     PL_LB_invlist = _new_invlist_C_array(_Perl_LB_invlist);
     PL_SCX_invlist = _new_invlist_C_array(_Perl_SCX_invlist);
 
+    PL_InBitmap = _new_invlist_C_array(_Perl_InBitmap_invlist);
     PL_AboveLatin1 = _new_invlist_C_array(AboveLatin1_invlist);
     PL_Latin1 = _new_invlist_C_array(Latin1_invlist);
     PL_UpperLatin1 = _new_invlist_C_array(UpperLatin1_invlist);
diff --git a/regcomp.h b/regcomp.h
@@ -183,21 +183,6 @@ struct regnode_2 {
     U16 arg2;
 };
 
-/* This give the number of code points that can be in the bitmap of an ANYOF
- * node.  The shift number must currently be one of: 8..12.  It can't be less
- * than 8 (256) because some code relies on it being at least that.  Above 12
- * (4096), and you start running into warnings that some data structure widths
- * have been exceeded, though the test suite as of this writing still passes
- * for up through 16, which is as high as anyone would ever want to go,
- * encompassing all of the Unicode BMP, and thus including all the economically
- * important world scripts.  At 12 most of them are: including Arabic,
- * Cyrillic, Greek, Hebrew, Indian subcontinent, Latin, and Thai; but not Han,
- * Japanese, nor Korean.  (The regarglen structure in regnodes.h is a U8, and
- * the trie types TRIEC and AHOCORASICKC are larger than U8 for shift values
- * above 12.)  Be sure to benchmark before changing, as larger sizes do
- * significantly slow down the test suite */
-#define NUM_ANYOF_CODE_POINTS   (1 << 8)
-
 #define ANYOF_BITMAP_SIZE	(NUM_ANYOF_CODE_POINTS / 8)   /* 8 bits/Byte */
 
 /* Note that these form structs which are supersets of the next smaller one, by
diff --git a/regen/mk_invlists.pl b/regen/mk_invlists.pl
@@ -61,6 +61,29 @@
 
 print $out_fh "/* See the generating file for comments */\n\n";
 
+print $out_fh <<'EOF';
+/* This gives the number of code points that can be in the bitmap of an ANYOF
+ * node.  The shift number must currently be one of: 8..12.  It can't be less
+ * than 8 (256) because some code relies on it being at least that.  Above 12
+ * (4096), and you start running into warnings that some data structure widths
+ * have been exceeded, though the test suite as of this writing still passes
+ * for up through 16, which is as high as anyone would ever want to go,
+ * encompassing all of the Unicode BMP, and thus including all the economically
+ * important world scripts.  At 12 most of them are: including Arabic,
+ * Cyrillic, Greek, Hebrew, Indian subcontinent, Latin, and Thai; but not Han,
+ * Japanese, nor Korean.  (The regarglen structure in regnodes.h is a U8, and
+ * the trie types TRIEC and AHOCORASICKC are larger than U8 for shift values
+ * above 12.)  Be sure to benchmark before changing, as larger sizes do
+ * significantly slow down the test suite */
+
+EOF
+
+my $num_anyof_code_points = '(1 << 8)';
+
+print $out_fh "#define NUM_ANYOF_CODE_POINTS   $num_anyof_code_points\n\n";
+
+$num_anyof_code_points = eval $num_anyof_code_points;
+
 # enums that should be made public
 my %public_enums = (
                     _Perl_SCX => 1
@@ -1125,6 +1148,13 @@ sub _Perl_CCC_non0_non230 {
     return \@return;
 }
 
+sub _Perl_InBitmap {
+    my @return;
+    push @return, $_ for 0 .. $num_anyof_code_points - 1;
+    @return = mk_invlist_from_sorted_cp_list(\@return);
+    return \@return;
+}
+
 sub output_table_common {
 
     # Common subroutine to actually output the generated rules table.
@@ -2353,6 +2383,7 @@ ($)
                     Case_Folding
                     &_Perl_IVCF
                     &_Perl_CCC_non0_non230
+                    &_Perl_InBitmap
                 );
                 # NOTE that the convention is that extra enum values come
                 # after the property name, separated by commas, with the enums
diff --git a/uni_keywords.h b/uni_keywords.h
@@ -7288,6 +7288,6 @@ MPH_VALt match_uniprop( const unsigned char * const key, const U16 key_len ) {
  * a712c758275b460d18fa77a26ed3589689bb3f69dcc1ea99b913e32db92a5cd2 lib/unicore/version
  * 2680b9254eb236c5c090f11b149605043e8c8433661b96efc4a42fb4709342a5 regen/charset_translations.pl
  * 03e51b0f07beebd5da62ab943899aa4934eee1f792fa27c1fb638c33bf4ac6ea regen/mk_PL_charclass.pl
- * 61ea8132bb9ea5c637609e2d026b0b85ce17d6bec544c2f08ce411e6f65e8386 regen/mk_invlists.pl
+ * eeb419293bc4fed3c653e3f41c9b7a889019e2134dc892b7bf669ccdcbeb869b regen/mk_invlists.pl
  * c56b78df81e0f96632246052d71580b212546ca02ba4075158965e11d892f21e regen/mph.pl
  * ex: set ro: */
