Re: A (but copied many) typo of char-mapping tables

2021-07-22 Thread Peter Eisentraut

On 16.07.21 10:02, Kyotaro Horiguchi wrote:

While I looked into a .map file in src/backend/utils/mb/Unicode, I
notice of a typo in it.

  > static const pg_mb_radix_tree euc_jp_from_unicode_tree =
  > {
  > ..
  >   0x, /* offset of table for 1-byte inputs */
  > ...
  >   0x0040, /* offset of table for 2-byte inputs */
  > ...
  >   0x02c3, /* offset of table for 3-byte inputs */
  > ...
!>   0x, /* offset of table for 3-byte inputs */
  >   0x00, /* b4_1_lower */
  >   0x00, /* b4_1_upper */
  > ...
  > };

Yeah, the line above prefixed by '!' is apparently a typo of "4-byte
inputs", which comes from a typo in convutils.pm.


fixed, thanks




A (but copied many) typo of char-mapping tables

2021-07-16 Thread Kyotaro Horiguchi
While I looked into a .map file in src/backend/utils/mb/Unicode, I
notice of a typo in it.

 > static const pg_mb_radix_tree euc_jp_from_unicode_tree =
 > {
 > ..
 >   0x, /* offset of table for 1-byte inputs */
 > ...
 >   0x0040, /* offset of table for 2-byte inputs */
 > ...
 >   0x02c3, /* offset of table for 3-byte inputs */
 > ...
!>   0x, /* offset of table for 3-byte inputs */
 >   0x00, /* b4_1_lower */
 >   0x00, /* b4_1_upper */
 > ...
 > };

Yeah, the line above prefixed by '!' is apparently a typo of "4-byte
inputs", which comes from a typo in convutils.pm.

Fortunately make maintainer-clean; make all in the directory results
in no other differences so we can apply the attached patch to fix the
all propagated typos.

I don't think no backpatch is needed.

regards.

-- 
Kyotaro Horiguchi
NTT Open Source Software Center
diff --git a/src/backend/utils/mb/Unicode/big5_to_utf8.map b/src/backend/utils/mb/Unicode/big5_to_utf8.map
index aa417bc9c8..b8332fb958 100644
--- a/src/backend/utils/mb/Unicode/big5_to_utf8.map
+++ b/src/backend/utils/mb/Unicode/big5_to_utf8.map
@@ -26,7 +26,7 @@ static const pg_mb_radix_tree big5_to_unicode_tree =
   0x00, /* b3_3_lower */
   0x00, /* b3_3_upper */
 
-  0x, /* offset of table for 3-byte inputs */
+  0x, /* offset of table for 4-byte inputs */
   0x00, /* b4_1_lower */
   0x00, /* b4_1_upper */
   0x00, /* b4_2_lower */
diff --git a/src/backend/utils/mb/Unicode/convutils.pm b/src/backend/utils/mb/Unicode/convutils.pm
index 5ad38514be..1155d8bb14 100644
--- a/src/backend/utils/mb/Unicode/convutils.pm
+++ b/src/backend/utils/mb/Unicode/convutils.pm
@@ -579,7 +579,7 @@ sub print_radix_table
 	printf $out "  0x%02x, /* b3_3_lower */\n", $b3_3_lower;
 	printf $out "  0x%02x, /* b3_3_upper */\n", $b3_3_upper;
 	printf $out "\n";
-	printf $out "  0x%04x, /* offset of table for 3-byte inputs */\n",
+	printf $out "  0x%04x, /* offset of table for 4-byte inputs */\n",
 	  $b4root;
 	printf $out "  0x%02x, /* b4_1_lower */\n", $b4_1_lower;
 	printf $out "  0x%02x, /* b4_1_upper */\n", $b4_1_upper;
diff --git a/src/backend/utils/mb/Unicode/euc_cn_to_utf8.map b/src/backend/utils/mb/Unicode/euc_cn_to_utf8.map
index 3801e08ef5..f8503d30c3 100644
--- a/src/backend/utils/mb/Unicode/euc_cn_to_utf8.map
+++ b/src/backend/utils/mb/Unicode/euc_cn_to_utf8.map
@@ -26,7 +26,7 @@ static const pg_mb_radix_tree euc_cn_to_unicode_tree =
   0x00, /* b3_3_lower */
   0x00, /* b3_3_upper */
 
-  0x, /* offset of table for 3-byte inputs */
+  0x, /* offset of table for 4-byte inputs */
   0x00, /* b4_1_lower */
   0x00, /* b4_1_upper */
   0x00, /* b4_2_lower */
diff --git a/src/backend/utils/mb/Unicode/euc_jis_2004_to_utf8.map b/src/backend/utils/mb/Unicode/euc_jis_2004_to_utf8.map
index d2da4a383b..4b6d4e0d42 100644
--- a/src/backend/utils/mb/Unicode/euc_jis_2004_to_utf8.map
+++ b/src/backend/utils/mb/Unicode/euc_jis_2004_to_utf8.map
@@ -26,7 +26,7 @@ static const pg_mb_radix_tree euc_jis_2004_to_unicode_tree =
   0xa1, /* b3_3_lower */
   0xfe, /* b3_3_upper */
 
-  0x, /* offset of table for 3-byte inputs */
+  0x, /* offset of table for 4-byte inputs */
   0x00, /* b4_1_lower */
   0x00, /* b4_1_upper */
   0x00, /* b4_2_lower */
diff --git a/src/backend/utils/mb/Unicode/euc_jp_to_utf8.map b/src/backend/utils/mb/Unicode/euc_jp_to_utf8.map
index 96b79a58a1..ee23de2c8f 100644
--- a/src/backend/utils/mb/Unicode/euc_jp_to_utf8.map
+++ b/src/backend/utils/mb/Unicode/euc_jp_to_utf8.map
@@ -26,7 +26,7 @@ static const pg_mb_radix_tree euc_jp_to_unicode_tree =
   0xa1, /* b3_3_lower */
   0xfe, /* b3_3_upper */
 
-  0x, /* offset of table for 3-byte inputs */
+  0x, /* offset of table for 4-byte inputs */
   0x00, /* b4_1_lower */
   0x00, /* b4_1_upper */
   0x00, /* b4_2_lower */
diff --git a/src/backend/utils/mb/Unicode/euc_kr_to_utf8.map b/src/backend/utils/mb/Unicode/euc_kr_to_utf8.map
index bf1fc4a98b..5d6bcc53ae 100644
--- a/src/backend/utils/mb/Unicode/euc_kr_to_utf8.map
+++ b/src/backend/utils/mb/Unicode/euc_kr_to_utf8.map
@@ -26,7 +26,7 @@ static const pg_mb_radix_tree euc_kr_to_unicode_tree =
   0x00, /* b3_3_lower */
   0x00, /* b3_3_upper */
 
-  0x, /* offset of table for 3-byte inputs */
+  0x, /* offset of table for 4-byte inputs */
   0x00, /* b4_1_lower */
   0x00, /* b4_1_upper */
   0x00, /* b4_2_lower */
diff --git a/src/backend/utils/mb/Unicode/euc_tw_to_utf8.map b/src/backend/utils/mb/Unicode/euc_tw_to_utf8.map
index 22af269924..5a1774617f 100644
--- a/src/backend/utils/mb/Unicode/euc_tw_to_utf8.map
+++ b/src/backend/utils/mb/Unicode/euc_tw_to_utf8.map
@@ -26,7 +26,7 @@ static const pg_mb_radix_tree euc_tw_to_unicode_tree =
   0x00, /* b3_3_lower */
   0x00, /* b3_3_upper */
 
-  0x1899, /* offset of table for 3-byte inputs */
+  0x1899, /* offset of table for 4-byte inputs */
   0x8e, /* b4_1_lower */
   0x8e, /* b4_1_upper */
   0xa1, /* b4_2_lower */
diff --git a/src/backend/utils/mb/Unicode/gb18030_to_utf8.map b/src/backend/