3 files changed, 56 insertions, 3 deletions

diff --git a/contrib/unaccent/expected/unaccent.out b/contrib/unaccent/expected/unaccent.out
index c1bd7cd897d..ee0ac71a1cc 100644
--- a/contrib/unaccent/expected/unaccent.out
+++ b/contrib/unaccent/expected/unaccent.out
@@ -37,6 +37,18 @@ SELECT unaccent('À');  -- Remove combining diacritical 0x0300
  A
 (1 row)
 
+SELECT unaccent('℃℉'); -- degree signs
+ unaccent 
+----------
+ °C°F
+(1 row)
+
+SELECT unaccent('℗'); -- sound recording copyright
+ unaccent 
+----------
+ (P)
+(1 row)
+
 SELECT unaccent('unaccent', 'foobar');
  unaccent 
 ----------
@@ -67,6 +79,18 @@ SELECT unaccent('unaccent', 'À');
  A
 (1 row)
 
+SELECT unaccent('unaccent', '℃℉');
+ unaccent 
+----------
+ °C°F
+(1 row)
+
+SELECT unaccent('unaccent', '℗');
+ unaccent 
+----------
+ (P)
+(1 row)
+
 SELECT ts_lexize('unaccent', 'foobar');
  ts_lexize 
 -----------
@@ -97,3 +121,23 @@ SELECT ts_lexize('unaccent', 'À');
  {A}
 (1 row)
 
+SELECT ts_lexize('unaccent', '℃℉');
+ ts_lexize 
+-----------
+ {°C°F}
+(1 row)
+
+SELECT ts_lexize('unaccent', '℗');
+ ts_lexize 
+-----------
+ {(P)}
+(1 row)
+
+-- Controversial case.  Black-Letter Capital H (U+210C) is translated by
+-- Latin-ASCII.xml as 'x', but it should be 'H'.
+SELECT unaccent('ℌ');
+ unaccent 
+----------
+ x
+(1 row)
+
diff --git a/contrib/unaccent/generate_unaccent_rules.py b/contrib/unaccent/generate_unaccent_rules.py
index c405e231b39..b4b4c38bebe 100644
--- a/contrib/unaccent/generate_unaccent_rules.py
+++ b/contrib/unaccent/generate_unaccent_rules.py
@@ -134,12 +134,12 @@ def get_plain_letter(codepoint, table):
             return table[codepoint.combining_ids[0]]
 
         # Should not come here
-        assert(False)
+        assert False, 'Codepoint U+%0.2X' % codepoint.id
     elif is_plain_letter(codepoint):
         return codepoint
 
     # Should not come here
-    assert(False)
+    assert False, 'Codepoint U+%0.2X' % codepoint.id
 
 
 def is_ligature(codepoint, table):
@@ -212,7 +212,6 @@ def special_cases():
     # Symbols of "Letterlike Symbols" Unicode Block (U+2100 to U+214F)
     charactersSet.add((0x2103, "\xb0C"))   # DEGREE CELSIUS
     charactersSet.add((0x2109, "\xb0F"))   # DEGREE FAHRENHEIT
-    charactersSet.add((0x2117, "(P)"))     # SOUND RECORDING COPYRIGHT
 
     return charactersSet
 
diff --git a/contrib/unaccent/sql/unaccent.sql b/contrib/unaccent/sql/unaccent.sql
index 2ae097ff2b8..3fc0c706be3 100644
--- a/contrib/unaccent/sql/unaccent.sql
+++ b/contrib/unaccent/sql/unaccent.sql
@@ -10,15 +10,25 @@ SELECT unaccent('ёлка');
 SELECT unaccent('ЁЖИК');
 SELECT unaccent('˃˖˗˜');
 SELECT unaccent('À');  -- Remove combining diacritical 0x0300
+SELECT unaccent('℃℉'); -- degree signs
+SELECT unaccent('℗'); -- sound recording copyright
 
 SELECT unaccent('unaccent', 'foobar');
 SELECT unaccent('unaccent', 'ёлка');
 SELECT unaccent('unaccent', 'ЁЖИК');
 SELECT unaccent('unaccent', '˃˖˗˜');
 SELECT unaccent('unaccent', 'À');
+SELECT unaccent('unaccent', '℃℉');
+SELECT unaccent('unaccent', '℗');
 
 SELECT ts_lexize('unaccent', 'foobar');
 SELECT ts_lexize('unaccent', 'ёлка');
 SELECT ts_lexize('unaccent', 'ЁЖИК');
 SELECT ts_lexize('unaccent', '˃˖˗˜');
 SELECT ts_lexize('unaccent', 'À');
+SELECT ts_lexize('unaccent', '℃℉');
+SELECT ts_lexize('unaccent', '℗');
+
+-- Controversial case.  Black-Letter Capital H (U+210C) is translated by
+-- Latin-ASCII.xml as 'x', but it should be 'H'.
+SELECT unaccent('ℌ');