Add simple codepoint redirections to unaccent.rules.

macdice · macdice · commit 18501841bcb4 · 2024-07-05T15:25:31.000+12:00
Previously we searched for code points where the Unicode data file listed an equivalent combining character sequence that added accents. Some codepoints redirect to a single other codepoint, instead of doing any combining. We can follow those references recursively to get the answer. Per bug report #18362, which reported missing Ancient Greek characters. Specifically, precomposed characters with oxia (from the polytonic accent system used for old Greek) just point to precomposed characters with tonos (from the monotonic accent system for modern Greek), and we have to follow the extra hop to find out that they are composed with an acute accent. Besides those, the new rule also: * pulls in a lot of 'Mathematical Alphanumeric Symbols', which are copies of the Latin and Greek alphabets and numbers rendered in different typefaces, and * corrects a single mathematical letter that previously came from the CLDR transliteration file, but the new rule extracts from the main Unicode database file, where clearly the latter is right and the former is a wrong (reported to CLDR). Reported-by: Cees van Zeeland <cees.van.zeeland@freedom.nl> Reviewed-by: Robert Haas <robertmhaas@gmail.com> Reviewed-by: Peter Eisentraut <peter@eisentraut.org> Reviewed-by: Michael Paquier <michael@paquier.xyz> Discussion: https://postgr.es/m/18362-be6d0cfe122b6354%40postgresql.org
diff --git a/contrib/unaccent/expected/unaccent.out b/contrib/unaccent/expected/unaccent.out
@@ -176,6 +176,6 @@ SELECT ts_lexize('unaccent', '〝');
 SELECT unaccent('ℌ');
  unaccent 
 ----------
- x
+ H
 (1 row)
 
diff --git a/contrib/unaccent/generate_unaccent_rules.py b/contrib/unaccent/generate_unaccent_rules.py
@@ -104,10 +104,11 @@ def is_letter_with_marks(codepoint, table):
     """Returns true for letters combined with one or more marks."""
     # See https://www.unicode.org/reports/tr44/tr44-14.html#General_Category_Values
 
-    # Letter may have no combining characters, in which case it has
-    # no marks.
-    if len(codepoint.combining_ids) == 1:
-        return False
+    # Some codepoints redirect directly to another, instead of doing any
+    # "combining"...  but sometimes they redirect to a codepoint that doesn't
+    # exist, so ignore those.
+    if len(codepoint.combining_ids) == 1 and codepoint.combining_ids[0] in table:
+        return is_letter_with_marks(table[codepoint.combining_ids[0]], table)
 
     # A letter without diacritical marks has none of them.
     if any(is_mark(table[i]) for i in codepoint.combining_ids[1:]) is False:
@@ -148,8 +149,7 @@ def get_plain_letter(codepoint, table):
 
 def is_ligature(codepoint, table):
     """Return true for letters combined with letters."""
-    return all(is_letter(table[i], table) for i in codepoint.combining_ids)
-
+    return all(i in table and is_letter(table[i], table) for i in codepoint.combining_ids)
 
 def get_plain_letters(codepoint, table):
     """Return a list of plain letters from a ligature."""
@@ -200,6 +200,11 @@ def parse_cldr_latin_ascii_transliterator(latinAsciiFilePath):
             # the parser of unaccent only accepts non-whitespace characters
             # for "src" and "trg" (see unaccent.c)
             if not src.isspace() and not trg.isspace():
+                if src == "\u210c":
+                    # This mapping seems to be in error, and causes a collision
+                    # by disagreeing with the main Unicode database file:
+                    # https://unicode-org.atlassian.net/browse/CLDR-17656
+                    continue
                 charactersSet.add((ord(src), trg))
 
     return charactersSet
@@ -251,7 +256,7 @@ def main(args):
     # walk through all the codepoints looking for interesting mappings
     for codepoint in all:
         if codepoint.general_category.startswith('L') and \
-           len(codepoint.combining_ids) > 1:
+           len(codepoint.combining_ids) > 0:
             if is_letter_with_marks(codepoint, table):
                 charactersSet.add((codepoint.id,
                                    chr(get_plain_letter(codepoint, table).id)))
diff --git a/contrib/unaccent/unaccent.rules b/contrib/unaccent/unaccent.rules
