From 59f47fb98dab6f4a59bdfdb8825a7560ca8f1cba Mon Sep 17 00:00:00 2001 From: Michael Paquier Date: Wed, 20 Sep 2023 12:29:36 +0900 Subject: [PATCH] unaccent: Add support for quoted translated characters As reported in bug #18057, the extension unaccent removes in its rule file whitespace characters that are intentionally specified when building unaccent.rules from UnicodeData.txt, causing an incorrect translation for some characters like numeric symbols. This is caused by the fact that all whitespaces before and after the origin and target characters are all discarded (this limitation is documented). This commit makes possible the use of quotes around target characters, so as whitespaces can be considered part of target characters. Some target characters use a double quote, these require an extra double quote. The documentation is updated to show how to use quoted areas, generate_unaccent_rules.py is updated to generate unaccent.rules and a couple of tests are added for numeric symbols. While working on this patch, I have implemented a fake rule file to test the parsing logic implemented, which is not included here as it would just consume extra cycles in the tests, and it requires the manipulation of an installation tree to be able to work correctly. As this requires a change of format in unaccent.rules, this cannot be backpatched, unfortunately. The idea to use double quotes as escaped characters comes from Tom Lane. Reported-by: Martin Schlossarek Author: Michael Paquier Discussion: https://postgr.es/m/18057-62712cad01bd202c@postgresql.org --- contrib/unaccent/expected/unaccent.out | 36 +++++++++ contrib/unaccent/generate_unaccent_rules.py | 4 + contrib/unaccent/sql/unaccent.sql | 6 ++ contrib/unaccent/unaccent.c | 86 ++++++++++++++++++--- contrib/unaccent/unaccent.rules | 56 +++++++------- doc/src/sgml/unaccent.sgml | 16 ++++ 6 files changed, 166 insertions(+), 38 deletions(-) diff --git a/contrib/unaccent/expected/unaccent.out b/contrib/unaccent/expected/unaccent.out index f080707c4a..d03374c799 100644 --- a/contrib/unaccent/expected/unaccent.out +++ b/contrib/unaccent/expected/unaccent.out @@ -51,6 +51,18 @@ SELECT unaccent('℗'); -- sound recording copyright (P) (1 row) +SELECT unaccent('1½'); -- math expression with whitespace + unaccent +---------- + 1 1/2 +(1 row) + +SELECT unaccent('〝'); -- quote + unaccent +---------- + " +(1 row) + SELECT unaccent('unaccent', 'foobar'); unaccent ---------- @@ -93,6 +105,18 @@ SELECT unaccent('unaccent', '℗'); (P) (1 row) +SELECT unaccent('unaccent', '1½'); + unaccent +---------- + 1 1/2 +(1 row) + +SELECT unaccent('unaccent', '〝'); + unaccent +---------- + " +(1 row) + SELECT ts_lexize('unaccent', 'foobar'); ts_lexize ----------- @@ -135,6 +159,18 @@ SELECT ts_lexize('unaccent', '℗'); {(P)} (1 row) +SELECT ts_lexize('unaccent', '1½'); + ts_lexize +----------- + {"1 1/2"} +(1 row) + +SELECT ts_lexize('unaccent', '〝'); + ts_lexize +----------- + {"\""} +(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'); diff --git a/contrib/unaccent/generate_unaccent_rules.py b/contrib/unaccent/generate_unaccent_rules.py index b4b4c38beb..cffb7db7ce 100644 --- a/contrib/unaccent/generate_unaccent_rules.py +++ b/contrib/unaccent/generate_unaccent_rules.py @@ -58,6 +58,10 @@ COMBINING_MARK_RANGES = ((0x0300, 0x0362), # Mn: Accents, IPA def print_record(codepoint, letter): if letter: + # If the letter has whitespace or double quotes, escape double + # quotes and apply more quotes around it. + if (' ' in letter) or ('"' in letter): + letter = '"' + letter.replace('"', '""') + '"' output = chr(codepoint) + "\t" + letter else: output = chr(codepoint) diff --git a/contrib/unaccent/sql/unaccent.sql b/contrib/unaccent/sql/unaccent.sql index 663646c1ac..70c7f1c0a0 100644 --- a/contrib/unaccent/sql/unaccent.sql +++ b/contrib/unaccent/sql/unaccent.sql @@ -20,6 +20,8 @@ SELECT unaccent('˃˖˗˜'); SELECT unaccent('À'); -- Remove combining diacritical 0x0300 SELECT unaccent('℃℉'); -- degree signs SELECT unaccent('℗'); -- sound recording copyright +SELECT unaccent('1½'); -- math expression with whitespace +SELECT unaccent('〝'); -- quote SELECT unaccent('unaccent', 'foobar'); SELECT unaccent('unaccent', 'ёлка'); @@ -28,6 +30,8 @@ SELECT unaccent('unaccent', '˃˖˗˜'); SELECT unaccent('unaccent', 'À'); SELECT unaccent('unaccent', '℃℉'); SELECT unaccent('unaccent', '℗'); +SELECT unaccent('unaccent', '1½'); +SELECT unaccent('unaccent', '〝'); SELECT ts_lexize('unaccent', 'foobar'); SELECT ts_lexize('unaccent', 'ёлка'); @@ -36,6 +40,8 @@ SELECT ts_lexize('unaccent', '˃˖˗˜'); SELECT ts_lexize('unaccent', 'À'); SELECT ts_lexize('unaccent', '℃℉'); SELECT ts_lexize('unaccent', '℗'); +SELECT ts_lexize('unaccent', '1½'); +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'. diff --git a/contrib/unaccent/unaccent.c b/contrib/unaccent/unaccent.c index 64c879e547..5635f04214 100644 --- a/contrib/unaccent/unaccent.c +++ b/contrib/unaccent/unaccent.c @@ -127,24 +127,30 @@ initTrie(const char *filename) * src and trg are sequences of one or more non-whitespace * characters, separated by whitespace. Whitespace at start * or end of line is ignored. If trg is omitted, an empty - * string is used as the replacement. + * string is used as the replacement. trg can be optionally + * quoted, in which case whitespaces are included in it. * * We use a simple state machine, with states * 0 initial (before src) * 1 in src * 2 in whitespace after src - * 3 in trg - * 4 in whitespace after trg - * -1 syntax error detected + * 3 in trg (non-quoted) + * 4 in trg (quoted) + * 5 in whitespace after trg + * -1 syntax error detected (two strings) + * -2 syntax error detected (unfinished quoted string) *---------- */ int state; char *ptr; char *src = NULL; char *trg = NULL; + char *trgstore = NULL; int ptrlen; int srclen = 0; int trglen = 0; + int trgstorelen = 0; + bool trgquoted = false; state = 0; for (ptr = line; *ptr; ptr += ptrlen) @@ -156,8 +162,10 @@ initTrie(const char *filename) if (state == 1) state = 2; else if (state == 3) - state = 4; - continue; + state = 5; + /* whitespaces are OK in quoted area */ + if (state != 4) + continue; } switch (state) { @@ -173,14 +181,41 @@ initTrie(const char *filename) break; case 2: /* start of trg */ + if (*ptr == '"') + { + trgquoted = true; + state = 4; + } + else + state = 3; + trg = ptr; trglen = ptrlen; - state = 3; break; case 3: - /* continue trg */ + /* continue non-quoted trg */ trglen += ptrlen; break; + case 4: + /* continue quoted trg */ + trglen += ptrlen; + + /* + * If this is a quote, consider it as the end of + * trg except if the follow-up character is itself + * a quote. + */ + if (*ptr == '"') + { + if (*(ptr + 1) == '"') + { + ptr++; + trglen += 1; + } + else + state = 5; + } + break; default: /* bogus line format */ state = -1; @@ -195,15 +230,46 @@ initTrie(const char *filename) trglen = 0; } + /* If still in a quoted area, fallback to an error */ + if (state == 4) + state = -2; + + /* If trg was quoted, remove its quotes and unescape it */ + if (trgquoted && state > 0) + { + /* Ignore first and end quotes */ + trgstore = palloc0(sizeof(char *) * trglen - 2); + trgstorelen = 0; + for (int i = 1; i < trglen - 1; i++) + { + trgstore[trgstorelen] = trg[i]; + trgstorelen++; + /* skip second double quotes */ + if (trg[i] == '"' && trg[i + 1] == '"') + i++; + } + } + else + { + trgstore = palloc0(sizeof(char *) * trglen); + trgstorelen = trglen; + memcpy(trgstore, trg, trgstorelen); + } + if (state > 0) rootTrie = placeChar(rootTrie, (unsigned char *) src, srclen, - trg, trglen); - else if (state < 0) + trgstore, trgstorelen); + else if (state == -1) ereport(WARNING, (errcode(ERRCODE_CONFIG_FILE_ERROR), errmsg("invalid syntax: more than two strings in unaccent rule"))); + else if (state == -2) + ereport(WARNING, + (errcode(ERRCODE_CONFIG_FILE_ERROR), + errmsg("invalid syntax: unfinished quoted string in unaccent rule"))); + pfree(trgstore); pfree(line); } skip = false; diff --git a/contrib/unaccent/unaccent.rules b/contrib/unaccent/unaccent.rules index 3030166ed6..ca6caa51f5 100644 --- a/contrib/unaccent/unaccent.rules +++ b/contrib/unaccent/unaccent.rules @@ -5,9 +5,9 @@ ® (R) ± +/- » >> -¼ 1/4 -½ 1/2 -¾ 3/4 +¼ " 1/4" +½ " 1/2" +¾ " 3/4" ¿ ? À A Á A @@ -403,7 +403,7 @@ ʪ ls ʫ lz ʹ ' -ʺ " +ʺ """" ʻ ' ʼ ' ʽ ' @@ -1058,15 +1058,15 @@ ’ ' ‚ , ‛ ' -“ " -” " +“ """" +” """" „ ,, -‟ " +‟ """" ․ . ‥ .. … ... ′ ' -″ " +″ """" ‹ < › > ‼ !! @@ -1134,22 +1134,22 @@ ⅇ e ⅈ i ⅉ j -⅐ 1/7 -⅑ 1/9 -⅒ 1/10 -⅓ 1/3 -⅔ 2/3 -⅕ 1/5 -⅖ 2/5 -⅗ 3/5 -⅘ 4/5 -⅙ 1/6 -⅚ 5/6 -⅛ 1/8 -⅜ 3/8 -⅝ 5/8 -⅞ 7/8 -⅟ 1/ +⅐ " 1/7" +⅑ " 1/9" +⅒ " 1/10" +⅓ " 1/3" +⅔ " 2/3" +⅕ " 1/5" +⅖ " 2/5" +⅗ " 3/5" +⅘ " 4/5" +⅙ " 1/6" +⅚ " 5/6" +⅛ " 1/8" +⅜ " 3/8" +⅝ " 5/8" +⅞ " 7/8" +⅟ " 1/" Ⅰ I Ⅱ II Ⅲ III @@ -1182,7 +1182,7 @@ ⅽ c ⅾ d ⅿ m -↉ 0/3 +↉ " 0/3" − - ∕ / ∖ \ @@ -1296,8 +1296,8 @@ 〙 ] 〚 [ 〛 ] -〝 " -〞 " +〝 """" +〞 """" ㍱ hPa ㍲ da ㍳ AU @@ -1512,7 +1512,7 @@ ﹪ % ﹫ @ ！ ! -＂ " +＂ """" ＃ # ＄ $ ％ % diff --git a/doc/src/sgml/unaccent.sgml b/doc/src/sgml/unaccent.sgml index f3ddc64bbc..94100ed260 100644 --- a/doc/src/sgml/unaccent.sgml +++ b/doc/src/sgml/unaccent.sgml @@ -84,6 +84,22 @@ + + + Some characters, like numeric symbols, may require whitespaces in their + translation rule. It is possible to use double quotes around the translated + characters in this case. A double quote needs to be escaped with a second + double quote when including one in the translated character. For example: + +¼ " 1/4" +½ " 1/2" +¾ " 3/4" +“ """" +” """" + + + + As with other PostgreSQL text search configuration files,