diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 6c4359d..ff44496 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -5934,7 +5934,7 @@ SELECT regexp_match('abc01234xyz', '(?:(.*?)(\d+)(.*)){1,1}'); TM prefix - translation mode (print localized day and month names based on + translation mode (use localized day and month names based on ) TMMonth @@ -5966,8 +5966,13 @@ SELECT regexp_match('abc01234xyz', '(?:(.*?)(\d+)(.*)){1,1}'); TM does not include trailing blanks. + + + + + to_timestamp and to_date ignore - the TM modifier. + the case when receiving names as an input. diff --git a/src/backend/utils/adt/formatting.c b/src/backend/utils/adt/formatting.c index 792f9ca..0c225de 100644 --- a/src/backend/utils/adt/formatting.c +++ b/src/backend/utils/adt/formatting.c @@ -1059,9 +1059,11 @@ static int from_char_parse_int_len(int *dest, const char **src, const int len, FormatNode *node, bool *have_error); static int from_char_parse_int(int *dest, const char **src, FormatNode *node, bool *have_error); -static int seq_search(const char *name, const char *const *array, int *len); +static int seq_search_ascii(const char *name, const char *const *array, int *len); +static int seq_search_localized(const char *name, char **array, int *len); static int from_char_seq_search(int *dest, const char **src, const char *const *array, + char **localized_array, FormatNode *node, bool *have_error); static void do_to_timestamp(text *date_txt, text *fmt, bool std, struct pg_tm *tm, fsec_t *fsec, int *fprec, @@ -2459,7 +2461,7 @@ from_char_parse_int(int *dest, const char **src, FormatNode *node, bool *have_er * suitable for comparisons to ASCII strings. */ static int -seq_search(const char *name, const char *const *array, int *len) +seq_search_ascii(const char *name, const char *const *array, int *len) { unsigned char firstc; const char *const *a; @@ -2505,8 +2507,63 @@ seq_search(const char *name, const char *const *array, int *len) } /* - * Perform a sequential search in 'array' for an entry matching the first - * character(s) of the 'src' string case-insensitively. + * Sequentially search an array of possibly non-English words for + * a case-insensitive match to the initial character(s) of "name". + * + * This has the same API as seq_search_ascii(), but we use a more general + * downcasing transformation to achieve case-insensitivity. + * + * The array is treated as const, but we don't declare it that way because + * the arrays exported by pg_locale.c aren't const. + */ +static int +seq_search_localized(const char *name, char **array, int *len) +{ + char **a; + char *lower_name; + + *len = 0; + + /* empty string can't match anything */ + if (!*name) + return -1; + + /* Now lower-case it */ + lower_name = str_tolower(unconstify(char *, name), strlen(name), + DEFAULT_COLLATION_OID); + + for (a = array; *a != NULL; a++) + { + char *lower_element; + int element_len; + + /* Lower-case array element, assuming it is normalized */ + lower_element = str_tolower(*a, strlen(*a), DEFAULT_COLLATION_OID); + element_len = strlen(lower_element); + + /* Match? */ + if (strncmp(lower_name, lower_element, element_len) == 0) + { + *len = element_len; + pfree(lower_element); + pfree(lower_name); + return a - array; + } + pfree(lower_element); + } + + pfree(lower_name); + return -1; +} + +/* + * Perform a sequential search in 'array' (or 'localized_array', if that's + * not NULL) for an entry matching the first character(s) of the 'src' + * string case-insensitively. + * + * The 'array' is presumed to be English words (all-ASCII), but + * if 'localized_array' is supplied, that might be non-English + * so we need a more expensive downcasing transformation. * * If a match is found, copy the array index of the match into the integer * pointed to by 'dest', advance 'src' to the end of the part of the string @@ -2520,11 +2577,15 @@ seq_search(const char *name, const char *const *array, int *len) */ static int from_char_seq_search(int *dest, const char **src, const char *const *array, + char **localized_array, FormatNode *node, bool *have_error) { int len; - *dest = seq_search(*src, array, &len); + if (localized_array == NULL) + *dest = seq_search_ascii(*src, array, &len); + else + *dest = seq_search_localized(*src, localized_array, &len); if (len <= 0) { @@ -3172,6 +3233,9 @@ DCH_from_char(FormatNode *node, const char *in, TmFromChar *out, bool std, /* number of extra skipped characters (more than given in format string) */ int extra_skip = 0; + /* cache localized days and months */ + cache_locale_time(); + for (n = node, s = in; n->type != NODE_TYPE_END && *s != '\0'; n++) { /* @@ -3272,7 +3336,7 @@ DCH_from_char(FormatNode *node, const char *in, TmFromChar *out, bool std, case DCH_P_M: case DCH_a_m: case DCH_p_m: - from_char_seq_search(&value, &s, ampm_strings_long, + from_char_seq_search(&value, &s, ampm_strings_long, NULL, n, have_error); CHECK_ERROR; from_char_set_int(&out->pm, value % 2, n, have_error); @@ -3283,7 +3347,7 @@ DCH_from_char(FormatNode *node, const char *in, TmFromChar *out, bool std, case DCH_PM: case DCH_am: case DCH_pm: - from_char_seq_search(&value, &s, ampm_strings, + from_char_seq_search(&value, &s, ampm_strings, NULL, n, have_error); CHECK_ERROR; from_char_set_int(&out->pm, value % 2, n, have_error); @@ -3396,7 +3460,7 @@ DCH_from_char(FormatNode *node, const char *in, TmFromChar *out, bool std, case DCH_B_C: case DCH_a_d: case DCH_b_c: - from_char_seq_search(&value, &s, adbc_strings_long, + from_char_seq_search(&value, &s, adbc_strings_long, NULL, n, have_error); CHECK_ERROR; from_char_set_int(&out->bc, value % 2, n, have_error); @@ -3406,7 +3470,7 @@ DCH_from_char(FormatNode *node, const char *in, TmFromChar *out, bool std, case DCH_BC: case DCH_ad: case DCH_bc: - from_char_seq_search(&value, &s, adbc_strings, + from_char_seq_search(&value, &s, adbc_strings, NULL, n, have_error); CHECK_ERROR; from_char_set_int(&out->bc, value % 2, n, have_error); @@ -3416,6 +3480,7 @@ DCH_from_char(FormatNode *node, const char *in, TmFromChar *out, bool std, case DCH_Month: case DCH_month: from_char_seq_search(&value, &s, months_full, + S_TM(n->suffix) ? localized_full_months : NULL, n, have_error); CHECK_ERROR; from_char_set_int(&out->mm, value + 1, n, have_error); @@ -3425,6 +3490,7 @@ DCH_from_char(FormatNode *node, const char *in, TmFromChar *out, bool std, case DCH_Mon: case DCH_mon: from_char_seq_search(&value, &s, months, + S_TM(n->suffix) ? localized_abbrev_months : NULL, n, have_error); CHECK_ERROR; from_char_set_int(&out->mm, value + 1, n, have_error); @@ -3439,6 +3505,7 @@ DCH_from_char(FormatNode *node, const char *in, TmFromChar *out, bool std, case DCH_Day: case DCH_day: from_char_seq_search(&value, &s, days, + S_TM(n->suffix) ? localized_full_days : NULL, n, have_error); CHECK_ERROR; from_char_set_int(&out->d, value, n, have_error); @@ -3449,6 +3516,7 @@ DCH_from_char(FormatNode *node, const char *in, TmFromChar *out, bool std, case DCH_Dy: case DCH_dy: from_char_seq_search(&value, &s, days_short, + S_TM(n->suffix) ? localized_abbrev_days : NULL, n, have_error); CHECK_ERROR; from_char_set_int(&out->d, value, n, have_error); @@ -3566,7 +3634,7 @@ DCH_from_char(FormatNode *node, const char *in, TmFromChar *out, bool std, break; case DCH_RM: case DCH_rm: - from_char_seq_search(&value, &s, rm_months_lower, + from_char_seq_search(&value, &s, rm_months_lower, NULL, n, have_error); CHECK_ERROR; from_char_set_int(&out->mm, MONTHS_PER_YEAR - value, diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c index 25fb7e2..64fd3ae 100644 --- a/src/backend/utils/adt/pg_locale.c +++ b/src/backend/utils/adt/pg_locale.c @@ -96,11 +96,17 @@ char *locale_monetary; char *locale_numeric; char *locale_time; -/* lc_time localization cache */ -char *localized_abbrev_days[7]; -char *localized_full_days[7]; -char *localized_abbrev_months[12]; -char *localized_full_months[12]; +/* + * lc_time localization cache. + * + * We use only the first 7 or 12 entries of these arrays. The last array + * element is left as NULL for the convenience of outside code that wants + * to sequentially scan these arrays. + */ +char *localized_abbrev_days[7 + 1]; +char *localized_full_days[7 + 1]; +char *localized_abbrev_months[12 + 1]; +char *localized_full_months[12 + 1]; /* indicates whether locale information cache is valid */ static bool CurrentLocaleConvValid = false; @@ -922,6 +928,8 @@ cache_locale_time(void) cache_single_string(&localized_full_days[i], bufptr, encoding); bufptr += MAX_L10N_DATA; } + localized_abbrev_days[7] = NULL; + localized_full_days[7] = NULL; /* localized months */ for (i = 0; i < 12; i++) @@ -931,6 +939,8 @@ cache_locale_time(void) cache_single_string(&localized_full_months[i], bufptr, encoding); bufptr += MAX_L10N_DATA; } + localized_abbrev_months[12] = NULL; + localized_full_months[12] = NULL; CurrentLCTimeValid = true; } diff --git a/src/test/regress/expected/collate.linux.utf8.out b/src/test/regress/expected/collate.linux.utf8.out index 37c6add..68b8f14 100644 --- a/src/test/regress/expected/collate.linux.utf8.out +++ b/src/test/regress/expected/collate.linux.utf8.out @@ -461,6 +461,16 @@ SELECT to_char(date '2010-04-01', 'DD TMMON YYYY' COLLATE "tr_TR"); 01 NİS 2010 (1 row) +-- to_date +SELECT to_date('01 ŞUB 2010', 'DD TMMON YYYY'); + to_date +------------ + 02-01-2010 +(1 row) + +SELECT to_date('1234567890ab 2010', 'TMMONTH YYYY'); -- fail +ERROR: invalid value "1234567890ab" for "MONTH" +DETAIL: The given value did not match any of the allowed values for this field. -- backwards parsing CREATE VIEW collview1 AS SELECT * FROM collate_test1 WHERE b COLLATE "C" >= 'bbc'; CREATE VIEW collview2 AS SELECT a, b FROM collate_test1 ORDER BY b COLLATE "C"; diff --git a/src/test/regress/sql/collate.linux.utf8.sql b/src/test/regress/sql/collate.linux.utf8.sql index 8c26f16..3d9a2ed 100644 --- a/src/test/regress/sql/collate.linux.utf8.sql +++ b/src/test/regress/sql/collate.linux.utf8.sql @@ -182,6 +182,11 @@ SELECT to_char(date '2010-02-01', 'DD TMMON YYYY' COLLATE "tr_TR"); SELECT to_char(date '2010-04-01', 'DD TMMON YYYY'); SELECT to_char(date '2010-04-01', 'DD TMMON YYYY' COLLATE "tr_TR"); +-- to_date + +SELECT to_date('01 ŞUB 2010', 'DD TMMON YYYY'); +SELECT to_date('1234567890ab 2010', 'TMMONTH YYYY'); -- fail + -- backwards parsing