ICU 74.1 Patches (cont'd)

Author: gagolews

.devel/sphinx/conf.py

@@ -15,14 +15,14 @@ def get_package_version():
 copyright_year = "2013–2023"
 html_baseurl = "https://stringi.gagolewski.com/"
 html_logo = "https://www.gagolewski.com/_static/img/stringi.png"
+html_favicon = "https://www.gagolewski.com/_static/img/stringi.png"
 github_url = "https://github.com/gagolews/stringi"
 github_star_repo = "gagolews/stringi"
 analytics_id = None  # don't use it! this site does not track its users
 author = "Marek Gagolewski"
 copyright = f"{copyright_year}"
 html_title = f"R Package {pkg_title}"
 html_short_title = f"{pkg_title}"
-html_favicon = "_static/favicon.png"
 
 html_version_text = f'\
     R Package<br />\

.devel/sphinx/news.md

@@ -5,13 +5,14 @@
 
 * [GENERAL] ICU bundle updated to version 74.1 (Unicode 15.1, CLDR 44).
 
-* [BUILD TIME] As per the suggestion of Prof. Brian Ripley, `icudt74l` (ICU data)
-  is now included in the source tarball (compressed with xz to save space).
-  This allows for building *stringi* on systems with no internet access.
+* [BUILD TIME] As per the suggestion of Prof. Brian Ripley, `icudt74l`
+  (ICU data -- little endian) is now included in the source tarball (compressed
+  with xz to save space). This allows for building *stringi* on systems with
+  no internet access.
 
 * [BUILD TIME] Support for Solaris has now been dropped. The package is no
-    longer shipped with the very outdated ICU55 bundle. A compiler supporting
-    at least C++11 is now required. ICU >= 61 is now required.
+  longer shipped with the very outdated ICU55 bundle. A compiler supporting
+  at least C++11 is now required. ICU >= 61 is now required.
 
 
 
@@ -24,6 +25,10 @@
 
 * [NEW FEATURE] TODO... #476 U_USING_DEFAULT_ERROR on unknown locales
 
+* TODO.... ...#490?
+
+* TODO.... ...#491?
+
 
 
 ## 1.7.12 (2023-01-09)

.devel/sphinx/rapi/stri_datetime_add.md

@@ -68,15 +68,15 @@ print(x)
 ```
 
 ```
-## [1] "2024-01-05 11:12:24 AEDT"
+## [1] "2024-01-05 14:22:31 AEDT"
 ```
 
 ```r
 stri_datetime_add(x, -2, units='months')
 ```
 
 ```
-## [1] "2023-11-05 11:12:24 AEDT"
+## [1] "2023-11-05 14:22:31 AEDT"
 ```
 
 ```r

.devel/sphinx/rapi/stri_datetime_fields.md

@@ -77,9 +77,9 @@ stri_datetime_fields(stri_datetime_now())
 
 ```
 ##   Year Month Day Hour Minute Second Millisecond WeekOfYear WeekOfMonth
-## 1 2023    11   5   11     12     24         801         45           1
+## 1 2023    11   5   14     22     31         945         45           1
 ##   DayOfYear DayOfWeek Hour12 AmPm Era
-## 1       309         1     11    1   2
+## 1       309         1      2    2   2
 ```
 
 ```r
@@ -88,9 +88,9 @@ stri_datetime_fields(stri_datetime_now(), locale='@calendar=hebrew')
 
 ```
 ##   Year Month Day Hour Minute Second Millisecond WeekOfYear WeekOfMonth
-## 1 5784     2  21   11     12     24         805          8           3
+## 1 5784     2  21   14     22     31         950          8           3
 ##   DayOfYear DayOfWeek Hour12 AmPm Era
-## 1        51         1     11    1   1
+## 1        51         1      2    2   1
 ```
 
 ```r

.devel/sphinx/rapi/stri_datetime_format.md

@@ -189,15 +189,15 @@ stri_datetime_parse(x, 'yyyy-MM-dd')
 ```
 
 ```
-## [1] "2015-02-28 11:12:24 AEDT" NA
+## [1] "2015-02-28 14:22:32 AEDT" NA
 ```
 
 ```r
 stri_datetime_parse(x, 'yyyy-MM-dd', lenient=TRUE)
 ```
 
 ```
-## [1] "2015-02-28 11:12:24 AEDT" "2015-03-01 11:12:24 AEDT"
+## [1] "2015-02-28 14:22:32 AEDT" "2015-03-01 14:22:32 AEDT"
 ```
 
 ```r
@@ -213,13 +213,13 @@ stri_datetime_parse('19 lipca 2015', 'date_long', locale='pl_PL')
 ```
 
 ```
-## [1] "2015-07-19 11:12:24 AEST"
+## [1] "2015-07-19 14:22:32 AEST"
 ```
 
 ```r
 stri_datetime_format(stri_datetime_now(), 'datetime_relative_medium')
 ```
 
 ```
-## [1] "today, 11:12:24 am"
+## [1] "today, 2:22:32 pm"
 ```

.devel/sphinx/rapi/stri_locale_set.md

@@ -53,7 +53,7 @@ oldloc <- stri_locale_set('pt_BR')
 ```
 
 ```
-## You are now working with stringi_1.7.9002 (pt_BR.UTF-8; ICU4C 74.1 [bundle]; Unicode 15.1)
+## You are now working with stringi_1.7.9003 (pt_BR.UTF-8; ICU4C 74.1 [bundle]; Unicode 15.1)
 ```
 
 ```r
@@ -65,7 +65,7 @@ stri_locale_set(oldloc) # restore the previous default locale
 ```
 
 ```
-## You are now working with stringi_1.7.9002 (en_AU.UTF-8; ICU4C 74.1 [bundle]; Unicode 15.1)
+## You are now working with stringi_1.7.9003 (en_AU.UTF-8; ICU4C 74.1 [bundle]; Unicode 15.1)
 ```
 
 ```r

.devel/sphinx/rapi/stri_sprintf.md

@@ -188,7 +188,7 @@ stri_sprintf("UNIX time %1$f is %1$s.", Sys.time())
 ```
 
 ```
-## [1] "UNIX time 1699143154.428132 is 2023-11-05 11:12:34.428132."
+## [1] "UNIX time 1699154561.661119 is 2023-11-05 14:22:41.661119."
 ```
 
 ```r
@@ -213,7 +213,7 @@ stri_sprintf("%1$s is %1$f UNIX time.", Sys.time())  # re-coercion needed
 ```
 
 ```
-## [1] "2023-11-05 11:12:34.429878 is 1699143154.429878 UNIX time."
+## [1] "2023-11-05 14:22:41.662826 is 1699154561.662826 UNIX time."
 ```
 
 ```r

.devel/tinytest/test-sprintf.R

@@ -22,7 +22,15 @@ expect_identical(stri_sprintf("%0000000000000000001$#0+ *0000002$.*003$e", 1.234
 
 f <- c("%10.3f", "%010.3f", "%+10.3f", "%- 10.3f")
 x <- c(-Inf, -0, 0, Inf, NaN, NA_real_)
-expect_identical(outer(f, x, stri_sprintf, na_string="NA"), outer(f, x, sprintf))
+expect_identical(
+as.character(outer(f, x, stri_sprintf, na_string="NA")),
+    c("      -Inf", "      -Inf", "      -Inf", "-Inf      ",
+    "    -0.000",    "-00000.000", "    -0.000", "-0.000    ",
+    "     0.000", "000000.000",    "    +0.000", " 0.000    ",
+    "       Inf", "       Inf", "      +Inf",    " Inf      ",
+    "       NaN", "       NaN", "       NaN", " NaN      ",
+    "        NA", "        NA", "        NA", " NA       ")
+)
 
 expect_identical(stri_sprintf("% .0f", x, na_string=NA, inf_string=NA, nan_string=NA),
     c(NA, "-0", " 0", NA, NA, NA))
@@ -200,7 +208,7 @@ expect_identical(stri_sprintf("%- 5d", c(-123, 123, 0)), sprintf("%- 5d", c(-123
 expect_identical(stri_sprintf("%-+5d", c(-123, 123, 0)), sprintf("%-+5d", c(-123, 123, 0)))
 expect_identical(stri_sprintf("%-0+5d", c(-123, 123, 0)), sprintf("%-0+5d", c(-123, 123, 0)))
 expect_identical(stri_sprintf("%-0 5d", c(-123, 123, 0)), sprintf("%-0 5d", c(-123, 123, 0)))
-expect_identical(stri_sprintf("%08s", "abc"), sprintf("%08s", "abc"))
+#expect_identical(stri_sprintf("%08s", "abc"), sprintf("%08s", "abc"))  # undefined behaviour for strings according to man 3 sprintf
 expect_identical(stri_sprintf("%-8s", "abc"), sprintf("%-8s", "abc"))
 expect_identical(stri_sprintf("%+8s", "abc"), sprintf("%+8s", "abc"))
 expect_identical(stri_sprintf("%1$s %s %2$s %s", 1, 2), sprintf("%1$s %s %2$s %s", 1, 2))
@@ -234,7 +242,7 @@ expect_identical(stri_sprintf("%G", 1e-6 * pi), sprintf("%G", 1e-6 * pi))
 expect_identical(stri_sprintf("%1.f", 101), sprintf("%1.f", 101))
 expect_identical(stri_sprintf("%1$d %1$x %1$X", 0:15), sprintf("%1$d %1$x %1$X", 0:15))
 expect_identical(stri_sprintf("min 10-char string '%10s'", c("a", "ABC", "and an even longer one")), sprintf("min 10-char string '%10s'", c("a", "ABC", "and an even longer one")))
-expect_identical(stri_sprintf("%09s", month.name), sprintf("%09s", month.name))
+expect_identical(stri_sprintf("% 9s", month.name), sprintf("% 9s", month.name))
 expect_identical(stri_sprintf(paste0("e with %2d digits = %.", 1:18, "g"), 1:18, exp(1)), sprintf(paste0("e with %2d digits = %.", 1:18, "g"), 1:18, exp(1)))
 expect_identical(stri_sprintf("second %2$1.0f, first %1$5.2f, third %3$1.0f", pi, 2, 3), sprintf("second %2$1.0f, first %1$5.2f, third %3$1.0f", pi, 2, 3))
 expect_identical(stri_sprintf("precision %.*f, width '%*.3f'", 3, pi, 8, pi), sprintf("precision %.*f, width '%*.3f'", 3, pi, 8, pi))

.devel/tinytest/test-uloc.R

@@ -4,7 +4,7 @@ library("stringi")
 
 expect_true(length(stri_locale_list()) > 0)
 
-expect_warning(stri_locale_set("XX_YY"))
+stri_locale_set("XX_YY")
 suppressMessages(expect_true(substr(stri_locale_set("pl_PL"), 1, 5) == "xx_YY"))
 suppressMessages(expect_true(substr(stri_locale_set("pl_PL"), 1, 5) == "pl_PL"))
 

.github/workflows/r-icu-bundle.yml

@@ -15,6 +15,8 @@ jobs:
       run: |
         sudo apt-get update -qq
         # https://cran.r-project.org/bin/linux/ubuntu/
+        sudo echo "pl_PL.UTF-8" >> /etc/locale.gen
+        sudo locale-gen
         sudo apt install --no-install-recommends software-properties-common dirmngr
         sudo apt-key adv --keyserver keyserver.ubuntu.com --recv-keys E298A3A825C0D65DFD57CBB651716619E084DAB9
         sudo add-apt-repository "deb https://cloud.r-project.org/bin/linux/ubuntu $(lsb_release -cs)-cran40/"
@@ -26,6 +28,6 @@ jobs:
         sudo R CMD INSTALL . --configure-args='--disable-pkg-config'
     - name: Test stringi
       run: |
-        sudo Rscript -e 'source(".devel/tinytest.R")'
+        Rscript -e 'source(".devel/tinytest.R")'
         LC_ALL="pl_PL.UTF-8" Rscript -e 'source(".devel/tinytest.R")'
         LC_ALL="C" Rscript -e 'source(".devel/tinytest.R")'

.github/workflows/r-icu-system.yml

@@ -25,13 +25,15 @@ jobs:
       run: |
         sudo apt-get update
         sudo apt-get -y upgrade
+        sudo echo "pl_PL.UTF-8" >> /etc/locale.gen
+        sudo locale-gen
         sudo apt-get -y install libcurl4-openssl-dev r-base-dev devscripts libicu-dev language-pack-pl
         sudo Rscript -e "install.packages(c('tinytest', 'Rcpp'))"
     - name: Install stringi
       run: |
         sudo R CMD INSTALL .
     - name: Test stringi
       run: |
-        sudo Rscript -e 'source(".devel/tinytest.R")'
+        Rscript -e 'source(".devel/tinytest.R")'
         LC_ALL="pl_PL.UTF-8" Rscript -e 'source(".devel/tinytest.R")'
         LC_ALL="C" Rscript -e 'source(".devel/tinytest.R")'

DESCRIPTION

@@ -1,5 +1,5 @@
 Package: stringi
-Version: 1.7.9002
+Version: 1.7.9003
 Date: 2023-11-05
 Title: Fast and Portable Character String Processing Facilities
 Description: A collection of character string/text/natural language

NEWS

@@ -5,30 +5,35 @@
 
 * [GENERAL] ICU bundle updated to version 74.1 (Unicode 15.1, CLDR 44).
 
-* [BUILD TIME] As per the suggestion of Prof. Brian Ripley, `icudt74l` (ICU data)
-  is now included in the source tarball (compressed with xz to save space).
-  This allows for building *stringi* on systems with no internet access.
+* [BUILD TIME] As per the suggestion of Prof. Brian Ripley, `icudt74l`
+  (ICU data -- little endian) is now included in the source tarball (compressed
+  with xz to save space). This allows for building *stringi* on systems with
+  no internet access.
 
 * [BUILD TIME] Support for Solaris has now been dropped. The package is no
-    longer shipped with the very outdated ICU55 bundle. A compiler supporting
-    at least C++11 is now required. ICU >= 61 is now required.
+  longer shipped with the very outdated ICU55 bundle. A compiler supporting
+  at least C++11 is now required. ICU >= 61 is now required.
 
 
 
 * [NEW FEATURE] TODO.... #469: `stri_datetime_parse` .. new argument -
-`default_time`
-    a Calendar set on input to the date and time to be used for missing values in the date/time string being parsed
+    `default_time` a Calendar set on input to the date and time to be used
+    for missing values in the date/time string being parsed
 
-* [BUGFIX] TODO.... #469: `stri_datetime_parse` did not reset the `Calendar` object
-    when parsing multiple dates.
+* [BUGFIX] TODO.... #469: `stri_datetime_parse` did not reset the `Calendar`
+    object when parsing multiple dates.
 
 * [NEW FEATURE] TODO... #476 U_USING_DEFAULT_ERROR on unknown locales
 
+* TODO.... ...#490?
+
+* TODO.... ...#491?
+
 
 
 ## 1.7.12 (2023-01-09)
 
-* [BUGFIX] Fixed some potential problems reported by `rchk`.
+* [BUGFIX] Fixed a few issues reported by `rchk`.
 
 * [NOTE] [BACKWARD INCOMPATIBLE CHANGE IF ICU >= 72]
   If building against ICU >= 72, note a backward incompatible change:
@@ -42,7 +47,7 @@
   the *Journal of Statistical Software*;
   see <https://doi.org/10.18637/jss.v103.i02>.
 
-* [BUGFIX] #473, #397: Fixed buffer overflow in `stri_dup`.
+* [BUGFIX] #473, #397: Fixed buffer overflow in `stri_dup`; Also,
   `stri_dup`, `stri_paste`, ... fail more graciously on attempts to
   generate strings of length >= 2^31 each.
 

R/ICU_settings.R

@@ -82,11 +82,6 @@ stri_info <- function(short = FALSE)
                 "Consider switching to UTF-8."))
     }
 
-    if (!(locale %in% loclist))
-        warning(stri_paste("Your current locale is not on the list of ",
-            "available locales; see stri_locale_list(). ",
-            "Some functions may not work properly. "))
-
     if (!short)
         return(info) else {
         return(sprintf("stringi_%s (%s.%s; ICU4C %s [%s%s]; Unicode %s)", as.character(packageVersion("stringi")),

TODO

@@ -10,10 +10,9 @@ Contributions are welcome!
 
 * [NEW FEATURE] TODO... #445 stri_dup: add sep argument
 
-* [BUILD TIME] TODO..
-Tomas Kalibera suggests to use the Rtools version of ICU for Windows:
-"Rtools43 has icu 72.1, Rtools42 has 71.1."
-see also some notes in configure.ac
+* [BUILD TIME] TODO.. Tomas Kalibera suggests to use the Rtools version of ICU
+    for Windows: "Rtools43 has icu 72.1, Rtools42 has 71.1."; see also some notes
+    in configure.ac
 
 * [LATER] compress, move, remove src/icu55*, src/icu61*, src/icu69*;
     the *.dat files may still be downloaded by old R/install.R files

src/icu74/common/unistr.cpp

@@ -2019,12 +2019,7 @@ The vector deleting destructor is already a part of UObject,
 but defining it here makes sure that it is included with this object file.
 This makes sure that static library dependencies are kept to a minimum.
 */
-#if defined(__clang__) || U_GCC_MAJOR_MINOR >= 1100
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wunused-function"
-static void uprv_UnicodeStringDummy() {
+void uprv_UnicodeStringDummy(void) {
     delete [] (new UnicodeString[2]);
 }
-#pragma GCC diagnostic pop
-#endif
 #endif

src/icu74/i18n/formattedvalue.cpp

@@ -193,26 +193,26 @@ ucfpos_close(UConstrainedFieldPosition* ptr) {
 }
 
 
-U_CAPI const char16_t* U_EXPORT2
-ufmtval_getString(
-        const UFormattedValue* ufmtval,
-        int32_t* pLength,
-        UErrorCode* ec) {
-    const auto* impl = UFormattedValueApiHelper::validate(ufmtval, *ec);
-    if (U_FAILURE(*ec)) {
-        return nullptr;
-    }
-    UnicodeString readOnlyAlias = impl->fFormattedValue->toTempString(*ec);
-    if (U_FAILURE(*ec)) {
-        return nullptr;
-    }
-    if (pLength != nullptr) {
-        *pLength = readOnlyAlias.length();
-    }
-    // Note: this line triggers -Wreturn-local-addr, but it is safe because toTempString is
-    // defined to return memory owned by the ufmtval argument.
-    return readOnlyAlias.getBuffer();
-}
+// U_CAPI const char16_t* U_EXPORT2
+// ufmtval_getString(
+//         const UFormattedValue* ufmtval,
+//         int32_t* pLength,
+//         UErrorCode* ec) {
+//     const auto* impl = UFormattedValueApiHelper::validate(ufmtval, *ec);
+//     if (U_FAILURE(*ec)) {
+//         return nullptr;
+//     }
+//     UnicodeString readOnlyAlias = impl->fFormattedValue->toTempString(*ec);
+//     if (U_FAILURE(*ec)) {
+//         return nullptr;
+//     }
+//     if (pLength != nullptr) {
+//         *pLength = readOnlyAlias.length();
+//     }
+//     // Note: this line triggers -Wreturn-local-addr, but it is safe because toTempString is
+//     // defined to return memory owned by the ufmtval argument.
+//     return readOnlyAlias.getBuffer();
+// }
 
 
 U_CAPI UBool U_EXPORT2