Rebuild translation table + support ordered factor in scan_data

.Rbuildignore

@@ -19,13 +19,11 @@ vignettes
 man/figures/
 ^tests/manual_tests$
 ^inst/translations$
-tests/testthat/_snaps
 tests/testthat/postgres.R
 tests/testthat/postgres-2.R
 tests/testthat/test-col_schema.R
 tests/testthat/test-column_roles.R
 tests/testthat/test-create_validation_steps.R
-tests/testthat/test-draft_validation.R
 tests/testthat/test-expectation_fns.R
 tests/testthat/test-file_naming.R
 tests/testthat/test-get_agent_report.R
@@ -34,6 +32,7 @@ tests/testthat/test-get_informant_report.R
 tests/testthat/test-get_multiagent_report.R
 tests/testthat/test-interrogate_simple.R
 tests/testthat/test-interrogate_with_agent.R
+tests/testthat/_snaps/interrogate_with_agent.md
 tests/testthat/test-interrogate_with_agent_db.R
 tests/testthat/test-interrogate_with_agent_segments.R
 tests/testthat/test-read_disk_multiagent.R

R/scan_data.R

@@ -455,6 +455,7 @@ probe_columns <- function(
             lang = lang,
             locale = locale
           ),
+          ordered = ,
           factor = probe_columns_factor(
             data = data,
             column = col_name,

R/tbl_from_file.R

@@ -575,33 +575,15 @@ download_remote_file <- function(url, ...) {
 
   if (grepl("^https?://", url)) {
 
-    is_r32 <- getRversion() >= "3.2"
-
     if (.Platform$OS.type == "windows") {
 
-      if (is_r32) {
-
-        method <- "wininet"
-
-      } else {
-
-        seti2 <- utils::"setInternet2"
-        internet2_start <- seti2(NA)
-
-        if (!internet2_start) {
-
-          on.exit(suppressWarnings(seti2(internet2_start)))
-          suppressWarnings(seti2(TRUE))
-        }
-
-        method <- "internal"
-      }
+      method <- "wininet"
 
       suppressWarnings(utils::download.file(url, method = method, ...))
 
     } else {
 
-      if (is_r32 && capabilities("libcurl")) {
+      if (capabilities("libcurl")) {
 
         method <- "libcurl"
 

data-raw/00-reencode_text.R

@@ -1,61 +1,5 @@
-library(tidyverse)
-library(here)
 library(yaml)
-library(stringi)
 
-reencode_utf8 <- function(x) {
+y <- yaml::read_yaml(here::here("data-raw/translations_source.yml"), fileEncoding = "UTF-8")
 
-  # Ensure that we encode non-UTF-8 strings to UTF-8 in a
-  # two-step process: (1) to native encoding, and then
-  # (2) to UTF-8
-  if (Encoding(x) != 'UTF-8') {
-    x <- enc2utf8(x)
-  }
-
-  # Use `iconv()` to convert to UTF-32 (big endian) as
-  # raw bytes and convert again to integer (crucial here
-  # to set the base to 16 for this conversion)
-  raw_bytes <-
-    iconv(x, "UTF-8", "UTF-32BE", toRaw = TRUE) %>%
-    unlist() %>%
-    strtoi(base = 16L)
-
-  # Split into a list of four bytes per element
-  chars <- split(raw_bytes, ceiling(seq_along(raw_bytes) / 4))
-
-  x <-
-    vapply(
-      chars,
-      FUN.VALUE = character(1),
-      USE.NAMES = FALSE,
-      FUN = function(x) {
-
-        bytes_nz <- x[min(which(x > 0)):length(x)]
-
-        if (length(bytes_nz) > 2) {
-          out <- paste("\\U", paste(as.hexmode(x), collapse = ""), sep = "")
-        } else if (length(bytes_nz) > 1) {
-          out <- paste("\\u", paste(as.hexmode(bytes_nz), collapse = ""), sep = "")
-        } else if (length(bytes_nz) == 1 && bytes_nz > 127) {
-          out <- paste("\\u", sprintf("%04s", paste(as.hexmode(bytes_nz)), collapse = ""), sep = "")
-        } else {
-          out <- rawToChar(as.raw(bytes_nz))
-        }
-        out
-      }
-    ) %>%
-    paste(collapse = "")
-
-  x
-}
-
-y <- yaml::read_yaml(here::here("data-raw/translations_source.yml"))
-
-# Obtain a list that reencodes all translation text to Unicode
-# code points
-translations_list <-
-  lapply(y, lapply, lapply, function(x) {
-    reencode_utf8(x) %>% stringi::stri_unescape_unicode()
-    })
-
-saveRDS(translations_list, file = here("inst/text/translations_built"))
+saveRDS(y, file = here::here("inst/text/translations_built"))

data-raw/translations_source.yml

@@ -1531,7 +1531,7 @@ table_scan:
     nl: "**pointblank** Versie"
   tbl_lab_r_version:
     en: "**R** Version"
-    fr: "version **R**"
+    fr: "Version **R**"
     de: "**R** Version"
     it: "versione **R**"
     es: "Versión **R**"
@@ -1545,7 +1545,7 @@ table_scan:
     nl: "**R**-versie"
   tbl_lab_system_os:
     en: "Operating System"
-    fr: "Système opérateur"
+    fr: "Système d'exploitation"
     de: "Betriebssystem"
     it: "Sistema operativo"
     es: "Sistema operativo"
@@ -1559,7 +1559,7 @@ table_scan:
     nl: "Besturingssysteem"
   tbl_lab_distinct:
     en: "Distinct"
-    fr: "valeurs uniques"
+    fr: "Valeurs uniques"
     de: "Einzigartige Werte"
     it: "Valori unici"
     es: "Valores únicos"
@@ -1782,19 +1782,19 @@ table_scan:
     sv: "Andra värden"
     nl: "Andere waarden"
   footer_text_fragment:
-    en: "Table scan generated with <a href=\"https://www.github.com/rstudio/pointblank\">pointblank</a>."
-    fr: "Scan de tableau généré avec <a href=\"https://www.github.com/rstudio/pointblank\">pointblank</a>."
-    de: "Mit <a href=\"https://www.github.com/rstudio/pointblank\">pointblank</a> generierter Scan der Tabelle."
-    it: "Scansione della tabella generata con <a href=\"https://www.github.com/rstudio/pointblank\">pointblank</a>."
-    es: "Escaneo de Tabla generado con <a href=\"https://www.github.com/rstudio/pointblank\">pointblank</a>."
-    pt: "Examen da tabela gerada com <a href=\"https://www.github.com/rstudio/pointblank\">pointblank</a>."
-    tr: "<a href=\"https://www.github.com/rstudio/pointblank\">pointblank</a> ile oluşturulan tablo taraması."
-    zh: "通过 <a href=\"https://www.github.com/rstudio/pointblank\">pointblank</a>建立表扫描。"
-    ru: "Сканирование таблиц, сгенерированное с помощью <a href=\"https://www.github.com/rstudio/pointblank\">pointblank</a>."
-    pl: "Skan tabeli wygenerowany za pomoca <a href=\"https://www.github.com/rstudio/pointblank\">pointblank</a>."
-    da: "Scan af tabel genereret med <a href=\"https://www.github.com/rstudio/pointblank\">pointblank</a>."
-    sv: "Genomsökning av tabellen genereras med <a href=\"https://www.github.com/rstudio/pointblank\">pointblank</a>."
-    nl: "Scan van tabel gegenereerd met <a href=\"https://www.github.com/rstudio/pointblank\">pointblank</a>."
+    en: "Table scan generated with <a href=\"https://github.com/rstudio/pointblank\">pointblank</a>."
+    fr: "Scan de tableau généré avec <a href=\"https://github.com/rstudio/pointblank\">pointblank</a>."
+    de: "Mit <a href=\"https://github.com/rstudio/pointblank\">pointblank</a> generierter Scan der Tabelle."
+    it: "Scansione della tabella generata con <a href=\"https://github.com/rstudio/pointblank\">pointblank</a>."
+    es: "Escaneo de Tabla generado con <a href=\"https://github.com/rstudio/pointblank\">pointblank</a>."
+    pt: "Examen da tabela gerada com <a href=\"https://github.com/rstudio/pointblank\">pointblank</a>."
+    tr: "<a href=\"https://github.com/rstudio/pointblank\">pointblank</a> ile oluşturulan tablo taraması."
+    zh: "通过 <a href=\"https://github.com/rstudio/pointblank\">pointblank</a>建立表扫描。"
+    ru: "Сканирование таблиц, сгенерированное с помощью <a href=\"https://github.com/rstudio/pointblank\">pointblank</a>."
+    pl: "Skan tabeli wygenerowany za pomoca <a href=\"https://github.com/rstudio/pointblank\">pointblank</a>."
+    da: "Scan af tabel genereret med <a href=\"https://github.com/rstudio/pointblank\">pointblank</a>."
+    sv: "Genomsökning av tabellen genereras med <a href=\"https://github.com/rstudio/pointblank\">pointblank</a>."
+    nl: "Scan van tabel gegenereerd met <a href=\"https://github.com/rstudio/pointblank\">pointblank</a>."
 multiagent_report:
   pointblank_multiagent_title_text:
     en: "Pointblank Validation Series"

inst/translations/ES/_pkgdown.yml

@@ -5,7 +5,7 @@ lang: es
 home:
   strip_header: true
 
-url: https://rich-iannone.github.io/pointblank/es
+url: https://rstudio.github.io/pointblank/es
 
 template:
   bootstrap: 5
@@ -87,7 +87,7 @@ reference:
     - conjointly
     - serially
     - specially
-    
+
   - title: Funciones de información
     desc: >
       Podemos añadir progresivamente información a un objeto *informant*
@@ -112,7 +112,7 @@ reference:
     - snip_stats
     - snip_lowest
     - snip_highest
-    
+
   - title: Creación de correo electrónico
     desc: >
       A veces queremos enviar por correo electrónico un informe de una
@@ -125,7 +125,7 @@ reference:
     - email_create
     - stock_msg_body
     - stock_msg_footer
-    
+
   - title: Registro
     desc: >
       El registro de las condiciones de fallo de validación es una buena
@@ -149,7 +149,7 @@ reference:
     contents:
     - interrogate
     - get_agent_report
-    
+
   - title: "El informante: incorporar e informar"
     desc: >
       Si tenemos un objeto *informante* que ha sido cargado con información
@@ -161,7 +161,7 @@ reference:
     contents:
     - incorporate
     - get_informant_report
-    
+
   - title: Después del interrogatorio
     desc: >
       El objeto `agente` siempre tiene una lista especial llamada 'x-list'.
@@ -180,7 +180,7 @@ reference:
     - get_sundered_data
     - all_passed
     - write_testthat_file
-    
+
   - title: Operaciones con objetos
     desc: >
       Tenemos opciones para escribir un agente o informante en el disco con
@@ -201,7 +201,7 @@ reference:
     - activate_steps
     - deactivate_steps
     - remove_steps
-    
+
   - title: El Multiagente
     desc: >
       El objeto `multiagente` es un grupo de agentes, cada uno de los
@@ -218,7 +218,7 @@ reference:
     - create_multiagent
     - read_disk_multiagent
     - get_multiagent_report
-  
+
   - title: pointblank YAML
     desc: >
       Los archivos YAML pueden ser utilizados en **pointblank** para dos
@@ -238,7 +238,7 @@ reference:
     - yaml_agent_show_exprs
     - yaml_informant_incorporate
     - yaml_exec
-    
+
   - title: Table Transformers
     desc: >
       Las funciones del **Table Transformers** pueden transformar
@@ -259,7 +259,7 @@ reference:
     - tt_time_shift
     - tt_time_slice
     - get_tt_param
-    
+
   - title: Funciones de utilidad y ayuda
     contents:
     - col_schema
@@ -268,15 +268,15 @@ reference:
     - affix_datetime
     - stop_if_not
     - from_github
-    
+
   - title: Conjuntos de datos
     contents:
     - small_table
     - small_table_sqlite
     - specifications
     - game_revenue
     - game_revenue_info
-    
+
 navbar:
   type: default
   left:
@@ -307,7 +307,7 @@ navbar:
   - text: News
     href: news/index.html
   - text: In English
-    href: https://rich-iannone.github.io/pointblank
+    href: https://rstudio.github.io/pointblank
 
 development:
   version_tooltip: "Development version"

inst/translations/ES/vignettes/INFO-1.Rmd

@@ -78,7 +78,7 @@ informant <-
     section_name = "further information", 
     `examples and documentation` = "Examples for how to use the `info_*()` functions
     (and many more) are available at the 
-    [**pointblank** site](https://rich-iannone.github.io/pointblank/)."
+    [**pointblank** site](https://rstudio.github.io/pointblank/)."
   )
 
 informant

inst/translations/ES/vignettes/VALID-V.Rmd

@@ -43,6 +43,6 @@ Just as with all the other workflows, the `tbl` supplied could be a data frame,
 
 # Languages and Locales
 
-The reporting generated by `scan_data()` can be presented in one of eight spoken languages: English (`"en"`, the default), French (`"fr"`), German (`"de"`), Italian (`"it"`), Spanish (`"es"`), Portuguese, (`"pt"`), Chinese (`"zh"`), and Russian (`"ru"`). These two-letter language codes can be used as an argument to the `lang` argument. When applied, all label text and other non-data elements will be set to the language of choice. We have checked the translations with native speakers of the respective languages but if you find an error that should be corrected, please [file an issue](https://github.com/rich-iannone/pointblank/issues).
+The reporting generated by `scan_data()` can be presented in one of eight spoken languages: English (`"en"`, the default), French (`"fr"`), German (`"de"`), Italian (`"it"`), Spanish (`"es"`), Portuguese, (`"pt"`), Chinese (`"zh"`), and Russian (`"ru"`). These two-letter language codes can be used as an argument to the `lang` argument. When applied, all label text and other non-data elements will be set to the language of choice. We have checked the translations with native speakers of the respective languages but if you find an error that should be corrected, please [file an issue](https://github.com/rstudio/pointblank/issues).
 
 Along with translations, numerical values that are generated as part of the reporting (e.g., table dimensions, summary statistics, etc.) are automatically formatted in the locale of the language (given in `lang`). This can be overridden with the `locale` argument which accepts a locale ID. Examples include `"en_US"` for English (United States) and `"fr_FR"` for French (France). More simply, this can be a language identifier without a country designation, like `"es"` for Spanish (Spain, same as `"es_ES"`). More than 700 locales are currently accepted.

tests/testthat/_snaps/draft_validation.md

@@ -283,7 +283,7 @@
     Code
       readLines(con = path) %>% paste0(collapse = "\n")
     Output
-      [1] "library(pointblank)\n\nagent <-\n  create_agent(\n    tbl = ~ tbl,\n    actions = action_levels(\n      warn_at = 0.05,\n      stop_at = 0.10\n    ),\n    tbl_name = \"tbl\",\n    label = \"Validation plan generated by `draft_validation()`.\",\n    lang = \"fr\",\n    locale = \"fr\"\n  ) %>%\n  # Attendez-vous à ce que la colonne `a` soit de type: integer\n  col_is_integer(\n    columns = c(\"a\")\n  ) %>%\n  # Attendez-vous à ce que les valeurs de `a` soient comprises entre `1` et `8`\n  col_vals_between(\n    columns = c(\"a\"),\n    left = 1,\n    right = 8\n  ) %>%\n  # Attendez-vous à ce que la colonne `b` soit de type: character\n  col_is_character(\n    columns = c(\"b\")\n  ) %>%\n  # Attendez-vous à ce que la colonne `c` soit de type: numeric\n  col_is_numeric(\n    columns = c(\"c\")\n  ) %>%\n  # Attendez-vous à ce que les valeurs de `c` soient comprises entre `2` et `9`\n  col_vals_between(\n    columns = c(\"c\"),\n    left = 2,\n    right = 9,\n    na_pass = TRUE\n  ) %>%\n  # Attendez-vous à ce que la colonne `d` soit de type: numeric\n  col_is_numeric(\n    columns = c(\"d\")\n  ) %>%\n  # Attendez-vous à ce que les valeurs de `d` soient comprises entre `108.34` et `9999.99`\n  col_vals_between(\n    columns = c(\"d\"),\n    left = 108.34,\n    right = 9999.99\n  ) %>%\n  # Attendez-vous à ce que la colonne `e` soit de type: logical\n  col_is_logical(\n    columns = c(\"e\")\n  ) %>%\n  # Attendez-vous à ce que la colonne `f` soit de type: character\n  col_is_character(\n    columns = c(\"f\")\n  ) %>%\n  # Attendez-vous à ce que les schémas de colonnes correspondent\n  col_schema_match(\n    schema = col_schema(\n      date_time = c(\"POSIXct\", \"POSIXt\"),\n      date = \"Date\",\n      a = \"integer\",\n      b = \"character\",\n      c = \"numeric\",\n      d = \"numeric\",\n      e = \"logical\",\n      f = \"character\"\n    )\n  ) %>%\n  interrogate()\n\nagent"
+      [1] "library(pointblank)\n\nagent <-\n  create_agent(\n    tbl = ~ tbl,\n    actions = action_levels(\n      warn_at = 0.05,\n      stop_at = 0.10\n    ),\n    tbl_name = \"tbl\",\n    label = \"Validation plan generated by `draft_validation()`.\",\n    lang = \"fr\",\n    locale = \"fr\"\n  ) %>%\n  # On s'attend à ce que la colonne `a` soit de type : integer\n  col_is_integer(\n    columns = c(\"a\")\n  ) %>%\n  # On s'attend à ce que les valeurs de `a` soient comprises entre `1` et `8`\n  col_vals_between(\n    columns = c(\"a\"),\n    left = 1,\n    right = 8\n  ) %>%\n  # On s'attend à ce que la colonne `b` soit de type : character\n  col_is_character(\n    columns = c(\"b\")\n  ) %>%\n  # On s'attend à ce que la colonne `c` soit de type : numeric\n  col_is_numeric(\n    columns = c(\"c\")\n  ) %>%\n  # On s'attend à ce que les valeurs de `c` soient comprises entre `2` et `9`\n  col_vals_between(\n    columns = c(\"c\"),\n    left = 2,\n    right = 9,\n    na_pass = TRUE\n  ) %>%\n  # On s'attend à ce que la colonne `d` soit de type : numeric\n  col_is_numeric(\n    columns = c(\"d\")\n  ) %>%\n  # On s'attend à ce que les valeurs de `d` soient comprises entre `108.34` et `9999.99`\n  col_vals_between(\n    columns = c(\"d\"),\n    left = 108.34,\n    right = 9999.99\n  ) %>%\n  # On s'attend à ce que la colonne `e` soit de type : logical\n  col_is_logical(\n    columns = c(\"e\")\n  ) %>%\n  # On s'attend à ce que la colonne `f` soit de type : character\n  col_is_character(\n    columns = c(\"f\")\n  ) %>%\n  # On s'attend à ce que les schémas de colonnes correspondent\n  col_schema_match(\n    schema = col_schema(\n      date_time = c(\"POSIXct\", \"POSIXt\"),\n      date = \"Date\",\n      a = \"integer\",\n      b = \"character\",\n      c = \"numeric\",\n      d = \"numeric\",\n      e = \"logical\",\n      f = \"character\"\n    )\n  ) %>%\n  interrogate()\n\nagent"
 
 ---
 

tests/testthat/helper.R

@@ -4,3 +4,8 @@ expect_equal_unlist <- function(object, expected, ...) {
     expected
   )
 }
+
+skip_if_not_utf8 <- function() {
+  # likely on Windows for R < 4.2
+  skip_if_not(l10n_info()$`UTF-8`)
+}

tests/testthat/test-draft_validation.R

@@ -1,5 +1,4 @@
-skip_on_os(os = "windows")
-
+skip_on_cran()
 work_path <- "./generated_r_files"
 
 if (fs::dir_exists(path = work_path)) {
@@ -92,7 +91,7 @@ test_that("draft validations for data tables can be generated", {
 })
 
 test_that("draft validations for data tables can be generated in different languages", {
-
+  skip_if_not_utf8()
   write_draft_snapshot_test(dataset = pointblank::small_table, filename = "st_en", lang = "en")
   write_draft_snapshot_test(dataset = pointblank::small_table, filename = "st_fr", lang = "fr")
   write_draft_snapshot_test(dataset = pointblank::small_table, filename = "st_de", lang = "de")