fix: Critical bug fixes and typo corrections

.github/workflows/R-CMD-check-all.yaml

@@ -0,0 +1,53 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+    branches: [main, master]
+
+name: R-CMD-check-all.yaml
+
+permissions: read-all
+
+jobs:
+  R-CMD-check:
+    runs-on: ${{ matrix.config.os }}
+
+    name: ${{ matrix.config.os }} (${{ matrix.config.r }})
+
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - {os: macos-latest,   r: 'release'}
+          - {os: windows-latest, r: 'release'}
+          - {os: ubuntu-latest,   r: 'devel', http-user-agent: 'release'}
+          - {os: ubuntu-latest,   r: 'release'}
+          - {os: ubuntu-latest,   r: 'oldrel-1'}
+
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+      R_KEEP_PKG_SOURCE: yes
+      COMPILE_VIG: ${{ secrets.COMPILE_VIG }}
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: r-lib/actions/setup-pandoc@v2
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          r-version: ${{ matrix.config.r }}
+          http-user-agent: ${{ matrix.config.http-user-agent }}
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::rcmdcheck
+          needs: check
+
+      - uses: r-lib/actions/check-r-package@v2
+        with:
+          upload-snapshots: true
+          build_args: 'c("--no-manual","--compact-vignettes=gs+qpdf")'

.github/workflows/R-CMD-check.yaml

@@ -1,10 +1,6 @@
 # Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
 # Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
 on:
-  push:
-    branches: [main, master]
-  pull_request:
-    branches: [main, master]
   schedule:
     - cron: "15 15 * * *"
 
@@ -23,10 +19,6 @@ jobs:
       matrix:
         config:
           - {os: macos-latest,   r: 'release'}
-          - {os: windows-latest, r: 'release'}
-          - {os: ubuntu-latest,   r: 'devel', http-user-agent: 'release'}
-          - {os: ubuntu-latest,   r: 'release'}
-          - {os: ubuntu-latest,   r: 'oldrel-1'}
 
     env:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}

R/cansim.R

@@ -2,13 +2,13 @@
 #'
 #' Facilitates working with Statistics Canada data table values retrieved using the package by setting all units to counts/dollars instead of millions, etc. If "replacement_value" is not set, it will replace the \code{VALUE} field with normalized values and drop the \code{scale} column. Otherwise it will keep the scale columns and create a new column named replacement_value with the normalized value. It will attempt to parse the \code{REF_DATE} field and create an R date variable. This is currently experimental.
 #'
-#' @param data A retrieved data table as returned from \code{get_cansim()} pr \code{get_cansim_ndm()}
+#' @param data A retrieved data table as returned from \code{get_cansim()} or \code{get_cansim_ndm()}
 #' @param replacement_value (Optional) the name of the column the manipulated value should be returned in. Defaults to "val_norm"
 #' @param normalize_percent (Optional) When \code{TRUE} (the default) normalizes percentages by changing them to rates
 #' @param default_month The default month that should be used when creating Date objects for annual data (default set to "01")
 #' @param default_day The default day of the month that should be used when creating Date objects for monthly data (default set to "01")
 #' @param factors (Optional) Logical value indicating if dimensions should be converted to factors. (Default set to \code{TRUE}).
-#' @param strip_classification_code (strip_classification_code) Logical value indicating if classification code should be stripped
+#' @param strip_classification_code Logical value indicating if classification code should be stripped
 #' from names. (Default set to \code{FALSE}, if \code{factors=TRUE} this is overridden and set to \code{TRUE}).
 #' @param cansimTableNumber (Optional) Only needed when operating on results of SQLite connections.
 #' @param internal (Optional) Flag to indicate that this function is called internally.
@@ -746,7 +746,7 @@ get_cansim_column_categories <- function(cansimTableNumber, column, language="en
       dplyr::pull(!!as.name(dimension_id_column))
     data_path <- paste0(base_path_for_table_language(cleaned_number,language),".Rda_column_",column_index)
     if (!file.exists(data_path)){
-      stop(paste0("Unkown column ",column),call.=FALSE)
+      stop(paste0("Unknown column ",column),call.=FALSE)
     }
     result <- readRDS(file=data_path)
   } else {
@@ -781,7 +781,7 @@ get_cansim_column_categories <- function(cansimTableNumber, column, language="en
                     exceeded_hierarchy_warning_message=exceeded_hierarchy_warning_message)
 
     if (nrow(result)==0){
-      stop(paste0("Unkown column ",column),call.=FALSE)
+      stop(paste0("Unknown column ",column),call.=FALSE)
     }
   }
 

R/cansim_helpers.R

@@ -41,7 +41,7 @@ table_base_path <- function(cansimTableNumber) {
 
 file_path_for_table_language <- function(cansimTableNumber, language){
   language <- cleaned_ndm_language(language)
-  if (is.na(language)) stop(paste0("Unkown Lanaguage ",language),call.=FALSE)
+  if (is.na(language)) stop(paste0("Unknown Lanaguage ",language),call.=FALSE)
   base_table <- naked_ndm_table_number(cansimTableNumber)
   file.path(paste0(base_table,"-",language))
 }
@@ -88,7 +88,7 @@ get_with_timeout_retry <- function(url,timeout=200,retry=3,path=NA,warn_only=FAL
     if ("curl_error_peer_failed_verification" %in% class(response$error)) {
       stop(stringr::str_wrap(gsub(".+\\): ","",as.character(response$error),80)),"\n",
            "This means that the authenticity of the StatCan API server can't be verified.\n",
-           "Statistics Canada has a history of failty SSL certificats on their API,\n",
+           "Statistics Canada has a history of faulty SSL certificats on their API,\n",
            "if you are reasonably sure that your connection is not getting hijacked you\n",
            "can disable peer checking for the duration of the R session by typing\n\n",
            "httr::set_config(httr::config(ssl_verifypeer=0,ssl_verifystatus=0))","\n\n","into the console.",call.=FALSE)
@@ -138,7 +138,7 @@ post_with_timeout_retry <- function(url,body,timeout=200,retry=3,warn_only=FALSE
     if ("curl_error_peer_failed_verification" %in% class(response$error)) {
       stop(stringr::str_wrap(gsub(".+\\): ","",as.character(response$error),80)),"\n",
            "This means that the authenticity of the StatCan API server can't be verified.\n",
-           "Statistics Canada has a history of failty SSL certificats on their API,\n",
+           "Statistics Canada has a history of faulty SSL certificats on their API,\n",
            "if you are reasonably sure that your connection is not getting hijacked you\n",
            "can disable peer checking for the duration of the R session by typing\n\n",
            "httr::set_config(httr::config(ssl_verifypeer=0,ssl_verifystatus=0))","\n\n","into the console.",call.=FALSE)
@@ -359,7 +359,7 @@ transform_value_column <- function(data,value_column){
         dplyr::mutate(!!value_column:=as.numeric(!!as.name(value_column)))
     }
   } else {
-    warning("Unkown table type")
+    warning("Unknown table type")
   }
   data
 }

R/cansim_metadata.R

@@ -390,7 +390,7 @@ get_cansim_table_template <- function(cansimTableNumber, language="english",refr
     mutate(cansimTableNumber=!!cansimTableNumber,.before="COORDINATE")
 
   attr(result, "cansimTableNumber") <- cansimTableNumber
-  attr(result, "langauge") <- language
+  attr(result, "language") <- language
 
   result
 }

R/cansim_parquet.R

@@ -179,7 +179,7 @@ get_cansim_connection <- function(cansimTableNumber,
     }
 
 
-    hd <- header[duplicated(toupper(header))]
+    hd <- header[duplicated(toupper(header)) | duplicated(toupper(header), fromLast = TRUE)]
 
     if (length(hd)>0) {
       dupes <- header[toupper(header) %in% hd]
@@ -616,7 +616,7 @@ list_cansim_cached_tables <- function(cache_path=Sys.getenv('CANSIM_CACHE_PATH')
   }
 
   result <- dplyr::tibble(path=dir(cache_path,"cansim_\\d+_parquet_eng|cansim_\\d+_parquet_fra|cansim_\\d+_feather_eng|cansim_\\d+_feather_fra|cansim_\\d+_sqlite_eng|cansim_\\d+_sqlite_fra")) %>%
-    dplyr::mutate(cansimTableNumber=gsub("^cansim_|_eng$|_fra$|_parquet_eng$|_parquet_fra|_feather_eng$|_feather_fra|_sqlite_eng$|_sqlte_fra$","",.data$path) %>% cleaned_ndm_table_number()) %>%
+    dplyr::mutate(cansimTableNumber=gsub("^cansim_|_eng$|_fra$|_parquet_eng$|_parquet_fra|_feather_eng$|_feather_fra|_sqlite_eng$|_sqlite_fra$","",.data$path) %>% cleaned_ndm_table_number()) %>%
     dplyr::mutate(dataFormat=case_when(grepl("_parquet",.data$path)~"parquet",
                                      grepl("_feather",.data$path)~"feather",
                                      grepl("_sqlite",.data$path)~"sqlite",

R/cansim_sql.R

@@ -25,7 +25,7 @@ TIME_FORMAT <- "%Y-%m-%d %H:%M:%S"
 #' con <- get_cansim_connection("34-10-0013", format="sqlite")
 #'
 #' # Work with the data connection
-#' gplimpse(con)
+#' glimpse(con)
 #'
 #' disconnect_cansim_sqlite(con)
 #' }

R/cansim_tables_list.R

@@ -110,7 +110,7 @@ list_cansim_cubes <- function(lite=FALSE,refresh=FALSE,quiet=FALSE){
       surveys_fr <- setNames(surveys$surveyFr,surveys$surveyCode)
       subjects <- get_cansim_code_set("subject")
       subjects_en <- setNames(subjects$subjectEn,subjects$subjectCode)
-      subjects_fr <- setNames(subjects$subjectEn,subjects$subjectCode)
+      subjects_fr <- setNames(subjects$subjectFr,subjects$subjectCode)
 
       if (lite) {
         r<-content %>%

R/cansim_vectors.R

@@ -519,7 +519,7 @@ get_cansim_data_for_table_coord_periods<-function(tableCoordinates, periods=NULL
   }
 
   attr(result,"language") <- cleaned_language
-  if (!is.null(failed_coordinates) && nrow(failed_coordinates > 0)) {
+  if (!is.null(failed_coordinates) && nrow(failed_coordinates) > 0) {
     regular_fails <- failed_coordinates %>%
       filter(substr(.data$cansimTableNumber,1,4) != CENSUS_TABLE_STARTING_STRING)
     census_fails <- failed_coordinates %>%