Merge pull request #360 from deschen1/na_handling_loadWorkbook

Fixes #72 by adding an optional argument na.convert
ycphs · Jun 29, 2022 · 547640d · 547640d
2 parents 4f14a99 + 7a0219f
commit 547640d
Show file tree

Hide file tree

Showing 8 changed files with 468 additions and 153 deletions.
diff --git a/NEWS.md b/NEWS.md
@@ -1,9 +1,12 @@
 # openxlsx (development version)
 
+## Fixes
+
 * Fixed warning on `dataValidation(..., type = "list")` ([#342](https://github.com/ycphs/openxlsx/issues/342))
 
 ## Improvements
 
+* Added optional argument to `loadWorkbook` to decide if empty/blank cells should be converted to NA_character_ (the default) or left blank as is
 * Improve detectDates ([#288](https://github.com/ycphs/openxlsx/issues/288))
 * Add type blanks and not blanks to conditional formatting ([#311](https://github.com/ycphs/openxlsx/pull/311))
 

diff --git a/R/loadWorkbook.R b/R/loadWorkbook.R
@@ -7,6 +7,7 @@
 #' @param file A path to an existing .xlsx or .xlsm file
 #' @param xlsxFile alias for file
 #' @param isUnzipped Set to TRUE if the xlsx file is already unzipped
+#' @param na.convert Should empty/blank cells be converted to `NA_character_`. Defaults to TRUE.
 #' @description  loadWorkbook returns a workbook object conserving styles and
 #' formatting of the original .xlsx file.
 #' @return Workbook object.
@@ -25,7 +26,7 @@
 #' saveWorkbook(wb, "loadExample.xlsx", overwrite = TRUE)
 #' }
 #'
-loadWorkbook <- function(file, xlsxFile = NULL, isUnzipped = FALSE) {
+loadWorkbook <- function(file, xlsxFile = NULL, isUnzipped = FALSE, na.convert = TRUE) {
 
   ## If this is a unzipped workbook, skip the temp dir stuff
   if (isUnzipped) {
@@ -264,7 +265,9 @@ loadWorkbook <- function(file, xlsxFile = NULL, isUnzipped = FALSE) {
     vals <- getNodes(xml = sharedStrings, tagIn = "<si>")
 
     if ("<si><t/></si>" %in% vals) {
-      vals[vals == "<si><t/></si>"] <- "<si><t>NA</t></si>"
+      if (na.convert){
+        vals[vals == "<si><t/></si>"] <- "<si><t>NA</t></si>"
+      }
       Encoding(vals) <- "UTF-8"
       attr(vals, "uniqueCount") <- uniqueCount - 1L
     } else {

diff --git a/inst/extdata/na_convert.xlsx b/inst/extdata/na_convert.xlsx
diff --git a/man/loadWorkbook.Rd b/man/loadWorkbook.Rd
diff --git a/revdep/README.md b/revdep/README.md
@@ -2,55 +2,65 @@
 
 |field    |value                        |
 |:--------|:----------------------------|
-|version  |R version 4.1.2 (2021-11-01) |
+|version  |R version 4.1.3 (2022-03-10) |
 |os       |Ubuntu 18.04.6 LTS           |
 |system   |x86_64, linux-gnu            |
 |ui       |X11                          |
 |language |(EN)                         |
 |collate  |C.UTF-8                      |
 |ctype    |C.UTF-8                      |
 |tz       |UTC                          |
-|date     |2022-02-08                   |
+|date     |2022-03-20                   |
 |pandoc   |2.7.3 @ /usr/bin/pandoc      |
 
 # Dependencies
 
-|package  |old   |new        |Δ  |
-|:--------|:-----|:----------|:--|
-|openxlsx |4.2.5 |4.2.5.9000 |*  |
-|Rcpp     |1.0.8 |1.0.8      |   |
-|stringi  |1.7.6 |1.7.6      |   |
-|zip      |2.2.0 |2.2.0      |   |
+|package  |old     |new        |Δ  |
+|:--------|:-------|:----------|:--|
+|openxlsx |4.2.5   |4.2.5.9000 |*  |
+|Rcpp     |1.0.8.3 |1.0.8.3    |   |
+|stringi  |1.7.6   |1.7.6      |   |
+|zip      |2.2.0   |2.2.0      |   |
 
 # Revdeps
 
-## Failed to check (25)
+## Failed to check (35)
 
 |package        |version |error |warning |note |
 |:--------------|:-------|:-----|:-------|:----|
 |appreci8R      |?       |      |        |     |
 |artMS          |?       |      |        |     |
+|bibliometrix   |3.2.1   |1     |        |     |
 |BoneProfileR   |?       |      |        |     |
+|breakaway      |?       |      |        |     |
 |bruceR         |?       |      |        |     |
+|cbaf           |?       |      |        |     |
 |CHRONOS        |?       |      |        |     |
+|CNVPanelizer   |?       |      |        |     |
 |CoTiMA         |?       |      |        |     |
 |DAPAR          |?       |      |        |     |
 |ddPCRclust     |?       |      |        |     |
+|Ecfun          |?       |      |        |     |
+|fedup          |?       |      |        |     |
 |GA4GHshiny     |?       |      |        |     |
 |genekitr       |?       |      |        |     |
 |hypeR          |1.10.0  |1     |        |     |
-|isoreader      |?       |      |        |     |
 |maEndToEnd     |?       |      |        |     |
+|MatrixQCvis    |?       |      |        |     |
 |MicroSEC       |?       |      |        |     |
-|MSEtool        |?       |      |        |     |
 |nanotatoR      |?       |      |        |     |
+|openPrimeR     |?       |      |        |     |
 |parameters     |?       |      |        |     |
 |Pigengene      |?       |      |        |     |
 |PloGO2         |?       |      |        |     |
 |rbiom          |?       |      |        |     |
-|sangeranalyseR |1.4.0   |1     |1       |2    |
+|RIPAT          |?       |      |        |     |
+|sangeranalyseR |?       |      |        |     |
 |SEtools        |?       |      |        |     |
+|sigFeature     |?       |      |        |     |
+|struct         |?       |      |        |     |
 |structToolbox  |?       |      |        |     |
+|TarSeqQC       |?       |      |        |     |
 |TPP            |3.22.1  |1     |        |3    |
 |uncoverappLib  |?       |      |        |     |
 
diff --git a/revdep/cran.md b/revdep/cran.md
@@ -1,6 +1,6 @@
 ## revdepcheck results
 
-We checked 138 reverse dependencies (0 from CRAN + 138 from Bioconductor), comparing R CMD check results across CRAN and dev versions of this package.
+We checked 141 reverse dependencies (0 from CRAN + 141 from Bioconductor), comparing R CMD check results across CRAN and dev versions of this package.
 
  * We saw 0 new problems
  * We failed to check 0 packages