01-create-yaml.Rmd

---
title: "01-Create-yaml"
output:
  pdf_document: default
  html_document: default
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
library(stringr)
```

## R Markdown - Create YAML files for Bioc2022 website

### STEPS
* Original input file is google excel https://docs.google.com/spreadsheets/d/1tGtGffcbCRxQFjE3ej42IcWlN4FJCsuQeZvETt9g0oA/edit#gid=0
* Export this file as TSV. Save file in "input" folder. 
* NOTE - For the "time" column, set format to custom "hh:mm" (IMPORTANT)
* Import TSV file into R. Run the code
* Output files generated in "yaml_output" folder name


### import TSV file

```{r}

if ("googlesheets4" %in% installed.packages()[,"Package"]) {
    ## This option requires authentication with a google account
    ## No need to download the google spreadsheet
    ss <- 'https://docs.google.com/spreadsheets/d/1-jN59YPubMhsE0lKNl4d4HdIuO_sViKmjbDLIsyWuSI/edit#gid=0'
    google_sheet <- googlesheets4::read_sheet(ss, sheet = 1)
    scheduleBlank <- as.data.frame(google_sheet)
    scheduleBlank[is.na(scheduleBlank)] <- "" 
    
} else {
    
    file_path <- "https://docs.google.com/spreadsheets/d/1-jN59YPubMhsE0lKNl4d4HdIuO_sViKmjbDLIsyWuSI/edit#gid=0&single=true&output=tsv"
    schedule <- read.csv(file = file_path, 
                     sep = "\t", stringsAsFactors = F, 
                     na.strings = "")
    #use "" instead of NAs
    scheduleBlank <- schedule #make copy
    scheduleBlank[is.na(scheduleBlank)] <- "" 
}

##  datetime to character
scheduleBlank$time <- sub("^.+ (.+):00", "\\1", scheduleBlank$time)
```

## Create a directory to store ouptut

```{r}
output_dir <- "yaml_output/"
if (!file.exists(output_dir)) {
    dir.create(output_dir)
} else {
    ## Overwrite whatever output was generated before
    unlink(output_dir, recursive=TRUE)
    dir.create(output_dir)
}
    
```

### loop through each entry in the input file. While loop for easy debugging

```{r}
iCount = 1
while(iCount <= nrow(scheduleBlank)) {
  #print(paste("iCount=", iCount))
  
  oneRow <- scheduleBlank[iCount, ] #one row
  
  ## get file name ready 
  fileNameSpace <- paste(oneRow$day, "_",
                         oneRow$time, "_",
                         oneRow$session_type,"_",
                         oneRow$paper,
                         ".yaml", 
                         sep = "" )
  
  #replace space and semi-colon by underscore
  fileNameFinal <- str_replace_all(string = fileNameSpace, 
                                   pattern =  c(" |:"), 
                                   replacement =   '')
  
  ## There are some trailing underscores in names without the paper field
  ## that should be removed
  fileNameFinal <- sub("_.yaml$", ".yaml", fileNameFinal)
  
  #loop through each columns to create the yaml file 
  iCount2 = 1
  while(iCount2 <= ncol(oneRow)) {
    #print(paste("iCount2=", iCount2))
    
    # write key value pair into file
    
    oneValueName <- names(oneRow)[iCount2]
    oneValue <- paste("\"",unlist(oneRow[iCount2]),"\"", sep ="")
    
    if (any(grepl("paper", oneValue))) {
        oneValue <- sub("^\"(.+)\"$", "\\1", oneValue)
    }
    
    #write to file for the first time. Create new file
    if (iCount2 == 1) {
      #create file , no append
      line <- paste(oneValueName, ": ", oneValue, sep = "")
      write.table(line, col.names = FALSE, row.names = FALSE, 
                  file = paste(output_dir, 
                               fileNameFinal, sep=""), 
                  append = FALSE, 
                  quote = FALSE, )
      
    } else {
      #append to existing file
      line <- paste(oneValueName, ": ", oneValue, sep = "")
      write.table(line, col.names = FALSE, row.names = FALSE,
                  file = paste(output_dir, 
                               fileNameFinal, sep=""), 
                  append = TRUE, 
                  quote = FALSE)
    } # end of else
    
    iCount2 <- iCount2 + 1
  } #end of inside  loop
  
  iCount <- iCount + 1
} # end of outside loop

```