Build off of {officer}

[matt-dray]

Use officer::docx_summary() to get the basics out, like the text and the doc styles. Then we can supply the appropriate markdown.

library(officer)
path <- r"{C:\Users\matt.dray\Documents\Temp\demo.docx}"
doc <- read_docx(path)
content <- docx_summary(doc)

markup_map <- c(
  "Title"     = "#",
  "heading 1" = "##",
  "heading 2" = "###",
  "heading 3" = "####"
)

content$markup <- markup_map[content$style_name]

content$govspeak <- ifelse(
  !is.na(content$markup),
  paste(content$markup, content$text),
  content$text
)

content$govspeak
# [1] "# This is the title"                                                        
# [2] "## This is a heading 1"                                                     
# [3] "This is some text. This is in bold. This is in italics. This is underlined."

But the font styles are missing from the {officer} output (unless there's a way to turn on this functionality?). So might have to dig into the unzipped docx file with e.g. wordup::wu_read(). We can then grab the styles, even if it is a bit awkward (remembering that some styles aren't accepted on GOV.UK, see #7).

body_list <- wordup::wu_read(path)
str(body_list, give.attr = FALSE, max.level = 3)

lapply(
  1:6,
  function(x) {
    list(
      text = body_list$document$body[[3]][[x]][["t"]][[1]],
      style = names(body_list$document$body[[3]][[x]][["rPr"]])[[1]]
    )
  }
)
# [[1]]
# [[1]]$text
# [1] "This is some text. "
# 
# [[1]]$style
# NULL
# 
# 
# [[2]]
# [[2]]$text
# [1] "This is in bold."
# 
# [[2]]$style
# [1] "b"
# 
# 
# [[3]]
# [[3]]$text
# [1] " "
# 
# [[3]]$style
# NULL
# 
# 
# [[4]]
# [[4]]$text
# [1] "This is in italics."
# 
# [[4]]$style
# [1] "i"
# 
# 
# [[5]]
# [[5]]$text
# [1] " "
# 
# [[5]]$style
# NULL
# 
# 
# [[6]]
# [[6]]$text
# [1] "This is underlined."
# 
# [[6]]$style
# [1] "u"

It's then a case of pasting like **This is bold**, since the text was recognised as 'b' style (italics was 'i', underlined was 'u').