dir.create("assets/docx", recursive = TRUE, showWarnings = FALSE)
office_doc_link <- function(url){
  stopifnot(requireNamespace("htmltools", quietly = TRUE))
  htmltools::tags$p(  htmltools::tags$span("Download file "),
    htmltools::tags$a(basename(url), href = url), 
    htmltools::tags$span(" - view with"),
    htmltools::tags$a("office web viewer", target="_blank", 
      href = paste0("https://view.officeapps.live.com/op/view.aspx?src=", url)
      ), 
    style="text-align:center;font-style:italic;color:gray;"
    )
}
library(officer)
# Package `magrittr` makes officer usage easier.
library(magrittr)

Quick start

  1. Start with read_docx

Use the function read_docx() to create an R object representing a Word document.

The initial Word file can be specified with the path argument. If none is provided, this file will be an empty document located in the package directory. Formats and styles are defined in the initial file.

From the initial document, we will be able to use an object containing not only paragraph styles, character styles and table styles of the original document but also its content.

my_doc <- read_docx() 
styles_info(my_doc)
  1. Add elements to document

By default new content is added at the end of the document. To understand how to add content at any location in the document, see the later section about cursor manipulation.

Let's create an image from a plot...

src <- tempfile(fileext = ".png")
png(filename = src, width = 5, height = 6, units = 'in', res = 300)
barplot(1:10, col = 1:10)
dev.off()

...and add that image to the document along with some new text paragraphs and a table.

my_doc <- my_doc %>% 
  body_add_img(src = src, width = 5, height = 6, style = "centered") %>% 
  body_add_par("Hello world!", style = "Normal") %>% 
  body_add_par("", style = "Normal") %>% # blank paragraph
  body_add_table(iris, style = "table_template")
  1. Write the Word file

An (updated) Word file can be generated using the print() function with the target argument:

print(my_doc, target = "assets/docx/first_example.docx")
office_doc_link(url = paste0("https://davidgohel.github.io/officer/articles/", "assets/docx/first_example.docx"))

Adding elements

There are two types of functions for adding elements.

body_add_* functions

The paragraph is the main top container for content within a Word document. Note that tables are top container, they are at the same level as paragraphs. body_add_* functions are designed to add content as a top container: text as an entire paragraph, table, image, page break...

A title is a paragraph. To add a title, use body_add_par() with the style argument pointing to the corresponding title style.

Use the function styles_info() to see available styles:

read_docx() %>% styles_info() %>% 
  subset( style_type %in% "paragraph" )

It is important to understand that these style names are read in the initial file provided to read_docx(). A few comments:

if( require("ggplot2") ){
  gg <- ggplot(data = iris, aes(Sepal.Length, Petal.Length)) + 
    geom_point()

  read_docx() %>% 
    body_add_par(value = "Table of content", style = "heading 1") %>% 
    body_add_toc(level = 2) %>% 
    body_add_break() %>% 

    body_add_par(value = "dataset iris", style = "heading 2") %>% 
    body_add_table(value = head(iris), style = "table_template" ) %>% 

    body_add_par(value = "plot examples", style = "heading 1") %>% 
    body_add_gg(value = gg, style = "centered" ) %>% 

    print(target = "assets/docx/body_add_demo.docx")
}
if( require("ggplot2") ){
  office_doc_link( url = paste0( "https://davidgohel.github.io/officer/articles/", "assets/docx/body_add_demo.docx" ) )
}

slip_in_* functions

The slip_in_* functions are designed to add content inside an existing paragraph: text, image or seq field. The element is inserted either at the beginning or end of the paragraph (pos = c('after', 'before')). Available functions are the following:

img.file <- file.path( R.home("doc"), "html", "logo.jpg" )
read_docx() %>%
  body_add_par("R logo: ", style = "Normal") %>%
  slip_in_img(src = img.file, style = "strong", 
              width = .3, height = .3, pos = "after") %>% 
  slip_in_text(" - This is ", style = "strong", pos = "before") %>% 
  slip_in_seqfield(str = "SEQ Figure \u005C* ARABIC",
    style = 'strong', pos = "before") %>% 
  print(target = "assets/docx/slip_in_demo.docx")
office_doc_link( url = paste0( "https://davidgohel.github.io/officer/articles/", "assets/docx/slip_in_demo.docx" ) )

These have been implemented mostly to allow the addition of Word's special sequence fields (which facilitate numbering) at the beginning of paragraphs used as reference entries (e.g. a table or plot caption). See the section Table and image captions.

Cursor manipulation

A cursor is available and can be manipulated so that content can be added relative to its position with the body_add_* functions:

Cursor functions are the following:

In order to illustrate the cursor functions, a document made up of several paragraphs will be used (let's use officer for that).

read_docx() %>%
  body_add_par("paragraph 1", style = "Normal") %>%
  body_add_par("paragraph 2", style = "Normal") %>%
  body_add_par("paragraph 3", style = "Normal") %>%
  body_add_par("paragraph 4", style = "Normal") %>%
  body_add_par("paragraph 5", style = "Normal") %>%
  body_add_par("paragraph 6", style = "Normal") %>%
  body_add_par("paragraph 7", style = "Normal") %>%
  print(target = "assets/docx/init_doc.docx" )
office_doc_link( url = paste0( "https://davidgohel.github.io/officer/articles/", "assets/docx/init_doc.docx" ) )

Now, let's use init_doc.docx with read_docx() and manipulate its content with cursor functions.

doc <- read_docx(path = "assets/docx/init_doc.docx") %>%

  # default template contains only an empty paragraph
  # Using cursor_begin and body_remove, we can delete it
  cursor_begin() %>% body_remove() %>%

  # Let add text at the beginning of the
  # paragraph containing text "paragraph 4"
  cursor_reach(keyword = "paragraph 4") %>%
  slip_in_text("This is ", pos = "before", style = "Default Paragraph Font") %>%

  # move the cursor forward and end a section
  cursor_forward() %>%
  body_add_par("The section stop here", style = "Normal") %>%
  body_end_section(landscape = TRUE, continuous = FALSE) %>%

  # move the cursor at the end of the document
  cursor_end() %>%
  body_add_par("The document ends now", style = "Normal")

print(doc, target = "assets/docx/cursor.docx")
office_doc_link( url = paste0( "https://davidgohel.github.io/officer/articles/", "assets/docx/cursor.docx" ) )

Remove content

The function body_remove() lets you remove content from a Word document. This function used with cursor_* functions is a convenient tool to update an existing document.

For illustration purposes, we will generate a document that will be used as an initial document later when showing how to use body_remove().

library(officer)
library(magrittr)

str1 <- "Lorem ipsum dolor sit amet, consectetur adipiscing elit. " %>% 
  rep(20) %>% paste(collapse = "")
str2 <- "Drop that text" 
str3 <- "Aenean venenatis varius elit et fermentum vivamus vehicula. " %>% 
  rep(20) %>% paste(collapse = "")

my_doc <- read_docx()  %>% 
  body_add_par(value = str1, style = "Normal") %>% 
  body_add_par(value = str2, style = "centered") %>% 
  body_add_par(value = str3, style = "Normal") 

print(my_doc, target = "assets/docx/ipsum_doc.docx")

The file ipsum_doc.docx now exists and contains a paragraph containing text that text. In the following example, we will position the cursor on that paragraph and then delete it:

my_doc <- read_docx(path = "assets/docx/ipsum_doc.docx")  %>% 
  cursor_reach(keyword = "that text") %>% 
  body_remove()

print(my_doc, target = "assets/docx/ipsum_doc.docx")

The text search is made via xpath 1.0 and regular expressions are not supported.

office_doc_link( url = paste0( "https://davidgohel.github.io/officer/articles/", "assets/docx/ipsum_doc.docx" ) )

Replace content

The body_add_* functions let you replace content in a Word document.

For illustration purposes, we will generate a document that will be used as an initial document later.

my_doc <- read_docx()  %>% 
  body_add_par(value = str1, style = "Normal") %>% 
  body_add_par(value = str2, style = "centered") %>% 
  body_add_par(value = str3, style = "Normal") 

print(my_doc, target = "assets/docx/replace_template.docx")

The file replace_template.docx now exists and contains a paragraph containing text that text. In the following example, we will position the cursor on that paragraph and then replace it. Using pos = "on" will replace content where the cursor is with new content.

my_doc <- read_docx(path = "assets/docx/replace_template.docx")  %>% 
  cursor_reach(keyword = "that text") %>% 
  body_add_par(value = "This is a new paragraph.", style = "centered", pos = "on")

print(my_doc, target = "assets/docx/replace_doc.docx")

Search-and-replace

You can also use the body_replace_* functions to search-and-replace text. body_replace_text_at_bkm() replaces text at a bookmark:

doc <- read_docx() %>%
  body_add_par("centered text", style = "centered") %>%
  slip_in_text(". How are you", style = "strong") %>%
  body_bookmark("text_to_replace") %>%
  body_replace_text_at_bkm("text_to_replace", "not left aligned")

To do the same with headers and footers of the Word document, use functions headers_replace_text_at_bkm and footers_replace_text_at_bkm.

body_replace_all_text() will, depending on the options provided, replace text either at the cursor or in the entire document:

doc <- read_docx() %>%
  body_add_par("Placeholder one") %>%
  body_add_par("Placeholder two")

# Show text chunk at cursor
docx_show_chunk(doc)  # Output is 'Placeholder two'

# Simple search-and-replace at current cursor, with regex turned off
body_replace_all_text(doc, "Placeholder", "new", only_at_cursor = TRUE, fixed=TRUE)
docx_show_chunk(doc)  # Output is 'new two'

# Do the same, but in the entire document and ignoring case
body_replace_all_text(doc, "placeholder", "new", only_at_cursor = FALSE, ignore.case=TRUE)
cursor_backward(doc)
docx_show_chunk(doc) # Output is 'new one'

# Use regex : replace all words starting with "n" with the word "example"
body_replace_all_text(doc, "\\bn.*?\\b", "example")
docx_show_chunk(doc) # Output is 'example one'
office_doc_link( url = paste0( "https://davidgohel.github.io/officer/articles/", "assets/docx/replace_doc.docx" ) )

To do the same with headers and footers of the Word document, use functions headers_replace_all_text and footers_replace_all_text.

Sections

A section starts at the end of the previous section (or the beginning of the document if no preceding section exists). It stops where the section is declared.

Sections can be added to a document by using a set of functions:

To add content into a landscape section, you will need to :

  1. Declare an ending section just before the content to be displayed in landscape orientation. Use function body_end_section_continuous().
  2. Add the content to be displayed in landscape orientation.
  3. Declare an ending section just after the content to be displayed in landscape orientation. Use function body_end_section_landscape().
str1 <- "Lorem ipsum dolor sit amet, consectetur adipiscing elit. " %>% 
  rep(5) %>% paste(collapse = "")
str2 <- "Aenean venenatis varius elit et fermentum vivamus vehicula. " %>% 
  rep(5) %>% paste(collapse = "")

my_doc <- read_docx()  %>% 
  body_add_par(value = str1, style = "centered") %>% 
  body_end_section_continuous() %>% 
  body_add_par(value = str2, style = "centered") %>% 
  body_end_section_landscape() 
print(my_doc, target = "assets/docx/landscape_section.docx")
office_doc_link( url = paste0( "https://davidgohel.github.io/officer/articles/", "assets/docx/landscape_section.docx" ) )

To add content into a section with columns, you will need to :

  1. Declare an ending section just before the content to be displayed in landscape orientation. Use function body_end_section_continuous().
  2. Add the content to be displayed in landscape orientation.
  3. Declare an ending section just after the content to be displayed in landscape orientation. Use function body_end_section_columns().

Function slip_in_column_break() can be used to add a column break. As it starts a new column, it has to be used on the paragraph where the break happens. By default slip_in_column_break() insert a column break at the beginning of the paragraph where the cursor is.

my_doc <- read_docx()  %>% 
  body_end_section_continuous() %>% 
  body_add_par(value = str1, style = "centered") %>% 
  body_add_par(value = str2, style = "centered") %>% 
  slip_in_column_break() %>%
  body_add_par(value = str2, style = "centered") %>% 
  body_end_section_columns(widths = c(2,2), sep = TRUE, space = 1) 
print(my_doc, target = "assets/docx/columns_section.docx")
office_doc_link( url = paste0( "https://davidgohel.github.io/officer/articles/", "assets/docx/columns_section.docx" ) )

To add content into a section with columns and landscape orientation, you will need to :

  1. Declare an ending section just before the content to be displayed in landscape orientation. Use function body_end_section_continuous().
  2. Add the content to be displayed in landscape orientation.
  3. Declare an ending section just after the content to be displayed in landscape orientation. Use function body_end_section_columns_landscape().
my_doc <- read_docx()  %>% 
  body_end_section_continuous() %>% 
  body_add_par(value = str1, style = "Normal") %>% 
  body_add_par(value = str2, style = "Normal") %>% 
  body_end_section_columns_landscape(widths = c(3,3), sep = TRUE, space = 1) 
print(my_doc, target = "assets/docx/columns_landscape_section.docx")
office_doc_link( url = paste0( "https://davidgohel.github.io/officer/articles/", "assets/docx/columns_landscape_section.docx" ) )

The following example demonstrate all known usages:

my_doc <- read_docx()  %>% 
  body_add_par(value = "Default section", style = "heading 1") %>% 
  body_add_par(value = str1, style = "centered") %>% 
  body_add_par(value = str2, style = "centered") %>% 

  body_end_section_continuous() %>% 
  body_add_par(value = "Landscape section", style = "heading 1") %>% 
  body_add_par(value = str1, style = "centered") %>% 
  body_add_par(value = str2, style = "centered") %>% 
  body_end_section_landscape() %>% 

  body_add_par(value = "Columns", style = "heading 1") %>% 
  body_end_section_continuous() %>% 
  body_add_par(value = str1, style = "centered") %>% 
  body_add_par(value = str2, style = "centered") %>% 
  slip_in_column_break() %>%
  body_add_par(value = str1, style = "centered") %>% 
  body_end_section_columns(widths = c(2,2), sep = TRUE, space = 1) %>% 

  body_add_par(value = str1, style = "Normal") %>% 
  body_add_par(value = str2, style = "Normal") %>% 
  slip_in_column_break() %>%
  body_end_section_columns_landscape(widths = c(3,3), sep = TRUE, space = 1)

print(my_doc, target = "assets/docx/section.docx")
office_doc_link( url = paste0( "https://davidgohel.github.io/officer/articles/", "assets/docx/section.docx" ) )

Table and image captions

slip_in_seqfield() and slip_in_text() can be combined to prefix a paragraph with references (i.e. chapter number and graphic index in the document). However, producing a plot or a table and its caption can be verbose.

Shortcut functions are implemented in the object shortcuts (it will at least give you a template of code to modify if it does not fit your needs exactly). slip_in_tableref(), slip_in_plotref() and body_add_gg() can make life easier.

Usage of these functions is illustrated below:

library(magrittr)
library(officer)
if( require("ggplot2") ){

gg1 <- ggplot(data = iris, aes(Sepal.Length, Petal.Length)) + 
  geom_point()
gg2 <- ggplot(data = iris, aes(Sepal.Length, Petal.Length, color = Species)) + 
  geom_point()


doc <- read_docx() %>% 
  body_add_par(value = "Table of content", style = "heading 1") %>% 
  body_add_toc(level = 2) %>% 

  body_add_par(value = "Tables", style = "heading 1") %>% 
  body_add_par(value = "dataset mtcars", style = "heading 2") %>% 
  body_add_table(value = head(mtcars)[, 1:4], style = "table_template" ) %>% 
  body_add_par(value = "data mtcars", style = "table title") %>% 
  shortcuts$slip_in_tableref(depth = 2) %>%

  body_add_par(value = "dataset iris", style = "heading 2") %>% 
  body_add_table(value = head(iris), style = "table_template" ) %>% 
  body_add_par(value = "data iris", style = "table title") %>% 
  shortcuts$slip_in_tableref(depth = 2) %>%

  body_end_section(continuous = FALSE, landscape = FALSE ) %>% 

  body_add_par(value = "plot examples", style = "heading 1") %>% 
  body_add_gg(value = gg1, style = "centered" ) %>% 
  body_add_par(value = "graph example 1", style = "graphic title") %>% 
  shortcuts$slip_in_plotref(depth = 1) %>%

  body_add_par(value = "plot 2", style = "heading 2") %>% 
  body_add_gg(value = gg2, style = "centered" ) %>% 
  body_add_par(value = "graph example 2", style = "graphic title") %>% 
  shortcuts$slip_in_plotref(depth = 2) %>%

  body_end_section(continuous = FALSE, landscape = TRUE) %>% 

  body_add_par(value = "Table of tables", style = "heading 2") %>% 
  body_add_toc(style = "table title") %>% 
  body_add_par(value = "Table of graphics", style = "heading 2") %>% 
  body_add_toc(style = "graphic title")

print(doc, target = "assets/docx/toc_and_captions.docx")
}
if( require("ggplot2") ){
  office_doc_link( url = paste0( "https://davidgohel.github.io/officer/articles/", "assets/docx/toc_and_captions.docx" ) )
}


davidgohel/oxbase documentation built on July 30, 2018, 4:57 a.m.