read content of a Word document and return a tidy dataset representing the document.

docx_summary(x)

Arguments

x

an rdocx object

Examples

example_pptx <- system.file(package = "officer", "doc_examples/example.docx") doc <- read_docx(example_pptx) docx_summary(doc)
#> doc_index content_type style_name #> 1 1 paragraph heading 1 #> 2 2 paragraph <NA> #> 3 3 paragraph heading 1 #> 4 4 paragraph List Paragraph #> 5 5 paragraph List Paragraph #> 6 6 paragraph List Paragraph #> 7 7 paragraph heading 2 #> 8 8 paragraph List Paragraph #> 9 9 paragraph List Paragraph #> 10 10 paragraph List Paragraph #> 11 11 paragraph <NA> #> 12 12 paragraph <NA> #> 13 13 paragraph heading 2 #> 14 14 paragraph <NA> #> 15 15 paragraph <NA> #> 1.1 16 table cell Light Shading #> 1.11 16 table cell Light Shading #> 1.12 16 table cell Light Shading #> 1.13 16 table cell Light Shading #> 1.14 16 table cell Light Shading #> 1.15 16 table cell Light Shading #> 1.16 16 table cell Light Shading #> 1.17 16 table cell Light Shading #> 1.18 16 table cell Light Shading #> 1.19 16 table cell Light Shading #> 1.110 16 table cell Light Shading #> 1.111 16 table cell Light Shading #> 1.112 16 table cell Light Shading #> 2.2 16 table cell Light Shading #> 2.31 16 table cell Light Shading #> 2.22 16 table cell Light Shading #> 2.23 16 table cell Light Shading #> 2.44 16 table cell Light Shading #> 2.25 16 table cell Light Shading #> 2.26 16 table cell Light Shading #> 2.27 16 table cell Light Shading #> 2.28 16 table cell Light Shading #> 2.29 16 table cell Light Shading #> 2.210 16 table cell Light Shading #> 2.211 16 table cell Light Shading #> 2.212 16 table cell Light Shading #> 3.3 16 table cell Light Shading #> 3.21 16 table cell Light Shading #> 3.32 16 table cell Light Shading #> 3.33 16 table cell Light Shading #> 3.24 16 table cell Light Shading #> 3.35 16 table cell Light Shading #> 3.36 16 table cell Light Shading #> 3.37 16 table cell Light Shading #> 3.38 16 table cell Light Shading #> 3.39 16 table cell Light Shading #> 3.310 16 table cell Light Shading #> 3.311 16 table cell Light Shading #> 3.312 16 table cell Light Shading #> 4.4 16 table cell Light Shading #> 4.41 16 table cell Light Shading #> 4.42 16 table cell Light Shading #> 4.43 16 table cell Light Shading #> 4.34 16 table cell Light Shading #> 4.45 16 table cell Light Shading #> 4.46 16 table cell Light Shading #> 4.47 16 table cell Light Shading #> 4.48 16 table cell Light Shading #> 4.49 16 table cell Light Shading #> 4.410 16 table cell Light Shading #> 4.411 16 table cell Light Shading #> 4.412 16 table cell Light Shading #> 16 17 paragraph <NA> #> 17 18 paragraph <NA> #> text #> 1 Title 1 #> 2 Lorem ipsum dolor sit amet, consectetur adipiscing elit. #> 3 Title 2 #> 4 Quisque tristique #> 5 Augue nisi, et convallis #> 6 Sapien mollis nec. #> 7 Sub title 1 #> 8 Quisque tristique #> 9 Augue nisi, et convallis #> 10 Sapien mollis nec. #> 11 #> 12 Phasellus nec nunc vitae nulla interdum volutpat eu ac massa. #> 13 Sub title 2 #> 14 Morbi rhoncus sapien sit amet leo eleifend, vel fermentum nisi mattis. #> 15 #> 1.1 Petals #> 1.11 5,621498349 #> 1.12 4,994616997 #> 1.13 4,767504884 #> 1.14 25,9242382 #> 1.15 6,489375001 #> 1.16 5,7858682 #> 1.17 5,645575295 #> 1.18 4,828953215 #> 1.19 6,783500773 #> 1.110 5,395076839 #> 1.111 4,683617783 #> 1.112 Note #> 2.2 Internode #> 2.31 <NA> #> 2.22 AA #> 2.23 <NA> #> 2.44 <NA> #> 2.25 25,21130805 #> 2.26 25,52433147 #> 2.27 Merged cell #> 2.28 <NA> #> 2.29 <NA> #> 2.210 <NA> #> 2.211 29,2459239 #> 2.212 <NA> #> 3.3 Sepal #> 3.21 2,46210657918,2034091 #> 3.32 2,429320759 #> 3.33 AAA #> 3.24 2,066051345 #> 3.35 2,901582763 #> 3.36 2,655642742 #> 3.37 2,278691288 #> 3.38 2,238467716 #> 3.39 2,202762147 #> 3.310 2,538375992 #> 3.311 2,601945544 #> 3.312 <NA> #> 4.4 Bract #> 4.41 <NA> #> 4.42 17,65204912 #> 4.43 <NA> #> 4.34 18,37915478 #> 4.45 17,3130473717,0721572418,2902189 #> 4.46 <NA> #> 4.47 <NA> #> 4.48 19,87376227 #> 4.49 19,85326662 #> 4.410 19,56545356 #> 4.411 18,95335451 #> 4.412 <NA> #> 16 #> 17 #> level num_id row_id is_header cell_id col_span row_span #> 1 NA NA NA NA NA NA NA #> 2 NA NA NA NA NA NA NA #> 3 NA NA NA NA NA NA NA #> 4 1 2 NA NA NA NA NA #> 5 1 2 NA NA NA NA NA #> 6 1 2 NA NA NA NA NA #> 7 NA NA NA NA NA NA NA #> 8 1 1 NA NA NA NA NA #> 9 1 1 NA NA NA NA NA #> 10 1 1 NA NA NA NA NA #> 11 NA NA NA NA NA NA NA #> 12 NA NA NA NA NA NA NA #> 13 NA NA NA NA NA NA NA #> 14 NA NA NA NA NA NA NA #> 15 NA NA NA NA NA NA NA #> 1.1 NA NA 1 TRUE 1 1 1 #> 1.11 NA NA 2 FALSE 1 2 1 #> 1.12 NA NA 3 FALSE 1 1 1 #> 1.13 NA NA 4 FALSE 1 1 1 #> 1.14 NA NA 5 FALSE 1 2 1 #> 1.15 NA NA 6 FALSE 1 1 1 #> 1.16 NA NA 7 FALSE 1 1 1 #> 1.17 NA NA 8 FALSE 1 1 1 #> 1.18 NA NA 9 FALSE 1 1 1 #> 1.19 NA NA 10 FALSE 1 1 1 #> 1.110 NA NA 11 FALSE 1 1 1 #> 1.111 NA NA 12 FALSE 1 1 1 #> 1.112 NA NA 13 FALSE 1 4 1 #> 2.2 NA NA 1 TRUE 2 1 1 #> 2.31 NA NA 2 FALSE 2 0 1 #> 2.22 NA NA 3 FALSE 2 1 2 #> 2.23 NA NA 4 FALSE 2 1 0 #> 2.44 NA NA 5 FALSE 2 0 1 #> 2.25 NA NA 6 FALSE 2 1 1 #> 2.26 NA NA 7 FALSE 2 1 1 #> 2.27 NA NA 8 FALSE 2 1 4 #> 2.28 NA NA 9 FALSE 2 1 0 #> 2.29 NA NA 10 FALSE 2 1 0 #> 2.210 NA NA 11 FALSE 2 1 0 #> 2.211 NA NA 12 FALSE 2 1 1 #> 2.212 NA NA 13 FALSE 2 0 1 #> 3.3 NA NA 1 TRUE 3 1 1 #> 3.21 NA NA 2 FALSE 3 2 1 #> 3.32 NA NA 3 FALSE 3 1 1 #> 3.33 NA NA 4 FALSE 3 2 1 #> 3.24 NA NA 5 FALSE 3 1 1 #> 3.35 NA NA 6 FALSE 3 1 1 #> 3.36 NA NA 7 FALSE 3 1 1 #> 3.37 NA NA 8 FALSE 3 1 1 #> 3.38 NA NA 9 FALSE 3 1 1 #> 3.39 NA NA 10 FALSE 3 1 1 #> 3.310 NA NA 11 FALSE 3 1 1 #> 3.311 NA NA 12 FALSE 3 1 1 #> 3.312 NA NA 13 FALSE 3 0 1 #> 4.4 NA NA 1 TRUE 4 1 1 #> 4.41 NA NA 2 FALSE 4 0 1 #> 4.42 NA NA 3 FALSE 4 1 1 #> 4.43 NA NA 4 FALSE 4 0 1 #> 4.34 NA NA 5 FALSE 4 1 1 #> 4.45 NA NA 6 FALSE 4 1 3 #> 4.46 NA NA 7 FALSE 4 1 0 #> 4.47 NA NA 8 FALSE 4 1 0 #> 4.48 NA NA 9 FALSE 4 1 1 #> 4.49 NA NA 10 FALSE 4 1 1 #> 4.410 NA NA 11 FALSE 4 1 1 #> 4.411 NA NA 12 FALSE 4 1 1 #> 4.412 NA NA 13 FALSE 4 0 1 #> 16 NA NA NA NA NA NA NA #> 17 NA NA NA NA NA NA NA