filter images by their metadata
pdimg_filter(x, min_size = NULL, max_size = NULL)output from pdimg_images()
a file coerceable by fs::fs_bytes()
same structure as pdimg_images()
x1 <- system.file("examples/Tierney2017JOSS.pdf", package="pdfimager")
x2 <- system.file("examples/vanGemert2018.pdf", package="pdfimager")
res <- pdimg_images(c(x1, x2))
res
#> [[1]]
#> # A tibble: 6 × 17
#> path page num type width height color comp bpc enc interp object
#> <chr> <int> <int> <chr> <int> <int> <chr> <int> <int> <chr> <chr> <int>
#> 1 /var/fol… 1 0 image 650 249 rgb 3 8 image no 6
#> 2 /var/fol… 1 1 smask 650 249 gray 1 8 image no 6
#> 3 /var/fol… 2 2 image 650 249 rgb 3 8 image no 6
#> 4 /var/fol… 2 3 smask 650 249 gray 1 8 image no 6
#> 5 /var/fol… 2 4 image 672 480 icc 3 8 image no 41
#> 6 /var/fol… 2 5 smask 672 480 gray 1 8 image no 41
#> # ℹ 5 more variables: ID <int>, x.ppi <int>, y.ppi <int>, size <chr>,
#> # ratio <chr>
#>
#> [[2]]
#> # A tibble: 8 × 17
#> path page num type width height color comp bpc enc interp object
#> <chr> <int> <int> <chr> <int> <int> <chr> <int> <int> <chr> <chr> <int>
#> 1 /var/fol… 1 0 image 1491 256 cmyk 4 8 jpeg no 352
#> 2 /var/fol… 3 1 image 121 53 sep 1 8 jpeg no 84
#> 3 /var/fol… 3 2 image 114 86 sep 1 8 jpeg no 83
#> 4 /var/fol… 3 3 image 108 39 sep 1 8 jpeg no 82
#> 5 /var/fol… 5 4 image 25 117 sep 1 8 image no 141
#> 6 /var/fol… 5 5 image 17 34 sep 1 8 image no 140
#> 7 /var/fol… 5 6 image 19 91 sep 1 8 image no 139
#> 8 /var/fol… 5 7 image 18 69 sep 1 8 image no 138
#> # ℹ 5 more variables: ID <int>, x.ppi <int>, y.ppi <int>, size <chr>,
#> # ratio <chr>
#>
res[[1]]$path
#> [1] "/var/folders/py/lcjn3y352g1106vf1rqk521r0000gn/T//RtmpQVrOR8/Tierney2017JOSS/img-000.ppm"
#> [2] "/var/folders/py/lcjn3y352g1106vf1rqk521r0000gn/T//RtmpQVrOR8/Tierney2017JOSS/img-001.ppm"
#> [3] "/var/folders/py/lcjn3y352g1106vf1rqk521r0000gn/T//RtmpQVrOR8/Tierney2017JOSS/img-002.ppm"
#> [4] "/var/folders/py/lcjn3y352g1106vf1rqk521r0000gn/T//RtmpQVrOR8/Tierney2017JOSS/img-003.ppm"
#> [5] "/var/folders/py/lcjn3y352g1106vf1rqk521r0000gn/T//RtmpQVrOR8/Tierney2017JOSS/img-004.ppm"
#> [6] "/var/folders/py/lcjn3y352g1106vf1rqk521r0000gn/T//RtmpQVrOR8/Tierney2017JOSS/img-005.ppm"
res[[2]]$path
#> [1] "/var/folders/py/lcjn3y352g1106vf1rqk521r0000gn/T//RtmpQVrOR8/vanGemert2018/img-000.ppm"
#> [2] "/var/folders/py/lcjn3y352g1106vf1rqk521r0000gn/T//RtmpQVrOR8/vanGemert2018/img-001.ppm"
#> [3] "/var/folders/py/lcjn3y352g1106vf1rqk521r0000gn/T//RtmpQVrOR8/vanGemert2018/img-002.ppm"
#> [4] "/var/folders/py/lcjn3y352g1106vf1rqk521r0000gn/T//RtmpQVrOR8/vanGemert2018/img-003.ppm"
#> [5] "/var/folders/py/lcjn3y352g1106vf1rqk521r0000gn/T//RtmpQVrOR8/vanGemert2018/img-004.ppm"
#> [6] "/var/folders/py/lcjn3y352g1106vf1rqk521r0000gn/T//RtmpQVrOR8/vanGemert2018/img-005.ppm"
#> [7] "/var/folders/py/lcjn3y352g1106vf1rqk521r0000gn/T//RtmpQVrOR8/vanGemert2018/img-006.ppm"
#> [8] "/var/folders/py/lcjn3y352g1106vf1rqk521r0000gn/T//RtmpQVrOR8/vanGemert2018/img-007.ppm"
pdimg_filter(x=res)
#> [[1]]
#> # A tibble: 1 × 17
#> path page num type width height color comp bpc enc interp object
#> <chr> <int> <int> <chr> <int> <int> <chr> <int> <int> <chr> <chr> <int>
#> 1 /var/fol… 2 4 image 672 480 icc 3 8 image no 41
#> # ℹ 5 more variables: ID <int>, x.ppi <int>, y.ppi <int>, size <chr>,
#> # ratio <chr>
#>
#> [[2]]
#> # A tibble: 8 × 17
#> path page num type width height color comp bpc enc interp object
#> <chr> <int> <int> <chr> <int> <int> <chr> <int> <int> <chr> <chr> <int>
#> 1 /var/fol… 1 0 image 1491 256 cmyk 4 8 jpeg no 352
#> 2 /var/fol… 3 1 image 121 53 sep 1 8 jpeg no 84
#> 3 /var/fol… 3 2 image 114 86 sep 1 8 jpeg no 83
#> 4 /var/fol… 3 3 image 108 39 sep 1 8 jpeg no 82
#> 5 /var/fol… 5 4 image 25 117 sep 1 8 image no 141
#> 6 /var/fol… 5 5 image 17 34 sep 1 8 image no 140
#> 7 /var/fol… 5 6 image 19 91 sep 1 8 image no 139
#> 8 /var/fol… 5 7 image 18 69 sep 1 8 image no 138
#> # ℹ 5 more variables: ID <int>, x.ppi <int>, y.ppi <int>, size <chr>,
#> # ratio <chr>
#>
x4 <- system.file("examples/Wunderlich2020.pdf", package="pdfimager")
res <- pdimg_images(x4)
pdimg_filter(res, min_size = "100K")
#> [[1]]
#> # A tibble: 1 × 17
#> path page num type width height color comp bpc enc interp object
#> <chr> <int> <int> <chr> <int> <int> <chr> <int> <int> <chr> <chr> <int>
#> 1 /var/fol… 8 4 image 1294 755 rgb 3 8 image no 118
#> # ℹ 5 more variables: ID <int>, x.ppi <int>, y.ppi <int>, size <chr>,
#> # ratio <chr>
#>