images2pdf is a command-line utility that uses pdf4tcl to store multiple images into a PDF file without converting or otherwise processing the image.
PYK 2016-03-10: The script on this page inserts jpeg and png images as-is into a pdf document without converting or transcoding the images. To verify this, extracted them again with a utility like pdfimages -all that just extacts images without processing them. The extracted images should be identical, bit-for-bit, to the original images.
Each image is output as an separate page, and the width and height of the page are the width and height of the image. To constrain one or the other, use the height or width options. The image width/height ratio is always preserved. The constraint only reflects how the image is dynamically resized for presentation, not now the image is stored in the PDF file -- which for png and jpg files is always as a bit-for-bit identical copy of the original image. Currently, only jpeg and png files are supported.
Some PDF readers don't provide controls to zoom to a size smaller than the dimensions of the page that contain it, but they do provide controls to magnify the image, so a default value of 800 is a good choice to ensure that the initial image fits into a reasonable display width, while still making it possible to zoom in for greater detail.
#! /bin/env tclsh
package require fileutil::magic::filetype
package require pdf4tcl
proc main {argv0 argv} {
set dims {}
set ftypes {}
set images {}
set orient {}
set maxheight -1
set maxwidth 800
while {[llength $argv]} {
set argv [lassign $argv[set argv {}] key val]
switch $key {
outfile {
set outfile $val
}
height {
set maxheight $val
}
image {
lappend images $val
}
images {
lappend images $val {*}$argv[set argv {}]
}
outprefix {
set outprefix $val
}
width {
set maxwidth val
}
default {
return -code error [list {unknown option} $key]
}
}
}
if {[info exists outprefix]} {
while {[file exists $outprefix-[incr outi]]} {}
} else {
while {[llength [glob -nocomplain [set outprefix [
string repeat 0 [incr outi]]]*]]} {}
}
pdf4tcl::new mypdf
foreach image $images {
set ftype [fileutil::magic::filetype $image]
if {[string match {JPEG *} $ftype]} {
set ftype jpeg
} elseif {} {
} else {
return -code error [list {unknown file type} $ftype]
}
lappend ftypes $ftype
# first run is just to get image dimensions
set id [mypdf addImage $image -type $ftype]
set width [mypdf getImageWidth $id]
set height [mypdf getImageHeight $id]
puts stderr [list image $image type $ftype height $height width $width]
while {($maxwidth > -1 && $width > $maxwidth)
|| ($maxheight > -1 && $height > $maxheight)} {
set height [expr {$height / 2}]
set width [expr {$width / 2}]
}
lappend dims [list $width $height]
}
mypdf destroy
set imagefiles {}
set idx -1
foreach image $images dim $dims ftype $ftypes {
pdf4tcl::new mypdf -paper $dim
set id [mypdf addImage $image -type $ftype]
mypdf putImage $id 0 0 -width [lindex $dim 0] -height [lindex $dim 1]
set fname $outprefix-[incr idx].pdf
mypdf write -file $fname
lappend imagefiles $fname
mypdf destroy
}
if {[llength $imagefiles] > 1} {
pdf4tcl::catPdf {*}$imagefiles $outfile
if {![info exists outfile]} {
set outfile $outprefix-[incr idx].pdf
}
file delete {*}$imagefiles
} else {
if {[info exists outfile]} {
file rename [lindex $imagefiles 0] $outfile
}
}
}
main $argv0 $argv