%!PS
% Copyright (C) 2001-2021 Artifex Software, Inc.
% All Rights Reserved.
%
% This software is provided AS-IS with no warranty, either express or
% implied.
%
% This software is distributed under license and may not be copied,
% modified or distributed except as expressly authorized under the terms
% of the license contained in the file LICENSE in this distribution.
%
% Refer to licensing information at http://www.artifex.com or contact
% Artifex Software, Inc., 1305 Grant Avenue - Suite 200, Novato,
% CA 94945, U.S.A., +1(415)492-9861, for further information.
%
%
% $Id: pdf_info.ps 6300 2005-12-28 19:56:24Z alexcher $
% Dump some info from a PDF file
% usage: gs -dNODISPLAY -q -sFile=____.pdf [-dDumpMediaSizes=false] [-dDumpFontsNeeded=false] [-dDumpXML]
% [-dDumpFontsUsed [-dShowEmbeddedFonts] ] lib/pdf_info.ps
128 dict begin
/QUIET true def % in case they forgot
/showoptions {
( where "options" are:) =
( -dDumpMediaSizes=false (default true) MediaBox and CropBox for each page) =
( -dDumpFontsNeeded=false (default true)Fonts used, but not embedded) =
( -dDumpXML print the XML Metadata from the PDF, if present) =
( -dDumpFontsUsed List all fonts used) =
( -dShowEmbeddedFonts only meaningful with -dDumpFontsUsed) =
(\n If no options are given, the default is -dDumpMediaSizes -dDumpFontsNeeded) =
() =
flush
} bind def
/DumpMediaSizes where { pop } { /DumpMediaSizes true def } ifelse
/DumpFontsNeeded where { pop } { /DumpFontsNeeded true def } ifelse
[ {.shellarguments} stopped not
{
{ counttomark 1 eq {
dup 0 get (-) 0 get ne {
% File specified on the command line using: -- lib/pdf_info.ps infile.pdf
/File exch def
false % don't show usage
} {
true % show usage and quit
} ifelse
} { true } ifelse
{
(\n*** Usage: gs [options] -- lib/pdf_info.ps infile.pdf ***\n\n) print
showoptions
quit
} if
} if
} if
/File where not {
(\n *** Missing input file name \(use -sFile=____.pdf\)\n) =
( usage: gs -dNODISPLAY -q -sFile=____.pdf [ options ] lib/pdf_info.ps\n) =
showoptions
quit
} if
cleartomark % discard the dict from --where--
% ---- No more executable code on the top level after this line -----
% ---- except 2 lines at the very end -----
% Write a character to the standard output.
/putchar [ % int -> -
(%stdout) (w) file
/exch cvx /write cvx
] cvx bind def
% Write U+xxxx to the standard output as UTF-8.
/put-ucode { % int -> -
dup 16#80 ge {
dup 16#800 ge {
dup 16#10000 ge {
dup -18 bitshift 16#f0 or putchar
dup -12 bitshift 16#3f and 16#80 or putchar
} {
dup -12 bitshift 16#e0 or putchar
} ifelse
dup -6 bitshift 16#3f and 16#80 or putchar
} {
dup -6 bitshift 16#C0 or putchar
} ifelse
16#3f and 16#80 or
} if
putchar
} bind def
% PDFDocEncoding to U+xxxx decoding table.
/doc-to-ucode [
0 1 23 {} for
16#2d8 16#2c7 16#2c6 16#2d9 16#2dd 16#2db 16#2da 16#2dc
32 1 127 {} for
16#2022 16#2020 16#2021 16#2026 16#2014 16#2013 16#192
16#2044 16#2039 16#203a 16#2212 16#2030 16#201e 16#201c
16#201d 16#2018 16#2019 16#201a 16#2122 16#fb01 16#fb02
16#141 16#152 16#160 16#178 16#17d 16#131 16#142 16#153
16#161 16#17e 0 16#20ac
161 1 255 {} for
] readonly def
% Convert a doc string from PDFDocEncoding or UTF-16BE to UTF-8
% and write it to standard output.
/write-doc-string { % (string) -> -
1024 string cvs <feff> anchorsearch {
pop
0 exch % hi16 (str)
0 2 2 index length 2 sub {
2 copy 2 copy % hi16 (str) i (str) i (str) i
get 256 mul 3 1 roll % hi16 (str) i hi*256 (str) i
1 add get add % hi16 (str) i 256*hi+lo
dup 16#fc00 and dup % hi16 (str) i 256*hi+lo tag tag
16#d800 eq { % High surrogate
pop
16#3ff and
10 bitshift
16#10000 add % hi16 (str) i hi16'
4 1 roll % hi16' hi16 (str) i
pop exch pop % hi16' (str)
} {
16#dc00 eq { % Low surrogate
16#3ff and % hi16 (str) i (256*hi+lo)&0x3ff
4 -1 roll add % (str) i (256*hi+lo)&0x3ff+hi16
put-ucode % (str) i
pop 0 exch % 0 (str)
} { % BMP plane
put-ucode % hi16 (str) i
pop % hi16 (str)
} ifelse
} ifelse
} for
pop pop % -
} {
{ //doc-to-ucode exch get put-ucode
} forall
} ifelse
} bind def
%% When checking Resources for Font objects, we must ensure that we don't end
%% up following a circular reference. Circular references in Resources should
%% not, of course, be present but we've seen a number of cases. If we do detect
%% a circular reference, then stop checking that chain.
/oforce_no_circular {
dup type /packedarraytype eq {
dup 0 get
currentdict /ProcessedResources known {
dup ProcessedResources exch known {
pop pop //null
} {
dup ProcessedResources 3 1 roll put
oforce
} ifelse
} {
oforce
} ifelse
} {
oforce
} ifelse
} bind def
/dump-pdf-info { % (fname) -> -
() = ( ) print print ( has ) print
PDFPageCount dup =print 10 mod 1 eq { ( page.\n) } { ( pages\n) } ifelse = flush
Trailer /Root oget /AcroForm knownoget {
/XFA knownoget {
(File uses XFA forms.\n\n) print
pop
} if
} if
/DumpXML where {
pop
Trailer /Root oget /Metadata knownoget {
//false resolvestream
{ dup 256 string readstring exch print not { exit } if } loop
pop % done with the stream
(\n_____________________________________________________________) =
flush
} if
} if
% Print out the "Info" dictionary if present
Trailer /Info knownoget {
dup /Title knownoget { (Title: ) print write-doc-string () = flush } if
dup /Author knownoget { (Author: ) print write-doc-string () = flush } if
dup /Subject knownoget { (Subject: ) print write-doc-string () = flush } if
dup /Keywords knownoget { (Keywords: ) print write-doc-string () = flush } if
dup /Creator knownoget { (Creator: ) print write-doc-string () = flush } if
dup /Producer knownoget { (Producer: ) print write-doc-string () = flush } if
dup /CreationDate knownoget { (CreationDate: ) print write-doc-string () = flush } if
dup /ModDate knownoget { (ModDate: ) print write-doc-string () = flush } if
dup /Trapped knownoget { (Trapped: ) print write-doc-string () = flush } if
pop
} if
} bind def
% <page index> <page dict> dump-media-sizes -
/dump-media-sizes {
DumpMediaSizes {
() =
% Print out the Page Size info for each page.
(Page ) print =print
dup /UserUnit pget {
( UserUnit: ) print =print
} if
dup /MediaBox pget {
( MediaBox: ) print oforce_array ==only
} if
dup /CropBox pget {
( CropBox: ) print oforce_array ==only
} if
dup /BleedBox pget {
( BleedBox: ) print oforce_array ==only
} if
dup /TrimBox pget {
( TrimBox: ) print oforce_array ==only
} if
dup /ArtBox pget {
( ArtBox: ) print oforce_array ==only
} if
dup /Rotate pget {
( Rotate = ) print =print
} if
dup /Annots pget {
pop
( Page contains Annotations) print
} if
dup pageusestransparency {
( Page uses transparency features) print
} if
dup pagespotcolors
dup length 0 gt {
(\n Page Spot colors: ) =
<< /Black 0 /Cyan 0 /Magenta 0 /Yellow 0 >> exch
{
pop % discard the value
1 index 1 index known not { % check if colorant is a standard one
( ) print
(') print =print (') =
} {
pop % ignore this standard colorant
} ifelse
} forall
pop % discard dict of standard colorants
} {
pop
} ifelse
pop % done with pagedict
() = flush
}
{
pop pop
} ifelse
} bind def
% List of standard font names for use when we are showing the FontsNeeded
/StdFontNames [
/Times-Roman /Helvetica /Courier /Symbol
/Times-Bold /Helvetica-Bold /Courier-Bold /ZapfDingbats
/Times-Italic /Helvetica-Oblique /Courier-Oblique
/Times-BoldItalic /Helvetica-BoldOblique /Courier-BoldOblique
] def
/res-type-dict 10 dict begin
/Font {
{
exch pop oforce_no_circular
dup //null ne {
dup /DescendantFonts knownoget {
exch pop 0 get oforce_no_circular
%% Check to see if a potentail circular reference was detected. This could be a
%% false positive caused by other fonts using the same DescendantFont(s), but if
%% so then we've already cehcked them anyway.
dup //null eq { pop << >>} if
} if
dup /FontDescriptor knownoget {
dup /FontFile known 1 index /FontFile2 known or exch /FontFile3 known or
/ShowEmbeddedFonts where { pop pop //false } if {
pop % skip embedded fonts
} {
/BaseFont knownoget { % not embedded
2 index exch //null put
} if
} ifelse
} {
/BaseFont knownoget { % no FontDescriptor, not embedded
2 index exch //null put
} if
} ifelse
} {
pop
} ifelse
} forall % traverse the dictionary
} bind def
/XObject {
{
exch pop oforce_no_circular
dup //null ne {
dup /Subtype knownoget {
/Form eq {
/Resources knownoget {
get-fonts-from-res
} if
} {
pop
} ifelse
} {
pop
} ifelse
} {
pop
} ifelse
} forall
} bind def
/Pattern {
{
exch pop oforce_no_circular
dup //null ne {
/Resources knownoget {
get-fonts-from-res
} if
} {
pop
} ifelse
} forall
} bind def
currentdict end readonly def
% <dict for fonts> <<res-dict>> get-fonts-from-res -
/get-fonts-from-res {
oforce_no_circular
dup //null ne {
{
oforce_no_circular
dup //null ne {
//res-type-dict 3 -1 roll
.knownget {
exec
} {
pop
} ifelse
} {
pop pop
} ifelse
} forall
} {
pop
} ifelse
} bind def
currentdict /res-type-dict undef
/getPDFfonts { % <dict for fonts> <page dict> getPDFfonts -
/ProcessedResources 10 dict def
dup /Resources pget { get-fonts-from-res } if
/Annots knownoget {
{ oforce_no_circular
dup //null ne {
/AP knownoget {
{ exch pop oforce_no_circular
dup //null ne {
dup /Resources knownoget {
get-fonts-from-res
} if
{ exch pop oforce_no_circular
dup type /dicttype eq {
/Resources knownoget {
get-fonts-from-res
} if
} {
pop
} ifelse
} forall
} {
pop
} ifelse
} forall
} if
} {
pop
} ifelse
} forall
} if
pop
currentdict /ProcessedResources undef
} bind def
% If running with -dSAFER, .sort may not be present. Define a (slower) PS alternative
systemdict /.sort known not {
% <array> <lt-proc> .sort <array>
/.sort
{ 1 index length 1 sub -1 1
{ 2 index exch 2 copy get 3 copy % arr proc arr i arr[i] arr i arr[i]
0 1 3 index 1 sub
{ 3 index 1 index get % arr proc arr i arr[i] arr imax amax j arr[j]
2 index 1 index 10 index exec
{ % ... amax < arr[j]
4 2 roll
}
if pop pop
}
for % arr proc arr i arr[i] arr imax amax
4 -1 roll exch 4 1 roll put put
}
for
pop
} bind def
} if
/dump-fonts-used { % <dict for fonts> dump-fonts-used -
% If DumpFontsUsed is not true, then remove the 'standard' fonts from the list
systemdict /DumpFontsUsed known not {
StdFontNames {
1 index 1 index known { 1 index 1 index undef } if
pop
} forall
} if
% Now dump the FontsUsed dict into an array so we can sort it.
[ 1 index { pop } forall ]
{ 100 string cvs exch 100 string cvs exch lt } .sort
systemdict /DumpFontsUsed known
{
(\nFont or CIDFont resources used (plain name and ASCIIHEX string representation):) =
{ 128 string cvs dup print ( ) print (<) print 128 string cvs {16 8 string cvrs print} forall (>) print (\n) print} forall
} {
DumpFontsNeeded {
dup length 0 gt {
(\nFonts Needed that are not embedded \(system fonts required\):) =
{ ( ) print 128 string cvs dup print ( ) print (<) print {16 8 string cvrs print} forall (>) print (\n) print} forall
} {
pop
(\nNo system fonts are needed.) =
} ifelse
} {
pop
} ifelse
} ifelse
pop
} bind def
% Copy selected subfiles to temporary files and return the file names
% as a PostScript names to protect them from restore.
% Currently, all PDF files in the Portfolio are extracted and returned.
%
% - pdf_collection_files [ /temp_file_name ... /temp_file_name
/pdf_collection_files {
mark
Trailer /Root oget
dup /Collection oknown {
/Names knownoget {
/EmbeddedFiles knownoget {
pdf_collection_names
} if
} if
} {
pop
} ifelse
} bind def
% Output all the info about the file
/dump { % (title) -> -
/PDFPageCount pdfpagecount def
dump-pdf-info
% dict will be populated with fonts through a call to 'getPDFfonts'
% per page, then the contents dumped out in 'dump-fonts-used'
1000 dict
1 1 PDFPageCount
{
dup pdfgetpage dup 3 -1 roll
dump-media-sizes
1 index exch getPDFfonts
} for
dump-fonts-used
} bind def
% Choose between collection vs plain file.
% Enumerate collections and apply the dump procedure.
/enum-pdfs { % - -> -
File (r) file runpdfbegin
pdf_collection_files
dup mark eq {
pop
File dump
runpdfend
} {
runpdfend
] 0 1 2 index length 1 sub {
2 copy get exch % [file ... ] file i
1 add (0123456789) cvs % [file ... ] file (i+1)
File exch ( part ) exch concatstrings concatstrings
exch % [file ... ] (fname part i+1) file
dup type /filetype eq {
runpdfbegin
dump
runpdfend
closefile
} {
1024 string cvs % .namestring is deprecated
% .namestring
dup (r) file
runpdfbegin
exch dump
runpdfend
deletefile
} ifelse
} for
pop
} ifelse
} bind def
enum-pdfs
end
quit
