GhostPDF - revamp PDF information extraction

A customer requested that we make pdf_info.ps work with the new
PDF interpreter, and generate the same information.

This commit modifies the way we extract information on a
page-by-page basis to potentially include the names of spot inks
and information about fonts used on the page.

This is now returned to the PostScript environment using a PDF
dictionary instead of a C structure. The pdf_info.ps program has
been updated so that it use the new information in broadly the
same way as the information from the old PDF interpreter.

There are differences; pdf_info.ps extracts font information
itself, rather than having the interpreter do it. This is not
possible with the new interpreter which is why we have the
PDF interpreter do it for us. In addition the pdf_info.ps
program only descended to the page level whereas the new PDF
interpreter evaluates all objects on the page, potentially
meaning that more fonts (and technically spot inks) might be
detected.

We now have an additional PostScript operator '.PDFPageInfoExt'
which returns 'extended' information about a page. This is the
same as .PDFPageInfo but includes the font and spot ink
information.

Running with -dPDFINFO using either Ghostscript or GhostPDF will
print more information than before, including the spot inks and
considerably more information about fonts than the pdf_info.ps
program emits, including embedding status, descendant fonts
(and their membedding status) and the presence of ToUnicode
CMaps.

Updated documentation for all of the above.

1 files changed, 159 insertions, 1 deletions

diff --git a/lib/pdf_info.ps b/lib/pdf_info.ps
index 35951e9a7..2a5f57966 100644
--- a/lib/pdf_info.ps
+++ b/lib/pdf_info.ps
@@ -527,6 +527,164 @@ systemdict /.sort known not {
   } ifelse
 } bind def
 
-enum-pdfs
+/NEWPDF where {/NEWPDF get}{false}ifelse
+{
+  /knownoget
+  {
+    2 copy known {
+      get
+      true
+    }{
+      pop pop false
+    } ifelse
+  }bind def
+
+  /PDFContext << >> .PDFInit def
+  {File (r) file PDFContext .PDFStream} stopped not
+  {
+
+    PDFContext .PDFInfo
+    File
+    () = (        ) print print ( has ) print
+    dup /NumPages get dup =print 10 mod 1 eq { ( page.\n) } { ( pages\n) } ifelse = flush
+
+    /DumpXML where {/DumpXML get}{//false}ifelse
+    {
+      (\n*** DumpXML is no longer supported. ***\n\n) print
+    }if
+
+    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
+    (\n) print flush
+
+    /EmbeddedFonts 10 dict def
+    /UnEmbeddedFonts 10 dict def
+    /FontNumbers 10 dict def
+
+    /NumPages get 0 1 3 -1 roll 1 sub
+    {
+      dup
+      PDFContext exch .PDFPageInfoExt exch
+      DumpMediaSizes {
+        (Page ) print 1 add =print
+        dup /UserUnit knownoget {( UserUnit: ) print =print} if
+        dup /MediaBox knownoget {( MediaBox: ) print ==only} if
+        dup /CropBox knownoget  {( CropBox: )  print ==only} if
+        dup /BleedBox knownoget {( BleedBox: ) print ==only} if
+        dup /TrimBox knownoget  {( TrimBox: )  print ==only} if
+        dup /ArtBox knownoget   {( ArtBox: )   print ==only} if
+        dup /Rotate knownoget not {0}if ( Rotate = ) print =print
+        dup /Annots knownoget {{(     Page contains Annotations) print} if} if
+        dup /UsesTransparency knownoget {{(     Page uses transparency features) print} if} if
+        dup /Spots knownoget {
+          (\n    Page Spot colors: ) =
+          {(        ) print (') print 256 string cvs print (') =} forall
+        } if
+        (\n) print flush
+        (\n) print flush
+      }
+      {
+        pop
+      } ifelse
+
+      /Fonts knownoget
+      {
+        {
+          dup /ObjectNum known
+          {
+            %% Fonts with an ObjectNumber may have been previously referenced on another page
+            dup /ObjectNum get
+            dup FontNumbers exch known
+            {
+              pop
+              %% found the ObjectNumber in the FontNumbers dictionary so we've seen this one.
+              //false
+            }
+            {
+              %% Not seen before, add the number to the array and process this font
+              FontNumbers exch dup put
+              //true
+            }ifelse
+          }{
+            %% Fonts without an ObjectNumber are defined inline and so must be unique
+            //true
+          } ifelse
+          {
+            % First time we've seen the font
+            dup /Descendants known
+            {
+              dup /BaseFont get
+              EmbeddedFonts exch dup put    % We class the Type 0 font as 'embedded', but it's really the descendant which is embedded or not.
+              dup /Descendants get
+              1 index /BaseFont get
+              2 index /Embedded get
+              {
+                EmbeddedFonts exch dup put
+              }
+              {
+                UnEmbeddedFonts exch dup put
+              }ifelse
+              pop
+            }
+            {
+              dup /BaseFont get
+              1 index /Embedded get
+              {
+                EmbeddedFonts exch dup put
+              }
+              {
+                UnEmbeddedFonts exch dup put
+              } ifelse
+            }ifelse
+            pop
+          }
+          {
+            pop
+          } ifelse
+        }forall
+      } if
+    } for
+
+    /DumpFontsUsed where {/DumpFontsUsed get}{//false}ifelse
+    {
+      [
+      UnEmbeddedFonts {pop} forall
+      /ShowEmbeddedFonts where {/ShowEmbeddedFonts get}{//false}ifelse
+      {
+        EmbeddedFonts {pop} forall
+      } if
+      ]
+      dup length 0 gt {
+        { 100 string cvs exch 100 string cvs exch lt } .sort
+        (\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
+      } if
+    }
+    {
+      [
+      DumpFontsNeeded
+      {
+        UnEmbeddedFonts {pop} forall
+      } if
+      ]
+      dup length 0 gt {
+        { 100 string cvs exch 100 string cvs exch lt } .sort
+        (\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
+      } if
+    }ifelse
+  } if
+  PDFContext .PDFClose
+}
+{
+  enum-pdfs
+} ifelse
 end
 quit