New PageList processing, supporting PDF and XPS random order.

Supports out-of-order ranges (if the parser allows it and disables the
PageHandler, i.e., flp device). Also adds support for ranges appended
to the "even" and "odd" keyword following a ":".

As before a trailing "-" in a range implies the last page, and as was
supported by the previous 'gxps' code, a leading "-" also is the last page.

For example, with XPS or PDF: -sPageList=odd:3-7,even:4-8,1-,-1,9
prints pages: 3, 5, 7, 4, 6, 8, 1, 2, ..., last, last, last-1, ..., 1, 9

The PageList string is parsed using C code into an array that consists of
an initial int that is > 0 if the list is ordered, followed by sets of
3 integers per range, even/odd flag (odd=1, even=2), start, end. The
final 3 ints are 0,0,0 as a marker.

The initial int is used by 'pagelist_test_printed' as an index to the next
range to be processed when the PageList is used for languages that can only
be processed sequentially (e.g. PS and PCL) and is updated when the page
passes the end of the current range.  A value of -1 means the ranges are
not ordered (not strctly increasing).

The flp_fillpage is changed to ignore errors from processing the PageList
performed by ParsePageList (called from SkipPage) when PageCount is 0
so that parsers that support out of order processing (PDF and XPS) can
continue until later. This should have little or no performance impact
since it is limited to PageCount == 0.

Note that the new PDF parser also uses the C code parser and then uses
the array of ranges returned by ".PDFparsePageList". The old PostScript
based parser has not been updated, although it is easy to do so.

1 files changed, 57 insertions, 131 deletions

diff --git a/Resource/Init/pdf_main.ps b/Resource/Init/pdf_main.ps
index 2a622eb88..07cddf5e8 100644
--- a/Resource/Init/pdf_main.ps
+++ b/Resource/Init/pdf_main.ps
@@ -835,125 +835,24 @@ currentdict /PDFSwitches undef
 /newpdf_runpdfpagerange
 {
   /PageList where {
-    pop PageList
-    (even) anchorsearch {
-      pop length 0 gt {
-        /runpdfpagerange cvx /syntaxerror signalerror
-      } if
-        /PDFPageList pdfpagecount 1 add array def
-        2 2 pdfpagecount {
-          PDFPageList exch 1 put
-        } for
-        QUIET not {
-          (Processing even-numbered pages\n) print (1 through ) print pdfpagecount =only
-          (.) = flush
-        } if
-    } {
-      (odd) anchorsearch {
-        pop length 0 gt {
-          /runpdfpagerange cvx /syntaxerror signalerror
-        } if
-        /PDFPageList pdfpagecount 1 add array def
-        1 2 pdfpagecount {
-          PDFPageList exch 1 put
-        } for
-        QUIET not {
-          (Processing odd-numbered pages\n) print (1 through ) print pdfpagecount =only
-          (.) = flush
-        } if
-      } {
-        %% validate string contents, check for digit comma or minus
-        dup
-        {
-          dup 44 eq not {
-            dup 45 eq not {
-              dup 48 lt 1 index 57 gt or {
-                /runpdfpagerange cvx /syntaxerror signalerror
-              } if
-            } if
-          } if
-          pop
-        }
-        forall
-        /PDFPageList pdfpagecount 1 add array def
-        {
-          (,) search {
-            %% We now have (post) (,) (pre)
-            exch pop %% get rid of the (,), leave the (post) as the string for the next iteration, deal with the section up to the comma
-            (-) search {
-              %% Now we have (end) (-) (start)
-              exch pop %% get rid of the minus (end) (start)
-              0 exch {48 sub exch 10 mul add} forall
-              %% Make sure the start of the range is inside the number of available pages
-              dup pdfpagecount le {
-                exch
-                %% deal with a trailing '-' by replacing it with the number of pages in the file
-                dup length 0 eq {
-                  pop pdfpagecount
-                }{
-                  0 exch {48 sub exch 10 mul add} forall
-                } ifelse
-                1 exch %% start 1 end
-                %% Make sure the end of the range is inside the number of available pages
-                dup pdfpagecount gt {pop pdfpagecount} if
-                {PDFPageList exch 1 put} for
-              } {
-                %% start of range invalid, drop this range.
-                pop pop
-              }ifelse
-            }{
-              %% no minus signs, must be a simple page number
-              0 exch {48 sub exch 10 mul add} forall
-              %% ensure its in the valid range of pages
-              dup pdfpagecount le {
-                 PDFPageList exch 1 put
-              } {
-                pop
-              } ifelse
-            } ifelse
-          }{
-            %% no commas separating pages, just the original string (), deal with its as a section, then exit the loop
-            (-) search {
-              %% Now we have (end) (-) (start)
-              exch pop %% get rid of the minus (end) (start)
-              0 exch {48 sub exch 10 mul add} forall
-              %% Make sure the start of the range is inside the number of available pages
-              dup pdfpagecount le {
-                exch
-                %% deal with a trailing '-' by replacing it with the number of pages in the file
-                dup length 0 eq {
-                  pop pdfpagecount
-                }{
-                  0 exch {48 sub exch 10 mul add} forall
-                } ifelse
-                1 exch %% start 1 end
-                %% Make sure the end of the range is inside the number of available pages
-                dup pdfpagecount gt {pop pdfpagecount} if
-                {PDFPageList exch 1 put} for
-              } {
-                %% start of range invalid, drop this range.
-                pop pop
-              }ifelse
-            }{
-              %% no minus signs, must be a simple page number
-              0 exch {48 sub exch 10 mul add} forall
-              %% ensure its in the valid range of pages
-              dup pdfpagecount le {
-                 PDFPageList exch 1 put
-              } {
-                pop
-              } ifelse
-            } ifelse
-            exit %% done all the sections.
-          } ifelse
-        } loop
-        QUIET not {
-          (Processing pages ) print PageList =only
-          (.) = flush
-        } if
-      } ifelse
-    } ifelse
-    1 pdfpagecount
+    pop
+    % make sure string is NUL terminated as C expects.
+    PageList 1 string dup 0 0 put concatstrings
+    pdfpagecount
+    .PDFparsePageList
+    dup 0 eq {	% No ranges, error
+      (\n   **** Error: Invalid PageList: ) print
+      PageList  print
+      (\n   No pages will be processed.) = flush
+      /runpdfpagerange cvx /syntaxerror signalerror
+    } if
+    array astore	% move integer triples from the stack to the array
+    % newpdf PDFPageList is an array of 3 elements per range: even/odd flag, start, end
+    /PDFPageList exch def
+    QUIET not {
+      (Processing pages ) print PageList =only (.) = flush
+    } if
+    1 pdfpagecount	% dummy parameters for newpdf_dopages
   }{
     /FirstPage where {
       pop FirstPage dup pdfpagecount gt {
@@ -1197,17 +1096,26 @@ currentdict /PDFSwitches undef
 
 % <int> <int> dopdfpages -
 % First Page and then LastPage
+% If PDFPageList array exists, the parameters are 1 pdfpagecount and are ignored.
 /newpdf_dopdfpages
 {
   //DisablePageHandlerDevice exec
-  1 exch
-  {
-      %% If we have a array of pages to render, use it.
-      /PDFPageList where {
-        pop dup PDFPageList exch get 1 eq
-      }
-      {//true} ifelse
-
+  %% If we have a array of page ranges to render, use it.
+  /PDFPageList where {
+    pop
+    pop pop		% don't use dummy parameters
+    PDFPageList
+    % process the ranges (3 elements per range)
+    0 3 2 index length 1 sub {
+      1 index 1 index get		% even = 2, odd = 1 any = 0
+      2 index 2 index 1 add get		% start of range
+      exch
+      3 index 3 index 2 add get		% end of range
+      exch
+      % stack: start end even/odd
+      0 eq { 1 } { 2 } ifelse
+      2 index 2 index gt { neg } if	% negate increment for reverse range
+      exch
       {
         pdfgetpage
         dup //null ne {
@@ -1221,10 +1129,28 @@ currentdict /PDFSwitches undef
             ( not found.\n) newpdf_pdfformaterror
           } ifelse
         } ifelse
-      }{
-        pop
-      }ifelse
-  } for
+      } for
+      pop		% for loop index
+    } for
+    pop		% done with array
+  } {
+    % else, Process the pages given by the FirstPage, LastPage
+    1 exch
+    {
+      pdfgetpage
+      dup //null ne {
+        pdfshowpage
+      } {
+        PDFSTOPONERROR {
+          /dopdfpages cvx /syntaxerror signalerror
+        } {
+          pop pop
+          (   **** Error: page) newpdf_pdfformaterror
+          ( not found.\n) newpdf_pdfformaterror
+        } ifelse
+      } ifelse
+    } for
+  } ifelse
   //EnablePageHandlerDevice exec
 } bind def