home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
PC World Komputer 2003 November A
/
PCWK1103A.iso
/
ABBYY FineReader 7.0 PRO
/
data1.cab
/
pdf_main.ps
< prev
next >
Wrap
Text File
|
2002-10-23
|
24KB
|
807 lines
% Copyright (C) 1994, 2000 Aladdin Enterprises. 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.
%
% For more information about licensing, please refer to
% http://www.ghostscript.com/licensing/. For information on
% commercial licensing, go to http://www.artifex.com/licensing/ or
% contact Artifex Software, Inc., 101 Lucas Valley Road #110,
% San Rafael, CA 94903, U.S.A., +1(415)492-9861.
% $Id: pdf_main.ps,v 1.35.2.2 2002/04/02 13:57:27 mpsuzuki Exp $
% pdf_main.ps
% PDF file- and page-level operations.
% ATAPY changes at 23.10.2002. Comments about changes started with string "(ATAPY changes)"
/.setlanguagelevel where { pop 2 .setlanguagelevel } if
.currentglobal true .setglobal
/pdfdict where { pop } { /pdfdict 100 dict def } ifelse
pdfdict begin
% Patch in an obsolete variable used by some third-party software.
/#? false def
% Test whether the current output device handles pdfmark.
/.writepdfmarkdict 1 dict dup /pdfmark null put readonly def
/.writepdfmarks { % - .writepdfmarks <bool>
currentdevice //.writepdfmarkdict .getdeviceparams
mark eq { false } { pop pop true } ifelse
systemdict /DOPDFMARKS known or
} bind def
% For simplicity, we use a single interpretation dictionary for all
% PDF graphics execution, even though this is too liberal.
/pdfopdict mark
objopdict { } forall
drawopdict { } forall
/endstream { exit } bind
(%%EOF) cvn { exit } bind % for filters
% PDF 1.1 operators
/BX { /BXlevel BXlevel 1 add store } bind
/EX { /BXlevel BXlevel 1 sub store } bind
/PS { cvx exec } bind
% PDF 1.2 operators
/BMC { pop } bind
/BDC { pop pop } bind
/EMC { }
/MP { pop } bind
/DP { pop pop } bind
.dicttomark readonly def
% ======================== Main program ======================== %
end % pdfdict
userdict begin
/defaultfontname /Times-Roman def
% Make sure the registered encodings are loaded, so we don't run the risk
% that some of the indices for their names will overflow the packed
% representation. (Yes, this is a hack.)
SymbolEncoding pop
DingbatsEncoding pop
% Redefine 'run' so it recognizes PDF files.
systemdict begin
/.runps /run load def
/runpdfstring 50 string def % length is arbitrary
% (ATAPY changes) Some PDF-creators produce PDF-s starting with empty line
/skipEmptyLine { % <file> skipEmptyLine <file>
dup ( ) .peekstring {
(\r\n) eq {
dup ( ) readstring pop pop
} if
} if
} bind def
% (End of ATAPY changes)
/run {
dup type /filetype ne { (r) file } if
skipEmptyLine % (ATAPY changes)
dup ( ) .peekstring {
(%) eq {
dup ( ) .peekstring {
(%P) eq {
dup //runpdfstring {
% Some invalid files might have extra-long first lines....
{ readline } .internalstopped not { pop pop exit } if
pop =string
} loop
//runpdfstring (%PDF-) anchorsearch {
pop pop runpdf
} {
pop cvx .runexec
} ifelse
} {
cvx .runps
} ifelse
} {
closefile
} ifelse
} {
cvx .runps
} ifelse
} {
closefile
} ifelse
} bind odef
currentdict /runpdfstring .undef
/runpdf % <file> runpdf -
{ userdict begin
/Page# null def
/Page null def
/DSCPageCount 0 def
/PDFSave null def
GS_PDF_ProcSet begin
pdfdict begin
pdfopen begin
Trailer /Root oget /Pages oget /CropBox knownoget
{ mark /CropBox 3 -1 roll /PAGES pdfmark
}
if
/FirstPage where
{ pop FirstPage dup pdfpagecount gt
{ (\nRequested FirstPage is greater than the number of pages in the file: ) print
pdfpagecount = flush
} if
} {
1
} ifelse
1
/LastPage where { pop LastPage pdfpagecount .min } { pdfpagecount } ifelse
2 index 1 index gt
{ ( No pages will be processed \(FirstPage > LastPage\).) = flush }
{ QUIET not
{ (Processing pages ) print 2 index =only ( through ) print dup =only
(.) = flush
}
if
}
ifelse
{ dup /Page# exch store
QUIET not { (Page ) print dup == flush } if
pdfgetpage pdfshowpage
} for
currentdict pdfclose
end % temporary dict
end % pdfdict
end % userdict
} bind def
end % systemdict
% Redefine the procedure that the C code uses for running piped input.
% It is OK to use { (%stdin) run } here, because a startjob cannot occur.
/.runstdin {
{ (%stdin) run } execute0
} bind def
end % userdict
pdfdict begin
% ======================== File parsing ======================== %
% Read the cross-reference and trailer sections.
/traileropdict mark
(<<) cvn { mark } bind
(>>) cvn /.dicttomark load
([) cvn { mark } bind % ditto
(]) cvn dup load
% /true true % see .pdfexectoken in pdf_base.ps
% /false false % ibid.
% /null null % ibid.
/R { /resolveR cvx 3 packedarray cvx } bind % see Objects below
/startxref /exit load
.dicttomark readonly def
% Because of EOL conversion, lines with fixed contents might be followed
% by one or more blanks.
/lineeq % <filestr> <conststr> lineeq <bool>
{ anchorsearch
{ pop { ( ) anchorsearch not { () eq exit } if pop } loop }
{ pop false }
ifelse
} bind def
/linene { lineeq not } bind def
% Read (mostly scan) the cross-reference table.
/readxref % <pos> readxref <trailerdict>
{ PDFoffset add PDFfile exch setfileposition
% In some PDF files, this position actually points to
% white space before the xref line. Skip over this here.
{ PDFfile fileposition PDFfile read pop 32 gt { exit } if pop
} loop
PDFfile exch setfileposition
% The PDF specification says that the 'xref' must be on a line
% by itself. The code here formerly used readline and linene to
% check this. However, Acrobat Reader only requires the line to
% begin with 'xref', and there are enough applications producing
% non-compliant PDF files that we have to do this too.
PDFfile pdfstring 0 4 getinterval readstring pop
(xref) ne { /readxref cvx /syntaxerror signalerror } if
% Store the xref table entry position for each object.
% We only need to read the run headers, not every entry.
{ PDFfile token pop % first object # or trailer
dup /trailer eq { pop exit } if
PDFfile pdfstring readline pop
token pop % entry count
exch pop exch
% This section might be adding new objects:
% ensure that Objects and Generations are big enough.
% Stack: count obj#
2 copy add growPDFobjects
PDFfile fileposition 3 -1 roll
{ Objects 2 index lget null eq % later update might have set it
{ Objects 2 index 2 index cvx lput }
if exch 1 add exch 20 add
}
repeat PDFfile exch setfileposition pop
} loop
count /pdfemptycount exch def
PDFfile traileropdict .pdfrun
} bind def
% Open a PDF file and read the header, trailer, and cross-reference.
/pdfopen { % <file> pdfopen <dict>
pdfopenfile begin
pdfopencache
.writepdfmarks {
% Copy bookmarks (outline) to the output.
Trailer /Root oget /Outlines knownoget {
/First knownoget {
{ dup writeoutline /Next knownoget not { exit } if } loop
} if
} if
} if % end .writepdfmarks
currentdict end
} bind def
/pdfopencache { % - pdfopencache -
% Create and initialize some caches.
/PageCount pdfpagecount def
/PageNumbers PageCount 65534 .min dict def
/PageIndex PageCount 65534 .min array def
} bind def
/pdfopenfile { % <file> pdfopenfile <dict>
pdfdict readonly pop % can't do it any earlier than this
15 dict begin
/LocalResources 0 dict def
/DefaultMatrix null def % establish binding
/Printed where { pop } {
% Guess whether the output device is a printer.
/Printed currentpagedevice /OutputFile known def
} ifelse
/PSLevel1 where { pop } { /PSLevel1 false def } ifelse
cvlit /PDFfile exch def
/PDFsource PDFfile def
/Repaired false def
PDFfile dup 0 setfileposition pdfstring readstring
not {/pdfopen cvx /syntaxerror signalerror} if
(%PDF-) search not {/pdfopen cvx /syntaxerror signalerror} if
length /PDFoffset exch def pop cvr /PDFversion exch def
findxref
initPDFobjects
% Read the last cross-reference table.
readxref /Trailer exch def
Trailer /Encrypt known
{ pdf_process_Encrypt % signal error
}
if
% Read any previous cross-reference tables.
Trailer { /Prev .knownget not { exit } if readxref } loop
Repaired { printrepaired } if
currentdict end
} bind def
% Skip backward over the %%EOF at the end of the PDF file, and read
% the preceding startxref line. The PDF specification unambiguously
% requires that the %%EOF appear on a line by itself, and that the
% startxref and the following position value appear on separate lines;
% however, some applications (including, apparently, Acrobat Distiller
% on the Macintosh) may add up to 2K of garbage after the %%EOF, and some
% other applications also truncate the %%EOF to %%EO, and/or put the
% startxref and the following value on the same line.
% A file reported from Distiller 3.02b for AIX 4.1.1 has 2076 bytes
% of garbage. The tolerance is increased to 4K to cover future
% applications and bigger allocation units.
/findxref { % - findxref <xrefpos>
PDFfile dup dup 0 setfileposition bytesavailable
dup /PDFfilelen exch def
% Find the last %%EOF string (within 4096 bytes)
4096 sub PDFoffset .max
2 copy setfileposition
PDFfilelen exch sub string 1 index exch readstring pop {
(\015%%EO) search { % Adobe can handle truncated key string
pop pop % if found, keep searching 'post' string
} {
(\012%%EO) search
{ pop pop } { exit } ifelse % exit if neither string found
} ifelse
} loop
PDFfilelen exch length sub 4 sub PDFoffset .max exch 1 index setfileposition
% Stack: eofpos
% Check for whether this is, in fact, a valid PDF file.
% (ATAPY changes) %%EOF may not be followed by end_of_line symbol
dup PDFfilelen exch sub dup dup 7 gt exch 5 lt or {
pop true
} {
string PDFfile exch readstring pop
dup (%%EOF) eq exch
dup (%%EOF\n) eq exch dup (%%EOF\r) eq
exch (%%EOF\r\n) eq or or or not
% (End of ATAPY changes)
} ifelse {
(
**** This file has a corrupted %%EOF marker, or garbage after the %%EOF.
) pdfformaterror
} if
PDFfile exch setfileposition
% Now read the startxref and xref start position.
prevline token not { null } if dup type /integertype eq {
exch pop cvi % xref start position
exch PDFfile exch setfileposition
prevline (startxref) linene { /findxref cvx /syntaxerror signalerror } if
pop
} { % else, this file has 'startxref #####' format
(startxref) ne { /findxref cvx /syntaxerror signalerror } if
cvi % xref start position
(
**** The format of the startxref line in this file is invalid.
) pdfformaterror
exch PDFfile exch setfileposition
} ifelse
} bind def
/stderrfile (%stderr) (w) file def
/stderrprint { % <string> stderrprint -
//stderrfile dup 3 -1 roll writestring flushfile
} bind def
/pdfformaterror { % <string> pdfformaterror -
stderrprint
/Repaired true store
} bind def
/printrepaired {
Trailer /Info knownoget {
/Producer knownoget not { null } if
} {
null
} ifelse
dup null eq {
pop (\
**** Please notify the author of the software that produced this file
)
} {
( **** The file was produced by ) stderrprint
% Handle a Unicode Producer.
(\376\377) anchorsearch {
pop dup length 2 idiv string 0 1 2 index length 1 sub {
% Stack: origstr newstr i
1 index exch 3 index 1 index 2 mul 1 add get put
} for exch pop
} if
stderrprint
(:
**** please notify the author of this software
)
} ifelse stderrprint
(\
**** that the file does not conform to Adobe's published PDF
**** specification. Processing of the file will continue normally.
) stderrprint
} bind def
% Write the outline structure for a file. Uses linkdest (below).
/writeoutline % <outlinedict> writeoutline -
{ mark
0 2 index /First knownoget
{ { exch 1 add exch /Next knownoget not { exit } if } loop }
if
% stack: dict mark count
dup 0 eq
{ pop 1 index
}
{ 2 index /Count knownoget { 0 lt { neg } if } if
/Count exch 3 index
}
ifelse linkdest /Title oget /Title exch /OUT pdfmark
/First knownoget
{ { dup writeoutline /Next knownoget not { exit } if } loop }
if
} bind def
% Close a PDF file.
/pdfclose % <dict> pdfclose -
{ begin
PDFfile closefile
end
} bind def
% ======================== Page accessing ======================== %
% Get a (possibly inherited) attribute of a page.
/pget % <pagedict> <key> pget <value> -true-
% <pagedict> <key> pget -false-
{ 2 copy knownoget
{ exch pop exch pop true
}
{ exch /Parent knownoget
{ exch pget }
{ pop false }
ifelse
}
ifelse
} bind def
% Get the value of a resource on a given page.
/rget { % <resname> <pagedict> <restype> rget <value> -true-
% <resname> <pagedict> <restype> rget -false-
LocalResources 1 index knownoget {
3 index knownoget
} {
false
} ifelse {
exch pop exch pop exch pop true
} {
exch /Resources pget {
exch knownoget { exch knownoget } { pop false } ifelse
} {
pop pop false
} ifelse
} ifelse
} bind def
% Get the total number of pages in the document.
/pdfpagecount % - pdfpagecount <int>
{ Trailer /Root oget /Pages oget /Count oget
} bind def
% Find the N'th page of the document by iterating through the Pages tree.
% The first page is numbered 1.
/pdffindpageref { % <int> pdffindpage <objref>
dup Trailer /Root oget /Pages get
{ % We should be able to tell when we reach a leaf
% by finding a Type unequal to /Pages. Unfortunately,
% some files distributed by Adobe lack the Type key
% in some of the Pages nodes! Instead, we check for Kids.
dup oforce /Kids knownoget not { exit } if
exch pop null
0 1 3 index length 1 sub {
2 index exch get
dup oforce dup /Kids known { /Count oget } { pop 1 } ifelse
% Stack: index kids null noderef count
dup 5 index ge { pop exch pop exit } if
5 -1 roll exch sub 4 1 roll pop
} for exch pop
% Stack: index null|noderef
dup null eq { pop pop 1 null exit } if
} loop
% Stack: index countleft noderef
1 index 1 ne { pop pop /pdffindpage cvx /rangecheck signalerror } if
exch pop
PageIndex 2 index 1 sub 65533 .min 2 index oforce put
PageNumbers 1 index oforce 3 index dup 65534 le
{ put }
{ pop pop pop } % don't store more than 65534 pagenumbers
ifelse
exch pop
} bind def
/pdffindpage { % <int> pdffindpage <pagedict>
pdffindpageref oforce
} bind def
% Find the N'th page of the document.
% The first page is numbered 1.
/pdfgetpage % <int> pdfgetpage <pagedict>
{ PageIndex 1 index 1 sub dup 65533 lt
{ get }
{ pop pop null }
ifelse
dup null ne
{ exch pop oforce }
{ pop pdffindpage }
ifelse
} bind def
% Find the page number of a page object (inverse of pdfgetpage).
/pdfpagenumber % <pagedict> pdfpagenumber <int>
{ % We use the simplest and stupidest of all possible algorithms....
PageNumbers 1 index .knownget
{ exch pop
}
{ 1 1 PageCount 1 add % will give a rangecheck if not found
{ dup pdfgetpage oforce 2 index eq { exit } if pop
}
for exch pop
}
ifelse
} bind def
% Display a given page.
/boxrect % [<llx> <lly> <urx> <ury>] boxrect <x> <y> <w> <h>
{ aload pop exch 3 index sub exch 2 index sub
} bind def
/resolvedest { % <name|string|other> resolvedest <other|null>
dup type /nametype eq {
Trailer /Root oget /Dests knownoget {
exch knownoget not { null } if
} {
null
} ifelse
} {
dup type /stringtype eq {
Trailer /Root oget /Names knownoget {
/Dests knownoget {
exch nameoget
} {
pop null
} ifelse
} {
pop null
} ifelse
} if
} ifelse
} bind def
/linkdest { % <link|outline> linkdest
% ([/Page <n>] /View <view> | ) <link|outline>
dup /Dest knownoget
{ resolvedest
dup type /dicttype eq { /D knownoget not { null } if } if
dup null eq
{ pop }
{ dup 0 oget
dup null eq
{ pop }
{ dup type /integertype ne { pdfpagenumber } if
/Page exch 4 -2 roll
}
ifelse
dup length 1 sub 1 exch getinterval /View exch 3 -1 roll
}
ifelse
}
if
} bind def
% <pagedict> mark ... -proc- -
/namedactions 8 dict dup begin
/FirstPage {
/Page 1 3 -1 roll
} def
/LastPage {
counttomark 2 add index pdfpagecount /Page exch 3 -1 roll
} def
/NextPage {
counttomark 2 add index pdfpagenumber 1 add /Page exch 3 -1 roll
} def
/PrevPage {
counttomark 2 add index pdfpagenumber 1 sub /Page exch 3 -1 roll
} def
end readonly def
% <pagedict> <annotdict> -proc- -
/annottypes 5 dict dup begin
/Text {
mark exch
{ /Rect /Open /Contents }
{ 2 copy knownoget { 3 -1 roll } { pop } ifelse }
forall pop /ANN pdfmark
} bind def
/Link {
mark exch
{ /Rect /Border }
{ 2 copy knownoget { 3 -1 roll } { pop } ifelse }
forall dup /A knownoget {
dup /URI known {
/A mark 3 2 roll % <<>> /A [ <<action>>
{ oforce } forall
.dicttomark
3 2 roll
} {
dup /D knownoget {
exch pop exch dup length dict copy dup /Dest 4 -1 roll put
} {
/N knownoget { % Assume /S /Named
namedactions exch .knownget { exec } if
} if
} ifelse
} ifelse
} if
linkdest pop /LNK pdfmark
} bind def
end readonly def
/pdfshowpage % <pagedict> pdfshowpage -
{ dup /Page exch store
pdfshowpage_init
pdfshowpage_setpage
save /PDFSave exch store
(before exec) VMDEBUG
pdfshowpage_finish
(after exec) VMDEBUG
PDFSave restore
} bind def
/pdfpagecontents % <pagedict> pdfpagecontents <contents>
{ } bind def
/pdfshowpage_init % <pagedict> pdfshowpage_init <pagedict>
{ /DSCPageCount DSCPageCount 1 add store
} bind def
/.pdfshowpage_Install { % <pagedict> [<prevproc>] .pdfshowpage_Install -
exch
% We would like to clip to the CropBox here, but the subsequent
% initgraphics would override it. Instead, we have to handle it
% in graphicsbeginpage.
dup /MediaBox pget {
dup 0 get neg exch 1 get neg translate
} if
pop 0 get exec
} bind def
/pdfshowpage_setpage { % <pagedict> pdfshowpage_setpage <pagedict>
4 dict begin % for setpagedevice
% Stack: pagedict
currentpagedevice /Orientation 2 index /Rotate pget not { 0 } if 90 idiv
% Rotate specifies *clockwise* rotation!
neg 3 and def
% Stack: pagedict currentpagedict
1 index /MediaBox pget {
% Set the page size.
boxrect 2 array astore /PageSize exch def pop pop
} if
dup /Install .knownget {
% Don't let the Install procedure get more deeply
% nested after every page.
dup type dup /arraytype eq exch /packedarraytype eq or {
dup length 4 eq {
dup 2 get /.pdfshowpage_Install load eq {
1 get 0 get % previous procedure
} if
} if
} if
} {
{ }
} ifelse 1 array astore
2 index exch /.pdfshowpage_Install load /exec load
4 packedarray cvx
% Stack: pagedict currentpagedict installproc
/Install exch def
% Stack: pagedict currentpagedict
pop currentdict end setpagedevice
} bind def
/pdfshowpage_finish { % <pagedict> pdfshowpage_finish -
.writepdfmarks {
% Copy the crop box.
dup /CropBox knownoget {
% If the page has been rotated, rotate the CropBox.
mark /CropBox 3 -1 roll
3 index /Rotate pget {
90 idiv 1 and 0 ne {
aload pop 4 -2 roll exch 4 2 roll exch 4 array astore
} if
} if
/PAGE pdfmark
} if
% Copy annotations and links.
dup /Annots knownoget {
0 1 2 index length 1 sub
{ 1 index exch oget
dup /Subtype oget annottypes exch .knownget { exec } { pop } ifelse
}
for pop
} if
} if % end .writepdfmarks
% Display the actual page contents.
6 dict begin
/BXlevel 0 def
/BGDefault currentblackgeneration def
/UCRDefault currentundercolorremoval def
%****** DOESN'T HANDLE COLOR TRANSFER YET ******
/TRDefault currenttransfer def
matrix currentmatrix 2 dict
2 index /CropBox knownoget {
boxrect 4 array astore 1 index /ClipRect 3 -1 roll put
} if
dictbeginpage /DefaultMatrix 1 index store setmatrix
dup % for showing annotations below
count /pdfemptycount exch store
gsave
% If the page uses any transparency features, show it within
% a transparency group.
PDFversion 1.4 lt {
showpagecontents
} {
dup pageusestransparency {
% Show the page within a PDF 1.4 device filter.
0 .pushpdf14devicefilter {
% If the page has a Group, enclose contents in transparency group.
% (Adobe Tech Note 5407, sec 9.2)
dup /Group knownoget {
1 index /CropBox knownoget not {
1 index /MediaBox oget
} if .beginformgroup {
showpagecontents
} .internalstopped {
.discardtransparencygroup stop
} if .endtransparencygroup
} {
showpagecontents
} ifelse
} .internalstopped {
% todo: discard
.popdevicefilter stop
} if .popdevicefilter
} {
showpagecontents
} ifelse
} ifelse
grestore
% todo: mixing drawing ops outside the device filter could cause
% problems, for example with the pnga device.
/Annots knownoget { { oforce drawannot } forall } if
endpage
end % scratch dict
} bind def
/showpagecontents { % <pagedict> showpagecontents -
/Contents knownoget not { 0 array } if
dup type /arraytype ne { 1 array astore } if {
oforce false resolvestream pdfopdict .pdfrun
} forall
} bind def
/processcolorspace { % - processcolorspace <colorspace>
% The following is per the PLRM3.
currentdevice 1 dict dup /ProcessColorModel dup put .getdeviceparams
exch pop exch pop
dup type /nametype ne { cvn } if
dup { setcolorspace } .internalstopped { pop /DeviceRGB } if
} bind def
% ------ Transparency support ------ %
% Determine whether a page might invoke any transparency features:
% - Group in the page dictionary
% - Non-default ca, CA, or SMask in an ExtGState
% - Form XObject with Group
% - Image XObject with SMask
% ****** DO WE NEED TO LOOK IN RESOURCE DICTS OF OTHER CONTENT STREAMS? ******
/pageusestransparency { % <pagedict> pageusestransparency <bool>
PDFversion 1.4 lt {
pop false
} {
dup /Group known {
pop true
} {
false exch {
dup resourceusestransparency { pop not exit } if
/Parent knownoget not { exit } if
} loop
} ifelse
} ifelse
} bind def
% Check the Resources of a page or Form.
/resourceusestransparency { % <dict> resourceusestransparency <bool>
{ % Use loop to provide an exitable context.
/Resources knownoget not { 0 dict } if
dup /ExtGState knownoget {
false exch {
exch pop oforce
dup /ca knownoget { 1 ne { pop not exit } if } if
dup /CA knownoget { 1 ne { pop not exit } if } if
dup /SMask knownoget { /None ne { pop not exit } if } if
pop
} forall { pop true exit } if
} if
dup /XObject knownoget {
false exch {
exch pop oforce dup /Subtype get
dup /Image eq { 1 index /SMask known { pop pop not exit } if } if
/Form eq {
dup /Group known { pop not exit } if
resourceusestransparency { not exit } if
} {
pop
} ifelse
} forall { pop true exit } if
} if
pop false exit
} loop
} bind def
end % pdfdict
.setglobal