fenix
/
cpdf-source
mirror of https://github.com/johnwhitington/cpdf-source.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

First recrypting example working

This commit is contained in:
John Whitington 2014-10-15 17:51:15 +01:00
parent 70226120d4
commit 8b02d20041
3 changed files with 102 additions and 78 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

140
cpdfcommand.ml
View File

@ -431,7 +431,9 @@ let banned banlist = function
| Decrypt | Encrypt -> true (* Never allowed *)
| _ -> mem Pdfcrypt.NoEdit banlist
let operation_allowed banlist = function
let operation_allowed banlist op =
args.recrypt || (* FIXME *)
match op with
| None -> true (* Merge *) (* changed to allow it *)
| Some op -> not (banned banlist op)
@ -1155,8 +1157,8 @@ let setlabelstartval i =
let setcpdflin s =
args.cpdflin <- Some s
let setrecrypt b =
args.recrypt <- b
let setrecrypt () =
args.recrypt <- true
(* Parse a control file, make an argv, and then make Arg parse it. *)
let rec make_control_argv_and_parse filename =
@ -1209,7 +1211,7 @@ and specs =
Arg.String setcpdflin,
" Set location of 'cpdflin'");
("-recrypt",
Arg.Bool setrecrypt,
Arg.Unit setrecrypt,
" Keep this file's encryption when writing");
("-raw",
Arg.Unit (setencoding Cpdf.Raw),
@ -1323,7 +1325,7 @@ and specs =
"");
("-squeeze",
Arg.Unit setsqueeze,
" Slow, lossless compression of a PDF file");
"");
("-list-bookmarks",
Arg.Unit (setop ListBookmarks),
" List Bookmarks");
@ -1705,16 +1707,87 @@ let filesize name =
with
_ -> 0
let pdf_of_stdin user_pw owner_pw =
let user_pw = Some user_pw
and owner_pw = if owner_pw = "" then None else Some owner_pw
in
let o, bytes = Pdfio.input_output_of_bytes 16384 in
try
while true do o.Pdfio.output_char (input_char stdin) done;
Pdf.empty ()
with
End_of_file ->
let i = Pdfio.input_of_bytes (Pdfio.extract_bytes_from_input_output o bytes) in
pdfread_pdf_of_input user_pw owner_pw i
let filenames = null_hash ()
(* This now memoizes on the name of the file to make sure we only load each
file once *)
let get_pdf_from_input_kind ((_, _, _, u, o) as input) op = function
| AlreadyInMemory pdf -> pdf
| InFile s ->
if args.squeeze then
begin
let size = filesize s in
initial_file_size := size;
Printf.printf "Initial file size is %i bytes\n" size
end;
begin try Hashtbl.find filenames s with
Not_found ->
let pdf = decrypt_if_necessary input op (pdfread_pdf_of_file (optstring u) (optstring o) s) in
Hashtbl.add filenames s pdf; pdf
end
| StdIn ->
decrypt_if_necessary input op (pdf_of_stdin u o)
let get_single_pdf op read_lazy =
match args.inputs with
| (InFile inname, _, _, u, o) as input::_ ->
if args.squeeze then
Printf.printf "Initial file size is %i bytes\n" (filesize inname);
let pdf =
if read_lazy then
pdfread_pdf_of_channel_lazy (optstring u) (optstring o) (open_in_bin inname)
else
pdfread_pdf_of_file (optstring u) (optstring o) inname
in
decrypt_if_necessary input op pdf
| (StdIn, _, _, u, o) as input::_ ->
decrypt_if_necessary input op (pdf_of_stdin u o)
| (AlreadyInMemory pdf, _, _, _, _)::_ -> pdf
| _ ->
raise (Arg.Bad "cpdf: No input specified.\n")
let get_single_pdf_nodecrypt read_lazy =
match args.inputs with
| (InFile inname, _, _, u, o)::_ ->
if args.squeeze then
Printf.printf "Initial file size is %i bytes\n" (filesize inname);
if read_lazy then
pdfread_pdf_of_channel_lazy (optstring u) (optstring o) (open_in_bin inname)
else
pdfread_pdf_of_file (optstring u) (optstring o) inname
| (StdIn, _, _, u, o)::_ -> pdf_of_stdin u o
| (AlreadyInMemory pdf, _, _, _, _)::_ -> pdf
| _ ->
raise (Arg.Bad "cpdf: No input specified.\n")
let really_write_pdf ?(encryption = None) mk_id pdf outname =
let outname' =
if args.linearize
then Filename.temp_file "cpdflin" ".pdf"
else outname
in
Pdfwrite.pdf_to_file_options
~preserve_objstm:args.preserve_objstm
~generate_objstm:args.create_objstm
false encryption mk_id pdf outname';
begin if args.recrypt then
Pdfwrite.pdf_to_file_recrypting
(get_single_pdf_nodecrypt false) pdf args.user outname'
else
Pdfwrite.pdf_to_file_options
~preserve_objstm:args.preserve_objstm
~generate_objstm:args.create_objstm
false encryption mk_id pdf outname'
end;
begin
if args.linearize then
let cpdflin =
@ -1781,62 +1854,13 @@ let write_pdf ?(encryption = None) ?(is_decompress=false) mk_id pdf =
with
End_of_file -> flush stdout (*r For Windows *)
let pdf_of_stdin user_pw owner_pw =
let user_pw = Some user_pw
and owner_pw = if owner_pw = "" then None else Some owner_pw
in
let o, bytes = Pdfio.input_output_of_bytes 16384 in
try
while true do o.Pdfio.output_char (input_char stdin) done;
Pdf.empty ()
with
End_of_file ->
let i = Pdfio.input_of_bytes (Pdfio.extract_bytes_from_input_output o bytes) in
pdfread_pdf_of_input user_pw owner_pw i
let get_single_pdf op read_lazy =
match args.inputs with
| (InFile inname, _, _, u, o) as input::_ ->
if args.squeeze then
Printf.printf "Initial file size is %i bytes\n" (filesize inname);
let pdf =
if read_lazy then
pdfread_pdf_of_channel_lazy (optstring u) (optstring o) (open_in_bin inname)
else
pdfread_pdf_of_file (optstring u) (optstring o) inname
in
decrypt_if_necessary input op pdf
| (StdIn, _, _, u, o) as input::_ ->
decrypt_if_necessary input op (pdf_of_stdin u o)
| (AlreadyInMemory pdf, _, _, _, _)::_ -> pdf
| _ ->
raise (Arg.Bad "cpdf: No input specified.\n")
let get_pagespec () =
match args.inputs with
| (_, ps, _, _, _)::_ -> ps
| _ -> error "get_pagespec"
let filenames = null_hash ()
(* This now memoizes on the name of the file to make sure we only load each
file once *)
let get_pdf_from_input_kind ((_, _, _, u, o) as input) op = function
| AlreadyInMemory pdf -> pdf
| InFile s ->
if args.squeeze then
begin
let size = filesize s in
initial_file_size := size;
Printf.printf "Initial file size is %i bytes\n" size
end;
begin try Hashtbl.find filenames s with
Not_found ->
let pdf = decrypt_if_necessary input op (pdfread_pdf_of_file (optstring u) (optstring o) s) in
Hashtbl.add filenames s pdf; pdf
end
| StdIn ->
decrypt_if_necessary input op (pdf_of_stdin u o)
(* Copy a font from [frompdf] with name [fontname] on page [fontpage] to [pdf] on all pages in [range] *)
let copy_font frompdf fontname fontpage range pdf =

BIN
cpdfmanual.pdf
View File

Binary file not shown.

40
cpdfmanual.tex
View File

@ -923,10 +923,10 @@ metadata. Add \texttt{-no-encrypt-metadata} to the command line.
\vspace{1.5mm}
\noindent\verb!cpdf -compress in.pdf -o out.pdf!
\vspace{1.5mm}
\noindent\verb!cpdf -squeeze in.pdf -o out.pdf!
%\vspace{1.5mm}
%\noindent\verb!cpdf -squeeze in.pdf -o out.pdf!
\end{framed}
\cpdf\ provides basic facilities for decompressing and compressing PDF streams, and a more advanced PDF \textit{squeezer}.
\cpdf\ provides basic facilities for decompressing and compressing PDF streams.
\section{Decompressing a Document}
\index{decompressing}
To decompress the streams in a PDF file, for instance to manually inspect the
@ -945,24 +945,24 @@ PDF, use:
\textbf{Flate\-Decode} method, with the exception of Metadata streams, which
are left uncompressed.
\section{Squeezing a Document}
\index{squeeze}
To \textit{squeeze} a PDF file, reducing its size by an average of about twenty percent (though sometimes not at all), use:
\begin{framed}
\small\verb!cpdf -squeeze in.pdf -o out.pdf!
\end{framed}
\noindent Adding \texttt{-squeeze} to the command line when using another operation will \textit{squeeze} the file or files upon output.
% \section{Squeezing a Document}
%\index{squeeze}
% To \textit{squeeze} a PDF file, reducing its size by an average of about twenty percent (though sometimes not at all), use:
% \begin{framed}
% \small\verb!cpdf -squeeze in.pdf -o out.pdf!
% \end{framed}
% \noindent Adding \texttt{-squeeze} to the command line when using another operation will \textit{squeeze} the file or files upon output.
%
% The \texttt{-squeeze} operation writes some information about the squeezing process to standard output. The squeezing process involves several processes which losslessly attempt to reduce the file size. It is slow, so should not be used without thought.
The \texttt{-squeeze} operation writes some information about the squeezing process to standard output. The squeezing process involves several processes which losslessly attempt to reduce the file size. It is slow, so should not be used without thought.
\begin{verbatim}
$ ./cpdf -squeeze in.pdf -o out.pdf
Beginning squeeze: 123847 objects
Squeezing... Down to 114860 objects
Squeezing... Down to 114842 objects
Squeezing page data
Recompressing document
\end{verbatim}
%\begin{verbatim}
%$ ./cpdf -squeeze in.pdf -o out.pdf
%Beginning squeeze: 123847 objects
%Squeezing... Down to 114860 objects
%Squeezing... Down to 114842 objects
%Squeezing page data
%Recompressing document
%\end{verbatim}
\chapter{Bookmarks}
\begin{framed}