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

First rough JSON outputter

This commit is contained in:
John Whitington 2020-01-31 12:17:55 +00:00
parent b09235e28b
commit 4b801006e8
1 changed files with 18 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
cpdfwriteJSON.ml
View File

@ -120,33 +120,43 @@ let json_of_op = function
| O.Op_BMC s -> J.Array [J.String "BMC"] | O.Op_BMC s -> J.Array [J.String "BMC"]
| O.Op_Unknown _ ->J.Array [J.String "Unknown"] *) | O.Op_Unknown _ ->J.Array [J.String "Unknown"] *)
let parse_content_stream str = (* parse_stream needs pdf and resources. These are for lexing of inline images,
let ops = Pdfops.parse_stream (Pdf.empty ()) (Pdf.Dictionary []) [Pdfio.bytes_of_string str] in * looking up the colourspace. We do not need to worry about inherited
* resources, though? For now, don't worry about inherited resources: check in
* PDF standard. *)
let parse_content_stream pdf resources bs =
let ops = Pdfops.parse_stream pdf resources [bs] in
J.Array (List.map json_of_op ops) J.Array (List.map json_of_op ops)
let json_of_pdf parse_content pdf = let json_of_pdf parse_content pdf =
let trailerdict = (0, json_of_object (fun x -> ()) pdf.Pdf.trailerdict) in let trailerdict = (0, json_of_object (fun x -> ()) pdf.Pdf.trailerdict) in
let content_streams = ref [] in let content_streams = ref [] in
let fcs n = content_streams := n::!content_streams in
let pairs = let pairs =
let ps = ref [] in let ps = ref [] in
Pdf.objiter Pdf.objiter
(fun i pdfobj -> (fun i pdfobj ->
ps := (i, json_of_object (fun n -> content_streams := n::!content_streams) pdfobj)::!ps) ps := (i, json_of_object fcs pdfobj)::!ps)
pdf; pdf;
trailerdict::!ps trailerdict::!ps
in in
List.iter (Printf.printf "Found content stream %i\n") !content_streams; List.iter (Printf.printf "Found content stream %i\n") !content_streams;
List.iter List.iter (fun n -> Pdfcodec.decode_pdfstream_until_unknown pdf (Pdf.lookup_obj pdf n)) !content_streams;
(fun n -> try Pdfcodec.decode_pdfstream_until_unknown pdf (Pdf.lookup_obj pdf n) with _ -> ()) (* Debug PDF to file here *)
!content_streams;
let pairs_parsed = let pairs_parsed =
if not parse_content then pairs else if not parse_content then pairs else
List.map List.map
(fun (objnum, obj) -> (fun (objnum, obj) ->
if Pdfutil.mem objnum !content_streams then if Pdfutil.mem objnum !content_streams then
begin match obj with begin match obj with
| J.Array [dict; J.String streamdata] -> | J.Array [dict; J.String _] ->
(objnum, J.Array [dict; parse_content_stream streamdata]) (* FIXME Proper resources here for reasons explained above *)
let streamdata =
match Pdf.lookup_obj pdf objnum with
| Stream {contents = (_, Got b)} -> b
| _ -> failwith "JSON: stream not decoded"
in
(objnum, J.Array [dict; parse_content_stream pdf (Pdf.Dictionary []) streamdata])
| _ -> failwith "json_of_pdf: stream parsing inconsistency" | _ -> failwith "json_of_pdf: stream parsing inconsistency"
end end
else else