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

more

This commit is contained in:
John Whitington 2021-11-01 13:17:54 +00:00
parent ee8a10aae4
commit f071f1805a
1 changed files with 1 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
cpdfjson.ml
View File

@ -453,22 +453,12 @@ let precombine_page_content pdf =
in in
Pdfpage.change_pages true pdf pages' Pdfpage.change_pages true pdf pages'
(* PDF strings (except /ID in the trailer dictionary) are either PDFDocEncoding
or UTF16BE. Many times the UTF16BE can all be represented in PDFDocEncoding.
In this case, there are just lots of \000 bytes getting in the way making the
JSON hard to edit. So we preprocess such simple UTF16BE strings into
PDFDocEncoding. *)
let preprocess_string s =
if Pdftext.is_unicode s
then Pdftext.pdfdocstring_of_utf8 (Pdftext.utf8_of_pdfdocstring s)
else s
let rec ppstring_single_object pdf = function let rec ppstring_single_object pdf = function
| Pdf.Dictionary d -> Pdf.recurse_dict (ppstring_single_object pdf) d | Pdf.Dictionary d -> Pdf.recurse_dict (ppstring_single_object pdf) d
| (Pdf.Stream {contents = (Pdf.Dictionary dict, data)}) -> | (Pdf.Stream {contents = (Pdf.Dictionary dict, data)}) ->
Pdf.Stream {contents = (Pdf.recurse_dict (ppstring_single_object pdf) dict, data)} Pdf.Stream {contents = (Pdf.recurse_dict (ppstring_single_object pdf) dict, data)}
| Pdf.Array a -> Pdf.recurse_array (ppstring_single_object pdf) a | Pdf.Array a -> Pdf.recurse_array (ppstring_single_object pdf) a
| Pdf.String s -> Pdf.String (preprocess_string s) | Pdf.String s -> Pdf.String (Pdftext.simplify_utf16be s)
| x -> x | x -> x
let preprocess_strings pdf = let preprocess_strings pdf =