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 2021-11-03 16:05:53 +00:00
parent 7c4fbf589d
commit 16aad662f4
2 changed files with 33 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Changes
View File

@ -1,6 +1,6 @@
2.5 (Upcoming 2022) 2.5 (Upcoming 2022)
o New operation -print-font-encoding o New operation -print-font-table gives (charcode, unicode, glyph name) triples
o Can now search for a font by real name with -font o Can now search for a font by real name with -font
o Text added in existing fonts is now encoding-aware (plus new raw mode) o Text added in existing fonts is now encoding-aware (plus new raw mode)
o New -print-dict-entry operation prints values for a given key o New -print-dict-entry operation prints values for a given key

37
cpdfcommand.ml
View File

@ -2377,12 +2377,12 @@ and specs =
("-stamp-as-xobject", ("-stamp-as-xobject",
Arg.String setstampasxobject, Arg.String setstampasxobject,
" Stamp a file as a form xobject in another"); " Stamp a file as a form xobject in another");
("-print-font-encoding", ("-print-font-table",
Arg.String setprintfontencoding, Arg.String setprintfontencoding,
" Print the encoding for a given font"); " Print the /ToUnicode table for a given font, if present.");
("-print-font-encoding-page", ("-print-font-table-page",
Arg.Int setfontpage, Arg.Int setfontpage,
" Set page for -print-font-encoding"); " Set page for -print-font-table");
(* These items are undocumented *) (* These items are undocumented *)
("-remove-unused-resources", Arg.Unit (setop RemoveUnusedResources), ""); ("-remove-unused-resources", Arg.Unit (setop RemoveUnusedResources), "");
("-stay-on-error", Arg.Unit setstayonerror, ""); ("-stay-on-error", Arg.Unit setstayonerror, "");
@ -3333,7 +3333,34 @@ let collate (names, pdfs, ranges) =
done; done;
split3 (rev !nis) split3 (rev !nis)
let print_font_encoding pdf fontname pagenumber = () let print_font_encoding pdf fontname pagenumber =
let page = try List.nth (Pdfpage.pages_of_pagetree pdf) (pagenumber - 1) with e -> error "page not found" in
match Pdf.lookup_direct pdf "/Font" page.Pdfpage.resources with
| Some fontdict ->
let font =
begin match Pdf.lookup_direct pdf fontname fontdict with
| Some font -> font
| None ->
(* For each item in the fontdict, follow its value and find the basename. If it matches, return that font *)
let font = ref None in
iter
(fun (k, v) ->
match Pdf.lookup_direct pdf "/BaseFont" v with
| Some (Pdf.Name n) when n = fontname -> font := Some v
| _ -> ())
(match fontdict with Pdf.Dictionary d -> d | _ -> []);
match !font with Some f -> f | None -> failwith (Printf.sprintf "print_font_encoding: font %s not found" fontname)
end
in
let extractor = Pdftext.text_extractor_of_font pdf font in
for x = 0 to 255 do
let str = string_of_char (char_of_int x) in
Printf.printf "%i = %s = %s\n"
x
(Pdftext.utf8_of_codepoints (Pdftext.codepoints_of_text extractor str))
(fold_left ( ^ ) "" (Pdftext.glyphnames_of_text extractor str))
done
| _ -> failwith "addtext: font not found for width"
(* Main function *) (* Main function *)
let go () = let go () =