| 1 | # This program is free software; you can redistribute it and/or modify |
|---|
| 2 | # it under the terms of the GNU General Public License as published by |
|---|
| 3 | # the Free Software Foundation; either version 2 of the License, or |
|---|
| 4 | # (at your option) any later version. |
|---|
| 5 | # |
|---|
| 6 | # This program is distributed in the hope that it will be useful, but WITHOUT |
|---|
| 7 | # ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS |
|---|
| 8 | # FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details |
|---|
| 9 | # |
|---|
| 10 | # You should have received a copy of the GNU General Public License along with |
|---|
| 11 | # this program; if not, write to the Free Software Foundation, Inc., |
|---|
| 12 | # 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. |
|---|
| 13 | """ Copyright (c) 2003-2007 LOGILAB S.A. (Paris, FRANCE). |
|---|
| 14 | http://www.logilab.fr/ -- mailto:contact@logilab.fr |
|---|
| 15 | |
|---|
| 16 | manipulate pdf and fdf files. pdftk recommended. |
|---|
| 17 | |
|---|
| 18 | Notes regarding pdftk, pdf forms and fdf files (form definition file) |
|---|
| 19 | fields names can be extracted with: |
|---|
| 20 | pdftk orig.pdf generate_fdf output truc.fdf |
|---|
| 21 | to merge fdf and pdf: |
|---|
| 22 | pdftk orig.pdf fill_form test.fdf output result.pdf [flatten] |
|---|
| 23 | without flatten, one could further edit the resulting form. |
|---|
| 24 | with flatten, everything is turned into text. |
|---|
| 25 | """ |
|---|
| 26 | |
|---|
| 27 | import os |
|---|
| 28 | |
|---|
| 29 | HEAD="""%FDF-1.2 |
|---|
| 30 | %\xE2\xE3\xCF\xD3 |
|---|
| 31 | 1 0 obj |
|---|
| 32 | << |
|---|
| 33 | /FDF |
|---|
| 34 | << |
|---|
| 35 | /Fields [ |
|---|
| 36 | """ |
|---|
| 37 | |
|---|
| 38 | TAIL="""] |
|---|
| 39 | >> |
|---|
| 40 | >> |
|---|
| 41 | endobj |
|---|
| 42 | trailer |
|---|
| 43 | |
|---|
| 44 | << |
|---|
| 45 | /Root 1 0 R |
|---|
| 46 | >> |
|---|
| 47 | %%EOF |
|---|
| 48 | """ |
|---|
| 49 | |
|---|
| 50 | def output_field( f ): |
|---|
| 51 | return "\xfe\xff" + "".join( [ "\x00"+c for c in f ] ) |
|---|
| 52 | |
|---|
| 53 | def extract_keys(lines): |
|---|
| 54 | keys = [] |
|---|
| 55 | for line in lines: |
|---|
| 56 | if line.startswith('/V'): |
|---|
| 57 | pass #print 'value',line |
|---|
| 58 | elif line.startswith('/T'): |
|---|
| 59 | key = line[7:-2] |
|---|
| 60 | key = ''.join(key.split('\x00')) |
|---|
| 61 | keys.append( key ) |
|---|
| 62 | return keys |
|---|
| 63 | |
|---|
| 64 | def write_field(out, key, value): |
|---|
| 65 | out.write("<<\n") |
|---|
| 66 | if value: |
|---|
| 67 | out.write("/V (%s)\n" %value) |
|---|
| 68 | else: |
|---|
| 69 | out.write("/V /\n") |
|---|
| 70 | out.write("/T (%s)\n" % output_field(key) ) |
|---|
| 71 | out.write(">> \n") |
|---|
| 72 | |
|---|
| 73 | def write_fields(out, fields): |
|---|
| 74 | out.write(HEAD) |
|---|
| 75 | for (key,value,comment) in fields: |
|---|
| 76 | write_field(out, key, value) |
|---|
| 77 | write_field(out, key+"a", value) # pour copie-carbone sur autres pages |
|---|
| 78 | out.write(TAIL) |
|---|
| 79 | |
|---|
| 80 | def extract_keys_from_pdf(filename): |
|---|
| 81 | # what about using 'pdftk filename dump_data_fields' and parsing the output ? |
|---|
| 82 | os.system('pdftk %s generate_fdf output /tmp/toto.fdf' % filename) |
|---|
| 83 | lines = file('/tmp/toto.fdf').readlines() |
|---|
| 84 | return extract_keys(lines) |
|---|
| 85 | |
|---|
| 86 | |
|---|
| 87 | def fill_pdf(infile, outfile, fields): |
|---|
| 88 | write_fields(file('/tmp/toto.fdf', 'w'), fields) |
|---|
| 89 | os.system('pdftk %s fill_form /tmp/toto.fdf output %s flatten' % (infile, outfile)) |
|---|
| 90 | |
|---|
| 91 | def testfill_pdf(infile, outfile): |
|---|
| 92 | keys = extract_keys_from_pdf(infile) |
|---|
| 93 | fields = [] |
|---|
| 94 | for key in keys: |
|---|
| 95 | fields.append( (key, key, '') ) |
|---|
| 96 | fill_pdf(infile, outfile, fields) |
|---|
