Fix PDF offset with acrobat-compatibility option.

PolyglotFile/__init__.py

@@ -2,6 +2,7 @@
 # -*- coding: utf-8 -*-
 
 from .polyglotpdfzip import PolyglotPdfZip
+from .polyglotpdfany import PolyglotPdfAny
 from .polyglotzippdf import PolyglotZipPdf
 from .polyglotszippdf import PolyglotSZipPdf
 

PolyglotFile/polyglotpdfany.py

@@ -0,0 +1,51 @@
+# -*- coding: utf-8 -*-
+
+import logging
+
+'''
+    |-------------------------------|    -
+    |--------- PDF Header ----------K1   | J1
+    |-------------------------------|    -
+    |---- PDF OBJ 1 = Payload 1 ----K2   |
+    |-------------------------------|    -
+    |---- Original PDF Ojbects -----K3   | J2
+    |-------------------------------|    -
+    |-- PDF Last OBJ = Payload 2 ---K4   |
+    |-------------------------------|    |
+    |---------- Xref Table ---------|    |
+    |-------------------------------K5   |
+    |----------- Trailer -----------|    |
+    |-------------------------------|    |
+'''
+
+
+class PolyglotPdfAny():
+    from PdfFileTransformer import Pdf
+
+    def __init__(self, Pdf, payload1filename, payload2filename):
+        self.buffer = bytearray()
+        self.pdf = Pdf
+        self.payload1 = bytearray()
+        if payload1filename is not None:
+            with open(payload1filename, "rb") as f:
+                self.payload1 = f.read()
+        self.payload2 = bytearray()
+        if payload2filename is not None:
+            with open(payload2filename, "rb") as f:
+                self.payload2 = f.read()
+
+        self.buffer = bytearray()
+
+    def generate(self):
+        k2stream = self.payload1
+        if len(k2stream) > 0:
+            self.pdf.insert_new_obj_stream_at_start(k2stream)
+        k4stream = self.payload2
+        if len(k4stream) > 0:
+            self.pdf.insert_new_obj_stream_at_end(k4stream)
+        self.buffer = self.pdf.get_build_buffer()
+
+    def write(self, filename):
+        fd = open(filename, "wb")
+        fd.write(self.buffer)
+        fd.close()

PolyglotFile/polyglotszippdf.py

@@ -81,6 +81,8 @@ class PolyglotSZipPdf(PolyglotPdfZip):
         k2_stream_offset = new_pdf.get_first_stream_offset()
 
         new_pdf.file_offset = offset
+        if self.acrobat_compatibility:
+            new_pdf.file_offset = new_pdf.file_offset + 1
         pdf_buffer = new_pdf.get_build_buffer()
         j2 = pdf_buffer[k2_stream_offset + size_k2_stream:]
 

truepolyglot

@@ -6,7 +6,10 @@ import logging
 
 from PdfFileTransformer import Pdf
 from ZipFileTransformer import Zip
-from PolyglotFile import PolyglotZipPdf, PolyglotPdfZip, PolyglotSZipPdf
+from PolyglotFile import PolyglotZipPdf
+from PolyglotFile import PolyglotPdfZip
+from PolyglotFile import PolyglotSZipPdf
+from PolyglotFile import PolyglotPdfAny
 
 
 def main():
@@ -17,9 +20,12 @@ def main():
                        ' The format is closest to ZIP.\n' +
                        '* szippdf: Generate a file valid as ZIP and PDF.' +
                        ' The format is strictly a ZIP.' +
-                       ' Archive is modified.')
+                       ' Archive is modified.\n' +
+                       '* pdfany: Generate a valid PDF file with payload1' +
+                       ' file content as first object or/and payload2 file' +
+                       ' content as last oject.\n')
     usage_str = '%(prog)s format [options] output-file'
-    epilog_str = 'TruePolyglot v1.4.1'
+    epilog_str = 'TruePolyglot v1.5.3'
     frm = argparse.RawTextHelpFormatter
     parser = argparse.ArgumentParser(description=description_str,
                                      epilog=epilog_str,
@@ -27,12 +33,17 @@ def main():
                                      formatter_class=frm)
     parser.add_argument('format', nargs='+', choices=["pdfzip",
                                                       "zippdf",
-                                                      "szippdf"],
+                                                      "szippdf",
+                                                      "pdfany"],
                         help='Output polyglot format')
     parser.add_argument('--pdffile', dest='pdffile',
                         help='PDF input file')
     parser.add_argument('--zipfile', dest='zipfile',
                         help='ZIP input file')
+    parser.add_argument('--payload1file', dest='payload1file',
+                        help='Payload 1 input file')
+    parser.add_argument('--payload2file', dest='payload2file',
+                        help='Payload 2 input file')
     parser.add_argument('--acrobat-compatibility',
                         dest='acrobat_compatibility',
                         help='Add a byte at start for Acrobat Reader compatibility with szippdf format',
@@ -46,14 +57,15 @@ def main():
 
     args = parser.parse_args()
 
-    formats = ["pdfzip", "zippdf", "szippdf"]
     if args.acrobat_compatibility and args.format[0] != "szippdf":
         parser.error('--acrobat-compatibility is for szippdf only')
-    if args.format[0] in formats:
+    if "pdf" in args.format[0] and args.pdffile is None:
-        if args.pdffile is None:
         parser.error('pdffile is required')
-        if args.zipfile is None:
+    if "zip" in args.format[0] and args.zipfile is None:
         parser.error('zipfile is required')
+    if ("any" in args.format[0] and args.payload1file is None and
+            args.payload2file is None):
+        parser.error('payload1file or payload2file is required')
 
     if args.verbose == "none":
         logging.basicConfig(level=logging.CRITICAL)
@@ -64,14 +76,22 @@ def main():
     if args.verbose == "debug":
         logging.basicConfig(level=logging.DEBUG)
 
+    if args.format[0] == "pdfzip":
         p = Pdf(args.pdffile)
         z = Zip(args.zipfile)
-    if args.format[0] == "pdfzip":
         a = PolyglotPdfZip(p, z)
     if args.format[0] == "zippdf":
+        p = Pdf(args.pdffile)
+        z = Zip(args.zipfile)
         a = PolyglotZipPdf(p, z)
     if args.format[0] == "szippdf":
+        p = Pdf(args.pdffile)
+        z = Zip(args.zipfile)
         a = PolyglotSZipPdf(p, z, args.acrobat_compatibility)
+    if args.format[0] == "pdfany":
+        p = Pdf(args.pdffile)
+        a = PolyglotPdfAny(p, args.payload1file, args.payload2file)
+
     a.generate()
     a.write(args.output_file[0])