Add pdfraw format, v1.5

3 files changed, 67 insertions, 10 deletions

diff --git a/PolyglotFile/__init__.py b/PolyglotFile/__init__.py
index 4261a1a..6800028 100644
--- a/PolyglotFile/__init__.py
+++ b/PolyglotFile/__init__.py
@@ -2,6 +2,7 @@
 # -*- coding: utf-8 -*-
 
 from .polyglotpdfzip import PolyglotPdfZip
+from .polyglotpdfraw import PolyglotPdfRaw
 from .polyglotzippdf import PolyglotZipPdf
 from .polyglotszippdf import PolyglotSZipPdf
 
diff --git a/PolyglotFile/polyglotpdfraw.py b/PolyglotFile/polyglotpdfraw.py
new file mode 100644
index 0000000..c524788
--- /dev/null
+++ b/PolyglotFile/polyglotpdfraw.py
@@ -0,0 +1,40 @@
+# -*- coding: utf-8 -*-
+
+import logging
+
+'''
+    |-------------------------------|    -
+    |--------- PDF Header ----------K1   | J1
+    |-------------------------------|    -
+    |----- PDF OBJ 1 = RAW Data ----K2   |
+    |-------------------------------|    -
+    |---- Original PDF Ojbects -----K3   | J2
+    |-------------------------------|    -
+    |---------- Xref Table ---------|    |
+    |-------------------------------K5   |
+    |----------- Trailer -----------|    |
+    |-------------------------------|    |
+'''
+
+
+class PolyglotPdfRaw():
+    from PdfFileTransformer import Pdf
+
+    def __init__(self, Pdf, Raw_filename):
+        self.buffer = bytearray()
+        self.pdf = Pdf
+        self.raw_filename = Raw_filename
+        self.buffer = bytearray()
+
+    def generate(self):
+        raw_buffer = bytearray()
+        with open(self.raw_filename, "rb") as f:
+            raw_buffer = f.read()
+        k2_stream = raw_buffer
+        self.pdf.insert_new_obj_stream_at_start(k2_stream)
+        self.buffer = self.pdf.get_build_buffer()
+
+    def write(self, filename):
+        fd = open(filename, "wb")
+        fd.write(self.buffer)
+        fd.close()
diff --git a/truepolyglot b/truepolyglot
index 4b4075f..5208e64 100755
--- a/truepolyglot
+++ b/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 PolyglotPdfRaw
 
 
 def main():
@@ -17,9 +20,11 @@ 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.'
+                       '* pdfraw: Generate a file strictly valid as a PDF ' +
+                       ' with a custom first object content.')
     usage_str = '%(prog)s format [options] output-file'
-    epilog_str = 'TruePolyglot v1.4.1'
+    epilog_str = 'TruePolyglot v1.5'
     frm = argparse.RawTextHelpFormatter
     parser = argparse.ArgumentParser(description=description_str,
                                      epilog=epilog_str,
@@ -27,12 +32,15 @@ def main():
                                      formatter_class=frm)
     parser.add_argument('format', nargs='+', choices=["pdfzip",
                                                       "zippdf",
-                                                      "szippdf"],
+                                                      "szippdf",
+                                                      "pdfraw"],
                         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('--rawfile', dest='rawfile',
+                        help='RAW 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 +54,14 @@ 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 args.pdffile is None:
+    if "pdf" in args.format[0] and 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 "raw" in args.format[0] and args.rawfile is None:
+            parser.error('rawfile is required')
 
     if args.verbose == "none":
         logging.basicConfig(level=logging.CRITICAL)
@@ -64,14 +72,22 @@ def main():
     if args.verbose == "debug":
         logging.basicConfig(level=logging.DEBUG)
 
-    p = Pdf(args.pdffile)
-    z = Zip(args.zipfile)
     if args.format[0] == "pdfzip":
+        p = Pdf(args.pdffile)
+        z = Zip(args.zipfile)
         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] == "pdfraw":
+        p = Pdf(args.pdffile)
+        a = PolyglotPdfRaw(p, args.rawfile)
+
     a.generate()
     a.write(args.output_file[0])