Fixed some ROM signature and extraction bugs; added debug info during file open…

Fixed some ROM signature and extraction bugs; added debug info during file open failures; updated plugins to use file.path instead of file.name

src/binwalk/core/common.py

@@ -258,7 +258,7 @@ class StringFile(object):
     '''
 
     def __init__(self, fname, mode='r'):
-        self.string = fname
+        self.string = fname #bytes2str(fname)
         self.name = "String"
         self.args.size = len(self.string)
 

src/binwalk/magic/filesystems

@@ -561,10 +561,10 @@
 >>0     string          !Rom\x2E        {invalid} unknown endianness
 >0      string          \x2EmoR         little endian,
 >>8     lelong          x               size: <= %d
->>8     lelong-0x20     x               {jump:%d}
+#>>8     lelong-0x20     x               {jump:%d}
 >0      string          Rom\x2E         big endian,
 >>8     belong          x               size: <= %d
->>8     belong-0x20     x               {jump:%d}
+#>>8     belong-0x20     x               {jump:%d}
 
 # Wind River MemFS file system, found in some VxWorks devices
 0       string    owowowowowowowowowowowowowowow    Wind River management filesystem,{overlap}

src/binwalk/modules/extractor.py

@@ -254,6 +254,7 @@ class Extractor(Module):
                     # Report the file_path, not the real_file_path, otherwise symlinks will be resolved and
                     # the same file can end up being listed multiple times if there are symlinks to it.
                     if real_file_path != dd_file_path:
+                        binwalk.core.common.debug("Adding %s (%s) (%s) to file list" % (file_path, f, real_file_path))
                         self.output[r.file.path].extracted[r.offset].files.append(file_path)
 
                     # If recursion was specified, and the file is not the same

src/binwalk/modules/general.py

@@ -219,4 +219,4 @@ class General(Module):
                 except KeyboardInterrupt as e:
                     raise e
                 except Exception as e:
-                    self.error(description="Cannot open file : %s" % str(e))
+                    self.error(description="Cannot open file %s (CWD: %s) : %s" % (tfile, os.getcwd(), str(e)))

src/binwalk/plugins/cpio.py

@@ -116,10 +116,10 @@ class CPIOPlugin(binwalk.core.plugin.Plugin):
                 result.jump = self.CPIO_HEADER_SIZE + file_size + file_name_length
                 self.consecutive_hits += 1
 
-                if not self.found_archive or self.found_archive_in_file != result.file.name:
+                if not self.found_archive or self.found_archive_in_file != result.file.path:
                     # This is the first entry. Set found_archive and allow the
                     # scan to continue normally.
-                    self.found_archive_in_file = result.file.name
+                    self.found_archive_in_file = result.file.path
                     self.found_archive = True
                     result.extract = True
                 elif 'TRAILER!!!' in result.description:

src/binwalk/plugins/dlromfsextract.py

 import os
+import zlib
 import struct
 import binwalk.core.plugin
 import binwalk.core.common
@@ -132,7 +133,12 @@ class RomFS(object):
         except KeyboardInterrupt as e:
             raise e
         except Exception as e:
-            pass
+            try:
+                data = zlib.decompress(data)
+            except KeyboardInterrupt as e:
+                raise e
+            except Exception as e:
+                pass
 
         return data
 

src/binwalk/plugins/gzipvalid.py

@@ -17,7 +17,7 @@ class GzipValidPlugin(binwalk.core.plugin.Plugin):
         # If this result is a gzip signature match, try to decompress the data
         if result.file and result.description.lower().startswith('gzip'):
             # Seek to and read the suspected gzip data
-            fd = self.module.config.open_file(result.file.name, offset=result.offset, length=self.MAX_DATA_SIZE)
+            fd = self.module.config.open_file(result.file.path, offset=result.offset, length=self.MAX_DATA_SIZE)
             data = fd.read(self.MAX_DATA_SIZE)
             fd.close()
 

src/binwalk/plugins/hilink.py

@@ -71,7 +71,7 @@ class HilinkDecryptor(binwalk.core.plugin.Plugin):
                 if result.description.lower().startswith(self.SIGNATURE_DESCRIPTION) is True:
                     # Read in the first 64 bytes of the suspected encrypted
                     # uImage header
-                    fd = self.module.config.open_file(result.file.name, offset=result.offset)
+                    fd = self.module.config.open_file(result.file.path, offset=result.offset)
                     encrypted_header_data = binwalk.core.compat.str2bytes(fd.read(64))
                     fd.close()
 

src/binwalk/plugins/jffs2valid.py

@@ -34,7 +34,7 @@ class JFFS2ValidPlugin(binwalk.core.plugin.Plugin):
         if result.file and result.description.lower().startswith('jffs2 filesystem'):
 
             # Seek to and read the suspected JFFS2 node header
-            fd = self.module.config.open_file(result.file.name, offset=result.offset)
+            fd = self.module.config.open_file(result.file.path, offset=result.offset)
             # JFFS2 headers are only 12 bytes in size, but reading larger amounts of
             # data from disk speeds up repeated disk access and decreases performance
             # hits (disk caching?).

src/binwalk/plugins/lzmavalid.py

@@ -52,7 +52,7 @@ class LZMAPlugin(binwalk.core.plugin.Plugin):
         if result.valid and result.file and result.description.lower().startswith('lzma compressed data'):
 
             # Seek to and read the suspected lzma data
-            fd = self.module.config.open_file(result.file.name, offset=result.offset, length=self.MAX_DATA_SIZE)
+            fd = self.module.config.open_file(result.file.path, offset=result.offset, length=self.MAX_DATA_SIZE)
             data = fd.read(self.MAX_DATA_SIZE)
             fd.close()
 

src/binwalk/plugins/tar.py

@@ -42,7 +42,7 @@ class TarPlugin(binwalk.core.plugin.Plugin):
         if result.description.lower().startswith('posix tar archive'):
             is_tar = True
             file_offset = result.offset
-            fd = self.module.config.open_file(result.file.name, offset=result.offset)
+            fd = self.module.config.open_file(result.file.path, offset=result.offset)
 
             while is_tar:
                 # read in the tar header struct

src/binwalk/plugins/ubivalid.py

@@ -27,7 +27,7 @@ class UBIValidPlugin(binwalk.core.plugin.Plugin):
         return header_crc == calculated_header_crc
 
     def _process_result(self, result):
-        if self.current_file == result.file.name:
+        if self.current_file == result.file.path:
             result.display = False
         else:
             # Reset everything in case new file is encountered
@@ -38,7 +38,7 @@ class UBIValidPlugin(binwalk.core.plugin.Plugin):
             # Display result and trigger extraction
             result.display = True
 
-        self.current_file = result.file.name
+        self.current_file = result.file.path
 
         if not self.peb_size and self.last_ec_hdr_offset:
             # Calculate PEB size by subtracting last EC block offset
@@ -56,7 +56,7 @@ class UBIValidPlugin(binwalk.core.plugin.Plugin):
     def scan(self, result):
         if result.file and result.description.lower().startswith('ubi erase count header'):
             # Seek to and read the suspected UBI erase count header
-            fd = self.module.config.open_file(result.file.name, offset=result.offset)
+            fd = self.module.config.open_file(result.file.path, offset=result.offset)
 
             ec_header = binwalk.core.compat.str2bytes(fd.read(1024))
             fd.close()

src/binwalk/plugins/zlibvalid.py

@@ -27,7 +27,7 @@ class ZlibValidPlugin(binwalk.core.plugin.Plugin):
             offset = result.offset - adjust
 
             # Seek to and read the suspected zlib data
-            fd = self.module.config.open_file(result.file.name)
+            fd = self.module.config.open_file(result.file.path)
             fd.seek(offset)
             data = fd.read(self.MAX_DATA_SIZE)[adjust:]
             fd.close()