ooo-build r11474 - in trunk: . scratch/sc-xlsutil scratch/sc-xlsutil/src
- From: kyoshida svn gnome org
- To: svn-commits-list gnome org
- Subject: ooo-build r11474 - in trunk: . scratch/sc-xlsutil scratch/sc-xlsutil/src
- Date: Thu, 31 Jan 2008 00:02:18 +0000 (GMT)
Author: kyoshida
Date: Thu Jan 31 00:02:17 2008
New Revision: 11474
URL: http://svn.gnome.org/viewvc/ooo-build?rev=11474&view=rev
Log:
2008-01-30 Kohei Yoshida <kyoshida novell com>
* scratch/sc-xlsutil/src/globals.py: better raw byte dumping output.
* scratch/sc-xlsutil/src/ole.py:
* scratch/sc-xlsutil/src/stream.py:
* scratch/sc-xlsutil/xls_dump.py: added mechanism to store the command
line options and pass them across the class instances, and fixed the
bug on incorrect stream construction when the stream is a short stream
and is located in the root storage.
Modified:
trunk/ChangeLog
trunk/scratch/sc-xlsutil/src/globals.py
trunk/scratch/sc-xlsutil/src/ole.py
trunk/scratch/sc-xlsutil/src/stream.py
trunk/scratch/sc-xlsutil/xls_dump.py
Modified: trunk/scratch/sc-xlsutil/src/globals.py
==============================================================================
--- trunk/scratch/sc-xlsutil/src/globals.py (original)
+++ trunk/scratch/sc-xlsutil/src/globals.py Thu Jan 31 00:02:17 2008
@@ -1,8 +1,14 @@
-import sys, struct
+import sys, struct, math
class ByteConvertError(Exception): pass
+
+class Params(object):
+ def __init__ (self):
+ self.Debug = False
+
+
def output (msg):
sys.stdout.write(msg)
@@ -61,16 +67,33 @@
subDivideLine = None
if subDivide != None:
subDivideLine = subDivide/16
- for i in xrange(0, len(chars)):
+
+ flushBytes = True
+ charLen = len(chars)
+ labelWidth = int(math.ceil(math.log(charLen, 10)))
+ for i in xrange(0, charLen):
+ if (i+1)%16 == 1:
+ # print line header with seek position
+ fmt = "%%%d.%dd: "%(labelWidth, labelWidth)
+ output(fmt%i)
+
byte = ord(chars[i])
output("%2.2X "%byte)
+ flushBytes = True
+
+ if (i+1)%4 == 0:
+ # put extra space at every 4 bytes.
+ output(" ")
+
if (i+1)%16 == 0:
output("\n")
+ flushBytes = False
if subDivideLine != None and (line+1)%subDivideLine == 0:
output("\n")
line += 1
- output("\n")
+ if flushBytes:
+ output("\n")
def getSectorPos (secID, secSize):
Modified: trunk/scratch/sc-xlsutil/src/ole.py
==============================================================================
--- trunk/scratch/sc-xlsutil/src/ole.py (original)
+++ trunk/scratch/sc-xlsutil/src/ole.py Thu Jan 31 00:02:17 2008
@@ -9,9 +9,8 @@
from globals import output
-def printSep (c='-', w=68, prefix=''):
- print(prefix + c*w)
+class NoRootStorage(Exception): pass
class ByteOrder:
LittleEndian = 0
@@ -41,7 +40,7 @@
return ByteOrder.Unknown
- def __init__ (self, bytes):
+ def __init__ (self, bytes, params):
self.bytes = bytes
self.MSAT = None
@@ -63,6 +62,7 @@
self.secSize = 512
self.secSizeShort = 64
+ self.params = params
def getSectorSize (self):
return 2**self.secSize
@@ -89,10 +89,17 @@
output("%2.2X "%ord(b))
output("\n")
+ def printSep (c='-', w=68, prefix=''):
+ print(prefix + c*w)
+
printSep('=', 68)
print("Compound Document Header")
printSep('-', 68)
+ if self.params.Debug:
+ globals.dumpBytes(self.bytes[0:512])
+ printSep('-', 68)
+
# document ID and unique ID
output("Document ID: ")
printRawBytes(self.docId)
@@ -174,7 +181,7 @@
self.numSecMSAT = getSignedInt(self.bytes[72:76])
# master sector allocation table
- self.MSAT = MSAT(2**self.secSize, self.bytes)
+ self.MSAT = MSAT(2**self.secSize, self.bytes, self.params)
# First part of MSAT consisting of an array of up to 109 sector IDs.
# Each sector ID is 4 bytes in length.
@@ -204,7 +211,7 @@
chain = self.getSAT().getSectorIDChain(ssatID)
if len(chain) == 0:
return None
- obj = SSAT(2**self.secSize, self.bytes)
+ obj = SSAT(2**self.secSize, self.bytes, self.params)
for secID in chain:
obj.addSector(secID)
obj.buildArray()
@@ -218,7 +225,7 @@
chain = self.getSAT().getSectorIDChain(dirID)
if len(chain) == 0:
return None
- obj = Directory(self)
+ obj = Directory(self, self.params)
for secID in chain:
obj.addSector(secID)
return obj
@@ -238,12 +245,14 @@
allocation table (SAT). The actual SAT are to be constructed by combining
all the sectors pointed by the sector IDs in order of occurrence.
"""
- def __init__ (self, sectorSize, bytes):
+ def __init__ (self, sectorSize, bytes, params):
self.sectorSize = sectorSize
self.secIDs = []
self.bytes = bytes
self.__SAT = None
+ self.params = params
+
def appendSectorID (self, id):
self.secIDs.append(id)
@@ -267,7 +276,7 @@
if self.__SAT != None:
return self.__SAT
- obj = SAT(self.sectorSize, self.bytes)
+ obj = SAT(self.sectorSize, self.bytes, self.params)
for id in self.secIDs:
obj.addSector(id)
obj.buildArray()
@@ -278,12 +287,14 @@
class SAT(object):
"""Sector Allocation Table (SAT)
"""
- def __init__ (self, sectorSize, bytes):
+ def __init__ (self, sectorSize, bytes, params):
self.sectorSize = sectorSize
self.sectorIDs = []
self.bytes = bytes
self.array = []
+ self.params = params
+
def getSectorSize (self):
return self.sectorSize
@@ -308,11 +319,15 @@
self.array.append(id)
- def output (self):
- print('')
- print("="*68)
- print("Sector Allocation Table (SAT)")
- print("-"*68)
+ def outputRawBytes (self):
+ bytes = []
+ for secID in self.sectorIDs:
+ pos = 512 + secID*self.sectorSize
+ bytes.extend(self.bytes[pos:pos+self.sectorSize])
+ globals.dumpBytes(bytes, 512)
+
+
+ def outputArrayStats (self):
sectorTotal = len(self.array)
sectorP = 0 # >= 0
sectorM1 = 0 # -1
@@ -347,6 +362,21 @@
print("* other sector count: %4d"%sectorMElse)
+ def output (self):
+ print('')
+ print("="*68)
+ print("Sector Allocation Table (SAT)")
+ print("-"*68)
+ if self.params.Debug:
+ self.outputRawBytes()
+ print("-"*68)
+ for i in xrange(0, len(self.array)):
+ print("%5d: %5d"%(i, self.array[i]))
+ print("-"*68)
+
+ self.outputArrayStats()
+
+
def getSectorIDChain (self, initID):
if initID < 0:
return []
@@ -370,21 +400,27 @@
sectors are contained in the SAT as a sector ID chain.
"""
- def __init__ (self, sectorSize, bytes):
- SAT.__init__(self, sectorSize, bytes)
- return
-
def output (self):
print('')
print("="*68)
print("Short Sector Allocation Table (SSAT)")
print("-"*68)
- for i in xrange(0, len(self.array)):
- item = self.array[i]
- output("%3d : %3d\n"%(i, item))
+ if self.params.Debug:
+ self.outputRawBytes()
+ print("-"*68)
+ for i in xrange(0, len(self.array)):
+ item = self.array[i]
+ output("%3d : %3d\n"%(i, item))
+
+ self.outputArrayStats()
class Directory(object):
+ """Directory Entries
+
+This stream contains a list of directory entries that are stored within the
+entire file stream.
+"""
class Type:
Empty = 0
@@ -414,9 +450,10 @@
self.TimeModified = None
self.StreamSectorID = -2
self.StreamSize = 0
+ self.bytes = []
- def __init__ (self, header):
+ def __init__ (self, header, params):
self.sectorSize = header.getSectorSize()
self.bytes = header.bytes
self.minStreamSize = header.minStreamSize
@@ -425,7 +462,21 @@
self.SAT = header.getSAT()
self.SSAT = header.getSSAT()
self.header = header
- self.posRootStorage = None
+ self.RootStorage = None
+ self.RootStorageBytes = []
+ self.params = params
+
+
+ def __buildRootStorageBytes (self):
+ if self.RootStorage == None:
+ # no root storage exists.
+ return
+
+ firstSecID = self.RootStorage.StreamSectorID
+ chain = self.header.getSAT().getSectorIDChain(firstSecID)
+ for secID in chain:
+ pos = 512 + secID*self.sectorSize
+ self.RootStorageBytes.extend(self.header.bytes[pos:pos+self.sectorSize])
def __getRawStream (self, entry):
@@ -435,14 +486,23 @@
elif entry.StreamLocation == StreamLocation.SSAT:
chain = self.header.getSSAT().getSectorIDChain(entry.StreamSectorID)
- offset = 512
- size = self.header.getSectorSize()
- bytes = []
+
if entry.StreamLocation == StreamLocation.SSAT:
- # get root storage position
- offset = self.posRootStorage
+ # Get the root storage stream.
+ if self.RootStorage == None:
+ raise NoRootStorage
+
+ bytes = []
+ self.__buildRootStorageBytes()
size = self.header.getShortSectorSize()
+ for id in chain:
+ pos = id*size
+ bytes.extend(self.RootStorageBytes[pos:pos+size])
+ return bytes
+ offset = 512
+ size = self.header.getSectorSize()
+ bytes = []
for id in chain:
pos = offset + id*size
bytes.extend(self.header.bytes[pos:pos+size])
@@ -495,6 +555,11 @@
else:
print("name: [empty] (name buffer size: %d bytes)"%entry.CharBufferSize)
+ if self.params.Debug:
+ print("-"*68)
+ globals.dumpBytes(entry.bytes)
+ print("-"*68)
+
output("type: ")
if entry.Type == Directory.Type.Empty:
print("empty")
@@ -614,6 +679,7 @@
def parseDirEntry (self, bytes):
entry = Directory.Entry()
+ entry.bytes = bytes
name = globals.getUTF8FromUTF16(bytes[0:64])
entry.Name = name
entry.CharBufferSize = getSignedInt(bytes[64:66])
@@ -637,7 +703,8 @@
entry.StreamLocation = StreamLocation.SSAT
if entry.Type == Directory.Type.RootStorage and entry.StreamSectorID >= 0:
- self.posRootStorage = 512 + entry.StreamSectorID*self.header.getSectorSize()
+ # This is an existing root storage.
+ self.RootStorage = entry
return entry
Modified: trunk/scratch/sc-xlsutil/src/stream.py
==============================================================================
--- trunk/scratch/sc-xlsutil/src/stream.py (original)
+++ trunk/scratch/sc-xlsutil/src/stream.py Thu Jan 31 00:02:17 2008
@@ -255,7 +255,7 @@
class XLStream(object):
- def __init__ (self, chars):
+ def __init__ (self, chars, params):
self.chars = chars
self.size = len(self.chars)
self.pos = 0
@@ -265,6 +265,8 @@
self.MSAT = None
self.SAT = None
+ self.params = params
+
def __printSep (self, c='-', w=68, prefix=''):
print(prefix + c*w)
@@ -276,7 +278,7 @@
print('')
def printHeader (self):
- self.header = ole.Header(self.chars)
+ self.header = ole.Header(self.chars, self.params)
self.pos = self.header.parse()
self.header.output()
self.MSAT = self.header.getMSAT()
@@ -321,7 +323,7 @@
bytes = []
if obj != None:
bytes = obj.getRawStreamByName(name)
- strm = XLDirStream(bytes)
+ strm = XLDirStream(bytes, self.params)
return strm
class DirType:
@@ -330,12 +332,14 @@
class XLDirStream(object):
- def __init__ (self, bytes):
+ def __init__ (self, bytes, params):
self.bytes = bytes
self.size = len(self.bytes)
self.pos = 0
self.type = DirType.Workbook
+ self.params = params
+
def seekBOF (self):
while self.pos < self.size-1:
b1, b2 = ord(self.bytes[self.pos]), ord(self.bytes[self.pos+1])
Modified: trunk/scratch/sc-xlsutil/xls_dump.py
==============================================================================
--- trunk/scratch/sc-xlsutil/xls_dump.py (original)
+++ trunk/scratch/sc-xlsutil/xls_dump.py Thu Jan 31 00:02:17 2008
@@ -18,8 +18,9 @@
class XLDumper(object):
- def __init__ (self, filepath):
+ def __init__ (self, filepath, params):
self.filepath = filepath
+ self.params = params
def __printDirHeader (self, dirname, byteLen):
dirname = globals.decodeName(dirname)
@@ -30,13 +31,13 @@
def dump (self):
file = open(self.filepath, 'rb')
- strm = stream.XLStream(file.read())
+ strm = stream.XLStream(file.read(), self.params)
file.close()
strm.printStreamInfo()
strm.printHeader()
strm.printMSAT()
strm.printSAT()
-# strm.printSSAT()
+ strm.printSSAT()
strm.printDirectory()
dirnames = strm.getDirectoryNames()
for dirname in dirnames:
@@ -81,12 +82,15 @@
usage(exname)
return
+ params = globals.Params()
try:
- opts, args = getopt.getopt(args, "h", ["help"])
+ opts, args = getopt.getopt(args, "h", ["help", "debug"])
for opt, arg in opts:
if opt in ['-h', '--help']:
usage(exname)
return
+ elif opt in ['--debug']:
+ params.Debug = True
else:
error("unknown option %s\n"%opt)
usage()
@@ -96,7 +100,7 @@
usage(exname)
return
- dumper = XLDumper(args[0])
+ dumper = XLDumper(args[0], params)
dumper.dump()
if __name__ == '__main__':
[
Date Prev][
Date Next] [
Thread Prev][
Thread Next]
[
Thread Index]
[
Date Index]
[
Author Index]
