ooo-build r14417 - in trunk: . scratch/sc-xlsutil scratch/sc-xlsutil/src
- From: kyoshida svn gnome org
- To: svn-commits-list gnome org
- Subject: ooo-build r14417 - in trunk: . scratch/sc-xlsutil scratch/sc-xlsutil/src
- Date: Tue, 28 Oct 2008 15:48:04 +0000 (UTC)
Author: kyoshida
Date: Tue Oct 28 15:48:04 2008
New Revision: 14417
URL: http://svn.gnome.org/viewvc/ooo-build?rev=14417&view=rev
Log:
2008-10-28 Kohei Yoshida <kyoshida novell com>
* scratch/sc-xlsutil/src/globals.py:
* scratch/sc-xlsutil/src/record.py:
* scratch/sc-xlsutil/src/stream.py:
* scratch/sc-xlsutil/xls_dump.py: parse PivotTable Cache substreams
and handle more PivotTable related records.
Modified:
trunk/ChangeLog
trunk/scratch/sc-xlsutil/src/globals.py
trunk/scratch/sc-xlsutil/src/record.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 Tue Oct 28 15:48:04 2008
@@ -5,11 +5,27 @@
class Params(object):
+ """command-line parameters."""
def __init__ (self):
self.debug = False
self.showSectorChain = False
+class StreamData(object):
+ """run-time stream data."""
+ def __init__ (self):
+ self.encrypted = False
+ self.pivotCacheIDs = {}
+
+ def appendPivotCacheId (self, newId):
+ # must be 4-digit with leading '0's.
+ strId = "%.4d"%newId
+ self.pivotCacheIDs[strId] = True
+
+ def isPivotCacheStream (self, name):
+ return self.pivotCacheIDs.has_key(name)
+
+
def output (msg):
sys.stdout.write(msg)
Modified: trunk/scratch/sc-xlsutil/src/record.py
==============================================================================
--- trunk/scratch/sc-xlsutil/src/record.py (original)
+++ trunk/scratch/sc-xlsutil/src/record.py Tue Oct 28 15:48:04 2008
@@ -7,13 +7,15 @@
class BaseRecordHandler(object):
- def __init__ (self, header, size, bytes):
+ def __init__ (self, header, size, bytes, strmData):
self.header = header
self.size = size
self.bytes = bytes
self.lines = []
self.pos = 0 # current byte position
+ self.strmData = strmData
+
def parseBytes (self):
"""Parse the original bytes and generate human readable output.
@@ -37,6 +39,11 @@
self.pos += length
return r
+ def readRemainingBytes (self):
+ r = self.bytes[self.pos:]
+ self.pos = self.size
+ return r
+
def getCurrentPos (self):
return self.pos
@@ -49,6 +56,19 @@
else:
return 'no'
+ def readUnsignedInt (self, length):
+ bytes = self.readBytes(length)
+ return globals.getUnsignedInt(bytes)
+
+ def readSignedInt (self, length):
+ bytes = self.readBytes(length)
+ return globals.getSignedInt(bytes)
+
+ def readDouble (self):
+ # double is always 8 bytes.
+ bytes = self.readBytes(8)
+ return globals.getDouble(bytes)
+
# --------------------------------------------------------------------
class BOF(BaseRecordHandler):
@@ -593,6 +613,91 @@
return verName
+class SXDb(BaseRecordHandler):
+
+ def parseBytes (self):
+ recCount = self.readUnsignedInt(4)
+ strmId = self.readUnsignedInt(2)
+ flags = self.readUnsignedInt(2)
+ self.appendLine("number of records: %d"%recCount)
+ self.appendLine("stream ID: 0x%4.4X"%strmId)
+ self.appendLine("flags: 0x%4.4X"%flags)
+
+ dbBlockRecs = self.readUnsignedInt(2)
+ baseFields = self.readUnsignedInt(2)
+ allFields = self.readUnsignedInt(2)
+ self.appendLine("DB block records: %d"%dbBlockRecs)
+ self.appendLine("base fields: %d"%baseFields)
+ self.appendLine("all fields: %d"%allFields)
+
+ dummy = self.readBytes(2)
+ type = self.readUnsignedInt(2)
+ self.appendLine("type: 0x%4.4X"%type)
+ textLen = self.readUnsignedInt(2)
+ changedBy, textLen = globals.getRichText(self.readRemainingBytes(), textLen)
+ self.appendLine("changed by: %s"%changedBy)
+
+
+class SXDbEx(BaseRecordHandler):
+
+ def parseBytes (self):
+ lastChanged = self.readDouble()
+ sxFmlaRecs = self.readUnsignedInt(4)
+ self.appendLine("last changed: %g"%lastChanged)
+ self.appendLine("SXFORMULA records: %d"%sxFmlaRecs)
+
+
+class SXField(BaseRecordHandler):
+
+ dataTypeNames = {
+ 0x0000: 'spc',
+ 0x0480: 'str',
+ 0x0520: 'int[+dbl]',
+ 0x0560: 'dbl',
+ 0x05A0: 'str+int[+dbl]',
+ 0x05E0: 'str+dbl',
+ 0x0900: 'dat',
+ 0x0D00: 'dat+int/dbl',
+ 0x0D80: 'dat+str[+int/dbl]'
+ }
+
+ def parseBytes (self):
+ flags = self.readUnsignedInt(2)
+ origItems = (flags & 0x0001)
+ postponed = (flags & 0x0002)
+ calculated = (flags & 0x0004)
+ groupChild = (flags & 0x0008)
+ numGroup = (flags & 0x0010)
+ longIndex = (flags & 0x0200)
+ self.appendLine("original items: %s"%self.getYesNo(origItems))
+ self.appendLine("postponed: %s"%self.getYesNo(postponed))
+ self.appendLine("calculated: %s"%self.getYesNo(calculated))
+ self.appendLine("group child: %s"%self.getYesNo(groupChild))
+ self.appendLine("num group: %s"%self.getYesNo(numGroup))
+ self.appendLine("long index: %s"%self.getYesNo(longIndex))
+ dataType = (flags & 0x0DE0)
+ if SXField.dataTypeNames.has_key(dataType):
+ self.appendLine("data type: %s (0x%4.4X)"%(SXField.dataTypeNames[dataType], dataType))
+ else:
+ self.appendLine("data type: unknown (0x%4.4X)"%dataType)
+
+ grpSubField = self.readUnsignedInt(2)
+ grpBaseField = self.readUnsignedInt(2)
+ itemCount = self.readUnsignedInt(2)
+ grpItemCount = self.readUnsignedInt(2)
+ baseItemCount = self.readUnsignedInt(2)
+ srcItemCount = self.readUnsignedInt(2)
+ self.appendLine("group sub-field: %d"%grpSubField)
+ self.appendLine("group base-field: %d"%grpBaseField)
+ self.appendLine("item count: %d"%itemCount)
+ self.appendLine("group item count: %d"%grpItemCount)
+ self.appendLine("base item count: %d"%baseItemCount)
+ self.appendLine("source item count: %d"%srcItemCount)
+
+ # field name
+ textLen = self.readUnsignedInt(2)
+ name, textLen = globals.getRichText(self.readRemainingBytes(), textLen)
+ self.appendLine("field name: %s"%name)
class SXStreamID(BaseRecordHandler):
@@ -602,6 +707,7 @@
return
strmId = globals.getSignedInt(self.bytes)
+ self.strmData.appendPivotCacheId(strmId)
self.appendLine("pivot cache stream ID in SX DB storage: %d"%strmId)
class SXViewSource(BaseRecordHandler):
@@ -745,6 +851,32 @@
pass
+class SXDouble(BaseRecordHandler):
+ def parseBytes (self):
+ val = self.readDouble()
+ self.appendLine("value: %g"%val)
+
+
+class SXBoolean(BaseRecordHandler):
+ def parseBytes (self):
+ pass
+
+class SXError(BaseRecordHandler):
+ def parseBytes (self):
+ pass
+
+
+class SXInteger(BaseRecordHandler):
+ def parseBytes (self):
+ pass
+
+
+class SXString(BaseRecordHandler):
+ def parseBytes (self):
+ textLen = self.readUnsignedInt(2)
+ text, textLen = globals.getRichText(self.readRemainingBytes(), textLen)
+ self.appendLine("value: %s"%text)
+
# -------------------------------------------------------------------
# CT - Change Tracking
Modified: trunk/scratch/sc-xlsutil/src/stream.py
==============================================================================
--- trunk/scratch/sc-xlsutil/src/stream.py (original)
+++ trunk/scratch/sc-xlsutil/src/stream.py Tue Oct 28 15:48:04 2008
@@ -105,8 +105,16 @@
0x00C2: ["ADDMENU", "Menu Addition"],
0x00C3: ["DELMENU", "Menu Deletion"],
0x00C5: ["SXDI", "Data Item"],
- 0x00C6: ["SXDB", "PivotTable Cache Data"],
- 0x00CD: ["SXSTRING", "String"],
+ 0x00C6: ["SXDB", "PivotTable Cache Data", record.SXDb],
+ 0x00C7: ["SXFIELD", "Pivot Field", record.SXField],
+ 0x00C8: ["SXINDEXLIST", "Indices to Source Data"],
+ 0x00C9: ["SXDOUBLE", "Double Value", record.SXDouble],
+ 0x00CA: ["SXBOOLEAN", "Boolean Value", record.SXBoolean],
+ 0x00CB: ["SXERROR", "Error Code", record.SXError],
+ 0x00CC: ["SXINTEGER", "Integer Value", record.SXInteger],
+ 0x00CD: ["SXSTRING", "String", record.SXString],
+ 0x00CE: ["SXDATETIME", "Date & Time Special Format"],
+ 0x00CF: ["SXEMPTY", "Empty Value"],
0x00D0: ["SXTBL", "Multiple Consolidation Source Info"],
0x00D1: ["SXTBRGIITM", "Page Item Name Count"],
0x00D2: ["SXTBPG", "Page Item Indexes"],
@@ -142,7 +150,7 @@
0x00FF: ["EXTSST", "Extended Shared String Table"],
0x0100: ["SXVDEX", "Extended PivotTable View Fields"],
0x0103: ["SXFORMULA", "PivotTable Formula Record"],
- 0x0122: ["SXDBEX", "PivotTable Cache Data"],
+ 0x0122: ["SXDBEX", "PivotTable Cache Data", record.SXDbEx],
0x013D: ["TABID", "Sheet Tab Index Array"],
0x0160: ["USESELFS", "Natural Language Formulas Flag"],
0x0161: ["DSF", "Double Stream File"],
@@ -261,7 +269,7 @@
class XLStream(object):
- def __init__ (self, chars, params):
+ def __init__ (self, chars, params, strmData):
self.chars = chars
self.size = len(self.chars)
self.pos = 0
@@ -272,6 +280,7 @@
self.SAT = None
self.params = params
+ self.strmData = strmData
def __printSep (self, c='-', w=68, prefix=''):
print(prefix + c*w)
@@ -329,22 +338,24 @@
bytes = []
if obj != None:
bytes = obj.getRawStreamByName(name)
- strm = XLDirStream(bytes, self.params)
+ strm = XLDirStream(bytes, self.params, self.strmData)
return strm
class DirType:
Workbook = 0
RevisionLog = 1
+ PivotTableCache = 2
class XLDirStream(object):
- def __init__ (self, bytes, params):
+ def __init__ (self, bytes, params, strmData):
self.bytes = bytes
self.size = len(self.bytes)
self.pos = 0
self.type = DirType.Workbook
self.params = params
+ self.strmData = strmData
def readRaw (self, size=1):
@@ -393,12 +404,12 @@
print("%4.4Xh: %s - %s (%4.4Xh)"%
(header, recData[header][0], recData[header][1], header))
if len(recData[header]) >= 3:
- handler = recData[header][2](header, size, bytes)
+ handler = recData[header][2](header, size, bytes, self.strmData)
elif self.type == DirType.RevisionLog and recDataRev.has_key(header):
print("%4.4Xh: %s - %s (%4.4Xh)"%
(header, recDataRev[header][0], recDataRev[header][1], header))
if len(recDataRev[header]) >= 3:
- handler = recDataRev[header][2](header, size, bytes)
+ handler = recDataRev[header][2](header, size, bytes, self.strmData)
else:
print("%4.4Xh: [unknown record name] (%4.4Xh)"%(header, header))
print("%4.4Xh: size = %d; pos = %d"%(header, size, pos))
Modified: trunk/scratch/sc-xlsutil/xls_dump.py
==============================================================================
--- trunk/scratch/sc-xlsutil/xls_dump.py (original)
+++ trunk/scratch/sc-xlsutil/xls_dump.py Tue Oct 28 15:48:04 2008
@@ -31,7 +31,8 @@
def dump (self):
file = open(self.filepath, 'rb')
- strm = stream.XLStream(file.read(), self.params)
+ strmData = globals.StreamData()
+ strm = stream.XLStream(file.read(), self.params, strmData)
file.close()
strm.printStreamInfo()
strm.printHeader()
@@ -59,6 +60,22 @@
header = dirstrm.readRecord()
except stream.EndOfStream:
continue
+ elif dirname == '_SX_DB_CUR':
+ dirstrm.type = stream.DirType.PivotTableCache
+ try:
+ header = 0x0000
+ while header != 0x000A:
+ header = dirstrm.readRecord()
+ except stream.EndOfStream:
+ continue
+ elif strmData.isPivotCacheStream(dirname):
+ dirstrm.type = stream.DirType.PivotTableCache
+ try:
+ header = 0x0000
+ while header != 0x000A:
+ header = dirstrm.readRecord()
+ except stream.EndOfStream:
+ continue
else:
globals.dumpBytes(dirstrm.bytes, 512)
[
Date Prev][
Date Next] [
Thread Prev][
Thread Next]
[
Thread Index]
[
Date Index]
[
Author Index]
