[Libreoffice-commits] .: src/ole.py src/xlsstream.py xls-dump.py

[Kohei Yoshida]

 src/ole.py       |    9 ++++++++-
 src/xlsstream.py |   10 ++++------
 xls-dump.py      |   18 ++++++++++--------
 3 files changed, 22 insertions(+), 15 deletions(-)

New commits:
commit 84c6b072d3107e4e418449e153bc223d6d55b773
Author: Kohei Yoshida <kyoshida at novell.com>
Date:   Thu Apr 7 23:43:56 2011 -0400

    Skip reading directories that are storages.
    
    Storages are equivalent of directories in a normal file system, so
    they only have header infos but no data streams (except for the
    root entry).  Don't treat them like streams.

diff --git a/src/ole.py b/src/ole.py
index 9b01928..744cda7 100644
--- a/src/ole.py
+++ b/src/ole.py
@@ -499,6 +499,9 @@ entire file stream.
             self.StreamSize = 0
             self.bytes = []
 
+        def isStorage (self):
+            return self.Type == Directory.Type.RootStorage or \
+                self.Type == Directory.Type.UserStorage
 
     def __init__ (self, header, params):
         self.sectorSize = header.getSectorSize()
@@ -533,7 +536,6 @@ entire file stream.
         elif entry.StreamLocation == StreamLocation.SSAT:
             chain = self.header.getSSAT().getSectorIDChain(entry.StreamSectorID)
 
-
         if entry.StreamLocation == StreamLocation.SSAT:
             # Get the root storage stream.
             if self.RootStorage == None:
@@ -556,6 +558,9 @@ entire file stream.
 
         return bytes
 
+    def getRawStream (self, entry):
+        bytes = self.__getRawStream(entry)
+        return bytes
 
     def getRawStreamByName (self, name):
         bytes = []
@@ -694,6 +699,8 @@ entire file stream.
             output("%2.2X "%ord(byte))
         print("")
 
+    def getDirectoryEntries (self):
+        return self.entries
 
     def getDirectoryNames (self):
         names = []
diff --git a/src/xlsstream.py b/src/xlsstream.py
index 0595d1f..6ab4195 100644
--- a/src/xlsstream.py
+++ b/src/xlsstream.py
@@ -367,19 +367,17 @@ class XLStream(object):
             return
         obj.output()
 
-
-    def getDirectoryNames (self):
+    def getDirectoryEntries (self):
         obj = self.__getDirectoryObj()
         if obj == None:
             return
-        return obj.getDirectoryNames()
-
+        return obj.getDirectoryEntries()
 
-    def getDirectoryStreamByName (self, name):
+    def getDirectoryStream (self, entry):
         obj = self.__getDirectoryObj()
         bytes = []
         if obj != None:
-            bytes = obj.getRawStreamByName(name)
+            bytes = obj.getRawStream(entry)
         strm = XLDirStream(bytes, self.params, self.strmData)
         return strm
 
diff --git a/xls-dump.py b/xls-dump.py
index 52ec00e..f47f260 100755
--- a/xls-dump.py
+++ b/xls-dump.py
@@ -90,14 +90,18 @@ class XLDumper(object):
         self.strm.printSAT()
         self.strm.printSSAT()
         self.strm.printDirectory()
-        dirnames = self.strm.getDirectoryNames()
-        for dirname in dirnames:
-            if len(dirname) == 0 or dirname == 'Root Entry':
+        dirEntries = self.strm.getDirectoryEntries()
+        for entry in dirEntries:
+            dirname = entry.Name
+            if len(dirname) == 0:
                 continue
 
-            dirstrm = self.strm.getDirectoryStreamByName(dirname)
+            dirstrm = self.strm.getDirectoryStream(entry)
             self.__printDirHeader(dirname, len(dirstrm.bytes))
-            if dirname == "Workbook":
+            if entry.isStorage():
+                continue
+
+            elif dirname == "Workbook":
                 success = True
                 while success: 
                     success = self.__readSubStream(dirstrm)
@@ -105,9 +109,7 @@ class XLDumper(object):
             elif dirname == "Revision Log":
                 dirstrm.type = xlsstream.DirType.RevisionLog
                 self.__readSubStream(dirstrm)
-            elif dirname == '_SX_DB_CUR':
-                dirstrm.type = xlsstream.DirType.PivotTableCache
-                self.__readSubStream(dirstrm)
+
             elif self.strmData.isPivotCacheStream(dirname):
                 dirstrm.type = xlsstream.DirType.PivotTableCache
                 self.__readSubStream(dirstrm)