[Libreoffice-commits] mso-dumper.git: src/docrecord.py src/docstream.py
src/docrecord.py |1 -
src/docstream.py |3 +++
2 files changed, 3 insertions(+), 1 deletion(-)
New commits:
commit c8a02ce6baad0b4e99c1eeb451ca1246eec9ae2c
Author: Miklos Vajna vmik...@suse.cz
Date: Tue Jun 25 18:03:46 2013 +0200
Don't crash on abi13064-1.doc
http://bugzilla.abisource.com/show_bug.cgi?id=13064 says it's corrupted
anyway, so just make the code not crash on it.
diff --git a/src/docrecord.py b/src/docrecord.py
index c747d91..87ece9d 100644
--- a/src/docrecord.py
+++ b/src/docrecord.py
@@ -3194,7 +3194,6 @@ class SttbListNames(DOCDirStream):
print 'string value=%s/' %
globals.encodeName(self.bytes[self.pos:self.pos+2*cchData].decode('utf-16'),
lowOnly = True)
self.pos += 2*cchData
print '/cchData'
-assert self.pos == self.mainStream.fcSttbListNames + self.size
print '/sttbListNames'
class SttbSavedBy(DOCDirStream):
diff --git a/src/docstream.py b/src/docstream.py
index cc0766b..398207c 100644
--- a/src/docstream.py
+++ b/src/docstream.py
@@ -952,6 +952,9 @@ class WordDocumentStream(DOCDirStream):
def retrieveCPs(self, start, end):
Retrieves a range of characters.
+if not len(self.clx.pcdt.plcPcd.aPcd):
+print 'info what=clx.pcdt.plcPcd.aPcd is empty, probably
corrupted document/'
+return
ret = []
i = start
while i end:
___
Libreoffice-commits mailing list
libreoffice-comm...@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/libreoffice-commits
[Libreoffice-commits] mso-dumper.git: src/docrecord.py src/docstream.py
src/docrecord.py | 47 +++ src/docstream.py |5 - 2 files changed, 51 insertions(+), 1 deletion(-) New commits: commit 353f15fa0823ae02b8f0d47333a1e1f734322d82 Author: Miklos Vajna vmik...@suse.cz Date: Thu May 16 19:09:18 2013 +0200 dump PlcftxbxBkd diff --git a/src/docrecord.py b/src/docrecord.py index 04bf1d0..fec80fe 100644 --- a/src/docrecord.py +++ b/src/docrecord.py @@ -2735,6 +2735,53 @@ class PlcftxbxTxt(DOCDirStream, PLC): print '/aCP' print '/plcftxbxTxt' +class Tbkd(DOCDirStream): +The Tbkd structure is used by the PlcftxbxBkd and PlcfTxbxHdrBkd structures to associate ranges of +text from the Textboxes Document and the Header Textboxes Document with FTXBXS objects. +size = 6 # 2.9.309 +def __init__(self, parent, offset): +DOCDirStream.__init__(self, parent.bytes) +self.parent = parent +self.pos = self.posOrig = offset + +def dump(self): +print 'aTbkd type=Tbkd offset=%d size=%d bytes' % (self.pos, Tbkd.size) +self.printAndSet(itxbxs, self.readuInt16()) +self.printAndSet(dcpDepend, self.readuInt16()) +buf = self.readuInt16() +self.printAndSet(reserved1, buf 0x03ff) # 1..10th bits +self.printAndSet(fMarkDelete, self.getBit(buf, 10)) +self.printAndSet(fUnk, self.getBit(buf, 11)) +self.printAndSet(fTextOverflow, self.getBit(buf, 12)) +self.printAndSet(reserved2, (buf 0xe000) 13) # 14..16th bits +print '/aTbkd' +assert self.posOrig + Tbkd.size == self.pos + +class PlcftxbxBkd(DOCDirStream, PLC): +Specifies which ranges of text go inside which textboxes. +def __init__(self, mainStream): +DOCDirStream.__init__(self, mainStream.doc.getDirectoryStreamByName(1Table).bytes, mainStream = mainStream) +PLC.__init__(self, mainStream.lcbPlcfTxbxBkd, 6) +self.pos = mainStream.fcPlcfTxbxBkd +self.size = mainStream.lcbPlcfTxbxBkd + +def dump(self): +print 'plcftxbxBkd type=PlcftxbxBkd offset=%d size=%d bytes' % (self.pos, self.size) +offset = self.mainStream.ccpText + self.mainStream.ccpFtn +pos = self.pos +for i in range(self.getElements()): +# aCp +start = self.getuInt32(pos = pos) +end = self.getuInt32(pos = pos + 4) +print 'aCP index=%d start=%d end=%d' % (i, start, end) +pos += 4 + +# aTbkd +Tbkd(self, self.getOffset(self.pos, i)).dump() +print 'transformed value=%s/' % self.quoteAttr(self.mainStream.retrieveCPs(offset + start, offset + end)) +print '/aCP' +print '/plcftxbxBkd' + class PlcfSpa(DOCDirStream, PLC): The PlcfSpa structure is a PLC structure in which the data elements are SPA structures. diff --git a/src/docstream.py b/src/docstream.py index 158748e..849dc19 100644 --- a/src/docstream.py +++ b/src/docstream.py @@ -399,7 +399,7 @@ class WordDocumentStream(DOCDirStream): [fcPlfLfo], [lcbPlfLfo, self.handleLcbPlfLfo], [fcPlcfTxbxBkd], -[lcbPlcfTxbxBkd], +[lcbPlcfTxbxBkd, self.handleLcbPlcfTxbxBkd], [fcPlcfTxbxHdrBkd], [lcbPlcfTxbxHdrBkd], [fcDocUndoWord9], @@ -601,6 +601,9 @@ class WordDocumentStream(DOCDirStream): def handleLcbSttbfBkmk(self): docrecord.SttbfBkmk(self).dump() +def handleLcbPlcfTxbxBkd(self): +docrecord.PlcftxbxBkd(self).dump() + def dumpFibRgFcLcb97(self, name): print '%s type=FibRgFcLcb97 size=744 bytes' % name self.__dumpFibRgFcLcb97() ___ Libreoffice-commits mailing list libreoffice-comm...@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/libreoffice-commits
[Libreoffice-commits] mso-dumper.git: src/docrecord.py src/docstream.py
src/docrecord.py | 11 ++- src/docstream.py |6 ++ 2 files changed, 12 insertions(+), 5 deletions(-) New commits: commit ddc6ca725bc05bdc82a00a30fe52bfea81dd97ad Author: Miklos Vajna vmik...@suse.cz Date: Thu May 16 19:17:36 2013 +0200 factor out duplicated code diff --git a/src/docrecord.py b/src/docrecord.py index fec80fe..dac6d83 100644 --- a/src/docrecord.py +++ b/src/docrecord.py @@ -1067,7 +1067,7 @@ class PlcfHdd(DOCDirStream, PLC): def dump(self): print 'plcfHdd type=PlcfHdd offset=%d size=%d bytes' % (self.pos, self.size) -offset = self.mainStream.ccpText + self.mainStream.ccpFtn +offset = self.mainStream.getHeaderOffset() pos = self.pos for i in range(self.getElements() - 1): start = self.getuInt32(pos = pos) @@ -1088,7 +1088,7 @@ class PlcfandTxt(DOCDirStream, PLC): def dump(self): print 'plcfandTxt type=PlcfandTxt offset=%d size=%d bytes' % (self.pos, self.size) -offset = self.mainStream.ccpText + self.mainStream.ccpFtn + self.mainStream.ccpHdd +offset = self.mainStream.getCommentOffset() pos = self.pos for i in range(self.getElements() - 1): start = self.getuInt32(pos = pos) @@ -2706,7 +2706,8 @@ class FTXBXS(DOCDirStream): self.printAndSet(lid, self.readuInt32()) self.printAndSet(txidUndo, self.readuInt32()) print '/aFTXBXS' -assert self.posOrig + FTXBXS.size == self.pos +if not self.fReusable: +assert self.posOrig + FTXBXS.size == self.pos class PlcftxbxTxt(DOCDirStream, PLC): Specifies which ranges of text are contained in which textboxes. @@ -2718,7 +2719,7 @@ class PlcftxbxTxt(DOCDirStream, PLC): def dump(self): print 'plcftxbxTxt type=PlcftxbxTxt offset=%d size=%d bytes' % (self.pos, self.size) -offset = self.mainStream.ccpText + self.mainStream.ccpFtn +offset = self.mainStream.getHeaderOffset() pos = self.pos for i in range(self.getElements() - 1): # aCp @@ -2767,7 +2768,7 @@ class PlcftxbxBkd(DOCDirStream, PLC): def dump(self): print 'plcftxbxBkd type=PlcftxbxBkd offset=%d size=%d bytes' % (self.pos, self.size) -offset = self.mainStream.ccpText + self.mainStream.ccpFtn +offset = self.mainStream.getHeaderOffset() pos = self.pos for i in range(self.getElements()): # aCp diff --git a/src/docstream.py b/src/docstream.py index 849dc19..e888299 100644 --- a/src/docstream.py +++ b/src/docstream.py @@ -893,4 +893,10 @@ class WordDocumentStream(DOCDirStream): i += 1 return .join(ret) +def getHeaderOffset(self): +return self.ccpText + self.ccpFtn + +def getCommentOffset(self): +return self.getHeaderOffset() + self.ccpHdd + # vim:set filetype=python shiftwidth=4 softtabstop=4 expandtab: ___ Libreoffice-commits mailing list libreoffice-comm...@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/libreoffice-commits
