[Libreoffice-commits] .: src/docrecord.py src/docstream.py test/doc
src/docrecord.py | 27 +--
src/docstream.py | 23 +++
test/doc/bookmark.doc |binary
test/doc/bookmark.rtf |7 +++
test/doc/test.py | 11 +++
5 files changed, 62 insertions(+), 6 deletions(-)
New commits:
commit 8f7af80bf491794f9b1781157cceb25783227741
Author: Miklos Vajna
Date: Sat Jan 19 14:25:33 2013 +0100
doc: dump bookmarks
diff --git a/src/docrecord.py b/src/docrecord.py
index f277196..36b29c3 100644
--- a/src/docrecord.py
+++ b/src/docrecord.py
@@ -202,11 +202,12 @@ class PlcFld(DOCDirStream, PLC):
class PlcfBkl(DOCDirStream, PLC):
"""The Plcfbkl structure is a PLC that contains only CPs and no additional
data."""
-def __init__(self, mainStream, offset, size):
+def __init__(self, mainStream, offset, size, start):
DOCDirStream.__init__(self,
mainStream.doc.getDirectoryStreamByName("1Table").bytes, mainStream =
mainStream)
PLC.__init__(self, size, 0) # 0 is defined by 2.8.12
self.pos = offset
self.size = size
+self.start = start
def dump(self):
print '' %
(self.pos, self.size)
@@ -216,7 +217,7 @@ class PlcfBkl(DOCDirStream, PLC):
# aCp
end = offset + self.getuInt32(pos = pos)
print '' % (i, end)
-start = self.mainStream.plcfAtnBkf.aCP[i]
+start = self.start.aCP[i]
print '' %
self.quoteAttr(self.mainStream.retrieveText(start, end))
pos += 4
print ''
@@ -2609,4 +2610,26 @@ class SttbSavedBy(DOCDirStream):
assert self.pos == self.mainStream.fcSttbSavedBy + self.size
print ''
+class SttbfBkmk(DOCDirStream):
+"""The SttbfBkmk structure is an STTB structure whose strings specify the
names of bookmarks."""
+def __init__(self, mainStream):
+DOCDirStream.__init__(self,
mainStream.doc.getDirectoryStreamByName("1Table").bytes)
+self.pos = mainStream.fcSttbfBkmk
+self.size = mainStream.lcbSttbfBkmk
+self.mainStream = mainStream
+
+def dump(self):
+print '' %
(self.pos, self.size)
+self.printAndSet("fExtended", self.readuInt16())
+self.printAndSet("cData", self.readuInt16())
+self.printAndSet("cbExtra", self.readuInt16())
+for i in range(self.cData):
+cchData = self.readuInt16()
+print '' % (i,
self.pos, cchData)
+print '' %
globals.encodeName(self.bytes[self.pos:self.pos+2*cchData].decode('utf-16'),
lowOnly = True)
+self.pos += 2*cchData
+print ''
+assert self.pos == self.mainStream.fcSttbfBkmk + self.size
+print ''
+
# vim:set filetype=python shiftwidth=4 softtabstop=4 expandtab:
diff --git a/src/docstream.py b/src/docstream.py
index 7633ccc..d9003aa 100644
--- a/src/docstream.py
+++ b/src/docstream.py
@@ -253,11 +253,11 @@ class WordDocumentStream(DOCDirStream):
["fcPlcfFldMcr"],
["lcbPlcfFldMcr"],
["fcSttbfBkmk"],
-["lcbSttbfBkmk"],
+["lcbSttbfBkmk", self.handleLcbSttbfBkmk],
["fcPlcfBkf"],
-["lcbPlcfBkf"],
+["lcbPlcfBkf", self.handleLcbPlcfBkf],
["fcPlcfBkl"],
-["lcbPlcfBkl"],
+["lcbPlcfBkl", self.handleLcbPlcfBkl],
["fcCmds"],
["lcbCmds", self.handleLcbCmds],
["fcUnused1"],
@@ -489,7 +489,19 @@ class WordDocumentStream(DOCDirStream):
def handleLcbPlcfAtnBkl(self):
offset = self.fcPlcfAtnBkl
size = self.lcbPlcfAtnBkl
-plcfBkl = docrecord.PlcfBkl(self, offset, size)
+plcfBkl = docrecord.PlcfBkl(self, offset, size, start =
self.plcfAtnBkf)
+plcfBkl.dump()
+
+def handleLcbPlcfBkf(self):
+offset = self.fcPlcfBkf
+size = self.lcbPlcfBkf
+self.plcfBkf = docrecord.PlcfBkf(self, offset, size)
+self.plcfBkf.dump()
+
+def handleLcbPlcfBkl(self):
+offset = self.fcPlcfBkl
+size = self.lcbPlcfBkl
+plcfBkl = docrecord.PlcfBkl(self, offset, size, start = self.plcfBkf)
plcfBkl.dump()
def handleLcbPlcfSed(self):
@@ -537,6 +549,9 @@ class WordDocumentStream(DOCDirStream):
def handleLcbSttbListNames(self):
docrecord.SttbListNames(self).dump()
+def handleLcbSttbfBkmk(self):
+docrecord.SttbfBkmk(self).dump()
+
def dumpFibRgFcLcb97(self, name):
print '<%s type="FibRgFcLcb97" size="744 bytes">' % name
self.__dumpFibRgFcLcb97()
diff --git a/test/doc/bookmark.doc b/test/doc/bookmark.doc
new file mode 100755
index 000..6d32ff6
Binary files /dev/null and b/test/doc/bookmark.doc differ
diff --git a/test/doc/bookmark.rtf b/test/doc/bookmark.rtf
new file mode 100644
index 000..05b3d42
--- /dev/null
+++ b/test/doc/bookmark.rtf
@@ -0,0 +1,7 @@
+{\rtf1
+{\*\bkmkstart firstword}
+Hello
+{\*\bkmkend firstword}
+ world!
+\par
+}
diff -
[Libreoffice-commits] .: src/docrecord.py src/docstream.py test/doc
src/docrecord.py | 67 +-
src/docstream.py |5 +++-
test/doc/list.doc |binary
test/doc/list.rtf | 49 +++
test/doc/test.py |6
5 files changed, 120 insertions(+), 7 deletions(-)
New commits:
commit abd802bff3247df6fb1c87ed41fce45ba01a9a95
Author: Miklos Vajna
Date: Fri Jan 11 12:19:28 2013 +0100
dump PlfLfo
diff --git a/src/docrecord.py b/src/docrecord.py
index 6e69156..ef87891 100644
--- a/src/docrecord.py
+++ b/src/docrecord.py
@@ -2393,13 +2393,14 @@ class PlcfGram(DOCDirStream, PLC):
class LSTF(DOCDirStream):
"""The LSTF structure contains formatting properties that apply to an
entire list."""
-def __init__(self, plfLst):
+def __init__(self, plfLst, index):
DOCDirStream.__init__(self, plfLst.bytes)
self.pos = plfLst.pos
self.size = 28
+self.index = index
def dump(self):
-print '' % (self.pos,
self.size)
+print '' %
(self.index, self.pos, self.size)
self.printAndSet("lsid", self.readInt32())
self.printAndSet("tplc", self.readInt32())
for i in range(9):
@@ -2445,12 +2446,13 @@ class LVLF(DOCDirStream):
class LVL(DOCDirStream):
"""The LVL structure contains formatting information about a specific
level in a list."""
-def __init__(self, plfLst):
+def __init__(self, plfLst, index):
DOCDirStream.__init__(self, plfLst.bytes)
self.pos = plfLst.pos
+self.index = index
def dump(self):
-print '' % self.pos
+print '' % (self.index,
self.pos)
lvlf = LVLF(self)
lvlf.dump()
self.pos = lvlf.pos
@@ -2489,7 +2491,7 @@ class PlfLst(DOCDirStream):
self.printAndSet("cLst", self.readInt16())
cLvl = 0
for i in range(self.cLst):
-rgLstf = LSTF(self)
+rgLstf = LSTF(self, i)
rgLstf.dump()
if rgLstf.fSimpleList:
cLvl += 1
@@ -2497,9 +2499,62 @@ class PlfLst(DOCDirStream):
cLvl += 9
self.pos = rgLstf.pos
for i in range(cLvl):
-lvl = LVL(self)
+lvl = LVL(self, i)
lvl.dump()
self.pos = lvl.pos
print ''
+class LFO(DOCDirStream):
+"""The LFO structure specifies the LSTF element that corresponds to a list
that contains a paragraph."""
+def __init__(self, plfLfo):
+DOCDirStream.__init__(self, plfLfo.bytes)
+self.pos = plfLfo.pos
+
+def dump(self):
+print '' % self.pos
+self.printAndSet("lsid", self.readInt32())
+self.printAndSet("unused1", self.readuInt32())
+self.printAndSet("unused2", self.readuInt32())
+self.printAndSet("clfolvl", self.readuInt8())
+self.printAndSet("ibstFltAutoNum", self.readuInt8())
+self.printAndSet("grfhic", self.readuInt8()) # TODO dump grfhic
+self.printAndSet("unused3", self.readuInt8())
+print ''
+
+class LFOData(DOCDirStream):
+"""The LFOData structure contains the Main Document CP of the
corresponding LFO."""
+def __init__(self, plfLfo, lfo):
+DOCDirStream.__init__(self, plfLfo.bytes)
+self.pos = plfLfo.pos
+self.lfo = lfo
+
+def dump(self):
+print '' % self.pos
+self.printAndSet("cp", self.readuInt32())
+if self.lfo.clfolvl > 0:
+print ''
+print ''
+
+class PlfLfo(DOCDirStream):
+"""The PlfLfo structure contains the list format override data for the
document."""
+def __init__(self, mainStream):
+DOCDirStream.__init__(self,
mainStream.doc.getDirectoryStreamByName("1Table").bytes, mainStream =
mainStream)
+self.pos = mainStream.fcPlfLfo
+self.size = mainStream.lcbPlfLfo
+
+def dump(self):
+print '' %
(self.pos, self.size)
+self.printAndSet("lfoMac", self.readInt32())
+lfos = []
+for i in range(self.lfoMac):
+lfo = LFO(self)
+lfos.append(lfo)
+lfo.dump()
+self.pos = lfo.pos
+for i in range(self.lfoMac):
+lfoData = LFOData(self, lfos[i])
+lfoData.dump()
+self.pos = lfoData.pos
+print ''
+
# vim:set filetype=python shiftwidth=4 softtabstop=4 expandtab:
diff --git a/src/docstream.py b/src/docstream.py
index ad46e1a..648fe81 100644
--- a/src/docstream.py
+++ b/src/docstream.py
@@ -352,7 +352,7 @@ class WordDocumentStream(DOCDirStream):
["fcPlfLst"],
["lcbPlfLst", self.handleLcbPlfLst],
["fcPlfLfo"],
-["lcbPlfLfo"],
+["lcbPlfLfo", self.handleLcbPlfLfo],
["fcPlcfTxbxBkd"],
["lcbPlcfTxbxBkd"],
["fcPlcfTxbxHdrBkd"],
@@ -521,6 +521,9 @@ class WordDocumentStream(DOCDirStream):
def handleLcbPlfLst(self):
docrecord.PlfLst(self).dump()
+def handleLcbP
[Libreoffice-commits] .: src/docrecord.py src/docstream.py test/doc
src/docrecord.py | 31 ++-
src/docstream.py |4 ++--
test/doc/sections.doc |binary
test/doc/test.py |7 +++
4 files changed, 23 insertions(+), 19 deletions(-)
New commits:
commit f922c24a1c0e7bf2f7e330503eb37f2d99f39b75
Author: Miklos Vajna
Date: Wed Jan 9 17:54:07 2013 +0100
PlcfSed: fix dumping section text
diff --git a/src/docrecord.py b/src/docrecord.py
index 9e30066..cae0153 100644
--- a/src/docrecord.py
+++ b/src/docrecord.py
@@ -30,24 +30,21 @@ class FcCompressed(DOCDirStream):
self.printAndSet("r1", self.r1)
print ''
-def getTransformedValue(self, start, end, logical = True):
+def getTransformedValue(self, start, end, logicalPositions = True,
logicalLength = True):
+offset = self.fc
if self.fCompressed:
offset = self.fc/2
-if logical:
-fro = offset
-to = offset+end-start
-else:
-fro = start
-to = end
+if logicalPositions:
+fro = offset + start
+to = offset + end
+else:
+fro = start
+to = end
+if self.fCompressed:
return globals.encodeName(self.mainStream.bytes[fro:to])
else:
-if logical:
-offset = self.fc
-fro = offset
-to = offset + (end - start) * 2
-else:
-fro = start
-to = end
+if logicalLength:
+to += (to - fro)
return
globals.encodeName(self.mainStream.bytes[fro:to].decode('utf-16'), lowOnly =
True)
class Pcd(DOCDirStream):
@@ -301,7 +298,7 @@ class PlcfSed(DOCDirStream, PLC):
self.size = size
def dump(self):
-print '' %
(self.pos, self.size)
+print '' %
(self.pos, self.size)
offset = self.mainStream.fcMin
pos = self.pos
for i in range(self.getElements()):
@@ -315,9 +312,9 @@ class PlcfSed(DOCDirStream, PLC):
aSed = Sed(self, self.getOffset(self.pos, i))
aSed.dump()
-print '' %
self.quoteAttr(self.mainStream.retrieveText(start, end, logical = True))
+print '' %
self.quoteAttr(self.mainStream.retrieveText(offset + start, offset + end,
logicalLength = True))
print ''
-print ''
+print ''
class Tcg(DOCDirStream):
"""The Tcg structure specifies command-related customizations."""
diff --git a/src/docstream.py b/src/docstream.py
index a0aba5e..6ec39f5 100644
--- a/src/docstream.py
+++ b/src/docstream.py
@@ -629,9 +629,9 @@ class WordDocumentStream(DOCDirStream):
index = i
return index
-def retrieveText(self, start, end, logical = False):
+def retrieveText(self, start, end, logicalLength = False):
plcPcd = self.clx.pcdt.plcPcd
idx = self.__findText(plcPcd, start)
-return plcPcd.aPcd[idx].fc.getTransformedValue(start, end, logical =
logical)
+return plcPcd.aPcd[idx].fc.getTransformedValue(start, end,
logicalPositions = False, logicalLength = logicalLength)
# vim:set filetype=python shiftwidth=4 softtabstop=4 expandtab:
diff --git a/test/doc/sections.doc b/test/doc/sections.doc
new file mode 100644
index 000..9e26fb4
Binary files /dev/null and b/test/doc/sections.doc differ
diff --git a/test/doc/test.py b/test/doc/test.py
index c2b955c..0088e41 100755
--- a/test/doc/test.py
+++ b/test/doc/test.py
@@ -146,6 +146,13 @@ class Test(unittest.TestCase):
result =
self.root.findall('stream[@name="WordDocument"]/fib/fibRgFcLcbBlob/lcbPlcfFldMom/plcFld/aCP[@index="2"]/transformed')
self.assertEqual('1', result[0].attrib['value'])
+def test_sections(self):
+self.dump('sections')
+
+sections =
self.root.findall('stream[@name="WordDocument"]/fib/fibRgFcLcbBlob/lcbPlcfSed/plcfSed/')
+self.assertEqual('Before section 1.\\x0D\\x0D\\x0C',
sections[0].findall('transformed')[0].attrib['value'])
+self.assertEqual("\\x0DThe next one isn't a balanced
one:\\x0D\\x0D\\x0C", sections[2].findall('transformed')[0].attrib['value'])
+
if __name__ == '__main__':
unittest.main()
___
Libreoffice-commits mailing list
libreoffice-comm...@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/libreoffice-commits
[Libreoffice-commits] .: src/docrecord.py src/docstream.py test/doc
src/docrecord.py | 61 +
src/docstream.py |5 +++-
test/doc/field.doc |binary
test/doc/field.rtf |8 ++
test/doc/test.py |9 +++
5 files changed, 82 insertions(+), 1 deletion(-)
New commits:
commit 134ed95ebe314473ad094f0ee0cf1dbad49e
Author: Miklos Vajna
Date: Wed Jan 9 11:38:36 2013 +0100
dump PlcFld
diff --git a/src/docrecord.py b/src/docrecord.py
index 0aa271d..9e30066 100644
--- a/src/docrecord.py
+++ b/src/docrecord.py
@@ -142,6 +142,67 @@ class PlcfBkf(DOCDirStream, PLC):
print ''
print ''
+class Fldch(DOCDirStream):
+"""The fldch structure determines the type of the field character."""
+def __init__(self, parent):
+DOCDirStream.__init__(self, parent.bytes)
+self.pos = parent.pos
+self.parent = parent
+
+def dump(self):
+print '' % self.pos
+buf = self.readuInt8()
+self.printAndSet("ch", buf & 0x1f) # 1..5th bits
+self.printAndSet("reserved", (buf & 0xe0) >> 5) # 6..8th bits
+print ''
+self.parent.pos = self.pos
+
+class Fld(DOCDirStream):
+"""The Fld structure specifies a field character."""
+def __init__(self, parent, offset):
+DOCDirStream.__init__(self, parent.bytes)
+self.pos = offset
+
+def dump(self):
+print '' % self.pos
+self.fldch = Fldch(self)
+self.fldch.dump()
+self.printAndSet("grffld", self.readuInt8()) # TODO parse flt and
grffldEnd
+print ''
+
+class PlcFld(DOCDirStream, PLC):
+"""The Plcfld structure specifies the location of fields in the
document."""
+def __init__(self, mainStream):
+DOCDirStream.__init__(self,
mainStream.doc.getDirectoryStreamByName("1Table").bytes, mainStream =
mainStream)
+PLC.__init__(self, mainStream.lcbPlcfFldMom, 2) # 2 is defined by
2.8.25
+self.pos = mainStream.fcPlcfFldMom
+self.size = mainStream.lcbPlcfFldMom
+
+def dump(self):
+print '' %
(self.pos, self.size)
+offset = self.mainStream.fcMin # 2.8.25: CPs relative to the start of
that document part.
+pos = self.pos
+aFlds = []
+for i in range(self.getElements()):
+# aCp
+value = self.getuInt32(pos = pos)
+print '' % (i, value)
+pos += 4
+
+# aFld
+aFld = Fld(self, self.getOffset(self.pos, i))
+aFld.dump()
+
+# This is a separator and the previous was a start: display the
field instructions.
+if aFld.fldch.ch == 0x14 and aFlds[-1][1].fldch.ch == 0x13:
+print '' %
self.quoteAttr(self.mainStream.retrieveText(offset + aFlds[-1][0] + 1, offset +
value))
+# This is an end and the previous was a separator: display the
field result.
+elif aFld.fldch.ch == 0x15 and aFlds[-1][1].fldch.ch == 0x14:
+print '' %
self.quoteAttr(self.mainStream.retrieveText(offset + aFlds[-1][0] + 1, offset +
value))
+aFlds.append((value, aFld))
+print ''
+print ''
+
class PlcfBkl(DOCDirStream, PLC):
"""The Plcfbkl structure is a PLC that contains only CPs and no additional
data."""
def __init__(self, mainStream, offset, size):
diff --git a/src/docstream.py b/src/docstream.py
index 167fb9c..a0aba5e 100644
--- a/src/docstream.py
+++ b/src/docstream.py
@@ -236,7 +236,7 @@ class WordDocumentStream(DOCDirStream):
["fcSttbfFfn"],
["lcbSttbfFfn", self.handleLcbSttbfFfn],
["fcPlcfFldMom"],
-["lcbPlcfFldMom"],
+["lcbPlcfFldMom", self.handleLcbPlcfFldMom],
["fcPlcfFldHdr"],
["lcbPlcfFldHdr"],
["fcPlcfFldFtn"],
@@ -509,6 +509,9 @@ class WordDocumentStream(DOCDirStream):
def handleLcbDggInfo(self):
docrecord.OfficeArtContent(self).dump()
+def handleLcbPlcfFldMom(self):
+docrecord.PlcFld(self).dump()
+
def dumpFibRgFcLcb97(self, name):
print '<%s type="FibRgFcLcb97" size="744 bytes">' % name
self.__dumpFibRgFcLcb97()
diff --git a/test/doc/field.doc b/test/doc/field.doc
new file mode 100644
index 000..247f024
Binary files /dev/null and b/test/doc/field.doc differ
diff --git a/test/doc/field.rtf b/test/doc/field.rtf
new file mode 100644
index 000..48e39d1
--- /dev/null
+++ b/test/doc/field.rtf
@@ -0,0 +1,8 @@
+{\rtf1
+Page number:
+{\field
+{\*\fldinst PAGE }
+{\fldrslt 1}
+}
+\par
+}
diff --git a/test/doc/test.py b/test/doc/test.py
index a97d0f5..c2b955c 100755
--- a/test/doc/test.py
+++ b/test/doc/test.py
@@ -137,6 +137,15 @@ class Test(unittest.TestCase):
# This first caused unhandled exceptions, then later invalid XML
output.
self.dump('escape')
+def test_field(self):
+self.dump('field')
+
+instruction =
self.root.findall('stream[@name="WordDocument"]/fib/fibRgFcLcbBlob/lcbPlcf
[Libreoffice-commits] .: src/docrecord.py src/docstream.py test/doc
src/docrecord.py |6 --
src/docstream.py |4 ++--
test/doc/test.py |6 ++
3 files changed, 8 insertions(+), 8 deletions(-)
New commits:
commit e2b8fcc9380b83e36742d66093f0aa9c888e012b
Author: Miklos Vajna
Date: Wed Nov 28 22:24:40 2012 +0100
PlcfBkl: dump the text of the commented text range, not just the start/end
positions
diff --git a/src/docrecord.py b/src/docrecord.py
index adf0de5..30e169f 100644
--- a/src/docrecord.py
+++ b/src/docrecord.py
@@ -130,6 +130,7 @@ class PlcfBkf(DOCDirStream, PLC):
PLC.__init__(self, size, 4) # 4 is defined by 2.8.10
self.pos = offset
self.size = size
+self.aCP = []
def dump(self):
print '' %
(self.pos, self.size)
@@ -138,8 +139,8 @@ class PlcfBkf(DOCDirStream, PLC):
for i in range(self.getElements()):
# aCp
start = offset + self.getuInt32(pos = pos)
+self.aCP.append(start)
print '' % (i, start)
-print '' %
FcCompressed.getFCTransformedValue(self.mainStream.bytes, start, start + 1)
pos += 4
# aFBKF
@@ -164,7 +165,8 @@ class PlcfBkl(DOCDirStream, PLC):
# aCp
end = offset + self.getuInt32(pos = pos)
print '' % (i, end)
-print '' %
FcCompressed.getFCTransformedValue(self.mainStream.bytes, end, end + 1)
+start = self.mainStream.plcfAtnBkf.aCP[i]
+print '' %
FcCompressed.getFCTransformedValue(self.mainStream.bytes, start, end)
pos += 4
print ''
print ''
diff --git a/src/docstream.py b/src/docstream.py
index dfc2d28..93b2a2a 100644
--- a/src/docstream.py
+++ b/src/docstream.py
@@ -457,8 +457,8 @@ class WordDocumentStream(DOCDirStream):
def handleLcbPlcfAtnBkf(self):
offset = self.fcPlcfAtnBkf
size = self.lcbPlcfAtnBkf
-plcfBkf = docrecord.PlcfBkf(self, offset, size)
-plcfBkf.dump()
+self.plcfAtnBkf = docrecord.PlcfBkf(self, offset, size)
+self.plcfAtnBkf.dump()
def handleLcbPlcfAtnBkl(self):
offset = self.fcPlcfAtnBkl
diff --git a/test/doc/test.py b/test/doc/test.py
index a0356d0..546c141 100755
--- a/test/doc/test.py
+++ b/test/doc/test.py
@@ -109,10 +109,8 @@ class Test(unittest.TestCase):
commentEnds =
self.root.findall('stream[@name="WordDocument"]/fib/fibRgFcLcbBlob/lcbPlcfAtnBkl/plcfBkl/aCP')
# The first comment covers Hello\x05, the second covers This\x05.
-self.assertEqual('H',
commentStarts[0].findall('transformed')[0].attrib['value'])
-self.assertEqual('\\x05',
commentEnds[0].findall('transformed')[0].attrib['value'])
-self.assertEqual('T',
commentStarts[1].findall('transformed')[0].attrib['value'])
-self.assertEqual('\\x05',
commentEnds[1].findall('transformed')[0].attrib['value'])
+self.assertEqual('Hello',
commentEnds[0].findall('transformed')[0].attrib['value'])
+self.assertEqual('This',
commentEnds[1].findall('transformed')[0].attrib['value'])
if __name__ == '__main__':
unittest.main()
___
Libreoffice-commits mailing list
libreoffice-comm...@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/libreoffice-commits
