ooo-build r14995 - in trunk: . scratch/sd-pptutil scratch/sd-pptutil/src
- From: thorstenb svn gnome org
- To: svn-commits-list gnome org
- Subject: ooo-build r14995 - in trunk: . scratch/sd-pptutil scratch/sd-pptutil/src
- Date: Sun, 4 Jan 2009 21:38:58 +0000 (UTC)
Author: thorstenb
Date: Sun Jan 4 21:38:58 2009
New Revision: 14995
URL: http://svn.gnome.org/viewvc/ooo-build?rev=14995&view=rev
Log:
* scratch/sd-pptutil/*: added license headers, gentle changes to
make stuff more py3-conformant; keeping input bytes as real
strings now throughout the code (more performant and also much
less error prone); added unpacking and pretty-printing of embedded
OOXML payload
Added:
trunk/scratch/sd-pptutil/src/xmlpp.py
Modified:
trunk/ChangeLog
trunk/scratch/sd-pptutil/ppt-dump.py
trunk/scratch/sd-pptutil/src/globals.py
trunk/scratch/sd-pptutil/src/ole.py
trunk/scratch/sd-pptutil/src/record.py
trunk/scratch/sd-pptutil/src/stream.py
Modified: trunk/scratch/sd-pptutil/ppt-dump.py
==============================================================================
--- trunk/scratch/sd-pptutil/ppt-dump.py (original)
+++ trunk/scratch/sd-pptutil/ppt-dump.py Sun Jan 4 21:38:58 2009
@@ -1,5 +1,18 @@
#!/usr/bin/env python
+########################################################################
+#
+# OpenOffice.org - a multi-platform office productivity suite
+#
+# Author:
+# Kohei Yoshida <kyoshida novell com>
+# Thorsten Behrens <tbehrens novell com>
+#
+# The Contents of this file are made available subject to
+# the terms of GNU Lesser General Public License Version 2.1.
+#
+########################################################################
+
import sys, os.path, getopt
sys.path.append(sys.path[0]+"/src")
import ole, stream, globals
Modified: trunk/scratch/sd-pptutil/src/globals.py
==============================================================================
--- trunk/scratch/sd-pptutil/src/globals.py (original)
+++ trunk/scratch/sd-pptutil/src/globals.py Sun Jan 4 21:38:58 2009
@@ -1,3 +1,14 @@
+########################################################################
+#
+# OpenOffice.org - a multi-platform office productivity suite
+#
+# Author:
+# Kohei Yoshida <kyoshida novell com>
+#
+# The Contents of this file are made available subject to
+# the terms of GNU Lesser General Public License Version 2.1.
+#
+########################################################################
import sys, struct, math
Modified: trunk/scratch/sd-pptutil/src/ole.py
==============================================================================
--- trunk/scratch/sd-pptutil/src/ole.py (original)
+++ trunk/scratch/sd-pptutil/src/ole.py Sun Jan 4 21:38:58 2009
@@ -1,3 +1,14 @@
+########################################################################
+#
+# OpenOffice.org - a multi-platform office productivity suite
+#
+# Author:
+# Kohei Yoshida <kyoshida novell com>
+#
+# The Contents of this file are made available subject to
+# the terms of GNU Lesser General Public License Version 2.1.
+#
+########################################################################
import sys
import stream, globals
@@ -314,7 +325,6 @@
self.sectorIDs = []
self.bytes = bytes
self.array = []
-
self.params = params
@@ -342,10 +352,10 @@
def outputRawBytes (self):
- bytes = []
+ bytes = ""
for secID in self.sectorIDs:
pos = 512 + secID*self.sectorSize
- bytes.extend(self.bytes[pos:pos+self.sectorSize])
+ bytes += self.bytes[pos:pos+self.sectorSize]
globals.dumpBytes(bytes, 512)
@@ -485,7 +495,7 @@
self.SSAT = header.getSSAT()
self.header = header
self.RootStorage = None
- self.RootStorageBytes = []
+ self.RootStorageBytes = ""
self.params = params
@@ -498,7 +508,7 @@
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])
+ self.RootStorageBytes += self.header.bytes[pos:pos+self.sectorSize]
def __getRawStream (self, entry):
@@ -514,20 +524,20 @@
if self.RootStorage == None:
raise NoRootStorage
- bytes = []
+ bytes = ""
self.__buildRootStorageBytes()
size = self.header.getShortSectorSize()
for id in chain:
pos = id*size
- bytes.extend(self.RootStorageBytes[pos:pos+size])
+ bytes += self.RootStorageBytes[pos:pos+size]
return bytes
offset = 512
size = self.header.getSectorSize()
- bytes = []
+ bytes = ""
for id in chain:
pos = offset + id*size
- bytes.extend(self.header.bytes[pos:pos+size])
+ bytes += self.header.bytes[pos:pos+size]
return bytes
@@ -683,10 +693,10 @@
return
# combine all sectors first.
- bytes = []
+ bytes = ""
for secID in self.sectorIDs:
pos = globals.getSectorPos(secID, self.sectorSize)
- bytes.extend(self.bytes[pos:pos+self.sectorSize])
+ bytes += self.bytes[pos:pos+self.sectorSize]
self.entries = []
Modified: trunk/scratch/sd-pptutil/src/record.py
==============================================================================
--- trunk/scratch/sd-pptutil/src/record.py (original)
+++ trunk/scratch/sd-pptutil/src/record.py Sun Jan 4 21:38:58 2009
@@ -1,6 +1,20 @@
+########################################################################
+#
+# OpenOffice.org - a multi-platform office productivity suite
+#
+# Author:
+# Kohei Yoshida <kyoshida novell com>
+# Thorsten Behrens <tbehrens novell com>
+#
+# The Contents of this file are made available subject to
+# the terms of GNU Lesser General Public License Version 2.1.
+#
+########################################################################
-import struct
+import StringIO
import globals
+import zipfile
+import xmlpp
# -------------------------------------------------------------------
# record handler classes
@@ -142,7 +156,7 @@
complexBytes = allComplexBytes[:propValue]
allComplexBytes = allComplexBytes[propValue:]
- if propData.has_key(propType):
+ if propType in propData:
handler = propData[propType][1](propType, propValue, isComplex, isBlip, complexBytes, self.appendLine)
handler.output()
else:
@@ -189,7 +203,7 @@
def parseBytes (self):
# any shape text set? if not, no chance to calc run lengths
- if not self.streamProperties.has_key("ShapeText"):
+ if not "ShapeText" in self.streamProperties:
self.appendLine("no shape text given, skipping props")
return
@@ -296,7 +310,7 @@
if styleMask & 0xE0000:
paraAsianLinebreaking = self.readUnsignedInt(2)
# filter bits not in flag field
- paraAsianLinebreaking = paraAsianLinebreaking & ((styleMask & 0xE0000) / 0x20000)
+ paraAsianLinebreaking = paraAsianLinebreaking & ((styleMask & 0xE0000) // 0x20000)
self.appendParaProp("para asian line breaking flags %4.4Xh"%paraAsianLinebreaking)
if styleMask & 0x200000:
@@ -356,11 +370,11 @@
self.bytes = complexBytes
self.pos = 0
self.printer = printer
- if propData.has_key(self.propType):
+ if self.propType in propData:
self.propEntry = propData[self.propType]
def output (self):
- if propData.has_key(self.propType):
+ if self.propType in propData:
self.printer("%4.4Xh: %s = %8.8Xh [\"%s\" - default handler]"%(self.propType, self.propEntry[0],
self.propValue, self.propEntry[2]))
@@ -370,7 +384,7 @@
def output (self):
bitMask = 1
for i in xrange(self.propType, self.propType-32):
- if propData.has_key(i):
+ if i in propData:
propEntry = propData[i]
if type(propEntry[1]) == type(BoolPropertyHandler):
flagValue = self.getTrueFalse(self.propValue & bitMask)
@@ -422,11 +436,11 @@
"""Color property."""
def split (self, packedColor):
- return (packedColor & 0xFF0000) / 0x10000, (packedColor & 0xFF00) / 0x100, (packedColor & 0xFF)
+ return (packedColor & 0xFF0000) // 0x10000, (packedColor & 0xFF00) / 0x100, (packedColor & 0xFF)
def output (self):
propEntry = ["<color atom>", None, "undocumented color property"]
- if propData.has_key(self.propType):
+ if self.propType in propData:
propEntry = propData[self.propType]
colorValue = self.propValue & 0xFFFFFF
if self.propValue & 0xFE000000 == 0xFE000000:
@@ -454,7 +468,43 @@
"""zip storage."""
def output (self):
- self.printer("zipped stuff")
+ class StreamWrap(object):
+ def __init__ (self,printer):
+ self.printer = printer
+ self.buffer = ""
+ def write (self,string):
+ self.buffer += string
+ def flush (self):
+ for line in self.buffer.splitlines():
+ self.printer(line)
+
+ self.printer("Zipped content:")
+ self.printer('='*61)
+ rawFile = StringIO.StringIO(self.bytes)
+ zipFile = zipfile.ZipFile(rawFile)
+ i = 0
+ # TODO: when 2.6/3.0 is in widespread use, change to infolist here
+ for filename in zipFile.namelist():
+ if i > 0:
+ self.printer('-'*61)
+ i += 1
+ self.printer(filename + ":")
+ self.printer('-'*61)
+
+ contents = zipFile.read(filename)
+ if filename.endswith(".xml") or contents.startswith("<?xml"):
+ wrapper = StreamWrap(self.printer)
+ xmlpp.pprint(contents,wrapper,1,80)
+ wrapper.flush()
+ else:
+ while len(contents):
+ self.printer(contents[:60].replace('\n','').replace('\r',''))
+ contents = contents[60:]
+# content = zipFile.open(zipInfo)
+# for line in content.readlines():
+# self.printer(line)
+ zipFile.close()
+
# -------------------------------------------------------------------
# special record handler: properties
Modified: trunk/scratch/sd-pptutil/src/stream.py
==============================================================================
--- trunk/scratch/sd-pptutil/src/stream.py (original)
+++ trunk/scratch/sd-pptutil/src/stream.py Sun Jan 4 21:38:58 2009
@@ -1,3 +1,15 @@
+########################################################################
+#
+# OpenOffice.org - a multi-platform office productivity suite
+#
+# Author:
+# Kohei Yoshida <kyoshida novell com>
+# Thorsten Behrens <tbehrens novell com>
+#
+# The Contents of this file are made available subject to
+# the terms of GNU Lesser General Public License Version 2.1.
+#
+########################################################################
import sys
import ole, globals, record
@@ -317,7 +329,7 @@
def printRecordHeader (self, startPos, recordInstance, recordVersion, recordType, size):
self.__printSep('=')
- if recData.has_key(recordType):
+ if recordType in recData:
self.__print("[%s]"%recData[recordType][0])
else:
self.__print("[anon record]")
@@ -344,7 +356,7 @@
startPos = self.pos
recordInstance = self.readUnsignedInt(2)
recordVersion = (recordInstance & 0x000F)
- recordInstance = recordInstance / 16
+ recordInstance = recordInstance // 16
recordType = self.readUnsignedInt(2)
size = self.readUnsignedInt(4)
@@ -352,7 +364,7 @@
bytes = self.readBytes(size)
recordInfo = None
- if recData.has_key(recordType) and len(recData[recordType]) >= 2:
+ if recordType in recData and len(recData[recordType]) >= 2:
recordInfo = recData[recordType]
if recordVersion == 0x0F:
Added: trunk/scratch/sd-pptutil/src/xmlpp.py
==============================================================================
--- (empty file)
+++ trunk/scratch/sd-pptutil/src/xmlpp.py Sun Jan 4 21:38:58 2009
@@ -0,0 +1,148 @@
+"""Pretty print an XML document.
+
+LICENCE:
+Copyright (c) 2008, Fredrik Ekholdt
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice,
+this list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+this list of conditions and the following disclaimer in the documentation
+and/or other materials provided with the distribution.
+
+* Neither the name of None nor the names of its contributors may be used to
+endorse or promote products derived from this software without specific prior
+written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE."""
+
+import sys as _sys
+import re as _re
+
+def _usage(this_file):
+ return """SYNOPSIS: pretty print an XML document
+USAGE: python %s <filename> \n""" % this_file
+
+def _pprint_line(indent_level, line, width=100, output=_sys.stdout):
+ if line.strip():
+ start = ""
+ number_chars = 0
+ for l in range(indent_level):
+ start = start + " "
+ number_chars = number_chars + 1
+ try:
+ elem_start = _re.findall("(\<\W{0,1}\w+) ?", line)[0]
+ elem_finished = _re.findall("([?|\]\]]*\>)", line)[0]
+ #should not have *
+ attrs = _re.findall("(\S*?\=\".*?\")", line)
+ output.write(start + elem_start)
+ number_chars = len(start + elem_start)
+ for attr in attrs:
+ if (attrs.index(attr) + 1) == len(attrs):
+ number_chars = number_chars + len(elem_finished)
+ if (number_chars + len(attr) + 1) > width:
+ output.write("\n")
+ for i in range(len(start + elem_start) + 1):
+ output.write(" ")
+ number_chars = len(start + elem_start) + 1
+ else:
+ output.write(" ")
+ number_chars = number_chars + 1
+ output.write(attr)
+ number_chars = number_chars + len(attr)
+ output.write(elem_finished + "\n")
+ except IndexError:
+ #give up pretty print this line
+ output.write(start + line + "\n")
+
+
+def _pprint_elem_content(indent_level, line, output=_sys.stdout):
+ if line.strip():
+ for l in range(indent_level):
+ output.write(" ")
+ output.write(line + "\n")
+
+def _get_next_elem(data):
+ start_pos = data.find("<")
+ end_pos = data.find(">") + 1
+ retval = data[start_pos:end_pos]
+ stopper = retval.rfind("/")
+ if stopper < retval.rfind("\""):
+ stopper = -1
+ single = (stopper > -1 and ((retval.find(">") - stopper) < (stopper - retval.find("<"))))
+
+ ignore_excl = retval.find("<!") > -1
+ ignore_question = retval.find("<?") > -1
+
+ if ignore_excl:
+ cdata = retval.find("<![CDATA[") > -1
+ if cdata:
+ end_pos = data.find("]]>")
+ if end_pos > -1:
+ end_pos = end_pos + len("]]>")
+
+ elif ignore_question:
+ end_pos = data.find("?>") + len("?>")
+ ignore = ignore_excl or ignore_question
+
+ no_indent = ignore or single
+
+ #print retval, end_pos, start_pos, stopper > -1, no_indent
+ return start_pos, \
+ end_pos, \
+ stopper > -1, \
+ no_indent
+
+def pprint(xml, output=_sys.stdout, indent=4, width=80):
+ """Pretty print xml.
+ Use output to select output stream. Default is sys.stdout
+ Use indent to select indentation level. Default is 4 """
+ data = xml
+ indent_level = 0
+ start_pos, end_pos, is_stop, no_indent = _get_next_elem(data)
+ while ((start_pos > -1 and end_pos > -1)):
+ _pprint_elem_content(indent_level, data[:start_pos].strip(),
+ output=output)
+ data = data[start_pos:]
+ if is_stop and not no_indent:
+ indent_level = indent_level - indent
+ _pprint_line(indent_level,
+ data[:end_pos - start_pos],
+ width=width,
+ output=output)
+ data = data[end_pos - start_pos:]
+ if not is_stop and not no_indent :
+ indent_level = indent_level + indent
+
+ if not data:
+ break
+ else:
+ start_pos, end_pos, is_stop, no_indent = _get_next_elem(data)
+
+
+if __name__ == "__main__":
+ if "-h" in _sys.argv or "--help" in _sys.argv:
+ _sys.stderr.write(_usage(_sys.argv[0]))
+ _sys.exit(1)
+ if len(_sys.argv) < 2:
+ _sys.stderr.write(_usage(_sys.argv[0]))
+ _sys.exit(1)
+ else:
+ filename = _sys.argv[1]
+ fh = open(filename)
+
+ pprint(fh.read(), output=_sys.stdout, indent=4, width=80)
[
Date Prev][
Date Next] [
Thread Prev][
Thread Next]
[
Thread Index]
[
Date Index]
[
Author Index]
