def GetWindowsInfo(self):
'''Gets information from the #WINDOWS file.
Checks the #WINDOWS file to see if it has any info that was
not found in #SYSTEM (topics, index or default page.
'''
result, ui = chmlib.chm_resolve_object(self.file, '/#WINDOWS')
if (result != chmlib.CHM_RESOLVE_SUCCESS):
return -1
size, text = chmlib.chm_retrieve_object(self.file, ui, 0l, 8)
if (size < 8):
return -2
buff = array.array('B', text)
num_entries = self.GetDWORD(buff, 0)
entry_size = self.GetDWORD(buff, 4)
if num_entries < 1:
return -3
size, text = chmlib.chm_retrieve_object(self.file, ui, 8l, entry_size)
if (size < entry_size):
return -4
buff = array.array('B', text)
toc_index = self.GetDWORD(buff, 0x60)
idx_index = self.GetDWORD(buff, 0x64)
dft_index = self.GetDWORD(buff, 0x68)
result, ui = chmlib.chm_resolve_object(self.file, '/#STRINGS')
if (result != chmlib.CHM_RESOLVE_SUCCESS):
return -5
size, text = chmlib.chm_retrieve_object(self.file, ui, 0l, ui.length)
if (size == 0):
return -6
if (not self.topics):
self.topics = self.GetString(text, toc_index)
if not self.topics.startswith("/"):
self.topics = "/" + self.topics
if (not self.index):
self.index = self.GetString(text, idx_index)
if not self.index.startswith("/"):
self.index = "/" + self.index
if (dft_index != 0):
self.home = self.GetString(text, dft_index)
if not self.home.startswith("/"):
self.home = "/" + self.home
def GetWindowsInfo(self):
'''Gets information from the #WINDOWS file.
Checks the #WINDOWS file to see if it has any info that was
not found in #SYSTEM (topics, index or default page.
'''
result, ui = chmlib.chm_resolve_object(self.file, '/#WINDOWS')
if (result != chmlib.CHM_RESOLVE_SUCCESS):
return -1
size, text = chmlib.chm_retrieve_object(self.file, ui, 0l, 8)
if (size < 8):
return -2
buff = array.array('B', text)
num_entries = self.GetDWORD(buff, 0)
entry_size = self.GetDWORD(buff, 4)
if num_entries < 1:
return -3
size, text = chmlib.chm_retrieve_object(self.file, ui, 8l, entry_size)
if (size < entry_size):
return -4
buff = array.array('B', text)
toc_index = self.GetDWORD(buff, 0x60)
idx_index = self.GetDWORD(buff, 0x64)
dft_index = self.GetDWORD(buff, 0x68)
result, ui = chmlib.chm_resolve_object(self.file, '/#STRINGS')
if (result != chmlib.CHM_RESOLVE_SUCCESS):
return -5
size, text = chmlib.chm_retrieve_object(self.file, ui, 0l, ui.length)
if (size == 0):
return -6
if (not self.topics):
self.topics = self.GetString(text, toc_index)
if not self.topics.startswith("/"):
self.topics = "/" + self.topics
if (not self.index):
self.index = self.GetString(text, idx_index)
if not self.index.startswith("/"):
self.index = "/" + self.index
if (dft_index != 0):
self.home = self.GetString(text, dft_index)
if not self.home.startswith("/"):
self.home = "/" + self.home
def ResolveObject(self, document):
'''Tries to locate a document in the archive.
This function tries to locate the document inside the archive. It
returns a tuple where the first element is zero if the function
was successful, and the second is the UnitInfo for that document.
The UnitInfo is used to retrieve the document contents
'''
if self.file:
path = os.path.abspath(document)
return chmlib.chm_resolve_object(self.file, path)
else:
return (1, None)
def ResolveObject(self, document):
'''Tries to locate a document in the archive.
This function tries to locate the document inside the archive. It
returns a tuple where the first element is zero if the function
was successful, and the second is the UnitInfo for that document.
The UnitInfo is used to retrieve the document contents
'''
if self.file:
path = os.path.abspath(document)
return chmlib.chm_resolve_object(self.file, path)
else:
return (1, None)
def GetIndex(self):
'''Reads and returns the index tree.
This auxiliary function reads and returns the index tree file
contents for the CHM archive.
'''
if self.index is None:
return None
if self.index:
res, ui = chmlib.chm_resolve_object(self.file, self.index)
if (res != chmlib.CHM_RESOLVE_SUCCESS):
return None
size, text = chmlib.chm_retrieve_object(self.file, ui, 0l, ui.length)
if (size == 0):
sys.stderr.write('GetIndex: file size = 0\n')
return None
return text
def GetIndex(self):
'''Reads and returns the index tree.
This auxiliary function reads and returns the index tree file
contents for the CHM archive.
'''
if self.index is None:
return None
if self.index:
res, ui = chmlib.chm_resolve_object(self.file, self.index)
if (res != chmlib.CHM_RESOLVE_SUCCESS):
return None
size, text = chmlib.chm_retrieve_object(self.file, ui, 0l, ui.length)
if (size == 0):
sys.stderr.write('GetIndex: file size = 0\n')
return None
return text
def GetArchiveInfo(self):
'''Obtains information on CHM archive.
This function checks the /#SYSTEM file inside the CHM archive to
obtain the index, home page, topics, encoding and title. It is called
from LoadCHM.
'''
self.searchable = extra.is_searchable(self.file)
self.lcid = None
result, ui = chmlib.chm_resolve_object(self.file, '/#SYSTEM')
if (result != chmlib.CHM_RESOLVE_SUCCESS):
sys.stderr.write('GetArchiveInfo: #SYSTEM does not exist\n')
return 0
size, text = chmlib.chm_retrieve_object(self.file, ui, 4l, ui.length)
if (size == 0):
sys.stderr.write('GetArchiveInfo: file size = 0\n')
return 0
buff = array.array('B', text)
index = 0
while (index < size):
cursor = buff[index] + (buff[index + 1] * 256)
if (cursor == 0):
index += 2
cursor = buff[index] + (buff[index + 1] * 256)
index += 2
self.topics = '/' + text[index:index + cursor - 1]
elif (cursor == 1):
index += 2
cursor = buff[index] + (buff[index + 1] * 256)
index += 2
self.index = '/' + text[index:index + cursor - 1]
elif (cursor == 2):
index += 2
cursor = buff[index] + (buff[index + 1] * 256)
index += 2
self.home = '/' + text[index:index + cursor - 1]
elif (cursor == 3):
index += 2
cursor = buff[index] + (buff[index + 1] * 256)
index += 2
self.title = text[index:index + cursor - 1]
elif (cursor == 4):
index += 2
cursor = buff[index] + (buff[index + 1] * 256)
index += 2
self.lcid = buff[index] + (buff[index + 1] * 256)
elif (cursor == 6):
index += 2
cursor = buff[index] + (buff[index + 1] * 256)
index += 2
tmp = text[index:index + cursor - 1]
if not self.topics:
tmp1 = '/' + tmp + '.hhc'
tmp2 = '/' + tmp + '.hhk'
res1, ui1 = chmlib.chm_resolve_object(self.file, tmp1)
res2, ui2 = chmlib.chm_resolve_object(self.file, tmp2)
if not self.topics and res1 == chmlib.CHM_RESOLVE_SUCCESS:
self.topics = '/' + tmp + '.hhc'
if not self.index and res2 == chmlib.CHM_RESOLVE_SUCCESS:
self.index = '/' + tmp + '.hhk'
elif (cursor == 16):
index += 2
cursor = buff[index] + (buff[index + 1] * 256)
index += 2
self.encoding = text[index:index + cursor - 1]
else:
index += 2
cursor = buff[index] + (buff[index + 1] * 256)
index += 2
index += cursor
self.GetWindowsInfo()
if not self.lcid:
self.lcid = extra.get_lcid(self.file)
return 1
def GetArchiveInfo(self):
'''Obtains information on CHM archive.
This function checks the /#SYSTEM file inside the CHM archive to
obtain the index, home page, topics, encoding and title. It is called
from LoadCHM.
'''
self.searchable = extra.is_searchable(self.file)
self.lcid = None
result, ui = chmlib.chm_resolve_object(self.file, '/#SYSTEM')
if (result != chmlib.CHM_RESOLVE_SUCCESS):
sys.stderr.write('GetArchiveInfo: #SYSTEM does not exist\n')
return 0
size, text = chmlib.chm_retrieve_object(self.file, ui, 4l, ui.length)
if (size == 0):
sys.stderr.write('GetArchiveInfo: file size = 0\n')
return 0
buff = array.array('B', text)
index = 0
while (index < size):
cursor = buff[index] + (buff[index+1] * 256)
if (cursor == 0):
index += 2
cursor = buff[index] + (buff[index+1] * 256)
index += 2
self.topics = '/' + text[index:index+cursor-1]
elif (cursor == 1):
index += 2
cursor = buff[index] + (buff[index+1] * 256)
index += 2
self.index = '/' + text[index:index+cursor-1]
elif (cursor == 2):
index += 2
cursor = buff[index] + (buff[index+1] * 256)
index += 2
self.home = '/' + text[index:index+cursor-1]
elif (cursor == 3):
index += 2
cursor = buff[index] + (buff[index+1] * 256)
index += 2
self.title = text[index:index+cursor-1]
elif (cursor == 4):
index += 2
cursor = buff[index] + (buff[index+1] * 256)
index += 2
self.lcid = buff[index] + (buff[index+1] * 256)
elif (cursor == 6):
index += 2
cursor = buff[index] + (buff[index+1] * 256)
index += 2
tmp = text[index:index+cursor-1]
if not self.topics:
tmp1 = '/' + tmp + '.hhc'
tmp2 = '/' + tmp + '.hhk'
res1, ui1 = chmlib.chm_resolve_object(self.file, tmp1)
res2, ui2 = chmlib.chm_resolve_object(self.file, tmp2)
if not self.topics and res1 == chmlib.CHM_RESOLVE_SUCCESS:
self.topics = '/' + tmp + '.hhc'
if not self.index and res2 == chmlib.CHM_RESOLVE_SUCCESS:
self.index = '/' + tmp + '.hhk'
elif (cursor == 16):
index += 2
cursor = buff[index] + (buff[index+1] * 256)
index += 2
self.encoding = text[index:index+cursor-1]
else:
index += 2
cursor = buff[index] + (buff[index+1] * 256)
index += 2
index += cursor
self.GetWindowsInfo()
if not self.lcid:
self.lcid = extra.get_lcid(self.file)
return 1