def extract_resources(self):
self.resource_map = []
known_types = {b'FLIS', b'FCIS', b'SRCS',
b'\xe9\x8e\r\n', b'RESC', b'BOUN', b'FDST', b'DATP',
b'AUDI', b'VIDE'}
for i, rec in enumerate(self.resource_records):
sig = rec.raw[:4]
payload = rec.raw
ext = 'dat'
prefix = 'binary'
suffix = ''
if sig in {b'HUFF', b'CDIC', b'INDX'}: continue
# TODO: Ignore CNCX records as well
if sig == b'FONT':
font = read_font_record(rec.raw)
if font['err']:
raise ValueError('Failed to read font record: %s Headers: %s'%(
font['err'], font['headers']))
payload = (font['font_data'] if font['font_data'] else
font['raw_data'])
prefix, ext = 'fonts', font['ext']
elif sig not in known_types:
q = imghdr.what(None, rec.raw)
if q:
prefix, ext = 'images', q
if prefix == 'binary':
if sig == b'\xe9\x8e\r\n':
suffix = '-EOF'
elif sig in known_types:
suffix = '-' + sig.decode('ascii')
self.resource_map.append(('%s/%06d%s.%s'%(prefix, i, suffix, ext),
payload))
def extract_resources(self, sections):
from calibre.ebooks.mobi.writer2.resources import PLACEHOLDER_GIF
resource_map = []
container = None
for x in ('fonts', 'images'):
os.mkdir(x)
for start, end in self.resource_offsets:
for i, sec in enumerate(sections[start:end]):
fname_idx = i + 1
data = sec[0]
typ = data[:4]
href = None
if typ in {
b'FLIS', b'FCIS', b'SRCS', b'\xe9\x8e\r\n', b'BOUN',
b'FDST', b'DATP', b'AUDI', b'VIDE', b'RESC', b'CMET',
b'PAGE'
}:
pass # Ignore these records
elif typ == b'FONT':
font = read_font_record(data)
href = "fonts/%05d.%s" % (fname_idx, font['ext'])
if font['err']:
self.log.warn('Reading font record %d failed: %s' %
(fname_idx, font['err']))
if font['headers']:
self.log.debug('Font record headers: %s' %
font['headers'])
with open(href.replace('/', os.sep), 'wb') as f:
f.write(font['font_data']
if font['font_data'] else font['raw_data'])
if font['encrypted']:
self.encrypted_fonts.append(href)
elif typ == b'CONT':
if data == b'CONTBOUNDARY':
container = None
continue
container = Container(data)
elif typ == b'CRES':
data, imgtype = container.load_image(data)
if data is not None:
href = 'images/%05d.%s' % (container.resource_index,
imgtype)
with open(href.replace('/', os.sep), 'wb') as f:
f.write(data)
elif typ == b'\xa0\xa0\xa0\xa0' and len(
data) == 4 and container is not None:
container.resource_index += 1
elif container is None:
if not (len(data) == len(PLACEHOLDER_GIF)
and data == PLACEHOLDER_GIF):
imgtype = find_imgtype(data)
href = 'images/%05d.%s' % (fname_idx, imgtype)
with open(href.replace('/', os.sep), 'wb') as f:
f.write(data)
resource_map.append(href)
return resource_map
def __init__(self, idx, record):
self.raw = record.raw
name = '%06d' % idx
self.font = read_font_record(self.raw)
if self.font['err']:
raise ValueError('Failed to read font record: %s Headers: %s' %
(self.font['err'], self.font['headers']))
self.payload = (self.font['font_data']
if self.font['font_data'] else self.font['raw_data'])
self.name = '%s.%s' % (name, self.font['ext'])
def __init__(self, idx, record):
self.raw = record.raw
name = '%06d'%idx
self.font = read_font_record(self.raw)
if self.font['err']:
raise ValueError('Failed to read font record: %s Headers: %s'%(
self.font['err'], self.font['headers']))
self.payload = (self.font['font_data'] if self.font['font_data'] else
self.font['raw_data'])
self.name = '%s.%s'%(name, self.font['ext'])
def extract_resources(self, sections):
from calibre.ebooks.mobi.writer2.resources import PLACEHOLDER_GIF
resource_map = []
container = None
for x in ('fonts', 'images'):
os.mkdir(x)
for start, end in self.resource_offsets:
for i, sec in enumerate(sections[start:end]):
fname_idx = i+1
data = sec[0]
typ = data[:4]
href = None
if typ in {b'FLIS', b'FCIS', b'SRCS', b'\xe9\x8e\r\n', b'BOUN',
b'FDST', b'DATP', b'AUDI', b'VIDE', b'RESC', b'CMET', b'PAGE'}:
pass # Ignore these records
elif typ == b'FONT':
font = read_font_record(data)
href = "fonts/%05d.%s" % (fname_idx, font['ext'])
if font['err']:
self.log.warn('Reading font record %d failed: %s'%(
fname_idx, font['err']))
if font['headers']:
self.log.debug('Font record headers: %s'%font['headers'])
with open(href.replace('/', os.sep), 'wb') as f:
f.write(font['font_data'] if font['font_data'] else
font['raw_data'])
if font['encrypted']:
self.encrypted_fonts.append(href)
elif typ == b'CONT':
if data == b'CONTBOUNDARY':
container = None
continue
container = Container(data)
elif typ == b'CRES':
data, imgtype = container.load_image(data)
if data is not None:
href = 'images/%05d.%s'%(container.resource_index, imgtype)
with open(href.replace('/', os.sep), 'wb') as f:
f.write(data)
elif typ == b'\xa0\xa0\xa0\xa0' and len(data) == 4 and container is not None:
container.resource_index += 1
elif container is None:
if not (len(data) == len(PLACEHOLDER_GIF) and data == PLACEHOLDER_GIF):
imgtype = find_imgtype(data)
href = 'images/%05d.%s'%(fname_idx, imgtype)
with open(href.replace('/', os.sep), 'wb') as f:
f.write(data)
resource_map.append(href)
return resource_map
def extract_resources(self):
resource_map = []
for x in ("fonts", "images"):
os.mkdir(x)
for i, sec in enumerate(self.resource_sections):
fname_idx = i + 1
data = sec[0]
typ = data[:4]
href = None
if typ in {
b"FLIS",
b"FCIS",
b"SRCS",
b"\xe9\x8e\r\n",
b"RESC",
b"BOUN",
b"FDST",
b"DATP",
b"AUDI",
b"VIDE",
}:
pass # Ignore these records
elif typ == b"FONT":
font = read_font_record(data)
href = "fonts/%05d.%s" % (fname_idx, font["ext"])
if font["err"]:
self.log.warn("Reading font record %d failed: %s" % (fname_idx, font["err"]))
if font["headers"]:
self.log.debug("Font record headers: %s" % font["headers"])
with open(href.replace("/", os.sep), "wb") as f:
f.write(font["font_data"] if font["font_data"] else font["raw_data"])
if font["encrypted"]:
self.encrypted_fonts.append(href)
else:
imgtype = what(None, data)
if imgtype is None:
from calibre.utils.magick.draw import identify_data
try:
imgtype = identify_data(data)[2]
except Exception:
imgtype = "unknown"
href = "images/%05d.%s" % (fname_idx, imgtype)
with open(href.replace("/", os.sep), "wb") as f:
f.write(data)
resource_map.append(href)
return resource_map
def extract_resources(self):
from calibre.ebooks.mobi.writer2.resources import PLACEHOLDER_GIF
resource_map = []
for x in ('fonts', 'images'):
os.mkdir(x)
for i, sec in enumerate(self.resource_sections):
fname_idx = i + 1
data = sec[0]
typ = data[:4]
href = None
if typ in {
b'FLIS', b'FCIS', b'SRCS', b'\xe9\x8e\r\n', b'BOUN',
b'FDST', b'DATP', b'AUDI', b'VIDE'
}:
pass # Ignore these records
elif typ == b'RESC':
self.resc_data = read_resc_record(data)
elif typ == b'FONT':
font = read_font_record(data)
href = "fonts/%05d.%s" % (fname_idx, font['ext'])
if font['err']:
self.log.warn('Reading font record %d failed: %s' %
(fname_idx, font['err']))
if font['headers']:
self.log.debug('Font record headers: %s' %
font['headers'])
with open(href.replace('/', os.sep), 'wb') as f:
f.write(font['font_data']
if font['font_data'] else font['raw_data'])
if font['encrypted']:
self.encrypted_fonts.append(href)
else:
if not (len(data) == len(PLACEHOLDER_GIF)
and data == PLACEHOLDER_GIF):
imgtype = what(None, data)
if imgtype is None:
from calibre.utils.magick.draw import identify_data
try:
imgtype = identify_data(data)[2]
except Exception:
imgtype = 'unknown'
href = 'images/%05d.%s' % (fname_idx, imgtype)
with open(href.replace('/', os.sep), 'wb') as f:
f.write(data)
resource_map.append(href)
return resource_map
def extract_resources(self):
from calibre.ebooks.mobi.writer2.resources import PLACEHOLDER_GIF
resource_map = []
for x in ('fonts', 'images'):
os.mkdir(x)
for i, sec in enumerate(self.resource_sections):
fname_idx = i+1
data = sec[0]
typ = data[:4]
href = None
if typ in {b'FLIS', b'FCIS', b'SRCS', b'\xe9\x8e\r\n', b'BOUN',
b'FDST', b'DATP', b'AUDI', b'VIDE'}:
pass # Ignore these records
elif typ == b'RESC':
self.resc_data = read_resc_record(data)
elif typ == b'FONT':
font = read_font_record(data)
href = "fonts/%05d.%s" % (fname_idx, font['ext'])
if font['err']:
self.log.warn('Reading font record %d failed: %s'%(
fname_idx, font['err']))
if font['headers']:
self.log.debug('Font record headers: %s'%font['headers'])
with open(href.replace('/', os.sep), 'wb') as f:
f.write(font['font_data'] if font['font_data'] else
font['raw_data'])
if font['encrypted']:
self.encrypted_fonts.append(href)
else:
if len(data) == len(PLACEHOLDER_GIF) and data == PLACEHOLDER_GIF:
continue
imgtype = what(None, data)
if imgtype is None:
from calibre.utils.magick.draw import identify_data
try:
imgtype = identify_data(data)[2]
except Exception:
imgtype = 'unknown'
href = 'images/%05d.%s'%(fname_idx, imgtype)
with open(href.replace('/', os.sep), 'wb') as f:
f.write(data)
resource_map.append(href)
return resource_map
def extract_resources(self):
self.resource_map = []
known_types = {
b'FLIS', b'FCIS', b'SRCS', b'\xe9\x8e\r\n', b'RESC', b'BOUN',
b'FDST', b'DATP', b'AUDI', b'VIDE'
}
for i, rec in enumerate(self.resource_records):
sig = rec.raw[:4]
payload = rec.raw
ext = 'dat'
prefix = 'binary'
suffix = ''
if sig in {b'HUFF', b'CDIC', b'INDX'}:
continue
# TODO: Ignore CNCX records as well
if sig == b'FONT':
font = read_font_record(rec.raw)
if font['err']:
raise ValueError(
'Failed to read font record: %s Headers: %s' %
(font['err'], font['headers']))
payload = (font['font_data']
if font['font_data'] else font['raw_data'])
prefix, ext = 'fonts', font['ext']
elif sig not in known_types:
q = what(None, rec.raw)
if q:
prefix, ext = 'images', q
if prefix == 'binary':
if sig == b'\xe9\x8e\r\n':
suffix = '-EOF'
elif sig in known_types:
suffix = '-' + sig.decode('ascii')
self.resource_map.append(
('%s/%06d%s.%s' % (prefix, i, suffix, ext), payload))
def extract_resources(self):
resource_map = []
for x in ('fonts', 'images'):
os.mkdir(x)
for i, sec in enumerate(self.resource_sections):
fname_idx = i+1
data = sec[0]
typ = data[:4]
href = None
if typ in {b'FLIS', b'FCIS', b'SRCS', b'\xe9\x8e\r\n',
b'RESC', b'BOUN', b'FDST', b'DATP', b'AUDI', b'VIDE'}:
pass # Ignore these records
elif typ == b'FONT':
font = read_font_record(data)
href = "fonts/%05d.%s" % (fname_idx, font['ext'])
if font['err']:
self.log.warn('Reading font record %d failed: %s'%(
fname_idx, font['err']))
if font['headers']:
self.log.debug('Font record headers: %s'%font['headers'])
with open(href.replace('/', os.sep), 'wb') as f:
f.write(font['font_data'] if font['font_data'] else
font['raw_data'])
if font['encrypted']:
self.encrypted_fonts.append(href)
else:
imgtype = imghdr.what(None, data)
if imgtype is None:
imgtype = 'unknown'
href = 'images/%05d.%s'%(fname_idx, imgtype)
with open(href.replace('/', os.sep), 'wb') as f:
f.write(data)
resource_map.append(href)
return resource_map
def extract_resources(self, records):
self.resource_map = []
self.containers = []
known_types = {b'FLIS', b'FCIS', b'SRCS',
b'\xe9\x8e\r\n', b'RESC', b'BOUN', b'FDST', b'DATP',
b'AUDI', b'VIDE', b'CRES', b'CONT', b'CMET', b'PAGE'}
container = None
for i, rec in enumerate(records):
for (l, r, offset) in self.resource_ranges:
if l <= i <= r:
resource_index = i + 1
if offset is not None and resource_index >= offset:
resource_index -= offset
break
else:
continue
sig = rec.raw[:4]
payload = rec.raw
ext = 'dat'
prefix = 'binary'
suffix = ''
if sig in {b'HUFF', b'CDIC', b'INDX'}:
continue
# TODO: Ignore CNCX records as well
if sig == b'FONT':
font = read_font_record(rec.raw)
if font['err']:
raise ValueError('Failed to read font record: %s Headers: %s'%(
font['err'], font['headers']))
payload = (font['font_data'] if font['font_data'] else
font['raw_data'])
prefix, ext = 'fonts', font['ext']
elif sig == b'CONT':
if payload == b'CONTBOUNDARY':
self.containers.append(container)
container = None
continue
container = ContainerHeader(payload)
elif sig == b'CRES':
container.resources.append(payload)
if container.is_image_container:
payload = payload[12:]
q = what(None, payload)
if q:
prefix, ext = 'hd-images', q
resource_index = len(container.resources)
elif sig == b'\xa0\xa0\xa0\xa0' and len(payload) == 4:
if container is None:
print('Found an end of container record with no container, ignoring')
else:
container.resources.append(None)
continue
elif sig not in known_types:
if container is not None and len(container.resources) == container.num_of_resource_records:
container.add_hrefs(payload)
continue
q = what(None, rec.raw)
if q:
prefix, ext = 'images', q
if prefix == 'binary':
if sig == b'\xe9\x8e\r\n':
suffix = '-EOF'
elif sig in known_types:
suffix = '-' + sig.decode('ascii')
self.resource_map.append(('%s/%06d%s.%s'%(prefix, resource_index, suffix, ext),
payload))
def extract_resources(self, records):
self.resource_map = []
self.containers = []
known_types = {
b'FLIS', b'FCIS', b'SRCS', b'\xe9\x8e\r\n', b'RESC', b'BOUN',
b'FDST', b'DATP', b'AUDI', b'VIDE', b'CRES', b'CONT', b'CMET',
b'PAGE'
}
container = None
for i, rec in enumerate(records):
for (l, r, offset) in self.resource_ranges:
if l <= i <= r:
resource_index = i + 1
if offset is not None and resource_index >= offset:
resource_index -= offset
break
else:
continue
sig = rec.raw[:4]
payload = rec.raw
ext = 'dat'
prefix = 'binary'
suffix = ''
if sig in {b'HUFF', b'CDIC', b'INDX'}:
continue
# TODO: Ignore CNCX records as well
if sig == b'FONT':
font = read_font_record(rec.raw)
if font['err']:
raise ValueError(
'Failed to read font record: %s Headers: %s' %
(font['err'], font['headers']))
payload = (font['font_data']
if font['font_data'] else font['raw_data'])
prefix, ext = 'fonts', font['ext']
elif sig == b'CONT':
if payload == b'CONTBOUNDARY':
self.containers.append(container)
container = None
continue
container = ContainerHeader(payload)
elif sig == b'CRES':
container.resources.append(payload)
if container.is_image_container:
payload = payload[12:]
q = what(None, payload)
if q:
prefix, ext = 'hd-images', q
resource_index = len(container.resources)
elif sig == b'\xa0\xa0\xa0\xa0' and len(payload) == 4:
if container is None:
print(
'Found an end of container record with no container, ignoring'
)
else:
container.resources.append(None)
continue
elif sig not in known_types:
if container is not None and len(
container.resources
) == container.num_of_resource_records:
container.add_hrefs(payload)
continue
q = what(None, rec.raw)
if q:
prefix, ext = 'images', q
if prefix == 'binary':
if sig == b'\xe9\x8e\r\n':
suffix = '-EOF'
elif sig in known_types:
suffix = '-' + sig.decode('ascii')
self.resource_map.append(
('%s/%06d%s.%s' % (prefix, resource_index, suffix, ext),
payload))
def extract_resources(self, sections):
from calibre.ebooks.mobi.writer2.resources import PLACEHOLDER_GIF
resource_map = []
container = None
for x in ("fonts", "images"):
os.mkdir(x)
for start, end in self.resource_offsets:
for i, sec in enumerate(sections[start:end]):
fname_idx = i + 1
data = sec[0]
typ = data[:4]
href = None
if typ in {
b"FLIS",
b"FCIS",
b"SRCS",
b"\xe9\x8e\r\n",
b"BOUN",
b"FDST",
b"DATP",
b"AUDI",
b"VIDE",
b"RESC",
b"CMET",
b"PAGE",
}:
pass # Ignore these records
elif typ == b"FONT":
font = read_font_record(data)
href = "fonts/%05d.%s" % (fname_idx, font["ext"])
if font["err"]:
self.log.warn("Reading font record %d failed: %s" % (fname_idx, font["err"]))
if font["headers"]:
self.log.debug("Font record headers: %s" % font["headers"])
with open(href.replace("/", os.sep), "wb") as f:
f.write(font["font_data"] if font["font_data"] else font["raw_data"])
if font["encrypted"]:
self.encrypted_fonts.append(href)
elif typ == b"CONT":
if data == b"CONTBOUNDARY":
container = None
continue
container = Container(data)
elif typ == b"CRES":
data, imgtype = container.load_image(data)
if data is not None:
href = "images/%05d.%s" % (container.resource_index, imgtype)
with open(href.replace("/", os.sep), "wb") as f:
f.write(data)
elif typ == b"\xa0\xa0\xa0\xa0" and len(data) == 4 and container is not None:
container.resource_index += 1
elif container is None:
if not (len(data) == len(PLACEHOLDER_GIF) and data == PLACEHOLDER_GIF):
imgtype = find_imgtype(data)
href = "images/%05d.%s" % (fname_idx, imgtype)
with open(href.replace("/", os.sep), "wb") as f:
f.write(data)
resource_map.append(href)
return resource_map
def extract_resources(self, records):
self.resource_map = []
self.containers = []
known_types = {
b"FLIS",
b"FCIS",
b"SRCS",
b"\xe9\x8e\r\n",
b"RESC",
b"BOUN",
b"FDST",
b"DATP",
b"AUDI",
b"VIDE",
b"CRES",
b"CONT",
b"CMET",
b"PAGE",
}
container = None
for i, rec in enumerate(records):
for (l, r, offset) in self.resource_ranges:
if l <= i <= r:
resource_index = i + 1
if offset is not None and resource_index >= offset:
resource_index -= offset
break
else:
continue
sig = rec.raw[:4]
payload = rec.raw
ext = "dat"
prefix = "binary"
suffix = ""
if sig in {b"HUFF", b"CDIC", b"INDX"}:
continue
# TODO: Ignore CNCX records as well
if sig == b"FONT":
font = read_font_record(rec.raw)
if font["err"]:
raise ValueError("Failed to read font record: %s Headers: %s" % (font["err"], font["headers"]))
payload = font["font_data"] if font["font_data"] else font["raw_data"]
prefix, ext = "fonts", font["ext"]
elif sig == b"CONT":
if payload == b"CONTBOUNDARY":
self.containers.append(container)
container = None
continue
container = ContainerHeader(payload)
elif sig == b"CRES":
container.resources.append(payload)
if container.is_image_container:
payload = payload[12:]
q = what(None, payload)
if q:
prefix, ext = "hd-images", q
resource_index = len(container.resources)
elif sig == b"\xa0\xa0\xa0\xa0" and len(payload) == 4:
container.resources.append(None)
continue
elif sig not in known_types:
if container is not None and len(container.resources) == container.num_of_resource_records:
container.add_hrefs(payload)
continue
q = what(None, rec.raw)
if q:
prefix, ext = "images", q
if prefix == "binary":
if sig == b"\xe9\x8e\r\n":
suffix = "-EOF"
elif sig in known_types:
suffix = "-" + sig.decode("ascii")
self.resource_map.append(("%s/%06d%s.%s" % (prefix, resource_index, suffix, ext), payload))
