def __init__(self, mf):
self.mf = mf
h, h8 = mf.mobi_header, mf.mobi8_header
first_text_record = 1
offset = 0
self.resource_ranges = [(h8.first_resource_record,
h8.last_resource_record, h8.first_image_index)
]
if mf.kf8_type == 'joint':
offset = h.exth.kf8_header_index
self.resource_ranges.insert(
0, (h.first_resource_record, h.last_resource_record,
h.first_image_index))
self.text_records = [
TextRecord(i, r, h8.extra_data_flags, mf.decompress8)
for i, r in enumerate(mf.records[first_text_record +
offset:first_text_record +
offset +
h8.number_of_text_records])
]
self.raw_text = b''.join(r.raw for r in self.text_records)
self.header = self.mf.mobi8_header
self.extract_resources(mf.records)
self.read_fdst()
self.read_indices()
self.build_files()
self.read_tbs()
def __init__(self, mf):
self.mf = mf
h, h8 = mf.mobi_header, mf.mobi8_header
first_text_record = 1
offset = 0
res_end = len(mf.records)
if mf.kf8_type == 'joint':
offset = h.exth.kf8_header_index
res_end = offset - 1
self.resource_records = mf.records[h.first_non_book_record:res_end]
self.text_records = [
TextRecord(i, r, h8.extra_data_flags, mf.decompress8)
for i, r in enumerate(mf.records[first_text_record +
offset:first_text_record +
offset +
h8.number_of_text_records])
]
self.raw_text = b''.join(r.raw for r in self.text_records)
self.header = self.mf.mobi8_header
self.extract_resources()
self.read_fdst()
self.read_indices()
self.build_files()
self.read_tbs()
def __init__(self, mf):
for x in ('raw', 'palmdb', 'record_headers', 'records', 'mobi_header',
'huffman_record_nums',):
setattr(self, x, getattr(mf, x))
self.index_header = self.index_record = None
self.indexing_record_nums = set()
pir = getattr(self.mobi_header, 'primary_index_record', NULL_INDEX)
if pir != NULL_INDEX:
self.index_header = IndexHeader(self.records[pir])
numi = self.index_header.index_count
self.cncx = CNCX(self.records[
pir+1+numi:pir+1+numi+self.index_header.num_of_cncx_blocks],
self.index_header.index_encoding)
self.index_record = IndexRecord(self.records[pir+1:pir+1+numi],
self.index_header, self.cncx)
self.indexing_record_nums = set(range(pir,
pir+1+numi+self.index_header.num_of_cncx_blocks))
self.secondary_index_record = self.secondary_index_header = None
sir = self.mobi_header.secondary_index_record
if sir != NULL_INDEX:
self.secondary_index_header = SecondaryIndexHeader(self.records[sir])
numi = self.secondary_index_header.index_count
self.indexing_record_nums.add(sir)
self.secondary_index_record = IndexRecord(
self.records[sir+1:sir+1+numi], self.secondary_index_header, self.cncx)
self.indexing_record_nums |= set(range(sir+1, sir+1+numi))
ntr = self.mobi_header.number_of_text_records
fii = self.mobi_header.first_image_index
self.text_records = [TextRecord(r, self.records[r],
self.mobi_header.extra_data_flags, mf.decompress6) for r in range(1,
min(len(self.records), ntr+1))]
self.image_records, self.binary_records = [], []
self.font_records = []
image_index = 0
for i in range(self.mobi_header.first_resource_record, min(self.mobi_header.last_resource_record, len(self.records))):
if i in self.indexing_record_nums or i in self.huffman_record_nums:
continue
image_index += 1
r = self.records[i]
fmt = None
if i >= fii and r.raw[:4] not in {b'FLIS', b'FCIS', b'SRCS',
b'\xe9\x8e\r\n', b'RESC', b'BOUN', b'FDST', b'DATP',
b'AUDI', b'VIDE', b'FONT', b'CRES', b'CONT', b'CMET'}:
try:
fmt = what(None, r.raw)
except:
pass
if fmt is not None:
self.image_records.append(ImageRecord(image_index, r, fmt))
elif r.raw[:4] == b'FONT':
self.font_records.append(FontRecord(i, r))
else:
self.binary_records.append(BinaryRecord(i, r))
if self.index_record is not None:
self.tbs_indexing = TBSIndexing(self.text_records,
self.index_record.indices, self.mobi_header.type_raw)
