This page hosts a formal specification of Shapefile index file using Kaitai Struct. This specification can be automatically translated into a variety of programming languages to get a parsing library.
All parsing code for Python generated by Kaitai Struct depends on the Python runtime library. You have to install it before you can parse data.
The Python runtime library can be installed from PyPI:
python3 -m pip install kaitaistructParse a local file and get structure in memory:
data = ShapefileIndex.from_file("path/to/local/file.shx")
Or parse structure from a bytes:
from kaitaistruct import KaitaiStream, BytesIO
raw = b"\x00\x01\x02..."
data = ShapefileIndex(KaitaiStream(BytesIO(raw)))
After that, one can get various attributes from the structure by invoking getter methods like:
data.records # => the size of this section of the file in bytes must equal (header.file_length * 2) - 100
# This is a generated file! Please edit source .ksy file and use kaitai-struct-compiler to rebuild
# type: ignore
import kaitaistruct
from kaitaistruct import KaitaiStruct, KaitaiStream, BytesIO
from enum import IntEnum
if getattr(kaitaistruct, 'API_VERSION', (0, 9)) < (0, 11):
raise Exception("Incompatible Kaitai Struct Python API: 0.11 or later is required, but you have %s" % (kaitaistruct.__version__))
class ShapefileIndex(KaitaiStruct):
class ShapeType(IntEnum):
null_shape = 0
point = 1
poly_line = 3
polygon = 5
multi_point = 8
point_z = 11
poly_line_z = 13
polygon_z = 15
multi_point_z = 18
point_m = 21
poly_line_m = 23
polygon_m = 25
multi_point_m = 28
multi_patch = 31
def __init__(self, _io, _parent=None, _root=None):
super(ShapefileIndex, self).__init__(_io)
self._parent = _parent
self._root = _root or self
self._read()
def _read(self):
self.header = ShapefileIndex.FileHeader(self._io, self, self._root)
self.records = []
i = 0
while not self._io.is_eof():
self.records.append(ShapefileIndex.Record(self._io, self, self._root))
i += 1
def _fetch_instances(self):
pass
self.header._fetch_instances()
for i in range(len(self.records)):
pass
self.records[i]._fetch_instances()
class BoundingBoxXYZM(KaitaiStruct):
def __init__(self, _io, _parent=None, _root=None):
super(ShapefileIndex.BoundingBoxXYZM, self).__init__(_io)
self._parent = _parent
self._root = _root
self._read()
def _read(self):
self.x = ShapefileIndex.BoundsMinMax(self._io, self, self._root)
self.y = ShapefileIndex.BoundsMinMax(self._io, self, self._root)
self.z = ShapefileIndex.BoundsMinMax(self._io, self, self._root)
self.m = ShapefileIndex.BoundsMinMax(self._io, self, self._root)
def _fetch_instances(self):
pass
self.x._fetch_instances()
self.y._fetch_instances()
self.z._fetch_instances()
self.m._fetch_instances()
class BoundsMinMax(KaitaiStruct):
def __init__(self, _io, _parent=None, _root=None):
super(ShapefileIndex.BoundsMinMax, self).__init__(_io)
self._parent = _parent
self._root = _root
self._read()
def _read(self):
self.min = self._io.read_f8be()
self.max = self._io.read_f8be()
def _fetch_instances(self):
pass
class FileHeader(KaitaiStruct):
def __init__(self, _io, _parent=None, _root=None):
super(ShapefileIndex.FileHeader, self).__init__(_io)
self._parent = _parent
self._root = _root
self._read()
def _read(self):
self.file_code = self._io.read_bytes(4)
if not self.file_code == b"\x00\x00\x27\x0A":
raise kaitaistruct.ValidationNotEqualError(b"\x00\x00\x27\x0A", self.file_code, self._io, u"/types/file_header/seq/0")
self.unused_field_1 = self._io.read_bytes(4)
if not self.unused_field_1 == b"\x00\x00\x00\x00":
raise kaitaistruct.ValidationNotEqualError(b"\x00\x00\x00\x00", self.unused_field_1, self._io, u"/types/file_header/seq/1")
self.unused_field_2 = self._io.read_bytes(4)
if not self.unused_field_2 == b"\x00\x00\x00\x00":
raise kaitaistruct.ValidationNotEqualError(b"\x00\x00\x00\x00", self.unused_field_2, self._io, u"/types/file_header/seq/2")
self.unused_field_3 = self._io.read_bytes(4)
if not self.unused_field_3 == b"\x00\x00\x00\x00":
raise kaitaistruct.ValidationNotEqualError(b"\x00\x00\x00\x00", self.unused_field_3, self._io, u"/types/file_header/seq/3")
self.unused_field_4 = self._io.read_bytes(4)
if not self.unused_field_4 == b"\x00\x00\x00\x00":
raise kaitaistruct.ValidationNotEqualError(b"\x00\x00\x00\x00", self.unused_field_4, self._io, u"/types/file_header/seq/4")
self.unused_field_5 = self._io.read_bytes(4)
if not self.unused_field_5 == b"\x00\x00\x00\x00":
raise kaitaistruct.ValidationNotEqualError(b"\x00\x00\x00\x00", self.unused_field_5, self._io, u"/types/file_header/seq/5")
self.file_length = self._io.read_s4be()
self.version = self._io.read_bytes(4)
if not self.version == b"\xE8\x03\x00\x00":
raise kaitaistruct.ValidationNotEqualError(b"\xE8\x03\x00\x00", self.version, self._io, u"/types/file_header/seq/7")
self.shape_type = KaitaiStream.resolve_enum(ShapefileIndex.ShapeType, self._io.read_s4le())
self.bounding_box = ShapefileIndex.BoundingBoxXYZM(self._io, self, self._root)
def _fetch_instances(self):
pass
self.bounding_box._fetch_instances()
class Record(KaitaiStruct):
def __init__(self, _io, _parent=None, _root=None):
super(ShapefileIndex.Record, self).__init__(_io)
self._parent = _parent
self._root = _root
self._read()
def _read(self):
self.offset = self._io.read_s4be()
self.content_length = self._io.read_s4be()
def _fetch_instances(self):
pass