/usr/lib/python2.7/dist-packages/shapefile.py is in python-pyshp 1.2.12+ds-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 | """
shapefile.py
Provides read and write support for ESRI Shapefiles.
author: jlawhead<at>geospatialpython.com
date: 2017/08/24
version: 1.2.12
Compatible with Python versions 2.7-3.x
"""
__version__ = "1.2.12"
from struct import pack, unpack, calcsize, error, Struct
import os
import sys
import time
import array
import tempfile
import itertools
import io
from datetime import date
#
# Constants for shape types
NULL = 0
POINT = 1
POLYLINE = 3
POLYGON = 5
MULTIPOINT = 8
POINTZ = 11
POLYLINEZ = 13
POLYGONZ = 15
MULTIPOINTZ = 18
POINTM = 21
POLYLINEM = 23
POLYGONM = 25
MULTIPOINTM = 28
MULTIPATCH = 31
MISSING = [None,'']
PYTHON3 = sys.version_info[0] == 3
if PYTHON3:
xrange = range
izip = zip
else:
from itertools import izip
def b(v):
if PYTHON3:
if isinstance(v, str):
# For python 3 encode str to bytes.
return v.encode('utf-8')
elif isinstance(v, bytes):
# Already bytes.
return v
else:
# Error.
raise Exception('Unknown input type')
else:
# For python 2 assume str passed in and return str.
return v
def u(v):
if PYTHON3:
# try/catch added 2014/05/07
# returned error on dbf of shapefile
# from www.naturalearthdata.com named
# "ne_110m_admin_0_countries".
# Just returning v as is seemed to fix
# the problem. This function could
# be condensed further.
try:
if isinstance(v, bytes):
# For python 3 decode bytes to str.
return v.decode('utf-8')
elif isinstance(v, str):
# Already str.
return v
else:
# Error.
raise Exception('Unknown input type')
except: return v
else:
# For python 2 assume str passed in and return str.
return v
def is_string(v):
if PYTHON3:
return isinstance(v, str)
else:
return isinstance(v, basestring)
class _Array(array.array):
"""Converts python tuples to lits of the appropritate type.
Used to unpack different shapefile header parts."""
def __repr__(self):
return str(self.tolist())
def signed_area(coords):
"""Return the signed area enclosed by a ring using the linear time
algorithm. A value >= 0 indicates a counter-clockwise oriented ring.
"""
xs, ys = map(list, zip(*coords))
xs.append(xs[1])
ys.append(ys[1])
return sum(xs[i]*(ys[i+1]-ys[i-1]) for i in range(1, len(coords)))/2.0
class _Shape:
def __init__(self, shapeType=NULL):
"""Stores the geometry of the different shape types
specified in the Shapefile spec. Shape types are
usually point, polyline, or polygons. Every shape type
except the "Null" type contains points at some level for
example verticies in a polygon. If a shape type has
multiple shapes containing points within a single
geometry record then those shapes are called parts. Parts
are designated by their starting index in geometry record's
list of shapes."""
self.shapeType = shapeType
self.points = []
self.parts = []
@property
def __geo_interface__(self):
if self.shapeType in [POINT, POINTM, POINTZ]:
return {
'type': 'Point',
'coordinates': tuple(self.points[0])
}
elif self.shapeType in [MULTIPOINT, MULTIPOINTM, MULTIPOINTZ]:
return {
'type': 'MultiPoint',
'coordinates': tuple([tuple(p) for p in self.points])
}
elif self.shapeType in [POLYLINE, POLYLINEM, POLYLINEZ]:
if len(self.parts) == 1:
return {
'type': 'LineString',
'coordinates': tuple([tuple(p) for p in self.points])
}
else:
ps = None
coordinates = []
for part in self.parts:
if ps == None:
ps = part
continue
else:
coordinates.append(tuple([tuple(p) for p in self.points[ps:part]]))
ps = part
else:
coordinates.append(tuple([tuple(p) for p in self.points[part:]]))
return {
'type': 'MultiLineString',
'coordinates': tuple(coordinates)
}
elif self.shapeType in [POLYGON, POLYGONM, POLYGONZ]:
if len(self.parts) == 1:
return {
'type': 'Polygon',
'coordinates': (tuple([tuple(p) for p in self.points]),)
}
else:
ps = None
coordinates = []
for part in self.parts:
if ps == None:
ps = part
continue
else:
coordinates.append(tuple([tuple(p) for p in self.points[ps:part]]))
ps = part
else:
coordinates.append(tuple([tuple(p) for p in self.points[part:]]))
polys = []
poly = [coordinates[0]]
for coord in coordinates[1:]:
if signed_area(coord) < 0:
polys.append(poly)
poly = [coord]
else:
poly.append(coord)
polys.append(poly)
if len(polys) == 1:
return {
'type': 'Polygon',
'coordinates': tuple(polys[0])
}
elif len(polys) > 1:
return {
'type': 'MultiPolygon',
'coordinates': polys
}
class _ShapeRecord:
"""A shape object of any type."""
def __init__(self, shape=None, record=None):
self.shape = shape
self.record = record
class ShapefileException(Exception):
"""An exception to handle shapefile specific problems."""
pass
class Reader:
"""Reads the three files of a shapefile as a unit or
separately. If one of the three files (.shp, .shx,
.dbf) is missing no exception is thrown until you try
to call a method that depends on that particular file.
The .shx index file is used if available for efficiency
but is not required to read the geometry from the .shp
file. The "shapefile" argument in the constructor is the
name of the file you want to open.
You can instantiate a Reader without specifying a shapefile
and then specify one later with the load() method.
Only the shapefile headers are read upon loading. Content
within each file is only accessed when required and as
efficiently as possible. Shapefiles are usually not large
but they can be.
"""
def __init__(self, *args, **kwargs):
self.shp = None
self.shx = None
self.dbf = None
self.shapeName = "Not specified"
self._offsets = []
self.shpLength = None
self.numRecords = None
self.fields = []
self.__dbfHdrLength = 0
# See if a shapefile name was passed as an argument
if len(args) > 0:
if is_string(args[0]):
self.load(args[0])
return
if "shp" in kwargs.keys():
if hasattr(kwargs["shp"], "read"):
self.shp = kwargs["shp"]
# Copy if required
try:
self.shp.seek(0)
except (NameError, io.UnsupportedOperation):
self.shp = io.BytesIO(self.shp.read())
if "shx" in kwargs.keys():
if hasattr(kwargs["shx"], "read"):
self.shx = kwargs["shx"]
# Copy if required
try:
self.shx.seek(0)
except (NameError, io.UnsupportedOperation):
self.shx = io.BytesIO(self.shx.read())
if "dbf" in kwargs.keys():
if hasattr(kwargs["dbf"], "read"):
self.dbf = kwargs["dbf"]
# Copy if required
try:
self.dbf.seek(0)
except (NameError, io.UnsupportedOperation):
self.dbf = io.BytesIO(self.dbf.read())
if self.shp or self.dbf:
self.load()
else:
raise ShapefileException("Shapefile Reader requires a shapefile or file-like object.")
def load(self, shapefile=None):
"""Opens a shapefile from a filename or file-like
object. Normally this method would be called by the
constructor with the file name as an argument."""
if shapefile:
(shapeName, ext) = os.path.splitext(shapefile)
self.shapeName = shapeName
try:
self.shp = open("%s.shp" % shapeName, "rb")
except IOError:
pass
try:
self.shx = open("%s.shx" % shapeName, "rb")
except IOError:
pass
try:
self.dbf = open("%s.dbf" % shapeName, "rb")
except IOError:
pass
if not (self.shp and self.dbf):
raise ShapefileException("Unable to open %s.dbf or %s.shp." % (shapeName, shapeName) )
if self.shp:
self.__shpHeader()
if self.dbf:
self.__dbfHeader()
def __getFileObj(self, f):
"""Checks to see if the requested shapefile file object is
available. If not a ShapefileException is raised."""
if not f:
raise ShapefileException("Shapefile Reader requires a shapefile or file-like object.")
if self.shp and self.shpLength is None:
self.load()
if self.dbf and len(self.fields) == 0:
self.load()
return f
def __restrictIndex(self, i):
"""Provides list-like handling of a record index with a clearer
error message if the index is out of bounds."""
if self.numRecords:
rmax = self.numRecords - 1
if abs(i) > rmax:
raise IndexError("Shape or Record index out of range.")
if i < 0: i = range(self.numRecords)[i]
return i
def __shpHeader(self):
"""Reads the header information from a .shp or .shx file."""
if not self.shp:
raise ShapefileException("Shapefile Reader requires a shapefile or file-like object. (no shp file found")
shp = self.shp
# File length (16-bit word * 2 = bytes)
shp.seek(24)
self.shpLength = unpack(">i", shp.read(4))[0] * 2
# Shape type
shp.seek(32)
self.shapeType= unpack("<i", shp.read(4))[0]
# The shapefile's bounding box (lower left, upper right)
self.bbox = _Array('d', unpack("<4d", shp.read(32)))
# Elevation
self.elevation = _Array('d', unpack("<2d", shp.read(16)))
# Measure
self.measure = _Array('d', unpack("<2d", shp.read(16)))
def __shape(self):
"""Returns the header info and geometry for a single shape."""
f = self.__getFileObj(self.shp)
record = _Shape()
nParts = nPoints = zmin = zmax = mmin = mmax = None
(recNum, recLength) = unpack(">2i", f.read(8))
# Determine the start of the next record
next = f.tell() + (2 * recLength)
shapeType = unpack("<i", f.read(4))[0]
record.shapeType = shapeType
# For Null shapes create an empty points list for consistency
if shapeType == 0:
record.points = []
# All shape types capable of having a bounding box
elif shapeType in (3,5,8,13,15,18,23,25,28,31):
record.bbox = _Array('d', unpack("<4d", f.read(32)))
# Shape types with parts
if shapeType in (3,5,13,15,23,25,31):
nParts = unpack("<i", f.read(4))[0]
# Shape types with points
if shapeType in (3,5,8,13,15,18,23,25,28,31):
nPoints = unpack("<i", f.read(4))[0]
# Read parts
if nParts:
record.parts = _Array('i', unpack("<%si" % nParts, f.read(nParts * 4)))
# Read part types for Multipatch - 31
if shapeType == 31:
record.partTypes = _Array('i', unpack("<%si" % nParts, f.read(nParts * 4)))
# Read points - produces a list of [x,y] values
if nPoints:
flat = unpack("<%sd" % (2 * nPoints), f.read(16*nPoints))
record.points = list(izip(*(iter(flat),) * 2))
# Read z extremes and values
if shapeType in (13,15,18,31):
(zmin, zmax) = unpack("<2d", f.read(16))
record.z = _Array('d', unpack("<%sd" % nPoints, f.read(nPoints * 8)))
# Read m extremes and values if header m values do not equal 0.0
if shapeType in (13,15,18,23,25,28,31) and not 0.0 in self.measure:
(mmin, mmax) = unpack("<2d", f.read(16))
# Measure values less than -10e38 are nodata values according to the spec
record.m = []
for m in _Array('d', unpack("<%sd" % nPoints, f.read(nPoints * 8))):
if m > -10e38:
record.m.append(m)
else:
record.m.append(None)
# Read a single point
if shapeType in (1,11,21):
record.points = [_Array('d', unpack("<2d", f.read(16)))]
# Read a single Z value
if shapeType == 11:
record.z = unpack("<d", f.read(8))
# Read a single M value
if shapeType in (11,21):
record.m = unpack("<d", f.read(8))
# Seek to the end of this record as defined by the record header because
# the shapefile spec doesn't require the actual content to meet the header
# definition. Probably allowed for lazy feature deletion.
f.seek(next)
return record
def __shapeIndex(self, i=None):
"""Returns the offset in a .shp file for a shape based on information
in the .shx index file."""
shx = self.shx
if not shx:
return None
if not self._offsets:
# File length (16-bit word * 2 = bytes) - header length
shx.seek(24)
shxRecordLength = (unpack(">i", shx.read(4))[0] * 2) - 100
numRecords = shxRecordLength // 8
# Jump to the first record.
shx.seek(100)
shxRecords = _Array('i')
# Each offset consists of two nrs, only the first one matters
shxRecords.fromfile(shx, 2 * numRecords)
if sys.byteorder != 'big':
shxRecords.byteswap()
self._offsets = [2 * el for el in shxRecords[::2]]
if not i == None:
return self._offsets[i]
def shape(self, i=0):
"""Returns a shape object for a shape in the the geometry
record file."""
shp = self.__getFileObj(self.shp)
i = self.__restrictIndex(i)
offset = self.__shapeIndex(i)
if not offset:
# Shx index not available so iterate the full list.
for j,k in enumerate(self.iterShapes()):
if j == i:
return k
shp.seek(offset)
return self.__shape()
def shapes(self):
"""Returns all shapes in a shapefile."""
shp = self.__getFileObj(self.shp)
# Found shapefiles which report incorrect
# shp file length in the header. Can't trust
# that so we seek to the end of the file
# and figure it out.
shp.seek(0,2)
self.shpLength = shp.tell()
shp.seek(100)
shapes = []
while shp.tell() < self.shpLength:
shapes.append(self.__shape())
return shapes
def iterShapes(self):
"""Serves up shapes in a shapefile as an iterator. Useful
for handling large shapefiles."""
shp = self.__getFileObj(self.shp)
shp.seek(0,2)
self.shpLength = shp.tell()
shp.seek(100)
while shp.tell() < self.shpLength:
yield self.__shape()
def __dbfHeader(self):
"""Reads a dbf header. Xbase-related code borrows heavily from ActiveState Python Cookbook Recipe 362715 by Raymond Hettinger"""
if not self.dbf:
raise ShapefileException("Shapefile Reader requires a shapefile or file-like object. (no dbf file found)")
dbf = self.dbf
# read relevant header parts
self.numRecords, self.__dbfHdrLength, self.__recordLength = \
unpack("<xxxxLHH20x", dbf.read(32))
# read fields
numFields = (self.__dbfHdrLength - 33) // 32
for field in range(numFields):
fieldDesc = list(unpack("<11sc4xBB14x", dbf.read(32)))
name = 0
idx = 0
if b("\x00") in fieldDesc[name]:
idx = fieldDesc[name].index(b("\x00"))
else:
idx = len(fieldDesc[name]) - 1
fieldDesc[name] = fieldDesc[name][:idx]
fieldDesc[name] = u(fieldDesc[name])
fieldDesc[name] = fieldDesc[name].lstrip()
fieldDesc[1] = u(fieldDesc[1])
self.fields.append(fieldDesc)
terminator = dbf.read(1)
if terminator != b("\r"):
raise ShapefileException("Shapefile dbf header lacks expected terminator. (likely corrupt?)")
self.fields.insert(0, ('DeletionFlag', 'C', 1, 0))
fmt,fmtSize = self.__recordFmt()
self.__recStruct = Struct(fmt)
def __recordFmt(self):
"""Calculates the format and size of a .dbf record."""
if self.numRecords is None:
self.__dbfHeader()
fmt = ''.join(['%ds' % fieldinfo[2] for fieldinfo in self.fields])
fmtSize = calcsize(fmt)
# total size of fields should add up to recordlength from the header
while fmtSize < self.__recordLength:
# if not, pad byte until reaches recordlength
fmt += "x"
fmtSize += 1
return (fmt, fmtSize)
def __record(self):
"""Reads and returns a dbf record row as a list of values."""
f = self.__getFileObj(self.dbf)
recordContents = self.__recStruct.unpack(f.read(self.__recStruct.size))
if recordContents[0] != b(' '):
# deleted record
return None
record = []
for (name, typ, size, deci), value in zip(self.fields, recordContents):
if name == 'DeletionFlag':
continue
elif typ in ("N","F"):
# numeric or float: number stored as a string, right justified, and padded with blanks to the width of the field.
value = value.replace(b('\0'), b('')).strip()
value = value.replace(b('*'), b('')) # QGIS NULL is all '*' chars
if value == b(''):
value = None
elif deci:
try:
value = float(value)
except ValueError:
#not parseable as float, set to None
value = None
else:
# force to int
try:
# first try to force directly to int.
# forcing a large int to float and back to int
# will lose information and result in wrong nr.
value = int(value)
except ValueError:
# forcing directly to int failed, so was probably a float.
try:
value = int(float(value))
except ValueError:
#not parseable as int, set to None
value = None
elif typ == 'D':
# date: 8 bytes - date stored as a string in the format YYYYMMDD.
if value.count(b('0')) == len(value): # QGIS NULL is all '0' chars
value = None
else:
try:
y, m, d = int(value[:4]), int(value[4:6]), int(value[6:8])
value = date(y, m, d)
except:
value = value.strip()
elif typ == 'L':
# logical: 1 byte - initialized to 0x20 (space) otherwise T or F.
if value == b(" "):
value = None # space means missing or not yet set
else:
if value in b('YyTt1'):
value = True
elif value in b('NnFf0'):
value = False
else:
value = None # unknown value is set to missing
else:
# anything else is forced to string/unicode
value = u(value)
value = value.strip()
record.append(value)
return record
def record(self, i=0):
"""Returns a specific dbf record based on the supplied index."""
f = self.__getFileObj(self.dbf)
if self.numRecords is None:
self.__dbfHeader()
i = self.__restrictIndex(i)
recSize = self.__recStruct.size
f.seek(0)
f.seek(self.__dbfHdrLength + (i * recSize))
return self.__record()
def records(self):
"""Returns all records in a dbf file."""
if self.numRecords is None:
self.__dbfHeader()
records = []
f = self.__getFileObj(self.dbf)
f.seek(self.__dbfHdrLength)
for i in range(self.numRecords):
r = self.__record()
if r:
records.append(r)
return records
def iterRecords(self):
"""Serves up records in a dbf file as an iterator.
Useful for large shapefiles or dbf files."""
if self.numRecords is None:
self.__dbfHeader()
f = self.__getFileObj(self.dbf)
f.seek(self.__dbfHdrLength)
for i in xrange(self.numRecords):
r = self.__record()
if r:
yield r
def shapeRecord(self, i=0):
"""Returns a combination geometry and attribute record for the
supplied record index."""
i = self.__restrictIndex(i)
return _ShapeRecord(shape=self.shape(i), record=self.record(i))
def shapeRecords(self):
"""Returns a list of combination geometry/attribute records for
all records in a shapefile."""
shapeRecords = []
return [_ShapeRecord(shape=rec[0], record=rec[1]) \
for rec in zip(self.shapes(), self.records())]
def iterShapeRecords(self):
"""Returns a generator of combination geometry/attribute records for
all records in a shapefile."""
for shape, record in izip(self.iterShapes(), self.iterRecords()):
yield _ShapeRecord(shape=shape, record=record)
class Writer:
"""Provides write support for ESRI Shapefiles."""
def __init__(self, shapeType=None):
self._shapes = []
self.fields = []
self.records = []
self.shapeType = shapeType
self.shp = None
self.shx = None
self.dbf = None
# Geometry record offsets and lengths for writing shx file.
self._offsets = []
self._lengths = []
# Use deletion flags in dbf? Default is false (0).
self.deletionFlag = 0
def __getFileObj(self, f):
"""Safety handler to verify file-like objects"""
if not f:
raise ShapefileException("No file-like object available.")
elif hasattr(f, "write"):
return f
else:
pth = os.path.split(f)[0]
if pth and not os.path.exists(pth):
os.makedirs(pth)
return open(f, "wb")
def __shpFileLength(self):
"""Calculates the file length of the shp file."""
# Start with header length
size = 100
# Calculate size of all shapes
for s in self._shapes:
# Add in record header and shape type fields
size += 12
# nParts and nPoints do not apply to all shapes
#if self.shapeType not in (0,1):
# nParts = len(s.parts)
# nPoints = len(s.points)
if hasattr(s,'parts'):
nParts = len(s.parts)
if hasattr(s,'points'):
nPoints = len(s.points)
# All shape types capable of having a bounding box
if self.shapeType in (3,5,8,13,15,18,23,25,28,31):
size += 32
# Shape types with parts
if self.shapeType in (3,5,13,15,23,25,31):
# Parts count
size += 4
# Parts index array
size += nParts * 4
# Shape types with points
if self.shapeType in (3,5,8,13,15,23,25,31):
# Points count
size += 4
# Points array
size += 16 * nPoints
# Calc size of part types for Multipatch (31)
if self.shapeType == 31:
size += nParts * 4
# Calc z extremes and values
if self.shapeType in (13,15,18,31):
# z extremes
size += 16
# z array
size += 8 * nPoints
# Calc m extremes and values
if self.shapeType in (15,23,25,31):
# m extremes
size += 16
# m array
size += 8 * nPoints
# Calc a single point
if self.shapeType in (1,11,21):
size += 16
# Calc a single Z value
if self.shapeType == 11:
size += 8
# Calc a single M value
if self.shapeType in (11,21):
size += 8
# Calculate size as 16-bit words
size //= 2
return size
def __bbox(self, shapes):
x = []
y = []
for s in shapes:
if len(s.points) > 0:
px, py = list(zip(*s.points))[:2]
x.extend(px)
y.extend(py)
if len(x) == 0:
return [0] * 4
return [min(x), min(y), max(x), max(y)]
def __zbox(self, shapes):
z = []
for s in shapes:
try:
for p in s.points:
z.append(p[2])
except IndexError:
pass
if not z: z.append(0)
return [min(z), max(z)]
def __mbox(self, shapes):
m = []
for s in shapes:
try:
for p in s.points:
m.append(p[3])
except IndexError:
pass
if not m: m.append(0)
return [min(m), max(m)]
def bbox(self):
"""Returns the current bounding box for the shapefile which is
the lower-left and upper-right corners. It does not contain the
elevation or measure extremes."""
return self.__bbox(self._shapes)
def zbox(self):
"""Returns the current z extremes for the shapefile."""
return self.__zbox(self._shapes)
def mbox(self):
"""Returns the current m extremes for the shapefile."""
return self.__mbox(self._shapes)
def __shapefileHeader(self, fileObj, headerType='shp'):
"""Writes the specified header type to the specified file-like object.
Several of the shapefile formats are so similar that a single generic
method to read or write them is warranted."""
f = self.__getFileObj(fileObj)
f.seek(0)
# File code, Unused bytes
f.write(pack(">6i", 9994,0,0,0,0,0))
# File length (Bytes / 2 = 16-bit words)
if headerType == 'shp':
f.write(pack(">i", self.__shpFileLength()))
elif headerType == 'shx':
f.write(pack('>i', ((100 + (len(self._shapes) * 8)) // 2)))
# Version, Shape type
f.write(pack("<2i", 1000, self.shapeType))
# The shapefile's bounding box (lower left, upper right)
if self.shapeType != 0:
try:
f.write(pack("<4d", *self.bbox()))
except error:
raise ShapefileException("Failed to write shapefile bounding box. Floats required.")
else:
f.write(pack("<4d", 0,0,0,0))
# Elevation
z = self.zbox()
# Measure
m = self.mbox()
try:
f.write(pack("<4d", z[0], z[1], m[0], m[1]))
except error:
raise ShapefileException("Failed to write shapefile elevation and measure values. Floats required.")
def __dbfHeader(self):
"""Writes the dbf header and field descriptors."""
f = self.__getFileObj(self.dbf)
f.seek(0)
version = 3
year, month, day = time.localtime()[:3]
year -= 1900
# Remove deletion flag placeholder from fields
for field in self.fields:
if str(field[0]).startswith("Deletion"):
self.fields.remove(field)
numRecs = len(self.records)
numFields = len(self.fields)
headerLength = numFields * 32 + 33
recordLength = sum([int(field[2]) for field in self.fields]) + 1
header = pack('<BBBBLHH20x', version, year, month, day, numRecs,
headerLength, recordLength)
f.write(header)
# Field descriptors
for field in self.fields:
name, fieldType, size, decimal = field
name = b(name)
name = name.replace(b(' '), b('_'))
name = name.ljust(11).replace(b(' '), b('\x00'))
fieldType = b(fieldType)
size = int(size)
fld = pack('<11sc4xBB14x', name, fieldType, size, decimal)
f.write(fld)
# Terminator
f.write(b('\r'))
def __shpRecords(self):
"""Write the shp records"""
f = self.__getFileObj(self.shp)
f.seek(100)
recNum = 1
for s in self._shapes:
self._offsets.append(f.tell())
# Record number, Content length place holder
f.write(pack(">2i", recNum, 0))
recNum += 1
start = f.tell()
# Shape Type
f.write(pack("<i", s.shapeType))
# All shape types capable of having a bounding box
if s.shapeType in (3,5,8,13,15,18,23,25,28,31):
try:
f.write(pack("<4d", *self.__bbox([s])))
except error:
raise ShapefileException("Falied to write bounding box for record %s. Expected floats." % recNum)
# Shape types with parts
if s.shapeType in (3,5,13,15,23,25,31):
# Number of parts
f.write(pack("<i", len(s.parts)))
# Shape types with multiple points per record
if s.shapeType in (3,5,8,13,15,23,25,31):
# Number of points
f.write(pack("<i", len(s.points)))
# Write part indexes
if s.shapeType in (3,5,13,15,23,25,31):
for p in s.parts:
f.write(pack("<i", p))
# Part types for Multipatch (31)
if s.shapeType == 31:
for pt in s.partTypes:
f.write(pack("<i", pt))
# Write points for multiple-point records
if s.shapeType in (3,5,8,13,15,23,25,31):
try:
[f.write(pack("<2d", *p[:2])) for p in s.points]
except error:
raise ShapefileException("Failed to write points for record %s. Expected floats." % recNum)
# Write z extremes and values
if s.shapeType in (13,15,18,31):
try:
f.write(pack("<2d", *self.__zbox([s])))
except error:
raise ShapefileException("Failed to write elevation extremes for record %s. Expected floats." % recNum)
try:
if hasattr(s,"z"):
f.write(pack("<%sd" % len(s.z), *s.z))
else:
[f.write(pack("<d", p[2])) for p in s.points]
except error:
raise ShapefileException("Failed to write elevation values for record %s. Expected floats." % recNum)
# Write m extremes and values
if s.shapeType in (13,15,18,23,25,28,31):
try:
if hasattr(s,"m") and None not in s.m:
f.write(pack("<%sd" % len(s.m), *s.m))
else:
f.write(pack("<2d", *self.__mbox([s])))
except error:
raise ShapefileException("Failed to write measure extremes for record %s. Expected floats" % recNum)
try:
[f.write(pack("<d", len(p) > 3 and p[3] or 0)) for p in s.points]
except error:
raise ShapefileException("Failed to write measure values for record %s. Expected floats" % recNum)
# Write a single point
if s.shapeType in (1,11,21):
try:
f.write(pack("<2d", s.points[0][0], s.points[0][1]))
except error:
raise ShapefileException("Failed to write point for record %s. Expected floats." % recNum)
# Write a single Z value
if s.shapeType == 11:
if hasattr(s, "z"):
try:
if not s.z:
s.z = (0,)
f.write(pack("<d", s.z[0]))
except error:
raise ShapefileException("Failed to write elevation value for record %s. Expected floats." % recNum)
else:
try:
if len(s.points[0])<3:
s.points[0].append(0)
f.write(pack("<d", s.points[0][2]))
except error:
raise ShapefileException("Failed to write elevation value for record %s. Expected floats." % recNum)
# Write a single M value
if s.shapeType in (11,21):
if hasattr(s, "m"):
try:
if not s.m:
s.m = (0,)
f.write(pack("<1d", s.m[0]))
except error:
raise ShapefileException("Failed to write measure value for record %s. Expected floats." % recNum)
else:
try:
if len(s.points[0])<4:
s.points[0].append(0)
f.write(pack("<1d", s.points[0][3]))
except error:
raise ShapefileException("Failed to write measure value for record %s. Expected floats." % recNum)
# Finalize record length as 16-bit words
finish = f.tell()
length = (finish - start) // 2
self._lengths.append(length)
# start - 4 bytes is the content length field
f.seek(start-4)
f.write(pack(">i", length))
f.seek(finish)
def __shxRecords(self):
"""Writes the shx records."""
f = self.__getFileObj(self.shx)
f.seek(100)
for i in range(len(self._shapes)):
f.write(pack(">i", self._offsets[i] // 2))
f.write(pack(">i", self._lengths[i]))
def __dbfRecords(self):
"""Writes the dbf records."""
f = self.__getFileObj(self.dbf)
for record in self.records:
if not self.fields[0][0].startswith("Deletion"):
f.write(b(' ')) # deletion flag
for (fieldName, fieldType, size, deci), value in zip(self.fields, record):
fieldType = fieldType.upper()
size = int(size)
if fieldType in ("N","F"):
# numeric or float: number stored as a string, right justified, and padded with blanks to the width of the field.
if value in MISSING:
value = str("*"*size) # QGIS NULL
elif not deci:
# force to int
try:
# first try to force directly to int.
# forcing a large int to float and back to int
# will lose information and result in wrong nr.
value = int(value)
except ValueError:
# forcing directly to int failed, so was probably a float.
value = int(float(value))
value = format(value, "d")[:size].rjust(size) # caps the size if exceeds the field size
else:
value = float(value)
value = format(value, ".%sf"%deci)[:size].rjust(size) # caps the size if exceeds the field size
elif fieldType == "D":
# date: 8 bytes - date stored as a string in the format YYYYMMDD.
if isinstance(value, date):
value = value.strftime("%Y%m%d")
elif isinstance(value, list) and len(value) == 3:
value = date(*value).strftime("%Y%m%d")
elif value in MISSING:
value = b('0') * 8 # QGIS NULL for date type
elif isinstance(value, str) and len(value) == 8:
pass # value is already a date string
else:
raise ShapefileException("Date values must be either a datetime.date object, a list, a YYYYMMDD string, or a missing value.")
elif fieldType == 'L':
# logical: 1 byte - initialized to 0x20 (space) otherwise T or F.
if value in MISSING:
value = b(' ') # missing is set to space
elif value in [True,1]:
value = b("T")
elif value in [False,0]:
value = b("F")
else:
value = b(' ') # unknown is set to space
else:
# anything else is forced to string
value = str(value)[:size].ljust(size)
if len(value) != size:
raise ShapefileException(
"Shapefile Writer unable to pack incorrect sized value"
" (size %d) into field '%s' (size %d)." % (len(value), fieldName, size))
value = b(value)
f.write(value)
def null(self):
"""Creates a null shape."""
self._shapes.append(_Shape(NULL))
def point(self, x, y, z=0, m=0, shapeType=POINT):
"""Creates a point shape."""
pointShape = _Shape(shapeType)
pointShape.points.append([x, y, z, m])
self._shapes.append(pointShape)
def line(self, parts=[], shapeType=POLYLINE):
"""Creates a line shape. This method is just a convienience method
which wraps 'poly()'.
"""
self.poly(parts, shapeType, [])
def poly(self, parts=[], shapeType=POLYGON, partTypes=[]):
"""Creates a shape that has multiple collections of points (parts)
including lines, polygons, and even multipoint shapes. If no shape type
is specified it defaults to 'polygon'. If no part types are specified
(which they normally won't be) then all parts default to the shape type.
"""
polyShape = _Shape(shapeType)
polyShape.parts = []
polyShape.points = []
# Make sure polygons are closed
if shapeType in (5,15,25,31):
for part in parts:
if part[0] != part[-1]:
part.append(part[0])
for part in parts:
polyShape.parts.append(len(polyShape.points))
for point in part:
# Ensure point is list
if not isinstance(point, list):
point = list(point)
# Make sure point has z and m values
while len(point) < 4:
point.append(0)
polyShape.points.append(point)
if polyShape.shapeType == 31:
if not partTypes:
for part in parts:
partTypes.append(polyShape.shapeType)
polyShape.partTypes = partTypes
self._shapes.append(polyShape)
def field(self, name, fieldType="C", size="50", decimal=0):
"""Adds a dbf field descriptor to the shapefile."""
if fieldType == "D":
size = "8"
decimal = 0
elif fieldType == "L":
size = "1"
decimal = 0
self.fields.append((name, fieldType, size, decimal))
def record(self, *recordList, **recordDict):
"""Creates a dbf attribute record. You can submit either a sequence of
field values or keyword arguments of field names and values. Before
adding records you must add fields for the record values using the
fields() method. If the record values exceed the number of fields the
extra ones won't be added. In the case of using keyword arguments to specify
field/value pairs only fields matching the already registered fields
will be added."""
record = []
fieldCount = len(self.fields)
# Compensate for deletion flag
if self.fields[0][0].startswith("Deletion"): fieldCount -= 1
if recordList:
record = [recordList[i] for i in range(fieldCount)]
elif recordDict:
for field in self.fields:
if field[0] in recordDict:
val = recordDict[field[0]]
if val is None:
record.append("")
else:
record.append(val)
else:
# Blank fields for empty record
record = ["" for i in range(fieldCount)]
self.records.append(record)
def shape(self, i):
return self._shapes[i]
def shapes(self):
"""Return the current list of shapes."""
return self._shapes
def saveShp(self, target):
"""Save an shp file."""
if not hasattr(target, "write"):
target = os.path.splitext(target)[0] + '.shp'
if self.shapeType is None:
# autoset file type to first non-null geometry
self.shapeType = next((s.shapeType for s in self._shapes if s.shapeType), NULL)
self.shp = self.__getFileObj(target)
self.__shapefileHeader(self.shp, headerType='shp')
self.__shpRecords()
def saveShx(self, target):
"""Save an shx file."""
if not hasattr(target, "write"):
target = os.path.splitext(target)[0] + '.shx'
if self.shapeType is None:
# autoset file type to first non-null geometry
self.shapeType = next((s.shapeType for s in self._shapes if s.shapeType != NULL), NULL)
self.shx = self.__getFileObj(target)
self.__shapefileHeader(self.shx, headerType='shx')
self.__shxRecords()
def saveDbf(self, target):
"""Save a dbf file."""
if not hasattr(target, "write"):
target = os.path.splitext(target)[0] + '.dbf'
self.dbf = self.__getFileObj(target)
self.__dbfHeader()
self.__dbfRecords()
def save(self, target=None, shp=None, shx=None, dbf=None):
"""Save the shapefile data to three files or
three file-like objects. SHP and DBF files can also
be written exclusively using saveShp, saveShx, and saveDbf respectively.
If target is specified but not shp,shx, or dbf then the target path and
file name are used. If no options or specified, a unique base file name
is generated to save the files and the base file name is returned as a
string.
"""
# Create a unique file name if one is not defined
if shp:
self.saveShp(shp)
if shx:
self.saveShx(shx)
if dbf:
self.saveDbf(dbf)
elif not shp and not shx and not dbf:
generated = False
if not target:
temp = tempfile.NamedTemporaryFile(prefix="shapefile_",dir=os.getcwd())
target = temp.name
generated = True
self.saveShp(target)
self.shp.close()
self.saveShx(target)
self.shx.close()
self.saveDbf(target)
self.dbf.close()
if generated:
return target
class Editor(Writer):
def __init__(self, shapefile=None, shapeType=POINT, autoBalance=1):
self.autoBalance = autoBalance
if not shapefile:
Writer.__init__(self, shapeType)
elif is_string(shapefile):
base = os.path.splitext(shapefile)[0]
if os.path.isfile("%s.shp" % base):
r = Reader(base)
Writer.__init__(self, r.shapeType)
self._shapes = r.shapes()
self.fields = r.fields
self.records = r.records()
def select(self, expr):
"""Select one or more shapes (to be implemented)"""
# TODO: Implement expressions to select shapes.
pass
def delete(self, shape=None, part=None, point=None):
"""Deletes the specified part of any shape by specifying a shape
number, part number, or point number."""
# shape, part, point
shape_param_exists = shape is not None
part_param_exists = part is not None
point_param_exists = point is not None
if shape_param_exists and part_param_exists and point_param_exists:
del self._shapes[shape][part][point]
# shape, part
elif shape_param_exists and part_param_exists and not point_param_exists:
del self._shapes[shape][part]
# shape
elif shape_param_exists and not part_param_exists and not point_param_exists:
del self._shapes[shape]
# point
elif not shape_param_exists and not part_param_exists and point_param_exists:
for s in self._shapes:
if s.shapeType == 1:
del self._shapes[point]
else:
for part in s.parts:
del s[part][point]
# part, point
elif not shape_param_exists and part_param_exists and point_param_exists:
for s in self._shapes:
del s[part][point]
# part
elif not shape_param_exists and part_param_exists and not point_param_exists:
for s in self._shapes:
del s[part]
def point(self, x=None, y=None, z=None, m=None, shape=None, part=None, point=None, addr=None):
"""Creates/updates a point shape. The arguments allows
you to update a specific point by shape, part, point of any
shape type."""
# shape, part, point
if shape and part and point:
try: self._shapes[shape]
except IndexError: self._shapes.append([])
try: self._shapes[shape][part]
except IndexError: self._shapes[shape].append([])
try: self._shapes[shape][part][point]
except IndexError: self._shapes[shape][part].append([])
p = self._shapes[shape][part][point]
if x: p[0] = x
if y: p[1] = y
if z: p[2] = z
if m: p[3] = m
self._shapes[shape][part][point] = p
# shape, part
elif shape and part and not point:
try: self._shapes[shape]
except IndexError: self._shapes.append([])
try: self._shapes[shape][part]
except IndexError: self._shapes[shape].append([])
points = self._shapes[shape][part]
for i in range(len(points)):
p = points[i]
if x: p[0] = x
if y: p[1] = y
if z: p[2] = z
if m: p[3] = m
self._shapes[shape][part][i] = p
# shape
elif shape and not part and not point:
try: self._shapes[shape]
except IndexError: self._shapes.append([])
# point
# part
if addr:
shape, part, point = addr
self._shapes[shape][part][point] = [x, y, z, m]
else:
Writer.point(self, x, y, z, m)
if self.autoBalance:
self.balance()
def validate(self):
"""An optional method to try and validate the shapefile
as much as possible before writing it (not implemented)."""
#TODO: Implement validation method
pass
def balance(self):
"""Adds a corresponding empty attribute or null geometry record depending
on which type of record was created to make sure all three files
are in synch."""
if len(self.records) > len(self._shapes):
self.null()
elif len(self.records) < len(self._shapes):
self.record()
def __fieldNorm(self, fieldName):
"""Normalizes a dbf field name to fit within the spec and the
expectations of certain ESRI software."""
if len(fieldName) > 11: fieldName = fieldName[:11]
fieldName = fieldName.upper()
fieldName.replace(' ', '_')
# Begin Testing
def test(**kwargs):
import doctest
doctest.NORMALIZE_WHITESPACE = 1
verbosity = kwargs.get('verbose', 0)
if verbosity == 0:
print('Running doctests...')
failure_count, test_count = doctest.testfile("README.md", verbose=verbosity)
if verbosity == 0 and failure_count == 0:
print('All test passed successfully')
return failure_count
if __name__ == "__main__":
"""
Doctests are contained in the file 'README.md'. This library was originally developed
using Python 2.3. Python 2.4 and above have some excellent improvements in the built-in
testing libraries but for now unit testing is done using what's available in
2.3.
"""
failure_count = test()
sys.exit(failure_count)
|