/usr/lib/python2.7/dist-packages/pymol/headering.py is in pymol 1.8.4.0+dfsg-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 | from __future__ import print_function
import os
import re
import sys
import struct
import pymol
import math
from .xray import space_group_map
if sys.byteorder == "big":
MACH_ARCH_CODE_INT = 1
MACH_ARCH_CODE_FLT = 1
else:
MACH_ARCH_CODE_INT = 4
MACH_ARCH_CODE_FLT = 4
class baseHeader:
"""
A simple base class used to parse biological data headers
"""
def __init__(self,filename):
self.filename = filename
self.cols = []
self.byteorder_int = None
self.byteorder_flt = None
self.wordsize = None
def parseFile(self):
pass
def getColumns(self):
return self.cols
def getColumnsOfType(self,targetType):
pass
def checkFile(self):
return os.path.isfile(self.filename)
def guessCols(self,mapType):
fC = self.getColumnsOfType("F")
pC = self.getColumnsOfType("P")
looksLike, FCol, PCol = [None]*3
for prg in ("refmac", "phenix", "phenix_no_fill", "buster"):
#
# default (refmac,phenix,phenix_no_fill,buster) names are in the format:
# "2FoFc-amplitude 2FoFc-phase FoFc-ampl FoFc-phase"
#
defaultNames = pymol.cmd.get_setting_text("default_%s_names" % (prg))
if len(defaultNames):
defaultNames = defaultNames.split()
if len(defaultNames):
if mapType.lower() == "2fofc":
defaultF, defaultP = defaultNames[0], defaultNames[1]
elif mapType.lower() == "fofc":
defaultF, defaultP = defaultNames[2], defaultNames[3]
else:
print("Error: Please provide the setting 'default_%s_names' a comma separated string" % (prg))
print(" with the values for 2FoFc and FoFc, amplitude and phase names, respectively.")
return [None]*3
else:
print("Error: Please provide the setting 'default_%s_names' a comma separated string" % (prg))
print(" with the values for 2FoFc and FoFc, amplitude and phase names, respectively.")
return [None]*3
# defaultF =~ "FWT", "2FOFCFWT", "2FOFCWT_no_fill", "2FOFCWT", "DELFWT", "FOFCWT", ..
for curFCol in fC:
if curFCol.endswith(defaultF):
# found F, now look for matching P
pfx = curFCol.rstrip(defaultF)
curPCol = pfx+defaultP
## print "curFCol = %s" % curFCol
## print "curPCol = %s" % curPCol
if curPCol in pC:
# found perfectly matching columns
looksLike = prg
FCol = curFCol
PCol = curPCol
return (FCol, PCol, looksLike)
return [None]*3
class CNSHeader(baseHeader):
"""
CNS format
"""
def __init__(self,filename):
## print "CNSHeader cstr"
baseHeader.__init__(self,filename)
self.parseFile()
class CIFHeader(baseHeader):
"""
mmCIF
"""
def __init__(self,filename):
baseHeader.__init__(self,filename)
self.parseFile()
def parseFile(self):
if self.checkFile():
try:
inFile = open(self.filename,'rb')
data = inFile.readlines()
inFile.close()
in_loop = False
curLine = data.pop(0)
while curLine!=None:
if in_loop:
if curLine.startswith("_refln."):
self.cols.append(curLine.split(".",1)[1].strip())
else:
in_loop=False
else:
if curLine.startswith("loop_"):
in_loop=True
if len(data):
curLine = data.pop(0)
else:
curLine = None
except IOError as e:
print("Error-CIFReader: Couldn't read '%s' for input." % (self.filename))
class MTZHeader(baseHeader):
HEADER_KEYWORDS = {
"VERS" : "VERS",
"TITLE" : "TITLE",
"NCOL" : "NCOL",
"CELL" : "CELL",
"SORT" : "SORT",
"SYMINF" : "SYMINF",
"SYMM" : "SYMM",
"RESO" : "RESO",
"VALM" : "VALM",
"NDIF" : "NDIF",
"COL" : "COL",
"PROJECT" : "PROJECT",
"CRYSTAL" : "CRYSTAL",
"DATASET" : "DATASET",
"DCELL" : "DCELL",
"DWAVEL" : "DWAVEL",
"BATCH" : "BATCH",
}
"""
MTZ/CCP4
"""
def __init__(self,filename):
baseHeader.__init__(self,filename)
self.version = None
self.title = None
self.ncol = None
self.nrefl = None
self.nbatches = None
self.cell = None
self.sort = None
self.syminf = None
self.symm = []
self.reso_min = None
self.reso_max = None
self.valm = None
self.ndif = None
self.col = None
self.project = None
self.crystal = None
self.dataset = None
self.dcell = None
self.dwavel = None
self.batch = None
self.datasets = {}
self.parseFile()
self.format_cols()
def format_cols(self,colType=None):
"""
updates self.cols to a list of cols of a
given MTZ type
"""
self.cols = []
# UNIQUE:
# crystal_name/dataset_name/col_label"
s = "/"
c = []
for key in self.datasets:
c=[]
## print "KEY = %s" % key
# user wants all columns
if colType==None:
c = list(self.datasets[key]["cols"].keys())
else:
# user wants a specfic column
for tmpCol in self.datasets[key]["cols"].keys():
if self.datasets[key]["cols"][tmpCol]["type"]==colType:
c.append(tmpCol)
## print "Columns of type %s are: " % colType
## print c
## print "Now formatting...."
if "crystal" in self.datasets[key]:
curCryst = [ self.datasets[key]["crystal"] ] * len(c)
else:
curCryst = "nameless_crystal" * len(c)
## print "CurCrystal is: %s." % curCryst
datName = [ self.datasets[key]["name"] ] * len(c)
self.cols.extend(
["/".join(x) for x in zip(curCryst,datName,c)])
def getColumns(self):
self.format_cols()
return baseHeader.getColumns(self)
def getColumnsOfType(self,colType):
self.format_cols(colType)
return baseHeader.getColumns(self)
def get_byteorder(self):
f = open(self.filename, 'rb')
f.seek(8)
d = struct.unpack("BBBB",f.read(4))
f.close()
return (d[1]>>4) & 0x0f, (d[0]>>4) & 0x0f
def authorStamp(self,f):
# seek the machine stamp
f.seek(8,0)
# read machine stamp
(B0,B1,B2,B3) = struct.unpack("BBBB", f.read(4))
# determines big or little endian:
# double, float, int, char
d = (B0 & 0xF0) >> 4
f = (B0 & 0x0F)
i = (B1 & 0xF0) >> 4
c = (B1 & 0x0F)
if d==1:
# big endian
self.byteorder_flt = ">"
elif d==4:
# little endian
self.byteorder_flt = "<"
if i==1:
# big
self.byteorder_int = ">"
self.wordsize = 1
elif i==4:
self.byteorder_int = "<"
self.wordsize = 4
def parseFile(self):
import shlex
if self.checkFile():
f = open(self.filename,'rb')
# sets authoring machine's details
self.authorStamp(f)
# get file size
f.seek(0,2)
file_len = f.tell()
# get header offset
f.seek(4)
if self.wordsize!=None:
(header_start,) = struct.unpack(self.byteorder_int+"i", f.read(4))
else:
print("Warning: Byte order of file unknown. Guessing header location.")
(header_start,) = struct.unpack("i", f.read(4))
# bAdjust is the byte adjustment to compensate for
# older machines with smaller atomic sizes
host_word_size = len(struct.pack('i',0))
author_word_size = self.wordsize
if host_word_size<author_word_size:
bAdjust = author_word_size / host_word_size
elif host_word_size>author_word_size:
bAdjust = author_word_size * host_word_size
else:
bAdjust = host_word_size
header_start = (header_start-1) * (bAdjust)
if file_len<header_start:
print("Error: File '%s' cannot be parsed because PyMOL cannot find the header. If you think")
print(" PyMOL should be able to read this, plese send the file and this mesage to ")
print(" help@schrodinger.com. Thanks!")
f.seek(header_start)
curLine = struct.unpack("80s", f.read(80))[0]
curLine = str(curLine.decode())
while not (curLine.startswith("END")):
# yank field identifier
(field, tokens) = curLine.split(" ",1)
H = MTZHeader.HEADER_KEYWORDS
try:
if field.startswith(H["VERS"]):
self.version = tokens
elif field.startswith(H["TITLE"]):
self.title = tokens
elif field.startswith(H["NCOL"]):
(self.ncols, self.nrefl, self.nbatches) = tokens.split()
elif field.startswith(H["CELL"]):
tokens = tokens.split()
self.cell_dim = tokens[:3]
self.cell_angles = tokens[3:]
elif field.startswith(H["SORT"]):
self.sort = tokens.split()
elif field.startswith(H["SYMINF"]):
tokens = shlex.split(tokens)
self.nsymmop = tokens[0]
self.nprimop = tokens[1]
self.lattice = tokens[2]
self.groupnum = tokens[3]
self.space_group = tokens[4]
self.pt_group = tokens[5]
# valid format for MTZ space group?
self.space_group = space_group_map.get(self.space_group, self.space_group)
elif field.startswith(H["SYMM"]):
tokens = tokens.split()
tokens = [x.strip(",").strip() for x in tokens]
self.symm.append(tokens)
elif field.startswith(H["RESO"]):
self.reso_min, self.reso_max = tokens.split()
self.reso_min = math.sqrt(1./float(self.reso_min))
self.reso_max = math.sqrt(1./float(self.reso_max))
elif field.startswith(H["VALM"]):
self.missing_flag = tokens
elif field.startswith(H["COL"]):
if field == "COLSRC":
raise pymol.cmd.QuietException
(lab,typ,m,M,i) = tokens.split()
if i not in self.datasets:
self.datasets[i] = {}
self.datasets[i]["cols"] = {}
self.datasets[i]["cols"][lab] = {}
self.datasets[i]["cols"][lab]["type"] = typ
self.datasets[i]["cols"][lab]["min"] = m
self.datasets[i]["cols"][lab]["max"] = M
self.datasets[i]["cols"][lab]["id"] = i
elif field.startswith(H["NDIF"]):
self.ndif = int(tokens)
elif field.startswith(H["PROJECT"]):
(i,proj) = tokens.split(None, 1)
if i not in self.datasets:
self.datasets[i] = {}
self.datasets[i]["project"] = proj.strip()
elif field.startswith(H["CRYSTAL"]):
# can have multiple crystals per dataset?
# if, so not supported (overwritten) here.
(i,cryst) = tokens.split(None, 1)
if i not in self.datasets:
self.datasets[i] = {}
self.datasets[i]["crystal"] = cryst.strip()
elif field.startswith(H["DATASET"]):
(i,d) = tokens.split(None, 1)
if i not in self.datasets:
self.datasets[i] = {}
self.datasets[i]["name"] = d.strip()
elif field.startswith(H["DCELL"]):
(i,x,y,z,a,b,g) = tokens.split()
if i not in self.datasets:
self.datasets[i] = {}
self.datasets[i]['x'] = x
self.datasets[i]['y'] = y
self.datasets[i]['z'] = z
self.datasets[i]['alpha'] = a
self.datasets[i]['beta'] = b
self.datasets[i]['gamma'] = g
elif field.startswith(H["DWAVEL"]):
(i,wl) = tokens.split()
if i not in self.datasets:
self.datasets[i] = {}
self.datasets[i]["wavelength"] = wl
elif field.startswith(H["BATCH"]):
self.batch = tokens
else:
print("Error Parsing MTZ Header: bad column name: '%s'" % field)
except ValueError:
print("Error: Parsing MTZ Header poorly formatted MTZ file")
print(" bad field: '%s'" % field)
except pymol.cmd.QuietException:
pass
curLine = struct.unpack("80s", f.read(80))[0]
curLine = str(curLine.decode())
if __name__=="__main__":
c = CIFHeader("test.cif")
print(c.getColumns())
m = MTZHeader("test.mtz")
print(m.getColumns())
|