File: ArtaxFileParser.py

package info (click to toggle)
pymca 5.6.3%2Bdfsg-1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 46,584 kB
  • sloc: python: 164,135; ansic: 20,050; sh: 175; makefile: 142; xml: 55
file content (349 lines) | stat: -rw-r--r-- 11,951 bytes parent folder | download
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
#!/usr/bin/env python
#/*##########################################################################
#
# The PyMca X-Ray Fluorescence Toolkit
#
# Copyright (c) 2020 European Synchrotron Radiation Facility
#
# This file is part of the PyMca X-ray Fluorescence Toolkit developed at
# the ESRF by the Software group.
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE.
#
#############################################################################*/
__author__ = "V.A. Sole - ESRF Data Analysis"
__contact__ = "sole@esrf.fr"
__license__ = "MIT"
__copyright__ = "European Synchrotron Radiation Facility, Grenoble, France"
import sys
import os
import numpy
import types
import logging

_logger = logging.getLogger(__name__)

#spx and rtx file formats based on XML
import xml.etree.ElementTree as ElementTree
from PyMca5.PyMcaIO import SpecFileAbstractClass

def myFloat(x):
    try:
        return float(x)
    except ValueError:
        if ',' in x:
            try:
                return float(x.replace(',','.'))
            except:
                return float(x)
        elif '.' in x:
            try:
                return float(x.replace('.',','))
            except:
                return float(x)
        else:
            raise

class ArtaxFileParser(object):
    '''
    Class to read ARTAX .spx or .rtx files
    '''
    def __init__(self, filename):
        '''
        Parameters:
        -----------
        filename : str
            Name of the .spx or .rtx file.
        '''

        if not os.path.exists(filename):
            raise IOError("File %s does not exists"  % filename)

        if not isArtaxFile(filename):
            raise IOError("This does not look as an Artax file")

        f = ElementTree.parse(filename)
        root = f.getroot()
        self._classDict = {}
        for classType in [#'TRTProject',
                          #'TRTBase',
                          #'TScanInfo',
                          #'TRTImageData',
                          'TRTSpectrum']:
            content = root.findall(".//ClassInstance[@Type='%s']" % classType)
            self._classDict[classType] = content

        self.__artaxTScanInfo = self.__getArtaxTScanInfo(root)

        self._cacheScan = None
        self._file = os.path.abspath(filename)
        if self.scanno():
            self._cacheScan = ArtaxScan(self._classDict["TRTSpectrum"][0], 0, self._file)
            self._lastScan = 0

    @property
    def artaxTScanInfo(self):
        return self.__artaxTScanInfo

    def __getArtaxTScanInfo(self, root):
        # obtain some Artax Map specific information
        node = root.find(".//ClassInstance[@Type='TScanInfo']")
        scanInfoKeys = ["XFirst",
                        "YFirst",
                        "ZFirst",
                        "XLast",
                        "YLast",
                        "ZLast",
                        "MeasNo", # number of spectra
                        "Mapping"]
        scanInfo = {}
        if node:
            for child in node:
                if child.tag in scanInfoKeys:
                    key = child.tag
                    if key == "Mapping":
                        if child.text.upper() == "TRUE":
                            scanInfo[key] = True
                        else:
                            scanInfo[key] = False
                    else:
                        scanInfo[key] = myFloat(child.text)

        for key in scanInfoKeys:
            if key in scanInfo:
                continue
            if key == "Mapping":
                scanInfo[key] = False
            else:
                scanInfo[key] = numpy.nan
        # done with the Artax map specific information
        return scanInfo
        
    def scanno(self):
        return len(self._classDict["TRTSpectrum"])

    def __getitem__(self, item):
        if item == self._lastScan and self._cacheScan:
            scan = self._cacheScan
        else:
            scan = ArtaxScan(self._classDict["TRTSpectrum"][item], item, self._file)
            self._lastScan = item
            self._cacheScan = scan
        return scan

    def list(self):
        return "1:%d" % self.scanno()

    def select(self, key):
        """
        key is of the from s.o
        scan number, scan order
        """
        n = key.split(".")
        return self.__getitem__(int(n[0])-1)

    def allmotors(self):
        if self.scanno():
            return self._cacheScan._motorNames * 1
        else:
            return []

class ArtaxScan(object):
    def __init__(self, spectrumNode, number, filename):
        self._node = spectrumNode
        self._number = number
        self.__data = None
        command = ""
        if "Name" in spectrumNode.keys():
            command = "%s" % self._node.attrib["Name"]
        else:
            command = "TRTSpectrum %d" % number

        # we expect only one spectrum (if not we would use findall)
        self._spectra = [self._node.find(".//Channels")]

        # get the position(s) at which the spectrum was collected
        self._motorNames = []
        self._motorValues = []
        keyToSearch = ".//ClassInstance[@Type='TRTAxesHeader']//AxesParameter"
        positionsNode = self._node.find(keyToSearch)
        if positionsNode:
            for child in positionsNode:
                if "AxisName" in child.attrib:
                    motorName = child.attrib["AxisName"]
                    if "AxisPosition" in child.attrib:
                        motorValue = myFloat(child.attrib["AxisPosition"])
                        self._motorNames.append(motorName)
                        self._motorValues.append(motorValue)
        elif "PDHID" in command and "(X " in command and " Y " in command:
            # Aaron's approximation to Artax files
            # we should not crash because of it
            try:
                import re
                expr = r"(?:[XY] \d+(?:[.]\d*)?|[.]\d+)"
                XY = re.findall(expr, command)
                if len(XY) == 2:
                    X, Y = XY
                    self._motorNames = ["x", "y"]
                    self._motorValues = [myFloat(X.split(" ")[-1]),
                                         myFloat(Y.split(" ")[-1])]
            except:
                _logger.warning("Could not extract positions from %s" % command)

        # get the additional information
        info = {}
        infoKeys = ['HighVoltage', 'TubeCurrent',
                    'RealTime', 'LifeTime', 'DeadTime',
                    'ZeroPeakPosition', 'ZeroPeakFrequency', 'PulseDensity',
                    'Amplification', 'ShapingTime',
                    'Date','Time',
                    'ChannelCount','CalibAbs', 'CalibLin']
        classTypeList = ['TRTSpectrumHeader',
                         'TRTGeneratorHeader',
                         'TRTSpectrumHardwareHeader']
        for classType in classTypeList:
            nodeToSearch = ".//ClassInstance[@Type='%s']" % classType
            target = self._node.find(nodeToSearch)
            if target is None:
                _logger.debug("Unused class <%s>" % classType)
                continue
            for child in target:
                if child.tag in ["Date", "Time"]:
                    info[child.tag] = child.text
                elif child.tag in infoKeys:
                    info[child.tag] = myFloat(child.text)

        for key in infoKeys:
            if key not in info:
                _logger.debug("key not found %s" % key)

        self._command = command
        scanheader = []
        scanheader.append("#S %d %s" % (self._number + 1, self.command()))
        i = 0
        for key in infoKeys:
            scanheader.append("#U%d %s %s" % (i, key, info.get(key, "Unknown")))
            i += 1
        liveTime = info.get('LifeTime', None)
        realTime = info.get('RealTime', liveTime)
        if liveTime is not None:
            scanheader.append("#@CTIME %f %f %f" % (myFloat(realTime)/1000.,
                                                    myFloat(liveTime)/1000.,
                                                    myFloat(realTime)/1000.))

        scanheader.append("#@CALIB %f %f 0" % (myFloat(info.get('CalibAbs', 0.0)),
                                               myFloat(info.get('CalibLin', 1.0))))
        self._scanHeader = scanheader

        self._fileHeader = ["#F %s" % filename]
        if len(self._motorNames):
            spacing = " " * 4
            motorsLine = "#O0%s" % spacing
            for mne in self._motorNames:
                motorsLine += "%s%s" % (spacing, mne)
            self._fileHeader.append(motorsLine)

    def _readSpectrum(self, channelsNode):
        if self.__data is None:
            self.__data = numpy.array([myFloat(x) for x in channelsNode.text.split(',')],
                                      dtype=numpy.float32)
        return self.__data

    def nbmca(self):
        return len(self._spectra)

    def mca(self, number):
        return self._readSpectrum(self._spectra[number - 1])

    def alllabels(self):
        return []

    def allmotorpos(self):
        return self._motorValues

    def command(self):
        return self._command

    def date(self):
        return self._data["TimeStamp"][self._number]

    def fileheader(self):
        return self._fileHeader

    def header(self, key):
        _logger.debug("Requested key = %s", key)
        _logger.debug("Requested key = %s", key)
        if key in ['S', '#S']:
            return self.fileheader()[0]
        elif key == 'N':
            return []
        elif key == 'L':
            return []
        elif key in ['D', '@CTIME', '@CALIB', '@CHANN']:
            for item in self._scanHeader:
                if item.startswith("#" + key):
                    return [item]
            return []
        elif key == "" or key == " ":
            return self._scanHeader
        else:
            return []

    def order(self):
        return 1

    def number(self):
        return self._number + 1

    def lines(self):
        return 0

def isArtaxFile(filename):
    try:
        if filename[-3:].lower() not in ["rtx", "spx"]:
            return False
        with open(filename, 'rb') as f:
            # expected to read an xml file
            someChar = f.read(20).decode()
        if "xml version" in someChar:
            return True
    except:
        pass
    return False

def test(filename):
    if isArtaxFile(filename):
        sf=ArtaxFileParser(filename)
    else:
        print("Not an Artax .spx or .rtx File")
        return
    sf = ArtaxFileParser(filename)
    print(sf[0].nbmca())
    print(sf[0].mca(1))
    print(sf[0].header('S'))
    #print(sf[0].header('D'))
    #print(sf[0].alllabels())
    print(sf.allmotors())
    print(sf[0].allmotorpos())
    print(sf[0].header('@CTIME'))
    print(sf[0].header('@CALIB'))
    print(sf[0].header(''))

if __name__ == "__main__":
    test(sys.argv[1])