build.bika.lims.exportimport.instruments.agilent.masshunter.quantitative.MasshunterQuantCSVParser.parse_sequencetableline() - Code Metrics - Inspection of "fixing cobas integra instrument import interface (..." - senaite/senaite.core - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( d8e2ec...90ae0b )

by Jordi

created 2019-03-11 15:48 UTC

MasshunterQuantCSVParser.parse_sequencetableline() F

↳ Parent: build.bika.lims.exportimport.instruments.agilent.masshunter.quantitative

Complexity

Conditions

Size

Total Lines	85
Code Lines	43

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
eloc	43
dl	0
loc	85
rs	1.8
c	0
b	0
f	0
cc	17
nop	2

How to fix Long Method Complexity

Long Method

Small methods make your code easier to understand, in particular if combined with a good name. Besides, if your method is small, finding a good name is usually much easier.

For example, if you find yourself adding comments to a method's body, this is usually a good sign to extract the commented part to a new method, and use the comment as a starting point when coming up with a good name for this new method.

Commonly applied refactorings include:

If many parameters/temporary variables are present:
- Replace temporary variables with Query
- Introduce parameter object; often combined with preserve whole object
- If the above two are insufficient: Replace method with method object
If you have long conditionals: Decompose Conditional
Otherwise: Extract method

Complexity

Complex classes like build.bika.lims.exportimport.instruments.agilent.masshunter.quantitative.MasshunterQuantCSVParser.parse_sequencetableline() often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.

Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.

# -*- coding: utf-8 -*-
#
# This file is part of SENAITE.CORE
#
# Copyright 2018 by it's authors.
# Some rights reserved. See LICENSE.rst, CONTRIBUTORS.rst.

""" Agilent's 'Masshunter Quant'
"""
from DateTime import DateTime
from Products.Archetypes.event import ObjectInitializedEvent
from Products.CMFCore.utils import getToolByName
from Products.Five.browser.pagetemplatefile import ViewPageTemplateFile
from bika.lims import bikaMessageFactory as _
from bika.lims.utils import t
from bika.lims import logger
from bika.lims.browser import BrowserView
from bika.lims.idserver import renameAfterCreation
from bika.lims.utils import changeWorkflowState
from bika.lims.utils import tmpID
from cStringIO import StringIO
from datetime import datetime
from operator import itemgetter
from plone.i18n.normalizer.interfaces import IIDNormalizer
from zope.component import getUtility
import csv
import json
import plone
import zope
import zope.event
from bika.lims.exportimport.instruments.resultsimport import InstrumentCSVResultsFileParser,\
    AnalysisResultsImporter
import traceback

title = "Agilent - Masshunter Quantitative"


def Import(context, request):
    """ Read Agilent's Masshunter Quant analysis results
    """
    infile = request.form['amhq_file']
    fileformat = request.form['amhq_format']
    artoapply = request.form['amhq_artoapply']
    override = request.form['amhq_override']
    instrument = request.form.get('instrument', None)
    errors = []
    logs = []

    # Load the most suitable parser according to file extension/options/etc...
    parser = None
    if not hasattr(infile, 'filename'):
        errors.append(_("No file selected"))
    elif fileformat == 'csv':
        parser = MasshunterQuantCSVParser(infile)
    else:
        errors.append(t(_("Unrecognized file format ${fileformat}",
                          mapping={"fileformat": fileformat})))

    if parser:
        # Load the importer
        status = ['sample_received', 'attachment_due', 'to_be_verified']
        if artoapply == 'received':
            status = ['sample_received']
        elif artoapply == 'received_tobeverified':
            status = ['sample_received', 'attachment_due', 'to_be_verified']

        over = [False, False]
        if override == 'nooverride':
            over = [False, False]
        elif override == 'override':
            over = [True, False]
        elif override == 'overrideempty':
            over = [True, True]

        importer = MasshunterQuantImporter(parser=parser,
                                           context=context,
                                           allowed_ar_states=status,
                                           allowed_analysis_states=None,
                                           override=over,
                                           instrument_uid=instrument)
        tbex = ''
        try:
            importer.process()
        except:
            tbex = traceback.format_exc()
        errors = importer.errors
        logs = importer.logs
        warns = importer.warns
        if tbex:
            errors.append(tbex)

    results = {'errors': errors, 'log': logs, 'warns': warns}


    return json.dumps(results)


class MasshunterQuantCSVParser(InstrumentCSVResultsFileParser):

    HEADERKEY_BATCHINFO = 'Batch Info'
    HEADERKEY_BATCHDATAPATH = 'Batch Data Path'
    HEADERKEY_ANALYSISTIME = 'Analysis Time'
    HEADERKEY_ANALYSTNAME = 'Analyst Name'
    HEADERKEY_REPORTTIME = 'Report Time'
    HEADERKEY_REPORTERNAME = 'Reporter Name'
    HEADERKEY_LASTCALIBRATION = 'Last Calib Update'
    HEADERKEY_BATCHSTATE = 'Batch State'
    SEQUENCETABLE_KEY = 'Sequence Table'
    SEQUENCETABLE_HEADER_DATAFILE = 'Data File'
    SEQUENCETABLE_HEADER_SAMPLENAME = 'Sample Name'
    SEQUENCETABLE_PRERUN = 'prerunrespchk.d'
    SEQUENCETABLE_MIDRUN = 'mid_respchk.d'
    SEQUENCETABLE_POSTRUN = 'post_respchk.d'
    SEQUENCETABLE_NUMERICHEADERS = ('Inj Vol',)
    QUANTITATIONRESULTS_KEY = 'Quantification Results'
    QUANTITATIONRESULTS_TARGETCOMPOUND = 'Target Compound'
    QUANTITATIONRESULTS_HEADER_DATAFILE = 'Data File'
    QUANTITATIONRESULTS_PRERUN = 'prerunrespchk.d'
    QUANTITATIONRESULTS_MIDRUN = 'mid_respchk.d'
    QUANTITATIONRESULTS_POSTRUN = 'post_respchk.d'
    QUANTITATIONRESULTS_NUMERICHEADERS = ('Resp', 'ISTD Resp', 'Resp Ratio',
                                          'Final Conc', 'Exp Conc', 'Accuracy')
    QUANTITATIONRESULTS_COMPOUNDCOLUMN = 'Compound'
    COMMAS = ','

    def __init__(self, csv):
        InstrumentCSVResultsFileParser.__init__(self, csv)
        self._end_header = False
        self._end_sequencetable = False
        self._sequences = []
        self._sequencesheader = []
        self._quantitationresultsheader = []
        self._numline = 0

    def getAttachmentFileType(self):
        return "Agilent's Masshunter Quant CSV"

    def _parseline(self, line):
        if self._end_header == False:
            return self.parse_headerline(line)
        elif self._end_sequencetable == False:
            return self.parse_sequencetableline(line)
        else:
            return self.parse_quantitationesultsline(line)

    def parse_headerline(self, line):
        """ Parses header lines

            Header example:
            Batch Info,2013-03-20T07:11:09.9053262-07:00,2013-03-20T07:12:55.5280967-07:00,2013-03-20T07:11:07.1047817-07:00,,,,,,,,,,,,,,
            Batch Data Path,D:\MassHunter\Data\130129\QuantResults\130129LS.batch.bin,,,,,,,,,,,,,,,,
            Analysis Time,3/20/2013 7:11 AM,Analyst Name,Administrator,,,,,,,,,,,,,,
            Report Time,3/20/2013 7:12 AM,Reporter Name,Administrator,,,,,,,,,,,,,,
            Last Calib Update,3/20/2013 7:11 AM,Batch State,Processed,,,,,,,,,,,,,,
            ,,,,,,,,,,,,,,,,,
        """
        if self._end_header == True:
            # Header already processed
            return 0

        if line.startswith(self.SEQUENCETABLE_KEY):
            self._end_header = True
            if len(self._header) == 0:
                self.err("No header found", numline=self._numline)
                return -1
            return 0

        splitted = [token.strip() for token in line.split(',')]

        # Batch Info,2013-03-20T07:11:09.9053262-07:00,2013-03-20T07:12:55.5280967-07:00,2013-03-20T07:11:07.1047817-07:00,,,,,,,,,,,,,,
        if splitted[0] == self.HEADERKEY_BATCHINFO:
            if self.HEADERKEY_BATCHINFO in self._header:
                self.warn("Header Batch Info already found. Discarding",
                          numline=self._numline, line=line)
                return 0

            self._header[self.HEADERKEY_BATCHINFO] = []
            for i in range(len(splitted) - 1):
                if splitted[i + 1]:
                    self._header[self.HEADERKEY_BATCHINFO].append(splitted[i + 1])

        # Batch Data Path,D:\MassHunter\Data\130129\QuantResults\130129LS.batch.bin,,,,,,,,,,,,,,,,
        elif splitted[0] == self.HEADERKEY_BATCHDATAPATH:
            if self.HEADERKEY_BATCHDATAPATH in self._header:
                self.warn("Header Batch Data Path already found. Discarding",
                          numline=self._numline, line=line)
                return 0;

            if splitted[1]:
                self._header[self.HEADERKEY_BATCHDATAPATH] = splitted[1]
            else:
                self.warn("Batch Data Path not found or empty",
                          numline=self._numline, line=line)

        # Analysis Time,3/20/2013 7:11 AM,Analyst Name,Administrator,,,,,,,,,,,,,,
        elif splitted[0] == self.HEADERKEY_ANALYSISTIME:
            if splitted[1]:

                try:
                    d = datetime.strptime(splitted[1], "%m/%d/%Y %I:%M %p")
                    self._header[self.HEADERKEY_ANALYSISTIME] = d
                except ValueError:
                    self.err("Invalid Analysis Time format",
                             numline=self._numline, line=line)
            else:
                self.warn("Analysis Time not found or empty",
                          numline=self._numline, line=line)

            if splitted[2] and splitted[2] == self.HEADERKEY_ANALYSTNAME:
                if splitted[3]:
                    self._header[self.HEADERKEY_ANALYSTNAME] = splitted[3]
                else:
                    self.warn("Analyst Name not found or empty",
                              numline=self._numline, line=line)
            else:
                self.err("Analyst Name not found",
                         numline=self._numline, line=line)

        # Report Time,3/20/2013 7:12 AM,Reporter Name,Administrator,,,,,,,,,,,,,,
        elif splitted[0] == self.HEADERKEY_REPORTTIME:
            if splitted[1]:
                try:
                    d = datetime.strptime(splitted[1], "%m/%d/%Y %I:%M %p")
                    self._header[self.HEADERKEY_REPORTTIME] = d
                except ValueError:
                    self.err("Invalid Report Time format",
                         numline=self._numline, line=line)
            else:
                self.warn("Report time not found or empty",
                          numline=self._numline, line=line)


            if splitted[2] and splitted[2] == self.HEADERKEY_REPORTERNAME:
                if splitted[3]:
                    self._header[self.HEADERKEY_REPORTERNAME] = splitted[3]
                else:
                    self.warn("Reporter Name not found or empty",
                              numline=self._numline, line=line)

            else:
                self.err("Reporter Name not found",
                         numline=self._numline, line=line)


        # Last Calib Update,3/20/2013 7:11 AM,Batch State,Processed,,,,,,,,,,,,,,
        elif splitted[0] == self.HEADERKEY_LASTCALIBRATION:
            if splitted[1]:
                try:
                    d = datetime.strptime(splitted[1], "%m/%d/%Y %I:%M %p")
                    self._header[self.HEADERKEY_LASTCALIBRATION] = d
                except ValueError:
                    self.err("Invalid Last Calibration time format",
                             numline=self._numline, line=line)

            else:
                self.warn("Last Calibration time not found or empty",
                          numline=self._numline, line=line)


            if splitted[2] and splitted[2] == self.HEADERKEY_BATCHSTATE:
                if splitted[3]:
                    self._header[self.HEADERKEY_BATCHSTATE] = splitted[3]
                else:
                    self.warn("Batch state not found or empty",
                              numline=self._numline, line=line)

            else:
                self.err("Batch state not found",
                         numline=self._numline, line=line)


        return 0

    def parse_sequencetableline(self, line):
        """ Parses sequence table lines

            Sequence Table example:
            Sequence Table,,,,,,,,,,,,,,,,,
            Data File,Sample Name,Position,Inj Vol,Level,Sample Type,Acq Method File,,,,,,,,,,,
            prerunrespchk.d,prerunrespchk,Vial 3,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            DSS_Nist_L1.d,DSS_Nist_L1,P1-A2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            DSS_Nist_L2.d,DSS_Nist_L2,P1-B2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            DSS_Nist_L3.d,DSS_Nist_L3,P1-C2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            UTAK_DS_L1.d,UTAK_DS_L1,P1-D2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            UTAK_DS_L2.d,UTAK_DS_L2,P1-E2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            mid_respchk.d,mid_respchk,Vial 3,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            UTAK_DS_low.d,UTAK_DS_Low,P1-F2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            FDBS_31.d,FDBS_31,P1-G2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            FDBS_32.d,FDBS_32,P1-H2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            LS_60-r001.d,LS_60,P1-G12,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            LS_60-r002.d,LS_60,P1-G12,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            LS_61-r001.d,LS_61,P1-H12,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            LS_61-r002.d,LS_61,P1-H12,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            post_respchk.d,post_respchk,Vial 3,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            ,,,,,,,,,,,,,,,,,
        """

        # Sequence Table,,,,,,,,,,,,,,,,,
        # prerunrespchk.d,prerunrespchk,Vial 3,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
        # mid_respchk.d,mid_respchk,Vial 3,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
        # ,,,,,,,,,,,,,,,,,
        if line.startswith(self.SEQUENCETABLE_KEY) \
            or line.startswith(self.SEQUENCETABLE_PRERUN) \
            or line.startswith(self.SEQUENCETABLE_MIDRUN) \
            or self._end_sequencetable == True:

            # Nothing to do, continue
            return 0

        # Data File,Sample Name,Position,Inj Vol,Level,Sample Type,Acq Method File,,,,,,,,,,,
        if line.startswith(self.SEQUENCETABLE_HEADER_DATAFILE):
            self._sequencesheader = [token.strip() for token in line.split(',') if token.strip()]
            return 0

        # post_respchk.d,post_respchk,Vial 3,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
        # Quantitation Results,,,,,,,,,,,,,,,,,
        if line.startswith(self.SEQUENCETABLE_POSTRUN) \
            or line.startswith(self.QUANTITATIONRESULTS_KEY) \
            or line.startswith(self.COMMAS):
            self._end_sequencetable = True
            if len(self._sequences) == 0:
                self.err("No Sequence Table found", linenum=self._numline)
                return -1

            # Jumps 2 lines:
            # Data File,Sample Name,Position,Inj Vol,Level,Sample Type,Acq Method File,,,,,,,,,,,
            # prerunrespchk.d,prerunrespchk,Vial 3,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
            return 2

        # DSS_Nist_L1.d,DSS_Nist_L1,P1-A2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
        splitted = [token.strip() for token in line.split(',')]
        sequence = {}
        for colname in self._sequencesheader:
            sequence[colname] = ''

        for i in range(len(splitted)):
            token = splitted[i]
            if i < len(self._sequencesheader):
                colname = self._sequencesheader[i]
                if token and colname in self.SEQUENCETABLE_NUMERICHEADERS:
                    try:
                        sequence[colname] = float(token)
                    except ValueError:
                        self.warn(
                            "No valid number ${token} in column ${index} (${column_name})",
                            mapping={"token": token,
                                     "index": str(i + 1),
                                     "column_name": colname},
                            numline=self._numline, line=line)
                        sequence[colname] = token
                else:
                    sequence[colname] = token
            elif token:
                self.err("Orphan value in column ${index} (${token})",
                         mapping={"index": str(i+1),
                                  "token": token},
                         numline=self._numline, line=line)
        self._sequences.append(sequence)

    def parse_quantitationesultsline(self, line):
        """ Parses quantitation result lines

            Quantitation results example:
            Quantitation Results,,,,,,,,,,,,,,,,,
            Target Compound,25-OH D3+PTAD+MA,,,,,,,,,,,,,,,,
            Data File,Compound,ISTD,Resp,ISTD Resp,Resp Ratio, Final Conc,Exp Conc,Accuracy,,,,,,,,,
            prerunrespchk.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,5816,274638,0.0212,0.9145,,,,,,,,,,,
            DSS_Nist_L1.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,6103,139562,0.0437,1.6912,,,,,,,,,,,
            DSS_Nist_L2.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,11339,135726,0.0835,3.0510,,,,,,,,,,,
            DSS_Nist_L3.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,15871,141710,0.1120,4.0144,,,,,,,,,,,
            mid_respchk.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,4699,242798,0.0194,0.8514,,,,,,,,,,,
            DSS_Nist_L3-r002.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,15659,129490,0.1209,4.3157,,,,,,,,,,,
            UTAK_DS_L1-r001.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,29846,132264,0.2257,7.7965,,,,,,,,,,,
            UTAK_DS_L1-r002.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,28696,141614,0.2026,7.0387,,,,,,,,,,,
            post_respchk.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,5022,231748,0.0217,0.9315,,,,,,,,,,,
            ,,,,,,,,,,,,,,,,,
            Target Compound,25-OH D2+PTAD+MA,,,,,,,,,,,,,,,,
            Data File,Compound,ISTD,Resp,ISTD Resp,Resp Ratio, Final Conc,Exp Conc,Accuracy,,,,,,,,,
            prerunrespchk.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,6222,274638,0.0227,0.8835,,,,,,,,,,,
            DSS_Nist_L1.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,1252,139562,0.0090,0.7909,,,,,,,,,,,
            DSS_Nist_L2.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,3937,135726,0.0290,0.9265,,,,,,,,,,,
            DSS_Nist_L3.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,826,141710,0.0058,0.7697,,,,,,,,,,,
            mid_respchk.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,7864,242798,0.0324,0.9493,,,,,,,,,,,
            DSS_Nist_L3-r002.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,853,129490,0.0066,0.7748,,,,,,,,,,,
            UTAK_DS_L1-r001.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,127496,132264,0.9639,7.1558,,,,,,,,,,,
            UTAK_DS_L1-r002.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,135738,141614,0.9585,7.1201,,,,,,,,,,,
            post_respchk.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,6567,231748,0.0283,0.9219,,,,,,,,,,,
            ,,,,,,,,,,,,,,,,,
        """

        # Quantitation Results,,,,,,,,,,,,,,,,,
        # prerunrespchk.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,5816,274638,0.0212,0.9145,,,,,,,,,,,
        # mid_respchk.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,4699,242798,0.0194,0.8514,,,,,,,,,,,
        # post_respchk.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,6567,231748,0.0283,0.9219,,,,,,,,,,,
        # ,,,,,,,,,,,,,,,,,
        if line.startswith(self.QUANTITATIONRESULTS_KEY) \
            or line.startswith(self.QUANTITATIONRESULTS_PRERUN) \
            or line.startswith(self.QUANTITATIONRESULTS_MIDRUN) \
            or line.startswith(self.QUANTITATIONRESULTS_POSTRUN) \
            or line.startswith(self.COMMAS):

            # Nothing to do, continue
            return 0

        # Data File,Compound,ISTD,Resp,ISTD Resp,Resp Ratio, Final Conc,Exp Conc,Accuracy,,,,,,,,,
        if line.startswith(self.QUANTITATIONRESULTS_HEADER_DATAFILE):
            self._quantitationresultsheader = [token.strip() for token in line.split(',') if token.strip()]
            return 0

        # Target Compound,25-OH D3+PTAD+MA,,,,,,,,,,,,,,,,
        if line.startswith(self.QUANTITATIONRESULTS_TARGETCOMPOUND):
            # New set of Quantitation Results
            splitted = [token.strip() for token in line.split(',')]
            if not splitted[1]:
                self.warn("No Target Compound found",
                          numline=self._numline, line=line)
            return 0

        # DSS_Nist_L1.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,1252,139562,0.0090,0.7909,,,,,,,,,,,
        splitted = [token.strip() for token in line.split(',')]
        quantitation = {}
        for colname in self._quantitationresultsheader:
            quantitation[colname] = ''

        for i in range(len(splitted)):
            token = splitted[i]
            if i < len(self._quantitationresultsheader):

                colname = self._quantitationresultsheader[i]
                if token and colname in self.QUANTITATIONRESULTS_NUMERICHEADERS:
                    try:
                        quantitation[colname] = float(token)
                    except ValueError:
                        self.warn(
                            "No valid number ${token} in column ${index} (${column_name})",
                            mapping={"token": token,
                                     "index": str(i + 1),
                                     "column_name": colname},
                            numline=self._numline, line=line)
                        quantitation[colname] = token
                else:
                    quantitation[colname] = token
            elif token:
                self.err("Orphan value in column ${index} (${token})",
                         mapping={"index": str(i+1),
                                  "token": token},
                         numline=self._numline, line=line)

        if self.QUANTITATIONRESULTS_COMPOUNDCOLUMN in quantitation:
            compound = quantitation[self.QUANTITATIONRESULTS_COMPOUNDCOLUMN]

            # Look for sequence matches and populate rawdata
            datafile = quantitation.get(self.QUANTITATIONRESULTS_HEADER_DATAFILE, '')
            if not datafile:
                self.err("No Data File found for quantitation result",
                         numline=self._numline, line=line)

            else:
                seqs = [sequence for sequence in self._sequences \
                        if sequence.get('Data File', '') == datafile]
                if len(seqs) == 0:
                    self.err("No sample found for quantitative result ${data_file}",
                             mapping={"data_file": datafile},
                             numline=self._numline, line=line)
                elif len(seqs) > 1:
                    self.err("More than one sequence found for quantitative result: ${data_file}",
                             mapping={"data_file": datafile},
                             numline=self._numline, line=line)
                else:
                    objid = seqs[0].get(self.SEQUENCETABLE_HEADER_SAMPLENAME, '')
                    if objid:
                        quantitation['DefaultResult'] = 'Final Conc'
                        quantitation['Remarks'] = _("Autoimport")
                        rows = self.getRawResults().get(objid, [])
                        raw = rows[0] if len(rows) > 0 else {}
                        raw[compound] = quantitation
                        self._addRawResult(objid, raw, True)
                    else:
                        self.err("No valid sequence for ${data_file}",
                                 mapping={"data_file": datafile},
                                 numline=self._numline, line=line)
        else:
            self.err("Value for column '${column}' not found",
                     mapping={"column": self.QUANTITATIONRESULTS_COMPOUNDCOLUMN},
                     numline=self._numline, line=line)


class MasshunterQuantImporter(AnalysisResultsImporter):

    def __init__(self, parser, context,  override,
                 allowed_ar_states=None, allowed_analysis_states=None,
                 instrument_uid=''):
        AnalysisResultsImporter.__init__(self, parser, context, 
                                         override, allowed_ar_states,
                                         allowed_analysis_states,
                                         instrument_uid)


1		# -- coding: utf-8 --
2		#
3		# This file is part of SENAITE.CORE
4		#
5		# Copyright 2018 by it's authors.
6		# Some rights reserved. See LICENSE.rst, CONTRIBUTORS.rst.
7
8		""" Agilent's 'Masshunter Quant'
9		"""
10		from DateTime import DateTime
11		from Products.Archetypes.event import ObjectInitializedEvent
12		from Products.CMFCore.utils import getToolByName
13		from Products.Five.browser.pagetemplatefile import ViewPageTemplateFile
14		from bika.lims import bikaMessageFactory as _
15		from bika.lims.utils import t
16		from bika.lims import logger
17		from bika.lims.browser import BrowserView
18		from bika.lims.idserver import renameAfterCreation
19		from bika.lims.utils import changeWorkflowState
20		from bika.lims.utils import tmpID
21		from cStringIO import StringIO
22		from datetime import datetime
23		from operator import itemgetter
24		from plone.i18n.normalizer.interfaces import IIDNormalizer
25		from zope.component import getUtility
26		import csv
27		import json
28		import plone
29		import zope
30		import zope.event
31		from bika.lims.exportimport.instruments.resultsimport import InstrumentCSVResultsFileParser,\
32		AnalysisResultsImporter
33		import traceback
34
35		title = "Agilent - Masshunter Quantitative"
36
37
38		def Import(context, request):
39		""" Read Agilent's Masshunter Quant analysis results
40		"""
41		infile = request.form['amhq_file']
42		fileformat = request.form['amhq_format']
43		artoapply = request.form['amhq_artoapply']
44		override = request.form['amhq_override']
45		instrument = request.form.get('instrument', None)
46		errors = []
47		logs = []
48
49		# Load the most suitable parser according to file extension/options/etc...
50		parser = None
51		if not hasattr(infile, 'filename'):
52		errors.append(_("No file selected"))
53		elif fileformat == 'csv':
54		parser = MasshunterQuantCSVParser(infile)
55		else:
56		errors.append(t(_("Unrecognized file format ${fileformat}",
57		mapping={"fileformat": fileformat})))
58
59		if parser:
60		# Load the importer
61		status = ['sample_received', 'attachment_due', 'to_be_verified']
62		if artoapply == 'received':
63		status = ['sample_received']
64		elif artoapply == 'received_tobeverified':
65		status = ['sample_received', 'attachment_due', 'to_be_verified']
66
67		over = [False, False]
68		if override == 'nooverride':
69		over = [False, False]
70		elif override == 'override':
71		over = [True, False]
72		elif override == 'overrideempty':
73		over = [True, True]
74
75		importer = MasshunterQuantImporter(parser=parser,
76		context=context,
77		allowed_ar_states=status,
78		allowed_analysis_states=None,
79		override=over,
80		instrument_uid=instrument)
81		tbex = ''
82		try:
83		importer.process()
84		except:
85		tbex = traceback.format_exc()
86		errors = importer.errors
87		logs = importer.logs
88		warns = importer.warns
89		if tbex:
90		errors.append(tbex)
91
92		results = {'errors': errors, 'log': logs, 'warns': warns}
		0 ignored issues – show introduced 2018-07-25 08:58 UTC by Report Bug Copy Issue Report The variable `warns` does not seem to be defined in case `parser` on line `59` is `False`. Are you sure this can never be the case? Loading history...
93
94		return json.dumps(results)
95
96
97		class MasshunterQuantCSVParser(InstrumentCSVResultsFileParser):
98
99		HEADERKEY_BATCHINFO = 'Batch Info'
100		HEADERKEY_BATCHDATAPATH = 'Batch Data Path'
101		HEADERKEY_ANALYSISTIME = 'Analysis Time'
102		HEADERKEY_ANALYSTNAME = 'Analyst Name'
103		HEADERKEY_REPORTTIME = 'Report Time'
104		HEADERKEY_REPORTERNAME = 'Reporter Name'
105		HEADERKEY_LASTCALIBRATION = 'Last Calib Update'
106		HEADERKEY_BATCHSTATE = 'Batch State'
107		SEQUENCETABLE_KEY = 'Sequence Table'
108		SEQUENCETABLE_HEADER_DATAFILE = 'Data File'
109		SEQUENCETABLE_HEADER_SAMPLENAME = 'Sample Name'
110		SEQUENCETABLE_PRERUN = 'prerunrespchk.d'
111		SEQUENCETABLE_MIDRUN = 'mid_respchk.d'
112		SEQUENCETABLE_POSTRUN = 'post_respchk.d'
113		SEQUENCETABLE_NUMERICHEADERS = ('Inj Vol',)
114		QUANTITATIONRESULTS_KEY = 'Quantification Results'
115		QUANTITATIONRESULTS_TARGETCOMPOUND = 'Target Compound'
116		QUANTITATIONRESULTS_HEADER_DATAFILE = 'Data File'
117		QUANTITATIONRESULTS_PRERUN = 'prerunrespchk.d'
118		QUANTITATIONRESULTS_MIDRUN = 'mid_respchk.d'
119		QUANTITATIONRESULTS_POSTRUN = 'post_respchk.d'
120		QUANTITATIONRESULTS_NUMERICHEADERS = ('Resp', 'ISTD Resp', 'Resp Ratio',
121		'Final Conc', 'Exp Conc', 'Accuracy')
122		QUANTITATIONRESULTS_COMPOUNDCOLUMN = 'Compound'
123		COMMAS = ','
124
125		def __init__(self, csv):
126		InstrumentCSVResultsFileParser.__init__(self, csv)
127		self._end_header = False
128		self._end_sequencetable = False
129		self._sequences = []
130		self._sequencesheader = []
131		self._quantitationresultsheader = []
132		self._numline = 0
133
134		def getAttachmentFileType(self):
135		return "Agilent's Masshunter Quant CSV"
136
137		def _parseline(self, line):
138		if self._end_header == False:
139		return self.parse_headerline(line)
140		elif self._end_sequencetable == False:
141		return self.parse_sequencetableline(line)
142		else:
143		return self.parse_quantitationesultsline(line)
144
145		def parse_headerline(self, line):
146		""" Parses header lines
147
148		Header example:
149		Batch Info,2013-03-20T07:11:09.9053262-07:00,2013-03-20T07:12:55.5280967-07:00,2013-03-20T07:11:07.1047817-07:00,,,,,,,,,,,,,,
150		Batch Data Path,D:\MassHunter\Data\130129\QuantResults\130129LS.batch.bin,,,,,,,,,,,,,,,,
151		Analysis Time,3/20/2013 7:11 AM,Analyst Name,Administrator,,,,,,,,,,,,,,
152		Report Time,3/20/2013 7:12 AM,Reporter Name,Administrator,,,,,,,,,,,,,,
153		Last Calib Update,3/20/2013 7:11 AM,Batch State,Processed,,,,,,,,,,,,,,
154		,,,,,,,,,,,,,,,,,
155		"""
156		if self._end_header == True:
157		# Header already processed
158		return 0
159
160		if line.startswith(self.SEQUENCETABLE_KEY):
161		self._end_header = True
162		if len(self._header) == 0:
163		self.err("No header found", numline=self._numline)
164		return -1
165		return 0
166
167		splitted = [token.strip() for token in line.split(',')]
168
169		# Batch Info,2013-03-20T07:11:09.9053262-07:00,2013-03-20T07:12:55.5280967-07:00,2013-03-20T07:11:07.1047817-07:00,,,,,,,,,,,,,,
170		if splitted[0] == self.HEADERKEY_BATCHINFO:
171		if self.HEADERKEY_BATCHINFO in self._header:
172		self.warn("Header Batch Info already found. Discarding",
173		numline=self._numline, line=line)
174		return 0
175
176		self._header[self.HEADERKEY_BATCHINFO] = []
177		for i in range(len(splitted) - 1):
178		if splitted[i + 1]:
179		self._header[self.HEADERKEY_BATCHINFO].append(splitted[i + 1])
180
181		# Batch Data Path,D:\MassHunter\Data\130129\QuantResults\130129LS.batch.bin,,,,,,,,,,,,,,,,
182		elif splitted[0] == self.HEADERKEY_BATCHDATAPATH:
183		if self.HEADERKEY_BATCHDATAPATH in self._header:
184		self.warn("Header Batch Data Path already found. Discarding",
185		numline=self._numline, line=line)
186		return 0;
187
188		if splitted[1]:
189		self._header[self.HEADERKEY_BATCHDATAPATH] = splitted[1]
190		else:
191		self.warn("Batch Data Path not found or empty",
192		numline=self._numline, line=line)
193
194		# Analysis Time,3/20/2013 7:11 AM,Analyst Name,Administrator,,,,,,,,,,,,,,
195		elif splitted[0] == self.HEADERKEY_ANALYSISTIME:
196	View Code Duplication	if splitted[1]:
		0 ignored issues – show Duplication introduced 2018-01-03 21:05 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
197		try:
198		d = datetime.strptime(splitted[1], "%m/%d/%Y %I:%M %p")
199		self._header[self.HEADERKEY_ANALYSISTIME] = d
200		except ValueError:
201		self.err("Invalid Analysis Time format",
202		numline=self._numline, line=line)
203		else:
204		self.warn("Analysis Time not found or empty",
205		numline=self._numline, line=line)
206
207		if splitted[2] and splitted[2] == self.HEADERKEY_ANALYSTNAME:
208		if splitted[3]:
209		self._header[self.HEADERKEY_ANALYSTNAME] = splitted[3]
210		else:
211		self.warn("Analyst Name not found or empty",
212		numline=self._numline, line=line)
213		else:
214		self.err("Analyst Name not found",
215		numline=self._numline, line=line)
216
217		# Report Time,3/20/2013 7:12 AM,Reporter Name,Administrator,,,,,,,,,,,,,,
218		elif splitted[0] == self.HEADERKEY_REPORTTIME:
219		if splitted[1]:
220		try:
221		d = datetime.strptime(splitted[1], "%m/%d/%Y %I:%M %p")
222		self._header[self.HEADERKEY_REPORTTIME] = d
223		except ValueError:
224		self.err("Invalid Report Time format",
225		numline=self._numline, line=line)
226		else:
227		self.warn("Report time not found or empty",
228		numline=self._numline, line=line)
229
230
231		if splitted[2] and splitted[2] == self.HEADERKEY_REPORTERNAME:
232		if splitted[3]:
233		self._header[self.HEADERKEY_REPORTERNAME] = splitted[3]
234		else:
235		self.warn("Reporter Name not found or empty",
236		numline=self._numline, line=line)
237
238		else:
239		self.err("Reporter Name not found",
240		numline=self._numline, line=line)
241
242
243		# Last Calib Update,3/20/2013 7:11 AM,Batch State,Processed,,,,,,,,,,,,,,
244		elif splitted[0] == self.HEADERKEY_LASTCALIBRATION:
245		if splitted[1]:
246		try:
247		d = datetime.strptime(splitted[1], "%m/%d/%Y %I:%M %p")
248		self._header[self.HEADERKEY_LASTCALIBRATION] = d
249		except ValueError:
250		self.err("Invalid Last Calibration time format",
251		numline=self._numline, line=line)
252
253		else:
254		self.warn("Last Calibration time not found or empty",
255		numline=self._numline, line=line)
256
257
258		if splitted[2] and splitted[2] == self.HEADERKEY_BATCHSTATE:
259		if splitted[3]:
260		self._header[self.HEADERKEY_BATCHSTATE] = splitted[3]
261		else:
262		self.warn("Batch state not found or empty",
263		numline=self._numline, line=line)
264
265		else:
266		self.err("Batch state not found",
267		numline=self._numline, line=line)
268
269
270		return 0
271
272		def parse_sequencetableline(self, line):
273		""" Parses sequence table lines
274
275		Sequence Table example:
276		Sequence Table,,,,,,,,,,,,,,,,,
277		Data File,Sample Name,Position,Inj Vol,Level,Sample Type,Acq Method File,,,,,,,,,,,
278		prerunrespchk.d,prerunrespchk,Vial 3,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
279		DSS_Nist_L1.d,DSS_Nist_L1,P1-A2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
280		DSS_Nist_L2.d,DSS_Nist_L2,P1-B2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
281		DSS_Nist_L3.d,DSS_Nist_L3,P1-C2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
282		UTAK_DS_L1.d,UTAK_DS_L1,P1-D2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
283		UTAK_DS_L2.d,UTAK_DS_L2,P1-E2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
284		mid_respchk.d,mid_respchk,Vial 3,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
285		UTAK_DS_low.d,UTAK_DS_Low,P1-F2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
286		FDBS_31.d,FDBS_31,P1-G2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
287		FDBS_32.d,FDBS_32,P1-H2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
288		LS_60-r001.d,LS_60,P1-G12,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
289		LS_60-r002.d,LS_60,P1-G12,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
290		LS_61-r001.d,LS_61,P1-H12,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
291		LS_61-r002.d,LS_61,P1-H12,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
292		post_respchk.d,post_respchk,Vial 3,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
293		,,,,,,,,,,,,,,,,,
294		"""
295
296		# Sequence Table,,,,,,,,,,,,,,,,,
297		# prerunrespchk.d,prerunrespchk,Vial 3,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
298		# mid_respchk.d,mid_respchk,Vial 3,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
299		# ,,,,,,,,,,,,,,,,,
300		if line.startswith(self.SEQUENCETABLE_KEY) \
301		or line.startswith(self.SEQUENCETABLE_PRERUN) \
302		or line.startswith(self.SEQUENCETABLE_MIDRUN) \
303		or self._end_sequencetable == True:
304
305		# Nothing to do, continue
306		return 0
307
308		# Data File,Sample Name,Position,Inj Vol,Level,Sample Type,Acq Method File,,,,,,,,,,,
309		if line.startswith(self.SEQUENCETABLE_HEADER_DATAFILE):
310		self._sequencesheader = [token.strip() for token in line.split(',') if token.strip()]
311		return 0
312
313		# post_respchk.d,post_respchk,Vial 3,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
314		# Quantitation Results,,,,,,,,,,,,,,,,,
315		if line.startswith(self.SEQUENCETABLE_POSTRUN) \
316		or line.startswith(self.QUANTITATIONRESULTS_KEY) \
317		or line.startswith(self.COMMAS):
318		self._end_sequencetable = True
319		if len(self._sequences) == 0:
320		self.err("No Sequence Table found", linenum=self._numline)
321		return -1
322
323		# Jumps 2 lines:
324		# Data File,Sample Name,Position,Inj Vol,Level,Sample Type,Acq Method File,,,,,,,,,,,
325		# prerunrespchk.d,prerunrespchk,Vial 3,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
326		return 2
327
328		# DSS_Nist_L1.d,DSS_Nist_L1,P1-A2,-1.00,,Sample,120824_VitD_MAPTAD_1D_MRM_practice.m,,,,,,,,,,,
329		splitted = [token.strip() for token in line.split(',')]
330		sequence = {}
331		for colname in self._sequencesheader:
332		sequence[colname] = ''
333
334		for i in range(len(splitted)):
335		token = splitted[i]
336		if i < len(self._sequencesheader):
337		colname = self._sequencesheader[i]
338		if token and colname in self.SEQUENCETABLE_NUMERICHEADERS:
339		try:
340		sequence[colname] = float(token)
341		except ValueError:
342		self.warn(
343		"No valid number ${token} in column ${index} (${column_name})",
344		mapping={"token": token,
345		"index": str(i + 1),
346		"column_name": colname},
347		numline=self._numline, line=line)
348		sequence[colname] = token
349		else:
350		sequence[colname] = token
351		elif token:
352		self.err("Orphan value in column ${index} (${token})",
353		mapping={"index": str(i+1),
354		"token": token},
355		numline=self._numline, line=line)
356		self._sequences.append(sequence)
357
358		def parse_quantitationesultsline(self, line):
359		""" Parses quantitation result lines
360
361		Quantitation results example:
362		Quantitation Results,,,,,,,,,,,,,,,,,
363		Target Compound,25-OH D3+PTAD+MA,,,,,,,,,,,,,,,,
364		Data File,Compound,ISTD,Resp,ISTD Resp,Resp Ratio, Final Conc,Exp Conc,Accuracy,,,,,,,,,
365		prerunrespchk.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,5816,274638,0.0212,0.9145,,,,,,,,,,,
366		DSS_Nist_L1.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,6103,139562,0.0437,1.6912,,,,,,,,,,,
367		DSS_Nist_L2.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,11339,135726,0.0835,3.0510,,,,,,,,,,,
368		DSS_Nist_L3.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,15871,141710,0.1120,4.0144,,,,,,,,,,,
369		mid_respchk.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,4699,242798,0.0194,0.8514,,,,,,,,,,,
370		DSS_Nist_L3-r002.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,15659,129490,0.1209,4.3157,,,,,,,,,,,
371		UTAK_DS_L1-r001.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,29846,132264,0.2257,7.7965,,,,,,,,,,,
372		UTAK_DS_L1-r002.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,28696,141614,0.2026,7.0387,,,,,,,,,,,
373		post_respchk.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,5022,231748,0.0217,0.9315,,,,,,,,,,,
374		,,,,,,,,,,,,,,,,,
375		Target Compound,25-OH D2+PTAD+MA,,,,,,,,,,,,,,,,
376		Data File,Compound,ISTD,Resp,ISTD Resp,Resp Ratio, Final Conc,Exp Conc,Accuracy,,,,,,,,,
377		prerunrespchk.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,6222,274638,0.0227,0.8835,,,,,,,,,,,
378		DSS_Nist_L1.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,1252,139562,0.0090,0.7909,,,,,,,,,,,
379		DSS_Nist_L2.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,3937,135726,0.0290,0.9265,,,,,,,,,,,
380		DSS_Nist_L3.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,826,141710,0.0058,0.7697,,,,,,,,,,,
381		mid_respchk.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,7864,242798,0.0324,0.9493,,,,,,,,,,,
382		DSS_Nist_L3-r002.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,853,129490,0.0066,0.7748,,,,,,,,,,,
383		UTAK_DS_L1-r001.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,127496,132264,0.9639,7.1558,,,,,,,,,,,
384		UTAK_DS_L1-r002.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,135738,141614,0.9585,7.1201,,,,,,,,,,,
385		post_respchk.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,6567,231748,0.0283,0.9219,,,,,,,,,,,
386		,,,,,,,,,,,,,,,,,
387		"""
388
389		# Quantitation Results,,,,,,,,,,,,,,,,,
390		# prerunrespchk.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,5816,274638,0.0212,0.9145,,,,,,,,,,,
391		# mid_respchk.d,25-OH D3+PTAD+MA,25-OH D3d3+PTAD+MA,4699,242798,0.0194,0.8514,,,,,,,,,,,
392		# post_respchk.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,6567,231748,0.0283,0.9219,,,,,,,,,,,
393		# ,,,,,,,,,,,,,,,,,
394		if line.startswith(self.QUANTITATIONRESULTS_KEY) \
395		or line.startswith(self.QUANTITATIONRESULTS_PRERUN) \
396		or line.startswith(self.QUANTITATIONRESULTS_MIDRUN) \
397		or line.startswith(self.QUANTITATIONRESULTS_POSTRUN) \
398		or line.startswith(self.COMMAS):
399
400		# Nothing to do, continue
401		return 0
402
403		# Data File,Compound,ISTD,Resp,ISTD Resp,Resp Ratio, Final Conc,Exp Conc,Accuracy,,,,,,,,,
404		if line.startswith(self.QUANTITATIONRESULTS_HEADER_DATAFILE):
405		self._quantitationresultsheader = [token.strip() for token in line.split(',') if token.strip()]
406		return 0
407
408		# Target Compound,25-OH D3+PTAD+MA,,,,,,,,,,,,,,,,
409		if line.startswith(self.QUANTITATIONRESULTS_TARGETCOMPOUND):
410		# New set of Quantitation Results
411		splitted = [token.strip() for token in line.split(',')]
412		if not splitted[1]:
413		self.warn("No Target Compound found",
414		numline=self._numline, line=line)
415		return 0
416
417		# DSS_Nist_L1.d,25-OH D2+PTAD+MA,25-OH D3d3+PTAD+MA,1252,139562,0.0090,0.7909,,,,,,,,,,,
418		splitted = [token.strip() for token in line.split(',')]
419		quantitation = {}
420		for colname in self._quantitationresultsheader:
421		quantitation[colname] = ''
422
423		for i in range(len(splitted)):
424		token = splitted[i]
425	View Code Duplication	if i < len(self._quantitationresultsheader):
		0 ignored issues – show Duplication introduced 2018-01-03 21:05 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
426		colname = self._quantitationresultsheader[i]
427		if token and colname in self.QUANTITATIONRESULTS_NUMERICHEADERS:
428		try:
429		quantitation[colname] = float(token)
430		except ValueError:
431		self.warn(
432		"No valid number ${token} in column ${index} (${column_name})",
433		mapping={"token": token,
434		"index": str(i + 1),
435		"column_name": colname},
436		numline=self._numline, line=line)
437		quantitation[colname] = token
438		else:
439		quantitation[colname] = token
440		elif token:
441		self.err("Orphan value in column ${index} (${token})",
442		mapping={"index": str(i+1),
443		"token": token},
444		numline=self._numline, line=line)
445
446		if self.QUANTITATIONRESULTS_COMPOUNDCOLUMN in quantitation:
447		compound = quantitation[self.QUANTITATIONRESULTS_COMPOUNDCOLUMN]
448
449		# Look for sequence matches and populate rawdata
450		datafile = quantitation.get(self.QUANTITATIONRESULTS_HEADER_DATAFILE, '')
451		if not datafile:
452		self.err("No Data File found for quantitation result",
453		numline=self._numline, line=line)
454
455		else:
456		seqs = [sequence for sequence in self._sequences \
457		if sequence.get('Data File', '') == datafile]
458		if len(seqs) == 0:
459		self.err("No sample found for quantitative result ${data_file}",
460		mapping={"data_file": datafile},
461		numline=self._numline, line=line)
462		elif len(seqs) > 1:
463		self.err("More than one sequence found for quantitative result: ${data_file}",
464		mapping={"data_file": datafile},
465		numline=self._numline, line=line)
466		else:
467		objid = seqs[0].get(self.SEQUENCETABLE_HEADER_SAMPLENAME, '')
468		if objid:
469		quantitation['DefaultResult'] = 'Final Conc'
470		quantitation['Remarks'] = _("Autoimport")
471		rows = self.getRawResults().get(objid, [])
472		raw = rows[0] if len(rows) > 0 else {}
473		raw[compound] = quantitation
474		self._addRawResult(objid, raw, True)
475		else:
476		self.err("No valid sequence for ${data_file}",
477		mapping={"data_file": datafile},
478		numline=self._numline, line=line)
479		else:
480		self.err("Value for column '${column}' not found",
481		mapping={"column": self.QUANTITATIONRESULTS_COMPOUNDCOLUMN},
482		numline=self._numline, line=line)
483
484
485		class MasshunterQuantImporter(AnalysisResultsImporter):
486
487		def __init__(self, parser, context, override,
488		allowed_ar_states=None, allowed_analysis_states=None,
489		instrument_uid=''):
490		AnalysisResultsImporter.__init__(self, parser, context,
491		override, allowed_ar_states,
492		allowed_analysis_states,
493		instrument_uid)
494

senaite / senaite.core

Push — master ( d8e2ec...90ae0b )

MasshunterQuantCSVParser.parse_sequencetableline() F

Complexity

Size

Duplication

Importance

How to fix Long Method Complexity

Long Method

Complexity

Duplication Side-by-Side

Filter issues like