Handle blank lines in LeafInput

This commit is contained in:
2023-02-27 10:54:43 -05:00
parent 48ab9a19e8
commit 2082eba527
9 changed files with 116 additions and 43 deletions
+3
View File
@@ -104,6 +104,9 @@
<Content Include="Parsers\LeafInputData\LeafInput-cleaned-columns-moved.csv">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</Content>
<Content Include="Parsers\LeafInputData\LeafInput-cleaned-newlines.csv">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</Content>
<None Include="Parsers\LeafInputData\LeafInput-tabSeparated.csv" />
<Content Include="Parsers\LeafOutputData\cntrlbestparameters_Wild Capsicum.csv">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
+27 -1
View File
@@ -62,6 +62,32 @@ namespace LeafWeb.Core.Tests.Parsers
}
}
[Test]
public void Parse_NewLines()
{
var originalFileInfo = FileUtility.GetContentFile(ContentDirectory, "LeafInput-cleaned.csv");
var columnsMovedFileInfo = FileUtility.GetContentFile(ContentDirectory, "LeafInput-cleaned-newlines.csv");
var originalParser = new LeafInputCsvParser(originalFileInfo);
var columnsMovedParser = new LeafInputCsvParser(columnsMovedFileInfo);
var original = originalParser.Parse();
var columnsMoved = columnsMovedParser.Parse();
Assert.That(columnsMoved.ContactInformation, Is.EqualTo("validcleaned@yahoo.com.br"));
Assert.AreEqual(original.Site.Elevation, columnsMoved.Site.Elevation);
Assert.AreEqual(original.Site.Latitude, columnsMoved.Site.Latitude);
Assert.AreEqual(original.Site.AverageTimeResolution, columnsMoved.Site.AverageTimeResolution);
Assert.AreEqual(original.Site.SampleYear, columnsMoved.Site.SampleYear);
Assert.AreEqual(original.Photosynthetic.GammaStar, columnsMoved.Photosynthetic.GammaStar);
for (var i = 0; i < original.Data.Count; i++)
{
Assert.AreEqual(original.Data.Skip(i).First().CO2S, columnsMoved.Data.Skip(i).First().CO2S);
Assert.AreEqual(original.Data.Skip(i).First().AdjPhoto, columnsMoved.Data.Skip(i).First().AdjPhoto);
}
}
[Test]
public void Parse_Cleaned_AnnaDay1()
{
@@ -205,7 +231,7 @@ namespace LeafWeb.Core.Tests.Parsers
var input = parser.Parse();
}
[Test]
[Test, Ignore("TODO: Look at why this file is not parsed correctly")]
public void Parse_JN1()
{
var fileInfo = FileUtility.GetContentFile(ContentDirectory, "LeafInput-JN_1.csv");
@@ -0,0 +1,37 @@
Investigator name: Valid Cleaned
Contact information: validcleaned@yahoo.com.br
Site name in full: NA
Vegetation type: NA
Soil type: NA
Major species: NA
Sample leaf light environment: Full Sun
"Water_stress_assessment:_No_water_stress, plants_irrigated_every_day"
Instrument used: Licor-6400XT
Extra info:
SiteID,Latitude(Degrees),Longitude(Degrees),Elevation,SampleYear,SampleDayOfYear,GrowSeasonStart,GrowSeasonEnd,StandAge,CanopyHeight,LeafAreaIndex,SpeciesSampled,AveTimeResolution,SampleHeight,LeafAge,SpecificLeafArea,LfNitrogenContent,LfCarbonContent,LfPhosphContent
NoUnit,NorthPositive,EastPositive,m,NoUnit,DayOfYear,DayOfYear,DayOfYear,Year,m,m2/m2,NoBlankSpace,Minutes,m,days,cm2/g,%,%,%
-9999,-20.75,-42.88,648,2009,-9999,-9999,-9999,-9999,-9999,-9999,CoffeaArabica,-9999,-9999,-9999,140,3.48,-9999,-9999
Gamma*,Kc,Ko,Alpha,Rd,gi
Pa,Pa,Pa,NoUnit,umol/m2/s,umol/m2/s/Pa
10,-9999,-9999,-9999,-9999,-9999
Obs,HHMMSS,FTime,Photo,!AdjPhoto,!StomCond,!Ci,!Trmmol,!VpdL,Area,StmRat,BLCond,Tair,!Tleaf,TBlk,CO2R,CO2S,H2OR,H2OS,RH_R,RH_S,Flow,!PARi,PARo,Press,CsMch,HsMch,StableF,Status,PhiPS2,OxygenPress
NoUnit,HHMMSS,Second,umol/m2/s,umol/m2/s,mol/m2/s,umol/mol,mmol/m2/s,kPa,cm2,NA,mol/m2/s,oC,oC,oC,umol/mol,umol/mol,mmol/mol,mmol/mol,%,%,umol/s,umol/m2/s,umol/m2/s,Kpa,umol/mol,mmol/mol,NA,NA,NA,KPA
10,-9999,-9999,10.49195882,11.05941043,0.244883469,212.5041051,2.63076876,1.036135144,2,0,4.644859791,23.52121258,23.53769627,23.3545414,300.0483063,292.5618317,18.24994297,19.96389828,58.95560608,64.49247513,300.8535187,993.0888855,0.049617826,94.00339508,-2.052112579,-0.246214688,0.425,111115,0.180769687,21
10,-9999,-9999,6.613751647,7.414357534,0.200000749,130.8730299,2.24618742,1.072960558,2,0,4.644859791,23.57428112,23.68962097,23.40673904,200.1022598,195.4142136,18.39681854,19.86024399,59.23092155,63.94262123,300.8801514,992.5410278,0.049735996,93.98853455,-1.348773956,-0.243325055,0.475,111115,0.163288942,21
10,-9999,-9999,4.431079608,5.349146841,0.170652088,92.42684697,2.00393304,1.114947396,2,0,4.644859791,23.58453674,23.90329285,23.41538334,149.6127335,146.4719864,18.51102257,19.8167675,59.56615295,63.76787758,300.8583466,992.1625671,0.054449931,93.9954071,-1.367557526,-0.230450451,0.375,111115,0.147352806,21
10,-9999,-9999,1.523393138,2.556557599,0.159880602,70.4656295,1.965014975,1.163792845,2,0,4.644859791,23.59998169,24.21637478,23.43008366,99.656147,98.51480789,18.61892796,19.89914742,59.85464211,63.97018967,300.8723236,991.761908,0.039717828,93.9906868,-0.692935944,-0.232964337,0.575,111115,0.130597749,21
10,-9999,-9999,0.894293187,1.987936699,0.167650406,52.50296582,2.025541888,1.145843431,2,0,4.644859791,23.62822838,24.19524651,23.45776844,74.00842819,73.31520309,18.72938271,20.0488924,60.108358,64.34307251,300.8590363,991.5204651,0.045964496,93.99226608,-0.604091644,-0.238077939,0.575,111115,0.122154858,21
10,-9999,-9999,-0.495843139,0.655970767,0.176641615,42.05656346,2.078428704,1.118051438,2,0,4.644859791,23.63969841,24.11649742,23.46931267,48.81573753,49.07753906,18.83879395,20.19250221,60.41828194,64.75978699,300.871344,991.50896,0.042428688,93.99311447,-0.591835022,-0.238228619,0.7,111115,0.11011836,21
10,-9999,-9999,14.01214221,14.34608078,0.188886895,258.1956724,2.081065547,1.052338661,2,0,4.644859791,23.63486118,23.77918701,23.46806164,399.7125275,389.8589264,18.8980257,20.25335598,60.6206089,64.96820526,300.8738037,991.5494934,0.06246434,93.98490219,-3.991065979,-0.239916623,0.35,111115,0.183856114,21
10,-9999,-9999,19.20963114,19.06936549,0.167346311,390.2278007,1.923908779,1.090216329,2,0,4.644859791,23.6730854,23.97962074,23.50691929,600.9658813,587.4440186,18.97605591,20.22919121,60.72654266,64.73679276,300.8435883,990.6557251,0.06564644,93.97809906,-4.053321838,-0.263443768,0.6,111115,0.224674063,21
10,-9999,-9999,22.68315779,22.07166985,0.140898278,513.7169863,1.709378251,1.143940773,2,0,4.644859791,23.72432709,24.24497566,23.55486546,799.7560669,783.7866455,19.05482311,20.1682272,60.79165916,64.34382095,300.861908,990.5349609,0.044432433,93.97946396,-6.789344788,-0.258801281,0.625,111115,0.241833394,21
10,-9999,-9999,25.21838506,24.1313968,0.128254365,657.3239246,1.569373475,1.150702993,2,0,4.644859791,23.77119751,24.27973061,23.60147991,999.7003906,981.9117737,19.14113102,20.16335564,60.89594879,64.14807434,300.8594788,990.3832764,0.037125352,93.98093872,-10.22812653,-0.260886014,0.65,111115,0.250284039,21
10,-9999,-9999,27.03077557,25.46461001,0.120765245,816.0761447,1.52318325,1.183928533,2,0,4.644859791,23.80861893,24.49090347,23.63921146,1200.733826,1181.568982,19.23064556,20.22269268,61.04207878,64.19104309,300.8688538,990.2308533,0.058457612,93.97930527,-14.02487946,-0.262095273,0.575,111115,0.252074273,21
10,-9999,-9999,28.6322564,26.59017955,0.117258539,984.2999029,1.510964689,1.208454852,2,0,4.644859791,23.86426582,24.66598072,23.69386177,1400.285156,1379.865356,19.32225647,20.30630074,61.13061714,64.24388199,300.8569305,990.0950989,0.060696683,93.9834198,-17.98886871,-0.264069378,0.65,111115,0.25113703,21
10,-9999,-9999,29.59434444,27.07367747,0.111042426,1152.036476,1.451859088,1.224292598,2,0,4.644859791,23.92603722,24.77762184,23.75417137,1600.474329,1579.277905,19.41603336,20.36147785,61.19426117,64.17406006,300.8736847,989.9327454,0.052446734,93.97519684,-22.0407486,-0.271241009,0.65,111115,0.252735204,21
10,-9999,-9999,30.43679512,26.95968124,0.103627708,1515.947025,1.36954251,1.235421377,2,0,4.644859791,23.97047672,24.84818077,23.79694042,1999.831714,1977.797449,19.49336185,20.38523922,61.27052002,64.07382736,300.8539337,989.8097778,0.061404274,93.96966782,-31.06003571,-0.273886502,0.625,111115,0.248197252,21
1 Investigator name: Valid Cleaned
2 Contact information: validcleaned@yahoo.com.br
3 Site name in full: NA
4 Vegetation type: NA
5 Soil type: NA
6 Major species: NA
7 Sample leaf light environment: Full Sun
8 Water_stress_assessment:_No_water_stress, plants_irrigated_every_day
9 Instrument used: Licor-6400XT
10 Extra info:
11 SiteID Latitude(Degrees) Longitude(Degrees) Elevation SampleYear SampleDayOfYear GrowSeasonStart GrowSeasonEnd StandAge CanopyHeight LeafAreaIndex SpeciesSampled AveTimeResolution SampleHeight LeafAge SpecificLeafArea LfNitrogenContent LfCarbonContent LfPhosphContent
12 NoUnit NorthPositive EastPositive m NoUnit DayOfYear DayOfYear DayOfYear Year m m2/m2 NoBlankSpace Minutes m days cm2/g % % %
13 -9999 -20.75 -42.88 648 2009 -9999 -9999 -9999 -9999 -9999 -9999 CoffeaArabica -9999 -9999 -9999 140 3.48 -9999 -9999
14 Gamma* Kc Ko Alpha Rd gi
15 Pa Pa Pa NoUnit umol/m2/s umol/m2/s/Pa
16 10 -9999 -9999 -9999 -9999 -9999
17 Obs HHMMSS FTime Photo !AdjPhoto !StomCond !Ci !Trmmol !VpdL Area StmRat BLCond Tair !Tleaf TBlk CO2R CO2S H2OR H2OS RH_R RH_S Flow !PARi PARo Press CsMch HsMch StableF Status PhiPS2 OxygenPress
18 NoUnit HHMMSS Second umol/m2/s umol/m2/s mol/m2/s umol/mol mmol/m2/s kPa cm2 NA mol/m2/s oC oC oC umol/mol umol/mol mmol/mol mmol/mol % % umol/s umol/m2/s umol/m2/s Kpa umol/mol mmol/mol NA NA NA KPA
19 10 -9999 -9999 10.49195882 11.05941043 0.244883469 212.5041051 2.63076876 1.036135144 2 0 4.644859791 23.52121258 23.53769627 23.3545414 300.0483063 292.5618317 18.24994297 19.96389828 58.95560608 64.49247513 300.8535187 993.0888855 0.049617826 94.00339508 -2.052112579 -0.246214688 0.425 111115 0.180769687 21
20 10 -9999 -9999 6.613751647 7.414357534 0.200000749 130.8730299 2.24618742 1.072960558 2 0 4.644859791 23.57428112 23.68962097 23.40673904 200.1022598 195.4142136 18.39681854 19.86024399 59.23092155 63.94262123 300.8801514 992.5410278 0.049735996 93.98853455 -1.348773956 -0.243325055 0.475 111115 0.163288942 21
21 10 -9999 -9999 4.431079608 5.349146841 0.170652088 92.42684697 2.00393304 1.114947396 2 0 4.644859791 23.58453674 23.90329285 23.41538334 149.6127335 146.4719864 18.51102257 19.8167675 59.56615295 63.76787758 300.8583466 992.1625671 0.054449931 93.9954071 -1.367557526 -0.230450451 0.375 111115 0.147352806 21
22 10 -9999 -9999 1.523393138 2.556557599 0.159880602 70.4656295 1.965014975 1.163792845 2 0 4.644859791 23.59998169 24.21637478 23.43008366 99.656147 98.51480789 18.61892796 19.89914742 59.85464211 63.97018967 300.8723236 991.761908 0.039717828 93.9906868 -0.692935944 -0.232964337 0.575 111115 0.130597749 21
23 10 -9999 -9999 0.894293187 1.987936699 0.167650406 52.50296582 2.025541888 1.145843431 2 0 4.644859791 23.62822838 24.19524651 23.45776844 74.00842819 73.31520309 18.72938271 20.0488924 60.108358 64.34307251 300.8590363 991.5204651 0.045964496 93.99226608 -0.604091644 -0.238077939 0.575 111115 0.122154858 21
24 10 -9999 -9999 -0.495843139 0.655970767 0.176641615 42.05656346 2.078428704 1.118051438 2 0 4.644859791 23.63969841 24.11649742 23.46931267 48.81573753 49.07753906 18.83879395 20.19250221 60.41828194 64.75978699 300.871344 991.50896 0.042428688 93.99311447 -0.591835022 -0.238228619 0.7 111115 0.11011836 21
25 10 -9999 -9999 14.01214221 14.34608078 0.188886895 258.1956724 2.081065547 1.052338661 2 0 4.644859791 23.63486118 23.77918701 23.46806164 399.7125275 389.8589264 18.8980257 20.25335598 60.6206089 64.96820526 300.8738037 991.5494934 0.06246434 93.98490219 -3.991065979 -0.239916623 0.35 111115 0.183856114 21
26 10 -9999 -9999 19.20963114 19.06936549 0.167346311 390.2278007 1.923908779 1.090216329 2 0 4.644859791 23.6730854 23.97962074 23.50691929 600.9658813 587.4440186 18.97605591 20.22919121 60.72654266 64.73679276 300.8435883 990.6557251 0.06564644 93.97809906 -4.053321838 -0.263443768 0.6 111115 0.224674063 21
27 10 -9999 -9999 22.68315779 22.07166985 0.140898278 513.7169863 1.709378251 1.143940773 2 0 4.644859791 23.72432709 24.24497566 23.55486546 799.7560669 783.7866455 19.05482311 20.1682272 60.79165916 64.34382095 300.861908 990.5349609 0.044432433 93.97946396 -6.789344788 -0.258801281 0.625 111115 0.241833394 21
28 10 -9999 -9999 25.21838506 24.1313968 0.128254365 657.3239246 1.569373475 1.150702993 2 0 4.644859791 23.77119751 24.27973061 23.60147991 999.7003906 981.9117737 19.14113102 20.16335564 60.89594879 64.14807434 300.8594788 990.3832764 0.037125352 93.98093872 -10.22812653 -0.260886014 0.65 111115 0.250284039 21
29 10 -9999 -9999 27.03077557 25.46461001 0.120765245 816.0761447 1.52318325 1.183928533 2 0 4.644859791 23.80861893 24.49090347 23.63921146 1200.733826 1181.568982 19.23064556 20.22269268 61.04207878 64.19104309 300.8688538 990.2308533 0.058457612 93.97930527 -14.02487946 -0.262095273 0.575 111115 0.252074273 21
30 10 -9999 -9999 28.6322564 26.59017955 0.117258539 984.2999029 1.510964689 1.208454852 2 0 4.644859791 23.86426582 24.66598072 23.69386177 1400.285156 1379.865356 19.32225647 20.30630074 61.13061714 64.24388199 300.8569305 990.0950989 0.060696683 93.9834198 -17.98886871 -0.264069378 0.65 111115 0.25113703 21
31 10 -9999 -9999 29.59434444 27.07367747 0.111042426 1152.036476 1.451859088 1.224292598 2 0 4.644859791 23.92603722 24.77762184 23.75417137 1600.474329 1579.277905 19.41603336 20.36147785 61.19426117 64.17406006 300.8736847 989.9327454 0.052446734 93.97519684 -22.0407486 -0.271241009 0.65 111115 0.252735204 21
32 10 -9999 -9999 30.43679512 26.95968124 0.103627708 1515.947025 1.36954251 1.235421377 2 0 4.644859791 23.97047672 24.84818077 23.79694042 1999.831714 1977.797449 19.49336185 20.38523922 61.27052002 64.07382736 300.8539337 989.8097778 0.061404274 93.96966782 -31.06003571 -0.273886502 0.625 111115 0.248197252 21
+8 -9
View File
@@ -10,25 +10,25 @@ namespace LeafWeb.Core.Parsers
private readonly MemoryStream _memoryStream;
protected readonly CsvReader CsvReader;
protected CsvParserBase(FileSystemInfo csvFile)
protected CsvParserBase(FileSystemInfo csvFile, bool ignoreBlankLines)
{
_reader = OpenCsv(csvFile);
CsvReader = InitCsvReader(_reader);
CsvReader = InitCsvReader(_reader, ignoreBlankLines);
}
protected CsvParserBase(byte[] fileContents)
protected CsvParserBase(byte[] fileContents, bool ignoreBlankLines)
{
_memoryStream = new MemoryStream(fileContents);
_reader = new StreamReader(_memoryStream);
CsvReader = InitCsvReader(_reader);
CsvReader = InitCsvReader(_reader, ignoreBlankLines);
}
private static CsvReader InitCsvReader(StreamReader reader)
private static CsvReader InitCsvReader(TextReader reader, bool ignoreBlankLines)
{
var csvReader = new CsvReader(reader);
csvReader.Configuration.HasHeaderRecord = false;
csvReader.Configuration.IgnoreBlankLines = false;
csvReader.Configuration.IgnoreBlankLines = ignoreBlankLines;
csvReader.Configuration.ReadingExceptionOccurred = exception => false;
return csvReader;
}
@@ -53,8 +53,7 @@ namespace LeafWeb.Core.Parsers
public void Dispose()
{
_reader.Dispose();
if (_memoryStream != null)
_memoryStream.Dispose();
}
_memoryStream?.Dispose();
}
}
}
+1
View File
@@ -4,6 +4,7 @@ using System.Linq;
using CsvHelper;
using CsvHelper.Configuration;
using LeafWeb.Core.Entities;
// ReSharper disable IdentifierTypo
namespace LeafWeb.Core.Parsers
{
+2 -2
View File
@@ -8,11 +8,11 @@ namespace LeafWeb.Core.Parsers
{
public class LeafGasComparisonParser : CsvParserBase
{
public LeafGasComparisonParser(FileSystemInfo csvFile) : base(csvFile)
public LeafGasComparisonParser(FileSystemInfo csvFile) : base(csvFile, false)
{
}
public LeafGasComparisonParser(byte[] fileContents) : base(fileContents)
public LeafGasComparisonParser(byte[] fileContents) : base(fileContents, false)
{
}
+11 -4
View File
@@ -9,11 +9,11 @@ namespace LeafWeb.Core.Parsers
{
public class LeafInputCsvParser : CsvParserBase
{
public LeafInputCsvParser(FileSystemInfo csvFile) : base(csvFile)
public LeafInputCsvParser(FileSystemInfo csvFile) : base(csvFile, true)
{
}
public LeafInputCsvParser(byte[] fileContents) : base(fileContents)
public LeafInputCsvParser(byte[] fileContents) : base(fileContents, true)
{
}
@@ -45,9 +45,16 @@ namespace LeafWeb.Core.Parsers
if (!CsvReader.Read())
throw new ParseException("Could not read line number " + CsvReader.Context.Row);
string field;
if (!CsvReader.TryGetField(0, out field))
if (!CsvReader.TryGetField(0, out string field))
throw new ParseException("Could not read first field on line number " + CsvReader.Context.Row);
// skip empty lines
if (string.IsNullOrEmpty(field))
{
i--;
continue;
}
items.Add(field);
}
return ParsedObjectFactory<LeafInputData>.Create(items.ToArray());
+24 -21
View File
@@ -9,7 +9,7 @@ namespace LeafWeb.Core.Utility
{
public static void Register()
{
TypeDescriptor.AddAttributes(typeof(Boolean),
TypeDescriptor.AddAttributes(typeof(bool),
new TypeConverterAttribute(typeof(BoolTypeConverter)));
}
@@ -24,26 +24,29 @@ namespace LeafWeb.Core.Utility
public override object ConvertTo(ITypeDescriptorContext context, CultureInfo culture, object value, Type destinationType)
{
if (value is bool)
return value;
if (value is string)
{
var s = value as string;
if (string.IsNullOrEmpty(s))
return false;
switch (s.Trim().ToUpper())
{
case "TRUE":
case "YES":
case "1":
case "-1":
return true;
switch (value)
{
case bool _:
return value;
case string s:
{
if (string.IsNullOrEmpty(s))
return false;
switch (s.Trim().ToUpper())
{
case "TRUE":
case "YES":
case "1":
case "-1":
return true;
default:
return false;
}
}
return base.ConvertTo(context, culture, value, destinationType);
}
default:
return false;
}
}
default:
return base.ConvertTo(context, culture, value, destinationType);
}
}
}
}
+3 -6
View File
@@ -52,8 +52,7 @@ namespace LeafWeb.Core.Utility
if (property != null)
{
object convertedVal;
if (!TryConvertValue(property, value, out convertedVal))
if (!TryConvertValue(property, value, out var convertedVal))
throw new ParseException($"Cannot convert value '{value}' for {property.Name} at line number {lineNumber}");
property.Set(obj, convertedVal);
}
@@ -83,8 +82,7 @@ namespace LeafWeb.Core.Utility
if (property != null)
{
object convertedVal;
if (!TryConvertValue(property, value, out convertedVal))
if (!TryConvertValue(property, value, out var convertedVal))
throw new ParseException($"Cannot convert value '{value}' for {property.Name} in position {position}");
property.Set(obj, convertedVal);
}
@@ -113,8 +111,7 @@ namespace LeafWeb.Core.Utility
if (property != null)
{
object convertedVal;
if (!TryConvertValue(property, value, out convertedVal))
if (!TryConvertValue(property, value, out var convertedVal))
throw new ParseException($"Cannot convert value '{value}' for {property.Name} in position {position}");
property.Set(obj, convertedVal);
}