Implement CsvFieldIndexer.

Fixes #2
This commit is contained in:
2023-08-05 14:15:38 +02:00
parent fedee8a61e
commit 6b4370b6ff
6 changed files with 437 additions and 0 deletions

View File

@@ -0,0 +1,142 @@
using CsvLib;
namespace CvsLib;
public class CsvFieldIndexerTests
{
#region GenerateIndex
[Fact]
public void GenerateIndex__Empty()
{
// --- Arrange
StringReader sr = new(string.Empty);
// --- Act
CsvFieldIndexer indexer = new();
indexer.GenerateIndex(sr);
// --- Assert
Assert.Single(indexer.Index);
Assert.Equal(0, indexer.Index[0]);
Assert.Empty(indexer.FieldIndex);
}
[Fact]
public void GenerateIndex__PlainText__OneRow()
{
// --- Arrange
StringReader sr = new("Hello World");
// --- Act
CsvFieldIndexer indexer = new();
indexer.GenerateIndex(sr);
// --- Assert
Assert.Equal(2, indexer.Index.Count);
Assert.Equal(0, indexer.Index[0]);
Assert.Equal(12, indexer.Index[1]);
Assert.Single(indexer.FieldIndex);
Assert.Equal(0, indexer.FieldIndex[0][0]);
Assert.Equal(10, indexer.FieldIndex[0][1]);
}
[Fact]
public void GenerateIndex__TwoLinesOfPainText__TwoRows()
{
// --- Arrange
StringReader sr = new("""
Hello World
Hello World
""");
// --- Act
CsvFieldIndexer indexer = new();
indexer.GenerateIndex(sr);
// --- Assert
Assert.Equal(3, indexer.Index.Count);
Assert.Equal(0, indexer.Index[0]);
Assert.Equal(12, indexer.Index[1]);
Assert.Equal(24, indexer.Index[2]);
Assert.Equal(2, indexer.FieldIndex.Count);
Assert.Equal(2, indexer.FieldIndex[0].Count);
Assert.Equal(0, indexer.FieldIndex[0][0]);
Assert.Equal(10, indexer.FieldIndex[0][1]);
Assert.Equal(2, indexer.FieldIndex[1].Count);
Assert.Equal(12, indexer.FieldIndex[1][0]);
Assert.Equal(22, indexer.FieldIndex[1][1]);
}
[Fact]
public void GenerateIndex__TwoLinesOfQuotedText__TwoRows()
{
// --- Arrange
StringReader sr = new("""
"Hello World"
"Hello World"
""");
// --- Act
CsvFieldIndexer indexer = new();
indexer.GenerateIndex(sr);
// --- Assert
Assert.Equal(3, indexer.Index.Count);
Assert.Equal(0, indexer.Index[0]);
Assert.Equal(14, indexer.Index[1]);
Assert.Equal(28, indexer.Index[2]);
Assert.Equal(2, indexer.FieldIndex.Count);
Assert.Equal(2, indexer.FieldIndex[0].Count);
Assert.Equal(1, indexer.FieldIndex[0][0]);
Assert.Equal(11, indexer.FieldIndex[0][1]);
Assert.Equal(2, indexer.FieldIndex[1].Count);
Assert.Equal(15, indexer.FieldIndex[1][0]);
Assert.Equal(25, indexer.FieldIndex[1][1]);
}
[Fact]
public void GenerateIndex__TwoLinesWithTwoQuotedColumns__TwoRowsTwoFields()
{
// --- Arrange
StringReader sr = new("""
"Hello","World"
"Hello","World"
""");
// --- Act
CsvFieldIndexer indexer = new();
indexer.GenerateIndex(sr);
// --- Assert
Assert.Equal(3, indexer.Index.Count);
Assert.Equal(0, indexer.Index[0]);
Assert.Equal(16, indexer.Index[1]);
Assert.Equal(32, indexer.Index[2]);
Assert.Equal(2, indexer.FieldIndex.Count);
Assert.Equal(4, indexer.FieldIndex[0].Count);
Assert.Equal(1, indexer.FieldIndex[0][0]);
Assert.Equal(5, indexer.FieldIndex[0][1]);
Assert.Equal(9, indexer.FieldIndex[0][2]);
Assert.Equal(13, indexer.FieldIndex[0][3]);
Assert.Equal(4, indexer.FieldIndex[1].Count);
Assert.Equal(17, indexer.FieldIndex[1][0]);
Assert.Equal(21, indexer.FieldIndex[1][1]);
Assert.Equal(25, indexer.FieldIndex[1][2]);
Assert.Equal(29, indexer.FieldIndex[1][3]);
}
#endregion GenerateIndex
}

View File

@@ -0,0 +1,29 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<TargetFramework>net7.0</TargetFramework>
<ImplicitUsings>enable</ImplicitUsings>
<Nullable>enable</Nullable>
<RootNamespace>CvsLib</RootNamespace>
<IsPackable>false</IsPackable>
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Microsoft.NET.Test.Sdk" Version="17.3.2" />
<PackageReference Include="xunit" Version="2.4.2" />
<PackageReference Include="xunit.runner.visualstudio" Version="2.4.5">
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
<PrivateAssets>all</PrivateAssets>
</PackageReference>
<PackageReference Include="coverlet.collector" Version="3.1.2">
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
<PrivateAssets>all</PrivateAssets>
</PackageReference>
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\CsvLib\CsvLib.csproj" />
</ItemGroup>
</Project>

1
CsvLib.Tests/Usings.cs Normal file
View File

@@ -0,0 +1 @@
global using Xunit;

View File

@@ -0,0 +1,54 @@
using System;
using System.IO;
using System.Text;
namespace CsvLib
{
public class BufferedTextReader : TextReader
{
private readonly TextReader _baseReader;
private int _position;
private readonly StringBuilder _sbBuffer = new StringBuilder();
public BufferedTextReader(TextReader baseReader)
{
_baseReader = baseReader;
}
public override int Read()
{
_position++;
int read = _baseReader.Read();
if (read != -1)
{
_sbBuffer.Append((char)read);
}
return read;
}
public override int Read(char[] buffer, int index, int count)
{
throw new NotImplementedException("Read buffered method on BufferedTextReader");
}
public override int Peek()
{
return _baseReader.Peek();
}
public int Position
{
get { return _position; }
}
public string GetBuffer()
{
return _sbBuffer.ToString();
}
public void CleanBuffer()
{
_sbBuffer.Clear();
}
}
}

205
CsvLib/CsvFieldIndexer.cs Normal file
View File

@@ -0,0 +1,205 @@
using System;
using System.Collections.Generic;
using System.IO;
using System.Text;
namespace CsvLib
{
public class CsvFieldIndexer
{
private bool _insideString;
private readonly char _separator;
private readonly char _quoteChar;
private readonly char _escapeChar;
public CsvFieldIndexer(char separator = ',', char quoteChar = '"', char escapeChar = '\\')
{
_separator = separator;
_quoteChar = quoteChar;
_escapeChar = escapeChar;
}
private List<long> _index = new List<long>();
public List<long> Index { get { return _index; } }
private List<List<long>> _fieldIndex = new List<List<long>>();
public List<List<long>> FieldIndex { get { return _fieldIndex; } }
private void DummyParser(string line)
{
for (int i = 0; i < line.Length; i++)
{
char c = line[i];
if (c == _separator && _insideString == false)
{
continue;
}
if (c == _quoteChar && _insideString == false)
{
_insideString = true;
continue;
}
if (c == _quoteChar && _insideString)
{
_insideString = false;
continue;
}
if (c == _escapeChar && _insideString)
{
i++;
c = line[i];
}
}
}
private List<long> ParseLineIndex(string line, long lineOffset)
{
List<long> fieldPositions = new List<long>();
long? fieldStartPosition = null;
long? fieldEndPosition = null;
for (int i = 0; i < line.Length; i++)
{
char c = line[i];
if (c == _separator && _insideString == false)
{
if (fieldStartPosition != null)
{
fieldPositions.Add((long)fieldStartPosition);
fieldPositions.Add((long)fieldEndPosition);
}
fieldStartPosition = null;
fieldEndPosition = null;
}
else if (c == _quoteChar && _insideString == false)
{
_insideString = true;
}
else if (c == _quoteChar && _insideString)
{
_insideString = false;
}
else if (c == _escapeChar && _insideString)
{
i++;
c = line[i];
}
else if ((c == '\n' || c == '\r') && _insideString == false)
{
break;
}
else
{
long absolutePosition = lineOffset + i;
if (fieldStartPosition == null) { fieldStartPosition = absolutePosition; }
fieldEndPosition = absolutePosition;
}
}
if (_insideString == false)
{
if (fieldStartPosition != null)
{
fieldPositions.Add((long)fieldStartPosition);
fieldPositions.Add((long)fieldEndPosition);
}
}
return fieldPositions;
}
public void GenerateIndex(string file)
{
using (FileStream stream = new FileStream(file, FileMode.Open))
using (StreamReader streamReader = new StreamReader(stream, Encoding.Default, true, 4096))
{
GenerateIndex(streamReader);
}
}
public void GenerateIndex(TextReader textReader)
{
_insideString = false;
_index.Clear();
_index.Add(0);
int idxRow = 0;
using (BufferedTextReader reader = new BufferedTextReader(textReader))
{
string currentLine;
while ((currentLine = reader.ReadLine()) != null)
{
DummyParser(currentLine);
if (_insideString) { continue; }
string fullLine = reader.GetBuffer();
reader.CleanBuffer();
List<long> fieldIndexes = ParseLineIndex(fullLine, _index[idxRow]);
_fieldIndex.Add(fieldIndexes);
_index.Add(reader.Position);
idxRow++;
}
}
}
private void Index_SaveFile(string indexFile)
{
if (File.Exists(indexFile))
{
File.Delete(indexFile);
}
Stream streamOut = File.Open(indexFile, FileMode.Create);
using (BinaryWriter binWriter = new BinaryWriter(streamOut))
{
binWriter.Write(_index.Count);
for (int i = 0; i < _index.Count; i++)
{
binWriter.Write(_index[i]);
}
}
streamOut.Close();
}
private static List<long> Index_LoadFile(string indexFile)
{
List<long> tempIndex = new List<long>();
Stream streamIn = File.Open(indexFile, FileMode.Open);
using (BinaryReader binReader = new BinaryReader(streamIn))
{
int numRegs = binReader.ReadInt32();
for (int i = 0; i < numRegs; i++)
{
long value = binReader.ReadInt64();
tempIndex.Add(value);
}
}
streamIn.Close();
return tempIndex;
}
public void LoadIndexOfFile(string file)
{
DateTime dtFile = File.GetCreationTime(file);
string indexFile = $"{file}.idx";
if (File.Exists(indexFile) && File.GetCreationTime(indexFile) > dtFile)
{
_index = Index_LoadFile(indexFile);
}
else
{
// Generate index
DateTime dtNow = DateTime.UtcNow;
GenerateIndex(file);
TimeSpan tsGenIndex = DateTime.UtcNow - dtNow;
// Save Index if expensive generation
if (tsGenIndex.TotalSeconds > 2)
{
Index_SaveFile(indexFile);
}
}
}
}
}

View File

@@ -7,6 +7,8 @@ Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "CsvView", "CsvView.csproj",
EndProject
Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "CsvLib", "CsvLib\CsvLib.csproj", "{EB0FDB60-8B9D-401C-85A8-4CF4105D5063}"
EndProject
Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "CsvLib.Tests", "CsvLib.Tests\CsvLib.Tests.csproj", "{EC5C84D8-1CDE-4AED-9C16-6C4086A20893}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|Any CPU = Debug|Any CPU
@@ -21,6 +23,10 @@ Global
{EB0FDB60-8B9D-401C-85A8-4CF4105D5063}.Debug|Any CPU.Build.0 = Debug|Any CPU
{EB0FDB60-8B9D-401C-85A8-4CF4105D5063}.Release|Any CPU.ActiveCfg = Release|Any CPU
{EB0FDB60-8B9D-401C-85A8-4CF4105D5063}.Release|Any CPU.Build.0 = Release|Any CPU
{EC5C84D8-1CDE-4AED-9C16-6C4086A20893}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
{EC5C84D8-1CDE-4AED-9C16-6C4086A20893}.Debug|Any CPU.Build.0 = Debug|Any CPU
{EC5C84D8-1CDE-4AED-9C16-6C4086A20893}.Release|Any CPU.ActiveCfg = Release|Any CPU
{EC5C84D8-1CDE-4AED-9C16-6C4086A20893}.Release|Any CPU.Build.0 = Release|Any CPU
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE