Compare commits

..

6 Commits

Author SHA1 Message Date
EliotJones
3131dae49e passing -r will repeat parsing the set n times, -f will run a single file 2025-07-26 17:30:43 -05:00
EliotJones
52c0635273 support performance profiling information in console runner 2025-07-26 15:04:03 -05:00
EliotJones
b6bd0a3169 bump version to 0.1.12-alpha001 2025-07-26 13:43:28 -05:00
EliotJones
3d2e12cb16 version 0.1.11 2025-07-26 13:16:01 -05:00
Eliot Jones
9cb3b71e62 update readme to avoid people using page.Text or asking about editing docs (#1109)
* update readme to avoid people using `page.Text` or asking about editing docs

we need to be more clear because beloved chat gpt falls into the trap of
recommending `page.Text` when asked about the library even though this
text is usually the wrong field to use

* tabs to spaces

* rogue tab
2025-07-26 18:58:35 +01:00
EliotJones
27df4af5f9 handle additional broken pdf files in the common crawl set
- a file contained 2 indices pointing to '.notdef' for the character name so
we just take the first rather than requiring a single
- a file contained '/' (empty name) as the subtype declaration, so we fall back
to trying type 1 and truetype parsing in this situation
2025-07-26 18:55:29 +01:00
12 changed files with 504 additions and 212 deletions

View File

@@ -1,23 +1,23 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<TargetFrameworks>netstandard2.0;net462;net471;net6.0;net8.0</TargetFrameworks>
<LangVersion>12</LangVersion>
<Version>0.1.11-alpha001</Version>
<IsTestProject>False</IsTestProject>
<GenerateDocumentationFile>true</GenerateDocumentationFile>
<SignAssembly>true</SignAssembly>
<AssemblyOriginatorKeyFile>..\pdfpig.snk</AssemblyOriginatorKeyFile>
</PropertyGroup>
<ItemGroup Condition="'$(TargetFramework)'=='net462'">
<PackageReference Include="System.ValueTuple" Version="4.5.0" />
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)'=='netstandard2.0' or '$(TargetFramework)'=='net462' OR '$(TargetFramework)'=='net471'">
<PackageReference Include="Microsoft.Bcl.HashCode" Version="6.0.0" />
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)'=='netstandard2.0' or '$(TargetFramework)'=='net462' or '$(TargetFramework)'=='net471'">
<PackageReference Include="System.Memory" Version="4.6.0" />
</ItemGroup>
<ItemGroup>
<None Include="..\pdfpig.snk" Link="pdfpig.snk" />
</ItemGroup>
<PropertyGroup>
<TargetFrameworks>netstandard2.0;net462;net471;net6.0;net8.0</TargetFrameworks>
<LangVersion>12</LangVersion>
<Version>0.1.12-alpha001</Version>
<IsTestProject>False</IsTestProject>
<GenerateDocumentationFile>true</GenerateDocumentationFile>
<SignAssembly>true</SignAssembly>
<AssemblyOriginatorKeyFile>..\pdfpig.snk</AssemblyOriginatorKeyFile>
</PropertyGroup>
<ItemGroup Condition="'$(TargetFramework)'=='net462'">
<PackageReference Include="System.ValueTuple" Version="4.5.0" />
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)'=='netstandard2.0' or '$(TargetFramework)'=='net462' OR '$(TargetFramework)'=='net471'">
<PackageReference Include="Microsoft.Bcl.HashCode" Version="6.0.0" />
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)'=='netstandard2.0' or '$(TargetFramework)'=='net462' or '$(TargetFramework)'=='net471'">
<PackageReference Include="System.Memory" Version="4.6.0" />
</ItemGroup>
<ItemGroup>
<None Include="..\pdfpig.snk" Link="pdfpig.snk" />
</ItemGroup>
</Project>

View File

@@ -1,22 +1,22 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<TargetFrameworks>netstandard2.0;net462;net471;net6.0;net8.0</TargetFrameworks>
<LangVersion>12</LangVersion>
<Version>0.1.11-alpha001</Version>
<IsTestProject>False</IsTestProject>
<GenerateDocumentationFile>true</GenerateDocumentationFile>
<SignAssembly>true</SignAssembly>
<AssemblyOriginatorKeyFile>..\pdfpig.snk</AssemblyOriginatorKeyFile>
</PropertyGroup>
<ItemGroup Condition="'$(TargetFramework)'=='net462'">
<PackageReference Include="System.ValueTuple" Version="4.5.0" />
</ItemGroup>
<ItemGroup>
<None Include="..\pdfpig.snk" Link="pdfpig.snk" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\UglyToad.PdfPig.Core\UglyToad.PdfPig.Core.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig.Fonts\UglyToad.PdfPig.Fonts.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig\UglyToad.PdfPig.csproj" />
</ItemGroup>
<PropertyGroup>
<TargetFrameworks>netstandard2.0;net462;net471;net6.0;net8.0</TargetFrameworks>
<LangVersion>12</LangVersion>
<Version>0.1.12-alpha001</Version>
<IsTestProject>False</IsTestProject>
<GenerateDocumentationFile>true</GenerateDocumentationFile>
<SignAssembly>true</SignAssembly>
<AssemblyOriginatorKeyFile>..\pdfpig.snk</AssemblyOriginatorKeyFile>
</PropertyGroup>
<ItemGroup Condition="'$(TargetFramework)'=='net462'">
<PackageReference Include="System.ValueTuple" Version="4.5.0" />
</ItemGroup>
<ItemGroup>
<None Include="..\pdfpig.snk" Link="pdfpig.snk" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\UglyToad.PdfPig.Core\UglyToad.PdfPig.Core.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig.Fonts\UglyToad.PdfPig.Fonts.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig\UglyToad.PdfPig.csproj" />
</ItemGroup>
</Project>

View File

@@ -32,7 +32,7 @@
public virtual string GetNameByStringId(int stringId)
{
return GlyphIdToStringIdAndName.SingleOrDefault(x => x.Value.stringId == stringId).Value.name;
return GlyphIdToStringIdAndName.FirstOrDefault(x => x.Value.stringId == stringId).Value.name;
}
public virtual int GetStringIdByGlyphId(int glyphId)

View File

@@ -1,40 +1,40 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<TargetFrameworks>netstandard2.0;net462;net471;net6.0;net8.0</TargetFrameworks>
<LangVersion>12</LangVersion>
<Version>0.1.11-alpha001</Version>
<IsTestProject>False</IsTestProject>
<GenerateDocumentationFile>true</GenerateDocumentationFile>
<SignAssembly>true</SignAssembly>
<AssemblyOriginatorKeyFile>..\pdfpig.snk</AssemblyOriginatorKeyFile>
</PropertyGroup>
<ItemGroup>
<None Remove="Resources\AdobeFontMetrics\*" />
<None Remove="Resources\GlyphList\*" />
</ItemGroup>
<ItemGroup>
<Content Include="Resources\AdobeFontMetrics\MustRead.html">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</Content>
</ItemGroup>
<ItemGroup>
<EmbeddedResource Include="Resources\AdobeFontMetrics\*" />
</ItemGroup>
<ItemGroup>
<EmbeddedResource Include="Resources\GlyphList\*" />
</ItemGroup>
<ItemGroup>
<None Include="..\pdfpig.snk" Link="pdfpig.snk" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\UglyToad.PdfPig.Core\UglyToad.PdfPig.Core.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig.Tokenization\UglyToad.PdfPig.Tokenization.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig.Tokens\UglyToad.PdfPig.Tokens.csproj" />
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)'=='net462'">
<PackageReference Include="System.ValueTuple" Version="4.5.0" />
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)'=='netstandard2.0' or '$(TargetFramework)'=='net462' or '$(TargetFramework)'=='net471'">
<PackageReference Include="System.Memory" Version="4.6.0" />
</ItemGroup>
<PropertyGroup>
<TargetFrameworks>netstandard2.0;net462;net471;net6.0;net8.0</TargetFrameworks>
<LangVersion>12</LangVersion>
<Version>0.1.12-alpha001</Version>
<IsTestProject>False</IsTestProject>
<GenerateDocumentationFile>true</GenerateDocumentationFile>
<SignAssembly>true</SignAssembly>
<AssemblyOriginatorKeyFile>..\pdfpig.snk</AssemblyOriginatorKeyFile>
</PropertyGroup>
<ItemGroup>
<None Remove="Resources\AdobeFontMetrics\*" />
<None Remove="Resources\GlyphList\*" />
</ItemGroup>
<ItemGroup>
<Content Include="Resources\AdobeFontMetrics\MustRead.html">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</Content>
</ItemGroup>
<ItemGroup>
<EmbeddedResource Include="Resources\AdobeFontMetrics\*" />
</ItemGroup>
<ItemGroup>
<EmbeddedResource Include="Resources\GlyphList\*" />
</ItemGroup>
<ItemGroup>
<None Include="..\pdfpig.snk" Link="pdfpig.snk" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\UglyToad.PdfPig.Core\UglyToad.PdfPig.Core.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig.Tokenization\UglyToad.PdfPig.Tokenization.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig.Tokens\UglyToad.PdfPig.Tokens.csproj" />
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)'=='net462'">
<PackageReference Include="System.ValueTuple" Version="4.5.0" />
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)'=='netstandard2.0' or '$(TargetFramework)'=='net462' or '$(TargetFramework)'=='net471'">
<PackageReference Include="System.Memory" Version="4.6.0" />
</ItemGroup>
</Project>

View File

@@ -1,21 +1,21 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<TargetFrameworks>netstandard2.0;net462;net471;net6.0;net8.0</TargetFrameworks>
<LangVersion>12</LangVersion>
<Version>0.1.11-alpha001</Version>
<IsTestProject>False</IsTestProject>
<GenerateDocumentationFile>true</GenerateDocumentationFile>
<SignAssembly>true</SignAssembly>
<AssemblyOriginatorKeyFile>..\pdfpig.snk</AssemblyOriginatorKeyFile>
</PropertyGroup>
<ItemGroup Condition="'$(TargetFramework)'=='net462'">
<PackageReference Include="System.ValueTuple" Version="4.5.0" />
</ItemGroup>
<ItemGroup>
<None Include="..\pdfpig.snk" Link="pdfpig.snk" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\UglyToad.PdfPig.Core\UglyToad.PdfPig.Core.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig.Tokens\UglyToad.PdfPig.Tokens.csproj" />
</ItemGroup>
<PropertyGroup>
<TargetFrameworks>netstandard2.0;net462;net471;net6.0;net8.0</TargetFrameworks>
<LangVersion>12</LangVersion>
<Version>0.1.12-alpha001</Version>
<IsTestProject>False</IsTestProject>
<GenerateDocumentationFile>true</GenerateDocumentationFile>
<SignAssembly>true</SignAssembly>
<AssemblyOriginatorKeyFile>..\pdfpig.snk</AssemblyOriginatorKeyFile>
</PropertyGroup>
<ItemGroup Condition="'$(TargetFramework)'=='net462'">
<PackageReference Include="System.ValueTuple" Version="4.5.0" />
</ItemGroup>
<ItemGroup>
<None Include="..\pdfpig.snk" Link="pdfpig.snk" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\UglyToad.PdfPig.Core\UglyToad.PdfPig.Core.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig.Tokens\UglyToad.PdfPig.Tokens.csproj" />
</ItemGroup>
</Project>

View File

@@ -1,23 +1,23 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<TargetFrameworks>netstandard2.0;net462;net471;net6.0;net8.0</TargetFrameworks>
<LangVersion>12</LangVersion>
<Version>0.1.11-alpha001</Version>
<IsTestProject>False</IsTestProject>
<GenerateDocumentationFile>true</GenerateDocumentationFile>
<SignAssembly>true</SignAssembly>
<AssemblyOriginatorKeyFile>..\pdfpig.snk</AssemblyOriginatorKeyFile>
</PropertyGroup>
<ItemGroup Condition="'$(TargetFramework)'=='net462'">
<PackageReference Include="System.ValueTuple" Version="4.5.0" />
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)'=='netstandard2.0' or '$(TargetFramework)'=='net462' or '$(TargetFramework)'=='net471'">
<PackageReference Include="System.Memory" Version="4.6.0" />
</ItemGroup>
<ItemGroup>
<None Include="..\pdfpig.snk" Link="pdfpig.snk" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\UglyToad.PdfPig.Core\UglyToad.PdfPig.Core.csproj" />
</ItemGroup>
<PropertyGroup>
<TargetFrameworks>netstandard2.0;net462;net471;net6.0;net8.0</TargetFrameworks>
<LangVersion>12</LangVersion>
<Version>0.1.12-alpha001</Version>
<IsTestProject>False</IsTestProject>
<GenerateDocumentationFile>true</GenerateDocumentationFile>
<SignAssembly>true</SignAssembly>
<AssemblyOriginatorKeyFile>..\pdfpig.snk</AssemblyOriginatorKeyFile>
</PropertyGroup>
<ItemGroup Condition="'$(TargetFramework)'=='net462'">
<PackageReference Include="System.ValueTuple" Version="4.5.0" />
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)'=='netstandard2.0' or '$(TargetFramework)'=='net462' or '$(TargetFramework)'=='net471'">
<PackageReference Include="System.Memory" Version="4.6.0" />
</ItemGroup>
<ItemGroup>
<None Include="..\pdfpig.snk" Link="pdfpig.snk" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\UglyToad.PdfPig.Core\UglyToad.PdfPig.Core.csproj" />
</ItemGroup>
</Project>

View File

@@ -44,6 +44,25 @@
return handler.Generate(dictionary);
}
// Try simple font recovery:
NameToken[] orderedFallbacks = [NameToken.Type1, NameToken.TrueType];
foreach (var fallback in orderedFallbacks)
{
if (!handlers.TryGetValue(fallback, out handler))
{
continue;
}
try
{
return handler.Generate(dictionary);
}
catch (Exception ex)
{
log?.Error($"Tried to parse font as fallback type: {fallback}", ex);
}
}
throw new NotImplementedException($"Parsing not implemented for fonts of type: {subtype}, please submit a pull request or an issue.");
}
}

View File

@@ -1,41 +1,41 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<TargetFrameworks>netstandard2.0;net462;net471;net6.0;net8.0</TargetFrameworks>
<LangVersion>12</LangVersion>
<Version>0.1.11-alpha001</Version>
<IsTestProject>False</IsTestProject>
<GenerateDocumentationFile>true</GenerateDocumentationFile>
<SignAssembly>true</SignAssembly>
<AssemblyOriginatorKeyFile>..\pdfpig.snk</AssemblyOriginatorKeyFile>
<Nullable>enable</Nullable>
</PropertyGroup>
<ItemGroup>
<None Remove="Resources\CMap\*" />
<None Remove="Resources\ICC\*" />
</ItemGroup>
<ItemGroup>
<EmbeddedResource Include="Resources\CMap\*" />
<EmbeddedResource Include="Resources\ICC\*" />
</ItemGroup>
<ItemGroup>
<None Include="..\pdfpig.snk" Link="pdfpig.snk" />
</ItemGroup>
<ItemGroup>
<PackageReference Include="Microsoft.SourceLink.GitHub" Version="8.0.0">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers</IncludeAssets>
</PackageReference>
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)'=='net462'">
<PackageReference Include="System.ValueTuple" Version="4.5.0" />
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)'=='netstandard2.0' or '$(TargetFramework)'=='net462' or '$(TargetFramework)'=='net471'">
<PackageReference Include="System.Memory" Version="4.6.0" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\UglyToad.PdfPig.Core\UglyToad.PdfPig.Core.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig.Fonts\UglyToad.PdfPig.Fonts.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig.Tokenization\UglyToad.PdfPig.Tokenization.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig.Tokens\UglyToad.PdfPig.Tokens.csproj" />
</ItemGroup>
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<TargetFrameworks>netstandard2.0;net462;net471;net6.0;net8.0</TargetFrameworks>
<LangVersion>12</LangVersion>
<Version>0.1.12-alpha001</Version>
<IsTestProject>False</IsTestProject>
<GenerateDocumentationFile>true</GenerateDocumentationFile>
<SignAssembly>true</SignAssembly>
<AssemblyOriginatorKeyFile>..\pdfpig.snk</AssemblyOriginatorKeyFile>
<Nullable>enable</Nullable>
</PropertyGroup>
<ItemGroup>
<None Remove="Resources\CMap\*" />
<None Remove="Resources\ICC\*" />
</ItemGroup>
<ItemGroup>
<EmbeddedResource Include="Resources\CMap\*" />
<EmbeddedResource Include="Resources\ICC\*" />
</ItemGroup>
<ItemGroup>
<None Include="..\pdfpig.snk" Link="pdfpig.snk" />
</ItemGroup>
<ItemGroup>
<PackageReference Include="Microsoft.SourceLink.GitHub" Version="8.0.0">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers</IncludeAssets>
</PackageReference>
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)'=='net462'">
<PackageReference Include="System.ValueTuple" Version="4.5.0" />
</ItemGroup>
<ItemGroup Condition="'$(TargetFramework)'=='netstandard2.0' or '$(TargetFramework)'=='net462' or '$(TargetFramework)'=='net471'">
<PackageReference Include="System.Memory" Version="4.6.0" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\UglyToad.PdfPig.Core\UglyToad.PdfPig.Core.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig.Fonts\UglyToad.PdfPig.Fonts.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig.Tokenization\UglyToad.PdfPig.Tokenization.csproj" />
<ProjectReference Include="..\UglyToad.PdfPig.Tokens\UglyToad.PdfPig.Tokens.csproj" />
</ItemGroup>
</Project>

View File

@@ -1,5 +1,10 @@
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Globalization;
using System.IO;
using System.Linq;
using System.Text;
using Console = System.Console;
@@ -7,6 +12,128 @@ namespace UglyToad.PdfPig.ConsoleRunner
{
public static class Program
{
private class OptionalArg
{
public required string ShortSymbol { get; init; }
public required string Symbol { get; init; }
public required bool SupportsValue { get; init; }
public string? Value { get; set; }
}
private class ParsedArgs
{
public required IReadOnlyList<OptionalArg> SuppliedArgs { get; init; }
public required string SuppliedDirectoryPath { get; init; }
}
private const string FileSymbol = "f";
private const string RepeatSymbol = "r";
private static IReadOnlyList<OptionalArg> GetSupportedArgs() =>
[
new OptionalArg
{
SupportsValue = false,
ShortSymbol = "nr",
Symbol = "no-recursion"
},
new OptionalArg
{
SupportsValue = true,
ShortSymbol = "o",
Symbol = "output"
},
new OptionalArg
{
SupportsValue = true,
ShortSymbol = "l",
Symbol = "limit"
},
new OptionalArg
{
SupportsValue = true,
ShortSymbol = "f",
Symbol = "file"
},
new OptionalArg
{
SupportsValue = true,
ShortSymbol = "r",
Symbol = "repeats"
}
];
private static bool TryParseArgs(
string[] args,
[NotNullWhen(true)] out ParsedArgs? parsed)
{
parsed = null;
string? path = null;
var suppliedOpts = new List<OptionalArg>();
var opts = GetSupportedArgs();
for (var i = 0; i < args.Length; i++)
{
var str = args[i];
var isOptFlag = str.StartsWith('-');
if (!isOptFlag)
{
if (path == null)
{
path = str;
}
else
{
return false;
}
}
else
{
var item = opts.SingleOrDefault(x =>
string.Equals("-" + x.ShortSymbol, str, StringComparison.OrdinalIgnoreCase)
|| string.Equals("--" + x.Symbol, str, StringComparison.OrdinalIgnoreCase));
if (item == null)
{
return false;
}
if (item.SupportsValue)
{
if (i == args.Length - 1)
{
return false;
}
i++;
item.Value = args[i];
}
suppliedOpts.Add(item);
}
}
if (path == null)
{
return false;
}
parsed = new ParsedArgs
{
SuppliedArgs = suppliedOpts,
SuppliedDirectoryPath = path
};
return true;
}
public static int Main(string[] args)
{
if (args.Length == 0)
@@ -15,71 +142,140 @@ namespace UglyToad.PdfPig.ConsoleRunner
return 7;
}
var path = args[0];
if (!Directory.Exists(path))
if (!TryParseArgs(args, out var parsed))
{
Console.WriteLine($"The provided path is not a valid directory: {path}.");
var strJoined = string.Join(" ", args);
Console.WriteLine($"Unrecognized arguments passed: {strJoined}");
return 7;
}
var maxCount = default(int?);
if (args.Length > 1 && int.TryParse(args[1], out var countIn))
if (!Directory.Exists(parsed.SuppliedDirectoryPath))
{
maxCount = countIn;
Console.WriteLine($"The provided path is not a valid directory: {parsed.SuppliedDirectoryPath}.");
return 7;
}
int? maxCount = null;
var limit = parsed.SuppliedArgs.SingleOrDefault(x => x.ShortSymbol == "l");
if (limit?.Value != null && int.TryParse(limit.Value, CultureInfo.InvariantCulture, out var maxCountArg))
{
Console.WriteLine($"Limiting input files to first: {maxCountArg}");
maxCount = maxCountArg;
}
var noRecursionMode = parsed.SuppliedArgs.Any(x => x.ShortSymbol == "nr");
var outputOpt = parsed.SuppliedArgs.SingleOrDefault(x => x.ShortSymbol == "o" && x.Value != null);
var fileOpt = parsed.SuppliedArgs.SingleOrDefault(x => x.ShortSymbol == FileSymbol && x.Value != null);
var hasError = false;
var errorBuilder = new StringBuilder();
var fileList = Directory.GetFiles(path, "*.pdf", SearchOption.AllDirectories);
var fileList = Directory.GetFiles(
parsed.SuppliedDirectoryPath,
"*.pdf",
noRecursionMode ? SearchOption.TopDirectoryOnly : SearchOption.AllDirectories)
.OrderBy(x => x).ToList();
var runningCount = 0;
Console.WriteLine($"Found {fileList.Length} files.");
Console.WriteLine($"{GetCleanFilename("File")}| Size\t| Words\t| Pages");
foreach (var file in fileList)
if (fileOpt?.Value != null)
{
if (maxCount.HasValue && runningCount >= maxCount)
{
break;
}
fileList = fileList.Where(x => x.EndsWith(fileOpt.Value, StringComparison.OrdinalIgnoreCase)).ToList();
}
try
var repeatOpt = parsed.SuppliedArgs.SingleOrDefault(x => x.ShortSymbol == RepeatSymbol);
var repeats = 1;
if (repeatOpt?.Value != null && int.TryParse(repeatOpt.Value, CultureInfo.InvariantCulture, out repeats))
{
}
Console.WriteLine($"Found {fileList.Count} files.");
Console.WriteLine();
PrintTableColumns("File", "Size", "Words", "Pages", "Open cost (μs)", "Total cost (μs)", "Page cost (μs)");
var dataList = new List<DataRecord>();
var sw = new Stopwatch();
for (int i = 0; i < repeats; i++)
{
foreach (var file in fileList)
{
var numWords = 0;
var numPages = 0;
using (var pdfDocument = PdfDocument.Open(file))
if (maxCount.HasValue && runningCount >= maxCount)
{
foreach (var page in pdfDocument.GetPages())
{
numPages++;
foreach (var word in page.GetWords())
{
if (word != null)
{
numWords++;
}
}
}
break;
}
var filename = Path.GetFileName(file);
try
{
var numWords = 0;
var numPages = 0;
long openMicros;
long totalPageMicros;
var size = new FileInfo(file);
sw.Reset();
sw.Start();
Console.WriteLine($"{GetCleanFilename(filename)}| {size.Length}\t| {numWords}\t| {numPages}");
using (var pdfDocument = PdfDocument.Open(file))
{
sw.Stop();
openMicros = sw.Elapsed.Microseconds;
sw.Start();
foreach (var page in pdfDocument.GetPages())
{
numPages++;
foreach (var word in page.GetWords())
{
if (word != null)
{
numWords++;
}
}
}
sw.Stop();
totalPageMicros = sw.Elapsed.Microseconds;
}
var filename = Path.GetFileName(file);
var size = new FileInfo(file);
var item = new DataRecord
{
FileName = filename,
OpenCostMicros = openMicros,
Pages = numPages,
Size = size.Length,
Words = numWords,
TotalCostMicros = totalPageMicros + openMicros,
PerPageMicros = Math.Round(totalPageMicros / (double)Math.Max(numPages, 1), 2)
};
dataList.Add(item);
PrintTableColumns(
item.FileName,
item.Size,
item.Words,
item.Pages,
item.OpenCostMicros,
item.TotalCostMicros,
item.PerPageMicros);
}
catch (Exception ex)
{
hasError = true;
errorBuilder.AppendLine($"Parsing document {file} failed due to an error.")
.Append(ex)
.AppendLine();
}
runningCount++;
}
catch (Exception ex)
{
hasError = true;
errorBuilder.AppendLine($"Parsing document {file} failed due to an error.")
.Append(ex)
.AppendLine();
}
runningCount++;
}
if (hasError)
@@ -88,12 +284,71 @@ namespace UglyToad.PdfPig.ConsoleRunner
return 5;
}
if (outputOpt != null && outputOpt.Value != null)
{
WriteOutput(outputOpt.Value, dataList);
}
Console.WriteLine("Complete! :)");
return 0;
}
private static string GetCleanFilename(string name, int maxLength = 30)
private static void WriteOutput(string outPath, IReadOnlyList<DataRecord> records)
{
using var fs = File.OpenWrite(outPath);
using var sw = new StreamWriter(fs);
sw.WriteLine("File,Size,Words,Pages,Open Cost,Total Cost,Per Page");
foreach (var record in records)
{
var sizeStr = record.Size.ToString("D", CultureInfo.InvariantCulture);
var wordsStr = record.Words.ToString("D", CultureInfo.InvariantCulture);
var pagesStr = record.Pages.ToString("D", CultureInfo.InvariantCulture);
var openCostStr = record.OpenCostMicros.ToString("D", CultureInfo.InvariantCulture);
var totalCostStr = record.TotalCostMicros.ToString("D", CultureInfo.InvariantCulture);
var ppcStr = record.PerPageMicros.ToString("F2", CultureInfo.InvariantCulture);
var numericPartsStr = string.Join(",",
[
sizeStr,
wordsStr,
pagesStr,
openCostStr,
totalCostStr,
ppcStr
]);
sw.WriteLine($"\"{record.FileName}\",{numericPartsStr}");
}
sw.Flush();
}
private static void PrintTableColumns(params object[] values)
{
for (var i = 0; i < values.Length; i++)
{
var value = values[i];
var valueStr = value.ToString();
var cleaned = GetCleanStr(valueStr ?? string.Empty);
var padChars = 16 - cleaned.Length;
var padding = padChars > 0 ? new string(' ', padChars) : string.Empty;
var padded = cleaned + padding;
Console.Write("| ");
Console.Write(padded);
}
Console.WriteLine();
}
private static string GetCleanStr(string name, int maxLength = 16)
{
if (name.Length <= maxLength)
{
@@ -105,4 +360,21 @@ namespace UglyToad.PdfPig.ConsoleRunner
return name.Substring(0, maxLength);
}
}
internal class DataRecord
{
public required string FileName { get; init; }
public required long Size { get; init; }
public required int Words { get; init; }
public required int Pages { get; init; }
public required long OpenCostMicros { get; init; }
public required long TotalCostMicros { get; init; }
public required double PerPageMicros { get; init; }
}
}

View File

@@ -1,8 +1,8 @@
{
"profiles": {
"UglyToad.PdfPig.ConsoleRunner": {
"commandName": "Project",
"commandLineArgs": "\"C:\\temp\\pdfs\\archive\""
"commandName": "Project",
"commandLineArgs": "\"C:\\temp\\pdfs\\archive\""
}
}
}

View File

@@ -4,6 +4,7 @@
<LangVersion>latest</LangVersion>
<OutputType>Exe</OutputType>
<TargetFramework>net8</TargetFramework>
<Nullable>enable</Nullable>
</PropertyGroup>
<ItemGroup>

View File

@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<TargetFrameworks>netstandard2.0;net462;net471;net6.0;net8.0</TargetFrameworks>
<PackageId>PdfPig</PackageId>
@@ -11,9 +11,9 @@
<PackageTags>PDF;Reader;Document;Adobe;PDFBox;PdfPig;pdf-extract;pdf-to-text;pdf;file;text;C#;dotnet;.NET</PackageTags>
<RepositoryUrl>https://github.com/UglyToad/PdfPig</RepositoryUrl>
<GenerateDocumentationFile>true</GenerateDocumentationFile>
<Version>0.1.11-alpha001</Version>
<AssemblyVersion>0.1.10.0</AssemblyVersion>
<FileVersion>0.1.10.0</FileVersion>
<Version>0.1.12-alpha001</Version>
<AssemblyVersion>0.1.12.0</AssemblyVersion>
<FileVersion>0.1.12.0</FileVersion>
<PackageIconUrl>https://raw.githubusercontent.com/UglyToad/PdfPig/master/documentation/pdfpig.png</PackageIconUrl>
<PackageIcon>pdfpig.png</PackageIcon>
<Product>PdfPig</Product>