lsm/PdfPig
1
0
Fork 0
mirror of https://github.com/UglyToad/PdfPig.git synced 2025-09-20 20:07:57 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

merge pull request #72 from uglytoad/fix-export-formatting

Browse Source 
fix export formatting
This commit is contained in:
Eliot Jones
2019-10-17 11:28:06 +01:00
committed by GitHub
parent 3f1321141a 09b26c43e0
commit a2147902a0
54 changed files with 2906 additions and 5143 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
src/UglyToad.PdfPig.Tests/Integration/PigProductionHandbookTests.cs
View File

@@ -4,6 +4,11 @@
using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Text;
using System.Xml;
using System.Xml.Linq;
using DocumentLayoutAnalysis;
using Export;
using Xunit;
public class PigProductionHandbookTests
@@ -32,7 +37,7 @@
var page = document.GetPage(1);
// Pinkish.
var (r, g , b) = page.Letters[0].Color.ToRGBValues();
var (r, g, b) = page.Letters[0].Color.ToRGBValues();
Assert.Equal(1, r);
Assert.Equal(0.914m, g);
@@ -98,7 +103,7 @@
[Fact]
public void Page4HasCorrectWords()
{
var expected = WordsPage4.Split(new[] {"\r", "\r\n", "\n", " "}, StringSplitOptions.RemoveEmptyEntries);
var expected = WordsPage4.Split(new[] { "\r", "\r\n", "\n", " " }, StringSplitOptions.RemoveEmptyEntries);
using (var document = PdfDocument.Open(GetFilename(), ParsingOptions.LenientParsingOff))
{
var page = document.GetPage(4);
@@ -129,6 +134,41 @@
}
}
[Fact]
public void CanExportAltoXmlFormat()
{
using (var document = PdfDocument.Open(GetFilename(), ParsingOptions.LenientParsingOff))
{
var exporter = new AltoXmlTextExporter(new NearestNeighbourWordExtractor(), new DocstrumBoundingBoxes());
var xml = exporter.Get(document.GetPage(4), true);
Assert.NotNull(xml);
using (var xmlStream = new MemoryStream(Encoding.UTF8.GetBytes(xml)))
using (var xmlReader = new XmlTextReader(xmlStream))
{
var xDocument = XDocument.Load(xmlReader);
Assert.NotNull(xDocument);
}
}
}
[Fact]
public void CanExportAltoXmlFormatPage16()
{
// Page 16 contains an unprintable string and a single line of text which causes problems for Docstrum.
using (var document = PdfDocument.Open(GetFilename(), ParsingOptions.LenientParsingOff))
{
var exporter = new AltoXmlTextExporter(new NearestNeighbourWordExtractor(), new DocstrumBoundingBoxes());
var xml = exporter.Get(document.GetPage(16), true);
Assert.NotNull(xml);
using (var xmlStream = new MemoryStream(Encoding.UTF8.GetBytes(xml)))
using (var xmlReader = new XmlTextReader(xmlStream))
{
var xDocument = XDocument.Load(xmlReader);
Assert.NotNull(xDocument);
}
}
}
[Fact]
public void LettersHaveCorrectPosition()
{