Skip to content

XliffCompare: Make non-breaking space edits visible in report #1044

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
murxh wants to merge 6 commits into
base: master
Choose a base branch
from
Open

XliffCompare: Make non-breaking space edits visible in report #1044

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
5b6a17e
XliffCompare fix: Make non-breaking space edits visible
murxh Jun 17, 2022
2c2ceea
Merge branch 'RWS:master' into master
murxh Jun 17, 2022
d18b72a
Merge branch 'RWS:master' into master
murxh Nov 22, 2023
1a9cef7
StudioViews ExportFiles():
murxh Nov 22, 2023
17966f9
Update ProjectFileService.cs
murxh Dec 8, 2024
ae4ce1a
Merge pull request #1 from murxh/murxh-patch-1
murxh Dec 8, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
103 changes: 59 additions & 44 deletions SdlXliff Compare/Sdl.Community.XliffCompare.Core/Comparer/TextComparer/TextComparer.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -329,50 +329,65 @@ internal static WordsCollection Parse(List<SDLXLIFF.SegmentSection> xSegmentSect
else
{

while (curPos < xSegmentSection.Content.Length)
{
var prevPos = curPos;
while (curPos < xSegmentSection.Content.Length &&
(char.IsControl(xSegmentSection.Content[curPos])
|| char.IsWhiteSpace(xSegmentSection.Content[curPos])))
{
curPos++;
}
prefix += xSegmentSection.Content.Substring(prevPos, curPos - prevPos);

if (curPos == xSegmentSection.Content.Length)
{

if (prefix != string.Empty)
{
words.Add(new Word(string.Empty, prefix, string.Empty));
}
break;
}

prevPos = curPos;
while (curPos < xSegmentSection.Content.Length &&
!char.IsControl(xSegmentSection.Content[curPos]) &&
!char.IsWhiteSpace(xSegmentSection.Content[curPos]))
{
curPos++;
}
var word = xSegmentSection.Content.Substring(prevPos, curPos - prevPos);


prevPos = curPos;
while (curPos < xSegmentSection.Content.Length &&
(char.IsControl(xSegmentSection.Content[curPos]) ||
char.IsWhiteSpace(xSegmentSection.Content[curPos])))
{
curPos++;
}
suffix = xSegmentSection.Content.Substring(prevPos, curPos - prevPos);
ProcessWord(words, prefix, word, suffix);
prefix = string.Empty;
}
}
}
while (curPos < xSegmentSection.Content.Length)
{
var prevPos = curPos;
while (curPos < xSegmentSection.Content.Length &&
xSegmentSection.Content[curPos] != '\xa0' && // stop at nbsp
(char.IsControl(xSegmentSection.Content[curPos])
|| char.IsWhiteSpace(xSegmentSection.Content[curPos])))
{
curPos++;
}
prefix += xSegmentSection.Content.Substring(prevPos, curPos - prevPos);

if (curPos == xSegmentSection.Content.Length)
{

if (prefix != string.Empty)
{
words.Add(new Word(string.Empty, prefix, string.Empty));
}
break;
}

prevPos = curPos;

if (xSegmentSection.Content[curPos] == '\xa0') // make nbsp a word
{
// a word may be a string of non-breaking spaces ...
while (xSegmentSection.Content[curPos] == '\xa0')
{
curPos++;
}
}
else
{
// ... or a string of non-whitespace/non-control
while (curPos < xSegmentSection.Content.Length &&
!char.IsControl(xSegmentSection.Content[curPos]) &&
!char.IsWhiteSpace(xSegmentSection.Content[curPos]))
{
curPos++;
}
}
var word = xSegmentSection.Content.Substring(prevPos, curPos - prevPos);


prevPos = curPos;
while (curPos < xSegmentSection.Content.Length &&
xSegmentSection.Content[curPos] != '\xa0' && // stop at nbsp
(char.IsControl(xSegmentSection.Content[curPos]) ||
char.IsWhiteSpace(xSegmentSection.Content[curPos])))
{
curPos++;
}
suffix = xSegmentSection.Content.Substring(prevPos, curPos - prevPos);
ProcessWord(words, prefix, word, suffix);
prefix = string.Empty;
}
}
}
return words;
}

Expand Down
11 changes: 10 additions & 1 deletion StudioViews/StudioViews/Services/ProjectFileService.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -242,7 +242,16 @@ public List<ProjectFileInfo> GetProjectFiles(string filePath)

try
{
var xml = XDocument.Load(filePath, LoadOptions.PreserveWhitespace);
//var xml = XDocument.Load(filePath, LoadOptions.PreserveWhitespace);
XDocument xml = null;
// avoid System.Xml.XmlException Message: '?', hexadecimal value 0x1C, 0x1E, ... is an invalid character.
XmlReaderSettings xmlReaderSettings = new XmlReaderSettings { CheckCharacters = false };
using (XmlReader xmlReader = XmlReader.Create(filePath, xmlReaderSettings))
{
xmlReader.MoveToContent();
xml = XDocument.Load(xmlReader, LoadOptions.PreserveWhitespace);
}

var xliff = xml.Root;
if (xliff != null &&
string.Compare(xliff.Name.LocalName, "xliff", StringComparison.InvariantCultureIgnoreCase) == 0)
Expand Down
5 changes: 3 additions & 2 deletions StudioViews/StudioViews/ViewModel/StudioViewsEditorViewModel.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -835,8 +835,9 @@ private ExportResult ExportFiles(IReadOnlyCollection<ProjectFile> projectFiles,
InputFiles = new List<string>(projectFiles.Select(a => a.LocalFilePath))
};

var sourceLanguage = projectFiles.FirstOrDefault()?.SourceFile.Language.CultureInfo;
var targetLanguage = projectFiles.FirstOrDefault()?.Language.CultureInfo;
// UNNECESSARY AND POSSIBLY A SOURCE FOR ERROR: SourceFile might be null in a WorldServer project
//var sourceLanguage = projectFiles.FirstOrDefault()?.SourceFile.Language.CultureInfo;
//var targetLanguage = projectFiles.FirstOrDefault()?.Language.CultureInfo;

foreach (var documentFile in projectFiles)
{
Expand Down