Skip to content
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

not add space character for CJK. #353

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

not add space character for CJK. #353

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
30f24db
not add space character for CJK.
Jun 22, 2018
d6267b5
fix qt low version problem
no6no6 Jun 29, 2018
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
16 changes: 16 additions & 0 deletions qt/src/Utils.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -221,3 +221,19 @@ QString Utils::getSpellingLanguage(const QString& lang) {
}
return syslang;
}

// Unicode blocks http://www.fileformat.info/info/unicode/block/index.htm
bool Utils::spacedWord(const QString& text, bool prevWord) {
short unicode = (prevWord ? text.at(text.size()-1) : text.at(0)).unicode();
// CJK Word
std::vector<std::pair<int, int>> cjkWordRange{{0x2480, 0x303f}, {0x31c0, 0x9fff}
, {0xf900, 0xfaff}, {0xfe30, 0xfe4f}, {0x20000, 0x2fa1f}};
for(int i = 0; i < cjkWordRange.size(); i++) {
if(unicode < cjkWordRange[i].first) {
return true;
} else if(unicode >= cjkWordRange[i].first && unicode <= cjkWordRange[i].second) {
return false;
}
}
return true;
}
2 changes: 2 additions & 0 deletions qt/src/Utils.hh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,8 @@ QByteArray download(QUrl url, QString& messages, int timeout = 60000);

QString getSpellingLanguage(const QString& lang = QString());

bool spacedWord(const QString& text, bool prevWord);

template<typename T>
class AsyncQueue {
public:
Expand Down
17 changes: 14 additions & 3 deletions qt/src/hocr/HOCRPdfExporter.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -685,6 +685,8 @@ void HOCRPdfExporter::printChildren(PDFPainter& painter, const HOCRItem* item, c
QString itemClass = item->itemClass();
QRect itemRect = item->bbox();
int childCount = item->children().size();
bool prevSpacedWord, currentSpacedWord;
prevSpacedWord = currentSpacedWord = false;
if(itemClass == "ocr_par" && pdfSettings.uniformizeLineSpacing) {
double yInc = double(itemRect.height()) / childCount;
double y = itemRect.top() + yInc;
Expand All @@ -703,15 +705,24 @@ void HOCRPdfExporter::printChildren(PDFPainter& painter, const HOCRItem* item, c
if(pdfSettings.fontSize == -1) {
painter.setFontSize(wordItem->fontSize() * pdfSettings.detectedFontScaling);
}

prevWordRight = wordRect.right();
QString text = wordItem->text();
currentSpacedWord = Utils::spacedWord(text, false);
// If distance from previous word is large, keep the space
if(wordRect.x() - prevWordRight > pdfSettings.preserveSpaceWidth * painter.getAverageCharWidth() / px2pu) {
x = wordRect.x();
} else {
//need space
if(currentSpacedWord && prevSpacedWord ) {
x += painter.getTextWidth(" ") / px2pu;
}
}
prevWordRight = wordRect.right();
QString text = wordItem->text();

double wordBaseline = (x - itemRect.x()) * baseline.first + baseline.second;
painter.drawText(x * px2pu, (y + wordBaseline) * px2pu, text);
x += painter.getTextWidth(text + " ") / px2pu;
x += painter.getTextWidth(text) / px2pu;
prevSpacedWord = Utils::spacedWord(text, true);
}
}
} else if(itemClass == "ocr_line" && !pdfSettings.uniformizeLineSpacing) {
Expand Down