Skip to content

Fix duplicated IDs in ALTO XML when multiple pages are present #4386

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

Merged
stweil merged 2 commits into from
May 1, 2025
Merged

Fix duplicated IDs in ALTO XML when multiple pages are present #4386

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c702b48
Fix alto xml duplicates IDs when multiple pages are present
jankal Jan 25, 2025
c6b7e05
Convert ALTO XML ID generation to conditional code based on the curre…
jankal Jan 26, 2025
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
26 changes: 20 additions & 6 deletions src/api/altorenderer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,20 @@ static void AddBoxToAlto(const ResultIterator *it, PageIteratorLevel level,
}
}

static std::string GetID(const char *prefix, int page_number, int counter) {
std::stringstream idstr;
// IDs will only have the counter for the first page to keep them consistent
// with the IDs assigned before this change was made.
// From the second page on, IDs will also contain the page number to make them unique.
if (page_number == 0) {
idstr << prefix << "_" << counter;
} else {
idstr << prefix << "_" << page_number << "_" << counter;
}

return idstr.str();
}

///
/// Append the ALTO XML for the beginning of the document
///
Expand Down Expand Up @@ -168,7 +182,7 @@ char *TessBaseAPI::GetAltoText(ETEXT_DESC *monitor, int page_number) {
case PT_PULLOUT_IMAGE: {
// Handle all kinds of images.
// TODO: optionally add TYPE, for example TYPE="photo".
alto_str << "\t\t\t\t<Illustration ID=\"cblock_" << bcnt++ << "\"";
alto_str << "\t\t\t\t<Illustration ID=\"" << GetID("cblock", page_number, bcnt++) << "\"";
AddBoxToAlto(res_it.get(), RIL_BLOCK, alto_str);
alto_str << "</Illustration>\n";
res_it->Next(RIL_BLOCK);
Expand All @@ -177,7 +191,7 @@ char *TessBaseAPI::GetAltoText(ETEXT_DESC *monitor, int page_number) {
case PT_HORZ_LINE:
case PT_VERT_LINE:
// Handle horizontal and vertical lines.
alto_str << "\t\t\t\t<GraphicalElement ID=\"cblock_" << bcnt++ << "\"";
alto_str << "\t\t\t\t<GraphicalElement ID=\"" << GetID("cblock", page_number, bcnt++) << "\"";
AddBoxToAlto(res_it.get(), RIL_BLOCK, alto_str);
alto_str << "</GraphicalElement >\n";
res_it->Next(RIL_BLOCK);
Expand All @@ -190,24 +204,24 @@ char *TessBaseAPI::GetAltoText(ETEXT_DESC *monitor, int page_number) {
}

if (res_it->IsAtBeginningOf(RIL_BLOCK)) {
alto_str << "\t\t\t\t<ComposedBlock ID=\"cblock_" << bcnt << "\"";
alto_str << "\t\t\t\t<ComposedBlock ID=\"" << GetID("cblock", page_number, bcnt) << "\"";
AddBoxToAlto(res_it.get(), RIL_BLOCK, alto_str);
alto_str << "\n";
}

if (res_it->IsAtBeginningOf(RIL_PARA)) {
alto_str << "\t\t\t\t\t<TextBlock ID=\"block_" << tcnt << "\"";
alto_str << "\t\t\t\t\t<TextBlock ID=\"" << GetID("block", page_number, tcnt) << "\"";
AddBoxToAlto(res_it.get(), RIL_PARA, alto_str);
alto_str << "\n";
}

if (res_it->IsAtBeginningOf(RIL_TEXTLINE)) {
alto_str << "\t\t\t\t\t\t<TextLine ID=\"line_" << lcnt << "\"";
alto_str << "\t\t\t\t\t\t<TextLine ID=\"" << GetID("line", page_number, lcnt) << "\"";
AddBoxToAlto(res_it.get(), RIL_TEXTLINE, alto_str);
alto_str << "\n";
}

alto_str << "\t\t\t\t\t\t\t<String ID=\"string_" << wcnt << "\"";
alto_str << "\t\t\t\t\t\t\t<String ID=\"" << GetID("string", page_number, wcnt) << "\"";
AddBoxToAlto(res_it.get(), RIL_WORD, alto_str);
alto_str << " CONTENT=\"";

Expand Down
Loading