maskantech/pdf
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

feat: implemented text extraction with bounding boxes

Browse Source
This commit is contained in:
Furqan-14
2026-05-25 14:47:38 +05:30
parent 5ce96ebd5d
commit f961c579bc
8 changed files with 165 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
bindings/python/pdfengine_py.cpp
+15
View File
@@ -96,6 +96,21 @@ PYBIND11_MODULE(pdfengine, m) {
.def("extract_text", [](const pdfengine::PdfPage& self) {
return get_or_throw(self.extractText());
})
.def("extract_text_with_bounds", [](const pdfengine::PdfPage& self) {
auto res = get_or_throw(self.extractTextWithBounds());
py::list py_list;
for (const auto& glyph : res) {
py::dict d;
d["text"] = glyph.text;
d["x"] = glyph.x;
d["y"] = glyph.y;
d["w"] = glyph.w;
d["h"] = glyph.h;
d["fontSize"] = glyph.fontSize;
py_list.append(d);
}
return py_list;
})
.def("page_to_device", &pdfengine::PdfPage::pageToDevice,
py::arg("page_point"), py::arg("device_width"), py::arg("device_height"), py::arg("rotate") = 0)
.def("device_to_page", &pdfengine::PdfPage::deviceToPage,