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
engine/tests/document_test.cpp
+31
View File
@@ -343,4 +343,35 @@ TEST(TextExtractionTest, ExtractUtf8ExtendedText) {
EXPECT_FALSE(text.empty());
}
TEST(TextExtractionTest, ExtractTextWithBounds) {
SKIP_IF_NO_PDFIUM();
auto path = getCorpusPath("basic", "hello_world.pdf");
if (!std::filesystem::exists(path)) {
GTEST_SKIP() << "hello_world.pdf not found in corpus.";
}
auto docRes = PdfDocument::loadFromFile(path.string());
ASSERT_TRUE(docRes.has_value());
auto pageRes = (*docRes)->getPage(0);
ASSERT_TRUE(pageRes.has_value());
auto boundsRes = (*pageRes)->extractTextWithBounds();
ASSERT_TRUE(boundsRes.has_value());
const auto& glyphs = *boundsRes;
ASSERT_FALSE(glyphs.empty());
bool found_hello = false;
for (const auto& glyph : glyphs) {
EXPECT_FALSE(glyph.text.empty());
EXPECT_GT(glyph.w, 0.0);
EXPECT_GT(glyph.h, 0.0);
EXPECT_GT(glyph.fontSize, 0.0);
if (glyph.text == "H" || glyph.text == "e" || glyph.text == "l" || glyph.text == "o") {
found_hello = true;
}
}
EXPECT_TRUE(found_hello);
}
}