From 8a046c897e42e9459aa99377589c80c773601efc Mon Sep 17 00:00:00 2001 From: Lukasz Kasprzak Date: Tue, 15 Sep 2026 00:02:37 +0200 Subject: tests read real documents from LibreOffice and pandoc; antiword's short-document limit documented --- internal/extract/testdata/real/book.epub | Bin 0 -> 4886 bytes internal/extract/testdata/real/doc.doc | Bin 0 -> 22528 bytes internal/extract/testdata/real/doc.docx | Bin 0 -> 6041 bytes internal/extract/testdata/real/doc.odt | Bin 0 -> 8506 bytes internal/extract/testdata/real/doc.pdf | Bin 0 -> 37442 bytes internal/extract/testdata/real/sheet.ods | Bin 0 -> 8686 bytes internal/extract/testdata/real/sheet.xls | Bin 0 -> 5632 bytes internal/extract/testdata/real/sheet.xlsx | Bin 0 -> 5538 bytes internal/extract/testdata/real/slides.pptx | Bin 0 -> 27659 bytes 9 files changed, 0 insertions(+), 0 deletions(-) create mode 100644 internal/extract/testdata/real/book.epub create mode 100644 internal/extract/testdata/real/doc.doc create mode 100644 internal/extract/testdata/real/doc.docx create mode 100644 internal/extract/testdata/real/doc.odt create mode 100644 internal/extract/testdata/real/doc.pdf create mode 100644 internal/extract/testdata/real/sheet.ods create mode 100644 internal/extract/testdata/real/sheet.xls create mode 100644 internal/extract/testdata/real/sheet.xlsx create mode 100644 internal/extract/testdata/real/slides.pptx (limited to 'internal/extract/testdata/real') diff --git a/internal/extract/testdata/real/book.epub b/internal/extract/testdata/real/book.epub new file mode 100644 index 0000000..741b3a7 Binary files /dev/null and b/internal/extract/testdata/real/book.epub differ diff --git a/internal/extract/testdata/real/doc.doc b/internal/extract/testdata/real/doc.doc new file mode 100644 index 0000000..8520659 Binary files /dev/null and b/internal/extract/testdata/real/doc.doc differ diff --git a/internal/extract/testdata/real/doc.docx b/internal/extract/testdata/real/doc.docx new file mode 100644 index 0000000..7bc9d04 Binary files /dev/null and b/internal/extract/testdata/real/doc.docx differ diff --git a/internal/extract/testdata/real/doc.odt b/internal/extract/testdata/real/doc.odt new file mode 100644 index 0000000..d3d287e Binary files /dev/null and b/internal/extract/testdata/real/doc.odt differ diff --git a/internal/extract/testdata/real/doc.pdf b/internal/extract/testdata/real/doc.pdf new file mode 100644 index 0000000..b46e40e Binary files /dev/null and b/internal/extract/testdata/real/doc.pdf differ diff --git a/internal/extract/testdata/real/sheet.ods b/internal/extract/testdata/real/sheet.ods new file mode 100644 index 0000000..0bb783a Binary files /dev/null and b/internal/extract/testdata/real/sheet.ods differ diff --git a/internal/extract/testdata/real/sheet.xls b/internal/extract/testdata/real/sheet.xls new file mode 100644 index 0000000..ee64a9d Binary files /dev/null and b/internal/extract/testdata/real/sheet.xls differ diff --git a/internal/extract/testdata/real/sheet.xlsx b/internal/extract/testdata/real/sheet.xlsx new file mode 100644 index 0000000..9788970 Binary files /dev/null and b/internal/extract/testdata/real/sheet.xlsx differ diff --git a/internal/extract/testdata/real/slides.pptx b/internal/extract/testdata/real/slides.pptx new file mode 100644 index 0000000..5ee037c Binary files /dev/null and b/internal/extract/testdata/real/slides.pptx differ -- cgit v1.3