@@ -8990,6 +8990,55 @@ (define-public python-pdftotext
(description "Pdftotext is a Python library of PDF text extraction.")
(license license:expat)))
+(define-public python-pymupdf
+ (package
+ (name "python-pymupdf")
+ (version "1.24.7")
+ (source
+ (origin
+ (method url-fetch)
+ (uri (pypi-uri "PyMuPDF" version))
+ (sha256
+ (base32 "1f2r7c0nfw2g49q8fgf0kwkadihnf6c47pa93zavl5gj0kiflk53"))))
+ (build-system pyproject-build-system)
+ (inputs
+ (list
+ mupdf/tesseract))
+ (native-inputs
+ (list
+ python-pillow
+ python-pytest
+ python-psutil
+ swig))
+ (propagated-inputs (list mupdf))
+ (arguments
+ (list
+ ;; Disable failing tests
+ #:test-flags
+ '(list
+ "-k" (string-append
+ "not test_flake8"
+ " and not test_fontarchive"
+ " and not test_subset_fonts"
+ " and not test_color_count"
+ " and not test_3050"
+ " and not test_pylint"
+ " and not test_textbox3"))
+ #:phases
+ '(modify-phases %standard-phases
+ (add-after 'unpack 'setenv
+ (lambda _
+ (setenv "PYMUPDF_SETUP_MUPDF_BUILD" "")
+ (setenv "PYMUPDF_SETUP_IMPLEMENTATIONS" "b"))))))
+ (home-page "https://github.com/pymupdf/PyMuPDF")
+ (synopsis
+ "Python library for the analysis and manipulation of PDF files")
+ (description
+ "This package provides a high performance Python library for data
+extraction, analysis, conversion & manipulation of PDF (and other)
+documents.")
+ (license license:agpl3+)))
+
(define-public python-pluginbase
(package
(name "python-pluginbase")