1 files changed, 53 insertions(+), 0 deletions(-)

M gnu/packages/pdf.scm

@@ 101,6 101,7 @@
   #:use-module (gnu packages nss)
   #:use-module (gnu packages ocaml)
   #:use-module (gnu packages ocr)
+  #:use-module (gnu packages package-management)
   #:use-module (gnu packages pcre)
   #:use-module (gnu packages perl)
   #:use-module (gnu packages photo)


@@ 1144,6 1145,58 @@ Open XML Paper Specification}, @acronym{CBZ, Comic Book ZI}P, @acronym{EPUB,
 Electronic Publication} and @acronym{FB2, Fiction Book 2} (e-books) format.")
     (license license:agpl3)))
 
+(define-public pdf-tocgen
+  (package
+    (name "pdf-tocgen")
+    (version "1.3.4")
+    (source
+     (origin
+       (method git-fetch)
+       (uri (git-reference
+              (url "https://github.com/Krasjet/pdf.tocgen")
+              (commit (string-append "v" version))))
+       (file-name (git-file-name name version))
+       (sha256
+        (base32 "0sqqnrw6zw2awcf9g6v66fm9nnrv2xm3l5ql1liq9skilkjkgkx3"))))
+    (build-system pyproject-build-system)
+    (arguments
+     (list
+      ;; A required file is missing, seemingly causing the test suite to fail,
+      ;; see https://github.com/Krasjet/pdf.tocgen/issues/41
+      #:tests? #f
+      #:phases #~(modify-phases %standard-phases
+                   (add-after 'unpack 'patch-tests
+                     ;; The test suite wants to run all commands with poetry,
+                     ;; this is superfluous and causes errors, so we disable that.
+                     (lambda _
+                       (substitute* "Makefile"
+                         (("@poetry run ") ""))))
+                   (replace 'check
+                     (lambda* (#:key tests? #:allow-other-keys)
+                       (when tests?
+                         (invoke "make" "test")))))))
+    (native-inputs (list poetry
+                         python-poetry-core
+                         python-mamba
+                         python-pylint))
+    (propagated-inputs (list
+                        python-chardet
+                        python-jedi
+                        python-pymupdf
+                        python-toml))
+    (home-page "https://krasjet.com/voice/pdf.tocgen/")
+    (synopsis "Automatically generate table of contents for pdf files")
+    (description "pdf.tocgen is a set of command-line tools for automatically
+extracting and generating the table of contents of a PDF file. It uses
+the embedded font attributes and position of headings to deduce the basic
+outline of a PDF file.
+
+It works best for PDF files produced from a TeX document, but it's designed to
+work with any software-generated PDF files (i.e. you shouldn't expect it to
+work with scanned PDFs). Some examples include troff/groff, Adobe InDesign,
+LibreOffice Writer, and probably more.")
+    (license license:gpl3+)))
+
 (define-public qpdf
   (package
     (name "qpdf")