From 6a9de26ac3efbdd9931c74db90e2aeac2bc0dca8 Mon Sep 17 00:00:00 2001
From: Visuwesh <visuweshm@gmail.com>
Date: Sun, 6 Oct 2024 18:02:06 +0530
Subject: [PATCH] Make imenu index generation for PDFs more reliable

Do away with parsing the output of "mutool show FILE outline"
since the URI reported in its output may not include the page
number of the heading, and instead may contained "nameddest"
elements which cannot be resolved using "mutool".  Instead, use
a MuPDF JS script to generate the PDF outline allowing to
resolve such URIs.

* lisp/doc-view.el (doc-view--outline-rx): Remove as no longer
needed.
(doc-view--outline): Reflect that outline can be generated for
non-PDF files too.
(doc-view--mutool-pdf-outline-script): Add new variable to hold
the JS script used to generate the outline.
(doc-view--pdf-outline): Use the script.  (bug#73638)
---
 lisp/doc-view.el | 48 ++++++++++++++++++++++++++++++++----------------
 1 file changed, 32 insertions(+), 16 deletions(-)

diff --git a/lisp/doc-view.el b/lisp/doc-view.el
index 446beeafd9f..a5e84f1e2ab 100644
--- a/lisp/doc-view.el
+++ b/lisp/doc-view.el
@@ -1969,14 +1969,26 @@ doc-view-search-previous-match
 	(doc-view-goto-page (caar (last doc-view--current-search-matches)))))))
 
 ;;;; Imenu support
-(defconst doc-view--outline-rx
-  "[^\t]+\\(\t+\\)\"\\(.+\\)\"\t#\\(?:page=\\)?\\([0-9]+\\)")
-
 (defvar-local doc-view--outline nil
-  "Cached PDF outline, so that it is only computed once per document.
+  "Cached document outline, so that it is only computed once per document.
 It can be the symbol `unavailable' to indicate that outline is
 unavailable for the document.")
 
+(defvar doc-view--mutool-pdf-outline-script
+  "var document = new Document.openDocument(\"%s\", \"application/pdf\");
+var outline = document.loadOutline();
+if(!outline) quit();
+function pp(outl, level){print(\"((level . \" + level + \")\");\
+print(\"(title . \" + repr(outl.title) + \")\");\
+print(\"(page . \" + document.resolveLink(outl.uri) + \"))\");\
+if(outl.down){for(var i=0; i<outl.down.length; i++){pp(outl.down[i], level+1);}}};
+function run(){print(\"BEGIN(\");\
+for(var i=0; i<outline.length; i++){pp(outline[i], 1);}print(\")\");};
+run()"
+  "JS script to extract the PDF's outline using mutool.
+The script has to be minified to pass it to the REPL.  The \"BEGIN\"
+marker is here to skip past the prompt characters.")
+
 (defun doc-view--pdf-outline (&optional file-name)
   "Return a list describing the outline of FILE-NAME.
 Return a list describing the current file if FILE-NAME is nil.
@@ -1986,21 +1998,25 @@ doc-view--pdf-outline
 structure is extracted by `doc-view--imenu-subtree'."
   (let ((fn (or file-name (buffer-file-name))))
     (when fn
-      (let ((outline nil)
-            (fn (expand-file-name fn)))
-        (with-temp-buffer
-          (unless (eql 0 (call-process doc-view-pdfdraw-program nil
-                                       (current-buffer) nil "show" fn "outline"))
+      (with-temp-buffer
+        (let ((proc (make-process
+                     :name "doc-view-pdf-outline"
+                     :command (list "mutool" "run")
+                     :buffer (current-buffer))))
+          (process-send-string proc (format doc-view--mutool-pdf-outline-script
+                                            (expand-file-name fn)))
+          ;; Need to send this twice for some reason...
+          (process-send-eof)
+          (process-send-eof)
+          (while (accept-process-output proc))
+          (unless (eq (process-status proc) 'exit)
             (setq doc-view--outline 'unavailable)
             (imenu-unavailable-error "Unable to create imenu index using `mutool'"))
           (goto-char (point-min))
-          (while (re-search-forward doc-view--outline-rx nil t)
-            (push `((level . ,(length (match-string 1)))
-                    (title . ,(replace-regexp-in-string "\\\\[rt]" " "
-                                                        (match-string 2)))
-                    (page . ,(string-to-number (match-string 3))))
-                  outline)))
-        (nreverse outline)))))
+          (search-forward "BEGIN")
+          (condition-case nil
+              (read (current-buffer))
+            (end-of-file nil)))))))
 
 (defun doc-view--djvu-outline (&optional file-name)
   "Return a list describing the outline of FILE-NAME.
-- 
2.45.2