Re: Bug: Plain https links with brackets are not recognised [9.4.4 (release_9.4.4-625-g763c7a @ /home/yantar92/.emacs.d/straight/build/org/)]

[Ihor Radchenko <yantar92@gmail.com>]

[-- Attachment #1: Type: text/plain, Size: 561 bytes --]

Updated version of the patch.

Ihor Radchenko <yantar92@gmail.com> writes:

> Nicolas Goaziou <mail@nicolasgoaziou.fr> writes:
>> Actually, this is (was?) intentional. By forbidding parenthesis in
>> a plain URL, you allow one to type, e.g., (https://orgmode.org), which
>> is, IMO, a more frequent need than having to deal with parenthesis in
>> the URL.
>
> The patch correctly recognises situations like this.
> https://orgmode.org is recognised correctly without parenthesis.
>
> I guess this example may be another addition to the tests.
>
> Best,
> Ihor


[-- Attachment #2: 0001-Improve-org-link-plain-re.patch --]
[-- Type: text/x-diff, Size: 6531 bytes --]

From 08efc990a578c925d42315c45e0b9b76536b92af Mon Sep 17 00:00:00 2001
From: Ihor Radchenko <yantar92@gmail.com>
Date: Wed, 24 Mar 2021 21:27:24 +0800
Subject: [PATCH] Improve org-link-plain-re

(org-link-plain-re): Update docstring.  Now, the docstring explicitly
mentions that the regexp must contain groups for the link type and the
path.

* lisp/ol.el (org-link-make-regexps): Allow URLs with up to two levels
of nested brackets.  Now, URLs like [1] can be matched.  The new
regexp is based on [2].

* testing/lisp/test-ol.el: Add tests for the plain link regexp

[1] https://doi.org/10.1016/0160-791x(79)90023-x
[2] https://daringfireball.net/2010/07/improved_regex_for_matching_urls
---
 lisp/ol.el              |  41 +++++++++++----
 testing/lisp/test-ol.el | 110 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 141 insertions(+), 10 deletions(-)

diff --git a/lisp/ol.el b/lisp/ol.el
index b8bd7d234..550c0cff6 100644
--- a/lisp/ol.el
+++ b/lisp/ol.el
@@ -519,7 +519,10 @@ links more efficient."
   "Matches link with angular brackets, spaces are allowed.")
 
 (defvar org-link-plain-re nil
-  "Matches plain link, without spaces.")
+  "Matches plain link, without spaces.
+Group 1 must contain the link type (i.e. https).
+Group 2 must contain the link path (i.e. //example.com).
+Used by `org-element-link-parser'.")
 
 (defvar org-link-bracket-re nil
   "Matches a link in double brackets.")
@@ -807,15 +810,33 @@ This should be called after the variable `org-link-parameters' has changed."
 	  (format "<%s:\\([^>\n]*\\(?:\n[ \t]*[^> \t\n][^>\n]*\\)*\\)>"
 		  types-re)
 	  org-link-plain-re
-	  (concat
-	   "\\<" types-re ":"
-	   "\\([^][ \t\n()<>]+\\(?:([[:word:]0-9_]+)\\|\\([^[:punct:] \t\n]\\|/\\)\\)\\)")
-	  ;;	 "\\([^]\t\n\r<>() ]+[^]\t\n\r<>,.;() ]\\)")
-	  org-link-bracket-re
-	  (rx (seq "[["
-		   ;; URI part: match group 1.
-		   (group
-		    (one-or-more
+          (let* ((non-space-bracket "[^][ \t\n()<>]")
+	         (parenthesis
+		  `(seq "("
+		        (0+ (or (regex ,non-space-bracket)
+			        (seq "("
+				     (0+ (regex ,non-space-bracket))
+				     ")")))
+		        ")")))
+	    ;; Heuristics for an URL link inspired by
+	    ;; https://daringfireball.net/2010/07/improved_regex_for_matching_urls
+	    (rx-to-string
+	     `(seq word-start
+                   ;; Link type: match group 1.
+		   (regexp ,types-re)
+		   ":"
+                   ;; Link path: match group 2.
+                   (group
+		    (1+ (or (regex ,non-space-bracket)
+			    ,parenthesis))
+		    (or (regexp "[^[:punct:] \t\n]")
+		        ?/
+		        ,parenthesis)))))
+          org-link-bracket-re
+          (rx (seq "[["
+	           ;; URI part: match group 1.
+	           (group
+	            (one-or-more
                      (or (not (any "[]\\"))
 			 (and "\\" (zero-or-more "\\\\") (any "[]"))
 			 (and (one-or-more "\\") (not (any "[]"))))))
diff --git a/testing/lisp/test-ol.el b/testing/lisp/test-ol.el
index 5b7dc513b..ddcc570b3 100644
--- a/testing/lisp/test-ol.el
+++ b/testing/lisp/test-ol.el
@@ -491,5 +491,115 @@
 	      (org-previous-link))
 	    (buffer-substring (point) (line-end-position))))))
 
+\f
+;;; Link regexps
+
+
+(defmacro test-ol-parse-link-in-text (text)
+  "Return list of :type and :path of link parsed in TEXT.
+\"<point>\" string must be at the beginning of the link to be parsed."
+  (declare (indent 1))
+  `(org-test-with-temp-text ,text
+     (list (org-element-property :type (org-element-link-parser))
+           (org-element-property :path (org-element-link-parser)))))
+
+(ert-deftest test-ol/plain-link-re ()
+  "Test `org-link-plain-re'."
+  (should
+   (equal
+    '("https" "//example.com")
+    (test-ol-parse-link-in-text
+        "(<point>https://example.com)")))
+  (should
+   (equal
+    '("https" "//example.com/qwe()")
+    (test-ol-parse-link-in-text
+        "(Some text <point>https://example.com/qwe())")))
+  (should
+   (equal
+    '("https" "//doi.org/10.1016/0160-791x(79)90023-x")
+    (test-ol-parse-link-in-text
+        "<point>https://doi.org/10.1016/0160-791x(79)90023-x")))
+  (should
+   (equal
+    '("file" "aa")
+    (test-ol-parse-link-in-text
+        "The <point>file:aa link")))
+  (should
+   (equal
+    '("file" "a(b)c")
+    (test-ol-parse-link-in-text
+        "The <point>file:a(b)c link")))
+  (should
+   (equal
+    '("file" "a()")
+    (test-ol-parse-link-in-text
+        "The <point>file:a() link")))
+  (should
+   (equal
+    '("file" "aa((a))")
+    (test-ol-parse-link-in-text
+        "The <point>file:aa((a)) link")))
+  (should
+   (equal
+    '("file" "aa(())")
+    (test-ol-parse-link-in-text
+        "The <point>file:aa(()) link")))
+  (should
+   (equal
+    '("file" "/a")
+    (test-ol-parse-link-in-text
+        "The <point>file:/a link")))
+  (should
+   (equal
+    '("file" "/a/")
+    (test-ol-parse-link-in-text
+        "The <point>file:/a/ link")))
+  (should
+   (equal
+    '("http" "//")
+    (test-ol-parse-link-in-text
+        "The <point>http:// link")))
+  (should
+   (equal
+    '("file" "ab")
+    (test-ol-parse-link-in-text
+        "The (some <point>file:ab) link")))
+  (should
+   (equal
+    '("file" "aa")
+    (test-ol-parse-link-in-text
+        "The <point>file:aa) link")))
+  (should
+   (equal
+    '("file" "aa")
+    (test-ol-parse-link-in-text
+        "The <point>file:aa( link")))
+  (should
+   (equal
+    '("http" "//foo.com/more_(than)_one_(parens)")
+    (test-ol-parse-link-in-text
+        "The <point>http://foo.com/more_(than)_one_(parens) link")))
+  (should
+   (equal
+    '("http" "//foo.com/blah_(wikipedia)#cite-1")
+    (test-ol-parse-link-in-text
+        "The <point>http://foo.com/blah_(wikipedia)#cite-1 link")))
+  (should
+   (equal
+    '("http" "//foo.com/blah_(wikipedia)_blah#cite-1")
+    (test-ol-parse-link-in-text
+        "The <point>http://foo.com/blah_(wikipedia)_blah#cite-1 link")))
+  (should
+   (equal
+    '("http" "//foo.com/unicode_(✪)_in_parens")
+    (test-ol-parse-link-in-text
+        "The <point>http://foo.com/unicode_(✪)_in_parens link")))
+  (should
+   (equal
+    '("http" "//foo.com/(something)?after=parens")
+    (test-ol-parse-link-in-text
+        "The <point>http://foo.com/(something)?after=parens link"))))
+
 (provide 'test-ol)
 ;;; test-ol.el ends here
-- 
2.26.2