awesome-emacs/org-roam
1
0
Fork 0
mirror of https://github.com/org-roam/org-roam synced 2025-08-01 12:17:21 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into v2

Browse Source 
* master:
  optimize filename normalize (#1460)
This commit is contained in:
Jethro Kuan
2021-04-07 09:51:50 +08:00
parent 73a04a611a 2d58651699
commit 50436a9b1c
1 changed files with 33 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
org-roam.el
View File

@ -134,6 +134,35 @@ Function should return a filename string based on title."
:type 'function
:group 'org-roam)
(defcustom org-roam-slug-trim-chars
'(;; Combining Diacritical Marks https://www.unicode.org/charts/PDF/U0300.pdf
768 ; U+0300 COMBINING GRAVE ACCENT
769 ; U+0301 COMBINING ACUTE ACCENT
770 ; U+0302 COMBINING CIRCUMFLEX ACCENT
771 ; U+0303 COMBINING TILDE
772 ; U+0304 COMBINING MACRON
774 ; U+0306 COMBINING BREVE
775 ; U+0307 COMBINING DOT ABOVE
776 ; U+0308 COMBINING DIAERESIS
777 ; U+0309 COMBINING HOOK ABOVE
778 ; U+030A COMBINING RING ABOVE
780 ; U+030C COMBINING CARON
795 ; U+031B COMBINING HORN
803 ; U+0323 COMBINING DOT BELOW
804 ; U+0324 COMBINING DIAERESIS BELOW
805 ; U+0325 COMBINING RING BELOW
807 ; U+0327 COMBINING CEDILLA
813 ; U+032D COMBINING CIRCUMFLEX ACCENT BELOW
814 ; U+032E COMBINING BREVE BELOW
816 ; U+0330 COMBINING TILDE BELOW
817 ; U+0331 COMBINING MACRON BELOW
)
"Characters to trim from Unicode normalization for slug.
By default, the characters are specified to remove Diacritical Marks from the Latin alphabet."
:type '(repeat character)
:group 'org-roam)
(defcustom org-roam-verbose t
"Echo messages that are not errors."
:type 'boolean
@ -315,10 +344,11 @@ Use external shell commands if defined in `org-roam-list-files-commands'."
(defun org-roam--title-to-slug (title)
"Convert TITLE to a filename-suitable slug."
(cl-flet* ((nonspacing-mark-p (char)
(eq 'Mn (get-char-code-property char 'general-category)))
(memq char org-roam-slug-trim-chars))
(strip-nonspacing-marks (s)
(apply #'string (seq-remove #'nonspacing-mark-p
(ucs-normalize-NFD-string s))))
(ucs-normalize-NFC-string
(apply #'string (seq-remove #'nonspacing-mark-p
(ucs-normalize-NFD-string s)))))
(cl-replace (title pair)
(replace-regexp-in-string (car pair) (cdr pair) title)))
(let* ((pairs `(("[^[:alnum:][:digit:]]" . "_") ;; convert anything not alphanumeric