Function: xselect--encode-string

xselect--encode-string is a byte-compiled function defined in select.el.gz.

Signature

(xselect--encode-string TYPE STR &optional CAN-MODIFY PREFER-STRING-TO-C-STRING)

Source Code

;; Defined in /usr/src/emacs/lisp/select.el.gz
(defun xselect--encode-string (type str &optional can-modify
                                    prefer-string-to-c-string)
  (when str
    ;; If TYPE is nil, this is a local request; return STR as-is.
    (if (null type)
	str
      ;; Otherwise, encode STR.
      (let ((coding (or next-selection-coding-system
			selection-coding-system)))
	(if coding
	    (setq coding (coding-system-base coding)))
	(let ((inhibit-read-only t))
	  ;; Suppress producing escape sequences for compositions.
	  ;; But avoid modifying the string if it's a buffer name etc.
	  (unless can-modify (setq str (substring str 0)))
	  (remove-text-properties 0 (length str) '(composition nil) str)
	  ;; For X selections, TEXT is a polymorphic target; choose
	  ;; the actual type from `UTF8_STRING', `COMPOUND_TEXT',
	  ;; `STRING', and `C_STRING'.  On Nextstep, always use UTF-8
	  ;; (see ns_string_to_pasteboard_internal in nsselect.m).
	  (when (eq type 'TEXT)
	    (cond
	     ((featurep 'ns)
	      (setq type 'UTF8_STRING))
	     ((not (multibyte-string-p str))
	      (setq type 'C_STRING))
	     (t
	      (let (non-latin-1 non-unicode eight-bit)
                (mapc (lambda (x)
                        (if (>= x #x100)
                            (if (< x #x110000)
                                (setq non-latin-1 t)
                              (if (< x #x3FFF80)
                                  (setq non-unicode t)
                                (setq eight-bit t)))))
		      str)
		(setq type (if (or non-unicode
				   (and
				    non-latin-1
				    ;; If a coding is specified for
				    ;; selection, and that is
				    ;; compatible with COMPOUND_TEXT,
				    ;; use it.
				    coding
				    (eq (coding-system-get coding :mime-charset)
					'x-ctext)))
			       'COMPOUND_TEXT
			     (if non-latin-1 'UTF8_STRING
			       (if eight-bit 'C_STRING
				 'STRING))))))))
	  (cond
	   ((or (eq type 'UTF8_STRING)
                (eq type 'text/plain\;charset=utf-8))
	    (if (or (not coding)
		    (not (eq (coding-system-type coding) 'utf-8)))
		(setq coding 'utf-8))
	    (setq str (encode-coding-string str coding)))

	   ((eq type 'STRING)
	    (if (or (not coding)
		    (not (eq (coding-system-type coding) 'charset)))
		(setq coding 'iso-8859-1))
	    (setq str (encode-coding-string str coding)))

           ((eq type 'text/plain)
            (if (or (not coding)
		    (not (eq (coding-system-type coding) 'charset)))
		(setq coding 'ascii))
	    (setq str (encode-coding-string str coding)))

	   ((eq type 'COMPOUND_TEXT)
	    (if (or (not coding)
		    (not (eq (coding-system-type coding) 'iso-2022)))
		(setq coding 'compound-text-with-extensions))
	    (setq str (encode-coding-string str coding)))

	   ((eq type 'C_STRING)
            ;; According to ICCCM Protocol v2.0 (para 2.7.1), C_STRING
            ;; is a zero-terminated sequence of raw bytes that
            ;; shouldn't be interpreted as text in any encoding.
            ;; Therefore, if STR is unibyte (the normal case), we use
            ;; it as-is; otherwise we assume some of the characters
            ;; are eight-bit and ensure they are converted to their
            ;; single-byte representation.
            (or (null (multibyte-string-p str))
                (setq str (encode-coding-string str 'raw-text-unix))))

	   (t
	    (error "Unknown selection type: %S" type)))))

      ;; Most programs are unable to handle NUL bytes in strings.
      (setq str (string-replace "\0" "\\0" str))

      (setq next-selection-coding-system nil)
      (cons (if (and prefer-string-to-c-string
                     (eq type 'C_STRING))
                'STRING type)
            str))))