feat: move mblog header handling into mime4cl r/3754

Accessing the headers of a MIME message feels like something mime4cl
should handle. We implemented this ad hoc in mblog before in order to
not need to worry about doing it in a sensible way. Now we introduce a
decent-ish interface for getting a header from a MIME message,
mime-message-header-values:

* It returns a list because MIME message headers may appear multiple
  times.

* It decodes RFC2047 only upon request, as you may want to be stricter
  about parsing certain fields.

* It checks header name equality case insensitively.

The code for decoding the RFC2047 string is retained and still uses
babel for doing the actual decoding.

Change-Id: I58bbbe4b46dbded04160b481a28a40d14775673d
Reviewed-on: https://cl.tvl.fyi/c/depot/+/5150
Tested-by: BuildkiteCI
Reviewed-by: sterni <sternenseemann@systemli.org>

4 files changed, 34 insertions, 2 deletions

diff --git a/third_party/lisp/mime4cl/default.nix b/third_party/lisp/mime4cl/default.nix
index a14d695c298e..9d3d6253f480 100644
--- a/third_party/lisp/mime4cl/default.nix
+++ b/third_party/lisp/mime4cl/default.nix
@@ -6,6 +6,7 @@ depot.nix.buildLisp.library {
   name = "mime4cl";
 
   deps = [
+    depot.third_party.lisp.babel
     depot.third_party.lisp.sclf
     depot.third_party.lisp.npg
     depot.third_party.lisp.trivial-gray-streams
diff --git a/third_party/lisp/mime4cl/endec.lisp b/third_party/lisp/mime4cl/endec.lisp
index 9f2f9c51c260..020c212e5ec4 100644
--- a/third_party/lisp/mime4cl/endec.lisp
+++ b/third_party/lisp/mime4cl/endec.lisp
@@ -644,7 +644,7 @@ method of RFC2047 and return a sequence of bytes."
            (vector-push-extend (char-code c) output-sequence)))
        finally (return output-sequence)))
 
-(defun decode-RFC2047-string (encoding string &key (start 0) (end (length string)))
+(defun decode-RFC2047-part (encoding string &key (start 0) (end (length string)))
   "Decode STRING according to RFC2047 and return a sequence of
 bytes."
   (gcase (encoding string-equal)
@@ -674,10 +674,24 @@ sequence, a charset string indicating the original coding."
             (push (subseq text previous-end start)
                   result))
           (setf previous-end (+ end 2))
-          (push (cons (decode-RFC2047-string encoding text :start (1+ second-?) :end end)
+          (push (cons (decode-RFC2047-part encoding text :start (1+ second-?) :end end)
                       charset)
                 result))
      finally (unless (= previous-end (length text))
                (push (subseq text previous-end (length text))
                      result))
        (return (nreverse result))))
+
+(defun decode-RFC2047 (text)
+  "Decode TEXT into a fully decoded string. Whenever a non ASCII part is
+  encountered, try to decode it using babel, otherwise signal an error."
+  (flet ((decode-part (part)
+           (etypecase part
+             (cons (babel:octets-to-string
+                    (car part)
+                    :encoding (babel-encodings:get-character-encoding
+                               (intern (string-upcase (cdr part)) 'keyword))))
+             (string part))))
+    (apply #'concatenate
+           (cons 'string
+                 (mapcar #'decode-part (mime:parse-RFC2047-text text))))))
diff --git a/third_party/lisp/mime4cl/mime.lisp b/third_party/lisp/mime4cl/mime.lisp
index 1b1d98bfaf99..5639aab23641 100644
--- a/third_party/lisp/mime4cl/mime.lisp
+++ b/third_party/lisp/mime4cl/mime.lisp
@@ -622,6 +622,20 @@ found in STREAM."
 
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 
+(defun mime-message-header-values (name message &key decode)
+  "Return all values of the header with NAME in MESSAGE, optionally decoding
+  it according to RFC2047 if :DECODE is T."
+  (loop ;; A header may occur multiple times
+        for header in (mime-message-headers message)
+        ;; MIME Headers should be case insensitive
+        ;; https://stackoverflow.com/a/6143644
+        when (string-equal (car header) name)
+        collect (if decode
+                    (decode-RFC2047 (cdr header))
+                    (cdr header))))
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
 (defvar *lazy-mime-decode* t
   "If true don't  decode mime bodies in memory.")
 
diff --git a/third_party/lisp/mime4cl/package.lisp b/third_party/lisp/mime4cl/package.lisp
index b1217a0b6818..5586bdc390e5 100644
--- a/third_party/lisp/mime4cl/package.lisp
+++ b/third_party/lisp/mime4cl/package.lisp
@@ -30,6 +30,8 @@
                           #:process-wait
                           #:process-alive-p
                           #:run-program)
+  (:import-from :babel :octets-to-string)
+  (:import-from :babel-encodings :get-character-encoding)
   (:export #:*lazy-mime-decode*
            #:print-mime-part
            #:read-mime-message
@@ -61,6 +63,7 @@
            #:mime-type-string
            #:mime-type-parameters
            #:mime-message-headers
+           #:mime-message-header-values
            #:mime=
            #:find-mime-part-by-path
            #:find-mime-part-by-id