Detect content-type when extension is missing or unknown

If a file has no known extension the content type gets set to
application/octet-stream causing the browser try and download the file
when viewed directly.

This quickly becomes annoying as many of the files I interact with often
have no extension. I.e., config files, log files, LICENSE files and
other random text files.

This patch uses libmagic to detect the file type and set the
content-type header. It also does this for the RSS feed and webdav for
sake of completeness.

This patch does not touch the front end at all so these files still have a 'txt'
button and a type of '%' in the web UI. But when clicked on, the browser
will display the files correctly.

This feature is enabled with the existing "magic" option. I thought this
fit as the existing functionality also uses libmagic and gives file
extensions to files on upload. Tell me if it should be its own option
instead.

The code base was very confusing, this patch works but I have no idea if
it's the way you'd like this implemented. Hopefully its acceptable as
is.

copyparty/__main__.py

@@ -1024,7 +1024,7 @@ def add_upload(ap):
     ap2.add_argument("--u2ts", metavar="TXT", type=u, default="c", help="how to timestamp uploaded files; [\033[32mc\033[0m]=client-last-modified, [\033[32mu\033[0m]=upload-time, [\033[32mfc\033[0m]=force-c, [\033[32mfu\033[0m]=force-u (volflag=u2ts)")
     ap2.add_argument("--rand", action="store_true", help="force randomized filenames, \033[33m--nrand\033[0m chars long (volflag=rand)")
     ap2.add_argument("--nrand", metavar="NUM", type=int, default=9, help="randomized filenames length (volflag=nrand)")
-    ap2.add_argument("--magic", action="store_true", help="enable filetype detection on nameless uploads (volflag=magic)")
+    ap2.add_argument("--magic", action="store_true", help="enable filetype detection on extensionless files (volflag=magic)")
     ap2.add_argument("--df", metavar="GiB", type=u, default="0", help="ensure \033[33mGiB\033[0m free disk space by rejecting upload requests; assumes gigabytes unless a unit suffix is given: [\033[32m256m\033[0m], [\033[32m4\033[0m], [\033[32m2T\033[0m] (volflag=df)")
     ap2.add_argument("--sparse", metavar="MiB", type=int, default=4, help="windows-only: minimum size of incoming uploads through up2k before they are made into sparse files")
     ap2.add_argument("--turbo", metavar="LVL", type=int, default=0, help="configure turbo-mode in up2k client; [\033[32m-1\033[0m] = forbidden/always-off, [\033[32m0\033[0m] = default-off and warn if enabled, [\033[32m1\033[0m] = default-off, [\033[32m2\033[0m] = on, [\033[32m3\033[0m] = on and disable datecheck")

copyparty/httpcli.py

@@ -1413,6 +1413,8 @@ class HttpCli(object):
             pass
 
         for i in hits:
+            f = fsenc(os.path.join(self.vn.realpath, i["rp"])) if "magic" in self.vn.flags else None
+
             iurl = html_escape("%s%s" % (baseurl, i["rp"]), True, True)
             title = unquotep(i["rp"].split("?")[0].split("/")[-1])
             title = html_escape(title, True, True)
@@ -1420,7 +1422,7 @@ class HttpCli(object):
             tag_a = str(i["tags"].get("artist") or "")
             desc = "%s - %s" % (tag_a, tag_t) if tag_t and tag_a else (tag_t or tag_a)
             desc = html_escape(desc, True, True) if desc else title
-            mime = html_escape(guess_mime(title))
+            mime = html_escape(guess_mime(title, f))
             lmod = formatdate(max(0, i["ts"]))
             zsa = (iurl, iurl, title, desc, lmod, iurl, mime, i["sz"])
             zs = (
@@ -1599,7 +1601,9 @@ class HttpCli(object):
                 "supportedlock": '<D:lockentry xmlns:D="DAV:"><D:lockscope><D:exclusive/></D:lockscope><D:locktype><D:write/></D:locktype></D:lockentry>',
             }
             if not isdir:
-                pvs["getcontenttype"] = html_escape(guess_mime(rp))
+                f = fsenc(os.path.join(tap, x["vp"])) if "magic" in self.vn.flags else None
+
+                pvs["getcontenttype"] = html_escape(guess_mime(rp), f)
                 pvs["getcontentlength"] = str(st.st_size)
 
             for k, v in pvs.items():
@@ -4156,6 +4160,8 @@ class HttpCli(object):
             mime = "text/plain; charset={}".format(self.uparam["txt"] or "utf-8")
         elif "mime" in self.uparam:
             mime = str(self.uparam.get("mime"))
+        elif "magic" in self.vn.flags:
+            mime = guess_mime(req_path, fsenc(fs_path))
         else:
             mime = guess_mime(req_path)
 

copyparty/util.py

@@ -3152,11 +3152,11 @@ def unescape_cookie(orig: str) -> str:
     return "".join(ret)
 
 
-def guess_mime(url: str, fallback: str = "application/octet-stream") -> str:
+def guess_mime_ext(url: str) -> str:
     try:
         ext = url.rsplit(".", 1)[1].lower()
     except:
-        return fallback
+        return None
 
     ret = MIMES.get(ext)
 
@@ -3164,6 +3164,24 @@ def guess_mime(url: str, fallback: str = "application/octet-stream") -> str:
         x = mimetypes.guess_type(url)
         ret = "application/{}".format(x[1]) if x[1] else x[0]
 
+    return ret
+
+
+def guess_mime(url: str, path: str = None, fallback: str = "application/octet-stream") -> str:
+    ret = guess_mime_ext(url)
+
+    if not ret and path:
+        import magic
+
+        try:
+            with open(path, 'rb', 0) as f:
+                ret = magic.from_buffer(f.read(4096), mime = True)
+                if ret == "text/html":
+                    # avoid serving up HTML content unless there was actually a .html extension
+                    ret = "text/plain"
+        except:
+            pass
+
     if not ret:
         ret = fallback