add streaming upload compression

README.md

@@ -494,6 +494,27 @@ you can also set transaction limits which apply per-IP and per-volume, but these
 * `:c,maxb=1g,300` allows 1 GiB total over 5 minutes from each IP (tracked per-volume)
 
 
+## compress uploads
+
+files can be autocompressed on upload, either on user-request (if config allows) or forced by server-config
+
+* volume flag `gz` allows gz compression
+* volume flag `xz` allows lzma compression
+* volume flag `pk` **forces** compression on all files
+* url parameter `pk` requests compression with server-default algorithm
+* url parameter `gz` or `xz` requests compression with a specific algorithm
+* url parameter `xz` requests xz compression
+
+things to note,
+* the `gz` and `xz` arguments take a single optional argument, the compression level (range 0 to 9)
+* the `pk` volume flag takes the optional argument `ALGORITHM,LEVEL` which will then be forced for all uploads, for example `gz,9` or `xz,0`
+* default compression is gzip level 9
+* all upload methods except up2k are supported
+* the files will be indexed after compression, so dupe-detection and file-search will not work as expected
+
+some examples,
+
+
 ## database location
 
 copyparty creates a subfolder named `.hist` inside each volume where it stores the database, thumbnails, and some other stuff
@@ -600,11 +621,11 @@ quick summary of more eccentric web-browsers trying to view a directory index:
   * `var xhr = new XMLHttpRequest(); xhr.open('POST', 'https://127.0.0.1:3923/msgs?raw'); xhr.send('foo');`
 
 * curl/wget: upload some files (post=file, chunk=stdin)
-  * `post(){ curl -b cppwd=wark http://127.0.0.1:3923/ -F act=bput -F f=@"$1";}`  
+  * `post(){ curl -b cppwd=wark -F act=bput -F f=@"$1" http://127.0.0.1:3923/;}`  
     `post movie.mkv`
-  * `post(){ wget --header='Cookie: cppwd=wark' http://127.0.0.1:3923/?raw --post-file="$1" -O-;}`  
+  * `post(){ wget --header='Cookie: cppwd=wark' --post-file="$1" -O- http://127.0.0.1:3923/?raw;}`  
     `post movie.mkv`
-  * `chunk(){ curl -b cppwd=wark http://127.0.0.1:3923/ -T-;}`  
+  * `chunk(){ curl -b cppwd=wark -T- http://127.0.0.1:3923/;}`  
     `chunk <movie.mkv`
 
 * FUSE: mount a copyparty server as a local filesystem

copyparty/authsrv.py

@@ -803,6 +803,10 @@ class AuthSrv(object):
             if use:
                 vol.lim = lim
 
+        for vol in vfs.all_vols.values():
+            if "pk" in vol.flags and "gz" not in vol.flags and "xz" not in vol.flags:
+                vol.flags["gz"] = False  # def.pk
+
         all_mte = {}
         errors = False
         for vol in vfs.all_vols.values():

copyparty/httpcli.py

@@ -13,6 +13,11 @@ import ctypes
 from datetime import datetime
 import calendar
 
+try:
+    import lzma
+except:
+    pass
+
 from .__init__ import E, PY2, WINDOWS, ANYWIN, unicode
 from .util import *  # noqa  # pylint: disable=unused-wildcard-import
 from .bos import bos
@@ -180,6 +185,9 @@ class HttpCli(object):
                 if kc in cookies and ku not in uparam:
                     uparam[ku] = cookies[kc]
 
+        if len(uparam) > 10 or len(cookies) > 50:
+            raise Pebkac(400, "u wot m8")
+
         self.uparam = uparam
         self.cookies = cookies
         self.vpath = unquotep(vpath)  # not query, so + means +
@@ -503,7 +511,59 @@ class HttpCli(object):
         if self.args.nw:
             path = os.devnull
 
-        with open(fsenc(path), "wb", 512 * 1024) as f:
+        open_f = open
+        open_a = [fsenc(path), "wb", 512 * 1024]
+        open_ka = {}
+
+        # user-request || config-force
+        if ("gz" in vfs.flags or "xz" in vfs.flags) and (
+            "pk" in vfs.flags
+            or "pk" in self.uparam
+            or "gz" in self.uparam
+            or "xz" in self.uparam
+        ):
+            fb = {"gz": 9, "xz": 0}  # default/fallback level
+            lv = {}  # selected level
+            alg = None  # selected algo (gz=preferred)
+
+            # user-prefs first
+            if "gz" in self.uparam or "pk" in self.uparam:  # def.pk
+                alg = "gz"
+            if "xz" in self.uparam:
+                alg = "xz"
+            if alg:
+                v = self.uparam.get(alg)
+                lv[alg] = fb[alg] if v is None else int(v)
+
+            if alg not in vfs.flags:
+                alg = "gz" if "gz" in vfs.flags else "xz"
+
+            # then server overrides
+            pk = vfs.flags.get("pk")
+            if pk is not None:
+                # config-forced on
+                alg = alg or "gz"  # def.pk
+                try:
+                    # config-forced opts
+                    alg, lv = pk.split(",")
+                    lv[alg] = int(lv)
+                except:
+                    pass
+
+            lv[alg] = lv.get(alg) or fb.get(alg)
+
+            self.log("compressing with {} level {}".format(alg, lv.get(alg)))
+            if alg == "gz":
+                open_f = gzip.GzipFile
+                open_a = [fsenc(path), "wb", lv[alg], None, 0x5FEE6600]  # 2021-01-01
+            elif alg == "xz":
+                open_f = lzma.open
+                open_a = [fsenc(path), "wb"]
+                open_ka = {"preset": lv[alg]}
+            else:
+                self.log("fallthrough? thats a bug", 1)
+
+        with open_f(*open_a, **open_ka) as f:
             post_sz, _, sha_b64 = hashcopy(reader, f)
 
         if lim: