exclude search results by regex (#120)

a better alternative to using `--no-idx` for this purpose since
this also excludes recent uploads, not just during fs-indexing,
and it doesn't prevent deduplication

also speeds up searches by a tiny amount due to building the
sanchecks into the exclude-filter while parsing the config,
instead of during each search query

README.md

@@ -1097,11 +1097,12 @@ using the GUI  (winXP or later):
   * on winXP only, click the `Sign up for online storage` hyperlink instead and put the URL there
   * providing your password as the username is recommended; the password field can be anything or empty
 
-known client bugs:
+the webdav client that's built into windows has the following list of bugs; you can avoid all of these by connecting with rclone instead:
 * win7+ doesn't actually send the password to the server when reauthenticating after a reboot unless you first try to login with an incorrect password and then switch to the correct password
   * or just type your password into the username field instead to get around it entirely
 * connecting to a folder which allows anonymous read will make writing impossible, as windows has decided it doesn't need to login
   * workaround: connect twice; first to a folder which requires auth, then to the folder you actually want, and leave both of those mounted
+  * or set the server-option `--dav-auth` to force password-auth for all webdav clients
 * win7+ may open a new tcp connection for every file and sometimes forgets to close them, eventually needing a reboot
   * maybe NIC-related (??), happens with win10-ltsc on e1000e but not virtio
 * windows cannot access folders which contain filenames with invalid unicode or forbidden characters (`<>:"/\|?*`), or names ending with `.`
@@ -1268,7 +1269,7 @@ note:
 
 ### exclude-patterns
 
-to save some time,  you can provide a regex pattern for filepaths to only index by filename/path/size/last-modified (and not the hash of the file contents) by setting `--no-hash \.iso$` or the volflag `:c,nohash=\.iso$`, this has the following consequences:
+to save some time,  you can provide a regex pattern for filepaths to only index by filename/path/size/last-modified (and not the hash of the file contents) by setting `--no-hash '\.iso$'` or the volflag `:c,nohash=\.iso$`, this has the following consequences:
 * initial indexing is way faster, especially when the volume is on a network disk
 * makes it impossible to [file-search](#file-search)
 * if someone uploads the same file contents, the upload will not be detected as a dupe, so it will not get symlinked or rejected
@@ -1279,6 +1280,8 @@ similarly, you can fully ignore files/folders using `--no-idx [...]` and `:c,noi
 
 if you set `--no-hash [...]` globally, you can enable hashing for specific volumes using flag `:c,nohash=`
 
+to exclude certain filepaths from search-results, use `--srch-excl` or volflag `srch_excl` instead of `--no-idx`, for example `--srch-excl 'password|logs/[0-9]'`
+
 ### filesystem guards
 
 avoid traversing into other filesystems  using `--xdev` / volflag `:c,xdev`, skipping any symlinks or bind-mounts to another HDD for example

copyparty/__main__.py

@@ -1401,6 +1401,7 @@ def add_db_general(ap, hcores):
     ap2.add_argument("--db-act", metavar="SEC", type=float, default=10.0, help="defer any scheduled volume reindexing until \033[33mSEC\033[0m seconds after last db write (uploads, renames, ...)")
     ap2.add_argument("--srch-time", metavar="SEC", type=int, default=45, help="search deadline -- terminate searches running for more than \033[33mSEC\033[0m seconds")
     ap2.add_argument("--srch-hits", metavar="N", type=int, default=7999, help="max search results to allow clients to fetch; 125 results will be shown initially")
+    ap2.add_argument("--srch-excl", metavar="PTN", type=u, default="", help="regex: exclude files from search results if the file-URL matches \033[33mPTN\033[0m (case-sensitive). Example: [\033[32mpassword|logs/[0-9]\033[0m] any URL containing 'password' or 'logs/DIGIT' (volflag=srch_excl)")
     ap2.add_argument("--dotsrch", action="store_true", help="show dotfiles in search results (volflags: dotsrch | nodotsrch)")
 
 

copyparty/authsrv.py

@@ -1880,6 +1880,7 @@ class AuthSrv(object):
                 ["no_hash", "nohash"],
                 ["no_idx", "noidx"],
                 ["og_ua", "og_ua"],
+                ["srch_excl", "srch_excl"],
             ]:
                 if vf in vol.flags:
                     ptn = re.compile(vol.flags.pop(vf))
@@ -2086,6 +2087,22 @@ class AuthSrv(object):
                 self.log(t.format(mtp), 1)
                 errors = True
 
+        for vol in vfs.all_vols.values():
+            re1: Optional[re.Pattern] = vol.flags.get("srch_excl")
+            excl = [re1.pattern] if re1 else []
+
+            vpaths = []
+            vtop = vol.vpath
+            for vp2 in vfs.all_vols.keys():
+                if vp2.startswith((vtop + "/").lstrip("/")) and vtop != vp2:
+                    vpaths.append(re.escape(vp2[len(vtop) :].lstrip("/")))
+            if vpaths:
+                excl.append("^(%s)/" % ("|".join(vpaths),))
+
+            vol.flags["srch_re_dots"] = re.compile("|".join(excl or ["^$"]))
+            excl.extend([r"^\.", r"/\."])
+            vol.flags["srch_re_nodot"] = re.compile("|".join(excl))
+
         have_daw = False
         for vol in vfs.all_nodes.values():
             daw = vol.flags.get("daw") or self.args.daw

copyparty/cfg.py

@@ -191,6 +191,7 @@ flagcats = {
         "xvol": "do not follow symlinks leaving the volume root",
         "dotsrch": "show dotfiles in search results",
         "nodotsrch": "hide dotfiles in search results (default)",
+        "srch_excl": "exclude search results with URL matching this regex",
     },
     'database, audio tags\n"mte", "mth", "mtp", "mtm" all work the same as -mte, -mth, ...': {
         "mtp=.bpm=f,audio-bpm.py": 'uses the "audio-bpm.py" program to\ngenerate ".bpm" tags from uploads (f = overwrite tags)',

copyparty/svchub.py

@@ -793,7 +793,7 @@ class SvcHub(object):
         al.exp_md = odfusion(exp, al.exp_md.replace(" ", ","))
         al.exp_lg = odfusion(exp, al.exp_lg.replace(" ", ","))
 
-        for k in ["no_hash", "no_idx", "og_ua"]:
+        for k in ["no_hash", "no_idx", "og_ua", "srch_excl"]:
             ptn = getattr(self.args, k)
             if ptn:
                 setattr(self.args, k, re.compile(ptn))

copyparty/u2idx.py

@@ -324,7 +324,8 @@ class U2idx(object):
         sort: bool,
         lim: int,
     ) -> tuple[list[dict[str, Any]], list[str], bool]:
-        if self.args.srch_dbg:
+        dbg = self.args.srch_dbg
+        if dbg:
             t = "searching across all %s volumes in which the user has 'r' (full read access):\n  %s"
             zs = "\n  ".join(["/%s = %s" % (x.vpath, x.realpath) for x in vols])
             self.log(t % (len(vols), zs), 5)
@@ -367,14 +368,14 @@ class U2idx(object):
             if not cur:
                 continue
 
-            excl = []
-            for vp2 in self.asrv.vfs.all_vols.keys():
-                if vp2.startswith((vtop + "/").lstrip("/")) and vtop != vp2:
-                    excl.append(vp2[len(vtop) :].lstrip("/"))
+            dots = flags.get("dotsrch") and uname in vol.axs.udot
+            zs = "srch_re_dots" if dots else "srch_re_nodot"
+            rex: re.Pattern = flags.get(zs)  # type: ignore
 
-            if self.args.srch_dbg:
-                t = "searching in volume /%s (%s), excludelist %s"
-                self.log(t % (vtop, ptop, excl), 5)
+            if dbg:
+                t = "searching in volume /%s (%s), excluding %s"
+                self.log(t % (vtop, ptop, rex.pattern), 5)
+                rex_cfg: Optional[re.Pattern] = flags.get("srch_excl")
 
             self.active_cur = cur
 
@@ -387,7 +388,6 @@ class U2idx(object):
 
             sret = []
             fk = flags.get("fk")
-            dots = flags.get("dotsrch") and uname in vol.axs.udot
             fk_alg = 2 if "fka" in flags else 1
             c = cur.execute(uq, tuple(vuv))
             for hit in c:
@@ -396,20 +396,23 @@ class U2idx(object):
                 if rd.startswith("//") or fn.startswith("//"):
                     rd, fn = s3dec(rd, fn)
 
-                if rd in excl or any([x for x in excl if rd.startswith(x + "/")]):
-                    if self.args.srch_dbg:
-                        zs = vjoin(vjoin(vtop, rd), fn)
-                        t = "database inconsistency in volume '/%s'; ignoring: %s"
-                        self.log(t % (vtop, zs), 1)
+                vp = vjoin(vjoin(vtop, rd), fn)
+
+                if vp in seen_rps:
                     continue
 
-                rp = quotep("/".join([x for x in [vtop, rd, fn] if x]))
-                if not dots and "/." in ("/" + rp):
-                    continue
-
-                if rp in seen_rps:
+                if rex.search(vp):
+                    if dbg:
+                        if rex_cfg and rex_cfg.search(vp):  # type: ignore
+                            self.log("filtered by srch_excl: %s" % (vp,), 6)
+                        elif not dots and "/." in ("/" + vp):
+                            pass
+                        else:
+                            t = "database inconsistency in volume '/%s'; ignoring: %s"
+                            self.log(t % (vtop, vp), 1)
                     continue
 
+                rp = quotep(vp)
                 if not fk:
                     suf = ""
                 else:
@@ -431,7 +434,7 @@ class U2idx(object):
                 if lim < 0:
                     break
 
-                if self.args.srch_dbg:
+                if dbg:
                     t = "in volume '/%s': hit: %s"
                     self.log(t % (vtop, rp), 5)
 
@@ -461,7 +464,7 @@ class U2idx(object):
             ret.extend(sret)
             # print("[{}] {}".format(ptop, sret))
 
-            if self.args.srch_dbg:
+            if dbg:
                 t = "in volume '/%s': got %d hits, %d total so far"
                 self.log(t % (vtop, len(sret), len(ret)), 5)
 

copyparty/up2k.py

@@ -1078,7 +1078,8 @@ class Up2k(object):
         ft = "\033[0;32m{}{:.0}"
         ff = "\033[0;35m{}{:.0}"
         fv = "\033[0;36m{}:\033[90m{}"
-        fx = set(("html_head", "rm_re_t", "rm_re_r", "mv_re_t", "mv_re_r"))
+        zs = "html_head mv_re_r mv_re_t rm_re_r rm_re_t srch_re_dots srch_re_nodot"
+        fx = set(zs.split())
         fd = vf_bmap()
         fd.update(vf_cmap())
         fd.update(vf_vmap())
@@ -1241,9 +1242,9 @@ class Up2k(object):
 
         # also consider volflags which affect indexing
         for vp in vps:
-            vf = self.vfs.all_vols[vp].flags.items()
-            vf = {k: v for k, v in vf if k in VF_AFFECTS_INDEXING}
-            seed.append(str(vf))
+            vf = self.vfs.all_vols[vp].flags
+            vf = {k: v for k, v in vf.items() if k in VF_AFFECTS_INDEXING}
+            seed.append(str(sorted(vf.items())))
 
         zb = hashlib.sha1("\n".join(seed).encode("utf-8", "replace")).digest()
         vcfg = ub64enc(zb[:18]).decode("ascii")

tests/util.py

@@ -122,7 +122,7 @@ class Cfg(Namespace):
     def __init__(self, a=None, v=None, c=None, **ka0):
         ka = {}
 
-        ex = "chpw daw dav_auth dav_inf dav_mac dav_rt e2d e2ds e2dsa e2t e2ts e2tsr e2v e2vu e2vp early_ban ed emp exp force_js getmod grid gsel hardlink ih ihead magic hardlink_only nid nih no_acode no_athumb no_clone no_cp no_dav no_db_ip no_del no_dirsz no_dupe no_lifetime no_logues no_mv no_pipe no_poll no_readme no_robots no_sb_md no_sb_lg no_scandir no_tarcmp no_thumb no_vthumb no_zip nrand nsort nw og og_no_head og_s_title ohead q rand re_dirsz rss smb srch_dbg stats uqe vague_403 vc ver write_uplog xdev xlink xvol zs"
+        ex = "chpw daw dav_auth dav_inf dav_mac dav_rt e2d e2ds e2dsa e2t e2ts e2tsr e2v e2vu e2vp early_ban ed emp exp force_js getmod grid gsel hardlink ih ihead magic hardlink_only nid nih no_acode no_athumb no_clone no_cp no_dav no_db_ip no_del no_dirsz no_dupe no_lifetime no_logues no_mv no_pipe no_poll no_readme no_robots no_sb_md no_sb_lg no_scandir no_tarcmp no_thumb no_vthumb no_zip nrand nsort nw og og_no_head og_s_title ohead q rand re_dirsz rss smb srch_dbg srch_excl stats uqe vague_403 vc ver write_uplog xdev xlink xvol zs"
         ka.update(**{k: False for k in ex.split()})
 
         ex = "dedup dotpart dotsrch hook_v no_dhash no_fastboot no_fpool no_htp no_rescan no_sendfile no_ses no_snap no_up_list no_voldump re_dhash plain_ip"