From f4511893e1a39f74c54269648e95471fdbde1a79 Mon Sep 17 00:00:00 2001
From: shamoon <4887959+shamoon@users.noreply.github.com>
Date: Fri, 29 Dec 2023 09:13:14 -0800
Subject: [PATCH] Support all URI schemes

---
 src/documents/serialisers.py |   3 +-
 src/documents/utils.py       | 378 +++++++++++++++++++++++++++++++++++
 2 files changed, 380 insertions(+), 1 deletion(-)

diff --git a/src/documents/serialisers.py b/src/documents/serialisers.py
index b6be62d9b..0c36a32b5 100644
--- a/src/documents/serialisers.py
+++ b/src/documents/serialisers.py
@@ -41,6 +41,7 @@ from documents.models import UiSettings
 from documents.parsers import is_mime_type_supported
 from documents.permissions import get_groups_with_only_permission
 from documents.permissions import set_permissions_for_object
+from documents.utils import ALL_URL_SCHEMES
 
 
 # https://www.django-rest-framework.org/api-guide/serializers/#example
@@ -499,7 +500,7 @@ class CustomFieldInstanceSerializer(serializers.ModelSerializer):
             and data["value"] is not None
             and len(data["value"]) > 0
         ):
-            URLValidator()(data["value"])
+            URLValidator(schemes=ALL_URL_SCHEMES)(data["value"])
         return data
 
     def reflect_doclinks(
diff --git a/src/documents/utils.py b/src/documents/utils.py
index b84c9b53c..2206ea4b5 100644
--- a/src/documents/utils.py
+++ b/src/documents/utils.py
@@ -40,3 +40,381 @@ def copy_file_with_basic_stats(
 
     shutil.copy(source, dest)
     copy_basic_file_stats(source, dest)
+
+
+ALL_URL_SCHEMES = [
+    "aaa",
+    "aaas",
+    "about",
+    "acap",
+    "acct",
+    "acd",
+    "acr",
+    "adiumxtra",
+    "adt",
+    "afp",
+    "afs",
+    "aim",
+    "amss",
+    "android",
+    "appdata",
+    "apt",
+    "ar",
+    "ark",
+    "at",
+    "attachment",
+    "aw",
+    "barion",
+    "bb",
+    "beshare",
+    "bitcoin",
+    "bitcoincash",
+    "blob",
+    "bolo",
+    "brid",
+    "browserext",
+    "cabal",
+    "calculator",
+    "callto",
+    "cap",
+    "cast",
+    "casts",
+    "chrome",
+    "chrome-extension",
+    "cid",
+    "coap",
+    "coap+tcp",
+    "coap+ws",
+    "coaps",
+    "coaps+tcp",
+    "coaps+ws",
+    "com-eventbrite-attendee",
+    "content",
+    "content-type",
+    "crid",
+    "cstr",
+    "cvs",
+    "dab",
+    "dat",
+    "data",
+    "dav",
+    "dhttp",
+    "diaspora",
+    "dict",
+    "did",
+    "dis",
+    "dlna-playcontainer",
+    "dlna-playsingle",
+    "dns",
+    "dntp",
+    "doi",
+    "dpp",
+    "drm",
+    "drop",
+    "dtmi",
+    "dtn",
+    "dvb",
+    "dvx",
+    "dweb",
+    "ed2k",
+    "eid",
+    "elsi",
+    "embedded",
+    "ens",
+    "ethereum",
+    "example",
+    "facetime",
+    "fax",
+    "feed",
+    "feedready",
+    "fido",
+    "file",
+    "filesystem",
+    "finger",
+    "first-run-pen-experience",
+    "fish",
+    "fm",
+    "ftp",
+    "fuchsia-pkg",
+    "geo",
+    "gg",
+    "git",
+    "gitoid",
+    "gizmoproject",
+    "go",
+    "gopher",
+    "graph",
+    "grd",
+    "gtalk",
+    "h323",
+    "ham",
+    "hcap",
+    "hcp",
+    "http",
+    "https",
+    "hxxp",
+    "hxxps",
+    "hydrazone",
+    "hyper",
+    "iax",
+    "icap",
+    "icon",
+    "im",
+    "imap",
+    "info",
+    "iotdisco",
+    "ipfs",
+    "ipn",
+    "ipns",
+    "ipp",
+    "ipps",
+    "irc",
+    "irc6",
+    "ircs",
+    "iris",
+    "iris.beep",
+    "iris.lwz",
+    "iris.xpc",
+    "iris.xpcs",
+    "isostore",
+    "itms",
+    "jabber",
+    "jar",
+    "jms",
+    "keyparc",
+    "lastfm",
+    "lbry",
+    "ldap",
+    "ldaps",
+    "leaptofrogans",
+    "lid",
+    "lorawan",
+    "lpa",
+    "lvlt",
+    "magnet",
+    "mailserver",
+    "mailto",
+    "maps",
+    "market",
+    "matrix",
+    "message",
+    "microsoft.windows.camera",
+    "microsoft.windows.camera.multipicker",
+    "microsoft.windows.camera.picker",
+    "mid",
+    "mms",
+    "modem",
+    "mongodb",
+    "moz",
+    "ms-access",
+    "ms-appinstaller",
+    "ms-browser-extension",
+    "ms-calculator",
+    "ms-drive-to",
+    "ms-enrollment",
+    "ms-excel",
+    "ms-eyecontrolspeech",
+    "ms-gamebarservices",
+    "ms-gamingoverlay",
+    "ms-getoffice",
+    "ms-help",
+    "ms-infopath",
+    "ms-inputapp",
+    "ms-launchremotedesktop",
+    "ms-lockscreencomponent-config",
+    "ms-media-stream-id",
+    "ms-meetnow",
+    "ms-mixedrealitycapture",
+    "ms-mobileplans",
+    "ms-newsandinterests",
+    "ms-officeapp",
+    "ms-people",
+    "ms-project",
+    "ms-powerpoint",
+    "ms-publisher",
+    "ms-remotedesktop",
+    "ms-remotedesktop-launch",
+    "ms-restoretabcompanion",
+    "ms-screenclip",
+    "ms-screensketch",
+    "ms-search",
+    "ms-search-repair",
+    "ms-secondary-screen-controller",
+    "ms-secondary-screen-setup",
+    "ms-settings",
+    "ms-settings-airplanemode",
+    "ms-settings-bluetooth",
+    "ms-settings-camera",
+    "ms-settings-cellular",
+    "ms-settings-cloudstorage",
+    "ms-settings-connectabledevices",
+    "ms-settings-displays-topology",
+    "ms-settings-emailandaccounts",
+    "ms-settings-language",
+    "ms-settings-location",
+    "ms-settings-lock",
+    "ms-settings-nfctransactions",
+    "ms-settings-notifications",
+    "ms-settings-power",
+    "ms-settings-privacy",
+    "ms-settings-proximity",
+    "ms-settings-screenrotation",
+    "ms-settings-wifi",
+    "ms-settings-workplace",
+    "ms-spd",
+    "ms-stickers",
+    "ms-sttoverlay",
+    "ms-transit-to",
+    "ms-useractivityset",
+    "ms-virtualtouchpad",
+    "ms-visio",
+    "ms-walk-to",
+    "ms-whiteboard",
+    "ms-whiteboard-cmd",
+    "ms-word",
+    "msnim",
+    "msrp",
+    "msrps",
+    "mss",
+    "mt",
+    "mtqp",
+    "mumble",
+    "mupdate",
+    "mvn",
+    "news",
+    "nfs",
+    "ni",
+    "nih",
+    "nntp",
+    "notes",
+    "num",
+    "ocf",
+    "oid",
+    "onenote",
+    "onenote-cmd",
+    "opaquelocktoken",
+    "openid",
+    "openpgp4fpr",
+    "otpauth",
+    "p1",
+    "pack",
+    "palm",
+    "paparazzi",
+    "payment",
+    "payto",
+    "pkcs11",
+    "platform",
+    "pop",
+    "pres",
+    "prospero",
+    "proxy",
+    "pwid",
+    "psyc",
+    "pttp",
+    "qb",
+    "query",
+    "quic-transport",
+    "redis",
+    "rediss",
+    "reload",
+    "res",
+    "resource",
+    "rmi",
+    "rsync",
+    "rtmfp",
+    "rtmp",
+    "rtsp",
+    "rtsps",
+    "rtspu",
+    "sarif",
+    "secondlife",
+    "secret-token",
+    "service",
+    "session",
+    "sftp",
+    "sgn",
+    "shc",
+    "shttp (OBSOLETE)",
+    "sieve",
+    "simpleledger",
+    "simplex",
+    "sip",
+    "sips",
+    "skype",
+    "smb",
+    "smp",
+    "sms",
+    "smtp",
+    "snews",
+    "snmp",
+    "soap.beep",
+    "soap.beeps",
+    "soldat",
+    "spiffe",
+    "spotify",
+    "ssb",
+    "ssh",
+    "starknet",
+    "steam",
+    "stun",
+    "stuns",
+    "submit",
+    "svn",
+    "swh",
+    "swid",
+    "swidpath",
+    "tag",
+    "taler",
+    "teamspeak",
+    "tel",
+    "teliaeid",
+    "telnet",
+    "tftp",
+    "things",
+    "thismessage",
+    "tip",
+    "tn3270",
+    "tool",
+    "turn",
+    "turns",
+    "tv",
+    "udp",
+    "unreal",
+    "upt",
+    "urn",
+    "ut2004",
+    "uuid-in-package",
+    "v-event",
+    "vemmi",
+    "ventrilo",
+    "ves",
+    "videotex",
+    "vnc",
+    "view-source",
+    "vscode",
+    "vscode-insiders",
+    "vsls",
+    "w3",
+    "wais",
+    "web3",
+    "wcr",
+    "webcal",
+    "web+ap",
+    "wifi",
+    "wpid",
+    "ws",
+    "wss",
+    "wtai",
+    "wyciwyg",
+    "xcon",
+    "xcon-userid",
+    "xfire",
+    "xmlrpc.beep",
+    "xmlrpc.beeps",
+    "xmpp",
+    "xri",
+    "ymsgr",
+    "z39.50",
+    "z39.50r",
+    "z39.50s",
+]  # pragma: no cover