From 1f189a1f626ae8b5fee87610e5018e70a0573ce2 Mon Sep 17 00:00:00 2001
From: Neur0toxine <pashok9825@gmail.com>
Date: Sat, 11 Nov 2023 19:49:22 +0300
Subject: [PATCH] initial

---
 .drone.yml                       | 26 ++++++++++++++++++++++++++
 .gitignore                       |  2 ++
 README.md                        | 10 ++++++++--
 data/az-cyrillic-idn-fix.patch   | 13 +++++++++++++
 data/geoip-generator-config.json | 32 ++++++++++++++++++++++++++++++++
 generate.sh                      | 28 ++++++++++++++++++++++++++++
 6 files changed, 109 insertions(+), 2 deletions(-)
 create mode 100644 .drone.yml
 create mode 100644 .gitignore
 create mode 100644 data/az-cyrillic-idn-fix.patch
 create mode 100644 data/geoip-generator-config.json
 create mode 100755 generate.sh

diff --git a/.drone.yml b/.drone.yml
new file mode 100644
index 0000000..d334bd2
--- /dev/null
+++ b/.drone.yml
@@ -0,0 +1,26 @@
+kind: pipeline
+type: docker
+name: default
+
+steps:
+- name: generate
+  image: ubuntu:latest
+  commands:
+  - apt install -y idn sipcalc gawk git golang-1.20
+  - bash generate.sh
+- name: release
+  image: plugins/gitea-release
+  settings:
+    api_key:
+      from_secret: gitea_api_key
+    base_url: https://gitea.neur0tx.site
+    files: .temp/result/*
+    checksum:
+      - sha256
+  when:
+    branch:
+    - master
+
+trigger:
+  event:
+  - push
\ No newline at end of file
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..b77553d
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+.temp
+.tool-versions
diff --git a/README.md b/README.md
index 8d6a567..4ed707a 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,9 @@
-# ru-blocklist
+# GeoIP & GeoSite with RU blacklist
 
-Generates ru-blocked-dlc.dat and ru-blocked-ips.dat files which can be used in Xray config to route only blocked domains & ips via proxy.
\ No newline at end of file
+Generates `geoip.dat` and `geosite.dat` for Xray with additional data:
+- Category with sites blocked in Russia (`geosite:category-ru-blocked-domains`).
+- category with second-level domains of sites blocked in Russia (`geosite:category-ru-blocked-zones`).
+
+Data sources:
+- [v2fly/geoip](https://github.com/v2fly/geoip) for `geoip.dat`.
+- [v2fly/domain-list-community](https://github.com/v2fly/domain-list-community) for `geosite.dat`.
\ No newline at end of file
diff --git a/data/az-cyrillic-idn-fix.patch b/data/az-cyrillic-idn-fix.patch
new file mode 100644
index 0000000..ec73a72
--- /dev/null
+++ b/data/az-cyrillic-idn-fix.patch
@@ -0,0 +1,13 @@
+diff --git a/parse.sh b/parse.sh
+index c15aba6..c840f3f 100755
+--- a/parse.sh
++++ b/parse.sh
+@@ -7,7 +7,7 @@ HERE="$(dirname "$(readlink -f "${0}")")"
+ cd "$HERE"
+ 
+ # Extract domains from list
+-awk -F ';' '{print $2}' temp/list.csv | sort -u | awk '/^$/ {next} /\\/ {next} /^[а-яА-Яa-zA-Z0-9\-\_\.\*]*+$/ {gsub(/\*\./, ""); gsub(/\.$/, ""); print}' | CHARSET=UTF-8 idn > result/hostlist_original.txt
++awk -F ';' '{print $2}' temp/list.csv | sort -u | awk '/^$/ {next} /\\/ {next} /^[а-яА-Яa-zA-Z0-9\-\_\.\*]*+$/ {gsub(/\*\./, ""); gsub(/\.$/, ""); print}' | grep -Fv 'bеllonа' | CHARSET=UTF-8 idn > result/hostlist_original.txt
+ 
+ # Generate zones from domains
+ # FIXME: nxdomain list parsing is disabled due to its instability on z-i
diff --git a/data/geoip-generator-config.json b/data/geoip-generator-config.json
new file mode 100644
index 0000000..5fbe8af
--- /dev/null
+++ b/data/geoip-generator-config.json
@@ -0,0 +1,32 @@
+{
+    "input": [
+      {
+        "type": "v2rayGeoIPDat",
+        "action": "add",
+        "args": {
+          "uri": "./geoip-src.dat"
+        }
+      },
+      {
+        "type": "text",
+        "action": "add",
+        "args": {
+          "inputDir": "./data"
+        }
+      }
+    ],
+    "output": [
+      {
+        "type": "v2rayGeoIPDat",
+        "action": "output",
+        "args": {
+          "outputName": "geoip.dat"
+        }
+      },
+      {
+        "type": "text",
+        "action": "output"
+      }
+    ]
+}
+  
\ No newline at end of file
diff --git a/generate.sh b/generate.sh
new file mode 100755
index 0000000..58cc2f9
--- /dev/null
+++ b/generate.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+set -euxo pipefail
+mkdir -p .temp/result
+[ ! -d .temp/az ] && \
+    git clone --depth=1 https://bitbucket.org/anticensority/antizapret-pac-generator-light.git .temp/az && \
+    cd .temp/az && \
+    patch < ../../data/az-cyrillic-idn-fix.patch && \
+    bash update.sh && \
+    bash parse.sh && \
+    cd ../..
+[ ! -d .temp/geoip ] && \
+    git clone --depth=1 https://github.com/v2fly/geoip.git .temp/geoip && \
+    cat data/geoip-generator-config.json > .temp/geoip/config.json && \
+    cd .temp/geoip && \
+    ([ ! -f geoip-src.dat ] && curl -fsSL https://github.com/v2fly/geoip/releases/latest/download/geoip.dat -o geoip-src.dat) && \
+    mkdir -p data && \
+    cp ../az/result/iplist_all.txt data/ru-blocked-ips-all && \
+    cp ../az/result/iplist_blockedbyip.txt data/ru-blocked-ips-directblock && \
+    cp ../az/result/iplist_blockedbyip_noid2971.txt data/ru-blocked-ips-noid2971 && \
+    go run ./ && \
+    mv output/dat/geoip.dat ../result/ && \
+    cd ../..
+[ ! -d .temp/geosite ] && \
+    git clone --depth=1 https://github.com/v2fly/domain-list-community.git .temp/geosite && \
+    cd .temp/geosite && \
+    cp ../az/result/hostlist_zones.txt data/category-ru-blocked-zones && \
+    cp ../az/result/hostlist_original.txt data/category-ru-blocked-domains && \
+    go run ./ --outputdir=../result --outputname=geosite.dat
\ No newline at end of file