Merge pull request #16 from sjdonado/automated/update-parsers

chore: Update UA regexes and GeoLite2 database

.dockerignore

@@ -1,5 +1,44 @@
 .git
+.gitignore
+.github
+
 /bin/
+/bit
+/cli
+/benchmark
+*.dwarf
+*.o
+*.a
+
+# Dependencies cache
 /.shards/
+/lib/.shards/
+
 /spec/
+
+# Database files (should be mounted as volumes)
 /sqlite/
+*.db
+*.db-shm
+*.db-wal
+
+# Logs and temporary files
+*.log
+
+# Documentation
+/docs/
+*.md
+README.md
+CODE_OF_CONDUCT.md
+CONTRIBUTING.md
+LICENSE
+DOCKER_MIGRATION.md
+
+# Development environment
+.env*
+.editorconfig
+
+# Docker files (not needed inside image)
+Dockerfile
+docker-compose.yml
+.dockerignore

.github/workflows/deploy-docs.yml

@@ -0,0 +1,33 @@
+name: Deploy API Documentation
+
+on:
+  push:
+    branches:
+      - master
+    paths:
+      - 'docs/openapi.yaml'
+      - '.github/workflows/deploy-docs.yml'
+  workflow_dispatch:
+
+permissions:
+  contents: write
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Generate Swagger UI
+        uses: Legion2/swagger-ui-action@v1
+        with:
+          output: swagger-ui
+          spec-file: docs/openapi.yaml
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Deploy to GitHub Pages
+        uses: peaceiris/actions-gh-pages@v3
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: swagger-ui

.github/workflows/publish.yml

@@ -8,12 +8,9 @@ on:
     types: [published]
 
 jobs:
-  build-platforms:
-    name: Build Platforms
+  build-and-push:
+    name: Build and Push Multi-Platform
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        platform: [linux/amd64, linux/arm64]
     permissions:
       contents: read
       packages: write
@@ -22,8 +19,11 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
 
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
         uses: docker/login-action@v3
@@ -40,45 +40,12 @@ jobs:
             echo "version=latest" >> $GITHUB_OUTPUT
           fi
 
-      - name: Build and push platform image
+      - name: Build and push multi-platform image
         uses: docker/build-push-action@v5
-        env:
-          CRYSTAL_WORKERS: ${{ matrix.platform == 'linux/amd64' && 4 || 2 }}
         with:
           context: .
-          platforms: ${{ matrix.platform }}
+          platforms: linux/amd64,linux/arm64
           push: true
-          tags: |
-            sjdonado/bit:${{ steps.version.outputs.version }}-${{ matrix.platform == 'linux/amd64' && 'amd64' || 'arm64' }}
-          build-args: |
-            TARGETARCH=${{ matrix.platform == 'linux/amd64' && 'amd64' || 'arm64' }}
+          tags: sjdonado/bit:${{ steps.version.outputs.version }}
           cache-from: type=gha
           cache-to: type=gha,mode=max
-
-  create-manifest:
-    name: Create Manifest
-    runs-on: ubuntu-latest
-    needs: build-platforms
-    permissions:
-      packages: write
-    steps:
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      - name: Determine version
-        id: version
-        run: |
-          if [ "${{ github.event_name }}" = "release" ]; then
-            echo "version=${{ github.event.release.tag_name }}" >> $GITHUB_OUTPUT
-          else
-            echo "version=latest" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Create manifest
-        run: |
-          docker buildx imagetools create \
-            -t sjdonado/bit:${{ steps.version.outputs.version }} \
-            sjdonado/bit:${{ steps.version.outputs.version }}-{amd64,arm64}

.github/workflows/update-parsers.yml

@@ -0,0 +1,63 @@
+name: Update Parsers
+
+on:
+  schedule:
+    # Run every two weeks on Sunday at 00:00 UTC (1st and 3rd Sunday of each month)
+    - cron: '0 0 1-7,15-21 * 0'
+  workflow_dispatch: # Allow manual trigger
+
+jobs:
+  update-parsers:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      pull-requests: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Install Crystal
+        uses: crystal-lang/install-crystal@v1
+
+      - name: Install dependencies
+        run: shards install
+
+      - name: Build CLI
+        run: crystal build scripts/cli.cr -o cli
+
+      - name: Update parsers
+        run: ./cli --update-parsers
+
+      - name: Check for changes
+        id: changes
+        run: |
+          if [ -n "$(git status --porcelain)" ]; then
+            echo "has_changes=true" >> $GITHUB_OUTPUT
+          else
+            echo "has_changes=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Create Pull Request
+        if: steps.changes.outputs.has_changes == 'true'
+        uses: peter-evans/create-pull-request@v6
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          commit-message: 'chore: update parsers'
+          title: 'chore: Update UA regexes and GeoLite2 database'
+          body: |
+            ## Automated Parser Update
+
+            This PR updates the following data files:
+            - User Agent parsing regexes
+            - GeoLite2 database
+
+            **Triggered by**: Scheduled workflow (runs every 2 weeks)
+            **Date**: ${{ github.event.repository.updated_at }}
+
+            Please review the changes and merge if everything looks good.
+          branch: automated/update-parsers
+          delete-branch: true
+          labels: |
+            dependencies
+            automated

.gitignore

@@ -7,4 +7,6 @@
 /sqlite/
 .env.production
 
-resource_usage.txt
+*.log
+bit
+cli

Dockerfile

@@ -1,41 +1,37 @@
-FROM debian:bookworm-slim AS build
+FROM alpine:edge AS build
 
-ARG TARGETARCH
 ENV ENV=production
 WORKDIR /usr/src/app
 
-RUN apt-get update && apt-get install -y \
-    curl \
-    gnupg \
-    ca-certificates \
-    && mkdir -p /etc/apt/keyrings \
-    && curl -fsSL https://packagecloud.io/84codes/crystal/gpgkey | gpg --dearmor > /etc/apt/trusted.gpg.d/84codes_crystal.gpg \
-    && echo "deb [signed-by=/etc/apt/trusted.gpg.d/84codes_crystal.gpg] https://packagecloud.io/84codes/crystal/debian/ bookworm main" > /etc/apt/sources.list.d/84codes_crystal.list
-
-RUN apt-get update && apt-get install -y \
+RUN apk add --no-cache \
     crystal \
-    libssl-dev \
-    libyaml-dev \
-    libsqlite3-dev \
+    shards \
+    openssl-dev \
+    yaml-dev \
+    sqlite-dev \
     libevent-dev \
-    && rm -rf /var/lib/apt/lists/*
+    tzdata
 
 COPY . .
 
 RUN shards install --production
 RUN shards build --release --no-debug --progress --stats
 
-FROM debian:bookworm-slim AS runtime
+FROM alpine:latest AS runtime
 
 ENV ENV=production
 WORKDIR /usr/src/app
 
-RUN apt-get update && apt-get install -y \
-    libssl3 \
-    libyaml-0-2 \
-    libsqlite3-0 \
-    libevent-2.1-7 \
-    && rm -rf /var/lib/apt/lists/*
+RUN apk add --no-cache \
+    gc-dev \
+    pcre2 \
+    libevent \
+    sqlite-libs \
+    openssl \
+    yaml \
+    gmp \
+    libgcc \
+    tzdata
 
 RUN mkdir -p sqlite
 

README.md

@@ -1,28 +1,93 @@
 [![Docker Pulls](https://img.shields.io/docker/pulls/sjdonado/bit.svg)](https://hub.docker.com/r/sjdonado/bit)
-[![Docker Stars](https://img.shields.io/docker/stars/sjdonado/bit.svg)](https://hub.docker.com/r/sjdonado/bit)
 [![Docker Image Size](https://img.shields.io/docker/image-size/sjdonado/bit/latest)](https://hub.docker.com/r/sjdonado/bit)
 
-Lightweight URL shortener service with minimal resource requirements. Average memory consumption is **20MB RAM** with container disk space under **50MB**.
+## Features
 
-Bit is highly performant, achieving over 1.8K requests per second with an average latency of 68ms. For detailed benchmark results, see [benchmark](docs/SETUP.md#benchmark).
+- Minimal tracking setup: Country, browser, OS, referer. No cookies or persistent tracking mechanisms are used beyond what's available from a basic client's request.
+- Includes `X-Forwarded-For` header.
+- Multiple users are supported via API key authentication. Create, list and delete keys via the [CLI](docs/SETUP.md#cli).
+- Easy to extend, Ruby on Rails inspired setup.
+- Auto update UA regexes and GeoLite2 database.
 
-Images available on [Docker Hub](https://hub.docker.com/r/sjdonado/bit/tags).
+## Why bit?
 
-## Why Bit?
-It is feature-complete by design. Its strength lies in simplicity, a reliable URL shortener without unnecessary bloat. Bug fixes will continue, but new features aren't planned.
+**Fast:** **11k req/sec**, latency 11ms, 40MiB avg memory usage (100k requests using 125 connections, [benchmark](docs/SETUP.md#benchmark)).
 
-- Minimal tracking setup: Country, browser, os, referer. No cookies or persistent tracking mechanisms are used beyond what's available from a basic client's request.
-- Flexible request forwarding system passes client context (IP, user-agent) to destinations via standard `X-Forwarded-For` and `User-Agent` headers, enabling advanced tracking and integration capabilities when needed.
-- Multiple users are supported via API key authentication. Create, list and delete via the [CLI](docs/SETUP.md#cli).
+**Lightweight:** Minimal dependencies, image size under 20 MiB, memory usage under 60 MiB at peak.
 
-## Minimum Requirements
-- 50MB disk space
-- 50MB RAM (20MB avg usage)
-- x86_64 or ARM64 architecture
+**Self-hosted:** [Dokku](docs/SETUP.md#dokku), [Docker Compose](docs/SETUP.md#docker-compose).
+
+**Production ready:** Feature-complete by design, simple and reliable without unnecessary bloat. Bug fixes will continue, but new features aren't planned.
+
+## Run It Anywhere
+
+All images available on [Docker Hub](https://hub.docker.com/r/sjdonado/bit/tags).
+
+### Docker
+
+```bash
+docker run \
+    --name bit \
+    -p 4000:4000 \
+    -e ENV="production" \
+    -e DATABASE_URL="sqlite3://./sqlite/data.db" \
+    -e APP_URL="http://localhost:4000" \
+    -e ADMIN_NAME="Admin" \
+    -e ADMIN_API_KEY=$(openssl rand -base64 32) \
+    sjdonado/bit
+
+# Create a new user
+# docker exec -it bit cli --create-user=Admin
+```
+
+### Docker Compose
+
+```bash
+docker-compose up
+
+# Optional: Generate an api key
+# docker-compose exec -it app cli --create-user=Admin
+```
+
+### Dokku
+
+- Dockerfile
+```dockerfile
+FROM sjdonado/bit
+```
+
+- Over ssh
+
+```bash
+dokku apps:create bit
+
+dokku domains:set bit bit.yourdomain.com
+dokku letsencrypt:enable bit
+
+dokku storage:ensure-directory bit-sqlite
+dokku storage:mount bit /var/lib/dokku/data/storage/bit-sqlite:/usr/src/app/sqlite/
+
+dokku config:set bit DATABASE_URL="sqlite3://./sqlite/data.db" APP_URL=https://bit.yourdomain.com ADMIN_NAME=Admin ADMIN_API_KEY=$(openssl rand -base64 32)
+
+dokku ports:add bit http:80:4000
+dokku ports:add bit https:443:4000
+
+# Create a new user
+# dokku run bit cli --create-user=Admin
+```
+
+### Dokku (subnetwork)
+Recommended for lower latency communication (no host network traversal)
+
+```bash
+  dokku network:create bit-net
+  dokku network:set bit attach-post-create bit-net
+  dokku network:set myapp attach-post-create bit-net
+```
 
 ## Documentation
-- [API Reference](docs/API.md)
-- [Advanced Setup](docs/SETUP.md)
+- [API Reference](https://sjdonado.github.io/bit/)
+- [Local Development](docs/SETUP.md)
 
 ## Contributing
 Found an issue or have a suggestion? Please follow our [contribution guidelines](CONTRIBUTING.md).

app/controllers/click.cr

@@ -0,0 +1,45 @@
+module App::Controllers
+  struct ClickController
+    include App::Models
+    include App::Lib
+    include App::Services
+
+    def self.redirect_handler
+      ->(env : HTTP::Server::Context) {
+        link_id, url = Database.raw_query("SELECT id, url FROM links WHERE slug = (?) LIMIT 1", env.params.url["slug"]) do |result|
+          result.move_next ? {result.read(Int64), result.read(String)} : nil
+        end || raise App::NotFoundException.new(env)
+
+        remote_address = env.request.headers["Cf-Connecting-Ip"]? || env.request.remote_address.to_s
+
+        # Send redirect immediately
+        env.response.status_code = 301
+        env.response.headers.add("Location", url)
+        env.response.headers.add("X-Forwarded-For", remote_address)
+        if user_agent = env.request.headers["User-Agent"]?
+          env.response.headers.add("User-Agent", user_agent)
+        end
+
+        # non-blocking click proccessing
+        spawn do
+          begin
+            client_ip = IpLookup.ip_from_address(remote_address)
+            family, _, _, os = UserAgent.parse(env.request.headers["User-Agent"]? || "")
+
+            click = App::Models::Click.new
+            click.link_id = link_id
+            click.country = client_ip ? IpLookup.country(client_ip) : nil
+            click.user_agent = env.request.headers["User-Agent"]?
+            click.browser = family
+            click.os = os.try &.[0]
+            click.referer = env.request.headers["Referer"]?.try { |r| URI.parse(r).host rescue r } || env.params.query["utm_source"]? || "Direct"
+
+            Database.insert(click)
+          rescue ex
+            Log.error { "Click tracking error: #{ex.message}" }
+          end
+        end
+      }
+    end
+  end
+end

app/controllers/link.cr

@@ -1,250 +1,153 @@
-require "uuid"
-require "user_agent_parser"
-
-require "../lib/controller.cr"
-require "../lib/ip_lookup"
-
-UserAgent.load_regexes(File.read("data/uap_core_regexes.yaml"))
-IpLookup.load_mmdb("data/GeoLite2-Country.mmdb")
-
-module App::Controllers::Link
-  class Create < App::Lib::BaseController
+module App::Controllers
+  class LinkController < App::Lib::BaseController
     include App::Models
     include App::Lib
     include App::Services
 
-    def call(env)
-      user = env.get("user").as(User)
-      body = parse_body(env, ["url"])
+    def initialize(@env : HTTP::Server::Context)
+      super(@env)
+    end
+
+    def create
+      body = parse_body(["url"])
       url = body["url"].to_s
 
-      query = Database::Query.where(url: url, user_id: user.id.as(String)).limit(1)
+      query = Database::Query.where(url: url, user_id: current_user_id).limit(1)
       existing_link = Database.all(Link, query, preload: [:clicks]).first?
       if existing_link
-        response = {"data" => App::Serializers::Link.new(existing_link)}
-        return response.to_json
+        return render_json({"data" => App::Serializers::Link.new(existing_link)})
       end
 
       link = Link.new
-      link.id = UUID.v4.to_s
       link.url = url
-      link.user = user
-      link.slug = SlugService.shorten_url(url, user.id.to_s)
+      link.user_id = current_user_id
+      link.slug = SlugService.shorten_url(url, current_user_id)
 
       changeset = Database.insert(link)
       if !changeset.valid?
-        raise App::UnprocessableEntityException.new(env, map_changeset_errors(changeset.errors))
+        raise App::UnprocessableEntityException.new(@env, map_changeset_errors(changeset.errors))
       end
 
-      link.clicks = [] of App::Models::Click
-      response = {"data" => App::Serializers::Link.new(link)}
+      inserted_link = Database.get!(Link, changeset.instance.id)
 
-      response.to_json
+      render_json({"data" => App::Serializers::Link.new(inserted_link)}, 201)
     end
-  end
 
-  class Index < App::Lib::BaseController
-    include App::Models
-    include App::Lib
-
-    def call(env)
-      slug = env.params.url["slug"]
-
-      link = Database.get_by(Link, slug: slug)
-      raise App::NotFoundException.new(env) if !link
-
-      remote_address = env.request.headers["Cf-Connecting-Ip"]?.try(&.presence) || env.request.remote_address.try &.to_s
-      user_agent_str = env.request.headers["User-Agent"]? || "Unknown"
-
-      client_ip = IpLookup.extract_ip(remote_address) || "Unknown"
-
-      env.response.status_code = 301
-      env.response.headers["Location"] = link.url!
-
-      env.response.headers["X-Forwarded-For"] = client_ip
-      env.response.headers["User-Agent"] = user_agent_str
-
-      spawn do
-        ip_lookup = client_ip != "Unknown" ? IpLookup.new(client_ip) : nil
-        country = ip_lookup.try &.country.try &.code
-
-        user_agent = user_agent_str != "Unknown" ? UserAgent.new(user_agent_str) : nil
-
-        source = env.params.query["utm_source"]? || "Direct"
-        referer_host = env.request.headers["Referer"]?.try { |r| begin URI.parse(r).host rescue r end } || source
-
-        click = Click.new
-        click.id = UUID.v4.to_s
-        click.link = link
-        click.country = country
-        click.user_agent = user_agent_str
-        click.browser = user_agent.try &.family
-        click.os = user_agent.try &.os.try &.family
-        click.referer = referer_host
-
-        changeset = Database.insert(click)
-        if changeset.errors.any?
-          Log.error { "Logging click event failed: #{changeset.errors}" }
-        end
-      end
-    end
-  end
-
-  class All < App::Lib::BaseController
-    include App::Models
-    include App::Lib
-
-    def call(env)
-      user = env.get("user").as(User)
-
-      limit = (env.params.query["limit"]? || "100").to_i
-      cursor = env.params.query["cursor"]?
-
-      query = Database::Query.where(user_id: user.id.as(String))
-      if cursor
-        query = query.where("id < ?", cursor)
-      end
+    def list_all
+      limit, cursor = pagination_params
 
+      query = Database::Query.where(user_id: current_user_id)
+      query = query.where("id < ?", cursor) if cursor
       query = query.order_by("id DESC").limit(limit + 1)
+
       links = Database.all(Link, query)
 
-      has_more = links.size > limit
-      links = links[0...limit] if has_more
-
-      next_cursor = has_more ? links.last.id : nil
-
-      response = {
-        "data" => links.map { |link| App::Serializers::Link.new(link) },
-        "pagination" => {
-          "has_more" => has_more,
-          "next" => next_cursor
-        }
-      }
-
-      response.to_json
+      paginated_response(links, limit) { |link| App::Serializers::Link.new(link) }
     end
-  end
 
-  class Get < App::Lib::BaseController
-    include App::Models
-    include App::Lib
+    def get
+      link_id = @env.params.url["id"].to_i64
 
-    def call(env)
-      user = env.get("user").as(User)
-      link_id = env.params.url["id"]
-
-      query = Database::Query.where(id: link_id.as(String), user_id: user.id.as(String)).limit(1)
+      query = Database::Query.where(id: link_id, user_id: current_user_id).limit(1)
       link = Database.all(Link, query).first?
-      raise App::NotFoundException.new(env) if link.nil?
+      raise App::NotFoundException.new(@env) if link.nil?
 
-      clicks_query = Database::Query.where(link_id: link_id.as(String))
-                                    .order_by("id DESC")
-                                    .limit(100)
+      clicks_query = Database::Query.where(link_id: link_id)
+                                   .order_by("id DESC")
+                                   .limit(100)
       link.clicks = Database.all(Click, clicks_query)
 
-      response = {"data" => App::Serializers::Link.new(link)}
-      response.to_json
+      render_json({"data" => App::Serializers::Link.new(link)})
     end
-  end
 
-  class Clicks < App::Lib::BaseController
-    include App::Models
-    include App::Lib
+    def list_clicks
+      link_id = @env.params.url["id"].to_i64
 
-    def call(env)
-      user = env.get("user").as(User)
-      link_id = env.params.url["id"]
-
-      link_query = Database::Query.where(id: link_id.as(String), user_id: user.id.as(String)).limit(1)
+      # Verify link exists and belongs to user
+      link_query = Database::Query.where(id: link_id, user_id: current_user_id).limit(1)
       link = Database.all(Link, link_query).first?
-      raise App::NotFoundException.new(env) if link.nil?
+      raise App::NotFoundException.new(@env) if link.nil?
 
-      limit = (env.params.query["limit"]? || "100").to_i
-      cursor = env.params.query["cursor"]?
-
-      query = Database::Query.where(link_id: link_id.as(String))
-      if cursor
-        query = query.where("id < ?", cursor)
-      end
+      limit, cursor = pagination_params
 
+      query = Database::Query.where(link_id: link_id)
+      query = query.where("id < ?", cursor) if cursor
       query = query.order_by("id DESC").limit(limit + 1)
+
       clicks = Database.all(Click, query)
 
-      has_more = clicks.size > limit
-      clicks = clicks[0...limit] if has_more
-      next_cursor = has_more ? clicks.last.id : nil
-
-      response = {
-        "data" => clicks.map { |click| App::Serializers::Click.new(click) },
-        "pagination" => {
-          "has_more" => has_more,
-          "next" => next_cursor
-        }
-      }
-
-      response.to_json
+      paginated_response(clicks, limit) { |click| App::Serializers::Click.new(click) }
     end
-  end
 
-  class Update < App::Lib::BaseController
-    include App::Models
-    include App::Lib
-    include App::Services
-
-    def call(env)
-      user = env.get("user").as(User)
-      id = env.params.url["id"]
-      body = parse_body(env, ["url"])
+    def update
+      id = @env.params.url["id"].to_i64
+      body = parse_body(["url"])
+      new_url = body["url"].to_s
 
       query = Database::Query.where(id: id).limit(1)
       link = Database.all(Link, query, preload: [:clicks]).first?
 
-      raise App::NotFoundException.new(env) if link.nil?
-      raise App::ForbiddenException.new(env) if link.user_id != user.id
+      raise App::NotFoundException.new(@env) if link.nil?
+      raise App::ForbiddenException.new(@env) if link.user_id != current_user_id
 
-      new_url = body["url"].to_s
-
-      existing_query = Database::Query.where(url: new_url, user_id: user.id.to_s).limit(1)
-      existing_link = Database.all(Link, existing_query).first?
-
-      if existing_link
-        raise App::UnprocessableEntityException.new(env, { "url" => ["URL already exists"] })
+      # Check for existing URL
+      existing_query = Database::Query.where(url: new_url, user_id: current_user_id).limit(1)
+      if Database.all(Link, existing_query).first?
+        raise App::UnprocessableEntityException.new(@env, { "url" => ["URL already exists"] })
       end
 
       link.url = new_url
-      link.slug = SlugService.shorten_url(new_url, user.id.to_s)
+      link.slug = SlugService.shorten_url(new_url, current_user_id)
 
       changeset = Database.update(link)
       if !changeset.valid?
-        raise App::UnprocessableEntityException.new(env, map_changeset_errors(changeset.errors))
+        raise App::UnprocessableEntityException.new(@env, map_changeset_errors(changeset.errors))
       end
 
-      response = {"data" => App::Serializers::Link.new(link)}
-      response.to_json
+      render_json({"data" => App::Serializers::Link.new(link)})
     end
-  end
 
-  class Delete < App::Lib::BaseController
-    include App::Models
-    include App::Lib
-
-    def call(env)
-      user = env.get("user").as(User)
-      id = env.params.url["id"]
+    def delete
+      id = @env.params.url["id"].to_i64
 
       link = Database.get(Link, id)
-      raise App::NotFoundException.new(env) if !link
+      raise App::NotFoundException.new(@env) if !link
+      raise App::ForbiddenException.new(@env) if link.user_id != current_user_id
 
-      if link.user_id != user.id
-        raise App::ForbiddenException.new(env)
-      end
-
-      result = Database.raw_exec("DELETE FROM links WHERE id = (?)", link.id) # tempfix: Database.delete does not work
+      result = Database.raw_exec("DELETE FROM links WHERE id = (?)", link.id)
       if result.rows_affected == 0
-        raise App::UnprocessableEntityException.new(env, { "id" => ["Row delete failed"] })
+        raise App::UnprocessableEntityException.new(@env, { "id" => ["Row delete failed"] })
       end
 
-      env.response.status_code = 204
+      @env.response.status_code = 204
+    end
+
+    private def current_user : User
+      @env.get("user").as(User)
+    end
+
+    private def current_user_id : Int64
+      current_user.id.as(Int64)
+    end
+
+    private def pagination_params
+      limit = (@env.params.query["limit"]? || "100").to_i32
+      cursor = @env.params.query["cursor"]?
+      {limit, cursor}
+    end
+
+    private def paginated_response(items, limit)
+      has_more = items.size > limit
+      items = items[0...limit] if has_more
+      next_cursor = has_more ? items.last.id : nil
+
+      render_json({
+        "data" => items.map { |item| yield item },
+        "pagination" => {
+          "has_more" => has_more,
+          "next" => next_cursor
+        }
+      })
     end
   end
 end

app/controllers/ping.cr

@@ -1,10 +1,13 @@
 require "../lib/controller.cr"
 
-module App::Controllers::Ping
-  class Get < App::Lib::BaseController
-    def call(env)
-      response = {"data" => "pong"}
-      response.to_json
+module App::Controllers
+  class PingController < App::Lib::BaseController
+    def initialize(@env : HTTP::Server::Context)
+      super(@env)
+    end
+
+    def ping
+      render_json({data: "pong"})
     end
   end
 end

app/lib/controller.cr

@@ -1,29 +1,45 @@
 module App::Lib
   abstract class BaseController
-    def map_changeset_errors(errors)
+    protected getter env : HTTP::Server::Context
+
+    def initialize(@env : HTTP::Server::Context); end
+
+    # Convert changeset errors to API-friendly format
+    protected def map_changeset_errors(errors)
       errors.reduce({} of String => Array(String)) do |memo, error|
-        memo[error[:field]] = memo[error[:field]]? || [] of String
-        memo[error[:field]] << error[:message]
+        field = error[:field].to_s
+        message = error[:message].to_s
+
+        memo[field] ||= [] of String
+        memo[field] << message
         memo
       end
     end
 
-    def parse_body(env, fields)
-      json_params = env.params.json.to_h
-      missing_fields = [] of String
+    protected def parse_body(required_fields : Array(String) = [] of String)
+      json_params = @env.params.json.try(&.to_h) || {} of String => JSON::Any
+      json_params = json_params.transform_values(&.to_s) # Convert JSON::Any to String
 
-      fields.each do |field|
-        unless json_params.has_key?(field)
-          missing_fields << field
-        end
-      end
+      missing_fields = required_fields.reject { |field| json_params.has_key?(field) }
 
       unless missing_fields.empty?
-        error_message = missing_fields.map { |field| "#{field}: Required field" }.join(", ")
-        raise App::BadRequestException.new(env, error_message)
+        error_message = "#{missing_fields.first}: Required field"
+        raise App::BadRequestException.new(@env, error_message)
       end
 
       json_params
     end
+
+    protected def render_json(data, status_code : Int32 = 200)
+      @env.response.status_code = status_code
+      @env.response.content_type = "application/json"
+      data.to_json
+    end
+
+    protected def param(key : String) : String
+      @env.params.url[key]
+    rescue KeyError
+      raise App::BadRequestException.new(@env, "Missing required parameter: #{key}")
+    end
   end
 end

app/lib/database.cr

@@ -1,6 +1,6 @@
 require "sqlite3"
 require "crecto"
-require"micrate"
+require "micrate"
 
 module App::Lib
   class Database
@@ -9,7 +9,15 @@ module App::Lib
     Query = Crecto::Repo::Query
 
     config do |conf|
-      conf.uri = ENV["DATABASE_URL"]
+      base_url = ENV["DATABASE_URL"]
+      separator = base_url.includes?("?") ? "&" : "?"
+
+      db_url = base_url + separator +
+        "&journal_mode=WAL" +
+        "&synchronous=NORMAL" +      # Better performance with reasonable safety
+        "&foreign_keys=true"
+
+      conf.uri = db_url
     end
 
     if ENV["ENV"] == "development"

app/lib/errors.cr

@@ -55,12 +55,3 @@ module App
     end
   end
 end
-
-error 500 do |env|
-  App::InternalServerErrorException.new(env)
-  ""
-end
-
-error 404 do |env|
-  ""
-end

app/lib/ip_lookup.cr

@@ -1,54 +1,45 @@
 require "maxminddb"
+require "log"
 
-class IpLookup
-  @@instance : MaxMindDB::Reader? = nil
+module App::Lib
+  struct IpLookup
+    MMDB_PATH = "data/GeoLite2-Country.mmdb"
 
-  record Country, code : String? = nil, name : String? = nil
+    @@reader : MaxMindDB::Reader? = nil
+    @@reader_mutex = Mutex.new
 
-  getter ip : String
-  getter country : Country?
-
-  def self.load_mmdb(mmdb_file_path : String)
-    @@instance = MaxMindDB.open(mmdb_file_path)
-  end
-
-  def initialize(ip_address : String)
-    @ip = ip_address
-    @country = nil
-
-    return if @@instance.nil? || ip_address == "Unknown" || ip_address.empty?
-
-    begin
-      lookup = @@instance.not_nil!.get(ip_address)
-
-      country_code = lookup["country"]?.try &.["iso_code"]?.try &.as_s
-      country_name = lookup["country"]?.try &.["names"]?.try &.["en"]?.try &.as_s
-
-      if country_code || country_name
-        @country = Country.new(
-          code: country_code,
-          name: country_name
-        )
+    private def self.get_reader : MaxMindDB::Reader
+      @@reader_mutex.synchronize do
+        @@reader ||= MaxMindDB.open(MMDB_PATH)
       end
-    rescue ex
-      # Silently handle lookup errors
-      Log.error { "IP lookup failed: #{ex.message}" }
     end
-  end
 
-  def self.extract_ip(address_string : String?) : String?
-    return nil if address_string.nil?
+    def self.country(ip_address : String) : String?
+      return nil if ip_address == "Unknown" || ip_address.empty?
 
-    if address_string.includes?('[') # IPv6 with port: [2001:db8::1]:8080
-      address_string.split(']').first.sub('[', '\'')
-    elsif address_string.includes?(':')
-      if address_string.count(':') > 1 # IPv6 without port
-        address_string
-      else # IPv4 with port: 192.168.1.1:8080
-        address_string.split(':').first
+      begin
+        lookup = get_reader.get(ip_address)
+        lookup["country"]?.try &.["iso_code"]?.try &.as_s
+      rescue ex
+        Log.error { "IP lookup failed: #{ex.message}" }
+        nil
+      end
+    end
+
+    def self.ip_from_address(address_string : String?) : String?
+      return nil if address_string.nil?
+
+      if address_string.includes?('[') # IPv6 with port: [2001:db8::1]:8080
+        address_string.split(']').first.sub('[', '\'')
+      elsif address_string.includes?(':')
+        if address_string.count(':') > 1 # IPv6 without port
+          address_string
+        else # IPv4 with port: 192.168.1.1:8080
+          address_string.split(':').first
+        end
+      else # Address without port
+        address_string
       end
-    else # Address without port
-      address_string
     end
   end
 end

app/lib/ua_parser.cr

@@ -0,0 +1,123 @@
+require "yaml"
+require "semantic_version"
+
+module App::Lib
+  struct UserAgent
+    REGEXES_PATH = "data/uap_core_regexes.yaml"
+
+    @@regexes_cache : YAML::Any? = nil
+    @@compiled_regexes = {} of String => Array(Tuple(Regex, YAML::Any))
+    @@mutex = Mutex.new
+
+    private def self.load_regexes
+      @@mutex.synchronize do
+        if @@regexes_cache.nil?
+          begin
+            regexes_yaml = File.read(REGEXES_PATH)
+            @@regexes_cache = YAML.parse(regexes_yaml)
+
+            # Pre-compile all regexes for better performance
+            ["user_agent_parsers", "os_parsers", "device_parsers"].each do |parser_type|
+              @@compiled_regexes[parser_type] = [] of Tuple(Regex, YAML::Any)
+
+              @@regexes_cache.not_nil![parser_type].as_a.each do |parser|
+                regex_str = parser["regex"].as_s
+                options = parser["regex_flag"]?.try(&.as_s) == "i" ?
+                  Regex::Options::IGNORE_CASE : Regex::Options::None
+
+                begin
+                  compiled_regex = Regex.new(regex_str, options)
+                  @@compiled_regexes[parser_type] << {compiled_regex, parser}
+                rescue
+                  # Skip invalid regexes
+                end
+              end
+            end
+          rescue ex
+            # If loading fails, set an empty cache to prevent repeated failures
+            @@regexes_cache = YAML.parse("{}")
+            @@compiled_regexes = {} of String => Array(Tuple(Regex, YAML::Any))
+          end
+        end
+      end
+    end
+
+    def self.parse(user_agent_string : String)
+      return {nil, nil, nil, nil} if user_agent_string.empty?
+
+      # Load regexes only once and cache them
+      load_regexes
+
+      family = nil
+      version = nil
+      device = nil
+      os = nil
+
+      @@compiled_regexes["user_agent_parsers"]?.try &.each do |regex_tuple|
+        regex, parser = regex_tuple
+        match = regex.match(user_agent_string)
+        next unless match
+
+        family = match[1]? || nil
+        v1 = (match[2]? || "0").to_i
+        v2 = (match[3]? || "0").to_i
+        v3 = (match[4]? || "0").to_i
+
+        # Apply replacements if defined
+        if replacement = parser["family_replacement"]?
+          family = replacement.as_s.gsub("$1", family.to_s)
+        end
+
+        version = SemanticVersion.new(v1, v2, v3)
+        break
+      end
+
+      @@compiled_regexes["os_parsers"]?.try &.each do |regex_tuple|
+        regex, parser = regex_tuple
+        match = regex.match(user_agent_string)
+        next unless match
+
+        os_family = match[1]? || nil
+        os_v1 = (match[2]? || "0").to_i
+        os_v2 = (match[3]? || "0").to_i
+        os_v3 = (match[4]? || "0").to_i
+
+        # Apply replacements if defined
+        if replacement = parser["os_replacement"]?
+          os_family = replacement.as_s.gsub("$1", os_family.to_s)
+        end
+
+        os = {os_family, SemanticVersion.new(os_v1, os_v2, os_v3)}
+        break
+      end
+
+      @@compiled_regexes["device_parsers"]?.try &.each do |regex_tuple|
+        regex, parser = regex_tuple
+        match = regex.match(user_agent_string)
+        next unless match
+
+        model = match[1]? || nil
+        device_name = model
+        brand = nil
+
+        # Apply replacements if defined
+        if device_replacement = parser["device_replacement"]?
+          device_name = device_replacement.as_s.gsub("$1", device_name.to_s)
+        end
+
+        if model_replacement = parser["model_replacement"]?
+          model = model_replacement.as_s.gsub("$1", model.to_s)
+        end
+
+        if brand_replacement = parser["brand_replacement"]?
+          brand = brand_replacement.as_s
+        end
+
+        device = {model, brand, device_name}
+        break
+      end
+
+      {family, version, device, os}
+    end
+  end
+end

app/middlewares/cors.cr

@@ -0,0 +1,29 @@
+module App::Middlewares
+  class CORSHandler < Kemal::Handler
+    exclude ["/api/ping", "/:slug"]
+
+    def initialize(
+      @allow_origin = "*",
+      @allow_methods = "GET, POST, PUT, DELETE, OPTIONS",
+      @allow_headers = "Content-Type, Accept, Origin, X-Api-Key"
+    )
+    end
+
+    def call(env)
+      return call_next(env) if exclude_match?(env)
+
+      env.response.headers["Access-Control-Allow-Origin"] = @allow_origin
+      env.response.headers["Access-Control-Allow-Methods"] = @allow_methods
+      env.response.headers["Access-Control-Allow-Headers"] = @allow_headers
+
+      if env.request.method == "OPTIONS"
+        env.response.status_code = 200
+        env.response.content_type = "text/plain"
+        env.response.print("")
+        return env
+      end
+
+      call_next(env)
+    end
+  end
+end

app/models/click.cr

@@ -3,7 +3,7 @@ require "crecto"
 module App::Models
   class Click < Crecto::Model
     schema :clicks do
-      field :id, String, primary_key: true
+      field :id, Int64, primary_key: true
       field :user_agent, String
       field :country, String
       field :browser, String

app/models/link.cr

@@ -6,7 +6,7 @@ require "./user.cr"
 module App::Models
   class Link < Crecto::Model
     schema :links do
-      field :id, String, primary_key: true
+      field :id, Int64, primary_key: true
       field :slug, String
       field :url, String
 

app/models/user.cr

@@ -4,7 +4,7 @@ require "crecto"
 module App::Models
   class User < Crecto::Model
     schema :users do
-      field :id, String, primary_key: true
+      field :id, Int64, primary_key: true
       field :name, String
       field :api_key, String
     end

app/routes.cr

@@ -1,45 +1,44 @@
 require "./controllers/**"
 
+require "kemal"
+
+add_handler App::Middlewares::CORSHandler.new
+add_handler App::Middlewares::Auth.new
+
 module App
-  before_all do |env|
-    env.response.headers["Access-Control-Allow-Origin"] = "*"
-    env.response.headers["Access-Control-Allow-Methods"] = "GET, POST, PUT, DELETE, OPTIONS"
-    env.response.headers["Access-Control-Allow-Headers"] = "Content-Type, Accept, Origin, X-Api-Key"
-  end
-
-  after_all do |env|
-    env.response.content_type = "application/json"
-  end
+  get "/:slug", &App::Controllers::ClickController.redirect_handler
 
+  # Namespace /api
   get "/api/ping" do |env|
-    Controllers::Ping::Get.new.call(env)
-  end
-
-  get "/:slug" do |env|
-    Controllers::Link::Index.new.call(env)
+    Controllers::PingController.new(env).ping
   end
 
   get "/api/links" do |env|
-    Controllers::Link::All.new.call(env)
+    Controllers::LinkController.new(env).list_all
   end
 
   get "/api/links/:id" do |env|
-    Controllers::Link::Get.new.call(env)
+    Controllers::LinkController.new(env).get
   end
 
   get "/api/links/:id/clicks" do |env|
-    Controllers::Link::Clicks.new.call(env)
+    Controllers::LinkController.new(env).list_clicks
   end
 
   post "/api/links" do |env|
-    Controllers::Link::Create.new.call(env)
+    Controllers::LinkController.new(env).create
   end
 
   put "/api/links/:id" do |env|
-    Controllers::Link::Update.new.call(env)
+    Controllers::LinkController.new(env).update
   end
 
   delete "/api/links/:id" do |env|
-    Controllers::Link::Delete.new.call(env)
+    Controllers::LinkController.new(env).delete
+  end
+
+  error 500 do |env|
+    App::InternalServerErrorException.new(env)
+    ""
   end
 end

app/services/cli.cr

@@ -8,12 +8,11 @@ require "../models/*"
 module App::Services::Cli
   def self.create_user(name, api_key = nil)
     user = App::Models::User.new
-    user.id = UUID.v4.to_s
     user.name = name
     user.api_key = api_key || Random::Secure.urlsafe_base64()
 
     changeset = App::Lib::Database.insert(user)
-    return changeset.errors if !changeset.valid?
+    return changeset.errors unless changeset.valid?
 
     "New user created: Name: #{user.name}, X-Api-Key: #{user.api_key}"
   end
@@ -74,7 +73,7 @@ module App::Services::Cli
     end
   end
 
-  def self.download_geolite_db
+  def self.update_geolite_db
     puts "Downloading GeoLite2 Country database..."
 
     FileUtils.mkdir_p("data")

app/services/slug.cr

@@ -2,7 +2,7 @@ require "digest"
 require "base64"
 
 module App::Services::SlugService
-  def self.shorten_url(url : String, user_id : String) : String
+  def self.shorten_url(url : String, user_id : Int64) : String
     combined = "#{user_id}-#{url}"
     crc32_hash = Digest::CRC32.digest(combined)
     base62_encoded = Base64.urlsafe_encode(crc32_hash).strip.tr("-_=", "")

benchmark.sh

@@ -1,156 +0,0 @@
-#!/bin/bash
-
-# Configuration variables
-server_url="http://localhost:4000"
-api_url="${server_url}/api/links"
-num_links=10000
-num_requests=10000
-concurrency=100
-resource_usage_interval=1
-container_name="bit"
-
-check_dependencies() {
-    if ! command -v bombardier &> /dev/null; then
-        echo "Error: bombardier is not installed. Please install it to proceed."
-        exit 1
-    fi
-
-    if ! command -v jq &> /dev/null; then
-        echo "Error: jq is not installed. Please install it to proceed."
-        exit 1
-    fi
-}
-
-setup_containers() {
-    echo "Setting up..."
-    docker compose up -d
-    if [ $? -ne 0 ]; then
-        echo "Failed to start Docker containers."
-        exit 1
-    fi
-
-    output=$(docker compose exec -T app cli --create-user=Admin)
-    api_key=$(echo "$output" | awk -F' ' '/X-Api-Key:/{print $NF}')
-    echo "Captured API Key: $api_key"
-
-    if [[ -z "$api_key" ]]; then
-        echo "Error: API key could not be retrieved."
-        exit 1
-    fi
-
-    echo "Waiting for the application to be ready..."
-    until curl --silent --head --fail --header "X-Api-Key: $api_key" "$server_url/api/ping"; do
-        sleep 2
-    done
-}
-
-monitor_resource_usage() {
-    echo "Starting resource usage monitoring..."
-    echo "Timestamp,CPU,Memory" > resource_usage.csv
-    while :; do
-        stats=$(docker stats --no-stream --format "{{.CPUPerc}},{{.MemUsage}}" $container_name)
-        cpu=$(echo $stats | awk -F',' '{print $1}' | sed 's/%//')
-        mem=$(echo $stats | awk -F',' '{print $2}' | awk '{print $1}')
-        timestamp=$(date +%s)
-        echo "$timestamp,$cpu,$mem" >> resource_usage.csv
-        sleep $resource_usage_interval
-    done
-}
-
-create_links() {
-    local temp_file=$(mktemp)
-
-    echo "Creating $num_links short links with $concurrency conrurrent requests..."
-
-    # Populate URLs into a file to feed into curl
-    for ((i=1; i<=num_links; i++)); do
-        url="https://example.com/${i}-${num_links}"
-        echo "--next" >> "$temp_file"
-        echo "--request POST" >> "$temp_file"
-        echo "--url \"$api_url\"" >> "$temp_file"
-        echo "--header \"X-Api-Key: $api_key\"" >> "$temp_file"
-        echo "--header \"Content-Type: application/json\"" >> "$temp_file"
-        echo "--data \"{ \\\"url\\\": \\\"$url\\\" }\"" >> "$temp_file"
-    done
-
-    curl --parallel --parallel-immediate --parallel-max $concurrency --config "$temp_file" --silent --write-out "%{http_code}\n" > /dev/null
-
-    echo "Link creation complete: $num_links links created."
-
-    # Clean up
-    rm -f "$temp_file"
-}
-
-run_benchmark() {
-    echo "Fetching all created links from /api/links..."
-    all_links_response=$(curl --silent --request GET \
-                              --url "$api_url" \
-                              --header "X-Api-Key: $api_key" \
-                              --header "Content-Type: application/json")
-
-    links=($(echo "$all_links_response" | jq -r '.data[] | .refer'))
-    if [[ ${#links[@]} -ne $num_links ]]; then
-        echo "Error: Expected $num_links links but found ${#links[@]}."
-        exit 1
-    fi
-
-    random_link="${links[RANDOM % ${#links[@]}]}"
-    echo "Selected link for benchmarking: $random_link"
-
-    echo "Starting benchmark with Bombardier..."
-    bombardier -c $concurrency -n $num_requests "$random_link"
-    echo "Benchmark completed."
-}
-
-analyze_resource_usage() {
-    echo "Analyzing resource usage..."
-    total_cpu=0
-    total_mem=0
-    count=0
-
-    while IFS=',' read -r timestamp cpu mem; do
-        # Skip header line and lines with empty cpu or mem values
-        if [[ $timestamp != "Timestamp" && -n $cpu && -n $mem ]]; then
-            mem=${mem%MiB}
-
-            total_cpu=$(echo "$total_cpu + $cpu" | bc)
-            total_mem=$(echo "$total_mem + $mem" | bc)
-            ((count++))
-        fi
-    done < resource_usage.csv
-
-    avg_cpu=0.00
-    avg_mem=0.00
-
-    if (( count > 0 )); then
-        avg_cpu=$(echo "scale=2; $total_cpu / $count" | bc)
-        avg_mem=$(echo "scale=2; $total_mem / $count" | bc)
-    fi
-
-    echo "**** Results ****"
-    echo "Average CPU Usage: $avg_cpu%"
-    echo "Average Memory Usage: $avg_mem MiB"
-}
-
-cleanup() {
-    rm -f resource_usage.csv
-    docker compose down
-}
-
-main() {
-    check_dependencies
-    setup_containers
-
-    monitor_resource_usage &  # Start monitoring in the background
-    monitor_pid=$!
-    trap 'kill $monitor_pid; cleanup; exit' INT
-
-    create_links
-    run_benchmark
-
-    kill $monitor_pid
-    analyze_resource_usage
-    cleanup
-}
-
-main

bit.cr

@@ -10,8 +10,6 @@ require "./app/services/*"
 require "./app/routes"
 
 add_context_storage_type(App::Models::User)
-add_handler(App::Middlewares::Auth.new)
-
 App::Services::Cli.setup_admin_user
 
 Kemal.run

data/uap_core_regexes.yaml

@@ -93,6 +93,10 @@ user_agent_parsers:
   - regex: '(NewRelicPinger)/(\d+)\.(\d+)'
     family_replacement: 'NewRelicPingerBot'
 
+  # Dynatrace/Ruxit synthetic monitor
+  - regex: '(RuxitSynthetic)/(\d+)\.(\d+)'
+    family_replacement: 'Ruxit Synthetic'
+
   # Tableau
   - regex: '(Tableau)/(\d+)\.(\d+)'
     family_replacement: 'Tableau'
@@ -148,7 +152,7 @@ user_agent_parsers:
     family_replacement: 'Pinterestbot'
 
   # Bots
-  - regex: '(CSimpleSpider|Cityreview Robot|CrawlDaddy|CrawlFire|Finderbots|Index crawler|Job Roboter|KiwiStatus Spider|Lijit Crawler|QuerySeekerSpider|ScollSpider|Trends Crawler|USyd-NLP-Spider|SiteCat Webbot|BotName\/\$BotVersion|123metaspider-Bot|1470\.net crawler|50\.nu|8bo Crawler Bot|Aboundex|Accoona-[A-z]{1,30}-Agent|AdsBot-Google(?:-[a-z]{1,30}|)|altavista|AppEngine-Google|archive.{0,30}\.org_bot|archiver|Ask Jeeves|[Bb]ai[Dd]u[Ss]pider(?:-[A-Za-z]{1,30})(?:-[A-Za-z]{1,30}|)|bingbot|BingPreview|blitzbot|BlogBridge|Bloglovin|BoardReader Blog Indexer|BoardReader Favicon Fetcher|boitho.com-dc|BotSeer|BUbiNG|\b\w{0,30}favicon\w{0,30}\b|\bYeti(?:-[a-z]{1,30}|)|Catchpoint(?: bot|)|[Cc]harlotte|Checklinks|clumboot|Comodo HTTP\(S\) Crawler|Comodo-Webinspector-Crawler|ConveraCrawler|CRAWL-E|CrawlConvera|Daumoa(?:-feedfetcher|)|Feed Seeker Bot|Feedbin|findlinks|Flamingo_SearchEngine|FollowSite Bot|furlbot|Genieo|gigabot|GomezAgent|gonzo1|(?:[a-zA-Z]{1,30}-|)Googlebot(?:-[a-zA-Z]{1,30}|)|GoogleOther|Google SketchUp|grub-client|gsa-crawler|heritrix|HiddenMarket|holmes|HooWWWer|htdig|ia_archiver|ICC-Crawler|Icarus6j|ichiro(?:/mobile|)|IconSurf|IlTrovatore(?:-Setaccio|)|InfuzApp|Innovazion Crawler|InternetArchive|IP2[a-z]{1,30}Bot|jbot\b|KaloogaBot|Kraken|Kurzor|larbin|LEIA|LesnikBot|Linguee Bot|LinkAider|LinkedInBot|Lite Bot|Llaut|lycos|Mail\.RU_Bot|masscan|masidani_bot|Mediapartners-Google|Microsoft .{0,30} Bot|mogimogi|mozDex|MJ12bot|msnbot(?:-media {0,2}|)|msrbot|Mtps Feed Aggregation System|netresearch|Netvibes|NewsGator[^/]{0,30}|^NING|Nutch[^/]{0,30}|Nymesis|ObjectsSearch|OgScrper|Orbiter|OOZBOT|PagePeeker|PagesInventory|PaxleFramework|Peeplo Screenshot Bot|PHPCrawl|PlantyNet_WebRobot|Pompos|Qwantify|Read%20Later|Reaper|RedCarpet|Retreiver|Riddler|Rival IQ|scooter|Scrapy|Scrubby|searchsight|seekbot|semanticdiscovery|SemrushBot|Simpy|SimplePie|SEOstats|SimpleRSS|SiteCon|Slackbot-LinkExpanding|Slack-ImgProxy|Slurp|snappy|Speedy Spider|Squrl Java|Stringer|TheUsefulbot|ThumbShotsBot|Thumbshots\.ru|Tiny Tiny RSS|Twitterbot|WhatsApp|URL2PNG|Vagabondo|VoilaBot|^vortex|Votay bot|^voyager|WASALive.Bot|Web-sniffer|WebThumb|WeSEE:[A-z]{1,30}|WhatWeb|WIRE|WordPress|Wotbox|www\.almaden\.ibm\.com|Xenu(?:.s|) Link Sleuth|Xerka [A-z]{1,30}Bot|yacy(?:bot|)|YahooSeeker|Yahoo! Slurp|Yandex\w{1,30}|YodaoBot(?:-[A-z]{1,30}|)|YottaaMonitor|Yowedo|^Zao|^Zao-Crawler|ZeBot_www\.ze\.bz|ZooShot|ZyBorg|ArcGIS Hub Indexer|GPTBot)(?:[ /]v?(\d+)(?:\.(\d+)(?:\.(\d+)|)|)|)'
+  - regex: '(CSimpleSpider|Cityreview Robot|CrawlDaddy|CrawlFire|Finderbots|Index crawler|Job Roboter|KiwiStatus Spider|Lijit Crawler|QuerySeekerSpider|ScollSpider|Trends Crawler|USyd-NLP-Spider|SiteCat Webbot|BotName\/\$BotVersion|123metaspider-Bot|1470\.net crawler|50\.nu|8bo Crawler Bot|Aboundex|Accoona-[A-z]{1,30}-Agent|AdsBot-Google(?:-[a-z]{1,30}|)|altavista|AppEngine-Google|archive.{0,30}\.org_bot|archiver|Ask Jeeves|[Bb]ai[Dd]u[Ss]pider(?:-[A-Za-z]{1,30})(?:-[A-Za-z]{1,30}|)|bingbot|BingPreview|blitzbot|BlogBridge|Bloglovin|BoardReader Blog Indexer|BoardReader Favicon Fetcher|boitho.com-dc|BotSeer|BUbiNG|\b\w{0,30}favicon\w{0,30}\b|\bYeti(?:-[a-z]{1,30}|)|Catchpoint(?: bot|)|[Cc]harlotte|Checklinks|clumboot|Comodo HTTP\(S\) Crawler|Comodo-Webinspector-Crawler|ConveraCrawler|CRAWL-E|CrawlConvera|Daumoa(?:-feedfetcher|)|Feed Seeker Bot|Feedbin|findlinks|Flamingo_SearchEngine|FollowSite Bot|furlbot|Genieo|gigabot|GomezAgent|gonzo1|(?:[a-zA-Z]{1,30}-|)Googlebot(?:-[a-zA-Z]{1,30}|)|GoogleOther|Google SketchUp|grub-client|gsa-crawler|heritrix|HiddenMarket|holmes|HooWWWer|htdig|ia_archiver|ICC-Crawler|Icarus6j|ichiro(?:/mobile|)|IconSurf|IlTrovatore(?:-Setaccio|)|InfuzApp|Innovazion Crawler|InternetArchive|IP2[a-z]{1,30}Bot|jbot\b|KaloogaBot|Kraken|Kurzor|larbin|LEIA|LesnikBot|Linguee Bot|LinkAider|LinkedInBot|Lite Bot|Llaut|lycos|Mail\.RU_Bot|masscan|masidani_bot|Mediapartners-Google|Microsoft .{0,30} Bot|mogimogi|mozDex|MJ12bot|msnbot(?:-media {0,2}|)|msrbot|Mtps Feed Aggregation System|netresearch|Netvibes|NewsGator[^/]{0,30}|^NING|Nutch[^/]{0,30}|Nymesis|ObjectsSearch|OgScrper|Orbiter|OOZBOT|PagePeeker|PagesInventory|PaxleFramework|Peeplo Screenshot Bot|PHPCrawl|PlantyNet_WebRobot|Pompos|Qwantify|Read%20Later|Reaper|RedCarpet|Retreiver|Riddler|Rival IQ|scooter|Scrapy|Scrubby|searchsight|seekbot|semanticdiscovery|SemrushBot|Simpy|SimplePie|SEOstats|SimpleRSS|SiteCon|Slackbot-LinkExpanding|Slack-ImgProxy|Slurp|snappy|Speedy Spider|Squrl Java|Stringer|TheUsefulbot|ThumbShotsBot|Thumbshots\.ru|Tiny Tiny RSS|Twitterbot|WhatsApp|URL2PNG|Vagabondo|VoilaBot|^vortex|Votay bot|^voyager|WASALive.Bot|Web-sniffer|WebThumb|WeSEE:[A-z]{1,30}|WhatWeb|WIRE|WordPress|Wotbox|www\.almaden\.ibm\.com|Xenu(?:.s|) Link Sleuth|Xerka [A-z]{1,30}Bot|yacy(?:bot|)|YahooSeeker|Yahoo! Slurp|Yandex\w{1,30}|YodaoBot(?:-[A-z]{1,30}|)|YottaaMonitor|Yowedo|^Zao|^Zao-Crawler|ZeBot_www\.ze\.bz|ZooShot|ZyBorg|ArcGIS Hub Indexer|GPTBot|Google-InspectionTool)(?:[ /]v?(\d+)(?:\.(\d+)(?:\.(\d+)|)|)|)'
 
   # AWS S3 Clients
   # must come before "Bots General matcher" to catch "boto"/"boto3" before "bot"
@@ -206,7 +210,12 @@ user_agent_parsers:
   - regex: '\[(Pinterest)/[^\]]{1,50}\]'
   - regex: '(Pinterest)(?: for Android(?: Tablet|)|)/(\d+)(?:\.(\d+)|)(?:\.(\d+)|)'
   # Instagram app
+  # iOS Instagram embeds the token inside a full WebKit UA:
+  #   Mozilla/5.0 (iPhone; ...) Mobile/... Instagram VERSION (...)
+  # Android Instagram uses a bare format with no browser wrapper:
+  #   Instagram VERSION Android (...)
   - regex: 'Mozilla.{1,200}Mobile.{1,100}(Instagram).(\d+)\.(\d+)\.(\d+)'
+  - regex: '(Instagram) (\d+)\.(\d+)\.(\d+)'
   # Flipboard app
   - regex: 'Mozilla.{1,200}Mobile.{1,100}(Flipboard).(\d+)\.(\d+)\.(\d+)'
   # Flipboard-briefing app
@@ -228,6 +237,9 @@ user_agent_parsers:
   # KakaoTalk
   - regex: 'Mozilla.{1,200}Mobile.{1,100}(KAKAOTALK)/(\d+)\.(\d+)\.(\d+)'
     family_replacement: 'KakaoTalk'
+  # Telegram
+  - regex: '(Telegram-Android)/(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'Telegram'
 
   # Phantom app
   - regex: 'Mozilla.{1,200}Mobile.{1,100}(Phantom\/ios|Phantom\/android).(\d+)\.(\d+)\.(\d+)'
@@ -248,6 +260,10 @@ user_agent_parsers:
   - regex: '(PaleMoon)/(\d+)\.(\d+)(?:\.(\d+)|)'
     family_replacement: 'Pale Moon'
 
+  # Camoufox - anti-detect Firefox fork for web scraping/automation; replaces the
+  # Firefox version token with "Camoufox Camoufox VERSION" in the UA string
+  - regex: '(Camoufox) Camoufox (\d+)\.(\d+)'
+
   # Firefox
   - regex: '(Fennec)/(\d+)\.(\d+)\.?([ab]?\d+[a-z]*)'
     family_replacement: 'Firefox Mobile'
@@ -296,7 +312,7 @@ user_agent_parsers:
 
   # UC Browser
   # we need check it before opera. In other case case UC Browser detected look like Opera Mini
-  - regex: '(UC? ?Browser|UCWEB|U3)[ /]?(\d+)\.(\d+)\.(\d+)'
+  - regex: '(UC? ?Browser|UCWEB|UCMobile|U3)[ /]?(\d+)\.(\d+)\.(\d+)'
     family_replacement: 'UC Browser'
 
   # Opera will stop at 9.80 and hide the real version in the Version string.
@@ -321,6 +337,14 @@ user_agent_parsers:
   - regex: '(?:Chrome).{1,300}(OPR)/(\d+)\.(\d+)\.(\d+)'
     family_replacement: 'Opera'
 
+  # Opera GX uses "OPX" instead of "OPR"
+  - regex: '(OPX)/(\d+)\.(\d+)(?:\.(\d+)|)'
+    family_replacement: 'Opera GX'
+
+  # Opera Touch uses "OPT"
+  - regex: '(OPT)/(\d+)\.(\d+)(?:\.(\d+)|)'
+    family_replacement: 'Opera Touch'
+
   # Opera Coast
   - regex: '(Coast)/(\d+).(\d+).(\d+)'
     family_replacement: 'Opera Coast'
@@ -410,10 +434,14 @@ user_agent_parsers:
   - regex: '(AlohaBrowser|ABB)/(\d+)\.(\d+)\.(\d+)(?:\.(\d+)|)'
     family_replacement: 'Aloha Browser'
 
-  # Brave Browser https://brave.com/ , should go before Safari and Chrome Mobile
+  # Brave Browser, should go before Safari and Chrome Mobile
   - regex: '((?:B|b)rave(?:\sChrome)?)/(\d+)(?:\.(\d+)|)(?:\.(\d+)|)(?:\.(\d+)|)'
     family_replacement: 'Brave'
 
+  # Brave iOS Browser, checks for (Brave) or Brave at end
+  - regex: '(?:\()?Brave(?:\))?\s*$'
+    family_replacement: 'Brave'
+
   # Amazon Silk, should go before Safari and Chrome Mobile
   - regex: '(Silk)/(\d+)\.(\d+)(?:\.([0-9\-]+)|)'
     family_replacement: 'Amazon Silk'
@@ -443,12 +471,6 @@ user_agent_parsers:
   - regex: '(coc_coc_browser)/(\d+)\.(\d+)(?:\.(\d+)|)'
     family_replacement: 'Coc Coc'
 
-  # Baidu Browsers (desktop spoofs chrome & IE, explorer is mobile)
-  - regex: '(baidubrowser)[/\s](\d+)(?:\.(\d+)|)(?:\.(\d+)|)'
-    family_replacement: 'Baidu Browser'
-  - regex: '(FlyFlow)/(\d+)\.(\d+)'
-    family_replacement: 'Baidu Explorer'
-
   # MxBrowser is Maxthon. Must go before Mobile Chrome for Android
   - regex: '(MxBrowser)/(\d+)\.(\d+)(?:\.(\d+)|)'
     family_replacement: 'Maxthon'
@@ -477,6 +499,12 @@ user_agent_parsers:
   - regex: 'Mozilla.{1,200}Android.{1,200}(GSA)/(\d+)\.(\d+)\.(\d+)'
     family_replacement: 'Google'
 
+  # Baidu Browsers (desktop spoofs chrome & IE, explorer is mobile)
+  - regex: '(baidubrowser)[/\s](\d+)(?:\.(\d+)|)(?:\.(\d+)|)'
+    family_replacement: 'Baidu Browser'
+  - regex: '(FlyFlow|flyflow|baiduboxapp)/(\d+)\.(\d+)(?:\.(\d+)|)(?:\.(\d+)|)'
+    family_replacement: 'Baidu Explorer'
+
   # QQ Browsers
   - regex: '(MQQBrowser/Mini)(?:(\d+)(?:\.(\d+)|)(?:\.(\d+)|)|)'
     family_replacement: 'QQ Browser Mini'
@@ -506,10 +534,34 @@ user_agent_parsers:
     family_replacement: 'Ecosia Android'
 
   # VivoBrowser
-  - regex: '(VivoBrowser)\/(\d+)\.(\d+)\.(\d+)\.(\d+)'
+  - regex: '(VivoBrowser)\/(\d+)\.(\d+)\.(\d+)(?:\.(\d+)|)'
 
   # HiBrowser
-  - regex: '(HiBrowser)\/v(\d+)\.(\d+)\.(\d+)\.(\d+)'
+  - regex: '(H[Ii]Browser)\/v(\d+)\.(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'HiBrowser'
+
+  # Honor Browser
+  - regex: '(HonorBrowser)/(\d+)\.(\d+)\.(\d+)(?:\.(\d+)|)'
+    family_replacement: 'Honor Browser'
+
+  # Honor Browser
+  - regex: '(bdhonorbrowser)/(\d+)\.(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'Honor Browser'
+
+  # HeyTap Browser
+  - regex: '(HeyTapBrowser)/(\d+)\.(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'HeyTap Browser'
+
+  # Weibo
+  # Must before Chrome Mobile WebView
+  - regex: '(weibo)__(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'Weibo'
+  - regex: '(WeiboliteiOS|WeiboIntliOS)'
+    family_replacement: 'Weibo'
+
+  # Phoenix Browser
+  - regex: '(PHX)/(\d+)\.(\d+)'
+    family_replacement: 'Phoenix Browser'
 
   # Chrome Mobile
   - regex: 'Version/.{1,300}(Chrome)/(\d+)\.(\d+)\.(\d+)\.(\d+)'
@@ -592,7 +644,7 @@ user_agent_parsers:
   - regex: '(115Browser)/(\d+)\.(\d+)\.(\d+)\.(\d+)'
     family_replacement: '115 Browser'
 
- # Avira
+  # Avira
   - regex: '(Avira)/(\d+)\.(\d+)\.(\d+)\.(\d+)'
     family_replacement: 'Avira'
 
@@ -612,9 +664,9 @@ user_agent_parsers:
     family_replacement: 'Quark PC'
 
   # Smart Lenovo Browser
-  - regex: '(SLBrowser)/(\d+)\.(\d+)\.(\d+)\.(\d+) SLBChan/(\d+)'
+  - regex: '(SLBrowser)/(\d+)\.(\d+)\.(\d+)'
     family_replacement: 'Smart Lenovo Browser'
-  
+
   # Atom Browser
   - regex: '(Atom)/(\d+)\.(\d+)\.(\d+)\.(\d+)'
     family_replacement: 'Atom Browser'
@@ -667,6 +719,50 @@ user_agent_parsers:
   - regex: '(JiSu)/(\d+)\.(\d+)\.(\d+)'
     family_replacement: 'JiSu Browser'
 
+  # Wolvic Browser
+  - regex: '(Wolvic)/(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'Wolvic Browser'
+
+  # SmartTV WebBrowser
+  - regex: '(Thano)/(\d+)\.(\d+)'
+    family_replacement: 'SmartTV WebBrowser'
+
+  # WeChat Browser
+  - regex: '(MicroMessenger)/(\d+)\.(\d+)(?:\.(\d+)|)'
+    family_replacement: 'WeChat Browser'
+
+  # Odin Browser
+  - regex: '(Odin)/(\d+)\.(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'Odin'
+  
+  # NetCast Smart TV
+  - regex: '(Colt)/(\d+)\.(\d+)'
+    family_replacement: 'NetCast Smart TV'
+  # Lite Browser
+  - regex: '(Lite Browser)/(\d+)\.(\d+)'
+    family_replacement: 'Lite Browser'
+
+  # Vewd Browser
+  - regex: '(OMI)/(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'Vewd Browser'
+
+  # Mypal
+  - regex: '(Mypal)/(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'Mypal Browser'
+
+  # Chess.com native app
+  - regex: '(Chesscom-Android)/(\d+)\.(\d+)\.(\d+)'
+
+  # Roblox native app
+  - regex: '(RobloxApp)/(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'Roblox App'
+
+  # Roadrunner iOS app (not the legacy Time Warner Cable ISP identifier)
+  - regex: '(Roadrunner)/IOS/\d+/(\d+)\.(\d+)\.(\d+)'
+
+  # Ancestry.com Android app
+  - regex: '(AncestryAndroid)/(\d+)\.(\d+)(?:\.(\d+)|)'
+
   #### END SPECIAL CASES TOP ####
 
   #### MAIN CASES - this catches > 50% of all browsers ####
@@ -764,6 +860,96 @@ user_agent_parsers:
   # Browser/major_version.minor_version
   - regex: '(bingbot|Bolt|AdobeAIR|Jasmine|IceCat|Skyfire|Midori|Maxthon|Lynx|Arora|IBrowse|Dillo|Camino|Shiira|Fennec|Phoenix|Flock|Netscape|Lunascape|Epiphany|WebPilot|Opera Mini|Opera|NetFront|Netfront|Konqueror|Googlebot|SeaMonkey|Kazehakase|Vienna|Iceape|Iceweasel|IceWeasel|Iron|K-Meleon|Sleipnir|Galeon|GranParadiso|iCab|iTunes|MacAppStore|NetNewsWire|Space Bison|Stainless|Orca|Dolfin|BOLT|Minimo|Tizen Browser|Polaris|Abrowser|Planetweb|ICE Browser|mDolphin|qutebrowser|Otter|QupZilla|MailBar|kmail2|YahooMobileMail|ExchangeWebServices|ExchangeServicesClient|Dragon|Outlook-iOS-Android)/(\d+)\.(\d+)(?:\.(\d+)|)'
 
+  # Qt Web Engine embedded browser, must be before Chrome
+  - regex: '(QtWebEngine)/(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'Qt Web Engine'
+
+  # OpenWave browser (Chromium-based), must be before Chrome
+  - regex: '(OpenWave)/(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'Open Wave'
+
+  # AtContent - confirmed APT29/Nobelium (Cozy Bear) C2 malware marker. The implant
+  # (AcroSup.dll, side-loaded via Adobe WCChromeNativeMessagingHost.exe) uses a hardcoded
+  # UA of the form 'Chrome/100.0.4896.75 Safari/537.36 AtContent/91.5.2444.45' to
+  # communicate with Dropbox C2. Also observed appended after Edg/ tokens.
+  # Source: Cluster25/DuskRise 'Cozy Smuggled Into the Box', May 2022
+  # (https://www.duskrise.com/2022/05/13/cozy-smuggled-into-the-box-apt29-abusing-legitimate-software-for-targeted-operations-in-europe/)
+
+  - regex: '(AtContent)/(\d+)\.(\d+)\.(\d+)'
+  # Trailer - suspicious fake UA token appended to Chrome/Edge/Opera UA strings
+  # (TOKEN/MAJOR.MINOR.BUILD.PATCH). No known legitimate browser uses this token.
+  # Structurally identical to AtContent (confirmed APT29/Nobelium C2 marker; see
+  # Cluster25/DuskRise 'Cozy Smuggled Into the Box', May 2022). Unconfirmed attribution;
+  # may be same actor rotating token names or a copycat using the same spoofing technique.
+  - regex: '(Trailer)/(\d+)\.(\d+)\.(\d+)'
+
+  # Agency - suspicious fake UA token appended to Chrome UA strings
+  # (TOKEN/MAJOR.MINOR.BUILD.PATCH). No known legitimate browser uses this token.
+  # Structurally identical to AtContent (confirmed APT29/Nobelium C2 marker; see
+  # Cluster25/DuskRise 'Cozy Smuggled Into the Box', May 2022). Unconfirmed attribution;
+  # may be same actor rotating token names or a copycat using the same spoofing technique.
+  - regex: '(Agency)/(\d+)\.(\d+)\.(\d+)'
+
+  # Herring - suspicious fake UA token appended to Chrome UA strings
+  # (TOKEN/MAJOR.MINOR.BUILD.PATCH). No known legitimate browser uses this token.
+  # Structurally identical to AtContent (confirmed APT29/Nobelium C2 marker; see
+  # Cluster25/DuskRise 'Cozy Smuggled Into the Box', May 2022). Unconfirmed attribution;
+  # may be same actor rotating token names or a copycat using the same spoofing technique.
+  - regex: '(Herring)/(\d+)\.(\d+)\.(\d+)'
+
+  # Config - suspicious fake UA token appended to Chrome UA strings
+  # (TOKEN/MAJOR.MINOR.BUILD.PATCH). No known legitimate browser uses this token.
+  # Structurally identical to AtContent (confirmed APT29/Nobelium C2 marker; see
+  # Cluster25/DuskRise 'Cozy Smuggled Into the Box', May 2022). Unconfirmed attribution;
+  # may be same actor rotating token names or a copycat using the same spoofing technique.
+  - regex: '(Config)/(\d+)\.(\d+)\.(\d+)'
+
+  # Viewer - suspicious fake UA token appended to Chrome UA strings
+  # (TOKEN/MAJOR.MINOR.BUILD.PATCH). No known legitimate browser uses this token.
+  # Structurally identical to AtContent (confirmed APT29/Nobelium C2 marker; see
+  # Cluster25/DuskRise 'Cozy Smuggled Into the Box', May 2022). Unconfirmed attribution;
+  # may be same actor rotating token names or a copycat using the same spoofing technique.
+  - regex: '(Viewer)/(\d+)\.(\d+)\.(\d+)'
+
+  # LikeWise - suspicious fake UA token appended to Chrome UA strings
+  # (TOKEN/MAJOR.MINOR.BUILD.PATCH). No known legitimate browser uses this token.
+  # Structurally identical to AtContent (confirmed APT29/Nobelium C2 marker; see
+  # Cluster25/DuskRise 'Cozy Smuggled Into the Box', May 2022). Unconfirmed attribution;
+  # may be same actor rotating token names or a copycat using the same spoofing technique.
+  - regex: '(LikeWise)/(\d+)\.(\d+)\.(\d+)'
+
+  # Unique - suspicious fake UA token appended to Chrome/Opera UA strings
+  # (TOKEN/MAJOR.MINOR.BUILD.PATCH). No known legitimate browser uses this token.
+  # Structurally identical to AtContent (confirmed APT29/Nobelium C2 marker; see
+  # Cluster25/DuskRise 'Cozy Smuggled Into the Box', May 2022). Unconfirmed attribution;
+  # may be same actor rotating token names or a copycat using the same spoofing technique.
+  - regex: '(Unique)/(\d+)\.(\d+)\.(\d+)'
+
+  # CitizenFX - embedded Chromium browser in FiveM/RedM (GTA V / RDR2 game mod frameworks)
+  - regex: '(CitizenFX)/(\d+)\.(\d+)\.(\d+)'
+
+  # R2Client - R2Games game launcher embedded browser (CEF-based)
+  - regex: '(R2Client)/(\d+)\.(\d+)(?:\.(\d+)|)'
+
+  # OBS Studio embedded browser (CEF-based, used for browser sources/docks)
+  - regex: '(OBS)/(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'OBS Studio'
+
+  # Adobe CEP - embedded Chromium runtime for extension panels in Adobe CC apps
+  - regex: '(AdobeCEP)/(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'Adobe CEP'
+
+  # Steam embedded browsers; version from Chrome. Must be before Chrome.
+  # GameOverlay = in-game overlay browser (Shift+Tab)
+  - regex: 'Valve Steam (GameOverlay).{1,200}Chrome/(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'Steam GameOverlay'
+  # Steam Deck built-in browser
+  - regex: 'Valve Steam (Gamepad)/Steam Deck.{1,200}Chrome/(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'Steam Deck'
+  # Steam desktop client browser
+  - regex: '(Valve(?: Steam|) Client).{1,200}Chrome/(\d+)\.(\d+)\.(\d+)'
+    family_replacement: 'Steam Client'
+
   # Chrome/Chromium/major_version.minor_version
   - regex: '(Chromium|Chrome)/(\d+)\.(\d+)(?:\.(\d+)|)(?:\.(\d+)|)'
 
@@ -1485,7 +1671,7 @@ os_parsers:
   # Box Drive and Box Sync on Mac OS X use OSX version numbers, not Darwin
   - regex: '^Box.{0,200};(Darwin)/(10)\.(1\d)(?:\.(\d+)|)'
     os_replacement: 'Mac OS X'
-  
+
   ##########
   # Hashicorp API
   # APN/1.0 HashiCorp/1.0 Terraform/1.8.0 (+https://www.terraform.io) terraform-provider-aws/4.67.0 (+https://registry.terraform.io/providers/hashicorp/aws) aws-sdk-go/1.44.261 (go1.19.8; darwin; arm64)
@@ -2013,7 +2199,7 @@ device_parsers:
   # Mobile Spiders
   # Catch the mobile crawler before checking for iPhones / Androids.
   #########
-  - regex: '^.{0,100}?(?:(?:iPhone|Windows CE|Windows Phone|Android).{0,300}(?:(?:Bot|Yeti)-Mobile|YRSpider|BingPreview|bots?/\d|(?:bot|spider)\.html)|AdsBot-Google-Mobile.{0,200}iPhone)'
+  - regex: '^.{0,100}?(?:(?:iPhone|Windows CE|Windows Phone|Android).{0,300}(?:(?:Bot|Yeti)-Mobile|YRSpider|BingPreview|bots?/\d|(?:bot|spider)\.html|Google-InspectionTool)|AdsBot-Google-Mobile.{0,200}iPhone)'
     regex_flag: 'i'
     device_replacement: 'Spider'
     brand_replacement: 'Spider'
@@ -3215,7 +3401,7 @@ device_parsers:
     device_replacement: 'HTC $1'
     brand_replacement: 'HTC'
     model_replacement: '$1'
-  - regex: '; {0,2}(ADR6200|ADR6400L|ADR6425LVW|Amaze|DesireS?|EndeavorU|Eris|EVO|Evo\d[A-Z]+|HD2|IncredibleS?|Inspire[A-Z0-9]*|Inspire[A-Z0-9]*|Sensation[A-Z0-9]*|Wildfire)[ _-](.{1,200}?)(?:[/;\)]|Build|MIUI|1\.0)'
+  - regex: '; {0,2}(ADR6200|ADR6400L|ADR6425LVW|Amaze|DesireS?|EndeavorU|Eris|EVO|Evo\d[A-Z]+|HD2|IncredibleS?|Inspire[A-Z0-9]*|Sensation[A-Z0-9]*|Wildfire)[ _-](.{1,200}?)(?:[/;\)]|Build|MIUI|1\.0)'
     regex_flag: 'i'
     device_replacement: 'HTC $1 $2'
     brand_replacement: 'HTC'
@@ -5619,7 +5805,6 @@ device_parsers:
     brand_replacement: 'Asus'
     model_replacement: '$1'
 
-
   ##########
   # Bird
   ##########
@@ -5819,7 +6004,6 @@ device_parsers:
     brand_replacement: 'Motorola'
     model_replacement: '$2'
 
-
   ##########
   # nintendo
   ##########
@@ -6023,7 +6207,7 @@ device_parsers:
   ##########
   # Spiders (this is a hack...)
   ##########
-  - regex: '^.{0,100}(bot|BUbiNG|zao|borg|DBot|oegp|silk|Xenu|zeal|^NING|CCBot|crawl|htdig|lycos|slurp|teoma|voila|yahoo|Sogou|CiBra|Nutch|^Java/|^JNLP/|Daumoa|Daum|Genieo|ichiro|larbin|pompos|Scrapy|snappy|speedy|spider|msnbot|msrbot|vortex|^vortex|crawler|favicon|indexer|Riddler|scooter|scraper|scrubby|WhatWeb|WinHTTP|bingbot|BingPreview|openbot|gigabot|furlbot|polybot|seekbot|^voyager|archiver|Icarus6j|mogimogi|Netvibes|blitzbot|altavista|charlotte|findlinks|Retreiver|TLSProber|WordPress|SeznamBot|ProoXiBot|wsr\-agent|Squrl Java|EtaoSpider|PaperLiBot|SputnikBot|A6\-Indexer|netresearch|searchsight|baiduspider|YisouSpider|ICC\-Crawler|http%20client|Python-urllib|dataparksearch|converacrawler|Screaming Frog|AppEngine-Google|YahooCacheSystem|fast\-webcrawler|Sogou Pic Spider|semanticdiscovery|Innovazion Crawler|facebookexternalhit|Google.{0,200}/\+/web/snippet|Google-HTTP-Java-Client|BlogBridge|IlTrovatore-Setaccio|InternetArchive|GomezAgent|WebThumbnail|heritrix|NewsGator|PagePeeker|Reaper|ZooShot|holmes|NL-Crawler|Pingdom|StatusCake|WhatsApp|masscan|Google Web Preview|Qwantify|Yeti|OgScrper|RecipeRadar|GPTBot)'
+  - regex: '^.{0,100}(bot|BUbiNG|zao|borg|DBot|oegp|silk|Xenu|zeal|^NING|CCBot|crawl|htdig|lycos|slurp|teoma|voila|yahoo|Sogou|CiBra|Nutch|^Java/|^JNLP/|Daumoa|Daum|Genieo|ichiro|larbin|pompos|Scrapy|snappy|speedy|spider|msnbot|msrbot|vortex|^vortex|crawler|favicon|indexer|Riddler|scooter|scraper|scrubby|WhatWeb|WinHTTP|bingbot|BingPreview|openbot|gigabot|furlbot|polybot|seekbot|^voyager|archiver|Icarus6j|mogimogi|Netvibes|blitzbot|altavista|charlotte|findlinks|Retreiver|TLSProber|WordPress|SeznamBot|ProoXiBot|wsr\-agent|Squrl Java|EtaoSpider|PaperLiBot|SputnikBot|A6\-Indexer|netresearch|searchsight|baiduspider|YisouSpider|ICC\-Crawler|http%20client|Python-urllib|dataparksearch|converacrawler|Screaming Frog|AppEngine-Google|YahooCacheSystem|fast\-webcrawler|Sogou Pic Spider|semanticdiscovery|Innovazion Crawler|facebookexternalhit|Google.{0,200}/\+/web/snippet|Google-HTTP-Java-Client|BlogBridge|IlTrovatore-Setaccio|InternetArchive|GomezAgent|WebThumbnail|heritrix|NewsGator|PagePeeker|Reaper|ZooShot|holmes|NL-Crawler|Pingdom|StatusCake|WhatsApp|masscan|Google Web Preview|Qwantify|Yeti|OgScrper|RecipeRadar|GPTBot|Google-InspectionTool)'
     regex_flag: 'i'
     device_replacement: 'Spider'
     brand_replacement: 'Spider'

db/migrations/20250318072657_replace_slug_index_with_covering_index.sql

@@ -0,0 +1,9 @@
+-- +micrate Up
+-- SQL in section 'Up' is executed when this migration is applied
+DROP INDEX IF EXISTS idx_links_slug;      -- Remove old composite index
+CREATE INDEX IF NOT EXISTS idx_links_slug_optimized ON links (slug, url);
+
+-- +micrate Down
+-- SQL in section 'Down' is executed when this migration is rolled back
+DROP INDEX IF EXISTS idx_links_slug_optimized;
+CREATE INDEX IF NOT EXISTS idx_links_slug ON links (id, slug, url);

db/migrations/20250319192003_convert_all_tables_text_ids_to_integer.sql

@@ -0,0 +1,102 @@
+-- +micrate Up
+-- SQL in section 'Up' is executed when this migration is applied
+-- 1. Create new users table with INTEGER PK
+CREATE TABLE users_new (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    name VARCHAR(100) NOT NULL,
+    api_key VARCHAR(64) UNIQUE NOT NULL,
+    created_at INTEGER DEFAULT CURRENT_TIMESTAMP NOT NULL,
+    updated_at INTEGER DEFAULT CURRENT_TIMESTAMP NOT NULL
+);
+
+-- Create a mapping table to track old and new user IDs
+CREATE TEMPORARY TABLE user_id_map (
+    old_id TEXT,
+    new_id INTEGER
+);
+
+-- Insert users data and capture the mappings
+INSERT INTO users_new (name, api_key, created_at, updated_at)
+SELECT name, api_key, created_at, updated_at FROM users;
+
+INSERT INTO user_id_map
+SELECT u.id, u_new.id
+FROM users u
+JOIN users_new u_new ON u_new.api_key = u.api_key;
+
+-- 2. Create new links table with INTEGER PK
+CREATE TABLE links_new (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    user_id INTEGER NOT NULL,
+    slug VARCHAR(8) UNIQUE NOT NULL,
+    url TEXT NOT NULL,
+    created_at INTEGER DEFAULT CURRENT_TIMESTAMP NOT NULL,
+    updated_at INTEGER DEFAULT CURRENT_TIMESTAMP NOT NULL,
+    FOREIGN KEY (user_id) REFERENCES users_new(id) ON DELETE CASCADE
+);
+
+-- Create a mapping table for links
+CREATE TEMPORARY TABLE link_id_map (
+    old_id TEXT,
+    new_id INTEGER
+);
+
+-- Insert links data with new user_id foreign keys
+INSERT INTO links_new (user_id, slug, url, created_at, updated_at)
+SELECT 
+    (SELECT new_id FROM user_id_map WHERE old_id = l.user_id),
+    l.slug,
+    l.url,
+    l.created_at,
+    l.updated_at
+FROM links l;
+
+-- Create the mapping for links
+INSERT INTO link_id_map
+SELECT l.id, l_new.id
+FROM links l
+JOIN links_new l_new ON l_new.slug = l.slug AND l_new.url = l.url;
+
+-- 3. Create new clicks table with INTEGER PK
+CREATE TABLE clicks_new (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    link_id INTEGER NOT NULL,
+    user_agent TEXT,
+    browser TEXT,
+    os TEXT,
+    referer TEXT,
+    country TEXT,
+    created_at INTEGER DEFAULT CURRENT_TIMESTAMP NOT NULL,
+    updated_at INTEGER DEFAULT CURRENT_TIMESTAMP NOT NULL,
+    FOREIGN KEY (link_id) REFERENCES links_new(id) ON DELETE CASCADE
+);
+
+-- Insert clicks data with new link_id foreign keys
+INSERT INTO clicks_new (link_id, user_agent, browser, os, referer, country, created_at, updated_at)
+SELECT 
+    (SELECT new_id FROM link_id_map WHERE old_id = c.link_id),
+    c.user_agent,
+    c.browser,
+    c.os,
+    c.referer,
+    c.country,
+    c.created_at,
+    c.updated_at
+FROM clicks c;
+
+-- 4. Drop old tables and rename new tables
+DROP TABLE clicks;
+DROP TABLE links;
+DROP TABLE users;
+
+ALTER TABLE clicks_new RENAME TO clicks;
+ALTER TABLE links_new RENAME TO links;
+ALTER TABLE users_new RENAME TO users;
+
+-- 5. Drop unused indexes
+DROP INDEX IF EXISTS index_users_api_key;
+DROP INDEX IF EXISTS idx_links_slug;
+DROP INDEX IF EXISTS idx_links_slug_optimized;
+
+-- +micrate Down
+-- SQL section 'Down' is executed when this migration is rolled back

db/seed.sql

@@ -0,0 +1,69 @@
+INSERT INTO users (name, api_key)
+VALUES
+('User 1', 'secure_api_key_1'),
+('User 2', 'secure_api_key_2');
+
+-- Create 10,000 links (5,000 per user)
+WITH RECURSIVE link_numbers(n) AS (
+    SELECT 1
+    UNION ALL
+    SELECT n+1 FROM link_numbers
+    LIMIT 10000
+)
+INSERT INTO links (user_id, slug, url)
+SELECT
+    ((n-1) % 2) + 1, -- User ID (1-2)
+    'slug' || n,      -- Unique slug
+    'https://sjdonado.com/page/' || n
+FROM link_numbers;
+
+-- Create 1,000 clicks per link (10 million total)
+WITH RECURSIVE counts(n) AS (
+    SELECT 1
+    UNION ALL
+    SELECT n+1 FROM counts
+    LIMIT 1000
+)
+INSERT INTO clicks (link_id, user_agent, browser, os, referer, country)
+SELECT
+    l.id,
+    CASE (c.n % 5)
+        WHEN 0 THEN 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)'
+        WHEN 1 THEN 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15)'
+        WHEN 2 THEN 'Mozilla/5.0 (iPhone; CPU iPhone OS 14_0)'
+        WHEN 3 THEN 'Mozilla/5.0 (X11; Linux x86_64)'
+        ELSE 'Mozilla/5.0 (Android 11; Mobile)'
+    END,
+    CASE (c.n % 3)
+        WHEN 0 THEN 'Firefox'
+        WHEN 1 THEN 'Chrome'
+        ELSE 'Safari'
+    END,
+    CASE (c.n % 4)
+        WHEN 0 THEN 'macOS'
+        WHEN 1 THEN 'Windows'
+        WHEN 2 THEN 'iOS'
+        ELSE 'Android'
+    END,
+    CASE (c.n % 6)
+        WHEN 0 THEN 'https://sjdonado.com'
+        WHEN 1 THEN 'https://donado.co'
+        WHEN 2 THEN 'https://idonthavespotify.donado.co'
+        WHEN 3 THEN 'https://spookyplanning.com'
+        WHEN 4 THEN 'https://github.com/sjdonado'
+        ELSE NULL
+    END,
+    CASE (c.n % 10)
+        WHEN 0 THEN 'Colombia'
+        WHEN 1 THEN 'Brazil'
+        WHEN 2 THEN 'Canada'
+        WHEN 3 THEN 'Germany'
+        WHEN 4 THEN 'France'
+        WHEN 5 THEN 'Japan'
+        WHEN 6 THEN 'Australia'
+        WHEN 7 THEN 'Brazil'
+        WHEN 8 THEN 'India'
+        ELSE 'China'
+    END
+FROM links l
+CROSS JOIN counts c;

docs/API.md

@@ -1,143 +0,0 @@
-# API Reference
-
-1. **Ping the API**
-
-   - Endpoint: `GET /api/ping`
-   - Payload: None
-   - Response Example
-     ```json
-     {
-       "data": "pong"
-     }
-     ```
-2. **Redirect by Slug**
-
-   - Endpoint: `GET /:slug`
-   - Payload: None
-   - Response: 301
-
-3. **List All Links**
-
-   - Endpoint: `GET /api/links`
-   - Headers: `X-Api-Key`
-   - Query Parameters:
-     - `limit` (optional): Number of results per page (default: 100)
-     - `cursor` (optional): Pagination cursor from previous response
-   - Response Example
-     ```json
-     {
-       "data": [
-         {
-           "id": "84f0c7a4-8c4e-4665-b676-cb9c5e40f1db",
-           "refer": "http://localhost:4000/3wP4BQ",
-           "origin": "https://monocuco.donado.co"
-         }
-       ],
-       "pagination": {
-         "has_more": true,
-         "next": "75e0a7f4-9c5e-1235-b546-eb9c5e40f7ac"
-       }
-     }
-     ```
-
-4. **List link by ID**
-   - Endpoint: `GET /api/links/:id`
-   - Headers: `X-Api-Key`
-   - Payload: None
-   - Note: This endpoint returns up to 100 of the most recent clicks. For complete click history, use the `/api/links/:id/clicks` endpoint with pagination.
-   - Response Example
-     ```json
-     {
-       "data": {
-         "id": "84f0c7a4-8c4e-4665-b676-cb9c5e40f1db",
-         "refer": "http://localhost:4000/3wP4BQ",
-         "origin": "https://monocuco.donado.co",
-         "clicks": [
-           {
-             "id": "730e2202-58f9-478c-a24c-f1c561df6716",
-             "user_agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:127.0) Gecko/20100101 Firefox/127.0",
-             "country": "DE",
-             "browser": "Firefox",
-             "os": "Mac OS X",
-             "referer": "Direct",
-             "created_at": "2024-07-12T19:25:22Z"
-           }
-         ]
-       }
-     }
-     ```
-
-5. **List Clicks for a Link**
-   - Endpoint: `GET /api/links/:id/clicks`
-   - Headers: `X-Api-Key`
-   - Query Parameters:
-     - `limit` (optional): Number of results per page (default: 100)
-     - `cursor` (optional): Pagination cursor from previous response
-   - Response Example
-     ```json
-     {
-       "data": [
-         {
-           "id": "730e2202-58f9-478c-a24c-f1c561df6716",
-           "user_agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:127.0) Gecko/20100101 Firefox/127.0",
-           "country": "DE",
-           "browser": "Firefox",
-           "os": "Mac OS X",
-           "referer": "Direct",
-           "created_at": "2024-07-12T19:25:22Z"
-         }
-       ],
-       "pagination": {
-         "has_more": true,
-         "next": "629e3301-47f8-389b-b24c-f1c561df9825"
-       }
-     }
-     ```
-
-6. **Create new link**
-   - Endpoint: `POST /api/links`
-   - Payload:
-     ```json
-     {
-       "url": "https://example.com"
-     }
-     ```
-   - Headers: `X-Api-Key`
-   - Response Example:
-     ```json
-     {
-       "data": {
-         "id": "84f0c7a4-8c4e-4665-b676-cb9c5e40f1db",
-         "refer": "http://localhost:4000/3wP4BQ",
-         "origin": "https://example.com",
-         "clicks": []
-       }
-     }
-     ```
-
-7. **Update an existing link by ID**
-   - Endpoint: `PUT /api/links/:id`
-   - Payload:
-     ```json
-     {
-       "url": "https://newexample.com"
-     }
-     ```
-   - Headers: `X-Api-Key`
-   - Response Example:
-     ```json
-     {
-       "data": {
-         "id": "84f0c7a4-8c4e-4665-b676-cb9c5e40f1db",
-         "refer": "http://localhost:4000/3wP4BQ",
-         "origin": "https://newexample.com",
-         "clicks": []
-       }
-     }
-     ```
-
-8. **Delete a link by ID**
-  - Endpoint: `DELETE /api/links/:id`
-  - Payload: None
-  - Headers: `X-Api-Key`
-  - Response: 204

docs/SETUP.md

@@ -3,67 +3,16 @@
 ```
 Usage: ./cli [options]
 Options:
-  --create-user=NAME    Create a new user with the given name
-  --list-users          List all users
-  --delete-user=USER_ID Delete a user by ID
-```
-
-## Run It Anywhere
-
-### Docker Compose
-
-```bash
-docker-compose up
-
-# Optional: Generate an api key
-# docker-compose exec -it app cli --create-user=Admin
-```
-
-### Docker CLI
-
-```bash
-docker run \
-    --name bit \
-    -p 4000:4000 \
-    -e ENV="production" \
-    -e DATABASE_URL="sqlite3://./sqlite/data.db?journal_mode=wal&synchronous=normal&foreign_keys=true" \
-    -e APP_URL="http://localhost:4000" \
-    -e ADMIN_NAME="Admin" \
-    -e ADMIN_API_KEY=$(openssl rand -base64 32) \
-    sjdonado/bit
-
-# Optional: Generate an api key
-# docker exec -it bit cli --create-user=Admin
-```
-
-### Self-Hosted with Dokku
-
-```dockerfile
-FROM sjdonado/bit
-```
-
-```bash
-dokku apps:create bit
-
-dokku domains:set bit bit.donado.co
-dokku letsencrypt:enable bit
-
-dokku storage:ensure-directory bit-sqlite
-dokku storage:mount bit /var/lib/dokku/data/storage/bit-sqlite:/usr/src/app/sqlite/
-
-dokku config:set bit DATABASE_URL="sqlite3://./sqlite/data.db?journal_mode=wal&synchronous=normal&foreign_keys=true" APP_URL=https://bit.donado.co ADMIN_NAME=Admin ADMIN_API_KEY=$(openssl rand -base64 32)
-
-dokku ports:add bit http:80:4000
-dokku ports:add bit https:443:4000
-
-# Optional: Generate an api key
-# dokku run bit cli --create-user=Admin
+  --create-user=NAME     Create a new user with the given name
+  --list-users           List all users
+  --delete-user=USER_ID  Delete a user by ID
+  --update-parsers       Download all required data files
 ```
 
 ## Local Development
 
 ### Requirements
-- Crystal 1.12+
+- Crystal 1.18+
 - Shards package manager
 - SQLite3
 
@@ -99,56 +48,140 @@ ENV=test crystal spec
 
 ## Benchmark
 
-CPU: Apple M3 Pro
+### Run
 
 ```
-> colima start --cpu 1 --memory 1
-INFO[0000] starting colima
-INFO[0000] runtime: docker
-INFO[0001] starting ...                                  context=vm
-INFO[0076] provisioning ...                              context=docker
-INFO[0077] starting ...                                  context=docker
-INFO[0077] done
+shards build --release --no-debug --progress --stats
+shards run benchmark
+```
 
-> ./benchmark.sh
-Setting up...
-[+] Running 2/2
- ✔ Network bit_default  Created                                                                                                                                                                     0.0s
- ✔ Container bit        Started                                                                                                                                                                     0.1s
-Captured API Key: v-8gljT0WjMhQECito3e5g
-Waiting for the application to be ready...
-HTTP/1.1 200 OK
-Connection: keep-alive
-Content-Type: application/json
-Date: Sun, 16 Mar 2025 10:51:22 GMT
-Access-Control-Allow-Origin: *
-Access-Control-Allow-Methods: GET, POST, PUT, DELETE, OPTIONS
-Access-Control-Allow-Headers: Content-Type, Accept, Origin, X-Api-Key
-Content-Length: 13
+### Output
 
-Starting resource usage monitoring...
-Creating 10000 short links with 100 conrurrent requests...
-Link creation complete: 10000 links created.
-Fetching all created links from /api/links...
-Selected link for benchmarking: http://localhost:4000/pKtTjA
-Starting benchmark with Bombardier...
-Bombarding http://localhost:4000/pKtTjA with 10000 request(s) using 100 connection(s)
- 10000 / 10000 [======================================================================================================================================================================] 100.00% 1424/s 7s
+Chip: Apple M4 Pro. Memory: 24GB
+
+```
+1762075350 ~/p/bit> shards build --release --no-debug --progress --stats
+                    shards run benchmark
+Dependencies are satisfied
+Building: bit
+Parse:                             00:00:00.000652375 (   1.17MB)
+Semantic (top level):              00:00:00.419246250 ( 163.45MB)
+Semantic (new):                    00:00:00.001636125 ( 163.45MB)
+Semantic (type declarations):      00:00:00.019569792 ( 179.45MB)
+Semantic (abstract def check):     00:00:00.009145125 ( 195.45MB)
+Semantic (restrictions augmenter): 00:00:00.008421709 ( 195.45MB)
+Semantic (ivars initializers):     00:00:00.019696584 ( 211.45MB)
+Semantic (cvars initializers):     00:00:00.106829666 ( 211.50MB)
+Semantic (main):                   00:00:00.649298375 ( 499.88MB)
+Semantic (cleanup):                00:00:00.000765250 ( 499.88MB)
+Semantic (recursive struct check): 00:00:00.000752250 ( 499.88MB)
+Codegen (crystal):                 00:00:00.521307417 ( 532.38MB)
+Codegen (bc+obj):                  00:00:00.143842542 ( 532.38MB)
+Codegen (linking):                 00:00:00.236228750 ( 532.38MB)
+
+Macro runs:
+ - /opt/homebrew/Cellar/crystal/1.18.2/share/crystal/src/ecr/process.cr: reused previous compilation (00:00:00.003593375)
+
+Codegen (bc+obj):
+ - all previous .o files were reused
+Building: cli
+Parse:                             00:00:00.000053291 (   1.17MB)
+Semantic (top level):              00:00:00.323534167 ( 163.45MB)
+Semantic (new):                    00:00:00.001705500 ( 163.45MB)
+Semantic (type declarations):      00:00:00.018311958 ( 179.45MB)
+Semantic (abstract def check):     00:00:00.007766750 ( 195.45MB)
+Semantic (restrictions augmenter): 00:00:00.005686667 ( 195.45MB)
+Semantic (ivars initializers):     00:00:00.011239792 ( 211.45MB)
+Semantic (cvars initializers):     00:00:00.100870833 ( 211.50MB)
+Semantic (main):                   00:00:00.285426750 ( 371.62MB)
+Semantic (cleanup):                00:00:00.000369875 ( 371.62MB)
+Semantic (recursive struct check): 00:00:00.000570917 ( 371.62MB)
+Codegen (crystal):                 00:00:00.317534875 ( 387.88MB)
+Codegen (bc+obj):                  00:00:00.097321417 ( 387.88MB)
+Codegen (linking):                 00:00:00.095931000 ( 387.88MB)
+
+Codegen (bc+obj):
+ - all previous .o files were reused
+Building: benchmark
+Parse:                             00:00:00.000228500 (   1.17MB)
+Semantic (top level):              00:00:00.242174458 ( 147.78MB)
+Semantic (new):                    00:00:00.000863333 ( 147.78MB)
+Semantic (type declarations):      00:00:00.011527792 ( 147.78MB)
+Semantic (abstract def check):     00:00:00.031242333 ( 147.78MB)
+Semantic (restrictions augmenter): 00:00:00.003593583 ( 147.78MB)
+Semantic (ivars initializers):     00:00:00.006753667 ( 147.78MB)
+Semantic (cvars initializers):     00:00:00.028373834 ( 195.78MB)
+Semantic (main):                   00:00:00.152039542 ( 243.83MB)
+Semantic (cleanup):                00:00:00.000249084 ( 243.83MB)
+Semantic (recursive struct check): 00:00:00.000460417 ( 243.83MB)
+Codegen (crystal):                 00:00:00.075461000 ( 259.83MB)
+Codegen (bc+obj):                  00:00:04.834914333 ( 259.83MB)
+Codegen (linking):                 00:00:00.119920416 ( 259.83MB)
+
+Codegen (bc+obj):
+ - no previous .o files were reused
+Dependencies are satisfied
+Building: benchmark
+Executing: benchmark
+Cleaning up benchmark database...
+Deleted existing database: ./sqlite/data.benchmark.db
+Database cleanup completed.
+Running database migrations...
+Migrating db, current version: 0, target: 20250319192003
+OK   20240512214223_create_links.sql
+OK   20240512225208_add_slug_index_to_links.sql
+OK   20240513115731_create_users.sql
+OK   20240513130054_add_api_key_index_to_users.sql
+OK   20240711224103_create_clicks.sql
+OK   20240714215409_update_slug_size_links.sql
+OK   20250316102350_add_country_to_clicks.sql
+OK   20250316111734_replace_unkwown_with_null.sql
+OK   20250318072657_replace_slug_index_with_covering_index.sql
+OK   20250319192003_convert_all_tables_text_ids_to_integer.sql
+Migrations completed successfully.
+Seeding benchmark database...
+Database seeded successfully.
+Starting application: ./bit...
+Application output will be saved to: app_output.log
+Application started with PID: 11638
+Using database: ./sqlite/data.benchmark.db
+Checking if server is ready at http://localhost:4001...
+.Server is ready!
+Fetching links from API...
+Selected link: http://localhost:4001/slug9391
+
+Starting benchmark with 100000 requests...
+Bombarding http://localhost:4001/slug9391 with 100000 request(s) using 125 connection(s)
+ 100000 / 100000 [============================================================================] 100.00% 11078/s 9s
 Done!
 Statistics        Avg      Stdev        Max
-  Reqs/sec      1885.24    7686.34  140641.16
-  Latency       68.00ms     6.43ms    89.56ms
+  Reqs/sec     11427.28    8889.68   30270.91
+  Latency       11.02ms     6.55ms    53.91ms
+  Latency Distribution
+     50%     1.85ms
+     75%     5.37ms
+     90%    39.36ms
+     95%    39.87ms
+     99%    42.66ms
   HTTP codes:
-    1xx - 0, 2xx - 0, 3xx - 10000, 4xx - 0, 5xx - 0
+    1xx - 0, 2xx - 0, 3xx - 100000, 4xx - 0, 5xx - 0
     others - 0
-  Throughput:   625.54KB/s
-Benchmark completed.
-Analyzing resource usage...
-**** Results ****
-Average CPU Usage: 42.98%
-Average Memory Usage: 33.25 MiB
-./benchmark.sh: line 135:  1500 Terminated: 15          monitor_resource_usage
-[+] Running 2/2
- ✔ Container bit        Removed                                                                                                                                                                    10.1s
- ✔ Network bit_default  Removed                                                                                                                                                                     0.0s
+  Throughput:     3.08MB/s
+
+Benchmark completed successfully.
+
+**** Resource Usage Statistics ****
+  Measurements: 12
+  Average CPU Usage: 71.5%
+  Average Memory Usage: 39.8 MiB
+  Peak CPU Usage: 100.0%
+  Peak Memory Usage: 53.41 MiB
+
+**** Files Generated ****
+  Resource stats: resource_usage.log
+  Application log: app_output.log
+  Database: ./sqlite/data.benchmark.db
+
+Stopping application...
+Application stopped.
 ```

docs/openapi.yaml

@@ -0,0 +1,503 @@
+openapi: 3.0.3
+info:
+  title: Bit - URL Shortener API
+  description: |
+    Fast, lightweight, self-hosted URL shortener service with minimal click tracking.
+
+    ## Getting Started
+
+    For setup instructions, please check the [README](https://github.com/sjdonado/bit/blob/master/README.md).
+
+    ## Authentication
+    
+    Multiple users are supported via `X-Api-Key` headers. Create, list and delete keys via the [CLI](https://github.com/sjdonado/bit/blob/master/SETUP.md#cli).
+  version: 1.6.0
+  contact:
+    name: sjdonado
+    url: https://sjdonado.com
+
+servers:
+  - url: http://localhost:4000
+    description: Development server
+
+security:
+  - ApiKeyAuth: []
+
+paths:
+  /api/ping:
+    get:
+      summary: Ping the API
+      description: Health check endpoint to verify the API is running
+      operationId: ping
+      tags:
+        - Health
+      security: []
+      responses:
+        '200':
+          description: API is healthy
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    type: string
+                    example: pong
+
+  /{slug}:
+    get:
+      summary: Redirect by slug
+      description: Redirects to the original URL and tracks the click asynchronously
+      operationId: redirectBySlug
+      tags:
+        - Redirects
+      security: []
+      parameters:
+        - name: slug
+          in: path
+          required: true
+          description: The short URL slug
+          schema:
+            type: string
+            example: 3wP4BQ
+        - name: utm_source
+          in: query
+          required: false
+          description: UTM source parameter for tracking
+          schema:
+            type: string
+            example: email_campaign
+      responses:
+        '301':
+          description: Redirect to original URL
+          headers:
+            Location:
+              description: The original URL
+              schema:
+                type: string
+                example: https://example.com
+            X-Forwarded-For:
+              description: Client IP address
+              schema:
+                type: string
+            User-Agent:
+              description: User agent string
+              schema:
+                type: string
+        '404':
+          description: Link not found
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+
+  /api/links:
+    get:
+      summary: List all links
+      description: Retrieve all links for the authenticated user with pagination support
+      operationId: listLinks
+      tags:
+        - Links
+      parameters:
+        - name: limit
+          in: query
+          description: Number of results per page
+          schema:
+            type: integer
+            default: 100
+            minimum: 1
+            maximum: 1000
+        - name: cursor
+          in: query
+          description: Pagination cursor from previous response
+          schema:
+            type: string
+      responses:
+        '200':
+          description: List of links
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    type: array
+                    items:
+                      $ref: '#/components/schemas/LinkSummary'
+                  pagination:
+                    $ref: '#/components/schemas/Pagination'
+        '401':
+          description: Unauthorized
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+
+    post:
+      summary: Create new link
+      description: Create a new shortened link
+      operationId: createLink
+      tags:
+        - Links
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              type: object
+              required:
+                - url
+              properties:
+                url:
+                  type: string
+                  format: uri
+                  description: The URL to shorten
+                  example: https://example.com
+      responses:
+        '201':
+          description: Link created successfully
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    $ref: '#/components/schemas/Link'
+        '400':
+          description: Bad request - invalid URL or missing field
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+              examples:
+                missingField:
+                  value:
+                    error: "url: Required field"
+                invalidUrl:
+                  value:
+                    errors:
+                      url:
+                        - is invalid
+        '401':
+          description: Unauthorized
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+
+  /api/links/{id}:
+    get:
+      summary: Get link by ID
+      description: Retrieve a specific link with up to 100 most recent clicks. For complete click history, use /api/links/{id}/clicks
+      operationId: getLink
+      tags:
+        - Links
+      parameters:
+        - name: id
+          in: path
+          required: true
+          description: Link ID
+          schema:
+            type: integer
+            format: int64
+      responses:
+        '200':
+          description: Link details
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    $ref: '#/components/schemas/Link'
+        '404':
+          description: Link not found
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+        '401':
+          description: Unauthorized
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+
+    put:
+      summary: Update link
+      description: Update the URL of an existing link
+      operationId: updateLink
+      tags:
+        - Links
+      parameters:
+        - name: id
+          in: path
+          required: true
+          description: Link ID
+          schema:
+            type: integer
+            format: int64
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              type: object
+              required:
+                - url
+              properties:
+                url:
+                  type: string
+                  format: uri
+                  description: The new URL
+                  example: https://newexample.com
+      responses:
+        '200':
+          description: Link updated successfully
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    $ref: '#/components/schemas/Link'
+        '400':
+          description: Bad request
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+        '401':
+          description: Unauthorized
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+        '403':
+          description: Forbidden - link belongs to another user
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+        '404':
+          description: Link not found
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+
+    delete:
+      summary: Delete link
+      description: Delete a link and all its associated clicks
+      operationId: deleteLink
+      tags:
+        - Links
+      parameters:
+        - name: id
+          in: path
+          required: true
+          description: Link ID
+          schema:
+            type: integer
+            format: int64
+      responses:
+        '204':
+          description: Link deleted successfully
+        '401':
+          description: Unauthorized
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+        '403':
+          description: Forbidden - link belongs to another user
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+        '404':
+          description: Link not found
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+
+  /api/links/{id}/clicks:
+    get:
+      summary: List clicks for a link
+      description: Retrieve all clicks for a specific link with pagination support
+      operationId: listClicks
+      tags:
+        - Clicks
+      parameters:
+        - name: id
+          in: path
+          required: true
+          description: Link ID
+          schema:
+            type: integer
+            format: int64
+        - name: limit
+          in: query
+          description: Number of results per page
+          schema:
+            type: integer
+            default: 100
+            minimum: 1
+            maximum: 1000
+        - name: cursor
+          in: query
+          description: Pagination cursor from previous response
+          schema:
+            type: string
+      responses:
+        '200':
+          description: List of clicks
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    type: array
+                    items:
+                      $ref: '#/components/schemas/Click'
+                  pagination:
+                    $ref: '#/components/schemas/Pagination'
+        '401':
+          description: Unauthorized
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+        '404':
+          description: Link not found
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/Error'
+
+components:
+  securitySchemes:
+    ApiKeyAuth:
+      type: apiKey
+      in: header
+      name: X-Api-Key
+      description: API key for authentication
+
+  schemas:
+    LinkSummary:
+      type: object
+      properties:
+        id:
+          type: integer
+          format: int64
+          description: Unique link identifier
+          example: 1
+        refer:
+          type: string
+          format: uri
+          description: The shortened URL
+          example: http://localhost:4000/3wP4BQ
+        origin:
+          type: string
+          format: uri
+          description: The original URL
+          example: https://monocuco.donado.co
+
+    Link:
+      allOf:
+        - $ref: '#/components/schemas/LinkSummary'
+        - type: object
+          properties:
+            clicks:
+              type: array
+              description: Array of click records (up to 100 most recent)
+              items:
+                $ref: '#/components/schemas/Click'
+
+    Click:
+      type: object
+      properties:
+        id:
+          type: integer
+          format: int64
+          description: Unique click identifier
+          example: 1
+        user_agent:
+          type: string
+          description: User agent string
+          example: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:127.0) Gecko/20100101 Firefox/127.0
+        country:
+          type: string
+          description: Country code (ISO 3166-1 alpha-2)
+          example: US
+          nullable: true
+        browser:
+          type: string
+          description: Browser name
+          example: Firefox
+          nullable: true
+        os:
+          type: string
+          description: Operating system
+          example: Mac OS X
+          nullable: true
+        referer:
+          type: string
+          description: Referer domain or utm_source
+          example: Direct
+          nullable: true
+        created_at:
+          type: string
+          format: date-time
+          description: Click timestamp
+          example: 2024-07-12T19:25:22Z
+
+    Pagination:
+      type: object
+      properties:
+        has_more:
+          type: boolean
+          description: Whether there are more results
+          example: true
+        next:
+          type: integer
+          format: int64
+          description: Cursor for next page (link/click ID)
+          example: 12
+          nullable: true
+
+    Error:
+      type: object
+      properties:
+        error:
+          type: string
+          description: Error message
+          example: Resource not found
+      required:
+        - error
+
+    ValidationErrors:
+      type: object
+      properties:
+        errors:
+          type: object
+          additionalProperties:
+            type: array
+            items:
+              type: string
+          description: Field-level validation errors
+          example:
+            url:
+              - is invalid
+
+tags:
+  - name: Health
+    description: Health check endpoints
+  - name: Redirects
+    description: URL redirection and click tracking
+  - name: Links
+    description: Link management operations
+  - name: Clicks
+    description: Click analytics and tracking

download_regexes.sh

@@ -1,11 +0,0 @@
-#!/bin/bash
-
-REGEXES_URL="https://raw.githubusercontent.com/ua-parser/uap-core/master/regexes.yaml"
-DOWNLOAD_DIR="data"
-REGEXES_FILE="regexes.yaml"
-
-mkdir -p $DOWNLOAD_DIR
-
-curl -L -o $DOWNLOAD_DIR/$REGEXES_FILE $REGEXES_URL
-
-echo "Regexes file downloaded to $DOWNLOAD_DIR/$REGEXES_FILE"

scripts/benchmark.cr

@@ -0,0 +1,341 @@
+#!/usr/bin/env crystal
+
+require "http/client"
+require "json"
+
+PORT               = "4001"
+APP_URL            = "http://localhost:#{PORT}"
+API_URL            = "#{APP_URL}/api/links"
+API_KEY            = "secure_api_key_1"
+NUMBER_OF_REQUESTS = 100000
+
+APP_COMMAND  = "./bit"
+APP_ARGS     = [] of String
+STATS_FILE   = "resource_usage.log"
+APP_LOG_FILE = "app_output.log"
+
+DATABASE_URL  = "sqlite3://./sqlite/data.benchmark.db?journal_mode=wal&synchronous=normal&foreign_keys=true"
+DATABASE_FILE = "./sqlite/data.benchmark.db"
+
+class ResourceMonitor
+  def initialize(@pid : Int32)
+    @running = false
+    @stats = [] of {timestamp: Time, cpu: Float64, memory: Float64}
+  end
+
+  def start
+    @running = true
+    @stats.clear
+    File.write(STATS_FILE, "Timestamp\tCPU(%)\tMemory(MiB)\n")
+
+    spawn do
+      while @running
+        if stat = capture_stats
+          File.open(STATS_FILE, "a") do |file|
+            file.puts "#{stat[:timestamp].to_unix}\t#{stat[:cpu]}\t#{stat[:memory]}"
+          end
+          @stats << stat
+        end
+        sleep 1.seconds
+      end
+    end
+  end
+
+  def stop
+    @running = false
+    sleep 1.seconds
+  end
+
+  private def capture_stats
+    output = IO::Memory.new
+    process = Process.run(
+      "ps", ["-p", @pid.to_s, "-o", "%cpu,%mem,rss"],
+      output: output
+    )
+
+    if process.success?
+      lines = output.to_s.strip.split("\n")
+      if lines.size >= 2
+        data_line = lines[1].strip.split
+        if data_line.size >= 3
+          cpu = data_line[0].to_f
+          # RSS is in KB on macOS, convert to MiB
+          memory_kb = data_line[2].to_f
+          memory_mib = memory_kb / 1024.0
+
+          return {timestamp: Time.utc, cpu: cpu, memory: memory_mib}
+        end
+      end
+    end
+    nil
+  end
+
+  def print_summary
+    return if @stats.empty?
+
+    total_cpu = 0.0
+    total_memory = 0.0
+    peak_cpu = 0.0
+    peak_memory = 0.0
+
+    @stats.each do |stat|
+      total_cpu += stat[:cpu]
+      total_memory += stat[:memory]
+      peak_cpu = stat[:cpu] if stat[:cpu] > peak_cpu
+      peak_memory = stat[:memory] if stat[:memory] > peak_memory
+    end
+
+    avg_cpu = total_cpu / @stats.size
+    avg_memory = total_memory / @stats.size
+
+    summary = <<-STATS
+
+    **** Resource Usage Statistics ****
+      Measurements: #{@stats.size}
+      Average CPU Usage: #{avg_cpu.round(2)}%
+      Average Memory Usage: #{avg_memory.round(2)} MiB
+      Peak CPU Usage: #{peak_cpu.round(2)}%
+      Peak Memory Usage: #{peak_memory.round(2)} MiB
+
+    STATS
+
+    File.open(STATS_FILE, "a") do |file|
+      file.puts summary
+    end
+
+    puts summary
+  end
+end
+
+def start_application : Process
+  puts "Starting application: #{APP_COMMAND}..."
+  puts "Application output will be saved to: #{APP_LOG_FILE}"
+
+  log_file = File.open(APP_LOG_FILE, "w")
+
+  process = Process.new(
+    APP_COMMAND,
+    APP_ARGS,
+    output: log_file,
+    error: log_file,
+    env: {
+      "DATABASE_URL" => DATABASE_URL,
+      "APP_URL"      => APP_URL,
+      "PORT"         => PORT,
+    }
+  )
+
+  puts "Application started with PID: #{process.pid}"
+  puts "Using database: #{DATABASE_FILE}"
+  process
+end
+
+def stop_application(process : Process)
+  puts "\nStopping application..."
+  process.signal(Signal::TERM)
+
+  # Give it a few seconds to shut down gracefully
+  sleep 3.seconds
+
+  # Force kill if still running
+  begin
+    process.signal(Signal::KILL)
+  rescue
+    # Process already terminated
+  end
+
+  puts "Application stopped."
+end
+
+def check_dependencies
+  {"bombardier", "sqlite3", "micrate"}.each do |cmd|
+    process = Process.run("which", [cmd], output: Process::Redirect::Close)
+    unless process.success?
+      puts "Error: #{cmd} is not installed. Please install it to proceed."
+      case cmd
+      when "bombardier"
+        puts "  brew install bombardier"
+      when "sqlite3"
+        puts "  brew install sqlite3"
+      when "micrate"
+        puts "  shards install"
+      end
+      exit(1)
+    end
+  end
+end
+
+def wait_for_server
+  puts "Checking if server is ready at #{APP_URL}..."
+
+  30.times do
+    begin
+      if HTTP::Client.get("#{APP_URL}/api/ping").success?
+        puts "Server is ready!"
+        return
+      end
+    rescue
+      # Server not ready yet
+    end
+    sleep 1.seconds
+    print "."
+  end
+
+  puts "\nError: Server is not responding. Please start your application first."
+  exit(1)
+end
+
+def run_benchmark
+  puts "Fetching links from API..."
+
+  response = HTTP::Client.get(
+    "#{API_URL}?limit=10000",
+    headers: HTTP::Headers{"X-Api-Key" => API_KEY}
+  )
+
+  unless response.success?
+    puts "Failed to fetch links. Status: #{response.status_code}"
+    puts "Make sure your server is running and the API key is correct."
+    exit(1)
+  end
+
+  data = JSON.parse(response.body)
+  links = data["data"].as_a.map { |link| link["refer"].as_s }
+
+  if links.empty?
+    puts "No links found. Please seed your database first."
+    exit(1)
+  end
+
+  random_link = links.sample
+  puts "Selected link: #{random_link}"
+  puts "\nStarting benchmark with #{NUMBER_OF_REQUESTS} requests..."
+
+  sleep 2.seconds
+
+  process = Process.new(
+    "bombardier",
+    ["-n", NUMBER_OF_REQUESTS.to_s, "-l", "--disableKeepAlives", random_link],
+    output: Process::Redirect::Inherit,
+    error: Process::Redirect::Inherit
+  )
+
+  status = process.wait
+
+  if status.success?
+    puts "\nBenchmark completed successfully."
+  else
+    puts "\nBombardier failed with error code: #{status.exit_code}"
+    exit(1)
+  end
+end
+
+def cleanup_database
+  puts "Cleaning up benchmark database..."
+
+  if File.exists?(DATABASE_FILE)
+    File.delete(DATABASE_FILE)
+    puts "Deleted existing database: #{DATABASE_FILE}"
+  end
+
+  # Also remove WAL and SHM files if they exist
+  ["#{DATABASE_FILE}-wal", "#{DATABASE_FILE}-shm"].each do |file|
+    if File.exists?(file)
+      File.delete(file)
+      puts "Deleted: #{file}"
+    end
+  end
+
+  # Ensure sqlite directory exists
+  Dir.mkdir_p("./sqlite")
+  puts "Database cleanup completed."
+end
+
+def run_migrations
+  puts "Running database migrations..."
+
+  process = Process.run("which", ["micrate"], output: Process::Redirect::Close)
+  unless process.success?
+    puts "Error: micrate is not installed. Please install it to proceed."
+    puts "  shards install"
+    exit(1)
+  end
+
+  process = Process.run(
+    "micrate",
+    ["up"],
+    env: {"DATABASE_URL" => DATABASE_URL},
+    output: Process::Redirect::Inherit,
+    error: Process::Redirect::Inherit
+  )
+
+  if process.success?
+    puts "Migrations completed successfully."
+  else
+    puts "Error: Migrations failed."
+    exit(1)
+  end
+end
+
+def seed_database
+  puts "Seeding benchmark database..."
+
+  unless File.exists?("./db/seed.sql")
+    puts "Warning: ./db/seed.sql not found. Skipping database seeding."
+    return
+  end
+
+  unless File.exists?(DATABASE_FILE)
+    puts "Warning: #{DATABASE_FILE} not found. Database may not be initialized."
+  end
+
+  process = Process.run(
+    "sqlite3",
+    [DATABASE_FILE],
+    input: File.open("./db/seed.sql"),
+    output: Process::Redirect::Inherit,
+    error: Process::Redirect::Inherit
+  )
+
+  if process.success?
+    puts "Database seeded successfully."
+  else
+    puts "Warning: Database seeding failed. Continuing anyway..."
+  end
+end
+
+def main
+  check_dependencies
+
+  # Setup benchmark database
+  cleanup_database
+  run_migrations
+  seed_database
+
+  app_process = start_application
+
+  begin
+    wait_for_server
+
+    # Give it a moment to settle
+    sleep 2.seconds
+
+    monitor = ResourceMonitor.new(app_process.pid.to_i32)
+    monitor.start
+
+    run_benchmark
+
+    monitor.stop
+    monitor.print_summary
+
+    puts "\n**** Files Generated ****"
+    puts "  Resource stats: #{STATS_FILE}"
+    puts "  Application log: #{APP_LOG_FILE}"
+    puts "  Database: #{DATABASE_FILE}"
+  ensure
+    # Always stop the application
+    stop_application(app_process)
+  end
+end
+
+main

scripts/cli.cr

@@ -1,4 +1,3 @@
-require "uuid"
 require "option_parser"
 
 require "../app/services/cli"
@@ -19,11 +18,11 @@ OptionParser.parse do |parser|
     exit
   end
 
-  parser.on("--update-data", "Download all required data files (UA Parser and GeoLite2)") do
+  parser.on("--update-parsers", "Download UA regexes and/or GeoLite2 database") do
     puts "=== Starting data files update ==="
     App::Services::Cli.update_uap_regexes
-    App::Services::Cli.download_geolite_db
-    puts "=== All data files updated successfully ==="
+    App::Services::Cli.update_geolite_db
+    puts "=== Data files updated successfully ==="
     exit
   end
 
@@ -33,6 +32,6 @@ OptionParser.parse do |parser|
     puts "  --create-user=NAME     Create a new user with the given name"
     puts "  --list-users           List all users"
     puts "  --delete-user=USER_ID  Delete a user by ID"
-    puts "  --update-data          Download all required data files"
+    puts "  --update-parsers          Download all required data files"
   end
 end

shard.lock

@@ -2,11 +2,11 @@ version: 2.0
 shards:
   backtracer:
     git: https://github.com/sija/backtracer.cr.git
-    version: 1.2.2
+    version: 1.2.4
 
   crecto:
     git: https://github.com/fridgerator/crecto.git
-    version: 0.12.1
+    version: 0.14.0
 
   db:
     git: https://github.com/crystal-lang/crystal-db.git
@@ -18,7 +18,7 @@ shards:
 
   exception_page:
     git: https://github.com/crystal-loot/exception_page.git
-    version: 0.4.1
+    version: 0.5.0
 
   ipaddress:
     git: https://github.com/sija/ipaddress.cr.git
@@ -26,7 +26,7 @@ shards:
 
   kemal:
     git: https://github.com/kemalcr/kemal.git
-    version: 1.5.0
+    version: 1.7.3
 
   maxminddb:
     git: https://github.com/delef/maxminddb.cr.git
@@ -56,7 +56,3 @@ shards:
     git: https://github.com/crystal-lang/crystal-sqlite3.git
     version: 0.19.0
 
-  user_agent_parser:
-    git: https://github.com/busyloop/user_agent_parser.git
-    version: 2.0.1
-

shard.yml

@@ -1,18 +1,21 @@
 name: bit
-version: 1.5.1
+version: 1.6.0
 
 authors:
-  - Juan Rodriguez <sjdonado@icloud.com>
+  - Juan Rodriguez Donado <@sjdonado>
 
 targets:
   bit:
     main: bit.cr
   cli:
     main: scripts/cli.cr
+  benchmark:
+    main: scripts/benchmark.cr
 
 dependencies:
   kemal:
     github: kemalcr/kemal
+    version: 1.7.3
   sqlite3:
     github: crystal-lang/crystal-sqlite3
   crecto:
@@ -20,8 +23,6 @@ dependencies:
   micrate:
     github: amberframework/micrate
     version: 0.15.1
-  user_agent_parser:
-    github: busyloop/user_agent_parser
   maxminddb:
     github: delef/maxminddb.cr
 
@@ -31,6 +32,6 @@ development_dependencies:
   spec-kemal:
     github: kemalcr/spec-kemal
 
-crystal: ">= 1.12.1"
+crystal: ">= 1.18.2"
 
 license: MIT

spec/integration/link_spec.cr

@@ -15,7 +15,7 @@ describe "App::Controllers::Link" do
         body: payload.to_json
       )
 
-      parsed_response = Hash(String, Hash(String, String | Int64 | Array(Hash(String, String)))).from_json(response.body)
+      parsed_response = Hash(String, Hash(String, String | Int64 | Array(Hash(String, String | Int64)))).from_json(response.body)
       parsed_response["data"]["origin"].should eq(payload["url"])
     end
 
@@ -87,11 +87,10 @@ describe "App::Controllers::Link" do
       test_user = create_test_user()
 
       test_link = create_test_link(test_user, link)
-      serialized_link = App::Serializers::Link.new(test_link)
 
       user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:127.0) Gecko/20100101 Firefox/127.0"
 
-      get(serialized_link.refer, headers: HTTP::Headers{
+      get("/#{test_link.slug}", headers: HTTP::Headers{
         "X-Api-Key" => test_user.api_key.to_s,
         "User-Agent" => user_agent
       })
@@ -106,12 +105,11 @@ describe "App::Controllers::Link" do
       test_user = create_test_user()
 
       test_link = create_test_link(test_user, link)
-      serialized_link = App::Serializers::Link.new(test_link)
 
       user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:127.0) Gecko/20100101 Firefox/127.0"
       referer = "https://example.com/page"
 
-      get(serialized_link.refer, headers: HTTP::Headers{
+      get("/#{test_link.slug}", headers: HTTP::Headers{
         "User-Agent" => user_agent,
         "Referer" => referer
       })
@@ -121,7 +119,7 @@ describe "App::Controllers::Link" do
       response.headers["Location"].should eq(link)
 
       # Verify that the click was recorded
-      updated_test_link = get_test_link(test_link.id)
+      updated_test_link = get_test_link(test_link.id.not_nil!)
       updated_test_link.clicks.size.should eq(test_link.clicks.size + 1)
 
       # Verify click details
@@ -137,14 +135,16 @@ describe "App::Controllers::Link" do
       test_user = create_test_user()
 
       test_link = create_test_link(test_user, link)
-      serialized_link = App::Serializers::Link.new(test_link)
 
       # Add utm_source parameter
-      get("#{serialized_link.refer}?utm_source=email_campaign")
+      user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:127.0) Gecko/20100101 Firefox/127.0"
+      get("/#{test_link.slug}?utm_source=email_campaign", headers: HTTP::Headers{
+        "User-Agent" => user_agent
+      })
 
-      Fiber.yield
+      sleep 0.2.seconds # Wait for async click creation
 
-      updated_test_link = get_test_link(test_link.id)
+      updated_test_link = get_test_link(test_link.id.not_nil!)
       latest_click = updated_test_link.clicks.last
       latest_click.referer.should eq("email_campaign")
     end
@@ -152,7 +152,7 @@ describe "App::Controllers::Link" do
     it "should return 404 - link does not exist" do
       test_user = create_test_user()
 
-      get("https://localhost:4001/R4kj2")
+      get("/R4kj2")
 
       expected = {"error" => "Resource not found"}.to_json
       response.status_code.should eq(404)
@@ -171,7 +171,7 @@ describe "App::Controllers::Link" do
 
       get("/api/links", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
 
-      parsed_response = Hash(String, Array(Hash(String, String | Int64)) | Hash(String, Bool | String?)).from_json(response.body)
+      parsed_response = Hash(String, Array(Hash(String, String | Int64)) | Hash(String, Bool | String? | Int64?)).from_json(response.body)
 
       # Check that each link is in the response data
       origins = parsed_response["data"].as(Array).map { |link| link["origin"] }
@@ -191,7 +191,7 @@ describe "App::Controllers::Link" do
 
       get("/api/links?limit=2", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
 
-      parsed_response = Hash(String, Array(Hash(String, String | Int64)) | Hash(String, Bool | String?)).from_json(response.body)
+      parsed_response = Hash(String, Array(Hash(String, String | Int64)) | Hash(String, Bool | String? | Int64?)).from_json(response.body)
       parsed_response["data"].as(Array).size.should eq(2)
       parsed_response["pagination"].as(Hash)["has_more"].should be_true
       parsed_response["pagination"].as(Hash)["next"].should_not be_nil
@@ -206,12 +206,12 @@ describe "App::Controllers::Link" do
 
       # Get first page
       get("/api/links?limit=2", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
-      first_page = Hash(String, Array(Hash(String, String | Int64)) | Hash(String, Bool | String?)).from_json(response.body)
+      first_page = Hash(String, Array(Hash(String, String | Int64)) | Hash(String, Bool | String? | Int64?)).from_json(response.body)
       cursor = first_page["pagination"].as(Hash)["next"]
 
       # Get second page using cursor
       get("/api/links?limit=2&cursor=#{cursor}", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
-      second_page = Hash(String, Array(Hash(String, String | Int64)) | Hash(String, Bool | String?)).from_json(response.body)
+      second_page = Hash(String, Array(Hash(String, String | Int64)) | Hash(String, Bool | String? | Int64?)).from_json(response.body)
 
       # Ensure different links are returned
       first_page_ids = first_page["data"].as(Array).map { |link| link["id"] }
@@ -234,7 +234,7 @@ describe "App::Controllers::Link" do
 
       get("/api/links", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
 
-      parsed_response = Hash(String, Array(Hash(String, String | Int64)) | Hash(String, Bool | String?)).from_json(response.body)
+      parsed_response = Hash(String, Array(Hash(String, String | Int64)) | Hash(String, Bool | String? | Int64?)).from_json(response.body)
       parsed_response["data"].as(Array).size.should eq(3)
 
       origins = parsed_response["data"].as(Array).map { |link| link["origin"] }
@@ -265,7 +265,7 @@ describe "App::Controllers::Link" do
 
       get("/api/links/#{test_link.id}", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
 
-      parsed_response = Hash(String, Hash(String, String | Int64 | Array(Hash(String, String)))).from_json(response.body)
+      parsed_response = Hash(String, Hash(String, String | Int64 | Array(Hash(String, String | Int64)))).from_json(response.body)
       parsed_response["data"]["origin"].should eq(link)
       parsed_response["data"]["clicks"].as(Array).size.should eq(100)
     end
@@ -273,7 +273,7 @@ describe "App::Controllers::Link" do
     it "should return 404 - link does not exist" do
       test_user = create_test_user()
 
-      get("/api/links/1", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
+      get("/api/links/999999", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
 
       expected = {"error" => "Resource not found"}.to_json
       response.status_code.should eq(404)
@@ -301,7 +301,7 @@ describe "App::Controllers::Link" do
 
       get("/api/links/#{test_link.id}/clicks", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
 
-      parsed_response = Hash(String, Array(Hash(String, String)) | Hash(String, Bool | String?)).from_json(response.body)
+      parsed_response = Hash(String, Array(Hash(String, String | Int64)) | Hash(String, Bool | String? | Int64?)).from_json(response.body)
       parsed_response["data"].as(Array).size.should eq(5)
       parsed_response["pagination"].as(Hash)["has_more"].should be_false
     end
@@ -317,7 +317,7 @@ describe "App::Controllers::Link" do
 
       get("/api/links/#{test_link.id}/clicks?limit=3", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
 
-      parsed_response = Hash(String, Array(Hash(String, String)) | Hash(String, Bool | String?)).from_json(response.body)
+      parsed_response = Hash(String, Array(Hash(String, String | Int64)) | Hash(String, Bool | String? | Int64?)).from_json(response.body)
       parsed_response["data"].as(Array).size.should eq(3)
       parsed_response["pagination"].as(Hash)["has_more"].should be_true
       parsed_response["pagination"].as(Hash)["next"].should_not be_nil
@@ -334,12 +334,12 @@ describe "App::Controllers::Link" do
 
       # Get first page
       get("/api/links/#{test_link.id}/clicks?limit=3", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
-      first_page = Hash(String, Array(Hash(String, String)) | Hash(String, Bool | String?)).from_json(response.body)
+      first_page = Hash(String, Array(Hash(String, String | Int64)) | Hash(String, Bool | String? | Int64?)).from_json(response.body)
       cursor = first_page["pagination"].as(Hash)["next"]
 
       # Get second page using cursor
       get("/api/links/#{test_link.id}/clicks?limit=3&cursor=#{cursor}", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
-      second_page = Hash(String, Array(Hash(String, String)) | Hash(String, Bool | String?)).from_json(response.body)
+      second_page = Hash(String, Array(Hash(String, String | Int64)) | Hash(String, Bool | String? | Int64?)).from_json(response.body)
 
       # Ensure different clicks are returned
       first_page_ids = first_page["data"].as(Array).map { |click| click["id"] }
@@ -352,7 +352,7 @@ describe "App::Controllers::Link" do
     it "should return 404 - link does not exist" do
       test_user = create_test_user()
 
-      get("/api/links/nonexistent_id/clicks", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
+      get("/api/links/999999/clicks", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
 
       expected = {"error" => "Resource not found"}.to_json
       response.status_code.should eq(404)
@@ -381,7 +381,7 @@ describe "App::Controllers::Link" do
         body: payload.to_json
       )
 
-      parsed_response = Hash(String, Hash(String, String | Int64 | Array(Hash(String, String)))).from_json(response.body)
+      parsed_response = Hash(String, Hash(String, String | Int64 | Array(Hash(String, String | Int64)))).from_json(response.body)
       parsed_response["data"]["origin"].should eq(payload["url"])
     end
 
@@ -390,7 +390,7 @@ describe "App::Controllers::Link" do
 
       payload = {"url" => "https://kagi.com.co"}
       put(
-        "/api/links/1",
+        "/api/links/999999",
         headers: HTTP::Headers{"Content-Type" => "application/json", "X-Api-Key" => test_user.api_key.to_s},
         body: payload.to_json
       )
@@ -428,7 +428,7 @@ describe "App::Controllers::Link" do
     it "should return 404 - link does not exist" do
       test_user = create_test_user()
 
-      delete("/api/links/1", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
+      delete("/api/links/999999", headers: HTTP::Headers{"X-Api-Key" => test_user.api_key.to_s})
 
       expected = {"error" => "Resource not found"}.to_json
       response.status_code.should eq(404)

spec/spec_helper.cr

@@ -1,4 +1,3 @@
-require "uuid"
 require "file_utils"
 
 require "spec-kemal"
@@ -24,7 +23,6 @@ end
 
 def create_test_user
   user = App::Models::User.new
-  user.id = UUID.v4.to_s
   user.name = "Tester"
   user.api_key = Random::Secure.urlsafe_base64()
 
@@ -34,13 +32,12 @@ def create_test_user
     raise "Test user creation failed #{error_messages}"
   end
 
-  user
+  changeset.instance
 end
 
 def create_test_link(user, url)
   link = App::Models::Link.new
-  link.id = UUID.v4.to_s
-  link.slug = App::Services::SlugService.shorten_url(url, user.id.to_s)
+  link.slug = App::Services::SlugService.shorten_url(url, user.id.not_nil!)
   link.url = url
   link.user = user
 
@@ -50,14 +47,14 @@ def create_test_link(user, url)
     raise "Test link creation failed: #{error_messages}"
   end
 
-  link.clicks = [] of App::Models::Click
+  inserted_link = changeset.instance
+  inserted_link.clicks = [] of App::Models::Click
 
-  link
+  inserted_link
 end
 
 def create_test_click(link)
   click = App::Models::Click.new
-  click.id = UUID.v4.to_s
   click.user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:127.0) Gecko/20100101 Firefox/127.0"
   click.browser = "Firefox"
   click.os = "Mac OS X"
@@ -65,18 +62,18 @@ def create_test_click(link)
   click.country = "US"
   click.created_at = Time.utc
   click.link = link
-  click.link_id = link.id
+  click.link_id = link.id.not_nil!
 
   changeset = App::Lib::Database.insert(click)
   unless changeset.valid?
     error_messages = changeset.errors.map { |error| "#{error}" }.join(", ")
     raise "Test click creation failed: #{error_messages}"
   end
-  click
+  changeset.instance
 end
 
-def get_test_link(link_id)
-  query = App::Lib::Database::Query.where(id: link_id.as(String)).limit(1)
+def get_test_link(link_id : Int64)
+  query = App::Lib::Database::Query.where(id: link_id).limit(1)
   link = App::Lib::Database.all(App::Models::Link, query, preload: [:clicks]).first?
 
   raise "Link not found" if link.nil?
@@ -84,6 +81,6 @@ def get_test_link(link_id)
   link
 end
 
-def delete_test_link(link_id)
+def delete_test_link(link_id : Int64)
   App::Lib::Database.raw_exec("DELETE FROM links WHERE id = (?)", link_id) # tempfix: Database.delete does not work
 end