Set alert_every to 0 for mdstat_raid monitor to prevent repeated alerts

Reviewed-on: https://git.iamthefij.com/iamthefij/minitor-go/pulls/13

.drone.yml

@@ -1,114 +1,53 @@
----
 kind: pipeline
-name: test
+type: kubernetes
+name: default
 
-steps:
+node_selector:
-
+  zone: dev
-  - name: test
-    image: golang:1.12
-    commands:
-      - make build
-      - make test
-
-  - name: check
-    image: python:3
-    commands:
-      - pip install pre-commit==1.20.0
-      - make check
-
-  - name: notify
-    image: drillster/drone-email
-    settings:
-      host:
-        from_secret: SMTP_HOST
-      username:
-        from_secret: SMTP_USER
-      password:
-        from_secret: SMTP_PASS
-      from: drone@iamthefij.com
-    when:
-      status: [changed, failure]
-
----
-kind: pipeline
-name: publish
-
-depends_on:
-  - test
 
 trigger:
   event:
     - push
     - tag
-  refs:
+
-    - refs/heads/master
+workspace:
-    - refs/tags/v*
+  path: /drone/src
 
 steps:
-  - name: build all binaries
+  - name: pull image to dockerhub
-    image: golang:1.12
+    image: docker.io/owncloudci/drone-docker-buildx:4
-    commands:
+    privileged: true
-      - make all
-
-  - name: push image - arm
-    image: plugins/docker
     settings:
-      repo: iamthefij/minitor-go
+      cache-from: [ "safebox/minitor" ]
-      auto_tag: true
+      repo: safebox/minitor
-      auto_tag_suffix: linux-arm
+      tags: latest
       username:
-        from_secret: docker_username
+        from_secret: dockerhub-username
       password: 
-        from_secret: docker_password
+        from_secret: dockerhub-password
-      build_args:
+      platforms:
-        - ARCH=arm
+        - linux/amd64
-        - REPO=arm32v7
+        - linux/arm64
-
-  - name: push image - arm64
-    image: plugins/docker
-    settings:
-      repo: iamthefij/minitor-go
-      auto_tag: true
-      auto_tag_suffix: linux-arm64
-      username:
-        from_secret: docker_username
-      password:
-        from_secret: docker_password
-      build_args:
-        - ARCH=arm64
-        - REPO=arm64v8
-
-  - name: push image - amd64
-    image: plugins/docker
-    settings:
-      repo: iamthefij/minitor-go
-      auto_tag: true
-      auto_tag_suffix: linux-amd64
-      username:
-        from_secret: docker_username
-      password:
-        from_secret: docker_password
-
-  - name: publish manifest
-    image: plugins/manifest
-    settings:
-      spec: manifest.tmpl
-      auto_tag: true
-      ignore_missing: true
-      username:
-        from_secret: docker_username
-      password:
-        from_secret: docker_password
-
-  - name: notify
-    image: drillster/drone-email
-    settings:
-      host:
-        from_secret: SMTP_HOST
-      username:
-        from_secret: SMTP_USER
-      password:
-        from_secret: SMTP_PASS
-      from: drone@iamthefij.com
     when:  
-      status: [changed, failure]
+      event:
+        - tag
+
+  - name: build multiarch from dev
+    image: docker.io/owncloudci/drone-docker-buildx:4
+    privileged: true
+    settings:
+      cache-from: [ "registry.dev.format.hu/minitor" ]
+      registry: registry.dev.format.hu
+      repo: registry.dev.format.hu/minitor
+      tags: latest
+      dockerfile: Dockerfile
+      username:
+        from_secret: dev-hu-registry-username
+      password: 
+        from_secret: dev-hu-registry-password
+      platforms:
+        - linux/amd64
+        - linux/arm64
+    when:  
+      event:
+        - push

.gitignore

@@ -14,8 +14,9 @@
 
 # User configuration
 config.yml
+config.hcl
 
 # Output binary
 minitor
-minitor-linux-*
+minitor-go
-minitor-darwin-amd64
+dist/

.golangci.yml

@@ -0,0 +1,52 @@
+version: "2"
+linters:
+  enable:
+    - errname
+    - errorlint
+    - exhaustive
+    - goprintffuncname
+    - misspell
+    - mnd
+    - tagliatelle
+    - testpackage
+    - thelper
+    - tparallel
+    - unconvert
+    - wrapcheck
+    - wsl
+  disable:
+    - gochecknoglobals
+  settings:
+    gosec:
+      excludes:
+        - G204
+    tagliatelle:
+      case:
+        rules:
+          json: snake
+          yaml: snake
+  exclusions:
+    generated: lax
+    presets:
+      - comments
+      - common-false-positives
+      - legacy
+      - std-error-handling
+    rules:
+      - linters:
+          - gosec
+        path: _test\.go
+    paths:
+      - third_party$
+      - builtin$
+      - examples$
+formatters:
+  enable:
+    - gofumpt
+    - goimports
+  exclusions:
+    generated: lax
+    paths:
+      - third_party$
+      - builtin$
+      - examples$

.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 ---
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v2.4.0
+    rev: v6.0.0
     hooks:
       - id: check-added-large-files
       - id: check-yaml
@@ -10,10 +10,11 @@ repos:
       - id: trailing-whitespace
       - id: end-of-file-fixer
       - id: check-merge-conflict
-  - repo: git://github.com/dnephin/pre-commit-golang
+  - repo: https://github.com/golangci/golangci-lint
-    rev: v0.3.5
+    rev: v2.7.2
     hooks:
-      - id: go-fmt
+      - id: golangci-lint
-      - id: go-imports
+  - repo: https://github.com/hadolint/hadolint
-      # - id: gometalinter
+    rev: refs/pull/1152/head
-      # - id: golangci-lint
+    hooks:
+      - id: hadolint-github

Dockerfile

@@ -1,27 +1,129 @@
-ARG REPO=library
+FROM golang:1.25 AS gomail-builder
-FROM multiarch/qemu-user-static:4.2.0-2 as qemu-user-static
+ARG TARGETARCH=amd64
-FROM ${REPO}/alpine:3.10
+ARG TARGETOS=linux
+WORKDIR /gomail
+RUN { \
+    echo 'package main'; \
+    echo ''; \
+    echo 'import ('; \
+    echo '    "fmt"'; \
+    echo '    "io"'; \
+    echo '    "net/mail"'; \
+    echo '    "net/smtp"'; \
+    echo '    "os"'; \
+    echo '    "strings"'; \
+    echo ')'; \
+    echo ''; \
+    echo 'func main() {'; \
+    echo '    readHeaders := strings.Contains(strings.Join(os.Args[1:], " "), "-t")'; \
+    echo '    recipients := []string{}'; \
+    echo '    for _, arg := range os.Args[1:] {'; \
+    echo '        if !strings.HasPrefix(arg, "-") {'; \
+    echo '            recipients = append(recipients, arg)'; \
+    echo '        }'; \
+    echo '    }'; \
+    echo ''; \
+    echo '    body, err := io.ReadAll(os.Stdin)'; \
+    echo '    if err != nil {'; \
+    echo '        fmt.Fprintln(os.Stderr, err)'; \
+    echo '        os.Exit(1)'; \
+    echo '    }'; \
+    echo ''; \
+    echo '    if readHeaders {'; \
+    echo '        msg, parseErr := mail.ReadMessage(strings.NewReader(string(body)))'; \
+    echo '        if parseErr != nil {'; \
+    echo '            fmt.Fprintln(os.Stderr, parseErr)'; \
+    echo '            os.Exit(1)'; \
+    echo '        }'; \
+    echo '        for _, hdr := range []string{"To", "Cc", "Bcc"} {'; \
+    echo '            if val := msg.Header.Get(hdr); val != "" {'; \
+    echo '                addrs, addrErr := mail.ParseAddressList(val)'; \
+    echo '                if addrErr != nil {'; \
+    echo '                    fmt.Fprintln(os.Stderr, addrErr)'; \
+    echo '                    os.Exit(1)'; \
+    echo '                }'; \
+    echo '                for _, addr := range addrs {'; \
+    echo '                    recipients = append(recipients, addr.Address)'; \
+    echo '                }'; \
+    echo '            }'; \
+    echo '        }'; \
+    echo '    }'; \
+    echo ''; \
+    echo '    if len(recipients) == 0 {'; \
+    echo '        fmt.Fprintln(os.Stderr, "usage: sendmail [-t] recipient...")'; \
+    echo '        os.Exit(1)'; \
+    echo '    }'; \
+    echo ''; \
+    echo '    relay := os.Getenv("SMTP_RELAY")'; \
+    echo '    if relay == "" {'; \
+    echo '        relay = "172.17.0.2"'; \
+    echo '    }'; \
+    echo ''; \
+    echo '    port := os.Getenv("SMTP_PORT")'; \
+    echo '    if port == "" {'; \
+    echo '        port = "25"'; \
+    echo '    }'; \
+    echo ''; \
+    echo '    sender := os.Getenv("EMAIL_FROM")'; \
+    echo '    if sender == "" {'; \
+    echo '        fmt.Fprintln(os.Stderr, "[sendmail] EMAIL_FROM is not set, skipping")'; \
+    echo '        os.Exit(0)'; \
+    echo '    }'; \
+    echo ''; \
+    echo '    debug := os.Getenv("DEBUG") != ""'; \
+    echo '    if debug {'; \
+    echo '        fmt.Fprintln(os.Stderr, fmt.Sprintf("[sendmail] relay=%s port=%s sender=%s recipients=%v", relay, port, sender, recipients))'; \
+    echo '        fmt.Fprintln(os.Stderr, "[sendmail] body:")'; \
+    echo '        fmt.Fprintln(os.Stderr, string(body))'; \
+    echo '    }'; \
+    echo ''; \
+    echo '    if err = smtp.SendMail(relay+":"+port, nil, sender, recipients, body); err != nil {'; \
+    echo '        fmt.Fprintln(os.Stderr, err)'; \
+    echo '        os.Exit(1)'; \
+    echo '    }'; \
+    echo '    if debug {'; \
+    echo '        fmt.Fprintln(os.Stderr, "[sendmail] sent successfully")'; \
+    echo '    }'; \
+    echo '}'; \
+    } > main.go
+RUN go mod init gomail && \
+    CGO_ENABLED=0 GOOS=${TARGETOS} GOARCH=${TARGETARCH} go build -o /usr/local/bin/sendmail .
 
-# Copying all qemu files because amd64 doesn't exist and cannot condional copy
-COPY --from=qemu-user-static /usr/bin/qemu-* /usr/bin/
 
+FROM golang:1.25 AS builder
+WORKDIR /app
+COPY ./go.mod ./go.sum /app/
+RUN go mod download
+COPY ./*.go /app/
+RUN rm -f /app/gomail.go
+
+ARG TARGETARCH=amd64
+ARG TARGETOS=linux
+ARG VERSION=dev
+RUN CGO_ENABLED=0 GOOS=${TARGETOS} GOARCH=${TARGETARCH} go build -ldflags "-X main.version=${VERSION}" -a -installsuffix nocgo -o minitor .
+
+FROM alpine:3.23
 RUN mkdir /app
 WORKDIR /app/
 
+# Copy minitor in
+COPY --from=builder /app/minitor .
+
+# Copy sendmail (gomail) in
+COPY --from=gomail-builder /usr/local/bin/sendmail /usr/local/bin/sendmail
+
 # Add common checking tools
-RUN apk --no-cache add bash=~5.0 curl=~7.66 jq=~1.6
+# hadolint ignore=DL3018
+RUN apk --no-cache add bash=~5 curl=~8 jq=~1 bind-tools=~9 tzdata
 
 # Add minitor user for running as non-root
 RUN addgroup -S minitor && adduser -S minitor -G minitor
 
 # Copy scripts
 COPY ./scripts /app/scripts
+COPY default_config.hcl /app/config.hcl
 RUN chmod -R 755 /app/scripts
 
-# Copy minitor in
-ARG ARCH=amd64
-COPY ./minitor-linux-${ARCH} ./minitor
-
 # Drop to non-root user
 USER minitor
 

Dockerfile.multi-stage

@@ -1,41 +0,0 @@
-ARG REPO=library
-FROM golang:1.12-alpine AS builder
-
-RUN apk add --no-cache git=~2
-
-RUN mkdir /app
-WORKDIR /app
-
-COPY ./go.mod ./go.sum /app/
-RUN go mod download
-
-COPY ./*.go /app/
-
-ARG ARCH=amd64
-ARG VERSION=dev
-ENV CGO_ENABLED=0 GOOS=linux GOARCH=${ARCH}
-RUN go build -ldflags "-X main.version=${VERSION}" -a -installsuffix nocgo -o minitor .
-
-FROM ${REPO}/alpine:3.10
-RUN mkdir /app
-WORKDIR /app/
-
-# Copy minitor in
-COPY --from=builder /app/minitor .
-
-# Add common checking tools
-RUN apk --no-cache add bash=~5.0 curl=~7.66 jq=~1.6
-
-# Add minitor user for running as non-root
-RUN addgroup -S minitor && adduser -S minitor -G minitor
-
-# Copy scripts
-COPY ./scripts /app/scripts
-RUN chmod -R 755 /app/scripts
-
-# Drop to non-root user
-USER minitor
-
-ENTRYPOINT [ "./minitor" ]
-
-# vim: set filetype=dockerfile:

Makefile

@@ -1,36 +1,43 @@
 DOCKER_TAG ?= minitor-go-${USER}
-GIT_TAG_NAME := $(shell git tag -l --contains HEAD)
+VERSION ?= $(shell git describe --tags --dirty)
-GIT_SHA := $(shell git rev-parse HEAD)
+GOFILES = *.go go.mod go.sum
-VERSION := $(if $(GIT_TAG_NAME),$(GIT_TAG_NAME),$(GIT_SHA))
+# Multi-arch targets are generated from this
+TARGET_ALIAS = minitor-linux-amd64 minitor-linux-arm minitor-linux-arm64 minitor-darwin-amd64
+TARGETS = $(addprefix dist/,$(TARGET_ALIAS))
+#
+# Default make target will run tests
+.DEFAULT_GOAL = test
 
+# Build all static Minitor binaries
 .PHONY: all
-all: minitor-linux-amd64 minitor-linux-arm minitor-linux-arm64
+all: $(TARGETS)
 
-.PHONY: default
+# Build all static Linux Minitor binaries. Used in Docker images
-default: test
+.PHONY: all-linux
+all-linux: $(filter dist/minitor-linux-%,$(TARGETS))
+
+# Build minitor for the current machine
+minitor: $(GOFILES)
+	@echo Version: $(VERSION)
+	go build -ldflags '-X "main.version=${VERSION}"' -o minitor
 
 .PHONY: build
 build: minitor
 
-minitor:
+# Run minitor for the current machine
-	@echo Version: $(VERSION)
-	go build -ldflags '-X "main.version=${VERSION}"' -o minitor
-
 .PHONY: run
-run: minitor build
+run: minitor
 	./minitor -debug
 
 .PHONY: run-metrics
-run-metrics: minitor build
+run-metrics: minitor
 	./minitor -debug -metrics
 
+# Run all tests
 .PHONY: test
 test:
 	go test -coverprofile=coverage.out
-	@echo
 	go tool cover -func=coverage.out
-	@echo
-	@# Check min coverage percentage
 	@go tool cover -func=coverage.out | awk -v target=80.0% \
 		'/^total:/ { print "Total coverage: " $$3 " Minimum coverage: " target; if ($$3+0.0 >= target+0.0) print "ok"; else { print "fail"; exit 1; } }'
 
@@ -39,7 +46,7 @@ test:
 install-hooks:
 	pre-commit install --install-hooks
 
-# Checks files for encryption
+# Runs pre-commit checks on files
 .PHONY: check
 check:
 	pre-commit run --all-files
@@ -47,9 +54,8 @@ check:
 .PHONY: clean
 clean:
 	rm -f ./minitor
-	rm -f ./minitor-linux-*
-	rm -f ./minitor-darwin-amd64
 	rm -f ./coverage.out
+	rm -fr ./dist
 
 .PHONY: docker-build
 docker-build:
@@ -57,39 +63,27 @@ docker-build:
 
 .PHONY: docker-run
 docker-run: docker-build
-	docker run --rm -v $(shell pwd)/config.yml:/root/config.yml $(DOCKER_TAG)
+	docker run --rm -v $(shell pwd)/sample-config.hcl:/root/config.hcl $(DOCKER_TAG)
 
 ## Multi-arch targets
-
+$(TARGETS): $(GOFILES)
-# Arch specific go build targets
+	mkdir -p ./dist
-minitor-darwin-amd64:
+	GOOS=$(word 2, $(subst -, ,$(@))) GOARCH=$(word 3, $(subst -, ,$(@))) CGO_ENABLED=0 \
-	GOOS=darwin GOARCH=amd64 CGO_ENABLED=0 \
 		go build -ldflags '-X "main.version=${VERSION}"' -a -installsuffix nocgo \
-		   -o minitor-darwin-amd64
+		-o $@
 
-minitor-linux-amd64:
+.PHONY: $(TARGET_ALIAS)
-	GOOS=linux GOARCH=amd64 CGO_ENABLED=0 \
+$(TARGET_ALIAS):
-		   go build -ldflags '-X "main.version=${VERSION}"' -a -installsuffix nocgo \
+	$(MAKE) $(addprefix dist/,$@)
-		   -o minitor-linux-amd64
-
-minitor-linux-arm:
-	GOOS=linux GOARCH=arm CGO_ENABLED=0 \
-		   go build -ldflags '-X "main.version=${VERSION}"' -a -installsuffix nocgo \
-		   -o minitor-linux-arm
-
-minitor-linux-arm64:
-	GOOS=linux GOARCH=arm64 CGO_ENABLED=0 \
-		   go build -ldflags '-X "main.version=${VERSION}"' -a -installsuffix nocgo \
-		   -o minitor-linux-arm64
 
 # Arch specific docker build targets
 .PHONY: docker-build-arm
-docker-build-arm: minitor-linux-arm
+docker-build-arm: dist/minitor-linux-arm
-	docker build --build-arg REPO=arm32v7 --build-arg ARCH=arm . -t ${DOCKER_TAG}-linux-arm
+	docker build --platform linux/arm . -t ${DOCKER_TAG}-linux-arm
 
-.PHONY: docker-build-arm
+.PHONY: docker-build-arm64
-docker-build-arm64: minitor-linux-arm64
+docker-build-arm64: dist/minitor-linux-arm64
-	docker build --build-arg REPO=arm64v8 --build-arg ARCH=arm64 . -t ${DOCKER_TAG}-linux-arm64
+	docker build  --platform linux/arm64 . -t ${DOCKER_TAG}-linux-arm64
 
 # Cross run on host architechture
 .PHONY: docker-run-arm

README.md

@@ -1,79 +1,220 @@
-# minitor-go
+# [minitor-go](https://git.iamthefij.com/iamthefij/minitor-go)
 
-A reimplementation of [Minitor](https://git.iamthefij.com/iamthefij/minitor) in Go
+A minimal monitoring system
 
-Minitor is already a minimal monitoring tool. Python 3 was a quick way to get something live, but Python itself comes with a large footprint. Thus Go feels like a better fit for the project, longer term.
+## What does it do?
 
-Initial target is meant to be roughly compatible requiring only minor changes to configuration. Future iterations may diverge to take advantage of Go specific features.
+Minitor accepts an HCL configuration file with a set of commands to run and a set of alerts to execute when those commands fail. Minitor has a narow feature set and instead follows a principle to outsource to other command line tools when possible. Thus, it relies on other command line tools to do checks and issue alerts. To make getting started a bit easier, Minitor includes a few scripts to help with common tasks.
 
-## Differences from Python version
+## But why?
 
+I'm running a few small services and found Sensu, Consul, Nagios, etc. to all be far too complicated for my usecase.
 
-Templating for Alert messages has been updated. In the Python version, `str.format(...)` was used with certain keys passed in that could be used to format messages. In the Go version, we use a struct, `AlertNotice` defined in `alert.go` and the built in Go templating format. Eg.
+## So how do I use it?
 
-minitor-py:
+### Running
-```yaml
+
-alerts:
+Install and execute with:
-  log_command:
+
-    command: ['echo', '{monitor_name}']
+```bash
-  log_shell:
+go install github.com/iamthefij/minitor-go/v2@latest
-    command: 'echo {monitor_name}'
+minitor
 ```
 
-minitor-go:
+If locally developing you can use:
-```yaml
+
-alerts:
+```bash
-  log_command:
+make run
-    command: ['echo', '{{.MonitorName}}']
-  log_shell:
-    command: 'echo {{.MonitorName}}'
 ```
 
-Finally, newlines in a shell command don't terminate a particular command. Semicolons must be used and continuations should not.
+It will read the contents of `sample-config.hcl` and begin its loop. You could also run it directly and provide a new config file via the `-config` argument.
 
-minitor-py:
+
-```yaml
+#### Docker
-alerts:
+
-  log_shell:
+You can pull this repository directly from Docker:
-    command: >
+
-      echo "line 1"
+```bash
-      echo "line 2"
+docker pull iamthefij/minitor-go:latest
-      echo "continued" \
-        "line"
 ```
 
-minitor-go:
+The Docker image uses a default `config.hcl` copied from `sample-config.hcl`. This won't really do anything for you, so when you run the Docker image, you should supply your own `config.hcl` file:
-```yaml
+
-alerts:
+```bash
-  log_shell:
+docker run -v $PWD/sample-config.hcl:/app/config.hcl iamthefij/minitor-go:latest
-    command: >
-      echo "line 1";
-      echo "line 2";
-      echo "continued"
-        "line"
 ```
 
-## To do
+Images are provided for `amd64`, `arm`, and `arm64` architechtures.
-There are two sets of task lists. The first is to get rough parity on key features with the Python version. The second is to make some improvements to the framework.
 
-Pairity:
+You can configure the timezone for the container by passing a `TZ` env variable. Eg. `TZ=America/Los_Angeles`.
 
-  - [x] Run monitor commands
+## Configuring
-  - [x] Run monitor commands in a shell
-  - [x] Run alert commands
-  - [x] Run alert commands in a shell
-  - [x] Allow templating of alert commands
-  - [x] Implement Prometheus client to export metrics
-  - [x] Test coverage
-  - [x] Integration testing (manual or otherwise)
-  - [x] Allow commands and shell commands in the same config key
 
-Improvement (potentially breaking):
+In this repo, you can explore the `sample-config.hcl` file for an example, but the general structure is as follows. If you are passing environment variables to your commands or alerts, you should be aware that `${VAR}` syntax is reserved for HCL variable interpolation. To avoid issues, you can use `$${VAR}` syntax to escape the `$` character, simply use `$VAR`.
 
-  - [ ] Implement leveled logging (maybe glog or logrus)
+```hcl
-  - [ ] Consider switching from YAML to TOML
+
-  - [ ] Consider value of templating vs injecting values into Env variables
+The global configurations are:
-  - [ ] Consider dropping `alert_up` and `alert_down` in favor of using Go templates that offer more control of messaging
+
-  - [ ] Async checking
+|key|value|
-  - [ ] Use durations rather than seconds checked in event loop
+|---|---|
-  - [ ] Revisit metrics and see if they all make sense
+|`check_interval`|Maximum frequency to run checks for each monitor as duration, eg. 1m2s.|
+|`default_alert_after`|A default value used as an `alert_after` value for a monitor if not specified. Defaults 1, which will alert immediately.|
+|`default_alert_every`|A default value used as an `alert_every` value for a monitor if not specified. Defaults to -1, which will re-alert exponentially.|
+|`default_alert_down`|Default down alerts to used by a monitor in case none are provided.|
+|`default_alert_up`|Default up alerts to used by a monitor in case none are provided.|
+|`monitor`|block listing monitors. Detailed description below|
+|`alert`|List of all alerts. Detailed description below|
+
+### Monitors
+
+Represent your monitors as blocks with a label indicating the name of the monitor.
+
+```hcl
+monitor "example" {
+  command = ["echo", "Hello, World!"]
+  alert_down = ["log"]
+  alert_up = ["log"]
+  check_interval = "1m"
+  alert_after = 1
+  alert_every = -1
+}
+```
+
+Each monitor allows the following configuration:
+
+|key|value|
+|---|---|
+|`name`|Name of the monitor running. This will show up in messages and logs.|
+|`command`|A list of strings representing a command to be executed. This command's exit value will determine whether the check is successful. This value is mutually exclusive to `shell_command`|
+|`shell_command`|A single string that represents a shell command to be executed. This command's exit value will determine whether the check is successful. This value is mutually exclusive to `command`|
+|`alert_down`|A list of Alerts to be triggered when the monitor is in a "down" state|
+|`alert_up`|A list of Alerts to be triggered when the monitor moves to an "up" state|
+|`check_interval`|The interval at which this monitor should be checked. This must be greater than the global `check_interval` value|
+|`alert_after`|Allows specifying the number of failed checks before an alert should be triggered. A value of 1 will start sending alerts after the first failure.|
+|`alert_every`|Allows specifying how often an alert should be retriggered. There are a few magic numbers here. Defaults to `-1` for an exponential backoff. Setting to `0` disables re-alerting. Positive values will allow retriggering after the specified number of checks|
+
+### Alerts
+
+Represent your alerts as blocks with a lable indicating the name of the alert. The name will be used in your monitor setup in `alert_down` and `alert_up`.
+
+```hcl
+monitor "example" {
+  command = ["false"]
+  alert_down = ["log"]
+}
+
+alert "log" {
+  shell_command = "echo '{{.MonitorName}} is down!'"
+}
+```
+
+Each alert allows the following configuration:
+
+|key|value|
+|---|---|
+|`command`|Specifies the command that should be executed in exec form. This is the command that will be run when the alert is executed. This can be templated with environment variables or the variables shown in the table below. This value is mutually exclusive to `shell_command`|
+|`shell_command`|Specifies a shell command as a single string. This is the command that will be run when the alert is executed. This can be templated with environment variables or the variables shown in the table below. This value is mutually exclusive to `command`|
+
+Also, when alerts are executed, they will be passed through Go's format function with arguments for some attributes of the Monitor. The following monitor specific variables can be referenced using Go formatting syntax:
+
+|token|value|
+|---|---|
+|`{{.AlertCount}}`|Number of times this monitor has alerted|
+|`{{.FailureCount}}`|The total number of sequential failed checks for this monitor|
+|`{{.LastCheckOutput}}`|The last returned value from the check command to either stderr or stdout|
+|`{{.LastSuccess}}`|The datetime of the last successful check as a go Time struct|
+|`{{.MonitorName}}`|The name of the monitor that failed and triggered the alert|
+|`{{.IsUp}}`|Indicates if the monitor that is alerting is up or not. Can be used in a conditional message template|
+
+To provide flexible formatting, the following non-standard functions are available in templates:
+
+|func|description|
+|---|---|
+|`ANSIC <Time>`|Formats provided time in ANSIC format|
+|`UnixDate <Time>`|Formats provided time in UnixDate format|
+|`RubyDate <Time>`|Formats provided time in RubyDate format|
+|`RFC822Z <Time>`|Formats provided time in RFC822Z format|
+|`RFC850 <Time>`|Formats provided time in RFC850 format|
+|`RFC1123 <Time>`|Formats provided time in RFC1123 format|
+|`RFC1123Z <Time>`|Formats provided time in RFC1123Z format|
+|`RFC3339 <Time>`|Formats provided time in RFC3339 format|
+|`RFC3339Nano <Time>`|Formats provided time in RFC3339Nano format|
+|`FormatTime <Time> <string template>`|Formats provided time according to provided template|
+|`InTZ <Time> <string timezone name>`|Converts provided time to parsed timezone from the provided name|
+
+For more information, check out the [Go documentation for the time module](https://pkg.go.dev/time@go1.20.7#pkg-constants).
+
+#### Running alerts on startup
+
+It's not the best feeling to find out your alerts are broken when you're expecting to be alerted about another failure. To avoid this and provide early insight into broken alerts, it is possible to specify a list of alerts to run when Minitor starts up. This can be done using the command line flag `-startup-alerts`. This flag accepts a comma separated list of strings and will run a test of each of those alerts. Minitor will then respond as it typically does for any failed alert. This can be used to allow you time to correct when initially launching, and to allow schedulers to more easily detect a failed deployment of Minitor.
+
+Eg.
+
+```bash
+minitor -startup-alerts=log_down,log_up -config ./config.hcl
+```
+
+### Metrics
+
+Minitor supports exporting metrics for [Prometheus](https://prometheus.io/). Prometheus is an open source tool for reading and querying metrics from different sources. Combined with another tool, [Grafana](https://grafana.com/), it allows building of charts and dashboards. You could also opt to just use Minitor to log check results, and instead do your alerting with Grafana.
+
+It is also possible to use the metrics endpoint for monitoring Minitor itself! This allows setting up multiple instances of Minitor on different servers and have them monitor each-other so that you can detect a minitor outage.
+
+To run minitor with metrics, use the `-metrics` flag. The metrics will be served on port `8080` by default, though it can be overriden using `-metrics-port`. They will be accessible on the path `/metrics`. Eg. `localhost:8080/metrics`.
+
+```bash
+minitor -metrics
+# or
+minitor -metrics -metrics-port 3000
+```
+
+## Migrating from v1 to v2
+
+Minitor v2 introduces some breaking changes from v1. The most notable changes are:
+  - The configuration file is now in HCL format instead of YAML.
+  - The the Python formatting backwards compatability is removed.
+  - The Command and ShellCommand fields are now mutually exclusive.
+  - The check_interval is now strictly a duration string value. Eg. "30s" rather than `30`.
+  - Default alert_every is now -1 (exponential backoff) rather than 0 (no re-alerting).
+
+For the configuration, a confic that looked like this in v1:
+
+```yaml
+check_interval: 60
+
+monitors:
+  - name: example
+    command: "false"
+    alert_down: ["log"]
+
+alerts:
+  log:
+    command: ["echo", "Minitor up={{.IsUp}} for {{.MonitorName}}"]
+```
+
+Would now look like this in v2:
+
+```hcl
+check_interval = "1m"
+
+monitor "example" {
+  # example showing string to shell command migration
+  shell_command = "false"
+  alert_down = ["log"]
+  check_interval = "1m"
+}
+
+alert "log" {
+  # example showing list to exec command migration
+  command = ["echo", "Minitor up={{.IsUp}} for {{.MonitorName}}"]
+}
+```
+
+## Contributing
+
+Whether you're looking to submit a patch or tell me I broke something, you can contribute through the Github mirror and I can merge PRs back to the source repository.
+
+Primary Repo: https://git.iamthefij.com/iamthefij/minitor.git
+
+Github Mirror: https://github.com/IamTheFij/minitor.git

alert.go

@@ -2,72 +2,120 @@ package main
 
 import (
 	"bytes"
+	"errors"
 	"fmt"
-	"log"
 	"os/exec"
-	"strings"
 	"text/template"
 	"time"
+
+	"git.iamthefij.com/iamthefij/slog"
+)
+
+var (
+	errNoTemplate = errors.New("no template")
+
+	// ErrAlertFailed indicates that an alert failed to send
+	ErrAlertFailed = errors.New("alert failed")
 )
 
 // Alert is a config driven mechanism for sending a notice
 type Alert struct {
-	Name                 string
+	Name                 string   `hcl:"name,label"`
-	Command              CommandOrShell
+	Command              []string `hcl:"command,optional"`
+	ShellCommand         string   `hcl:"shell_command,optional"`
 	commandTemplate      []*template.Template
 	commandShellTemplate *template.Template
 }
 
 // AlertNotice captures the context for an alert to be sent
 type AlertNotice struct {
-	MonitorName     string
+	AlertCount      int
-	AlertCount      int16
+	FailureCount    int
-	FailureCount    int16
-	LastCheckOutput string
-	LastSuccess     time.Time
 	IsUp            bool
+	LastSuccess     time.Time
+	MonitorName     string
+	LastCheckOutput string
 }
 
-// IsValid returns a boolean indicating if the Alert has been correctly
+// Validate checks that the Alert is properly configured and returns errors if not
-// configured
+func (alert Alert) Validate() error {
-func (alert Alert) IsValid() bool {
+	hasCommand := len(alert.Command) > 0
-	return !alert.Command.Empty()
+	hasShellCommand := alert.ShellCommand != ""
+
+	var err error
+
+	hasAtLeastOneCommand := hasCommand || hasShellCommand
+	if !hasAtLeastOneCommand {
+		err = errors.Join(err, fmt.Errorf(
+			"%w: alert %s has no command or shell_command configured",
+			ErrInvalidAlert,
+			alert.Name,
+		))
+	}
+
+	hasAtMostOneCommand := !(hasCommand && hasShellCommand)
+	if !hasAtMostOneCommand {
+		err = errors.Join(err, fmt.Errorf(
+			"%w: alert %s has both command and shell_command configured",
+			ErrInvalidAlert,
+			alert.Name,
+		))
+	}
+
+	return err
 }
 
 // BuildTemplates compiles command templates for the Alert
 func (alert *Alert) BuildTemplates() error {
-	// TODO: Remove legacy template support later after 1.0
+	slog.Debugf("Building template for alert %s", alert.Name)
-	legacy := strings.NewReplacer(
+
-		"{alert_count}", "{{.AlertCount}}",
+	// Time format func factory
-		"{alert_message}", "{{.MonitorName}} check has failed {{.FailureCount}} times",
+	tff := func(formatString string) func(time.Time) string {
-		"{failure_count}", "{{.FailureCount}}",
+		return func(t time.Time) string {
-		"{last_output}", "{{.LastCheckOutput}}",
+			return t.Format(formatString)
-		"{last_success}", "{{.LastSuccess}}",
-		"{monitor_name}", "{{.MonitorName}}",
-	)
-	if LogDebug {
-		log.Printf("DEBUG: Building template for alert %s", alert.Name)
 		}
-	if alert.commandTemplate == nil && alert.Command.Command != nil {
+	}
+
+	// Create some functions for formatting datetimes in popular formats
+	timeFormatFuncs := template.FuncMap{
+		"ANSIC":       tff(time.ANSIC),
+		"UnixDate":    tff(time.UnixDate),
+		"RubyDate":    tff(time.RubyDate),
+		"RFC822Z":     tff(time.RFC822Z),
+		"RFC850":      tff(time.RFC850),
+		"RFC1123":     tff(time.RFC1123),
+		"RFC1123Z":    tff(time.RFC1123Z),
+		"RFC3339":     tff(time.RFC3339),
+		"RFC3339Nano": tff(time.RFC3339Nano),
+		"FormatTime": func(t time.Time, timeFormat string) string {
+			return t.Format(timeFormat)
+		},
+		"InTZ": func(t time.Time, tzName string) (time.Time, error) {
+			tz, err := time.LoadLocation(tzName)
+			if err != nil {
+				return t, fmt.Errorf("failed to convert time to specified tz: %w", err)
+			}
+
+			return t.In(tz), nil
+		},
+	}
+
+	switch {
+	case alert.Command != nil:
 		alert.commandTemplate = []*template.Template{}
-		for i, cmdPart := range alert.Command.Command {
+		for i, cmdPart := range alert.Command {
-			if PyCompat {
-				cmdPart = legacy.Replace(cmdPart)
-			}
 			alert.commandTemplate = append(alert.commandTemplate, template.Must(
-				template.New(alert.Name+string(i)).Parse(cmdPart),
+				template.New(alert.Name+fmt.Sprint(i)).Funcs(timeFormatFuncs).Parse(cmdPart),
 			))
 		}
-	} else if alert.commandShellTemplate == nil && alert.Command.ShellCommand != "" {
+	case alert.ShellCommand != "":
-		shellCmd := alert.Command.ShellCommand
+		shellCmd := alert.ShellCommand
-		if PyCompat {
+
-			shellCmd = legacy.Replace(shellCmd)
-		}
 		alert.commandShellTemplate = template.Must(
-			template.New(alert.Name).Parse(shellCmd),
+			template.New(alert.Name).Funcs(timeFormatFuncs).Parse(shellCmd),
 		)
-	} else {
+	default:
-		return fmt.Errorf("No template provided for alert %s", alert.Name)
+		return fmt.Errorf("No template provided for alert %s: %w", alert.Name, errNoTemplate)
 	}
 
 	return nil
@@ -75,30 +123,40 @@ func (alert *Alert) BuildTemplates() error {
 
 // Send will send an alert notice by executing the command template
 func (alert Alert) Send(notice AlertNotice) (outputStr string, err error) {
-	log.Printf("INFO: Sending alert %s for %s", alert.Name, notice.MonitorName)
+	slog.Infof("Sending alert %s for %s", alert.Name, notice.MonitorName)
+
 	var cmd *exec.Cmd
-	if alert.commandTemplate != nil {
+
+	switch {
+	case alert.commandTemplate != nil:
 		command := []string{}
+
 		for _, cmdTmp := range alert.commandTemplate {
 			var commandBuffer bytes.Buffer
+
 			err = cmdTmp.Execute(&commandBuffer, notice)
 			if err != nil {
 				return
 			}
+
 			command = append(command, commandBuffer.String())
 		}
+
 		cmd = exec.Command(command[0], command[1:]...)
-	} else if alert.commandShellTemplate != nil {
+	case alert.commandShellTemplate != nil:
 		var commandBuffer bytes.Buffer
+
 		err = alert.commandShellTemplate.Execute(&commandBuffer, notice)
 		if err != nil {
 			return
 		}
+
 		shellCommand := commandBuffer.String()
 
 		cmd = ShellCommand(shellCommand)
-	} else {
+	default:
-		err = fmt.Errorf("No templates compiled for alert %v", alert.Name)
+		err = fmt.Errorf("No templates compiled for alert %s: %w", alert.Name, errNoTemplate)
+
 		return
 	}
 
@@ -110,22 +168,16 @@ func (alert Alert) Send(notice AlertNotice) (outputStr string, err error) {
 	var output []byte
 	output, err = cmd.CombinedOutput()
 	outputStr = string(output)
-	if LogDebug {
+	slog.Debugf("Alert output for: %s\n---\n%s\n---", alert.Name, outputStr)
-		log.Printf("DEBUG: Alert output for: %s\n---\n%s\n---", alert.Name, outputStr)
+
+	if err != nil {
+		err = fmt.Errorf(
+			"Alert %s failed to send. Returned %w: %w",
+			alert.Name,
+			err,
+			ErrAlertFailed,
+		)
 	}
 
 	return outputStr, err
 }
-
-// NewLogAlert creates an alert that does basic logging using echo
-func NewLogAlert() *Alert {
-	return &Alert{
-		Name: "log",
-		Command: CommandOrShell{
-			Command: []string{
-				"echo",
-				"{{.MonitorName}} check has failed {{.FailureCount}} times",
-			},
-		},
-	}
-}

alert_test.go

@@ -1,133 +1,140 @@
-package main
+package main_test
 
 import (
-	"log"
+	"errors"
 	"testing"
+
+	m "git.iamthefij.com/iamthefij/minitor-go/v2"
 )
 
-func TestAlertIsValid(t *testing.T) {
+func TestAlertValidate(t *testing.T) {
+	t.Parallel()
+
 	cases := []struct {
-		alert    Alert
+		alert    m.Alert
-		expected bool
+		expected error
 		name     string
 	}{
-		{Alert{Command: CommandOrShell{Command: []string{"echo", "test"}}}, true, "Command only"},
+		{m.Alert{Command: []string{"echo", "test"}}, nil, "Command only"},
-		{Alert{Command: CommandOrShell{ShellCommand: "echo test"}}, true, "CommandShell only"},
+		{m.Alert{ShellCommand: "echo test"}, nil, "CommandShell only"},
-		{Alert{}, false, "No commands"},
+		{m.Alert{Command: []string{"echo", "test"}, ShellCommand: "echo test"}, m.ErrInvalidAlert, "Both commands"},
+		{m.Alert{}, m.ErrInvalidAlert, "No commands"},
 	}
 
 	for _, c := range cases {
-		log.Printf("Testing case %s", c.name)
+		c := c
-		actual := c.alert.IsValid()
+
-		if actual != c.expected {
+		t.Run(c.name, func(t *testing.T) {
-			t.Errorf("IsValid(%v), expected=%t actual=%t", c.name, c.expected, actual)
+			t.Parallel()
-			log.Printf("Case failed: %s", c.name)
+
+			actual := c.alert.Validate()
+			hasErr := (actual != nil)
+			expectErr := (c.expected != nil)
+
+			if hasErr != expectErr || !errors.Is(actual, c.expected) {
+				t.Errorf("expected=%t actual=%t", c.expected, actual)
 			}
-		log.Println("-----")
+		})
 	}
 }
 
 func TestAlertSend(t *testing.T) {
 	cases := []struct {
-		alert          Alert
+		alert          m.Alert
-		notice         AlertNotice
+		notice         m.AlertNotice
 		expectedOutput string
 		expectErr      bool
 		name           string
-		pyCompat       bool
 	}{
 		{
-			Alert{Command: CommandOrShell{Command: []string{"echo", "{{.MonitorName}}"}}},
+			m.Alert{Command: []string{"echo", "{{.MonitorName}}"}},
-			AlertNotice{MonitorName: "test"},
+			m.AlertNotice{MonitorName: "test"},
 			"test\n",
 			false,
 			"Command with template",
-			false,
 		},
 		{
-			Alert{Command: CommandOrShell{ShellCommand: "echo {{.MonitorName}}"}},
+			m.Alert{ShellCommand: "echo {{.MonitorName}}"},
-			AlertNotice{MonitorName: "test"},
+			m.AlertNotice{MonitorName: "test"},
 			"test\n",
 			false,
 			"Command shell with template",
-			false,
 		},
 		{
-			Alert{Command: CommandOrShell{Command: []string{"echo", "{{.Bad}}"}}},
+			m.Alert{Command: []string{"echo", "{{.Bad}}"}},
-			AlertNotice{MonitorName: "test"},
+			m.AlertNotice{MonitorName: "test"},
 			"",
 			true,
 			"Command with bad template",
-			false,
 		},
 		{
-			Alert{Command: CommandOrShell{ShellCommand: "echo {{.Bad}}"}},
+			m.Alert{ShellCommand: "echo {{.Bad}}"},
-			AlertNotice{MonitorName: "test"},
+			m.AlertNotice{MonitorName: "test"},
 			"",
 			true,
 			"Command shell with bad template",
-			false,
-		},
-		{
-			Alert{Command: CommandOrShell{ShellCommand: "echo {alert_message}"}},
-			AlertNotice{MonitorName: "test", FailureCount: 1},
-			"test check has failed 1 times\n",
-			false,
-			"Command shell with legacy template",
-			true,
 		},
 	}
 
 	for _, c := range cases {
-		log.Printf("Testing case %s", c.name)
+		c := c
-		// Set PyCompat to value of compat flag
+
-		PyCompat = c.pyCompat
+		t.Run(c.name, func(t *testing.T) {
-		c.alert.BuildTemplates()
+			t.Parallel()
+
+			err := c.alert.BuildTemplates()
+			if err != nil {
+				t.Errorf("Send(%v output), error building templates: %v", c.name, err)
+			}
+
 			output, err := c.alert.Send(c.notice)
 			hasErr := (err != nil)
+
 			if output != c.expectedOutput {
 				t.Errorf("Send(%v output), expected=%v actual=%v", c.name, c.expectedOutput, output)
-			log.Printf("Case failed: %s", c.name)
 			}
+
 			if hasErr != c.expectErr {
 				t.Errorf("Send(%v err), expected=%v actual=%v", c.name, "Err", err)
-			log.Printf("Case failed: %s", c.name)
 			}
-		// Set PyCompat back to default value
+		})
-		PyCompat = false
-		log.Println("-----")
 	}
 }
 
 func TestAlertSendNoTemplates(t *testing.T) {
-	alert := Alert{}
+	alert := m.Alert{}
-	notice := AlertNotice{}
+	notice := m.AlertNotice{}
+
 	output, err := alert.Send(notice)
 	if err == nil {
 		t.Errorf("Send(no template), expected=%v actual=%v", "Err", output)
 	}
-	log.Println("-----")
 }
 
 func TestAlertBuildTemplate(t *testing.T) {
 	cases := []struct {
-		alert     Alert
+		alert     m.Alert
 		expectErr bool
 		name      string
 	}{
-		{Alert{Command: CommandOrShell{Command: []string{"echo", "test"}}}, false, "Command only"},
+		{m.Alert{Command: []string{"echo", "test"}}, false, "Command only"},
-		{Alert{Command: CommandOrShell{ShellCommand: "echo test"}}, false, "CommandShell only"},
+		{m.Alert{ShellCommand: "echo test"}, false, "CommandShell only"},
-		{Alert{}, true, "No commands"},
+		{m.Alert{}, true, "No commands"},
 	}
 
 	for _, c := range cases {
-		log.Printf("Testing case %s", c.name)
+		c := c
+
+		t.Run(c.name, func(t *testing.T) {
+			t.Parallel()
+
 			err := c.alert.BuildTemplates()
 			hasErr := (err != nil)
+
 			if hasErr != c.expectErr {
 				t.Errorf("IsValid(%v), expected=%t actual=%t", c.name, c.expectErr, err)
-			log.Printf("Case failed: %s", c.name)
 			}
-		log.Println("-----")
+
+		})
 	}
 }

config.go

@@ -2,98 +2,126 @@ package main
 
 import (
 	"errors"
-	"io/ioutil"
+	"fmt"
-	"log"
+	"time"
 
-	"gopkg.in/yaml.v2"
+	"git.iamthefij.com/iamthefij/slog"
+	"github.com/hashicorp/hcl/v2/hclsimple"
+)
+
+var (
+	ErrLoadingConfig  = errors.New("Failed to load or parse configuration")
+	ErrConfigInit     = errors.New("Failed to initialize configuration")
+	ErrInvalidConfig  = errors.New("Invalid configuration")
+	ErrNoAlerts       = errors.New("No alerts provided")
+	ErrInvalidAlert   = errors.New("Invalid alert configuration")
+	ErrNoMonitors     = errors.New("No monitors provided")
+	ErrInvalidMonitor = errors.New("Invalid monitor configuration")
+	ErrUnknownAlert   = errors.New("Unknown alert")
 )
 
 // Config type is contains all provided user configuration
 type Config struct {
-	CheckInterval int64 `yaml:"check_interval"`
+	CheckIntervalStr string `hcl:"check_interval"`
-	Monitors      []*Monitor
+	CheckInterval    time.Duration
-	Alerts        map[string]*Alert
-}
 
-// CommandOrShell type wraps a string or list of strings
+	DefaultAlertAfter int        `hcl:"default_alert_after,optional"`
-// for executing a command directly or in a shell
+	DefaultAlertEvery *int       `hcl:"default_alert_every,optional"`
-type CommandOrShell struct {
+	DefaultAlertDown  []string   `hcl:"default_alert_down,optional"`
-	ShellCommand string
+	DefaultAlertUp    []string   `hcl:"default_alert_up,optional"`
-	Command      []string
+	Monitors          []*Monitor `hcl:"monitor,block"`
-}
+	Alerts            []*Alert   `hcl:"alert,block"`
 
-// Empty checks if the Command has a value
+	alertLookup map[string]*Alert
-func (cos CommandOrShell) Empty() bool {
-	return (cos.ShellCommand == "" && cos.Command == nil)
-}
-
-// UnmarshalYAML allows unmarshalling either a string or slice of strings
-// and parsing them as either a command or a shell command.
-func (cos *CommandOrShell) UnmarshalYAML(unmarshal func(interface{}) error) error {
-	var cmd []string
-	err := unmarshal(&cmd)
-	// Error indicates this is shell command
-	if err != nil {
-		var shellCmd string
-		err := unmarshal(&shellCmd)
-		if err != nil {
-			return err
-		}
-		cos.ShellCommand = shellCmd
-	} else {
-		cos.Command = cmd
-	}
-	return nil
-}
-
-// IsValid checks config validity and returns true if valid
-func (config Config) IsValid() (isValid bool) {
-	isValid = true
-
-	// Validate alerts
-	if config.Alerts == nil || len(config.Alerts) == 0 {
-		// This should never happen because there is a default alert named 'log' for now
-		log.Printf("ERROR: Invalid alert configuration: Must provide at least one alert")
-		isValid = false
-	}
-	for _, alert := range config.Alerts {
-		if !alert.IsValid() {
-			log.Printf("ERROR: Invalid alert configuration: %s", alert.Name)
-			isValid = false
-		}
-	}
-
-	// Validate monitors
-	if config.Monitors == nil || len(config.Monitors) == 0 {
-		log.Printf("ERROR: Invalid monitor configuration: Must provide at least one monitor")
-		isValid = false
-	}
-	for _, monitor := range config.Monitors {
-		if !monitor.IsValid() {
-			log.Printf("ERROR: Invalid monitor configuration: %s", monitor.Name)
-			isValid = false
-		}
-		// Check that all Monitor alerts actually exist
-		for _, isUp := range []bool{true, false} {
-			for _, alertName := range monitor.GetAlertNames(isUp) {
-				if _, ok := config.Alerts[alertName]; !ok {
-					log.Printf(
-						"ERROR: Invalid monitor configuration: %s. Unknown alert %s",
-						monitor.Name, alertName,
-					)
-					isValid = false
-				}
-			}
-		}
-	}
-
-	return
 }
 
 // Init performs extra initialization on top of loading the config from file
 func (config *Config) Init() (err error) {
-	for name, alert := range config.Alerts {
+	config.CheckInterval, err = time.ParseDuration(config.CheckIntervalStr)
-		alert.Name = name
+	if err != nil {
+		return fmt.Errorf("failed to parse top level check_interval duration: %w", err)
+	}
+
+	if config.DefaultAlertAfter == 0 {
+		minAlertAfter := 1
+		config.DefaultAlertAfter = minAlertAfter
+	}
+
+	if config.DefaultAlertEvery == nil {
+		defaultDefaultAlertEvery := -1
+		config.DefaultAlertEvery = &defaultDefaultAlertEvery
+	}
+
+	for _, monitor := range config.Monitors {
+		if err = monitor.Init(
+			config.DefaultAlertAfter,
+			config.DefaultAlertEvery,
+			config.DefaultAlertDown,
+			config.DefaultAlertUp,
+		); err != nil {
+			return
+		}
+	}
+
+	err = config.BuildAllTemplates()
+
+	return
+}
+
+// IsValid checks config validity and returns true if valid
+func (config Config) IsValid() error {
+	var err error
+
+	// Validate alerts
+	if len(config.Alerts) == 0 {
+		err = errors.Join(err, ErrNoAlerts)
+	}
+
+	for _, alert := range config.Alerts {
+		err = errors.Join(err, alert.Validate())
+	}
+
+	// Validate monitors
+	if len(config.Monitors) == 0 {
+		err = errors.Join(err, ErrNoMonitors)
+	}
+
+	for _, monitor := range config.Monitors {
+		err = errors.Join(err, monitor.Validate())
+
+		// Check that all Monitor alerts actually exist
+		for _, isUp := range []bool{true, false} {
+			for _, alertName := range monitor.GetAlertNames(isUp) {
+				if _, ok := config.GetAlert(alertName); !ok {
+					err = errors.Join(
+						err,
+						fmt.Errorf("%w: %s. %w: %s", ErrInvalidMonitor, monitor.Name, ErrUnknownAlert, alertName),
+					)
+				}
+			}
+		}
+	}
+
+	return err
+}
+
+// GetAlert returns an alert by name
+func (c Config) GetAlert(name string) (*Alert, bool) {
+	if c.alertLookup == nil {
+		c.alertLookup = map[string]*Alert{}
+		for _, alert := range c.Alerts {
+			c.alertLookup[alert.Name] = alert
+		}
+	}
+
+	v, ok := c.alertLookup[name]
+
+	return v, ok
+}
+
+// BuildAllTemplates builds all alert templates
+func (c *Config) BuildAllTemplates() (err error) {
+	for _, alert := range c.Alerts {
 		if err = alert.BuildTemplates(); err != nil {
 			return
 		}
@@ -103,39 +131,23 @@ func (config *Config) Init() (err error) {
 }
 
 // LoadConfig will read config from the given path and parse it
-func LoadConfig(filePath string) (config Config, err error) {
+func LoadConfig(filePath string) (Config, error) {
-	data, err := ioutil.ReadFile(filePath)
+	var config Config
-	if err != nil {
+
-		return
+	if err := hclsimple.DecodeFile(filePath, nil, &config); err != nil {
+		return config, errors.Join(ErrLoadingConfig, err)
 	}
 
-	err = yaml.Unmarshal(data, &config)
+	slog.Debugf("Config values:\n%v\n", config)
-	if err != nil {
-		return
-	}
-
-	if LogDebug {
-		log.Printf("DEBUG: Config values:\n%v\n", config)
-	}
-
-	// Add log alert if not present
-	if PyCompat {
-		// Intialize alerts list if not present
-		if config.Alerts == nil {
-			config.Alerts = map[string]*Alert{}
-		}
-		if _, ok := config.Alerts["log"]; !ok {
-			config.Alerts["log"] = NewLogAlert()
-		}
-	}
-
-	if !config.IsValid() {
-		err = errors.New("Invalid configuration")
-		return
-	}
 
 	// Finish initializing configuration
-	err = config.Init()
+	if err := config.Init(); err != nil {
-
+		return config, errors.Join(ErrConfigInit, err)
-	return
+	}
+
+	if err := config.IsValid(); err != nil {
+		return config, errors.Join(ErrInvalidConfig, err)
+	}
+
+	return config, nil
 }

config_test.go

@@ -1,103 +1,193 @@
-package main
+package main_test
 
 import (
-	"log"
+	"errors"
 	"testing"
+	"time"
+
+	m "git.iamthefij.com/iamthefij/minitor-go/v2"
 )
 
 func TestLoadConfig(t *testing.T) {
 	cases := []struct {
 		configPath  string
-		expectErr  bool
+		expectedErr error
 		name        string
-		pyCompat   bool
 	}{
-		{"./test/valid-config.yml", false, "Valid config file", false},
+		{"./test/does-not-exist", m.ErrLoadingConfig, "Invalid config path"},
-		{"./test/valid-default-log-alert.yml", false, "Valid config file with default log alert PyCompat", true},
+		{"./test/invalid-config-wrong-hcl-type.hcl", m.ErrLoadingConfig, "Incorrect HCL type"},
-		{"./test/valid-default-log-alert.yml", true, "Invalid config file no log alert", false},
+		{"./test/invalid-config-missing-alerts.hcl", m.ErrNoAlerts, "Invalid config missing alerts"},
-		{"./test/does-not-exist", true, "Invalid config path", false},
+		{"./test/invalid-config-missing-alerts.hcl", m.ErrInvalidConfig, "Invalid config general"},
-		{"./test/invalid-config-type.yml", true, "Invalid config type for key", false},
+		{"./test/invalid-config-invalid-duration.hcl", m.ErrConfigInit, "Invalid config type for key"},
-		{"./test/invalid-config-missing-alerts.yml", true, "Invalid config missing alerts", false},
+		{"./test/invalid-config-unknown-alert.hcl", m.ErrUnknownAlert, "Invalid config unknown alert"},
-		{"./test/invalid-config-unknown-alert.yml", true, "Invalid config unknown alert", false},
+		{"./test/valid-config-default-values.hcl", nil, "Valid config file with default values"},
+		{"./test/valid-config.hcl", nil, "Valid config file"},
+	}
+	for _, c := range cases {
+		c := c
+
+		t.Run(c.name, func(t *testing.T) {
+			t.Parallel()
+
+			_, err := m.LoadConfig(c.configPath)
+			hasErr := (err != nil)
+			expectErr := (c.expectedErr != nil)
+
+			if hasErr != expectErr || !errors.Is(err, c.expectedErr) {
+				t.Errorf("LoadConfig(%v), expected_error=%v actual=%v", c.name, c.expectedErr, err)
+			}
+		})
+	}
+}
+
+func TestDefaultConfig(t *testing.T) {
+	cases := []struct {
+		configPath     string
+		expectedResult m.Config
+		name           string
+	}{
+		{
+			"./test/valid-config-default-values.hcl",
+			m.Config{
+				CheckInterval:     1 * time.Second,
+				DefaultAlertAfter: 2,
+				DefaultAlertEvery: Ptr(0),
+				DefaultAlertDown:  []string{"log_command"},
+			},
+			"override defaults",
+		},
+		{
+			"./test/valid-config.hcl",
+			m.Config{
+				CheckInterval:     30 * time.Second,
+				DefaultAlertAfter: 1,
+				DefaultAlertEvery: Ptr(-1),
+				DefaultAlertDown:  []string{},
+			},
+			"default defaults",
+		},
 	}
 
 	for _, c := range cases {
-		log.Printf("Testing case %s", c.name)
+		c := c
-		// Set PyCompat based on compatibility mode
+
-		PyCompat = c.pyCompat
+		t.Run(c.name, func(t *testing.T) {
-		_, err := LoadConfig(c.configPath)
+			t.Parallel()
-		hasErr := (err != nil)
+
-		if hasErr != c.expectErr {
+			config, err := m.LoadConfig(c.configPath)
-			t.Errorf("LoadConfig(%v), expected_error=%v actual=%v", c.name, c.expectErr, err)
+			if err != nil {
-			log.Printf("Case failed: %s", c.name)
+				t.Errorf("Got error when loading config file %q: %s", c.configPath, err)
 			}
-		// Set PyCompat to default value
+
-		PyCompat = false
+			// Test Config has default values
-		log.Println("-----")
+			if config.DefaultAlertAfter != c.expectedResult.DefaultAlertAfter {
+				t.Errorf("Got unexpected DefaultAlertAfter from file %q: expected=%v actual=%v", c.configPath, c.expectedResult.DefaultAlertAfter, config.DefaultAlertAfter)
+			}
+
+			if *config.DefaultAlertEvery != *c.expectedResult.DefaultAlertEvery {
+				t.Errorf("Got unexpected DefaultAlertEvery from file %q: expected=%v actual=%v", c.configPath, *c.expectedResult.DefaultAlertEvery, *config.DefaultAlertEvery)
+			}
+
+			if !m.EqualSliceString(config.DefaultAlertUp, c.expectedResult.DefaultAlertUp) {
+				t.Errorf("Got unexpected DefaultAlertUp from file %q: expected=%v actual=%v", c.configPath, c.expectedResult.DefaultAlertUp, config.DefaultAlertUp)
+			}
+
+			if !m.EqualSliceString(config.DefaultAlertDown, c.expectedResult.DefaultAlertDown) {
+				t.Errorf("Got unexpected DefaultAlertDown from file %q: expected=%v actual=%v", c.configPath, c.expectedResult.DefaultAlertDown, config.DefaultAlertDown)
+			}
+
+			// Check that monitor defaults propagate
+			var defaultMonitor *m.Monitor
+			for _, monitor := range config.Monitors {
+				if monitor.Name == "Default" {
+					defaultMonitor = monitor
+				}
+			}
+
+			if defaultMonitor == nil {
+				t.Errorf("failed to find default monitor in %q", c.configPath)
+			}
+
+			if defaultMonitor.AlertAfter != c.expectedResult.DefaultAlertAfter {
+				t.Errorf("Got unexpected AlertAfter from file %q: expected=%v actual=%v", c.configPath, c.expectedResult.DefaultAlertAfter, defaultMonitor.AlertAfter)
+			}
+
+			if *defaultMonitor.AlertEvery != *c.expectedResult.DefaultAlertEvery {
+				t.Errorf("Got unexpected AlertEvery from file %q: expected=%v actual=%v", c.configPath, *c.expectedResult.DefaultAlertEvery, *defaultMonitor.AlertEvery)
+			}
+
+			if !m.EqualSliceString(defaultMonitor.AlertUp, c.expectedResult.DefaultAlertUp) {
+				t.Errorf("Got unexpected AlertUp from file %q: expected=%v actual=%v", c.configPath, c.expectedResult.DefaultAlertUp, defaultMonitor.AlertUp)
+			}
+
+			// NOTE: Can't compare AlertDown because default is empty and that is invalid
+		})
 	}
 }
 
 // TestMultiLineConfig is a more complicated test stepping through the parsing
 // and execution of mutli-line strings presented in YAML
 func TestMultiLineConfig(t *testing.T) {
-	log.Println("Testing multi-line string config")
+	t.Parallel()
-	config, err := LoadConfig("./test/valid-verify-multi-line.yml")
+
+	config, err := m.LoadConfig("./test/valid-verify-multi-line.hcl")
 	if err != nil {
 		t.Fatalf("TestMultiLineConfig(load), expected=no_error actual=%v", err)
 	}
 
-	log.Println("-----")
+	t.Run("Test Monitor with Indented Multi-Line String", func(t *testing.T) {
-	log.Println("TestMultiLineConfig(parse > string)")
+		// Verify indented heredoc is as expected
-	expected := "echo 'Some string with stuff'; echo \"<angle brackets>\"; exit 1\n"
+		expected := "echo 'Some string with stuff'\necho \"<angle brackets>\"\nexit 1\n"
-	actual := config.Monitors[0].Command.ShellCommand
+		actual := config.Monitors[0].ShellCommand
+
 		if expected != actual {
-		t.Errorf("TestMultiLineConfig(>) failed")
+			t.Error("Heredoc mismatch")
-		t.Logf("string expected=`%v`", expected)
+			t.Errorf("string expected=`%v`", expected)
-		t.Logf("string actual  =`%v`", actual)
+			t.Errorf("string actual  =`%v`", actual)
-		t.Logf("bytes expected=%v", []byte(expected))
-		t.Logf("bytes actual  =%v", []byte(actual))
 		}
 
-	log.Println("-----")
+		// Run the monitor and verify the output
-	log.Println("TestMultiLineConfig(execute > string)")
 		_, notice := config.Monitors[0].Check()
 		if notice == nil {
-		t.Fatalf("Did not receive an alert notice")
+			t.Fatal("Did not receive an alert notice and should have")
 		}
+
+		// Verify the output of the monitor is as expected
 		expected = "Some string with stuff\n<angle brackets>\n"
 		actual = notice.LastCheckOutput
+
 		if expected != actual {
-		t.Errorf("TestMultiLineConfig(execute > string) check failed")
+			t.Error("Output mismatch")
-		t.Logf("string expected=`%v`", expected)
+			t.Errorf("string expected=`%v`", expected)
-		t.Logf("string actual  =`%v`", actual)
+			t.Errorf("string actual  =`%v`", actual)
-		t.Logf("bytes expected=%v", []byte(expected))
+		}
-		t.Logf("bytes actual  =%v", []byte(actual))
+	})
+
+	t.Run("Test Alert with Multi-Line String", func(t *testing.T) {
+		alert, ok := config.GetAlert("log_shell")
+		if !ok {
+			t.Fatal("Could not find expected alert 'log_shell'")
 		}
 
-	log.Println("-----")
+		expected := "    echo 'Some string with stuff'\n    echo '<angle brackets>'\n"
-	log.Println("TestMultiLineConfig(parse | string)")
+		actual := alert.ShellCommand
-	expected = "echo 'Some string with stuff'\necho '<angle brackets>'\n"
+
-	actual = config.Alerts["log_shell"].Command.ShellCommand
 		if expected != actual {
-		t.Errorf("TestMultiLineConfig(|) failed")
+			t.Error("Heredoc mismatch")
-		t.Logf("string expected=`%v`", expected)
+			t.Errorf("string expected=`%v`", expected)
-		t.Logf("string actual  =`%v`", actual)
+			t.Errorf("string actual  =`%v`", actual)
-		t.Logf("bytes expected=%v", []byte(expected))
-		t.Logf("bytes actual  =%v", []byte(actual))
 		}
 
-	log.Println("-----")
+		actual, err = alert.Send(m.AlertNotice{})
-	log.Println("TestMultiLineConfig(execute | string)")
-	actual, err = config.Alerts["log_shell"].Send(AlertNotice{})
 		if err != nil {
-		t.Errorf("Execution of alert failed")
+			t.Fatal("Execution of alert failed")
 		}
+
 		expected = "Some string with stuff\n<angle brackets>\n"
 		if expected != actual {
-		t.Errorf("TestMultiLineConfig(execute | string) check failed")
+			t.Error("Output mismatch")
-		t.Logf("string expected=`%v`", expected)
+			t.Errorf("string expected=`%v`", expected)
-		t.Logf("string actual  =`%v`", actual)
+			t.Errorf("string actual  =`%v`", actual)
-		t.Logf("bytes expected=%v", []byte(expected))
-		t.Logf("bytes actual  =%v", []byte(actual))
 		}
+	})
 }

default_config.hcl

@@ -0,0 +1,29 @@
+check_interval = "1s"
+
+monitor "mdstat_raid" {
+  command = [
+    "sh",
+    "-c",
+    "grep -q '\\[U_\\|_U\\]' /host_proc/mdstat && exit 1 || exit 0"
+  ]
+  check_interval = "30s"
+  alert_after = 1
+  alert_every = 0
+
+  alert_down = ["email_alert"]
+  alert_up   = ["email_recovery"]
+}
+alert "email_alert" {
+  command = [
+      "sh",
+          "-c",
+            "EMAIL=$EMAIL_RECIPIENT; printf 'Subject: RAID ALERT\nTo: %s\n\nRAID degraded\n' \"$EMAIL\" | /usr/local/bin/sendmail -t || true"
+                ]
+}
+alert "email_recovery" {
+  command = [
+      "sh",
+          "-c",
+              "EMAIL=$EMAIL_RECIPIENT; printf 'Subject: RAID ALERT\nTo: %s\n\nRAID clean\n' \"$EMAIL\" | /usr/local/bin/sendmail -t || true"
+                ]
+}

go.mod

@@ -1,8 +1,27 @@
-module git.iamthefij.com/iamthefij/minitor-go
+module git.iamthefij.com/iamthefij/minitor-go/v2
 
-go 1.12
+go 1.25.0
 
 require (
-	github.com/prometheus/client_golang v1.2.1
+	git.iamthefij.com/iamthefij/slog v1.3.0
-	gopkg.in/yaml.v2 v2.2.4
+	github.com/hashicorp/hcl/v2 v2.11.1
+	github.com/prometheus/client_golang v1.23.2
+)
+
+require (
+	github.com/agext/levenshtein v1.2.1 // indirect
+	github.com/apparentlymart/go-textseg/v13 v13.0.0 // indirect
+	github.com/beorn7/perks v1.0.1 // indirect
+	github.com/cespare/xxhash/v2 v2.3.0 // indirect
+	github.com/google/go-cmp v0.7.0 // indirect
+	github.com/mitchellh/go-wordwrap v0.0.0-20150314170334-ad45545899c7 // indirect
+	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
+	github.com/prometheus/client_model v0.6.2 // indirect
+	github.com/prometheus/common v0.66.1 // indirect
+	github.com/prometheus/procfs v0.16.1 // indirect
+	github.com/zclconf/go-cty v1.8.0 // indirect
+	go.yaml.in/yaml/v2 v2.4.2 // indirect
+	golang.org/x/sys v0.35.0 // indirect
+	golang.org/x/text v0.28.0 // indirect
+	google.golang.org/protobuf v1.36.8 // indirect
 )

go.sum

@@ -1,78 +1,96 @@
-github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
+git.iamthefij.com/iamthefij/slog v1.3.0 h1:4Hu5PQvDrW5e3FrTS3q2iIXW0iPvhNY/9qJsqDR3K3I=
-github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
+git.iamthefij.com/iamthefij/slog v1.3.0/go.mod h1:1RUj4hcCompZkAxXCRfUX786tb3cM/Zpkn97dGfUfbg=
-github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
+github.com/agext/levenshtein v1.2.1 h1:QmvMAjj2aEICytGiWzmxoE0x2KZvE0fvmqMOfy2tjT8=
-github.com/alecthomas/units v0.0.0-20190717042225-c3de453c63f4/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
+github.com/agext/levenshtein v1.2.1/go.mod h1:JEDfjyjHDjOF/1e4FlBE/PkbqA9OfWu2ki2W0IB5558=
-github.com/beorn7/perks v0.0.0-20180321164747-3a771d992973/go.mod h1:Dwedo/Wpr24TaqPxmxbtue+5NUziq4I4S80YR8gNf3Q=
+github.com/apparentlymart/go-dump v0.0.0-20180507223929-23540a00eaa3/go.mod h1:oL81AME2rN47vu18xqj1S1jPIPuN7afo62yKTNn3XMM=
-github.com/beorn7/perks v1.0.0/go.mod h1:KWe93zE9D1o94FZ5RNwFwVgaQK1VOXiVxmqh+CedLV8=
+github.com/apparentlymart/go-textseg v1.0.0/go.mod h1:z96Txxhf3xSFMPmb5X/1W05FF/Nj9VFpLOpjS5yuumk=
+github.com/apparentlymart/go-textseg/v13 v13.0.0 h1:Y+KvPE1NYz0xl601PVImeQfFyEy6iT90AvPUL1NNfNw=
+github.com/apparentlymart/go-textseg/v13 v13.0.0/go.mod h1:ZK2fH7c4NqDTLtiYLvIkEghdlcqw7yxLeM89kiTRPUo=
 github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
 github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
-github.com/cespare/xxhash/v2 v2.1.0 h1:yTUvW7Vhb89inJ+8irsUqiWjh8iT6sQPZiQzI6ReGkA=
+github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
-github.com/cespare/xxhash/v2 v2.1.0/go.mod h1:dgIUBU3pDso/gPgZ1osOZ0iQf77oPR28Tjxl5dIMyVM=
+github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
-github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/go-kit/kit v0.8.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
+github.com/go-test/deep v1.0.3 h1:ZrJSEWsXzPOxaZnFteGEfooLba+ju3FYIbOrS+rQd68=
-github.com/go-kit/kit v0.9.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
+github.com/go-test/deep v1.0.3/go.mod h1:wGDj63lr65AM2AQyKZd/NYHGb0R+1RLqB8NKt3aSFNA=
-github.com/go-logfmt/logfmt v0.3.0/go.mod h1:Qt1PoO58o5twSAckw1HlFXLmHsOX5/0LbT9GBnD5lWE=
+github.com/golang/protobuf v1.1.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
-github.com/go-logfmt/logfmt v0.4.0/go.mod h1:3RMwSq7FuexP4Kalkev3ejPJsZTpXXBr9+V4qmtdjCk=
-github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY=
-github.com/gogo/protobuf v1.1.1/go.mod h1:r8qH/GZQm5c6nD/R0oafs1akxWv10x8SbQlK7atdtwQ=
-github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
 github.com/golang/protobuf v1.3.1/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
-github.com/golang/protobuf v1.3.2 h1:6nsPYzhq5kReh6QImI3k5qWzO4PEbvbIW2cwSfR/6xs=
+github.com/golang/protobuf v1.3.4/go.mod h1:vzj43D7+SQXF/4pzW/hwtAqwc6iTitCiVSaWz5lYuqw=
-github.com/golang/protobuf v1.3.2/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
+github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
-github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
+github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
-github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
+github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
-github.com/json-iterator/go v1.1.6/go.mod h1:+SdeFBvtyEkXs7REEP0seUULqWtbJapLOCVDaaPEHmU=
+github.com/hashicorp/hcl/v2 v2.11.1 h1:yTyWcXcm9XB0TEkyU/JCRU6rYy4K+mgLtzn2wlrJbcc=
-github.com/json-iterator/go v1.1.7/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
+github.com/hashicorp/hcl/v2 v2.11.1/go.mod h1:FwWsfWEjyV/CMj8s/gqAuiviY72rJ1/oayI9WftqcKg=
-github.com/julienschmidt/httprouter v1.2.0/go.mod h1:SYymIcj16QtmaHHD7aYtjjsJG7VTCxuUUipMqKk8s4w=
+github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo=
-github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
+github.com/klauspost/compress v1.18.0/go.mod h1:2Pp+KzxcywXVXMr50+X0Q/Lsb43OQHYWRCY2AiWywWQ=
-github.com/kr/logfmt v0.0.0-20140226030751-b84e30acd515/go.mod h1:+0opPa2QZZtGFBFZlji/RkVcI2GknAs/DXo4wKdlNEc=
+github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
-github.com/matttproud/golang_protobuf_extensions v1.0.1 h1:4hp9jkHxhMHkqkrB3Ix0jegS5sx/RkqARlsWZ6pIwiU=
+github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
-github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
+github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
-github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
+github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
-github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
+github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
-github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
+github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
-github.com/modern-go/reflect2 v1.0.1/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
+github.com/kylelemons/godebug v0.0.0-20170820004349-d65d576e9348/go.mod h1:B69LEHPfb2qLo0BaaOLcbitczOKLWTsrBG9LczfCD4k=
-github.com/mwitkow/go-conntrack v0.0.0-20161129095857-cc309e4a2223/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
+github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
-github.com/pkg/errors v0.8.0/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
+github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
-github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
+github.com/mitchellh/go-wordwrap v0.0.0-20150314170334-ad45545899c7 h1:DpOJ2HYzCv8LZP15IdmG+YdwD2luVPHITV96TkirNBM=
+github.com/mitchellh/go-wordwrap v0.0.0-20150314170334-ad45545899c7/go.mod h1:ZXFpozHsX6DPmq2I0TCekCxypsnAUbP2oI0UX1GXzOo=
+github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
+github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
-github.com/prometheus/client_golang v0.9.1/go.mod h1:7SWBe2y4D6OKWSNQJUaRYU/AaXPKyh/dDVn+NZz0KFw=
+github.com/prometheus/client_golang v1.23.2 h1:Je96obch5RDVy3FDMndoUsjAhG5Edi49h0RJWRi/o0o=
-github.com/prometheus/client_golang v1.0.0/go.mod h1:db9x61etRT2tGnBNRi70OPL5FsnadC4Ky3P0J6CfImo=
+github.com/prometheus/client_golang v1.23.2/go.mod h1:Tb1a6LWHB3/SPIzCoaDXI4I8UHKeFTEQ1YCr+0Gyqmg=
-github.com/prometheus/client_golang v1.2.1 h1:JnMpQc6ppsNgw9QPAGF6Dod479itz7lvlsMzzNayLOI=
+github.com/prometheus/client_model v0.6.2 h1:oBsgwpGs7iVziMvrGhE53c/GrLUsZdHnqNwqPLxwZyk=
-github.com/prometheus/client_golang v1.2.1/go.mod h1:XMU6Z2MjaRKVu/dC1qupJI9SiNkDYzz3xecMgSW/F+U=
+github.com/prometheus/client_model v0.6.2/go.mod h1:y3m2F6Gdpfy6Ut/GBsUqTWZqCUvMVzSfMLjcu6wAwpE=
-github.com/prometheus/client_model v0.0.0-20180712105110-5c3871d89910/go.mod h1:MbSGuTsp3dbXC40dX6PRTWyKYBIrTGTE9sqQNg2J8bo=
+github.com/prometheus/common v0.66.1 h1:h5E0h5/Y8niHc5DlaLlWLArTQI7tMrsfQjHV+d9ZoGs=
-github.com/prometheus/client_model v0.0.0-20190129233127-fd36f4220a90/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
+github.com/prometheus/common v0.66.1/go.mod h1:gcaUsgf3KfRSwHY4dIMXLPV0K/Wg1oZ8+SbZk/HH/dA=
-github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4 h1:gQz4mCbXsO+nc9n1hCxHcGA3Zx3Eo+UHZoInFGUIXNM=
+github.com/prometheus/procfs v0.16.1 h1:hZ15bTNuirocR6u0JZ6BAHHmwS1p8B4P6MRqxtzMyRg=
-github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
+github.com/prometheus/procfs v0.16.1/go.mod h1:teAbpZRB1iIAJYREa1LsoWUXykVXA1KlTmWl8x/U+Is=
-github.com/prometheus/common v0.4.1/go.mod h1:TNfzLD0ON7rHzMJeJkieUDPYmFC7Snx/y86RQel1bk4=
+github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
-github.com/prometheus/common v0.7.0 h1:L+1lyG48J1zAQXA3RBX/nG/B3gjlHq0zTt2tlbJLyCY=
+github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
-github.com/prometheus/common v0.7.0/go.mod h1:DjGbpBbp5NYNiECxcL/VnbXCCaQpKd3tt26CguLLsqA=
+github.com/sergi/go-diff v1.0.0 h1:Kpca3qRNrduNnOQeazBd0ysaKrUJiIuISHxogkT9RPQ=
-github.com/prometheus/procfs v0.0.0-20181005140218-185b4288413d/go.mod h1:c3At6R/oaqEKCNdg8wHV1ftS6bRYblBhIjjI8uT2IGk=
+github.com/sergi/go-diff v1.0.0/go.mod h1:0CfEIISq7TuYL3j771MWULgwwjU+GofnZX9QAmXWZgo=
-github.com/prometheus/procfs v0.0.2/go.mod h1:TjEm7ze935MbeOT/UhFTIMYKhuLP4wbCsTZCD3I8kEA=
+github.com/spf13/pflag v1.0.2/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4=
-github.com/prometheus/procfs v0.0.5 h1:3+auTFlqw+ZaQYJARz6ArODtkaIwtvBTx3N2NehQlL8=
-github.com/prometheus/procfs v0.0.5/go.mod h1:4A/X28fw3Fc593LaREMrKMqOKvUAntwMDaekg4FpcdQ=
-github.com/sirupsen/logrus v1.2.0/go.mod h1:LxeOpSwHxABJmUn/MG1IvRgCAasNZTLOkJPxbbu5VWo=
-github.com/sirupsen/logrus v1.4.2/go.mod h1:tLMulIdttU9McNUspp0xgXVQah82FyeX6MwdIuYE2rE=
-github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
-github.com/stretchr/objx v0.1.1/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
-github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
+github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
-golang.org/x/crypto v0.0.0-20180904163835-0709b304e793/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
+github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
+github.com/vmihailenco/msgpack v3.3.3+incompatible/go.mod h1:fy3FlTQTDXWkZ7Bh6AcGMlsjHatGryHQYUTf1ShIgkk=
+github.com/vmihailenco/msgpack/v4 v4.3.12/go.mod h1:gborTTJjAo/GWTqqRjrLCn9pgNN+NXzzngzBKDPIqw4=
+github.com/vmihailenco/tagparser v0.1.1/go.mod h1:OeAg3pn3UbLjkWt+rN9oFYB6u/cQgqMEUPoW2WPyhdI=
+github.com/zclconf/go-cty v1.2.0/go.mod h1:hOPWgoHbaTUnI5k4D2ld+GRpFJSCe6bCM7m1q/N4PQ8=
+github.com/zclconf/go-cty v1.8.0 h1:s4AvqaeQzJIu3ndv4gVIhplVD0krU+bgrcLSVUnaWuA=
+github.com/zclconf/go-cty v1.8.0/go.mod h1:vVKLxnk3puL4qRAv72AO+W99LUD4da90g3uUAzyuvAk=
+github.com/zclconf/go-cty-debug v0.0.0-20191215020915-b22d67c1ba0b/go.mod h1:ZRKQfBXbGkpdV6QMzT3rU1kSTAnfu1dO8dPKjYprgj8=
+go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
+go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
+go.yaml.in/yaml/v2 v2.4.2 h1:DzmwEr2rDGHl7lsFgAHxmNz/1NlQ7xLIrlN2h5d1eGI=
+go.yaml.in/yaml/v2 v2.4.2/go.mod h1:081UH+NErpNdqlCXm3TtEran0rJZGxAYx9hb/ELlsPU=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
-golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/crypto v0.0.0-20190426145343-a29dc8fdc734/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
-golang.org/x/net v0.0.0-20190613194153-d28f0bde5980/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20180811021610-c39426892332/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
-golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
-golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/net v0.0.0-20190603091049-60506f45cf65/go.mod h1:HSz+uSET+XFnRR8LxR5pz3Of3rY3CfYBVs4xY44aLks=
-golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/net v0.0.0-20200301022130-244492dfa37a/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
-golang.org/x/sys v0.0.0-20181116152217-5ac8a444bdc5/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
-golang.org/x/sys v0.0.0-20190422165155-953cdadca894/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20191010194322-b09406accb47/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190502175342-a43fa875dd82/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.35.0 h1:vz1N37gP5bs89s7He8XuIYXpyY0+QlsKmzipCbUtyxI=
+golang.org/x/sys v0.35.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
-gopkg.in/alecthomas/kingpin.v2 v2.2.6/go.mod h1:FMv+mEhP44yOT+4EoQTLFTRgOQ1FBLkstjWtayDeSgw=
+golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
+golang.org/x/text v0.3.5/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.28.0 h1:rhazDwis8INMIwQ4tpjLDzUhx6RlXqZNPEM0huQojng=
+golang.org/x/text v0.28.0/go.mod h1:U8nCwOR8jO/marOQ0QbDiOngZVEBB7MAiitBuMjXiNU=
+golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM=
+google.golang.org/appengine v1.6.5/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=
+google.golang.org/protobuf v1.36.8 h1:xHScyCOEuuwZEc6UtSOvPbAT4zRh0xcNRYekJwfqyMc=
+google.golang.org/protobuf v1.36.8/go.mod h1:fuxRtAxBytpl4zzqUh6/eyUujkJdNiuEkXntxiD/uRU=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
-gopkg.in/yaml.v2 v2.2.1/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
-gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
-gopkg.in/yaml.v2 v2.2.4 h1:/eiJrUcujPVeJ3xlSWaiNi3uSVmDGBK1pDHUHAnao1I=
+gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
-gopkg.in/yaml.v2 v2.2.4/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

main.go

@@ -1,16 +1,16 @@
 package main
 
 import (
+	"errors"
 	"flag"
 	"fmt"
-	"log"
+	"strings"
 	"time"
+
+	"git.iamthefij.com/iamthefij/slog"
 )
 
 var (
-	// LogDebug will control whether debug messsages should be logged
-	LogDebug = false
-
 	// ExportMetrics will track whether or not we want to export metrics to prometheus
 	ExportMetrics = false
 	// MetricsPort is the port to expose metrics on
@@ -18,63 +18,70 @@ var (
 	// Metrics contains all active metrics
 	Metrics = NewMetrics()
 
-	// PyCompat enables support for legacy Python templates
-	PyCompat = false
-
 	// version of minitor being run
 	version = "dev"
+
+	errUnknownAlert = errors.New("unknown alert")
 )
 
-func checkMonitors(config *Config) error {
+func SendAlerts(config *Config, monitor *Monitor, alertNotice *AlertNotice) error {
-	for _, monitor := range config.Monitors {
+	slog.Debugf("Received an alert notice from %s", alertNotice.MonitorName)
-		if monitor.ShouldCheck() {
-			success, alertNotice := monitor.Check()
-
-			hasAlert := alertNotice != nil
-
-			// Track status metrics
-			Metrics.SetMonitorStatus(monitor.Name, success)
-			Metrics.CountCheck(monitor.Name, success, hasAlert)
-
-			// Should probably consider refactoring everything below here
-			if alertNotice != nil {
-				if LogDebug {
-					log.Printf("DEBUG: Recieved an alert notice from %s", alertNotice.MonitorName)
-				}
 	alertNames := monitor.GetAlertNames(alertNotice.IsUp)
+
 	if alertNames == nil {
 		// This should only happen for a recovery alert. AlertDown is validated not empty
-					log.Printf(
+		slog.Warningf(
-						"WARNING: Recieved alert, but no alert mechanisms exist. MonitorName=%s IsUp=%t",
+			"Received alert, but no alert mechanisms exist. MonitorName=%s IsUp=%t",
 			alertNotice.MonitorName, alertNotice.IsUp,
 		)
+
+		return nil
 	}
+
 	for _, alertName := range alertNames {
-					if alert, ok := config.Alerts[alertName]; ok {
+		if alert, ok := config.GetAlert(alertName); ok {
 			output, err := alert.Send(*alertNotice)
 			if err != nil {
-							log.Printf(
+				slog.Errorf(
-								"ERROR: Alert '%s' failed. result=%v: output=%s",
+					"Alert '%s' failed. result=%v: output=%s",
 					alert.Name,
 					err,
 					output,
 				)
-							return fmt.Errorf(
+
-								"Unsuccessfully triggered alert '%s'. "+
+				return err
-									"Crashing to avoid false negatives: %v",
-								alert.Name,
-								err,
-							)
 			}
 
 			// Count alert metrics
 			Metrics.CountAlert(monitor.Name, alert.Name)
 		} else {
 			// This case should never actually happen since we validate against it
-						log.Printf("ERROR: Unknown alert for monitor %s: %s", alertNotice.MonitorName, alertName)
+			slog.Errorf("Unknown alert for monitor %s: %s", alertNotice.MonitorName, alertName)
-						return fmt.Errorf("Unknown alert for monitor %s: %s", alertNotice.MonitorName, alertName)
+
+			return fmt.Errorf("unknown alert for monitor %s: %s: %w", alertNotice.MonitorName, alertName, errUnknownAlert)
 		}
 	}
+
+	return nil
+}
+
+func CheckMonitors(config *Config) error {
+	// TODO: Run this in goroutines and capture exceptions
+	for _, monitor := range config.Monitors {
+		if monitor.ShouldCheck() {
+			success, alertNotice := monitor.Check()
+			hasAlert := alertNotice != nil
+
+			// Track status metrics
+			Metrics.SetMonitorStatus(monitor.Name, monitor.IsUp())
+			Metrics.CountCheck(monitor.Name, success, monitor.LastCheckMilliseconds(), hasAlert)
+
+			if alertNotice != nil {
+				err := SendAlerts(config, monitor, alertNotice)
+				// If there was an error in sending an alert, exit early and bubble it up
+				if err != nil {
+					return err
+				}
 			}
 		}
 	}
@@ -82,41 +89,75 @@ func checkMonitors(config *Config) error {
 	return nil
 }
 
+func SendStartupAlerts(config *Config, alertNames []string) error {
+	for _, alertName := range alertNames {
+		var err error
+
+		alert, ok := config.GetAlert(alertName)
+		if !ok {
+			err = fmt.Errorf("unknown alert %s: %w", alertName, errUnknownAlert)
+		}
+
+		if err == nil {
+			_, err = alert.Send(AlertNotice{
+				AlertCount:      0,
+				FailureCount:    0,
+				IsUp:            true,
+				LastSuccess:     time.Now(),
+				MonitorName:     fmt.Sprintf("First Run Alert Test: %s", alert.Name),
+				LastCheckOutput: "",
+			})
+		}
+
+		if err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
 func main() {
-	// Get debug flag
+	showVersion := flag.Bool("version", false, "Display the version of minitor and exit")
-	flag.BoolVar(&LogDebug, "debug", false, "Enables debug logs (default: false)")
+	configPath := flag.String("config", "config.hcl", "Alternate configuration path (default: config.hcl)")
+	startupAlerts := flag.String("startup-alerts", "", "List of alerts to run on startup. This can help determine unhealthy alerts early on. (default \"\")")
+
+	flag.BoolVar(&slog.DebugLevel, "debug", false, "Enables debug logs (default: false)")
 	flag.BoolVar(&ExportMetrics, "metrics", false, "Enables prometheus metrics exporting (default: false)")
-	flag.BoolVar(&PyCompat, "py-compat", false, "Enables support for legacy Python Minitor config. Will eventually be removed. (default: false)")
+	flag.IntVar(&MetricsPort, "metrics-port", MetricsPort, "The port that Prometheus metrics should be exported on, if enabled. (default: 8080)")
-	var showVersion = flag.Bool("version", false, "Display the version of minitor and exit")
-	var configPath = flag.String("config", "config.yml", "Alternate configuration path (default: config.yml)")
 	flag.Parse()
 
 	// Print version if flag is provided
 	if *showVersion {
-		log.Println("Minitor version:", version)
+		fmt.Println("Minitor version:", version)
+
 		return
 	}
 
 	// Load configuration
 	config, err := LoadConfig(*configPath)
-	if err != nil {
+	slog.OnErrFatalf(err, "Error loading config")
-		log.Fatalf("Error loading config: %v", err)
-	}
 
 	// Serve metrics exporter, if specified
 	if ExportMetrics {
-		log.Println("INFO: Exporting metrics to Prometheus")
+		slog.Infof("Exporting metrics to Prometheus on port %d", MetricsPort)
+
 		go ServeMetrics()
 	}
 
+	if *startupAlerts != "" {
+		alertNames := strings.Split(*startupAlerts, ",")
+
+		err = SendStartupAlerts(&config, alertNames)
+
+		slog.OnErrPanicf(err, "Error running startup alerts")
+	}
+
 	// Start main loop
 	for {
-		err = checkMonitors(&config)
+		err = CheckMonitors(&config)
-		if err != nil {
+		slog.OnErrPanicf(err, "Error checking monitors")
-			panic(err)
-		}
 
-		sleepTime := time.Duration(config.CheckInterval) * time.Second
+		time.Sleep(config.CheckInterval)
-		time.Sleep(sleepTime)
 	}
 }

main_test.go

@@ -1,114 +1,192 @@
-package main
+package main_test
 
-import "testing"
+import (
+	"testing"
 
+	m "git.iamthefij.com/iamthefij/minitor-go/v2"
+)
+
+func Ptr[T any](v T) *T {
+	return &v
+}
+
+// TestCheckConfig tests the checkConfig function
+// It also tests results for potentially invalid configuration. For example, no alerts
 func TestCheckMonitors(t *testing.T) {
 	cases := []struct {
-		config    Config
+		config             m.Config
-		expectErr bool
+		expectFailureError bool
+		expectRecoverError bool
 		name               string
 	}{
 		{
-			config:    Config{},
+			config: m.Config{
-			expectErr: false,
+				CheckIntervalStr: "1s",
-			name:      "Empty",
+				Monitors: []*m.Monitor{
-		},
 					{
-			config: Config{
-				Monitors: []*Monitor{
-					&Monitor{
 						Name: "Success",
-						Command: CommandOrShell{Command: []string{"true"}},
 					},
 				},
 			},
-			expectErr: false,
+			expectFailureError: false,
-			name:      "Monitor success, no alerts",
+			expectRecoverError: false,
+			name:               "No alerts",
 		},
 		{
-			config: Config{
+			config: m.Config{
-				Monitors: []*Monitor{
+				CheckIntervalStr: "1s",
-					&Monitor{
+				Monitors: []*m.Monitor{
+					{
 						Name:       "Failure",
-						Command:    CommandOrShell{Command: []string{"false"}},
-						AlertAfter: 1,
-					},
-					&Monitor{
-						Name:       "Failure",
-						Command:    CommandOrShell{Command: []string{"false"}},
 						AlertDown:  []string{"unknown"},
-						AlertAfter: 1,
-					},
-				},
-			},
-			expectErr: false,
-			name:      "Monitor failure, no and unknown alerts",
-		},
-		{
-			config: Config{
-				Monitors: []*Monitor{
-					&Monitor{
-						Name:       "Success",
-						Command:    CommandOrShell{Command: []string{"ls"}},
-						alertCount: 1,
-					},
-					&Monitor{
-						Name:       "Success",
-						Command:    CommandOrShell{Command: []string{"true"}},
 						AlertUp:    []string{"unknown"},
-						alertCount: 1,
+						AlertAfter: 1,
 					},
 				},
 			},
-			expectErr: false,
+			expectFailureError: true,
-			name:      "Monitor recovery, no alerts",
+			expectRecoverError: true,
+			name:               "Unknown alerts",
 		},
 		{
-			config: Config{
+			config: m.Config{
-				Monitors: []*Monitor{
+				CheckIntervalStr: "1s",
-					&Monitor{
+				Monitors: []*m.Monitor{
+					{
 						Name:       "Failure",
-						Command:    CommandOrShell{Command: []string{"false"}},
 						AlertDown:  []string{"good"},
+						AlertUp:    []string{"good"},
 						AlertAfter: 1,
 					},
 				},
-				Alerts: map[string]*Alert{
+				Alerts: []*m.Alert{{
-					"good": &Alert{
+					Name:    "good",
-						Command: CommandOrShell{Command: []string{"true"}},
+					Command: []string{"true"},
+				}},
 			},
-				},
+			expectFailureError: false,
-			},
+			expectRecoverError: false,
-			expectErr: false,
+			name:               "Successful alert",
-			name:      "Monitor failure, successful alert",
 		},
 		{
-			config: Config{
+			config: m.Config{
-				Monitors: []*Monitor{
+				CheckIntervalStr: "1s",
-					&Monitor{
+				Monitors: []*m.Monitor{
+					{
 						Name:       "Failure",
-						Command:    CommandOrShell{Command: []string{"false"}},
 						AlertDown:  []string{"bad"},
+						AlertUp:    []string{"bad"},
 						AlertAfter: 1,
 					},
 				},
-				Alerts: map[string]*Alert{
+				Alerts: []*m.Alert{{
-					"bad": &Alert{
 					Name:    "bad",
-						Command: CommandOrShell{Command: []string{"false"}},
+					Command: []string{"false"},
+				}},
 			},
-				},
+			expectFailureError: true,
-			},
+			expectRecoverError: true,
-			expectErr: true,
+			name:               "Failing alert",
-			name:      "Monitor failure, bad alert",
 		},
 	}
 
 	for _, c := range cases {
-		c.config.Init()
+		c := c
-		err := checkMonitors(&c.config)
+
+		t.Run(c.name, func(t *testing.T) {
+			t.Parallel()
+
+			err := c.config.Init()
+			if err != nil {
+				t.Errorf("checkMonitors(%s): unexpected error reading config: %v", c.name, err)
+			}
+
+			for _, check := range []struct {
+				shellCmd  string
+				name      string
+				expectErr bool
+			}{
+				{"false", "Failure", c.expectFailureError}, {"true", "Success", c.expectRecoverError},
+			} {
+				// Set the shell command for this check
+				c.config.Monitors[0].ShellCommand = check.shellCmd
+
+				// Run the check
+				err = m.CheckMonitors(&c.config)
+
+				// Check the results
+				if err == nil && check.expectErr {
+					t.Errorf("checkMonitors(%s:%s): Expected error, the code did not error", c.name, check.name)
+				} else if err != nil && !check.expectErr {
+					t.Errorf("checkMonitors(%s:%s): Did not expect an error, but we got one anyway: %v", c.name, check.name, err)
+				}
+			}
+		})
+	}
+}
+
+func TestFirstRunAlerts(t *testing.T) {
+	cases := []struct {
+		config        m.Config
+		expectErr     bool
+		startupAlerts []string
+		name          string
+	}{
+		{
+			config: m.Config{
+				CheckIntervalStr: "1s",
+			},
+			expectErr:     true,
+			startupAlerts: []string{"missing"},
+			name:          "Unknown",
+		},
+		{
+			config: m.Config{
+				CheckIntervalStr: "1s",
+				Alerts: []*m.Alert{
+					{
+						Name:    "good",
+						Command: []string{"true"},
+					},
+				},
+			},
+			expectErr:     false,
+			startupAlerts: []string{"good"},
+			name:          "Successful alert",
+		},
+		{
+			config: m.Config{
+				CheckIntervalStr: "1s",
+				Alerts: []*m.Alert{
+					{
+						Name:    "bad",
+						Command: []string{"false"},
+					},
+				},
+			},
+			expectErr:     true,
+			startupAlerts: []string{"bad"},
+			name:          "Failed alert",
+		},
+	}
+
+	for _, c := range cases {
+		c := c
+
+		t.Run(c.name, func(t *testing.T) {
+			t.Parallel()
+
+			err := c.config.Init()
+			if err != nil {
+				t.Errorf("sendFirstRunAlerts(%s): unexpected error reading config: %v", c.name, err)
+			}
+
+			err = m.SendStartupAlerts(&c.config, c.startupAlerts)
 			if err == nil && c.expectErr {
-			t.Errorf("checkMonitors(%s): Expected panic, the code did not panic", c.name)
+				t.Errorf("sendFirstRunAlerts(%s): Expected error, the code did not error", c.name)
-		}
+			} else if err != nil && !c.expectErr {
+				t.Errorf("sendFirstRunAlerts(%s): Did not expect an error, but we got one anyway: %v", c.name, err)
+			}
+		})
 	}
 }

manifest.tmpl

@@ -1,25 +0,0 @@
-image: iamthefij/minitor-go:{{#if build.tag}}{{trimPrefix "v" build.tag}}{{else}}latest{{/if}}
-{{#if build.tags}}
-tags:
-{{#each build.tags}}
-  - {{this}}
-{{/each}}
-{{/if}}
-manifests:
-  -
-    image: iamthefij/minitor-go:{{#if build.tag}}{{trimPrefix "v" build.tag}}-{{/if}}linux-amd64
-    platform:
-      architecture: amd64
-      os: linux
-  -
-    image: iamthefij/minitor-go:{{#if build.tag}}{{trimPrefix "v" build.tag}}-{{/if}}linux-arm64
-    platform:
-      architecture: arm64
-      os: linux
-      variant: v8
-  -
-    image: iamthefij/minitor-go:{{#if build.tag}}{{trimPrefix "v" build.tag}}-{{/if}}linux-arm
-    platform:
-      architecture: arm
-      os: linux
-      variant: v7

metrics.go

@@ -19,6 +19,7 @@ import (
 type MinitorMetrics struct {
 	alertCount    *prometheus.CounterVec
 	checkCount    *prometheus.CounterVec
+	checkTime     *prometheus.GaugeVec
 	monitorStatus *prometheus.GaugeVec
 }
 
@@ -40,6 +41,13 @@ func NewMetrics() *MinitorMetrics {
 			},
 			[]string{"monitor", "status", "is_alert"},
 		),
+		checkTime: prometheus.NewGaugeVec(
+			prometheus.GaugeOpts{
+				Name: "minitor_check_milliseconds",
+				Help: "Time in miliseconds that a check ran for",
+			},
+			[]string{"monitor", "status"},
+		),
 		monitorStatus: prometheus.NewGaugeVec(
 			prometheus.GaugeOpts{
 				Name: "minitor_monitor_up_count",
@@ -52,6 +60,7 @@ func NewMetrics() *MinitorMetrics {
 	// Register newly created metrics
 	prometheus.MustRegister(metrics.alertCount)
 	prometheus.MustRegister(metrics.checkCount)
+	prometheus.MustRegister(metrics.checkTime)
 	prometheus.MustRegister(metrics.monitorStatus)
 
 	return metrics
@@ -63,11 +72,12 @@ func (metrics *MinitorMetrics) SetMonitorStatus(monitor string, isUp bool) {
 	if isUp {
 		val = 1.0
 	}
+
 	metrics.monitorStatus.With(prometheus.Labels{"monitor": monitor}).Set(val)
 }
 
 // CountCheck counts the result of a particular Monitor check
-func (metrics *MinitorMetrics) CountCheck(monitor string, isSuccess bool, isAlert bool) {
+func (metrics *MinitorMetrics) CountCheck(monitor string, isSuccess bool, ms int64, isAlert bool) {
 	status := "failure"
 	if isSuccess {
 		status = "success"
@@ -81,6 +91,10 @@ func (metrics *MinitorMetrics) CountCheck(monitor string, isSuccess bool, isAler
 	metrics.checkCount.With(
 		prometheus.Labels{"monitor": monitor, "status": status, "is_alert": alertVal},
 	).Inc()
+
+	metrics.checkTime.With(
+		prometheus.Labels{"monitor": monitor, "status": status},
+	).Set(float64(ms))
 }
 
 // CountAlert counts an alert
@@ -96,6 +110,8 @@ func (metrics *MinitorMetrics) CountAlert(monitor string, alert string) {
 // ServeMetrics starts an http server with a Prometheus metrics handler
 func ServeMetrics() {
 	http.Handle("/metrics", promhttp.Handler())
+
 	host := fmt.Sprintf(":%d", MetricsPort)
+
 	_ = http.ListenAndServe(host, nil)
 }

monitor.go

@@ -1,82 +1,164 @@
 package main
 
 import (
-	"log"
+	"errors"
+	"fmt"
 	"math"
 	"os/exec"
 	"time"
+
+	"git.iamthefij.com/iamthefij/slog"
 )
 
 // Monitor represents a particular periodic check of a command
-type Monitor struct {
+type Monitor struct { //nolint:maligned
 	// Config values
-	Name          string
+	CheckIntervalStr *string `hcl:"check_interval,optional"`
-	Command       CommandOrShell
+	CheckInterval    time.Duration
-	AlertDown     []string `yaml:"alert_down"`
+
-	AlertUp       []string `yaml:"alert_up"`
+	Name         string `hcl:"name,label"`
-	CheckInterval float64  `yaml:"check_interval"`
+	AlertCount   int
-	AlertAfter    int16    `yaml:"alert_after"`
+	AlertAfter   int      `hcl:"alert_after,optional"`
-	AlertEvery    int16    `yaml:"alert_every"`
+	AlertEvery   *int     `hcl:"alert_every,optional"`
+	AlertDown    []string `hcl:"alert_down,optional"`
+	AlertUp      []string `hcl:"alert_up,optional"`
+	Command      []string `hcl:"command,optional"`
+	ShellCommand string   `hcl:"shell_command,optional"`
+
 	// Other values
+	failureCount      int
 	lastCheck         time.Time
-	lastOutput   string
-	alertCount   int16
-	failureCount int16
 	lastSuccess       time.Time
+	lastOutput        string
+	lastCheckDuration time.Duration
 }
 
-// IsValid returns a boolean indicating if the Monitor has been correctly
+// Init initializes the Monitor with default values
-// configured
+func (monitor *Monitor) Init(defaultAlertAfter int, defaultAlertEvery *int, defaultAlertDown []string, defaultAlertUp []string) error {
-func (monitor Monitor) IsValid() bool {
+	// Parse the check_interval string into a time.Duration
-	return (!monitor.Command.Empty() &&
+	if monitor.CheckIntervalStr != nil {
-		monitor.getAlertAfter() > 0 &&
+		var err error
-		monitor.AlertDown != nil)
+
+		monitor.CheckInterval, err = time.ParseDuration(*monitor.CheckIntervalStr)
+		if err != nil {
+			return fmt.Errorf("failed to parse check_interval duration for monitor %s: %w", monitor.Name, err)
+		}
 	}
 
-// ShouldCheck returns a boolean indicating if the Monitor is ready to be
+	// Set default values for monitor alerts
-// be checked again
+	if monitor.AlertAfter == 0 {
+		minAlertAfter := 1
+		monitor.AlertAfter = max(defaultAlertAfter, minAlertAfter)
+	}
+
+	if monitor.AlertEvery == nil {
+		monitor.AlertEvery = defaultAlertEvery
+	}
+
+	if len(monitor.AlertDown) == 0 {
+		monitor.AlertDown = defaultAlertDown
+	}
+
+	if len(monitor.AlertUp) == 0 {
+		monitor.AlertUp = defaultAlertUp
+	}
+
+	return nil
+}
+
+// Validate checks that the Monitor is properly configured and returns errors if not
+func (monitor Monitor) Validate() error {
+	hasCommand := len(monitor.Command) > 0
+	hasShellCommand := monitor.ShellCommand != ""
+	hasValidAlertAfter := monitor.AlertAfter > 0
+	hasAlertDown := len(monitor.AlertDown) > 0
+
+	var err error
+
+	hasAtLeastOneCommand := hasCommand || hasShellCommand
+	if !hasAtLeastOneCommand {
+		err = errors.Join(err, fmt.Errorf(
+			"%w: monitor %s has no command or shell_command configured",
+			ErrInvalidMonitor,
+			monitor.Name,
+		))
+	}
+
+	hasAtMostOneCommand := !(hasCommand && hasShellCommand)
+	if !hasAtMostOneCommand {
+		err = errors.Join(err, fmt.Errorf(
+			"%w: monitor %s has both command and shell_command configured",
+			ErrInvalidMonitor,
+			monitor.Name,
+		))
+	}
+
+	if !hasValidAlertAfter {
+		err = errors.Join(err, fmt.Errorf(
+			"%w: monitor %s has invalid alert_after value %d. Must be greater than 0",
+			ErrInvalidMonitor,
+			monitor.Name,
+			monitor.AlertAfter,
+		))
+	}
+
+	if !hasAlertDown {
+		err = errors.Join(err, fmt.Errorf(
+			"%w: monitor %s has no alert_down configured. Configure one here or add a default_alert_down",
+			ErrInvalidMonitor,
+			monitor.Name,
+		))
+	}
+
+	return err
+}
+
+func (monitor Monitor) LastOutput() string {
+	return monitor.lastOutput
+}
+
+// ShouldCheck returns a boolean indicating if the Monitor is ready to be be checked again
 func (monitor Monitor) ShouldCheck() bool {
-	if monitor.lastCheck.IsZero() {
+	if monitor.lastCheck.IsZero() || monitor.CheckInterval == 0 {
 		return true
 	}
 
-	sinceLastCheck := time.Now().Sub(monitor.lastCheck).Seconds()
+	sinceLastCheck := time.Since(monitor.lastCheck)
+
 	return sinceLastCheck >= monitor.CheckInterval
 }
 
-// Check will run the command configured by the Monitor and return a status
+// Check will run the command configured by the Monitor and return a status and a possible AlertNotice
-// and a possible AlertNotice
 func (monitor *Monitor) Check() (bool, *AlertNotice) {
 	var cmd *exec.Cmd
-	if monitor.Command.Command != nil {
+	if len(monitor.Command) > 0 {
-		cmd = exec.Command(monitor.Command.Command[0], monitor.Command.Command[1:]...)
+		cmd = exec.Command(monitor.Command[0], monitor.Command[1:]...)
+	} else if monitor.ShellCommand != "" {
+		cmd = ShellCommand(monitor.ShellCommand)
 	} else {
-		cmd = ShellCommand(monitor.Command.ShellCommand)
+		slog.Fatalf("Monitor %s has no command configured", monitor.Name)
 	}
 
+	checkStartTime := time.Now()
 	output, err := cmd.CombinedOutput()
 	monitor.lastCheck = time.Now()
 	monitor.lastOutput = string(output)
+	monitor.lastCheckDuration = monitor.lastCheck.Sub(checkStartTime)
 
 	var alertNotice *AlertNotice
+
 	isSuccess := (err == nil)
 	if isSuccess {
-		alertNotice = monitor.success()
+		alertNotice = monitor.Success()
 	} else {
-		alertNotice = monitor.failure()
+		alertNotice = monitor.Failure()
 	}
 
-	if LogDebug {
+	slog.Debugf("Command output: %s", monitor.lastOutput)
-		log.Printf("DEBUG: Command output: %s", monitor.lastOutput)
+	slog.OnErrWarnf(err, "Command result: %v", err)
-	}
-	if err != nil {
-		if LogDebug {
-			log.Printf("DEBUG: Command result: %v", err)
-		}
-	}
 
-	log.Printf(
+	slog.Infof(
-		"INFO: %s success=%t, alert=%t",
+		"%s success=%t, alert=%t",
 		monitor.Name,
 		isSuccess,
 		alertNotice != nil,
@@ -85,89 +167,89 @@ func (monitor *Monitor) Check() (bool, *AlertNotice) {
 	return isSuccess, alertNotice
 }
 
-func (monitor Monitor) isUp() bool {
+// GetAlertNames gives a list of alert names for a given monitor status
-	return monitor.alertCount == 0
+func (monitor Monitor) GetAlertNames(up bool) []string {
+	if up {
+		return monitor.AlertUp
 	}
 
-func (monitor *Monitor) success() (notice *AlertNotice) {
+	return monitor.AlertDown
-	if !monitor.isUp() {
+}
+
+// IsUp returns the status of the current monitor
+func (monitor Monitor) IsUp() bool {
+	return monitor.AlertCount == 0
+}
+
+// LastCheckMilliseconds gives number of miliseconds the last check ran for
+func (monitor Monitor) LastCheckMilliseconds() int64 {
+	return monitor.lastCheckDuration.Milliseconds()
+}
+
+func (monitor *Monitor) Success() (notice *AlertNotice) {
+	if !monitor.IsUp() {
 		// Alert that we have recovered
 		notice = monitor.createAlertNotice(true)
 	}
+
 	monitor.failureCount = 0
-	monitor.alertCount = 0
+	monitor.AlertCount = 0
 	monitor.lastSuccess = time.Now()
 
 	return
 }
 
-func (monitor *Monitor) failure() (notice *AlertNotice) {
+func (monitor *Monitor) Failure() (notice *AlertNotice) {
 	monitor.failureCount++
 	// If we haven't hit the minimum failures, we can exit
-	if monitor.failureCount < monitor.getAlertAfter() {
+	if monitor.failureCount < monitor.AlertAfter {
-		if LogDebug {
+		slog.Debugf(
-			log.Printf(
+			"%s failed but did not hit minimum failures. "+
-				"DEBUG: %s failed but did not hit minimum failures. "+
 				"Count: %v alert after: %v",
 			monitor.Name,
 			monitor.failureCount,
-				monitor.getAlertAfter(),
+			monitor.AlertAfter,
 		)
-		}
+
 		return
 	}
 
 	// Take number of failures after minimum
-	failureCount := (monitor.failureCount - monitor.getAlertAfter())
+	failureCount := (monitor.failureCount - monitor.AlertAfter)
 
 	// Use alert cadence to determine if we should alert
-	if monitor.AlertEvery > 0 {
+	switch {
-		// Handle integer number of failures before alerting
+	case monitor.AlertEvery == nil, *monitor.AlertEvery == 0:
-		if failureCount%monitor.AlertEvery == 0 {
-			notice = monitor.createAlertNotice(false)
-		}
-	} else if monitor.AlertEvery == 0 {
 		// Handle alerting on first failure only
 		if failureCount == 0 {
 			notice = monitor.createAlertNotice(false)
 		}
-	} else {
+	case *monitor.AlertEvery > 0:
+		// Handle integer number of failures before alerting
+		if failureCount%*monitor.AlertEvery == 0 {
+			notice = monitor.createAlertNotice(false)
+		}
+	default:
 		// Handle negative numbers indicating an exponential backoff
-		if failureCount >= int16(math.Pow(2, float64(monitor.alertCount))-1) {
+		if failureCount >= int(math.Pow(2, float64(monitor.AlertCount))-1) { //nolint:mnd
 			notice = monitor.createAlertNotice(false)
 		}
 	}
 
 	// If we're going to alert, increment count
 	if notice != nil {
-		monitor.alertCount++
+		monitor.AlertCount++
+		notice.AlertCount = monitor.AlertCount
 	}
 
-	return
+	return notice
-}
-
-func (monitor Monitor) getAlertAfter() int16 {
-	// TODO: Come up with a better way than this method
-	// Zero is one!
-	if monitor.AlertAfter == 0 {
-		return 1
-	}
-	return monitor.AlertAfter
-}
-
-// GetAlertNames gives a list of alert names for a given monitor status
-func (monitor Monitor) GetAlertNames(up bool) []string {
-	if up {
-		return monitor.AlertUp
-	}
-	return monitor.AlertDown
 }
 
 func (monitor Monitor) createAlertNotice(isUp bool) *AlertNotice {
 	// TODO: Maybe add something about recovery status here
 	return &AlertNotice{
 		MonitorName:     monitor.Name,
-		AlertCount:      monitor.alertCount,
+		AlertCount:      monitor.AlertCount,
 		FailureCount:    monitor.failureCount,
 		LastCheckOutput: monitor.lastOutput,
 		LastSuccess:     monitor.lastSuccess,

monitor_test.go

@@ -1,159 +1,196 @@
-package main
+package main_test
 
 import (
-	"log"
+	"errors"
+	"reflect"
 	"testing"
 	"time"
+
+	m "git.iamthefij.com/iamthefij/minitor-go/v2"
 )
 
-// TestMonitorIsValid tests the Monitor.IsValid()
+func TestMonitorValidate(t *testing.T) {
-func TestMonitorIsValid(t *testing.T) {
+	t.Parallel()
+
 	cases := []struct {
-		monitor  Monitor
+		monitor  m.Monitor
-		expected bool
+		expected error
 		name     string
 	}{
-		{Monitor{Command: CommandOrShell{Command: []string{"echo", "test"}}, AlertDown: []string{"log"}}, true, "Command only"},
+		{m.Monitor{AlertAfter: 1, Command: []string{"echo", "test"}, AlertDown: []string{"log"}}, nil, "Command only"},
-		{Monitor{Command: CommandOrShell{ShellCommand: "echo test"}, AlertDown: []string{"log"}}, true, "CommandShell only"},
+		{m.Monitor{AlertAfter: 1, ShellCommand: "echo test", AlertDown: []string{"log"}}, nil, "CommandShell only"},
-		{Monitor{Command: CommandOrShell{Command: []string{"echo", "test"}}}, false, "No AlertDown"},
+		{m.Monitor{AlertAfter: 1, Command: []string{"echo", "test"}}, m.ErrInvalidMonitor, "No AlertDown"},
-		{Monitor{AlertDown: []string{"log"}}, false, "No commands"},
+		{m.Monitor{AlertAfter: 1, AlertDown: []string{"log"}}, m.ErrInvalidMonitor, "No commands"},
-		{Monitor{Command: CommandOrShell{Command: []string{"echo", "test"}}, AlertDown: []string{"log"}, AlertAfter: -1}, false, "Invalid alert threshold, -1"},
+		{m.Monitor{AlertAfter: -1, Command: []string{"echo", "test"}, AlertDown: []string{"log"}}, m.ErrInvalidMonitor, "Invalid alert threshold, -1"},
 	}
 
 	for _, c := range cases {
-		log.Printf("Testing case %s", c.name)
+		c := c
-		actual := c.monitor.IsValid()
+
-		if actual != c.expected {
+		t.Run(c.name, func(t *testing.T) {
+			t.Parallel()
+
+			actual := c.monitor.Validate()
+			hasErr := (actual != nil)
+			expectErr := (c.expected != nil)
+
+			if hasErr != expectErr || !errors.Is(actual, c.expected) {
 				t.Errorf("IsValid(%v), expected=%t actual=%t", c.name, c.expected, actual)
-			log.Printf("Case failed: %s", c.name)
 			}
-		log.Println("-----")
+		})
 	}
 }
 
 // TestMonitorShouldCheck tests the Monitor.ShouldCheck()
 func TestMonitorShouldCheck(t *testing.T) {
-	timeNow := time.Now()
+	t.Parallel()
-	timeTenSecAgo := time.Now().Add(time.Second * -10)
-	timeTwentySecAgo := time.Now().Add(time.Second * -20)
 
-	cases := []struct {
+	// Create a monitor that should check every second and then verify it checks with some sleeps
-		monitor  Monitor
+	monitor := m.Monitor{ShellCommand: "true", CheckInterval: time.Second}
-		expected bool
+
-		name     string
+	if !monitor.ShouldCheck() {
-	}{
+		t.Errorf("New monitor should be ready to check")
-		{Monitor{}, true, "Empty"},
-		{Monitor{lastCheck: timeNow, CheckInterval: 15}, false, "Just checked"},
-		{Monitor{lastCheck: timeTenSecAgo, CheckInterval: 15}, false, "-10s"},
-		{Monitor{lastCheck: timeTwentySecAgo, CheckInterval: 15}, true, "-20s"},
 	}
 
-	for _, c := range cases {
+	monitor.Check()
-		actual := c.monitor.ShouldCheck()
+
-		if actual != c.expected {
+	if monitor.ShouldCheck() {
-			t.Errorf("ShouldCheck(%v), expected=%t actual=%t", c.name, c.expected, actual)
+		t.Errorf("Monitor should not be ready to check after a check")
 	}
+
+	time.Sleep(time.Second)
+
+	if !monitor.ShouldCheck() {
+		t.Errorf("Monitor should be ready to check after a second")
 	}
 }
 
-// TestMonitorIsUp tests the Monitor.isUp()
+// TestMonitorIsUp tests the Monitor.IsUp()
 func TestMonitorIsUp(t *testing.T) {
-	cases := []struct {
+	t.Parallel()
-		monitor  Monitor
+
-		expected bool
+	// Creating a monitor that should alert after 2 failures. The monitor should be considered up until we reach two failed checks
-		name     string
+	monitor := m.Monitor{ShellCommand: "false", AlertAfter: 2}
-	}{
+	if !monitor.IsUp() {
-		{Monitor{}, true, "Empty"},
+		t.Errorf("New monitor should be considered up")
-		{Monitor{alertCount: 1}, false, "Has alert"},
-		{Monitor{alertCount: -1}, false, "Negative alerts"},
-		{Monitor{alertCount: 0}, true, "No alerts"},
 	}
 
-	for _, c := range cases {
+	monitor.Check()
-		log.Printf("Testing case %s", c.name)
+
-		actual := c.monitor.isUp()
+	if !monitor.IsUp() {
-		if actual != c.expected {
+		t.Errorf("Monitor should be considered up with one failure and no alerts")
-			t.Errorf("isUp(%v), expected=%t actual=%t", c.name, c.expected, actual)
-			log.Printf("Case failed: %s", c.name)
 	}
-		log.Println("-----")
+
+	monitor.Check()
+
+	if monitor.IsUp() {
+		t.Errorf("Monitor should be considered down with one alert")
 	}
 }
 
 // TestMonitorGetAlertNames tests that proper alert names are returned
 func TestMonitorGetAlertNames(t *testing.T) {
 	cases := []struct {
-		monitor  Monitor
+		monitor  m.Monitor
 		up       bool
 		expected []string
 		name     string
 	}{
-		{Monitor{}, true, nil, "Empty up"},
+		{m.Monitor{}, true, nil, "Empty up"},
-		{Monitor{}, false, nil, "Empty down"},
+		{m.Monitor{}, false, nil, "Empty down"},
-		{Monitor{AlertUp: []string{"alert"}}, true, []string{"alert"}, "Return up"},
+		{m.Monitor{AlertUp: []string{"alert"}}, true, []string{"alert"}, "Return up"},
-		{Monitor{AlertDown: []string{"alert"}}, false, []string{"alert"}, "Return down"},
+		{m.Monitor{AlertDown: []string{"alert"}}, false, []string{"alert"}, "Return down"},
 	}
 
 	for _, c := range cases {
-		log.Printf("Testing case %s", c.name)
+		c := c
+
+		t.Run(c.name, func(t *testing.T) {
+			t.Parallel()
+
 			actual := c.monitor.GetAlertNames(c.up)
-		if !EqualSliceString(actual, c.expected) {
+			if !reflect.DeepEqual(actual, c.expected) {
 				t.Errorf("GetAlertNames(%v), expected=%v actual=%v", c.name, c.expected, actual)
-			log.Printf("Case failed: %s", c.name)
 			}
-		log.Println("-----")
+		})
 	}
 }
 
-// TestMonitorSuccess tests the Monitor.success()
+func TestMonitorAlertCount(t *testing.T) {
-func TestMonitorSuccess(t *testing.T) {
+	alertEvery := 1
+
 	cases := []struct {
-		monitor      Monitor
+		checkSuccess bool
-		expectNotice bool
+		alertCount   int
 		name         string
 	}{
-		{Monitor{}, false, "Empty"},
+		{false, 1, "First failure and first alert"},
-		{Monitor{alertCount: 0}, false, "No alerts"},
+		{false, 2, "Second failure and first alert"},
-		{Monitor{alertCount: 1}, true, "Has alert"},
+		{true, 2, "Success should preserve past alert count"},
+		{false, 1, "First failure and first alert after success"},
 	}
 
+	// Unlike previous tests, this one requires a static Monitor with repeated
+	// calls to the failure method
+	monitor := m.Monitor{AlertAfter: 1, AlertEvery: &alertEvery}
+
 	for _, c := range cases {
-		log.Printf("Testing case %s", c.name)
+		t.Logf("Testing case %s", c.name)
-		notice := c.monitor.success()
+
-		hasNotice := (notice != nil)
+		var notice *m.AlertNotice
-		if hasNotice != c.expectNotice {
+		if c.checkSuccess {
-			t.Errorf("success(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice)
+			notice = monitor.Success()
-			log.Printf("Case failed: %s", c.name)
+		} else {
+			notice = monitor.Failure()
+		}
+
+		if notice == nil {
+			t.Fatalf("failure(%v) expected notice, got nil", c.name)
+		}
+
+		if notice.AlertCount != c.alertCount {
+			t.Errorf("failure(%v), expected=%v actual=%v", c.name, c.alertCount, notice.AlertCount)
+			t.Logf("Case failed: %s", c.name)
 		}
-		log.Println("-----")
 	}
 }
 
 // TestMonitorFailureAlertAfter tests that alerts will not trigger until
 // hitting the threshold provided by AlertAfter
 func TestMonitorFailureAlertAfter(t *testing.T) {
+	var alertEveryOne int = 1
+
 	cases := []struct {
-		monitor      Monitor
+		monitor      m.Monitor
+		numChecks    int
 		expectNotice bool
 		name         string
 	}{
-		{Monitor{AlertAfter: 1}, true, "Empty"}, // Defaults to true because and AlertEvery default to 0
+		{m.Monitor{ShellCommand: "false", AlertAfter: 1}, 1, true, "Empty After 1"}, // Defaults to true because and AlertEvery default to 0
-		{Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: 1}, true, "Alert after 1: first failure"},
+		{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: &alertEveryOne}, 1, true, "Alert after 1: first failure"},
-		{Monitor{failureCount: 1, AlertAfter: 1, AlertEvery: 1}, true, "Alert after 1: second failure"},
+		{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: &alertEveryOne}, 2, true, "Alert after 1: second failure"},
-		{Monitor{failureCount: 0, AlertAfter: 20, AlertEvery: 1}, false, "Alert after 20: first failure"},
+		{m.Monitor{ShellCommand: "false", AlertAfter: 20, AlertEvery: &alertEveryOne}, 1, false, "Alert after 20: first failure"},
-		{Monitor{failureCount: 19, AlertAfter: 20, AlertEvery: 1}, true, "Alert after 20: 20th failure"},
+		{m.Monitor{ShellCommand: "false", AlertAfter: 20, AlertEvery: &alertEveryOne}, 20, true, "Alert after 20: 20th failure"},
-		{Monitor{failureCount: 20, AlertAfter: 20, AlertEvery: 1}, true, "Alert after 20: 21st failure"},
+		{m.Monitor{ShellCommand: "false", AlertAfter: 20, AlertEvery: &alertEveryOne}, 21, true, "Alert after 20: 21st failure"},
 	}
 
 	for _, c := range cases {
-		log.Printf("Testing case %s", c.name)
+		c := c
-		notice := c.monitor.failure()
+
-		hasNotice := (notice != nil)
+		t.Run(c.name, func(t *testing.T) {
+			t.Parallel()
+
+			hasNotice := false
+
+			for i := 0; i < c.numChecks; i++ {
+				_, notice := c.monitor.Check()
+				hasNotice = (notice != nil)
+			}
+
 			if hasNotice != c.expectNotice {
 				t.Errorf("failure(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice)
-			log.Printf("Case failed: %s", c.name)
 			}
-		log.Println("-----")
+		})
 	}
 }
 
@@ -161,51 +198,42 @@ func TestMonitorFailureAlertAfter(t *testing.T) {
 // on the expected intervals
 func TestMonitorFailureAlertEvery(t *testing.T) {
 	cases := []struct {
-		monitor      Monitor
+		monitor        m.Monitor
-		expectNotice bool
+		expectedNotice []bool
 		name           string
 	}{
-		/*
+		{m.Monitor{ShellCommand: "false", AlertAfter: 1}, []bool{true}, "No AlertEvery set"}, // Defaults to true because AlertAfter and AlertEvery default to nil
-			TODO: Actually found a bug in original implementation. There is an inconsistency in the way AlertAfter is treated.
-			For "First alert only" (ie. AlertEvery=0), it is the number of failures to ignore before alerting, so AlertAfter=1
-			will ignore the first failure and alert on the second failure
-			For other intervals (ie. AlertEvery=1), it is essentially indexed on one. Essentially making AlertAfter=1 trigger
-			on the first failure.
-
-			For usabilty, this should be consistent. Consistent with what though? minitor-py? Or itself? Dun dun duuuunnnnn!
-		*/
-		{Monitor{AlertAfter: 1}, true, "Empty"}, // Defaults to true because AlertAfter and AlertEvery default to 0
 		// Alert first time only, after 1
-		{Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: 0}, true, "Alert first time only after 1: first failure"},
+		{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: Ptr(0)}, []bool{true, false, false}, "Alert first time only after 1"},
-		{Monitor{failureCount: 1, AlertAfter: 1, AlertEvery: 0}, false, "Alert first time only after 1: second failure"},
-		{Monitor{failureCount: 2, AlertAfter: 1, AlertEvery: 0}, false, "Alert first time only after 1: third failure"},
 		// Alert every time, after 1
-		{Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: 1}, true, "Alert every time after 1: first failure"},
+		{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: Ptr(1)}, []bool{true, true, true}, "Alert every time after 1"},
-		{Monitor{failureCount: 1, AlertAfter: 1, AlertEvery: 1}, true, "Alert every time after 1: second failure"},
-		{Monitor{failureCount: 1, AlertAfter: 1, AlertEvery: 1}, true, "Alert every time after 1: third failure"},
 		// Alert every other time, after 1
-		{Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: 2}, true, "Alert every other time after 1: first failure"},
+		{m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: Ptr(2)}, []bool{true, false, true, false}, "Alert every other time after 1"},
-		{Monitor{failureCount: 1, AlertAfter: 1, AlertEvery: 2}, false, "Alert every other time after 1: second failure"},
-		{Monitor{failureCount: 2, AlertAfter: 1, AlertEvery: 2}, true, "Alert every other time after 1: third failure"},
-		{Monitor{failureCount: 3, AlertAfter: 1, AlertEvery: 2}, false, "Alert every other time after 1: fourth failure"},
 	}
 
 	for _, c := range cases {
-		log.Printf("Testing case %s", c.name)
+		c := c
 
-		notice := c.monitor.failure()
+		t.Run(c.name, func(t *testing.T) {
+			t.Parallel()
+
+			for i, expectNotice := range c.expectedNotice {
+				_, notice := c.monitor.Check()
 				hasNotice := (notice != nil)
-		if hasNotice != c.expectNotice {
+
-			t.Errorf("failure(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice)
+				if hasNotice != expectNotice {
-			log.Printf("Case failed: %s", c.name)
+					t.Errorf("failed %s check %d: expected=%t actual=%t", c.name, i, expectNotice, hasNotice)
 				}
-		log.Println("-----")
+			}
+		})
 	}
 }
 
 // TestMonitorFailureExponential tests that alerts will trigger
 // with an exponential backoff after repeated failures
 func TestMonitorFailureExponential(t *testing.T) {
+	var alertEveryExp int = -1
+
 	cases := []struct {
 		expectNotice bool
 		name         string
@@ -222,17 +250,18 @@ func TestMonitorFailureExponential(t *testing.T) {
 
 	// Unlike previous tests, this one requires a static Monitor with repeated
 	// calls to the failure method
-	monitor := Monitor{failureCount: 0, AlertAfter: 1, AlertEvery: -1}
+	monitor := m.Monitor{ShellCommand: "false", AlertAfter: 1, AlertEvery: &alertEveryExp}
-	for _, c := range cases {
-		log.Printf("Testing case %s", c.name)
 
-		notice := monitor.failure()
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			// NOTE: These tests are not parallel because they rely on the state of the Monitor
+			_, notice := monitor.Check()
 			hasNotice := (notice != nil)
+
 			if hasNotice != c.expectNotice {
 				t.Errorf("failure(%v), expected=%t actual=%t", c.name, c.expectNotice, hasNotice)
-			log.Printf("Case failed: %s", c.name)
 			}
-		log.Println("-----")
+		})
 	}
 }
 
@@ -243,53 +272,54 @@ func TestMonitorCheck(t *testing.T) {
 		hasNotice  bool
 		lastOutput string
 	}
+
 	cases := []struct {
-		monitor Monitor
+		monitor m.Monitor
 		expect  expected
 		name    string
 	}{
 		{
-			Monitor{Command: CommandOrShell{Command: []string{"echo", "success"}}},
+			m.Monitor{AlertAfter: 1, Command: []string{"echo", "success"}},
 			expected{isSuccess: true, hasNotice: false, lastOutput: "success\n"},
 			"Test successful command",
 		},
 		{
-			Monitor{Command: CommandOrShell{ShellCommand: "echo success"}},
+			m.Monitor{AlertAfter: 1, ShellCommand: "echo success"},
 			expected{isSuccess: true, hasNotice: false, lastOutput: "success\n"},
 			"Test successful command shell",
 		},
 		{
-			Monitor{Command: CommandOrShell{Command: []string{"total", "failure"}}},
+			m.Monitor{AlertAfter: 1, Command: []string{"total", "failure"}},
 			expected{isSuccess: false, hasNotice: true, lastOutput: ""},
 			"Test failed command",
 		},
 		{
-			Monitor{Command: CommandOrShell{ShellCommand: "false"}},
+			m.Monitor{AlertAfter: 1, ShellCommand: "false"},
 			expected{isSuccess: false, hasNotice: true, lastOutput: ""},
 			"Test failed command shell",
 		},
 	}
 
 	for _, c := range cases {
-		log.Printf("Testing case %s", c.name)
+		c := c
+
+		t.Run(c.name, func(t *testing.T) {
+			t.Parallel()
 
 			isSuccess, notice := c.monitor.Check()
 			if isSuccess != c.expect.isSuccess {
 				t.Errorf("Check(%v) (success), expected=%t actual=%t", c.name, c.expect.isSuccess, isSuccess)
-			log.Printf("Case failed: %s", c.name)
 			}
 
 			hasNotice := (notice != nil)
 			if hasNotice != c.expect.hasNotice {
 				t.Errorf("Check(%v) (notice), expected=%t actual=%t", c.name, c.expect.hasNotice, hasNotice)
-			log.Printf("Case failed: %s", c.name)
 			}
 
-		lastOutput := c.monitor.lastOutput
+			lastOutput := c.monitor.LastOutput()
 			if lastOutput != c.expect.lastOutput {
 				t.Errorf("Check(%v) (output), expected=%v actual=%v", c.name, c.expect.lastOutput, lastOutput)
-			log.Printf("Case failed: %s", c.name)
 			}
-		log.Println("-----")
+		})
 	}
 }

renovate.json

@@ -0,0 +1,3 @@
+{
+  "$schema": "https://docs.renovatebot.com/renovate-schema.json"
+}

sample-config.hcl

@@ -0,0 +1,52 @@
+check_interval = "5s"
+
+monitor "Fake Website" {
+  command = ["curl", "-s", "-o", "/dev/null", "https://minitor.mon"]
+  alert_down = ["log_down", "mailgun_down", "sms_down"]
+  alert_up = ["log_up", "email_up"]
+  check_interval = "10s" # Must be at minimum the global `check_interval`
+  alert_after = 3
+  alert_every = -1 # Defaults to -1 for exponential backoff. 0 to disable repeating
+}
+
+monitor "Real Website" {
+  command = ["curl", "-s", "-o", "/dev/null", "https://google.com"]
+  alert_down = ["log_down", "mailgun_down", "sms_down"]
+  alert_up = ["log_up", "email_up"]
+  check_interval = "5s"
+  alert_after = 3
+  alert_every = -1
+}
+
+alert "log_down" {
+  command = ["echo", "Minitor failure for {{.MonitorName}}"]
+}
+
+alert "log_up" {
+  command = ["echo", "Minitor recovery for {{.MonitorName}}"]
+}
+
+alert "email_up" {
+  command = ["sendmail", "me@minitor.mon", "Recovered: {monitor_name}", "We're back!"]
+}
+
+alert "mailgun_down" {
+  shell_command = <<-EOF
+  curl -s -X POST \
+    -F subject="Alert! {{.MonitorName}} failed" \
+    -F from="Minitor <minitor@minitor.mon>" \
+    -F to=me@minitor.mon \
+    -F text="Our monitor failed" \
+    https://api.mailgun.net/v3/minitor.mon/messages \
+    -u "api:$${MAILGUN_API_KEY}"
+  EOF
+}
+
+alert "sms_down" {
+  shell_command = <<-EOF
+  curl -s -X POST -F "Body=Failure! {{.MonitorName}} has failed" \
+    -F "From=$${AVAILABLE_NUMBER}" -F "To=$${MY_PHONE}" \
+    "https://api.twilio.com/2010-04-01/Accounts/$${ACCOUNT_SID}/Messages" \
+    -u "$${ACCOUNT_SID}:$${AUTH_TOKEN}"
+  EOF
+}

sample-config.yml

@@ -1,41 +0,0 @@
----
-check_interval: 5
-
-monitors:
-  - name: Fake Website
-    command: ['curl', '-s', '-o', '/dev/null', 'https://minitor.mon']
-    alert_down: [log_down, mailgun_down, sms_down]
-    alert_up: [log_up, email_up]
-    check_interval: 10  # Must be at minimum the global `check_interval`
-    alert_after: 3
-    alert_every: -1  # Defaults to -1 for exponential backoff. 0 to disable repeating
-  - name: Real Website
-    command: ['curl', '-s', '-o', '/dev/null', 'https://google.com']
-    alert_down: [log_down, mailgun_down, sms_down]
-    alert_up: [log_up, email_up]
-    check_interval: 5
-    alert_after: 3
-    alert_every: -1
-
-alerts:
-  log_down:
-    command: ["echo", "Minitor failure for {{.MonitorName}}"]
-  log_up:
-    command: ["echo", "Minitor recovery for {{.MonitorName}}"]
-  email_up:
-    command: [sendmail, "me@minitor.mon", "Recovered: {monitor_name}", "We're back!"]
-  mailgun_down:
-    command: >
-      curl -s -X POST
-      -F subject="Alert! {{.MonitorName}} failed"
-      -F from="Minitor <minitor@minitor.mon>"
-      -F to=me@minitor.mon
-      -F text="Our monitor failed"
-      https://api.mailgun.net/v3/minitor.mon/messages
-      -u "api:${MAILGUN_API_KEY}"
-  sms_down:
-    command: >
-      curl -s -X POST -F "Body=Failure! {{.MonitorName}} has failed"
-      -F "From=${AVAILABLE_NUMBER}" -F "To=${MY_PHONE}"
-      "https://api.twilio.com/2010-04-01/Accounts/${ACCOUNT_SID}/Messages"
-      -u "${ACCOUNT_SID}:${AUTH_TOKEN}"

scripts/curl_ok.sh

@@ -0,0 +1,6 @@
+#! /bin/sh
+
+# Used for a basic HTTP health check
+# Avoids output from non-errors and will fail if the HTTP response is unsuccessful
+
+curl --silent --show-error --fail -o /dev/null "$@"

scripts/docker_check.sh

@@ -11,6 +11,7 @@ set -e
 # To override, export DOCKER_HOST to a new hostname
 DOCKER_HOST="${DOCKER_HOST:=socket}"
 container_name="$1"
+num_log_lines="$2"
 
 # Curls Docker either using a socket or URL
 function curl_docker {
@@ -31,21 +32,32 @@ function get_container_id {
 
 # Returns container JSON
 function inspect_container {
-    local container_id=$1
+    local container_id="$1"
     curl_docker "containers/$container_id/json"
 }
 
+# Gets some lines from docker log
+function get_logs {
+    container_id="$1"
+    num_lines="$2"
+    curl_docker "containers/$container_id/logs?stdout=1&stderr=1" | tail -n "$num_lines"
+}
+
 if [ -z "$container_name" ]; then
-    echo "Usage: $0 container_name"
+    echo "Usage: $0 container_name [num_log_lines]"
     echo "Will exit with the last status code of continer with provided name"
     exit 1
 fi
 
-container_id=$(get_container_id $container_name)
+container_id=$(get_container_id "$container_name")
 if [ -z "$container_id" ]; then
     echo "ERROR: Could not find container with name: $container_name"
     exit 1
 fi
 exit_code=$(inspect_container "$container_id" | jq -r .State.ExitCode)
 
+if [ -n "$num_log_lines" ]; then
+    get_logs "$container_id" "$num_log_lines"
+fi
+
 exit "$exit_code"

scripts/docker_healthcheck.sh

@@ -11,6 +11,7 @@ set -e
 # To override, export DOCKER_HOST to a new hostname
 DOCKER_HOST="${DOCKER_HOST:=socket}"
 container_name="$1"
+num_log_lines="$2"
 
 # Curls Docker either using a socket or URL
 function curl_docker {
@@ -35,8 +36,15 @@ function inspect_container {
     curl_docker "containers/$container_id/json"
 }
 
+# Gets some lines from docker log
+function get_logs {
+    container_id="$1"
+    num_lines="$2"
+    curl_docker "containers/$container_id/logs?stdout=1&stderr=1" | tail -n "$num_lines"
+}
+
 if [ -z "$container_name" ]; then
-    echo "Usage: $0 container_name"
+    echo "Usage: $0 container_name [num_log_lines]"
     echo "Will return results of healthcheck for continer with provided name"
     exit 1
 fi
@@ -48,6 +56,10 @@ if [ -z "$container_id" ]; then
 fi
 health=$(inspect_container "$container_id" | jq -r '.State.Health.Status')
 
+if [ -n "$num_log_lines" ]; then
+    get_logs "$container_id" "$num_log_lines"
+fi
+
 case "$health" in
     null)
         echo "No healthcheck results"

test/invalid-config-invalid-duration.hcl

@@ -0,0 +1 @@
+check_interval = "woops, I'm not an int!"

test/invalid-config-missing-alerts.hcl

@@ -0,0 +1,7 @@
+check_interval = "1s"
+
+monitor "Command" {
+    command = ["echo", "$PATH"]
+    alert_down = [ "alert_down", "log_shell", "log_command" ]
+    alert_every = 0
+}

test/invalid-config-missing-alerts.yml

@@ -1,8 +0,0 @@
-check_interval: 1
-
-monitors:
-  - name: Command
-    command: ['echo', '$PATH']
-    alert_down: [ 'alert_down', 'log_shell', 'log_command' ]
-    # alert_every: -1
-    alert_every: 0

test/invalid-config-type.yml

@@ -1 +0,0 @@
-check_interval: woops, I'm not an int!

test/invalid-config-unknown-alert.hcl

@@ -0,0 +1,12 @@
+check_interval = "1s"
+
+monitor "Command" {
+  command = ["echo", "$PATH"]
+  alert_down = ["not_log"]
+  alert_every = 0
+}
+
+
+alert "log" {
+  command = ["true"]
+}

test/invalid-config-unknown-alert.yml

@@ -1,13 +0,0 @@
-check_interval: 1
-
-monitors:
-  - name: Command
-    command: ['echo', '$PATH']
-    alert_down: [ 'not_log']
-    # alert_every: -1
-    alert_every: 0
-
-
-alerts:
-  log:
-    command: ['true']

test/invalid-config-wrong-hcl-type.hcl

@@ -0,0 +1,12 @@
+check_interval = "1s"
+
+alert "log_command" {
+  command = "should be a list"
+}
+
+monitor "Command" {
+  command =  ["echo", "$PATH"]
+  alert_down =  ["log_command"]
+  alert_every =  2
+  check_interval =  "10s"
+}

test/valid-config-default-values.hcl

@@ -0,0 +1,16 @@
+check_interval = "1s"
+default_alert_down = ["log_command"]
+default_alert_every = 0
+default_alert_after = 2
+
+monitor "Default" {
+  command = ["echo"]
+}
+
+monitor "Command" {
+  command = ["echo", "$PATH"]
+}
+
+alert "log_command" {
+  command = ["echo", "default", "'command!!!'", "{{.MonitorName}}"]
+}

test/valid-config.hcl

@@ -0,0 +1,34 @@
+check_interval = "1s"
+
+alert "log_command" {
+  command = ["echo", "regular", "'command!!!'", "{{.MonitorName}}"]
+}
+
+alert "log_shell" {
+  shell_command = "echo \"Failure on {{.MonitorName}} User is $USER\""
+}
+
+monitor "Default" {
+  command = ["echo"]
+  alert_down = ["log_command"]
+}
+
+monitor "Command" {
+  command =  ["echo", "$PATH"]
+  alert_down =  ["log_command", "log_shell"]
+  alert_every =  2
+  check_interval =  "10s"
+}
+
+monitor "Shell" {
+  shell_command = <<-EOF
+    echo 'Some string with stuff'
+    echo 'another line'
+    echo $PATH
+    exit 1
+  EOF
+  alert_down = ["log_command", "log_shell"]
+  alert_after = 5
+  alert_every = 0
+  check_interval = "1m"
+}

test/valid-config.yml

@@ -1,23 +0,0 @@
----
-check_interval: 1
-
-monitors:
-  - name: Command
-    command: ['echo', '$PATH']
-    alert_down: ['log_command', 'log_shell']
-    alert_every: 0
-  - name: Shell
-    command: >
-      echo 'Some string with stuff';
-      echo 'another line';
-      echo $PATH;
-      exit 1
-    alert_down: ['log_command', 'log_shell']
-    alert_after: 5
-    alert_every: 0
-
-alerts:
-  log_command:
-    command: ['echo', 'regular', '"command!!!"', "{{.MonitorName}}"]
-  log_shell:
-    command: echo "Failure on {{.MonitorName}} User is $USER"

test/valid-default-log-alert.yml

@@ -1,8 +0,0 @@
----
-check_interval: 1
-
-monitors:
-  - name: Command
-    command: ['echo', '$PATH']
-    alert_down: ['log']
-    alert_every: 0

test/valid-verify-multi-line.hcl

@@ -0,0 +1,19 @@
+check_interval = "1s"
+
+monitor "Shell" {
+  shell_command = <<-EOF
+    echo 'Some string with stuff'
+    echo "<angle brackets>"
+    exit 1
+  EOF
+  alert_down = ["log_shell"]
+  alert_after =  1
+  alert_every =  0
+}
+
+alert "log_shell" {
+  shell_command = <<EOF
+    echo 'Some string with stuff'
+    echo '<angle brackets>'
+EOF
+}

test/valid-verify-multi-line.yml

@@ -1,18 +0,0 @@
----
-check_interval: 1
-
-monitors:
-  - name: Shell
-    command: >
-      echo 'Some string with stuff';
-      echo "<angle brackets>";
-      exit 1
-    alert_down: ['log_shell']
-    alert_after: 1
-    alert_every: 0
-
-alerts:
-  log_shell:
-    command: |
-      echo 'Some string with stuff'
-      echo '<angle brackets>'

util.go

@@ -8,7 +8,7 @@ import (
 // ShellCommand takes a string and executes it as a command using `sh`
 func ShellCommand(command string) *exec.Cmd {
 	shellCommand := []string{"sh", "-c", strings.TrimSpace(command)}
-	//log.Printf("Shell command: %v", shellCommand)
+
 	return exec.Command(shellCommand[0], shellCommand[1:]...)
 }
 
@@ -17,10 +17,12 @@ func EqualSliceString(a, b []string) bool {
 	if len(a) != len(b) {
 		return false
 	}
+
 	for i, val := range a {
 		if val != b[i] {
 			return false
 		}
 	}
+
 	return true
 }

util_test.go

@@ -1,6 +1,9 @@
 package main
 
-import "testing"
+import (
+	"fmt"
+	"testing"
+)
 
 func TestUtilEqualSliceString(t *testing.T) {
 	cases := []struct {
@@ -21,6 +24,11 @@ func TestUtilEqualSliceString(t *testing.T) {
 	}
 
 	for _, c := range cases {
+		c := c
+
+		t.Run(fmt.Sprintf("%v %v", c.a, c.b), func(t *testing.T) {
+			t.Parallel()
+
 			actual := EqualSliceString(c.a, c.b)
 			if actual != c.expected {
 				t.Errorf(
@@ -28,5 +36,6 @@ func TestUtilEqualSliceString(t *testing.T) {
 					c.a, c.b, c.expected, actual,
 				)
 			}
+		})
 	}
 }