package catalogue

import (
	"encoding/json"
	"fmt"
	"net"
	"regexp"
	"sort"
	"strings"
)

// A definition names no installation (novox/hq ADR 0112, ADR 0155, issues 122 and 134).
//
// A module definition holds what is true of the module everywhere; what is particular to one mesh —
// a public name, a forge's address, a node's public address — is resolved at assignment. The rule
// stood for a month with nothing checking it, and a sweep found thirty of seventy-one definitions
// naming the installation they were written in. This is the check.
//
// **What is judged is what the mesh acts on, not what a person reads.** A domain in a `why` or a
// `description` is documentation the mesh never reads; reporting it beside `KC_HOSTNAME` would teach
// people to ignore the report. What is judged is every other string value: a name under a public
// top-level domain, or a public address. Two families of name are the world's and not this mesh's,
// and are allowed where they can only mean the world: the public registries an `image` may be pulled
// from, and the public resolvers a machine may forward to. The container runtime's own alias for
// its host is the runtime's, true on every machine that runs it.
//
// **A name that is right where it stands is declared, one by one, with its reason.** A federated
// server's config names the federation's public directory; an application built outside the mesh
// is pulled from the registry that built it, until the mesh builds it. The resource carries
// `names-on-purpose`, a map from each such name to why — the shape `secrets-in-environment` has,
// per name — so a reader sees which names a definition means to carry and why, a name the map does
// not cover is still reported, and the catalogue-wide test is the list that shrinks as names move.

// NamesOnPurpose is the catalogue-level word a resource carries for the names it means to name:
// each name mapped to its reason. The host never sees it.
const NamesOnPurpose = "names-on-purpose"

// prose is every key whose value the mesh never reads.
var prose = map[string]bool{"why": true, "description": true}

// Registries the world runs, which an image may name because an image reference must say where it
// is pulled from. Anything else in an image reference is a registry of some installation.
var worldsRegistries = map[string]bool{
	"docker.io": true, "registry-1.docker.io": true, "index.docker.io": true, "ghcr.io": true,
	"quay.io": true, "gcr.io": true, "registry.k8s.io": true, "k8s.gcr.io": true,
	"mcr.microsoft.com": true, "lscr.io": true, "public.ecr.aws": true, "registry.gitlab.com": true,
	"codeberg.org": true, "cgr.dev": true,
}

// Services the world runs that a definition may name as a policy default, the way it may name a
// public resolver: the public certificate authorities' ACME directories. Anything else a served
// fact or a file names is somebody's installation.
var worldsServices = map[string]bool{
	"acme-v02.api.letsencrypt.org": true, "acme-staging-v02.api.letsencrypt.org": true,
	"api.buypass.com": true, "api.test4.buypass.no": true, "dv.acme-v02.api.pki.goog": true,
	"acme.zerossl.com": true,
}

// Resolvers the world runs, which a machine's resolver may forward to as a policy default.
var worldsResolvers = map[string]bool{
	"1.1.1.1": true, "1.0.0.1": true, "8.8.8.8": true, "8.8.4.4": true, "9.9.9.9": true,
	"149.112.112.112": true, "208.67.222.222": true, "208.67.220.220": true,
}

// hostname is a dotted name whose last label is a top-level domain a real installation would have.
// Not every dotted token: `module.json`, `index.html` and `docker.sock` are dotted and name nothing.
// Boundaries are checked by hand rather than in the pattern, because two names one character apart
// — `a.example.tld,b.example.tld` — would otherwise share the delimiter and the second would be lost.
var hostname = regexp.MustCompile(
	`(?i)(?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\.)+` +
		`(?:be|nl|de|fr|uk|eu|com|net|org|io|dev|app|cloud|site|online|me|co|ch|at|lu|` +
		`internal|example|tld|test|invalid)`)

// address is a dotted quad.
var address = regexp.MustCompile(`(?:[0-9]{1,3}\.){3}[0-9]{1,3}`)

// isName is whether a byte may be part of a name; a match bordered by one is a longer token.
func isName(b byte) bool {
	return b == '.' || b == '-' || (b >= 'a' && b <= 'z') || (b >= 'A' && b <= 'Z') || (b >= '0' && b <= '9')
}

// standalone are the matches of re in value that are whole tokens, not parts of a longer one.
func standalone(re *regexp.Regexp, value string) []string {
	var out []string
	for _, span := range re.FindAllStringIndex(value, -1) {
		if span[0] > 0 && isName(value[span[0]-1]) {
			continue
		}
		if span[1] < len(value) && isName(value[span[1]]) {
			continue
		}
		out = append(out, value[span[0]:span[1]])
	}
	return out
}

// InstallationProblems is every value of a definition that names an installation, in the
// definition's own words: where it is, and what it names.
func InstallationProblems(m Manifest) []string {
	raw, err := json.Marshal(m)
	if err != nil {
		return []string{fmt.Sprintf("%s could not be read back: %v", m.Module, err)}
	}
	var tree any
	if err := json.Unmarshal(raw, &tree); err != nil {
		return []string{fmt.Sprintf("%s could not be read back: %v", m.Module, err)}
	}
	var problems []string
	// The module's own name is a value too: a module named after the domain it serves is a
	// definition that can only be installed there (issue 134).
	for _, name := range namesIn(m.Module) {
		problems = append(problems, fmt.Sprintf(
			"%s is named after %s, and a module is named for what it is, not for where it runs", m.Module, name))
	}
	walk(tree, "", nil, func(at string, value string, meant map[string]bool, isImage bool) {
		for _, name := range namesIn(value) {
			if (isImage && worldsRegistries[strings.ToLower(name)]) || meant[name] {
				continue
			}
			problems = append(problems, fmt.Sprintf("%s names %s at %s", m.Module, name, at))
		}
		for _, ip := range addressesIn(value) {
			if meant[ip] {
				continue
			}
			problems = append(problems, fmt.Sprintf("%s names the public address %s at %s", m.Module, ip, at))
		}
	})
	sort.Strings(problems)
	return problems
}

// walk visits every string in the tree with its path, the names the enclosing resource means to
// name (with a reason), and whether it is an image reference.
func walk(node any, at string, meant map[string]bool, visit func(at, value string, meant map[string]bool, isImage bool)) {
	switch v := node.(type) {
	case map[string]any:
		if declared, has := v[NamesOnPurpose].(map[string]any); has {
			widened := map[string]bool{}
			for name := range meant {
				widened[name] = true
			}
			for name, reason := range declared {
				if r, ok := reason.(string); ok && strings.TrimSpace(r) != "" {
					widened[strings.ToLower(name)] = true
				}
			}
			meant = widened
		}
		keys := make([]string, 0, len(v))
		for k := range v {
			keys = append(keys, k)
		}
		sort.Strings(keys)
		for _, k := range keys {
			if prose[k] || k == NamesOnPurpose || (at == "" && k == "module") {
				continue
			}
			child := at + "." + k
			if at == "" {
				child = k
			}
			if s, isString := v[k].(string); isString {
				visit(child, s, meant, k == "image")
				continue
			}
			walk(v[k], child, meant, visit)
		}
	case []any:
		for i, item := range v {
			child := fmt.Sprintf("%s[%d]", at, i)
			if s, isString := item.(string); isString {
				visit(child, s, meant, false)
				continue
			}
			walk(item, child, meant, visit)
		}
	}
}

// namesIn is every hostname in a value that could belong to an installation.
func namesIn(value string) []string {
	var out []string
	for _, found := range standalone(hostname, value) {
		name := strings.ToLower(found)
		switch {
		case strings.HasSuffix(name, ".docker.internal"):
			// The container runtime's alias for its own host: every machine running it has one.
		case worldsServices[name]:
			// A public authority named as a policy default, true of any mesh that wants it.
		case name == "example.tld", strings.HasSuffix(name, ".example.tld"),
			name == "example.com", name == "example.net", name == "example.org",
			strings.HasSuffix(name, ".example.com"), strings.HasSuffix(name, ".example.net"),
			strings.HasSuffix(name, ".example.org"), strings.HasSuffix(name, ".example"),
			strings.HasSuffix(name, ".test"), strings.HasSuffix(name, ".invalid"):
			// Documentation names, which is what a definition's own example should use.
		default:
			out = append(out, name)
		}
	}
	return out
}

// addressesIn is every public address in a value: not a private range, loopback, link-local, the
// unspecified address, a documentation range, or a resolver the world runs.
func addressesIn(value string) []string {
	var out []string
	for _, found := range standalone(address, value) {
		ip := net.ParseIP(found)
		if ip == nil || ip.IsPrivate() || ip.IsLoopback() || ip.IsLinkLocalUnicast() ||
			ip.IsUnspecified() || ip.IsMulticast() || worldsResolvers[found] || documentation(ip) {
			continue
		}
		out = append(out, found)
	}
	return out
}

func documentation(ip net.IP) bool {
	for _, cidr := range []string{"192.0.2.0/24", "198.51.100.0/24", "203.0.113.0/24", "100.64.0.0/10"} {
		_, block, _ := net.ParseCIDR(cidr)
		if block.Contains(ip) {
			return true
		}
	}
	return false
}