key-cape/src/internal/validator/validator.go

package validator

import (
	"fmt"
	"net/mail"
	"strings"

	"keycape/internal/domain"
)

// Snapshot is the input to the validator: a resolved canonical directory.
type Snapshot struct {
	Users  []domain.User
	Groups []domain.Group
}

// Validate runs all structural and semantic rules against the snapshot.
// The mode string is recorded in the report but does not change rule behaviour in v0.1.
func Validate(snap Snapshot, mode Mode) Report {
	report := Report{
		Mode: string(mode),
	}

	report.Structural = runStructural(snap)
	report.Semantic = runSemantic(snap)

	report.Passed = allPassed(report.Structural) && allPassed(report.Semantic)
	return report
}

// --- structural rules ---

func runStructural(snap Snapshot) []RuleResult {
	return []RuleResult{
		checkValidDNStructure(snap),
		checkRequiredAttributesPresent(snap),
		checkRawAttributesWellFormed(snap),
		checkValidGroupMemberships(snap),
	}
}

// checkValidDNStructure verifies that all user and group IDs are non-empty
// and contain only characters valid in a LDAP uid/cn naming attribute.
func checkValidDNStructure(snap Snapshot) RuleResult {
	r := RuleResult{Rule: "valid_dn_structure", Passed: true}
	for _, u := range snap.Users {
		if u.ID == "" {
			r.Passed = false
			r.Message = appendMsg(r.Message, "user has empty id")
			continue
		}
		if !isValidNamingValue(u.Username) {
			r.Passed = false
			r.Message = appendMsg(r.Message, fmt.Sprintf("user %q has invalid username for DN: %q", u.ID, u.Username))
		}
	}
	for _, g := range snap.Groups {
		if g.ID == "" {
			r.Passed = false
			r.Message = appendMsg(r.Message, "group has empty id")
			continue
		}
		if !isValidNamingValue(g.Name) {
			r.Passed = false
			r.Message = appendMsg(r.Message, fmt.Sprintf("group %q has invalid name for DN: %q", g.ID, g.Name))
		}
	}
	return r
}

// checkRequiredAttributesPresent verifies users have uid, cn, sn equivalents
// (id, username, displayName) and groups have id and name.
func checkRequiredAttributesPresent(snap Snapshot) RuleResult {
	r := RuleResult{Rule: "required_attributes_present", Passed: true}
	for _, u := range snap.Users {
		if u.Username == "" {
			r.Passed = false
			r.Message = appendMsg(r.Message, fmt.Sprintf("user %q missing required attribute: username (uid)", u.ID))
		}
		if u.DisplayName == "" {
			r.Passed = false
			r.Message = appendMsg(r.Message, fmt.Sprintf("user %q missing required attribute: displayName (cn)", u.ID))
		}
	}
	for _, g := range snap.Groups {
		if g.Name == "" {
			r.Passed = false
			r.Message = appendMsg(r.Message, fmt.Sprintf("group %q missing required attribute: name (cn)", g.ID))
		}
	}
	return r
}

// canonicalLDAPMappings are the directory attributes the canonical model already
// owns: User.username maps to uid, User.displayName to cn, User.email to mail,
// and Group.name to cn. A raw attribute restating one of these creates a second
// source for a value the model defines, which is how an export and the directory
// it came from drift apart.
var canonicalLDAPMappings = map[string]string{
	"uid":  "username",
	"cn":   "displayName",
	"mail": "email",
}

// checkRawAttributesWellFormed validates the raw LDAP attributes a snapshot
// carries alongside the canonical fields (KEY-WP-0021).
//
// `ldapAttributes` is defined as the attributes the canonical model does *not*
// cover, so there is no schema-derived allow-list of permitted names to check
// against — the field exists to carry exactly what the schema does not name.
// What can be enforced is that each name is writable to a directory, does not
// shadow a mapping the model owns, and is not the same attribute twice.
func checkRawAttributesWellFormed(snap Snapshot) RuleResult {
	r := RuleResult{Rule: "raw_attributes_well_formed", Passed: true}
	for _, u := range snap.Users {
		// LDAP attribute descriptors are case-insensitive, so keys differing
		// only by case are one attribute supplied twice, not two attributes.
		seen := make(map[string]string, len(u.LDAPAttributes))
		for key := range u.LDAPAttributes {
			switch {
			case strings.TrimSpace(key) == "":
				r.Passed = false
				r.Message = appendMsg(r.Message, fmt.Sprintf("user %q has blank LDAP attribute key", u.ID))
				continue
			case !validAttributeDescriptor(key):
				r.Passed = false
				r.Message = appendMsg(r.Message, fmt.Sprintf(
					"user %q has LDAP attribute %q that is not a valid attribute descriptor", u.ID, key))
				continue
			}
			folded := strings.ToLower(key)
			if field, canonical := canonicalLDAPMappings[folded]; canonical {
				r.Passed = false
				r.Message = appendMsg(r.Message, fmt.Sprintf(
					"user %q carries LDAP attribute %q as a raw attribute; it is owned by the canonical %s field",
					u.ID, key, field))
				continue
			}
			if first, duplicate := seen[folded]; duplicate {
				r.Passed = false
				r.Message = appendMsg(r.Message, fmt.Sprintf(
					"user %q has LDAP attributes %q and %q that differ only by case", u.ID, first, key))
				continue
			}
			seen[folded] = key
		}
	}
	return r
}

// validAttributeDescriptor reports whether name is an LDAP attribute descriptor
// per RFC 4512: either a numeric OID, or a letter followed by letters, digits
// and hyphens. Options after a semicolon (e.g. "description;lang-de") are not
// accepted, since a canonical snapshot carries values, not transfer encodings.
func validAttributeDescriptor(name string) bool {
	if name == "" {
		return false
	}
	if name[0] >= '0' && name[0] <= '9' {
		return validNumericOID(name)
	}
	for i := 0; i < len(name); i++ {
		c := name[i]
		switch {
		case c >= 'a' && c <= 'z', c >= 'A' && c <= 'Z':
		case c >= '0' && c <= '9', c == '-':
			if i == 0 {
				return false
			}
		default:
			return false
		}
	}
	return true
}

// validNumericOID reports whether name is a dotted-decimal OID with at least two
// arcs and no empty or leading-zero arc.
func validNumericOID(name string) bool {
	arcs := strings.Split(name, ".")
	if len(arcs) < 2 {
		return false
	}
	for _, arc := range arcs {
		if arc == "" || (len(arc) > 1 && arc[0] == '0') {
			return false
		}
		for i := 0; i < len(arc); i++ {
			if arc[i] < '0' || arc[i] > '9' {
				return false
			}
		}
	}
	return true
}

// checkValidGroupMemberships verifies that every member ID listed in a group
// is non-empty.
func checkValidGroupMemberships(snap Snapshot) RuleResult {
	r := RuleResult{Rule: "valid_group_memberships", Passed: true}
	for _, g := range snap.Groups {
		for i, m := range g.Members {
			if strings.TrimSpace(m) == "" {
				r.Passed = false
				r.Message = appendMsg(r.Message, fmt.Sprintf("group %q has blank member at index %d", g.ID, i))
			}
		}
	}
	return r
}

// --- semantic rules ---

func runSemantic(snap Snapshot) []RuleResult {
	return []RuleResult{
		checkReferencedUsersExist(snap),
		checkNoCyclicGroups(snap),
		checkUsernamesUnique(snap),
		checkEmailFormatValid(snap),
	}
}

// checkReferencedUsersExist verifies that every member ID in every group
// refers to an existing user.
func checkReferencedUsersExist(snap Snapshot) RuleResult {
	r := RuleResult{Rule: "referenced_users_exist", Passed: true}
	userIDs := make(map[string]bool, len(snap.Users))
	for _, u := range snap.Users {
		userIDs[u.ID] = true
	}
	for _, g := range snap.Groups {
		for _, m := range g.Members {
			if !userIDs[m] {
				r.Passed = false
				r.Message = appendMsg(r.Message, fmt.Sprintf("group %q references unknown user %q", g.ID, m))
			}
		}
	}
	return r
}

// checkNoCyclicGroups detects cycles in group.Members referencing other groups.
// In v0.1 Members are user IDs (not group IDs), so any group ID in Members is a cycle.
func checkNoCyclicGroups(snap Snapshot) RuleResult {
	r := RuleResult{Rule: "no_cyclic_groups", Passed: true}
	groupIDs := make(map[string]bool, len(snap.Groups))
	for _, g := range snap.Groups {
		groupIDs[g.ID] = true
	}
	for _, g := range snap.Groups {
		for _, m := range g.Members {
			if groupIDs[m] {
				r.Passed = false
				r.Message = appendMsg(r.Message, fmt.Sprintf("group %q contains group member %q (cycles not allowed)", g.ID, m))
			}
		}
	}
	return r
}

// checkUsernamesUnique verifies no two users share the same username.
func checkUsernamesUnique(snap Snapshot) RuleResult {
	r := RuleResult{Rule: "usernames_unique", Passed: true}
	seen := make(map[string]string) // username -> first user id
	for _, u := range snap.Users {
		if first, dup := seen[u.Username]; dup {
			r.Passed = false
			r.Message = appendMsg(r.Message, fmt.Sprintf("duplicate username %q: users %q and %q", u.Username, first, u.ID))
		} else {
			seen[u.Username] = u.ID
		}
	}
	return r
}

// checkEmailFormatValid verifies that all non-empty user email addresses parse correctly.
func checkEmailFormatValid(snap Snapshot) RuleResult {
	r := RuleResult{Rule: "email_format_valid", Passed: true}
	for _, u := range snap.Users {
		if u.Email == "" {
			continue
		}
		if _, err := mail.ParseAddress(u.Email); err != nil {
			r.Passed = false
			r.Message = appendMsg(r.Message, fmt.Sprintf("user %q has invalid email %q: %v", u.ID, u.Email, err))
		}
	}
	return r
}

// --- helpers ---

func allPassed(results []RuleResult) bool {
	for _, r := range results {
		if !r.Passed {
			return false
		}
	}
	return true
}

func appendMsg(existing, msg string) string {
	if existing == "" {
		return msg
	}
	return existing + "; " + msg
}

// isValidNamingValue checks that a DN naming attribute value is non-empty
// and does not contain characters that would break an LDAP DN.
// The restricted characters are: , = + < > # ; \ "
func isValidNamingValue(v string) bool {
	if v == "" {
		return false
	}
	for _, c := range v {
		switch c {
		case ',', '=', '+', '<', '>', '#', ';', '\\', '"':
			return false
		}
	}
	return true
}