coraza: ship rules-catalog.json generated from bundled CRS at build time

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

coraza-spoa/Dockerfile

@@ -27,6 +27,16 @@ RUN git clone --depth 1 --branch "${CORAZA_SPOA_VERSION}" \
     && go mod download \
     && CGO_ENABLED=0 go build -trimpath -ldflags='-s -w' -o /out/coraza-spoa .
 
+# Catalog extractor: walks the bundled CRS at build time and emits
+# rules-catalog.json so WHP's UI can render rule metadata without parsing
+# .conf files at runtime. Uses the SAME coraza-coreruleset version pin as
+# the coraza-spoa binary above (drift between the two would mislabel rules).
+FROM repo.anhonesthost.net/cloud-hosting-platform/golang:1.25 AS catalog
+WORKDIR /src
+COPY catalog-extractor/ .
+RUN go build -trimpath -o /out/catalog-extractor . \
+    && /out/catalog-extractor > /out/rules-catalog.json
+
 # Distroless runtime: no shell, no package manager, no /tmp by default —
 # smallest attack surface for an exposed service. Audit log directory is
 # bind-mounted; coraza-spoa writes to it via direct file I/O (no shell needed).
@@ -41,6 +51,7 @@ COPY config.yaml /etc/coraza-spoa/config.yaml
 COPY overrides.conf /etc/coraza/overrides.conf
 COPY local-overrides.conf /etc/coraza/local-overrides.conf
 COPY host-exceptions/ /etc/coraza/host-exceptions/
+COPY --from=catalog /out/rules-catalog.json /etc/coraza/rules-catalog.json
 
 # Audit log directory — bind-mount /var/log/coraza:/var/log/coraza from host
 # so logs persist across container restarts and AI Monitor can tail them.

coraza-spoa/catalog-extractor/go.mod

@@ -0,0 +1,7 @@
+module catalog-extractor
+
+go 1.25
+
+require github.com/corazawaf/coraza-coreruleset/v4 v4.25.0
+
+require github.com/magefile/mage v1.17.0 // indirect

coraza-spoa/catalog-extractor/go.sum

@@ -0,0 +1,12 @@
+github.com/corazawaf/coraza-coreruleset/v4 v4.25.0 h1:tqFO1lfVpTiyWtlN618OXpZMfw+nnN0Q4///W5W+/HM=
+github.com/corazawaf/coraza-coreruleset/v4 v4.25.0/go.mod h1:nRuGXITxOPvsLF2VxaTB7pYok8QB8BitX3ZenXcUryY=
+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/magefile/mage v1.17.0 h1:dS4tkq997Ism03akafC8509iqDjeE7TNTexI25Y7sXM=
+github.com/magefile/mage v1.17.0/go.mod h1:Yj51kqllmsgFpvvSzgrZPK9WtluG3kUhFaBUVLo4feA=
+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/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
+github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

coraza-spoa/catalog-extractor/main.go

@@ -0,0 +1,80 @@
+package main
+
+import (
+	"encoding/json"
+	"fmt"
+	"io/fs"
+	"os"
+	"regexp"
+	"strconv"
+	"strings"
+
+	crs "github.com/corazawaf/coraza-coreruleset/v4"
+)
+
+type Rule struct {
+	ID       int      `json:"id"`
+	Msg      string   `json:"msg"`
+	Severity string   `json:"severity"`
+	Tags     []string `json:"tags"`
+	File     string   `json:"file"`
+}
+
+var (
+	idRe       = regexp.MustCompile(`(?i)\bid:'?(\d+)'?`)
+	msgRe      = regexp.MustCompile(`(?i)\bmsg:'([^']+)'`)
+	severityRe = regexp.MustCompile(`(?i)\bseverity:'?([A-Z]+)'?`)
+	tagRe      = regexp.MustCompile(`(?i)\btag:'([^']+)'`)
+)
+
+func main() {
+	out := []Rule{}
+	err := fs.WalkDir(crs.FS, ".", func(path string, d fs.DirEntry, err error) error {
+		if err != nil || d.IsDir() {
+			return err
+		}
+		if !strings.HasSuffix(path, ".conf") {
+			return nil
+		}
+		b, err := fs.ReadFile(crs.FS, path)
+		if err != nil {
+			return err
+		}
+		// Coalesce backslash-continuation lines so id/msg/etc on the same
+		// logical rule are visible to the per-line scanner.
+		text := regexp.MustCompile(`\\\s*\n\s*`).ReplaceAllString(string(b), " ")
+		for _, line := range strings.Split(text, "\n") {
+			line = strings.TrimSpace(line)
+			if !strings.HasPrefix(line, "SecRule") && !strings.HasPrefix(line, "SecAction") {
+				continue
+			}
+			m := idRe.FindStringSubmatch(line)
+			if m == nil {
+				continue
+			}
+			id, _ := strconv.Atoi(m[1])
+			r := Rule{ID: id, File: path}
+			if mm := msgRe.FindStringSubmatch(line); mm != nil {
+				r.Msg = mm[1]
+			}
+			if mm := severityRe.FindStringSubmatch(line); mm != nil {
+				r.Severity = strings.ToLower(mm[1])
+			}
+			for _, mm := range tagRe.FindAllStringSubmatch(line, -1) {
+				r.Tags = append(r.Tags, mm[1])
+			}
+			out = append(out, r)
+		}
+		return nil
+	})
+	if err != nil {
+		fmt.Fprintln(os.Stderr, err)
+		os.Exit(1)
+	}
+	enc := json.NewEncoder(os.Stdout)
+	enc.SetIndent("", "  ")
+	if err := enc.Encode(out); err != nil {
+		fmt.Fprintln(os.Stderr, err)
+		os.Exit(1)
+	}
+}