fix: zig platform data lost in cache, expand classifier coverage

- Fix zig Platform.Size type: string in upstream JSON (json.Number)
- Fix zig Platforms json tag: was "-" (dropped in cache), now serializes
- Add riscv64, loong64, armv5 archs to buildmeta and classifier
- Add mipsle, mips64le arch detection patterns
- Add plan9 OS detection
- Add "mac" (word boundary) → darwin OS detection
- Add armhf → armv7, arm7 → armv7 patterns
- Infer Linux from .deb/.rpm format when OS absent
- Filter source archives and buildable-artifact meta-assets

Batch 2 tested: zig (246), flutter (2082), chromedriver (10300),
terraform (5550), julia (1783), iterm2 (262), mariadb (207), gpg (45)
serviceman/aliasman: 0 (source-only, no binary assets)

CAT-RULES.md

@@ -57,6 +57,28 @@ source archives (`_src.tar.gz`), and `buildable-artifact`.
 - Node "odd major = beta" heuristic — v15, v17, v19, v21, v23 are "current" not LTS
 - Go version prefix: stripped `go` from `go1.23.6` → `1.23.6` for clean parsing
 
+## Batch 2 (zig, flutter, chromedriver, terraform, julia, iterm2, mariadb, gpg, serviceman, aliasman)
+
+### Zig Fetcher Fix
+
+The zig upstream API returns `"size"` as a JSON string, not a number.
+Changed `Platform.Size` from `int64` to `json.Number` to avoid unmarshal failures.
+Also changed `Platforms` tag from `json:"-"` to `json:"platforms,omitempty"` so
+platform data is preserved in cache.
+
+### Source-Only Packages
+
+serviceman and aliasman have GitHub releases with empty `assets:[]`. These are
+source-only repos that install via `go install` or script download, not binary
+releases. The classifier correctly produces 0 distributables for them — they
+don't belong in the binary CSV.
+
+### Flutter Arch Detection
+
+Early Flutter releases (pre-2020) had no arch-specific builds — single
+platform SDK. No arch in filename → empty arch in CSV. This is correct;
+the installer would default to x86_64 on supported platforms.
+
 ### TODO for Next Batches
 
 - Hugo "extended" variant should be captured in `extra` column

cmd/classify/main.go

@@ -537,9 +537,9 @@ type zigRelease struct {
 }
 
 type zigPlatform struct {
-	Tarball string `json:"tarball"`
-	Shasum  string `json:"shasum"`
-	Size    int64  `json:"size"`
+	Tarball string      `json:"tarball"`
+	Shasum  string      `json:"shasum"`
+	Size    json.Number `json:"size"`
 }
 
 func classifyZigDist(pkg string, d *rawcache.Dir) ([]Dist, error) {
@@ -550,33 +550,23 @@ func classifyZigDist(pkg string, d *rawcache.Dir) ([]Dist, error) {
 
 	var dists []Dist
 	for _, data := range releases {
-		// Parse the raw JSON to get version, date, and platform entries.
-		var raw map[string]json.RawMessage
-		if err := json.Unmarshal(data, &raw); err != nil {
+		// Parse the cached JSON which has version, date, platforms.
+		var rel struct {
+			Version   string                  `json:"version"`
+			Date      string                  `json:"date"`
+			Platforms map[string]zigPlatform   `json:"platforms"`
+		}
+		if err := json.Unmarshal(data, &rel); err != nil {
 			continue
 		}
 
-		var version, date string
-		if v, ok := raw["version"]; ok {
-			json.Unmarshal(v, &version)
-		}
-		if d, ok := raw["date"]; ok {
-			json.Unmarshal(d, &date)
-		}
-
 		channel := "stable"
-		if strings.Contains(version, "+") || strings.Contains(version, "-") || !strings.Contains(version, ".") {
+		if strings.Contains(rel.Version, "+") || strings.Contains(rel.Version, "-") || !strings.Contains(rel.Version, ".") {
 			channel = "beta"
 		}
 
-		for key, val := range raw {
-			switch key {
-			case "version", "date", "notes", "src":
-				continue
-			}
-
-			var plat zigPlatform
-			if err := json.Unmarshal(val, &plat); err != nil || plat.Tarball == "" {
+		for key, plat := range rel.Platforms {
+			if plat.Tarball == "" {
 				continue
 			}
 
@@ -592,7 +582,7 @@ func classifyZigDist(pkg string, d *rawcache.Dir) ([]Dist, error) {
 
 			dists = append(dists, Dist{
 				Package:  pkg,
-				Version:  version,
+				Version:  rel.Version,
 				Channel:  channel,
 				OS:       os_,
 				Arch:     arch,
@@ -600,8 +590,8 @@ func classifyZigDist(pkg string, d *rawcache.Dir) ([]Dist, error) {
 				Download: plat.Tarball,
 				Filename: filepath.Base(plat.Tarball),
 				SHA256:   plat.Shasum,
-				Size:     plat.Size,
-				Date:     date,
+				Size:     zigSize(plat.Size),
+				Date:     rel.Date,
 			})
 		}
 	}
@@ -633,6 +623,11 @@ func normalizeZigArch(a string) string {
 	}
 }
 
+func zigSize(n json.Number) int64 {
+	v, _ := n.Int64()
+	return v
+}
+
 func normalizeZigOS(o string) string {
 	switch o {
 	case "macos":

internal/releases/zigdist/zigdist.go

@@ -22,14 +22,14 @@ type Release struct {
 	Version   string              `json:"version"` // set by us from the key or inner "version" field
 	Date      string              `json:"date"`
 	Notes     string              `json:"notes,omitempty"`
-	Platforms map[string]Platform `json:"-"` // "x86_64-linux" → Platform
+	Platforms map[string]Platform `json:"platforms,omitempty"` // "x86_64-linux" → Platform
 }
 
 // Platform is one downloadable artifact for a specific arch-os combo.
 type Platform struct {
-	Tarball string `json:"tarball"`
-	Shasum  string `json:"shasum"`
-	Size    int64  `json:"size"`
+	Tarball string      `json:"tarball"`
+	Shasum  string      `json:"shasum"`
+	Size    json.Number `json:"size"` // upstream sends as string
 }
 
 // Fetch retrieves the Zig release index.