adds manage.sh.

linted

.gitignore

@@ -1,3 +1,4 @@
 api-raml/
-*article-json/
+*article-json*/
 validate-article-json
+linux-amd64*

go.mod

@@ -1,6 +1,6 @@
 module validate-article-json
 
-go 1.20
+go 1.21
 
 require (
 	github.com/santhosh-tekuri/jsonschema/v5 v5.3.1

go.sum

@@ -10,6 +10,7 @@ github.com/sourcegraph/conc v0.3.0/go.mod h1:Sdozi7LEKbFPqYX2/J+iBAM6HpqSLTASQIK
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
 github.com/stretchr/testify v1.8.1 h1:w7B6lhMri9wdJUVmEZPGGhZzrYTPvgJArz7wNPgYKsk=
+github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
 github.com/tidwall/gjson v1.15.0 h1:5n/pM+v3r5ujuNl4YLZLsQ+UE5jlkLVm7jMzT5Mpolw=
 github.com/tidwall/gjson v1.15.0/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
 github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA=
@@ -22,3 +23,4 @@ go.uber.org/atomic v1.7.0/go.mod h1:fEN4uk6kAWBTFdckzkM89CLk9XfWZrxpCo0nPH17wJc=
 go.uber.org/multierr v1.9.0 h1:7fIwc/ZtS0q++VgcfqFDxSBZVv/Xo49/SYnDFupUwlI=
 go.uber.org/multierr v1.9.0/go.mod h1:X2jQV1h+kxSjClGpnseKVIxpmcjrj7MNnI0bnlfKTVQ=
 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

@@ -9,6 +9,8 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
+	"runtime"
+	"slices"
 	"strconv"
 	"strings"
 	"time"
@@ -48,7 +50,7 @@ func configure_validator() map[string]Foo {
 	schema_map := map[string]Foo{}
 	for label, path := range schema_file_list {
 		rdr, err := loader(path)
-		panic_on_err(err, fmt.Sprintf("loading '%s' schema file: ", label, path))
+		panic_on_err(err, fmt.Sprintf("loading '%s' schema file: %s", label, path))
 		err = c.AddResource(label, rdr)
 		panic_on_err(err, "adding schema to compiler: "+label)
 		schema, err := c.Compile(label)
@@ -190,40 +192,59 @@ func long_validation_error(err error) {
 	fmt.Printf("%#v\n", err)
 }
 
+func die(b bool, msg string) {
+	if b {
+		fmt.Println(msg)
+		os.Exit(1)
+	}
+}
+
 func main() {
+	var err error
 	args := os.Args[1:]
+
 	// required first argument is path to an xml document or a directory of xml.
+	die(len(args) < 1, "path to article-json file or directory of files required")
 	input_path := args[0]
+	die(!path_exists(input_path), "input path does not exist")
+
+	// optional second argument is sample size
+	sample_size := 1000
 
-	if !path_exists(input_path) {
-		panic("input path does not exist")
+	if len(args) == 2 {
+		sample_size, err = strconv.Atoi(args[1])
+		die(err != nil, "second argument is not an integer. use -1 for 'all' articles. default is 1000.")
 	}
+
 	if path_is_dir(input_path) {
 		// validate many
 		path_list, err := os.ReadDir(input_path)
 		panic_on_err(err, "reading contents of directory: "+input_path)
-		sample_size := 1000
-		if len(args) == 2 {
-			// optional second argument is sample size
-			sample_size, err = strconv.Atoi(args[1])
-			panic_on_err(err, "converting sample size to an integer")
-		}
 
 		if sample_size == -1 || sample_size > len(path_list) {
 			// validate all files in dir
 			sample_size = len(path_list)
 		}
 
-		// filter directories from path listing
+		// filter any directories from path listing
 		file_list := []string{}
 		for _, path := range path_list[:sample_size] {
 			if !path.IsDir() {
-				file_list = append(file_list, input_path+path.Name())
+				file_list = append(file_list, filepath.Join(input_path, path.Name()))
 			}
 		}
 
+		slices.Sort(file_list)    // sort strings
+		slices.Reverse(file_list) // DESC
+
 		capture_errors := false
-		num_workers := 10 // todo: set to num cpus
+		num_workers := 1
+		if runtime.NumCPU() > 2 {
+			// on local machine with 12 cores average validation time on first
+			// 1k articles improves from ~450ms to ~350ms at 10 cores.
+			// feel free to tweak/remove.
+			num_workers = runtime.NumCPU() - 2
+		}
 		p := pool.NewWithResults[Result]().WithMaxGoroutines(num_workers)
 
 		start_time := time.Now()
@@ -267,7 +288,7 @@ func main() {
 		}
 
 	} else {
-		// assume file or a link pointing to a file, validate single
+		// validate single
 		capture_errors := true
 		result := validate_article(input_path, capture_errors)
 		if !result.Success {

manage.sh

@@ -0,0 +1,57 @@
+#!/bin/bash
+set -e
+
+cmd="$1"
+
+if test ! "$cmd"; then
+    echo "command required."
+    echo
+    echo "available commands:"
+    echo "  build        build project"
+    echo "  release      build project for distribution"
+    echo "  update-deps  update project dependencies"
+    exit 1
+fi
+
+shift
+rest=$*
+
+if test "$cmd" = "build"; then
+    # CGO_ENABLED=0 skips CGO and linking against glibc to build static binaries.
+    # -v 'verbose'
+    CGO_ENABLED=0 go build \
+        -v
+    exit 0
+
+elif test "$cmd" = "release"; then
+    # GOOS is 'Go OS' and is being explicit in which OS to build for.
+    # CGO_ENABLED=0 skips CGO and linking against glibc to build static binaries.
+    # ld -s is 'disable symbol table'
+    # ld -w is 'disable DWARF generation'
+    # -trimpath removes leading paths to source files
+    # -v 'verbose'
+    # -o 'output'
+    GOOS=linux CGO_ENABLED=0 go build \
+        -ldflags="-s -w" \
+        -trimpath \
+        -v \
+        -o linux-amd64
+    sha256sum linux-amd64 > linux-amd64.sha256
+    echo ---
+    echo "wrote linux-amd64"
+    echo "wrote linux-amd64.sha256"
+    exit 0
+
+elif test "$cmd" = "update-deps"; then
+    # -u 'update modules [...] to use newer minor or patch releases when available'
+    go get -u
+    go mod tidy
+    ./manage.sh build
+    exit 0
+
+# ...
+
+fi
+
+echo "unknown command: $cmd"
+exit 1