ata-validator 1.23.0 → 1.25.0

package/lib/scan-runtime.js

@@ -0,0 +1,158 @@
+'use strict';
+
+// Helpers shared by every generated scanner. The scanner reads a JSON document
+// straight out of the text and answers the schema from it, so anything here
+// that is laxer than JSON.parse turns into a document accepted that parsing
+// would have rejected. Each function below is written to the JSON grammar,
+// not to what looks close enough.
+
+// Four hex digits after a \u escape. JSON.parse throws without them.
+function hex4(s, i) {
+  for (let k = i; k < i + 4; k++) {
+    const c = s.charCodeAt(k);
+    if (c >= 48 && c <= 57) continue;
+    if (c >= 97 && c <= 102) continue;
+    if (c >= 65 && c <= 70) continue;
+    return false;
+  }
+  return true;
+}
+
+// The depth at which a skipped subtree stops being skipped and the caller
+// falls back to JSON.parse. V8's own parser gives up somewhere past this, and
+// the point is not to guess where: past this depth the scanner declines rather
+// than risk answering a document the parser would have refused.
+const MAX_SKIP_DEPTH = 512;
+
+const MALFORMED = -1;
+const TOO_DEEP = -2;
+
+// Validate one JSON value starting at `i` and return the index just past it,
+// MALFORMED if the text is not JSON, or TOO_DEEP. Iterative: a nesting depth
+// the schema knows nothing about must not be able to overflow the stack.
+function skipValue(s, i) {
+  const len = s.length;
+  // `stack` holds, per open container, 0 for an object and 1 for an array.
+  const stack = [];
+  let depth = 0;
+  for (;;) {
+    // --- one value
+    let c = s.charCodeAt(i);
+    while (c === 32 || c === 10 || c === 9 || c === 13) c = s.charCodeAt(++i);
+    if (c === 34) {
+      i = skipString(s, i);
+      if (i < 0) return MALFORMED;
+    } else if (c === 123 || c === 91) {
+      if (depth >= MAX_SKIP_DEPTH) return TOO_DEEP;
+      stack[depth++] = c === 123 ? 0 : 1;
+      i++;
+      c = s.charCodeAt(i);
+      while (c === 32 || c === 10 || c === 9 || c === 13) c = s.charCodeAt(++i);
+      if (c === (stack[depth - 1] === 0 ? 125 : 93)) { depth--; i++; }
+      else if (stack[depth - 1] === 0) {
+        // an object member starts with a key
+        if (c !== 34) return MALFORMED;
+        i = skipString(s, i);
+        if (i < 0) return MALFORMED;
+        c = s.charCodeAt(i);
+        while (c === 32 || c === 10 || c === 9 || c === 13) c = s.charCodeAt(++i);
+        if (c !== 58) return MALFORMED;
+        i++;
+        continue;
+      } else {
+        continue;
+      }
+    } else if (c === 116) {
+      if (s.charCodeAt(i + 1) !== 114 || s.charCodeAt(i + 2) !== 117 || s.charCodeAt(i + 3) !== 101) return MALFORMED;
+      i += 4;
+    } else if (c === 102) {
+      if (s.charCodeAt(i + 1) !== 97 || s.charCodeAt(i + 2) !== 108 || s.charCodeAt(i + 3) !== 115 || s.charCodeAt(i + 4) !== 101) return MALFORMED;
+      i += 5;
+    } else if (c === 110) {
+      if (s.charCodeAt(i + 1) !== 117 || s.charCodeAt(i + 2) !== 108 || s.charCodeAt(i + 3) !== 108) return MALFORMED;
+      i += 4;
+    } else {
+      i = skipNumber(s, i);
+      if (i < 0) return MALFORMED;
+    }
+
+    // --- close as many containers as the next punctuation closes
+    for (;;) {
+      if (depth === 0) return i;
+      let c2 = s.charCodeAt(i);
+      while (c2 === 32 || c2 === 10 || c2 === 9 || c2 === 13) c2 = s.charCodeAt(++i);
+      const inObject = stack[depth - 1] === 0;
+      if (c2 === 44) {
+        i++;
+        if (inObject) {
+          let c3 = s.charCodeAt(i);
+          while (c3 === 32 || c3 === 10 || c3 === 9 || c3 === 13) c3 = s.charCodeAt(++i);
+          if (c3 !== 34) return MALFORMED;
+          i = skipString(s, i);
+          if (i < 0) return MALFORMED;
+          c3 = s.charCodeAt(i);
+          while (c3 === 32 || c3 === 10 || c3 === 9 || c3 === 13) c3 = s.charCodeAt(++i);
+          if (c3 !== 58) return MALFORMED;
+          i++;
+        }
+        break; // read the next value
+      }
+      if (c2 === (inObject ? 125 : 93)) { depth--; i++; continue; }
+      return MALFORMED;
+    }
+    if (i > len) return MALFORMED;
+  }
+}
+
+// `i` is at the opening quote; returns the index just past the closing one.
+function skipString(s, i) {
+  i++;
+  for (;;) {
+    const c = s.charCodeAt(i);
+    if (c === 34) return i + 1;
+    if (c === 92) {
+      const e = s.charCodeAt(i + 1);
+      if (e === 117) {
+        if (!hex4(s, i + 2)) return -1;
+        i += 6;
+        continue;
+      }
+      if (e === 34 || e === 92 || e === 47 || e === 98 || e === 102 || e === 110 || e === 114 || e === 116) { i += 2; continue; }
+      return -1;
+    }
+    // NaN at end of input fails this too, which is the unterminated case.
+    if (!(c >= 32)) return -1;
+    i++;
+  }
+}
+
+function skipNumber(s, i) {
+  let c = s.charCodeAt(i);
+  if (c === 45) c = s.charCodeAt(++i);
+  if (c === 48) c = s.charCodeAt(++i);
+  else if (c >= 49 && c <= 57) { do { c = s.charCodeAt(++i); } while (c >= 48 && c <= 57); }
+  else return -1;
+  if (c === 46) {
+    c = s.charCodeAt(++i);
+    if (!(c >= 48 && c <= 57)) return -1;
+    do { c = s.charCodeAt(++i); } while (c >= 48 && c <= 57);
+  }
+  if (c === 101 || c === 69) {
+    c = s.charCodeAt(++i);
+    if (c === 43 || c === 45) c = s.charCodeAt(++i);
+    if (!(c >= 48 && c <= 57)) return -1;
+    do { c = s.charCodeAt(++i); } while (c >= 48 && c <= 57);
+  }
+  return i;
+}
+
+// The decoded value of a string span, for the checks that need the string
+// itself. `p` is just past the opening quote, `e` is at the closing one.
+// An escaped span is decoded by the parser, so the result is what JSON.parse
+// would have produced for that member and nothing subtler.
+function span(s, p, e, escaped) {
+  if (!escaped) return s.slice(p, e);
+  return JSON.parse(s.slice(p - 1, e + 1));
+}
+
+module.exports = { hex4, skipValue, skipString, skipNumber, span, MALFORMED, TOO_DEEP, MAX_SKIP_DEPTH };

package/lib/schema-hash.js

@@ -0,0 +1,39 @@
+'use strict';
+
+// A stable content hash for a schema, so a compiled artifact can say which
+// schema it came from and a build can detect staleness by comparing hashes
+// instead of embedding its own. The hash is over a canonical JSON form
+// (object keys sorted at every level), so the same schema hashes the same
+// however its keys were ordered, and it is FNV-1a with two independent
+// bases, 16 hex characters. This is an integrity aid, not a security
+// boundary: it detects drift, it does not authenticate anything.
+
+function canonical (value) {
+  if (value === null || typeof value !== 'object') return JSON.stringify(value);
+  if (Array.isArray(value)) return '[' + value.map(canonical).join(',') + ']';
+  const keys = Object.keys(value).sort();
+  const parts = [];
+  for (const k of keys) {
+    if (value[k] === undefined) continue;
+    parts.push(JSON.stringify(k) + ':' + canonical(value[k]));
+  }
+  return '{' + parts.join(',') + '}';
+}
+
+function fnv1a (str, seed) {
+  let h = seed >>> 0;
+  for (let i = 0; i < str.length; i++) {
+    h ^= str.charCodeAt(i);
+    h = Math.imul(h, 0x01000193) >>> 0;
+  }
+  return h >>> 0;
+}
+
+function schemaHash (schema) {
+  const text = canonical(schema);
+  const a = fnv1a(text, 0x811c9dc5);
+  const b = fnv1a(text, 0xcbf29ce4);
+  return a.toString(16).padStart(8, '0') + b.toString(16).padStart(8, '0');
+}
+
+module.exports = { schemaHash };

package/lib/strict-check.js

@@ -32,6 +32,33 @@ function specKeywords() {
   return SPEC_KEYWORDS;
 }
 
+// Which instance type each constraining keyword acts on. A keyword sitting on
+// a node whose `type` excludes it is inert: `minimum` on a string can never
+// fire, so the rule the author meant is absent, which is the same fail-open
+// class as a typo. Only nodes with an explicit `type` are judged, since
+// without one the keyword legitimately waits for matching data.
+const KEYWORD_TYPES = new Map(Object.entries({
+  minLength: ['string'], maxLength: ['string'], pattern: ['string'],
+  minimum: ['number'], maximum: ['number'],
+  exclusiveMinimum: ['number'], exclusiveMaximum: ['number'], multipleOf: ['number'],
+  items: ['array'], prefixItems: ['array'], additionalItems: ['array'],
+  minItems: ['array'], maxItems: ['array'], uniqueItems: ['array'],
+  contains: ['array'], minContains: ['array'], maxContains: ['array'], unevaluatedItems: ['array'],
+  properties: ['object'], patternProperties: ['object'], additionalProperties: ['object'],
+  required: ['object'], minProperties: ['object'], maxProperties: ['object'],
+  propertyNames: ['object'], dependentRequired: ['object'], dependentSchemas: ['object'],
+  unevaluatedProperties: ['object'],
+}));
+
+function typeAllows(declared, wanted) {
+  const list = Array.isArray(declared) ? declared : [declared];
+  for (const t of list) {
+    if (t === wanted) return true;
+    if (wanted === 'number' && t === 'integer') return true;
+  }
+  return false;
+}
+
 // Where subschemas live, so the walk knows a key under `properties` is a
 // property name and a key directly on a schema object is a keyword.
 const SCHEMA_MAPS = new Set(['properties', 'patternProperties', '$defs', 'definitions', 'dependentSchemas']);
@@ -113,6 +140,32 @@ function checkSchemaStrict(root, options) {
         problems.push({ path: at, message: `$ref "${value}" does not resolve in this document` });
         continue;
       }
+      // An inert keyword: the node's own type excludes the one this keyword
+      // acts on, so it can never fire.
+      if (typeof node.type === 'string' || Array.isArray(node.type)) {
+        const acts = KEYWORD_TYPES.get(key);
+        if (acts && !acts.some((t) => typeAllows(node.type, t))) {
+          problems.push({
+            path: at,
+            message: `"${key}" has no effect here: it applies to ${acts.join('/')} and this node's type is ${JSON.stringify(node.type)}`,
+          });
+          continue;
+        }
+      }
+      // `required` naming a property that `properties` does not define, on a
+      // node that admits no other properties: no document can satisfy it, so
+      // the validator built from it rejects everything, silently.
+      if (key === 'required' && Array.isArray(value) && node.properties && typeof node.properties === 'object'
+          && node.additionalProperties === false && !node.patternProperties) {
+        for (const name of value) {
+          if (typeof name === 'string' && !Object.prototype.hasOwnProperty.call(node.properties, name)) {
+            problems.push({
+              path: at,
+              message: `required property "${name}" is not defined in properties and additionalProperties is false, so nothing can satisfy this schema`,
+            });
+          }
+        }
+      }
       if (DATA_VALUED.has(key)) continue;
       if (SCHEMA_MAPS.has(key)) {
         if (value !== null && typeof value === 'object' && !Array.isArray(value)) {

package/lib/version.js

@@ -7,4 +7,4 @@
 //
 // Kept in lockstep with package.json by `tests/test_version_sync.js`.
 
-module.exports = '1.23.0';
+module.exports = '1.25.0';

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ata-validator",
-  "version": "1.23.0",
+  "version": "1.25.0",
   "description": "JSON Schema validation that compiles for speed and still runs where code generation is blocked. Compiled and interpreted engines answer identically at 100% of the official suite. TypeScript inference, Standard Schema V1, and a build step that emits dependency-free modules.",
   "main": "index.js",
   "module": "index.mjs",
@@ -51,7 +51,7 @@
     "release:check": "node scripts/regen-safe-regex-source.js && node tests/test_pack_purity.js && node scripts/check-doc-coverage.js && node tests/test_error_codes_lock.js && node tests/test_safe_regex_source_sync.js && node tests/test_version_sync.js",
     "build": "cmake-js build --target ata",
     "rebuild": "cmake-js rebuild --target ata",
-    "test": "node test.js && node tests/test_removed_aot_methods.js && node tests/test_no_native.js && node tests/test_no_eval.js && node tests/test_property_dependencies.js && node tests/test_v1_dialect.js && node tests/test_buffer_path_parity.js && node tests/test_buffer_gate.js && node tests/test_buffer_reject_cost.js && node tests/test_nan_verdict.js && node tests/test_remove_additional_nested.js && node tests/test_exclusive_bounds.js && node tests/test_engine_differential.js && node tests/test_error_shape_differential.js && node tests/test_output_format.js && node tests/test_retry_message.js && node tests/test_describe_schema.js && node tests/test_aot_parse.js && node tests/test_draft7_semantics.js && node tests/test_metaschema_ref.js && node tests/test_pure_js_unsupported.js && node tests/test_native_load_order.js && node tests/test_pack_purity.js && node tests/test_make_native_package.js && node tests/test_browser_nofs.js && node tests/test_browser_imports_guard.js && node tests/test_version_sync.js && node tests/test_native_loaded.js && node tests/test_safe_regex_source_sync.js && node tests/test_t_builder.js && node tests/test_async_refine.js && node tests/test_safe_regex.js && node tests/test_safe_regex_integration.js && node tests/test_aot_build.js && node tests/test_aot_differential.js && node tests/test_aot_cli_build.js && node tests/test_aot_cli_smoke.js && node tests/test_bundle_standalone.js && node tests/test_standalone_anyof.js && node tests/test_standalone_formats.js && node tests/test_aot_format_mode.js && node tests/test_aot_additional_props_errors.js && node tests/test_id_anchor_refs.js && node tests/test_engine_routing.js && node tests/test_compile_cache_order.js && node tests/test_engine_diagnostic.js && node tests/test_format_engine_parity.js && node tests/test_uri_helper_parity.js && node tests/test_formats_single_pass.js && node tests/test_format_single_error.js && node tests/test_defs_pointer_alias.js && node tests/test_cross_doc_root_ref.js && node tests/test_codegen_entrypoint_agreement.js && node tests/test_hybrid_agreement.js && node tests/test_codegen_edge_shapes.js && node tests/test_ajv_errors.js && node tests/test_custom_keywords.js && node tests/test_strict_schema.js && node tests/test_aot_external_checks.js && node tests/test_ajv_parity.js && node tests/test_user_format_error_path.js && node tests/test_unevaluated_error_path.js && node tests/test_unevaluated_error_shape.js && node tests/test_pattern_properties_errors.js && node tests/test_additional_properties_scaling.js && node tests/test_no_input_mutation.js && node tests/test_typed_validator_runner.js && node tests/test_define_schema.js && node tests/test_error_codes_lock.js && node tests/test_error_code_lookup.js && node tests/test_error_order.js && node tests/test_error_order_ordinal.js && node tests/test_rejection_shape.js && node tests/test_lazy_normalization.js && node tests/test_value_equality.js && node tests/test_vocabulary.js && node tests/test_schema_scan.js && node tests/test_lazy_errors.js && node tests/test_lazy_instance.js && node tests/test_cyclic_input.js && node tests/test_native_error_codes.js && node tests/test_verdict_preprocess.js && node tests/test_plan_compiler.js && node tests/test_nullable.js && node tests/test_validate_and_parse.js && node tests/test_validate_data.js && node tests/test_enrich_error.js && node tests/test_enrich_received.js && node tests/test_rich_errors_optout.js && node tests/test_error_messages.js && node tests/test_source_positions.js && node tests/fuzz_positions.js && node tests/test_malformed_json_termination.js && node tests/test_data_positions.js && node tests/test_render_shared.js && node tests/test_renderers.js && node tests/test_additive_fields.js && node tests/test_diagnostic_source.js && node tests/test_diagnose.js && node tests/test_correlate.js && node tests/test_diagnostics_score.js && node tests/test_runtime_error_dx.js && node tests/test_aot_error_dx.js && node tests/test_abort_early.js && node tests/test_branch_collapse.js && node tests/test_suggestions.js && node tests/test_cli_validate.js && node tests/test_cli_version.js && node benchmark/bench_aot_size.mjs",
+    "test": "node test.js && node tests/test_removed_aot_methods.js && node tests/test_no_native.js && node tests/test_no_eval.js && node tests/test_property_dependencies.js && node tests/test_v1_dialect.js && node tests/test_buffer_path_parity.js && node tests/test_buffer_gate.js && node tests/test_scanner_differential.js && node tests/test_buffer_reject_cost.js && node tests/test_nan_verdict.js && node tests/test_remove_additional_nested.js && node tests/test_exclusive_bounds.js && node tests/test_engine_differential.js && node tests/test_error_shape_differential.js && node tests/test_output_format.js && node tests/test_retry_message.js && node tests/test_describe_schema.js && node tests/test_aot_parse.js && node tests/test_draft7_semantics.js && node tests/test_metaschema_ref.js && node tests/test_pure_js_unsupported.js && node tests/test_native_load_order.js && node tests/test_pack_purity.js && node tests/test_make_native_package.js && node tests/test_browser_nofs.js && node tests/test_browser_imports_guard.js && node tests/test_version_sync.js && node tests/test_native_loaded.js && node tests/test_safe_regex_source_sync.js && node tests/test_t_builder.js && node tests/test_async_refine.js && node tests/test_safe_regex.js && node tests/test_safe_regex_integration.js && node tests/test_aot_build.js && node tests/test_aot_differential.js && node tests/test_aot_cli_build.js && node tests/test_aot_cli_smoke.js && node tests/test_bundle_standalone.js && node tests/test_standalone_anyof.js && node tests/test_standalone_formats.js && node tests/test_aot_format_mode.js && node tests/test_aot_additional_props_errors.js && node tests/test_id_anchor_refs.js && node tests/test_engine_routing.js && node tests/test_compile_cache_order.js && node tests/test_engine_diagnostic.js && node tests/test_format_engine_parity.js && node tests/test_uri_helper_parity.js && node tests/test_formats_single_pass.js && node tests/test_format_single_error.js && node tests/test_defs_pointer_alias.js && node tests/test_cross_doc_root_ref.js && node tests/test_codegen_entrypoint_agreement.js && node tests/test_hybrid_agreement.js && node tests/test_codegen_edge_shapes.js && node tests/test_ajv_errors.js && node tests/test_custom_keywords.js && node tests/test_strict_schema.js && node tests/test_aot_external_checks.js && node tests/test_ajv_parity.js && node tests/test_user_format_error_path.js && node tests/test_unevaluated_error_path.js && node tests/test_unevaluated_error_shape.js && node tests/test_pattern_properties_errors.js && node tests/test_additional_properties_scaling.js && node tests/test_no_input_mutation.js && node tests/test_typed_validator_runner.js && node tests/test_define_schema.js && node tests/test_error_codes_lock.js && node tests/test_error_code_lookup.js && node tests/test_error_order.js && node tests/test_error_order_ordinal.js && node tests/test_rejection_shape.js && node tests/test_lazy_normalization.js && node tests/test_value_equality.js && node tests/test_vocabulary.js && node tests/test_schema_scan.js && node tests/test_lazy_errors.js && node tests/test_lazy_instance.js && node tests/test_cyclic_input.js && node tests/test_native_error_codes.js && node tests/test_verdict_preprocess.js && node tests/test_plan_compiler.js && node tests/test_nullable.js && node tests/test_validate_and_parse.js && node tests/test_validate_data.js && node tests/test_enrich_error.js && node tests/test_enrich_received.js && node tests/test_rich_errors_optout.js && node tests/test_error_messages.js && node tests/test_source_positions.js && node tests/fuzz_positions.js && node tests/test_malformed_json_termination.js && node tests/test_data_positions.js && node tests/test_file_positions.js && node tests/test_schema_hash.js && node tests/test_render_shared.js && node tests/test_renderers.js && node tests/test_additive_fields.js && node tests/test_diagnostic_source.js && node tests/test_diagnose.js && node tests/test_correlate.js && node tests/test_diagnostics_score.js && node tests/test_runtime_error_dx.js && node tests/test_aot_error_dx.js && node tests/test_abort_early.js && node tests/test_branch_collapse.js && node tests/test_suggestions.js && node tests/test_cli_validate.js && node tests/test_cli_version.js && node benchmark/bench_aot_size.mjs",
     "bench:size": "node benchmark/bench_aot_size.mjs",
     "test:suite": "node tests/run_suite.js && node tests/run_suite.js draft7 && node tests/run_suite.js v1",
     "test:compat": "node tests/test_compat.js",
@@ -122,13 +122,13 @@
     "LICENSE"
   ],
   "optionalDependencies": {
-    "@ata-validator/native-darwin-arm64": "1.23.0",
-    "@ata-validator/native-darwin-x64": "1.23.0",
-    "@ata-validator/native-linux-arm64-gnu": "1.23.0",
-    "@ata-validator/native-linux-arm64-musl": "1.23.0",
-    "@ata-validator/native-linux-x64-gnu": "1.23.0",
-    "@ata-validator/native-linux-x64-musl": "1.23.0",
-    "@ata-validator/native-win32-x64": "1.23.0"
+    "@ata-validator/native-darwin-arm64": "1.25.0",
+    "@ata-validator/native-darwin-x64": "1.25.0",
+    "@ata-validator/native-linux-arm64-gnu": "1.25.0",
+    "@ata-validator/native-linux-arm64-musl": "1.25.0",
+    "@ata-validator/native-linux-x64-gnu": "1.25.0",
+    "@ata-validator/native-linux-x64-musl": "1.25.0",
+    "@ata-validator/native-win32-x64": "1.25.0"
   },
   "peerDependencies": {
     "yaml": "^2.0.0"