ata-validator 1.53.0 → 1.54.0

package/README.md

@@ -298,6 +298,13 @@ for.
 process is not a cost anyone notices, and the runtime API is the simpler thing to reach
 for. Speed is the same either way once warm.
 
+**On Node 22 or later, a process that starts often can keep V8's compiled code between
+starts.** Point `NODE_COMPILE_CACHE` at a directory that survives the restart, or call
+`module.enableCompileCache()` in your entry. Measured on an Apple M4 Pro, Node 25.2.1:
+loading ata goes from 4.9 to 2.7 ms, and a fresh process reaches its first validated
+document in 5.3 ms instead of 7.8. This is Node's feature, it covers every module the
+process loads, and ata does not turn it on for you.
+
 **In a browser, on an edge runtime, or anywhere cold starts are charged, compile.** This
 is where the difference is the whole story, and it is also where `new Function` is often
 blocked outright, which the compiled module does not need. With a bundler, adding `@ata-project/unplugin`

package/compat.js

@@ -21,6 +21,9 @@ const { resolvePointer } = require('./lib/pointer.js');
 // `strictTuples` and `strictRequired` are accepted and ignored.
 
 const { Validator } = require('./index');
+// The interpreted engine's coercion where each type is checked and its
+// discriminator, which only compat asks for (see lib/interpreter-compat.js).
+require('./lib/interpreter-core')._setCompat(require('./lib/interpreter-compat'));
 const { METASCHEMAS } = require('./lib/metaschemas');
 const { normalizeExclusiveBounds } = require('./lib/draft7');
 const { createShaper, asReferenceKeyword } = require('./lib/compat-errors');
@@ -680,8 +683,16 @@ function fragmentKey(key) {
 // What a schema holds anywhere below it, read from the walk normalization
 // makes of it anyway (lib/schema-scan.js), which remembers it per object.
 const _scan = require('./lib/schema-scan');
-const F_BEYOND = _scan.BEYOND_ITEMS, F_DISCR = _scan.DISCRIMINATOR, F_DEFAULT = _scan.HAS_DEFAULT;
-const F_REF = _scan.HAS_REF, F_ALLOF = _scan.HAS_ALLOF, F_FORMAT = _scan.HAS_FORMAT;
+const F_REF = 1 << 16, F_BEYOND = 1 << 17, F_DISCR = 1 << 18, F_DEFAULT = 1 << 19, F_ALLOF = 1 << 20, F_FORMAT = 1 << 21;
+_scan._setExtraKeys(new Map([
+  ['$ref', F_REF | F_BEYOND], ['$dynamicRef', F_BEYOND], ['allOf', F_ALLOF | F_BEYOND],
+  ['anyOf', F_BEYOND], ['oneOf', F_BEYOND], ['not', F_BEYOND], ['if', F_BEYOND],
+  ['then', F_BEYOND], ['else', F_BEYOND], ['additionalProperties', F_BEYOND],
+  ['patternProperties', F_BEYOND], ['prefixItems', F_BEYOND], ['additionalItems', F_BEYOND],
+  ['contains', F_BEYOND], ['dependentSchemas', F_BEYOND], ['dependencies', F_BEYOND],
+  ['propertyNames', F_BEYOND], ['unevaluatedProperties', F_BEYOND], ['unevaluatedItems', F_BEYOND],
+  ['discriminator', F_DISCR], ['default', F_DEFAULT], ['format', F_FORMAT],
+]));
 const features = _scan.scan;
 
 const _metaValidators = new Map();

package/lib/codegen-engine.js

@@ -69,7 +69,8 @@ function richBuilder(combRich, root, presentFallback, fallback, plain, cleanPlai
   return (data) => {
     const r = combRich(data);
     if (r.valid || !r.errors || !r.errors.length) return presentFallback(fallback, data);
-    const out = _needsOrdering(r.errors) ? _sortErrors(root, r.errors) : r.errors;
+    // `mo`: the list came out in the reader's order (see compileToJSCombined).
+    const out = r.mo === true || !_needsOrdering(r.errors) ? r.errors : _sortErrors(root, r.errors);
     // A collapsed oneOf or anyOf comes out plain (no docUrl) and is enriched
     // here, its branch errors with it, as presentErrors would.
     for (let i = 0; i < out.length; i++) {

package/lib/dialect.js

@@ -28,4 +28,39 @@ function isV1Dialect(schema) {
   return V1_DIALECTS.has(uri);
 }
 
-module.exports = { isV1Dialect, V1_DIALECTS };
+// The earlier dialects by their meta-schema URIs. draftCode is asked of every
+// schema, so it lives here, in a file every validator loads, and the
+// normalizers in draft7.js load only for a schema that declares one of these.
+// draft-06 is read through the draft-07 rules (see draft7.js).
+const DRAFT7_SCHEMAS = new Set([
+  'http://json-schema.org/draft-07/schema#',
+  'http://json-schema.org/draft-07/schema',
+  'http://json-schema.org/draft-06/schema#',
+  'http://json-schema.org/draft-06/schema',
+]);
+const DRAFT6_SCHEMAS = new Set([
+  'http://json-schema.org/draft-06/schema#',
+  'http://json-schema.org/draft-06/schema',
+]);
+// draft-04 is read through the draft-06 rules plus its own: `id` for `$id`,
+// and no `const`, `contains` or `propertyNames` (see draft7.js).
+const DRAFT4_SCHEMAS = new Set([
+  'http://json-schema.org/draft-04/schema#',
+  'http://json-schema.org/draft-04/schema',
+]);
+const DRAFT2019_SCHEMAS = new Set([
+  'https://json-schema.org/draft/2019-09/schema',
+  'https://json-schema.org/draft/2019-09/schema#',
+]);
+
+// 0 for 2020-12 and later, 1 draft-07, 2 draft-06, 3 2019-09, 4 draft-04.
+function draftCode(uri) {
+  if (typeof uri !== 'string') return 0;
+  if (DRAFT4_SCHEMAS.has(uri)) return 4;
+  if (DRAFT6_SCHEMAS.has(uri)) return 2;
+  if (DRAFT7_SCHEMAS.has(uri)) return 1;
+  if (DRAFT2019_SCHEMAS.has(uri)) return 3;
+  return 0;
+}
+
+module.exports = { isV1Dialect, V1_DIALECTS, DRAFT7_SCHEMAS, DRAFT6_SCHEMAS, DRAFT4_SCHEMAS, DRAFT2019_SCHEMAS, draftCode };

package/lib/draft7.js

@@ -6,16 +6,7 @@
 // this, a draft-06 schema was read under 2020-12 and its tuple `items`,
 // `additionalItems` and `dependencies` were not applied: 30 cases of the
 // official draft-06 suite accepted documents they must reject.
-const DRAFT7_SCHEMAS = new Set([
-  'http://json-schema.org/draft-07/schema#',
-  'http://json-schema.org/draft-07/schema',
-  'http://json-schema.org/draft-06/schema#',
-  'http://json-schema.org/draft-06/schema',
-])
-const DRAFT6_SCHEMAS = new Set([
-  'http://json-schema.org/draft-06/schema#',
-  'http://json-schema.org/draft-06/schema',
-])
+const { DRAFT7_SCHEMAS, DRAFT6_SCHEMAS, DRAFT4_SCHEMAS, DRAFT2019_SCHEMAS, draftCode } = require('./dialect')
 
 function isDraft7(schema) {
   return !!(schema && typeof schema.$schema === 'string' && DRAFT7_SCHEMAS.has(schema.$schema))
@@ -28,9 +19,11 @@ function isDraft6(schema) {
 // `force` applies the draft-07 rules to a document that declares no dialect
 // of its own, which is how a retrieved schema inherits the root's draft.
 // `draft6` says the document, or the root it inherits from, is draft-06.
-function normalizeDraft7(schema, force, draft6) {
+// `draft4`: draft-04, read as draft-06 plus its own differences (below).
+function normalizeDraft7(schema, force, draft6, draft4) {
   if (!force && !isDraft7(schema)) return schema
-  _normalize(schema, draft6 === true || isDraft6(schema))
+  const d4 = draft4 === true || (typeof schema.$schema === 'string' && DRAFT4_SCHEMAS.has(schema.$schema))
+  _normalize(schema, d4 || draft6 === true || isDraft6(schema), d4)
   return schema
 }
 
@@ -38,13 +31,21 @@ function normalizeDraft7(schema, force, draft6) {
 // definitions are addressable by pointer, annotations are inert.
 const REF_SIBLINGS_KEPT = new Set(['$ref', '$defs', 'definitions', '$schema', '$comment', 'title', 'description', 'examples', 'default', 'readOnly', 'writeOnly'])
 
-function _normalize(schema, d6) {
+function _normalize(schema, d6, d4) {
   if (typeof schema !== 'object' || schema === null) return
 
   // draft-06 has no conditional: `if`, `then` and `else` are unknown keywords
   // there, so they are dropped rather than applied.
   if (d6) { delete schema.if; delete schema.then; delete schema.else }
 
+  // draft-04 names a schema's identifier `id`, and has none of draft-06's
+  // `const`, `contains` or `propertyNames`: unknown keywords there.
+  if (d4) {
+    delete schema.const; delete schema.contains; delete schema.propertyNames
+    if (typeof schema.id === 'string' && schema.$id === undefined && typeof schema.$ref !== 'string') schema.$id = schema.id
+    delete schema.id
+  }
+
   // In draft-07 an object with `$ref` is that reference and nothing else:
   // sibling keywords, `$id` included, are ignored. Dropping them here gives
   // every engine the same reading without each having to know the draft.
@@ -97,7 +98,7 @@ function _normalize(schema, d6) {
       for (const k in m) {
         if (!Object.prototype.hasOwnProperty.call(m, k)) continue
         const v = m[k]
-        if (typeof v === 'object' && v !== null) _normalize(v, d6)
+        if (typeof v === 'object' && v !== null) _normalize(v, d6, d4)
       }
     }
   }
@@ -108,7 +109,7 @@ function _normalize(schema, d6) {
     if (Array.isArray(a)) {
       for (let i = 0; i < a.length; i++) {
         const v = a[i]
-        if (typeof v === 'object' && v !== null) _normalize(v, d6)
+        if (typeof v === 'object' && v !== null) _normalize(v, d6, d4)
       }
     }
   }
@@ -116,7 +117,7 @@ function _normalize(schema, d6) {
   // Recurse into single sub-schemas
   for (const key of D7_SINGLE_SUBS) {
     const v = schema[key]
-    if (typeof v === 'object' && v !== null) _normalize(v, d6)
+    if (typeof v === 'object' && v !== null) _normalize(v, d6, d4)
   }
 }
 // The schema-bearing keywords _normalize walks, built once rather than per node.
@@ -313,10 +314,6 @@ function _stripFormat(schema, seen) {
 // carries the anchor, and a plain `$ref: "#"` when it does not, which is what
 // 2019-09 says it means then. The outward search for the outermost anchored
 // resource is the same rule in both drafts.
-const DRAFT2019_SCHEMAS = new Set([
-  'https://json-schema.org/draft/2019-09/schema',
-  'https://json-schema.org/draft/2019-09/schema#',
-])
 const RECURSIVE_ANCHOR = '__ata_recursive_anchor'
 
 function isDraft2019(schema) {
@@ -368,12 +365,4 @@ function _normalize2019(node, resourceRoot, isRoot) {
 // The draft a `$schema` value names, for the normalizers: 2 draft-06,
 // 1 draft-07, 3 2019-09, 0 anything else. Takes the string so the caller
 // reads the property once.
-function draftCode(uri) {
-  if (typeof uri !== 'string') return 0
-  if (DRAFT6_SCHEMAS.has(uri)) return 2
-  if (DRAFT7_SCHEMAS.has(uri)) return 1
-  if (DRAFT2019_SCHEMAS.has(uri)) return 3
-  return 0
-}
-
 module.exports = { draftCode, isDraft7, isDraft6, isDraft2019, normalizeDraft2019, normalizeDraft7, normalizeNullable, normalizeExclusiveBounds, stripFormatAssertions }

package/lib/enrich-site.js

@@ -16,9 +16,31 @@ const { reprValue, expectedFor, detailFor, rankFor, MISSING, DOC_BASE } = requir
 // output. A module of its own because only the code generator reaches it, and
 // ata-validator/lite, which enriches through `enrich`, should not carry it.
 const NO_EXPECTED = {};
+// `detail` (see detailFor in lib/enrich-error.js), worked out at the site as
+// far as the site allows: the whole string when it depends only on the
+// params, its fixed head when only the received value is left to append, and
+// neither when it depends on the value (type) or the params are not fixed.
+const DETAIL_AT_RUN = 0;
+const DETAIL_FIXED = 1;
+const DETAIL_HEAD = 2;
+const RANGE_KEYWORDS = new Set(['minimum', 'maximum', 'exclusiveMinimum', 'exclusiveMaximum', 'minLength', 'maxLength']);
+function siteDetail (keyword, params, expected) {
+  if (params === undefined || keyword === 'type') return [DETAIL_AT_RUN, undefined];
+  switch (keyword) {
+    case 'required': return [DETAIL_FIXED, `missing required property "${params.missingProperty}"`];
+    case 'additionalProperties': return [DETAIL_FIXED, `unknown property "${params.additionalProperty}"`];
+    case 'unevaluatedProperties': return [DETAIL_FIXED, `unevaluated property "${params.unevaluatedProperty}"`];
+    case 'format': return [DETAIL_HEAD, `not a valid ${params.format}: `];
+  }
+  if (RANGE_KEYWORDS.has(keyword) || expected) return [DETAIL_HEAD, `expected ${expected}, found `];
+  return [DETAIL_FIXED, undefined];
+}
+
 function errorSite (keyword, schemaPath, params, format) {
   const dependent = keyword === 'required' && typeof schemaPath === 'string' && schemaPath.endsWith('/dependentRequired');
   const code = (dependent && 'ATA7005') || codeFor(keyword, format) || 'ATA9001';
+  const expected = params === undefined ? NO_EXPECTED : expectedFor({ keyword, params });
+  const [detailKind, detail] = siteDetail(keyword, params, expected);
   return {
     code,
     keyword,
@@ -26,7 +48,9 @@ function errorSite (keyword, schemaPath, params, format) {
     docUrl: DOC_BASE + code,
     rank: rankFor(keyword),
     headline: (CODES[code] && CODES[code].headline) || 'validation failed',
-    expected: params === undefined ? NO_EXPECTED : expectedFor({ keyword, params }),
+    expected,
+    detailKind,
+    detail,
   };
 }
 
@@ -49,7 +73,10 @@ function makeRich (site, path, params, message, value, root, spPrefix) {
   };
   const sugg = suggestFor(out, root, at === MISSING ? undefined : at);
   if (sugg) out.suggestion = sugg;
-  const detail = detailFor({ keyword: site.keyword, params }, out, at);
+  const kind = site.detailKind;
+  const detail = kind === DETAIL_FIXED ? site.detail
+    : kind === DETAIL_HEAD ? site.detail + out.received
+      : detailFor({ keyword: site.keyword, params }, out, at);
   if (detail !== undefined) out.detail = detail;
   out.rank = site.rank;
   return out;

package/lib/error-runtime.js

@@ -23,6 +23,8 @@ const FILES = [
   'safe-regex',
   'unique-items',
   'formats',
+  // The URI walk formats.js loads; left out with formats (see OPTIONAL).
+  'uri-core',
 ];
 // The parts a build can leave out when none of its schemas needs them. The
 // decision is made on the schemas the runtime walks (as embedded, see
@@ -91,8 +93,10 @@ function errorRuntimeSource(format, version, features, schemaMode) {
   if (hit !== undefined) return hit;
   const defs = [];
   for (const name of schemaMode ? FILES.concat(SCHEMA_FILES) : FILES) {
-    const src = OPTIONAL[name] !== undefined && !want(name)
-      ? OPTIONAL[name].stub
+    // uri-core goes with formats: only formats.js requires it.
+    const part = name === 'uri-core' ? 'formats' : name;
+    const src = OPTIONAL[part] !== undefined && !want(part)
+      ? (name === 'uri-core' ? 'module.exports = {};' : OPTIONAL[part].stub)
       : dropCommentLines(fs.readFileSync(path.join(__dirname, name + '.js'), 'utf8'), name);
     // The files' own require('./x') calls go to the table under another name:
     // a tool that reads the runtime without scope (knip, a lint rule) took a

package/lib/formats-source.js

@@ -6,44 +6,11 @@
 // checks the interpreted engine calls, so a bundle without the code generator
 // (ata-validator/lite) does not carry them.
 
-const { DURATION_RE, URI_TEMPLATE_EXPR, URI_FAST } = require('./formats');
+// The three patterns below are read from lib/formats.js when a source that
+// needs one is written, not when this file loads: a compile with no uri,
+// uri-template or duration format then does not load formats.js at all.
+const _formats = () => require('./formats');
 
-const uriCharsSource = (v, from) =>
-  `for(let _ri=${from};_ri<${v}.length;_ri++){const _rc=${v}.charCodeAt(_ri);` +
-  'if(_rc<33||_rc>126||_rc===34||_rc===60||_rc===62||_rc===92||_rc===94||_rc===96||_rc===123||_rc===124||_rc===125)return false;' +
-  `if(_rc===37){const _h1=${v}.charCodeAt(_ri+1),_h2=${v}.charCodeAt(_ri+2);` +
-  'if(!((_h1>=48&&_h1<=57)||(_h1>=97&&_h1<=102)||(_h1>=65&&_h1<=70))||' +
-  '!((_h2>=48&&_h2<=57)||(_h2>=97&&_h2<=102)||(_h2>=65&&_h2<=70)))return false;_ri+=2}}';
-const uriAuthoritySource = (v, start) =>
-  `if(${v}.charCodeAt(${start})===47&&${v}.charCodeAt(${start}+1)===47){` +
-  `let _ae=${v}.length;` +
-  `for(let _ai=${start}+2;_ai<${v}.length;_ai++){const _ac=${v}.charCodeAt(_ai);` +
-  'if(_ac===47||_ac===63||_ac===35){_ae=_ai;break}}' +
-  `const _au=${v}.slice(${start}+2,_ae);const _aat=_au.lastIndexOf('@');` +
-  'if(_aat!==-1&&/[[\\]]/.test(_au.slice(0,_aat)))return false;' +
-  'const _hp=_aat===-1?_au:_au.slice(_aat+1);' +
-  'if(_hp.charCodeAt(0)===91){const _cl=_hp.indexOf("]");' +
-  'if(_cl===-1)return false;const _rs=_hp.slice(_cl+1);' +
-  'if(_rs!==""){if(_rs.charCodeAt(0)!==58||!/^[0-9]*$/.test(_rs.slice(1)))return false}}' +
-  'else{const _co=_hp.lastIndexOf(":");' +
-  'if(_co!==-1){if(_hp.indexOf(":")!==_co)return false;' +
-  'if(!/^[0-9]*$/.test(_hp.slice(_co+1)))return false}}}';
-const iriCharsSource = (v, from) =>
-  `for(let _ii=${from};_ii<${v}.length;_ii++){const _ic=${v}.charCodeAt(_ii);` +
-  'if(_ic===127||(_ic<127&&(_ic<33||_ic===34||_ic===60||_ic===62||_ic===92||_ic===94||_ic===96||_ic===123||_ic===124||_ic===125)))return false;' +
-  `if(_ic===37){const _j1=${v}.charCodeAt(_ii+1),_j2=${v}.charCodeAt(_ii+2);` +
-  'if(!((_j1>=48&&_j1<=57)||(_j1>=97&&_j1<=102)||(_j1>=65&&_j1<=70))||' +
-  '!((_j2>=48&&_j2<=57)||(_j2>=97&&_j2<=102)||(_j2>=65&&_j2<=70)))return false;_ii+=2}}';
-function iriSource (v, isStr) {
-  return guard(v, isStr, `const _n=${v}.length;if(_n===0)return false;` +
-    `const _f=${v}.charCodeAt(0);if(!((_f>=97&&_f<=122)||(_f>=65&&_f<=90)))return false;` +
-    `let _co=-1;for(let _i=1;_i<_n;_i++){const _c=${v}.charCodeAt(_i);if(_c===58){_co=_i;break}` +
-    `if(!((_c>=48&&_c<=57)||(_c>=97&&_c<=122)||(_c>=65&&_c<=90)||_c===43||_c===45||_c===46))return false}` +
-    `if(_co===-1)return false;` +
-    iriCharsSource(v, '_co+1') +
-    uriAuthoritySource(v, '_co+1'));
-}
-function iriReferenceSource (v, isStr) { return guard(v, isStr, iriCharsSource(v, '0')); }
 function idnEmailSource (v, isStr) {
   const inner =
     `const _at=${v}.lastIndexOf('@');` +
@@ -57,6 +24,7 @@ function idnEmailSource (v, isStr) {
       `else{` +
         `if(_dm.charCodeAt(0)===46||_dm.charCodeAt(_dm.length-1)===46)return false;` +
         `if(_dm.indexOf('..')!==-1)return false;` +
+        `if(_dm.charCodeAt(0)===45||_dm.charCodeAt(_dm.length-1)===45||_dm.indexOf('-.')!==-1||_dm.indexOf('.-')!==-1)return false;` +
         `for(let _di=0;_di<_dm.length;_di++){const _dc=_dm.charCodeAt(_di);` +
         `if(_dc<=32||_dc===127||_dc===64)return false}` +
       `}` +
@@ -180,31 +148,34 @@ function timeSource (v, isStr) {
     'if(_u!==1439)return false}');
 }
 
-// The same walk as `uri` above, as source, for the code generator to hoist
-// once per compiled function and call. Two copies of one algorithm is what
-// this file has always done for every format, so they sit together here and
-// tests/test_uri_helper_parity.js holds them to the same answer over a corpus
-// built from the walk's own boundaries.
-const URI_HELPER_TABLES = 'const _uct=new Uint8Array(128);for(let _i=33;_i<127;_i++)_uct[_i]=1;' +
-  '_uct[34]=_uct[60]=_uct[62]=_uct[92]=_uct[94]=_uct[96]=_uct[123]=_uct[124]=_uct[125]=0;' +
-  'const _uch=new Uint8Array(128);for(let _i=48;_i<58;_i++)_uch[_i]=1;' +
-  'for(let _i=97;_i<103;_i++)_uch[_i]=1;for(let _i=65;_i<71;_i++)_uch[_i]=1;' +
-  'const _ucs=new Uint8Array(128);for(let _i=48;_i<58;_i++)_ucs[_i]=1;' +
-  'for(let _i=97;_i<123;_i++)_ucs[_i]=1;for(let _i=65;_i<91;_i++)_ucs[_i]=1;' +
-  '_ucs[43]=1;_ucs[45]=1;_ucs[46]=1;const _ufa=/' + URI_FAST.source + '/';
-const URI_HELPER_BODY = 'if(_ufa.test(_s))return true;const _n=_s.length;if(_n===0)return false;let _c=_s.charCodeAt(0);if(_c>127||_ucs[_c]===0||(_c>=48&&_c<=57)||_c===43||_c===45||_c===46)return false;let _co=-1;for(let _i=1;_i<_n;_i++){_c=_s.charCodeAt(_i);if(_c===58){_co=_i;break}if(_c>127||_ucs[_c]===0)return false}if(_co===-1)return false;let _i=_co+1;let _ae=_n;if(_s.charCodeAt(_i)===47&&_s.charCodeAt(_i+1)===47){const _as=_i+2;let _at=-1,_fc=-1,_lc=-1,_br=0,_ba=0,_hs=_as;_ae=-1;for(_i=_as;_i<_n;_i++){_c=_s.charCodeAt(_i);if(_c>127||_uct[_c]===0)return false;if(_c===47||_c===63||_c===35){_ae=_i;break}if(_c===37){const _h1=_s.charCodeAt(_i+1),_h2=_s.charCodeAt(_i+2);if(!(_h1<=127)||!(_h2<=127)||_uch[_h1]===0||_uch[_h2]===0)return false;_i+=2;continue}if(_c===64){_ba=_br;_at=_i;_fc=-1;_lc=-1;_hs=_i+1}else if(_c===58){if(_fc===-1)_fc=_i;_lc=_i}else if(_c===91||_c===93){_br=1}}if(_ae===-1)_ae=_n;if(_at!==-1&&_ba)return false;if(_s.charCodeAt(_hs)===91){let _cl=-1;for(let _j=_hs+1;_j<_ae;_j++){if(_s.charCodeAt(_j)===93){_cl=_j;break}}if(_cl===-1)return false;if(_cl+1!==_ae){if(_s.charCodeAt(_cl+1)!==58)return false;for(let _j=_cl+2;_j<_ae;_j++){const _d=_s.charCodeAt(_j);if(_d<48||_d>57)return false}}}else if(_lc!==-1){if(_fc!==_lc)return false;for(let _j=_lc+1;_j<_ae;_j++){const _d=_s.charCodeAt(_j);if(_d<48||_d>57)return false}}_i=_ae}for(;_i<_n;_i++){_c=_s.charCodeAt(_i);if(_c>127||_uct[_c]===0)return false;if(_c===37){const _h1=_s.charCodeAt(_i+1),_h2=_s.charCodeAt(_i+2);if(!(_h1<=127)||!(_h2<=127)||_uch[_h1]===0||_uch[_h2]===0)return false;_i+=2}}return true;';
+// The URI family: the walk in lib/uri-core.js, emitted as its factory's source
+// and built once per compiled function (uriHelperSource, hoisted under `name`),
+// so a standalone module carries the same walk the interpreted engine runs.
+// tests/test_uri_helper_parity.js holds the two to one answer over a corpus
+// built from the walk's own boundaries. `uri` keeps the regex for the common
+// shape in front of the walk; the others go straight to it with their mode.
+// The walk takes the IPv6 check for a bracketed host as its argument, and
+// here that is ipv6Source as a function, so the module carries one copy.
+// The factory's text with the spaces around punctuation taken out, about
+// 40% shorter, since it lands in every generated function and standalone
+// module that checks a URI. No string literal inside holds a space, and every
+// statement ends in a semicolon or a brace, so the joins are safe;
+// tests/test_uri_helper_parity.js runs this text against the function.
+let _uriSrc = null
+const uriWalkText = () => _uriSrc !== null ? _uriSrc : (_uriSrc = require('./uri-core').__ataUri.toString().replace(/\s*([=,(){};<>+\-&|?:!])\s*/g, '$1'))
+const uriWalkSource = () => `(${uriWalkText()})(function(_s){${ipv6Source('_s', true)}return true})`
+// `_uri(s)` is the uri check, `_urif(s, mode)` the other three (the
+// expression in front for an iri), `_uriw(s, mode)` the walk alone.
 const uriHelperSource = (name) =>
-  URI_HELPER_TABLES + ';function ' + name + '(_s){' + URI_HELPER_BODY + '}';
-
-function uriSource (v, isStr) {
-  return guard(v, isStr, `const _n=${v}.length;if(_n===0)return false;` +
-    `const _f=${v}.charCodeAt(0);if(!((_f>=97&&_f<=122)||(_f>=65&&_f<=90)))return false;` +
-    `let _co=-1;for(let _i=1;_i<_n;_i++){const _c=${v}.charCodeAt(_i);if(_c===58){_co=_i;break}` +
-    `if(!((_c>=48&&_c<=57)||(_c>=97&&_c<=122)||(_c>=65&&_c<=90)||_c===43||_c===45||_c===46))return false}` +
-    `if(_co===-1)return false;` +
-    uriCharsSource(v, '_co+1') +
-    uriAuthoritySource(v, '_co+1'));
-}
+  'const _ufa=/' + _formats().URI_FAST.source + '/;const ' + name + 'w=' + uriWalkSource() + ';' +
+  'function ' + name + '(_s){if(_ufa.test(_s))return true;return ' + name + 'w(_s,1)}' +
+  'function ' + name + 'f(_s,_m){if((_m&1)===1&&_ufa.test(_s))return true;return ' + name + 'w(_s,_m)}'
+// The inline forms, for a caller with no function to hoist into: the walk is
+// built in place, which costs a factory per call, so the generators hoist.
+function uriSource (v, isStr) { return guard(v, isStr, `if(!/${_formats().URI_FAST.source}/.test(${v})&&!${uriWalkSource()}(${v},1))return false`) }
+function uriReferenceSource (v, isStr) { return guard(v, isStr, `if(!${uriWalkSource()}(${v},0))return false`) }
+function iriSource (v, isStr) { return guard(v, isStr, `if(!/${_formats().URI_FAST.source}/.test(${v})&&!${uriWalkSource()}(${v},3))return false`) }
+function iriReferenceSource (v, isStr) { return guard(v, isStr, `if(!${uriWalkSource()}(${v},2))return false`) }
 
 function ipv6Source (v, isStr) {
   return guard(v, isStr, `const _n=${v}.length;if(_n<2||_n>45)return false;let _end=_n,_g=0;` +
@@ -245,6 +216,9 @@ function uriTemplateSource (v, isStr) {
       `const _c=${v}.charCodeAt(_i);` +
       `if(_c===125)return false;` +
       `if(_c!==123&&(_c<=32||_c===127))return false;` +
+      `if(_c===37){const _h1=${v}.charCodeAt(_i+1),_h2=${v}.charCodeAt(_i+2);` +
+      'if(!((_h1>=48&&_h1<=57)||(_h1>=97&&_h1<=102)||(_h1>=65&&_h1<=70))||' +
+      '!((_h2>=48&&_h2<=57)||(_h2>=97&&_h2<=102)||(_h2>=65&&_h2<=70)))return false;_i+=3;continue}' +
       `if(_c!==123){_i++;continue}` +
       // `_ute`, not `_e`: this source is spliced into a generated function whose
       // error accumulator is `_e`, and a `const _e` here shadowed it, so
@@ -254,7 +228,7 @@ function uriTemplateSource (v, isStr) {
       `if(_ute===-1)return false;` +
       `const _x=${v}.slice(_i+1,_ute);` +
       `if(_x===''||_x.indexOf('{')!==-1)return false;` +
-      `if(!${URI_TEMPLATE_EXPR.toString()}.test(_x))return false;` +
+      `if(!${_formats().URI_TEMPLATE_EXPR.toString()}.test(_x))return false;` +
       `_i=_ute+1` +
     `}`;
   return isStr ? `{${inner}}` : `if(typeof ${v}==='string'){${inner}}`;
@@ -296,7 +270,10 @@ function emailSource (v, isStr) {
     `const _n0=${v}.length;let _at;` +
     `if(${v}.charCodeAt(0)===34){` +
       `_at=${v}.lastIndexOf('@');` +
-      `if(_at<2||_at===_n0-1||_at>64||${v}.charCodeAt(_at-1)!==34)return false` +
+      `if(_at<2||_at===_n0-1||_at>64||${v}.charCodeAt(_at-1)!==34)return false;` +
+      `for(let _qi=1;_qi<_at-1;_qi++){const _qc=${v}.charCodeAt(_qi);` +
+      `if(_qc===92){const _qp=${v}.charCodeAt(_qi+1);if(_qp<32||_qp>126||_qi+1>=_at-1)return false;_qi++;continue}` +
+      `if(_qc<32||_qc>126||_qc===34)return false}` +
     `}else{` +
       `if(${v}.charCodeAt(0)===46)return false;` +
       `_at=-1;let _pd=false;` +
@@ -310,14 +287,14 @@ function emailSource (v, isStr) {
       `const _dm=${v}.slice(_at+1);` +
       `if(_dm.charCodeAt(_dm.length-1)!==93||_dm.length<=2)return false;` +
       `const _in=_dm.slice(1,-1);` +
-      `if(_in.startsWith('IPv6:')){const _i6=_in.slice(5);${ipv6Source('_i6', true)}}` +
+      `if((_in.charCodeAt(0)|32)===105&&(_in.charCodeAt(1)|32)===112&&(_in.charCodeAt(2)|32)===118&&_in.charCodeAt(3)===54&&_in.charCodeAt(4)===58){const _i6=_in.slice(5);${ipv6Source('_i6', true)}}` +
       `else{${ipv4Source('_in', true)}}` +
     `}` +
     `else{${hostnameRangeSource(v, '_at+1', `${v}.length`)}}`;
   return isStr ? `{${inner}}` : `if(typeof ${v}==='string'){${inner}}`;
 }
 function durationSource (v, isStr) {
-  const inner = `if(!${DURATION_RE.toString()}.test(${v}))return false`;
+  const inner = `if(!${_formats().DURATION_RE.toString()}.test(${v}))return false`;
   return isStr ? inner : `if(typeof ${v}==='string'&&${inner.slice(3)}`;
 }
-module.exports = { uriHelperSource, uriCharsSource, uriAuthoritySource, iriSource, iriReferenceSource, idnEmailSource, dateSource, ipv4Source, dateTimeSource, ipv6Source, hostnameSource, uriSource, uuidSource, timeSource, noReservedSource, jsonPointerSource, relativeJsonPointerSource, uriTemplateSource, emailSource, durationSource };
+module.exports = { uriHelperSource, uriSource, uriReferenceSource, iriSource, iriReferenceSource, idnEmailSource, dateSource, ipv4Source, dateTimeSource, ipv6Source, hostnameSource, uriSource, uuidSource, timeSource, noReservedSource, jsonPointerSource, relativeJsonPointerSource, uriTemplateSource, emailSource, durationSource };