@terascope/data-mate 2.23.1 → 2.25.0

package/dist/src/function-configs/string/replaceLiteral.js.map

@@ -1 +1 @@
-{"version":3,"file":"replaceLiteral.js","sourceRoot":"","sources":["../../../../src/function-configs/string/replaceLiteral.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAC7C,OAAO,EACmB,WAAW,EAAE,sBAAsB,EAC9B,0BAA0B,GACxD,MAAM,kBAAkB,CAAC;AAO1B,MAAM,QAAQ,GAAoD;IAC9D;QACI,IAAI,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE;QACvC,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,QAAQ;QACf,MAAM,EAAE,QAAQ;KACnB;IACD;QACI,IAAI,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE;QACvC,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,QAAQ;QACf,MAAM,EAAE,QAAQ;QAChB,WAAW,EAAE,8CAA8C;KAC9D;CACJ,CAAC;AAEF,MAAM,CAAC,MAAM,oBAAoB,GAA6C;IAC1E,IAAI,EAAE,gBAAgB;IACtB,IAAI,EAAE,sBAAsB,CAAC,eAAe;IAC5C,YAAY,EAAE,WAAW,CAAC,iBAAiB;IAC3C,QAAQ,EAAE,0BAA0B,CAAC,MAAM;IAC3C,WAAW,EAAE,wEAAwE;IACrF,QAAQ;IACR,MAAM,CAAC,EAAE,IAAI,EAAE,EAAE,OAAO,EAAE,MAAM,EAAE,EAAE;QAChC,OAAO,CAAC,KAAc,EAAE,EAAE,CAAC,SAAS,CAAC,KAAe,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC;IAC3E,CAAC;IACD,OAAO,EAAE,CAAC,SAAS,CAAC,MAAM,CAAC;IAC3B,eAAe,EAAE;QACb,MAAM,EAAE;YACJ,IAAI,EAAE,SAAS,CAAC,MAAM;YACtB,KAAK,EAAE,KAAK;YACZ,WAAW,EAAE,sCAAsC;SACtD;QACD,OAAO,EAAE;YACL,IAAI,EAAE,SAAS,CAAC,MAAM;YACtB,KAAK,EAAE,KAAK;YACZ,WAAW,EAAE,mDAAmD;SACnE;KACJ;IACD,kBAAkB,EAAE,CAAC,QAAQ,EAAE,SAAS,CAAC;CAC5C,CAAC;AAEF,SAAS,SAAS,CAAC,KAAa,EAAE,MAAc,EAAE,MAAc;IAC5D,OAAO,KAAK,CAAC,OAAO,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;AACzC,CAAC"}
+{"version":3,"file":"replaceLiteral.js","sourceRoot":"","sources":["../../../../src/function-configs/string/replaceLiteral.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAC7C,OAAO,EACmB,WAAW,EAAE,sBAAsB,EAC9B,0BAA0B,GACxD,MAAM,kBAAkB,CAAC;AAC1B,OAAO,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAO/C,MAAM,QAAQ,GAAoD;IAC9D;QACI,IAAI,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE;QACvC,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,QAAQ;QACf,MAAM,EAAE,QAAQ;KACnB;IACD;QACI,IAAI,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE;QACvC,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,QAAQ;QACf,MAAM,EAAE,QAAQ;QAChB,WAAW,EAAE,8CAA8C;KAC9D;CACJ,CAAC;AAEF,MAAM,CAAC,MAAM,oBAAoB,GAA6C;IAC1E,IAAI,EAAE,gBAAgB;IACtB,IAAI,EAAE,sBAAsB,CAAC,eAAe;IAC5C,YAAY,EAAE,WAAW,CAAC,iBAAiB;IAC3C,QAAQ,EAAE,0BAA0B,CAAC,MAAM;IAC3C,WAAW,EAAE,wEAAwE;IACrF,QAAQ;IACR,MAAM,CAAC,EAAE,IAAI,EAAE,EAAE,OAAO,EAAE,MAAM,EAAE,EAAE;QAChC,OAAO,CAAC,KAAc,EAAE,EAAE,CAAC,SAAS,CAAC,KAAe,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC;IAC3E,CAAC;IACD;;;;;;;;;;;MAWE;IACF,GAAG,EAAE;QACD,UAAU,EAAE,CAAC,EAAE,KAAK,EAAE,IAAI,EAAE,EAAE,EAAE;YAC5B,MAAM,MAAM,GAAG,UAAU,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;YACvC,MAAM,EAAE,GAAG,YAAY,MAAM,OAAO,KAAK,GAAG,CAAC;YAC7C,OAAO,aAAa,EAAE,aAAa,KAAK,EAAE;kBACpC,mBAAmB,KAAK,QAAQ,EAAE,YAAY,UAAU,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE;kBACxE,iBAAiB,KAAK,KAAK,EAAE,aAAa,MAAM,QAAQ,CAAC;QACnE,CAAC;KACJ;IACD,OAAO,EAAE,CAAC,SAAS,CAAC,MAAM,CAAC;IAC3B,eAAe,EAAE;QACb,MAAM,EAAE;YACJ,IAAI,EAAE,SAAS,CAAC,MAAM;YACtB,KAAK,EAAE,KAAK;YACZ,WAAW,EAAE,sCAAsC;SACtD;QACD,OAAO,EAAE;YACL,IAAI,EAAE,SAAS,CAAC,MAAM;YACtB,KAAK,EAAE,KAAK;YACZ,WAAW,EAAE,mDAAmD;SACnE;KACJ;IACD,kBAAkB,EAAE,CAAC,QAAQ,EAAE,SAAS,CAAC;CAC5C,CAAC;AAEF,SAAS,SAAS,CAAC,KAAa,EAAE,MAAc,EAAE,MAAc;IAC5D,OAAO,KAAK,CAAC,OAAO,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;AACzC,CAAC"}

package/dist/src/function-configs/string/replaceRegex.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"replaceRegex.d.ts","sourceRoot":"","sources":["../../../../src/function-configs/string/replaceRegex.ts"],"names":[],"mappings":"AAEA,OAAO,EACH,oBAAoB,EAEvB,MAAM,kBAAkB,CAAC;AAE1B,MAAM,WAAW,gBAAgB;IAC7B,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE,MAAM,CAAC;IAChB,UAAU,CAAC,EAAE,OAAO,CAAC;IACrB,MAAM,CAAC,EAAE,OAAO,CAAC;CACpB;AAmCD,eAAO,MAAM,kBAAkB,EAAE,oBAAoB,CAAC,gBAAgB,CAkDrE,CAAC"}
+{"version":3,"file":"replaceRegex.d.ts","sourceRoot":"","sources":["../../../../src/function-configs/string/replaceRegex.ts"],"names":[],"mappings":"AAEA,OAAO,EACH,oBAAoB,EAEvB,MAAM,kBAAkB,CAAC;AAI1B,MAAM,WAAW,gBAAgB;IAC7B,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE,MAAM,CAAC;IAChB,UAAU,CAAC,EAAE,OAAO,CAAC;IACrB,MAAM,CAAC,EAAE,OAAO,CAAC;CACpB;AAmCD,eAAO,MAAM,kBAAkB,EAAE,oBAAoB,CAAC,gBAAgB,CAkFrE,CAAC"}

package/dist/src/function-configs/string/replaceRegex.js

@@ -1,6 +1,8 @@
 import { isString, isRegExpLike } from '@terascope/core-utils';
 import { FieldType } from '@terascope/types';
 import { ProcessMode, FunctionDefinitionType, FunctionDefinitionCategory, } from '../interfaces.js';
+import { sqlLiteral } from '../sql-helpers.js';
+import { hasPortableEscapes, isLiteralReplacement, isRe2Safe, withClassGuard } from './sql-regex-utils.js';
 const examples = [
     {
         args: { regex: 's|e', replace: 'd' },
@@ -43,6 +45,38 @@ export const replaceRegexConfig = {
         return (input) => replaceFn(input, replace, regex, ignoreCase, global);
     },
     examples,
+    /**
+     * `regexp_replace`, guarded on both the pattern and the replacement.
+     *
+     * RE2 has no lookaround or backreferences and errors on them, and `$1` is a capture group in
+     * JavaScript but literal text in DuckDB. Patterns and replacements that use either keep the
+     * UDF; see `sql-regex-utils.ts`.
+    */
+    sql: {
+        /**
+         * A pattern that compiles in both engines can still match different characters.
+         * JavaScript's `\s` matches 20 characters that RE2's does not (vertical tab, NBSP, the `Zs`
+         * spaces, U+2028, U+2029 and the BOM), `\S` differs on the same 20, and `.` differs on CR,
+         * U+2028 and U+2029. `\w`, `\d` and `\b` agree.
+         *
+         * Patterns using `.`, `\s`, `\S` or a negated class are therefore guarded per value rather
+         * than rejected, since rejecting every pattern with a `.` would exclude most patterns.
+         * Values containing one of the differing characters, or an astral character, go to the UDF;
+         * everything else uses `regexp_replace`. See `withClassGuard`.
+        */
+        needs_udf_fallback: true,
+        applies: (args) => typeof args.regex === 'string'
+            && isRe2Safe(args.regex)
+            && hasPortableEscapes(args.regex)
+            && isLiteralReplacement(String(args.replace ?? '')),
+        expression: ({ value, args, udf }) => {
+            const flags = `${args.ignoreCase ? 'i' : ''}${args.global ? 'g' : ''}`;
+            const rest = flags ? `, ${sqlLiteral(flags)}` : '';
+            const native = `regexp_replace(${value}, ${sqlLiteral(args.regex)},`
+                + ` ${sqlLiteral(String(args.replace ?? ''))}${rest})`;
+            return withClassGuard(args.regex, value, native, udf);
+        },
+    },
     accepts: [FieldType.String],
     argument_schema: {
         regex: {

package/dist/src/function-configs/string/replaceRegex.js.map

@@ -1 +1 @@
-{"version":3,"file":"replaceRegex.js","sourceRoot":"","sources":["../../../../src/function-configs/string/replaceRegex.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAC;AAC/D,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAC7C,OAAO,EACmB,WAAW,EAAE,sBAAsB,EAC9B,0BAA0B,GACxD,MAAM,kBAAkB,CAAC;AAS1B,MAAM,QAAQ,GAAkD;IAC5D;QACI,IAAI,EAAE,EAAE,KAAK,EAAE,KAAK,EAAE,OAAO,EAAE,GAAG,EAAE;QACpC,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,YAAY;QACnB,MAAM,EAAE,YAAY;KACvB;IACD;QACI,IAAI,EAAE,EAAE,KAAK,EAAE,KAAK,EAAE,OAAO,EAAE,GAAG,EAAE,MAAM,EAAE,IAAI,EAAE;QAClD,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,YAAY;QACnB,MAAM,EAAE,YAAY;KACvB;IACD;QACI,IAAI,EAAE;YACF,KAAK,EAAE,KAAK,EAAE,OAAO,EAAE,GAAG,EAAE,MAAM,EAAE,IAAI,EAAE,UAAU,EAAE,IAAI;SAC7D;QACD,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,YAAY;QACnB,MAAM,EAAE,YAAY;KACvB;IACD;QACI,IAAI,EAAE,EAAE,KAAK,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,EAAE,MAAM,EAAE,IAAI,EAAE;QACjD,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,WAAW;QAClB,MAAM,EAAE,KAAK;KAChB;CACJ,CAAC;AAEF,MAAM,CAAC,MAAM,kBAAkB,GAA2C;IACtE,IAAI,EAAE,cAAc;IACpB,IAAI,EAAE,sBAAsB,CAAC,eAAe;IAC5C,YAAY,EAAE,WAAW,CAAC,iBAAiB;IAC3C,QAAQ,EAAE,0BAA0B,CAAC,MAAM;IAC3C,WAAW,EAAE,gGAAgG;IAC7G,MAAM,CAAC,EACH,IAAI,EAAE,EACF,OAAO,EACP,KAAK,EACL,UAAU,GAAG,KAAK,EAClB,MAAM,GAAG,KAAK,EACjB,EACJ;QACG,OAAO,CAAC,KAAc,EAAE,EAAE,CAAC,SAAS,CAAC,KAAe,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE,MAAM,CAAC,CAAC;IAC9F,CAAC;IACD,QAAQ;IACR,OAAO,EAAE,CAAC,SAAS,CAAC,MAAM,CAAC;IAC3B,eAAe,EAAE;QACb,KAAK,EAAE;YACH,IAAI,EAAE,SAAS,CAAC,MAAM;YACtB,KAAK,EAAE,KAAK;YACZ,WAAW,EAAE,iCAAiC;SACjD;QACD,OAAO,EAAE;YACL,IAAI,EAAE,SAAS,CAAC,MAAM;YACtB,KAAK,EAAE,KAAK;YACZ,WAAW,EAAE,wDAAwD;SACxE;QACD,UAAU,EAAE;YACR,IAAI,EAAE,SAAS,CAAC,OAAO;YACvB,KAAK,EAAE,KAAK;YACZ,WAAW,EAAE,oEAAoE;SACpF;QACD,MAAM,EAAE;YACJ,IAAI,EAAE,SAAS,CAAC,OAAO;YACvB,KAAK,EAAE,KAAK;YACZ,WAAW,EAAE,oFAAoF;SACpG;KACJ;IACD,2FAA2F;IAC3F,kBAAkB,EAAE,CAAC,OAAO,CAAC;IAC7B,kBAAkB,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE;QACjC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,YAAY,CAAC,KAAK,CAAC,EAAE,CAAC;YAC1C,MAAM,IAAI,KAAK,CAAC,qEAAqE,CAAC,CAAC;QAC3F,CAAC;QACD,IAAI,CAAC,QAAQ,CAAC,OAAO,CAAC,EAAE,CAAC;YACrB,MAAM,IAAI,KAAK,CAAC,6DAA6D,CAAC,CAAC;QACnF,CAAC;IACL,CAAC;CACJ,CAAC;AAEF,SAAS,SAAS,CACd,KAAa,EACb,OAAe,EACf,KAAa,EACb,UAAmB,EACnB,MAAe;IAEf,IAAI,OAAO,GAAG,EAAE,CAAC;IAEjB,IAAI,UAAU;QAAE,OAAO,IAAI,GAAG,CAAC;IAC/B,IAAI,MAAM;QAAE,OAAO,IAAI,GAAG,CAAC;IAE3B,MAAM,EAAE,GAAG,IAAI,MAAM,CAAC,KAAK,EAAE,OAAO,CAAC,CAAC;IACtC,OAAO,KAAK,CAAC,OAAO,CAAC,EAAE,EAAE,OAAO,CAAC,CAAC;AACtC,CAAC"}
+{"version":3,"file":"replaceRegex.js","sourceRoot":"","sources":["../../../../src/function-configs/string/replaceRegex.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAC;AAC/D,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAC7C,OAAO,EACmB,WAAW,EAAE,sBAAsB,EAC9B,0BAA0B,GACxD,MAAM,kBAAkB,CAAC;AAC1B,OAAO,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAC/C,OAAO,EAAE,kBAAkB,EAAE,oBAAoB,EAAE,SAAS,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAC;AAS3G,MAAM,QAAQ,GAAkD;IAC5D;QACI,IAAI,EAAE,EAAE,KAAK,EAAE,KAAK,EAAE,OAAO,EAAE,GAAG,EAAE;QACpC,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,YAAY;QACnB,MAAM,EAAE,YAAY;KACvB;IACD;QACI,IAAI,EAAE,EAAE,KAAK,EAAE,KAAK,EAAE,OAAO,EAAE,GAAG,EAAE,MAAM,EAAE,IAAI,EAAE;QAClD,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,YAAY;QACnB,MAAM,EAAE,YAAY;KACvB;IACD;QACI,IAAI,EAAE;YACF,KAAK,EAAE,KAAK,EAAE,OAAO,EAAE,GAAG,EAAE,MAAM,EAAE,IAAI,EAAE,UAAU,EAAE,IAAI;SAC7D;QACD,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,YAAY;QACnB,MAAM,EAAE,YAAY;KACvB;IACD;QACI,IAAI,EAAE,EAAE,KAAK,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,EAAE,MAAM,EAAE,IAAI,EAAE;QACjD,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,WAAW;QAClB,MAAM,EAAE,KAAK;KAChB;CACJ,CAAC;AAEF,MAAM,CAAC,MAAM,kBAAkB,GAA2C;IACtE,IAAI,EAAE,cAAc;IACpB,IAAI,EAAE,sBAAsB,CAAC,eAAe;IAC5C,YAAY,EAAE,WAAW,CAAC,iBAAiB;IAC3C,QAAQ,EAAE,0BAA0B,CAAC,MAAM;IAC3C,WAAW,EAAE,gGAAgG;IAC7G,MAAM,CAAC,EACH,IAAI,EAAE,EACF,OAAO,EACP,KAAK,EACL,UAAU,GAAG,KAAK,EAClB,MAAM,GAAG,KAAK,EACjB,EACJ;QACG,OAAO,CAAC,KAAc,EAAE,EAAE,CAAC,SAAS,CAAC,KAAe,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE,MAAM,CAAC,CAAC;IAC9F,CAAC;IACD,QAAQ;IACR;;;;;;MAME;IACF,GAAG,EAAE;QACD;;;;;;;;;;UAUE;QACF,kBAAkB,EAAE,IAAI;QACxB,OAAO,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,OAAO,IAAI,CAAC,KAAK,KAAK,QAAQ;eAC1C,SAAS,CAAC,IAAI,CAAC,KAAK,CAAC;eACrB,kBAAkB,CAAC,IAAI,CAAC,KAAK,CAAC;eAC9B,oBAAoB,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC;QACvD,UAAU,EAAE,CAAC,EAAE,KAAK,EAAE,IAAI,EAAE,GAAG,EAAE,EAAE,EAAE;YACjC,MAAM,KAAK,GAAG,GAAG,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,GAAG,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC;YACvE,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,KAAK,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;YACnD,MAAM,MAAM,GAAG,kBAAkB,KAAK,KAAK,UAAU,CAAC,IAAI,CAAC,KAAe,CAAC,GAAG;kBACxE,IAAI,UAAU,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC,GAAG,IAAI,GAAG,CAAC;YAC3D,OAAO,cAAc,CAAC,IAAI,CAAC,KAAe,EAAE,KAAK,EAAE,MAAM,EAAE,GAAG,CAAC,CAAC;QACpE,CAAC;KACJ;IACD,OAAO,EAAE,CAAC,SAAS,CAAC,MAAM,CAAC;IAC3B,eAAe,EAAE;QACb,KAAK,EAAE;YACH,IAAI,EAAE,SAAS,CAAC,MAAM;YACtB,KAAK,EAAE,KAAK;YACZ,WAAW,EAAE,iCAAiC;SACjD;QACD,OAAO,EAAE;YACL,IAAI,EAAE,SAAS,CAAC,MAAM;YACtB,KAAK,EAAE,KAAK;YACZ,WAAW,EAAE,wDAAwD;SACxE;QACD,UAAU,EAAE;YACR,IAAI,EAAE,SAAS,CAAC,OAAO;YACvB,KAAK,EAAE,KAAK;YACZ,WAAW,EAAE,oEAAoE;SACpF;QACD,MAAM,EAAE;YACJ,IAAI,EAAE,SAAS,CAAC,OAAO;YACvB,KAAK,EAAE,KAAK;YACZ,WAAW,EAAE,oFAAoF;SACpG;KACJ;IACD,2FAA2F;IAC3F,kBAAkB,EAAE,CAAC,OAAO,CAAC;IAC7B,kBAAkB,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE;QACjC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,YAAY,CAAC,KAAK,CAAC,EAAE,CAAC;YAC1C,MAAM,IAAI,KAAK,CAAC,qEAAqE,CAAC,CAAC;QAC3F,CAAC;QACD,IAAI,CAAC,QAAQ,CAAC,OAAO,CAAC,EAAE,CAAC;YACrB,MAAM,IAAI,KAAK,CAAC,6DAA6D,CAAC,CAAC;QACnF,CAAC;IACL,CAAC;CACJ,CAAC;AAEF,SAAS,SAAS,CACd,KAAa,EACb,OAAe,EACf,KAAa,EACb,UAAmB,EACnB,MAAe;IAEf,IAAI,OAAO,GAAG,EAAE,CAAC;IAEjB,IAAI,UAAU;QAAE,OAAO,IAAI,GAAG,CAAC;IAC/B,IAAI,MAAM;QAAE,OAAO,IAAI,GAAG,CAAC;IAE3B,MAAM,EAAE,GAAG,IAAI,MAAM,CAAC,KAAK,EAAE,OAAO,CAAC,CAAC;IACtC,OAAO,KAAK,CAAC,OAAO,CAAC,EAAE,EAAE,OAAO,CAAC,CAAC;AACtC,CAAC"}

package/dist/src/function-configs/string/reverse.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"reverse.d.ts","sourceRoot":"","sources":["../../../../src/function-configs/string/reverse.ts"],"names":[],"mappings":"AAEA,OAAO,EACH,oBAAoB,EAKvB,MAAM,kBAAkB,CAAC;AA4E1B,eAAO,MAAM,aAAa,EAAE,oBAW3B,CAAC"}
+{"version":3,"file":"reverse.d.ts","sourceRoot":"","sources":["../../../../src/function-configs/string/reverse.ts"],"names":[],"mappings":"AAEA,OAAO,EACH,oBAAoB,EAKvB,MAAM,kBAAkB,CAAC;AA6E1B,eAAO,MAAM,aAAa,EAAE,oBA0B3B,CAAC"}

package/dist/src/function-configs/string/reverse.js

@@ -1,6 +1,7 @@
 import { getTypeOf, isString } from '@terascope/core-utils';
 import { FieldType } from '@terascope/types';
 import { ProcessMode, FunctionDefinitionType, FunctionDefinitionCategory } from '../interfaces.js';
+import { sqlLiteral, NEEDS_GRAPHEME_REVERSE } from '../sql-helpers.js';
 /**
  * Strings containing a surrogate pair, a combining mark, or a zero-width joiner cannot
  * be reversed one UTF-16 code unit at a time:
@@ -75,6 +76,21 @@ export const reverseConfig = {
     create() {
         return _reverse;
     },
+    /**
+     * `reverse()` for strings that do not need grapheme segmentation, the UDF for those that do,
+     * and NULL for the empty string, which is what `_reverse` returns.
+     *
+     * The guard matches the same strings as `NEEDS_SEGMENTATION` above: an astral code point, a
+     * zero-width joiner or a combining mark. RE2 supports `\p{M}` and `\x{...}`, so it matches the
+     * same strings as the JavaScript regex. The segmentation path is about 11x slower, and this
+     * keeps it to the values that need it.
+    */
+    sql: {
+        needs_udf_fallback: true,
+        expression: ({ value, udf }) => `CASE WHEN ${value} = '' THEN NULL`
+            + ` WHEN regexp_matches(${value}, ${sqlLiteral(NEEDS_GRAPHEME_REVERSE)})`
+            + ` THEN ${udf(value)} ELSE reverse(${value}) END`,
+    },
     accepts: [FieldType.String],
 };
 //# sourceMappingURL=reverse.js.map

package/dist/src/function-configs/string/reverse.js.map

@@ -1 +1 @@
-{"version":3,"file":"reverse.js","sourceRoot":"","sources":["../../../../src/function-configs/string/reverse.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,SAAS,EAAE,QAAQ,EAAE,MAAM,uBAAuB,CAAC;AAC5D,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAC7C,OAAO,EAEH,WAAW,EACX,sBAAsB,EACtB,0BAA0B,EAE7B,MAAM,kBAAkB,CAAC;AAE1B;;;;;;;;;;;;;;;;;;GAkBG;AACH,MAAM,kBAAkB,GAAG,uCAAuC,CAAC;AAEnE,IAAI,SAAqC,CAAC;AAE1C,SAAS,QAAQ,CAAC,KAAc;IAC5B,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC;QACnB,MAAM,IAAI,KAAK,CAAC,iBAAiB,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,yBAAyB,SAAS,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;IACvG,CAAC;IAED,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,IAAI,CAAC;IAEpC,IAAI,kBAAkB,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;QACjC,SAAS,KAAK,IAAI,IAAI,CAAC,SAAS,CAAC,IAAI,EAAE,EAAE,WAAW,EAAE,UAAU,EAAE,CAAC,CAAC;QAEpE,MAAM,SAAS,GAAa,EAAE,CAAC;QAC/B,KAAK,MAAM,EAAE,OAAO,EAAE,IAAI,SAAS,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC;YACjD,SAAS,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;QAC5B,CAAC;QAED,OAAO,SAAS,CAAC,OAAO,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACxC,CAAC;IAED,IAAI,OAAO,GAAG,EAAE,CAAC;IAEjB,KAAK,IAAI,CAAC,GAAG,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC;QACzC,OAAO,IAAI,KAAK,CAAC,CAAC,CAAC,CAAC;IACxB,CAAC;IAED,OAAO,OAAO,CAAC;AACnB,CAAC;AAED,MAAM,QAAQ,GAAyD;IACnE;QACI,IAAI,EAAE,EAAE;QACR,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,OAAO;QACd,MAAM,EAAE,OAAO;KAClB;IACD;QACI,IAAI,EAAE,EAAE;QACR,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,YAAY;QACnB,MAAM,EAAE,YAAY;KACvB;IACD;QACI,IAAI,EAAE,EAAE;QACR,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,KAAK,EAAE,IAAI,EAAE,EAAE,EAAE;QACtF,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,CAAC,OAAO,EAAE,MAAM,CAAC;QACxB,MAAM,EAAE,CAAC,OAAO,EAAE,MAAM,CAAC;KAC5B;CACJ,CAAC;AAEF,MAAM,CAAC,MAAM,aAAa,GAAyB;IAC/C,IAAI,EAAE,SAAS;IACf,IAAI,EAAE,sBAAsB,CAAC,eAAe;IAC5C,YAAY,EAAE,WAAW,CAAC,iBAAiB;IAC3C,QAAQ,EAAE,0BAA0B,CAAC,MAAM;IAC3C,WAAW,EAAE,gEAAgE;IAC7E,QAAQ;IACR,MAAM;QACF,OAAO,QAAQ,CAAC;IACpB,CAAC;IACD,OAAO,EAAE,CAAC,SAAS,CAAC,MAAM,CAAC;CAC9B,CAAC"}
+{"version":3,"file":"reverse.js","sourceRoot":"","sources":["../../../../src/function-configs/string/reverse.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,SAAS,EAAE,QAAQ,EAAE,MAAM,uBAAuB,CAAC;AAC5D,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAC7C,OAAO,EAEH,WAAW,EACX,sBAAsB,EACtB,0BAA0B,EAE7B,MAAM,kBAAkB,CAAC;AAC1B,OAAO,EAAE,UAAU,EAAE,sBAAsB,EAAE,MAAM,mBAAmB,CAAC;AAEvE;;;;;;;;;;;;;;;;;;GAkBG;AACH,MAAM,kBAAkB,GAAG,uCAAuC,CAAC;AAEnE,IAAI,SAAqC,CAAC;AAE1C,SAAS,QAAQ,CAAC,KAAc;IAC5B,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC;QACnB,MAAM,IAAI,KAAK,CAAC,iBAAiB,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,yBAAyB,SAAS,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;IACvG,CAAC;IAED,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,IAAI,CAAC;IAEpC,IAAI,kBAAkB,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;QACjC,SAAS,KAAK,IAAI,IAAI,CAAC,SAAS,CAAC,IAAI,EAAE,EAAE,WAAW,EAAE,UAAU,EAAE,CAAC,CAAC;QAEpE,MAAM,SAAS,GAAa,EAAE,CAAC;QAC/B,KAAK,MAAM,EAAE,OAAO,EAAE,IAAI,SAAS,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC;YACjD,SAAS,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;QAC5B,CAAC;QAED,OAAO,SAAS,CAAC,OAAO,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACxC,CAAC;IAED,IAAI,OAAO,GAAG,EAAE,CAAC;IAEjB,KAAK,IAAI,CAAC,GAAG,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC;QACzC,OAAO,IAAI,KAAK,CAAC,CAAC,CAAC,CAAC;IACxB,CAAC;IAED,OAAO,OAAO,CAAC;AACnB,CAAC;AAED,MAAM,QAAQ,GAAyD;IACnE;QACI,IAAI,EAAE,EAAE;QACR,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,OAAO;QACd,MAAM,EAAE,OAAO;KAClB;IACD;QACI,IAAI,EAAE,EAAE;QACR,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,YAAY;QACnB,MAAM,EAAE,YAAY;KACvB;IACD;QACI,IAAI,EAAE,EAAE;QACR,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,KAAK,EAAE,IAAI,EAAE,EAAE,EAAE;QACtF,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,CAAC,OAAO,EAAE,MAAM,CAAC;QACxB,MAAM,EAAE,CAAC,OAAO,EAAE,MAAM,CAAC;KAC5B;CACJ,CAAC;AAEF,MAAM,CAAC,MAAM,aAAa,GAAyB;IAC/C,IAAI,EAAE,SAAS;IACf,IAAI,EAAE,sBAAsB,CAAC,eAAe;IAC5C,YAAY,EAAE,WAAW,CAAC,iBAAiB;IAC3C,QAAQ,EAAE,0BAA0B,CAAC,MAAM;IAC3C,WAAW,EAAE,gEAAgE;IAC7E,QAAQ;IACR,MAAM;QACF,OAAO,QAAQ,CAAC;IACpB,CAAC;IACD;;;;;;;;MAQE;IACF,GAAG,EAAE;QACD,kBAAkB,EAAE,IAAI;QACxB,UAAU,EAAE,CAAC,EAAE,KAAK,EAAE,GAAG,EAAE,EAAE,EAAE,CAAC,aAAa,KAAK,iBAAiB;cAC7D,wBAAwB,KAAK,KAAK,UAAU,CAAC,sBAAsB,CAAC,GAAG;cACvE,SAAS,GAAG,CAAC,KAAK,CAAC,iBAAiB,KAAK,OAAO;KACzD;IACD,OAAO,EAAE,CAAC,SAAS,CAAC,MAAM,CAAC;CAC9B,CAAC"}

package/dist/src/function-configs/string/split.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"split.d.ts","sourceRoot":"","sources":["../../../../src/function-configs/string/split.ts"],"names":[],"mappings":"AACA,OAAO,EACH,oBAAoB,EAEvB,MAAM,kBAAkB,CAAC;AAE1B,MAAM,WAAW,SAAS;IACtB,SAAS,CAAC,EAAE,MAAM,CAAC;CACtB;AAkCD,eAAO,MAAM,WAAW,EAAE,oBAAoB,CAAC,SAAS,CA0BvD,CAAC"}
+{"version":3,"file":"split.d.ts","sourceRoot":"","sources":["../../../../src/function-configs/string/split.ts"],"names":[],"mappings":"AACA,OAAO,EACH,oBAAoB,EAEvB,MAAM,kBAAkB,CAAC;AAG1B,MAAM,WAAW,SAAS;IACtB,SAAS,CAAC,EAAE,MAAM,CAAC;CACtB;AAkCD,eAAO,MAAM,WAAW,EAAE,oBAAoB,CAAC,SAAS,CAsCvD,CAAC"}

package/dist/src/function-configs/string/split.js

@@ -1,5 +1,6 @@
 import { FieldType } from '@terascope/types';
 import { ProcessMode, FunctionDefinitionType, FunctionDefinitionCategory, } from '../interfaces.js';
+import { sqlLiteral } from '../sql-helpers.js';
 const examples = [
     {
         args: {},
@@ -41,6 +42,18 @@ export const splitConfig = {
     create({ args: { delimiter = '' } }) {
         return splitFn(delimiter);
     },
+    /**
+     * `string_split`, for a non-empty delimiter only.
+     *
+     * The default delimiter is `''`, and `String(x).split('')` splits into UTF-16 code units, which
+     * can produce lone surrogates for astral input. `string_split` with an empty delimiter does
+     * not, so that case keeps the UDF.
+    */
+    sql: {
+        applies: (args) => typeof args.delimiter === 'string' && args.delimiter !== '',
+        expression: ({ value, args }) => `string_split(${value},`
+            + ` ${sqlLiteral(args.delimiter)})`,
+    },
     accepts: [FieldType.String],
     argument_schema: {
         delimiter: {

package/dist/src/function-configs/string/split.js.map

@@ -1 +1 @@
-{"version":3,"file":"split.js","sourceRoot":"","sources":["../../../../src/function-configs/string/split.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAC7C,OAAO,EACmB,WAAW,EAAE,sBAAsB,EAC9B,0BAA0B,GACxD,MAAM,kBAAkB,CAAC;AAM1B,MAAM,QAAQ,GAA2C;IACrD;QACI,IAAI,EAAE,EAAE;QACR,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,SAAS;QAChB,MAAM,EAAE,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC;KAC9C;IACD;QACI,IAAI,EAAE,EAAE,SAAS,EAAE,GAAG,EAAE;QACxB,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,SAAS;QAChB,MAAM,EAAE,CAAC,SAAS,CAAC;QACnB,WAAW,EAAE,uDAAuD;KACvE;IACD;QACI,IAAI,EAAE,EAAE,SAAS,EAAE,GAAG,EAAE;QACxB,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,WAAW;QAClB,MAAM,EAAE,CAAC,GAAG,EAAE,MAAM,EAAE,IAAI,CAAC;KAC9B;IACD;QACI,IAAI,EAAE,EAAE,SAAS,EAAE,GAAG,EAAE;QACxB,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,UAAU;QACjB,MAAM,EAAE,CAAC,GAAG,EAAE,QAAQ,CAAC;KAC1B;CACJ,CAAC;AAEF,MAAM,CAAC,MAAM,WAAW,GAAoC;IACxD,IAAI,EAAE,OAAO;IACb,IAAI,EAAE,sBAAsB,CAAC,eAAe;IAC5C,YAAY,EAAE,WAAW,CAAC,iBAAiB;IAC3C,QAAQ,EAAE,0BAA0B,CAAC,MAAM;IAC3C,WAAW,EAAE,2GAA2G;IACxH,QAAQ;IACR,MAAM,CAAC,EAAE,IAAI,EAAE,EAAE,SAAS,GAAG,EAAE,EAAE,EAAE;QAC/B,OAAO,OAAO,CAAC,SAAS,CAAC,CAAC;IAC9B,CAAC;IACD,OAAO,EAAE,CAAC,SAAS,CAAC,MAAM,CAAC;IAC3B,eAAe,EAAE;QACb,SAAS,EAAE;YACP,IAAI,EAAE,SAAS,CAAC,MAAM;YACtB,KAAK,EAAE,KAAK;YACZ,WAAW,EAAE,qDAAqD;SACrE;KACJ;IACD,WAAW,CAAC,EAAE,YAAY,EAAE;QACxB,OAAO;YACH,YAAY,EAAE;gBACV,GAAG,YAAY;gBACf,KAAK,EAAE,IAAI;aACd;SACJ,CAAC;IACN,CAAC;CACJ,CAAC;AAEF,SAAS,OAAO,CAAC,SAAiB;IAC9B,OAAO,SAAS,MAAM,CAAC,KAAK;QACxB,OAAO,MAAM,CAAC,KAAK,CAAC,CAAC,KAAK,CAAC,SAAS,CAAC,CAAC;IAC1C,CAAC,CAAC;AACN,CAAC"}
+{"version":3,"file":"split.js","sourceRoot":"","sources":["../../../../src/function-configs/string/split.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAC7C,OAAO,EACmB,WAAW,EAAE,sBAAsB,EAC9B,0BAA0B,GACxD,MAAM,kBAAkB,CAAC;AAC1B,OAAO,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAM/C,MAAM,QAAQ,GAA2C;IACrD;QACI,IAAI,EAAE,EAAE;QACR,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,SAAS;QAChB,MAAM,EAAE,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC;KAC9C;IACD;QACI,IAAI,EAAE,EAAE,SAAS,EAAE,GAAG,EAAE;QACxB,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,SAAS;QAChB,MAAM,EAAE,CAAC,SAAS,CAAC;QACnB,WAAW,EAAE,uDAAuD;KACvE;IACD;QACI,IAAI,EAAE,EAAE,SAAS,EAAE,GAAG,EAAE;QACxB,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,WAAW;QAClB,MAAM,EAAE,CAAC,GAAG,EAAE,MAAM,EAAE,IAAI,CAAC;KAC9B;IACD;QACI,IAAI,EAAE,EAAE,SAAS,EAAE,GAAG,EAAE;QACxB,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,SAAS,CAAC,MAAM,EAAE,EAAE,EAAE;QACzE,KAAK,EAAE,WAAW;QAClB,KAAK,EAAE,UAAU;QACjB,MAAM,EAAE,CAAC,GAAG,EAAE,QAAQ,CAAC;KAC1B;CACJ,CAAC;AAEF,MAAM,CAAC,MAAM,WAAW,GAAoC;IACxD,IAAI,EAAE,OAAO;IACb,IAAI,EAAE,sBAAsB,CAAC,eAAe;IAC5C,YAAY,EAAE,WAAW,CAAC,iBAAiB;IAC3C,QAAQ,EAAE,0BAA0B,CAAC,MAAM;IAC3C,WAAW,EAAE,2GAA2G;IACxH,QAAQ;IACR,MAAM,CAAC,EAAE,IAAI,EAAE,EAAE,SAAS,GAAG,EAAE,EAAE,EAAE;QAC/B,OAAO,OAAO,CAAC,SAAS,CAAC,CAAC;IAC9B,CAAC;IACD;;;;;;MAME;IACF,GAAG,EAAE;QACD,OAAO,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,OAAO,IAAI,CAAC,SAAS,KAAK,QAAQ,IAAI,IAAI,CAAC,SAAS,KAAK,EAAE;QAC9E,UAAU,EAAE,CAAC,EAAE,KAAK,EAAE,IAAI,EAAE,EAAE,EAAE,CAAC,gBAAgB,KAAK,GAAG;cACnD,IAAI,UAAU,CAAC,IAAI,CAAC,SAAmB,CAAC,GAAG;KACpD;IACD,OAAO,EAAE,CAAC,SAAS,CAAC,MAAM,CAAC;IAC3B,eAAe,EAAE;QACb,SAAS,EAAE;YACP,IAAI,EAAE,SAAS,CAAC,MAAM;YACtB,KAAK,EAAE,KAAK;YACZ,WAAW,EAAE,qDAAqD;SACrE;KACJ;IACD,WAAW,CAAC,EAAE,YAAY,EAAE;QACxB,OAAO;YACH,YAAY,EAAE;gBACV,GAAG,YAAY;gBACf,KAAK,EAAE,IAAI;aACd;SACJ,CAAC;IACN,CAAC;CACJ,CAAC;AAEF,SAAS,OAAO,CAAC,SAAiB;IAC9B,OAAO,SAAS,MAAM,CAAC,KAAK;QACxB,OAAO,MAAM,CAAC,KAAK,CAAC,CAAC,KAAK,CAAC,SAAS,CAAC,CAAC;IAC1C,CAAC,CAAC;AACN,CAAC"}

package/dist/src/function-configs/string/sql-regex-utils.d.ts

@@ -0,0 +1,91 @@
+/**
+ * Where DuckDB's regex engine (RE2) and JavaScript's differ.
+ *
+ * Some differences stop RE2 from compiling a pattern, which fails loudly. Others compile in both
+ * engines but match different characters, which silently returns a different answer. The helpers
+ * here detect both.
+*/
+/**
+ * Whether a regex can be handed to RE2, DuckDB's engine.
+ *
+ * RE2 has no lookaround and no backreferences, and the query errors if a pattern uses them.
+ * Anything containing `(?=`, `(?!`, `(?<=`, `(?<!` or a backreference like `\1` keeps the UDF.
+ *
+ * Named groups `(?<name>...)` are excluded by the same `(?<` test. RE2 supports them as
+ * `(?P<name>...)`, so this is stricter than necessary, which is the safe direction.
+*/
+export declare function isRe2Safe(pattern: string): boolean;
+/**
+ * Whether a replacement string is a plain literal.
+ *
+ * `$1` is a capture group in JavaScript but literal text in DuckDB, which uses `\1`: `'abc'` with
+ * `/(a)(b)/g` and `'$2$1'` gives `'bac'` in JavaScript and `'$2$1c'` in DuckDB. `$&`, `` $` ``,
+ * `$'` and `$$` also have meanings, so any replacement containing `$` keeps the UDF.
+*/
+export declare function isLiteralReplacement(replace: string): boolean;
+/**
+ * Every character where RE2's `\s`, `\S` and `.` disagree with JavaScript's, as an RE2 class.
+ *
+ * A pattern that passes `isRe2Safe` can still match different characters in the two engines:
+ *
+ * - `\s` differs on 20 characters. JavaScript's `\s` includes vertical tab, NBSP, the whole `Zs`
+ *   category, U+2028, U+2029 and the BOM; RE2's is exactly `[\t\n\f\r ]`. `\S` differs on the same
+ *   20.
+ * - `.` differs on 3. JavaScript's `.` excludes CR, U+2028 and U+2029 as well as LF; RE2's excludes
+ *   only LF.
+ * - `\w`, `\d` and `\b` agree, because both engines are ASCII-only there.
+ *
+ * Astral input is a separate problem. A pattern that matches any character (`.`, `\S`, a negated
+ * class) consumes one UTF-16 code unit in JavaScript and one code point in RE2, so `/\S/g` makes
+ * two replacements per astral character in JavaScript and one in SQL. Translating the class cannot
+ * fix that, so `withClassGuard` combines this class with `HAS_ASTRAL`.
+ *
+ * The guard is applied to the value, not the pattern: a value containing none of these characters
+ * takes the native path, and one that does keeps the UDF.
+*/
+export declare const RE2_CLASS_DIVERGENCE: string;
+/**
+ * Whether a pattern contains a class whose meaning differs between the engines.
+ *
+ * Only `.`, `\s`, `\S` and negated classes do; see `RE2_CLASS_DIVERGENCE`. A `.` inside a character
+ * class (`[.]`) is a literal dot, but detecting that requires parsing the pattern, so any `.`
+ * triggers the guard. Over-guarding costs a UDF call for unusual values; under-guarding returns a
+ * wrong answer.
+*/
+export declare function needsClassGuard(pattern: string): boolean;
+/**
+ * Whether a pattern's escapes mean the same thing in both engines.
+ *
+ * `\p{...}` and `\P{...}` are Unicode property escapes in RE2, but in JavaScript only under the `u`
+ * flag. Without it `\p` is an identity escape, so `/\p{L}/` matches the literal text `p{L}`.
+ * `\u{...}` behaves the same way. Neither errors, so patterns using them keep the UDF.
+*/
+export declare function hasPortableEscapes(pattern: string): boolean;
+/**
+ * Wraps a native regex expression in the per-value class guard, when the pattern needs it.
+ *
+ * Values the engine differences cannot affect, which is nearly all real text, use the native
+ * expression; the rest use the UDF.
+*/
+export declare function withClassGuard(pattern: string, value: string, native: string, udf: (v: string) => string): string;
+/** A literal, escaped for use inside an RE2 pattern. */
+export declare function re2Literal(value: string): string;
+/**
+ * How many capture groups a pattern has, or null if JavaScript cannot compile it.
+ *
+ * `matchAll` collects every group of every match, while `regexp_extract_all` takes one group index,
+ * so more than one group has no native form. The count comes from compiling `pattern|`, which
+ * matches the empty string and so reports the group count whether or not the pattern itself
+ * matches.
+*/
+export declare function countGroups(pattern: string): number | null;
+/**
+ * `JS_WHITESPACE` as an RE2 character class, generated from the code points.
+ *
+ * Several `core-utils` regexes use `\s`, and RE2's `\s` is narrower than JavaScript's (see
+ * `RE2_CLASS_DIVERGENCE`). When the pattern is one of ours, copied from `core-utils` rather than
+ * supplied by a caller, this class replaces `\s` so the pattern means what it means in JavaScript.
+ * Generating it from `JS_WHITESPACE` keeps the two in sync.
+*/
+export declare const JS_WHITESPACE_CLASS: string;
+//# sourceMappingURL=sql-regex-utils.d.ts.map

package/dist/src/function-configs/string/sql-regex-utils.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"sql-regex-utils.d.ts","sourceRoot":"","sources":["../../../../src/function-configs/string/sql-regex-utils.ts"],"names":[],"mappings":"AAEA;;;;;;EAME;AACF;;;;;;;;EAQE;AACF,wBAAgB,SAAS,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAIlD;AACD;;;;;;EAME;AACF,wBAAgB,oBAAoB,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAE7D;AACD;;;;;;;;;;;;;;;;;;;EAmBE;AACF,eAAO,MAAM,oBAAoB,QAC8B,CAAC;AAChE;;;;;;;EAOE;AACF,wBAAgB,eAAe,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAExD;AACD;;;;;;EAME;AACF,wBAAgB,kBAAkB,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAE3D;AACD;;;;;EAKE;AACF,wBAAgB,cAAc,CAC1B,OAAO,EAAE,MAAM,EACf,KAAK,EAAE,MAAM,EACb,MAAM,EAAE,MAAM,EACd,GAAG,EAAE,CAAC,CAAC,EAAE,MAAM,KAAK,MAAM,GAC3B,MAAM,CAKR;AACD,wDAAwD;AACxD,wBAAgB,UAAU,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CAEhD;AACD;;;;;;;EAOE;AACF,wBAAgB,WAAW,CAAC,OAAO,EAAE,MAAM,GAAG,MAAM,GAAG,IAAI,CAO1D;AACD;;;;;;;EAOE;AACF,eAAO,MAAM,mBAAmB,QAEhB,CAAC"}

package/dist/src/function-configs/string/sql-regex-utils.js

@@ -0,0 +1,123 @@
+import { HAS_ASTRAL, JS_WHITESPACE, sqlLiteral } from '../sql-helpers.js';
+/**
+ * Where DuckDB's regex engine (RE2) and JavaScript's differ.
+ *
+ * Some differences stop RE2 from compiling a pattern, which fails loudly. Others compile in both
+ * engines but match different characters, which silently returns a different answer. The helpers
+ * here detect both.
+*/
+/**
+ * Whether a regex can be handed to RE2, DuckDB's engine.
+ *
+ * RE2 has no lookaround and no backreferences, and the query errors if a pattern uses them.
+ * Anything containing `(?=`, `(?!`, `(?<=`, `(?<!` or a backreference like `\1` keeps the UDF.
+ *
+ * Named groups `(?<name>...)` are excluded by the same `(?<` test. RE2 supports them as
+ * `(?P<name>...)`, so this is stricter than necessary, which is the safe direction.
+*/
+export function isRe2Safe(pattern) {
+    if (/\(\?[=!]/.test(pattern))
+        return false;
+    if (/\(\?</.test(pattern))
+        return false;
+    return !/\\[1-9]/.test(pattern);
+}
+/**
+ * Whether a replacement string is a plain literal.
+ *
+ * `$1` is a capture group in JavaScript but literal text in DuckDB, which uses `\1`: `'abc'` with
+ * `/(a)(b)/g` and `'$2$1'` gives `'bac'` in JavaScript and `'$2$1c'` in DuckDB. `$&`, `` $` ``,
+ * `$'` and `$$` also have meanings, so any replacement containing `$` keeps the UDF.
+*/
+export function isLiteralReplacement(replace) {
+    return !replace.includes('$');
+}
+/**
+ * Every character where RE2's `\s`, `\S` and `.` disagree with JavaScript's, as an RE2 class.
+ *
+ * A pattern that passes `isRe2Safe` can still match different characters in the two engines:
+ *
+ * - `\s` differs on 20 characters. JavaScript's `\s` includes vertical tab, NBSP, the whole `Zs`
+ *   category, U+2028, U+2029 and the BOM; RE2's is exactly `[\t\n\f\r ]`. `\S` differs on the same
+ *   20.
+ * - `.` differs on 3. JavaScript's `.` excludes CR, U+2028 and U+2029 as well as LF; RE2's excludes
+ *   only LF.
+ * - `\w`, `\d` and `\b` agree, because both engines are ASCII-only there.
+ *
+ * Astral input is a separate problem. A pattern that matches any character (`.`, `\S`, a negated
+ * class) consumes one UTF-16 code unit in JavaScript and one code point in RE2, so `/\S/g` makes
+ * two replacements per astral character in JavaScript and one in SQL. Translating the class cannot
+ * fix that, so `withClassGuard` combines this class with `HAS_ASTRAL`.
+ *
+ * The guard is applied to the value, not the pattern: a value containing none of these characters
+ * takes the native path, and one that does keeps the UDF.
+*/
+export const RE2_CLASS_DIVERGENCE = '[\\x{0b}\\x{0d}\\x{a0}\\x{1680}\\x{2000}-\\x{200a}'
+    + '\\x{2028}\\x{2029}\\x{202f}\\x{205f}\\x{3000}\\x{feff}]';
+/**
+ * Whether a pattern contains a class whose meaning differs between the engines.
+ *
+ * Only `.`, `\s`, `\S` and negated classes do; see `RE2_CLASS_DIVERGENCE`. A `.` inside a character
+ * class (`[.]`) is a literal dot, but detecting that requires parsing the pattern, so any `.`
+ * triggers the guard. Over-guarding costs a UDF call for unusual values; under-guarding returns a
+ * wrong answer.
+*/
+export function needsClassGuard(pattern) {
+    return /\\[sS]/.test(pattern) || pattern.includes('.') || pattern.includes('[^');
+}
+/**
+ * Whether a pattern's escapes mean the same thing in both engines.
+ *
+ * `\p{...}` and `\P{...}` are Unicode property escapes in RE2, but in JavaScript only under the `u`
+ * flag. Without it `\p` is an identity escape, so `/\p{L}/` matches the literal text `p{L}`.
+ * `\u{...}` behaves the same way. Neither errors, so patterns using them keep the UDF.
+*/
+export function hasPortableEscapes(pattern) {
+    return !/\\[pP]\{/.test(pattern) && !/\\u\{/.test(pattern);
+}
+/**
+ * Wraps a native regex expression in the per-value class guard, when the pattern needs it.
+ *
+ * Values the engine differences cannot affect, which is nearly all real text, use the native
+ * expression; the rest use the UDF.
+*/
+export function withClassGuard(pattern, value, native, udf) {
+    if (!needsClassGuard(pattern))
+        return native;
+    const guard = `${RE2_CLASS_DIVERGENCE.slice(0, -1)}${HAS_ASTRAL.slice(1)}`;
+    return `CASE WHEN regexp_matches(${value}, ${sqlLiteral(guard)})`
+        + ` THEN ${udf(value)} ELSE ${native} END`;
+}
+/** A literal, escaped for use inside an RE2 pattern. */
+export function re2Literal(value) {
+    return value.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
+}
+/**
+ * How many capture groups a pattern has, or null if JavaScript cannot compile it.
+ *
+ * `matchAll` collects every group of every match, while `regexp_extract_all` takes one group index,
+ * so more than one group has no native form. The count comes from compiling `pattern|`, which
+ * matches the empty string and so reports the group count whether or not the pattern itself
+ * matches.
+*/
+export function countGroups(pattern) {
+    try {
+        const probe = new RegExp(`${pattern}|`).exec('');
+        return probe ? probe.length - 1 : null;
+    }
+    catch {
+        return null;
+    }
+}
+/**
+ * `JS_WHITESPACE` as an RE2 character class, generated from the code points.
+ *
+ * Several `core-utils` regexes use `\s`, and RE2's `\s` is narrower than JavaScript's (see
+ * `RE2_CLASS_DIVERGENCE`). When the pattern is one of ours, copied from `core-utils` rather than
+ * supplied by a caller, this class replaces `\s` so the pattern means what it means in JavaScript.
+ * Generating it from `JS_WHITESPACE` keeps the two in sync.
+*/
+export const JS_WHITESPACE_CLASS = `[${[...JS_WHITESPACE]
+    .map((char) => `\\x{${char.codePointAt(0).toString(16).padStart(2, '0')}}`)
+    .join('')}]`;
+//# sourceMappingURL=sql-regex-utils.js.map

package/dist/src/function-configs/string/sql-regex-utils.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"sql-regex-utils.js","sourceRoot":"","sources":["../../../../src/function-configs/string/sql-regex-utils.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,aAAa,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAE1E;;;;;;EAME;AACF;;;;;;;;EAQE;AACF,MAAM,UAAU,SAAS,CAAC,OAAe;IACrC,IAAI,UAAU,CAAC,IAAI,CAAC,OAAO,CAAC;QAAE,OAAO,KAAK,CAAC;IAC3C,IAAI,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC;QAAE,OAAO,KAAK,CAAC;IACxC,OAAO,CAAC,SAAS,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;AACpC,CAAC;AACD;;;;;;EAME;AACF,MAAM,UAAU,oBAAoB,CAAC,OAAe;IAChD,OAAO,CAAC,OAAO,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC;AAClC,CAAC;AACD;;;;;;;;;;;;;;;;;;;EAmBE;AACF,MAAM,CAAC,MAAM,oBAAoB,GAAG,oDAAoD;MAClF,yDAAyD,CAAC;AAChE;;;;;;;EAOE;AACF,MAAM,UAAU,eAAe,CAAC,OAAe;IAC3C,OAAO,QAAQ,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,OAAO,CAAC,QAAQ,CAAC,GAAG,CAAC,IAAI,OAAO,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;AACrF,CAAC;AACD;;;;;;EAME;AACF,MAAM,UAAU,kBAAkB,CAAC,OAAe;IAC9C,OAAO,CAAC,UAAU,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;AAC/D,CAAC;AACD;;;;;EAKE;AACF,MAAM,UAAU,cAAc,CAC1B,OAAe,EACf,KAAa,EACb,MAAc,EACd,GAA0B;IAE1B,IAAI,CAAC,eAAe,CAAC,OAAO,CAAC;QAAE,OAAO,MAAM,CAAC;IAC7C,MAAM,KAAK,GAAG,GAAG,oBAAoB,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC;IAC3E,OAAO,4BAA4B,KAAK,KAAK,UAAU,CAAC,KAAK,CAAC,GAAG;UAC3D,SAAS,GAAG,CAAC,KAAK,CAAC,SAAS,MAAM,MAAM,CAAC;AACnD,CAAC;AACD,wDAAwD;AACxD,MAAM,UAAU,UAAU,CAAC,KAAa;IACpC,OAAO,KAAK,CAAC,OAAO,CAAC,qBAAqB,EAAE,MAAM,CAAC,CAAC;AACxD,CAAC;AACD;;;;;;;EAOE;AACF,MAAM,UAAU,WAAW,CAAC,OAAe;IACvC,IAAI,CAAC;QACD,MAAM,KAAK,GAAG,IAAI,MAAM,CAAC,GAAG,OAAO,GAAG,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACjD,OAAO,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;IAC3C,CAAC;IAAC,MAAM,CAAC;QACL,OAAO,IAAI,CAAC;IAChB,CAAC;AACL,CAAC;AACD;;;;;;;EAOE;AACF,MAAM,CAAC,MAAM,mBAAmB,GAAG,IAAI,CAAC,GAAG,aAAa,CAAC;KACpD,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,OAAO,IAAI,CAAC,WAAW,CAAC,CAAC,CAAE,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,GAAG,CAAC;KAC3E,IAAI,CAAC,EAAE,CAAC,GAAG,CAAC"}

package/dist/src/function-configs/string/sql-utils.d.ts

@@ -0,0 +1,191 @@
+/**
+ * Helpers shared by the SQL expressions on the string function configs.
+*/
+/**
+ * `validator.isAlpha`'s `en-US` alphabet, as an RE2 pattern.
+ *
+ * Other locales use different letter sets, and several cannot be written as a simple class, so the
+ * functions using this handle only the default locale.
+*/
+export declare const ALPHA_LOCALES = "^[A-Za-z]+$";
+/** `validator.isAlphanumeric`'s `en-US` set. */
+export declare const ALPHANUMERIC_LOCALES = "^[0-9A-Za-z]+$";
+/** True when no locale was given, so `validator`'s `en-US` default applies. */
+export declare function defaultLocale(locale: unknown): boolean;
+/**
+ * `encodeURIComponent`, built from `url_encode` plus the five characters it over-escapes.
+ *
+ * `url_encode` percent-escapes `!`, `'`, `(`, `)` and `*`, which `encodeURIComponent` leaves alone.
+ * Unescaping them afterwards is safe: a literal `%` in the input is already `%25` by then, so a
+ * `%21` in the output can only come from a real `!`.
+*/
+export declare function encodeURIComponentSql(value: string): string;
+/**
+ * `validator.isHash`'s length table, copied from its source. The check is only `^[a-fA-F0-9]{N}$`.
+*/
+export declare const HASH_LENGTHS: Record<string, number>;
+export declare function uuidPattern(version: unknown): string | null;
+/**
+ * lodash's test for which word splitter to use. The case converters run in SQL only when it does
+ * not match.
+ *
+ * `_.camelCase` and the other converters run `words(deburr(string).replace(/['’]/g, ''))`, and
+ * `words` picks one of two algorithms:
+ *
+ * ```js
+ * var reHasUnicodeWord = /[a-z][A-Z]|[A-Z]{2}[a-z]|[0-9][a-zA-Z]|[a-zA-Z][0-9]|[^a-zA-Z0-9 ]/;
+ * var reAsciiWord = /[^\x00-\x2f\x3a-\x40\x5b-\x60\x7b-\x7f]+/g;
+ * ```
+ *
+ * When `reHasUnicodeWord` does not match, the result is `string.match(reAsciiWord)`, which splits
+ * on ASCII punctuation only, and SQL reproduces that exactly. The other algorithm handles case
+ * transitions, digit/letter boundaries, acronyms like `XMLHttpRequest` and combining marks, and
+ * keeps the UDF.
+ *
+ * `deburr` does nothing to input this guard admits, which contains only `[a-zA-Z0-9 ]`.
+*/
+export declare const HAS_UNICODE_WORD = "[a-z][A-Z]|[A-Z]{2}[a-z]|[0-9][a-zA-Z]|[a-zA-Z][0-9]|[^a-zA-Z0-9 ]";
+/**
+ * A case conversion over the ASCII word list.
+ *
+ * `join` is the separator between words; `first` and `rest` say how each word is cased. An empty
+ * word list gives `''`, which is what `_.camelCase('')` and `_.camelCase('---')` return.
+*/
+export declare function caseConvertSql(value: string, options: {
+    join: string;
+    first: (word: string) => string;
+    rest: (word: string) => string;
+}): string;
+/** `word[0].toUpperCase() + word.slice(1).toLowerCase()`, which is lodash's `capitalize`. */
+export declare function capitalizeSql(word: string): string;
+/**
+ * `_.upperFirst`: the first character uppercased and the rest left as is.
+ *
+ * This is not `capitalize`, which also lowercases the rest. `_.startCase` uses this one, which is
+ * why `startCase('HELLO WORLD')` is `'HELLO WORLD'` and not `'Hello World'`.
+*/
+export declare function upperFirstSql(word: string): string;
+/**
+ * Base64 validation per RFC 4648 with padding, `validator.isBase64`'s default.
+ *
+ * ```js
+ * var base64WithPadding = /^[A-Za-z0-9+/]+={0,2}$/;
+ * if (str === '') return true;
+ * if (options.padding && str.length % 4 !== 0) return false;
+ * ```
+ *
+ * This intentionally does not reproduce `core-utils`' `isBase64`, which also requires a UTF-8 round
+ * trip to be lossless. `toString('utf8')` replaces every invalid byte with U+FFFD, so that check
+ * accepts only base64 of UTF-8 text and rejects most base64-encoded binary.
+*/
+export declare function isBase64Sql(value: string): string;
+/**
+ * `validator.isFQDN` with its default options, for ASCII input.
+ *
+ * The function has no TLD list, which is what makes it expressible in SQL. With the defaults
+ * (`require_tld`, no underscores, no trailing dot, no wildcard, no numeric TLD, max length
+ * enforced) the algorithm is:
+ *
+ * 1. at least two dot-separated parts;
+ * 2. the last part matches `/^([a-z…]{2,}|xn[a-z0-9-]{2,})$/i`, contains no whitespace and is not
+ *    all digits;
+ * 3. every part is 1-63 characters, matches `/^[a-z_0-9-]+$/i`, has no full-width character, and
+ *    neither starts nor ends with `-`; and with `allow_underscores` false, contains no `_`.
+ *
+ * Non-ASCII input keeps the UDF. `validator`'s character classes run to `\u{ffff}` and include a
+ * full-width exclusion, which is not worth reproducing.
+*/
+export declare function isFQDNSql(value: string, udf: (v: string) => string): string;
+/**
+ * A hash or byte encoding of a string in SQL, shared by `encode` and `createID`.
+ *
+ * Returns null for a combination DuckDB cannot express, which is what the callers' `applies` check.
+ * The results match `node:crypto` and `Buffer` byte for byte, including for empty, non-ASCII,
+ * astral and combining-mark input:
+ *
+ * - `md5`, `sha1` and `sha256` return a lowercase hex digest, matching
+ *   `createHash(...).digest('hex')`. There is no `sha512` or `sha384`.
+ * - A base64 digest is `to_base64(unhex(<digest>))`.
+ * - `Buffer.from(x).toString('hex')` is `lower(hex(encode(x)))`. `hex()` is uppercase, and
+ *   `encode()` is used because a VARCHAR-to-BLOB cast rejects non-ASCII.
+ * - `Buffer.from(x).toString('base64')` is `to_base64(encode(x))`.
+*/
+export declare const SQL_HASHES: readonly string[];
+export declare function hashSql(algo: string, digest: string, value: string): string | null;
+/** Whether `hashSql` has an expression for this pair, so an `applies` need not build it. */
+export declare function hasHashSql(algo: unknown, digest: unknown): boolean;
+/**
+ * Whether a value is a single code point (not a single UTF-16 code unit).
+ *
+ * `extract`'s marker mode compares `char === start` while iterating code points, so a
+ * multi-character marker never matches and an astral one matches as a unit.
+*/
+export declare function isOneCodePoint(value: unknown): boolean;
+/**
+ * `extract`'s marker mode: the text between the first `start` and the first `end` after it.
+ *
+ * This mirrors `_subSlice`, which finds `start` and then collects characters until `end`. A second
+ * `start` before the `end` is content (`'<a<b>'` extracts `'a<b'`), an unterminated run yields
+ * null, and `'a|b|c'` with `|` for both markers extracts `'b'`.
+*/
+export declare function extractMarkerSql(value: string, start: string, end: string): string;
+/**
+ * `extract`'s marker mode with `global`: every extraction, as a list.
+ *
+ * The repeated scan is a non-greedy `(?s).*?` between the two escaped markers. `(?s)` is required
+ * because the scan collects newlines and RE2's `.` does not match one without it. For example,
+ * `'a|b|c|d'` gives `['b']` and `'<>'` gives `['']`.
+*/
+export declare function extractMarkerAllSql(value: string, start: string, end: string): string;
+/**
+ * `extract`'s regex mode, built from what `matchAll` does.
+ *
+ * `matchAll` forces the `g` flag and, per match, collects every capture group if the pattern has
+ * any, or the whole match otherwise. `extract` then takes the first element, or the whole list
+ * under `global`. So the SQL is `regexp_extract` at group 0 or 1, and `regexp_extract_all` for the
+ * list.
+ *
+ * The no-match case needs care. `matchAll` returns null when nothing matched, and its loop also
+ * stops on an empty match, so a pattern whose first match is empty gives null, not `''`.
+ * `regexp_extract` returns `''` for both, which `nullif` maps to null. When extracting a group, the
+ * whole match is tested first, because a group can capture the empty string inside a non-empty
+ * match.
+*/
+export declare function extractRegexSql(value: string, pattern: string, group: number): string;
+/** `extract`'s regex mode with `global`: every match, or every first capture group. */
+export declare function extractRegexAllSql(value: string, pattern: string, group: number): string;
+/**
+ * A list expression that returns NULL rather than `[]` when nothing matched.
+ *
+ * `extract` under `global` returns null for no match in both modes, never an empty list, while
+ * `regexp_extract_all` returns `[]`.
+*/
+export declare function emptyToNull(list: string): string;
+/**
+ * `isPhoneNumberLike`: strip every non-digit and check that 7 to 20 digits remain. It does not use
+ * libphonenumber.
+ *
+ * ```
+ * const testValue = toString(input).trim().replace(/\D/g, '');
+ * return inNumberRange(testValue.length, { min: 7, max: 20, inclusive: true });
+ * ```
+ *
+ * `trim()` cannot change the answer because whitespace is not a digit. `\D` is `[^0-9]` in both
+ * engines, and the remaining digits are ASCII, so `length()` counting characters agrees with
+ * JavaScript counting code units.
+*/
+export declare function phoneNumberLikeSql(value: string): string;
+/**
+ * Shannon entropy without an aggregate: split into characters, count each distinct one, and sum the
+ * terms.
+ *
+ * `list_filter` over the distinct characters does the per-character counting. It is quadratic in
+ * the number of distinct characters, which for text is bounded by the alphabet rather than the
+ * string length. The result is exact.
+ *
+ * The JavaScript builds its frequency table over code points (`for (const char of input)`) but
+ * divides by `input.length`, which counts UTF-16 code units. The two differ only for astral input,
+ * so astral input keeps the UDF.
+*/
+export declare function shannonEntropySql(value: string): string;
+//# sourceMappingURL=sql-utils.d.ts.map

package/dist/src/function-configs/string/sql-utils.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"sql-utils.d.ts","sourceRoot":"","sources":["../../../../src/function-configs/string/sql-utils.ts"],"names":[],"mappings":"AAGA;;EAEE;AAEF;;;;;EAKE;AACF,eAAO,MAAM,aAAa,gBAAgB,CAAC;AAE3C,gDAAgD;AAChD,eAAO,MAAM,oBAAoB,mBAAmB,CAAC;AAErD,+EAA+E;AAC/E,wBAAgB,aAAa,CAAC,MAAM,EAAE,OAAO,GAAG,OAAO,CAEtD;AAED;;;;;;EAME;AACF,wBAAgB,qBAAqB,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CAQ3D;AAED;;EAEE;AACF,eAAO,MAAM,YAAY,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAc/C,CAAC;AAYF,wBAAgB,WAAW,CAAC,OAAO,EAAE,OAAO,GAAG,MAAM,GAAG,IAAI,CAkB3D;AAED;;;;;;;;;;;;;;;;;;EAkBE;AACF,eAAO,MAAM,gBAAgB,uEAAuE,CAAC;AAOrG;;;;;EAKE;AACF,wBAAgB,cAAc,CAC1B,KAAK,EAAE,MAAM,EACb,OAAO,EAAE;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,KAAK,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,MAAM,CAAC;IAAC,IAAI,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,MAAM,CAAA;CAAE,GAC3F,MAAM,CAMR;AAED,6FAA6F;AAC7F,wBAAgB,aAAa,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAElD;AAED;;;;;EAKE;AACF,wBAAgB,aAAa,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAElD;AAED;;;;;;;;;;;;EAYE;AACF,wBAAgB,WAAW,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CAGjD;AAED;;;;;;;;;;;;;;;EAeE;AACF,wBAAgB,SAAS,CAAC,KAAK,EAAE,MAAM,EAAE,GAAG,EAAE,CAAC,CAAC,EAAE,MAAM,KAAK,MAAM,GAAG,MAAM,CAW3E;AAED;;;;;;;;;;;;;EAaE;AACF,eAAO,MAAM,UAAU,EAAE,SAAS,MAAM,EAA8B,CAAC;AAEvE,wBAAgB,OAAO,CAAC,IAAI,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAAG,MAAM,GAAG,IAAI,CAOlF;AAED,4FAA4F;AAC5F,wBAAgB,UAAU,CAAC,IAAI,EAAE,OAAO,EAAE,MAAM,EAAE,OAAO,GAAG,OAAO,CAIlE;AAED;;;;;EAKE;AACF,wBAAgB,cAAc,CAAC,KAAK,EAAE,OAAO,GAAG,OAAO,CAEtD;AAED;;;;;;EAME;AACF,wBAAgB,gBAAgB,CAAC,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,GAAG,EAAE,MAAM,GAAG,MAAM,CAMlF;AAED;;;;;;EAME;AACF,wBAAgB,mBAAmB,CAAC,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,GAAG,EAAE,MAAM,GAAG,MAAM,CAGrF;AAED;;;;;;;;;;;;;EAaE;AACF,wBAAgB,eAAe,CAC3B,KAAK,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAC9C,MAAM,CAMR;AAED,uFAAuF;AACvF,wBAAgB,kBAAkB,CAC9B,KAAK,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAC9C,MAAM,CAER;AAED;;;;;EAKE;AACF,wBAAgB,WAAW,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAEhD;AAED;;;;;;;;;;;;EAYE;AACF,wBAAgB,kBAAkB,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CAExD;AAED;;;;;;;;;;;EAWE;AACF,wBAAgB,iBAAiB,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CAYvD"}