@platforma-sdk/workflow-tengo 1.8.1 → 2.0.0

package/dist/tengo/lib/pframes.util.lib.tengo

@@ -4,14 +4,6 @@ constants := import("@platforma-sdk/workflow-tengo:pframes.constants")
 objects := import("@platforma-sdk/workflow-tengo:objects")
 
 _PRE_PROCESS_STEP_SCHEMA := [`or`,
-	{
-		// Replace cell value with the first full RegEx match
-		// https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/match
-		`type`: `string,regex=regexpExtract`,
-		// String representing ECMAScript RegEx
-		// If there are no or more than one matches - result would become NA
-		`pattern`: `string`
-	},
 	{
 		// Perform JS String.prototype.replace() operation
 		// https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/replace
@@ -25,23 +17,58 @@ _PRE_PROCESS_STEP_SCHEMA := [`or`,
 		// https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/replace#specifying_a_string_as_the_replacement
 		// Empty string as result would become NA.
 		`replacement`: `string`
+	},
+	{
+		// Simplified 'regexpReplace' with replacement set to $1.
+		// This means that string is replaced with first capture group value.
+		// Example 1:
+		// - input: 123___abc.xlsx
+		// - pattern: \d+___([a-z]+).xlsx
+		// - result: abc
+		// Example 2:
+		// - input: 123___abc.xlsx
+		// - pattern: (\d+)___([a-z]+).xlsx
+		// - result: 123
+		// Example 3:
+		// - input: 123___abc.xlsx
+		// - pattern: ((\d+)___([a-z]+)).xlsx
+		// - result: 123___abc
+		`type`: `string,regex=regexpExtract`,
+		// String representing ECMAScript RegEx with at least one capturing group.
+		// RegEx must match the entire string, this would be enforced even when ^ and $ are skipped.
+		// If there are no matches - value would be replaced with empty string.
+		// Wrong example:
+		// - input: 123___abc.xlsx
+		// - pattern: (\d+___[a-z]+)
+		// - result: empty string, as .xlsx part is missing in pattern, so pattern was not matched
+		// Correct example:
+		// - input: 123___abc.xlsx
+		// - pattern: (\d+___[a-z]+).xlsx
+		// - result: 123___abc
+		`pattern`: `string`
 	}]
 
 _SPEC_AXES_SCHEMA := {
 	// Column label from XSV
 	`column`: `string`,
-	// Pre-processing operations to be performed just after reading XSV, before any other operations
+	// Regular expression, if matched - whole row would be skipped;
+	// Performed just after reading XSV before any other operations;
+	// default: no filter
+	`filterOutRegex,omitempty`: `string`,
+	// Pre-processing operations to be performed just after filtering out rows
 	`preProcess,omitempty`: [_PRE_PROCESS_STEP_SCHEMA],
+	// Regular expression, if matched - value is considered to be N/A;
+	// default: Int, Long - check that the value is a valid integer number;
+	//          Float, Double - check that the value is a valid float number, not a NaN;
+	//          String - accept anything;
+	`naRegex,omitempty`: `string`,
 	// Should the N/A values (or empty rows) be allowed;
 	// default: false
 	`allowNA,omitempty`: `bool`,
-	// Should the parsing error be interpreted as N/A;
-	// default: false
-	`parseErrorToNA,omitempty`: `bool`,
 	// Specification of the axis
 	`spec`: {
-		// Type of the axis value
-		`type`: `string,regex=Int|Long|Float|Double|String|Bytes`,
+		// Type of axis values
+		`type`: `string,regex=Int|Long|Float|Double|String`,
 		// Name of the axis to be used in spec;
 		// default: column label
 		`name,omitempty`: `string`,
@@ -60,23 +87,27 @@ _SPEC_AXES_SCHEMA := {
 _SPEC_COLUMN_SCHEMA := {
 	// Column label from XSV
 	`column`: `string`,
-	// ID of the column to be used in spec and as a saved filename;
-	// default: column label with all special characters replaced with '_'
-	`id,omitempty`: `string`,
-	// Pre-processing operations to be performed just after reading XSV, before any other operations;
-	// warning: when pre-processing is used, spec valueType must be set
+	// Regular expression, if matched - whole row would be skipped;
+	// Performed just after reading XSV before any other operations;
+	// default: no filter
+	`filterOutRegex,omitempty`: `string`,
+	// Pre-processing operations to be performed just after filtering out rows
 	`preProcess,omitempty`: [_PRE_PROCESS_STEP_SCHEMA],
+	// Regular expression, if matched - value is considered to be N/A;
+	// default: Int, Long - check that the value is a valid integer number;
+	//          Float, Double - check that the value is a valid float number, not a NaN;
+	//          String - accept anything;
+	`naRegex,omitempty`: `string`,
 	// Should the N/A values (or empty rows) be allowed;
 	// default: true
 	`allowNA,omitempty`: `bool`,
-	// Should the parsing error be interpreted as N/A;
-	// default: false
-	`parseErrorToNA,omitempty`: `bool`,
+	// ID of the column to be used in spec and as a saved filename;
+	// default: column label with all special characters replaced with '_'
+	`id,omitempty`: `string`,
 	// Specification of the column
-	`spec,omitempty`: {
-		// Type of column values;
-		// default: automatically detected to be one of Long, Double, String
-		`type,omitempty`: `string,regex=Int|Long|Float|Double|String|Bytes`,
+	`spec`: {
+		// Type of column values
+		`valueType`: `string,regex=Int|Long|Float|Double|String`,
 		// Name of the column to be used in spec;
 		// default: column label
 		`name,omitempty`: `string`,
@@ -107,42 +138,33 @@ _SPEC_INDEX_SCHEMA := {
 }
 
 PFCONV_IMPORT_CFG_SCHEMA := {
-	// Columns would be stored using specified format;
-	// default: Binary
-	`storageFormat,omitempty` : `string,regex=Binary|Json`,
-	// Partitioning key length;
-	// default: 0
-	`partitionKeyLength,omitempty` : `number`,
-	// XSV columns to use as PColumn axes, order of axes in resulting columns
-	// would match the order of spec entries provided here
-	`axes`: [_SPEC_AXES_SCHEMA],
-	// XSV columns to use as PColumn values, each exported individually
-	`columns`: [_SPEC_COLUMN_SCHEMA],
-	// Axis of type Int with XSV row numbers (would be the last one);
-	// default: do not create additional axis with indexes
-	`index,omitempty`: _SPEC_INDEX_SCHEMA,
-	// String representing NA values of types Int, Long, Float, Double;
-	// default: NaN
-	`naStr,omitempty`: `string`,
-	// String representing NA values of types String, Bytes;
-	// default: null
-	`nullStr,omitempty`: `string`,
 	// Single ASCII character to be used as separator;
 	// default: ',' for .csv, '\t' for .tsv
 	`separator,omitempty`: `string`,
-	// Interpret empty string as NA value;
-	// default: true
-	`emptyStrAsNA,omitempty`: `bool`,
-	// Prefix all column names with given string;
-	// default: names would be preserved
-	`columnNamePrefix,omitempty`: `string`,
 	// Resolve duplicates by adding sequential suffixes to column labels;
 	// default: true
 	`allowColumnLabelDuplicates,omitempty`: `bool`,
+	// XSV columns to use as PColumn axes, order of axes in resulting columns
+	// would match the order of spec entries provided here
+	`axes`: [_SPEC_AXES_SCHEMA],
+	// Axis of type Long with XSV row numbers (would be the last one);
+	// default: do not create additional axis with indexes
+	`index,omitempty`: _SPEC_INDEX_SCHEMA,
+	// XSV columns to use as PColumn values, each exported individually
+	`columns`: [_SPEC_COLUMN_SCHEMA],
 	// When columns spec is provided but no such column was found in XSV - create such column
 	// filled with NA values instead of failing;
 	// default: false
-	`allowArtificialColumns,omitempty`: `bool`
+	`allowArtificialColumns,omitempty`: `bool`,
+	// Prefix all column names with given string;
+	// default: names would be preserved
+	`columnNamePrefix,omitempty`: `string`,
+	// Columns would be stored using specified format;
+	// default: Binary
+	`storageFormat,omitempty` : `string,regex=Binary|Json`,
+	// Partitioning key length;
+	// default: 0
+	`partitionKeyLength,omitempty` : `number`
 }
 
 _COLUMN_FILTER_SCHEMA := {
@@ -179,7 +201,7 @@ PFCONV_EXPORT_CFG_SCHEMA := {
 	// During export, columns with equal axes specifications would be joined into single table
 	// using the join type specified;
 	// default: Full
-	`joinType,omitempty` : `string,regex=Full|Inner`
+	`joinType,omitempty`: `string,regex=Full|Inner`
 }
 
 /**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@platforma-sdk/workflow-tengo",
-  "version": "1.8.1",
+  "version": "2.0.0",
   "description": "Tengo SDK library",
   "types": "./dist/index.d.ts",
   "main": "./dist/index.js",
@@ -16,7 +16,7 @@
     "./dist/**/*"
   ],
   "dependencies": {
-    "@milaboratories/software-pframes-conv": "1.6.8",
+    "@milaboratories/software-pframes-conv": "2.0.1",
     "@platforma-open/milaboratories.software-small-binaries": "^1.14.5"
   },
   "devDependencies": {