@ai-sdk-tool/rxml 0.1.0 → 0.1.2-canary.0

package/dist/index.d.cts

@@ -1,4 +1,4 @@
-import { Transform, TransformCallback, Readable } from 'stream';
+import { Transform, TransformCallback, Readable } from 'node:stream';
 
 /**
  * Core types for the robust-xml parser
@@ -66,6 +66,28 @@ interface StringifyOptions {
     strictBooleanAttributes?: boolean;
 }
 
+/**
+ * XML stringification based on TXML's stringify approach
+ * Replaces the fast-xml-parser XMLBuilder with a native implementation
+ */
+
+/**
+ * Stringify an object to XML
+ */
+declare function stringify(rootTag: string, obj: unknown, options?: StringifyOptions): string;
+/**
+ * Stringify parsed XML nodes back to XML string
+ */
+declare function stringifyNodes(nodes: (RXMLNode | string)[], format?: boolean, options?: Pick<StringifyOptions, "strictBooleanAttributes" | "minimalEscaping">): string;
+/**
+ * Stringify a single XML node
+ */
+declare function stringifyNode(node: RXMLNode, depth?: number, format?: boolean, options?: Pick<StringifyOptions, "strictBooleanAttributes" | "minimalEscaping">): string;
+/**
+ * Convert content to a string representation (similar to TXML's toContentString)
+ */
+declare function toContentString(nodes: (RXMLNode | string)[]): string;
+
 /**
  * Main XML parser that integrates tokenization, schema awareness, and error tolerance
  * This replaces the fast-xml-parser dependency with a TXML-based implementation
@@ -90,7 +112,7 @@ declare function simplify(children: (RXMLNode | string)[]): unknown;
 /**
  * Filter XML nodes (similar to TXML's filter)
  */
-declare function filter(children: (RXMLNode | string)[], filterFn: (node: RXMLNode, index: number, depth: number, path: string) => boolean, depth?: number, path?: string): RXMLNode[];
+declare function filter(children: (RXMLNode | string)[], filterFn: (node: RXMLNode, index: number, currentDepth: number, currentPath: string) => boolean, depth?: number, path?: string): RXMLNode[];
 
 /**
  * Streaming XML parser based on TXML's transformStream approach
@@ -102,14 +124,22 @@ declare function filter(children: (RXMLNode | string)[], filterFn: (node: RXMLNo
  */
 declare class XMLTransformStream extends Transform {
     private buffer;
-    private position;
     private readonly parseOptions;
     private emittedCount;
     private sawTagChar;
-    constructor(offset?: number | string, parseOptions?: ParseOptions);
-    _transform(chunk: Buffer, encoding: BufferEncoding, callback: TransformCallback): void;
+    constructor(_offset?: number | string, parseOptions?: ParseOptions);
+    _transform(chunk: Buffer, _encoding: BufferEncoding, callback: TransformCallback): void;
     _flush(callback: TransformCallback): void;
     private processBuffer;
+    private trimToNextTag;
+    private tryProcessSpecialNode;
+    private trySkipStrayClosingTag;
+    private extractTagInfo;
+    private tryProcessSelfClosingTag;
+    private tryProcessRegularElement;
+    private findMatchingClosingTag;
+    private findNextOpeningTag;
+    private advancePastClosingTag;
     /**
      * Emit an element and recursively emit its children as separate events
      */
@@ -146,10 +176,62 @@ declare class XMLTokenizer {
     private readonly xmlString;
     private readonly options;
     constructor(xmlString: string, options?: ParseOptions);
+    /**
+     * Handle closing tag parsing
+     */
+    private handleClosingTag;
+    /**
+     * Check if we're at end of string and should throw unclosed tag error
+     */
+    private checkUnclosedTag;
+    /**
+     * Process special content (comments, CDATA, DOCTYPE) and track if we consumed to end
+     */
+    private processSpecialContent;
+    /**
+     * Handle text content parsing
+     */
+    private handleTextContent;
+    /**
+     * Handle regular element parsing
+     */
+    private handleRegularElement;
+    /**
+     * Process a single child element based on the current character
+     */
+    private processSingleChild;
     /**
      * Parse XML children recursively
      */
     parseChildren(tagName?: string): (RXMLNode | string)[];
+    /**
+     * Check if character is whitespace
+     */
+    private isWhitespace;
+    /**
+     * Skip whitespace characters
+     */
+    private skipWhitespace;
+    /**
+     * Parse attribute value
+     */
+    private parseAttributeValue;
+    /**
+     * Parse single attribute
+     */
+    private parseAttribute;
+    /**
+     * Parse all attributes
+     */
+    private parseAttributes;
+    /**
+     * Parse special tag content (script, style)
+     */
+    private parseSpecialTagContent;
+    /**
+     * Parse node children based on tag type
+     */
+    private parseNodeChildren;
     /**
      * Parse a single XML node
      */
@@ -184,6 +266,35 @@ declare class XMLTokenizer {
     setPosition(pos: number): void;
 }
 
+/**
+ * Error classes for robust-xml parser
+ */
+declare class RXMLParseError extends Error {
+    cause?: unknown;
+    line?: number;
+    column?: number;
+    constructor(message: string, cause?: unknown, line?: number, column?: number);
+}
+declare class RXMLDuplicateStringTagError extends Error {
+    constructor(message: string);
+}
+declare class RXMLCoercionError extends Error {
+    cause?: unknown;
+    constructor(message: string, cause?: unknown);
+}
+declare class RXMLStringifyError extends Error {
+    cause?: unknown;
+    constructor(message: string, cause?: unknown);
+}
+declare class RXMLStreamError extends Error {
+    cause?: unknown;
+    constructor(message: string, cause?: unknown);
+}
+
+declare function unwrapJsonSchema(schema: unknown): unknown;
+declare function getSchemaType(schema: unknown): string | undefined;
+declare function coerceBySchema(value: unknown, schema?: unknown): unknown;
+
 /**
  * Schema-aware type coercion for robust-xml
  * Integrates with the existing coercion system but adds XML-specific handling
@@ -238,53 +349,18 @@ declare function countTagOccurrences(xmlContent: string, tagName: string, exclud
     start: number;
     end: number;
 }>, shouldSkipFirst?: boolean): number;
-
-/**
- * XML stringification based on TXML's stringify approach
- * Replaces the fast-xml-parser XMLBuilder with a native implementation
- */
-
 /**
- * Stringify an object to XML
+ * Find all top-level ranges for a tag (for handling duplicates)
  */
-declare function stringify(rootTag: string, obj: unknown, options?: StringifyOptions): string;
-/**
- * Stringify parsed XML nodes back to XML string
- */
-declare function stringifyNodes(nodes: (RXMLNode | string)[], format?: boolean, options?: Pick<StringifyOptions, "strictBooleanAttributes" | "minimalEscaping">): string;
-/**
- * Stringify a single XML node
- */
-declare function stringifyNode(node: RXMLNode, depth?: number, format?: boolean, options?: Pick<StringifyOptions, "strictBooleanAttributes" | "minimalEscaping">): string;
-/**
- * Convert content to a string representation (similar to TXML's toContentString)
- */
-declare function toContentString(nodes: (RXMLNode | string)[]): string;
+declare function findAllTopLevelRanges(xmlContent: string, tagName: string): Array<{
+    start: number;
+    end: number;
+}>;
 
 /**
- * Error classes for robust-xml parser
+ * Unescape XML entities
  */
-declare class RXMLParseError extends Error {
-    cause?: unknown | undefined;
-    line?: number | undefined;
-    column?: number | undefined;
-    constructor(message: string, cause?: unknown | undefined, line?: number | undefined, column?: number | undefined);
-}
-declare class RXMLDuplicateStringTagError extends Error {
-    constructor(message: string);
-}
-declare class RXMLCoercionError extends Error {
-    cause?: unknown | undefined;
-    constructor(message: string, cause?: unknown | undefined);
-}
-declare class RXMLStringifyError extends Error {
-    cause?: unknown | undefined;
-    constructor(message: string, cause?: unknown | undefined);
-}
-declare class RXMLStreamError extends Error {
-    cause?: unknown | undefined;
-    constructor(message: string, cause?: unknown | undefined);
-}
+declare function unescapeXml(text: string): string;
 
 interface Options {
     textNodeName?: string;
@@ -292,4 +368,4 @@ interface Options {
     onError?: (message: string, context?: Record<string, unknown>) => void;
 }
 
-export { type Options, type ParseOptions, RXMLCoercionError, RXMLDuplicateStringTagError, type RXMLNode, RXMLParseError, RXMLStreamError, RXMLStringifyError, type StringifyOptions, XMLTokenizer, XMLTransformStream, coerceDomBySchema, countTagOccurrences, createXMLStream, domToObject, extractRawInner, filter, findElementByIdStream, findElementsByClassStream, findFirstTopLevelRange, getPropertySchema, getStringTypedProperties, parse, parseFromStream, parseNode, parseWithoutSchema, processArrayContent, processIndexedTuple, processXMLStream, simplify, stringify, stringifyNode, stringifyNodes, toContentString };
+export { type Options, type ParseOptions, RXMLCoercionError, RXMLDuplicateStringTagError, type RXMLNode, RXMLParseError, RXMLStreamError, RXMLStringifyError, type StringifyOptions, XMLTokenizer, XMLTransformStream, coerceBySchema, coerceDomBySchema, countTagOccurrences, createXMLStream, domToObject, extractRawInner, filter, findAllTopLevelRanges, findElementByIdStream, findElementsByClassStream, findFirstTopLevelRange, getPropertySchema, getSchemaType, getStringTypedProperties, parse, parseFromStream, parseNode, parseWithoutSchema, processArrayContent, processIndexedTuple, processXMLStream, simplify, stringify, stringifyNode, stringifyNodes, toContentString, unescapeXml, unwrapJsonSchema };

package/dist/index.d.ts

@@ -1,4 +1,4 @@
-import { Transform, TransformCallback, Readable } from 'stream';
+import { Transform, TransformCallback, Readable } from 'node:stream';
 
 /**
  * Core types for the robust-xml parser
@@ -66,6 +66,28 @@ interface StringifyOptions {
     strictBooleanAttributes?: boolean;
 }
 
+/**
+ * XML stringification based on TXML's stringify approach
+ * Replaces the fast-xml-parser XMLBuilder with a native implementation
+ */
+
+/**
+ * Stringify an object to XML
+ */
+declare function stringify(rootTag: string, obj: unknown, options?: StringifyOptions): string;
+/**
+ * Stringify parsed XML nodes back to XML string
+ */
+declare function stringifyNodes(nodes: (RXMLNode | string)[], format?: boolean, options?: Pick<StringifyOptions, "strictBooleanAttributes" | "minimalEscaping">): string;
+/**
+ * Stringify a single XML node
+ */
+declare function stringifyNode(node: RXMLNode, depth?: number, format?: boolean, options?: Pick<StringifyOptions, "strictBooleanAttributes" | "minimalEscaping">): string;
+/**
+ * Convert content to a string representation (similar to TXML's toContentString)
+ */
+declare function toContentString(nodes: (RXMLNode | string)[]): string;
+
 /**
  * Main XML parser that integrates tokenization, schema awareness, and error tolerance
  * This replaces the fast-xml-parser dependency with a TXML-based implementation
@@ -90,7 +112,7 @@ declare function simplify(children: (RXMLNode | string)[]): unknown;
 /**
  * Filter XML nodes (similar to TXML's filter)
  */
-declare function filter(children: (RXMLNode | string)[], filterFn: (node: RXMLNode, index: number, depth: number, path: string) => boolean, depth?: number, path?: string): RXMLNode[];
+declare function filter(children: (RXMLNode | string)[], filterFn: (node: RXMLNode, index: number, currentDepth: number, currentPath: string) => boolean, depth?: number, path?: string): RXMLNode[];
 
 /**
  * Streaming XML parser based on TXML's transformStream approach
@@ -102,14 +124,22 @@ declare function filter(children: (RXMLNode | string)[], filterFn: (node: RXMLNo
  */
 declare class XMLTransformStream extends Transform {
     private buffer;
-    private position;
     private readonly parseOptions;
     private emittedCount;
     private sawTagChar;
-    constructor(offset?: number | string, parseOptions?: ParseOptions);
-    _transform(chunk: Buffer, encoding: BufferEncoding, callback: TransformCallback): void;
+    constructor(_offset?: number | string, parseOptions?: ParseOptions);
+    _transform(chunk: Buffer, _encoding: BufferEncoding, callback: TransformCallback): void;
     _flush(callback: TransformCallback): void;
     private processBuffer;
+    private trimToNextTag;
+    private tryProcessSpecialNode;
+    private trySkipStrayClosingTag;
+    private extractTagInfo;
+    private tryProcessSelfClosingTag;
+    private tryProcessRegularElement;
+    private findMatchingClosingTag;
+    private findNextOpeningTag;
+    private advancePastClosingTag;
     /**
      * Emit an element and recursively emit its children as separate events
      */
@@ -146,10 +176,62 @@ declare class XMLTokenizer {
     private readonly xmlString;
     private readonly options;
     constructor(xmlString: string, options?: ParseOptions);
+    /**
+     * Handle closing tag parsing
+     */
+    private handleClosingTag;
+    /**
+     * Check if we're at end of string and should throw unclosed tag error
+     */
+    private checkUnclosedTag;
+    /**
+     * Process special content (comments, CDATA, DOCTYPE) and track if we consumed to end
+     */
+    private processSpecialContent;
+    /**
+     * Handle text content parsing
+     */
+    private handleTextContent;
+    /**
+     * Handle regular element parsing
+     */
+    private handleRegularElement;
+    /**
+     * Process a single child element based on the current character
+     */
+    private processSingleChild;
     /**
      * Parse XML children recursively
      */
     parseChildren(tagName?: string): (RXMLNode | string)[];
+    /**
+     * Check if character is whitespace
+     */
+    private isWhitespace;
+    /**
+     * Skip whitespace characters
+     */
+    private skipWhitespace;
+    /**
+     * Parse attribute value
+     */
+    private parseAttributeValue;
+    /**
+     * Parse single attribute
+     */
+    private parseAttribute;
+    /**
+     * Parse all attributes
+     */
+    private parseAttributes;
+    /**
+     * Parse special tag content (script, style)
+     */
+    private parseSpecialTagContent;
+    /**
+     * Parse node children based on tag type
+     */
+    private parseNodeChildren;
     /**
      * Parse a single XML node
      */
@@ -184,6 +266,35 @@ declare class XMLTokenizer {
     setPosition(pos: number): void;
 }
 
+/**
+ * Error classes for robust-xml parser
+ */
+declare class RXMLParseError extends Error {
+    cause?: unknown;
+    line?: number;
+    column?: number;
+    constructor(message: string, cause?: unknown, line?: number, column?: number);
+}
+declare class RXMLDuplicateStringTagError extends Error {
+    constructor(message: string);
+}
+declare class RXMLCoercionError extends Error {
+    cause?: unknown;
+    constructor(message: string, cause?: unknown);
+}
+declare class RXMLStringifyError extends Error {
+    cause?: unknown;
+    constructor(message: string, cause?: unknown);
+}
+declare class RXMLStreamError extends Error {
+    cause?: unknown;
+    constructor(message: string, cause?: unknown);
+}
+
+declare function unwrapJsonSchema(schema: unknown): unknown;
+declare function getSchemaType(schema: unknown): string | undefined;
+declare function coerceBySchema(value: unknown, schema?: unknown): unknown;
+
 /**
  * Schema-aware type coercion for robust-xml
  * Integrates with the existing coercion system but adds XML-specific handling
@@ -238,53 +349,18 @@ declare function countTagOccurrences(xmlContent: string, tagName: string, exclud
     start: number;
     end: number;
 }>, shouldSkipFirst?: boolean): number;
-
-/**
- * XML stringification based on TXML's stringify approach
- * Replaces the fast-xml-parser XMLBuilder with a native implementation
- */
-
 /**
- * Stringify an object to XML
+ * Find all top-level ranges for a tag (for handling duplicates)
  */
-declare function stringify(rootTag: string, obj: unknown, options?: StringifyOptions): string;
-/**
- * Stringify parsed XML nodes back to XML string
- */
-declare function stringifyNodes(nodes: (RXMLNode | string)[], format?: boolean, options?: Pick<StringifyOptions, "strictBooleanAttributes" | "minimalEscaping">): string;
-/**
- * Stringify a single XML node
- */
-declare function stringifyNode(node: RXMLNode, depth?: number, format?: boolean, options?: Pick<StringifyOptions, "strictBooleanAttributes" | "minimalEscaping">): string;
-/**
- * Convert content to a string representation (similar to TXML's toContentString)
- */
-declare function toContentString(nodes: (RXMLNode | string)[]): string;
+declare function findAllTopLevelRanges(xmlContent: string, tagName: string): Array<{
+    start: number;
+    end: number;
+}>;
 
 /**
- * Error classes for robust-xml parser
+ * Unescape XML entities
  */
-declare class RXMLParseError extends Error {
-    cause?: unknown | undefined;
-    line?: number | undefined;
-    column?: number | undefined;
-    constructor(message: string, cause?: unknown | undefined, line?: number | undefined, column?: number | undefined);
-}
-declare class RXMLDuplicateStringTagError extends Error {
-    constructor(message: string);
-}
-declare class RXMLCoercionError extends Error {
-    cause?: unknown | undefined;
-    constructor(message: string, cause?: unknown | undefined);
-}
-declare class RXMLStringifyError extends Error {
-    cause?: unknown | undefined;
-    constructor(message: string, cause?: unknown | undefined);
-}
-declare class RXMLStreamError extends Error {
-    cause?: unknown | undefined;
-    constructor(message: string, cause?: unknown | undefined);
-}
+declare function unescapeXml(text: string): string;
 
 interface Options {
     textNodeName?: string;
@@ -292,4 +368,4 @@ interface Options {
     onError?: (message: string, context?: Record<string, unknown>) => void;
 }
 
-export { type Options, type ParseOptions, RXMLCoercionError, RXMLDuplicateStringTagError, type RXMLNode, RXMLParseError, RXMLStreamError, RXMLStringifyError, type StringifyOptions, XMLTokenizer, XMLTransformStream, coerceDomBySchema, countTagOccurrences, createXMLStream, domToObject, extractRawInner, filter, findElementByIdStream, findElementsByClassStream, findFirstTopLevelRange, getPropertySchema, getStringTypedProperties, parse, parseFromStream, parseNode, parseWithoutSchema, processArrayContent, processIndexedTuple, processXMLStream, simplify, stringify, stringifyNode, stringifyNodes, toContentString };
+export { type Options, type ParseOptions, RXMLCoercionError, RXMLDuplicateStringTagError, type RXMLNode, RXMLParseError, RXMLStreamError, RXMLStringifyError, type StringifyOptions, XMLTokenizer, XMLTransformStream, coerceBySchema, coerceDomBySchema, countTagOccurrences, createXMLStream, domToObject, extractRawInner, filter, findAllTopLevelRanges, findElementByIdStream, findElementsByClassStream, findFirstTopLevelRange, getPropertySchema, getSchemaType, getStringTypedProperties, parse, parseFromStream, parseNode, parseWithoutSchema, processArrayContent, processIndexedTuple, processXMLStream, simplify, stringify, stringifyNode, stringifyNodes, toContentString, unescapeXml, unwrapJsonSchema };