@wdprlib/parser 0.1.5 → 1.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (6) hide show
  1. package/README.md +63 -0
  2. package/dist/index.cjs +1532 -219
  3. package/dist/index.d.cts +10 -1
  4. package/dist/index.d.ts +10 -1
  5. package/dist/index.js +1532 -219
  6. package/package.json +2 -2
package/dist/index.d.cts CHANGED
@@ -4,7 +4,7 @@ import { Position } from "@wdprlib/ast";
4
4
  /**
5
5
  * Token types for Wikidot markup
6
6
  */
7
- type TokenType = "EOF" | "TEXT" | "IDENTIFIER" | "NEWLINE" | "WHITESPACE" | "BLOCK_OPEN" | "BLOCK_CLOSE" | "BLOCK_END_OPEN" | "BOLD_MARKER" | "ITALIC_MARKER" | "UNDERLINE_MARKER" | "STRIKE_MARKER" | "SUPER_MARKER" | "SUB_MARKER" | "MONO_MARKER" | "MONO_CLOSE" | "HEADING_MARKER" | "HR_MARKER" | "LIST_BULLET" | "LIST_NUMBER" | "BLOCKQUOTE_MARKER" | "TABLE_MARKER" | "TABLE_HEADER" | "TABLE_LEFT" | "TABLE_CENTER" | "TABLE_RIGHT" | "CODE_OPEN" | "CODE_CLOSE" | "LINK_OPEN" | "LINK_CLOSE" | "BRACKET_OPEN" | "BRACKET_CLOSE" | "BRACKET_ANCHOR" | "BRACKET_STAR" | "PIPE" | "EQUALS" | "COLON" | "SLASH" | "STAR" | "HASH" | "AT" | "AMPERSAND" | "BACKSLASH" | "QUOTED_STRING" | "RAW_OPEN" | "RAW_CLOSE" | "RAW_BLOCK_OPEN" | "RAW_BLOCK_CLOSE" | "COLOR_MARKER" | "UNDERSCORE" | "COMMENT_OPEN" | "COMMENT_CLOSE" | "CLEAR_FLOAT" | "CLEAR_FLOAT_LEFT" | "CLEAR_FLOAT_RIGHT" | "LEFT_DOUBLE_ANGLE" | "RIGHT_DOUBLE_ANGLE";
7
+ type TokenType = "EOF" | "TEXT" | "IDENTIFIER" | "NEWLINE" | "WHITESPACE" | "BLOCK_OPEN" | "BLOCK_CLOSE" | "BLOCK_END_OPEN" | "BOLD_MARKER" | "ITALIC_MARKER" | "UNDERLINE_MARKER" | "STRIKE_MARKER" | "SUPER_MARKER" | "SUB_MARKER" | "MONO_MARKER" | "MONO_CLOSE" | "HEADING_MARKER" | "HR_MARKER" | "LIST_BULLET" | "LIST_NUMBER" | "BLOCKQUOTE_MARKER" | "TABLE_MARKER" | "TABLE_HEADER" | "TABLE_LEFT" | "TABLE_CENTER" | "TABLE_RIGHT" | "CODE_OPEN" | "CODE_CLOSE" | "LINK_OPEN" | "LINK_CLOSE" | "BRACKET_OPEN" | "BRACKET_CLOSE" | "BRACKET_ANCHOR" | "BRACKET_STAR" | "PIPE" | "EQUALS" | "COLON" | "SLASH" | "STAR" | "HASH" | "AT" | "AMPERSAND" | "BACKSLASH" | "QUOTED_STRING" | "RAW_OPEN" | "RAW_CLOSE" | "RAW_BLOCK_OPEN" | "RAW_BLOCK_CLOSE" | "COLOR_MARKER" | "UNDERSCORE" | "BACKSLASH_BREAK" | "COMMENT_OPEN" | "COMMENT_CLOSE" | "CLEAR_FLOAT" | "CLEAR_FLOAT_LEFT" | "CLEAR_FLOAT_RIGHT" | "LEFT_DOUBLE_ANGLE" | "RIGHT_DOUBLE_ANGLE";
8
8
  /**
9
9
  * Token
10
10
  */
@@ -32,6 +32,7 @@ interface LexerOptions {
32
32
  declare class Lexer {
33
33
  private state;
34
34
  private options;
35
+ private splitBlockClosePositions;
35
36
  constructor(source: string, options?: LexerOptions);
36
37
  /**
37
38
  * Tokenize the entire source
@@ -46,6 +47,14 @@ declare class Lexer {
46
47
  */
47
48
  private current;
48
49
  /**
50
+ * Check if [[# is followed by an invalid anchor name that closes with ]].
51
+ * Valid: [[# valid-name]] where name matches [-_A-Za-z0-9.%]+
52
+ * Invalid: [[# name with spaces]] or [[# name$special]]
53
+ * When invalid, returns the position of the closing ]] so the lexer can
54
+ * emit tokens that allow the inner [# text] to be parsed as a described link.
55
+ */
56
+ private findInvalidAnchorNameEnd;
57
+ /**
49
58
  * Check if source matches pattern at current position
50
59
  */
51
60
  private match;
package/dist/index.d.ts CHANGED
@@ -4,7 +4,7 @@ import { Position } from "@wdprlib/ast";
4
4
  /**
5
5
  * Token types for Wikidot markup
6
6
  */
7
- type TokenType = "EOF" | "TEXT" | "IDENTIFIER" | "NEWLINE" | "WHITESPACE" | "BLOCK_OPEN" | "BLOCK_CLOSE" | "BLOCK_END_OPEN" | "BOLD_MARKER" | "ITALIC_MARKER" | "UNDERLINE_MARKER" | "STRIKE_MARKER" | "SUPER_MARKER" | "SUB_MARKER" | "MONO_MARKER" | "MONO_CLOSE" | "HEADING_MARKER" | "HR_MARKER" | "LIST_BULLET" | "LIST_NUMBER" | "BLOCKQUOTE_MARKER" | "TABLE_MARKER" | "TABLE_HEADER" | "TABLE_LEFT" | "TABLE_CENTER" | "TABLE_RIGHT" | "CODE_OPEN" | "CODE_CLOSE" | "LINK_OPEN" | "LINK_CLOSE" | "BRACKET_OPEN" | "BRACKET_CLOSE" | "BRACKET_ANCHOR" | "BRACKET_STAR" | "PIPE" | "EQUALS" | "COLON" | "SLASH" | "STAR" | "HASH" | "AT" | "AMPERSAND" | "BACKSLASH" | "QUOTED_STRING" | "RAW_OPEN" | "RAW_CLOSE" | "RAW_BLOCK_OPEN" | "RAW_BLOCK_CLOSE" | "COLOR_MARKER" | "UNDERSCORE" | "COMMENT_OPEN" | "COMMENT_CLOSE" | "CLEAR_FLOAT" | "CLEAR_FLOAT_LEFT" | "CLEAR_FLOAT_RIGHT" | "LEFT_DOUBLE_ANGLE" | "RIGHT_DOUBLE_ANGLE";
7
+ type TokenType = "EOF" | "TEXT" | "IDENTIFIER" | "NEWLINE" | "WHITESPACE" | "BLOCK_OPEN" | "BLOCK_CLOSE" | "BLOCK_END_OPEN" | "BOLD_MARKER" | "ITALIC_MARKER" | "UNDERLINE_MARKER" | "STRIKE_MARKER" | "SUPER_MARKER" | "SUB_MARKER" | "MONO_MARKER" | "MONO_CLOSE" | "HEADING_MARKER" | "HR_MARKER" | "LIST_BULLET" | "LIST_NUMBER" | "BLOCKQUOTE_MARKER" | "TABLE_MARKER" | "TABLE_HEADER" | "TABLE_LEFT" | "TABLE_CENTER" | "TABLE_RIGHT" | "CODE_OPEN" | "CODE_CLOSE" | "LINK_OPEN" | "LINK_CLOSE" | "BRACKET_OPEN" | "BRACKET_CLOSE" | "BRACKET_ANCHOR" | "BRACKET_STAR" | "PIPE" | "EQUALS" | "COLON" | "SLASH" | "STAR" | "HASH" | "AT" | "AMPERSAND" | "BACKSLASH" | "QUOTED_STRING" | "RAW_OPEN" | "RAW_CLOSE" | "RAW_BLOCK_OPEN" | "RAW_BLOCK_CLOSE" | "COLOR_MARKER" | "UNDERSCORE" | "BACKSLASH_BREAK" | "COMMENT_OPEN" | "COMMENT_CLOSE" | "CLEAR_FLOAT" | "CLEAR_FLOAT_LEFT" | "CLEAR_FLOAT_RIGHT" | "LEFT_DOUBLE_ANGLE" | "RIGHT_DOUBLE_ANGLE";
8
8
  /**
9
9
  * Token
10
10
  */
@@ -32,6 +32,7 @@ interface LexerOptions {
32
32
  declare class Lexer {
33
33
  private state;
34
34
  private options;
35
+ private splitBlockClosePositions;
35
36
  constructor(source: string, options?: LexerOptions);
36
37
  /**
37
38
  * Tokenize the entire source
@@ -46,6 +47,14 @@ declare class Lexer {
46
47
  */
47
48
  private current;
48
49
  /**
50
+ * Check if [[# is followed by an invalid anchor name that closes with ]].
51
+ * Valid: [[# valid-name]] where name matches [-_A-Za-z0-9.%]+
52
+ * Invalid: [[# name with spaces]] or [[# name$special]]
53
+ * When invalid, returns the position of the closing ]] so the lexer can
54
+ * emit tokens that allow the inner [# text] to be parsed as a described link.
55
+ */
56
+ private findInvalidAnchorNameEnd;
57
+ /**
49
58
  * Check if source matches pattern at current position
50
59
  */
51
60
  private match;