1 USING: help.markup help.syntax kernel math sequences strings
6 { $var-description "Stores the current " { $link lexer } " instance." }
7 { $class-description "An object for tokenizing parser input. It has the following slots:"
9 { { $snippet "text" } " - the lines being parsed; an array of strings" }
10 { { $snippet "line" } " - the line number being parsed; unlike most indices this is 1-based for friendlier error reporting and integration with text editors" }
11 { { $snippet "column" } " - the current column position, zero-based" }
13 "Custom lexing can be implemented by delegating a tuple to an instance of this class and implementing the " { $link skip-word } " and " { $link skip-blank } " generic words." } ;
16 { $values { "text" { $sequence string } } { "lexer" lexer } }
17 { $description "Creates a new lexer for tokenizing the given sequence of lines." } ;
20 { $values { "lexer" lexer } }
21 { $description "Advances the lexer to the next input line, discarding the remainder of the current line." } ;
24 { $error-description "Thrown when the lexer encounters invalid input. A lexer error wraps an underlying error together with line and column numbers." } ;
27 { $values { "msg" "an error" } { "error" lexer-error } }
28 { $description "Creates a new " { $link lexer-error } ", filling in the location information from the current " { $link lexer } "." } ;
31 { $values { "i" "a starting index" } { "seq" sequence } { "?" boolean } { "n" integer } }
32 { $description "Skips to the first space character (if " { $snippet "boolean" } " is " { $link f } ") or the first non-space character (otherwise). Tabulations used as separators instead of spaces will be flagged as an error." } ;
34 HELP: change-lexer-column
35 { $values { "lexer" lexer } { "quot" { $quotation ( ..a col line -- ..b newcol ) } } }
36 { $description "Applies a quotation to the current column and line text to produce a new column, and moves the lexer position." } ;
39 { $values { "lexer" lexer } }
40 { $contract "Skips whitespace characters." }
41 { $notes "Custom lexers can implement this generic word." } ;
44 { $values { "lexer" lexer } }
46 "Skips until the end of the current token."
48 "The default implementation treats a single " { $snippet "\"" } " as a word by itself; otherwise it searches forward until a whitespace character or the end of the line."
50 { $notes "Custom lexers can implement this generic word." } ;
52 HELP: still-parsing-line?
53 { $values { "lexer" lexer } { "?" boolean } }
54 { $description "Outputs " { $link f } " if the end of the current line has been reached, " { $link t } " otherwise." } ;
57 { $values { "lexer" lexer } { "str/f" { $maybe string } } }
58 { $description "Reads the next token from the lexer. Tokens are delimited by whitespace, with the exception that " { $snippet "\"" } " is treated like a single token even when not followed by whitespace." } ;
61 { $values { "str/f" { $maybe string } } }
62 { $description "Reads the next token from the lexer. Tokens are delimited by whitespace, with the exception that " { $snippet "\"" } " is treated like a single token even when not followed by whitespace. This word outputs " { $link f } " on end of input. To throw an error on end of input, use " { $link scan-token } " instead." }
66 { $values { "str" string } }
67 { $description "Reads the next token from the lexer. Tokens are delimited by whitespace, with the exception that " { $snippet "\"" } " is treated like a single token even when not followed by whitespace. This word throws " { $link unexpected-eof } " on end of input. To output " { $link f } " on end of input, use " { $link ?scan-token } " instead." }
71 { $values { "lexer" lexer } { "?" boolean } }
72 { $description "Outputs " { $link f } " if end of input has been reached, " { $link t } " otherwise." } ;
75 { $values { "end" string } { "quot" { $quotation ( ... token -- ... ) } } }
76 { $description "Reads a sequence of tokens until the first occurrence of " { $snippet "end" } ". " { $snippet "quot" } " is called on each token as it is read." }
77 { $examples "This word is used to implement " { $link POSTPONE: USING: } "." }
81 { $values { "end" string } { "quot" { $quotation ( ... token -- ... elt ) } } { "seq" { $sequence object } } }
82 { $description "Reads a sequence of tokens until the first occurrence of " { $snippet "end" } ". " { $snippet "quot" } " is called on each token as it is read, and the results are collected into a new output sequence." }
86 { $values { "end" string } { "seq" { $sequence string } } }
87 { $description "Reads a sequence of tokens until the first occurrence of " { $snippet "end" } ". The tokens remain as strings and are not processed in any way. This word is equivalent to " { $link map-tokens } " with an empty quotation." }
91 { $values { "want" { $maybe word } } { "got" word } }
92 { $description "Throws an " { $link unexpected } " error." }
93 { $error-description "Thrown by the parser if an unmatched closing delimiter is encountered." }
95 "Parsing the following snippet will throw this error:"
100 { $values { "word" "a " { $link word } } }
101 { $description "Throws an " { $link unexpected } " error indicating the parser was looking for an occurrence of " { $snippet "word" } " but encountered end of file." } ;
104 { $values { "lexer" lexer } { "quot" quotation } { "newquot" quotation } }
105 { $description "Calls the quotation with the " { $link lexer } " variable set to the given lexer. The quotation can make use of words such as " { $link scan-token } ". Any errors thrown by the quotation are wrapped in " { $link lexer-error } " instances." } ;
107 ARTICLE: "parser-lexer" "The lexer"
108 "A variable that encapsulate internal parser state:"
109 { $subsections lexer }
110 "Creating a default lexer:"
111 { $subsections <lexer> }
112 "A word to test of the end of input has been reached:"
113 { $subsections still-parsing? }
114 "A word to advance the lexer to the next line:"
115 { $subsections next-line }
116 "Two generic words to override the lexer's token boundary detection:"
121 "Utility combinator:"
122 { $subsections with-lexer } ;