A PEG.js parser for ICU MessageFormat strings – part of messageformat. Outputs an AST defined by parser.pegjs.
The generated parse(src, [options]) function takes two parameters, first the string to be parsed, and a second optional parameter options, an object with the following possible keys:
-
cardinalandordinal– Arrays of valid plural categories for the current locale, used to validatepluralandselectordinalkeys. If these are missing or set to false, the full set of valid Unicode CLDR keys is used:'zero', 'one', 'two', 'few', 'many', 'other'. To disable this check, pass in an empty array. -
strictNumberSign– Inside apluralorselectordinalstatement, a pound symbol (#) is replaced with the input number. By default,#is also parsed as a special character in nested statements too, and can be escaped using apostrophes ('#'). SettingstrictNumberSignto true will make the parser follow the ICU MessageFormat spec more closely, and only parse#as a special character directly inside apluralorselectordinalstatement. Outside those,#and'#'will be parsed as literal text.
The parser only supports the default DOUBLE_OPTIONAL apostrophe mode. A single apostrophe only starts quoted literal text if preceded by a curly brace ({}) or a pound symbol (#) inside a plural or selectordinal statement, depending on the value of strictNumberSign. Otherwise, it is a literal apostrophe. A double apostrophe is always a literal apostrophe.
npm install messageformat-parser> var parse = require('messageformat-parser').parse; > parse('So {wow}.') [ 'So ', { type: 'argument', arg: 'wow' }, '.' ] > parse('Such { thing }. { count, selectordinal, one {First} two {Second}' + ' few {Third} other {#th} } word.') [ 'Such ', { type: 'argument', arg: 'thing' }, '. ', { type: 'selectordinal', arg: 'count', offset: 0, cases: [ { key: 'one', tokens: [ 'First' ] }, { key: 'two', tokens: [ 'Second' ] }, { key: 'few', tokens: [ 'Third' ] }, { key: 'other', tokens: [ { type: 'octothorpe' }, 'th' ] } ] }, ' word.' ] > parse('Many{type,select,plural{ numbers}selectordinal{ counting}' + 'select{ choices}other{ some {type}}}.') [ 'Many', { type: 'select', arg: 'type', cases: [ { key: 'plural', tokens: [ ' numbers' ] }, { key: 'selectordinal', tokens: [ ' counting' ] }, { key: 'select', tokens: [ ' choices' ] }, { key: 'other', tokens: [ ' some', { type: 'argument', arg: 'type' } ] } ] }, '.' ] > parse('{Such compliance') // SyntaxError: Expected ",", "}" or [ \t\n\r] but "c" found. > var msg = '{words, plural, zero{No words} one{One word} other{# words}}'; > var englishKeys = { cardinal: [ 'one', 'other' ], ordinal: [ 'one', 'two', 'few', 'other' ] }; > parse(msg) [ { type: 'plural', arg: 'words', offset: 0, cases: [ { key: 'zero', tokens: [ 'No words' ] }, { key: 'one', tokens: [ 'One word' ] }, { key: 'other', tokens: [ { type: 'octothorpe' }, ' words' ] } ] } ] > parse(msg, englishKeys) // Error: Invalid key `zero` for argument `words`. Valid plural keys for this // locale are `one`, `other`, and explicit keys like `=0`.For more example usage, please take a look at our test suite.
The output of parse() is a Token array:
type Token = string | Argument | Plural | Select | Function type Argument = { type: 'argument', arg: Identifier } type Plural = { type: 'plural' | 'selectordinal', arg: Identifier, offset: number, cases: PluralCase[] } type Select = { type: 'select', arg: Identifier, cases: SelectCase[] } type Function = { type: 'function', arg: Identifier, key: Identifier, param: string | null } type PluralCase = { key: 'zero' | 'one' | 'two' | 'few' | 'many' | 'other' | '=0' | '=1' | '=2' | ..., tokens: (Token | Octothorpe)[] } type SelectCase = { key: Identifier, tokens: strictNumberSign ? Token[] : (Token | Octothorpe)[] } type Octothorpe = { type: 'octothorpe' } type Identifier = string // not containing whitespace or control charactersReleased under the MIT license. See the messageformat README for details.