Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
78 changes: 55 additions & 23 deletions readme.md
Original file line number Diff line number Diff line change
Expand Up @@ -69,9 +69,11 @@ License: MIT
- [Tuple](#Tuple)
- [Union](#Union)
- [Array](#Array)
- [Until](#Until)
- [Optional](#Optional)
- [Epsilon](#Epsilon)
- [Range](#Range)
- [Until](#Until)
- [UntilNonEmpty](#UntilNonEmpty)
- [Terminals](#Terminals)
- [Number](#Number)
- [String](#String)
Expand Down Expand Up @@ -187,27 +189,6 @@ const R2 = Runtime.Parse(T, 'X X X Y Z') // const R2 = [['X', 'X', '
const R3 = Runtime.Parse(T, 'Y Z') // const R3 = [[], 'Y Z']
```

### Until

The Until combinator will parse characters up to (but not including) one of the specified sentinel string values. If a sentinel value is not found, parsing fails.

**BNF**

```bnf
<T> ::= ? any character until ['Z'] ?
```

**TypeScript**

```typescript
const T = Runtime.Until(['Z']) // const T = {
// type: 'Until',
// values: ['Z']
// }

const R = Runtime.Parse(T, 'X Y Z') // const R = ['X Y ', 'Z']
```

### Optional

The Optional combinator parses zero or one occurrence of the interior parser, returning a tuple with one element or an empty tuple if there is no match.
Expand Down Expand Up @@ -256,7 +237,58 @@ const R1 = Runtime.Parse(T, 'X Y Z') // const R1 = [['X', 'Y'], '
const R2 = Runtime.Parse(T, 'Y Z') // const R2 = [[], 'Y Z']
```

## Terminals
## Range Combinators

ParseBox range combinators match character sequences up to one or more terminating sentinel strings. These combinators are used to match arbituary Unicode (UTF-16) sequences.


### Until

The Until combinator parses characters up to (but not including) one of the specified sentinel string values. It captures all characters encountered before the sentinel. If a sentinel value is not found in the input, parsing fails. Until succeeds even if it matches a zero-length string. This occurs if a sentinel is found immediately at the current parsing position.

**BNF**

```bnf
<T> ::= ? any character sequence (0 or more) until 'Z' ?
```

**TypeScript**

```typescript
const T = Runtime.Until(['Z']) // const T = {
// type: 'Until',
// values: ['Z']
// }

const R = Runtime.Parse(T, 'X Y Z') // const R = ['X Y ', 'Z']
```

### UntilNonEmpty

The UntilNonEmpty combinator works the same as Until, but it fails if the parsed content yields a zero-length string.

**BNF**

```bnf
<T> ::= ? any character sequence (1 or more) until 'Z'. fails on zero length ?
```

**TypeScript**

```typescript
const T = Runtime.UntilNonEmpty(['Z']) // const T = {
// type: 'UntilNonEmpty',
// values: ['Z']
// }

const R1 = Runtime.Parse(T, 'X Y Z') // const R1 = ['X Y ', 'Z']

const R2 = Runtime.Parse(T, ' Z') // const R2 = [' ', 'Z']

const R3 = Runtime.Parse(T, 'Z') // const R3 = []
```

## Terminal Combinators

ParseBox provides combinators for parsing common lexical tokens, such as numbers, identifiers, and strings, enabling static, optimized parsing of typical JavaScript constructs.

Expand Down
52 changes: 28 additions & 24 deletions src/compile/common/comment.ts
Original file line number Diff line number Diff line change
Expand Up @@ -27,58 +27,62 @@ THE SOFTWARE.
---------------------------------------------------------------------------*/

// deno-fmt-ignore-file
// deno-lint-ignore-file no-unused-vars
// deno-lint-ignore-file

import { Runtime } from '../../runtime/index.ts'
import { Unreachable } from './unreachable.ts'
import { Escape } from './escape.ts'

function FromArray(parser: Runtime.IArray): string {
return `${FromParser(parser.parser)}[]`
}
function FromContext(parser: Runtime.IContext): string {
return `${FromParser(parser.left)} -> ${FromParser(parser.right)}`
}
function FromTuple(parser: Runtime.ITuple): string {
return `[${parser.parsers.map((parser) => `${FromParser(parser)}`).join(', ')}]`
function FromConst(parser: Runtime.IConst): string {
return `'${Escape(parser.value)}'`
}
function FromUnion(parser: Runtime.IUnion): string {
return parser.parsers.map((parser) => `${FromParser(parser)}`).join(' | ')
function FromIdent(parser: Runtime.IIdent): string {
return `<Ident>`
}
function FromArray(parser: Runtime.IArray): string {
return `${FromParser(parser.parser)}[]`
function FromNumber(parser: Runtime.INumber): string {
return `<Number>`
}
function FromOptional(parser: Runtime.IOptional): string {
return `${FromParser(parser.parser)}?`
}
function FromRef(parser: Runtime.IRef): string {
return `${parser.ref}`
}
function FromConst(parser: Runtime.IConst): string {
return `'${Escape(parser.value)}'`
function FromString(parser: Runtime.IString): string {
return `<String>`
}
function FromUntil(parser: Runtime.IUntil): string {
return `string`
function FromTuple(parser: Runtime.ITuple): string {
return `[${parser.parsers.map((parser) => `${FromParser(parser)}`).join(', ')}]`
}
function FromIdent(parser: Runtime.IIdent): string {
return `<Ident>`
function FromUnion(parser: Runtime.IUnion): string {
return parser.parsers.map((parser) => `${FromParser(parser)}`).join(' | ')
}
function FromString(parser: Runtime.IString): string {
return `<String>`
function FromUntil(parser: Runtime.IUntil): string {
return `string`
}
function FromNumber(parser: Runtime.INumber): string {
return `<Number>`
function FromUntilNonEmpty(parser: Runtime.IUntilNonEmpty): string {
return `string`
}
function FromParser(parser: Runtime.IParser): string {
return (
Runtime.IsContext(parser) ? FromContext(parser) :
Runtime.IsTuple(parser) ? FromTuple(parser) :
Runtime.IsUnion(parser) ? FromUnion(parser) :
Runtime.IsArray(parser) ? FromArray(parser) :
Runtime.IsContext(parser) ? FromContext(parser) :
Runtime.IsConst(parser) ? FromConst(parser) :
Runtime.IsIdent(parser) ? FromIdent(parser) :
Runtime.IsNumber(parser) ? FromNumber(parser) :
Runtime.IsOptional(parser) ? FromOptional(parser) :
Runtime.IsRef(parser) ? FromRef(parser) :
Runtime.IsString(parser) ? FromString(parser) :
Runtime.IsConst(parser) ? FromConst(parser) :
Runtime.IsTuple(parser) ? FromTuple(parser) :
Runtime.IsUnion(parser) ? FromUnion(parser) :
Runtime.IsUntil(parser) ? FromUntil(parser) :
Runtime.IsRef(parser) ? FromRef(parser) :
Runtime.IsIdent(parser) ? FromIdent(parser) :
Runtime.IsNumber(parser) ? FromNumber(parser) :
Runtime.IsUntilNonEmpty(parser) ? FromUntilNonEmpty(parser) :
Unreachable(parser)
)
}
Expand Down
48 changes: 33 additions & 15 deletions src/compile/common/infer.ts
Original file line number Diff line number Diff line change
Expand Up @@ -32,40 +32,58 @@ THE SOFTWARE.
import { Runtime } from '../../runtime/index.ts'
import { Unreachable } from './unreachable.ts'

function InferUnion(parsers: Runtime.IParser[]): string {
return [...new Set(parsers.map((parser) => Infer(parser)))].join(' | ')
}
function InferTuple(parsers: Runtime.IParser[]): string {
return `[${parsers.map(() => 'unknown').join(', ')}]`
}
function InferArray(parser: Runtime.IParser): string {
return `(${Infer(parser)})[]`
}
function InferContext(left: Runtime.IParser, right: Runtime.IParser) {
return Infer(right)
}
function InferConst(parser: Runtime.IConst) {
return `'${parser.value}'`
}
function InferOptional(parser: Runtime.IParser) {
return `([${Infer(parser)}] | [])`
}
function InferConst(parser: Runtime.IConst) {
return `'${parser.value}'`


function InferUnion(parsers: Runtime.IParser[]): string {
return [...new Set(parsers.map((parser) => Infer(parser)))].join(' | ')
}
function InferString(parser: Runtime.IString) {
return `string`
}
function InferRef(parser: Runtime.IRef) {
return `unknown`
}
function InferIdent(parser: Runtime.IIdent) {
return `string`
}
function InferNumber(parser: Runtime.INumber) {
return `string`
}
function InferTuple(parsers: Runtime.IParser[]): string {
return `[${parsers.map(() => 'unknown').join(', ')}]`
}
function InferUntil(parser: Runtime.IUntil) {
return `string`
}
function InferUntilNonEmpty(parser: Runtime.IUntilNonEmpty) {
return `string`
}
export function Infer(parser: Runtime.IParser): string {
return (
Runtime.IsArray(parser) ? InferArray(parser.parser) :
Runtime.IsContext(parser) ? InferContext(parser.right, parser.right) :
Runtime.IsConst(parser) ? InferConst(parser) :
Runtime.IsIdent(parser) ? InferIdent(parser) :
Runtime.IsNumber(parser) ? InferNumber(parser) :
Runtime.IsOptional(parser) ? InferOptional(parser.parser) :
Runtime.IsRef(parser) ? InferRef(parser) :
Runtime.IsString(parser) ? InferString(parser) :
Runtime.IsTuple(parser) ? InferTuple(parser.parsers) :
Runtime.IsUnion(parser) ? InferUnion(parser.parsers) :
Runtime.IsArray(parser) ? InferArray(parser.parser) :
Runtime.IsOptional(parser) ? InferOptional(parser.parser) :
Runtime.IsRef(parser) ? `unknown` :
Runtime.IsConst(parser) ? InferConst(parser) :
Runtime.IsUntil(parser) ? InferUntil(parser) :
Runtime.IsString(parser) ? `string` :
Runtime.IsIdent(parser) ? `string` :
Runtime.IsNumber(parser) ? `string` :
Runtime.IsUntilNonEmpty(parser) ? InferUntilNonEmpty(parser) :
Unreachable(parser)
)
}
84 changes: 46 additions & 38 deletions src/compile/func/func.ts
Original file line number Diff line number Diff line change
Expand Up @@ -44,20 +44,6 @@ function FromContext(options: Options, name: string, left: Runtime.IParser, righ
return `If(${FromParser(options, name, left)}, ([_0, input]) => ${FromParser(options, name, right).replace('context', `_0 as ${options.contextType}`)}, () => [])`
}
// ------------------------------------------------------------------
// Tuple
// ------------------------------------------------------------------
function FromTuple(options: Options, name: string, parsers: Runtime.IParser[]): string {
const parameters = `[${parsers.map((_, index) => `_${index}`).join(', ')}]`
const initial = `[${parameters}, input]`
return parsers.reduceRight((result, right, index) => `If(${FromParser(options, name, right)}, ([_${index}, input]) => ${result})`, initial)
}
// ------------------------------------------------------------------
// Union
// ------------------------------------------------------------------
function FromUnion(options: Options, name: string, parsers: Runtime.IParser[]): string {
return parsers.length === 0 ? '[]' : parsers.reduceRight((result, right) => `If(${FromParser(options, name, right)}, ([_0, input]) => [_0, input], () => ${result})`, '[]')
}
// ------------------------------------------------------------------
// Array
// ------------------------------------------------------------------
function FromArrayReducer(options: Options, name: string, parser: Runtime.IParser): string {
Expand All @@ -71,25 +57,12 @@ function FromArray(options: Options, name: string, parser: Runtime.IParser): str
return `${reducer_name}(input, context)`
}
// ------------------------------------------------------------------
// Optional
// ------------------------------------------------------------------
function FromOptional(options: Options, name: string, parser: Runtime.IOptional): string {
return `If(${FromParser(options, name, parser.parser)}, ([_0, input]) => [[_0], input], () => [[], input])`
}
// ------------------------------------------------------------------
// Const
// ------------------------------------------------------------------
function FromConst(options: Options, name: string, value: string): string {
return `Runtime.Token.Const('${Escape(value)}', input)`
}
// ------------------------------------------------------------------
// Const
// ------------------------------------------------------------------
function FromUntil(options: Options, name: string, values: string[]): string {
const escaped = values.map(value => `'${Escape(value)}'`)
return `Runtime.Token.Until([${escaped.join(', ')}], input)`
}
// ------------------------------------------------------------------
// Ident
// ------------------------------------------------------------------
function FromIdent(options: Options, name: string): string {
Expand All @@ -102,34 +75,69 @@ function FromNumber(options: Options, name: string): string {
return `Runtime.Token.Number(input)`
}
// ------------------------------------------------------------------
// Optional
// ------------------------------------------------------------------
function FromOptional(options: Options, name: string, parser: Runtime.IOptional): string {
return `If(${FromParser(options, name, parser.parser)}, ([_0, input]) => [[_0], input], () => [[], input])`
}
// ------------------------------------------------------------------
// Ref
// ------------------------------------------------------------------
function FromRef(options: Options, name: string, ref: string): string {
return `${ref}(input, context)`
}
// ------------------------------------------------------------------
// String
// ------------------------------------------------------------------
function FromString(options: Options, name: string, string_options: string[]): string {
const _options = string_options.map((option) => `'${Escape(option)}'`).join(', ')
return `Runtime.Token.String([${_options}], input)`
}
// ------------------------------------------------------------------
// Ref
// Tuple
// ------------------------------------------------------------------
function FromRef(options: Options, name: string, ref: string): string {
return `${ref}(input, context)`
function FromTuple(options: Options, name: string, parsers: Runtime.IParser[]): string {
const parameters = `[${parsers.map((_, index) => `_${index}`).join(', ')}]`
const initial = `[${parameters}, input]`
return parsers.reduceRight((result, right, index) => `If(${FromParser(options, name, right)}, ([_${index}, input]) => ${result})`, initial)
}
// ------------------------------------------------------------------
// Ref
// Union
// ------------------------------------------------------------------
function FromUnion(options: Options, name: string, parsers: Runtime.IParser[]): string {
return parsers.length === 0 ? '[]' : parsers.reduceRight((result, right) => `If(${FromParser(options, name, right)}, ([_0, input]) => [_0, input], () => ${result})`, '[]')
}
// ------------------------------------------------------------------
// Until
// ------------------------------------------------------------------
function FromUntil(options: Options, name: string, values: string[]): string {
const escaped = values.map(value => `'${Escape(value)}'`)
return `Runtime.Token.Until([${escaped.join(', ')}], input)`
}
// ------------------------------------------------------------------
// UntilNonEmpty
// ------------------------------------------------------------------
function FromUntilNonEmpty(options: Options, name: string, values: string[]): string {
const escaped = values.map(value => `'${Escape(value)}'`)
return `Runtime.Token.UntilNonEmpty([${escaped.join(', ')}], input)`
}
// ------------------------------------------------------------------
// Parser
// ------------------------------------------------------------------
function FromParser(options: Options, name: string, parser: Runtime.IParser): string {
return (
Runtime.IsContext(parser) ? FromContext(options, name, parser.left, parser.right) :
Runtime.IsTuple(parser) ? FromTuple(options, name, parser.parsers) :
Runtime.IsUnion(parser) ? FromUnion(options, name, parser.parsers) :
Runtime.IsArray(parser) ? FromArray(options, name, parser.parser) :
Runtime.IsOptional(parser) ? FromOptional(options, name, parser) :
Runtime.IsString(parser) ? FromString(options, name, parser.options) :
Runtime.IsContext(parser) ? FromContext(options, name, parser.left, parser.right) :
Runtime.IsConst(parser) ? FromConst(options, name, parser.value) :
Runtime.IsUntil(parser) ? FromUntil(options, name, parser.values) :
Runtime.IsRef(parser) ? FromRef(options, name, parser.ref) :
Runtime.IsIdent(parser) ? FromIdent(options, name) :
Runtime.IsNumber(parser) ? FromNumber(options, name) :
Runtime.IsOptional(parser) ? FromOptional(options, name, parser) :
Runtime.IsRef(parser) ? FromRef(options, name, parser.ref) :
Runtime.IsString(parser) ? FromString(options, name, parser.options) :
Runtime.IsTuple(parser) ? FromTuple(options, name, parser.parsers) :
Runtime.IsUnion(parser) ? FromUnion(options, name, parser.parsers) :
Runtime.IsUntil(parser) ? FromUntil(options, name, parser.values) :
Runtime.IsUntilNonEmpty(parser) ? FromUntilNonEmpty(options, name, parser.values) :
Unreachable(parser)
)
}
Expand Down
Loading