chore: more restructuring

This commit is contained in:
Evan You 2019-09-16 15:27:40 -04:00
parent 16fa44bd57
commit ca387afeea
3 changed files with 193 additions and 193 deletions

View File

@ -77,11 +77,6 @@ function createParserContext(
}
}
function getCursor(context: ParserContext): Position {
const { column, line, offset } = context
return { column, line, offset }
}
function parseChildren(
context: ParserContext,
mode: TextModes,
@ -172,134 +167,6 @@ function parseChildren(
return nodes
}
function getSelection(
context: ParserContext,
start: Position,
end?: Position
): SourceLocation {
end = end || getCursor(context)
return {
start,
end,
source: context.originalSource.slice(start.offset, end.offset)
}
}
function last<T>(xs: T[]): T | undefined {
return xs[xs.length - 1]
}
function startsWith(source: string, searchString: string): boolean {
return source.startsWith(searchString)
}
function advanceBy(context: ParserContext, numberOfCharacters: number): void {
__DEV__ && assert(numberOfCharacters <= context.source.length)
const { column, source } = context
const str = source.slice(0, numberOfCharacters)
const lines = str.split(/\r?\n/)
context.source = source.slice(numberOfCharacters)
context.offset += numberOfCharacters
context.line += lines.length - 1
context.column =
lines.length === 1
? column + numberOfCharacters
: Math.max(1, lines.pop()!.length)
}
function advanceSpaces(context: ParserContext): void {
const match = /^[\t\r\n\f ]+/.exec(context.source)
if (match) {
advanceBy(context, match[0].length)
}
}
function getNewPosition(
context: ParserContext,
start: Position,
numberOfCharacters: number
): Position {
const { originalSource } = context
const str = originalSource.slice(start.offset, numberOfCharacters)
const lines = str.split(/\r?\n/)
const newPosition = {
column: start.column,
line: start.line,
offset: start.offset
}
newPosition.offset += numberOfCharacters
newPosition.line += lines.length - 1
newPosition.column =
lines.length === 1
? start.column + numberOfCharacters
: Math.max(1, lines.pop()!.length)
return newPosition
}
function emitError(
context: ParserContext,
type: ParserErrorTypes,
offset?: number
): void {
const loc = getCursor(context)
if (offset) {
loc.offset += offset
loc.column += offset
}
context.onError(type, loc)
}
function isEnd(
context: ParserContext,
mode: TextModes,
ancestors: ElementNode[]
): boolean {
const s = context.source
switch (mode) {
case TextModes.DATA:
if (startsWith(s, '</')) {
//TODO: probably bad performance
for (let i = ancestors.length - 1; i >= 0; --i) {
if (startsWithEndTagOpen(s, ancestors[i].tag)) {
return true
}
}
}
break
case TextModes.RCDATA:
case TextModes.RAWTEXT: {
const parent = last(ancestors)
if (parent && startsWithEndTagOpen(s, parent.tag)) {
return true
}
break
}
case TextModes.CDATA:
if (startsWith(s, ']]>')) {
return true
}
break
}
return !s
}
function startsWithEndTagOpen(source: string, tag: string): boolean {
return (
startsWith(source, '</') &&
source.substr(2, tag.length).toLowerCase() === tag.toLowerCase() &&
/[\t\n\f />]/.test(source[2 + tag.length] || '>')
)
}
function pushNode(
context: ParserContext,
nodes: RootNode['children'],
@ -887,6 +754,145 @@ function parseTextData(
return text
}
function getCursor(context: ParserContext): Position {
const { column, line, offset } = context
return { column, line, offset }
}
function getSelection(
context: ParserContext,
start: Position,
end?: Position
): SourceLocation {
end = end || getCursor(context)
return {
start,
end,
source: context.originalSource.slice(start.offset, end.offset)
}
}
function last<T>(xs: T[]): T | undefined {
return xs[xs.length - 1]
}
function startsWith(source: string, searchString: string): boolean {
return source.startsWith(searchString)
}
function advanceBy(context: ParserContext, numberOfCharacters: number): void {
__DEV__ && assert(numberOfCharacters <= context.source.length)
const { column, source } = context
const str = source.slice(0, numberOfCharacters)
const lines = str.split(/\r?\n/)
context.source = source.slice(numberOfCharacters)
context.offset += numberOfCharacters
context.line += lines.length - 1
context.column =
lines.length === 1
? column + numberOfCharacters
: Math.max(1, lines.pop()!.length)
}
function advanceSpaces(context: ParserContext): void {
const match = /^[\t\r\n\f ]+/.exec(context.source)
if (match) {
advanceBy(context, match[0].length)
}
}
function getNewPosition(
context: ParserContext,
start: Position,
numberOfCharacters: number
): Position {
const { originalSource } = context
const str = originalSource.slice(start.offset, numberOfCharacters)
const lines = str.split(/\r?\n/)
const newPosition = {
column: start.column,
line: start.line,
offset: start.offset
}
newPosition.offset += numberOfCharacters
newPosition.line += lines.length - 1
newPosition.column =
lines.length === 1
? start.column + numberOfCharacters
: Math.max(1, lines.pop()!.length)
return newPosition
}
function emitError(
context: ParserContext,
type: ParserErrorTypes,
offset?: number
): void {
const loc = getCursor(context)
if (offset) {
loc.offset += offset
loc.column += offset
}
context.onError(type, loc)
}
function isEnd(
context: ParserContext,
mode: TextModes,
ancestors: ElementNode[]
): boolean {
const s = context.source
switch (mode) {
case TextModes.DATA:
if (startsWith(s, '</')) {
//TODO: probably bad performance
for (let i = ancestors.length - 1; i >= 0; --i) {
if (startsWithEndTagOpen(s, ancestors[i].tag)) {
return true
}
}
}
break
case TextModes.RCDATA:
case TextModes.RAWTEXT: {
const parent = last(ancestors)
if (parent && startsWithEndTagOpen(s, parent.tag)) {
return true
}
break
}
case TextModes.CDATA:
if (startsWith(s, ']]>')) {
return true
}
break
}
return !s
}
function startsWithEndTagOpen(source: string, tag: string): boolean {
return (
startsWith(source, '</') &&
source.substr(2, tag.length).toLowerCase() === tag.toLowerCase() &&
/[\t\n\f />]/.test(source[2 + tag.length] || '>')
)
}
function assert(condition: boolean, msg?: string) {
if (!condition) {
throw new Error(msg || `unexpected parser condition`)
}
}
// https://html.spec.whatwg.org/multipage/parsing.html#numeric-character-reference-end-state
const CCR_REPLACEMENTS: { [key: number]: number | undefined } = {
0x80: 0x20ac,
@ -917,9 +923,3 @@ const CCR_REPLACEMENTS: { [key: number]: number | undefined } = {
0x9e: 0x017e,
0x9f: 0x0178
}
function assert(condition: boolean, msg?: string) {
if (!condition) {
throw new Error(msg || `unexpected parser condition`)
}
}

View File

@ -35,3 +35,55 @@ export const enum ParserErrorTypes {
X_MISSING_INTERPOLATION_END,
X_MISSING_DYNAMIC_DIRECTIVE_ARGUMENT_END
}
export const errorMessages: { [code: number]: string } = {
[ParserErrorTypes.ABRUPT_CLOSING_OF_EMPTY_COMMENT]: 'Illegal comment.',
[ParserErrorTypes.ABSENCE_OF_DIGITS_IN_NUMERIC_CHARACTER_REFERENCE]:
'Illegal numeric character reference: invalid character.',
[ParserErrorTypes.CDATA_IN_HTML_CONTENT]:
'CDATA section is allowed only in XML context.',
[ParserErrorTypes.CHARACTER_REFERENCE_OUTSIDE_UNICODE_RANGE]:
'Illegal numeric character reference: too big.',
[ParserErrorTypes.CONTROL_CHARACTER_REFERENCE]:
'Illegal numeric character reference: control character.',
[ParserErrorTypes.DUPLICATE_ATTRIBUTE]: 'Duplicate attribute.',
[ParserErrorTypes.END_TAG_WITH_ATTRIBUTES]: 'End tag cannot have attributes.',
[ParserErrorTypes.END_TAG_WITH_TRAILING_SOLIDUS]: "Illegal '/' in tags.",
[ParserErrorTypes.EOF_BEFORE_TAG_NAME]: 'Unexpected EOF in tag.',
[ParserErrorTypes.EOF_IN_CDATA]: 'Unexpected EOF in CDATA section.',
[ParserErrorTypes.EOF_IN_COMMENT]: 'Unexpected EOF in comment.',
[ParserErrorTypes.EOF_IN_SCRIPT_HTML_COMMENT_LIKE_TEXT]:
'Unexpected EOF in script.',
[ParserErrorTypes.EOF_IN_TAG]: 'Unexpected EOF in tag.',
[ParserErrorTypes.INCORRECTLY_CLOSED_COMMENT]: 'Incorrectly closed comment.',
[ParserErrorTypes.INCORRECTLY_OPENED_COMMENT]: 'Incorrectly opened comment.',
[ParserErrorTypes.INVALID_FIRST_CHARACTER_OF_TAG_NAME]:
"Illegal tag name. Use '&lt;' to print '<'.",
[ParserErrorTypes.MISSING_ATTRIBUTE_VALUE]: 'Attribute value was expected.',
[ParserErrorTypes.MISSING_END_TAG_NAME]: 'End tag name was expected.',
[ParserErrorTypes.MISSING_SEMICOLON_AFTER_CHARACTER_REFERENCE]:
'Semicolon was expected.',
[ParserErrorTypes.MISSING_WHITESPACE_BETWEEN_ATTRIBUTES]:
'Whitespace was expected.',
[ParserErrorTypes.NESTED_COMMENT]: "Unexpected '<!--' in comment.",
[ParserErrorTypes.NONCHARACTER_CHARACTER_REFERENCE]:
'Illegal numeric character reference: non character.',
[ParserErrorTypes.NULL_CHARACTER_REFERENCE]:
'Illegal numeric character reference: null character.',
[ParserErrorTypes.SURROGATE_CHARACTER_REFERENCE]:
'Illegal numeric character reference: non-pair surrogate.',
[ParserErrorTypes.UNEXPECTED_CHARACTER_IN_ATTRIBUTE_NAME]:
'Attribute name cannot contain U+0022 ("), U+0027 (\'), and U+003C (<).',
[ParserErrorTypes.UNEXPECTED_CHARACTER_IN_UNQUOTED_ATTRIBUTE_VALUE]:
'Unquoted attribute value cannot contain U+0022 ("), U+0027 (\'), U+003C (<), U+003D (=), and U+0060 (`).',
[ParserErrorTypes.UNEXPECTED_EQUALS_SIGN_BEFORE_ATTRIBUTE_NAME]:
"Attribute name cannot start with '='.",
[ParserErrorTypes.UNEXPECTED_QUESTION_MARK_INSTEAD_OF_TAG_NAME]:
"'<?' is allowed only in XML context.",
[ParserErrorTypes.UNEXPECTED_SOLIDUS_IN_TAG]: "Illegal '/' in tags.",
[ParserErrorTypes.UNKNOWN_NAMED_CHARACTER_REFERENCE]: 'Unknown entity name.',
[ParserErrorTypes.X_INVALID_END_TAG]: 'Invalid end tag.',
[ParserErrorTypes.X_MISSING_END_TAG]: 'End tag was not found.',
[ParserErrorTypes.X_MISSING_INTERPOLATION_END]:
'Interpolation end sign was not found.'
}

View File

@ -1,6 +1,6 @@
import { TextModes, ParserOptions } from './parser'
import { ElementNode, Namespaces, Position, Node } from './ast'
import { ParserErrorTypes } from './parserErrorTypes'
import { ParserErrorTypes, errorMessages } from './parserErrorTypes'
export const parserOptionsMinimal: ParserOptions = {
delimiters: [`{{`, `}}`],
@ -47,7 +47,7 @@ export const parserOptionsMinimal: ParserOptions = {
onError(code: ParserErrorTypes, loc: Position): void {
const error: any = new SyntaxError(
`${messages[code]} (${loc.line}:${loc.column})`
`${errorMessages[code]} (${loc.line}:${loc.column})`
)
error.code = code
error.loc = loc
@ -58,55 +58,3 @@ export const parserOptionsMinimal: ParserOptions = {
return node
}
}
const messages: { [code: number]: string } = {
[ParserErrorTypes.ABRUPT_CLOSING_OF_EMPTY_COMMENT]: 'Illegal comment.',
[ParserErrorTypes.ABSENCE_OF_DIGITS_IN_NUMERIC_CHARACTER_REFERENCE]:
'Illegal numeric character reference: invalid character.',
[ParserErrorTypes.CDATA_IN_HTML_CONTENT]:
'CDATA section is allowed only in XML context.',
[ParserErrorTypes.CHARACTER_REFERENCE_OUTSIDE_UNICODE_RANGE]:
'Illegal numeric character reference: too big.',
[ParserErrorTypes.CONTROL_CHARACTER_REFERENCE]:
'Illegal numeric character reference: control character.',
[ParserErrorTypes.DUPLICATE_ATTRIBUTE]: 'Duplicate attribute.',
[ParserErrorTypes.END_TAG_WITH_ATTRIBUTES]: 'End tag cannot have attributes.',
[ParserErrorTypes.END_TAG_WITH_TRAILING_SOLIDUS]: "Illegal '/' in tags.",
[ParserErrorTypes.EOF_BEFORE_TAG_NAME]: 'Unexpected EOF in tag.',
[ParserErrorTypes.EOF_IN_CDATA]: 'Unexpected EOF in CDATA section.',
[ParserErrorTypes.EOF_IN_COMMENT]: 'Unexpected EOF in comment.',
[ParserErrorTypes.EOF_IN_SCRIPT_HTML_COMMENT_LIKE_TEXT]:
'Unexpected EOF in script.',
[ParserErrorTypes.EOF_IN_TAG]: 'Unexpected EOF in tag.',
[ParserErrorTypes.INCORRECTLY_CLOSED_COMMENT]: 'Incorrectly closed comment.',
[ParserErrorTypes.INCORRECTLY_OPENED_COMMENT]: 'Incorrectly opened comment.',
[ParserErrorTypes.INVALID_FIRST_CHARACTER_OF_TAG_NAME]:
"Illegal tag name. Use '&lt;' to print '<'.",
[ParserErrorTypes.MISSING_ATTRIBUTE_VALUE]: 'Attribute value was expected.',
[ParserErrorTypes.MISSING_END_TAG_NAME]: 'End tag name was expected.',
[ParserErrorTypes.MISSING_SEMICOLON_AFTER_CHARACTER_REFERENCE]:
'Semicolon was expected.',
[ParserErrorTypes.MISSING_WHITESPACE_BETWEEN_ATTRIBUTES]:
'Whitespace was expected.',
[ParserErrorTypes.NESTED_COMMENT]: "Unexpected '<!--' in comment.",
[ParserErrorTypes.NONCHARACTER_CHARACTER_REFERENCE]:
'Illegal numeric character reference: non character.',
[ParserErrorTypes.NULL_CHARACTER_REFERENCE]:
'Illegal numeric character reference: null character.',
[ParserErrorTypes.SURROGATE_CHARACTER_REFERENCE]:
'Illegal numeric character reference: non-pair surrogate.',
[ParserErrorTypes.UNEXPECTED_CHARACTER_IN_ATTRIBUTE_NAME]:
'Attribute name cannot contain U+0022 ("), U+0027 (\'), and U+003C (<).',
[ParserErrorTypes.UNEXPECTED_CHARACTER_IN_UNQUOTED_ATTRIBUTE_VALUE]:
'Unquoted attribute value cannot contain U+0022 ("), U+0027 (\'), U+003C (<), U+003D (=), and U+0060 (`).',
[ParserErrorTypes.UNEXPECTED_EQUALS_SIGN_BEFORE_ATTRIBUTE_NAME]:
"Attribute name cannot start with '='.",
[ParserErrorTypes.UNEXPECTED_QUESTION_MARK_INSTEAD_OF_TAG_NAME]:
"'<?' is allowed only in XML context.",
[ParserErrorTypes.UNEXPECTED_SOLIDUS_IN_TAG]: "Illegal '/' in tags.",
[ParserErrorTypes.UNKNOWN_NAMED_CHARACTER_REFERENCE]: 'Unknown entity name.',
[ParserErrorTypes.X_INVALID_END_TAG]: 'Invalid end tag.',
[ParserErrorTypes.X_MISSING_END_TAG]: 'End tag was not found.',
[ParserErrorTypes.X_MISSING_INTERPOLATION_END]:
'Interpolation end sign was not found.'
}