This repository has been archived by the owner on Feb 26, 2022. It is now read-only.
forked from bbc/react-transcript-editor
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Fix issues with straight-through SRT
- Loading branch information
Showing
14 changed files
with
523 additions
and
41 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,194 @@ | ||
| /** | ||
| * The MIT License (MIT) | ||
| * Copyright (c) 2015 Guilherme Santiago | ||
| * | ||
| * Permission is hereby granted, free of charge, to any person obtaining a copy | ||
| * of this software and associated documentation files (the "Software"), to deal | ||
| * in the Software without restriction, including without limitation the rights | ||
| * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell | ||
| * copies of the Software, and to permit persons to whom the Software is | ||
| * furnished to do so, subject to the following conditions: | ||
| * | ||
| * The above copyright notice and this permission notice shall be included in all | ||
| * copies or substantial portions of the Software. | ||
| * | ||
| * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR | ||
| * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, | ||
| * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE | ||
| * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER | ||
| * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, | ||
| * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE | ||
| * SOFTWARE. | ||
| */ | ||
|
|
||
| import stripBom from 'strip-bom' | ||
| import { RE_TIMESTAMP, parseTimestamps } from './parseTimestamps' | ||
| import type {Node} from './types' | ||
|
|
||
| export type Pusher = (node: Node) => void | ||
|
|
||
| export interface ParseState { | ||
| expect: 'header' | 'id' | 'timestamp' | 'text' | ||
| row: number | ||
| hasContentStarted: boolean | ||
| isWebVTT: boolean | ||
| node: Partial<Node> | ||
| buffer: string[] | ||
| } | ||
|
|
||
| export class Parser { | ||
| private push: Pusher | ||
| private state: ParseState | ||
|
|
||
| constructor({ push }: { push: Pusher }) { | ||
| this.push = push | ||
| this.state = { | ||
| expect: 'header', | ||
| row: 0, | ||
| hasContentStarted: false, | ||
| isWebVTT: false, | ||
| node: {}, | ||
| buffer: [] | ||
| } | ||
| } | ||
|
|
||
| private isIndex(line: string): boolean { | ||
| return /^\d+$/.test(line.trim()) | ||
| } | ||
|
|
||
| private isTimestamp(line: string): boolean { | ||
| return RE_TIMESTAMP.test(line) | ||
| } | ||
|
|
||
| private getError(expected: string, index: number, row: string): Error { | ||
| return new Error( | ||
| `expected ${expected} at row ${index + 1}, but received: "${row}"` | ||
| ) | ||
| } | ||
|
|
||
| public parseLine(line: string): void { | ||
| const contents = this.state.row === 0 ? stripBom(line) : line | ||
|
|
||
| if (!this.state.hasContentStarted) { | ||
| if (contents.trim()) { | ||
| this.state.hasContentStarted = true | ||
| } else { | ||
| return | ||
| } | ||
| } | ||
|
|
||
| const parse = { | ||
| header: this.parseHeader, | ||
| id: this.parseId, | ||
| timestamp: this.parseTimestamp, | ||
| text: this.parseText | ||
| }[this.state.expect] | ||
|
|
||
| parse.call(this, contents) | ||
|
|
||
| this.state.row++ | ||
| } | ||
|
|
||
| public flush(): void { | ||
| if (this.state.buffer.length > 0) { | ||
| this.pushNode() | ||
| } | ||
| } | ||
|
|
||
| private parseHeader(line: string) { | ||
| if (!this.state.isWebVTT) { | ||
| this.state.isWebVTT = /^WEBVTT/.test(line) | ||
|
|
||
| if (this.state.isWebVTT) { | ||
| this.state.node.type = 'header' | ||
| } else { | ||
| this.parseId(line) | ||
| return | ||
| } | ||
| } | ||
|
|
||
| this.state.buffer.push(line) | ||
|
|
||
| if (!line) { | ||
| this.state.expect = 'id' | ||
| return | ||
| } | ||
| } | ||
|
|
||
| private parseId(line: string) { | ||
| this.state.expect = 'timestamp' | ||
|
|
||
| if (this.state.node.type === 'header') { | ||
| this.pushNode() | ||
| } | ||
|
|
||
| if (!this.isIndex(line)) { | ||
| this.parseTimestamp(line) | ||
| } | ||
| } | ||
|
|
||
| private parseTimestamp(line: string) { | ||
| if (!this.isTimestamp(line)) { | ||
| throw this.getError('timestamp', this.state.row, line) | ||
| } | ||
|
|
||
| this.state.node = { | ||
| type: 'cue', | ||
| data: { | ||
| ...parseTimestamps(line), | ||
| text: '' | ||
| } | ||
| } | ||
|
|
||
| this.state.expect = 'text' | ||
| } | ||
|
|
||
| private parseText(line: string) { | ||
| if (this.state.buffer.length > 0 && this.isTimestamp(line)) { | ||
| const lastIndex = this.state.buffer.length - 1 | ||
|
|
||
| if (this.isIndex(this.state.buffer[lastIndex])) { | ||
| this.state.buffer.pop() | ||
| } | ||
|
|
||
| this.pushNode() | ||
| this.parseTimestamp(line) | ||
| } else { | ||
| this.state.buffer.push(line) | ||
| } | ||
| } | ||
|
|
||
| private pushNode(): void { | ||
| if (this.state.node.type === 'cue') { | ||
| while (true) { | ||
| const lastItem = this.state.buffer[this.state.buffer.length - 1] | ||
| if (['', '\n'].includes(lastItem)) { | ||
| this.state.buffer.pop() | ||
| } else { | ||
| break | ||
| } | ||
| } | ||
|
|
||
| while (true) { | ||
| const firstItem = this.state.buffer[0] | ||
| if (['', '\n'].includes(firstItem)) { | ||
| this.state.buffer.shift() | ||
| } else { | ||
| break | ||
| } | ||
| } | ||
|
|
||
| this.state.node.data!.text = this.state.buffer.join('\n') | ||
| } | ||
|
|
||
| if (this.state.node.type === 'header') { | ||
| this.state.node.data = this.state.buffer.join('\n').trim() | ||
| } | ||
|
|
||
| this.push(this.state.node as Node) | ||
|
|
||
| this.state.node = {} | ||
| this.state.buffer = [] | ||
| } | ||
| } |
Oops, something went wrong.