Merge pull request #4 from akosbalasko/feat-support-v2-export-format

manifest.json

@@ -1,7 +1,7 @@
 {
  "id": "onyx-boox-extractor",
  "name": "Onyx Boox Annotation & Highlight Extractor",
- "version": "1.0.3",
+ "version": "1.1.0",
  "minAppVersion": "0.12.0",
  "description": "This plugin extracts annotations and highlights files exported from Onyx Boox tablets, and converts them to reference, literature and permanent notes fitting to the Zettelkasten method.",
  "author": "Akos Balasko",

package.json

@@ -1,6 +1,6 @@
 {
  "name": "onyx-boox-extractor",
- "version": "1.0.3",
+ "version": "1.1.0",
  "description": "Onyx Boox Annotation & Highlight Extractor",
  "main": "main.js",
  "scripts": {

src/extract-onyx-notes.ts

@@ -1,31 +1,98 @@
 import { createReferenceNote } from "./create-reference-note";
 import { createZettelNotes } from "./create-zettel-notes";
-import { OnyxBooxExtractorSettings, ReferenceNoteDetails } from "./models";
+import { OnyxBooxExtractorSettings, ReadingNoteDetails, ReferenceNoteDetails } from "./models";
 import { parseNote } from "./parse-onyx-note";
+import { isVersion2 } from "./utils/is-version-2";
+
+const extractOnyxReadingNotesV1 = async (vault: any, settings: OnyxBooxExtractorSettings, fileContent: string) => {
 
-export const extractOnyxReadingNotes = async (vault: any, settings: OnyxBooxExtractorSettings, fileContent: string) => {
  const NOTE_SEPARATOR = '-------------------';
- let readingNotesArray = fileContent.split(NOTE_SEPARATOR);
+ let readingNotesStringArray = fileContent.split(NOTE_SEPARATOR);
  // parse reading note
  // first contains the ref info
- const firstNote = readingNotesArray.shift();
+ const firstNote = readingNotesStringArray.shift();
  let firstNoteLines = firstNote.split('\n')
 
  // readingNotesArray 
  const title = firstNoteLines.shift().split('|')[1].replace(/<<|>>/g,'');
  const authors = firstNoteLines.shift();
  firstNoteLines.reverse().push('\n');
  firstNoteLines = firstNoteLines.reverse();
- readingNotesArray.push(firstNote);
- readingNotesArray = readingNotesArray.filter(note => note.contains('【Original Text】'));
+ readingNotesStringArray.push(firstNote);
+ readingNotesStringArray = readingNotesStringArray.filter(note => note.contains('【Original Text】'));
  const referenceInfo: ReferenceNoteDetails = {
  title,
  authors,
  };
+ const readingNotesArray = readingNotesStringArray.map(note => {return {raw: note}});
  const referenceNoteId = await createReferenceNote(vault, settings, referenceInfo);
  for (const readingNote of readingNotesArray){
  const noteDetails = parseNote(readingNote);
  await createZettelNotes(vault, settings, referenceNoteId, referenceInfo, noteDetails);
 
  }
 }
+
+const extractOnyxReadingNotesV2 = async (vault: any, settings: OnyxBooxExtractorSettings, fileContent: string) => {
+
+ const NOTE_SEPARATOR = '-------------------';
+ const mainMetadata = fileContent.split('\n')[0];
+ let readingNotesArray = fileContent.split('\n')
+ readingNotesArray.shift();
+ readingNotesArray = readingNotesArray.join('\n').split(NOTE_SEPARATOR);
+ // parse reading note
+ // first contains the ref info
+ /*const firstNote = readingNotesArray.shift();
+ let firstNoteLines = firstNote.split('\n')
+*/
+ // readingNotesArray 
+ const titleAndAuthor = mainMetadata.split('|')[1];
+ const title = titleAndAuthor.split('>>')[0].replace(/<|>/g, '');
+ const authors = titleAndAuthor.split('>>')?.[1];
+ /*firstNoteLines = firstNoteLines.reverse()
+ firstNoteLines.push('\n');
+ firstNoteLines = firstNoteLines.reverse();
+ readingNotesArray = readingNotesArray.reverse()
+ readingNotesArray.push(firstNote);
+ readingNotesArray = readingNotesArray.reverse();*/
+ //readingNotesArray = readingNotesArray.filter(note => note.contains('【Original Text】'));
+ const referenceInfo: ReferenceNoteDetails = {
+ title,
+ authors,
+ };
+ // parse chapters
+ const readingNotesArrayObj = parseChapters(readingNotesArray);
+ const referenceNoteId = await createReferenceNote(vault, settings, referenceInfo);
+ for (const readingNote of readingNotesArrayObj){
+ const noteDetails = parseNote(readingNote);
+ await createZettelNotes(vault, settings, referenceNoteId, referenceInfo, noteDetails);
+
+ }
+}
+
+const parseChapters = (readingNotesArray: Array<string>): Array<ReadingNoteDetails> => {
+ let currentChapter;
+ const readingNotes = [];
+ for (const note of readingNotesArray){
+ const noteLines = note.split('\n').filter(line=> line !== '');
+ // trying to parse the creation date 
+ const fullFirstLine = noteLines[0];
+ const creationTimeCandidate = fullFirstLine?.split('|')[0].trim();
+ const creationTimeCandidateDate = new Date(creationTimeCandidate);
+ if (creationTimeCandidateDate.toString() === 'Invalid Date'){
+ currentChapter = fullFirstLine
+ noteLines.splice(0,1);
+ }
+ readingNotes.push({
+ section: currentChapter,
+ raw: noteLines.join('\n')
+ })
+ }
+ return readingNotes;
+}
+
+export const extractOnyxReadingNotes = async (vault: any, settings: OnyxBooxExtractorSettings, fileContent: string) => {
+ if (isVersion2) await extractOnyxReadingNotesV2(vault, settings, fileContent)
+ else await extractOnyxReadingNotesV1(vault, settings, fileContent)
+
+}

src/models/reading-note-details.ts

@@ -1,7 +1,8 @@
 export interface ReadingNoteDetails {
- section: string;
- creationTime: Date;
- page: number;
- originalText: string;
- annotation: string;
+ section?: string;
+ creationTime?: Date;
+ page?: number;
+ originalText?: string;
+ annotation?: string;
+ raw?: string
 }

src/parse-onyx-note.ts

@@ -1,7 +1,16 @@
 import { ReadingNoteDetails } from "./models";
 import { getStringBetween } from "./utils";
+import { isVersion2 } from "./utils/is-version-2";
 
-export const parseNote = (readingNote: string): ReadingNoteDetails => {
+export const parseNote = (readingNote: ReadingNoteDetails): ReadingNoteDetails => {
+ return (readingNote.raw && isVersion2(readingNote.raw))
+ ? parseNoteV2(readingNote)
+ : parseNoteV1(readingNote)
+
+}
+
+const parseNoteV1 = (readingNoteObj: ReadingNoteDetails): ReadingNoteDetails => {
+ const readingNote = readingNoteObj?.raw;
  const readingNoteLines = readingNote.split('\n');
 
  return {
@@ -12,3 +21,20 @@ export const parseNote = (readingNote: string): ReadingNoteDetails => {
  page: Number(getStringBetween(readingNote,'【Page Number】', '\n').trim()),
  };
 }
+
+
+const parseNoteV2 = (readingNoteObj: ReadingNoteDetails): ReadingNoteDetails => {
+ const readingNote = readingNoteObj?.raw;
+
+ const readingNoteLines = readingNote.split('\n');
+ const firstNoteLine = readingNoteLines[0]
+ readingNoteLines.shift() // remove metadata
+
+ return {
+ section: readingNoteObj.section,
+ creationTime: new Date(firstNoteLine.split('|')[0].trim()),
+ originalText: readingNoteLines.join('\n').split('【Note】')[0],
+ annotation: (readingNote.split('【Note】').length > 0) ? readingNote.split('【Note】')[1]: undefined ,
+ page: Number(firstNoteLine.split('Page No.:')[1].trim()),
+ };
+}

src/utils/create-permanent-note-content.ts

@@ -1,7 +1,7 @@
 import { ReadingNoteDetails, ReferenceNoteDetails } from "src/models";
 
 export const createPermanentNoteContent = (noteDetails: ReadingNoteDetails,literatureFileName: string, referenceNoteId: string, referenceInfo: ReferenceNoteDetails): string => {
- return (noteDetails.annotation?.replace(/\n/g,'').trim() === '')
+ return (!noteDetails.annotation || noteDetails.annotation.replace(/\n/g,'').trim() === '')
  ? undefined
  : `---
 

src/utils/get-strings-between.ts

@@ -3,7 +3,7 @@ export const getStringBetween = (text: string, after: string, before: string): s
  const textArray =text.split(after);
 
  return (textArray.length > 0)
- ? textArray[1].split(before)[0]
+ ? textArray[0].split(before)[0]
  : ''
 
 }

src/utils/is-version-2.ts

@@ -0,0 +1,4 @@
+export const isVersion2 = (fileContent: string): boolean => {
+ return !fileContent.contains('【Original Text】')
+
+}

versions.json

@@ -2,5 +2,7 @@
  "1.0.0": "0.9.7",
  "1.0.1": "0.12.0",
  "1.0.2": "0.12.0",
- "1.0.3": "0.12.0"
+ "1.0.3": "0.12.0",
+ "1.1.0": "0.12.0"
+
 }