org-report-stats/parse_orgmode_to_json.mjs

526 lines
15 KiB
JavaScript
Raw Normal View History

2023-03-04 23:52:46 +01:00
/**
* convertir un fichier .org vers des données structurées en json
* @type {*}
*/
import fs from 'node-fs';
2023-03-05 23:13:16 +01:00
import moment from 'moment';
/**********************
* initialize configs
**********************/
const sourceFileName = 'all_tasks.org'
2023-03-05 23:13:16 +01:00
const sourceFilePath = './sources/' + sourceFileName;
const outputAbsolutePath = '~/Nextcloud/ressources/social sorting/output/';
const outputFileNameJson = 'export_' + sourceFileName + '_parsed.json';
2023-03-04 23:52:46 +01:00
let headers = []
2023-03-04 23:57:03 +01:00
let tasksObjectsForJsonExport = []
2023-03-04 23:52:46 +01:00
let headersByKind = {}
2023-03-05 23:13:16 +01:00
let writeJsonAfterParse = false;
writeJsonAfterParse = true;
2023-04-18 12:23:52 +02:00
moment.locale('FR')
2023-03-04 23:52:46 +01:00
2023-03-05 23:13:16 +01:00
/**************************************************************
* fetch the source orgmode file to read its contents
*************************************************************/
2023-03-04 23:52:46 +01:00
console.log('---------- parse some org file', sourceFilePath)
2023-03-05 23:13:16 +01:00
if (!sourceFilePath) {
console.error('pas de fichier à ouvrir')
}
2023-03-04 23:52:46 +01:00
fs.stat(sourceFilePath, function (err, stat) {
if (err == null) {
console.log(`File ${sourceFilePath} exists`);
} else if (err.code === 'ENOENT') {
// file does not exist
console.error(`le fichier ${sourceFilePath} est introuvable. Impossible d en extraire des infos.`, err);
} else {
console.log('Some other error: ', err.code);
}
});
2023-03-05 23:13:16 +01:00
/**********************
* search elements
*********************/
let stateKeywordList = ['SOMEDAY', 'NEXT', 'TODO', 'CANCELLED', 'DONE', 'WAITING'];
let dateKeywordList = ['CREATED', 'SCHEDULED', 'DEADLINE', 'CLOSED', 'Refiled'];
2023-03-05 23:13:16 +01:00
let sectionKeywordList = ['PROPERTIES', 'LOGBOOK', 'END'];
let propertiesSection = {} // TODO properties listing
let logBookSection = {} // TODO logbook listing
let statistics = {
tags: {},
words: {},
dates: {
havingDate: 0,
havingNoDate: 0,
oldEst: 0,
mostRecent: 0,
2023-04-18 12:23:52 +02:00
years: {},
weeks: {},
months: {},
days: {}
}
}
2023-03-04 23:52:46 +01:00
2023-03-05 23:13:16 +01:00
let headerKeywordSearch = '[' + stateKeywordList.join('|') + ']'
/**
* task object example
* @type {{level: string, header: string, dates: {CREATED: string, DONE: string, REFILED: string}, state: string, content: string, properties: {}, tags: [], tagsInherited: []}}
*/
2023-03-05 11:05:06 +01:00
let task = {
2023-03-05 23:13:16 +01:00
header: "",
level: "",
corpus: "",
2023-03-05 23:13:16 +01:00
state: "",
tags: [],
2023-03-06 00:15:27 +01:00
children: [], // TODO list children tasks with a reference to the parent when level is superior to previous task
tagsInherited: [], // TODO inherit tags
2023-04-18 21:59:16 +02:00
dates: {
havingDate: 0,
havingNoDate: 0,
oldEst: 0,
mostRecent: 0,
years: {},
weeks: {},
months: {},
days: {},
},
2023-03-05 23:13:16 +01:00
logbook: {},
properties: {},
2023-03-05 11:05:06 +01:00
}
2023-03-05 23:13:16 +01:00
let isHeader = false;
let isProperty = false;
let isLogbook = false;
let isFirst = true;
2023-03-05 11:05:06 +01:00
// init first task object as empty clone
2023-04-18 12:23:52 +02:00
let currentTask = Object.create(task);
/**
* add to tasks to export and refresh current task
*/
function addAndRefreshCurrentTask() {
2023-04-18 13:24:20 +02:00
makeWordsStatistics(currentTask.header.trim())
makeWordsStatistics(currentTask.corpus.trim())
tasksObjectsForJsonExport.push(currentTask)
2023-04-18 12:23:52 +02:00
// réinitialisation de tâche pour remplir de nouveau
currentTask = Object.create(task);
currentTask.dates = {};
2023-04-18 12:23:52 +02:00
currentTask.tags = [];
2023-04-18 13:24:20 +02:00
}
function makeWordsStatistics(sentence) {
2023-03-14 18:04:54 +01:00
let split = sentence.split(' ');
if (split && split.length) {
split.forEach(word => {
if (!statistics.words[word]) {
statistics.words[word] = 0
}
statistics.words[word]++
})
}
}
2023-04-18 13:24:20 +02:00
const dateStats = {
created: 0,
refiled: 0,
closed: 0,
cancelled: 0,
scheduled: 0,
deadline: 0,
2023-04-18 21:59:16 +02:00
tasks_done: []
2023-04-18 13:24:20 +02:00
}
function fillPeriodTime(periodStat, keyword){
if (keyword === 'CLOSED') {
periodStat.closed++;
}
if (keyword === 'CREATED') {
periodStat.created++;
}
if (keyword === 'Refiled') {
periodStat.refiled++;
}
if (keyword === 'CANCELLED') {
periodStat.cancelled++;
}
if (keyword === 'SCHEDULED') {
periodStat.scheduled++;
}
if (keyword === 'DEADLINE') {
periodStat.deadline++;
}
}
/**
* pour chaque période de temps, compter les tâches créées et fermées
* @param keyword
* @param dateFoundElement
*/
2023-04-18 21:59:16 +02:00
function statisticDateFill(keyword, dateFoundElement, header) {
// décompte par années
2023-04-18 12:23:52 +02:00
let convertedDate = new Date(dateFoundElement)
let yearOfDate = convertedDate.getFullYear()
2023-04-18 12:23:52 +02:00
let monthOfDate = yearOfDate + '-' + convertedDate.getMonth()
// add zeros
let convertedWeek = moment(convertedDate).week() < 10 ? '0' + moment(convertedDate).week() : moment(convertedDate).week()
let weekOfDate = yearOfDate + '-' + convertedWeek
2023-04-18 12:23:52 +02:00
let convertedMonth = convertedDate.getMonth() < 10 ? '0' + convertedDate.getMonth() : convertedDate.getMonth()
let convertedDay = convertedDate.getDay() < 10 ? '0' + convertedDate.getDay() : convertedDate.getDay()
let dayOfDate = convertedDate.getFullYear() + '-' + convertedMonth + '-' + convertedDay
if (!statistics.dates.years[yearOfDate]) {
2023-04-18 13:24:20 +02:00
statistics.dates.years[yearOfDate] = Object.create(dateStats)
2023-04-18 12:23:52 +02:00
}
2023-04-18 13:24:20 +02:00
fillPeriodTime(statistics.dates.years[yearOfDate], keyword)
2023-04-18 12:23:52 +02:00
// par année-semaine
if (!statistics.dates.weeks[weekOfDate]) {
2023-04-18 13:24:20 +02:00
statistics.dates.weeks[weekOfDate] = Object.create(dateStats)
}
2023-04-18 13:24:20 +02:00
fillPeriodTime(statistics.dates.weeks[weekOfDate], keyword)
2023-04-18 21:59:16 +02:00
statistics.dates.weeks[weekOfDate].tasks_done.push(header)
// décompte par mois
2023-04-18 12:23:52 +02:00
if (!statistics.dates.months[monthOfDate]) {
2023-04-18 13:24:20 +02:00
statistics.dates.months[monthOfDate] = Object.create(dateStats)
}
2023-04-18 13:24:20 +02:00
fillPeriodTime(statistics.dates.months[monthOfDate], keyword)
// décompte par jours
2023-04-18 12:23:52 +02:00
if (!statistics.dates.days[dayOfDate]) {
2023-04-18 13:24:20 +02:00
statistics.dates.days[dayOfDate] = Object.create(dateStats)
}
2023-04-18 13:24:20 +02:00
fillPeriodTime(statistics.dates.days[dayOfDate], keyword)
2023-04-18 21:59:16 +02:00
statistics.dates.days[dayOfDate].tasks_done.push(header)
}
2023-04-18 12:23:52 +02:00
function findOldestDate(currentDate) {
// trouver la plus ancienne date
if (!statistics.dates.oldEst) {
statistics.dates.oldEst = currentDate;
} else {
var beginningTime = moment(statistics.dates.oldEst);
var endTime = moment(currentDate);
if (!beginningTime.isBefore(endTime)) {
statistics.dates.oldEst = currentDate;
}
}
}
2023-03-05 23:13:16 +01:00
/**********************
* loop to parse all
*********************/
2023-03-04 23:52:46 +01:00
fs.readFile(sourceFilePath, 'utf8', function (err, data) {
2023-03-04 23:52:46 +01:00
if (err) {
return console.log(err);
}
console.log(" parsing...")
// parcourir chaque ligne du fichier org
let everyline = data.split('\n');
// trouver les entêtes toutes les lignes qui commencent par * et espace.
everyline.forEach((line) => {
2023-03-05 23:13:16 +01:00
// gérer la création d'objets définissant les tâches et leurs propriétés
2023-03-04 23:52:46 +01:00
if (line.match(/^\*+? /)) {
2023-03-05 11:05:06 +01:00
// add last task to export list
2023-03-05 23:13:16 +01:00
if (!isFirst) {
addAndRefreshCurrentTask();
2023-03-05 23:13:16 +01:00
} else {
isFirst = false;
}
isHeader = true;
// compter les étoiles pour trouver le niveau du header
2023-03-14 18:04:54 +01:00
if (line.match(/\*/g)) {
let match = line.match(/\*/g);
currentTask.level = match.length
}
2023-03-05 23:13:16 +01:00
2023-03-05 11:05:06 +01:00
// create a new task
2023-03-05 23:13:16 +01:00
headers.push(cleanHeader(line))
currentTask.header = cleanHeader(line);
2023-03-05 23:13:16 +01:00
stateKeywordList.forEach(keyword => {
let keywordIsFound = lineHasKeyword(line, keyword)
2023-03-05 11:05:06 +01:00
2023-03-05 23:13:16 +01:00
if (keywordIsFound) {
2023-03-05 11:05:06 +01:00
currentTask.state = keyword
}
2023-03-05 23:13:16 +01:00
})
// trouver les tags
2023-04-18 12:23:52 +02:00
let tagsList = line.match(/\:([\w\_]*)\:/g)
if (tagsList) {
tagsList = tagsList[0];
let tagList = tagsList.split(':');
2023-03-14 18:04:54 +01:00
if (tagList.length) {
2023-03-14 18:04:54 +01:00
tagList.forEach(tag => {
if (tag.length > 1) {
2023-03-14 18:04:54 +01:00
if (!statistics.tags[tag]) {
statistics.tags[tag] = 0
}
statistics.tags[tag]++
currentTask.tags.push(tag)
}
})
}
2023-03-05 23:13:16 +01:00
}
// ------------- fin des recherches dans la ligne de Header -------------
2023-03-05 23:13:16 +01:00
} else {
isHeader = false;
}
// examen des lignes de corps de tâche, ou de corps de section suite au header.
// classer les dates de création, cloture, et de logbook
let dateFound = searchDate(line)
if (dateFound) {
/**
* we have found a date in the current line
*/
statistics.dates.havingDate += 1;
dateKeywordList.forEach(keyword => {
if (lineHasSubstring(line, keyword)) {
if (!currentTask.dates[keyword]) {
currentTask.dates[keyword] = '';
}
2023-04-18 12:23:52 +02:00
let convertedDate = dateFound[0].substring(0, 10);
2023-04-18 12:23:52 +02:00
if (dateFound[0].length == 15) {
// sans heure: "2022-12-21 mer."
convertedDate = moment(dateFound[0], 'YYYY-MM-DD ddd')
} else if (dateFound[0].length == 21) {
// avec heure: "2022-11-01 mar. 00:44"
convertedDate = moment(dateFound[0], 'YYYY-MM-DD ddd HH:mm')
}
let formattedDate = moment(convertedDate).format()
2023-04-18 21:59:16 +02:00
console.log('currentTask.header', currentTask.header)
statisticDateFill(keyword, convertedDate, currentTask.header)
2023-04-18 12:23:52 +02:00
findOldestDate(convertedDate)
currentTask.dates[keyword] = formattedDate;
} else {
// console.log('keyword', keyword)
2023-03-05 11:05:06 +01:00
}
})
} else {
statistics.dates.havingNoDate += 1;
2023-04-18 12:23:52 +02:00
if (
line.indexOf(dateKeywordList) !== -1 &&
line.indexOf(stateKeywordList) !== -1 &&
line.indexOf(sectionKeywordList) !== -1
) {
// ajouter le corps complet de la section après le header
if (line.length && !isHeader) {
let cleanedLine = line.replace(/\s\s/g, ' ');
cleanedLine = line.replace(/ {2,}/g, ' ')
2023-03-05 23:13:16 +01:00
2023-04-18 13:24:20 +02:00
cleanedLine = cleanedLine.trim()
currentTask.corpus += `${cleanedLine}
`
}
}
}
2023-03-04 23:52:46 +01:00
})
2023-04-18 13:24:20 +02:00
2023-03-05 23:13:16 +01:00
// ajouter la dernière tâche parsée
addAndRefreshCurrentTask();
2023-03-05 23:13:16 +01:00
2023-03-04 23:52:46 +01:00
console.log(" parsing fini")
// ranger par valeur décroissante les tags
let sorted_stats = [];
2023-04-18 12:23:52 +02:00
// rangement par valeur et par date
console.log('write file ', outputAbsolutePath, outputFileNameJson);
statistics.dates.years = sortByKey(statistics.dates.years)
statistics.dates.weeks = sortByKey(statistics.dates.weeks)
statistics.dates.months = sortByKey(statistics.dates.months)
statistics.dates.days = sortByKey(statistics.dates.days)
2023-04-18 13:24:20 +02:00
statistics = sortByKey(statistics)
2023-03-04 23:52:46 +01:00
2023-03-05 23:13:16 +01:00
const jsonContent = {
statistics: {
lines_count: everyline.length,
headers_count: headers.length,
2023-04-18 13:24:20 +02:00
statistics
2023-03-05 23:13:16 +01:00
},
meta_data: {
author: '@tykayn@mastodon.Cipherbliss.com',
generated_at: new Date(),
generated_from_file: sourceFilePath + sourceFileName,
sources: 'https://forge.chapril.org/tykayn/org-report-stats.git'
},
tasks_list: tasksObjectsForJsonExport
}
2023-03-05 23:13:16 +01:00
if (writeJsonAfterParse) {
2023-04-18 12:23:52 +02:00
writeFileInOuputFolderFromJsonObject(outputFileNameJson, jsonContent);
2023-03-05 23:13:16 +01:00
}
2023-03-04 23:57:03 +01:00
2023-03-04 23:52:46 +01:00
})
2023-04-18 12:23:52 +02:00
2023-03-05 23:13:16 +01:00
function lineHasKeyword(line, keyword = 'TODO') {
2023-03-04 23:52:46 +01:00
2023-03-05 23:13:16 +01:00
let isFound = (line.indexOf('* ' + keyword) !== -1)
if (isFound) {
createNewHeaderKind(keyword)
2023-03-04 23:52:46 +01:00
headersByKind[keyword].push(line);
if (!statistics[keyword]) {
statistics[keyword] = 0
}
statistics[keyword]++
2023-03-04 23:52:46 +01:00
}
2023-03-05 23:13:16 +01:00
return isFound;
}
function lineHasSubstring(line, keyword) {
let isFound = (line.indexOf(keyword) !== -1)
if (!statistics[keyword]) {
statistics[keyword] = 0
}
statistics[keyword]++
2023-03-05 23:13:16 +01:00
return isFound
2023-03-04 23:52:46 +01:00
}
function createNewHeaderKind(keyword) {
if (!headersByKind[keyword]) {
headersByKind[keyword] = [];
}
2023-03-04 23:57:03 +01:00
}
2023-03-05 23:13:16 +01:00
/**
* chercher des dates et heures au format
* YYYY-MM-DD HH:II:SS
*
* @param line
* @returns {*}
*/
function searchDate(line) {
// return line.match(/[(\d{4}\-\d{2}\-\d{2} ?\d{2}?\:?\d{2}?\:?\d{2}?)(\d{4}\-\d{2}\-\d{2})]/)
let simpleDay = line.match(/\d{4}\-\d{2}\-\d{2} \w{3}?\.?/)
let simpleDayHour = line.match(/\d{4}\-\d{2}\-\d{2} \w{3}?\.? \d{2}\:\d{2}/)
let simpleDayHourSec = line.match(/\d{4}\-\d{2}\-\d{2} \w{3}?\.? \d{2}\:\d{2}\:\d{2}/)
if (simpleDayHourSec) {
2023-03-05 23:13:16 +01:00
return simpleDayHourSec;
}
if (simpleDayHour) {
2023-03-05 23:13:16 +01:00
return simpleDayHour;
}
if (simpleDay) {
2023-03-05 23:13:16 +01:00
return simpleDay;
}
}
/**
* get the cleaned content of the header
* @param line
*/
function cleanHeader(line) {
line = '' + line;
stateKeywordList.forEach(keyword => {
line = line.replace(keyword, '')
})
line = line.replace(/\** /, '');
line = line.replace(/\[.*\]/g, '');
line = line.replace(/\:.*\:/g, '');
line = line.replace(' ', '');
return line.trim();
}
2023-04-18 12:23:52 +02:00
/**
* ranger un objet littéral par ordre alphabétique de ses clés
* @param objectStuff
* @returns {{}}
*/
function sortByKey(objectStuff) {
return Object.keys(objectStuff).sort().reduce(
(obj, key) => {
obj[key] = objectStuff[key];
return obj;
},
{}
);
}
2023-04-18 13:24:20 +02:00
/**
* ranger un objet littéral selon la valeur décroissante de ses paires
* @param literalobject
* @returns {any}
*/
function sortByValue(literalobject) {
let sortable = [];
for (var keyName in literalobject) {
sortable[keyName] = literalobject[keyName];
}
// return literalobject
return sortable.sort(function (a, b) {
return b[1] - a[1];
});
}
2023-04-18 12:23:52 +02:00
export async function writeFileInOuputFolderFromJsonObject(fileName, jsonObjectThing) {
2023-04-18 21:59:16 +02:00
// console.log('statistics.dates', statistics.dates)
2023-03-05 23:13:16 +01:00
2023-03-14 18:04:54 +01:00
return await fs.writeFile(
`${outputAbsolutePath}${fileName}`,
JSON.stringify(jsonObjectThing, null,2),
2023-03-05 11:05:06 +01:00
"utf8",
(err) => {
if (err) {
console.log(`Error writing file: ${err}`);
} else {
console.log(`File ${fileName} is written successfully!`);
}
}
);
2023-03-04 23:52:46 +01:00
}