clean content by special chars lines removal, add content word statistics

parse_orgmode_to_json.mjs

@@ -17,6 +17,7 @@ let headers = []
 let tasksObjectsForJsonExport = []
 let headersByKind = {}
 let writeJsonAfterParse = false;
+writeJsonAfterParse = true;
 
 /**************************************************************
  * fetch the source orgmode file to read its contents
@@ -44,8 +45,14 @@ fs.stat(sourceFilePath, function (err, stat) {
 let stateKeywordList = ['SOMEDAY', 'NEXT', 'TODO', 'CANCELLED', 'DONE', 'WAITING'];
 let dateKeywordList = ['CREATED', 'SCHEDULED', 'DEADLINE', 'CLOSED', 'Refiled'];
 let sectionKeywordList = ['PROPERTIES', 'LOGBOOK', 'END'];
-let propertiesSection = {}
-let logBookSection = {}
+
+let propertiesSection = {} // TODO properties listing
+let logBookSection = {} // TODO logbook listing
+
+let statistics = {
+    tags: {},
+    words: {}
+}
 
 let headerKeywordSearch = '[' + stateKeywordList.join('|') + ']'
 /**
@@ -55,7 +62,7 @@ let headerKeywordSearch = '[' + stateKeywordList.join('|') + ']'
 let task = {
     header: "",
     level: "",
-    content: "",
+    corpus: "",
     state: "",
     tags: [],
     tagsInherited: [],
@@ -63,17 +70,39 @@ let task = {
     logbook: {},
     properties: {},
 }
-// init first task object as empty clone
-let currentTask = {...task};
+
 let isHeader = false;
 let isProperty = false;
 let isLogbook = false;
 let isFirst = true;
 
+// init first task object as empty clone
+let currentTask = {...task};
+
+/**
+ * add to tasks to export and refresh current task
+ */
+function addAndRefreshCurrentTask() {
+    tasksObjectsForJsonExport.push(currentTask)
+    currentTask = {...task};
+    currentTask.dates = {};
+};
+
+function makeWordsStatistics(sentence) {
+    sentence.split(' ')?.forEach(word => {
+        if (!statistics.words[word]) {
+            statistics.words[word] = 0
+        }
+        statistics.words[word]++
+    })
+}
+
 /**********************
  * loop to parse all
  *********************/
 fs.readFile(sourceFilePath, 'utf8', function (err, data) {
+
+
     if (err) {
         return console.log(err);
     }
@@ -90,10 +119,8 @@ fs.readFile(sourceFilePath, 'utf8', function (err, data) {
         if (line.match(/^\*+? /)) {
             // add last task to export list
             if (!isFirst) {
-                tasksObjectsForJsonExport.push(currentTask)
 
-                console.log('currentTask.dates', currentTask.dates)
-                currentTask = {...task};
+                addAndRefreshCurrentTask();
             } else {
                 isFirst = false;
             }
@@ -105,11 +132,9 @@ fs.readFile(sourceFilePath, 'utf8', function (err, data) {
             // create a new task
 
 
-            line = line.replace('*', '')
-            line = line.replace(stateKeywordList, [].fill('', 0, stateKeywordList.length))
-
-            headers.push(line)
-            currentTask.header = line;
+            headers.push(cleanHeader(line))
+            currentTask.header = cleanHeader(line);
+            makeWordsStatistics(cleanHeader(line));
             stateKeywordList.forEach(keyword => {
                 let keywordIsFound = lineHasKeyword(line, keyword)
 
@@ -123,18 +148,26 @@ fs.readFile(sourceFilePath, 'utf8', function (err, data) {
             let tagsFound = line.match(/\:(.*)\:/g)
             if (tagsFound) {
                 tagsFound = tagsFound[0];
-                console.log('tagsFound', tagsFound)
-                tagsFound = tagsFound.split(':').filter(item => item.length)
-                currentTask.tags = tagsFound;
+                let tagList = tagsFound.split(':');
+                tagList?.forEach(tag => {
+                    if (tag.length > 1) {
+
+                        if (!statistics.tags[tag]) {
+                            statistics.tags[tag] = 0
+                        }
+                        statistics.tags[tag]++
+
+                        currentTask.tags.push(tag)
+                    }
+                })
             }
 
 
-            // fin des recherches dans la ligne de Header
+            // ------------- fin des recherches dans la ligne de Header -------------
         } 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) {
@@ -149,31 +182,38 @@ fs.readFile(sourceFilePath, 'utf8', function (err, data) {
                     // console.log('keyword', keyword)
                 }
             })
-        }
+        } else {
 
+            if (line.indexOf(dateKeywordList) !== -1 && line.indexOf(stateKeywordList) !== -1 && line.indexOf(sectionKeywordList) !== -1) {
+
+                makeWordsStatistics(line)
                 // ajouter le corps complet de la section après le header
                 if (line.length && !isHeader) {
 
-            let cleanedLine = line.replace(/\s\s/g, ' ')
+                    let cleanedLine = line.replace(/\s\s/g, ' ');
                     cleanedLine = line.replace(/ {2,}/g, ' ')
-            console.log('line', cleanedLine)
-            currentTask.corpus += `
- ` + cleanedLine;
-        }
 
+                    currentTask.corpus += `${cleanedLine}
+`
+                }
+            }
+        }
     })
     // ajouter la dernière tâche parsée
-    tasksObjectsForJsonExport.push(currentTask)
+    addAndRefreshCurrentTask();
 
-    console.log('headers', headers)
     console.log(" parsing fini")
-    stateKeywordList.forEach(keyword => console.log('nombre de headers', keyword, headersByKind[keyword]?.length))
+    // stateKeywordList.forEach(keyword => console.log('nombre de headers', keyword, headersByKind[keyword]?.length))
 
 
     const jsonContent = {
         statistics: {
             lines_count: everyline.length,
             headers_count: headers.length,
+            statistics: Object.keys(statistics).sort(function (a, b) {
+                return statistics[a] - statistics[b]
+            })
+
         },
         meta_data: {
             author: '@tykayn@mastodon.Cipherbliss.com',
@@ -183,13 +223,14 @@ fs.readFile(sourceFilePath, 'utf8', function (err, data) {
         },
         tasks_list: tasksObjectsForJsonExport
     }
+
+    console.log('statistics', statistics)
     // console.log('tasksObjectsForJsonExport', jsonContent)
 
     if (writeJsonAfterParse) {
-        writeJsonFile('export_' + sourceFileName + '.json', JSON.stringify(jsonContent));
+        writeJsonFile('export_' + sourceFileName + '_parsed.json', JSON.stringify(jsonContent));
     }
 
-    return;
 })
 
 function lineHasKeyword(line, keyword = 'TODO') {
@@ -198,13 +239,22 @@ function lineHasKeyword(line, keyword = 'TODO') {
     if (isFound) {
         createNewHeaderKind(keyword)
         headersByKind[keyword].push(line);
+        if (!statistics[keyword]) {
+            statistics[keyword] = 0
+        }
+        statistics[keyword]++
     }
     return isFound;
 }
 
 function lineHasSubstring(line, keyword) {
+    let isFound = (line.indexOf(keyword) !== -1)
+    if (!statistics[keyword]) {
+        statistics[keyword] = 0
+    }
+    statistics[keyword]++
 
-    return (line.indexOf(keyword) !== -1)
+    return isFound
 }
 
 function createNewHeaderKind(keyword) {
@@ -249,6 +299,23 @@ function compareDatesAndKeepOldest(date1, date2) {
     date2 = moment(date2)
 }
 
+/**
+ * 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();
+}
+
 function writeJsonFile(fileName, fileContent) {
     console.log('write file ', fileName);