worked on fixing the code

2026-06-15 18:01:52 +02:00 · 2025-11-24 16:40:12 +01:00
parent af13907fdc
commit a5a60635fc
4 changed files with 140 additions and 123 deletions
@@ -139,7 +139,7 @@ electron.ipcMain.on("file_submit", async (event, args) => {
        let audiopath = ""
        let transcriptpath = ""

-        console.log("\n\n Running the Video to Audio Extractor");
+     /*   console.log("\n\n Running the Video to Audio Extractor");
        // This code handles the Video to Audio extraction module call
        await mapFunctions.get("module-handler").function(args.video.module, {inputVideoPath: args.video.inputVideoPath, outputType: args.video.outputType}).then(resp => {
            console.log(resp);
@@ -164,11 +164,13 @@ electron.ipcMain.on("file_submit", async (event, args) => {
            mainWindow.webContents.send("error", err)
            return
        })
-
+*/

        console.log("\n\n Running the Transcription Summarizer module");
        // This code summarises the transcript, so that it can be used by an llm
-        await mapFunctions.get("summarize-transcription").function(transcriptpath).then(resp => {
+       // await mapFunctions.get("summarize-transcription").function(transcriptpath).then(resp => {
+        await mapFunctions.get("summarize-transcription").function('/Users/santa/Proj25/video2document/storage/transcripts/IMG_2978.json').then(resp => {
+
            console.log(resp);
            transcriptpath = resp
            curstep++
@@ -299,6 +299,7 @@
      "resolved": "https://registry.npmjs.org/@types/node/-/node-24.9.2.tgz",
      "integrity": "sha512-uWN8YqxXxqFMX2RqGOrumsKeti4LlmIMIyV0lgut4jx7KQBcBiW6vkDtIBvHnHIquwNfJhk8v2OtmO8zXWHfPA==",
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "undici-types": "~7.16.0"
      }
@@ -2534,6 +2535,7 @@
      "integrity": "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw==",
      "dev": true,
      "license": "Apache-2.0",
+      "peer": true,
      "bin": {
        "tsc": "bin/tsc",
        "tsserver": "bin/tsserver"
@@ -1,5 +1,3 @@
-const fs = require("fs");
-const path = require("path");

 // Prepare output directory (always storage/transcriptionSummaries under project root)
 const outputDir = `${__dirname}/../../../storage/transcriptionSummaries`;
@@ -14,49 +12,98 @@ module.exports = {
    type: "summarizer", // value used to differentiate each module to order them in the UI
    displayname: "Summarizer",  // The displayname used within the UI
    async function(args) {
-        let inputJson = args.json;
+        return new Promise(async (resolve, reject) => {
+            let inputJson = args.json;

-        //JSON Path
-        if (args.jsonPath) {
-            try {
-                const raw = fs.readFileSync(args.jsonPath, "utf-8");
-                inputJson = JSON.parse(raw);
-            } catch (e) {
-                console.error("Failed to load JSON from file:", e);
-                return { error: "Could not read JSON from file path." };
+            //JSON Path
+            if (args.jsonPath) {
+                try {
+                    const raw = fs.readFileSync(args.jsonPath, "utf-8");
+                    inputJson = JSON.parse(raw);
+                } catch (e) {
+                    console.error("Failed to load JSON from file:", e);
+                    return { error: "Could not read JSON from file path." };
+                }
            }
-        }
-        // JSON parsen
-        if (typeof inputJson === "string") {
-            try {
-                inputJson = JSON.parse(inputJson);
-            } catch (e) {
-                console.log("Invalid JSON in summarize-transcription");
-                return { error: "Invalid JSON" };
+            // JSON parsen
+            if (typeof args === "string") {
+                try {
+                        await fs.readFile(args, 'utf8', function (err, data) {
+                        if (err) throw err;
+                        inputJson = JSON.parse(data);
+                    });
+                } catch (e) {
+                    console.log("Invalid JSON in summarize-transcription");
+                    console.log(e)
+                    return { error: "Invalid JSON" };
+                }
            }
-        }

-        const words = inputJson.words;
-        if (!Array.isArray(words)) {
-            return { error: "No words Array found" };
-        }
+            const words = inputJson.words;
+            if (!Array.isArray(words)) {
+                return { error: "No words Array found" };
+            }

-        const ENDINGS = [".", "!", "?"]; // '...' auch als Satzende ?
-        const ABBREVIATIONS = new Set(["z.B.", "bzw.", "u.a.", "Dr.", "Mr.", "Mrs.", "Prof.", "etc."]); //TODO weitere Ergaenzen
+            const ENDINGS = [".", "!", "?"]; // '...' auch als Satzende ?
+            const ABBREVIATIONS = new Set(["z.B.", "bzw.", "u.a.", "Dr.", "Mr.", "Mrs.", "Prof.", "etc."]); //TODO weitere Ergaenzen

-        const result = [];
-        let currentSentence = "";
-        let currentSpeaker = null;
-        let startTime = null;
-        let endTime = null;
+            const result = [];
+            let currentSentence = "";
+            let currentSpeaker = null;
+            let startTime = null;
+            let endTime = null;

-        for (const w of words) {
-            if (!currentSpeaker) currentSpeaker = w.speaker;
-            if (startTime === null) startTime = w.start;
-            endTime = w.end;
+            for (const w of words) {
+                if (!currentSpeaker) currentSpeaker = w.speaker;
+                if (startTime === null) startTime = w.start;
+                endTime = w.end;
        
-            //speaker changing
-            if (currentSpeaker !== w.speaker && currentSentence) { 
+                //speaker changing
+                if (currentSpeaker !== w.speaker && currentSentence) { 
+                    const lastEntry = result[result.length - 1];
+                    if (lastEntry && lastEntry.speaker === currentSpeaker) {
+                        lastEntry.sentence += " " + currentSentence;
+                        lastEntry.end = endTime;
+                    } else {
+                        result.push({
+                            speaker: currentSpeaker,
+                            sentence: currentSentence,
+                            start: startTime,
+                            end: endTime
+                        });
+                    }
+                    currentSentence = "";
+                    startTime = w.start;
+                }
+                currentSpeaker = w.speaker;
+                currentSentence += (currentSentence ? " " : "") + w.text; //sentence beginning or not
+                const lastWord = w.text.trim();
+                const lastChar = lastWord.slice(-1);
+                const isAbbreviation = ABBREVIATIONS.has(lastWord);
+
+                //sentence ending
+                if (ENDINGS.includes(lastChar) && !isAbbreviation) {
+                    const lastEntry = result[result.length - 1];
+                    if (lastEntry && lastEntry.speaker === currentSpeaker) {
+                        lastEntry.sentence += " " + currentSentence;
+                        lastEntry.end = endTime;
+                    } else {
+                        result.push({
+                            speaker: currentSpeaker,
+                            sentence: currentSentence,
+                            start: startTime,
+                            end: endTime
+                        });
+                    }
+                    currentSentence = "";
+                    startTime = null;
+                    endTime = null;
+                    currentSpeaker = null;
+                }
+            }
+
+            // safe last sentence 
+            if (currentSentence) {
                const lastEntry = result[result.length - 1];
                if (lastEntry && lastEntry.speaker === currentSpeaker) {
                    lastEntry.sentence += " " + currentSentence;
@@ -69,70 +116,30 @@ module.exports = {
                        end: endTime
                    });
                }
-                currentSentence = "";
-                startTime = w.start;
            }
-            currentSpeaker = w.speaker;
-            currentSentence += (currentSentence ? " " : "") + w.text; //sentence beginning or not
-            const lastWord = w.text.trim();
-            const lastChar = lastWord.slice(-1);
-            const isAbbreviation = ABBREVIATIONS.has(lastWord);

-            //sentence ending
-            if (ENDINGS.includes(lastChar) && !isAbbreviation) {
-                const lastEntry = result[result.length - 1];
-                if (lastEntry && lastEntry.speaker === currentSpeaker) {
-                    lastEntry.sentence += " " + currentSentence;
-                    lastEntry.end = endTime;
-                } else {
-                    result.push({
-                        speaker: currentSpeaker,
-                        sentence: currentSentence,
-                        start: startTime,
-                        end: endTime
-                    });
-                }
-                currentSentence = "";
-                startTime = null;
-                endTime = null;
-                currentSpeaker = null;
+            // Output as Text
+            const output = result.map(r => 
+                `Sprecher ${r.speaker} [${r.start.toFixed(2)} - ${r.end.toFixed(2)}]: ${r.sentence}`
+            );
+
+            // Output on cosole
+            //console.log("\n------------\nMerged Transcription Result:\n", output, "\n------------\n");
+
+            try {
+                const jsonPath = path.join(outputDir, "transcription_result.json");
+                fs.writeFileSync(jsonPath, JSON.stringify(result, null, 2), "utf-8");
+
+                const txtPath = path.join(outputDir, "transcription_result.txt");
+                fs.writeFileSync(txtPath, output.join("\n"), "utf-8");
+
+                console.log(`Summary successfully saved:\n- ${jsonPath}\n- ${txtPath}`);
+
+                resolve(jsonPath);
+            } catch (err) {
+                console.error("Error saving Summary:", err);
+                reject(err);
            }
-        }
-
-        // safe last sentence 
-        if (currentSentence) {
-            const lastEntry = result[result.length - 1];
-            if (lastEntry && lastEntry.speaker === currentSpeaker) {
-                lastEntry.sentence += " " + currentSentence;
-                lastEntry.end = endTime;
-            } else {
-                result.push({
-                    speaker: currentSpeaker,
-                    sentence: currentSentence,
-                    start: startTime,
-                    end: endTime
-                });
-            }
-        }
-
-        // Output as Text
-        const output = result.map(r => 
-            `Sprecher ${r.speaker} [${r.start.toFixed(2)} - ${r.end.toFixed(2)}]: ${r.sentence}`
-        );
-
-        // Output on cosole
-        //console.log("\n------------\nMerged Transcription Result:\n", output, "\n------------\n");
-
-        try {
-            const jsonPath = path.join(outputDir, "transcription_result.json");
-            fs.writeFileSync(jsonPath, JSON.stringify(result, null, 2), "utf-8");
-
-            const txtPath = path.join(outputDir, "transcription_result.txt");
-            fs.writeFileSync(txtPath, output.join("\n"), "utf-8");
-
-            console.log(`Summary successfully saved:\n- ${jsonPath}\n- ${txtPath}`);
-        } catch (err) {
-            console.error("Error saving Summary:", err);
-        }
+        })
    }
 }
@@ -79,6 +79,8 @@ function saveTranscript(transcript, sessionId) {
  fs.writeFileSync(outputPath, JSON.stringify(transcript, null, 2));

  console.log(`Transcript saved: ${outputPath}`);
+
+  return outputPath;
 }

 //---------------------------------------------------Modul---------------------------------------------------
@@ -89,29 +91,33 @@ module.exports = {
  displayname: 'AssemblyAI',

  async function(audioFileName) {
-    try {
-      // audioFileName ist nur "datei.mp3"
-      const audioPath = audioFileName;
+    return new Promise(async (resolve, reject) => {
+      try {
+        // audioFileName ist nur "datei.mp3"
+        const audioPath = audioFileName;

-      let audioUrl;
+        let audioUrl;

-      if (/^https?:\/\//i.test(audioFileName)) {
-        audioUrl = audioFileName;
-      } else {
-        if (!fs.existsSync(audioPath)) {
-          throw new Error(`Audio file not found: ${audioPath}`);
+        if (/^https?:\/\//i.test(audioFileName)) {
+          audioUrl = audioFileName;
+        } else {
+          if (!fs.existsSync(audioPath)) {
+            throw new Error(`Audio file not found: ${audioPath}`);
+          }
+          audioUrl = await uploadAudio(audioPath);
        }
-        audioUrl = await uploadAudio(audioPath);
+
+        const transcriptId = await createTranscript(audioUrl);
+        const transcript = await pollTranscript(transcriptId);
+
+        const sessionId = getSessionId(audioFileName);
+        
+        resolve(saveTranscript(transcript, sessionId));
+
+      } catch (error) {
+        console.error('Transcription error:', error.message);
+        reject(error);
      }
-
-      const transcriptId = await createTranscript(audioUrl);
-      const transcript = await pollTranscript(transcriptId);
-
-      const sessionId = getSessionId(audioFileName);
-      saveTranscript(transcript, sessionId);
-
-    } catch (error) {
-      console.error('Transcription error:', error.message);
-    }
+    })
  }
 };