Fixed support for filename matching

data_extractor/pyprocess.js

@@ -48,6 +48,7 @@ function process() {
   resultElement().style.display = "none";
 
   const file = fileInput().files[0];
+  const filename = file.name
   const reader = file.stream().getReader();
   const sendToWorker = ({ done, value }) => {
     if (done) {
@@ -60,7 +61,7 @@ function process() {
     reader.read().then(sendToWorker);
   };
   console.log("process: send event: initData");
-  pyWorker.postMessage({ eventType: "initData", size: file.size });
+  pyWorker.postMessage({ eventType: "initData", filename: filename, size: file.size });
   reader.read().then(sendToWorker);
 }
 

data_extractor/pyworker.js

@@ -10,28 +10,39 @@ loadPyodide({ indexURL: "https://cdn.jsdelivr.net/pyodide/v0.19.0/full/" }).then
 });
 
 let file = undefined
+var filename = undefined
 
 onmessage = (event) => {
   const { eventType } = event.data;
   if (eventType === "loadScript") {
     self.pyodide.runPython(event.data.script)
   } else if (eventType === "initData") {
-    file = self.pyodide.FS.open("user-data", "w")
+    filename = event.data.filename
+    file = self.pyodide.FS.open(filename, "w")
   } else if (eventType === "data") {
     self.pyodide.FS.write(file, event.data.chunk, 0, event.data.chunk.length)
   } else if (eventType === "processData") {
     const result = self.pyodide.runPython(`
     def _process_data():
       import json
       import html
-      result = process(open("user-data", "rb"))
+      import pandas as pd
+
+      result = process("${filename}")
+
+      if not result:
+        data_frame = pd.DataFrame()
+        data_frame["Messages"] = pd.Series(["Unfortunately, no data could be extracted from the selected file."], name="Messages")
+        result = [{"id": "important_feedback", "title": "Important feedback", "data_frame": data_frame}]
+
       data_output = []
       html_output = []
       for data in result:
         html_output.append(f"""<h1 class="text-title4 font-title4 sm:text-title3 sm:font-title3 mt-12 mb-6 text-grey1">{html.escape(data['title'])}</h1>""")
         df = data['data_frame']
         html_output.append(df.to_html(classes=["data-donation-extraction-results"], justify="left"))
         data_output.append({"id": data["id"], "data_frame": df.to_json()})
+
       return {
         "html": "\\n".join(html_output),
         "data": json.dumps(data_output),

data_extractor/whatsapp_chat/__init__.py

@@ -693,7 +693,7 @@ def process(file_data):
     try:
         zfile = zipfile.ZipFile(file_data)
     except:
-        if FILE_RE.match(file_data.name):
+        if FILE_RE.match(file_data):
             tfile = open(file_data, encoding="utf8")
             chat = parse_chat(log_error, tfile.read())