Some adaptations to better support new research studies

data_extractor/example/__init__.py

@@ -0,0 +1,20 @@
+__version__ = '0.2.0'
+
+import zipfile
+import pandas as pd
+
+
+def process(file_data):
+    names = []
+    zfile = zipfile.ZipFile(file_data)
+    data = []
+    for name in zfile.namelist():
+        names.append(name)
+        info = zfile.getinfo(name)
+        data.append((name, info.compress_size, info.file_size))
+
+    return [{
+        "id": "overview",
+        "title": "The following files where read:",
+        "data_frame": pd.DataFrame(data, columns=["filename", "compressed size", "size"])
+    }]

data_extractor/example/index.html

@@ -0,0 +1,11 @@
+<script src="../pyprocess.js" data-script="./example/__init__.py"></script>
+<div id="controls">
+  <p id="loading-indicator">Loading...</p>
+  <input type="file" id="fileItem" disabled onChange="toggleProcessButton()" />
+  <button onClick="process()" id="process" disabled>Process</button>
+</div>
+
+<div id="results" style="display: none">
+  <p id="summary" />
+  <div id="html" />
+</div>

data_extractor/google_search_history/index.html

@@ -0,0 +1,11 @@
+<script src="../pyprocess.js" data-script="./google_search_history/__init__.py"></script>
+<div id="controls">
+  <p id="loading-indicator">Loading...</p>
+  <input type="file" id="fileItem" disabled onChange="toggleProcessButton()" />
+  <button onClick="process()" id="process" disabled>Process</button>
+</div>
+
+<div id="results" style="display: none">
+  <p id="summary" />
+  <div id="html" />
+</div>

data_extractor/google_search_history/simulation_gsh.py

@@ -157,16 +157,16 @@ def browserhistory(num: int, site_diff: float, time_diff: bool,
     parts = _create_bins(num)
     # create browserhistory data
     results = []
-    for moment in PERIODS:
+    for moment, period in PERIODS.items():
         # simulate dates
         if moment == 'during':
             perc = 0.15+site_diff
-            dates = _create_date(num=parts[moment], start=PERIODS[moment][0],
-                                 end=PERIODS[moment][1], time_perc=time_diff)
+            dates = _create_date(num=parts[moment], start=period[0],
+                                 end=period[1], time_perc=time_diff)
         else:
             perc = 0.15
-            dates = _create_date(num=parts[moment], start=PERIODS[moment][0],
-                                 end=PERIODS[moment][1], time_perc=0)
+            dates = _create_date(num=parts[moment], start=period[0],
+                                 end=period[1], time_perc=0)
         # simulate website URLs
         url = _create_website(num=parts[moment], perc=perc, fake=fake)
         for i in range(parts[moment]):

data_extractor/google_semantic_location_history/index.html

@@ -0,0 +1,11 @@
+<script src="../pyprocess.js" data-script="./google_semantic_location_history/__init__.py"></script>
+<div id="controls">
+  <p id="loading-indicator">Loading...</p>
+  <input type="file" id="fileItem" disabled onChange="toggleProcessButton()" />
+  <button onClick="process()" id="process" disabled>Process</button>
+</div>
+
+<div id="results" style="display: none">
+  <p id="summary" />
+  <div id="html" />
+</div>

data_extractor/google_semantic_location_history/simulation_gslh.py

@@ -180,7 +180,7 @@ def fake_data(json_file, seed=0):
     places = _create_places(total=max(NPLACES.values()))
 
     # Get json schema from json file
-    with open(json_file) as file_object:
+    with open(json_file, encoding="utf-8") as file_object:
         json_data = json.load(file_object)
         json_schema = get_json_schema(json_data)