Berickson/20260113 extension tab ids

VERSION

@@ -1 +1 @@
-0.1.0+2026.02.02T16.19.01.249Z.2ae8ac1a.berickson.20260120.comm.protocol.targets
+0.1.0+2026.02.02T20.54.51.168Z.c0f2a8f0.berickson.20260113.extension.tab.ids

extension/writing-process/src/background.js

@@ -3,8 +3,7 @@ Background script. This works across all of Google Chrome.
 */
 
 import { CONFIG } from "./service_worker_config.js";
-import { googledocs_id_from_url } from './writing_common';
-
+import { googledocs_id_from_url, googledocs_tab_id_from_url } from './writing_common';
 import * as loEvent from 'lo_event/lo_event/lo_event.js';
 import * as loEventDebug from 'lo_event/lo_event/debugLog.js';
 import { websocketLogger } from 'lo_event/lo_event/websocketLogger.js';
@@ -203,6 +202,7 @@ chrome.webRequest.onBeforeRequest.addListener(
                   versus GMT. */
                 event = {
                     'doc_id': googledocs_id_from_url(request.url),
+                    'tab_id': googledocs_tab_id_from_url(request.url),
                     'url': request.url,
                     'bundles': JSON.parse(formdata.bundles),
                     'rev': formdata.rev,
@@ -216,6 +216,7 @@ chrome.webRequest.onBeforeRequest.addListener(
                 */
                 event = {
                     'doc_id': googledocs_id_from_url(request.url),
+                    'tab_id': googledocs_tab_id_from_url(request.url),
                     'url': request.url,
                     'formdata': formdata,
                     'rev': formdata.rev,

extension/writing-process/src/writing.js

@@ -5,7 +5,7 @@
 /* For debugging purposes: we know the extension is active */
 // document.body.style.border = "1px solid blue";
 
-import { googledocs_id_from_url, treeget } from './writing_common';
+import { googledocs_id_from_url, googledocs_tab_id_from_url, treeget } from './writing_common';
 /*
    General Utility Functions
 */
@@ -49,6 +49,7 @@ function log_event(event_type, event) {
         "type": "http://schema.learning-observer.org/writing-observer/",
         "title": google_docs_title(),
         "id": doc_id(),
+        "tab_id": tab_id(),
         "url": window.location.href,
     };
 
@@ -78,6 +79,18 @@ function doc_id() {
     }
 }
 
+function tab_id() {
+    /*
+      Extract the Google document's current Tab ID from the window
+    */
+    try {
+        return googledocs_tab_id_from_url(window.location.href);
+    } catch(error) {
+        log_error("Couldn't read document's tab id");
+        return null;
+    }
+}
+
 
 function this_is_a_google_doc() {
     /*

extension/writing-process/src/writing_common.js

@@ -78,6 +78,30 @@ export function googledocs_id_from_url(url) {
     return null;
 }
 
+export function googledocs_tab_id_from_url(url) {
+    /*
+      Given a URL like:
+        https://docs.google.com/document/d/<doc_id>/edit?tab=t.95yb7msfl8ul
+        https://docs.google.com/document/d/<doc_id>/edit?tab=t.95yb7msfl8ul#heading=h.abc123
+      extract the associated tab ID:
+        t.95yb7msfl8ul
+      Return null if not a valid Google Docs URL or tab param.
+
+      Regex explanation:
+      1. `/.*:\/\/` - match any protocol (http/https) followed by ://
+      2. `docs\.google\.com\/document\/` - match google docs domain
+      3. `.*` - match any characters until we find the tab param
+      4. `[?&]tab=` - match tab parameter in query string
+      5. `([^&#]+)` - capture tab value, stopping at & (next param) or # (hash fragment)
+      6. `/i` - case insensitive
+    */
+    var match = url.match(/.*:\/\/docs\.google\.com\/document\/.*[?&]tab=([^&#]+)/i);
+    if (match) {
+        return match[1];
+    }
+    return null;
+}
+
 var writing_lasthash = "";
 function unique_id() {
     /*

modules/writing_observer/VERSION

@@ -1 +1 @@
-0.1.0+2026.01.13T18.33.25.519Z.0984e08f.berickson.20260113.abstract.time.on.task.reducers
+0.1.0+2026.02.02T20.54.51.168Z.c0f2a8f0.berickson.20260113.extension.tab.ids

modules/writing_observer/writing_observer/module.py

@@ -261,7 +261,13 @@
     {
         'context': "org.mitros.writing_analytics",
         'scope': writing_observer.writing_analysis.gdoc_scope,
-        'function': writing_observer.writing_analysis.time_on_task,
+        'function': writing_observer.writing_analysis.gdoc_scope_time_on_task,
+        'default': {'saved_ts': 0}
+    },
+    {
+        'context': "org.mitros.writing_analytics",
+        'scope': writing_observer.writing_analysis.gdoc_tab_scope,
+        'function': writing_observer.writing_analysis.gdoc_tab_scope_time_on_task,
         'default': {'saved_ts': 0}
     },
     {
@@ -286,6 +292,12 @@
         'function': writing_observer.writing_analysis.document_list,
         'default': {'docs': []}
     },
+    {
+        'context': "org.mitros.writing_analytics",
+        'scope': writing_observer.writing_analysis.gdoc_scope,
+        'function': writing_observer.writing_analysis.tab_list,
+        'default': {'tabs': {}}
+    },
     {
         'context': "org.mitros.writing_analytics",
         'scope': writing_observer.writing_analysis.student_scope,

modules/writing_observer/writing_observer/reconstruct_doc.py

@@ -40,6 +40,7 @@ def __new__(cls):
         new_object._text = ""
         new_object._position = 0
         new_object._edit_metadata = {}
+        new_object._tabs = {}
         new_object.fix_validity()
         return new_object
 
@@ -100,6 +101,14 @@ def from_json(json_rep):
         new_object._text = json_rep.get('text', '')
         new_object._position = json_rep.get('position', 0)
         new_object._edit_metadata = json_rep.get('edit_metadata', {})
+
+        if 'tabs' in json_rep and json_rep['tabs']:
+            new_object._tabs = {}
+            for tab_id, tab_data in json_rep['tabs'].items():
+                new_object._tabs[tab_id] = google_text.from_json(tab_data)
+        else:
+            new_object._tabs = {}
+
         new_object.fix_validity()
         return new_object
 
@@ -155,11 +164,14 @@ def json(self):
         '''
         This serializes to JSON.
         '''
-        return {
+        result = {
             'text': self._text,
             'position': self._position,
             'edit_metadata': self._edit_metadata
         }
+        if self._tabs:
+            result['tabs'] = {tab_id: tab.json for tab_id, tab in self._tabs.items()}
+        return result
 
 
 def get_parsed_text(self):
@@ -169,18 +181,23 @@ def get_parsed_text(self):
     return self._text.replace(PLACEHOLDER, "")
 
 
+def dispatch_command(doc, cmd):
+    if cmd['ty'] in dispatch:
+        doc = dispatch[cmd['ty']](doc, **cmd)
+    else:
+        print("Unrecogized Google Docs command: " + repr(cmd['ty']))
+        # TODO: Log issue and fix it!
+    return doc
+
+
 def command_list(doc, commands):
     '''
     This will process a list of commands. It is helpful either when
     loading the history of a new doc, or in updating a document from
     new `save` requests.
     '''
     for item in commands:
-        if item['ty'] in dispatch:
-            doc = dispatch[item['ty']](doc, **item)
-        else:
-            print("Unrecogized Google Docs command: " + repr(item['ty']))
-            # TODO: Log issue and fix it!
+        doc = dispatch_command(doc, item)
     return doc
 
 
@@ -301,6 +318,34 @@ def null(doc, **kwargs):
     return doc
 
 
+def nm(doc, nmc, nmr, **kwargs):
+    '''
+    Handle named commands for tabs (sub-documents).
+
+    * `nmc` is the command to execute
+    * `nmr` is the name/reference list, which contains the target tab ID
+    '''
+    # Find the target tab from the nmr list
+    target_tab = None
+    for item in reversed(nmr or []):
+        if isinstance(item, str) and item.startswith("t."):
+            target_tab = item
+            break
+
+    if target_tab is None:
+        # No tab specified, apply to main document
+        doc = dispatch_command(doc, nmc)
+    else:
+        # Ensure the tab exists
+        if target_tab not in doc._tabs:
+            doc._tabs[target_tab] = google_text()
+
+        # Apply the command to the sub-document
+        doc._tabs[target_tab] = dispatch_command(doc._tabs[target_tab], nmc)
+
+    return doc
+
+
 # This dictionary maps the `ty` parameter to the function which
 # handles data of that type.
 
@@ -312,6 +357,7 @@ def null(doc, **kwargs):
 # these can't be handled like plain 'is' or 'ds' because the include different fields
 # (e.g., 'sugid', presumably, suggestion id.)
 dispatch = {
+    'ac': null, # new tab title
     'ae': null,
     'ase': null,  # suggestion
     'ast': null,  # suggestion. Image?
@@ -326,8 +372,10 @@ def null(doc, **kwargs):
     'is': insert,
     'iss': null,  # suggested insertion
     'mefd': null,  # suggestion
+    'mkch': null,  # name of the first tab
     'mlti': multi,
     'msfd': null,  # suggestion
+    'nm': nm,   # named command for tabs
     'null': null,
     'ord': null,
     'ras': null,  # suggestion. Autospell?
@@ -344,6 +392,7 @@ def null(doc, **kwargs):
     'sl': null,
     'ste': null,  # suggestion
     'sue': null,  # suggestion
+    'ucp': null,  # updated tab title
     'uefd': null,  # suggestion
     'use': null,  # suggestion
     'umv': null,