From d64002f441ed6e33b25f3e75a8be1b6e20f0d7c2 Mon Sep 17 00:00:00 2001
From: j <@>
Date: Fri, 2 Sep 2022 14:41:35 -0500
Subject: [PATCH 01/17] Add cmd line args. Readability cleanup. No output
 change.

---
 HangoutJsonParser.py | 30 ++++++++++++++----------------
 1 file changed, 14 insertions(+), 16 deletions(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index 3110e01..47f92f7 100644
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -1,11 +1,5 @@
-import json
-
-# location of Hangouts Json file obtained from Google Takeout
-with open('/path/to/JSON/data/file.json', 'r', encoding='utf-8') as f:
-    jsonData = json.load(f)
-
-simpleJson = []
-
+#!/usr/bin/python
+import argparse, json, os
 
 def parseData():
     for i in range(0, len(jsonData['conversations'])):
@@ -17,8 +11,7 @@ def parseData():
         for j in range(0, len(jsonData['conversations'][i]['events'])):
             message = {}
             message['sender'] = {}
-            message['sender']['name'] = getName(
-                jsonData['conversations'][i]['events'][j]['sender_id']['gaia_id'], conversation['participants'])
+            message['sender']['name'] = getName(jsonData['conversations'][i]['events'][j]['sender_id']['gaia_id'], conversation['participants'])
             message['sender']['id'] = jsonData['conversations'][i]['events'][j]['sender_id']['gaia_id']
             message['unixtime'] = (int(jsonData['conversations'][i]
                                        ['events'][j]['timestamp']))/1000000
@@ -57,9 +50,9 @@ def getParticipants(index):
 
 
 def getName(id, participants):
-    for i in range(0, len(participants)):
-        if id == participants[i]['id']:
-            return participants[i]['name']
+    for p in participants:
+        if id == p['id']:
+            return p['name']
     return id
 
 
@@ -76,8 +69,13 @@ def chatName(i):
     name = participants[index]
     return name
 
-
 if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('INPUT_JSON_PATH', help='Path location of Hangouts.json file obtained from Google Takeout.')
+    parser.add_argument('OUTPUT_DIRECTORY', help='Path to write output files.')
+    args = parser.parse_args()
+
+    jsonData = json.load(open(args.INPUT_JSON_PATH, 'r', encoding='utf-8'))
+    simpleJson = []
     parseData()
-    with open("clean_hangoutsData.json", "w", encoding="utf-8") as write_file:
-        json.dump(simpleJson, write_file, indent=4)
+    json.dump(simpleJson, open(os.path.join(args.OUTPUT_DIRECTORY, 'clean_hangoutsData.json'), 'w', encoding='utf-8'), indent=4)

From f31ea4ef1a107d477afbdd0fad9192744fa17d34 Mon Sep 17 00:00:00 2001
From: j <@>
Date: Fri, 2 Sep 2022 14:49:16 -0500
Subject: [PATCH 02/17] Readability cleanup. No output change.

---
 HangoutJsonParser.py | 37 ++++++++++++++-----------------------
 1 file changed, 14 insertions(+), 23 deletions(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index 47f92f7..0189997 100644
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -8,26 +8,23 @@ def parseData():
         conversation['participants'] = getParticipants(i)
         conversation['messages'] = []
 
-        for j in range(0, len(jsonData['conversations'][i]['events'])):
+        for event in jsonData['conversations'][i]['events']:
             message = {}
             message['sender'] = {}
-            message['sender']['name'] = getName(jsonData['conversations'][i]['events'][j]['sender_id']['gaia_id'], conversation['participants'])
-            message['sender']['id'] = jsonData['conversations'][i]['events'][j]['sender_id']['gaia_id']
-            message['unixtime'] = (int(jsonData['conversations'][i]
-                                       ['events'][j]['timestamp']))/1000000
+            message['sender']['name'] = getName(event['sender_id']['gaia_id'], conversation['participants'])
+            message['sender']['id'] = event['sender_id']['gaia_id']
+            message['unixtime'] = (int(event['timestamp']))/1000000
 
-            if 'chat_message' in jsonData['conversations'][i]['events'][j]:
+            if 'chat_message' in event:
                 # if it's a message(normal hangouts, image...)
-                if 'segment' in jsonData['conversations'][i]['events'][j]['chat_message']['message_content']:
+                if 'segment' in event['chat_message']['message_content']:
                     # if it's a normal hangouts message
                     content = ""
-                    for k in range(0, len(jsonData['conversations'][i]['events'][j]['chat_message']['message_content']['segment'])):
-                        if jsonData['conversations'][i]['events'][j]['chat_message']['message_content']['segment'][k]['type'] == "TEXT":
-                            content = content + \
-                                jsonData['conversations'][i]['events'][j]['chat_message']['message_content']['segment'][k]['text']
-                        elif jsonData['conversations'][i]['events'][j]['chat_message']['message_content']['segment'][k]['type'] == "LINK":
-                            content = content + \
-                                jsonData['conversations'][i]['events'][j]['chat_message']['message_content']['segment'][k]['text']
+                    for k in range(0, len(event['chat_message']['message_content']['segment'])):
+                        if event['chat_message']['message_content']['segment'][k]['type'] == "TEXT":
+                            content = content + event['chat_message']['message_content']['segment'][k]['text']
+                        elif event['chat_message']['message_content']['segment'][k]['type'] == "LINK":
+                            content = content + event['chat_message']['message_content']['segment'][k]['text']
                     message['content'] = content
 
             conversation['messages'].append(message)
@@ -59,15 +56,9 @@ def getName(id, participants):
 def chatName(i):
     if (('name' in jsonData['conversations'][i]['conversation']['conversation'])and(jsonData['conversations'][i]['conversation']['conversation']['name'] != "")):
         return jsonData['conversations'][i]['conversation']['conversation']['name']
-    participants = []
-    index = 0
-    for k in range(0, len(simpleJson[i]['participants'])):
-        participants.append(simpleJson[i]['participants'][k]['name'])
-        if simpleJson[i]['participants'][k]['id'] == jsonData['conversations'][i]['conversation']['conversation']['self_conversation_state']['self_read_state']['participant_id']['gaia_id']:
-            index = k
-            break
-    name = participants[index]
-    return name
+    for part in simpleJson[i]['participants']:
+        if part['id'] == jsonData['conversations'][i]['conversation']['conversation']['self_conversation_state']['self_read_state']['participant_id']['gaia_id']:
+            return part['name']
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()

From 471765259bd82b274d0814e37b7921f2939c8f94 Mon Sep 17 00:00:00 2001
From: j <@>
Date: Fri, 2 Sep 2022 15:01:29 -0500
Subject: [PATCH 03/17] Readability cleanup. No output change.

---
 HangoutJsonParser.py | 30 ++++++++++++------------------
 1 file changed, 12 insertions(+), 18 deletions(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index 0189997..c99096e 100644
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -5,7 +5,7 @@ def parseData():
     for i in range(0, len(jsonData['conversations'])):
         conversation = {}
         conversation['chatName'] = ""
-        conversation['participants'] = getParticipants(i)
+        conversation['participants'] = getParticipants(jsonData['conversations'][i]['conversation']['conversation']['participant_data'])
         conversation['messages'] = []
 
         for event in jsonData['conversations'][i]['events']:
@@ -33,32 +33,26 @@ def parseData():
         simpleJson[i]['chatName'] = chatName(i)
 
 
-def getParticipants(index):
-    participants = []
-    for i in range(0, len(jsonData['conversations'][index]['conversation']['conversation']['participant_data'])):
-        person = {}
-        person['id'] = jsonData['conversations'][index]['conversation']['conversation']['participant_data'][i]['id']['gaia_id']
-        if 'fallback_name' in jsonData['conversations'][index]['conversation']['conversation']['participant_data'][i]:
-            person['name'] = jsonData['conversations'][index]['conversation']['conversation']['participant_data'][i]['fallback_name']
-        else:
-            person['name'] = jsonData['conversations'][index]['conversation']['conversation']['participant_data'][i]['id']['gaia_id']
-        participants.append(person)
-    return participants
+def getParticipants(participant_data):
+    return [{
+        'id': participant['id']['gaia_id'],
+        'name': participant.get('fallback_name', participant['id']['gaia_id'])
+    } for participant in participant_data]
 
 
-def getName(id, participants):
+def getName(pid, participants):
     for p in participants:
-        if id == p['id']:
+        if pid == p['id']:
             return p['name']
-    return id
+    return pid
 
 
 def chatName(i):
     if (('name' in jsonData['conversations'][i]['conversation']['conversation'])and(jsonData['conversations'][i]['conversation']['conversation']['name'] != "")):
         return jsonData['conversations'][i]['conversation']['conversation']['name']
-    for part in simpleJson[i]['participants']:
-        if part['id'] == jsonData['conversations'][i]['conversation']['conversation']['self_conversation_state']['self_read_state']['participant_id']['gaia_id']:
-            return part['name']
+    for participant in simpleJson[i]['participants']:
+        if participant['id'] == jsonData['conversations'][i]['conversation']['conversation']['self_conversation_state']['self_read_state']['participant_id']['gaia_id']:
+            return participant['name']
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()

From 2d26ce8482faea7aee9d0bd371443880cf293e12 Mon Sep 17 00:00:00 2001
From: j <@>
Date: Fri, 2 Sep 2022 15:03:44 -0500
Subject: [PATCH 04/17] Readability cleanup. No output change.

---
 HangoutJsonParser.py | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index c99096e..feb27c5 100644
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -5,7 +5,14 @@ def parseData():
     for i in range(0, len(jsonData['conversations'])):
         conversation = {}
         conversation['chatName'] = ""
-        conversation['participants'] = getParticipants(jsonData['conversations'][i]['conversation']['conversation']['participant_data'])
+        conversation['participants'] = [
+            {
+                'id': participant['id']['gaia_id'],
+                'name': participant.get('fallback_name', participant['id']['gaia_id'])
+            }
+            for participant in
+            jsonData['conversations'][i]['conversation']['conversation']['participant_data']
+        ]
         conversation['messages'] = []
 
         for event in jsonData['conversations'][i]['events']:
@@ -32,21 +39,12 @@ def parseData():
         simpleJson.append(conversation)
         simpleJson[i]['chatName'] = chatName(i)
 
-
-def getParticipants(participant_data):
-    return [{
-        'id': participant['id']['gaia_id'],
-        'name': participant.get('fallback_name', participant['id']['gaia_id'])
-    } for participant in participant_data]
-
-
 def getName(pid, participants):
     for p in participants:
         if pid == p['id']:
             return p['name']
     return pid
 
-
 def chatName(i):
     if (('name' in jsonData['conversations'][i]['conversation']['conversation'])and(jsonData['conversations'][i]['conversation']['conversation']['name'] != "")):
         return jsonData['conversations'][i]['conversation']['conversation']['name']

From 2eec2096bdb58284f3132fc267e0daf2cef46a0d Mon Sep 17 00:00:00 2001
From: j <@>
Date: Fri, 2 Sep 2022 15:10:45 -0500
Subject: [PATCH 05/17] Readability cleanup. No output change.

---
 HangoutJsonParser.py | 39 ++++++++++++++++++++-------------------
 1 file changed, 20 insertions(+), 19 deletions(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index feb27c5..af16a3c 100644
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -2,20 +2,21 @@
 import argparse, json, os
 
 def parseData():
-    for i in range(0, len(jsonData['conversations'])):
-        conversation = {}
-        conversation['chatName'] = ""
-        conversation['participants'] = [
-            {
-                'id': participant['id']['gaia_id'],
-                'name': participant.get('fallback_name', participant['id']['gaia_id'])
-            }
-            for participant in
-            jsonData['conversations'][i]['conversation']['conversation']['participant_data']
-        ]
-        conversation['messages'] = []
+    for orig_conv in jsonData['conversations']:
+        conversation = {
+            'chatName': '',
+            'participants': [
+                {
+                    'id': participant['id']['gaia_id'],
+                    'name': participant.get('fallback_name', participant['id']['gaia_id'])
+                }
+                for participant in
+                orig_conv['conversation']['conversation']['participant_data']
+            ],
+            'messages': []
+        }
 
-        for event in jsonData['conversations'][i]['events']:
+        for event in orig_conv['events']:
             message = {}
             message['sender'] = {}
             message['sender']['name'] = getName(event['sender_id']['gaia_id'], conversation['participants'])
@@ -36,8 +37,8 @@ def parseData():
 
             conversation['messages'].append(message)
 
+        conversation['chatName'] = chatName(orig_conv, conversation['participants'])
         simpleJson.append(conversation)
-        simpleJson[i]['chatName'] = chatName(i)
 
 def getName(pid, participants):
     for p in participants:
@@ -45,11 +46,11 @@ def getName(pid, participants):
             return p['name']
     return pid
 
-def chatName(i):
-    if (('name' in jsonData['conversations'][i]['conversation']['conversation'])and(jsonData['conversations'][i]['conversation']['conversation']['name'] != "")):
-        return jsonData['conversations'][i]['conversation']['conversation']['name']
-    for participant in simpleJson[i]['participants']:
-        if participant['id'] == jsonData['conversations'][i]['conversation']['conversation']['self_conversation_state']['self_read_state']['participant_id']['gaia_id']:
+def chatName(orig_conv, participants):
+    if (('name' in orig_conv['conversation']['conversation']) and (orig_conv['conversation']['conversation']['name'] != "")):
+        return orig_conv['conversation']['conversation']['name']
+    for participant in participants:
+        if participant['id'] == orig_conv['conversation']['conversation']['self_conversation_state']['self_read_state']['participant_id']['gaia_id']:
             return participant['name']
 
 if __name__ == '__main__':

From 23c2232ce8d721a736b179524d5d53ea6688d335 Mon Sep 17 00:00:00 2001
From: j <@>
Date: Fri, 2 Sep 2022 15:15:32 -0500
Subject: [PATCH 06/17] Readability cleanup. No output change.

---
 HangoutJsonParser.py | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index af16a3c..6f67e46 100644
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -17,22 +17,24 @@ def parseData():
         }
 
         for event in orig_conv['events']:
-            message = {}
-            message['sender'] = {}
-            message['sender']['name'] = getName(event['sender_id']['gaia_id'], conversation['participants'])
-            message['sender']['id'] = event['sender_id']['gaia_id']
-            message['unixtime'] = (int(event['timestamp']))/1000000
+            message = {
+                'sender': {
+                    'name': getName(event['sender_id']['gaia_id'], conversation['participants']),
+                    'id':   event['sender_id']['gaia_id']
+                },
+                'unixtime': int(event['timestamp'])/1000000
+            }
 
             if 'chat_message' in event:
                 # if it's a message(normal hangouts, image...)
                 if 'segment' in event['chat_message']['message_content']:
                     # if it's a normal hangouts message
                     content = ""
-                    for k in range(0, len(event['chat_message']['message_content']['segment'])):
-                        if event['chat_message']['message_content']['segment'][k]['type'] == "TEXT":
-                            content = content + event['chat_message']['message_content']['segment'][k]['text']
-                        elif event['chat_message']['message_content']['segment'][k]['type'] == "LINK":
-                            content = content + event['chat_message']['message_content']['segment'][k]['text']
+                    for segment in event['chat_message']['message_content']['segment']:
+                        if segment['type'] == "TEXT":
+                            content = content + segment['text']
+                        elif segment['type'] == "LINK":
+                            content = content + segment['text']
                     message['content'] = content
 
             conversation['messages'].append(message)

From fa2ae5855984a22155b2d12cf32ad0a2b6c60138 Mon Sep 17 00:00:00 2001
From: j <@>
Date: Fri, 2 Sep 2022 16:04:23 -0500
Subject: [PATCH 07/17] Add more outputs in the form of text files.

---
 HangoutJsonParser.py | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index 6f67e46..e9a4f1c 100644
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -1,5 +1,5 @@
 #!/usr/bin/python
-import argparse, json, os
+import argparse, datetime, hashlib, json, os
 
 def parseData():
     for orig_conv in jsonData['conversations']:
@@ -65,3 +65,10 @@ def chatName(orig_conv, participants):
     simpleJson = []
     parseData()
     json.dump(simpleJson, open(os.path.join(args.OUTPUT_DIRECTORY, 'clean_hangoutsData.json'), 'w', encoding='utf-8'), indent=4)
+    for chat in simpleJson:
+        filename = ', '.join(i['name'] for i in chat['participants'])+'.txt'
+        if len(filename) > os.statvfs(args.OUTPUT_DIRECTORY).f_namemax:
+            filename = hashlib.sha256(filename.encode('ascii')).hexdigest()+'.txt'
+        with open(os.path.join(args.OUTPUT_DIRECTORY, filename), 'w') as outtext:
+            for msg in chat['messages']:
+                outtext.write(datetime.datetime.fromtimestamp(msg['unixtime']).strftime('%Y-%m-%d %H:%M:%S')+' '+msg['sender']['name']+': '+msg.get('content','')+'\n')

From 6659dbd8f886dbda59e8cce9e0269b92e2975af9 Mon Sep 17 00:00:00 2001
From: j <@>
Date: Fri, 2 Sep 2022 16:11:39 -0500
Subject: [PATCH 08/17] Fix missing linebreaks.

---
 HangoutJsonParser.py | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index e9a4f1c..8be1985 100644
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -31,10 +31,11 @@ def parseData():
                     # if it's a normal hangouts message
                     content = ""
                     for segment in event['chat_message']['message_content']['segment']:
-                        if segment['type'] == "TEXT":
-                            content = content + segment['text']
-                        elif segment['type'] == "LINK":
+                        if segment['type'] in ('TEXT','LINK'):
                             content = content + segment['text']
+                        elif segment['type'] == 'LINE_BREAK':
+                            content += '\n'
+                        else: raise segment
                     message['content'] = content
 
             conversation['messages'].append(message)

From 80dbe88c69ab4a2851c7feef3690e98e8b41cf5b Mon Sep 17 00:00:00 2001
From: j <@>
Date: Sat, 3 Sep 2022 03:08:48 +0000
Subject: [PATCH 09/17] Reorder code for readability and to make it obvious
 where a bunch of cases were being totally ignored, with TODOs. No output
 change.

---
 HangoutJsonParser.py | 52 +++++++++++++++++++++++++++++---------------
 1 file changed, 34 insertions(+), 18 deletions(-)
 mode change 100644 => 100755 HangoutJsonParser.py

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
old mode 100644
new mode 100755
index 8be1985..7e346cd
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -17,28 +17,44 @@ def parseData():
         }
 
         for event in orig_conv['events']:
-            message = {
+            def get_readable_content(event):
+                match event['event_type']:
+                    case 'REGULAR_CHAT_MESSAGE':
+                        content = None
+                        # if it's a message(normal hangouts, image...)
+                        for msg_k,msg_v in event['chat_message']['message_content'].items():
+                            match msg_k:
+                                case 'segment': # if it's a normal hangouts message
+                                    if content == None: content = ''
+                                    for segment in msg_v:
+                                        match segment['type']:
+                                            case 'TEXT'|'LINK':
+                                                content += segment['text']
+                                            case 'LINE_BREAK':
+                                                content += '\n'
+                                            case _: raise segment
+                                case 'attachment':
+                                    pass # TODO
+                                case _: raise msg_k
+                        return content
+                    case 'HANGOUT_EVENT':
+                        return None # TODO
+                    case 'ADD_USER'|'REMOVE_USER':
+                        return None # TODO
+                    case 'GROUP_LINK_SHARING_MODIFICATION':
+                        return None # TODO
+                    case 'RENAME_CONVERSATION':
+                        return None # TODO
+                    case _: raise Exception('unhandled event type '+event['event_type'])
+
+            conversation['messages'].append({
                 'sender': {
                     'name': getName(event['sender_id']['gaia_id'], conversation['participants']),
                     'id':   event['sender_id']['gaia_id']
                 },
-                'unixtime': int(event['timestamp'])/1000000
-            }
-
-            if 'chat_message' in event:
-                # if it's a message(normal hangouts, image...)
-                if 'segment' in event['chat_message']['message_content']:
-                    # if it's a normal hangouts message
-                    content = ""
-                    for segment in event['chat_message']['message_content']['segment']:
-                        if segment['type'] in ('TEXT','LINK'):
-                            content = content + segment['text']
-                        elif segment['type'] == 'LINE_BREAK':
-                            content += '\n'
-                        else: raise segment
-                    message['content'] = content
-
-            conversation['messages'].append(message)
+                'unixtime': int(event['timestamp'])/1000000,
+                **({'content':_} if (_:=get_readable_content(event)) != None else {})
+            })
 
         conversation['chatName'] = chatName(orig_conv, conversation['participants'])
         simpleJson.append(conversation)

From a7a65bfbcc3a01ed60265dac7b57a6d0bd3cc8f2 Mon Sep 17 00:00:00 2001
From: j <@>
Date: Sat, 3 Sep 2022 03:12:13 +0000
Subject: [PATCH 10/17] Add simple HANGOUT_EVENT text.

---
 HangoutJsonParser.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index 7e346cd..fd1a36a 100755
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -38,7 +38,7 @@ def get_readable_content(event):
                                 case _: raise msg_k
                         return content
                     case 'HANGOUT_EVENT':
-                        return None # TODO
+                        return event['event_type']+' '+event['hangout_event']['event_type']
                     case 'ADD_USER'|'REMOVE_USER':
                         return None # TODO
                     case 'GROUP_LINK_SHARING_MODIFICATION':

From 94336c73bc48c0431b52168c679c16c01c57a73a Mon Sep 17 00:00:00 2001
From: j <@>
Date: Sat, 3 Sep 2022 03:28:05 +0000
Subject: [PATCH 11/17] Assert. Why does google pointlessly duplicate that
 field though.

---
 HangoutJsonParser.py | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index fd1a36a..4126002 100755
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -49,7 +49,7 @@ def get_readable_content(event):
 
             conversation['messages'].append({
                 'sender': {
-                    'name': getName(event['sender_id']['gaia_id'], conversation['participants']),
+                    'name': getName(event['sender_id'], conversation['participants']),
                     'id':   event['sender_id']['gaia_id']
                 },
                 'unixtime': int(event['timestamp'])/1000000,
@@ -59,11 +59,12 @@ def get_readable_content(event):
         conversation['chatName'] = chatName(orig_conv, conversation['participants'])
         simpleJson.append(conversation)
 
-def getName(pid, participants):
+def getName(user, participants):
+    assert user['gaia_id'] == user['chat_id']
     for p in participants:
-        if pid == p['id']:
+        if user['gaia_id'] == p['id']:
             return p['name']
-    return pid
+    return user['gaia_id']
 
 def chatName(orig_conv, participants):
     if (('name' in orig_conv['conversation']['conversation']) and (orig_conv['conversation']['conversation']['name'] != "")):

From 7fca2d778961069d0dd4c011a8857d0fa46f8b97 Mon Sep 17 00:00:00 2001
From: j <@>
Date: Sat, 3 Sep 2022 03:31:03 +0000
Subject: [PATCH 12/17] Add ADD_USER/REMOVE_USER text.

---
 HangoutJsonParser.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index 4126002..553432b 100755
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -40,7 +40,12 @@ def get_readable_content(event):
                     case 'HANGOUT_EVENT':
                         return event['event_type']+' '+event['hangout_event']['event_type']
                     case 'ADD_USER'|'REMOVE_USER':
-                        return None # TODO
+                        ret = (
+                            event['event_type']+' '+event['membership_change'].pop('type')+' '+event['membership_change'].pop('leave_reason')+' '+
+                            ' '.join(repr(getName(i, conversation['participants'])) for i in event['membership_change'].pop('participant_id'))
+                        )
+                        assert event['membership_change'] == {}
+                        return ret
                     case 'GROUP_LINK_SHARING_MODIFICATION':
                         return None # TODO
                     case 'RENAME_CONVERSATION':

From ecc1f37461ac465ad8e516362e67f69774fabe6f Mon Sep 17 00:00:00 2001
From: j <@>
Date: Sat, 3 Sep 2022 03:33:20 +0000
Subject: [PATCH 13/17] Add GROUP_LINK_SHARING_MODIFICATION text.

---
 HangoutJsonParser.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index 553432b..9e7d7fd 100755
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -47,7 +47,7 @@ def get_readable_content(event):
                         assert event['membership_change'] == {}
                         return ret
                     case 'GROUP_LINK_SHARING_MODIFICATION':
-                        return None # TODO
+                        return event['event_type']+' '+repr( event['group_link_sharing_modification'])
                     case 'RENAME_CONVERSATION':
                         return None # TODO
                     case _: raise Exception('unhandled event type '+event['event_type'])

From 60172b972097af4d3f98881ced46d69df77aff07 Mon Sep 17 00:00:00 2001
From: j <@>
Date: Sat, 3 Sep 2022 03:35:22 +0000
Subject: [PATCH 14/17] Add simple RENAME_CONVERSATION text.

---
 HangoutJsonParser.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index 9e7d7fd..e94e4da 100755
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -49,7 +49,7 @@ def get_readable_content(event):
                     case 'GROUP_LINK_SHARING_MODIFICATION':
                         return event['event_type']+' '+repr( event['group_link_sharing_modification'])
                     case 'RENAME_CONVERSATION':
-                        return None # TODO
+                        return event['event_type']+' '+repr(event['conversation_rename'])
                     case _: raise Exception('unhandled event type '+event['event_type'])
 
             conversation['messages'].append({

From 88dd9e2d315564c29994cad825657544c5d33877 Mon Sep 17 00:00:00 2001
From: j <@>
Date: Sat, 3 Sep 2022 14:13:35 +0000
Subject: [PATCH 15/17] Add some not-so-pretty handling of attachments and
 weird Google+ things, so at least they are not totally lost.

---
 HangoutJsonParser.py | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index e94e4da..f188a7e 100755
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -20,12 +20,11 @@ def parseData():
             def get_readable_content(event):
                 match event['event_type']:
                     case 'REGULAR_CHAT_MESSAGE':
-                        content = None
+                        content = ''
                         # if it's a message(normal hangouts, image...)
                         for msg_k,msg_v in event['chat_message']['message_content'].items():
                             match msg_k:
                                 case 'segment': # if it's a normal hangouts message
-                                    if content == None: content = ''
                                     for segment in msg_v:
                                         match segment['type']:
                                             case 'TEXT'|'LINK':
@@ -34,7 +33,15 @@ def get_readable_content(event):
                                                 content += '\n'
                                             case _: raise segment
                                 case 'attachment':
-                                    pass # TODO
+                                    for att in msg_v:
+                                        match att['embed_item']['type']:
+                                            case ['PLUS_PHOTO']:
+                                                content += ' [attachment '+att['embed_item']['plus_photo']['url']+' ]'
+                                            case ['PLACE_V2', 'THING_V2', 'THING']:
+                                                content += ' [place '+', '.join(k+' '+repr(v) for k,v in att['embed_item']['place_v2'].items())+']'
+                                            case ['DYNAMITE_MESSAGE_METADATA']:
+                                                content += ' [upload_metadata '+repr(att['embed_item']['dynamite_message_metadata'])+']'
+                                            case _: raise Exception('unhandled attachment '+json.dumps(att,indent=4))
                                 case _: raise msg_k
                         return content
                     case 'HANGOUT_EVENT':
@@ -58,7 +65,7 @@ def get_readable_content(event):
                     'id':   event['sender_id']['gaia_id']
                 },
                 'unixtime': int(event['timestamp'])/1000000,
-                **({'content':_} if (_:=get_readable_content(event)) != None else {})
+                'content': get_readable_content(event)
             })
 
         conversation['chatName'] = chatName(orig_conv, conversation['participants'])
@@ -94,4 +101,4 @@ def chatName(orig_conv, participants):
             filename = hashlib.sha256(filename.encode('ascii')).hexdigest()+'.txt'
         with open(os.path.join(args.OUTPUT_DIRECTORY, filename), 'w') as outtext:
             for msg in chat['messages']:
-                outtext.write(datetime.datetime.fromtimestamp(msg['unixtime']).strftime('%Y-%m-%d %H:%M:%S')+' '+msg['sender']['name']+': '+msg.get('content','')+'\n')
+                outtext.write(datetime.datetime.fromtimestamp(msg['unixtime']).strftime('%Y-%m-%d %H:%M:%S')+' '+msg['sender']['name']+': '+msg['content']+'\n')

From 533141f1867cec45a7da55ad42704e3cc85a52f2 Mon Sep 17 00:00:00 2001
From: j <@>
Date: Sat, 3 Sep 2022 14:44:42 +0000
Subject: [PATCH 16/17] Deal with issue in the Hangouts.json, where some
 conversations lack a name for a user. First use the locally defined name if
 available. Fall back to global name, then to no name at all just ID.

---
 HangoutJsonParser.py | 28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index f188a7e..fb6b805 100755
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -2,13 +2,22 @@
 import argparse, datetime, hashlib, json, os
 
 def parseData():
+    global gaia_to_name
+    # First pass just to collect names, to deal with issue in the Hangouts.json, where some conversations lack a name for a user, when others show the name correctly.
+    gaia_to_name = {}
+    for orig_conv in jsonData['conversations']:
+        for participant in orig_conv['conversation']['conversation']['participant_data']:
+            assert participant['id']['gaia_id'] == participant['id']['chat_id']
+            if 'fallback_name' in participant:
+                gaia_to_name[participant['id']['gaia_id']] = participant['fallback_name']
+
     for orig_conv in jsonData['conversations']:
         conversation = {
             'chatName': '',
             'participants': [
                 {
                     'id': participant['id']['gaia_id'],
-                    'name': participant.get('fallback_name', participant['id']['gaia_id'])
+                    'name': participant.get('fallback_name')
                 }
                 for participant in
                 orig_conv['conversation']['conversation']['participant_data']
@@ -49,7 +58,7 @@ def get_readable_content(event):
                     case 'ADD_USER'|'REMOVE_USER':
                         ret = (
                             event['event_type']+' '+event['membership_change'].pop('type')+' '+event['membership_change'].pop('leave_reason')+' '+
-                            ' '.join(repr(getName(i, conversation['participants'])) for i in event['membership_change'].pop('participant_id'))
+                            ' '.join(repr(getName(i['gaia_id'],conversation)) for i in event['membership_change'].pop('participant_id'))
                         )
                         assert event['membership_change'] == {}
                         return ret
@@ -61,7 +70,7 @@ def get_readable_content(event):
 
             conversation['messages'].append({
                 'sender': {
-                    'name': getName(event['sender_id'], conversation['participants']),
+                    'name': getName(event['sender_id']['gaia_id'],conversation),
                     'id':   event['sender_id']['gaia_id']
                 },
                 'unixtime': int(event['timestamp'])/1000000,
@@ -71,12 +80,13 @@ def get_readable_content(event):
         conversation['chatName'] = chatName(orig_conv, conversation['participants'])
         simpleJson.append(conversation)
 
-def getName(user, participants):
-    assert user['gaia_id'] == user['chat_id']
-    for p in participants:
-        if user['gaia_id'] == p['id']:
+def getName(user_id, conversation):
+    global gaia_to_name
+    # First use the locally defined one if available.
+    for p in conversation['participants']:
+        if user_id == p['id'] and p['name'] != None:
             return p['name']
-    return user['gaia_id']
+    return gaia_to_name.get(user_id, user_id) # Fall back to global name, then to no name at all just ID.
 
 def chatName(orig_conv, participants):
     if (('name' in orig_conv['conversation']['conversation']) and (orig_conv['conversation']['conversation']['name'] != "")):
@@ -96,7 +106,7 @@ def chatName(orig_conv, participants):
     parseData()
     json.dump(simpleJson, open(os.path.join(args.OUTPUT_DIRECTORY, 'clean_hangoutsData.json'), 'w', encoding='utf-8'), indent=4)
     for chat in simpleJson:
-        filename = ', '.join(i['name'] for i in chat['participants'])+'.txt'
+        filename = ', '.join(getName(i['id'],chat) for i in chat['participants'])+'.txt'
         if len(filename) > os.statvfs(args.OUTPUT_DIRECTORY).f_namemax:
             filename = hashlib.sha256(filename.encode('ascii')).hexdigest()+'.txt'
         with open(os.path.join(args.OUTPUT_DIRECTORY, filename), 'w') as outtext:

From 56becbcbdcd85215e03859c5e9cc3372695a232d Mon Sep 17 00:00:00 2001
From: j <@>
Date: Sat, 3 Sep 2022 14:57:03 +0000
Subject: [PATCH 17/17] Ensure python3 up front.

---
 HangoutJsonParser.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/HangoutJsonParser.py b/HangoutJsonParser.py
index fb6b805..3375ed5 100755
--- a/HangoutJsonParser.py
+++ b/HangoutJsonParser.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/python3 -Bubb
 import argparse, datetime, hashlib, json, os
 
 def parseData():
@@ -101,10 +101,10 @@ def chatName(orig_conv, participants):
     parser.add_argument('OUTPUT_DIRECTORY', help='Path to write output files.')
     args = parser.parse_args()
 
-    jsonData = json.load(open(args.INPUT_JSON_PATH, 'r', encoding='utf-8'))
+    jsonData = json.load(open(args.INPUT_JSON_PATH, 'r'))
     simpleJson = []
     parseData()
-    json.dump(simpleJson, open(os.path.join(args.OUTPUT_DIRECTORY, 'clean_hangoutsData.json'), 'w', encoding='utf-8'), indent=4)
+    json.dump(simpleJson, open(os.path.join(args.OUTPUT_DIRECTORY, 'clean_hangoutsData.json'), 'w'), indent=4)
     for chat in simpleJson:
         filename = ', '.join(getName(i['id'],chat) for i in chat['participants'])+'.txt'
         if len(filename) > os.statvfs(args.OUTPUT_DIRECTORY).f_namemax: