kununu · biolds · Jan 3, 2025 · Jan 3, 2025
diff --git a/slackdump2html.py b/slackdump2html.py
@@ -18,13 +18,17 @@ def get_input_file_path() -> str:
     input_file = get_input_file_path()
     data_cleaner = SlackDataCleaner()
 
-    print("Reading slack dump...", flush=True)
+    data_dir = None
+    if input_file.endswith(".json") and os.path.exists(input_file[:-5]):
+        data_dir = input_file[:-5]
+
+    print(f"Reading slack dump...", flush=True)
     reader = SlackDumpReader(data_cleaner)
-    slack_data = reader.read(input_file)
+    slack_data = reader.read(input_file, data_dir)
 
     print("Cleaning data...", flush=True)
     data_cleaner.replace_names(slack_data)
 
     print("Printing output file...", flush=True)
-    html_printer = HtmlPrinter(slack_data)
+    html_printer = HtmlPrinter(slack_data, data_dir)
     html_printer.print()
diff --git a/src/HtmlPrinter.py b/src/HtmlPrinter.py
@@ -1,21 +1,27 @@
 import os
 import re
+import shutil
+import urllib
 from datetime import datetime
+from html import escape
+from pathlib import Path
 
 import emoji
 
 from src.SlackDataCleaner import SlackDataCleaner
-from src.SlackDumpReader import SlackData, SlackMessage, SlackThreadMessage
+from src.SlackDumpReader import SlackData, SlackFile, SlackMessage, SlackThreadMessage
 
 
 class HtmlPrinter:
     slack_data: SlackData
     standard_emojis: dict[str, str] = dict()
     used_custom_emojis: set[str] = set()
     data_cleaner = SlackDataCleaner()
+    data_dir: str | None
 
-    def __init__(self, slack_data: SlackData):
+    def __init__(self, slack_data: SlackData, data_dir: str | None):
         self.slack_data = slack_data
+        self.data_dir = data_dir
 
     def print(self):
         html1 = "<!DOCTYPE html>\n"
@@ -71,6 +77,7 @@ def print_message(self, message: SlackMessage) -> str:
         html += f'                <span class="date">{self.to_time(message.date)}</span>\n'
         html += "            </p>\n"
         html += f'            <p class="message">{self.format_message(message.text)}</p>\n'
+        html += self.print_files(message.files)
         html += self.print_reactions(message.reactions)
         html += self.print_replies(message)
         html += "        </div>\n"
@@ -90,7 +97,7 @@ def calc_color_num(self, user: str) -> int:
             letter_sum += ord(letter)
         return letter_sum % 15
 
-    def format_message(self, text: str) -> str:        
+    def format_message(self, text: str) -> str:
         text = text.replace("<!here>", '<span class="user-mention">here</span>')
         text = text.replace("<!channel>", '<span class="user-mention">channel</span>')
         text = re.sub(r"<(http.*?)\|(.*?)>", self.create_html_url_with_alias, text)
@@ -182,6 +189,27 @@ def print_replies(self, message: SlackMessage) -> str:
             html += "		    </div>\n"
         return html
 
+    def print_files(self, files: list[SlackFile]) -> str:
+        html = ""
+        for file in files:
+            input_filename = f"{self.data_dir}/{file.id}-{file.name}"
+            output_filename = f"{self.slack_data.channel_name}/{file.id}-{file.name}"
+            output_file = Path("out/" + output_filename)
+            output_file.parent.mkdir(parents=True, exist_ok=True)
+            shutil.copyfile(input_filename, f"out/{output_filename}")
+            relative_url = urllib.parse.quote(output_filename)
+
+            if file.mimetype.startswith("image/"):
+                html += f'            <p class="embedded embedded-img"><img src="{relative_url}"></p>\n'
+            elif file.mimetype.startswith("video/"):
+                html += f'            <p class="embedded embedded-video"><video controls><source src="{relative_url}" /></video></p>\n'
+            elif file.mimetype.startswith("audio/"):
+                html += f'            <p class="embedded"><audio controls src="{relative_url}"></p>\n'
+            else:
+                text = escape(file.title)
+                html += f'            <p class="embedded"><a href="{relative_url}" download>Download {text}</a></p>\n'
+        return html
+
     def print_reply(self, reply: SlackThreadMessage) -> str:
         html = '		        <div class="reply">\n'
         html += self.print_user_image(reply.user)
@@ -190,6 +218,7 @@ def print_reply(self, reply: SlackThreadMessage) -> str:
         html += f'		                <span class="date">{self.to_datetime(reply.date)}</span>\n'
         html += "		            </p>\n"
         html += f'		            <p class="message">{self.format_message(reply.text)}</p>\n'
+        html += self.print_files(reply.files)
         html += self.print_reactions(reply.reactions)
         html += "		        </div>\n"
         return html

diff --git a/src/SlackDataCleaner.py b/src/SlackDataCleaner.py
@@ -189,6 +189,8 @@ def _read_channel_file(self):
         for line in lines[1:]:
             line = line.replace("🔒 ", "🔒").strip()
             parts = line.split(" ")
+            if parts[-1] == '(archived)':
+                continue
             self.channel_map[parts[0]] = (ChannelType(parts[-1][0]), parts[-1][1:])
 
     def replace_names(self, slack_data: SlackData):

diff --git a/src/SlackDumpReader.py b/src/SlackDumpReader.py
@@ -6,7 +6,7 @@
 from typing import Tuple
 
 from src.SlackDataCleaner import SlackDataCleaner
-from src.data_structures import SlackData, SlackMessage, SlackThreadMessage, ChannelType
+from src.data_structures import SlackData, SlackFile, SlackMessage, SlackThreadMessage, ChannelType
 
 EMOJI_PATH = "data/emojis/emojis/"
 
@@ -17,22 +17,23 @@ class SlackDumpReader:
     def __init__(self, data_cleaner: SlackDataCleaner):
         self.data_cleaner = data_cleaner
 
-    def read(self, file_path: str) -> SlackData:
+    def read(self, file_path: str, data_dir: str | None) -> SlackData:
         dump_file = open(file_path, encoding="utf-8")
         file_name = Path(file_path).stem
         dump_data = json.load(dump_file)
 
         messages: list[SlackMessage] = list()
 
         for message in dump_data["messages"]:
-            if message["type"] == "message" and "subtype" not in message and "text" in message:
-                replies = self.read_replies(message)
+            if message["type"] == "message" and "subtype" not in message:
+                replies = self.read_replies(message, data_dir)
                 messages.append(
                     SlackMessage(
                         user=self.get_user(message),
                         text=self.get_message_content(message),
                         date=self.to_datetime(message["ts"]),
                         reactions=self.read_reactions(message),
+                        files=self.read_files(message, data_dir),
                         replies=replies,
                     )
                 )
@@ -65,7 +66,7 @@ def get_message_content(self, message: dict) -> str:
         if self.is_gif(message):
             return f'<img src="{message["blocks"][0]["image_url"]}" alt="{message["text"]}">'
         else:
-            return message["text"]
+            return message.get("text", "")
 
     def is_gif(self, message: dict) -> bool:
         return (
@@ -74,7 +75,7 @@ def is_gif(self, message: dict) -> bool:
             and str(message["blocks"][0]["image_url"]).__contains__("giphy.com")
         )
 
-    def read_replies(self, message: dict) -> list[SlackThreadMessage]:
+    def read_replies(self, message: dict, data_dir: str | None) -> list[SlackThreadMessage]:
         replies: list[SlackThreadMessage] = list()
         if "slackdump_thread_replies" in message:
             for reply in message["slackdump_thread_replies"]:
@@ -85,10 +86,31 @@ def read_replies(self, message: dict) -> list[SlackThreadMessage]:
                             text=self.get_message_content(reply),
                             date=self.to_datetime(reply["ts"]),
                             reactions=self.read_reactions(reply),
+                            files=self.read_files(reply, data_dir)
                         )
                     )
         return replies
 
+    def read_files(self, message: dict, data_dir: str | None) -> list[SlackFile]:
+        files: list[SlackFile] = list()
+        if "files" in message and data_dir:
+            for file in message["files"]:
+                if not file["id"] or not file["name"]:
+                    continue
+                data_file = Path(data_dir) / ("%s-%s" % (file["id"], file["name"]))
+                if not data_file.exists():
+                    print(f"missing file {data_file}")
+                    continue
+                files.append(
+                    SlackFile(
+                        id=file["id"],
+                        name=file["name"],
+                        title=file["title"],
+                        mimetype=file["mimetype"],
+                    )
+                )
+        return files
+
     def read_reactions(self, message: dict) -> dict[str, int]:
         reactions: dict[str, int] = dict()
         if "reactions" in message:

diff --git a/src/data_structures.py b/src/data_structures.py
@@ -3,12 +3,20 @@
 from enum import StrEnum
 
 
+@dataclass
+class SlackFile:
+    id: str
+    name: str
+    title: str
+    mimetype: str
+
 @dataclass
 class SlackThreadMessage:
     user: str
     text: str
     date: datetime
     reactions: dict[str, int]
+    files: list[SlackFile]
 
 
 @dataclass
@@ -18,6 +26,7 @@ class SlackMessage:
     date: datetime
     reactions: dict[str, int]
     replies: list[SlackThreadMessage]
+    files: list[SlackFile]
 
 
 class ChannelType(StrEnum):

diff --git a/src/style/style.css b/src/style/style.css
@@ -226,6 +226,20 @@ h1 {
 	max-width: 1.1em;
 }
 
+.embedded {
+    margin-left: 3.5em;
+}
+
+.embedded-img > img {
+    max-height: 35vh;
+    max-width: 100vh;
+}
+
+.embedded-video > video {
+    max-height: 35vh;
+    max-width: 100vh;
+}
+
 code {
     background-color: #efefef;
     border: 1px solid #d4d4d4;