Project base (no login)

.gitignore

@@ -0,0 +1,87 @@
+# Covers JetBrains IDEs: IntelliJ, GoLand, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# AWS User-specific
+.idea/**/aws.xml
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# SonarLint plugin
+.idea/sonarlint/
+.idea/sonarlint.xml # see https://community.sonarsource.com/t/is-the-file-idea-idea-idea-sonarlint-xml-intended-to-be-under-source-control/121119
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based HTTP Client
+.idea/httpRequests
+http-client.private.env.json
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+# Apifox Helper cache
+.idea/.cache/.Apifox_Helper
+.idea/ApifoxUploaderProjectSetting.xml
+
+# Project specific
+key.json
+venv

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/CaptionProject.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,44 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="31">
+            <item index="0" class="java.lang.String" itemvalue="httpx" />
+            <item index="1" class="java.lang.String" itemvalue="python-dateutil" />
+            <item index="2" class="java.lang.String" itemvalue="python-dotenv" />
+            <item index="3" class="java.lang.String" itemvalue="h11" />
+            <item index="4" class="java.lang.String" itemvalue="MarkupSafe" />
+            <item index="5" class="java.lang.String" itemvalue="requests" />
+            <item index="6" class="java.lang.String" itemvalue="Jinja2" />
+            <item index="7" class="java.lang.String" itemvalue="sniffio" />
+            <item index="8" class="java.lang.String" itemvalue="typing-inspection" />
+            <item index="9" class="java.lang.String" itemvalue="exceptiongroup" />
+            <item index="10" class="java.lang.String" itemvalue="eval_type_backport" />
+            <item index="11" class="java.lang.String" itemvalue="zipp" />
+            <item index="12" class="java.lang.String" itemvalue="certifi" />
+            <item index="13" class="java.lang.String" itemvalue="anyio" />
+            <item index="14" class="java.lang.String" itemvalue="urllib3" />
+            <item index="15" class="java.lang.String" itemvalue="itsdangerous" />
+            <item index="16" class="java.lang.String" itemvalue="Flask" />
+            <item index="17" class="java.lang.String" itemvalue="blinker" />
+            <item index="18" class="java.lang.String" itemvalue="annotated-types" />
+            <item index="19" class="java.lang.String" itemvalue="importlib_metadata" />
+            <item index="20" class="java.lang.String" itemvalue="pydantic" />
+            <item index="21" class="java.lang.String" itemvalue="six" />
+            <item index="22" class="java.lang.String" itemvalue="Werkzeug" />
+            <item index="23" class="java.lang.String" itemvalue="click" />
+            <item index="24" class="java.lang.String" itemvalue="pydantic_core" />
+            <item index="25" class="java.lang.String" itemvalue="colorama" />
+            <item index="26" class="java.lang.String" itemvalue="typing_extensions" />
+            <item index="27" class="java.lang.String" itemvalue="charset-normalizer" />
+            <item index="28" class="java.lang.String" itemvalue="mistralai" />
+            <item index="29" class="java.lang.String" itemvalue="httpcore" />
+            <item index="30" class="java.lang.String" itemvalue="idna" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (CaptionProject)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/CaptionProject.iml" filepath="$PROJECT_DIR$/.idea/CaptionProject.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="" />
+  </component>
+</project>

captions.jsonl

@@ -0,0 +1,5 @@
+{"clean_text": "measure", "start_time": 0.0, "user_id": 11, "signer": 39, "file": "Aj9SDSAOXf4", "end_time": 1.435, "url": "www.youtube.com/watch?v=Aj9SDSAOXf4", "text": "measure"}
+{"clean_text": "apple", "start_time": 1.5, "user_id": 11, "signer": 39, "file": "Aj9SDSAOXf4", "end_time": 1.6, "url": "www.youtube.com/watch?v=Aj9SDSAOXf4", "text": "apple"}
+{"clean_text": "test", "start_time": 0.0, "user_id": 11, "signer": 39, "file": "c2ORbHSQ5pw", "end_time": 1.435, "url": "www.youtube.com/watch?v=c2ORbHSQ5pw", "text": "test"}
+{"clean_text": "aaaaaaaaaa", "start_time": 1.5, "user_id": 11, "signer": 39, "file": "c2ORbHSQ5pw", "end_time": 1.6, "url": "www.youtube.com/watch?v=c2ORbHSQ5pw", "text": "aaaaaaaaaa"}
+{"clean_text": "bbbbbbbb", "start_time": 1.5, "user_id": 11, "signer": 39, "file": "c2ORbHSQ5pw", "end_time": 1.6, "url": "www.youtube.com/watch?v=c2ORbHSQ5pw", "text": "bbbbbbbb"}

captions2.jsonl

@@ -0,0 +1,2 @@
+{"clean_text":"measure","start_time":0.0,"user_id":11,"signer":39,"file":"a1NeXe8bhuo","end_time":1.435,"url":"www.youtube.com\/watch?v=a1NeXe8bhuo","text":"measure"}
+{"clean_text":"apple","start_time":1.5,"user_id":11,"signer":39,"file":"a1NeXe8bhuo","end_time":1.6,"url":"www.youtube.com\/watch?v=a1NeXe8bhuo","text":"apple"}

db_upload.py

@@ -0,0 +1,12 @@
+import firebase_admin
+from firebase_admin import db
+import json
+
+cred_obj = firebase_admin.credentials.Certificate('key.json')
+default_app = firebase_admin.initialize_app(cred_obj, {
+    'databaseURL': "https://video-link-db-default-rtdb.europe-west1.firebasedatabase.app/"
+    })
+videos_ref = db.reference("/Videos")
+with open("videos.json", "r") as f:
+    file_contents = json.load(f)
+videos_ref.set(file_contents)

main.py

@@ -0,0 +1,121 @@
+import gradio as gr
+import pandas as pd
+import re
+import firebase_admin
+from firebase_admin import db
+import hashlib
+import jsonlines
+import json
+
+cred_obj = firebase_admin.credentials.Certificate('key.json')
+default_app = firebase_admin.initialize_app(cred_obj, {
+    'databaseURL': "https://video-link-db-default-rtdb.europe-west1.firebasedatabase.app/"
+    })
+videos_ref = db.reference("/Videos")
+
+with open("captions.jsonl") as file:
+    captions = pd.read_json(file, lines=True)
+
+# videos = ["Aj9SDSAOXf4", "c2ORbHSQ5pw"]
+current_video = 0
+video_links = videos_ref.get()[1:]
+
+css = """
+.container {
+    position: relative;
+    width: 100%;
+    height: 0;
+    padding-bottom: 56.25%;
+}
+.video {
+    position: absolute;
+    top: 0;
+    left: 0;
+    width: 100%;
+    height: 100%;
+}"""
+
+
+def auth_function(username, password):
+    return True
+
+
+def youtube_link_to_id(link):
+    video_id = re.findall("=(.*?)&", link)
+    if len(video_id) == 0:
+        video_id = re.findall("=(.*)", link)
+    return video_id[0]
+
+
+def get_captions(video_id):
+    global captions
+    captions_edit = captions[captions['file'] == video_id]
+    captions_edit = captions_edit[['start_time', 'text', 'end_time']]
+    captions_edit.columns = ["Start", "Text", "End"]
+    return captions_edit
+
+
+def get_next_captions():
+    global current_video, video_links
+    return get_captions(youtube_link_to_id(video_links[current_video]))
+    # global current_video, videos
+    # return get_captions(videos[current_video])
+
+
+def get_youtube_video(video_id):
+    return f"""
+    <div class="container">
+    <iframe src="https://www.youtube.com/embed/{video_id}" frameborder="0" allowfullscreen class="video"></iframe>
+    </div>"""
+
+
+def get_next_youtube_video():
+    global current_video, video_links
+    current_video += 1
+    if current_video == len(video_links):
+        current_video = 0
+    return get_youtube_video(youtube_link_to_id(video_links[current_video]))
+    # global current_video, videos
+    # current_video += 1
+    # if current_video == len(videos):
+    #     current_video = 0
+    # return get_youtube_video(videos[current_video])
+
+
+def refresh_components():
+    next_video = get_next_youtube_video()
+    next_captions = get_next_captions()
+    return next_video, next_captions
+
+
+def save(df):
+    try:
+        global captions
+        captions['start_time'] = df['Start'].apply(lambda x: float(x))
+        captions['text'] = df['Text']
+        captions['end_time'] = df['End'].apply(lambda x: float(x))
+        captions.to_json('captions2.jsonl', orient='records', lines=True)
+        return "Save successful!"
+    except ValueError:
+        return "Save failed: Incorrect input format"
+
+
+with gr.Blocks(css=css) as app:
+    gr.Markdown("## Caption Editor")
+    with gr.Row():
+        with gr.Column():
+            caption_editor = gr.DataFrame(interactive=True,
+                                          value=get_captions(youtube_link_to_id(video_links[current_video])),
+                                          datatype=["number", "str", "number"],
+                                          row_count=(get_captions(youtube_link_to_id(video_links[current_video])).shape[0], "fixed"),
+                                          col_count=(3, "fixed"), column_widths=["20%", "60%", "20%"])
+            save_button = gr.Button("Save")
+            save_result = gr.Markdown()
+        with gr.Column():
+            video_embed = gr.HTML(value=get_youtube_video(youtube_link_to_id(video_links[0])))
+            next_video_button = gr.Button("Next")
+
+    next_video_button.click(fn=refresh_components, outputs=[video_embed, caption_editor])
+    save_button.click(fn=save, inputs=caption_editor, outputs=save_result)
+
+app.launch(auth=auth_function)

videos.json

@@ -0,0 +1,4 @@
+{
+  "1": "www.youtube.com/watch?v=c2ORbHSQ5pw",
+  "2": "www.youtube.com/watch?v=Aj9SDSAOXf4"
+}