comic-ocr-reader 0.0.2__tar.gz

comic_ocr_reader-0.0.2/.gitignore

@@ -0,0 +1,95 @@
+# 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/
+# see https://community.sonarsource.com/t/is-the-file-idea-idea-idea-sonarlint-xml-intended-to-be-under-source-control/121119
+.idea/sonarlint.xml
+
+# 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
+
+# Github Copilot persisted session migrations, see: https://github.com/microsoft/copilot-intellij-feedback/issues/712#issuecomment-3322062215
+.idea/**/copilot.data.migration.*.xml
+
+# ------------------------------------------------------
+/src/test-pics
+/src/outputs
+/test-pics
+/outputs
+/temporary
+/dist

comic_ocr_reader-0.0.2/.idea/comic-ocr.iml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module version="4">
+  <component name="PyDocumentationSettings">
+    <option name="format" value="GOOGLE" />
+    <option name="myDocStringFormat" value="Google" />
+  </component>
+</module>

comic_ocr_reader-0.0.2/.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,40 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="HtmlUnknownTag" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="myValues">
+        <value>
+          <list size="7">
+            <item index="0" class="java.lang.String" itemvalue="nobr" />
+            <item index="1" class="java.lang.String" itemvalue="noembed" />
+            <item index="2" class="java.lang.String" itemvalue="comment" />
+            <item index="3" class="java.lang.String" itemvalue="noscript" />
+            <item index="4" class="java.lang.String" itemvalue="embed" />
+            <item index="5" class="java.lang.String" itemvalue="script" />
+            <item index="6" class="java.lang.String" itemvalue="div" />
+          </list>
+        </value>
+      </option>
+      <option name="myCustomValuesEnabled" value="true" />
+    </inspection_tool>
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <list>
+          <option value="typing_extensions" />
+          <option value="cffi" />
+          <option value="attrs" />
+          <option value="beautifulsoup4" />
+          <option value="soupsieve" />
+          <option value="google" />
+        </list>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyPep8NamingInspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <option name="ignoredErrors">
+        <list>
+          <option value="N812" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

comic_ocr_reader-0.0.2/.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>

comic_ocr_reader-0.0.2/.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.14 (comic-ocr) (2)" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.14 (comic-ocr)" project-jdk-type="Python SDK" />
+</project>

comic_ocr_reader-0.0.2/.idea/vcs.xml

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

comic_ocr_reader-0.0.2/LICENSE.MD

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Haganta R. Ginting
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

comic_ocr_reader-0.0.2/LICENSE.md

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Haganta R. Ginting
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

comic_ocr_reader-0.0.2/PKG-INFO

@@ -0,0 +1,56 @@
+Metadata-Version: 2.4
+Name: comic_ocr_reader
+Version: 0.0.2
+Summary: A Python package made for processing Japanese manga into a format usable with web-based on-screen dictionaries like Yomitan.
+Project-URL: Homepage, https://github.com/HagantaRG/comic-ocr
+Author-email: HRG <rhaganta@gmail.com>
+License-Expression: MIT
+License-File: LICENSE.MD
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.9
+Requires-Dist: easyocr~=1.7.2
+Requires-Dist: loguru
+Requires-Dist: manga-ocr
+Requires-Dist: numpy~=2.5.1
+Requires-Dist: pillow~=12.3.0
+Requires-Dist: tqdm
+Description-Content-Type: text/markdown
+
+# Jelly's Manga Reading Thingy.
+This is my own rendition of the excellent [Mokuro](https://github.com/kha-white/mokuro) project, made mostly just to do it.
+That being said, if you have any suggestions, please give me a heads-up and I will be happy to implement it. Probably.
+
+## Usage
+1. Prepare a folder containing the images you would like to process. As of v.0.0.1 the images in this folder must be named the page number you would like that image to be.
+   (e.g. the PNG image you would like to use as the second page should be titled "2.png")
+   The name of the folder will be the name of the resultant HTML file. (e.g. if your folder is titled "Naruto" the output HTML file will be "Naruto.html" )
+2. Run comic-reader-ocr and enter the "folder" command.
+3. Enter the absolute path of the folder from step 1 and wait for comic-reader-ocr to process all the images.
+4. Once finished, the resulting HTML file will be placed in an outputs folder within the folder from step 1.
+5. Open the resulting HTML using your web browser of choice.
+
+## FAQs (as decided by Myself)
+1. Is this a worse version of various other projects (e.g. [Mokuro](https://github.com/kha-white/mokuro))?
+
+   - Yes.
+
+2. Do you know how to like. Write things. That work?
+
+   - No.
+
+3. Why did you do this?
+
+   - As a learning exercise, mostly. Plus, I like trying to reinvent wheels.
+
+4. Can I make suggestions?
+
+   - Yes. 
+
+5. Did you use AI for this?
+
+   - Yes. Most of the HTML and JS was AI generated, as unfortunately I really *really* don't like looking at either of those things.
+
+6. Are you going to try to make this a webapp because that probably makes a lot of sense or just. Like. Something that isn't Python so that it's easier to distribute or something?
+
+   - Yes. I'll probably try to rewrite this in Rust or do something like the [mokuro-reader](https://github.com/Gnathonic/mokuro-reader) project.

comic_ocr_reader-0.0.2/README.md

@@ -0,0 +1,37 @@
+# Jelly's Manga Reading Thingy.
+This is my own rendition of the excellent [Mokuro](https://github.com/kha-white/mokuro) project, made mostly just to do it.
+That being said, if you have any suggestions, please give me a heads-up and I will be happy to implement it. Probably.
+
+## Usage
+1. Prepare a folder containing the images you would like to process. As of v.0.0.1 the images in this folder must be named the page number you would like that image to be.
+   (e.g. the PNG image you would like to use as the second page should be titled "2.png")
+   The name of the folder will be the name of the resultant HTML file. (e.g. if your folder is titled "Naruto" the output HTML file will be "Naruto.html" )
+2. Run comic-reader-ocr and enter the "folder" command.
+3. Enter the absolute path of the folder from step 1 and wait for comic-reader-ocr to process all the images.
+4. Once finished, the resulting HTML file will be placed in an outputs folder within the folder from step 1.
+5. Open the resulting HTML using your web browser of choice.
+
+## FAQs (as decided by Myself)
+1. Is this a worse version of various other projects (e.g. [Mokuro](https://github.com/kha-white/mokuro))?
+
+   - Yes.
+
+2. Do you know how to like. Write things. That work?
+
+   - No.
+
+3. Why did you do this?
+
+   - As a learning exercise, mostly. Plus, I like trying to reinvent wheels.
+
+4. Can I make suggestions?
+
+   - Yes. 
+
+5. Did you use AI for this?
+
+   - Yes. Most of the HTML and JS was AI generated, as unfortunately I really *really* don't like looking at either of those things.
+
+6. Are you going to try to make this a webapp because that probably makes a lot of sense or just. Like. Something that isn't Python so that it's easier to distribute or something?
+
+   - Yes. I'll probably try to rewrite this in Rust or do something like the [mokuro-reader](https://github.com/Gnathonic/mokuro-reader) project.

comic_ocr_reader-0.0.2/pyproject.toml

@@ -0,0 +1,30 @@
+[build-system]
+requires = ["hatchling >= 1.26"]
+build-backend = "hatchling.build"
+
+[project]
+name = "comic_ocr_reader"
+version = "0.0.2"
+authors = [
+  { name="HRG", email="rhaganta@gmail.com" },
+]
+description = "A Python package made for processing Japanese manga into a format usable with web-based on-screen dictionaries like Yomitan."
+readme = "README.md"
+requires-python = ">=3.9"
+dependencies = [
+  "easyocr~=1.7.2",
+  "pillow~=12.3.0",
+  "numpy~=2.5.1",
+  "manga-ocr",
+  "tqdm",
+  "loguru",
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+]
+license = "MIT"
+license-files = ["LICENSE.MD"]
+
+[project.urls]
+Homepage = "https://github.com/HagantaRG/comic-ocr"

comic_ocr_reader-0.0.2/readme.md

@@ -0,0 +1,37 @@
+# Jelly's Manga Reading Thingy.
+This is my own rendition of the excellent [Mokuro](https://github.com/kha-white/mokuro) project, made mostly just to do it.
+That being said, if you have any suggestions, please give me a heads-up and I will be happy to implement it. Probably.
+
+## Usage
+1. Prepare a folder containing the images you would like to process. As of v.0.0.1 the images in this folder must be named the page number you would like that image to be.
+   (e.g. the PNG image you would like to use as the second page should be titled "2.png")
+   The name of the folder will be the name of the resultant HTML file. (e.g. if your folder is titled "Naruto" the output HTML file will be "Naruto.html" )
+2. Run comic-reader-ocr and enter the "folder" command.
+3. Enter the absolute path of the folder from step 1 and wait for comic-reader-ocr to process all the images.
+4. Once finished, the resulting HTML file will be placed in an outputs folder within the folder from step 1.
+5. Open the resulting HTML using your web browser of choice.
+
+## FAQs (as decided by Myself)
+1. Is this a worse version of various other projects (e.g. [Mokuro](https://github.com/kha-white/mokuro))?
+
+   - Yes.
+
+2. Do you know how to like. Write things. That work?
+
+   - No.
+
+3. Why did you do this?
+
+   - As a learning exercise, mostly. Plus, I like trying to reinvent wheels.
+
+4. Can I make suggestions?
+
+   - Yes. 
+
+5. Did you use AI for this?
+
+   - Yes. Most of the HTML and JS was AI generated, as unfortunately I really *really* don't like looking at either of those things.
+
+6. Are you going to try to make this a webapp because that probably makes a lot of sense or just. Like. Something that isn't Python so that it's easier to distribute or something?
+
+   - Yes. I'll probably try to rewrite this in Rust or do something like the [mokuro-reader](https://github.com/Gnathonic/mokuro-reader) project.

comic_ocr_reader-0.0.2/requirements.txt

@@ -0,0 +1,4 @@
+easyocr~=1.7.2
+pillow~=12.3.0
+numpy~=2.5.1
+manga-ocr

comic_ocr_reader-0.0.2/src/comic_ocr_reader/filepaths.py

@@ -0,0 +1,3 @@
+from pathlib import Path
+
+PROJECT_FOLDER: Path = Path(__file__).parent.parent

comic_ocr_reader-0.0.2/src/comic_ocr_reader/functions/__init__.py

@@ -0,0 +1,58 @@
+from datetime import datetime
+from pathlib import Path
+
+from PIL import Image
+from easyocr import Reader
+from manga_ocr import MangaOcr
+
+from comic_ocr_reader.html_utils import Textbox, Page
+from comic_ocr_reader.img_utils import merge_textboxes_easyocr
+
+def process_page(
+        manga: dict[int, Page],
+        filepath: Path,
+        detector: Reader,
+        recogniser: MangaOcr,
+        page_num: int
+) -> None:
+
+    result = detector.detect(str(filepath))
+    with Image.open(filepath) as img:
+        textboxes: list[Textbox] = []
+        width, height = img.size
+
+        count: int = 0
+        page: Page = Page(
+            img_filepath=f"{filepath.stem}{filepath.suffix}",
+            page_num=page_num,
+            page_class="page"
+        )
+        merged_regions: list[list[int]] = merge_textboxes_easyocr(
+            result[0][0],
+            padding=1
+        )
+        for item in merged_regions:
+            count += 1
+            nums: list[int] = []
+            for np_num in item:
+                nums.append(int(np_num))
+
+            box_width: int = nums[1] - nums[0]
+            box_height: int = nums[3] - nums[2]
+            percent_width: int = round(box_width / width * 100)
+            percent_height: int = round(box_height / height * 100)
+
+            region = img.crop((nums[0], nums[2], nums[1], nums[3]))
+            start = datetime.now()
+            text: str = recogniser(region)
+            end = datetime.now()
+            textbox: Textbox = Textbox(
+                top=round(nums[2] / height * 100),
+                left=round(nums[0] / width * 100),
+                height=int(percent_height),
+                width=int(percent_width),
+                text=text
+            )
+            textboxes.append(textbox)
+            page.textboxes = textboxes
+        manga[page_num] = page

comic_ocr_reader-0.0.2/src/comic_ocr_reader/html_utils/__init__.py

@@ -0,0 +1,111 @@
+from pathlib import Path
+
+HTML_UTILS_FOLDER: Path = Path(__file__).parent
+class Textbox:
+    """Class containing details of the textbox on a page
+    Attributes:
+        top     %-age of page down from top of page to place textbox.
+        left    %-age of page right from left of page to place textbox.
+        width   %-age width of textbox in terms of containing page.
+        height  %-age height of textbox in terms of containing page.
+    """
+    top: int
+    left: int
+    width: int
+    height: int
+    text: str
+    btn_class: str
+    def __init__(
+            self,
+            top: int,
+            left: int,
+            width: int,
+            height: int,
+            text: str
+    ) -> None:
+        self.top = top
+        self.left = left
+        self.width = width
+        self.height = height
+        self.text = text
+
+class Page:
+    textboxes: list[Textbox] = []
+    img_filepath: Path
+    page_num: int
+    page_html: str
+    page_class: str
+
+    def __init__(
+            self,
+            img_filepath: Path|str,
+            page_num: int,
+            page_class: str
+    ):
+        self.img_filepath = img_filepath
+        self.page_num = page_num
+        self.page_class = page_class
+
+    def make_page_html(self) -> None:
+        """
+        Constructs the HTML of a page, shoves it into the page_html attribute of this object.
+        :return:
+        """
+        page_html: str = f"""
+        <div class="{self.page_class}" id="page{self.page_num}">
+        <button class="page-nav prev" onclick="lastPage()">Prev. Page</button>
+        <button class="page-nav next" onclick="nextPage()">Next Page</button>
+        <div class="zoom-hint">Ctrl + wheel to zoom</div>
+        <div class="page-content">
+        <div class="page-content-inner">
+        <img src="{self.img_filepath}" alt="Snow">
+        """
+        for textbox in self.textboxes:
+            page_html += f"""
+            <button class="text-btn"
+                    style="--top:{textbox.top}%;--left:{textbox.left}%;--height:{textbox.height}%;--width:{textbox.width}%;">
+                <span>{textbox.text}</span>
+            </button>
+            """
+        page_html+="""
+        </div>
+        </div>
+        </div>
+        """
+        self.page_html = page_html
+
+    def set_page_class(self, page_class: str):
+        self.page_class = page_class
+
+
+def make_html_file(
+        pages: dict[int, Page],
+        template: str|Path = f"{HTML_UTILS_FOLDER}/html_template.html"
+) -> str:
+    html_body: str = ""
+    for i in range(1, len(pages.keys())+1):
+        if (i - 1) % 2 == 0:
+            html_body += """
+            <div class="spread">
+            <button class="spread-nav prev" onclick="lastPage()">Prev. Page</button>
+            <button class="spread-nav next" onclick="nextPage()">Next Page</button>
+            <div class="spread-hint">Ctrl + wheel to zoom</div>
+            <div class="spread-scroll">
+            <div class="spread-content">
+            """
+        if i == len(pages):
+            pages[i].set_page_class("page last")
+        elif i == 1:
+            pages[i].set_page_class("page first")
+        pages[i].make_page_html()
+        html_body += pages[i].page_html
+        if (i - 1) % 2 == 1 or i == len(pages):
+            html_body += """
+            </div>
+            </div>
+            </div>
+            """
+    with open(template, "r", encoding="utf-8") as html_template:
+        template: str = html_template.read()
+        template = template.replace("{{BODY}}", html_body)
+    return template