Feat/webapp (#16)

feat: webapp using streamlit --------- Signed-off-by: Frost Ming <[email protected]> Co-authored-by: yihong <[email protected]>
yihong0618 · Jan 4, 2024 · 8235a03 · 8235a03
1 parent d177558
commit 8235a03
Show file tree

Hide file tree

Showing 8 changed files with 1,229 additions and 15 deletions.
diff --git a/README.md b/README.md
@@ -11,7 +11,22 @@ git clone https://github.com/yihong0618/epubhv.git
 cd epubhv && bash ./setup.sh
 ```
 
-## Use
+## Using pipx
+
+If you are using [pipx](https://pypi.org/project/pipx/), you can directly run `epubhv` with:
+
+```console
+pipx run epubhv a.epub
+```
+
+## Use the web
+
+```console
+pip install epubhv[web]
+streamlit run web.py
+```
+
+## Use CLI
 
 ```console
 epubhv a.epub # will generate a file a-v.epub that is vertical
@@ -29,13 +44,13 @@ epubhv tests/test_epub # will generate all epub files to epub-v
 
 # you can specify the punctuation style
 epubhv e.epub --convert s2t --punctuation auto
-# you can add `ruby` for Japanese(furigana) and Chinese(pinyin) 
+# you can add `ruby` for Japanese(furigana) and Chinese(pinyin)
 epubhv e.epub --h --ruby
 # if you want to learn `cantonese` 粤语
 epubhv f.epub --h --ruby --cantonese
 ```
 
-**About [cantonese](https://jyutping.org/docs/cantonese/)** 
+**About [cantonese](https://jyutping.org/docs/cantonese/)**
 
 ## Contribution
 

diff --git a/epubhv/__init__.py b/epubhv/__init__.py
@@ -0,0 +1 @@
+from .epubhv import EPUBHV as EPUBHV
diff --git a/epubhv/cli.py b/epubhv/cli.py
@@ -56,7 +56,7 @@ def main() -> None:
     parser.add_argument(
         "--punctuation",
         dest="punctuation",
-        choices=["auto", "t2s", "s2t", "s2s", "t2t", "none"],
+        choices=["auto", "t2s", "s2t", "none"],
         default="auto",
         help="""convert punctuation to specific locale and direction (default: auto)
 

diff --git a/epubhv/epubhv.py b/epubhv/epubhv.py
@@ -378,7 +378,7 @@ def convert(self, method: str = "to_vertical") -> None:
                 with open(html_file, "w", encoding="utf-8") as file:
                     file.write(ruby_soup.prettify())
 
-    def pack(self, method: str = "to_vertical", dest: Path = Path.cwd()) -> None:
+    def pack(self, method: str = "to_vertical", dest: Path = Path.cwd()) -> Path:
         lang = "original"
         if self.convert_to is not None:
             lang = self.convert_to
@@ -395,8 +395,9 @@ def pack(self, method: str = "to_vertical", dest: Path = Path.cwd()) -> None:
         )
         os.rename(src=f"{pack_to}.zip", dst=pack_to)
         shutil.rmtree(self.book_path)
+        return pack_to
 
-    def run(self, method: str = "to_vertical", dest: Path = Path.cwd()) -> None:
+    def run(self, method: str = "to_vertical", dest: Path = Path.cwd()) -> Path:
         assert method in [
             "to_horizontal",
             "to_vertical",
@@ -411,4 +412,4 @@ def run(self, method: str = "to_vertical", dest: Path = Path.cwd()) -> None:
             raise Exception("Only support epub to vertical or horizontal for now")
 
         self.convert(method=method)
-        self.pack(method=method, dest=dest)
+        return self.pack(method=method, dest=dest)
diff --git a/pdm.lock b/pdm.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -19,7 +19,7 @@ dependencies = [
     "ToJyutping",
 ]
 
-requires-python = ">=3.8"
+requires-python = ">=3.8,!=3.9.7"
 readme = "README.md"
 license = { text = "MIT" }
 
@@ -28,6 +28,11 @@ Homepage = "https://github.com/yihong0618/epubhv"
 
 [project.scripts]
 epubhv = "epubhv.cli:main"
+
+[project.optional-dependencies]
+web = [
+    "streamlit>=1.29.0",
+]
 [build-system]
 requires = ["pdm-backend"]
 build-backend = "pdm.backend"

diff --git a/requirements.txt b/requirements.txt
@@ -0,0 +1,68 @@
+# This file is @generated by PDM.
+# Please do not edit it manually.
+
+altair==5.2.0
+attrs==23.2.0
+backports-zoneinfo==0.2.1; python_version < "3.9"
+beautifulsoup4==4.12.2
+blinker==1.7.0
+cachetools==5.3.2
+certifi==2023.11.17
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6; sys_platform == "win32" or platform_system == "Windows"
+cssutils==2.7.1
+docstring-parser==0.15
+fugashi==1.3.0
+gitdb==4.0.11
+gitpython==3.1.40
+idna==3.6
+importlib-metadata==6.11.0
+importlib-resources==6.1.1; python_version < "3.9"
+jieba==0.42.1
+jinja2==3.1.2
+jsonschema==4.20.0
+jsonschema-specifications==2023.12.1
+langdetect==1.0.9
+lxml==4.9.3
+markdown-it-py==3.0.0
+markupsafe==2.1.3
+mdurl==0.1.2
+mypy-extensions==1.0.0
+numpy==1.24.4
+opencc-python-reimplemented==0.1.7
+packaging==23.2
+pandas==2.0.3
+pillow==10.2.0
+pkgutil-resolve-name==1.3.10; python_version < "3.9"
+protobuf==4.25.1
+pyarrow==14.0.2
+pydeck==0.8.1b0
+pygments==2.17.2
+pygtrie==2.5.0
+pypinyin==0.50.0
+python-dateutil==2.8.2
+pytz==2023.3.post1
+referencing==0.32.0
+requests==2.31.0
+rich==13.7.0
+rpds-py==0.16.2
+six==1.16.0
+smmap==5.0.1
+soupsieve==2.5
+streamlit==1.29.0
+tenacity==8.2.3
+tojyutping==0.2.3
+toml==0.10.2
+toolz==0.12.0
+tornado==6.4
+typed-argument-parser==1.8.1
+typing-extensions==4.9.0
+typing-inspect==0.9.0
+tzdata==2023.4
+tzlocal==5.2
+unidic-lite==1.0.8
+urllib3==2.1.0
+validators==0.22.0
+watchdog==3.0.0; platform_system != "Darwin"
+zipp==3.17.0
diff --git a/web.py b/web.py
@@ -0,0 +1,120 @@
+import base64
+import tempfile
+from pathlib import Path
+
+import streamlit as st
+import streamlit.components.v1 as components
+
+from epubhv import EPUBHV
+
+LABELS = {
+    "none": "None",
+    "auto": "Auto",
+    "s2t": "Simplified Chinese to Traditional Chinese",
+    "t2s": "Traditional Chinese to Simplified Chinese",
+    "s2tw": "Simplified Chinese to Traditional Chinese (Taiwan Standard)",
+    "tw2s": "Traditional Chinese (Taiwan Standard) to Simplified Chinese",
+    "s2hk": "Simplified Chinese to Traditional Chinese (Hong Kong variant)",
+    "hk2s": "Traditional Chinese (Hong Kong variant) to Simplified Chinese",
+    "s2twp": "Simplified Chinese to Traditional Chinese (Taiwan variant)",
+    "tw2sp": "Traditional Chinese (Taiwan variant) to Simplified Chinese",
+    "t2tw": "Traditional Chinese (OpenCC Standard) to Taiwan Standard",
+    "hk2t": "Traditional Chinese (Hong Kong variant) to Traditional Chinese",
+    "t2hk": "Traditional Chinese (OpenCC Standard) to Hong Kong variant",
+    "t2jp": "Traditional Chinese Characters (Kyūjitai) to New Japanese Kanji",
+    "jp2t": "New Japanese Kanji to Traditional Chinese Characters (Kyūjitai)",
+    "tw2t": "Traditional Chinese (OpenCC Standard) to Traditional Chinese (Taiwan standard)",
+}
+
+
+def download_button(data: bytes, download_filename: str) -> None:
+    b64 = base64.b64encode(data).decode()
+
+    dl_link = f"""
+    <html>
+    <head>
+    <title>Start Auto Download file</title>
+    <script src="http://code.jquery.com/jquery-3.2.1.min.js"></script>
+    <script>
+    $('<a href="data:text/csv;base64,{b64}" download="{download_filename}">')[0].click()
+    </script>
+    </head>
+    </html>
+    """
+    components.html(dl_link, height=0)
+
+
+st.set_page_config(
+    page_title="EPUBHV, a toolset to convert your EPUB",
+    page_icon="📖",
+    layout="centered",
+    initial_sidebar_state="auto",
+    menu_items=None,
+)
+st.header("📖 EPUBHV, a toolset to convert your EPUB", divider="rainbow")
+st.caption(
+    "Author: [@yihong0618](https://github.com/yihong0618) | [GitHub](https://github.com/yihong0618/epubhv) | [PyPI](https://pypi.org/project/epubhv/)",
+)
+
+
+def run():
+    if st.session_state["epubfile"] is None:
+        st.error("Please upload an epub file")
+        return
+    epubfile = st.session_state["epubfile"]
+    with tempfile.TemporaryDirectory() as tmpdir, st.spinner("Processing..."):
+        with open(Path(tmpdir) / epubfile.name, "wb") as f:
+            f.write(epubfile.read())
+        convert = st.session_state["convert"]
+        epubhv = EPUBHV(
+            file_path=Path(tmpdir) / epubfile.name,
+            need_ruby=st.session_state["need_ruby"],
+            need_cantonese=st.session_state["need_cantonese"],
+            convert_to=None if convert == "none" else convert,
+            convert_punctuation=st.session_state["punctuation"],
+        )
+        result = epubhv.run(method=st.session_state["method"], dest=Path(tmpdir))
+        download_button(result.read_bytes(), result.name)
+
+
+with st.form(key="my_form"):
+    epubfile = st.file_uploader("Upload an epub file", type="epub", key="epubfile")
+    method = st.radio(
+        "Choose a method",
+        ("to_vertical", "to_horizontal"),
+        format_func=lambda x: x.replace("_", " ").title(),
+        horizontal=True,
+        key="method",
+    )
+    need_ruby = st.checkbox("Need ruby", key="need_ruby")
+    need_cantonese = st.checkbox("Need cantonese", key="need_cantonese")
+
+    convert = st.selectbox(
+        "Transform text",
+        options=[
+            "none",
+            "s2t",
+            "t2s",
+            "s2tw",
+            "tw2s",
+            "s2hk",
+            "hk2s",
+            "s2twp",
+            "tw2sp",
+            "t2tw",
+            "hk2t",
+            "t2hk",
+            "t2jp",
+            "jp2t",
+            "tw2t",
+        ],
+        format_func=LABELS.__getitem__,
+        key="convert",
+    )
+    punctuation = st.selectbox(
+        "Transform punctuation",
+        options=["auto", "t2s", "s2t", "none"],
+        format_func=LABELS.__getitem__,
+        key="punctuation",
+    )
+    st.form_submit_button(label="Transform", on_click=run)