epub-translator 0.0.6__py3-none-any.whl → 0.1.0__py3-none-any.whl

epub_translator/xml/tag.py

@@ -1,93 +0,0 @@
-from io import StringIO
-from enum import auto, Enum
-from typing import Generator
-from dataclasses import dataclass
-
-
-class TagKind(Enum):
-  OPENING = auto()
-  CLOSING = auto()
-  SELF_CLOSING = auto()
-
-@dataclass
-class Tag:
-  kind: TagKind
-  name: str
-  proto: str
-  attributes: list[tuple[str, str]]
-
-  def __str__(self):
-    buffer = StringIO()
-    buffer.write("<")
-    if self.kind == TagKind.CLOSING:
-      buffer.write("/")
-    buffer.write(self.name)
-    if len(self.attributes) > 0:
-      buffer.write(" ")
-      for i, (attr_name, attr_value) in enumerate(self.attributes):
-        buffer.write(attr_name)
-        buffer.write("=")
-        buffer.write("\"")
-        buffer.write(attr_value)
-        buffer.write("\"")
-        if i < len(self.attributes) - 1:
-          buffer.write(" ")
-    if self.kind == TagKind.SELF_CLOSING:
-      buffer.write("/>")
-    else:
-      buffer.write(">")
-    return buffer.getvalue()
-
-  def find_invalid_name(self) -> str | None:
-    for name in self._iter_tag_names():
-      if not all(is_valid_value_char(c) for c in name):
-        return name
-      # https://www.w3schools.com/xml/xml_elements.asp
-      # The following logic enforces a subset of XML naming rules:
-      # - Names must not be empty.
-      # - Names must start with a letter (a-z, A-Z) or an underscore (_).
-      if name == "":
-        return name
-      char = name[0]
-      if char == "_":
-        continue
-      if "a" <= char <= "z" or "A" <= char <= "Z":
-        continue
-      return name
-
-    return None
-
-  def find_invalid_attr_value(self) -> tuple[str, str] | None:
-    for attr_name, attr_value in self.attributes:
-      if not all(is_valid_value_char(c) for c in attr_value):
-        return attr_name, attr_value
-    return None
-
-  def _iter_tag_names(self) -> Generator[str, None, None]:
-    yield self.name
-    for attr_name, _ in self.attributes:
-      yield attr_name
-
-def is_valid_value_char(char: str) -> bool:
-  if is_valid_name_char(char):
-    return True
-  if char == ",":
-    return True
-  if char == ".":
-    return True
-  if char == "/":
-    return True
-  return False
-
-def is_valid_name_char(char: str) -> bool:
-  if "a" <= char <= "z":
-    return True
-  if "A" <= char <= "Z":
-    return True
-  if "0" <= char <= "9":
-    return True
-  if char == "_":
-    return True
-  if char == "-":
-    return True
-  return False

epub_translator/xml/transform.py

@@ -1,34 +0,0 @@
-from xml.etree.ElementTree import Element
-from .tag import Tag, TagKind
-
-
-def tag_to_element(tag: Tag) -> Element:
-  element = Element(tag.name)
-  for attr_name, attr_value in tag.attributes:
-    element.set(attr_name, attr_value)
-  return element
-
-def element_to_tag(element: Element, kind: TagKind, proto: str = "") -> Tag:
-  tag = Tag(
-    kind=kind,
-    name=element.tag,
-    proto=proto,
-    attributes=[],
-  )
-  if kind != TagKind.CLOSING:
-    for attr_name in sorted(list(element.keys())):
-      attr_value = element.get(attr_name, "")
-      tag.attributes.append((attr_name, attr_value))
-
-  # To make LLM easier to understand, the naming here is restricted in a more strict way.
-  # https://github.com/oomol-lab/pdf-craft/issues/149
-  invalid_name = tag.find_invalid_name()
-  if invalid_name is not None:
-    raise ValueError(f"find invalid tag name or attribute name: {invalid_name}")
-
-  invalid_attr_pair = tag.find_invalid_attr_value()
-  if invalid_attr_pair is not None:
-    attr_name, attr_value = invalid_attr_pair
-    raise ValueError(f"find invalid attribute value: {attr_name}=\"{attr_value}\"")
-
-  return tag

epub_translator/xml/utils.py

@@ -1,12 +0,0 @@
-from xml.etree.ElementTree import Element
-
-def clone(element: Element) -> Element:
-  new_element = Element(element.tag)
-  for attr_name, attr_value in element.items():
-    new_element.set(attr_name, attr_value)
-  new_element.text = element.text
-  for child in element:
-    new_child = clone(child)
-    new_element.append(new_child)
-    new_child.tail = child.tail
-  return new_element

epub_translator/zip_context.py

@@ -1,74 +0,0 @@
-import zipfile
-
-from typing import Generator, Callable
-from pathlib import Path
-from lxml.etree import parse
-from .epub import EpubContent, HTMLFile
-
-
-class ZipContext:
-  def __init__(self, epub_path: Path, temp_dir: Path):
-    with zipfile.ZipFile(epub_path, "r") as zip_ref:
-      for member in zip_ref.namelist():
-        target_path = temp_dir / member
-        if member.endswith("/"):
-          target_path.mkdir(parents=True, exist_ok=True)
-        else:
-          target_path.parent.mkdir(parents=True, exist_ok=True)
-          with zip_ref.open(member) as source:
-            with open(target_path, "wb") as file:
-              file.write(source.read())
-
-    self._temp_dir: Path = temp_dir
-    self._epub_content: EpubContent = EpubContent(str(temp_dir))
-
-  def archive(self, saved_path: Path):
-    with zipfile.ZipFile(saved_path, "w") as zip_file:
-      for file_path in self._temp_dir.rglob("*"):
-        if not file_path.is_file():
-          continue
-        relative_path = file_path.relative_to(self._temp_dir)
-        zip_file.write(
-          filename=file_path,
-          arcname=str(relative_path),
-        )
-
-  def search_spine_paths(self) -> Generator[Path, None, None]:
-    for spine in self._epub_content.spines:
-      if spine.media_type == "application/xhtml+xml":
-        yield Path(spine.path)
-
-  def read_spine_file(self, spine_path: Path) -> HTMLFile:
-    with open(spine_path, "r", encoding="utf-8") as file:
-      return HTMLFile(file.read())
-
-  def write_spine_file(self, spine_path: Path, file: HTMLFile):
-    with open(spine_path, "w", encoding="utf-8") as f:
-      f.write(file.file_content)
-
-  def replace_ncx(self, replace: Callable[[list[str]], list[str]]):
-    ncx_path = self._epub_content.ncx_path
-    if ncx_path is None:
-      return
-
-    tree = parse(ncx_path)
-    root = tree.getroot()
-    namespaces={ "ns": root.nsmap.get(None) }
-    text_doms = []
-    text_list = []
-
-    for text_dom in root.xpath("//ns:text", namespaces=namespaces):
-      text_doms.append(text_dom)
-      text_list.append(text_dom.text or "")
-
-    for index, text in enumerate(replace(text_list)):
-      text_dom = text_doms[index]
-      text_dom.text = self._link_translated(text_dom.text, text)
-
-    tree.write(ncx_path, pretty_print=True)
-
-  def _link_translated(self, origin: str, target: str) -> str:
-    if origin == target:
-      return origin
-    else:
-      return f"{origin} - {target}"

epub_translator-0.0.6.dist-info/METADATA

@@ -1,170 +0,0 @@
-Metadata-Version: 2.3
-Name: epub-translator
-Version: 0.0.6
-Summary: Translate the epub book using LLM. The translated book will retain the original text and list the translated text side by side with the original text.
-License: MIT
-Keywords: epub,llm,translation,translator
-Author: Tao Zeyu
-Author-email: i@taozeyu.com
-Maintainer: Tao Zeyu
-Maintainer-email: i@taozeyu.com
-Requires-Python: >=3.10,<3.13
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Requires-Dist: jinja2 (>=3.1.5,<4.0.0)
-Requires-Dist: langchain[openai] (>=0.3.21,<0.4.0)
-Requires-Dist: lxml (>=6.0.0,<7.0.0)
-Requires-Dist: resource-segmentation (>=0.0.3,<0.1.0)
-Requires-Dist: tiktoken (>=0.9.0,<0.10.0)
-Project-URL: Homepage, https://hub.oomol.com/package/book-translator
-Project-URL: Repository, https://github.com/oomol-flows/books-translator
-Description-Content-Type: text/markdown
-
-<div align=center>
-  <h1>EPUB Translator</h1>
-  <p>
-    <a href="https://github.com/oomol-lab/epub-translator/actions/workflows/build.yml" target="_blank"><img src="https://img.shields.io/github/actions/workflow/status/oomol-lab/epub-translator/build.yml" alt"ci" /></a>
-    <a href="https://pypi.org/project/epub-translator/" target="_blank"><img src="https://img.shields.io/badge/pip_install-epub--translator-blue" alt="pip install epub-translator" /></a>
-    <a href="https://pypi.org/project/epub-translator/" target="_blank"><img src="https://img.shields.io/pypi/v/epub-translator.svg" alt"pypi epub-translator" /></a>
-    <a href="https://pypi.org/project/epub-translator/" target="_blank"><img src="https://img.shields.io/pypi/pyversions/epub-translator.svg" alt="python versions" /></a>
-    <a href="https://github.com/oomol-lab/epub-translator/blob/main/LICENSE" target="_blank"><img src="https://img.shields.io/github/license/oomol-lab/epub-translator" alt"license" /></a>
-  </p>
-  <p><a href="https://hub.oomol.com/package/books-translator?open=true" target="_blank"><img src="https://static.oomol.com/assets/button.svg" alt="Open in OOMOL Studio" /></a></p>
-  <p>English | <a href="./README_zh-CN.md">中文</a></p>
-</div>
-
-## Introduction
-
-epub-translator uses AI big models to automatically translate EPUB e-books, and retains 100% of the original book's format, illustrations, catalog and layout, while generating bilingual comparison versions for easy language learning or international sharing.
-
-Whether you are a developer, language learner, or e-book lover, epub-translator can help you easily overcome language barriers.
-
-- [x] **Multi-language translation**: Supports translation between mainstream languages ​​such as English, Chinese, Japanese, Spanish, French, and German.
-- [x] **Bilingual comparison**: Generates bilingual EPUBs with top-down comparisons for easy comparison and learning.
-- [x] **Insert prompt words**: Guide AI translation, such as glossary, character name list, etc.
-- [x] **Optional AI model**: Supports mainstream big models such as DeepSeek and ChatGPT.
-- [x] **High-performance parallelism**: AI requests multiple concurrent channels to quickly translate the entire book.
-
-## Environment
-
-You can call EPUB Translator directly as a library, or use [OOMOL Studio](https://oomol.com/) to run it directly.
-
-### Run with OOMOL Studio
-
-OOMOL uses container technology to directly package the dependencies required by EPUB Translator, and it is ready to use out of the box.
-
-[![](./docs/images/link2youtube.png)](https://www.youtube.com/watch?v=QsAdiskxfXI)
-
-### Call directly as a library
-
-You can also write python code directly and call it as a library. At this time, you need python 3.10 or higher (3.10.16 is recommended).
-
-```shell
-pip install epub-translator
-```
-
-## Quick start
-
-First, construct the `LLM` object that calls the AI ​​Large Language Model.
-
-```python
-from epub_translator import LLM
-
-llm = LLM(
-  key="<LLM-API-KEY>", # LLM's API key
-  url="https://api.deepseek.com", # LLM's base URL
-  model="deepseek-chat", # LLM's model name
-  token_encoding="o200k_base", # Local model for calculating the number of tokens
-)
-```
-
-Then, you can call the `translate` method to translate.
-
-```python
-from epub_translator import translate, Language
-
-translate(
-  llm=llm, # llm object constructed in the previous step
-  source_path="/path/to/epub/file", # Original EPUB file to be translated
-  translated_path="/path/to/translated/epub/file", # Path to save the translated EPUB
-  target_language=Language.ENGLISH, # Target language for translation, in this case English.
-)
-```
-
-After calling this method, the translation can be inserted under the original text while retaining the EPUB format.
-
-![](./docs/images/translation.png)
-
-## Function
-
-### Save translation progress
-
-Calling `translate` to translate the entire EPUB e-book takes a long time, and this process may be interrupted for various reasons. For example, when calling LLM, an error is reported and the process is interrupted due to network reasons, or the user can't wait and manually interrupts the process.
-
-EPUB Translator can cache the translated content as a local file, so that when translating the same book, the translation progress can be saved and the progress can be restored from the last translation interruption.
-
-Just configure the `working_path` field when calling `translate` and specify a path to cache the files generated by the translation. The next time it is started, EPUB Translator will try to read the translation progress from this path in advance.
-
-```python
-translate(
-  ..., # other parameters
-  working_path="/path/to/cache/translating/files",
-)
-```
-
-Please note that each call to the `translate` method will write a cache file to the folder where the `workspace_path` is located. This will cause the folder to grow larger and larger. You need to handle it yourself, for example, automatically clear the folder after the translation is successful.
-
-### Monitor translation progress
-
-When calling `translate`, pass a callback function through `report_progress`, and receive a `float` type parameter representing the progress from 0.0 to 1.0, so that the translation progress of the whole book can be monitored.
-
-```python
-from tqdm import tqdm
-from epub_translator import translate
-
-with tqdm(total=1.0, desc="Translating") as bar:
-  def refresh_progress(progress: float) -> None:
-    bar.n = progress
-    bar.refresh()
-
-  translate(
-    ..., # other parameters
-    report_progress=refresh_progress,
-  )
-```
-
-### Insert prompt words
-
-Insert prompt words to guide the AI ​​language model on how to translate. For example, you can insert a glossary so that AI can unify the terms when translating. Just add the `user_prompt` field when calling `translate`.
-
-```python
-translate(
-  ..., # other parameters
-  user_prompt='Le Petit Prince should be translated as "Little Prince".',
-)
-```
-
-### Large Language Model Parameters
-
-There are more configuration options when building the `LLM` object.
-
-```python
-llm = LLM(
-  key="<LLM-API-KEY>", # LLM's API key
-  url="https://api.deepseek.com", # LLM's base URL
-  model="deepseek-chat", # LLM's model name
-  token_encoding="o200k_base", # Local model for calculating the number of tokens
-  timeout=60.0, # Request timeout (in seconds)
-  top_p=0.6, # Creativity
-  temperature=0.85, # Temperature
-  retry_times=5, # Retry times. If the request still fails after this number, an error will be reported
-  retry_interval_seconds=6.0, # Retry interval (in seconds)
-)
-```
-
-## Related open source libraries
-
-[PDF Craft](https://github.com/oomol-lab/pdf-craft) can convert PDF files into various other formats. This project will focus on the processing of PDF files of scanned books. Use this library with the scanned PDF books to convert and translate them. For more information, please refer to [Video: Convert scanned PDF books to EPUB format and translate them into bilingual books](https://www.bilibili.com/video/BV1tMQZY5EYY/).

epub_translator-0.0.6.dist-info/RECORD

@@ -1,36 +0,0 @@
-epub_translator/__init__.py,sha256=69k-70xbqxLgTvLyJE_MPFyymmPgyUAFg4mCSfEn49k,106
-epub_translator/data/format.jinja,sha256=1dXiMAhznuHWA2vpDx-968pm95FCXCRV3cKVmy3EXYA,3710
-epub_translator/data/translate.jinja,sha256=XWiMgeQS3tKCnh9cC6p1KQs9kqb1GO6m_j_cNeDq8lQ,1768
-epub_translator/epub/__init__.py,sha256=vqD29XWxgcfHw8LFCHQxupQeJufEEoS5_KHNphwfEYU,73
-epub_translator/epub/content_parser.py,sha256=Y-2fEcACCAl_ucA6VwwOoQ95BMHr9f-hryuxnsYNONM,4403
-epub_translator/epub/html/__init__.py,sha256=Yyg0TrWjecolaJP6qLzDnOlhi7SrkW0Is7wh9Fr0-Bg,26
-epub_translator/epub/html/dom_operator.py,sha256=Ryayv6hG0jEXv7RkXrZTbIP54P0fyPTbMVbymMtBUnU,1935
-epub_translator/epub/html/empty_tags.py,sha256=GSSe-CV4YkUhWv4F0fiiRsf2vz0ZBAsC21Ovnqo5oIA,601
-epub_translator/epub/html/file.py,sha256=AqUV-Tmptk5J2EYmw3oRVsLjGSqEMNz5rItnoRbGstc,2477
-epub_translator/epub/html/texts_searcher.py,sha256=vamO99pki6_sX2PeKCJk7mPwHdApZq1sOgSYDTPckx8,1376
-epub_translator/llm/__init__.py,sha256=wMBWLgh5iLNQBioniSOmWC83NS7RLM41hIs1V1uZiWI,21
-epub_translator/llm/error.py,sha256=fG0A3z69YoSNu0MNVWVFMtHCB_4fpOvAEb0Kajn9OHc,1401
-epub_translator/llm/executor.py,sha256=Z8mpsTAEEfG80E43Pv5VJJzaDKrrClyUhr8GFA2yVxA,4498
-epub_translator/llm/increasable.py,sha256=Dpu5z4JK5h1OtLorZgsOAdRFeTH2LOkdroasgmCWAIo,1136
-epub_translator/llm/node.py,sha256=qdkBY06OOt0mq8tnLgMJZS5dc3WFColzpeHmyWLE7KU,6104
-epub_translator/template.py,sha256=GdV3QnypProKFCMH1kBNfdt6wiShygP_-xGnE5EOUwU,1460
-epub_translator/translation/__init__.py,sha256=oYRMq3PJf2eZfIAAHkFmC_MZ3vLdeCQFzowuwAd9jd8,100
-epub_translator/translation/chunk.py,sha256=ERIDvhM7kZB_ZqWGw4UQfKgjIHn7TDWsxa-RuTpxRs0,3639
-epub_translator/translation/splitter.py,sha256=9YLEdRRA01NEWKmI-UUtAXHq2iJOyZtCnt1ZWQ0h0dU,2696
-epub_translator/translation/store.py,sha256=T6OYhQZETPz5p-ykmPC_wDLzmRet8o7jDY3sHxWVV1o,1057
-epub_translator/translation/translation.py,sha256=BBmaNME7Pd0zytK_7CCx10dsoWLootB3uggvYLW-rQM,7079
-epub_translator/translation/types.py,sha256=Pnzll2V4MnOsW_kIP0XU6Cj-QQkLTByB6dr_U4sdNH8,989
-epub_translator/translation/utils.py,sha256=G6Gqq6mot3lgFA-jqUD0UqtDS0GC1wrb9DnK7rTxJNs,223
-epub_translator/translator.py,sha256=t5vgiDPiYda1CiKtEB91hjqVrN2dDZ7sTBLTotIVv3w,5487
-epub_translator/xml/__init__.py,sha256=o2_qwUYU_MUcyfmfKkiOQ-cKUQyl4PiRL8YHVzCTAZU,106
-epub_translator/xml/decoder.py,sha256=UlqgmEKQDzxt3lvBeNGHgZP6jznmnq_1HLJuAe5X0C4,2181
-epub_translator/xml/encoder.py,sha256=p4A7GRSOM2i0WOh1lLtEdTTg2gXSQrxDdzMgUqbiV18,2428
-epub_translator/xml/parser.py,sha256=3JuFLFLX4w98pzME72ywdpq0JzSBgzwZMFbH8IfB9T4,5545
-epub_translator/xml/tag.py,sha256=QLZImF0PtYyiASI7swrB8DL_qUwcYpU6cL68jEXDnvg,2353
-epub_translator/xml/transform.py,sha256=vS_a4d_o2Qqf9B6k2CovQVLUknp6TyUi3FyLOu21Vio,1126
-epub_translator/xml/utils.py,sha256=KDNGWHwaIiFKS27sjZF0e-bBSjeTxzceae_aeuj4wzI,384
-epub_translator/zip_context.py,sha256=SwkqghokGLGx-tlZ_K7sJTF-g-cm6dErurSZCM-ZLeM,2414
-epub_translator-0.0.6.dist-info/LICENSE,sha256=5RF32sL3LtMOJIErdDKp1ZEYPGXS8WPpsiSz_jMBnGI,1066
-epub_translator-0.0.6.dist-info/METADATA,sha256=D_355033oXlgbht7x16tq6eHP50NZnHtStSyTDfF0-o,8081
-epub_translator-0.0.6.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-epub_translator-0.0.6.dist-info/RECORD,,