Merge pull request #9 from NeiH4207/translate-docx-file

update translator for docx file

.github/workflows/python-package-conda.yml

@@ -1,34 +1,33 @@
-name: Python Package using Conda
+name: transipy
 
-on: [push]
+on: [push, pull_request]
 
 jobs:
-  build-linux:
+  build:
     runs-on: ubuntu-latest
-    strategy:
-      max-parallel: 5
 
     steps:
-    - uses: actions/checkout@v4
-    - name: Set up Python 3.10
-      uses: actions/setup-python@v3
+    - name: Checkout repository
+      uses: actions/checkout@v2
+
+    - name: Set up Conda environment
+      uses: conda-incubator/setup-miniconda@v2
       with:
-        python-version: '3.10'
-    - name: Add conda to system path
-      run: |
-        # $CONDA is an environment variable pointing to the root of the miniconda directory
-        echo $CONDA/bin >> $GITHUB_PATH
-    - name: Install dependencies
+        environment-file: environment.yml
+        python-version: 3.9
+        auto-update-conda: true
+
+    - name: Set Conda solver to classic and disable plugins
       run: |
-        conda env update --file environment.yml --name base
-    - name: Lint with flake8
+        conda config --set solver classic
+        CONDA_NO_PLUGINS=true conda env update --file environment.yml --name base
+
+    - name: Install additional pip dependencies
       run: |
-        conda install flake8
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-    - name: Test with pytest
+        source activate base
+        pip install -r requirements.txt
+
+    - name: Run tests
       run: |
-        conda install pytest
+        source activate base
         pytest

environment.yml

@@ -0,0 +1,8 @@
+name: transipy
+channels:
+  - defaults
+
+dependencies:
+  - python=3.9
+  - pytest
+  - pip

requirements.txt

@@ -1,7 +1,9 @@
 loguru==0.7.2
 pandas==2.2.2
+bottleneck==1.3.6
 googletrans==4.0.0rc1
 openpyxl==3.1.2
 requests==2.31.0
 h2==3.2.0
-httpx==0.13.3
+httpx==0.13.3
+python-docx==1.1.2

transipy/main.py

@@ -3,13 +3,13 @@
 import os
 from loguru import logger
 import pandas as pd
-from transipy.trans_helper import translate_df, translate_excel
+from transipy.trans_helper import translate_df, translate_docx, translate_excel
 from transipy.utils import *
 from googletrans import LANGUAGES
 
 def get_parser():
     parser = argparse.ArgumentParser(
-        description='Translate text in a file (.csv/.txt) from source language to target language.',
+        description='Translate text in a file (.csv/.txt/.tsv/.docx/.xlsx) from source language to target language.',
     )
     parser.add_argument('-f', '--file-path', type=str, required=True, help='The source file path')
     parser.add_argument('-l', '--sep', type=str, default=None, help='The separator of the file [comma, tab, space,...]')
@@ -60,7 +60,7 @@ def main():
     file_extension = get_file_extension(input_file)
 
     if not is_supported_file(input_file):
-        logger.error("Unsupported file format. Please use .csv/.txt or .xlsx files.")
+        logger.error("Unsupported file format. Please use .csv/.tsv/.txt/.docx or .xlsx files.")
         return
 
     if not args.output_file:
@@ -133,6 +133,15 @@ def main():
         )
         with open(output_file, 'w') as f:
             f.write('\n'.join(df['text'].tolist()))
+    elif is_docx(file_extension):
+        translate_docx(
+            file_path=input_file, 
+            src=source_language, 
+            dest=target_language, 
+            chunk_size=chunk_size, 
+            dictionary=dictionary, 
+            output_file=output_file
+        )
     else:
         logger.error("Unsupported file format. Please use .csv/.tsv/.txt or .xlsx files.")
-        return
+        return

transipy/trans_helper.py

@@ -1,5 +1,5 @@
 from time import sleep
-import time
+import docx
 import requests
 import ast
 import requests
@@ -147,4 +147,33 @@ def translate_excel(dfs, sheets=None, src='en', dest='vi', chunk_size=4, diction
         with pd.ExcelWriter(output_file) as writer:
             for sheet_name in sheets:
                 dfs[sheet_name].to_excel(writer, sheet_name=sheet_name, index=False)
-    return dfs
+    return dfs
+
+def translate_docx(file_path, src='en', dest='vi', chunk_size=4, dictionary={}, output_file=None):
+    doc = docx.Document(file_path)
+    translated_doc = docx.Document()
+
+    raw_docs = []
+
+    for paragraph in doc.paragraphs:
+        raw_docs.append(paragraph.text)
+
+    df = pd.DataFrame(raw_docs, columns=['text'])
+
+    df = translate_df(
+        df=df, 
+        columns=['text'],
+        src=src, 
+        dest=dest, 
+        chunk_size=chunk_size, 
+        dictionary=dictionary, 
+        output_file=output_file
+    )
+
+    for text in df['text']:
+        translated_doc.add_paragraph(text)
+
+    if output_file:
+        translated_doc.save(output_file)
+
+    return translated_doc

transipy/utils.py

@@ -17,6 +17,9 @@ def is_excel(file_path):
 def is_text(file_path):
     return get_file_extension(file_path) == '.txt'
 
+def is_docx(file_path):
+    return get_file_extension(file_path) == '.docx'
+
 def get_separetor(sep):
     if sep == 'comma':
         return ','
@@ -34,7 +37,7 @@ def get_all_excel_sheet_names(file_path, skip_list: list = []):
     return [sheet for sheet in sheets if sheet not in skip_list]
 
 def is_supported_file(file_path):
-    return is_csv(file_path) or is_tsv(file_path) or is_excel(file_path) or is_text(file_path)
+    return is_csv(file_path) or is_tsv(file_path) or is_excel(file_path) or is_text(file_path) or is_docx(file_path)
 
 
 def split_df_by_group(df, chunks):