BackTranslation 0.4.0__tar.gz → 0.5.0__tar.gz

{backtranslation-0.4.0 → backtranslation-0.5.0}/BackTranslation/languages.py

@@ -15,6 +15,7 @@ LANG_CODES = {
     'chichewa': 'ny',
     'chinese (simplified)': 'zh-cn',
     'chinese (traditional)': 'zh-tw',
+    'chinese (cantonese)': 'yue',
     'corsican': 'co',
     'croatian': 'hr',
     'czech': 'cs',

{backtranslation-0.4.0 → backtranslation-0.5.0}/BackTranslation/translated.py

@@ -2,23 +2,22 @@ class Translated(object):
     """
     Save the translated result
     """
-    def __init__(self, src_lang, tmp_lang, text, trans_text, back_text):
+    def __init__(self, src_lang, tmp_lang, text, trans_text, back_text, dst_lang=None, mode='back_translation'):
         self.source_text = text
         self.src = src_lang
         self.tmp = tmp_lang
+        self.dst = dst_lang if dst_lang is not None else tmp_lang
+        self.mode = mode
         self.tran_text = trans_text
         self.result_text = back_text
 
-
     def __str__(self):
         return self.__unicode__()
 
-
-
     def __unicode__(self):
         if len(self.result_text.split(' ')) > 30:
             show_text = ' '.join(self.result_text.split(' ')[:30])
             show_text += '...'
         else:
             show_text = self.result_text
-        return u'Translated(src={src}, tmp={tmp}, result_text={text})'.format(src=self.src, tmp=self.tmp, text=show_text)
+        return u'Translated(src={src}, tmp={tmp}, result_text={text})'.format(src=self.src, tmp=self.tmp, text=show_text)

{backtranslation-0.4.0 → backtranslation-0.5.0}/BackTranslation/translation.py

@@ -31,12 +31,8 @@ class BackTranslation(object):
         self.MAX_LENGTH = 5000
 
     def translate(self, text, src=None, tmp=None, sleeping=0):
-
-        if not src:
-            src = self.translator.detect(text).lang
-
-        if src.lower() not in self.Languages:
-            raise ValueError("'{}': INVALID source language.".format(src))
+        src = self._resolve_src(text, src)
+        self._validate_language(src, 'source')
 
         # if tmp is null, set a default language for tmp.
         if not tmp:
@@ -45,52 +41,74 @@ class BackTranslation(object):
             else:
                 tmp = 'en'
 
-        if tmp not in self.Languages:
-            raise ValueError("'{}': INVALID transited language.".format(tmp))
-
-        if src == tmp:
-            raise ValueError("Transited language ({tmp}) should different from source language ({src}).".format(
-                tmp=tmp, src=src))
+        self._validate_language(tmp, 'transited')
+        self._validate_different(src, tmp, 'Transited')
 
         # check the length of text
         if len(text) > self.MAX_LENGTH:
             original_sentences = self._split_segement(sent_tokenize(text))
 
-            try:
-                t_text = self.translator.translate(original_sentences, src=src, dest=tmp)
-            except httpcore.ConnectTimeout:
-                raise httpcore.ConnectTimeout("Connection timed out. If you are blocked by Google, try using the 'proxies' parameter or a different 'url'.")
-            except Exception as e:
-                raise Exception("Translation failed (try increasing the 'sleeping' parameter): {}".format(e))
+            t_text = self._translate_with_google(original_sentences, src, tmp, 'Translation')
             tran_text = ' '.join([t.text for t in t_text])
             time.sleep(sleeping)
-            try:
-                r_text = self.translator.translate([t.text for t in t_text], src=tmp, dest=src)
-            except httpcore.ConnectTimeout:
-                raise httpcore.ConnectTimeout("Connection timed out. If you are blocked by Google, try using the 'proxies' parameter or a different 'url'.")
-            except Exception as e:
-                raise Exception("Back-translation failed (try increasing the 'sleeping' parameter): {}".format(e))
+            r_text = self._translate_with_google([t.text for t in t_text], tmp, src, 'Back-translation')
             back_text = ' '.join([r.text for r in r_text])
             back_text.rstrip()
         else:
-            try:
-                mid_text = self.translator.translate(text, src=src, dest=tmp)
-            except httpcore.ConnectTimeout:
-                raise httpcore.ConnectTimeout("Connection timed out. If you are blocked by Google, try using the 'proxies' parameter or a different 'url'.")
-            except Exception as e:
-                raise Exception("Translation failed (try increasing the 'sleeping' parameter): {}".format(e))
+            mid_text = self._translate_with_google(text, src, tmp, 'Translation')
             tran_text = mid_text.text
             time.sleep(sleeping)  # Sleep between translation
-            try:
-                result_text = self.translator.translate(tran_text, src=tmp, dest=src)
-            except httpcore.ConnectTimeout:
-                raise httpcore.ConnectTimeout("Connection timed out. If you are blocked by Google, try using the 'proxies' parameter or a different 'url'.")
-            except Exception as e:
-                raise Exception("Back-translation failed (try increasing the 'sleeping' parameter): {}".format(e))
+            result_text = self._translate_with_google(tran_text, tmp, src, 'Back-translation')
             back_text = result_text.text
-        result = Translated(src_lang=src, tmp_lang=tmp, text=text, trans_text=tran_text, back_text=back_text)
+        result = Translated(src_lang=src, tmp_lang=tmp, text=text, trans_text=tran_text, back_text=back_text,
+                            dst_lang=tmp, mode='back_translation')
         return result
 
+    def direct_translate(self, text, src=None, dst=None, sleeping=0):
+        if not dst:
+            raise ValueError("destination language is required")
+
+        src = self._resolve_src(text, src)
+
+        self._validate_language(src, 'source')
+        self._validate_language(dst, 'destination')
+        self._validate_different(src, dst, 'Destination')
+
+        if len(text) > self.MAX_LENGTH:
+            original_sentences = self._split_segement(sent_tokenize(text))
+            translated_text = self._translate_with_google(original_sentences, src, dst, 'Translation')
+            result_text = ' '.join([t.text for t in translated_text])
+        else:
+            translated_text = self._translate_with_google(text, src, dst, 'Translation')
+            result_text = translated_text.text
+
+        result = Translated(src_lang=src, tmp_lang=dst, text=text, trans_text=result_text, back_text=result_text,
+                            dst_lang=dst, mode='direct')
+        return result
+
+    def _resolve_src(self, text, src):
+        if not src:
+            return self.translator.detect(text).lang
+        return src
+
+    def _validate_language(self, language, language_type):
+        if language.lower() not in self.Languages:
+            raise ValueError("'{}': INVALID {} language.".format(language, language_type))
+
+    def _validate_different(self, src, dst, dst_label):
+        if src == dst:
+            raise ValueError("{} language ({dst}) should different from source language ({src}).".format(
+                dst_label, dst=dst, src=src))
+
+    def _translate_with_google(self, text, src, dst, action):
+        try:
+            return self.translator.translate(text, src=src, dest=dst)
+        except httpcore.ConnectTimeout:
+            raise httpcore.ConnectTimeout(
+                "Connection timed out. If you are blocked by Google, try using the 'proxies' parameter or a different 'url'.")
+        except Exception as e:
+            raise Exception("{} failed (try increasing the 'sleeping' parameter): {}".format(action, e))
+
     def _split_segement(self, sentences):
         """
         Split the long sentences into multiple sentences whose lengths are less than MAX_LENGTH.

{backtranslation-0.4.0 → backtranslation-0.5.0}/BackTranslation/translation_Baidu.py

@@ -72,6 +72,48 @@ class BackTranslation_Baidu(object):
         result = Translated(src_lang=src, tmp_lang=tmp, text=text, trans_text=tran_text, back_text=back_text)
         return result
 
+    def direct_translate(self, text, src='auto', dst=None, sleeping=1):
+        if not dst:
+            raise ValueError("destination language is required")
+
+        if src == dst:
+            raise ValueError(
+                "Destination language ({dst}) should different from source language ({src}).".format(dst=dst, src=src))
+
+        if len(text.encode('utf-8')) > self.MAX_LENGTH:
+            original_sentences = [
+                sentence for sentence in self._split_segement(sent_tokenize(text))
+                if sentence != ""
+            ]
+            tran_text = []
+            resolved_src = src
+            for index, sentence in enumerate(original_sentences):
+                result = self._sendRequest(sentence, resolved_src, dst)
+                if resolved_src == 'auto':
+                    resolved_src = self._get_srcLang(result)
+                    if resolved_src == dst:
+                        raise ValueError(
+                            "Destination language ({dst}) should different from source language ({src}).".format(
+                                dst=dst, src=resolved_src))
+                tran_text.append(self._get_translatedText(result))
+                if index < len(original_sentences) - 1:
+                    time.sleep(sleeping)
+            tran_text = ' '.join(tran_text)
+            src = resolved_src
+        else:
+            result = self._sendRequest(text, src, dst)
+            if src == 'auto':
+                src = self._get_srcLang(result)
+                if src == dst:
+                    raise ValueError(
+                        "Destination language ({dst}) should different from source language ({src}).".format(
+                            dst=dst, src=src))
+            tran_text = self._get_translatedText(result)
+
+        result = Translated(src_lang=src, tmp_lang=dst, text=text, trans_text=tran_text, back_text=tran_text,
+                            dst_lang=dst, mode='direct')
+        return result
+
     def _sendRequest(self, text, src, tmp):
         salt = random.randint(32768, 65536)
         sign = hashlib.md5((self.appid + text + str(salt) + self.secretKey).encode()).hexdigest()

{backtranslation-0.4.0 → backtranslation-0.5.0}/BackTranslation.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BackTranslation
-Version: 0.4.0
+Version: 0.5.0
 Summary: Back translation for Natural Language Processing (NLP) using Google Translate
 Home-page: https://github.com/hhhwwwuuu/BackTranslation
 Author: Zhiqiang Wu
@@ -30,11 +30,11 @@ Dynamic: requires-python
 Dynamic: summary
 
 # BackTranslation
-[![version](https://img.shields.io/badge/version-0.3.1-blue)](https://pypi.org/project/BackTranslation/#description)
+[![version](https://img.shields.io/badge/version-0.5.0-blue)](https://pypi.org/project/BackTranslation/#description)
 [![Downloads](https://pepy.tech/badge/backtranslation)](https://pepy.tech/project/backtranslation)
 [![license](https://img.shields.io/badge/license-MIT-green)](https://github.com/hhhwwwuuu/BackTranslation/blob/main/LICENSE)
 
-BackTranslation is a python library that implemented to back translate the words among any two languages. This utilizes [googletrans](https://py-googletrans.readthedocs.io/en/latest/) library and [Baidu Translation API](http://api.fanyi.baidu.com/) to translate the words.
+BackTranslation is a python library that implements back translation and direct translation among languages. It utilizes the [googletrans](https://py-googletrans.readthedocs.io/en/latest/) library and [Baidu Translation API](http://api.fanyi.baidu.com/) to translate text.
 
 Since there is an error in current verison of googletrans, you have to create only one instance to do back-translation for your work. Otherwise, it is easy to cause a bug from multi-requests. We will keep implementing this library with other translator libraries soon.
 
@@ -49,6 +49,37 @@ $ pip install BackTranslation
 
 
 ## Usage
+### Direct translation with googletrans
+Translate text from language A directly to language B without translating it back.
+
+Parameters:
+* **url**: option. provide a list of services urls for translation if need. Default url is _translate.google.com_.
+* **proxies**: Optional. Proxies configuration. Dictionary mapping protocol or protocol and host to the URL of the proxy.
+  i.e. proxies = {'http': '127.0.0.1:1234', 'http://host.name': '127.0.0.1:4012'}
+* **text**: required. Original text that need to translate.
+* **src**: option. Source language code of original text. If this parameter is None, the method will detect the language of text automatically. (Default: None)
+* **dst**: required. Destination language code.
+* **sleeping**: option. Kept for API consistency. Direct translation only sends the A-to-B request. (Default: 0)
+
+Return parameter: object _Translated_.
+
+Attributes:
+* source_text: original sentence.
+* src: the language of original sentence.
+* dst: the target language.
+* tmp: the same as dst for direct translation.
+* tran_text: translated result in dst language.
+* result_text: translated result in dst language.
+* mode: _direct_.
+
+```python
+from BackTranslation import BackTranslation
+trans = BackTranslation()
+result = trans.direct_translate('hello', src='en', dst='zh-cn')
+print(result.result_text)
+# '你好'
+```
+
 ### Backtranslation with googletrans
 Translate the original text to other language and translate back to augment the diversity of data in NLP research.
 
@@ -67,8 +98,10 @@ Attributes:
 * source_text: original sentence.
 * src: the language of original sentence
 * tmp: the target language as middle man
-* trans_text: intermediate result
-* back_text: back-tranlsated result
+* dst: the same as tmp for back-translation
+* tran_text: intermediate result
+* result_text: back-translated result
+* mode: _back_translation_
 
 ```python
 from BackTranslation import BackTranslation
@@ -113,7 +146,9 @@ Parameters:
 from BackTranslation import BackTranslation
 trans = BackTranslation()
 trans.searchLanguage('Chinese')
-# {'chinese (simplified)': 'zh-cn', 'chinese (traditional)': 'zh-tw'}
+# {'chinese (simplified)': 'zh-cn', 'chinese (traditional)': 'zh-tw', 'chinese (cantonese)': 'yue'}
+trans.searchLanguage('Cantonese')
+# {'chinese (cantonese)': 'yue'}
 ```
 ### Backtranslation_Baidu with Baidu Translation API
 To use this stable translation, you are required to register in [Baidu Translation API]((http://api.fanyi.baidu.com/)) for getting your own appID.
@@ -121,6 +156,16 @@ It supports 2 million chacters per day for free.
 _Note: Currently, they only support Chinese phone number to register the accout._
 * **sleeping**: option. Baidu standard API allows only 1 request per second (QPS limit). Set `sleeping=1` (default) to stay within the limit. Increase if you encounter errors. (Default: 1)
 
+Direct translation:
+````python
+from BackTranslation import BackTranslation_Baidu
+trans = BackTranslation_Baidu(appid='YOUR APPID', secretKey='YOUR SECRETKEY')
+result = trans.direct_translate('hello', src='en', dst='zh')
+print(result.result_text) # direct translated result
+trans.closeHTTP()
+````
+
+Back-translation:
 ````python
 from BackTranslation import BackTranslation_Baidu
 trans = BackTranslation_Baidu(appid='YOUR APPID', secretKey='YOUR SECRETKEY')
@@ -134,7 +179,11 @@ Since Baidu provides the different language code, it will be updated soon.
 
 
 ## Version Information
-**Version 0.3.1: fix some bugs for Baidu translator.**
+**Version 0.5.0: add direct translation APIs for Google and Baidu translators, keep existing back-translation behavior compatible, extend `Translated` with `dst` and `mode`, add Cantonese (`yue`) language support, and update tests and documentation.**
+
+Version 0.4.0: fix bugs (#1 #2 #3 #4 #6), add automated tests and CI/CD pipeline.
+
+Version 0.3.1: fix some bugs for Baidu translator.
 
 Version 0.2.2: fix the services url for Google Translator.
 

{backtranslation-0.4.0 → backtranslation-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BackTranslation
-Version: 0.4.0
+Version: 0.5.0
 Summary: Back translation for Natural Language Processing (NLP) using Google Translate
 Home-page: https://github.com/hhhwwwuuu/BackTranslation
 Author: Zhiqiang Wu
@@ -30,11 +30,11 @@ Dynamic: requires-python
 Dynamic: summary
 
 # BackTranslation
-[![version](https://img.shields.io/badge/version-0.3.1-blue)](https://pypi.org/project/BackTranslation/#description)
+[![version](https://img.shields.io/badge/version-0.5.0-blue)](https://pypi.org/project/BackTranslation/#description)
 [![Downloads](https://pepy.tech/badge/backtranslation)](https://pepy.tech/project/backtranslation)
 [![license](https://img.shields.io/badge/license-MIT-green)](https://github.com/hhhwwwuuu/BackTranslation/blob/main/LICENSE)
 
-BackTranslation is a python library that implemented to back translate the words among any two languages. This utilizes [googletrans](https://py-googletrans.readthedocs.io/en/latest/) library and [Baidu Translation API](http://api.fanyi.baidu.com/) to translate the words.
+BackTranslation is a python library that implements back translation and direct translation among languages. It utilizes the [googletrans](https://py-googletrans.readthedocs.io/en/latest/) library and [Baidu Translation API](http://api.fanyi.baidu.com/) to translate text.
 
 Since there is an error in current verison of googletrans, you have to create only one instance to do back-translation for your work. Otherwise, it is easy to cause a bug from multi-requests. We will keep implementing this library with other translator libraries soon.
 
@@ -49,6 +49,37 @@ $ pip install BackTranslation
 
 
 ## Usage
+### Direct translation with googletrans
+Translate text from language A directly to language B without translating it back.
+
+Parameters:
+* **url**: option. provide a list of services urls for translation if need. Default url is _translate.google.com_.
+* **proxies**: Optional. Proxies configuration. Dictionary mapping protocol or protocol and host to the URL of the proxy.
+  i.e. proxies = {'http': '127.0.0.1:1234', 'http://host.name': '127.0.0.1:4012'}
+* **text**: required. Original text that need to translate.
+* **src**: option. Source language code of original text. If this parameter is None, the method will detect the language of text automatically. (Default: None)
+* **dst**: required. Destination language code.
+* **sleeping**: option. Kept for API consistency. Direct translation only sends the A-to-B request. (Default: 0)
+
+Return parameter: object _Translated_.
+
+Attributes:
+* source_text: original sentence.
+* src: the language of original sentence.
+* dst: the target language.
+* tmp: the same as dst for direct translation.
+* tran_text: translated result in dst language.
+* result_text: translated result in dst language.
+* mode: _direct_.
+
+```python
+from BackTranslation import BackTranslation
+trans = BackTranslation()
+result = trans.direct_translate('hello', src='en', dst='zh-cn')
+print(result.result_text)
+# '你好'
+```
+
 ### Backtranslation with googletrans
 Translate the original text to other language and translate back to augment the diversity of data in NLP research.
 
@@ -67,8 +98,10 @@ Attributes:
 * source_text: original sentence.
 * src: the language of original sentence
 * tmp: the target language as middle man
-* trans_text: intermediate result
-* back_text: back-tranlsated result
+* dst: the same as tmp for back-translation
+* tran_text: intermediate result
+* result_text: back-translated result
+* mode: _back_translation_
 
 ```python
 from BackTranslation import BackTranslation
@@ -113,7 +146,9 @@ Parameters:
 from BackTranslation import BackTranslation
 trans = BackTranslation()
 trans.searchLanguage('Chinese')
-# {'chinese (simplified)': 'zh-cn', 'chinese (traditional)': 'zh-tw'}
+# {'chinese (simplified)': 'zh-cn', 'chinese (traditional)': 'zh-tw', 'chinese (cantonese)': 'yue'}
+trans.searchLanguage('Cantonese')
+# {'chinese (cantonese)': 'yue'}
 ```
 ### Backtranslation_Baidu with Baidu Translation API
 To use this stable translation, you are required to register in [Baidu Translation API]((http://api.fanyi.baidu.com/)) for getting your own appID.
@@ -121,6 +156,16 @@ It supports 2 million chacters per day for free.
 _Note: Currently, they only support Chinese phone number to register the accout._
 * **sleeping**: option. Baidu standard API allows only 1 request per second (QPS limit). Set `sleeping=1` (default) to stay within the limit. Increase if you encounter errors. (Default: 1)
 
+Direct translation:
+````python
+from BackTranslation import BackTranslation_Baidu
+trans = BackTranslation_Baidu(appid='YOUR APPID', secretKey='YOUR SECRETKEY')
+result = trans.direct_translate('hello', src='en', dst='zh')
+print(result.result_text) # direct translated result
+trans.closeHTTP()
+````
+
+Back-translation:
 ````python
 from BackTranslation import BackTranslation_Baidu
 trans = BackTranslation_Baidu(appid='YOUR APPID', secretKey='YOUR SECRETKEY')
@@ -134,7 +179,11 @@ Since Baidu provides the different language code, it will be updated soon.
 
 
 ## Version Information
-**Version 0.3.1: fix some bugs for Baidu translator.**
+**Version 0.5.0: add direct translation APIs for Google and Baidu translators, keep existing back-translation behavior compatible, extend `Translated` with `dst` and `mode`, add Cantonese (`yue`) language support, and update tests and documentation.**
+
+Version 0.4.0: fix bugs (#1 #2 #3 #4 #6), add automated tests and CI/CD pipeline.
+
+Version 0.3.1: fix some bugs for Baidu translator.
 
 Version 0.2.2: fix the services url for Google Translator.
 

{backtranslation-0.4.0 → backtranslation-0.5.0}/README.md

@@ -1,9 +1,9 @@
 # BackTranslation
-[![version](https://img.shields.io/badge/version-0.3.1-blue)](https://pypi.org/project/BackTranslation/#description)
+[![version](https://img.shields.io/badge/version-0.5.0-blue)](https://pypi.org/project/BackTranslation/#description)
 [![Downloads](https://pepy.tech/badge/backtranslation)](https://pepy.tech/project/backtranslation)
 [![license](https://img.shields.io/badge/license-MIT-green)](https://github.com/hhhwwwuuu/BackTranslation/blob/main/LICENSE)
 
-BackTranslation is a python library that implemented to back translate the words among any two languages. This utilizes [googletrans](https://py-googletrans.readthedocs.io/en/latest/) library and [Baidu Translation API](http://api.fanyi.baidu.com/) to translate the words.
+BackTranslation is a python library that implements back translation and direct translation among languages. It utilizes the [googletrans](https://py-googletrans.readthedocs.io/en/latest/) library and [Baidu Translation API](http://api.fanyi.baidu.com/) to translate text.
 
 Since there is an error in current verison of googletrans, you have to create only one instance to do back-translation for your work. Otherwise, it is easy to cause a bug from multi-requests. We will keep implementing this library with other translator libraries soon.
 
@@ -18,6 +18,37 @@ $ pip install BackTranslation
 
 
 ## Usage
+### Direct translation with googletrans
+Translate text from language A directly to language B without translating it back.
+
+Parameters:
+* **url**: option. provide a list of services urls for translation if need. Default url is _translate.google.com_.
+* **proxies**: Optional. Proxies configuration. Dictionary mapping protocol or protocol and host to the URL of the proxy.
+  i.e. proxies = {'http': '127.0.0.1:1234', 'http://host.name': '127.0.0.1:4012'}
+* **text**: required. Original text that need to translate.
+* **src**: option. Source language code of original text. If this parameter is None, the method will detect the language of text automatically. (Default: None)
+* **dst**: required. Destination language code.
+* **sleeping**: option. Kept for API consistency. Direct translation only sends the A-to-B request. (Default: 0)
+
+Return parameter: object _Translated_.
+
+Attributes:
+* source_text: original sentence.
+* src: the language of original sentence.
+* dst: the target language.
+* tmp: the same as dst for direct translation.
+* tran_text: translated result in dst language.
+* result_text: translated result in dst language.
+* mode: _direct_.
+
+```python
+from BackTranslation import BackTranslation
+trans = BackTranslation()
+result = trans.direct_translate('hello', src='en', dst='zh-cn')
+print(result.result_text)
+# '你好'
+```
+
 ### Backtranslation with googletrans
 Translate the original text to other language and translate back to augment the diversity of data in NLP research.
 
@@ -36,8 +67,10 @@ Attributes:
 * source_text: original sentence.
 * src: the language of original sentence
 * tmp: the target language as middle man
-* trans_text: intermediate result
-* back_text: back-tranlsated result
+* dst: the same as tmp for back-translation
+* tran_text: intermediate result
+* result_text: back-translated result
+* mode: _back_translation_
 
 ```python
 from BackTranslation import BackTranslation
@@ -82,7 +115,9 @@ Parameters:
 from BackTranslation import BackTranslation
 trans = BackTranslation()
 trans.searchLanguage('Chinese')
-# {'chinese (simplified)': 'zh-cn', 'chinese (traditional)': 'zh-tw'}
+# {'chinese (simplified)': 'zh-cn', 'chinese (traditional)': 'zh-tw', 'chinese (cantonese)': 'yue'}
+trans.searchLanguage('Cantonese')
+# {'chinese (cantonese)': 'yue'}
 ```
 ### Backtranslation_Baidu with Baidu Translation API
 To use this stable translation, you are required to register in [Baidu Translation API]((http://api.fanyi.baidu.com/)) for getting your own appID.
@@ -90,6 +125,16 @@ It supports 2 million chacters per day for free.
 _Note: Currently, they only support Chinese phone number to register the accout._
 * **sleeping**: option. Baidu standard API allows only 1 request per second (QPS limit). Set `sleeping=1` (default) to stay within the limit. Increase if you encounter errors. (Default: 1)
 
+Direct translation:
+````python
+from BackTranslation import BackTranslation_Baidu
+trans = BackTranslation_Baidu(appid='YOUR APPID', secretKey='YOUR SECRETKEY')
+result = trans.direct_translate('hello', src='en', dst='zh')
+print(result.result_text) # direct translated result
+trans.closeHTTP()
+````
+
+Back-translation:
 ````python
 from BackTranslation import BackTranslation_Baidu
 trans = BackTranslation_Baidu(appid='YOUR APPID', secretKey='YOUR SECRETKEY')
@@ -103,7 +148,11 @@ Since Baidu provides the different language code, it will be updated soon.
 
 
 ## Version Information
-**Version 0.3.1: fix some bugs for Baidu translator.**
+**Version 0.5.0: add direct translation APIs for Google and Baidu translators, keep existing back-translation behavior compatible, extend `Translated` with `dst` and `mode`, add Cantonese (`yue`) language support, and update tests and documentation.**
+
+Version 0.4.0: fix bugs (#1 #2 #3 #4 #6), add automated tests and CI/CD pipeline.
+
+Version 0.3.1: fix some bugs for Baidu translator.
 
 Version 0.2.2: fix the services url for Google Translator.
 
@@ -118,4 +167,4 @@ Welcome to contribute BackTranslation library!
 
 ## reference
 - [googletrans](https://py-googletrans.readthedocs.io/en/latest/)
-- [Baidu Translation API](http://api.fanyi.baidu.com/)
+- [Baidu Translation API](http://api.fanyi.baidu.com/)

{backtranslation-0.4.0 → backtranslation-0.5.0}/tests/test_translated.py

@@ -11,10 +11,23 @@ def test_attributes():
     assert r.source_text == 'hello'
     assert r.src == 'en'
     assert r.tmp == 'zh-cn'
+    assert r.dst == 'zh-cn'
+    assert r.mode == 'back_translation'
     assert r.tran_text == '你好'
     assert r.result_text == 'hello there'
 
 
+def test_direct_attributes():
+    r = Translated(src_lang='en', tmp_lang='zh-cn', text='hello', trans_text='你好',
+                   back_text='你好', dst_lang='zh-cn', mode='direct')
+    assert r.src == 'en'
+    assert r.tmp == 'zh-cn'
+    assert r.dst == 'zh-cn'
+    assert r.mode == 'direct'
+    assert r.tran_text == '你好'
+    assert r.result_text == '你好'
+
+
 def test_str_short():
     r = make_result('hello there')
     s = str(r)

{backtranslation-0.4.0 → backtranslation-0.5.0}/tests/test_translation.py

@@ -46,6 +46,32 @@ def test_basic_translation():
     assert result.result_text == 'Hello there'
 
 
+def test_direct_translation():
+    trans, mock_translator = _build_trans()
+    mock_translator.translate.return_value = _make_translate_result('你好')
+    result = trans.direct_translate('hello', src='en', dst='zh-cn')
+    assert result.src == 'en'
+    assert result.tmp == 'zh-cn'
+    assert result.dst == 'zh-cn'
+    assert result.mode == 'direct'
+    assert result.source_text == 'hello'
+    assert result.tran_text == '你好'
+    assert result.result_text == '你好'
+    mock_translator.translate.assert_called_once_with('hello', src='en', dest='zh-cn')
+
+
+def test_direct_translation_to_cantonese():
+    trans, mock_translator = _build_trans()
+    mock_translator.translate.return_value = _make_translate_result('你好')
+    result = trans.direct_translate('hello', src='en', dst='yue')
+    assert result.src == 'en'
+    assert result.tmp == 'yue'
+    assert result.dst == 'yue'
+    assert result.mode == 'direct'
+    assert result.result_text == '你好'
+    mock_translator.translate.assert_called_once_with('hello', src='en', dest='yue')
+
+
 def test_auto_detect_src():
     trans, mock_translator = _build_trans()
     mock_translator.translate.side_effect = [
@@ -56,6 +82,14 @@ def test_auto_detect_src():
     assert result.src == 'en'
 
 
+def test_direct_auto_detect_src():
+    trans, mock_translator = _build_trans()
+    mock_translator.translate.return_value = _make_translate_result('你好')
+    result = trans.direct_translate('hello', dst='zh-cn')
+    assert result.src == 'en'
+    mock_translator.detect.assert_called_once_with('hello')
+
+
 def test_default_tmp_when_src_en():
     trans, mock_translator = _build_trans()
     mock_translator.translate.side_effect = [
@@ -76,24 +110,62 @@ def test_default_tmp_when_src_not_en():
     assert result.tmp == 'en'
 
 
+def test_back_translation_with_cantonese_tmp():
+    trans, mock_translator = _build_trans()
+    mock_translator.translate.side_effect = [
+        _make_translate_result('你好'),
+        _make_translate_result('Hello there'),
+    ]
+    result = trans.translate('hello', src='en', tmp='yue')
+    assert result.src == 'en'
+    assert result.tmp == 'yue'
+    assert result.dst == 'yue'
+    assert result.tran_text == '你好'
+    assert result.result_text == 'Hello there'
+
+
 def test_invalid_src_raises():
     trans, _ = _build_trans()
     with pytest.raises(ValueError, match='INVALID source language'):
         trans.translate('hello', src='xx')
 
 
+def test_direct_missing_dst_raises():
+    trans, _ = _build_trans()
+    with pytest.raises(ValueError, match='destination language is required'):
+        trans.direct_translate('hello', src='en')
+
+
+def test_direct_invalid_src_raises():
+    trans, _ = _build_trans()
+    with pytest.raises(ValueError, match='INVALID source language'):
+        trans.direct_translate('hello', src='xx', dst='zh-cn')
+
+
 def test_invalid_tmp_raises():
     trans, _ = _build_trans()
     with pytest.raises(ValueError, match='INVALID transited language'):
         trans.translate('hello', src='en', tmp='xx')
 
 
+def test_direct_invalid_dst_raises():
+    trans, _ = _build_trans()
+    with pytest.raises(ValueError, match='INVALID destination language'):
+        trans.direct_translate('hello', src='en', dst='xx')
+
+
 def test_same_src_tmp_raises():
     trans, _ = _build_trans()
     with pytest.raises(ValueError, match='should different'):
         trans.translate('hello', src='en', tmp='en')
 
 
+def test_direct_same_src_dst_raises():
+    trans, _ = _build_trans()
+    with pytest.raises(ValueError, match='should different'):
+        trans.direct_translate('hello', src='en', dst='en')
+
+
 def test_sleeping_is_called(mocker):
     trans, mock_translator = _build_trans()
     mock_translator.translate.side_effect = [
@@ -112,6 +184,13 @@ def test_connect_timeout_raises_friendly_message():
         trans.translate('hello', src='en', tmp='zh-cn')
 
 
+def test_direct_connect_timeout_raises_friendly_message():
+    trans, mock_translator = _build_trans()
+    mock_translator.translate.side_effect = httpcore.ConnectTimeout()
+    with pytest.raises(httpcore.ConnectTimeout, match='proxies'):
+        trans.direct_translate('hello', src='en', dst='zh-cn')
+
+
 def test_general_exception_raises_with_hint():
     trans, mock_translator = _build_trans()
     mock_translator.translate.side_effect = Exception('some googletrans error')
@@ -119,10 +198,24 @@ def test_general_exception_raises_with_hint():
         trans.translate('hello', src='en', tmp='zh-cn')
 
 
+def test_direct_general_exception_raises_with_hint():
+    trans, mock_translator = _build_trans()
+    mock_translator.translate.side_effect = Exception('some googletrans error')
+    with pytest.raises(Exception, match="sleeping"):
+        trans.direct_translate('hello', src='en', dst='zh-cn')
+
+
 def test_search_language():
     trans, _ = _build_trans()
     result = trans.searchLanguage('Chinese')
     assert 'zh-cn' in result.values()
+    assert 'yue' in result.values()
+
+
+def test_search_cantonese_language():
+    trans, _ = _build_trans()
+    result = trans.searchLanguage('Cantonese')
+    assert result == {'chinese (cantonese)': 'yue'}
 
 
 def test_search_language_not_found():
@@ -146,3 +239,17 @@ def test_long_text_split(mocker):
     result = trans.translate(long_text, src='en', tmp='zh-cn')
     assert result.src == 'en'
     assert mock_sleep.called
+
+
+def test_direct_long_text_split(mocker):
+    trans, mock_translator = _build_trans()
+    long_text = 'Hello world. ' * 500
+    sentences = ['Hello world. ' * 250, 'Hello world. ' * 250]
+    mock_translator.translate.return_value = [
+        _make_translate_result('你好一'),
+        _make_translate_result('你好二'),
+    ]
+    mocker.patch('BackTranslation.translation.sent_tokenize', return_value=sentences)
+    result = trans.direct_translate(long_text, src='en', dst='zh-cn')
+    assert result.result_text == '你好一 你好二'
+    mock_translator.translate.assert_called_once_with([s.rstrip() for s in sentences], src='en', dest='zh-cn')

{backtranslation-0.4.0 → backtranslation-0.5.0}/tests/test_translation_baidu.py

@@ -32,6 +32,29 @@ def test_basic_translation(trans):
     assert result.result_text == 'Hello there'
 
 
+def test_direct_translation(trans):
+    trans._sendRequest.return_value = _mock_response('en', '你好')
+    result = trans.direct_translate('hello', src='en', dst='zh')
+    assert result.src == 'en'
+    assert result.tmp == 'zh'
+    assert result.dst == 'zh'
+    assert result.mode == 'direct'
+    assert result.tran_text == '你好'
+    assert result.result_text == '你好'
+    trans._sendRequest.assert_called_once_with('hello', 'en', 'zh')
+
+
+def test_direct_translation_to_cantonese(trans):
+    trans._sendRequest.return_value = _mock_response('en', '你好')
+    result = trans.direct_translate('hello', src='en', dst='yue')
+    assert result.src == 'en'
+    assert result.tmp == 'yue'
+    assert result.dst == 'yue'
+    assert result.mode == 'direct'
+    assert result.result_text == '你好'
+    trans._sendRequest.assert_called_once_with('hello', 'en', 'yue')
+
+
 def test_back_translation_uses_tran_text_not_original(trans):
     """Issue #6: back-translation must use tran_text, not the original text."""
     calls = []
@@ -49,6 +72,23 @@ def test_back_translation_uses_tran_text_not_original(trans):
     assert calls[1][0] == '你好', "Back-translation must use intermediate text, not original"
 
 
+def test_back_translation_with_cantonese_tmp(trans):
+    trans._sendRequest.side_effect = [
+        _mock_response('en', '你好'),
+        _mock_response('yue', 'Hello there'),
+    ]
+    result = trans.translate('hello', src='en', tmp='yue')
+    assert result.src == 'en'
+    assert result.tmp == 'yue'
+    assert result.dst == 'yue'
+    assert result.tran_text == '你好'
+    assert result.result_text == 'Hello there'
+    assert trans._sendRequest.call_args_list == [
+        call('hello', 'en', 'yue'),
+        call('你好', 'yue', 'en'),
+    ]
+
+
 def test_auto_detect_src(trans):
     trans._sendRequest.side_effect = [
         _mock_response('en', 'detected'),
@@ -59,6 +99,19 @@ def test_auto_detect_src(trans):
     assert result.src == 'en'
 
 
+def test_direct_auto_detect_src(trans):
+    trans._sendRequest.return_value = _mock_response('en', '你好')
+    result = trans.direct_translate('hello', src='auto', dst='zh')
+    assert result.src == 'en'
+    trans._sendRequest.assert_called_once_with('hello', 'auto', 'zh')
+
+
+def test_direct_auto_detect_same_src_dst_raises(trans):
+    trans._sendRequest.return_value = _mock_response('en', 'hello')
+    with pytest.raises(ValueError, match='should different'):
+        trans.direct_translate('hello', src='auto', dst='en')
+
+
 def test_default_tmp_when_src_en(trans):
     trans._sendRequest.side_effect = [
         _mock_response('en', '你好'),
@@ -82,6 +135,16 @@ def test_same_src_tmp_raises(trans):
         trans.translate('hello', src='en', tmp='en')
 
 
+def test_direct_missing_dst_raises(trans):
+    with pytest.raises(ValueError, match='destination language is required'):
+        trans.direct_translate('hello', src='en')
+
+
+def test_direct_same_src_dst_raises(trans):
+    with pytest.raises(ValueError, match='should different'):
+        trans.direct_translate('hello', src='en', dst='en')
+
+
 def test_invalid_appid():
     with patch('BackTranslation.translation_Baidu.http.client.HTTPConnection'):
         with pytest.raises(ValueError, match='INVALID appid'):
@@ -113,3 +176,22 @@ def test_default_sleeping_is_one(trans, mocker):
     mock_sleep = mocker.patch('BackTranslation.translation_Baidu.time.sleep')
     trans.translate('hello', src='en', tmp='zh')
     mock_sleep.assert_called_with(1)
+
+
+def test_direct_long_text_split(trans, mocker):
+    long_text = 'Hello world. ' * 600
+    mocker.patch('BackTranslation.translation_Baidu.sent_tokenize', return_value=['ignored'])
+    mocker.patch.object(trans, '_split_segement', return_value=['hello one', 'hello two'])
+    trans._sendRequest.side_effect = [
+        _mock_response('en', '你好一'),
+        _mock_response('en', '你好二'),
+    ]
+    mock_sleep = mocker.patch('BackTranslation.translation_Baidu.time.sleep')
+    result = trans.direct_translate(long_text, src='auto', dst='zh')
+    assert result.src == 'en'
+    assert result.result_text == '你好一 你好二'
+    assert trans._sendRequest.call_args_list == [
+        call('hello one', 'auto', 'zh'),
+        call('hello two', 'en', 'zh'),
+    ]
+    mock_sleep.assert_called_once_with(1)