Spaces:
Build error
Build error
File size: 12,025 Bytes
e3cb97b fdc056d e3cb97b fdc056d e3cb97b 6514731 e3cb97b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 |
"""Base class for translation provider implementations."""
import logging
import re
from abc import ABC, abstractmethod
from typing import List, TYPE_CHECKING
if TYPE_CHECKING:
from ...domain.models.translation_request import TranslationRequest
from ...domain.models.text_content import TextContent
from ...domain.interfaces.translation import ITranslationService
from ...domain.exceptions import TranslationFailedException
logger = logging.getLogger(__name__)
class TranslationProviderBase(ITranslationService, ABC):
"""Abstract base class for translation provider implementations."""
def __init__(self, provider_name: str, supported_languages: dict[str, list[str]] = None):
"""
Initialize the translation provider.
Args:
provider_name: Name of the translation provider
supported_languages: Dict mapping source languages to supported target languages
"""
self.provider_name = provider_name
self.supported_languages = supported_languages or {}
self.max_chunk_length = 1000 # Default chunk size for text processing
def translate(self, request: 'TranslationRequest') -> 'TextContent':
"""
Translate text from source language to target language.
Args:
request: The translation request
Returns:
TextContent: The translated text
Raises:
TranslationFailedException: If translation fails
"""
try:
logger.info(f"Starting translation with {self.provider_name} provider")
logger.info(f"Translating from {request.source_text.language} to {request.target_language}")
self._validate_request(request)
# Split text into chunks for processing
text_chunks = self._chunk_text(request.source_text.text)
logger.info(f"Split text into {len(text_chunks)} chunks for processing")
# Translate each chunk
translated_chunks = []
for i, chunk in enumerate(text_chunks):
logger.info(f"Translating chunk {i+1}/{len(text_chunks)}")
translated_chunk = self._translate_chunk(
chunk,
request.source_text.language,
request.target_language
)
translated_chunks.append(translated_chunk)
# Reassemble translated text
translated_text = self._reassemble_chunks(translated_chunks)
# Create TextContent from translation result
from ...domain.models.text_content import TextContent
result = TextContent(
text=translated_text,
language=request.target_language,
encoding='utf-8'
)
logger.info(f"Translation completed successfully with {self.provider_name}")
logger.info(f"Original length: {len(request.source_text.text)}, Translated length: {len(translated_text)}")
return result
except Exception as e:
logger.error(f"Translation failed with {self.provider_name}: {str(e)}")
raise TranslationFailedException(f"Translation failed: {str(e)}") from e
@abstractmethod
def _translate_chunk(self, text: str, source_language: str, target_language: str) -> str:
"""
Translate a single chunk of text using provider-specific implementation.
Args:
text: The text chunk to translate
source_language: Source language code
target_language: Target language code
Returns:
str: The translated text chunk
"""
pass
@abstractmethod
def is_available(self) -> bool:
"""
Check if the translation provider is available and ready to use.
Returns:
bool: True if provider is available, False otherwise
"""
pass
@abstractmethod
def get_supported_languages(self) -> dict[str, list[str]]:
"""
Get supported language pairs for this provider.
Returns:
dict: Mapping of source languages to supported target languages
"""
pass
def _chunk_text(self, text: str) -> List[str]:
"""
Split text into chunks for translation processing.
Args:
text: The text to chunk
Returns:
List[str]: List of text chunks
"""
if len(text) <= self.max_chunk_length:
return [text]
chunks = []
current_chunk = ""
# Split by sentences first to maintain context
sentences = self._split_into_sentences(text)
for sentence in sentences:
# If adding this sentence would exceed chunk limit
if len(current_chunk) + len(sentence) > self.max_chunk_length:
if current_chunk:
chunks.append(current_chunk.strip())
current_chunk = ""
# If single sentence is too long, split by words
if len(sentence) > self.max_chunk_length:
word_chunks = self._split_long_sentence(sentence)
chunks.extend(word_chunks[:-1]) # Add all but last chunk
current_chunk = word_chunks[-1] # Start new chunk with last piece
else:
current_chunk = sentence
else:
current_chunk += " " + sentence if current_chunk else sentence
# Add remaining chunk
if current_chunk.strip():
chunks.append(current_chunk.strip())
logger.info(f"Text chunked into {len(chunks)} pieces")
return chunks
def _split_into_sentences(self, text: str) -> List[str]:
"""
Split text into sentences using basic punctuation rules.
Args:
text: The text to split
Returns:
List[str]: List of sentences
"""
# Simple sentence splitting using regex
# This handles basic cases - more sophisticated NLP libraries could be used
sentence_endings = r'[.!?]+\s+'
sentences = re.split(sentence_endings, text)
# Filter out empty sentences and strip whitespace
sentences = [s.strip() for s in sentences if s.strip()]
return sentences
def _split_long_sentence(self, sentence: str) -> List[str]:
"""
Split a long sentence into smaller chunks by words.
Args:
sentence: The sentence to split
Returns:
List[str]: List of word chunks
"""
words = sentence.split()
chunks = []
current_chunk = ""
for word in words:
if len(current_chunk) + len(word) + 1 > self.max_chunk_length:
if current_chunk:
chunks.append(current_chunk.strip())
current_chunk = word
else:
# Single word is too long, just add it
chunks.append(word)
else:
current_chunk += " " + word if current_chunk else word
if current_chunk.strip():
chunks.append(current_chunk.strip())
return chunks
def _reassemble_chunks(self, chunks: List[str]) -> str:
"""
Reassemble translated chunks into a single text.
Args:
chunks: List of translated text chunks
Returns:
str: Reassembled text
"""
# Simple reassembly with space separation
# More sophisticated approaches could preserve original formatting
return " ".join(chunk.strip() for chunk in chunks if chunk.strip())
def _validate_request(self, request: 'TranslationRequest') -> None:
"""
Validate the translation request.
Args:
request: The translation request to validate
Raises:
TranslationFailedException: If request is invalid
"""
if not request.source_text.text.strip():
raise TranslationFailedException("Source text cannot be empty")
if request.source_text.language == request.target_language:
raise TranslationFailedException("Source and target languages cannot be the same")
# Check if language pair is supported
if self.supported_languages:
source_lang = request.source_text.language
target_lang = request.target_language
if source_lang not in self.supported_languages:
raise TranslationFailedException(
f"Source language {source_lang} not supported by {self.provider_name}. "
f"Supported source languages: {list(self.supported_languages.keys())}"
)
if target_lang not in self.supported_languages[source_lang]:
raise TranslationFailedException(
f"Translation from {source_lang} to {target_lang} not supported by {self.provider_name}. "
f"Supported target languages for {source_lang}: {self.supported_languages[source_lang]}"
)
def _preprocess_text(self, text: str) -> str:
"""
Preprocess text before translation.
Args:
text: The text to preprocess
Returns:
str: Preprocessed text
"""
# Basic text preprocessing
# Remove excessive whitespace
text = re.sub(r'\s+', ' ', text)
# Strip leading/trailing whitespace
text = text.strip()
return text
def _postprocess_text(self, text: str) -> str:
"""
Postprocess text after translation.
Args:
text: The text to postprocess
Returns:
str: Postprocessed text
"""
# Basic text postprocessing
# Remove excessive whitespace
text = re.sub(r'\s+', ' ', text)
# Strip leading/trailing whitespace
text = text.strip()
# Fix common spacing issues around punctuation
text = re.sub(r'\s+([.!?,:;])', r'\1', text)
text = re.sub(r'([.!?])\s*([A-Z])', r'\1 \2', text)
return text
def _handle_provider_error(self, error: Exception, context: str = "") -> None:
"""
Handle provider-specific errors and convert to domain exceptions.
Args:
error: The original error
context: Additional context about when the error occurred
"""
error_msg = f"{self.provider_name} error"
if context:
error_msg += f" during {context}"
error_msg += f": {str(error)}"
logger.error(error_msg, exception=error)
raise TranslationFailedException(error_msg) from error
def set_chunk_size(self, chunk_size: int) -> None:
"""
Set the maximum chunk size for text processing.
Args:
chunk_size: Maximum characters per chunk
"""
if chunk_size <= 0:
raise ValueError("Chunk size must be positive")
self.max_chunk_length = chunk_size
logger.info(f"Chunk size set to {chunk_size} characters")
def get_translation_stats(self, request: 'TranslationRequest') -> dict:
"""
Get statistics about a translation request.
Args:
request: The translation request
Returns:
dict: Translation statistics
"""
text = request.source_text.text
chunks = self._chunk_text(text)
return {
'provider': self.provider_name,
'source_language': request.source_text.language,
'target_language': request.target_language,
'text_length': len(text),
'word_count': len(text.split()),
'chunk_count': len(chunks),
'max_chunk_length': max(len(chunk) for chunk in chunks) if chunks else 0,
'avg_chunk_length': sum(len(chunk) for chunk in chunks) / len(chunks) if chunks else 0
} |