text-rewrite 0.1.0__py3-none-any.whl

text_rewrite/__init__.py

@@ -0,0 +1,3 @@
+from .pipeline import Pipeline
+
+__all__ = ["Pipeline"]

text_rewrite/filters/__init__.py

@@ -0,0 +1,9 @@
+from .base import BaseFilter
+from .hotword import HotwordFilter
+from .regex import RegexFilter
+from .ner import NERFilter
+from .jieba_ner import JiebaNERFilter
+from .fuzzy_phoneme import FuzzyPhonemeFilter
+from .entity_fuzzy import EntityAwareFuzzyFilter
+
+__all__ = ["BaseFilter", "HotwordFilter", "RegexFilter", "NERFilter", "JiebaNERFilter", "FuzzyPhonemeFilter", "EntityAwareFuzzyFilter"]

text_rewrite/filters/base.py

@@ -0,0 +1,15 @@
+from abc import ABC, abstractmethod
+
+class BaseFilter(ABC):
+    """
+    Abstract base class for all text filters.
+    """
+    def __init__(self, name: str = None):
+        self.name = name or self.__class__.__name__
+
+    @abstractmethod
+    def process(self, text: str) -> str:
+        """
+        Process the input text and return the filtered text.
+        """
+        pass

text_rewrite/filters/entity_fuzzy.py

@@ -0,0 +1,187 @@
+import logging
+import re
+from typing import List
+from collections import defaultdict
+from .base import BaseFilter
+from .fuzzy_phoneme import FuzzyPhonemeFilter
+logger = logging.getLogger(__name__)
+
+class EntityAwareFuzzyFilter(BaseFilter):
+    """
+    SOTA Entity-Aware Fuzzy Phoneme Filter.
+    Combines high-speed global phoneme matching with Jieba-based NER tagging
+    to correct ASR homophone errors accurately and efficiently.
+    """
+    def __init__(self, name: str = "EntityAwareFuzzyFilter", rules: List[str] = None):
+        """
+        :param rules: A list of rule strings. 
+                      Format: `[tag]word1:threshold1|word2:replacement2:threshold2`
+                      tag, replacement, and threshold are optional.
+                      Example: "[nr]叶开:0.8|张三:0.7", "李四:0.7", "欧阳锋"
+        """
+        super().__init__(name=name)
+        self.global_hotwords = {}
+        self.global_thresholds = {}
+        self.tagged_hotwords = defaultdict(dict)
+        self.tagged_thresholds = defaultdict(dict)
+        
+        self.global_filter = None
+        self.tagged_filters = {}
+        self.ner_filter = None
+        
+        if rules:
+            self.add_rules(rules)
+            
+    def add_rules(self, rules: List[str]):
+        tag_pattern = re.compile(r'^\[([^\]]+)\]')
+        for rule in rules:
+            self._parse_rule(rule, tag_pattern)
+                
+        self._rebuild_filters()
+        self._setup_ner_filter()
+
+    def _parse_rule(self, rule: str, tag_pattern: re.Pattern):
+        rule = rule.strip()
+        if not rule:
+            return
+            
+        tag_match = tag_pattern.match(rule)
+        tag = tag_match.group(1) if tag_match else None
+        
+        if tag_match:
+            rule = rule[tag_match.end():]
+            
+        parts = [p.strip() for p in rule.split('|')]
+        for part in parts:
+            if not part:
+                continue
+                
+            subparts = [sp.strip() for sp in part.split(':')]
+            word = subparts[0]
+            replacement = word
+            threshold = 0.6
+            
+            if len(subparts) == 2:
+                try:
+                    threshold = float(subparts[1])
+                except ValueError:
+                    replacement = subparts[1]
+            elif len(subparts) >= 3:
+                replacement = subparts[1]
+                try:
+                    threshold = float(subparts[2])
+                except ValueError:
+                    pass
+            
+            if tag:
+                self.tagged_hotwords[tag][word] = replacement
+                self.tagged_thresholds[tag][word] = threshold
+            else:
+                self.global_hotwords[word] = replacement
+                self.global_thresholds[word] = threshold
+
+    def _rebuild_filters(self):
+        # Rebuild global filter
+        if self.global_hotwords:
+            self.global_filter = FuzzyPhonemeFilter(hotwords=self.global_hotwords, threshold=0.6)
+            self.global_filter.custom_thresholds = self.global_thresholds
+            
+        # Rebuild tagged filters
+        for tag, hw_dict in self.tagged_hotwords.items():
+            f = FuzzyPhonemeFilter(hotwords=hw_dict, threshold=0.6)
+            f.custom_thresholds = self.tagged_thresholds[tag]
+            self.tagged_filters[tag] = f
+
+    def _setup_ner_filter(self):
+        # Init JiebaNERFilter if tagged rules exist
+        if not self.tagged_filters:
+            return
+
+        import functools
+        
+        # Cache the processing of individual words to avoid redundant phoneme DP searches
+        # Since tagged filters don't change state during processing, caching per tag is safe.
+        word_cache = {}
+        for tag in self.tagged_filters:
+            word_cache[tag] = functools.lru_cache(maxsize=4096)(self.tagged_filters[tag].process)
+            
+        def jieba_callback(terms, text):
+            new_text = text
+            
+            # Keep track of character offsets manually since jieba
+            # splits continuously.
+            offset = 0
+            entities = []
+            for term in terms:
+                word = term.word
+                tag_str = term.flag
+                
+                if tag_str in self.tagged_filters:
+                    entities.append({
+                        'word': word,
+                        'tag': tag_str,
+                        'start': offset,
+                        'end': offset + len(word)
+                    })
+                offset += len(word)
+            
+            # Process from back to front to avoid index shifting after string replacement
+            for ent in reversed(entities):
+                word = ent['word']
+                tag = ent['tag']
+                start = ent['start']
+                end = ent['end']
+                
+                # Fuzzy phoneme search on the isolated entity word (Cached)
+                corrected = word_cache[tag](word)
+                if corrected != word:
+                    new_text = new_text[:start] + corrected + new_text[end:]
+                    
+            return new_text
+
+        from .jieba_ner import JiebaNERFilter
+        self.ner_filter = JiebaNERFilter(replace_callback=jieba_callback)
+        self.ner_filter._load_model() # Pre-load it
+        
+        # Build prechecker
+        all_tagged_hw = {}
+        all_tagged_thresholds = {}
+        for tag, hw_dict in self.tagged_hotwords.items():
+            all_tagged_hw.update(hw_dict)
+            all_tagged_thresholds.update(self.tagged_thresholds[tag])
+            
+        if all_tagged_hw:
+            self.ner_prechecker = FuzzyPhonemeFilter(hotwords=all_tagged_hw, threshold=0.6)
+            self.ner_prechecker.custom_thresholds = all_tagged_thresholds
+        else:
+            self.ner_prechecker = None
+
+    def process(self, text: str) -> str:
+        """
+        Execute SOTA cascading replacement.
+        1. Global Numba match (fastest, for long words or safe thresholds).
+        2. Jieba NER constraint match (for tags like 'nr').
+        """
+        if not text:
+            return text
+
+            
+        # Step 1: Global substitution
+        if self.global_filter:
+            text = self.global_filter.process(text)
+            
+        # Step 2: Tag-constrained substitution
+        if self.ner_filter:
+            # 预检：如果不可能有带标签的热词出现，直接跳过 jieba 分词
+            skip_ner = False
+            if hasattr(self, 'ner_prechecker') and self.ner_prechecker:
+                from text_rewrite.utils.algo_phoneme import get_phoneme_info
+                inp = get_phoneme_info(text)
+                cands = self.ner_prechecker.rag.index.get_candidates(inp)
+                if not cands:
+                    skip_ner = True
+            
+            if not skip_ner:
+                text = self.ner_filter.process(text)
+            
+        return text

text_rewrite/filters/fuzzy_phoneme.py

@@ -0,0 +1,130 @@
+import logging
+from typing import Dict
+from .base import BaseFilter
+from ..utils.algo_phoneme import get_phoneme_info, get_phoneme_seq
+from ..utils.rag_fast import FastRAG
+
+logger = logging.getLogger(__name__)
+
+class FuzzyPhonemeFilter(BaseFilter):
+    """
+    Fuzzy Phoneme Filter using Numba JIT DP acceleration.
+    Handles exact and fuzzy phoneme matches to correct ASR homophone errors.
+    """
+    def __init__(self, name: str = "FuzzyPhonemeFilter", hotwords: Dict[str, str] = None, threshold: float = 0.6):
+        """
+        :param threshold: The similarity threshold (0.0 to 1.0) for a phoneme sequence to match.
+                          0.6 is a good default for allowing some ASR errors.
+        """
+        super().__init__(name=name)
+        self.rag = FastRAG(threshold=threshold)
+        self.hotword_replacements = {}
+        # Cache hw_info to avoid recomputing
+        self._hw_info_cache = {}
+        
+        # Optional mapping of original word -> specific threshold
+        self.custom_thresholds = {}
+        
+        if hotwords:
+            self.add_hotwords(hotwords)
+            
+    def add_hotwords(self, hotwords: Dict[str, str], custom_thresholds: Dict[str, float] = None):
+        """
+        Add hotwords dynamically.
+        :param hotwords: Dictionary mapping the phonetic target (e.g., "张三") to the replacement string (e.g., "张三").
+        :param custom_thresholds: Optional dictionary mapping target word to its specific threshold.
+        """
+        if custom_thresholds:
+            self.custom_thresholds.update(custom_thresholds)
+            
+        hw_dict = {}
+        for original, replacement in hotwords.items():
+            phonemes = get_phoneme_seq(original)
+            hw_dict[original] = phonemes
+            self.hotword_replacements[original] = replacement
+            self._hw_info_cache[original] = [p.info for p in phonemes]
+        
+        self.rag.add_hotwords(hw_dict)
+        self.rag.numba_searcher.build_cache(self._hw_info_cache)
+
+    def process(self, text: str) -> str:
+        """
+        Process text by converting to phonemes, searching for fuzzy matches, 
+        mapping indices back, and replacing.
+        """
+        if not text:
+            return text
+            
+        # 1. Get input phonemes with char_start/char_end
+        input_phonemes = get_phoneme_info(text)
+        if not input_phonemes:
+            return text
+            
+        # 2. Get candidates from inverted index to avoid full scan
+        candidates = self.rag.index.get_candidates(input_phonemes)
+        if not candidates:
+            return text
+            
+        input_info = [p.info for p in input_phonemes]
+        
+        # Find the absolute minimum threshold to query Numba, post-filter later
+        min_thresh = self.rag.threshold
+        if self.custom_thresholds:
+            min_thresh = min(min_thresh, min(self.custom_thresholds.values()))
+            
+        # 3. Perform fine-grained Numba Substring DP search
+        replacements = []
+        
+        # Pre-encode input_info ONCE to avoid O(N_candidates) encoding overhead
+        inp_codes, inp_langs, _, inp_is_ws, inp_is_we = self.rag.numba_searcher.encode_input_vecs(input_info)
+        
+        candidate_keys = [hw_key for hw_key, _ in candidates]
+        
+        batch_res = self.rag.numba_searcher.search_batch_with_encoded_input(
+            candidate_keys, inp_codes, inp_langs, inp_is_ws, inp_is_we, threshold=min_thresh
+        )
+        
+        for hw_key, res_list in batch_res.items():
+            for score, start_idx, end_idx in res_list:
+                # Apply word-specific threshold
+                if score >= self.custom_thresholds.get(hw_key, self.rag.threshold):
+                    replacements.append({
+                        'score': score,
+                        'start_idx': start_idx,
+                        'end_idx': end_idx,
+                        'replacement': self.hotword_replacements[hw_key]
+                    })
+        
+        if not replacements:
+            return text
+            
+        # 4. Resolve overlaps (greedy: highest score, then longest span)
+        replacements.sort(key=lambda x: (-x['score'], -(x['end_idx'] - x['start_idx'])))
+        
+        final_reps = []
+        used_indices = set()
+        for r in replacements:
+            r_set = set(range(r['start_idx'], r['end_idx']))
+            if not r_set.intersection(used_indices):
+                final_reps.append(r)
+                used_indices.update(r_set)
+                
+        # 5. Execute replacements from back to front to avoid index shifting issues
+        final_reps.sort(key=lambda x: x['start_idx'], reverse=True)
+        
+        result_text = text
+        for r in final_reps:
+            # Map phoneme index to char index
+            # end_idx is exclusive in phoneme array
+            start_p = r['start_idx']
+            end_p = r['end_idx'] - 1
+            
+            if start_p >= len(input_phonemes) or end_p >= len(input_phonemes) or start_p > end_p:
+                continue
+                
+            char_start = input_phonemes[start_p].char_start
+            char_end = input_phonemes[end_p].char_end
+            
+            result_text = result_text[:char_start] + r['replacement'] + result_text[char_end:]
+            
+        return result_text

text_rewrite/filters/hotword.py

@@ -0,0 +1,50 @@
+from typing import Dict, List
+from .base import BaseFilter
+
+try:
+    from flashtext import KeywordProcessor
+except ImportError:
+    KeywordProcessor = None
+
+
+class HotwordFilter(BaseFilter):
+    """
+    Hotword Filter for high-performance exact word replacements.
+    Uses Aho-Corasick algorithm via flashtext library.
+    Ideal for massive dictionaries (100k+ words).
+    """
+    def __init__(self, name: str = "HotwordFilter", hotwords: Dict[str, str] = None, case_sensitive: bool = False):
+        super().__init__(name=name)
+        if KeywordProcessor is None:
+            raise ImportError("flashtext library is required for HotwordFilter. Run `pip install flashtext`.")
+            
+        self.keyword_processor = KeywordProcessor(case_sensitive=case_sensitive)
+        if hotwords:
+            self.add_hotwords(hotwords)
+
+    def add_hotwords(self, hotwords: Dict[str, str]):
+        """
+        Add hotword replacements dynamically.
+        :param hotwords: Dictionary mapping original words to target replacement words.
+                         Note: flashtext format is { 'replacement': ['word1', 'word2'] } for add_keywords_from_dict.
+                         Since we get { 'word': 'replacement' }, we iterate or transform it.
+        """
+        for original_word, replacement_word in hotwords.items():
+            self.keyword_processor.add_keyword(original_word, replacement_word)
+
+    def remove_hotwords(self, words: List[str]):
+        """
+        Remove hotwords from the trie dynamically.
+        """
+        for word in words:
+            self.keyword_processor.remove_keyword(word)
+
+    def process(self, text: str) -> str:
+        """
+        Process text by efficiently finding and replacing all matching hotwords.
+        """
+        if not text:
+            return text
+            
+        # flashtext operates in O(N) where N is text length, extremely fast.
+        return self.keyword_processor.replace_keywords(text)

text_rewrite/filters/jieba_ner.py

@@ -0,0 +1,65 @@
+import logging
+from typing import Callable, Any
+from .base import BaseFilter
+
+logger = logging.getLogger(__name__)
+
+class JiebaNERFilter(BaseFilter):
+    """
+    Extremely fast POS/NER Filter using Jieba.
+    Uses `jieba.posseg` to perform POS tagging.
+    """
+    def __init__(self, name: str = "JiebaNERFilter", replace_callback: Callable[[Any, str], str] = None):
+        """
+        :param replace_callback: A custom function that takes the jieba.posseg output (generator of pairs)
+                                 and returns the modified text string.
+        """
+        super().__init__(name=name)
+        self.replace_callback = replace_callback
+        self._posseg = None
+        self._loaded = False
+
+    def _load_model(self):
+        """
+        Lazy load jieba to avoid overhead if not used.
+        """
+        if self._loaded:
+            return
+            
+        logger.info("Lazy loading Jieba POS tagger...")
+        try:
+            import jieba.posseg as pseg
+            self._posseg = pseg
+            # Warm up jieba to load dictionary
+            list(pseg.cut("预热"))
+            self._loaded = True
+            logger.info("Jieba loaded successfully.")
+        except ImportError:
+            raise ImportError("jieba is required for JiebaNERFilter. Run `pip install jieba`.")
+        except Exception as e:
+            logger.error(f"Failed to load jieba: {e}")
+            raise
+
+    def process(self, text: str) -> str:
+        if not text:
+            return text
+            
+        if not self._loaded:
+            self._load_model()
+            
+        if not self._posseg:
+            return text
+
+        try:
+            # pseg.cut returns a generator of pair(word, flag)
+            # flag corresponds to POS tag, e.g., 'nr' for person name
+            terms = list(self._posseg.cut(text, HMM=False))
+            
+            if self.replace_callback:
+                return self.replace_callback(terms, text)
+            else:
+                return text
+                
+        except Exception as e:
+            logger.error(f"Jieba NER processing failed: {e}")
+            return text

text_rewrite/filters/ner.py

@@ -0,0 +1,72 @@
+import logging
+from typing import Callable, Any
+from .base import BaseFilter
+
+logger = logging.getLogger(__name__)
+
+class NERFilter(BaseFilter):
+    """
+    NER Filter for replacing or normalizing entities based on Named Entity Recognition.
+    Uses HanLP. Supports lazy loading of the model to save memory until first use.
+    """
+    def __init__(self, name: str = "NERFilter", model_name: str = "LARGE_ALBERT_BASE", replace_callback: Callable[[Any], str] = None):
+        """
+        :param model_name: HanLP model identifier for NER/POS.
+        :param replace_callback: A custom function that takes the HanLP output (e.g., list of words/tags)
+                                 and returns the modified text string.
+        """
+        super().__init__(name=name)
+        self.model_name = model_name
+        self.replace_callback = replace_callback
+        self._model = None
+        self._loaded = False
+
+    def _load_model(self):
+        """
+        Lazy load the HanLP model.
+        """
+        if self._loaded:
+            return
+            
+        logger.info(f"Lazy loading HanLP NER model '{self.model_name}'...")
+        try:
+            import hanlp
+            # In a real scenario, you'd load the specific NER/POS model you need.
+            # Example: tok/pos/ner pipeline
+            self._model = hanlp.load(hanlp.pretrained.mtl.CLOSE_TOK_POS_NER_SRL_DEP_SDP_CON_ELECTRA_SMALL_ZH)
+            self._loaded = True
+            logger.info("HanLP NER model loaded successfully.")
+        except ImportError:
+            raise ImportError("hanlp is required for NERFilter. Run `pip install hanlp`.")
+        except Exception as e:
+            logger.error(f"Failed to load HanLP model: {e}")
+            raise
+
+    def process(self, text: str) -> str:
+        """
+        Process text by extracting entities and applying the replacement logic.
+        """
+        if not text:
+            return text
+            
+        if not self._loaded:
+            self._load_model()
+            
+        if not self._model:
+            return text # Fail-safe, return original if model failed to load but no exception was raised
+
+        try:
+            # Note: actual HanLP return format depends on the specific model loaded.
+            # Here we assume a MTL (multi-task learning) model that returns a dict.
+            doc = self._model(text)
+            
+            if self.replace_callback:
+                return self.replace_callback(doc, text)
+            else:
+                # Default behavior: do nothing if no callback is provided, or implement a basic rule
+                # (e.g., wrap entities in brackets). Here we just return the text.
+                return text
+                
+        except Exception as e:
+            logger.error(f"NER processing failed: {e}")
+            return text

text_rewrite/filters/regex.py

@@ -0,0 +1,42 @@
+import re
+from typing import Dict, List, Tuple
+from .base import BaseFilter
+
+class RegexFilter(BaseFilter):
+    """
+    Regex Filter for pattern-based text replacements.
+    Patterns are pre-compiled for performance.
+    """
+    def __init__(self, name: str = "RegexFilter", rules: Dict[str, str] = None):
+        super().__init__(name=name)
+        self.compiled_rules: List[Tuple[re.Pattern, str]] = []
+        if rules:
+            self.add_rules(rules)
+
+    def add_rules(self, rules: Dict[str, str]):
+        """
+        Add new regex replacement rules.
+        :param rules: A dictionary where key is the regex pattern and value is the replacement string.
+        """
+        for pattern, replacement in rules.items():
+            compiled_pattern = re.compile(pattern)
+            self.compiled_rules.append((compiled_pattern, replacement))
+
+    def clear_rules(self):
+        """
+        Clear all existing regex rules.
+        """
+        self.compiled_rules.clear()
+
+    def process(self, text: str) -> str:
+        """
+        Process text by sequentially applying all regex replacements.
+        """
+        if not text:
+            return text
+            
+        current_text = text
+        for compiled_pattern, replacement in self.compiled_rules:
+            current_text = compiled_pattern.sub(replacement, current_text)
+            
+        return current_text

text_rewrite/pipeline.py

@@ -0,0 +1,44 @@
+from typing import List
+import logging
+from .filters.base import BaseFilter
+
+logger = logging.getLogger(__name__)
+
+class Pipeline:
+    """
+    TextRewrite Pipeline.
+    Manages a sequence of filters and applies them to input text in order.
+    """
+    def __init__(self):
+        self.filters: List[BaseFilter] = []
+
+    def add_filter(self, text_filter: BaseFilter):
+        """
+        Register a filter to the pipeline.
+        """
+        if not isinstance(text_filter, BaseFilter):
+            raise TypeError("Filter must be an instance of BaseFilter")
+        self.filters.append(text_filter)
+        return self # For method chaining
+
+    def process(self, text: str) -> str:
+        """
+        Process the input text through all registered filters sequentially.
+        """
+        if not text:
+            return text
+            
+        current_text = text
+        for f in self.filters:
+            try:
+                current_text = f.process(current_text)
+            except Exception as e:
+                logger.error(f"Error processing text in filter {f.name}: {e}")
+                # Depending on strictness, we might want to re-raise or continue.
+                # For ASR/OCR robustness, continuing with the unmodified text of this step is often preferred.
+                continue
+                
+        return current_text
+
+    def __call__(self, text: str) -> str:
+        return self.process(text)