sharedkernel 2.7.0__py3-none-any.whl → 2.9.0__py3-none-any.whl

sharedkernel/chunker/chunk_rule.py

@@ -0,0 +1,84 @@
+from __future__ import annotations
+import re
+from typing import List, Optional, Protocol, Tuple
+
+
+class SplitRule(Protocol):
+    """Interface for chunk split rules."""
+
+    def apply(
+        self, segment: str, offset: int
+    ) -> Tuple[Optional[int], Optional[str], Optional[str]]: ...
+
+
+class PunctuationRule(SplitRule):
+    """Split after the first matching punctuation character."""
+
+    def __init__(self, punctuations: str = ".,;:!?"):
+        self.punctuations = set(punctuations)
+
+    def apply(
+        self, segment: str, offset: int
+    ) -> Tuple[Optional[int], Optional[str], Optional[str]]:
+        for i, ch in enumerate(segment):
+            if ch in self.punctuations:
+                return offset + i + 1, ch, "punctuation"
+        return None, None, None
+
+
+class RegexRule(SplitRule):
+    """Split after the first regex match."""
+
+    def __init__(self, pattern: str):
+        self.regex = re.compile(pattern) if pattern else None
+
+    def apply(
+        self, segment: str, offset: int
+    ) -> Tuple[Optional[int], Optional[str], Optional[str]]:
+        if not self.regex:
+            return None, None, None
+        m = self.regex.search(segment)
+        if m:
+            return offset + m.end(), segment[m.start() : m.end()], "regex"
+        return None, None, None
+
+
+class CutWordRule(SplitRule):
+    """Split after the first occurrence of any configured word/phrase."""
+
+    def __init__(self, cut_words: List[str]):
+        self.cut_words = [w.lower() for w in cut_words]
+
+    def apply(
+        self, segment: str, offset: int
+    ) -> Tuple[Optional[int], Optional[str], Optional[str]]:
+        lowered = segment.lower()
+        for word in self.cut_words:
+            idx = lowered.find(word)
+            if idx != -1:
+                phrase = segment[idx : idx + len(word)]
+                return offset + idx + len(word), phrase, "cut_word"
+        return None, None, None
+
+
+class SpaceFallbackRule(SplitRule):
+    """Split near the center on space; otherwise hard-cut at max_len."""
+
+    def __init__(self, max_len: int):
+        self.max_len = max_len
+
+    def apply(
+        self, segment: str, offset: int
+    ) -> Tuple[Optional[int], Optional[str], Optional[str]]:
+        centre = len(segment) // 2
+        left = segment.rfind(" ", 0, centre)
+        right = segment.find(" ", centre)
+
+        if left != -1:
+            split = left
+        elif right != -1:
+            split = right
+        else:
+            split = self.max_len
+
+        return offset + split, None, "space_fallback"

sharedkernel/chunker/text_chunker.py

@@ -0,0 +1,107 @@
+from dataclasses import dataclass
+from typing import List, Optional
+
+from .chunk_rule import (
+    SplitRule,
+)
+
+
+@dataclass
+class Chunk:
+    """A single chunk produced by TextChunker."""
+
+    text: str
+    number: int
+    begin: int
+    end: int
+    method: str
+    phrase: Optional[str]
+
+
+class TextChunker:
+    """Split text into chunks based on ordered split rules."""
+
+    def __init__(self, min_len: int, max_len: int, rules: List[SplitRule]):
+        if min_len < 1:
+            raise ValueError("min_len must be >= 1")
+        if max_len < min_len:
+            raise ValueError("max_len must be >= min_len")
+
+        self.min_len = min_len
+        self.max_len = max_len
+        self.rules = rules
+
+    def chunk(self, text: str) -> List[Chunk]:
+        if not text:
+            return []
+
+        chunks: List[Chunk] = []
+        pos = 0
+        number = 1
+
+        while pos < len(text):
+            if len(text) - pos <= self.max_len:
+                chunk_text = text[pos:]
+                chunks.append(Chunk(chunk_text, number, pos, len(text), "final", None))
+                break
+
+            window_end = pos + self.max_len
+            window = text[pos:window_end]
+
+            split_idx: Optional[int] = None
+            phrase: Optional[str] = None
+            method: Optional[str] = None
+
+            for rule in self.rules:
+                candidate, cand_phrase, cand_method = rule.apply(window, pos)
+                if candidate is not None and candidate - pos >= self.min_len:
+                    split_idx, phrase, method = candidate, cand_phrase, cand_method
+                    break
+
+            if split_idx is None:
+                split_idx = pos + self.max_len
+                method = "hard_cut"
+
+            chunk_text = text[pos:split_idx]
+            chunks.append(Chunk(chunk_text, number, pos, split_idx, method, phrase))
+            pos = split_idx
+            number += 1
+
+        return chunks
+
+    def chunks(self, text: str):
+        """Yield chunks lazily, using the same logic as `chunk`."""
+        if not text:
+            return
+
+        pos = 0
+        number = 1
+
+        while pos < len(text):
+            if len(text) - pos <= self.max_len:
+                chunk_text = text[pos:]
+                yield Chunk(chunk_text, number, pos, len(text), "final", None)
+                break
+
+            window_end = pos + self.max_len
+            window = text[pos:window_end]
+
+            split_idx: Optional[int] = None
+            phrase: Optional[str] = None
+            method: Optional[str] = None
+
+            for rule in self.rules:
+                candidate, cand_phrase, cand_method = rule.apply(window, pos)
+                if candidate is not None and candidate - pos >= self.min_len:
+                    split_idx, phrase, method = candidate, cand_phrase, cand_method
+                    break
+
+            if split_idx is None:
+                split_idx = pos + self.max_len
+                method = "hard_cut"
+
+            chunk_text = text[pos:split_idx]
+            yield Chunk(chunk_text, number, pos, split_idx, method, phrase)
+
+            pos = split_idx
+            number += 1

sharedkernel/config.py

@@ -26,7 +26,6 @@ IP_SESSION_CACHE_DATABASE_NUMBER = os.getenv("IP_SESSION_CACHE_DATABASE_NUMBER")
 REDIS_URL = os.getenv("REDIS_URL")
 REDIS_PASSWORD = os.getenv("REDIS_PASSWORD")
 REDIS_USER = os.getenv("REDIS_USER")
-REDIS_CONNECTION_STRING = os.getenv("REDIS_CONNECTION_STRING")
 CACHE_DATABASE_NUMBER = os.getenv("CACHE_DATABASE_NUMBER")
 REDIS_CONNECTION_STRING = os.getenv(
     "REDIS_CONNECTION_STRING", f"redis://{REDIS_USER}:{REDIS_PASSWORD}@{REDIS_URL}"

sharedkernel/database/cache/redis_generic_cache.py

@@ -2,7 +2,7 @@ from typing import Generic, Optional, Type, TypeVar
 from pydantic import BaseModel
 from redis.asyncio import Redis
 
-from cache.cache_repository import CacheRepository
+from .cache_repository import CacheRepository
 
 T = TypeVar("T", bound=BaseModel)
 

sharedkernel/enum/__init__.py

@@ -1,2 +1,7 @@
 from .error_code import ErrorCode
-from .redis_mode_enum import RedisMode
+from .redis_mode_enum import RedisMode
+from .feature_key import FeatureKey
+from .plan_type import PlanType
+from .plan_interval import PlanInterval
+from .order_type import OrderType
+from .feature_display_type import FeatureDisplayType

sharedkernel/enum/error_code.py

@@ -9,3 +9,13 @@ class ErrorCode(str, Enum):
     Intents_Count_Should_Equal_One = "فقط یک اینتنت میتوانید وارد نمایید"
     Unsupported_Date_Type = "تاریخ داده شده پیشتیبانی نمیشود."
     Unsupported_IP = "آی پی داده شده معتبر نمی باشد"
+    Subscription_Not_Found = "اشتراک فعالی برای شما یافت نشد"
+    Subscription_Insufficient_Bot_Feature = "اعتبار شما برای ساخت بات کافی نیست"
+    Subscription_Insufficient_Message_Feature = "اعتبار شما برای ارسال پیام کافی نیست"
+    Subscription_Insufficient_URL_FEATURE = "اعتبار تعداد پردازش آدرس شما به اتمام رسیده"
+    Subscription_Insufficient_TEXT_FEATURE = "اعتبار تعداد پردازش متن شما به اتمام رسیده"
+    Subscription_Insufficient_FILE_FEATURE = "اعتبار تعداد پردازش فایل شما به اتمام رسیده"
+    Subscription_Insufficient_OCR_FEATURE = "اعتبار تعداد پردازش صفحات تصویر به متن شما به اتمام رسیده"
+    Subscription_Insufficient_TTS_FEATURE = "اعتبار تعداد پردازش متن به گفتار شما به اتمام رسیده"
+    Subscription_Insufficient_ASR_FEATURE = "اعتبار تعداد پردازش گفتار به متن شما به اتمام رسیده"
+    Subscription_Expired = "اشتراک شما منقضی شده است"

sharedkernel/enum/feature_display_type.py

@@ -0,0 +1,5 @@
+from enum import Enum
+
+class FeatureDisplayType(str, Enum):
+    LINEAR = "linear"
+    CIRCULAR = "circular"

sharedkernel/enum/feature_key.py

@@ -0,0 +1,11 @@
+from enum import Enum
+
+class FeatureKey(str, Enum):
+    MESSAGES = "messages"
+    ASR = "asr"
+    TTS = "tts"
+    BOTS = "bots"
+    FILES = "files"
+    URLS = "urls"
+    TEXTS = "texts"
+    OCR = "ocr"

sharedkernel/enum/order_type.py

@@ -0,0 +1,5 @@
+from enum import Enum
+
+class OrderType(str, Enum):
+    PLAN = "plan"
+    FEATURE_TOPUP = "feature_topup"

sharedkernel/enum/plan_interval.py

@@ -0,0 +1,7 @@
+from enum import Enum
+
+class PlanInterval(str, Enum):
+    DAY = 'day'
+    WEEK = 'week'
+    MONTH = 'month'
+    YEAR = 'year'

sharedkernel/enum/plan_type.py

@@ -0,0 +1,7 @@
+from enum import Enum
+
+class PlanType(str, Enum):
+    NORMAL = 'normal'
+    CUSTOM = 'custom'
+    FREE = 'free'
+    UNLIMITED = "unlimited"

sharedkernel/objects/subscription.py

@@ -0,0 +1,33 @@
+from datetime import datetime
+from typing import List, Optional
+from pydantic import BaseModel
+from sharedkernel.objects.base_document import BaseDocument
+from sharedkernel.enum import PlanInterval, OrderType, PlanType, FeatureKey, FeatureDisplayType
+
+
+class SubscriptionFeature(BaseModel):
+    feature_key: FeatureKey
+    feature_unit: Optional[str] = None
+    remaining: int
+    original: int
+    title: str
+    description: Optional[str] = None
+    display_type: FeatureDisplayType = FeatureDisplayType.CIRCULAR
+
+class Subscription(BaseDocument):
+    order_id: str
+    plan_id: str
+    plan_title: str
+    user_id: str
+    workspace_id: str
+    interval: PlanInterval
+    interval_count: int
+    type: OrderType
+    plan_type: PlanType | None = PlanType.FREE
+    features: List[SubscriptionFeature] | None = []
+    paid_at: datetime | None = None
+    from_date: datetime | None = None
+    to_date: datetime | None = None
+    is_active: bool
+    sum_messages: int | None = 0
+    avg_messages: float | None = 0

sharedkernel/toolbox_service.py

@@ -0,0 +1,70 @@
+from typing import Type
+from pydantic import BaseModel
+import aiohttp
+
+from sharedkernel.objects.result import Result
+from sharedkernel.enum import FeatureKey, PlanType
+from sharedkernel.enum import ErrorCode
+from sharedkernel.objects.subscription import Subscription
+from sharedkernel.exception.exception import BusinessException
+
+
+class ToolboxService:
+    def __init__(self, cache):
+        self.cache = cache
+
+    async def send_request(
+        self,
+        method: str,
+        endpoint: str,
+        payload: dict = None,
+        params: dict | None = None,
+        headers: dict | None = None,
+        model: Type[BaseModel] | None = None,
+    ) -> Result:
+
+        async with aiohttp.ClientSession() as session:
+            async with session.request(
+                method=method.upper(),
+                url=endpoint,
+                json=payload,
+                params=params,
+                headers=headers,
+            ) as response:
+
+                response_data = await response.json()
+                return Result(
+                    **response_data,
+                )
+
+
+
+    def check_user_subscription(
+        self,
+        user_subscription: Subscription,
+        feature: FeatureKey,
+        quantity: int = 1
+    ):
+
+        feature_errors = {
+            FeatureKey.MESSAGES: ErrorCode.Subscription_Insufficient_Message_Feature,
+            FeatureKey.BOTS: ErrorCode.Subscription_Insufficient_Bot_Feature,
+            FeatureKey.URLS: ErrorCode.Subscription_Insufficient_URL_FEATURE,
+            FeatureKey.TEXTS: ErrorCode.Subscription_Insufficient_TEXT_FEATURE,
+            FeatureKey.FILES: ErrorCode.Subscription_Insufficient_FILE_FEATURE,
+            FeatureKey.OCR: ErrorCode.Subscription_Insufficient_OCR_FEATURE,
+            FeatureKey.TTS: ErrorCode.Subscription_Insufficient_TTS_FEATURE,
+            FeatureKey.ASR: ErrorCode.Subscription_Insufficient_ASR_FEATURE,
+        }
+
+        if not user_subscription:
+            raise BusinessException(error_code=ErrorCode.Subscription_Not_Found)
+
+        if user_subscription.plan_type == PlanType.UNLIMITED:
+            return
+
+        for _feature in user_subscription.features:
+            if _feature.feature_key == feature:
+                if _feature.remaining - quantity < 0:
+                    raise BusinessException(error_code=feature_errors[feature])
+                break

{sharedkernel-2.7.0.dist-info → sharedkernel-2.9.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sharedkernel
-Version: 2.7.0
+Version: 2.9.0
 Summary: sharekernel is a shared package between all python projects
 Author: Smilinno
 Description-Content-Type: text/markdown
@@ -21,6 +21,7 @@ Requires-Dist: beautifulsoup4
 Requires-Dist: deepdiff
 Requires-Dist: kombu
 Requires-Dist: redis==8.0.0
+Requires-Dist: aiohttp
 Dynamic: author
 Dynamic: description
 Dynamic: description-content-type
@@ -31,6 +32,10 @@ Dynamic: summary
 this is a shared kernel package
 
 # Change Log
+### Version 2.9.0
+- Add toolbox_service
+### Version 2.8.0
+- Add chunker for tts
 ### Version 2.7.0
 - Add Redis and cache repository
 ### Version 2.6.4

{sharedkernel-2.7.0.dist-info → sharedkernel-2.9.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
 sharedkernel/common.py,sha256=HL5vsuJBaIeBcoXA8Hbe6jnYAv4danIszo5Y7G2gGDA,622
-sharedkernel/config.py,sha256=H_PjT9jawZqKtwnlVCSuefkh_b24QJX2ckP-YNGp6aA,1996
+sharedkernel/config.py,sha256=63qBvXrd7OYTInWg0g9g4cIRx6wGMoQcyTZjzDtQJ1U,1932
 sharedkernel/data_format_converter.py,sha256=GWGbfhKJBifkz-cfnqKAFjJM43WC0qdq9KSELj3xR30,3774
 sharedkernel/date_converter.py,sha256=Cjd4ewm0pIfQzv7nlgAAB_EYrr-VvXxQGehJCNphgXc,4491
 sharedkernel/diff_utils.py,sha256=mtwJmc05GAXUOB0ZLtqAhfBT1kGoSQ7qmP5N44P73ho,2564
@@ -10,6 +10,9 @@ sharedkernel/multipart_upload.py,sha256=JVlCBlznB9dWh2_spjAqzLOqQT1CHUTvrR4m7ug8
 sharedkernel/regex_masking.py,sha256=zQrgteP8Cuq1EC9B7QUJqAXUxK9ISD9kWMYK2AbRfw0,3288
 sharedkernel/s3_uploader.py,sha256=VWgN-RVHmLXMDuxgZux3M-iFwWk5zhRnUIECKS0auW4,3637
 sharedkernel/string_extentions.py,sha256=ld02W06gd0Ql80GQU6nlqPAeUSfOe2Yr8cCzf3lJgQY,98
+sharedkernel/toolbox_service.py,sha256=l4nPm7DiXCudeQd-JRYyS-T52g7q_YCsTJ9Sz9iDKAY,2440
+sharedkernel/chunker/chunk_rule.py,sha256=djxeQ3UvMx3_suH-heAQB0VwINT7uMfV7rnuuJChmwU,2531
+sharedkernel/chunker/text_chunker.py,sha256=QL8rQjJX-7U9TXMWiQBPldb9h1EeEECmFwLF1JLoGAM,3146
 sharedkernel/database/__init__.py,sha256=AtIbU7pDKwY6YCg_J8PX62WcYld1lAvBcVFW62MdiFg,241
 sharedkernel/database/audit_model.py,sha256=SMAYrvMb7XvPi4076TDgkOLaxh_3Jg_tfE12qKOy8RA,364
 sharedkernel/database/distributed_cache.py,sha256=XRhyK1MVBY-kPjFaAa99XVPE6ofdjBCdbvu_Xdh758k,3945
@@ -19,9 +22,14 @@ sharedkernel/database/mongo_health_checker.py,sha256=IYAaV8mJgGG_uxfnSRRvbq6Jybx
 sharedkernel/database/pagination_response_dto.py,sha256=91Gkajx4hHmYfypP7EJTiMP1ZrzopjwRuEyMrzQ3SVE,389
 sharedkernel/database/cache/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sharedkernel/database/cache/cache_repository.py,sha256=xL5Q18wgsSzIID_Zq8r0sa2OKC_c96q7cg2zUALzPwg,750
-sharedkernel/database/cache/redis_generic_cache.py,sha256=9_jUDfvUP37_IQ0ANDzniHv-Hj6lQDKPtJ0J76e8r7A,2526
-sharedkernel/enum/__init__.py,sha256=BQxVEO5O1PrNB8gm5nUrh_9Us2HcdgPF-8iZuro7UEM,73
-sharedkernel/enum/error_code.py,sha256=M_z-rAW4-zmWs1hMcc97zo4CpqzmoUidMarwo9UuNAk,551
+sharedkernel/database/cache/redis_generic_cache.py,sha256=kJbKeVFjmfgfRnZVhshSuQ21fcL9XSx5rzyqEeCR95w,2521
+sharedkernel/enum/__init__.py,sha256=pO4_p4pSJZWgeXHNej4j_cHGroQdnn46pOyShnh2bBE,273
+sharedkernel/enum/error_code.py,sha256=oVi85wKUxZNpoOQFD7f2j0tHWkNz9fKHbjCCIlqNSMM,1747
+sharedkernel/enum/feature_display_type.py,sha256=aMaLtbUu4vo_efCyRNmVVYIl_UgDwt5N_C4Ghf5YU10,107
+sharedkernel/enum/feature_key.py,sha256=6ZOfnduGlhDjx2fN3AqogQuEdIW4tRwYh04b4MkTUig,201
+sharedkernel/enum/order_type.py,sha256=Aj9p7il4HxM6iM_1QU9Obja6CH_e7j6RnFFRJcjJWbs,104
+sharedkernel/enum/plan_interval.py,sha256=Fn_E6NyswYa00OETE4E8wV8o4gNE7WfP6tsDxYO_fPQ,125
+sharedkernel/enum/plan_type.py,sha256=ExcPl8wKTbRu1gYB7jZqweaj-K1F8HTXlCuxEOIvl3g,139
 sharedkernel/enum/redis_mode_enum.py,sha256=v_n9g7_rq_pdMiZrC8mMveRcjgF3eBv3K2tsaV1Pidc,136
 sharedkernel/enum/sort_order.py,sha256=T_1AknuVg2OSJMlIDkEiCUNHPW0yDnFvbzoNpTgG3-I,97
 sharedkernel/exception/__init__.py,sha256=Yjkd1VsLFuzfWcMj-v8YYTA-vjtUlF4ESglBFeN1zvs,315
@@ -42,8 +50,9 @@ sharedkernel/objects/base_document.py,sha256=TERbRaZaW_zExm7Ddpk_3nCwMvSroGC3Kkd
 sharedkernel/objects/json_string_model.py,sha256=j63tnoqiok0EmBP6T-ChYuQYKPw7mLqUOHuaCDUZkmw,1333
 sharedkernel/objects/jwt_model.py,sha256=XQHQhTbg7PT8XiUh5fd9MwRH4ldPsesI_hfbjaSqdKg,134
 sharedkernel/objects/result.py,sha256=I_9hX5TPEO1oStzuFLjFh1rtimXorz7ml-OaW_2BMvc,680
+sharedkernel/objects/subscription.py,sha256=9MT2Vu-cf8ozO4pwh00ovk6aRNMjbJboKP8NkJgeSRI,1043
 sharedkernel/objects/user_info.py,sha256=51WyspRxlIWzK7Lfxgqg4D6mylXeHe9ZSenf-RhYTdA,286
-sharedkernel-2.7.0.dist-info/METADATA,sha256=8tNBtxeSL5t9rwHqbq94K3xGS3SXVyVjhWHCPZ56fW0,4092
-sharedkernel-2.7.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
-sharedkernel-2.7.0.dist-info/top_level.txt,sha256=TVTOnV1MItSSlpSjqkiijuHkoVsGHS4CArpsM-lylkE,13
-sharedkernel-2.7.0.dist-info/RECORD,,
+sharedkernel-2.9.0.dist-info/METADATA,sha256=twWnN61qrWLNK3QiXFbgzl273OXIfJOp4y0c8O9mEHk,4195
+sharedkernel-2.9.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+sharedkernel-2.9.0.dist-info/top_level.txt,sha256=TVTOnV1MItSSlpSjqkiijuHkoVsGHS4CArpsM-lylkE,13
+sharedkernel-2.9.0.dist-info/RECORD,,