reach_commons 0.18.42__py3-none-any.whl → 0.18.43__py3-none-any.whl

reach_commons/sms_smart_encoding.py

@@ -2,6 +2,30 @@ from dataclasses import dataclass, field
 from math import ceil
 from typing import Union
 
+# Basic GSM-7 char set (without extension table handling).
+# If you want 100% accuracy for GSM-7, we can add the extension table later.
+GSM7_BASIC = set(
+    "@£$¥èéùìòÇ\nØø\rÅåΔ_ΦΓΛΩΠΨΣΘΞ"
+    "ÆæßÉ !\"#¤%&'()*+,-./"
+    "0123456789:;<=>?"
+    "¡ABCDEFGHIJKLMNOPQRSTUVWXYZÄÖÑܧ"
+    "¿abcdefghijklmnopqrstuvwxyzäöñüà"
+)
+
+
+def is_gsm7(text: str) -> bool:
+    return all(ch in GSM7_BASIC for ch in text)
+
+
+def ucs2_units(text: str) -> int:
+    # UTF-16 code units: emoji counts as 2 (surrogate pair), which matches UCS-2 segment math used in practice.
+    return len(text.encode("utf-16-be")) // 2
+
+
+def fix_surrogates(text: str) -> str:
+    # Turns surrogate pairs like \uD83D\uDC96 into the real character (💖)
+    return text.encode("utf-16", "surrogatepass").decode("utf-16")
+
 
 @dataclass
 class MessageSmartEncoding:
@@ -31,15 +55,25 @@ class MessageSmartEncoding:
     segments: int = field(init=False)
 
     def __post_init__(self):
-        # Convert body to string if it's a list
-        if isinstance(self.body, list):
-            body_text = " ".join(str(item) for item in self.body)
-        else:
-            body_text = self.body
+        body_text = (
+            " ".join(map(str, self.body))
+            if isinstance(self.body, list)
+            else str(self.body)
+        )
+        self.normalized_text = fix_surrogates(self.normalize(body_text))
 
-        self.normalized_text = self.normalize(body_text)
-        self.length = len(self.normalized_text)
-        self.segments = ceil(self.length / 160)
+        if is_gsm7(self.normalized_text):
+            self.encoding = "GSM-7"
+            text_length = len(self.normalized_text)
+            self.length = text_length
+            per_segment = 160 if text_length <= 160 else 153
+            self.segments = ceil(text_length / per_segment)
+        else:
+            self.encoding = "UCS-2"
+            text_units_count = ucs2_units(self.normalized_text)
+            self.length = text_units_count
+            per_segment = 70 if text_units_count <= 70 else 67
+            self.segments = ceil(text_units_count / per_segment)
 
     def normalize(self, text: str) -> str:
         for char, replacement in self.replacements.items():

{reach_commons-0.18.42.dist-info → reach_commons-0.18.43.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: reach_commons
-Version: 0.18.42
+Version: 0.18.43
 Summary: Reach Commons is a versatile utility library designed to streamline and enhance development workflows within the Reach ecosystem.
 License: MIT
 Author: Engineering

{reach_commons-0.18.42.dist-info → reach_commons-0.18.43.dist-info}/RECORD

@@ -27,9 +27,9 @@ reach_commons/reach_aws/s3.py,sha256=2MLlDNFx0SROJBpE_KjJefyrB7lMqTlrYuRhSZx4iKs
 reach_commons/reach_aws/sqs.py,sha256=IKKWrd-qbhMMVYUvGbaq1ouVRdx-0u-SqwYaTcp0tWY,21645
 reach_commons/reach_base_model.py,sha256=vgdGDcZr3iXMmyRhmBhOf_LKWB_6QzT3r_Yiyo6OmEk,3009
 reach_commons/redis_manager.py,sha256=yRed53ZKlbIb6rZnL53D1F_aB-xWT3nbeUP2cqYzhoc,3668
-reach_commons/sms_smart_encoding.py,sha256=92y0RmZ0l4ONHpC9qeO5KfViSNq64yE2rc7lhNDSZqE,1241
+reach_commons/sms_smart_encoding.py,sha256=Hpc9tIgTJM0ZKdhloSjgIPQCi52gDAFEOKIoO2rtJ30,2537
 reach_commons/utils.py,sha256=dMgKIGqTgoSItuBI8oz81gKtW3qi21Jkljv9leS_V88,8475
 reach_commons/validations.py,sha256=x_lkrtlrCAJC_f7mZb19JjfKFbYlPFv-P84K_lbZyYs,1056
-reach_commons-0.18.42.dist-info/METADATA,sha256=GcTKPeC_hnviyGqRmrpxr2VsoTr6SBdYwpPSQsH7MdQ,1863
-reach_commons-0.18.42.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-reach_commons-0.18.42.dist-info/RECORD,,
+reach_commons-0.18.43.dist-info/METADATA,sha256=BY3z5YCwX2Koe9hUbM4vrG6I0cID8zGUz9DkPm2dNT0,1863
+reach_commons-0.18.43.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+reach_commons-0.18.43.dist-info/RECORD,,