reach_commons 0.18.42__tar.gz → 0.18.43__tar.gz

{reach_commons-0.18.42 → reach_commons-0.18.43}/PKG-INFO

@@ -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 → reach_commons-0.18.43}/pyproject.toml

@@ -1,7 +1,7 @@
 # isort .; black .; poetry build; poetry publish
 [tool.poetry]
 name = "reach_commons"
-version = "0.18.42"
+version = "0.18.43"
 description = "Reach Commons is a versatile utility library designed to streamline and enhance development workflows within the Reach ecosystem."
 authors = ["Engineering <engineering@getreach.ai>"]
 license = "MIT"

reach_commons-0.18.43/reach_commons/sms_smart_encoding.py

@@ -0,0 +1,81 @@
+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:
+    """
+    Sms Message Representation
+    """
+
+    replacements = {
+        "“": '"',
+        "”": '"',
+        "‘": "'",
+        "’": "'",
+        "–": "-",
+        "—": "-",
+        "…": "...",
+        "•": "-",
+        "€": "EUR",
+        "™": "",
+        "©": "",
+        "®": "",
+        "\u0002": "",
+        "\u001b": "",
+    }
+    body: Union[str, list]
+    normalized_text: str = field(init=False)
+    length: int = field(init=False)
+    segments: int = field(init=False)
+
+    def __post_init__(self):
+        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))
+
+        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():
+            text = text.replace(char, replacement)
+        return text

reach_commons-0.18.42/reach_commons/sms_smart_encoding.py

@@ -1,47 +0,0 @@
-from dataclasses import dataclass, field
-from math import ceil
-from typing import Union
-
-
-@dataclass
-class MessageSmartEncoding:
-    """
-    Sms Message Representation
-    """
-
-    replacements = {
-        "“": '"',
-        "”": '"',
-        "‘": "'",
-        "’": "'",
-        "–": "-",
-        "—": "-",
-        "…": "...",
-        "•": "-",
-        "€": "EUR",
-        "™": "",
-        "©": "",
-        "®": "",
-        "\u0002": "",
-        "\u001b": "",
-    }
-    body: Union[str, list]
-    normalized_text: str = field(init=False)
-    length: int = field(init=False)
-    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
-
-        self.normalized_text = self.normalize(body_text)
-        self.length = len(self.normalized_text)
-        self.segments = ceil(self.length / 160)
-
-    def normalize(self, text: str) -> str:
-        for char, replacement in self.replacements.items():
-            text = text.replace(char, replacement)
-        return text