release: 1.0.0

first stable release. pre-1.0.0 verification complete: all surviving MED regressions and
gaps resolved and independently re-fired, tree audited clean across the suite.

Signed-off-by: disqualifier <dev@disqualifier.me>

README.md

@@ -7,7 +7,7 @@ text chunking, timestamp helpers, interactive await-prompts, and a limit-safe se
 ## Install
 
 ```
-dpy_commons @ git+ssh://git@git.rethinkstudios.io/rethink-public/dpy_commons.git@v0.1.0
+dpy_commons @ git+ssh://git@git.rethinkstudios.io/rethink-public/dpy_commons.git@v0.1.3
 ```
 
 ## Usage
@@ -59,7 +59,9 @@ prompt stays live), disable their components after resolve/timeout, accept custo
 anywhere an emoji goes, and take `cleanup=True` to delete the prompt afterward. `choose`
 auto-switches to a select dropdown for more than 5 options or long labels, truncates select
 option labels and the placeholder to Discord's caps, and raises `ValueError` for more than 25
-options (Discord's per-select cap).
+options (Discord's per-select cap). An emoji-only key is label-less on the button path (a
+button may be emoji-only), but on the select path it gets a non-empty fallback label (the
+key's own text form) alongside its emoji, since Discord rejects a select option with no label.
 
 ## What's inside
 
@@ -89,7 +91,10 @@ apply to **every** chunked message, not just the first, so a suppressed `@everyo
 stays suppressed across the whole split. Once-only kwargs (`file`, `files`, `stickers`,
 `nonce`, `reference`, `mention_author`, `view`, `poll`, `delete_after`) still ride the first
 message only. A bare `safe_send(destination)` with no content/embeds sends a single message
-with `content=None`.
+with `content=None`. A singular `embed=` kwarg is folded into the `embeds` pipeline (fit +
+split like any other embed); passing both `embed` and `embeds` raises `TypeError`, matching
+discord.py's own `Messageable.send` rule. Any kwarg `safe_send` doesn't recognize also raises
+`TypeError` naming it, rather than being silently dropped.
 
 ## Notes / deviations
 

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "dpy_commons"
-version = "0.1.1"
+version = "1.0.0"
 description = "Shared discord.py utilities — message/embed parsing, limit-fitting, link extraction, chunking, timestamps, await-prompts, limit-safe send. Config-free, installable."
 requires-python = ">=3.10"
 dependencies = [

src/dpy_commons/__init__.py

@@ -4,8 +4,12 @@ a module of functions grouped by concern: message/embed parsing, embed sanitizin
 limit-fitting, link extraction, text chunking, timestamp helpers, interactive await-prompts,
 and a limit-safe send. see each submodule's docstring for the contract.
 """
+from importlib.metadata import PackageNotFoundError, version
+
 from .embeds import fit_embed, sanitize_embed, split_embeds
 from .limits import (
+    BUTTON_LABEL_MAX,
+    BUTTON_ROW_MAX,
     EMBED_AUTHOR,
     EMBED_DESC,
     EMBED_FIELD_NAME,
@@ -16,6 +20,9 @@ from .limits import (
     EMBED_TOTAL,
     MSG_LIMIT,
     MSG_MAX_EMBEDS,
+    SELECT_MAX_OPTIONS,
+    SELECT_OPTION_LABEL_MAX,
+    SELECT_PLACEHOLDER_MAX,
 )
 from .parsing import extract_message_links, parse_message, sanitize_mentions
 from .prompts import choose, confirm
@@ -29,7 +36,10 @@ from .text import (
     wrap_bare_links,
 )
 
-__version__ = "0.1.1"
+try:
+    __version__ = version("dpy_commons")
+except PackageNotFoundError:
+    __version__ = "0.0.0+unknown"
 
 __all__ = [
     "parse_message",
@@ -57,5 +67,10 @@ __all__ = [
     "EMBED_TOTAL",
     "EMBED_MAX_FIELDS",
     "MSG_MAX_EMBEDS",
+    "BUTTON_ROW_MAX",
+    "BUTTON_LABEL_MAX",
+    "SELECT_OPTION_LABEL_MAX",
+    "SELECT_PLACEHOLDER_MAX",
+    "SELECT_MAX_OPTIONS",
     "__version__",
 ]

src/dpy_commons/embeds.py

@@ -2,6 +2,7 @@
 and split a list into sendable groups; none of these mutate their input"""
 from __future__ import annotations
 
+import copy
 import logging
 
 import discord
@@ -25,8 +26,12 @@ _ZWSP = "​"
 
 
 def _copy(embed: discord.Embed) -> discord.Embed:
-    """deep copy via dict round-trip so the input is never mutated"""
-    return discord.Embed.from_dict(embed.to_dict())
+    """deep copy via dict round-trip so the input is never mutated
+
+    discord.py 2.7.1's to_dict() reuses the embed's own _fields list rather than copying
+    it, so from_dict(embed.to_dict()) would still share that list with the input; the
+    explicit deepcopy breaks that aliasing"""
+    return discord.Embed.from_dict(copy.deepcopy(embed.to_dict()))
 
 
 def fit_embed(embed: discord.Embed) -> discord.Embed:
@@ -130,6 +135,22 @@ def _normalize_colour(value: object) -> "discord.Colour | None":
 
 
 def split_embeds(embeds: "list[discord.Embed]") -> "list[list[discord.Embed]]":
-    """chunk a list of embeds into groups of <= 10 (MSG_MAX_EMBEDS) so each group sends in one
-    message"""
-    return [embeds[i:i + MSG_MAX_EMBEDS] for i in range(0, len(embeds), MSG_MAX_EMBEDS)]
+    """chunk embeds into sendable groups bounded by BOTH the 10-per-message count and the
+    6000-char combined total (EMBED_TOTAL); a new group starts before either cap is exceeded
+
+    each embed is assumed already within its own limits (run fit_embed first); a single
+    embed over EMBED_TOTAL still lands alone in its own group"""
+    groups: "list[list[discord.Embed]]" = []
+    current: "list[discord.Embed]" = []
+    running = 0
+    for embed in embeds:
+        size = len(embed)
+        if current and (len(current) >= MSG_MAX_EMBEDS or running + size > EMBED_TOTAL):
+            groups.append(current)
+            current = []
+            running = 0
+        current.append(embed)
+        running += size
+    if current:
+        groups.append(current)
+    return groups

src/dpy_commons/prompts.py

@@ -10,6 +10,7 @@ treating a timeout as a normal None return.
 from __future__ import annotations
 
 import logging
+import unicodedata
 from typing import Any, Optional, Union
 
 import discord
@@ -172,7 +173,9 @@ async def choose(
     """render a button per option (or a select dropdown for >5 options or long labels), await
     the click, and return the chosen option's VALUE or None(timeout); options maps an emoji
     (unicode / '<:name:id>' / Emoji) or a label to a return value; raises ValueError on empty
-    options or more than 25 (discord's per-select option cap)"""
+    options or more than 25 (discord's per-select option cap); on the select path an
+    emoji-only key gets a non-empty fallback label (the key's text form) alongside its emoji,
+    since discord's select options require a label but a button may be emoji-only"""
     if not options:
         raise ValueError("choose requires at least one option")
     if len(options) > SELECT_MAX_OPTIONS:
@@ -190,8 +193,7 @@ async def choose(
             token = str(i)
             mapping[token] = options[key]
             label, emoji = _split_key(key)
-            if label is not None:
-                label = truncate(label, SELECT_OPTION_LABEL_MAX)
+            label = truncate(label or str(key) or " ", SELECT_OPTION_LABEL_MAX)
             select.add_option(label=label, value=token, emoji=emoji)
         view.add_item(select)
     else:
@@ -226,6 +228,43 @@ def _split_key(key: Any) -> "tuple[Optional[str], Optional[Union[str, discord.Pa
     return str(key), None
 
 
+def _is_emoji_codepoint(ch: str) -> bool:
+    """whether a single character is emoji-composition material
+
+    covers the pictographic symbols themselves (category So), skin-tone modifiers (Sk),
+    and the glue that binds a compound emoji into one grapheme: ZWJ (U+200D), variation
+    selectors (U+FE00-FE0F), regional-indicator letters (flags, U+1F1E6-1F1FF), and the
+    keycap combiner (U+20E3). a plain letter/digit/space is none of these.
+    """
+    code = ord(ch)
+    if ch == "‍" or ch == "⃣":
+        return True
+    if 0xFE00 <= code <= 0xFE0F:
+        return True
+    if 0x1F1E6 <= code <= 0x1F1FF:
+        return True
+    return unicodedata.category(ch) in ("So", "Sk")
+
+
 def _looks_unicode_emoji(value: str) -> bool:
-    """heuristic: a short non-ascii token is treated as a unicode emoji key"""
-    return bool(value) and len(value) <= 4 and not value.isascii()
+    """whether value is a unicode emoji key rather than a text label
+
+    true only when EVERY codepoint is emoji-composition material (see _is_emoji_codepoint)
+    and at least one is a pictographic symbol - so a compound emoji (ZWJ family, flag,
+    skin-tone) classifies as one emoji, while a short non-ascii text label (Sí/да/はい/確定/
+    café) is a label because its letters are not emoji codepoints. does not cap length:
+    a long emoji-only run is still an emoji, a run mixing letters and emoji is a label.
+    """
+    if not value:
+        return False
+    # a keycap sequence is [0-9#*] + optional VS16 + U+20E3 - its base is an ascii digit/
+    # symbol (not So), so treat the whole run as an emoji when the keycap combiner is present
+    if value.endswith("⃣") and all(c in "0123456789#*️⃣" for c in value):
+        return True
+    has_symbol = False
+    for ch in value:
+        if not _is_emoji_codepoint(ch):
+            return False
+        if unicodedata.category(ch) == "So":
+            has_symbol = True
+    return has_symbol

src/dpy_commons/send.py

@@ -34,14 +34,28 @@ async def safe_send(
     `view`, `poll`, `delete_after`) ride only on the FIRST message so they aren't duplicated
     across the split
 
+    a singular `embed=` kwarg is folded into the `embeds` pipeline (fit + split like any
+    other embed); passing both `embed` and `embeds` raises `TypeError`, matching
+    discord.py's own `Messageable.send` rule. Any other kwarg not recognized by either
+    whitelist above also raises `TypeError` naming it, instead of being silently dropped
+
     with no content and no embeds, one message is still sent (content=None) so a bare
     safe_send(destination) or a files/view-only call goes out as a single message rather than
     silently doing nothing"""
-    content_chunks = chunk_text(content) if content else []
-    embed_groups = split_embeds([fit_embed(embed) for embed in embeds]) if embeds else []
+    embed = kwargs.pop("embed", None)
+    if embed is not None:
+        if embeds is not None:
+            raise TypeError("safe_send() cannot mix embed and embeds")
+        embeds = [embed]
 
     per_chunk = {k: v for k, v in kwargs.items() if k in _PER_CHUNK_KWARGS}
     once_only = {k: v for k, v in kwargs.items() if k in _ONCE_ONLY_KWARGS}
+    unexpected = [k for k in kwargs if k not in _PER_CHUNK_KWARGS and k not in _ONCE_ONLY_KWARGS]
+    if unexpected:
+        raise TypeError(f"safe_send() got unexpected keyword argument(s): {', '.join(unexpected)}")
+
+    content_chunks = chunk_text(content) if content else []
+    embed_groups = split_embeds([fit_embed(e) for e in embeds]) if embeds else []
 
     messages: "list[discord.Message]" = []
     first = True
@@ -58,7 +72,10 @@ async def safe_send(
         first = False
 
     if not messages:
-        messages.append(await _send(destination, content, None, True, per_chunk, once_only))
+        # nothing chunked out (no content, or whitespace-only that chunk_text dropped) and no
+        # embeds: send content=None so a files/view-only call still goes out as one message,
+        # WITHOUT re-injecting the raw whitespace chunk_text discarded (which Discord 50006s)
+        messages.append(await _send(destination, None, None, True, per_chunk, once_only))
 
     return messages
 

src/dpy_commons/text.py

@@ -54,7 +54,7 @@ def chunk_text(text: str, limit: int = MSG_LIMIT) -> list[str]:
     if limit < 1:
         raise ValueError(f"limit must be >= 1, got {limit}")
     if len(text) <= limit:
-        return [text] if text else []
+        return [text] if text.strip() else []
 
     chunks: list[str] = []
     remaining = text
@@ -65,11 +65,13 @@ def chunk_text(text: str, limit: int = MSG_LIMIT) -> list[str]:
             split = window.rfind(" ")
         if split <= 0:
             split = limit
-        chunks.append(remaining[:split])
+        piece = remaining[:split]
+        if piece.strip():
+            chunks.append(piece)
         remaining = remaining[split:]
         if remaining.startswith(("\n", " ")):
             remaining = remaining[1:]
-    if remaining:
+    if remaining.strip():
         chunks.append(remaining)
     return chunks