fix(library): cut display titles at 80 UTF-16 units, never inside a pair
The server counted code points while the Library's JavaScript counts UTF-16 units, so a first line of emoji kept 80 emoji on cards but showed 40 in the Library. Both now cut at 80 UTF-16 units and drop a character that would straddle the limit instead of leaving half a surrogate pair.
This commit is contained in:
+19
-4
@@ -22,14 +22,29 @@ _JS_TRIM = "".join(map(chr, _TRIM_CODES))
|
||||
DISPLAY_TITLE_LIMIT = 80
|
||||
|
||||
|
||||
def _utf16_units(text: str) -> int:
|
||||
"""JavaScript ``length``: characters beyond the BMP count as two units."""
|
||||
return len(text) + sum(1 for ch in text if ord(ch) > 0xFFFF)
|
||||
|
||||
|
||||
def _utf16_prefix(text: str, units: int) -> str:
|
||||
"""The longest prefix within ``units`` UTF-16 units, never splitting a pair."""
|
||||
used = 0
|
||||
for index, ch in enumerate(text):
|
||||
used += 2 if ord(ch) > 0xFFFF else 1
|
||||
if used > units:
|
||||
return text[:index]
|
||||
return text
|
||||
|
||||
|
||||
def titled(stored_titles: tuple, text: object) -> tuple[str | None, str | None]:
|
||||
"""Return ``(title, source)``: a stored title, else the text's first line.
|
||||
|
||||
``source`` is ``"stored"`` for the first non-blank stored title (blank as
|
||||
in JavaScript's trim, like the Library view), ``"text"`` for the first line,
|
||||
and None when both are empty. The first line is trimmed and, past
|
||||
DISPLAY_TITLE_LIMIT characters, cut with an ellipsis like the Library's
|
||||
``title()``.
|
||||
DISPLAY_TITLE_LIMIT UTF-16 units, cut with an ellipsis like the Library's
|
||||
``libraryTitle()`` (never inside a surrogate pair).
|
||||
"""
|
||||
for title in stored_titles:
|
||||
if isinstance(title, str) and title.strip(_JS_TRIM):
|
||||
@@ -37,8 +52,8 @@ def titled(stored_titles: tuple, text: object) -> tuple[str | None, str | None]:
|
||||
if not isinstance(text, str):
|
||||
return None, None
|
||||
first = text.split("\n")[0].strip(_JS_TRIM)
|
||||
if len(first) > DISPLAY_TITLE_LIMIT:
|
||||
first = first[:DISPLAY_TITLE_LIMIT] + "\u2026"
|
||||
if _utf16_units(first) > DISPLAY_TITLE_LIMIT:
|
||||
first = _utf16_prefix(first, DISPLAY_TITLE_LIMIT) + "\u2026"
|
||||
return (first, "text") if first else (None, None)
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user