2024-05-05 19:32:23 +00:00
|
|
|
import re
|
|
|
|
|
import unicodedata
|
2024-05-22 05:28:32 +00:00
|
|
|
import functools
|
2024-05-05 19:32:23 +00:00
|
|
|
|
|
|
|
|
ANSI_ESCAPE_SEQUENCE = re.compile(r"\x1b\[[ -@]*[A-~]")
|
|
|
|
|
|
|
|
|
|
|
2024-05-22 05:28:32 +00:00
|
|
|
@functools.cache
|
2024-05-05 19:32:23 +00:00
|
|
|
def str_width(c: str) -> int:
|
2024-05-22 05:28:32 +00:00
|
|
|
if ord(c) < 128:
|
|
|
|
|
return 1
|
2024-05-05 19:32:23 +00:00
|
|
|
w = unicodedata.east_asian_width(c)
|
|
|
|
|
if w in ('N', 'Na', 'H', 'A'):
|
|
|
|
|
return 1
|
|
|
|
|
return 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def wlen(s: str) -> int:
|
gh-119517: Fixes for pasting in pyrepl (#120253)
* Remove pyrepl's optimization for self-insert
This will be replaced by a less specialized optimization.
* Use line-buffering when pyrepl echoes pastes
Previously echoing was totally suppressed until the entire command had
been pasted and the terminal ended paste mode, but this gives the user
no feedback to indicate that an operation is in progress. Drawing
something to the screen once per line strikes a balance between
perceived responsiveness and performance.
* Remove dead code from pyrepl
`msg_at_bottom` is always true.
* Speed up pyrepl's screen rendering computation
The Reader in pyrepl doesn't hold a complete representation of the
screen area being drawn as persistent state. Instead, it recomputes it,
on each keypress. This is fast enough for a few hundred bytes, but
incredibly slow as the input buffer grows into the kilobytes (likely
because of pasting).
Rather than making some expensive and expansive changes to the repl's
internal representation of the screen, add some caching: remember some
data from one refresh to the next about what was drawn to the screen
and, if we don't find anything that has invalidated the results that
were computed last time around, reuse them. To keep this caching as
simple as possible, all we'll do is look for lines in the buffer that
were above the cursor the last time we were asked to update the screen,
and that are still above the cursor now. We assume that nothing can
affect a line that comes before both the old and new cursor location
without us being informed. Based on this assumption, we can reuse old
lines, which drastically speeds up the overwhelmingly common case where
the user is typing near the end of the buffer.
* Speed up pyrepl prompt drawing
Cache the `can_colorize()` call rather than repeatedly recomputing it.
This call looks up an environment variable, and is called once per
character typed at the REPL. The environment variable lookup shows up as
a hot spot when profiling, and we don't expect this to change while the
REPL is running.
* Speed up pasting multiple lines into the REPL
Previously, we were checking whether the command should be accepted each
time a line break was encountered, but that's not the expected behavior.
In bracketed paste mode, we expect everything pasted to be part of
a single block of code, and encountering a newline shouldn't behave like
a user pressing <Enter> to execute a command. The user should always
have a chance to review the pasted command before running it.
* Use a read buffer for input in pyrepl
Previously we were reading one byte at a time, which causes much slower
IO than necessary. Instead, read in chunks, processing previously read
data before asking for more.
* Optimize finding width of a single character
`wlen` finds the width of a multi-character string by adding up the
width of each character, and then subtracting the width of any escape
sequences. It's often called for single character strings, however,
which can't possibly contain escape sequences. Optimize for that case.
* Optimize disp_str for ASCII characters
Since every ASCII character is known to display as single width, we can
avoid not only the Unicode data lookup in `disp_str` but also the one
hidden in `str_width` for them.
* Speed up cursor movements in long pyrepl commands
When the current pyrepl command buffer contains many lines, scrolling up
becomes slow. We have optimizations in place to reuse lines above the
cursor position from one refresh to the next, but don't currently try to
reuse lines below the cursor position in the same way, so we wind up
with quadratic behavior where all lines of the buffer below the cursor
are recomputed each time the cursor moves up another line.
Optimize this by only computing one screen's worth of lines beyond the
cursor position. Any lines beyond that can't possibly be shown by the
console, and bounding this makes scrolling up have linear time
complexity instead.
---------
Signed-off-by: Matt Wozniski <mwozniski@bloomberg.net>
Co-authored-by: Pablo Galindo <pablogsal@gmail.com>
2024-06-11 16:42:10 +00:00
|
|
|
if len(s) == 1:
|
|
|
|
|
return str_width(s)
|
2024-05-05 19:32:23 +00:00
|
|
|
length = sum(str_width(i) for i in s)
|
|
|
|
|
# remove lengths of any escape sequences
|
2024-05-22 05:28:32 +00:00
|
|
|
sequence = ANSI_ESCAPE_SEQUENCE.findall(s)
|
2024-07-30 12:03:52 +00:00
|
|
|
ctrl_z_cnt = s.count('\x1a')
|
|
|
|
|
return length - sum(len(i) for i in sequence) + ctrl_z_cnt
|