mirror of
https://github.com/neovim/neovim.git
synced 2025-12-10 08:32:42 +00:00
Problem: Some servers write log to stdout and there's no way to avoid it. See https://github.com/neovim/neovim/pull/35743#pullrequestreview-3379705828 Solution: We can extract `content-length` field byte by byte and skip invalid lines via a simple state machine (name/colon/value/invalid), with minimal performance impact. I chose byte parsing here instead of pattern. Although it's a bit more complex, it provides more stable performance and allows for more accurate error info when needed. Here is a bench result and script: parse header1 by pattern: 59.52377ms 45 parse header1 by byte: 7.531128ms 45 parse header2 by pattern: 26.06936ms 45 parse header2 by byte: 5.235724ms 45 parse header3 by pattern: 9.348495ms 45 parse header3 by byte: 3.452389ms 45 parse header4 by pattern: 9.73156ms 45 parse header4 by byte: 3.638386ms 45 Script: ```lua local strbuffer = require('string.buffer') --- @param header string local function get_content_length(header) for line in header:gmatch('(.-)\r?\n') do if line == '' then break end local key, value = line:match('^%s*(%S+)%s*:%s*(%d+)%s*$') if key and key:lower() == 'content-length' then return assert(tonumber(value)) end end error('Content-Length not found in header: ' .. header) end --- @param header string local function get_content_length_by_byte(header) local state = 'name' local i, len = 1, #header local j, name = 1, 'content-length' local buf = strbuffer.new() local digit = true while i <= len do local c = header:byte(i) if state == 'name' then if c >= 65 and c <= 90 then -- lower case c = c + 32 end if (c == 32 or c == 9) and j == 1 then -- skip OWS for compatibility only elseif c == name:byte(j) then j = j + 1 elseif c == 58 and j == 15 then state = 'colon' else state = 'invalid' end elseif state == 'colon' then if c ~= 32 and c ~= 9 then -- skip OWS normally state = 'value' i = i - 1 end elseif state == 'value' then if c == 13 and header:byte(i + 1) == 10 then -- must end with \r\n local value = buf:get() return assert(digit and tonumber(value), 'value of Content-Length is not number: ' .. value) else buf:put(string.char(c)) end if c < 48 and c ~= 32 and c ~= 9 or c > 57 then digit = false end elseif state == 'invalid' then if c == 10 then -- reset for next line state, j = 'name', 1 end end i = i + 1 end error('Content-Length not found in header: ' .. header) end --- @param fn fun(header: string): number local function bench(label, header, fn, count) local start = vim.uv.hrtime() local value --- @type number for _ = 1, count do value = fn(header) end local elapsed = (vim.uv.hrtime() - start) / 1e6 print(label .. ':', elapsed .. 'ms', value) end -- header starting with log lines local header1 = 'WARN: no common words file defined for Khmer - this language might not be correctly auto-detected\nWARN: no common words file defined for Japanese - this language might not be correctly auto-detected\nContent-Length: 45 \r\n\r\n' -- header starting with content-type local header2 = 'Content-Type: application/json-rpc; charset=utf-8\r\nContent-Length: 45 \r\n' -- regular header local header3 = ' Content-Length: 45\r\n' -- regular header ending with content-type local header4 = ' Content-Length: 45 \r\nContent-Type: application/json-rpc; charset=utf-8\r\n' local count = 10000 collectgarbage('collect') bench('parse header1 by pattern', header1, get_content_length, count) collectgarbage('collect') bench('parse header1 by byte', header1, get_content_length_by_byte, count) collectgarbage('collect') bench('parse header2 by pattern', header2, get_content_length, count) collectgarbage('collect') bench('parse header2 by byte', header2, get_content_length_by_byte, count) collectgarbage('collect') bench('parse header3 by pattern', header3, get_content_length, count) collectgarbage('collect') bench('parse header3 by byte', header3, get_content_length_by_byte, count) collectgarbage('collect') bench('parse header4 by pattern', header4, get_content_length, count) collectgarbage('collect') bench('parse header4 by byte', header4, get_content_length_by_byte, count) ``` Also, I removed an outdated testaccd392f4d/test/functional/plugin/lsp_spec.lua (L1950)and tweaked the boilerplate in two other tests for reusability while keeping the final assertions the same.accd392f4d/test/functional/plugin/lsp_spec.lua (L5704)accd392f4d/test/functional/plugin/lsp_spec.lua (L5721)
112 lines
2.4 KiB
Lua
112 lines
2.4 KiB
Lua
-- Basic shim for LuaJIT's stringbuffer.
|
|
-- Note this does not implement the full API.
|
|
-- This is intentionally internal-only. If we want to expose it, we should
|
|
-- reimplement this a userdata and ship it as `string.buffer`
|
|
-- (minus the FFI stuff) for Lua 5.1.
|
|
local M = {}
|
|
|
|
local has_strbuffer, strbuffer = pcall(require, 'string.buffer')
|
|
|
|
if has_strbuffer then
|
|
M.new = strbuffer.new
|
|
|
|
-- Lua 5.1 does not have __len metamethod so we need to provide a len()
|
|
-- function to use instead.
|
|
|
|
--- @param buf vim._stringbuffer
|
|
--- @return integer
|
|
function M.len(buf)
|
|
return #buf
|
|
end
|
|
|
|
return M
|
|
end
|
|
|
|
--- @class vim._stringbuffer
|
|
--- @field private buf string[]
|
|
--- @field package len integer absolute length of the `buf`
|
|
--- @field package skip_ptr integer
|
|
local StrBuffer = {}
|
|
StrBuffer.__index = StrBuffer
|
|
|
|
--- @return string
|
|
function StrBuffer:tostring()
|
|
if #self.buf > 1 then
|
|
self.buf = { table.concat(self.buf) }
|
|
end
|
|
|
|
-- assert(self.len == #(self.buf[1] or ''), 'len mismatch')
|
|
|
|
if self.skip_ptr > 0 then
|
|
if self.buf[1] then
|
|
self.buf[1] = self.buf[1]:sub(self.skip_ptr + 1)
|
|
self.len = self.len - self.skip_ptr
|
|
end
|
|
self.skip_ptr = 0
|
|
end
|
|
|
|
-- assert(self.len == #(self.buf[1] or ''), 'len mismatch')
|
|
|
|
return self.buf[1] or ''
|
|
end
|
|
|
|
StrBuffer.__tostring = StrBuffer.tostring
|
|
|
|
--- @private
|
|
--- Efficiently peak at the first `n` characters of the buffer.
|
|
--- @param n integer
|
|
--- @return string
|
|
function StrBuffer:_peak(n)
|
|
local skip, buf1 = self.skip_ptr, self.buf[1]
|
|
if buf1 and (n + skip) < #buf1 then
|
|
return buf1:sub(skip + 1, skip + n)
|
|
end
|
|
return self:tostring():sub(1, n)
|
|
end
|
|
|
|
--- @param chunk string
|
|
function StrBuffer:put(chunk)
|
|
local s = tostring(chunk)
|
|
self.buf[#self.buf + 1] = s
|
|
self.len = self.len + #s
|
|
return self
|
|
end
|
|
|
|
--- @param str string
|
|
function StrBuffer:set(str)
|
|
return self:reset():put(str)
|
|
end
|
|
|
|
--- @param n? integer
|
|
--- @return string
|
|
function StrBuffer:get(n)
|
|
n = n or self.len
|
|
local r = self:_peak(n)
|
|
self:skip(n)
|
|
return r
|
|
end
|
|
|
|
--- @param n integer
|
|
function StrBuffer:skip(n)
|
|
self.skip_ptr = math.min(self.len, self.skip_ptr + n)
|
|
return self
|
|
end
|
|
|
|
function StrBuffer:reset()
|
|
self.buf = {}
|
|
self.skip_ptr = 0
|
|
self.len = 0
|
|
return self
|
|
end
|
|
|
|
function M.new()
|
|
return setmetatable({}, StrBuffer):reset()
|
|
end
|
|
|
|
--- @param buf vim._stringbuffer
|
|
function M.len(buf)
|
|
return buf.len - buf.skip_ptr
|
|
end
|
|
|
|
return M
|