mirror of
https://github.com/koreader/koreader
synced 2024-10-31 21:20:20 +00:00
e9df73f6dc
* Fixed up all of util and added when absent * Updated widget examples to new coding style
376 lines
13 KiB
Lua
376 lines
13 KiB
Lua
--[[--
|
|
This module contains miscellaneous helper functions for the KOReader frontend.
|
|
]]
|
|
|
|
local BaseUtil = require("ffi/util")
|
|
local util = {}
|
|
|
|
--- Strips all punctuation and spaces from a string.
|
|
---- @string text the string to be stripped
|
|
---- @treturn string stripped text
|
|
function util.stripePunctuations(text)
|
|
if not text then return end
|
|
-- strip ASCII punctuation characters around text
|
|
-- and strip any generic punctuation (U+2000 - U+206F) in the text
|
|
return text:gsub("\226[\128-\131][\128-\191]", ''):gsub("^%p+", ''):gsub("%p+$", '')
|
|
end
|
|
|
|
--[[--
|
|
Splits a string by a pattern
|
|
|
|
Lua doesn't have a string.split() function and most of the time
|
|
you don't really need it because string.gmatch() is enough.
|
|
However string.gmatch() has one significant disadvantage for me:
|
|
You can't split a string while matching both the delimited
|
|
strings and the delimiters themselves without tracking positions
|
|
and substrings. The gsplit function below takes care of
|
|
this problem.
|
|
|
|
Author: Peter Odding
|
|
|
|
License: MIT/X11
|
|
|
|
Source: <a href="http://snippets.luacode.org/snippets/String_splitting_130">http://snippets.luacode.org/snippets/String_splitting_130</a>
|
|
]]
|
|
----@string str string to split
|
|
----@param pattern the pattern to split against
|
|
----@bool capture
|
|
function util.gsplit(str, pattern, capture)
|
|
pattern = pattern and tostring(pattern) or '%s+'
|
|
if (''):find(pattern) then
|
|
error('pattern matches empty string!', 2)
|
|
end
|
|
return coroutine.wrap(function()
|
|
local index = 1
|
|
repeat
|
|
local first, last = str:find(pattern, index)
|
|
if first and last then
|
|
if index < first then
|
|
coroutine.yield(str:sub(index, first - 1))
|
|
end
|
|
if capture then
|
|
coroutine.yield(str:sub(first, last))
|
|
end
|
|
index = last + 1
|
|
else
|
|
if index <= #str then
|
|
coroutine.yield(str:sub(index))
|
|
end
|
|
break
|
|
end
|
|
until index > #str
|
|
end)
|
|
end
|
|
|
|
--[[--
|
|
Converts seconds to a clock string.
|
|
|
|
Source: <a href="https://gist.github.com/jesseadams/791673">https://gist.github.com/jesseadams/791673</a>
|
|
]]
|
|
---- @int seconds number of seconds
|
|
---- @bool withoutSeconds if true 00:00, if false 00:00:00
|
|
---- @treturn string clock string in the form of 00:00 or 00:00:00
|
|
function util.secondsToClock(seconds, withoutSeconds)
|
|
seconds = tonumber(seconds)
|
|
if seconds == 0 or seconds ~= seconds then
|
|
if withoutSeconds then
|
|
return "00:00";
|
|
else
|
|
return "00:00:00";
|
|
end
|
|
else
|
|
local hours = string.format("%02.f", math.floor(seconds / 3600));
|
|
local mins = string.format("%02.f", math.floor(seconds / 60 - (hours * 60)));
|
|
if withoutSeconds then
|
|
return hours .. ":" .. mins
|
|
end
|
|
local secs = string.format("%02.f", math.floor(seconds - hours * 3600 - mins * 60));
|
|
return hours .. ":" .. mins .. ":" .. secs
|
|
end
|
|
end
|
|
|
|
--- Returns number of keys in a table.
|
|
---- @param T Lua table
|
|
---- @treturn int number of keys in table T
|
|
function util.tableSize(T)
|
|
local count = 0
|
|
for _ in pairs(T) do count = count + 1 end
|
|
return count
|
|
end
|
|
|
|
--- Append all elements from t2 into t1.
|
|
---- @param t1 Lua table
|
|
---- @param t2 Lua table
|
|
function util.arrayAppend(t1, t2)
|
|
for _, v in ipairs(t2) do
|
|
table.insert(t1, v)
|
|
end
|
|
end
|
|
|
|
--[[--
|
|
Gets last index of string in character
|
|
|
|
Returns the index within this string of the last occurrence of the specified character
|
|
or -1 if the character does not occur.
|
|
|
|
To find . you need to escape it.
|
|
]]
|
|
---- @string string
|
|
---- @string ch
|
|
---- @treturn int last occurrence or -1 if not found
|
|
function util.lastIndexOf(string, ch)
|
|
local i = string:match(".*" .. ch .. "()")
|
|
if i == nil then return -1 else return i - 1 end
|
|
end
|
|
|
|
|
|
--- Splits string into a list of UTF-8 characters.
|
|
---- @string text the string to be split.
|
|
---- @treturn table list of UTF-8 chars
|
|
function util.splitToChars(text)
|
|
local tab = {}
|
|
if text ~= nil then
|
|
local prevcharcode, charcode = 0
|
|
for uchar in string.gfind(text, "([%z\1-\127\194-\244][\128-\191]*)") do
|
|
charcode = BaseUtil.utf8charcode(uchar)
|
|
if prevcharcode then -- utf8
|
|
table.insert(tab, uchar)
|
|
end
|
|
prevcharcode = charcode
|
|
end
|
|
end
|
|
return tab
|
|
end
|
|
|
|
--- Tests whether c is a CJK character
|
|
---- @string c
|
|
---- @treturn boolean true if CJK
|
|
function util.isCJKChar(c)
|
|
return string.match(c, "[\228-\234][\128-\191].") == c
|
|
end
|
|
|
|
--- Tests whether str contains CJK characters
|
|
---- @string str
|
|
---- @treturn boolean true if CJK
|
|
function util.hasCJKChar(str)
|
|
return string.match(str, "[\228-\234][\128-\191].") ~= nil
|
|
end
|
|
|
|
--- Split texts into a list of words, spaces and punctuation.
|
|
---- @string text text to split
|
|
---- @treturn table list of words, spaces and punctuation
|
|
function util.splitToWords(text)
|
|
local wlist = {}
|
|
for word in util.gsplit(text, "[%s%p]+", true) do
|
|
-- if space splitted word contains CJK characters
|
|
if util.hasCJKChar(word) then
|
|
-- split with CJK characters
|
|
for char in util.gsplit(word, "[\228-\234\192-\255][\128-\191]+", true) do
|
|
table.insert(wlist, char)
|
|
end
|
|
else
|
|
table.insert(wlist, word)
|
|
end
|
|
end
|
|
return wlist
|
|
end
|
|
|
|
-- We don't want to split on a space if it is followed by some
|
|
-- specific punctuation : e.g. "word :" or "word )"
|
|
-- (In french, there is a space before a colon, and it better
|
|
-- not be wrapped there.)
|
|
local non_splittable_space_tailers = ":;,.!?)]}$%=-+*/|<>»”"
|
|
-- Same if a space has some specific other punctuation before it
|
|
local non_splittable_space_leaders = "([{$=-+*/|<>«“"
|
|
|
|
|
|
-- Similar rules exist for CJK text. Taken from :
|
|
-- https://en.wikipedia.org/wiki/Line_breaking_rules_in_East_Asian_languages
|
|
|
|
local cjk_non_splittable_tailers = table.concat( {
|
|
-- Simplified Chinese
|
|
"!%),.:;?]}¢°·’\"†‡›℃∶、。〃〆〕〗〞﹚﹜!"%'),.:;?!]}~",
|
|
-- Traditional Chinese
|
|
"!),.:;?]}¢·–—’\"•、。〆〞〕〉》」︰︱︲︳﹐﹑﹒﹔﹕﹖﹘﹚﹜!),.:;?︶︸︺︼︾﹀﹂﹗]|}、",
|
|
-- Japanese
|
|
")]}〕〉》」』】〙〗〟’\"⦆»ヽヾーァィゥェォッャュョヮヵヶぁぃぅぇぉっゃゅょゎゕゖㇰㇱㇲㇳㇴㇵㇶㇷㇸㇹㇺㇻㇼㇽㇾㇿ々〻‐゠–〜?!‼⁇⁈⁉・、:;,。.",
|
|
-- Korean
|
|
"!%),.:;?]}¢°’\"†‡℃〆〈《「『〕!%),.:;?]}",
|
|
})
|
|
|
|
local cjk_non_splittable_leaders = table.concat( {
|
|
-- Simplified Chinese
|
|
"$(£¥·‘\"〈《「『【〔〖〝﹙﹛$(.[{£¥",
|
|
-- Traditional Chinese
|
|
"([{£¥‘\"‵〈《「『〔〝︴﹙﹛({︵︷︹︻︽︿﹁﹃﹏",
|
|
-- Japanese
|
|
"([{〔〈《「『【〘〖〝‘\"⦅«",
|
|
-- Korean
|
|
"$([{£¥‘\"々〇〉》」〔$([{⦆¥₩#",
|
|
})
|
|
|
|
local cjk_non_splittable = table.concat( {
|
|
-- Japanese
|
|
"—…‥〳〴〵",
|
|
})
|
|
|
|
--- Test whether a string can be separated by this char for multi-line rendering.
|
|
-- Optional next or prev chars may be provided to help make the decision
|
|
---- @string c
|
|
---- @string next_c
|
|
---- @string prev_c
|
|
---- @treturn boolean true if splittable, false if not
|
|
function util.isSplittable(c, next_c, prev_c)
|
|
if util.isCJKChar(c) then
|
|
-- a CJKChar is a word in itself, and so is splittable
|
|
if cjk_non_splittable:find(c, 1, true) then
|
|
-- except a few of them
|
|
return false
|
|
elseif next_c and cjk_non_splittable_tailers:find(next_c, 1, true) then
|
|
-- but followed by a char that is not permitted at start of line
|
|
return false
|
|
elseif prev_c and cjk_non_splittable_leaders:find(prev_c, 1, true) then
|
|
-- but preceded by a char that is not permitted at end of line
|
|
return false
|
|
else
|
|
-- we can split on this CJKchar
|
|
return true
|
|
end
|
|
elseif c == " " then
|
|
-- we only split on a space (so punctuation sticks to prev word)
|
|
-- if next_c or prev_c is provided, we can make a better decision
|
|
if next_c and non_splittable_space_tailers:find(next_c, 1, true) then
|
|
-- this space is followed by some punctuation that is better kept with us
|
|
return false
|
|
elseif prev_c and non_splittable_space_leaders:find(prev_c, 1, true) then
|
|
-- this space is lead by some punctuation that is better kept with us
|
|
return false
|
|
else
|
|
-- we can split on this space
|
|
return true
|
|
end
|
|
end
|
|
-- otherwise, non splittable
|
|
return false
|
|
end
|
|
|
|
--- Gets filesystem type of a path.
|
|
--
|
|
-- Checks if the path occurs in <code>/proc/mounts</code>
|
|
---- @string path an absolute path
|
|
---- @treturn string filesystem type
|
|
function util.getFilesystemType(path)
|
|
local mounts = io.open("/proc/mounts", "r")
|
|
if not mounts then return nil end
|
|
local type
|
|
while true do
|
|
local line
|
|
local mount = {}
|
|
line = mounts:read()
|
|
if line == nil then
|
|
break
|
|
end
|
|
for param in line:gmatch("%S+") do table.insert(mount, param) end
|
|
if string.match(path, mount[2]) then
|
|
type = mount[3]
|
|
if mount[2] ~= '/' then
|
|
break
|
|
end
|
|
end
|
|
end
|
|
mounts:close()
|
|
return type
|
|
end
|
|
|
|
--- Replaces characters that are invalid filenames.
|
|
--
|
|
-- Replaces the characters <code>\/:*?"<>|</code> with an <code>_</code>.
|
|
-- These characters are problematic on Windows filesystems. On Linux only
|
|
-- <code>/</code> poses a problem.
|
|
---- @string str filename
|
|
---- @treturn string sanitized filename
|
|
function util.replaceInvalidChars(str)
|
|
if str then
|
|
return str:gsub('[\\,%/,:,%*,%?,%",%<,%>,%|]','_')
|
|
end
|
|
end
|
|
|
|
--- Replaces slash with an underscore.
|
|
---- @string str
|
|
---- @treturn string
|
|
function util.replaceSlashChar(str)
|
|
if str then
|
|
return str:gsub('%/','_')
|
|
end
|
|
end
|
|
|
|
--- Splits a file into its path and name
|
|
---- @string file
|
|
---- @treturn string path, filename
|
|
function util.splitFilePathName(file)
|
|
if file == nil or file == "" then return "", "" end
|
|
if string.find(file, "/") == nil then return "", file end
|
|
return string.gsub(file, "(.*/)(.*)", "%1"), string.gsub(file, ".*/", "")
|
|
end
|
|
|
|
--- Splits a file name into its pure file name and suffix
|
|
---- @string file
|
|
---- @treturn string path, extension
|
|
function util.splitFileNameSuffix(file)
|
|
if file == nil or file == "" then return "", "" end
|
|
if string.find(file, "%.") == nil then return file, "" end
|
|
return string.gsub(file, "(.*)%.(.*)", "%1"), string.gsub(file, ".*%.", "")
|
|
end
|
|
|
|
--- Gets file extension
|
|
---- @string filename
|
|
---- @treturn string extension
|
|
function util.getFileNameSuffix(file)
|
|
local _, suffix = util.splitFileNameSuffix(file)
|
|
return suffix
|
|
end
|
|
|
|
--- Adds > to touch menu items with a submenu
|
|
function util.getMenuText(item)
|
|
local text
|
|
if item.text_func then
|
|
text = item.text_func()
|
|
else
|
|
text = item.text
|
|
end
|
|
if item.sub_item_table ~= nil then
|
|
text = text .. " \226\150\184"
|
|
end
|
|
return text
|
|
end
|
|
|
|
--- Replaces invalid UTF-8 characters with a replacement string.
|
|
--
|
|
-- Based on <a href="http://notebook.kulchenko.com/programming/fixing-malformed-utf8-in-lua">http://notebook.kulchenko.com/programming/fixing-malformed-utf8-in-lua</a>
|
|
---- @string str the string to be checked for invalid characters
|
|
---- @string replacement the string to replace invalid characters with
|
|
---- @treturn string valid UTF-8
|
|
function util.fixUtf8(str, replacement)
|
|
local pos = 1
|
|
local len = #str
|
|
while pos <= len do
|
|
if pos == str:find("[%z\1-\127]", pos) then pos = pos + 1
|
|
elseif pos == str:find("[\194-\223][\128-\191]", pos) then pos = pos + 2
|
|
elseif pos == str:find( "\224[\160-\191][\128-\191]", pos)
|
|
or pos == str:find("[\225-\236][\128-\191][\128-\191]", pos)
|
|
or pos == str:find( "\237[\128-\159][\128-\191]", pos)
|
|
or pos == str:find("[\238-\239][\128-\191][\128-\191]", pos) then pos = pos + 3
|
|
elseif pos == str:find( "\240[\144-\191][\128-\191][\128-\191]", pos)
|
|
or pos == str:find("[\241-\243][\128-\191][\128-\191][\128-\191]", pos)
|
|
or pos == str:find( "\244[\128-\143][\128-\191][\128-\191]", pos) then pos = pos + 4
|
|
else
|
|
str = str:sub(1, pos - 1) .. replacement .. str:sub(pos + 1)
|
|
pos = pos + #replacement
|
|
len = len + #replacement - 1
|
|
end
|
|
end
|
|
return str
|
|
end
|
|
|
|
return util
|