built-in markdown crack down on locals; still very slow
This commit is contained in:
parent
68cd576bf4
commit
167a4595a5
|
@ -130,31 +130,33 @@ setfenv(1, M)
|
||||||
-- Locks table t from changes, writes an error if someone attempts to change the table.
|
-- Locks table t from changes, writes an error if someone attempts to change the table.
|
||||||
-- This is useful for detecting variables that have "accidently" been made global. Something
|
-- This is useful for detecting variables that have "accidently" been made global. Something
|
||||||
-- I tend to do all too much.
|
-- I tend to do all too much.
|
||||||
function lock(t)
|
function M.lock(t)
|
||||||
function lock_new_index(t, k, v)
|
local function lock_new_index(t, k, v)
|
||||||
error("module has been locked -- " .. k .. " must be declared local", 2)
|
error("module has been locked -- " .. k .. " must be declared local", 2)
|
||||||
end
|
end
|
||||||
|
|
||||||
local mt = {__newindex = lock_new_index}
|
local mt = {__newindex = lock_new_index}
|
||||||
if getmetatable(t) then mt.__index = getmetatable(t).__index end
|
if getmetatable(t) then
|
||||||
|
mt.__index = getmetatable(t).__index
|
||||||
|
end
|
||||||
setmetatable(t, mt)
|
setmetatable(t, mt)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Returns the result of mapping the values in table t through the function f
|
-- Returns the result of mapping the values in table t through the function f
|
||||||
function map(t, f)
|
local function map(t, f)
|
||||||
local out = {}
|
local out = {}
|
||||||
for k,v in pairs(t) do out[k] = f(v,k) end
|
for k,v in pairs(t) do out[k] = f(v,k) end
|
||||||
return out
|
return out
|
||||||
end
|
end
|
||||||
|
|
||||||
-- The identity function, useful as a placeholder.
|
-- The identity function, useful as a placeholder.
|
||||||
function identity(text) return text end
|
local function identity(text) return text end
|
||||||
|
|
||||||
-- Functional style if statement. (NOTE: no short circuit evaluation)
|
-- Functional style if statement. (NOTE: no short circuit evaluation)
|
||||||
function iff(t, a, b) if t then return a else return b end end
|
local function iff(t, a, b) if t then return a else return b end end
|
||||||
|
|
||||||
-- Splits the text into an array of separate lines.
|
-- Splits the text into an array of separate lines.
|
||||||
function split(text, sep)
|
local function split(text, sep)
|
||||||
sep = sep or "\n"
|
sep = sep or "\n"
|
||||||
local lines = {}
|
local lines = {}
|
||||||
local pos = 1
|
local pos = 1
|
||||||
|
@ -168,7 +170,7 @@ function split(text, sep)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Converts tabs to spaces
|
-- Converts tabs to spaces
|
||||||
function detab(text)
|
local function detab(text)
|
||||||
local tab_width = 4
|
local tab_width = 4
|
||||||
local function rep(match)
|
local function rep(match)
|
||||||
local spaces = -match:len()
|
local spaces = -match:len()
|
||||||
|
@ -180,7 +182,7 @@ function detab(text)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Applies string.find for every pattern in the list and returns the first match
|
-- Applies string.find for every pattern in the list and returns the first match
|
||||||
function find_first(s, patterns, index)
|
local function find_first(s, patterns, index)
|
||||||
local res = {}
|
local res = {}
|
||||||
for _,p in ipairs(patterns) do
|
for _,p in ipairs(patterns) do
|
||||||
local match = {s:find(p, index)}
|
local match = {s:find(p, index)}
|
||||||
|
@ -192,7 +194,7 @@ end
|
||||||
-- If a replacement array is specified, the range [start, stop] in the array is replaced
|
-- If a replacement array is specified, the range [start, stop] in the array is replaced
|
||||||
-- with the replacement array and the resulting array is returned. Without a replacement
|
-- with the replacement array and the resulting array is returned. Without a replacement
|
||||||
-- array the section of the array between start and stop is returned.
|
-- array the section of the array between start and stop is returned.
|
||||||
function splice(array, start, stop, replacement)
|
local function splice(array, start, stop, replacement)
|
||||||
if replacement then
|
if replacement then
|
||||||
local n = stop - start + 1
|
local n = stop - start + 1
|
||||||
while n > 0 do
|
while n > 0 do
|
||||||
|
@ -213,7 +215,7 @@ function splice(array, start, stop, replacement)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Outdents the text one step.
|
-- Outdents the text one step.
|
||||||
function outdent(text)
|
local function outdent(text)
|
||||||
text = "\n" .. text
|
text = "\n" .. text
|
||||||
text = text:gsub("\n ? ? ?", "\n")
|
text = text:gsub("\n ? ? ?", "\n")
|
||||||
text = text:sub(2)
|
text = text:sub(2)
|
||||||
|
@ -221,7 +223,7 @@ function outdent(text)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Indents the text one step.
|
-- Indents the text one step.
|
||||||
function indent(text)
|
local function indent(text)
|
||||||
text = text:gsub("\n", "\n ")
|
text = text:gsub("\n", "\n ")
|
||||||
return text
|
return text
|
||||||
end
|
end
|
||||||
|
@ -229,7 +231,7 @@ end
|
||||||
-- Does a simple tokenization of html data. Returns the data as a list of tokens.
|
-- Does a simple tokenization of html data. Returns the data as a list of tokens.
|
||||||
-- Each token is a table with a type field (which is either "tag" or "text") and
|
-- Each token is a table with a type field (which is either "tag" or "text") and
|
||||||
-- a text field (which contains the original token data).
|
-- a text field (which contains the original token data).
|
||||||
function tokenize_html(html)
|
local function tokenize_html(html)
|
||||||
local tokens = {}
|
local tokens = {}
|
||||||
local pos = 1
|
local pos = 1
|
||||||
while true do
|
while true do
|
||||||
|
@ -287,7 +289,7 @@ local HASH = {
|
||||||
|
|
||||||
-- Inits hashing. Creates a hash_identifier that doesn't occur anywhere
|
-- Inits hashing. Creates a hash_identifier that doesn't occur anywhere
|
||||||
-- in the text.
|
-- in the text.
|
||||||
function init_hash(text)
|
local function init_hash(text)
|
||||||
HASH.inited = true
|
HASH.inited = true
|
||||||
HASH.identifier = ""
|
HASH.identifier = ""
|
||||||
HASH.counter = 0
|
HASH.counter = 0
|
||||||
|
@ -305,7 +307,7 @@ function init_hash(text)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Returns the hashed value for s.
|
-- Returns the hashed value for s.
|
||||||
function hash(s)
|
local function hash(s)
|
||||||
assert(HASH.inited)
|
assert(HASH.inited)
|
||||||
if not HASH.table[s] then
|
if not HASH.table[s] then
|
||||||
HASH.counter = HASH.counter + 1
|
HASH.counter = HASH.counter + 1
|
||||||
|
@ -342,18 +344,18 @@ local PD = {
|
||||||
-- Nested data.
|
-- Nested data.
|
||||||
-- </div>
|
-- </div>
|
||||||
-- </div>
|
-- </div>
|
||||||
function block_pattern(tag)
|
local function block_pattern(tag)
|
||||||
return "\n<" .. tag .. ".-\n</" .. tag .. ">[ \t]*\n"
|
return "\n<" .. tag .. ".-\n</" .. tag .. ">[ \t]*\n"
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Pattern for matching a block tag that begins and ends with a newline
|
-- Pattern for matching a block tag that begins and ends with a newline
|
||||||
function line_pattern(tag)
|
local function line_pattern(tag)
|
||||||
return "\n<" .. tag .. ".-</" .. tag .. ">[ \t]*\n"
|
return "\n<" .. tag .. ".-</" .. tag .. ">[ \t]*\n"
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Protects the range of characters from start to stop in the text and
|
-- Protects the range of characters from start to stop in the text and
|
||||||
-- returns the protected string.
|
-- returns the protected string.
|
||||||
function protect_range(text, start, stop)
|
local function protect_range(text, start, stop)
|
||||||
local s = text:sub(start, stop)
|
local s = text:sub(start, stop)
|
||||||
local h = hash(s)
|
local h = hash(s)
|
||||||
PD.blocks[h] = s
|
PD.blocks[h] = s
|
||||||
|
@ -363,7 +365,7 @@ end
|
||||||
|
|
||||||
-- Protect every part of the text that matches any of the patterns. The first
|
-- Protect every part of the text that matches any of the patterns. The first
|
||||||
-- matching pattern is protected first, etc.
|
-- matching pattern is protected first, etc.
|
||||||
function protect_matches(text, patterns)
|
local function protect_matches(text, patterns)
|
||||||
while true do
|
while true do
|
||||||
local start, stop = find_first(text, patterns)
|
local start, stop = find_first(text, patterns)
|
||||||
if not start then break end
|
if not start then break end
|
||||||
|
@ -373,7 +375,7 @@ function protect_matches(text, patterns)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Protects blocklevel tags in the specified text
|
-- Protects blocklevel tags in the specified text
|
||||||
function protect(text)
|
local function protect(text)
|
||||||
-- First protect potentially nested block tags
|
-- First protect potentially nested block tags
|
||||||
text = protect_matches(text, map(PD.tags, block_pattern))
|
text = protect_matches(text, map(PD.tags, block_pattern))
|
||||||
-- Then protect block tags at the line level.
|
-- Then protect block tags at the line level.
|
||||||
|
@ -385,12 +387,12 @@ function protect(text)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Returns true if the string s is a hash resulting from protection
|
-- Returns true if the string s is a hash resulting from protection
|
||||||
function is_protected(s)
|
local function is_protected(s)
|
||||||
return PD.blocks[s]
|
return PD.blocks[s]
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Unprotects the specified text by expanding all the nonces
|
-- Unprotects the specified text by expanding all the nonces
|
||||||
function unprotect(text)
|
local function unprotect(text)
|
||||||
for k,v in pairs(PD.blocks) do
|
for k,v in pairs(PD.blocks) do
|
||||||
v = v:gsub("%%", "%%%%")
|
v = v:gsub("%%", "%%%%")
|
||||||
text = text:gsub(k, v)
|
text = text:gsub(k, v)
|
||||||
|
@ -410,14 +412,14 @@ end
|
||||||
-- Returns true if the line is a ruler of (char) characters.
|
-- Returns true if the line is a ruler of (char) characters.
|
||||||
-- The line must contain at least three char characters and contain only spaces and
|
-- The line must contain at least three char characters and contain only spaces and
|
||||||
-- char characters.
|
-- char characters.
|
||||||
function is_ruler_of(line, char)
|
local function is_ruler_of(line, char)
|
||||||
if not line:match("^[ %" .. char .. "]*$") then return false end
|
if not line:match("^[ %" .. char .. "]*$") then return false end
|
||||||
if not line:match("%" .. char .. ".*%" .. char .. ".*%" .. char) then return false end
|
if not line:match("%" .. char .. ".*%" .. char .. ".*%" .. char) then return false end
|
||||||
return true
|
return true
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Identifies the block level formatting present in the line
|
-- Identifies the block level formatting present in the line
|
||||||
function classify(line)
|
local function classify(line)
|
||||||
local info = {line = line, text = line}
|
local info = {line = line, text = line}
|
||||||
|
|
||||||
if line:match("^ ") then
|
if line:match("^ ") then
|
||||||
|
@ -483,7 +485,7 @@ end
|
||||||
|
|
||||||
-- Find headers constisting of a normal line followed by a ruler and converts them to
|
-- Find headers constisting of a normal line followed by a ruler and converts them to
|
||||||
-- header entries.
|
-- header entries.
|
||||||
function headers(array)
|
local function headers(array)
|
||||||
local i = 1
|
local i = 1
|
||||||
while i <= #array - 1 do
|
while i <= #array - 1 do
|
||||||
if array[i].type == "normal" and array[i+1].type == "ruler" and
|
if array[i].type == "normal" and array[i+1].type == "ruler" and
|
||||||
|
@ -500,8 +502,10 @@ function headers(array)
|
||||||
return array
|
return array
|
||||||
end
|
end
|
||||||
|
|
||||||
|
local block_transform, blocks_to_html, encode_code, span_transform, encode_backslash_escapes
|
||||||
|
|
||||||
-- Find list blocks and convert them to protected data blocks
|
-- Find list blocks and convert them to protected data blocks
|
||||||
function lists(array, sublist)
|
local function lists(array, sublist)
|
||||||
local function process_list(arr)
|
local function process_list(arr)
|
||||||
local function any_blanks(arr)
|
local function any_blanks(arr)
|
||||||
for i = 1, #arr do
|
for i = 1, #arr do
|
||||||
|
@ -624,7 +628,7 @@ function lists(array, sublist)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Find and convert blockquote markers.
|
-- Find and convert blockquote markers.
|
||||||
function blockquotes(lines)
|
local function blockquotes(lines)
|
||||||
local function find_blockquote(lines)
|
local function find_blockquote(lines)
|
||||||
local start
|
local start
|
||||||
for i,line in ipairs(lines) do
|
for i,line in ipairs(lines) do
|
||||||
|
@ -674,7 +678,7 @@ function blockquotes(lines)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Find and convert codeblocks.
|
-- Find and convert codeblocks.
|
||||||
function codeblocks(lines)
|
local function codeblocks(lines)
|
||||||
local function find_codeblock(lines)
|
local function find_codeblock(lines)
|
||||||
local start
|
local start
|
||||||
for i,line in ipairs(lines) do
|
for i,line in ipairs(lines) do
|
||||||
|
@ -764,7 +768,7 @@ end
|
||||||
|
|
||||||
-- Debug function for printing a line array to see the result
|
-- Debug function for printing a line array to see the result
|
||||||
-- of partial transforms.
|
-- of partial transforms.
|
||||||
function print_lines(lines)
|
local function print_lines(lines)
|
||||||
for i, line in ipairs(lines) do
|
for i, line in ipairs(lines) do
|
||||||
print(i, line.type, line.text or line.line)
|
print(i, line.type, line.text or line.line)
|
||||||
end
|
end
|
||||||
|
@ -778,10 +782,10 @@ end
|
||||||
|
|
||||||
-- These characters may need to be escaped because they have a special
|
-- These characters may need to be escaped because they have a special
|
||||||
-- meaning in markdown.
|
-- meaning in markdown.
|
||||||
escape_chars = "'\\`*_{}[]()>#+-.!'"
|
local escape_chars = "'\\`*_{}[]()>#+-.!'"
|
||||||
escape_table = {}
|
local escape_table = {}
|
||||||
|
|
||||||
function init_escape_table()
|
local function init_escape_table()
|
||||||
escape_table = {}
|
escape_table = {}
|
||||||
for i = 1,#escape_chars do
|
for i = 1,#escape_chars do
|
||||||
local c = escape_chars:sub(i,i)
|
local c = escape_chars:sub(i,i)
|
||||||
|
@ -790,7 +794,7 @@ function init_escape_table()
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Adds a new escape to the escape table.
|
-- Adds a new escape to the escape table.
|
||||||
function add_escape(text)
|
local function add_escape(text)
|
||||||
if not escape_table[text] then
|
if not escape_table[text] then
|
||||||
escape_table[text] = hash(text)
|
escape_table[text] = hash(text)
|
||||||
end
|
end
|
||||||
|
@ -798,7 +802,7 @@ function add_escape(text)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Escape characters that should not be disturbed by markdown.
|
-- Escape characters that should not be disturbed by markdown.
|
||||||
function escape_special_chars(text)
|
local function escape_special_chars(text)
|
||||||
local tokens = tokenize_html(text)
|
local tokens = tokenize_html(text)
|
||||||
|
|
||||||
local out = ""
|
local out = ""
|
||||||
|
@ -826,7 +830,7 @@ function encode_backslash_escapes(t)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Unescape characters that have been encoded.
|
-- Unescape characters that have been encoded.
|
||||||
function unescape_special_chars(t)
|
local function unescape_special_chars(t)
|
||||||
local tin = t
|
local tin = t
|
||||||
for k,v in pairs(escape_table) do
|
for k,v in pairs(escape_table) do
|
||||||
k = k:gsub("%%", "%%%%")
|
k = k:gsub("%%", "%%%%")
|
||||||
|
@ -850,7 +854,7 @@ function encode_code(s)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Handle backtick blocks.
|
-- Handle backtick blocks.
|
||||||
function code_spans(s)
|
local function code_spans(s)
|
||||||
s = s:gsub("\\\\", escape_table["\\"])
|
s = s:gsub("\\\\", escape_table["\\"])
|
||||||
s = s:gsub("\\`", escape_table["`"])
|
s = s:gsub("\\`", escape_table["`"])
|
||||||
|
|
||||||
|
@ -880,7 +884,7 @@ function code_spans(s)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Encode alt text... enodes &, and ".
|
-- Encode alt text... enodes &, and ".
|
||||||
function encode_alt(s)
|
local function encode_alt(s)
|
||||||
if not s then return s end
|
if not s then return s end
|
||||||
s = s:gsub('&', '&')
|
s = s:gsub('&', '&')
|
||||||
s = s:gsub('"', '"')
|
s = s:gsub('"', '"')
|
||||||
|
@ -888,8 +892,10 @@ function encode_alt(s)
|
||||||
return s
|
return s
|
||||||
end
|
end
|
||||||
|
|
||||||
|
local link_database
|
||||||
|
|
||||||
-- Handle image references
|
-- Handle image references
|
||||||
function images(text)
|
local function images(text)
|
||||||
local function reference_link(alt, id)
|
local function reference_link(alt, id)
|
||||||
alt = encode_alt(alt:match("%b[]"):sub(2,-2))
|
alt = encode_alt(alt:match("%b[]"):sub(2,-2))
|
||||||
id = id:match("%[(.*)%]"):lower()
|
id = id:match("%[(.*)%]"):lower()
|
||||||
|
@ -922,7 +928,7 @@ function images(text)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Handle anchor references
|
-- Handle anchor references
|
||||||
function anchors(text)
|
local function anchors(text)
|
||||||
local function reference_link(text, id)
|
local function reference_link(text, id)
|
||||||
text = text:match("%b[]"):sub(2,-2)
|
text = text:match("%b[]"):sub(2,-2)
|
||||||
id = id:match("%b[]"):sub(2,-2):lower()
|
id = id:match("%b[]"):sub(2,-2):lower()
|
||||||
|
@ -955,7 +961,7 @@ function anchors(text)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Handle auto links, i.e. <http://www.google.com/>.
|
-- Handle auto links, i.e. <http://www.google.com/>.
|
||||||
function auto_links(text)
|
local function auto_links(text)
|
||||||
local function link(s)
|
local function link(s)
|
||||||
return add_escape("<a href=\"" .. s .. "\">") .. s .. "</a>"
|
return add_escape("<a href=\"" .. s .. "\">") .. s .. "</a>"
|
||||||
end
|
end
|
||||||
|
@ -1004,7 +1010,7 @@ end
|
||||||
|
|
||||||
-- Encode free standing amps (&) and angles (<)... note that this does not
|
-- Encode free standing amps (&) and angles (<)... note that this does not
|
||||||
-- encode free >.
|
-- encode free >.
|
||||||
function amps_and_angles(s)
|
local function amps_and_angles(s)
|
||||||
-- encode amps not part of &..; expression
|
-- encode amps not part of &..; expression
|
||||||
local pos = 1
|
local pos = 1
|
||||||
while true do
|
while true do
|
||||||
|
@ -1029,7 +1035,7 @@ function amps_and_angles(s)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Handles emphasis markers (* and _) in the text.
|
-- Handles emphasis markers (* and _) in the text.
|
||||||
function emphasis(text)
|
local function emphasis(text)
|
||||||
for _, s in ipairs {"%*%*", "%_%_"} do
|
for _, s in ipairs {"%*%*", "%_%_"} do
|
||||||
text = text:gsub(s .. "([^%s][%*%_]?)" .. s, "<strong>%1</strong>")
|
text = text:gsub(s .. "([^%s][%*%_]?)" .. s, "<strong>%1</strong>")
|
||||||
text = text:gsub(s .. "([^%s][^<>]-[^%s][%*%_]?)" .. s, "<strong>%1</strong>")
|
text = text:gsub(s .. "([^%s][^<>]-[^%s][%*%_]?)" .. s, "<strong>%1</strong>")
|
||||||
|
@ -1044,7 +1050,7 @@ function emphasis(text)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Handles line break markers in the text.
|
-- Handles line break markers in the text.
|
||||||
function line_breaks(text)
|
local function line_breaks(text)
|
||||||
return text:gsub(" +\n", " <br/>\n")
|
return text:gsub(" +\n", " <br/>\n")
|
||||||
end
|
end
|
||||||
|
|
||||||
|
@ -1067,7 +1073,7 @@ end
|
||||||
|
|
||||||
-- Cleanup the text by normalizing some possible variations to make further
|
-- Cleanup the text by normalizing some possible variations to make further
|
||||||
-- processing easier.
|
-- processing easier.
|
||||||
function cleanup(text)
|
local function cleanup(text)
|
||||||
-- Standardize line endings
|
-- Standardize line endings
|
||||||
text = text:gsub("\r\n", "\n") -- DOS to UNIX
|
text = text:gsub("\r\n", "\n") -- DOS to UNIX
|
||||||
text = text:gsub("\r", "\n") -- Mac to UNIX
|
text = text:gsub("\r", "\n") -- Mac to UNIX
|
||||||
|
@ -1086,7 +1092,7 @@ function cleanup(text)
|
||||||
end
|
end
|
||||||
|
|
||||||
-- Strips link definitions from the text and stores the data in a lookup table.
|
-- Strips link definitions from the text and stores the data in a lookup table.
|
||||||
function strip_link_definitions(text)
|
local function strip_link_definitions(text)
|
||||||
local linkdb = {}
|
local linkdb = {}
|
||||||
|
|
||||||
local function link_def(id, url, title)
|
local function link_def(id, url, title)
|
||||||
|
@ -1112,7 +1118,7 @@ end
|
||||||
link_database = {}
|
link_database = {}
|
||||||
|
|
||||||
-- Main markdown processing function
|
-- Main markdown processing function
|
||||||
function markdown(text)
|
local function markdown(text)
|
||||||
init_hash(text)
|
init_hash(text)
|
||||||
init_escape_table()
|
init_escape_table()
|
||||||
|
|
||||||
|
@ -1132,7 +1138,7 @@ setfenv(1, _G)
|
||||||
M.lock(M)
|
M.lock(M)
|
||||||
|
|
||||||
-- Expose markdown function to the world
|
-- Expose markdown function to the world
|
||||||
markdown = M.markdown
|
_G.markdown = M.markdown
|
||||||
|
|
||||||
-- Class for parsing command-line options
|
-- Class for parsing command-line options
|
||||||
local OptionParser = {}
|
local OptionParser = {}
|
||||||
|
@ -1168,6 +1174,7 @@ end
|
||||||
-- where successfully parsed and false otherwise.
|
-- where successfully parsed and false otherwise.
|
||||||
function OptionParser:run(args)
|
function OptionParser:run(args)
|
||||||
local pos = 1
|
local pos = 1
|
||||||
|
local param
|
||||||
while pos <= #args do
|
while pos <= #args do
|
||||||
local arg = args[pos]
|
local arg = args[pos]
|
||||||
if arg == "--" then
|
if arg == "--" then
|
||||||
|
|
Loading…
Reference in New Issue