2025-01-14 19:48:32 +01:00
|
|
|
|
|
|
|
local function trim(str)
|
|
|
|
return str:match("^%s*(.-)%s*$")
|
|
|
|
end
|
|
|
|
|
2025-01-18 18:50:03 +01:00
|
|
|
local function shallow_copy(t)
|
|
|
|
local t2 = {}
|
|
|
|
for k,v in pairs(t) do
|
|
|
|
t2[k] = v
|
|
|
|
end
|
|
|
|
return t2
|
|
|
|
end
|
2025-01-14 19:48:32 +01:00
|
|
|
|
|
|
|
|
|
|
|
local M = {}
|
|
|
|
|
|
|
|
local RAW_TEXT_TAGS = {
|
|
|
|
script = true,
|
|
|
|
style = true,
|
|
|
|
pre = true
|
|
|
|
}
|
|
|
|
|
|
|
|
-- void tags are content-less, or so-called "self-closing", tags
|
|
|
|
local VOID_TAGS = {
|
|
|
|
area = true,
|
|
|
|
base = true,
|
|
|
|
br = true,
|
|
|
|
col = true,
|
|
|
|
embed = true,
|
|
|
|
hr = true,
|
|
|
|
img = true,
|
|
|
|
input = true,
|
|
|
|
link = true,
|
|
|
|
meta = true,
|
|
|
|
param = true, -- deprecated
|
|
|
|
source = true,
|
|
|
|
track = true,
|
|
|
|
wbr = true,
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
function M.make_dom_element( tag_name, parent_elem )
|
|
|
|
local o = {
|
|
|
|
tag_name = tag_name,
|
|
|
|
attributes = {},
|
2025-01-18 13:03:01 +01:00
|
|
|
content = "",
|
|
|
|
|
|
|
|
children = {},
|
|
|
|
parent = parent_elem,
|
|
|
|
|
|
|
|
get_child_index = function( self )
|
|
|
|
if not self.parent then
|
|
|
|
return -1
|
|
|
|
end
|
|
|
|
|
|
|
|
for i, child in ipairs(self.parent.children) do
|
|
|
|
if child == self then return i end
|
|
|
|
end
|
|
|
|
end,
|
|
|
|
|
2025-01-18 18:50:38 +01:00
|
|
|
get_next_sibling = function( self )
|
2025-01-18 13:03:01 +01:00
|
|
|
if not self.parent then return nil end
|
|
|
|
|
|
|
|
local found_self = false
|
|
|
|
for _, child in ipairs(self.parent.children) do
|
|
|
|
if found_self then
|
|
|
|
return child
|
|
|
|
end
|
|
|
|
|
|
|
|
if child == self then
|
|
|
|
found_self = true
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
return nil
|
|
|
|
end,
|
2025-01-18 18:52:17 +01:00
|
|
|
|
|
|
|
check_simple_selector = function( self, selector )
|
|
|
|
return M.check_simple_selector( self, selector )
|
|
|
|
end,
|
|
|
|
|
|
|
|
foreach = function( self, fn )
|
|
|
|
fn( self )
|
|
|
|
|
|
|
|
for _, child in ipairs(self.children or {}) do
|
|
|
|
child:foreach( fn )
|
|
|
|
end
|
|
|
|
end
|
2025-01-14 19:48:32 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
if parent_elem then
|
|
|
|
table.insert( parent_elem.children, o )
|
|
|
|
end
|
|
|
|
|
|
|
|
local mt = {
|
|
|
|
__newindex = function(table, key, value)
|
|
|
|
-- Allow modification of existing attributes
|
|
|
|
if rawget(table.attributes, key) ~= nil then
|
|
|
|
rawset(table.attributes, key, value)
|
|
|
|
else
|
|
|
|
-- Prevent adding new attributes
|
|
|
|
error("Cannot add new attribute to DOM element: " .. tostring(key))
|
|
|
|
end
|
|
|
|
end,
|
|
|
|
__index = function(table, key)
|
|
|
|
-- Allow access to attributes
|
|
|
|
return rawget(table.attributes, key)
|
|
|
|
end
|
|
|
|
}
|
|
|
|
|
|
|
|
setmetatable(o, mt)
|
|
|
|
return o
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
function M.preprocess( content )
|
|
|
|
-- remove "self closing" slashes as they MUST be ignored (spec)
|
|
|
|
-- and would cause problems
|
|
|
|
content = content:gsub("/%s*>", ">")
|
|
|
|
-- remove whitespace at the start of "</closing>" tags.
|
|
|
|
content = content:gsub("</%s*/%s*", "</")
|
|
|
|
|
|
|
|
return content
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
function M.tokenise( content )
|
|
|
|
local TOKENS = {}
|
|
|
|
|
|
|
|
-- state
|
|
|
|
local in_tag = false
|
|
|
|
local currently_opened_quotes = nil
|
|
|
|
local text_memory = ""
|
|
|
|
|
|
|
|
local skipping_from = nil
|
|
|
|
local skip_target = nil
|
|
|
|
local skip_mode = "before"
|
|
|
|
|
|
|
|
local function set_skipping_to( str, mode )
|
|
|
|
mode = mode or "before"
|
|
|
|
if mode ~= "before" and mode ~= "after" then
|
|
|
|
error("Unexpected skipping mode: " .. mode .. ", in looking for " .. str)
|
|
|
|
end
|
|
|
|
|
|
|
|
skip_target = str
|
|
|
|
skip_mode = mode
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
local i = 1
|
|
|
|
|
|
|
|
while i <= #content do
|
|
|
|
local char = content:sub(i,i)
|
|
|
|
|
|
|
|
if skip_target ~= nil then
|
|
|
|
if skipping_from == nil then
|
|
|
|
skipping_from = i
|
|
|
|
end
|
|
|
|
|
|
|
|
if skip_mode == "before" then
|
|
|
|
local end_i = i + #skip_target - 1
|
|
|
|
|
|
|
|
if trim(content:sub(i, end_i)) == skip_target then
|
|
|
|
table.insert( TOKENS, {type="TEXT", value=content:sub(skipping_from, i-1)} )
|
|
|
|
|
|
|
|
-- release from skip
|
|
|
|
--i = end_i - 1
|
|
|
|
i = i - 1
|
|
|
|
skip_target = nil
|
|
|
|
skipping_from = nil
|
|
|
|
end
|
|
|
|
|
|
|
|
goto continue
|
|
|
|
else
|
|
|
|
local start_i = i - #skip_target + 1
|
|
|
|
|
|
|
|
if trim(content:sub(start_i, i)) == skip_target then
|
|
|
|
table.insert( TOKENS, {type="TEXT", value=content:sub(skipping_from, start_i-1)} )
|
|
|
|
|
|
|
|
-- release from skip
|
|
|
|
i = start_i
|
|
|
|
skip_target = nil
|
|
|
|
skipping_from = nil
|
|
|
|
end
|
|
|
|
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if char == "<" then
|
|
|
|
if content:sub(i, i+3) == "<!--" then
|
|
|
|
set_skipping_to("-->", "after")
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
|
|
|
|
if content:sub(i, i+1) == "<!" then
|
|
|
|
i = content:find(">", i)
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
|
|
|
|
---------------------------------
|
|
|
|
if #text_memory ~= 0 then
|
|
|
|
table.insert( TOKENS, {type="TEXT", value=text_memory} )
|
|
|
|
text_memory = ""
|
|
|
|
end
|
|
|
|
|
|
|
|
in_tag = true
|
|
|
|
|
|
|
|
-- closing tag
|
|
|
|
if content:sub(i, i+1) == "</" then
|
|
|
|
table.insert( TOKENS, {type="START_CLOSING_TAG"} )
|
|
|
|
i = i+1
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
|
|
|
|
table.insert( TOKENS, {type="START_OPENING_TAG"} )
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
|
|
|
|
if char == ">" then
|
|
|
|
if #text_memory ~= 0 then
|
|
|
|
if in_tag and currently_opened_quotes == nil then
|
|
|
|
local word = trim(text_memory)
|
|
|
|
|
|
|
|
if TOKENS[#TOKENS] and ( TOKENS[#TOKENS].type == "START_OPENING_TAG") then
|
|
|
|
if RAW_TEXT_TAGS[word] then
|
|
|
|
print("Warning: "..word.." tags may contain text that would be incorrectly parsed as HTML.")
|
|
|
|
-- made possible because of the whitespace removal at the start
|
|
|
|
set_skipping_to("</" .. word)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2025-01-19 14:00:13 +01:00
|
|
|
if not word:match("^%s*$") then
|
|
|
|
table.insert( TOKENS, {type="WORD", value=word})
|
|
|
|
end
|
2025-01-14 19:48:32 +01:00
|
|
|
else
|
|
|
|
table.insert( TOKENS, {type="TEXT", value=text_memory} )
|
|
|
|
end
|
|
|
|
|
|
|
|
text_memory = ""
|
|
|
|
end
|
|
|
|
|
|
|
|
in_tag = false
|
|
|
|
table.insert( TOKENS, {type = "END_TAG"} )
|
|
|
|
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if in_tag then
|
|
|
|
if currently_opened_quotes == nil and char:match("%s") then
|
|
|
|
if #text_memory ~= 0 then
|
|
|
|
local word = trim(text_memory)
|
|
|
|
|
|
|
|
if TOKENS[#TOKENS] and ( TOKENS[#TOKENS].type == "START_OPENING_TAG" ) then
|
|
|
|
if RAW_TEXT_TAGS[word] then
|
|
|
|
print("Warning: "..word.." tags may contain text that would be incorrectly parsed as HTML.")
|
|
|
|
-- made possible because of the whitespace removal at the start
|
|
|
|
set_skipping_to("</" .. word)
|
|
|
|
text_memory = ""
|
|
|
|
|
|
|
|
-- advance to closing ">"
|
|
|
|
i = content:find(">", i)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2025-01-19 14:00:13 +01:00
|
|
|
if not word:match("^%s*$") then
|
|
|
|
table.insert( TOKENS, {type="WORD", value=word})
|
|
|
|
text_memory = ""
|
|
|
|
end
|
2025-01-14 19:48:32 +01:00
|
|
|
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
if char == "'" or char == '"' then
|
|
|
|
if currently_opened_quotes == char then
|
|
|
|
currently_opened_quotes = nil
|
|
|
|
else
|
|
|
|
currently_opened_quotes = char
|
|
|
|
end
|
|
|
|
|
|
|
|
text_memory = text_memory .. char
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
|
|
|
|
text_memory = text_memory .. char
|
|
|
|
goto continue
|
|
|
|
else
|
|
|
|
text_memory = text_memory .. char
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
::continue::
|
|
|
|
i = i+1
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
return TOKENS
|
|
|
|
end
|
|
|
|
|
|
|
|
|
2025-01-18 18:52:17 +01:00
|
|
|
function M.check_simple_selector(element, selector)
|
|
|
|
-- Skip text nodes
|
|
|
|
if element.tag_name == ":text" then
|
|
|
|
return false
|
|
|
|
end
|
|
|
|
|
|
|
|
-- Check tag name if specified
|
|
|
|
if selector.tag_name and element.tag_name ~= selector.tag_name then
|
|
|
|
return false
|
|
|
|
end
|
|
|
|
|
|
|
|
-- Check ID if specified
|
|
|
|
if selector.id and element.attributes.id ~= selector.id then
|
|
|
|
return false
|
|
|
|
end
|
|
|
|
|
|
|
|
-- Check classes if specified
|
|
|
|
if selector.class and #selector.class > 0 then
|
|
|
|
local element_classes = element.attributes.class
|
|
|
|
if not element_classes then
|
|
|
|
return false
|
|
|
|
end
|
|
|
|
|
|
|
|
for _, class in ipairs(selector.class) do
|
|
|
|
local found = false
|
|
|
|
for _, elem_class in ipairs(element_classes) do
|
|
|
|
if elem_class == class then
|
|
|
|
found = true
|
|
|
|
break
|
|
|
|
end
|
|
|
|
end
|
|
|
|
if not found then
|
|
|
|
return false
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
return true
|
|
|
|
end
|
|
|
|
|
|
|
|
function M.query_simple_selector(document, selector)
|
|
|
|
local matches = {}
|
|
|
|
|
|
|
|
local function traverse(node)
|
|
|
|
if M.check_simple_selector(node, selector) then
|
|
|
|
table.insert(matches, node)
|
|
|
|
end
|
|
|
|
|
|
|
|
for _, child in ipairs(node.children) do
|
|
|
|
traverse(child)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
traverse(document)
|
|
|
|
return matches
|
|
|
|
end
|
|
|
|
|
|
|
|
|
2025-01-14 19:48:32 +01:00
|
|
|
function M.parse_tokens_into_document( TOKENS )
|
|
|
|
local DOCUMENT = M.make_dom_element(nil, nil)
|
|
|
|
local current_doc_element = DOCUMENT
|
|
|
|
local in_opening_tag_for = nil
|
|
|
|
|
|
|
|
local i = 1
|
|
|
|
while i <= #TOKENS do
|
|
|
|
local token = TOKENS[i]
|
|
|
|
|
|
|
|
if token.type == "WORD" then
|
2025-01-18 13:14:05 +01:00
|
|
|
if current_doc_element.tag_name == ":text" then
|
2025-01-14 19:48:32 +01:00
|
|
|
current_doc_element = current_doc_element.parent
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
if i > 0 and TOKENS[i-1].type == "START_OPENING_TAG" then
|
|
|
|
local new_elem = M.make_dom_element( token.value, current_doc_element )
|
|
|
|
current_doc_element = new_elem
|
|
|
|
in_opening_tag_for = token.value
|
|
|
|
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
|
|
|
|
if i > 0 and TOKENS[i-1].type == "START_CLOSING_TAG" then
|
|
|
|
local curr_elem = current_doc_element
|
|
|
|
|
|
|
|
while curr_elem.parent and curr_elem.tag_name ~= token.value do
|
|
|
|
curr_elem = curr_elem.parent
|
|
|
|
end
|
|
|
|
|
|
|
|
if curr_elem.parent == nil then
|
|
|
|
-- reached DOCUMENT root
|
|
|
|
print("Warning: reached document root while trying to match for closing " .. token.value .. " token.")
|
|
|
|
current_doc_element = DOCUMENT
|
|
|
|
else
|
|
|
|
current_doc_element = curr_elem.parent
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if in_opening_tag_for then
|
|
|
|
local pattern = "([%w-]+)=['\"](.-)['\"]"
|
|
|
|
|
|
|
|
local name, raw_value = token.value:match(pattern)
|
|
|
|
|
|
|
|
if name == nil or raw_value == nil then
|
|
|
|
name = token.value:match("([%w-]+)")
|
|
|
|
|
|
|
|
if name == nil then
|
2025-01-19 14:00:13 +01:00
|
|
|
error("Unrecognised word: " .. tostring(name) .. " (Token ".. tostring(i) .." , type=" .. tostring(token.type) .. ", value=" .. tostring(token.value) .. ")")
|
2025-01-14 19:48:32 +01:00
|
|
|
end
|
|
|
|
|
|
|
|
current_doc_element.attributes[name] = true
|
|
|
|
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
local value = nil
|
|
|
|
if raw_value == "" or raw_value == nil then
|
|
|
|
value = nil
|
|
|
|
else
|
|
|
|
value = trim(raw_value)
|
2025-01-18 15:45:11 +01:00
|
|
|
|
|
|
|
if name == "class" then
|
|
|
|
local classes = {}
|
|
|
|
|
|
|
|
for class in value:gmatch("%S+") do
|
|
|
|
table.insert( classes, class )
|
|
|
|
end
|
|
|
|
|
|
|
|
value = classes
|
|
|
|
end
|
2025-01-14 19:48:32 +01:00
|
|
|
end
|
|
|
|
|
|
|
|
current_doc_element.attributes[name] = value
|
|
|
|
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
if token.type == "END_TAG" then
|
|
|
|
if in_opening_tag_for then
|
|
|
|
if VOID_TAGS[in_opening_tag_for] then
|
|
|
|
if current_doc_element.parent == nil then
|
|
|
|
-- reached DOCUMENT root
|
|
|
|
current_doc_element = DOCUMENT
|
|
|
|
else
|
|
|
|
current_doc_element = current_doc_element.parent
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
end
|
|
|
|
|
|
|
|
in_opening_tag_for = nil
|
|
|
|
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
if token.type == "TEXT" then
|
2025-01-18 13:14:05 +01:00
|
|
|
local new_elem = M.make_dom_element( ":text", current_doc_element )
|
2025-01-14 19:48:32 +01:00
|
|
|
new_elem.content = token.value
|
|
|
|
current_doc_element = new_elem
|
|
|
|
|
|
|
|
goto continue
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
::continue::
|
|
|
|
i = i+1
|
|
|
|
end
|
|
|
|
|
2025-01-18 18:50:03 +01:00
|
|
|
M.clean_text_nodes( DOCUMENT )
|
2025-01-18 13:03:01 +01:00
|
|
|
|
2025-01-14 19:48:32 +01:00
|
|
|
return DOCUMENT
|
|
|
|
end
|
|
|
|
|
|
|
|
|
|
|
|
function M.clean_text_nodes(node)
|
2025-01-18 13:14:05 +01:00
|
|
|
if node.tag_name ~= ":text" then
|
2025-01-14 19:48:32 +01:00
|
|
|
-- Don't clean anything in raw text tags
|
|
|
|
if RAW_TEXT_TAGS[node.tag_name] then
|
|
|
|
return
|
|
|
|
end
|
|
|
|
|
2025-01-18 18:50:03 +01:00
|
|
|
for _, child in ipairs( shallow_copy(node.children) ) do
|
2025-01-14 19:48:32 +01:00
|
|
|
M.clean_text_nodes( child )
|
|
|
|
end
|
|
|
|
return
|
|
|
|
end
|
|
|
|
|
|
|
|
-- purge content-less text nodes
|
|
|
|
if #trim(node.content) == 0 then
|
|
|
|
if not node.parent then
|
|
|
|
error("Text node without a parent; should be impossible !")
|
|
|
|
end
|
|
|
|
|
2025-01-18 18:50:03 +01:00
|
|
|
for i, child in ipairs( shallow_copy(node.parent.children) ) do
|
2025-01-14 19:48:32 +01:00
|
|
|
if child == node then
|
|
|
|
table.remove( node.parent.children, i )
|
|
|
|
break
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
return
|
|
|
|
end
|
|
|
|
|
|
|
|
node.content = trim( node.content:gsub("%s+", " ") )
|
|
|
|
end
|
|
|
|
|
|
|
|
|
2025-01-19 13:47:54 +01:00
|
|
|
function M._tostring(node, indent, include_internal_pseudoelements)
|
2025-01-14 19:48:32 +01:00
|
|
|
-- Default indentation is 0 (root level)
|
|
|
|
indent = indent or 0
|
2025-01-18 18:52:52 +01:00
|
|
|
include_internal_pseudoelements = include_internal_pseudoelements or false
|
|
|
|
|
|
|
|
local is_pseudo_element = (node.tag_name or ":root"):sub(1,1) == ":"
|
|
|
|
|
2025-01-14 19:48:32 +01:00
|
|
|
|
|
|
|
local indent_level_str = " "
|
|
|
|
-- Create the indentation string (e.g., " " for each level)
|
|
|
|
local indent_str = string.rep(indent_level_str, indent)
|
|
|
|
|
2025-01-18 13:14:05 +01:00
|
|
|
if node.tag_name == ":text" then
|
2025-01-18 18:52:52 +01:00
|
|
|
local str = ""
|
|
|
|
|
|
|
|
if include_internal_pseudoelements then
|
|
|
|
str = str .. "<:text>"
|
|
|
|
end
|
|
|
|
|
|
|
|
str = str .. node.content
|
|
|
|
|
|
|
|
if include_internal_pseudoelements then
|
|
|
|
str = str .. "</:text>"
|
|
|
|
end
|
|
|
|
|
|
|
|
return str
|
2025-01-14 19:48:32 +01:00
|
|
|
end
|
|
|
|
|
|
|
|
local node_name = ""
|
|
|
|
|
2025-01-18 18:52:52 +01:00
|
|
|
if not is_pseudo_element or include_internal_pseudoelements then
|
2025-01-14 19:48:32 +01:00
|
|
|
-- Print the current node's tag name
|
2025-01-18 18:52:52 +01:00
|
|
|
node_name = node_name .. "\n" .. indent_str .. "<" .. (node.tag_name or ":root")
|
|
|
|
end
|
2025-01-14 19:48:32 +01:00
|
|
|
|
|
|
|
-- Print attributes if any
|
|
|
|
if next(node.attributes) ~= nil then
|
|
|
|
for attr, value in pairs(node.attributes) do
|
2025-01-18 15:45:11 +01:00
|
|
|
if type(value) == "table" then
|
|
|
|
node_name = node_name .. " " .. attr .. "=\""
|
|
|
|
for i, val in ipairs( value ) do
|
|
|
|
if i > 1 then node_name = node_name .. " " end
|
|
|
|
node_name = node_name .. tostring(val)
|
|
|
|
end
|
|
|
|
node_name = node_name .. "\""
|
|
|
|
else
|
|
|
|
node_name = node_name .. " " .. attr .. "=\"" .. tostring(value) .. "\""
|
|
|
|
end
|
2025-01-14 19:48:32 +01:00
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2025-01-18 18:52:52 +01:00
|
|
|
if not is_pseudo_element or include_internal_pseudoelements then
|
|
|
|
node_name = node_name .. ">"
|
|
|
|
end
|
2025-01-14 19:48:32 +01:00
|
|
|
|
2025-01-18 18:52:52 +01:00
|
|
|
--print( node_name )
|
2025-01-14 19:48:32 +01:00
|
|
|
|
2025-01-18 18:52:52 +01:00
|
|
|
local next_indent = indent + 1
|
|
|
|
if is_pseudo_element and not include_internal_pseudoelements then
|
|
|
|
next_indent = indent
|
|
|
|
end
|
2025-01-14 19:48:32 +01:00
|
|
|
|
|
|
|
-- Recursively print children
|
|
|
|
for _, child in ipairs(node.children) do
|
2025-01-19 13:47:54 +01:00
|
|
|
node_name = node_name .. M._tostring(child, next_indent, include_internal_pseudoelements)
|
2025-01-18 18:52:52 +01:00
|
|
|
end
|
|
|
|
|
|
|
|
if not VOID_TAGS[node.tag_name] and ( not is_pseudo_element or include_internal_pseudoelements ) then
|
|
|
|
-- Print the closing tag
|
|
|
|
local end_indent = ""
|
|
|
|
local closing_text_tag = "</:text>"
|
|
|
|
if node_name:sub(#node_name, #node_name) == ">" and node_name:sub(#node_name - #closing_text_tag + 1, #node_name) ~= closing_text_tag then
|
|
|
|
end_indent = "\n" .. indent_str
|
|
|
|
end
|
|
|
|
node_name = node_name .. end_indent .. "</" .. (node.tag_name or ":root") .. ">"
|
2025-01-14 19:48:32 +01:00
|
|
|
end
|
|
|
|
|
2025-01-18 18:52:52 +01:00
|
|
|
return node_name
|
2025-01-14 19:48:32 +01:00
|
|
|
end
|
|
|
|
|
2025-01-19 13:47:54 +01:00
|
|
|
function M.tostring(node, base_indent, include_internal_pseudoelements)
|
|
|
|
return trim( M._tostring(node, base_indent, include_internal_pseudoelements) )
|
|
|
|
end
|
2025-01-18 13:14:05 +01:00
|
|
|
|
|
|
|
|
2025-01-18 18:52:52 +01:00
|
|
|
|
|
|
|
|
2025-01-14 19:48:32 +01:00
|
|
|
function M.parse( html_string )
|
|
|
|
local clean_html = M.preprocess( html_string )
|
|
|
|
|
|
|
|
local tokens = M.tokenise( clean_html )
|
|
|
|
|
|
|
|
local document = M.parse_tokens_into_document( tokens )
|
|
|
|
|
2025-01-18 13:03:01 +01:00
|
|
|
return document
|
2025-01-14 19:48:32 +01:00
|
|
|
end
|
|
|
|
|
|
|
|
return M
|