function stripHTML(document,fieldname)
str = document:getFieldValue(fieldname)
if str ~=nil then
mylog("str is not nil");
str = string.gsub(str,"<.->","")
str=stripBlank(str);
str = convertEntities(str)
--mylog("str========\n"..str);
document:setFieldValue(fieldname, str)
else
mylog("str is nil");
end
end
--strip the blank lines
function stripBlank(str)
str = string.gsub(str,"(\n+)","\n")
return str;
end
function convertEntities(str)
local entities =
{
-- chinese entities,I get it from
http://www.w3schools.com/HTML/html_entities.asp --your lua scipts file should save in u8-dos,otherwise some code here will convert into question mark
nbsp = " ",
lt = "<",
gt = ">",
amp = "&",
}
str = string.gsub(str, "&(%a+);",entities)
return str
end
function stripHTML(document,fieldname)
str = document:getFieldValue(fieldname)
if str ~=nil then
mylog("str is not nil");
str = string.gsub(str,"<.->","")
str=stripBlank(str);
str = convertEntities(str)
--mylog("str========\n"..str);
document:setFieldValue(fieldname, str)
else
mylog("str is nil");
end
end
--strip the blank lines
function stripBlank(str)
str = string.gsub(str,"(\n+)","\n")
return str;
end
function convertEntities(str)
local entities =
{
-- chinese entities,I get it from
http://www.w3schools.com/HTML/html_entities.asp --your lua scipts file should save in u8-dos,otherwise some code here will convert into question mark
nbsp = " ",
lt = "<",
gt = ">",
amp = "&",
}
str = string.gsub(str, "&(%a+);",entities)
return str
end
function stripHTML(document,fieldname)
str = document:getFieldValue(fieldname)
if str ~=nil then
mylog("str is not nil");
str = string.gsub(str,"<.->","")
str=stripBlank(str);
str = convertEntities(str)
--mylog("str========\n"..str);
document:setFieldValue(fieldname, str)
else
mylog("str is nil");
end
end
--strip the blank lines
function stripBlank(str)
str = string.gsub(str,"(\n+)","\n")
return str;
end
function convertEntities(str)
local entities =
{
-- chinese entities,I get it from
http://www.w3schools.com/HTML/html_entities.asp --your lua scipts file should save in u8-dos,otherwise some code here will convert into question mark
nbsp = " ",
lt = "<",
gt = ">",
amp = "&",
}
str = string.gsub(str, "&(%a+);",entities)
return str
end
