How to structure HTML text (tags and attributes) for processing in LiveCode?

[Mark Schonewille]

/*** Formatting HTML code ***
indentHtml v.0.1.0, 13 June 2011
Adjust kTags to define tags that need indentation.
Parameters:
theHtml: any valid HTML source code;
theTabSpaces: the number of positions occupied by one tab character
theSoftWrapCol: the column (=position number) after which lines are wrapped
theReplaceTabs: replace tabs with spaces (true, false)
theDontBreakLinks: treat links as regular text, don't indent.
If you change kTags, you should be able to format any mark-up language as
long as it uses < and > to define tags.
By Mark Schonewille
Economy-x-Talk
Nijmegen, the Netherlands
http://economy-x-talk.com
For questions and comments, use the contact form on the website
*/
constant kTags = "html,body,head,title,a,b,i,font,h1,h2,h3,h4,h5,div,center,table,tr,td,th,form,select"
local myTagArray
function indentHtml theHtml,theTabSpaces,theSoftWrapCol,theReplaceTabs,theDontBreakLinks
     replace cr with empty in theHtml
     put 0 into myOldOffset
     put 0 into myPreviousOldOffset
     put 0 into myLevel
     put empty into myTabs
     repeat
          put offset("<",theHtml,myOldOffset) into myNewOffset -- open tag
          if myNewOffset is 0 then exit repeat else add myOldOffset to myNewOffset
          put offset(">",theHtml,myNewOffset) into myOldOffset -- close tag
          if myOldOffset is 0 then exit repeat else add myNewOffset to myOldOffset
          put word 1 of (char myNewOffset+1 to myOldOffset-1 of theHtml) into myTag
          put ((myTag is "a" or myTag is "/a") and theDontBreakLinks is true) into myCurrentTagIsLink
          ///if myTag is "/a" then breakpoint
          put char myPreviousOldOffset+1 to myNewOffset-1 of theHtml into myData
          if myData is not empty then
               put theSoftWrapCol - theTabSpaces*(number of chars of myTabs+1) into myTempWrapCol
               put 1 into myLineCounter
               if myCurrentTagIsLink or (myPreviousTag is "/a" and theDontBreakLinks is true) then
                    // put offset("<",myData) into myTagPosition
                    repeat
                         if number of chars of line myLineCounter of myData > myTempWrapCol and "<" is not in \
                                char 1 to myTempWrapCol of line myLineCounter of myData then
                              put cr & myTabs before word (number of words of (char 1 to myTempWrapCol of line \
                                     myLineCounter of myData) + 1) of line myLineCounter of myData
                              add 1 to myLineCounter
                         else
                              exit repeat
                         end if
                         
                    end repeat
                    if myTag is not "/a" and myPreviousTag is not "/a" then
                         put myTabs before line 1 of myData
                    end if
               else if theTabSpaces is a number and theTabSpaces > 0 and theSoftWrapCol is a number and \
                      theSoftWrapCol > 0 then
                    repeat
                         if number of chars of line myLineCounter of myData > myTempWrapCol then
                              put cr before word (number of words of (char 1 to myTempWrapCol of line \
                                     myLineCounter of myData) + 1) of line myLineCounter of myData
                              add 1 to myLineCounter
                         else
                              exit repeat
                         end if
                         put myTabs before line myLineCounter-1 of myData
                    end repeat
                    if last char of myData is cr then delete last char of myData
                    put myTabs before the last line of myData
               end if
               if myCurrentTagIsLink then
                    put myData after myNewData
               else
                    put myData & cr after myNewData
               end if
          end if
          
          if (char 1 of myTag is slash and char 2 to -1 of myTag is among the items of kTags) then
               subtract 1 from myLevel
               put empty into myTabs
               repeat myLevel
                    put tab after myTabs
               end repeat
          end if
          if myLevel < 0 then put 0 into myLevel
          
          if myCurrentTagIsLink then
               put char myNewOffset to myOldOffset of theHtml after myNewData
          else
               put myTabs & char myNewOffset to myOldOffset of theHtml & cr after myNewData
          end if
          put myOldOffset into myPreviousOldOffset
          // if opening tag then after
          if myTag is among the items of kTags then
               add 1 to myLevel
               put empty into myTabs
               repeat myLevel
                    put tab after myTabs
               end repeat
          end if
          put myTag into myPreviousTag
     end repeat
     put myTabs & char myOldOffset+1 to -1 of theHtml after myNewData
     if theTabSpaces is a number and theTabSpaces > 0 and theReplaceTabs is true then
          put empty into mySpaces
          repeat theTabSpaces
               put space after mySpaces
          end repeat
          replace tab with mySpaces in myNewData
     end if
     return myNewData
end indentHtml

/*
--
Best regards,

Mark Schonewille

Economy-x-Talk Consulting and Software Engineering
Homepage: http://economy-x-talk.com
Twitter: http://twitter.com/xtalkprogrammer
KvK: 50277553

New: Download the Installer Maker Plugin 1.6 for LiveCode here http://qery.us/ce
*/