Conversion of RTF document to plain Text/HTML document using %iKnow.Source.Converter

Not sure about iKnow, but check the article Converting documents with Caché and LibreOffice.

Hi,

I knocked up some code to extract the plain text from an RTF document. It works for my purposes but would like to know if anyone can find a case where it does a bad job.

Copy your .rtf file into a flat array, eg x(1)=first line, x(2)=second line then:

d ##class(yourclass).StripRTF(.x,.y)

and you'll get the plain text in y

/// accepts an RTF doc in array form, doesn't care if lines are split across array members
/// returns plain text from the doc with one array item per line 
/// quit value is number of lines in array
ClassMethod StripRTF(ByRef rtfText = "", ByRef %plainText) As %Integer
{
 // use this code to view an rtf doc split into groups and indented when group level goes up
 // S IN=0,C=0 F I=1:1 S C=##class(ZSS.SMTP).EXTRACT(.x,I) Q:C="" I C="{" {S IN=IN+1 W !?IN*2,"(",IN,")"} W C I C="}" {W "(",IN,")" S IN=IN-1 W !?IN*2}
 n %line
 kill %plainText Set %line=0
 // you could add some speed here by working out how to set characters in the R array to null and
 // reducing the i pointer accordingly
 m R=rtfText
 d ..Brace(.R,$i(i))
 q %line
}

/// A bit like $Extract but the first argument is a single level array, like array(1)="some text", array(2)="some more text"
/// ..EXTRACT(.array,9,11) would return "tso" as the 9th, 10th, and 11th characters of the data in the array
ClassMethod EXTRACT(ByRef array, from As %Integer, to As %Integer, SetToNull = 0) As %String
{
 i '$d(to) s to=from
 S UncleLen=from-to+1 // length of string to return
 s string=""
 f index=1:1 {
  q:'$d(array(index))
  s short=array(index)
  i from'>$l(short) {
   s string=string_$e(short,from,to)
   // mimic SET $EXTRACT
   I SetToNull S $e(array(index),from,to)=""
   q:$l(string)=UncleLen
  }
  s from=from-$l(short),to=to-$l(short)
  i from<0 s from=0
 }
 q string
}
/// discard everything between two braces including the braces
/// done by either moving i to the last brace
/// or if SetToNull is passed as 1 then actually removing the characters from the RTF array
ClassMethod Discard(ByRef rtfText, ByRef i, SetToNull = 0)
{
 s inGroup=1,start=i,stop=i,discarded=""
 f  {
  s discard=..EXTRACT(.rtfText,$i(i))
  q:discard=""
  i discard="}" {
   s inGroup=inGroup-1
  }
  i discard="{" s inGroup=inGroup+1
 q
 }
}
i SetToNull d ..EXTRACT(.rtfText,start,i,1)
}
/// return the contents of a Slash
ClassMethod Slash(ByRef R, ByRef i) As %String
{
 s string="\"
 F  {
  Set char=..EXTRACT(.R, $I(i))
  q:char="" // should never happen but don't want to get stuck in a loop because of a bad file
  i char="}" s i=i-1 q
  i char=" " q
  i char="\" s i=i-1 q
  i char="{" {
   i string?1"\"1a.an {
    // everything inside something like \abc1{this stuff}
    // example {\fonttbl{\fprq2{02020603050405020304}TimesNew Roman;} should all be discarded
    d ..Discard(.R,.i)
    s string=$c(127)
    q
   }
  s char=..Brace(.R,.i)
  }
  i char="*",..EXTRACT(.R, i-2,i+1)="{\*\" {
   // "{\*\" at the start of a brace means the whole brace including nested braces can be ignored
   d ..Discard(.R,.i)
   s string=$c(127)
   q
  }
  i char="'" {
   s string=string_char_..EXTRACT(.R, $I(i),$I(i))
   q
  }
  s string=string_char
  // everything in here should disappear because it looks like {\stylesheet{
  i string="\stylesheet"!(string="\info") {
   d ..Discard(.R,.i)
   s string=$c(127)
   q
  }
 }
 //
 // add stuff here for special characters represented by \codeword
 // you could put them on a global
 //
 i string'="" {
  try {
  // catching stupid subscripts
  s string=$G(^GMAT("RTF","special characters",string),string)
  }
  catch {
   // do nowt
  }
 }
 i string="\lquote" s string="'"
 i string="\rquote" s string="'"
 i string="\ldblquote" s string=""""
 i string="\rdblquote" s string=""""
 i string="\'93" s string=""""  // $c($zh("93")) should be a left double quote
 i string="\'94" s string=""""
 i string?1"\'"2an s string=$c($zh($p(string,"'",2)))
 i string="\par" s string=$c(13,10)
 // REMOVING \codename and \codename1 and \codename1;
 i string ?1"\"1a.an.1";" q ""
 // REMOVING \codename-20
 i string ?1"\"1.a1"-"1.n.1";" q ""
 i string="{}" q ""
 q string
 }
/// return the contents of a pair of braces (troosers!)
ClassMethod Brace(ByRef R, ByRef i) As %String
{
 s string="{"
 F  {
  Set char=..EXTRACT(.R, $I(i),i+1)
  // reached the end and there will be a loose "}"
  i char="",string="}" s string=""
  q:char=""
  // escaped characters that should be allowed through to the text
  s escape=0
  i $lf($lb("\\","\{","\}"),char) s i=i+1,escape=1
  e  s char=$e(char)
  i char="\" {
  s char=..Slash(.R,.i)
  // we hit a ..Discard so remove the brace before it
  i char=$c(127) s char="",$e(string,*)=""
  s string=string_char
  continue
 }
 i char="{" {
  s char=..Brace(.R,.i)
  i char=$c(13,10) {
   //works for 1st line only s %plainText($i(%line))=string,string="",char=""
  f {
   s %plainText($i(%line))=$p(string,$c(13,10),1)
   s string=$p(string,$c(13,10),2,*)
   q:string=""
  }
  s char=""
  }
  s string=string_char
  continue
  }
  // HEX ascii
  i char="\'" {
   s char=$C($ZHEX(..EXTRACT(.R, $I(i),$I(i))))
  }
  s string=string_$e(char,*)
  i string="{}" s string=""
  q:char="}"
 }
 i string="{}" {
  s string=""
 }
 i $e(string)="{",$e(string,*)="}" {
  s string=$e(string,2,*-1)
 }
 q string
}