xsl-list
[Top] [All Lists]

Re: [xsl] Expanding Tabs

2010-03-31 03:27:02
Here is an alternative solution:

<xsl:function name="wl:spaces" as="xs:string">
  <xsl:param name="repeats" as="xs:integer"/>
  <xsl:choose>
    <xsl:when test="$repeats=0">  <!-- be more general -->
      <xsl:value-of select="''"/>
    </xsl:when>
    <xsl:when test="$repeats=1">
      <xsl:value-of select="' '"/>
    </xsl:when>
    <xsl:otherwise>
      <xsl:variable name="half" select="$repeats idiv 2"/>
      <xsl:value-of select="concat(wl:spaces($half),wl:spaces($repeats
- $half))"/>
    </xsl:otherwise>
  </xsl:choose>
</xsl:function>

<!-- tabify <pos> <head> <tail>
     Recurse, appending spaces according to <pos> and first <tail>
item to <head> -->
<xsl:function name="wl:tabify" as="xs:string">
  <xsl:param name="pos"  as="xs:integer"/>
  <xsl:param name="head" as="xs:string"/>
  <xsl:param name="tail" as="xs:string*"/>
  <xsl:choose>
    <xsl:when test="count($tail)=0">
      <xsl:value-of select="$head"/>
    </xsl:when>
    <xsl:otherwise>
      <xsl:value-of
        select="wl:tabify($pos,concat($head,wl:spaces($pos -
string-length($head) mod $pos),$tail[1]),subsequence($tail,2))"/>
    </xsl:otherwise>
  </xsl:choose>
</xsl:function>

<!-- expand <str> <pos>
     Expand <str> inserting spaces for TABs, assuming tab stops apart
by <pos> chars. -->
<xsl:function name="wl:expand" as="xs:string">
  <xsl:param name="str" as="xs:string"/>
  <xsl:param name="pos" as="xs:integer"/>
  <xsl:choose>
    <xsl:when test="string-length($str)=0">
      <xsl:value-of select="''"/>
    </xsl:when>
    <xsl:otherwise>
      <xsl:variable name="tokens" as="xs:string+" select="tokenize($str,'\t')"/>
      <xsl:value-of select="wl:tabify($pos,$tokens[1],subsequence($tokens,2))"/>
    </xsl:otherwise>
  </xsl:choose>
</xsl:function>

<xsl:template name="expand">
<text>
<xsl:for-each select="tokenize(unparsed-text($textpath), '\r?\n')">
  <line><xsl:value-of select="wl:expand(.,8)"/></line>
</xsl:for-each>
</text>
</xsl:template>

Cheers
-W


On Tue, Mar 30, 2010 at 11:10 PM, Alex Muir 
<alex(_dot_)g(_dot_)muir(_at_)gmail(_dot_)com> wrote:

Hi,

Wrote some code that does the job for the files we are using.
Basically looks for a line containing a tab then splits the line
recursively by the text before the tab, the tab and the text following
the tab and calculates the number of spaces needed using some modulus.

A maxTabSize variable is set to 8 as a parameter in the style sheet
given this is what is the maximum number of spaces in our documents in
both textpad and notepad for a tab.

I tested it and couldn't break it however could be buggy given just wrote it.

Regards


 <xsl:template match="/" name="start">
   <xsl:element name="document">

     <xsl:variable name="regex">
       <xsl:text>([^\t]*?)(\t)(.*?$)</xsl:text>
     </xsl:variable>

     <xsl:element name="content">
       <xsl:element name="text">
         <xsl:for-each select="tokenize(unparsed-text($input_uri,
'UTF-8'), '\r?\n')">

           <xsl:choose>
             <xsl:when test="matches(.,$regex)">
               <xsl:call-template name="expandTabs">
                 <xsl:with-param name="maxTabSize"
select="xs:integer($maxTabSize)"/>
                 <xsl:with-param name="content" select="."/>
               </xsl:call-template>
             </xsl:when>
             <xsl:otherwise>
               <xsl:value-of select="."/>
             </xsl:otherwise>
           </xsl:choose>
         </xsl:for-each>
   </xsl:element>
 </xsl:template>


 <xsl:template name="expandTabs">
   <xsl:param name="maxTabSize" as="xs:integer"/>
   <xsl:param name="content"/>
   <xsl:variable name="regex">
     <xsl:text>([^\t]*?)(\t)(.*?$)</xsl:text>
   </xsl:variable>
   <xsl:choose>
     <xsl:when test="string-length($content) > 0">
       <xsl:analyze-string select="$content" regex="{$regex}">
         <xsl:matching-substring>

           <xsl:value-of select="regex-group(1)"/>

           <xsl:variable name="lenghtBeforeTabStop"
             select="string-length(regex-group(1)) mod $maxTabSize"
as="xs:integer"/>

           <xsl:call-template name="insertSpace">
             <xsl:with-param name="n" select="$maxTabSize -
$lenghtBeforeTabStop"/>
             <xsl:with-param name="i" select="1"/>
           </xsl:call-template>
           <xsl:choose>
           <xsl:when test="matches(regex-group(3),$regex)">
             <xsl:call-template name="expandTabs">
               <xsl:with-param name="maxTabSize" select="$maxTabSize"/>
               <xsl:with-param name="content" select="regex-group(3)"/>
             </xsl:call-template>
           </xsl:when>
             <xsl:otherwise>
               <xsl:value-of select="regex-group(3)"/>
             </xsl:otherwise>
             </xsl:choose>

         </xsl:matching-substring>
       </xsl:analyze-string>
     </xsl:when>
   </xsl:choose>

 </xsl:template>


 <xsl:template name="insertSpace">
   <xsl:param name="i" as="xs:integer"/>
   <xsl:param name="n" as="xs:integer"/>
   <xsl:choose>
     <xsl:when test="$i le $n">
       <xsl:text>&#x20;</xsl:text>
       <xsl:call-template name="insertSpace">
         <xsl:with-param name="n" select="$n"/>
         <xsl:with-param name="i" select="$i + 1"/>
       </xsl:call-template>
     </xsl:when>
   </xsl:choose>
 </xsl:template>

On Tue, Mar 30, 2010 at 2:18 PM, Wolfgang Laun 
<wolfgang(_dot_)laun(_at_)gmail(_dot_)com> wrote:
Tab stops are always by convention and rarely contained in a data file.

At least that's my experience with generations of text editors and
frequent anger due to seeing weird alignment after switching editors.

-W

On Tue, Mar 30, 2010 at 4:00 PM, Dave Pawson 
<davep(_at_)dpawson(_dot_)co(_dot_)uk> wrote:

On Tue, 30 Mar 2010 14:08:26 +0100
"Michael Kay" <mike(_at_)saxonica(_dot_)com> wrote:


What I'm doing is converting old text documents into XML.

So why not run a text-based utility on them to convert tabs into
spaces, before you do anything else?

Isn't the line length, tab-stop setting etc missing from the XML?
Even with text pre-processing I'm not sure how this can be done?

guesswork?


regards



--

regards

--
Dave Pawson
XSLT XSL-FO FAQ.
http://www.dpawson.co.uk

--~------------------------------------------------------------------
XSL-List info and archive:  http://www.mulberrytech.com/xsl/xsl-list
To unsubscribe, go to: http://lists.mulberrytech.com/xsl-list/
or e-mail: 
<mailto:xsl-list-unsubscribe(_at_)lists(_dot_)mulberrytech(_dot_)com>
--~--


--~------------------------------------------------------------------
XSL-List info and archive:  http://www.mulberrytech.com/xsl/xsl-list
To unsubscribe, go to: http://lists.mulberrytech.com/xsl-list/
or e-mail: 
<mailto:xsl-list-unsubscribe(_at_)lists(_dot_)mulberrytech(_dot_)com>
--~--





--
Alex
https://sites.google.com/a/utg.edu.gm/alex

Some Good Music
http://sites.google.com/site/greigconteh/

--~------------------------------------------------------------------
XSL-List info and archive:  http://www.mulberrytech.com/xsl/xsl-list
To unsubscribe, go to: http://lists.mulberrytech.com/xsl-list/
or e-mail: 
<mailto:xsl-list-unsubscribe(_at_)lists(_dot_)mulberrytech(_dot_)com>
--~--


--~------------------------------------------------------------------
XSL-List info and archive:  http://www.mulberrytech.com/xsl/xsl-list
To unsubscribe, go to: http://lists.mulberrytech.com/xsl-list/
or e-mail: <mailto:xsl-list-unsubscribe(_at_)lists(_dot_)mulberrytech(_dot_)com>
--~--

<Prev in Thread] Current Thread [Next in Thread>