CMT3315: Lab 2 - XML Vs. HTML

Questions:

Have a look at the documents below. Some are XML documents, some are HTML documents, some may be neither. See if you can decide which are which.

Document 1 is an HTML file which is indicated with the used of the <head> and <body> tags. Also it uses metdata which is used by search engines.

Document 2 is an XML file as it has a <DOCTYPE> which is an XML declaration to point to a DTD. Also it contains an XSL document linked to it which means that data in it will contain some formatting

Document 3 is an HTML file as it is also making use of the <head> tag. Also there is a declaration for an Input form, which will contain a drop down and a button. Also the document has some Javascript declared in the

Document 4 is an XML file again containg a <DOCTYPE> pointing to a dtd. This particular XML does not contain any XSL for formatting.

Document 5 is again another XML file pointing to a DTD.

Document 6 is yet another XML file pointing to a DTD.

Document 7 is an HTML file containing Javascript again having the same characteristics as the other HTML files

Make a list of the distinctive characteristics of an XML document, in terms of things that you can spot when looking at the code.

An XML document should have an XML declaration
An XML document should be an assignment of a DTD or XSL schema
All opening tags must be closed
Attributes are placed within quotes
An XML document contains only one root element.

Assume that (with suitable changes) all these documents could become XML documents. Imagine, and describe, applications that could use these documents.

Document 1 can hold a list of surgical procedures of Ancient Egyptian time

Document 2 is used for data and list regarding adverts

Document 3 is used to select files and load them.

Document 4 is holding all the information and structure of a story and/or a book

Document 5 is holding all the information and structure of a poem

Document 6 is storing specific information on every country

Document 7 holds various information about people and then specific information form it can be displayed depending on what the user chooses

Appendix: XML and HTML documents for identification:

NB I’ve removed one or more lines from each document to stop it being too easy.

<head>

<title>The Edwin Smith Surgical Papyrus</title>

</head>

<body background="Back25.jpg" bgcolor="#FFFFFF" text="#000000"

link="#808000" vlink="#008080">

<tr>

var id=305; var jar=new Date();var s=jar.getSeconds();var m=jar.getMinutes();

var flash=s*m+id;var cgi='http://ads.touregypt.net/cgi-bin/adcycle';

var p='<iframe src="'+cgi+'/adcycle.cgi?gid=1&t=_top&id='+flash+'&type=iframe" ';

p+='height=60 width=468 border=0 marginwidth=0 marginheight=0 hspace=0 ';

p+='vspace=0 frameborder=0 scrolling=no>';

p+='<a href="'+cgi+'/adclick.cgi?gid=1&id='+flash+'" target="_top">';

p+='<img src="'+cgi+'/adcycle.cgi?gid=1&id='+flash+'" width=468 height=60 ';

p+='border=1 alt="Click to Visit"></a></iframe>'; document.write(p); // -->

</script><noscript><a href="http://ads.touregypt.net/cgi-bin/adcycle/adclick.cgi?gid=1&id=305" target="_top">

</center>

</td>

</tr>

</table>

<tr>

<td>

<b>The Edwin Smith Surgical Papyrus</b>

</font>

<p>

The Edwin Smith Surgical Papyrus, dating from the seventeenth century B.C., is one of the oldest of all known medical papyri. Its differs fundamentally from the others in the following ways:

</font>

<P>

</font>

<ol>

<li>

The seventeen columns on the recto comprise part of a surgical treatise, the first thus far discovered in the ancient Orient, whether in Egypt or Asia. It is therefore the oldest known surgical treatise.

</font>

<li>

<!DOCTYPE advertisement SYSTEM "advertisement.dtd">

<?xml-stylesheet type="text/xsl" href="ad1.xsl" ?>

NYT.19980701.12345.107

</id>

19980731

</expiration>

Ad to sell Linda's car.

</reference>

Up sold to add Friday repeat.

</comment>

<name>

John Smyth

</name>

<address_line>c/o Bat Accessories, Inc.</address_line>

<address_line>Hitchcock Building, 80th Floor</address_line>

<address_line>1313 Mockingbird Lane</address_line>

<city>New York</city>,

</address>

<phone>

19085551212

</phone>

<fax>

19085551213

</fax>

<email>

jsymth@batacc.com

</email>

<url>

http://www.batacc.com/~smyth

</url>

</contact>

19980701 12290200

</timestamp>

JK1892

</userid>

</updated>

19980701 12225800

</timestamp>

JK1892

</userid>

</created>

NYT.19980621.90810.98

</base>

</source>

19085551212-1

</account>

<contact_ref link="contact1"></contact_ref>

<charge_card brand="amex"></charge_card>

<charge_account>3710-111111-99995</charge_account>

<charge_expiration>19991231</charge_expiration>

<contact_ref link="contact1"></contact_ref>

<charge_authorization status="allowed">4561</charge_authorization>

</charge>

</payment>

</advertiser>

<auto_side value="sell">sell</auto_side>

<auto_category value="used">used</auto_category>

<auto_year>1991</auto_year>

<auto_make>Saab</auto_make>

<auto_model>900 Convertible</auto_model>

<auto_mileage>72000</auto_mileage>

<auto_price>$13,900</auto_price>

<auto_exterior>white</auto_exterior>

<auto_interior>gray leather</auto_interior>

<auto_body value="convertible">convertible</auto_body>

<auto_vin>372AB918098910X</auto_vin>

</automotive>

</contact>

</coding>

<text>

</center>

</font>

<keyword name="auto_exterior" punct=" ">yellow </keyword>

<keyword name="auto_body" punct=", ">convertible, </keyword>

<keyword name="auto_mileage" format="9'k miles'" scale="1000"

punct=", ">14k miles, </keyword>

Auto, PL, PW, AC, power leather Seats

Showroom cond. Assume lease.

Call

212-333-3333

</keyword>

</center>

</text>

<pub_alias>

981011301

</pub_alias>

<pub_price>

$128.00

</pub_price>

<pub_options>

<claim>

</claim>

</columns>

Please email replies to <mailbox>T1234</mailbox>@nytimes.com

<rate basis="Email forwarding service charge--Full run"

unit="ad">$25.00

</rate>

</forwarding>

</tearsheet>

</shading>

</pub_options>

<class>

3720

<title>Autos/Vans/Sports Utilities</title>

<classword>Automotive</classword>

<lines>

</lines>

SAAB91900

</sortkey>

<zone>

</zone>

19980719

<rate basis="Automotive, Open, Sunday NY Region"

unit="line">$23.10

</rate>

</instance>

</instance>

</instance>

</instance>

</instance>

</rundate>

19980724

<rate basis="Automotive, Open, Weekday NY Region--

Sunday ad repeated on Friday (within 7 days)"

unit="line">$8.90

</rate>

<rate basis="Automotive, Open, Weekday NY Region"

unit="line" type="comparison">$15.20

</rate>

<edition>METRO</edition>

</instance>

</rundate>

</class>

</publication>

</advertisement>

<head>

<title>Display</title>

function loadFile ()

{

var filename

var selectionValue

selectionValue = document.forms[0].selectList.selectedIndex

filename = document.forms[0].selectList.options[selectionValue].value

parent.rightFrame.location = filename

}

</script>

</head>

<body>

<H4>XML File Chooser</H4>

<P>Select the file you wish to see displayed in the right-hand frame.

<P>

<OPTION VALUE="countryList/countryList.xml"> Country Data

<OPTION VALUE="playerList/playerList.xml"> Baseball Player Data

</SELECT>

<P>

</FORM>

</body>

<!DOCTYPE story SYSTEM "storyxsl.dtd">

<story>

<title>Freedom's Dream</title>

<author>by Charles White</author>

<para>Had it been a dream, Antron Crimea's memory of the clenched fist piercing the

sky of a tumultuous, thundering crowd would have been bearable solitude. As

it was though, the reality brought him to another place, to a distance only

something like a dream could take him.</para>

<para>"The crowd forgot everything," is how Antron described the situation to his

psychiatrist, <link id="ChesapeakeLink">

Chesapeake Alert.</link>

Antron remembered the rhythm, the pulse,

everything. After all this time the energy of the crowd still seemed to reverberate through

his head.</para>

<para>Chesapeake Alert was nothing but a large bulbous mass of jelly-like flesh; a

brain plopped down on an empty, expensive slice of carpet. And though he

had no legitimate locomotive capabilities of his own, he was aware of the

movements of a billion others.</para>

<para>Antron's hundred legs crawled around what was left of the carpet in the kind of

pace unknown to you or I. His earlier confusion had long ago been dissolved

by the righteous events of what he had seen during the course of events Billy

Freedom had ignited.</para>

<para>"Sometimes betrayal is a necessity,"said Chesapeake. "Startling. And

expensive. It must be weighed carefully."</para>

</section>

<auto-link

xml:link="simple"

actuate="user"

href="sec_2.xml"

show="replace">click here to continue</auto-link>

</story>

<!DOCTYPE my.dtd [

    <!ELEMENT anthology      - -  (poem+)>

    <!ELEMENT poem           - -  (title?, stanza+)>

    <!ELEMENT title          - O  (#PCDATA) >

    <!ELEMENT stanza         - O  (line+)   >

    <!ELEMENT line           O O  (#PCDATA) >

]>

<my.dtd>

<anthology>

         <poem><title>The SICK ROSE

         <stanza>

              <line>O Rose thou art sick.

              <line>The invisible worm,

              <line>That flies in the night

              <line>In the howling storm:

         <stanza>

              <line>Has found out thy bed

              <line>Of crimson joy:

              <line>And his dark secret love

              <line>Does thy life destroy.

          <poem>

              <!-- more poems go here    -->

    </anthology>

</my.dtd>

<!DOCTYPE countryCollection SYSTEM "countryList.dtd">

<officialName>United States of America</officialName>

<label>Common Names:</label>

<commonName>United States</commonName>

<label>Capital:</label>

<capital>Washington, D.C.</capital>

<label>Major Cities:</label>

<majorCity> Los Angeles </majorCity>

<majorCity> Chicago </majorCity>

<majorCity> Dallas </majorCity>

<label>Bordering Bodies of Water:</label>

<borderingBodyOfWater> Atlantic Ocean </borderingBodyOfWater>

<borderingBodyOfWater> Pacific Ocean </borderingBodyOfWater>

<borderingBodyOfWater> Gulf of Mexico </borderingBodyOfWater>

<label>Bordering Countries:</label>

<borderingCountry> Canada </borderingCountry>

<borderingCountry> Mexico </borderingCountry>

</country>

<officialName> Japan </officialName>

<label>Common Names:</label>

<commonName> Japan </commonName>

<label>Capital:</label>

<capital>Tokyo</capital>

<label>Major Cities:</label>

<majorCity> Nagoya </majorCity>

<majorCity> Osaka </majorCity>

<label>Bordering Bodies of Water:</label>

<borderingBodyOfWater> Sea of Japan </borderingBodyOfWater>

<borderingBodyOfWater> Pacific Ocean </borderingBodyOfWater>

</country>

<officialName> Republic of Kenya </officialName>

<label>Common Names:</label>

<commonName> Kenya </commonName>

<label>Capital:</label>

<capital> Nairobi </capital>

<label>Major Cities:</label>

<majorCity> Mombasa </majorCity>

<majorCity> Malindi </majorCity>

<majorCity> Kisumu </majorCity>

<label>Bordering Bodies of Water:</label>

<borderingBodyOfWater> Indian Ocean </borderingBodyOfWater>

</country>

</countryList>

<head>

//The global variable containing the XML string we'll examine. Normally, global variables are to be avoided. But here, it's the easiest way to

//approach the problem, since it would be easy to have a server-side script include the contents of the XML file as a single line here.

gXMLString = " <officialName> United States of America </officialName> <commonName> United States </commonName> <commonName> U.S. </commonName> <capital> Washington, D.C. </capital> <majorCity> Los Angeles </majorCity> <majorCity> New York </majorCity> <majorCity> Chicago </majorCity> <majorCity> Dallas </majorCity> <borderingBodyOfWater> Atlantic Ocean </borderingBodyOfWater> <borderingBodyOfWater> Pacific Ocean </borderingBodyOfWater> <borderingBodyOfWater> Gulf of Mexico </borderingBodyOfWater> <borderingCountry> Canada </borderingCountry> <borderingCountry> Mexico </borderingCountry>"

function findTagsPresent()

{

var arrayOfPieces = new Array()

arrayOfPieces = gXMLString.split(" ")

numberOfPieces = arrayOfPieces.length

var tagsPresent = new Array()

var tagsPresentCounter

tagsPresentCounter = 0

for (i=0; i<numberOfPieces; i++)

{

if ((arrayOfPieces[i].indexOf("<") == 0) && (arrayOfPieces[i].indexOf(">") == (arrayOfPieces[i].length-1)) && (arrayOfPieces[i].indexOf("</") == -1))

// If that's the case, then we've found an opening tag.

{

var arrayLength

arrayLength = tagsPresent.length

var foundIt

foundIt = false

for (j=0; j<arrayLength; j++)

{

if (tagsPresent[j] == arrayOfPieces[i])

{

foundIt = true

break

}

if (foundIt != true)

//And if that's the case, it's not already in tagsPresent

{

tagsPresent[tagsPresentCounter] = arrayOfPieces[i]

tagsPresentCounter++

}

return tagsPresent

}

function writeListOfTagsPresentWithCheckboxes()

{

var listOfTags

listOfTags = findTagsPresent()

var listLength

listLength = listOfTags.length

var numberOfCheckBoxes

numberOfCheckBoxes = 0

for (i=0; i<listLength; i++)

{

var tagStringLength

tagStringLength = listOfTags[i].length

var strippedTagString

strippedTagString = listOfTags[i].substring(1, (tagStringLength-1))

document.write("<BR>")

document.write("<INPUT TYPE='checkbox' NAME='box" + i + "' VALUE='" + strippedTagString + "'>  ")

document.write(strippedTagString)

numberOfCheckBoxes++

}

document.write("<P>")

document.write("<INPUT TYPE='button' value='Display' onClick='displaySelectedXMLData(" + numberOfCheckBoxes + ")'>")

}

function contentsTaggedThisWay(tagString)

{

var arrayOfPieces = new Array()

arrayOfPieces = gXMLString.split(" ")

var numberOfPieces

numberOfPieces = arrayOfPieces.length

var taggedData

taggedData = ""

var i

i = 0

while (i<numberOfPieces)

{

if (arrayOfPieces[i] == ("<" + tagString + ">"))

{

var foundEndTag

taggedData += "<BR>"

foundEndTag = false

var j

j = 1

while (!(foundEndTag))

{

if (arrayOfPieces[(i + j)] == ("</" + tagString + ">"))

{

foundEndTag = true

}

else

{

taggedData += arrayOfPieces[(i + j)]

taggedData += " "

j++

}

i++

}

return taggedData

}

function displaySelectedXMLData(numberOfBoxes)

{

var stringToWrite

stringToWrite = ""

parent.rightFrame.location.reload()

stringToWrite = "<HTML> <HEAD> </HEAD> <BODY>"

var i

i=0

while (i<numberOfBoxes)

{

currentBoxName = "box" + i

if (document.selectionForm.elements[currentBoxName].checked)

{

stringToWrite += "<P><B>" + document.selectionForm.elements[currentBoxName].value + "</B>"

stringToWrite += contentsTaggedThisWay(document.selectionForm.elements[currentBoxName].value)

}

i++

}

stringToWrite += "</BODY> </HTML>"

parent.rightFrame.document.write(stringToWrite)

}

</script>

</head>

<body>

<H4>Data Chooser</H4>

<P>Choose the tags whose data you want to display.

writeListOfTagsPresentWithCheckboxes()

</SCRIPT>

<P>

</FORM>

</body>

CMT3315

Monday, 7 November 2011

Lab 2 - XML Vs. HTML

No comments:

Post a Comment

About Me

Blog Archive