From 2f99a6b86bf74ff8b618b9b429c0102ffddbbe12 Mon Sep 17 00:00:00 2001
From: Martin Goik <goik@hdm-stuttgart.de>
Date: Sun, 21 Apr 2013 13:59:22 +0200
Subject: [PATCH] Exercise converting XML data to SQL INSERTs by SAX
---
Doc/course.xml | 134 +++++++++++++++++-
.../main/java/sax/context/Catalog2Sql.java | 40 ++++++
.../java/sax/context/Catalog2SqlDriver.java | 11 ++
.../main/java/sax/context/ImportHandler.java | 95 +++++++++++++
.../src/main/java/sax/context/products.xml | 23 +++
.../Jdbc/src/main/java/sax/context/schema.sql | 23 +++
6 files changed, 325 insertions(+), 1 deletion(-)
create mode 100644 ws/eclipse/Jdbc/src/main/java/sax/context/Catalog2Sql.java
create mode 100644 ws/eclipse/Jdbc/src/main/java/sax/context/Catalog2SqlDriver.java
create mode 100644 ws/eclipse/Jdbc/src/main/java/sax/context/ImportHandler.java
create mode 100644 ws/eclipse/Jdbc/src/main/java/sax/context/products.xml
create mode 100644 ws/eclipse/Jdbc/src/main/java/sax/context/schema.sql
diff --git a/Doc/course.xml b/Doc/course.xml
index b421a9dcb..73bdae33d 100644
--- a/Doc/course.xml
+++ b/Doc/course.xml
@@ -15433,6 +15433,120 @@ controlled for these purposes by the company.</para>
</section>
</chapter>
+ <chapter xml:id="extraExercises">
+ <title>Additional exercises</title>
+
+ <para>Exercises appearing here have been added during the current
+ lecture period. They do appear here in order not to interfere with
+ currently existing exercises and their corresponding numbers.</para>
+
+ <qandaset role="exercise">
+ <qandadiv>
+ <qandaentry>
+ <question>
+ <para>Consider the following DTD + document instance
+ example:</para>
+
+ <figure xml:id="catalogProductDescriptionsExample">
+ <title>A sample catalog containing products and corresponding
+ descriptions.</title>
+
+ <programlisting><!DOCTYPE catalog [
+ <!ELEMENT catalog (product*)>
+ <!ELEMENT product (name, description*, age?)>
+ <!ATTLIST product id ID #REQUIRED>
+ <!ELEMENT name (#PCDATA)>
+ <!ELEMENT description (#PCDATA)>
+ <!ELEMENT age (#PCDATA)>
+]>
+<catalog>
+ <product id="mpt">
+ <name>Monkey Picked Tea</name>
+ <description>Rare wild Chinese tea</description>
+ <description>Picked only by specially trained monkeys</description>
+ </product>
+ <product id="instantTent">
+ <name>4-Person Instant Tent</name>
+ <description>4-person, 1-room tent</description>
+ <description>Pre-attached tent poles</description>
+ <description>Exclusive WeatherTec system.</description>
+ <age>15</age>
+ </product>
+</catalog></programlisting>
+ </figure>
+
+ <para>Data being contained in catalog instances shall be
+ transferred to a relational database system. Implement and test
+ a <link linkend="gloss_SAX"><abbrev>SAX</abbrev></link>
+ application by following the subsequently described
+ steps:</para>
+
+ <glosslist>
+ <glossentry>
+ <glossterm>Database schema</glossterm>
+
+ <glossdef>
+ <para>Create a database schema matching a product of your
+ choice (<productname>Mysql</productname>,
+ <productname>Oracle</productname>, ...). Your schema
+ should map type and integrity constraints of the given
+ DTD. In particular:</para>
+
+ <itemizedlist>
+ <listitem>
+ <para>The element <tag class="starttag">age</tag> is
+ optional and always expected to be of integer
+ type.</para>
+ </listitem>
+
+ <listitem>
+ <para>description elements are being composed in
+ <product> elements and should thus be modeled as
+ a 1:n relation. Thus you need a suitable foreign
+ key.</para>
+ </listitem>
+ </itemizedlist>
+ </glossdef>
+ </glossentry>
+
+ <glossentry>
+ <glossterm>SAX Application</glossterm>
+
+ <glossdef>
+ <para>The order of appearance of the XML elements <tag
+ class="starttag">product</tag>, <tag
+ class="starttag">name</tag> and <tag
+ class="starttag">age</tag> does not permit a linear
+ generation of suitable SQL <code>INSERT</code> statements
+ by a <link linkend="gloss_SAX"><abbrev>SAX</abbrev></link>
+ content handler. Instead you will have to keep copies of
+ local element values when implementing
+ <methodname>org.xml.sax.ContentHandler.startElement(String,String,String,org.xml.sax.Attributes)</methodname>
+ and related callback methods. The following sequence of
+ insert statements corresponds to the XML data being
+ contained in <xref
+ linkend="catalogProductDescriptionsExample"/>. You may use
+ these statements as a blueprint to be generated by your
+ <link linkend="gloss_SAX"><abbrev>SAX</abbrev></link>
+ application:</para>
+
+ <programlisting><emphasis role="bold">INSERT INTO Product VALUES ('mpt', 'Monkey Picked Tea', NULL);</emphasis>
+INSERT INTO Description VALUES('mpt', 'Picked only by specially trained monkeys');
+INSERT INTO Description VALUES('mpt', 'Rare wild Chinese tea');
+
+<emphasis role="bold">INSERT INTO Product VALUES ('instantTent', '4-Person Instant Tent', 15);</emphasis>
+INSERT INTO Description VALUES('instantTent', 'Exclusive WeatherTec system.');
+INSERT INTO Description VALUES('instantTent', '4-person, 1-room tent');
+INSERT INTO Description VALUES('instantTent', 'Pre-attached tent poles');</programlisting>
+ </glossdef>
+ </glossentry>
+ </glosslist>
+ </question>
+ </qandaentry>
+ </qandadiv>
+ </qandaset>
+ </chapter>
+
<appendix>
<title>W3C production rules</title>
@@ -18345,7 +18459,7 @@ public class PersistUser {
<question>
<para>Replace set by <classname>java.util.List</classname>
and assure that the order of components is being preserved
- in a JPA2 compliant manner. </para>
+ in a JPA2 compliant manner.</para>
</question>
</qandaentry>
</qandadiv>
@@ -18410,6 +18524,24 @@ public class PersistUser {
</glossdef>
</glossentry>
+ <glossentry xml:id="gloss_SAX">
+ <glossterm><abbrev>SAX</abbrev></glossterm>
+
+ <glossdef>
+ <para><link xlink:href="http://www.saxproject.org">Simple API for
+ XML</link>.</para>
+ </glossdef>
+ </glossentry>
+
+ <glossentry xml:id="gloss_SQL">
+ <glossterm><abbrev>SQL</abbrev></glossterm>
+
+ <glossdef>
+ <para><link xlink:href="http://en.wikipedia.org/wiki/SQL">Structured
+ query language</link>.</para>
+ </glossdef>
+ </glossentry>
+
<glossentry xml:id="gloss_XML">
<glossterm><abbrev>XML</abbrev></glossterm>
diff --git a/ws/eclipse/Jdbc/src/main/java/sax/context/Catalog2Sql.java b/ws/eclipse/Jdbc/src/main/java/sax/context/Catalog2Sql.java
new file mode 100644
index 000000000..46e251e07
--- /dev/null
+++ b/ws/eclipse/Jdbc/src/main/java/sax/context/Catalog2Sql.java
@@ -0,0 +1,40 @@
+package sax.context;
+
+import java.io.IOException;
+
+import javax.xml.parsers.ParserConfigurationException;
+import javax.xml.parsers.SAXParser;
+import javax.xml.parsers.SAXParserFactory;
+
+import org.xml.sax.SAXException;
+import org.xml.sax.XMLReader;
+
+import dom.MySaxErrorHandler;
+
+/** Parsing catalog instances for import to RDBMS. */
+public class Catalog2Sql {
+
+ /** Set up a validating parser instance.
+ *
+ * @throws SAXException
+ * @throws ParserConfigurationException */
+ public Catalog2Sql()
+
+ throws SAXException, ParserConfigurationException {
+ final SAXParserFactory saxPf = SAXParserFactory.newInstance();
+ final SAXParser saxParser = saxPf.newSAXParser();
+ xmlReader = saxParser.getXMLReader();
+ xmlReader.setFeature("http://xml.org/sax/features/validation", true);
+ xmlReader.setContentHandler(new ImportHandler());
+ xmlReader.setErrorHandler(new MySaxErrorHandler(System.out));
+ }
+ /** Initiate parsing
+ * @param uri
+ * @throws IOException
+ * @throws SAXException */
+ public void parse(final String uri)
+ throws IOException, SAXException{
+ xmlReader.parse(uri);
+ }
+ private final XMLReader xmlReader;
+}
\ No newline at end of file
diff --git a/ws/eclipse/Jdbc/src/main/java/sax/context/Catalog2SqlDriver.java b/ws/eclipse/Jdbc/src/main/java/sax/context/Catalog2SqlDriver.java
new file mode 100644
index 000000000..824cee237
--- /dev/null
+++ b/ws/eclipse/Jdbc/src/main/java/sax/context/Catalog2SqlDriver.java
@@ -0,0 +1,11 @@
+package sax.context;
+
+public class Catalog2SqlDriver {
+
+
+ public static void main(String argv[]) throws Exception{
+ final Catalog2Sql importer = new Catalog2Sql();
+ importer.parse("src/main/java/sax/context/products.xml");
+ }
+
+}
diff --git a/ws/eclipse/Jdbc/src/main/java/sax/context/ImportHandler.java b/ws/eclipse/Jdbc/src/main/java/sax/context/ImportHandler.java
new file mode 100644
index 000000000..e79148fe3
--- /dev/null
+++ b/ws/eclipse/Jdbc/src/main/java/sax/context/ImportHandler.java
@@ -0,0 +1,95 @@
+package sax.context;
+
+import java.util.HashSet;
+import java.util.Set;
+
+import org.xml.sax.Attributes;
+import org.xml.sax.ContentHandler;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+
+/** Reading attributes from element events */
+public class ImportHandler implements ContentHandler {
+
+ private Set<String> currentDescriptions = new HashSet<String>();
+ String lastCharacterUnit = null
+ ,lastAgeString = null
+ ,currentProductId;
+ @Override
+ public void startElement(String uri, String localName, String qName,
+ Attributes attributes) throws SAXException {
+ switch(qName) {
+ case "product":
+ currentProductId = attributes.getValue("id");
+ System.out.print("INSERT INTO Product VALUES ('" + currentProductId + "'");
+ }
+ }
+
+ @Override
+ public void endElement(final String uri, final String localName, final String qName)
+ throws SAXException {
+ switch(qName) {
+ case "product":
+ if (null == lastAgeString) {
+ System.out.print( ", NULL");
+ } else {
+ try {
+ System.out.print(", " + Integer.parseInt(lastCharacterUnit));
+ } catch (NumberFormatException ex) {
+ System.err.println("Age is not an integer value:" + lastCharacterUnit);
+ }
+ lastAgeString = null;
+ }
+
+ System.out.println(");");
+ flushDescriptionEntries();
+ break;
+ case "name":
+ System.out.print(", '" + lastCharacterUnit + "'");
+ break;
+
+ case "description":
+ // Do not interfere with the current INSERT INTO Product ...
+ // statement. Instead postpone related INSERT INTO Description ...
+ // operations, see flushDescriptionEntries().
+ currentDescriptions.add(lastCharacterUnit);
+ break;
+ case "age":
+ lastAgeString = lastCharacterUnit;
+ break;
+ }
+ }
+ private void flushDescriptionEntries() {
+ // Add <description> related INSERTs
+ for (final String description: currentDescriptions) {
+ System.out.println("INSERT INTO Description VALUES('" +
+ currentProductId + "', '" + description + "');");
+ }
+ // Next <product> is yet to come, so
+ // clear the current set of descriptions.
+ currentDescriptions.clear();
+ }
+
+ @Override
+ public void characters(final char[] ch, final int start, final int length)
+ throws SAXException {
+ lastCharacterUnit = new String(ch, start,length);
+ }
+
+ // We don't need these remaining callbacks
+
+ @Override public void setDocumentLocator(Locator locator) {}
+ @Override public void startDocument() throws SAXException {}
+ @Override public void endDocument() throws SAXException {}
+ @Override public void startPrefixMapping(String prefix, String uri)
+ throws SAXException {}
+ @Override public void endPrefixMapping(String prefix)
+ throws SAXException {}
+ @Override public void ignorableWhitespace(char[] ch, int start, int length)
+ throws SAXException {}
+
+ @Override public void processingInstruction(String target, String data)
+ throws SAXException {}
+
+ @Override public void skippedEntity(String name) throws SAXException {}
+}
\ No newline at end of file
diff --git a/ws/eclipse/Jdbc/src/main/java/sax/context/products.xml b/ws/eclipse/Jdbc/src/main/java/sax/context/products.xml
new file mode 100644
index 000000000..7bf5b33fc
--- /dev/null
+++ b/ws/eclipse/Jdbc/src/main/java/sax/context/products.xml
@@ -0,0 +1,23 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE catalog [
+ <!ELEMENT catalog (product*)>
+ <!ELEMENT product (name, description*, age?)>
+ <!ATTLIST product id ID #REQUIRED>
+ <!ELEMENT name (#PCDATA)>
+ <!ELEMENT description (#PCDATA)>
+ <!ELEMENT age (#PCDATA)>
+]>
+<catalog>
+ <product id="mpt">
+ <name>Monkey Picked Tea</name>
+ <description>Rare wild Chinese tea</description>
+ <description>Picked only by specially trained monkeys</description>
+ </product>
+ <product id="instantTent">
+ <name>4-Person Instant Tent</name>
+ <description>4-person, 1-room tent</description>
+ <description>Pre-attached tent poles</description>
+ <description>Exclusive WeatherTec system.</description>
+ <age>15</age>
+ </product>
+</catalog>
\ No newline at end of file
diff --git a/ws/eclipse/Jdbc/src/main/java/sax/context/schema.sql b/ws/eclipse/Jdbc/src/main/java/sax/context/schema.sql
new file mode 100644
index 000000000..60f6bccce
--- /dev/null
+++ b/ws/eclipse/Jdbc/src/main/java/sax/context/schema.sql
@@ -0,0 +1,23 @@
+CREATE TABLE Product (
+ id CHAR(20) NOT NULL PRIMARY KEY
+ ,name VARCHAR(255) NOT NULL
+ ,age SMALLINT
+);
+
+CREATE TABLE Description (
+ product CHAR(20) NOT NULL REFERENCES Product
+ ,text VARCHAR(255) NOT NULL
+);
+
+-- example data corresponding to products.xml --
+INSERT INTO Product VALUES ('mpt', 'Monkey Picked Tea', NULL);
+INSERT INTO Description VALUES('mpt', 'Picked only by specially trained monkeys');
+INSERT INTO Description VALUES('mpt', 'Rare wild Chinese tea');
+INSERT INTO Product VALUES ('instantTent', '4-Person Instant Tent', 15);
+INSERT INTO Description VALUES('instantTent', 'Exclusive WeatherTec system.');
+INSERT INTO Description VALUES('instantTent', '4-person, 1-room tent');
+INSERT INTO Description VALUES('instantTent', 'Pre-attached tent poles');
+
+-- tidy up --
+DROP TABLE Description;
+DROP TABLE Product;
\ No newline at end of file
--
GitLab