My process stops in certaing cases and i do not really find the answer what the reason is. Sometimes the message is that: Process failed: Tha name "µ
g" is not legal for JDOM/XML attributes: XML names cannot begin with the charater "µ". Do you know the reason??
my code is:
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.1.003">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.1.003" expanded="true" name="Process">
<process expanded="true" height="426" width="1036">
<operator activated="true" class="read_csv" compatibility="5.1.003" expanded="true" height="60" name="Read CSV" width="90" x="45" y="120">
<parameter key="csv_file" value="C:\input.csv"/>
<list key="annotations"/>
<list key="data_set_meta_data_information"/>
</operator>
<operator activated="true" class="web:retrieve_webpages" compatibility="5.1.000" expanded="true" height="60" name="Get Pages" width="90" x="179" y="120">
<parameter key="link_attribute" value="link"/>
<parameter key="page_attribute" value="oldal"/>
<parameter key="random_user_agent" value="true"/>
<parameter key="follow_redirects" value="false"/>
</operator>
<operator activated="true" class="text:data_to_documents" compatibility="5.1.001" expanded="true" height="60" name="Data to Documents" width="90" x="313" y="120">
<list key="specify_weights"/>
</operator>
<operator activated="true" class="multiply" compatibility="5.1.003" expanded="true" height="94" name="Multiply" width="90" x="447" y="165"/>
<operator activated="true" class="text:process_documents" compatibility="5.1.001" expanded="true" height="94" name="Process Documents (2)" width="90" x="648" y="30">
<parameter key="create_word_vector" value="false"/>
<process expanded="true" height="428" width="634">
<operator activated="true" class="text:cut_document" compatibility="5.1.001" expanded="true" height="60" name="Cut Document (3)" width="90" x="313" y="30">
<parameter key="query_type" value="XPath"/>
<list key="string_machting_queries"/>
<list key="regular_expression_queries"/>
<list key="regular_region_queries"/>
<list key="xpath_queries">
<parameter key="termeklap" value="h:html/h:body/h:table[2]/h:tr/h:td[2]/h:table[1]/h:tr/h:td[1]/h:div[1]"/>
</list>
<list key="namespaces"/>
<list key="index_queries"/>
<process expanded="true" height="446" width="652">
<operator activated="true" class="text:extract_information" compatibility="5.1.001" expanded="true" height="60" name="Extract Information (3)" width="90" x="281" y="30">
<parameter key="query_type" value="XPath"/>
<list key="string_machting_queries"/>
<list key="regular_expression_queries"/>
<list key="regular_region_queries"/>
<list key="xpath_queries">
<parameter key="kategoria" value="//h:a[1]/text()"/>
<parameter key="kategoria2" value="//h:a[2]/text()"/>
<parameter key="kategoria3" value="//h:a[3]/text()"/>
</list>
<list key="namespaces"/>
<list key="index_queries"/>
</operator>
<connect from_port="segment" to_op="Extract Information (3)" to_port="document"/>
<connect from_op="Extract Information (3)" from_port="document" to_port="document 1"/>
<portSpacing port="source_segment" spacing="0"/>
<portSpacing port="sink_document 1" spacing="0"/>
<portSpacing port="sink_document 2" spacing="0"/>
</process>
</operator>
<connect from_port="document" to_op="Cut Document (3)" to_port="document"/>
<connect from_op="Cut Document (3)" from_port="documents" to_port="document 1"/>
<portSpacing port="source_document" spacing="0"/>
<portSpacing port="sink_document 1" spacing="0"/>
<portSpacing port="sink_document 2" spacing="0"/>
</process>
</operator>
<operator activated="true" class="write_excel" compatibility="5.1.003" expanded="true" height="60" name="Write Excel" width="90" x="849" y="75">
<parameter key="excel_file" value="C:\termek_kategoriak.xls"/>
</operator>
<operator activated="true" class="text:process_documents" compatibility="5.1.001" expanded="true" height="94" name="Process Documents" width="90" x="648" y="210">
<parameter key="create_word_vector" value="false"/>
<process expanded="true" height="446" width="652">
<operator activated="true" class="text:cut_document" compatibility="5.1.001" expanded="true" height="60" name="Cut Document (2)" width="90" x="246" y="75">
<parameter key="query_type" value="XPath"/>
<list key="string_machting_queries"/>
<list key="regular_expression_queries"/>
<list key="regular_region_queries"/>
<list key="xpath_queries">
<parameter key="termeklap" value="h:html/h:head"/>
</list>
<list key="namespaces"/>
<list key="index_queries"/>
<process expanded="true" height="446" width="652">
<operator activated="true" class="text:extract_information" compatibility="5.1.001" expanded="true" height="60" name="Extract Information (2)" width="90" x="281" y="30">
<parameter key="query_type" value="XPath"/>
<list key="string_machting_queries"/>
<list key="regular_expression_queries"/>
<list key="regular_region_queries"/>
<list key="xpath_queries">
<parameter key="termeknev" value="//h:title/text()"/>
</list>
<list key="namespaces"/>
<list key="index_queries"/>
</operator>
<connect from_port="segment" to_op="Extract Information (2)" to_port="document"/>
<connect from_op="Extract Information (2)" from_port="document" to_port="document 1"/>
<portSpacing port="source_segment" spacing="0"/>
<portSpacing port="sink_document 1" spacing="0"/>
<portSpacing port="sink_document 2" spacing="0"/>
</process>
</operator>
<connect from_port="document" to_op="Cut Document (2)" to_port="document"/>
<connect from_op="Cut Document (2)" from_port="documents" to_port="document 1"/>
<portSpacing port="source_document" spacing="0"/>
<portSpacing port="sink_document 1" spacing="0"/>
<portSpacing port="sink_document 2" spacing="0"/>
</process>
</operator>
<operator activated="true" class="write_excel" compatibility="5.1.003" expanded="true" height="60" name="Write Excel (2)" width="90" x="849" y="300">
<parameter key="excel_file" value="C:\output.xls"/>
</operator>
<connect from_op="Read CSV" from_port="output" to_op="Get Pages" to_port="Example Set"/>
<connect from_op="Get Pages" from_port="Example Set" to_op="Data to Documents" to_port="example set"/>
<connect from_op="Data to Documents" from_port="documents" to_op="Multiply" to_port="input"/>
<connect from_op="Multiply" from_port="output 1" to_op="Process Documents" to_port="documents 1"/>
<connect from_op="Multiply" from_port="output 2" to_op="Process Documents (2)" to_port="documents 1"/>
<connect from_op="Process Documents (2)" from_port="example set" to_op="Write Excel" to_port="input"/>
<connect from_op="Process Documents (2)" from_port="word list" to_port="result 1"/>
<connect from_op="Write Excel" from_port="through" to_port="result 2"/>
<connect from_op="Process Documents" from_port="example set" to_op="Write Excel (2)" to_port="input"/>
<connect from_op="Process Documents" from_port="word list" to_port="result 3"/>
<connect from_op="Write Excel (2)" from_port="through" to_port="result 4"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="0"/>
<portSpacing port="sink_result 3" spacing="0"/>
<portSpacing port="sink_result 4" spacing="0"/>
<portSpacing port="sink_result 5" spacing="0"/>
</process>
</operator>
</process>
