The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
Error for Process Documents from Files
Hi all and Happy New Year,
I have a html file in the operator Process Documents from Files , which is causing following error:
Process failed.
The name ... (some japanese characters) is not legal for JDOM/XML attributes: XML names cannot contain the character "c" (looks like c...).
Any ideas?
Thanks in advance.
I have a html file in the operator Process Documents from Files , which is causing following error:
Process failed.
The name ... (some japanese characters) is not legal for JDOM/XML attributes: XML names cannot contain the character "c" (looks like c...).
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.3.013">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.3.013" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="text:process_document_from_file" compatibility="5.3.002" expanded="true" height="76" name="Process Documents from Files (2)" width="90" x="112" y="30">
<list key="text_directories">
<parameter key="testhtml" value="/home/nick/Documents/RapidMinerTest/allhtml"/>
</list>
<parameter key="file_pattern" value="*.html"/>
<parameter key="encoding" value="UTF-8"/>
<parameter key="vector_creation" value="Term Occurrences"/>
<parameter key="keep_text" value="true"/>
<process expanded="true">
<operator activated="true" class="web:extract_html_text_content" compatibility="5.3.001" expanded="true" height="60" name="Extract Content" width="90" x="45" y="30">
<parameter key="minimum_text_block_length" value="3"/>
</operator>
<operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Tokenize (2)" width="90" x="179" y="30"/>
<operator activated="true" class="text:filter_by_length" compatibility="5.3.002" expanded="true" height="60" name="Filter Tokens (2)" width="90" x="313" y="30">
<parameter key="min_chars" value="3"/>
<parameter key="max_chars" value="30"/>
</operator>
<operator activated="true" class="text:transform_cases" compatibility="5.3.002" expanded="true" height="60" name="Transform Cases (2)" width="90" x="447" y="30"/>
<operator activated="true" class="text:filter_stopwords_english" compatibility="5.3.002" expanded="true" height="60" name="Filter Stopwords (2)" width="90" x="581" y="30"/>
<connect from_port="document" to_op="Extract Content" to_port="document"/>
<connect from_op="Extract Content" from_port="document" to_op="Tokenize (2)" to_port="document"/>
<connect from_op="Tokenize (2)" from_port="document" to_op="Filter Tokens (2)" to_port="document"/>
<connect from_op="Filter Tokens (2)" from_port="document" to_op="Transform Cases (2)" to_port="document"/>
<connect from_op="Transform Cases (2)" from_port="document" to_op="Filter Stopwords (2)" to_port="document"/>
<connect from_op="Filter Stopwords (2)" from_port="document" 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>
<connect from_op="Process Documents from Files (2)" from_port="example set" to_port="result 2"/>
<connect from_op="Process Documents from Files (2)" from_port="word list" to_port="result 1"/>
<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"/>
</process>
</operator>
</process>
Any ideas?
Thanks in advance.
Tagged:
0