Good Day all.
I try to preprocessing text from CSV file to .txt file. However, I couldn't get the output written in the .txt file. If it does, it only rewrites the input file.
However, the good thing is I could get the output at the stdout for logging results.
Here I attach my XML code.
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.2.006">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.2.006" expanded="true" name="Process">
<parameter key="logverbosity" value="status"/>
<parameter key="random_seed" value="2001"/>
<parameter key="send_mail" value="never"/>
<parameter key="notification_email" value=""/>
<parameter key="process_duration_for_mail" value="30"/>
<parameter key="encoding" value="SYSTEM"/>
<process expanded="true" height="370" width="820">
<operator activated="true" class="text:read_document" compatibility="5.2.002" expanded="true" height="60" name="Read Document" width="90" x="45" y="30">
<parameter key="file" value="C:\Users\user\Desktop\product2e.csv"/>
<parameter key="extract_text_only" value="true"/>
<parameter key="use_file_extension_as_type" value="true"/>
<parameter key="content_type" value="txt"/>
<parameter key="encoding" value="SYSTEM"/>
</operator>
<operator activated="true" class="text:tokenize" compatibility="5.2.002" expanded="true" height="60" name="Tokenize" width="90" x="45" y="120">
<parameter key="mode" value="non letters"/>
<parameter key="characters" value=".:"/>
<parameter key="language" value="English"/>
<parameter key="max_token_length" value="3"/>
</operator>
<operator activated="true" class="text:transform_cases" compatibility="5.2.002" expanded="true" height="60" name="Transform Cases" width="90" x="179" y="120">
<parameter key="transform_to" value="lower case"/>
</operator>
<operator activated="true" class="text:filter_stopwords_english" compatibility="5.2.002" expanded="true" height="60" name="Filter Stopwords (English)" width="90" x="313" y="120"/>
<operator activated="true" class="write_as_text" compatibility="5.2.006" expanded="true" height="76" name="Write as Text" width="90" x="581" y="120">
<parameter key="result_file" value="C:\Users\user\Desktop\result1.txt"/>
<parameter key="encoding" value="SYSTEM"/>
</operator>
<connect from_op="Read Document" from_port="output" to_op="Tokenize" to_port="document"/>
<connect from_op="Tokenize" from_port="document" to_op="Transform Cases" to_port="document"/>
<connect from_op="Transform Cases" from_port="document" to_op="Filter Stopwords (English)" to_port="document"/>
<connect from_op="Filter Stopwords (English)" from_port="document" to_op="Write as Text" to_port="input 1"/>
<connect from_op="Write as Text" from_port="input 1" to_port="result 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="234"/>
<portSpacing port="sink_result 2" spacing="0"/>
</process>
</operator>
</process>
|
and one more thing is how am I going to write the output line by line? At the stdout, it writes all the words together without separate.
Thanks all.
Fizah.
