Parse Sentences
Splits a text into different sentences.
Command availability: IBM RPA SaaS and IBM RPA on premises
Description
Splits the text into individual sentences according to the defined language.
The results that this command returns might vary according to the selected NLP provider. For more information, see Setting an NLP provider.
Script syntax
IBM RPA's proprietary script language has a syntax similar to other programming languages. The script syntax defines the command's syntax in the script file. You can work with this syntax in IBM RPA Studio's Script mode.
parseSentences --culture(Culture) --text(String) (List<String>)=sentences (Boolean)=success
Input parameter
The following table displays the list of input parameters available in this command. In the table, you can see the parameter name when working in IBM RPA Studio's Script mode and its Designer mode equivalent label.
| Designer mode label | Script mode name | Required | Accepted variable types | Description |
|---|---|---|---|---|
| Language | culture |
Required |
Text, Culture |
The language that is used to analyze the input text. If you define the language manually, make sure to enter only supported language codes. See the culture parameter options for supported languages. |
| Text | text |
Required |
Text |
Text to be analyzed. |
culture parameter options
The following table displays the options available for the culture input parameter. The table shows the options available when working in Script mode and the equivalent label in the Designer mode.
| Designer mode label | Script mode name | Description | Supported provider |
|---|---|---|---|
ar |
ar |
Arabic | Watson NLP |
zh-CN |
zh-CN |
Chinese (Simplified) | Watson NLP |
zh-TW |
zh-TW |
Chinese (Traditional) | Watson NLP |
cs |
cs |
Czech | Watson NLP |
da |
da |
Danish | Watson NLP |
nl |
nl |
Dutch | Watson NLP |
de-DE |
de-DE |
German | Watson NLP |
en-US |
en-US |
English | Legacy and Watson NLP |
fi |
fi |
Finnish | Watson NLP |
fr-FR |
fr-FR |
French (France) | Watson NLP |
fr-CA |
fr-CA |
French (Canada) | Watson NLP |
he |
he |
Hebrew | Watson NLP |
it-IT |
it-IT |
Italian | Watson NLP |
ja-JP |
ja-JP |
Japanese | Watson NLP |
ko-KR |
ko-KR |
Korean | Watson NLP |
nb |
nb |
Norwegian Bokmal | Watson NLP |
nn |
nn |
Norwegian Nynorsk | Watson NLP |
pt-BR |
pt-BR |
Portuguese (Brazil) | Legacy and Watson NLP |
pt-PT |
pt-PT |
Portuguese (Portugal) | Legacy and Watson NLP |
pl |
pl |
Polish | Watson NLP |
ro |
ro |
Romanian | Watson NLP |
ru-RU |
ru-RU |
Russian | Watson NLP |
sk |
sk |
Slovak | Watson NLP |
es-ES |
es-ES |
Spanish | Watson NLP |
sv |
sv |
Swedish | Watson NLP |
tr |
tr |
Turkish | Watson NLP |
Output parameter
| Designer mode label | Script mode name | Accepted variable types | Description |
|---|---|---|---|
| Parsed Sentences | sentences |
List<Text> |
A list of all divided sentences. |
| Success | success |
Boolean |
Returns True if the text was successfully split, otherwise returns False. |
Example
The following example splits a single paragraph text into individual sentences.
defVar --name parsedSentence --type List --innertype String
defVar --name executionSuccess --type Boolean
defVar --name analyzedText --type String --value "Adapt the Robot without Programming Knowledge. Fast, Reliable and Secure. Automate Any Business Process. Reduce Costs and Increase Productivity. Increase Productivity. Process Automation. Data extraction. Reduce Costs by Up to 70%"
parseSentences --culture "en-US" --text "${analyzedText}" parsedSentence=sentences executionSuccess=success
logMessage --message "\r\nSentences obtained after division:\r\n${parsedSentence}\r\nSuccess: ${executionSuccess}" --type "Info"
// Return obtained after executing the script:
// Sentences obtained after division:
// [Adapt the Robot without Programming Knowledge.,Fast, Reliable and Secure.,Automate Any Business Process.,Reduce Costs and Increase Productivity.,Increase Productivity.,Process Automation.,Data extraction.,Reduce Costs by Up to 70%]
// Success: True
// Execution success: True