aboutsummaryrefslogtreecommitdiff
path: root/test/data/translator-test-inputs.json
diff options
context:
space:
mode:
Diffstat (limited to 'test/data/translator-test-inputs.json')
-rw-r--r--test/data/translator-test-inputs.json60
1 files changed, 38 insertions, 22 deletions
diff --git a/test/data/translator-test-inputs.json b/test/data/translator-test-inputs.json
index 03ec938a..c9047716 100644
--- a/test/data/translator-test-inputs.json
+++ b/test/data/translator-test-inputs.json
@@ -21,12 +21,7 @@
"sortFrequencyDictionary": null,
"sortFrequencyDictionaryOrder": "descending",
"removeNonJapaneseCharacters": true,
- "convertHalfWidthCharacters": "false",
- "convertNumericCharacters": "false",
- "convertAlphabeticCharacters": "false",
- "convertHiraganaToKatakana": "false",
- "convertKatakanaToHiragana": "false",
- "collapseEmphaticSequences": "false",
+ "language": "ja",
"textReplacements": [
null
],
@@ -361,7 +356,7 @@
"options": "default"
},
{
- "name": "Test text transformations - convertNumericCharacters",
+ "name": "Test text preprocessors - convertNumericCharacters",
"func": "findTerms",
"mode": "split",
"text": "39",
@@ -369,13 +364,12 @@
"default",
{
"type": "terms",
- "convertNumericCharacters": "true",
"removeNonJapaneseCharacters": false
}
]
},
{
- "name": "Test text transformations - convertAlphabeticCharacters",
+ "name": "Test text preprocessors - convertAlphabeticCharacters",
"func": "findTerms",
"mode": "split",
"text": "utsu",
@@ -383,61 +377,83 @@
"default",
{
"type": "terms",
- "convertAlphabeticCharacters": "true",
"removeNonJapaneseCharacters": false
}
]
},
{
- "name": "Test text transformations - convertKatakanaToHiragana",
+ "name": "Test text preprocessors - convertKatakanaToHiragana",
"func": "findTerms",
"mode": "split",
"text": "ウツ",
"options": [
"default",
{
- "type": "terms",
- "convertKatakanaToHiragana": "true"
+ "type": "terms"
}
]
},
{
- "name": "Test text transformations - convertHiraganaToKatakana",
+ "name": "Test text preprocessors - convertHiraganaToKatakana",
"func": "findTerms",
"mode": "split",
"text": "てきすと",
"options": [
"default",
{
- "type": "terms",
- "convertHiraganaToKatakana": "true"
+ "type": "terms"
}
]
},
{
- "name": "Test text transformations - convertHalfWidthCharacters, convertKatakanaToHiragana",
+ "name": "Test text preprocessors - convertHalfWidthCharacters, convertKatakanaToHiragana",
"func": "findTerms",
"mode": "split",
"text": "ウツ",
"options": [
"default",
{
- "type": "terms",
- "convertHalfWidthCharacters": "true",
- "convertKatakanaToHiragana": "true"
+ "type": "terms"
}
]
},
{
- "name": "Test text transformations - collapseEmphaticSequences",
+ "name": "Test text preprocessors - collapseEmphaticSequences",
"func": "findTerms",
"mode": "split",
"text": "すっっごーーい",
"options": [
"default",
{
+ "type": "terms"
+ }
+ ]
+ },
+ {
+ "name": "Test text preprocessors - capitalizeFirstLetter",
+ "func": "findTerms",
+ "mode": "split",
+ "text": "english",
+ "options": [
+ "default",
+ {
"type": "terms",
- "collapseEmphaticSequences": "full"
+ "language": "en",
+ "removeNonJapaneseCharacters": false
+ }
+ ]
+ },
+ {
+ "name": "Test text preprocessors - decapitalize",
+ "func": "findTerms",
+ "mode": "split",
+ "text": "LANGUAGE",
+ "options": [
+ "default",
+ {
+ "type": "terms",
+ "language": "en",
+ "removeNonJapaneseCharacters": false
}
]
}