wzray/tt9
1
0
Fork 0
Code Activity

Hindi

Browse source 
* Added Hindi language

	* Removed the hardcoded special characters from language validation. Now reading them from the .yml

	* improved method of hiding the letters on 0 and 1, when needed

	* virtual keypad adjustments

	* improved the single-letter validation during build time

	* improved Devanagari validation script

	* improved sorting when filters are on
This commit is contained in:
sspanak 2024-12-01 18:47:41 +02:00 • committed by Dimo Karaivanov
parent 622a954633
commit f8e6668281
18 changed files with 1305176 additions and 103 deletions
Download patch file Download diff file Expand all files Collapse all files

45
app/validate-languages.gradle
View file

@ -43,7 +43,7 @@ ext.validateLanguageFiles = { definitionsDir, dictionariesDir, validationDir ->
ext.parseLanguageDefintion = { File languageFile, String dictionariesDir ->
String alphabet = ""
String alphabet = ''
int layoutKey = 0
HashMap<String, String> sounds = new HashMap<>()
HashMap<String, String> layoutSounds = new HashMap<>()
@ -58,10 +58,6 @@ ext.parseLanguageDefintion = { File languageFile, String dictionariesDir ->
String localeString = ""
String dictionaryFileName = ""
alphabet = languageFile.name.contains("Catalan") ? '·' : alphabet
alphabet = languageFile.name.contains("Hebrew") || languageFile.name.contains("Yiddish") ? '"' : alphabet
alphabet = languageFile.name.contains("Korean") ? '：' : alphabet
for (String line : languageFile.readLines()) {
if (
line.matches("^[a-zA-Z].*")
@ -110,19 +106,15 @@ ext.parseLanguageDefintion = { File languageFile, String dictionariesDir ->
// alphabet string
def lineCharacters = extractAlphabetCharsFromLine(line)
lineCharacters = lineCharacters.isEmpty() ? extractAlphabetExtraCharsFromLine(languageFile.name, line) : lineCharacters
alphabet += lineCharacters
// sounds, single letters
// sounds, single letters or special characters that are treated as letters
if (lineCharacters) {
lineCharacters.each { letter ->
layoutSounds.put(letter, layoutKey.toString())
}
} else if (line.contains("PUNCTUATION")) {
layoutSounds.put("-", layoutKey.toString())
layoutSounds.put(".", layoutKey.toString())
layoutSounds.put("'", layoutKey.toString())
layoutSounds.put('"', layoutKey.toString())
layoutSounds.put('·', layoutKey.toString())
}
if (isLayoutLine(line)) {
@ -178,7 +170,8 @@ ext.parseLanguageDefintion = { File languageFile, String dictionariesDir ->
// this cannot be static, because DictionaryTools will not be visible
def validateDictionary(File dictionaryFile, String alphabet, HashMap<String, String> sounds, boolean isAlphabeticLanguage, Locale locale, int maxErrors, String csvDelimiter, int maxWordFrequency) {
final VALID_CHARS = alphabet.toUpperCase(locale) == alphabet ? "^[${alphabet}\\-\\.']+\$" : "^[${alphabet}${alphabet.toUpperCase(locale)}\\-\\.']+\$"
String regexSafeAlphabet = alphabet.replaceAll("([\\[\\]\\-\\.])", "")
final VALID_CHARS = alphabet.toUpperCase(locale) == alphabet ? "^[${regexSafeAlphabet}\\.\\-]+\$" : "^[${regexSafeAlphabet}${regexSafeAlphabet.toUpperCase(locale)}\\.\\-]+\$"
int errorCount = 0
String errorMsg = ''
@ -238,6 +231,30 @@ def validateDictionary(File dictionaryFile, String alphabet, HashMap<String, Str
//////////////////// PARSING ////////////////////
static def extractAlphabetExtraCharsFromLine(String languageName, String line) {
if (languageName == null || !line.contains('PUNCTUATION') || !isLayoutLine(line)) {
return ''
}
final DEFAULT = "'-."
if (languageName.contains('Korean')) {
return DEFAULT
} else if (languageName.contains("Hebrew") || languageName.contains("Yiddish")) {
return DEFAULT + '"'
}
String allChars = line
.replaceFirst('\\].*', '')
.replaceFirst('^\\s+- \\[', '')
.replaceFirst("PUNCTUATION[^,\\s]*", '')
.replace(',', '')
.replace(' ', '')
return DEFAULT + allChars
}
static def extractAlphabetCharsFromLine(String line) {
if (line.contains('PUNCTUATION') || line.contains('SPECIAL') || !isLayoutLine(line)) {
return ''
@ -298,7 +315,7 @@ static def validateWord(String word, String validCharacters, boolean isAlphabeti
errors += "${errorMsgPrefix}. Found a garbage word: '${word}' on line ${lineNumber}.\n"
}
if (isAlphabeticLanguage && word.matches("^(.|\\p{L}\\p{M}?)\$")) {
if (isAlphabeticLanguage && word.trim().length() == 1) {
errorCount++
errors += "${errorMsgPrefix}. Found a single letter: '${word}' on line ${lineNumber}. Only uppercase single letters are allowed. The rest of the alphabet will be added automatically.\n"
}