Ran phpcbf over code
This commit is contained in:
parent
205e77da0e
commit
27528c9cf7
|
@ -10,7 +10,6 @@ declare(strict_types = 1);
|
||||||
* Abstract class to be inherited by classes for writing consolidated vocabulary names.
|
* Abstract class to be inherited by classes for writing consolidated vocabulary names.
|
||||||
*/
|
*/
|
||||||
abstract class NodaConsolidatedNamesAbstract {
|
abstract class NodaConsolidatedNamesAbstract {
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* This function sanitizes a string.
|
* This function sanitizes a string.
|
||||||
*
|
*
|
||||||
|
|
|
@ -120,5 +120,4 @@ final class NodaConsolidatedNamesForPersinst extends NodaConsolidatedNamesAbstra
|
||||||
return \trim($name, " ;.\t" . PHP_EOL);
|
return \trim($name, " ;.\t" . PHP_EOL);
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
|
@ -105,8 +105,7 @@ final class NodaConsolidatedNamesForPlaces extends NodaConsolidatedNamesAbstract
|
||||||
|
|
||||||
// Skip entries like "Vaci utca 12 Budapest, Vaci utca"
|
// Skip entries like "Vaci utca 12 Budapest, Vaci utca"
|
||||||
$indicatorTrimmed = trim($indicator);
|
$indicatorTrimmed = trim($indicator);
|
||||||
if (
|
if ((str_ends_with($parts[0], $indicatorTrimmed) && str_contains($parts[1], $indicatorTrimmed))
|
||||||
(str_ends_with($parts[0], $indicatorTrimmed) && str_contains($parts[1], $indicatorTrimmed))
|
|
||||||
|| (str_ends_with($parts[1], $indicatorTrimmed) && str_contains($parts[0], $indicatorTrimmed))
|
|| (str_ends_with($parts[1], $indicatorTrimmed) && str_contains($parts[0], $indicatorTrimmed))
|
||||||
) {
|
) {
|
||||||
return $name;
|
return $name;
|
||||||
|
@ -133,10 +132,8 @@ final class NodaConsolidatedNamesForPlaces extends NodaConsolidatedNamesAbstract
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
return $name;
|
return $name;
|
||||||
|
|
||||||
}
|
}
|
||||||
|
@ -334,7 +331,6 @@ final class NodaConsolidatedNamesForPlaces extends NodaConsolidatedNamesAbstract
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Cleans and consolidates name parts appearing regularly in Ukrainian place names.
|
* Cleans and consolidates name parts appearing regularly in Ukrainian place names.
|
||||||
*
|
*
|
||||||
|
@ -427,15 +423,12 @@ final class NodaConsolidatedNamesForPlaces extends NodaConsolidatedNamesAbstract
|
||||||
|
|
||||||
// If one of the parts is a blacklisted term or a cardinal directions, skip this
|
// If one of the parts is a blacklisted term or a cardinal directions, skip this
|
||||||
|
|
||||||
if (
|
if ((in_array($parts[0], self::_COUNTRY_REWRITE_BLACKLISTED_TERMS, true)
|
||||||
(in_array($parts[0], self::_COUNTRY_REWRITE_BLACKLISTED_TERMS, true)
|
|| in_array($parts[0], $cardinal_directions, true)
|
||||||
|| in_array($parts[0], $cardinal_directions, true)
|
|| in_array(strtolower($parts[0]), $cardinal_directions, true))
|
||||||
|| in_array(strtolower($parts[0]), $cardinal_directions, true)
|
|
||||||
)
|
|
||||||
|| (in_array($parts[1], self::_COUNTRY_REWRITE_BLACKLISTED_TERMS, true)
|
|| (in_array($parts[1], self::_COUNTRY_REWRITE_BLACKLISTED_TERMS, true)
|
||||||
|| in_array($parts[1], $cardinal_directions, true)
|
|| in_array($parts[1], $cardinal_directions, true)
|
||||||
|| in_array(strtolower($parts[1]), $cardinal_directions, true)
|
|| in_array(strtolower($parts[1]), $cardinal_directions, true))
|
||||||
)
|
|
||||||
) {
|
) {
|
||||||
return $name;
|
return $name;
|
||||||
}
|
}
|
||||||
|
|
|
@ -10,7 +10,6 @@ declare(strict_types = 1);
|
||||||
* contains a string.
|
* contains a string.
|
||||||
*/
|
*/
|
||||||
final class NodaDistinctlyTypedStrings {
|
final class NodaDistinctlyTypedStrings {
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Checks the vocabulary database whether it contains a given string.
|
* Checks the vocabulary database whether it contains a given string.
|
||||||
*
|
*
|
||||||
|
@ -40,5 +39,4 @@ final class NodaDistinctlyTypedStrings {
|
||||||
return $cur[0];
|
return $cur[0];
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
|
@ -11,7 +11,7 @@ declare(strict_types = 1);
|
||||||
*/
|
*/
|
||||||
final class NodaSplitTime {
|
final class NodaSplitTime {
|
||||||
|
|
||||||
const DEFAULT_DATE = '0001-01-01';
|
public const DEFAULT_DATE = '0001-01-01';
|
||||||
|
|
||||||
public readonly string $start_year;
|
public readonly string $start_year;
|
||||||
public readonly string $end_year;
|
public readonly string $end_year;
|
||||||
|
@ -40,11 +40,13 @@ final class NodaSplitTime {
|
||||||
$start_date = $end_date = $year . '-' . $month . '-' . $day;
|
$start_date = $end_date = $year . '-' . $month . '-' . $day;
|
||||||
|
|
||||||
if ($before_after_indicator === NodaTimeBeforeAfterIndicator::before
|
if ($before_after_indicator === NodaTimeBeforeAfterIndicator::before
|
||||||
|| $before_after_indicator === NodaTimeBeforeAfterIndicator::until) {
|
|| $before_after_indicator === NodaTimeBeforeAfterIndicator::until
|
||||||
|
) {
|
||||||
$start_year = $start_date = '?';
|
$start_year = $start_date = '?';
|
||||||
}
|
}
|
||||||
if ($before_after_indicator === NodaTimeBeforeAfterIndicator::after
|
if ($before_after_indicator === NodaTimeBeforeAfterIndicator::after
|
||||||
|| $before_after_indicator === NodaTimeBeforeAfterIndicator::since) {
|
|| $before_after_indicator === NodaTimeBeforeAfterIndicator::since
|
||||||
|
) {
|
||||||
$end_year = $end_date = '?';
|
$end_year = $end_date = '?';
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -94,7 +96,6 @@ final class NodaSplitTime {
|
||||||
throw new MDgenericInvalidInputsException("Times with no certain end need to have a question mark (?) entered as a end date");
|
throw new MDgenericInvalidInputsException("Times with no certain end need to have a question mark (?) entered as a end date");
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
|
@ -272,7 +273,6 @@ final class NodaSplitTime {
|
||||||
|
|
||||||
return "";
|
return "";
|
||||||
|
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
|
@ -330,7 +330,6 @@ final class NodaSplitTime {
|
||||||
$this->end_date = '9999-12-31';
|
$this->end_date = '9999-12-31';
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
if (!isset($this->start_date) && false !== $start_date) {
|
if (!isset($this->start_date) && false !== $start_date) {
|
||||||
$this->start_date = date("Y-m-d", MD_STD::strtotime($start_date));
|
$this->start_date = date("Y-m-d", MD_STD::strtotime($start_date));
|
||||||
}
|
}
|
||||||
|
@ -361,7 +360,5 @@ final class NodaSplitTime {
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
|
@ -888,11 +888,10 @@ final class NodaTimeSplitter {
|
||||||
|
|
||||||
$datum = self::clean_input($datum);
|
$datum = self::clean_input($datum);
|
||||||
|
|
||||||
|
|
||||||
// TODO: Check if this is duplicate
|
// TODO: Check if this is duplicate
|
||||||
|
|
||||||
// 17. Jahrhundert
|
// 17. Jahrhundert
|
||||||
if (\preg_match("/^[0-9]{2}(\.|)" . self::REGEX_CENTURIES ."$/", $datum)) {
|
if (\preg_match("/^[0-9]{2}(\.|)" . self::REGEX_CENTURIES . "$/", $datum)) {
|
||||||
if ($centuryNo = \intval(\substr($datum, 0, 2))) {
|
if ($centuryNo = \intval(\substr($datum, 0, 2))) {
|
||||||
$centuryNo--;
|
$centuryNo--;
|
||||||
return new NodaSplitTime((string)$centuryNo . "01", \strval($centuryNo + 1) . "00");
|
return new NodaSplitTime((string)$centuryNo . "01", \strval($centuryNo + 1) . "00");
|
||||||
|
|
|
@ -94,9 +94,9 @@ final class NodaUncertaintyHelper {
|
||||||
"Без датування", // No dating
|
"Без датування", // No dating
|
||||||
"б.р.", // No dating
|
"б.р.", // No dating
|
||||||
"б.д.", // No dating
|
"б.д.", // No dating
|
||||||
];
|
];
|
||||||
|
|
||||||
const TIME_UNCERTAINTY_PREFIXES = [
|
const TIME_UNCERTAINTY_PREFIXES = [
|
||||||
"c. ",
|
"c. ",
|
||||||
"ca ",
|
"ca ",
|
||||||
"ca. ",
|
"ca. ",
|
||||||
|
@ -130,9 +130,9 @@ final class NodaUncertaintyHelper {
|
||||||
"майже", // UK: Almost / nearly / about
|
"майже", // UK: Almost / nearly / about
|
||||||
"орієнтовно", // UK: approximately
|
"орієнтовно", // UK: approximately
|
||||||
"Прибл.", // UK: approximately
|
"Прибл.", // UK: approximately
|
||||||
];
|
];
|
||||||
|
|
||||||
const TIME_UNCERTAINTY_SUFFIXES = [
|
const TIME_UNCERTAINTY_SUFFIXES = [
|
||||||
"(?)",
|
"(?)",
|
||||||
"?",
|
"?",
|
||||||
" (ca.)",
|
" (ca.)",
|
||||||
|
@ -145,11 +145,11 @@ final class NodaUncertaintyHelper {
|
||||||
", um",
|
", um",
|
||||||
" (um)",
|
" (um)",
|
||||||
" (ок.)",
|
" (ок.)",
|
||||||
];
|
];
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Substrings used to express uncertainty about the validity of a place name.
|
* Substrings used to express uncertainty about the validity of a place name.
|
||||||
*/
|
*/
|
||||||
const PLACE_INDICATORS_DISALLOWED = [
|
const PLACE_INDICATORS_DISALLOWED = [
|
||||||
"Unbekannt",
|
"Unbekannt",
|
||||||
"unbekannt",
|
"unbekannt",
|
||||||
|
@ -173,9 +173,9 @@ final class NodaUncertaintyHelper {
|
||||||
"не вказано", // No place
|
"не вказано", // No place
|
||||||
"не вказане", // No place
|
"не вказане", // No place
|
||||||
"невідоме", // No place
|
"невідоме", // No place
|
||||||
];
|
];
|
||||||
|
|
||||||
const PLACE_UNCERTAINTY_PREFIXES = [
|
const PLACE_UNCERTAINTY_PREFIXES = [
|
||||||
"ca ",
|
"ca ",
|
||||||
"Ca ",
|
"Ca ",
|
||||||
"ca. ",
|
"ca. ",
|
||||||
|
@ -210,9 +210,9 @@ final class NodaUncertaintyHelper {
|
||||||
"Wahrscheinlich ",
|
"Wahrscheinlich ",
|
||||||
"можливо",
|
"можливо",
|
||||||
"?",
|
"?",
|
||||||
];
|
];
|
||||||
|
|
||||||
const PLACE_UNCERTAINTY_SUFFIXES = [
|
const PLACE_UNCERTAINTY_SUFFIXES = [
|
||||||
"(?)",
|
"(?)",
|
||||||
"(vermutl.)",
|
"(vermutl.)",
|
||||||
"[vermutl.]",
|
"[vermutl.]",
|
||||||
|
@ -221,206 +221,206 @@ final class NodaUncertaintyHelper {
|
||||||
"(wohl)",
|
"(wohl)",
|
||||||
"[wohl]",
|
"[wohl]",
|
||||||
"?",
|
"?",
|
||||||
];
|
];
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Trims common characters and charater marks.
|
* Trims common characters and charater marks.
|
||||||
*
|
*
|
||||||
* @param string $input Input text.
|
* @param string $input Input text.
|
||||||
*
|
*
|
||||||
* @return string
|
* @return string
|
||||||
*/
|
*/
|
||||||
public static function trim(string $input):string {
|
public static function trim(string $input):string {
|
||||||
|
|
||||||
$input = \trim($input, ", \t\n\r\n;-:");
|
$input = \trim($input, ", \t\n\r\n;-:");
|
||||||
return $input;
|
return $input;
|
||||||
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Removes uncertainty indicators from an time name.
|
|
||||||
*
|
|
||||||
* @param string $name Input string.
|
|
||||||
*
|
|
||||||
* @return string
|
|
||||||
*/
|
|
||||||
public static function cleanUncertaintyIndicatorsTime(string $name):string {
|
|
||||||
|
|
||||||
$name = self::trim($name);
|
|
||||||
|
|
||||||
if (\in_array($name, self::TIME_INDICATORS_DISALLOWED, true)) {
|
|
||||||
return "";
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// Remove uncertainty prefixes
|
/**
|
||||||
foreach (NodaUncertaintyHelper::TIME_UNCERTAINTY_PREFIXES as $prefix) {
|
* Removes uncertainty indicators from an time name.
|
||||||
if (\substr($name, 0, \strlen($prefix)) === "$prefix") {
|
*
|
||||||
$name = substr($name, \strlen($prefix));
|
* @param string $name Input string.
|
||||||
|
*
|
||||||
|
* @return string
|
||||||
|
*/
|
||||||
|
public static function cleanUncertaintyIndicatorsTime(string $name):string {
|
||||||
|
|
||||||
|
$name = self::trim($name);
|
||||||
|
|
||||||
|
if (\in_array($name, self::TIME_INDICATORS_DISALLOWED, true)) {
|
||||||
|
return "";
|
||||||
}
|
}
|
||||||
}
|
|
||||||
|
|
||||||
// Remove uncertainty sufixes
|
// Remove uncertainty prefixes
|
||||||
foreach (NodaUncertaintyHelper::TIME_UNCERTAINTY_SUFFIXES as $suffix) {
|
foreach (NodaUncertaintyHelper::TIME_UNCERTAINTY_PREFIXES as $prefix) {
|
||||||
if (\substr($name, \strlen($suffix) * -1) === "$suffix") {
|
if (\substr($name, 0, \strlen($prefix)) === "$prefix") {
|
||||||
$name = \substr($name, 0, \strlen($suffix) * -1);
|
$name = substr($name, \strlen($prefix));
|
||||||
|
}
|
||||||
}
|
}
|
||||||
}
|
|
||||||
|
|
||||||
return self::trim($name);
|
// Remove uncertainty sufixes
|
||||||
|
foreach (NodaUncertaintyHelper::TIME_UNCERTAINTY_SUFFIXES as $suffix) {
|
||||||
}
|
if (\substr($name, \strlen($suffix) * -1) === "$suffix") {
|
||||||
|
$name = \substr($name, 0, \strlen($suffix) * -1);
|
||||||
/**
|
}
|
||||||
* Attempts guessing whether time is uncertain. Returns true if the name
|
|
||||||
* indicates certainty, false if it indicates uncertainty.
|
|
||||||
*
|
|
||||||
* @param string $zeit_name Time name.
|
|
||||||
*
|
|
||||||
* @return boolean
|
|
||||||
*/
|
|
||||||
public static function guessTimeCertainty(string $zeit_name):bool {
|
|
||||||
|
|
||||||
$zeit_name = \strtolower($zeit_name);
|
|
||||||
|
|
||||||
// Attempt to guess uncertainty based on prefixes.
|
|
||||||
foreach (self::TIME_UNCERTAINTY_PREFIXES as $prefix) {
|
|
||||||
if (\substr($zeit_name, 0, \strlen($prefix)) === $prefix) {
|
|
||||||
return false; // Uncertainty found
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
return self::trim($name);
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// Attempt to guess uncertainty based on prefixes.
|
/**
|
||||||
foreach (self::TIME_UNCERTAINTY_SUFFIXES as $prefix) {
|
* Attempts guessing whether time is uncertain. Returns true if the name
|
||||||
if (\substr($zeit_name, -1 * \strlen($prefix)) === $prefix) {
|
* indicates certainty, false if it indicates uncertainty.
|
||||||
return false; // Uncertainty found
|
*
|
||||||
|
* @param string $zeit_name Time name.
|
||||||
|
*
|
||||||
|
* @return boolean
|
||||||
|
*/
|
||||||
|
public static function guessTimeCertainty(string $zeit_name):bool {
|
||||||
|
|
||||||
|
$zeit_name = \strtolower($zeit_name);
|
||||||
|
|
||||||
|
// Attempt to guess uncertainty based on prefixes.
|
||||||
|
foreach (self::TIME_UNCERTAINTY_PREFIXES as $prefix) {
|
||||||
|
if (\substr($zeit_name, 0, \strlen($prefix)) === $prefix) {
|
||||||
|
return false; // Uncertainty found
|
||||||
|
}
|
||||||
}
|
}
|
||||||
}
|
|
||||||
|
|
||||||
return true; // No uncertainty found
|
// Attempt to guess uncertainty based on prefixes.
|
||||||
|
foreach (self::TIME_UNCERTAINTY_SUFFIXES as $prefix) {
|
||||||
}
|
if (\substr($zeit_name, -1 * \strlen($prefix)) === $prefix) {
|
||||||
|
return false; // Uncertainty found
|
||||||
/**
|
}
|
||||||
* Removes uncertainty indicators from an place name.
|
|
||||||
*
|
|
||||||
* @param string $ort_name Input string.
|
|
||||||
*
|
|
||||||
* @return string
|
|
||||||
*/
|
|
||||||
public static function cleanUncertaintyIndicatorsPlace(string $ort_name):string {
|
|
||||||
|
|
||||||
$ort_name = self::trim($ort_name);
|
|
||||||
|
|
||||||
if (\in_array($ort_name, self::PLACE_INDICATORS_DISALLOWED, true)) {
|
|
||||||
return "";
|
|
||||||
}
|
|
||||||
|
|
||||||
// Remove uncertainty prefixes
|
|
||||||
foreach (NodaUncertaintyHelper::PLACE_UNCERTAINTY_PREFIXES as $prefix) {
|
|
||||||
if (\substr($ort_name, 0, \strlen($prefix)) === "$prefix") {
|
|
||||||
$ort_name = substr($ort_name, \strlen($prefix));
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
return true; // No uncertainty found
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// Remove uncertainty sufixes
|
/**
|
||||||
foreach (NodaUncertaintyHelper::PLACE_UNCERTAINTY_SUFFIXES as $suffix) {
|
* Removes uncertainty indicators from an place name.
|
||||||
if (\substr($ort_name, \strlen($suffix) * -1) === "$suffix") {
|
*
|
||||||
$ort_name = \substr($ort_name, 0, \strlen($suffix) * -1);
|
* @param string $ort_name Input string.
|
||||||
|
*
|
||||||
|
* @return string
|
||||||
|
*/
|
||||||
|
public static function cleanUncertaintyIndicatorsPlace(string $ort_name):string {
|
||||||
|
|
||||||
|
$ort_name = self::trim($ort_name);
|
||||||
|
|
||||||
|
if (\in_array($ort_name, self::PLACE_INDICATORS_DISALLOWED, true)) {
|
||||||
|
return "";
|
||||||
}
|
}
|
||||||
}
|
|
||||||
|
|
||||||
return self::trim($ort_name);
|
// Remove uncertainty prefixes
|
||||||
|
foreach (NodaUncertaintyHelper::PLACE_UNCERTAINTY_PREFIXES as $prefix) {
|
||||||
}
|
if (\substr($ort_name, 0, \strlen($prefix)) === "$prefix") {
|
||||||
|
$ort_name = substr($ort_name, \strlen($prefix));
|
||||||
/**
|
}
|
||||||
* Attempts guessing whether place is uncertain. Returns true if the name
|
|
||||||
* indicates certainty, false if it indicates uncertainty.
|
|
||||||
*
|
|
||||||
* @param string $ort_name Place name.
|
|
||||||
*
|
|
||||||
* @return boolean
|
|
||||||
*/
|
|
||||||
public static function guessPlaceCertainty(string $ort_name):bool {
|
|
||||||
|
|
||||||
$ort_name = \strtolower($ort_name);
|
|
||||||
|
|
||||||
// Attempt to guess uncertainty based on prefixes.
|
|
||||||
foreach (NodaUncertaintyHelper::PLACE_UNCERTAINTY_PREFIXES as $prefix) {
|
|
||||||
if (\substr($ort_name, 0, \strlen($prefix)) === $prefix) {
|
|
||||||
return false; // Uncertain
|
|
||||||
}
|
}
|
||||||
}
|
|
||||||
|
|
||||||
// Attempt to guess uncertainty based on prefixes.
|
// Remove uncertainty sufixes
|
||||||
foreach (NodaUncertaintyHelper::PLACE_UNCERTAINTY_SUFFIXES as $prefix) {
|
foreach (NodaUncertaintyHelper::PLACE_UNCERTAINTY_SUFFIXES as $suffix) {
|
||||||
if (\substr($ort_name, -1 * \strlen($prefix)) === $prefix) {
|
if (\substr($ort_name, \strlen($suffix) * -1) === "$suffix") {
|
||||||
return false; // Uncertain
|
$ort_name = \substr($ort_name, 0, \strlen($suffix) * -1);
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
return self::trim($ort_name);
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
return true; // Certain / no uncertainty found
|
/**
|
||||||
|
* Attempts guessing whether place is uncertain. Returns true if the name
|
||||||
|
* indicates certainty, false if it indicates uncertainty.
|
||||||
|
*
|
||||||
|
* @param string $ort_name Place name.
|
||||||
|
*
|
||||||
|
* @return boolean
|
||||||
|
*/
|
||||||
|
public static function guessPlaceCertainty(string $ort_name):bool {
|
||||||
|
|
||||||
}
|
$ort_name = \strtolower($ort_name);
|
||||||
|
|
||||||
/**
|
// Attempt to guess uncertainty based on prefixes.
|
||||||
* Removes uncertainty indicators from an actor name.
|
foreach (NodaUncertaintyHelper::PLACE_UNCERTAINTY_PREFIXES as $prefix) {
|
||||||
*
|
if (\substr($ort_name, 0, \strlen($prefix)) === $prefix) {
|
||||||
* @param string $value Input string.
|
return false; // Uncertain
|
||||||
*
|
}
|
||||||
* @return string
|
|
||||||
*/
|
|
||||||
public static function cleanUncertaintyIndicatorsPersinst(string $value):string {
|
|
||||||
|
|
||||||
$value = self::trim($value);
|
|
||||||
|
|
||||||
if (\in_array(trim($value, ";. "), self::PERSINST_INDICATORS_DISALLOWED, true)) {
|
|
||||||
return "";
|
|
||||||
}
|
|
||||||
|
|
||||||
foreach (self::PERSINST_UNCERTAINTY_PREFIXES as $toRemove) {
|
|
||||||
if (\mb_substr($value, 0, \mb_strlen($toRemove)) === $toRemove) {
|
|
||||||
$value = substr($value, \mb_strlen($toRemove));
|
|
||||||
}
|
}
|
||||||
}
|
|
||||||
|
|
||||||
foreach (self::PLACE_UNCERTAINTY_SUFFIXES as $suffix) {
|
// Attempt to guess uncertainty based on prefixes.
|
||||||
if (\mb_substr($value, \mb_strlen($suffix) * -1) === "$suffix") {
|
foreach (NodaUncertaintyHelper::PLACE_UNCERTAINTY_SUFFIXES as $prefix) {
|
||||||
$value = \mb_substr($value, 0, \mb_strlen($suffix) * -1);
|
if (\substr($ort_name, -1 * \strlen($prefix)) === $prefix) {
|
||||||
|
return false; // Uncertain
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
return true; // Certain / no uncertainty found
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
return self::trim($value);
|
/**
|
||||||
|
* Removes uncertainty indicators from an actor name.
|
||||||
|
*
|
||||||
|
* @param string $value Input string.
|
||||||
|
*
|
||||||
|
* @return string
|
||||||
|
*/
|
||||||
|
public static function cleanUncertaintyIndicatorsPersinst(string $value):string {
|
||||||
|
|
||||||
}
|
$value = self::trim($value);
|
||||||
|
|
||||||
/**
|
if (\in_array(trim($value, ";. "), self::PERSINST_INDICATORS_DISALLOWED, true)) {
|
||||||
* Attempts guessing whether persinst is uncertain. Returns true if the name
|
return "";
|
||||||
* indicates certainty, false if it indicates uncertainty.
|
|
||||||
*
|
|
||||||
* @param string $name Persinst name.
|
|
||||||
*
|
|
||||||
* @return boolean
|
|
||||||
*/
|
|
||||||
public static function guessPersinstCertainty(string $name):bool {
|
|
||||||
|
|
||||||
$name = \trim(\strtolower($name));
|
|
||||||
|
|
||||||
// Attempt to guess uncertainty based on prefixes.
|
|
||||||
foreach (NodaUncertaintyHelper::PERSINST_UNCERTAINTY_PREFIXES as $prefix) {
|
|
||||||
if (\substr($name, 0, \strlen($prefix)) === $prefix) {
|
|
||||||
return false; // Uncertain
|
|
||||||
}
|
}
|
||||||
}
|
|
||||||
|
|
||||||
// Attempt to guess uncertainty based on prefixes.
|
foreach (self::PERSINST_UNCERTAINTY_PREFIXES as $toRemove) {
|
||||||
foreach (NodaUncertaintyHelper::PERSINST_UNCERTAINTY_SUFFIXES as $prefix) {
|
if (\mb_substr($value, 0, \mb_strlen($toRemove)) === $toRemove) {
|
||||||
if (\substr($name, -1 * \strlen($prefix)) === $prefix) {
|
$value = substr($value, \mb_strlen($toRemove));
|
||||||
return false; // Uncertain
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
foreach (self::PLACE_UNCERTAINTY_SUFFIXES as $suffix) {
|
||||||
|
if (\mb_substr($value, \mb_strlen($suffix) * -1) === "$suffix") {
|
||||||
|
$value = \mb_substr($value, 0, \mb_strlen($suffix) * -1);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
return self::trim($value);
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
return true; // Certain / no uncertainty found
|
/**
|
||||||
|
* Attempts guessing whether persinst is uncertain. Returns true if the name
|
||||||
|
* indicates certainty, false if it indicates uncertainty.
|
||||||
|
*
|
||||||
|
* @param string $name Persinst name.
|
||||||
|
*
|
||||||
|
* @return boolean
|
||||||
|
*/
|
||||||
|
public static function guessPersinstCertainty(string $name):bool {
|
||||||
|
|
||||||
}
|
$name = \trim(\strtolower($name));
|
||||||
|
|
||||||
|
// Attempt to guess uncertainty based on prefixes.
|
||||||
|
foreach (NodaUncertaintyHelper::PERSINST_UNCERTAINTY_PREFIXES as $prefix) {
|
||||||
|
if (\substr($name, 0, \strlen($prefix)) === $prefix) {
|
||||||
|
return false; // Uncertain
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Attempt to guess uncertainty based on prefixes.
|
||||||
|
foreach (NodaUncertaintyHelper::PERSINST_UNCERTAINTY_SUFFIXES as $prefix) {
|
||||||
|
if (\substr($name, -1 * \strlen($prefix)) === $prefix) {
|
||||||
|
return false; // Uncertain
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
return true; // Certain / no uncertainty found
|
||||||
|
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
|
@ -19,9 +19,9 @@ final class NodaValidationHelper {
|
||||||
* made.
|
* made.
|
||||||
*
|
*
|
||||||
* @param string $description Input descrition.
|
* @param string $description Input descrition.
|
||||||
* @param string $name Names of the actor. Optional. Setting this enables
|
* @param string $name Names of the actor. Optional. Setting this enables
|
||||||
* checks e.g. to prevent duplicating the actor name
|
* checks e.g. to prevent duplicating the actor name
|
||||||
* as a description.
|
* as a description.
|
||||||
*
|
*
|
||||||
* @return void
|
* @return void
|
||||||
*/
|
*/
|
||||||
|
|
|
@ -56,7 +56,6 @@ final class NodaConsolidatedNamesForPlacesTest extends TestCase {
|
||||||
self::assertEquals("Deák Ferenc utca 16-18. (Budapest, 5. kerület)", NodaConsolidatedNamesForPlaces::consolidate_name("hu", "Deák Ferenc utca 16-18. Budapest, V."));
|
self::assertEquals("Deák Ferenc utca 16-18. (Budapest, 5. kerület)", NodaConsolidatedNamesForPlaces::consolidate_name("hu", "Deák Ferenc utca 16-18. Budapest, V."));
|
||||||
self::assertEquals("Deák Ferenc utca 16-18. Budapest, V. abc", NodaConsolidatedNamesForPlaces::consolidate_name("hu", "Deák Ferenc utca 16-18. Budapest, V. abc"));
|
self::assertEquals("Deák Ferenc utca 16-18. Budapest, V. abc", NodaConsolidatedNamesForPlaces::consolidate_name("hu", "Deák Ferenc utca 16-18. Budapest, V. abc"));
|
||||||
|
|
||||||
|
|
||||||
// Rewriting country names in brackets
|
// Rewriting country names in brackets
|
||||||
self::assertEquals("Köln (Deutschland)", NodaConsolidatedNamesForPlaces::consolidate_name("de", "Deutschland-Köln"));
|
self::assertEquals("Köln (Deutschland)", NodaConsolidatedNamesForPlaces::consolidate_name("de", "Deutschland-Köln"));
|
||||||
self::assertEquals("Köln (Deutschland)", NodaConsolidatedNamesForPlaces::consolidate_name("de", "Deutschland, Köln"));
|
self::assertEquals("Köln (Deutschland)", NodaConsolidatedNamesForPlaces::consolidate_name("de", "Deutschland, Köln"));
|
||||||
|
|
|
@ -37,7 +37,6 @@ final class NodaTimeSplitterTest extends TestCase {
|
||||||
self::assertEquals($output->toTimeName(), "02.01.2020");
|
self::assertEquals($output->toTimeName(), "02.01.2020");
|
||||||
self::assertEquals(NodaTimeSplitter::timePartsToCountingYear($output), 2020);
|
self::assertEquals(NodaTimeSplitter::timePartsToCountingYear($output), 2020);
|
||||||
|
|
||||||
|
|
||||||
$output = NodaTimeSplitter::attempt_splitting("02.1.25 v. Chr");
|
$output = NodaTimeSplitter::attempt_splitting("02.1.25 v. Chr");
|
||||||
self::assertNotEmpty($output);
|
self::assertNotEmpty($output);
|
||||||
self::assertEquals($output->toOldFormat(), [
|
self::assertEquals($output->toOldFormat(), [
|
||||||
|
|
|
@ -12,8 +12,6 @@ use PHPUnit\Framework\Attributes\Small;
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* This script contains tests for the validation of single field contents.
|
* This script contains tests for the validation of single field contents.
|
||||||
*
|
|
||||||
* @covers \NodaValidationHelper
|
|
||||||
*/
|
*/
|
||||||
#[small]
|
#[small]
|
||||||
#[CoversClass(\NodaValidationHelper::class)]
|
#[CoversClass(\NodaValidationHelper::class)]
|
||||||
|
|
|
@ -20,6 +20,5 @@ declare(strict_types = 1);
|
||||||
}
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
});
|
});
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue
Block a user