dendy
/
anker
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Compare commits

base: dendy:a838347ff5fd089edf93934edc44b03e379f7cb5
Branches Tags
dendy:main
dendy:mainF
..
compare: dendy:da9d4d344ac934d754850c2b7eeb85cb35b86081
Branches Tags
dendy:main
dendy:mainF

No commits in common. "a838347ff5fd089edf93934edc44b03e379f7cb5" and "da9d4d344ac934d754850c2b7eeb85cb35b86081" have entirely different histories.
a838347ff5 ... da9d4d344a

11 changed files with 63 additions and 318 deletions
Show Stats Expand all files Collapse all files

4
.gitignore vendored
View File

@ -23,7 +23,3 @@
/public/assets/
/assets/vendor/
###< symfony/asset-mapper ###
###> phpstan/phpstan ###
phpstan.neon
###< phpstan/phpstan ###

2
composer.json
View File

@ -96,8 +96,6 @@
}
},
"require-dev": {
"phpstan/phpstan": "^2.1",
"phpstan/phpstan-symfony": "^2.0",
"phpunit/phpunit": "^9.5",
"symfony/browser-kit": "7.1.*",
"symfony/css-selector": "7.1.*",

131
composer.lock generated
View File

@ -4,7 +4,7 @@
"Read more about it at https://getcomposer.org/doc/01-basic-usage.md#installing-dependencies",
"This file is @generated automatically"
],
"content-hash": "14aafa03aea05ab652ae5863659345dd",
"content-hash": "bfa3fd6c661ba7df71cffe78211433ff",
"packages": [
{
"name": "composer/semver",
@ -7868,135 +7868,6 @@
},
"time": "2022-02-21T01:04:05+00:00"
},
{
"name": "phpstan/phpstan",
"version": "2.1.22",
"source": {
"type": "git",
"url": "https://github.com/phpstan/phpstan.git",
"reference": "41600c8379eb5aee63e9413fe9e97273e25d57e4"
},
"dist": {
"type": "zip",
"url": "https://api.github.com/repos/phpstan/phpstan/zipball/41600c8379eb5aee63e9413fe9e97273e25d57e4",
"reference": "41600c8379eb5aee63e9413fe9e97273e25d57e4",
"shasum": ""
},
"require": {
"php": "^7.4|^8.0"
},
"conflict": {
"phpstan/phpstan-shim": "*"
},
"bin": [
"phpstan",
"phpstan.phar"
],
"type": "library",
"autoload": {
"files": [
"bootstrap.php"
]
},
"notification-url": "https://packagist.org/downloads/",
"license": [
"MIT"
],
"description": "PHPStan - PHP Static Analysis Tool",
"keywords": [
"dev",
"static analysis"
],
"support": {
"docs": "https://phpstan.org/user-guide/getting-started",
"forum": "https://github.com/phpstan/phpstan/discussions",
"issues": "https://github.com/phpstan/phpstan/issues",
"security": "https://github.com/phpstan/phpstan/security/policy",
"source": "https://github.com/phpstan/phpstan-src"
},
"funding": [
{
"url": "https://github.com/ondrejmirtes",
"type": "github"
},
{
"url": "https://github.com/phpstan",
"type": "github"
}
],
"time": "2025-08-04T19:17:37+00:00"
},
{
"name": "phpstan/phpstan-symfony",
"version": "2.0.7",
"source": {
"type": "git",
"url": "https://github.com/phpstan/phpstan-symfony.git",
"reference": "392f7ab8f52a0a776977be4e62535358c28e1b15"
},
"dist": {
"type": "zip",
"url": "https://api.github.com/repos/phpstan/phpstan-symfony/zipball/392f7ab8f52a0a776977be4e62535358c28e1b15",
"reference": "392f7ab8f52a0a776977be4e62535358c28e1b15",
"shasum": ""
},
"require": {
"ext-simplexml": "*",
"php": "^7.4 || ^8.0",
"phpstan/phpstan": "^2.1.13"
},
"conflict": {
"symfony/framework-bundle": "<3.0"
},
"require-dev": {
"php-parallel-lint/php-parallel-lint": "^1.2",
"phpstan/phpstan-phpunit": "^2.0",
"phpstan/phpstan-strict-rules": "^2.0",
"phpunit/phpunit": "^9.6",
"psr/container": "1.1.2",
"symfony/config": "^5.4 || ^6.1",
"symfony/console": "^5.4 || ^6.1",
"symfony/dependency-injection": "^5.4 || ^6.1",
"symfony/form": "^5.4 || ^6.1",
"symfony/framework-bundle": "^5.4 || ^6.1",
"symfony/http-foundation": "^5.4 || ^6.1",
"symfony/messenger": "^5.4",
"symfony/polyfill-php80": "^1.24",
"symfony/serializer": "^5.4",
"symfony/service-contracts": "^2.2.0"
},
"type": "phpstan-extension",
"extra": {
"phpstan": {
"includes": [
"extension.neon",
"rules.neon"
]
}
},
"autoload": {
"psr-4": {
"PHPStan\\": "src/"
}
},
"notification-url": "https://packagist.org/downloads/",
"license": [
"MIT"
],
"authors": [
{
"name": "Lukáš Unger",
"email": "looky.msc@gmail.com",
"homepage": "https://lookyman.net"
}
],
"description": "Symfony Framework extensions and rules for PHPStan",
"support": {
"issues": "https://github.com/phpstan/phpstan-symfony/issues",
"source": "https://github.com/phpstan/phpstan-symfony/tree/2.0.7"
},
"time": "2025-07-22T09:40:57+00:00"
},
{
"name": "phpunit/php-code-coverage",
"version": "9.2.32",

8
phpstan.dist.neon
View File

@ -1,8 +0,0 @@
parameters:
level: 6
paths:
- bin/
- config/
- public/
- src/
- tests/

101
src/Command/CreateProductionCommand.php
View File

@ -8,12 +8,13 @@ use App\Entity\Term;
use App\Service\AnkiService;
use App\Utils\Japanese;
use App\Utils\Progress;
use Symfony\Component\Console\Attribute\AsCommand;
use Symfony\Component\Console\Command\Command;
use Symfony\Component\Console\Input\InputArgument;
use Symfony\Component\Console\Input\InputInterface;
use Symfony\Component\Console\Input\InputOption;
use Symfony\Component\Console\Output\OutputInterface;
use Symfony\Component\Console\Style\SymfonyStyle;
#[AsCommand(
name: 'app:create-production',
@ -27,7 +28,6 @@ class CreateProductionCommand extends Command
parent::__construct();
}
/** @return list<string> */
private static function extractKanji(string $str): array
{
preg_match_all('/\p{Script=Han}/u', $str, $matches);
@ -39,7 +39,6 @@ class CreateProductionCommand extends Command
return preg_replace('/[^\p{Script=Han}]/u', '', $str);
}
/** @param array<string, 0> $ref */
private static function kanjiDiff(array &$ref, string $subject): bool
{
$len = mb_strlen($subject);
@ -48,7 +47,7 @@ class CreateProductionCommand extends Command
for ($i = 0; $i < $len; $i++) {
$subKanji = mb_substr($subject, $i, 1);
foreach (array_keys($ref) as $refKanji) {
foreach ($ref as $refKanji => $value) {
if ($subKanji === $refKanji) continue 2;
}
@ -61,11 +60,10 @@ class CreateProductionCommand extends Command
protected function configure(): void
{
$this->addArgument(
'count',
InputArgument::REQUIRED,
'Amount of cards to make',
);
$this
->addArgument('count', InputArgument::OPTIONAL, 'Amount of cards to make', 1);
//->addOption('option1', null, InputOption::VALUE_NONE, 'Option description')
;
}
protected function createProductionNoteFromTerm(Term $term): void
@ -114,105 +112,71 @@ class CreateProductionCommand extends Command
protected function execute(InputInterface $input, OutputInterface $output): int
{
$allSentenceNotes = $this->getAllSentenceNotes();
$allSentenceNotes = $this->getAllSentenceNotes();
$allListeningNotes = $this->getAllSentenceListeningNotes();
// Index of all the Terms indexed by its TermKanji
$allTerms = []; // ["パレートの法則" => App\Entity\Term]
// Set of known Kanji Characters
$knownKanji = []; // ["法" => 0, "則" => 0]
// How many times it appears (not as a term, but in KanjiSentence)
$termCounts = []; // ["パレートの法則" => 1]
// --------- Getting list<SentenceNote> into array<TermKanji, Term> ---
$allTerms = [];
$knownKanji = [];
$termCounts = [];
printf('Indexing all terms...');
foreach ($allSentenceNotes as $note) {
foreach ($note->getTerms() as &$term) {
// Deduplicate list
assert($term instanceof Term);
if (key_exists($term->getKanji(), $allTerms)) continue;
// Actual indexing
$allTerms[$term->getKanji()] = &$term;
// Just simple intialization
$termCounts[$term->getKanji()] = 0;
$allTerms[$term->getKanji()] = &$term;
foreach (self::extractKanji($term->getKanji()) as $kanji) {
$knownKanji[$kanji] = 0;
}
}
}
printf(" OK (%d)\n", count($knownKanji));
printf(" OK (%d)\n", count($allTerms));
// Populate $knownKanji ["例" => 378, ...];
// TODO: Move this into own function to prevent side-effects. It's
// looping through the whole thing again anyway, so there's no
// need for it in here.
//
// Maybe while you're at it, it could be simplified into a
// function like $this->anki->getKanji('origField', 'countField')
// Where count can be null so it's just a Set
$progress = new Progress('Getting frequenciees', count($allSentenceNotes));
foreach ($allSentenceNotes as $note) {
$progress->tick();
// Sanitize sentence (remove those pesky \u{200E})
$_sentKanji = str_replace(
$sentKanji = str_replace(
"\u{200E}",
'',
strip_tags($note->getFields()['SentKanji'])
);
foreach ($knownKanji as $kanji => &$count) {
if (str_contains($_sentKanji, $kanji)) $count++;
if (str_contains($sentKanji, $kanji)) $count++;
}
}
// TODO: Make progress a function with a callback? That way scope inside
// and side-effects are easy to control & track
unset($progress);
printf("\n");
// Build the values to be used in the ordering process
// TODO: It kinda feels wrong that $termCounts is used in this special
// manner while $seenScore is separate. Does it make sense to
// build them at this stage? Make a generic orderer?
//
// $termOrdering = ['first' => 32, 'second' => 34, 'apple' => 2];
//
// At first we just built the term list, then we generate an
// ordering array where the list is ordered
$seenKanji = $this->ankiService->getKnownSlnKanjiCounts();
printf('Rating terms...');
$studiedKanji = $this->ankiService->getKnownSlnKanjiCounts('ASC');
$seenScore = [];
foreach ($allTerms as $key => $term) {
$diff = Japanese::kanjiDiff($term->getKanji(), array_keys($studiedKanji));
$count = Japanese::kanjiDiff(
$term->getKanji(),
array_keys($seenKanji),
);
if (count($diff) <= 0) {
if ($count <= 0) {
unset($allTerms[$key]);
unset($termCounts[$key]);
continue;
}
// Build $seenScore
$seenScore[$key] = 0;
foreach (Japanese::getKanjiList($key) as $_kanji) {
$seenScore[$key] += $studiedKanji[$_kanji] ?? 0;
}
// Build $termCounts
$termCounts[$term->getKanji()] = count($diff);
$termCounts[$term->getKanji()] = $count;
}
// Ordering in having:
// 1. Least new Kanji (ideally we just one 1 new kanji)
// 2. Most Kanji (most amount of unique kanji)
// 3. Least studied kanji
uksort($termCounts, fn($a, $b) => $seenScore[$a] <=> $seenScore[$b]);
uksort($termCounts, function ($a, $b) {
$aLen = count(Japanese::getKanjiList($a));
$bLen = count(Japanese::getKanjiList($b));
$aLen = mb_strlen(Japanese::getOnlyKanji($a));
$bLen = mb_strlen(Japanese::getOnlyKanji($b));
return $bLen <=> $aLen;
});
asort($termCounts, SORT_NUMERIC);
asort($termCounts);
printf(" OK\n");
// Have into account the ones that have already been created.
// This will not only skip them but also update the general array for
// already seen kanji.
@ -220,6 +184,8 @@ class CreateProductionCommand extends Command
printf('Filtering out terms with no new kanji...');
// First pass: Get the list of the kanji we've seen
foreach ($allListeningNotes as $listeningNote) {
assert($listeningNote instanceof SentenceListeningNote);
$termKanji = self::getOnlyKanji($listeningNote->getTerm()->getKanji());
self::kanjiDiff($seenKanji, $termKanji);
}
@ -243,8 +209,11 @@ class CreateProductionCommand extends Command
foreach ($termCounts as $term => $count) {
if ($newNotesCount <= 0) break;
// FIXME: This shouldn't happen at all
if (!$allTerms[$term] instanceof Term) continue;
$termKanji = self::getOnlyKanji($term);
printf("%s %d | %d\n", "{$term}：", $count, $seenScore[$term]);
printf("%s: %d\n", $term, $count);
//$len = mb_strlen($termKanji);
//for ($i = 0; $i < $len; $i++) {
@ -252,7 +221,7 @@ class CreateProductionCommand extends Command
// printf(" - %s: %0.2f\n", $iKanji, $knownKanji[$iKanji] / $len);
//}
//$this->createProductionNoteFromTerm($allTerms[$term]);
$this->createProductionNoteFromTerm($allTerms[$term]);
$newNotesCount -= 1;
};

8
src/Controller/AnkiController.php
View File

@ -73,14 +73,6 @@ class AnkiController extends AbstractController
]);
}
#[Route('/kanji', 'kanji', methods: 'GET')]
public function kanji()
{
$thing = $this->ankiService->getKnownSnKanjiCounts();
asort($thing, SORT_DESC);
return new Response(implode('', array_keys($thing)));
}
#[Route('/note/{nid}/get', name: 'get_note')]
public function get_note(int $nid)
{

2
src/Entity/SentenceNote.php
View File

@ -11,12 +11,10 @@ class SentenceNote extends Note
// -------------------------------------------------- Getters & setters ---
/** @return list<Term> */
public function getTerms(): array
{
return $this->terms;
}
/** @param list<Terms> $terms */
public function setTerms(array $terms): static
{
$this->terms = $terms;

21
src/Entity/Term.php
View File

@ -18,21 +18,15 @@ class Term
return self::parseFurigana($this->kanji)['kanji'];
}
/**
* Get the kanji version & the reading for a given term
*
* TODO: Make this smarter & handle mixing of kanji & hiradana
*
* @return array{'kanji': string, 'reading': null|string}
* */
public static function parseFurigana(string $furigana): array
{
// 0: all, 1: (kanji/hiragana), 2: ([reading, ...]), 3: (reading)
// 0: all, 1: (kanji/hiragana), 2: ([reading]): 3: (reading)
preg_match_all('/([^ \[]+)(\[([^\]]*)\])? ?/', $furigana, $matches, PREG_SET_ORDER);
$matchedKanji = array_map(fn($x) => $x[1], $matches);
$matchedReading = array_map(fn($x) => $x[3] ?? $x[1], $matches);
return [
'kanji' => join('', $matchedKanji),
'reading' => $matchedKanji == $matchedReading
@ -41,7 +35,7 @@ class Term
];
}
public function toAnkiVocabDef(): string
public function toAnkiVocabDef()
{
$ret = '<span ' . Note::HIGHLIGHT_ATTR_KANJI . '>' . $this->kanji;
@ -85,7 +79,10 @@ class Term
'」' => ']',
'　' => ' ',
]));
$def = mb_trim($def);
$def = mb_trim($def);
if (!is_string($term->kanji)) {
return null;
}
// -------------------------------------------------- No definition ---
@ -142,10 +139,6 @@ class Term
return Term::fromVocabDefLine($kanji . $separator . $def);
}
/**
* @param array<string, string> $fields
* @return list<Term>
*/
public static function fromNoteFields(array $fields): array
{
// -------------------- Trying to extract it with the modern syntax ---

30
src/Service/AnkiService.php
View File

@ -134,7 +134,7 @@ class AnkiService
}
/** @return array<string, int> */
public function getKnownSlnKanjiCounts(?string $order = null): array
public function getKnownSlnKanjiCounts(): array
{
$allListeningIds = $this->getAllSentenceListeningNoteIds();
$ret = [];
@ -152,34 +152,6 @@ class AnkiService
}
}
uasort($ret, function (int $a, int $b) use ($order) {
return $order === 'ASC' ? $a <=> $b : $b <=> $a;
});
return $ret;
}
/** @return array<string, int> */
public function getKnownSnKanjiCounts(): array
{
$allListeningIds = $this->getAllSentenceNoteIds();
$ret = [];
foreach ($this->getNotes($allListeningIds) as $sNote) {
assert($sNote instanceof SentenceNote);
foreach ($sNote->getTerms() as $term) {
$termKanji = Japanese::getOnlyKanji($term->getKanji());
$len = mb_strlen($termKanji);
for ($i = 0; $i < $len; $i++) {
$kanji = mb_substr($termKanji, $i, 1);
$ret[$kanji] ??= 0;
$ret[$kanji]++;
}
}
}
return $ret;
}
}

53
src/Utils/Japanese.php
View File

@ -6,48 +6,33 @@ class Japanese
{
public static function getOnlyKanji(string $str): string
{
return preg_replace('/[^\p{Script=Han}]/u', '', $str) ?? '';
return preg_replace('/[^\p{Script=Han}]/u', '', $str);
}
/** @return \Generator<int, string> */
public static function mbIterate(
string $str,
int $start = 0,
int $length = 1,
?string $encoding = null,
): \Generator {
while (($char = mb_substr($str, $start++, $length, $encoding)) !== '') {
yield $char;
}
}
/** @return list<string> */
public static function getKanjiList(string $str): array
{
$ret = [];
foreach (self::mbIterate(self::getOnlyKanji($str)) as $kanji) {
$ret[$kanji] = 0;
}
return array_keys($ret);
}
/**
* Get the list of kanji that are not present in a given string.
* Only kanji are considered, not katakana, hiragana or any other symbols.
/** Get the number of kanji of a string that are not in the given set
* of kanji
*
* Only kanji are considere, not katakana, hiragana or any other symbols.
*
* @param list<string> $kanjiSet
* @return list<string>
*/
public static function kanjiDiff(string $str, array $kanjiSet): array
public static function kanjiDiff(string $str, array $kanjiSet): int
{
$ret = [];
$ret = 0;
foreach (self::mbIterate(self::getOnlyKanji($str)) as $kanji) {
if (!array_search($kanji, $kanjiSet)) $ret[$kanji] = 0;
$strKanji = self::getOnlyKanji($str);
$len = mb_strlen($strKanji);
for ($i = 0; $i < $len; $i++) {
$kanji = mb_substr($strKanji, $i, 1);
if (!array_search($kanji, $kanjiSet)) {
$ret++;
}
}
return array_keys($ret);
//dump($str, $strKanji, $ret);
//echo "\n";
return $ret;
}
}

21
symfony.lock
View File

@ -1,13 +1,4 @@
{
"doctrine/deprecations": {
"version": "1.1",
"recipe": {
"repo": "github.com/symfony/recipes",
"branch": "main",
"version": "1.0",
"ref": "87424683adc81d7dc305eefec1fced883084aab9"
}
},
"doctrine/doctrine-bundle": {
"version": "2.13",
"recipe": {
@ -35,18 +26,6 @@
"migrations/.gitignore"
]
},
"phpstan/phpstan": {
"version": "2.1",
"recipe": {
"repo": "github.com/symfony/recipes-contrib",
"branch": "main",
"version": "1.0",
"ref": "5e490cc197fb6bb1ae22e5abbc531ddc633b6767"
},
"files": [
"phpstan.dist.neon"
]
},
"phpunit/phpunit": {
"version": "9.6",
"recipe": {