From 7006a6b42dfd8d4b4f3da01fd2bd50688aa4325f Mon Sep 17 00:00:00 2001 From: mvalentsev Date: Sat, 18 Apr 2026 21:53:11 +0500 Subject: [PATCH] feat(i18n): add entity detection to German locale --- mempalace/i18n/de.json | 82 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) diff --git a/mempalace/i18n/de.json b/mempalace/i18n/de.json index c6677b3..f2476e1 100644 --- a/mempalace/i18n/de.json +++ b/mempalace/i18n/de.json @@ -40,5 +40,87 @@ "stop_words": "der die das ein eine eines einer einem einen den dem des und oder aber denn weil wenn als ob auch noch schon sehr viel nur nicht mehr kann wird hat ist sind war waren sein haben wurde mit von zu für auf in an um über nach durch", "quote_pattern": "\\u201E([^\\u201C]{10,200})\\u201C|\"([^\"]{10,200})\"", "action_pattern": "(?:gebaut|behoben|geschrieben|hinzugefügt|gepusht|gemessen|getestet|überprüft|erstellt|gelöscht|aktualisiert|konfiguriert|bereitgestellt|migriert)\\s+[\\wÄÖÜäöüß\\s]{3,30}" + }, + "entity": { + "candidate_pattern": "[A-ZÄÖÜ][a-zäöüß]{1,19}", + "multi_word_pattern": "[A-ZÄÖÜ][a-zäöüß]+(?:\\s+[A-ZÄÖÜ][a-zäöüß]+)+", + "person_verb_patterns": [ + "\\b{name}\\s+sagte\\b", + "\\b{name}\\s+fragte\\b", + "\\b{name}\\s+antwortete\\b", + "\\b{name}\\s+erzählte\\b", + "\\b{name}\\s+lachte\\b", + "\\b{name}\\s+lächelte\\b", + "\\b{name}\\s+weinte\\b", + "\\b{name}\\s+fühlte\\b", + "\\b{name}\\s+denkt\\b", + "\\b{name}\\s+will\\b", + "\\b{name}\\s+liebt\\b", + "\\b{name}\\s+hasst\\b", + "\\b{name}\\s+weiß\\b", + "\\b{name}\\s+entschied\\b", + "\\b{name}\\s+schrieb\\b" + ], + "pronoun_patterns": [ + "\\ber\\b", + "\\bsie\\b", + "\\bes\\b", + "\\bihn\\b", + "\\bihm\\b", + "\\bihr\\b", + "\\bsein\\b", + "\\bihre\\b", + "\\bihnen\\b" + ], + "dialogue_patterns": [ + "^>\\s*{name}[:\\s]", + "^{name}:\\s", + "^\\[{name}\\]", + "\"{name}\\s+sagte" + ], + "direct_address_pattern": "\\bhallo\\s+{name}\\b|\\bhi\\s+{name}\\b|\\bhey\\s+{name}\\b|\\bdanke\\s+{name}\\b|\\bservus\\s+{name}\\b|\\blieber\\s+{name}\\b|\\bliebe\\s+{name}\\b|\\bsehr\\s+geehrter\\s+{name}\\b|\\bsehr\\s+geehrte\\s+{name}\\b", + "project_verb_patterns": [ + "\\bbaue\\s+{name}\\b", + "\\bgebaut\\s+{name}\\b", + "\\bstarte\\s+{name}\\b", + "\\bgestartet\\s+{name}\\b", + "\\bdeploye\\s+{name}\\b", + "\\binstalliert\\s+{name}\\b", + "\\bdie\\s+{name}\\s+architektur\\b", + "\\bdie\\s+{name}\\s+pipeline\\b", + "\\bdas\\s+{name}\\s+system\\b", + "\\bdas\\s+{name}\\s+repository\\b", + "\\b{name}\\s+v\\d+\\b", + "\\b{name}\\.py\\b", + "\\bimport\\s+{name}\\b", + "\\bpip\\s+install\\s+{name}\\b" + ], + "stopwords": [ + "der", "die", "das", "ein", "eine", "eines", "einer", "einem", "einen", + "den", "dem", "des", "und", "oder", "aber", "denn", "weil", "wenn", "als", + "ob", "auch", "noch", "schon", "sehr", "viel", "nur", "nicht", "mehr", + "kann", "wird", "hat", "ist", "sind", "war", "waren", "sein", "haben", + "wurde", "worden", "werden", "mit", "von", "zu", "für", "auf", "in", + "an", "um", "über", "nach", "durch", "bei", "aus", "seit", "vor", "zwischen", + "ich", "du", "er", "sie", "es", "wir", "ihr", "mich", "dich", "mir", "dir", + "uns", "euch", "mein", "dein", "unser", "euer", "ihre", "seine", + "wer", "was", "wann", "wo", "wie", "warum", "welcher", "welche", "welches", + "so", "dann", "jetzt", "heute", "gestern", "morgen", "hier", "dort", "da", + "immer", "nie", "manchmal", "oft", "selten", "bald", "spät", + "ja", "nein", "vielleicht", "gut", "schlecht", "besser", "bitte", "danke", + "hallo", "hi", "hey", "tschüss", + "tag", "tage", "woche", "monat", "jahr", "jahre", "zeit", "welt", "leben", + "mensch", "menschen", "leute", "person", "ding", "dinge", "sache", "sachen", + "teil", "art", "weise", "stelle", "platz", "ort", "zimmer", "haus", "land", + "grund", "frage", "antwort", "fakt", "sinn", "idee", "punkt", "fall", "aspekt", + "beispiel", "version", "nummer", "zahl", "name", "namen", "system", "modell", + "sprache", "technologie", "gesellschaft", "kultur", "geschichte", + "wissenschaft", "zukunft", "erinnerung", "gedächtnis", + "datei", "ordner", "pfad", "schlüssel", "wert", "fehler", "warnung", + "ergebnis", "eingabe", "ausgabe", "quelle", "ziel", "daten", "elemente", + "montag", "dienstag", "mittwoch", "donnerstag", "freitag", "samstag", "sonntag", + "januar", "februar", "märz", "april", "mai", "juni", "juli", "august", + "september", "oktober", "november", "dezember" + ] } }