blob: 8adc35c963b383cbdd555b7f44e974aeefe4e015 [file] [log] [blame]
Akron3dd560e2026-02-04 11:23:08 +01001! Gender-sensitive endings (German)
2! By M. Kupietz (KorAP-Tokenizer)
3
4! Matches patterns like: in, innen, In, Innen, IN, INNEN (case-insensitive)
5define genderEndingsIn [ [i | I] [n | N] ( [n | N] [e | E] [n | N] ) ];
6
7! Slash forms are restricted to lowercase in/innen to avoid
8! false positives in compounds like "Nutzer/Innenarchitekt".
9define genderEndingsInLower [ i n ( n e n ) ];
10
11! Gender-sensitive endings with frau/frauen
12! (lowercase only - capitalized Frau is a standalone word)
13! Note: This is now only used for words ending in "mann"
14! (with non-empty prefix) for Kaufmann/frau pattern
15! Matches: Kaufmann, Geschäftsmann, etc. but NOT just "mann"
16define genderEndingsFrau [ {frau} ( {en} ) ];
17
18! General gender endings (only -in/-innen forms for colon, slash, parenthetical)
19! Colon forms: Nutzer:in, Nutzer:In, Nutzer:innen
20! Slash forms for -in/-innen: Nutzer/in, Nutzer/innen, Nutzer/-in, Kosovo-Albaner/innen
21define genderIn [ ":" genderEndingsIn | Slash ( %- ) genderEndingsInLower ];
22
23! Slash forms for -frau: Kaufmann/frau, Kaufmann/-frau, Geschäftsmann/frau
24! Only applies when word ends in "mann" (with non-empty prefix before it)
25define genderFrau [ {mann} Slash ( %- ) genderEndingsFrau ];
26
27! Parenthetical forms for -in/-innen: Nutzer(in), Nutzer(innen), Nutzer(-in)
28define genderParenIn %( ( %- ) genderEndingsIn %);
29
30! Parenthetical forms for -frau: Kaufmann(frau), Kaufmann(-frau)
31! Only applies when word ends in "mann" (with non-empty prefix before it)
32define genderParenFrau {mann} %( ( %- ) genderEndingsFrau %);
33
34define GenderEndings [ genderIn | genderFrau | genderParenIn | genderParenFrau ];