Add lemma rules

2024-11-11 04:08:09 +03:00 · 2016-12-18 15:36:20 +01:00 · 2016-12-18 15:36:20 +01:00 · 2eb163c5dd
commit 2eb163c5dd
parent 29ad8143d8
1 changed files with 42 additions and 0 deletions
--- a/spacy/en/lemma_rules.py
+++ b/spacy/en/lemma_rules.py
@ -0,0 +1,42 @@
+# encoding: utf8
+from __future__ import unicode_literals
+
+
+LEMMA_RULES = {
+    "noun": [
+        ["s", ""],
+        ["ses", "s"],
+        ["ves", "f"],
+        ["xes", "x"],
+        ["zes", "z"],
+        ["ches", "ch"],
+        ["shes", "sh"],
+        ["men", "man"],
+        ["ies", "y"]
+    ],
+
+    "verb": [
+        ["s", ""],
+        ["ies", "y"],
+        ["es", "e"],
+        ["es", ""],
+        ["ed", "e"],
+        ["ed", ""],
+        ["ing", "e"],
+        ["ing", ""]
+    ],
+
+    "adj": [
+        ["er", ""],
+        ["est", ""],
+        ["er", "e"],
+        ["est", "e"]
+    ],
+
+    "punct": [
+        ["“", "\""],
+        ["”", "\""],
+        ["\u2018", "'"],
+        ["\u2019", "'"]
+    ]
+}