Rename MWE patterns for clarity

meghdadFar · Apr 8, 2024 · 5cd378c · 5cd378c
1 parent d90c129
commit 5cd378c
Showing 1 changed file with 60 additions and 36 deletions.
diff --git a/wordview/mwes/patterns.py b/wordview/mwes/patterns.py
@@ -4,56 +4,80 @@
 class EnMWEPatterns:
     patterns: Dict[str, List[str]] = {}
 
-    def __init__(self, mwe_types=["LVC", "NC2", "NC3", "ANC2", "ANC3", "VPC"]):
-        if "LVC" in mwe_types:
-            self.patterns["LVC"] = [
-                "LVC: {<VB*><DT><\\w+>}",
+    def __init__(
+        self,
+        mwe_types=[
+            "Light Verb Constructions",
+            "Noun Noun Compounds",
+            "Noun Noun Noun Compounds",
+            "Adjective Noun Compounds",
+            "Adjective Adjective Noun Compounds",
+            "Verb Particle Constructions",
+        ],
+    ):
+        if "Light Verb Constructions" in mwe_types:
+            self.patterns["Light Verb Constructions"] = [
+                "Light Verb Constructions: {<VB*><DT><\\w+>}",
             ]
-        if "NC2" in mwe_types:
-            self.patterns["NC2"] = [
-                "NC2: {<NN|NNS><NN|NNS>}",
+        if "Noun Noun Compounds" in mwe_types:
+            self.patterns["Noun Noun Compounds"] = [
+                "Noun Noun Compounds: {<NN|NNS><NN|NNS>}",
             ]
-        if "NC3" in mwe_types:
-            self.patterns["NC3"] = [
-                "NC3: {<NN|NNS><NN|NNS><NN|NNS>}",
+        if "Noun Noun Noun Compounds" in mwe_types:
+            self.patterns["Noun Noun Noun Compounds"] = [
+                "Noun Noun Noun Compounds: {<NN|NNS><NN|NNS><NN|NNS>}",
             ]
-        if "ANC2" in mwe_types:
-            self.patterns["ANC2"] = [
-                "ANC2: {<JJ><NN|NNS>}",
+        if "Adjective Noun Compounds" in mwe_types:
+            self.patterns["Adjective Noun Compounds"] = [
+                "Adjective Noun Compounds: {<JJ><NN|NNS>}",
             ]
-        if "ANC3" in mwe_types:
-            self.patterns["ANC3"] = ["ANC3: {<JJ><JJ><NN|NNS>}"]
-        if "VPC" in mwe_types:
-            self.patterns["VPC"] = [
-                "VPC: {<VB|VBP><RP>}",
+        if "Adjective Adjective Noun Compounds" in mwe_types:
+            self.patterns["Adjective Adjective Noun Compounds"] = [
+                "Adjective Adjective Noun Compounds: {<JJ><JJ><NN|NNS>}"
+            ]
+        if "Verb Particle Constructions" in mwe_types:
+            self.patterns["Verb Particle Constructions"] = [
+                "Verb Particle Constructions: {<VB|VBP><RP>}",
             ]
 
 
 class DeMWEPatterns:
     patterns: Dict[str, List[str]] = {}
 
-    def __init__(self, mwe_types=["LVC", "NC2", "NC3", "ANC2", "ANC3", "VPC"]):
-        if "LVC" in mwe_types:
-            self.patterns["LVC"] = [
-                "LVC: {<VB*><DT><\\w+>}",
+    def __init__(
+        self,
+        mwe_types=[
+            "Light Verb Constructions",
+            "Noun Noun Compounds",
+            "Noun Noun Noun Compounds",
+            "Adjective Noun Compounds",
+            "Adjective Adjective Noun Compounds",
+            "Verb Particle Constructions",
+        ],
+    ):
+        if "Light Verb Constructions" in mwe_types:
+            self.patterns["Light Verb Constructions"] = [
+                "Light Verb Constructions: {<VB*><DT><\\w+>}",
             ]
         # Define the patterns for 2 and 3-word noun compounds (e.g., "Hausaufgaben", "Fußballplatz")
-        if "NC2" in mwe_types:
-            self.patterns["NC2"] = [
-                "NC2: {<NN|NNS><NN|NNS>}",
+        if "Noun Noun Compounds" in mwe_types:
+            self.patterns["Noun Noun Compounds"] = [
+                "Noun Noun Compounds: {<NN|NNS><NN|NNS>}",
+            ]
+        if "Noun Noun Noun Compounds" in mwe_types:
+            self.patterns["Noun Noun Noun Compounds"] = [
+                "Noun Noun Noun Compounds: {<NN|NNS><NN|NNS><NN|NNS>}",
             ]
-        if "NC3" in mwe_types:
-            self.patterns["NC3"] = [
-                "NC3: {<NN|NNS><NN|NNS><NN|NNS>}",
+        if "Adjective Noun Compounds" in mwe_types:
+            self.patterns["Adjective Noun Compounds"] = [
+                "Adjective Noun Compounds: {<JJ><NN|NNS>}",
             ]
-        if "ANC2" in mwe_types:
-            self.patterns["ANC2"] = [
-                "ANC2: {<JJ><NN|NNS>}",
+        if "Adjective Adjective Noun Compounds" in mwe_types:
+            self.patterns["Adjective Adjective Noun Compounds"] = [
+                "Adjective Adjective Noun Compounds: {<JJ><JJ><NN|NNS>}"
             ]
-        if "ANC3" in mwe_types:
-            self.patterns["ANC3"] = ["ANC3: {<JJ><JJ><NN|NNS>}"]
         # Define the patterns for verb particle constructions (e.g., "aufstehen", "zurückkommen")
-        if "VPC" in mwe_types:
-            self.patterns["VPC"] = [
-                "VPC: {<VB|VBP><RP>}",
+        if "Verb Particle Constructions" in mwe_types:
+            self.patterns["Verb Particle Constructions"] = [
+                "Verb Particle Constructions: {<VB|VBP><RP>}",
             ]