Small modifications due to weird changes in output in SWUM

SCANL · Nov 27, 2024 · a383c78 · a383c78
1 parent 391a437
commit a383c78
Show file tree

Hide file tree

Showing 5 changed files with 8 additions and 6 deletions.
diff --git a/HTTPRequest b/HTTPRequest
diff --git a/SWUM b/SWUM
diff --git a/ensemble_tagger_implementation/ensemble_functions.py b/ensemble_tagger_implementation/ensemble_functions.py
@@ -26,6 +26,7 @@ def Process_identifier_with_swum(identifier_data, context_of_identifier):
     split_identifier_name = '_'.join(ronin.split(identifier_type_and_name[1]))
     if Get_identifier_context(context_of_identifier) != CODE_CONTEXT.FUNCTION:
         swum_string = "{identifier_type} {identifier_name}".format(identifier_name = split_identifier_name, identifier_type = identifier_type_and_name[0])
+        print(['java', '-jar', '../SWUM/SWUM_POS/swum.jar', swum_string, '2', 'true'])
         swum_process = subprocess.Popen(['java', '-jar', '../SWUM/SWUM_POS/swum.jar', swum_string, '2', 'true'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
     else:
         split_identifier_name = split_identifier_name+'('+identifier_data.split('(')[1]

diff --git a/ensemble_tagger_implementation/preprocess_identifiers.py b/ensemble_tagger_implementation/preprocess_identifiers.py
@@ -20,13 +20,14 @@ def Split_raw_identifier(identifier_data):
     return identifier_type_and_name
 
 def Parse_swum(swum_output, split_identifier_name):
-    code_context = swum_output.split('#')
+    code_context = swum_output.split(':')
+    print(code_context)
     raw_grammar_pattern = grammar_pattern = identifier = []
     if code_context[0] == 'FIELD':
-        identifier = code_context[1].split('-')[1].split()
+        identifier = code_context[2].split('-')[1].split()
         raw_grammar_pattern = re.findall('([A-Z]+)', ' '.join(identifier))
     else:
-        identifier = code_context[1].split('@')[1].split('|')
+        identifier = code_context[3].split('|')
         raw_grammar_pattern = re.findall('([A-Z]+)', ' '.join(identifier))
 
     for pos in raw_grammar_pattern:

diff --git a/srcSAXEventDispatch b/srcSAXEventDispatch
+36 −0		.circleci/config.yml
+30 −13		.gitignore
+3 −0		.gitmodules
+19 −0		CMakeLists.txt
+36 −24		README.md
+61 −10		azure-pipelines.yml
+3 −7		example/Makefile
+28 −0		example/example.sln
+9 −5		example/example.vcxproj
+16 −42		example/example.xcodeproj/project.pbxproj
+7 −0		example/example.xcodeproj/project.xcworkspace/contents.xcworkspacedata
+104 −0		example/main.cpp
+1 −0		external/Catch2
+1,038 −389		include/HTTPRequest.hpp
+14 −0		sonar-project.properties
+0 −85		test/main.cpp
+21 −0		tests/CMakeLists.txt
+28 −0		tests/Makefile
+95 −0		tests/encoding.cpp
+2 −0		tests/main.cpp
+484 −0		tests/parsing.cpp
+1 −1		tests/tests.sln
+167 −0		tests/tests.vcxproj
+320 −0		tests/tests.xcodeproj/project.pbxproj
+1 −1		tests/tests.xcodeproj/project.xcworkspace/contents.xcworkspacedata
+2 −1		SWUM_POS/META-INF/MANIFEST.MF
+5 −53		SWUM_POS/data/swum/eval.txt
+0 −13		SWUM_POS/data/swum/eval_fields.txt
+1 −3		SWUM_POS/src/edu/udel/nlpa/swum/nodes/IEquivalenceNode.java
+8 −13		SWUM_POS/src/edu/udel/nlpa/swum/nodes/IMethodDecl.java
+5 −27		SWUM_POS/src/edu/udel/nlpa/swum/research/SWUMAccuracyHarness.java
+1 −1		SWUM_POS/src/edu/udel/nlpa/swum/rules/unigram/EventHandlerRule.java
+1 −1		SWUM_POS/src/edu/udel/nlpa/swum/rules/unigram/LeadingPrepositionRule.java
+1 −1		SWUM_POS/src/edu/udel/nlpa/swum/rules/unigram/NounPhraseRule.java
+1 −1		SWUM_POS/src/edu/udel/nlpa/swum/rules/unigram/UnigramMethodRule.java
+ −		SWUM_POS/swum.jar