Semantic profiler and report generation module integration

Added the modules for generating the report based on the syntactic and semantic feature present in the code

Signed-off-by: Pankaj Thorat <thorat.pankaj9@gmail.com>

transforms/code/code_profiler/README.md

@@ -61,3 +61,5 @@ The high-level system design is as follows:
 For each new target language, the offline phase is utilized to create deterministic rules by harnessing the capabilities of LLMs and working with exemplar code samples from the target language. In this process, Workflow W1 facilitates the creation of rules around syntactic structures based on exemplar code samples, while Workflow W2 is used to establish semantic dimensions for profiling. Subsequently, we derive rules that connect syntactic constructs to the predefined semantic concepts. These rules are then stored in a rule database, ready to be employed during the online phase.
 
 In the online phase, the system dynamically generates profiling outputs for any incoming code snippets. This is achieved by extracting concepts from the snippets using the rules in the database and storing these extractions in a tabular format. The structured tabular format allows for generating additional concept columns, which are then utilized to create comprehensive profiling reports.
+
+

transforms/code/code_profiler/input/data_profiler_params.json

@@ -1,5 +1,6 @@
 {
     "input": "multi-package.parquet",
-    "contents": "Contents",
-    "language": "Language"
+    "dynamic_schema_mapping": "True",
+    "contents": "contents",
+    "language": "language"
 }

transforms/code/code_profiler/python/Makefile

@@ -35,7 +35,7 @@ setup:: .transforms.setup
 set-versions:
 	$(MAKE) TRANSFORM_PYTHON_VERSION=$(CODE_PROFILER_PYTHON_VERSION) TOML_VERSION=$(CODE_PROFILER_PYTHON_VERSION) .transforms.set-versions 
 
-build-dist:: .defaults.build-dist 
+build-dist:: .defaults.build-dist
 
 publish-dist:: .defaults.publish-dist
 
@@ -51,5 +51,5 @@ run-local-sample: .transforms.run-local-sample
 
 run-local-python-sample:
 	$(MAKE) RUN_FILE=code_profiler_local_python.py \
-	RUN_ARGS="--content 'Contents' --language 'Language'" \
+	RUN_ARGS="--content 'contents' --language 'language'" \
 	.transforms.run-local-python-sample

transforms/code/code_profiler/python/README.md

@@ -17,6 +17,14 @@ the options provided by
 the [python launcher](../../../../data-processing-lib/doc/python-launcher-options.md).
 
 ### Running the samples
+
+The code profiler can be run on mach-arm64 and x86_64 host architecture.
+Depending on your host architecture, please change the `RUNTIME_HOST_ARCH` in the Makefile.
+```
+# values possible mach-arm64, x86_64
+export RUNTIME_HOST_ARCH=x86_64
+```
+
 To run the samples, use the following `make` targets
 
 * `run-local-sample` - runs src/code_profiler_local.py

transforms/code/code_profiler/python/src/UAST_parser.py

@@ -228,8 +228,9 @@ def _add_user_defined(self, node):
         return
 
     # Traversing through the AST to create nodes recursively.
-    def _dfs(self, AST_node, parent) :
-        if (AST_node.type in self.rules) :
+    def _dfs(self, AST_node, parent):
+
+        if (AST_node.type in self.rules):
             ast_snippet = AST_node.text.decode("utf8")
             node_type = self.rules[AST_node.type]["uast_node_type"]
             exec_string = self.rules[AST_node.type]["extractor"]
@@ -269,3 +270,31 @@ def _extract(self, ast_snippet, node_type, exec_string):
             return self.grammar[node_type]["keyword"] + " " + self.extracted        
         except Exception as e:
             print(e)
+
+def uast_read(jsonstring):
+    """
+    Reads an input json string into UAST class object
+    """
+    uast = UAST()
+    if jsonstring is not None and jsonstring != 'null':
+        uast.load_from_json_string(jsonstring)
+        return uast
+    return None
+
+def extract_ccr(uast):
+    """
+    Calculates the code to comment ratio given an UAST object as input
+    """
+    if uast is not None:
+        total_comment_loc = 0
+        for node_idx in uast.nodes:
+            node = uast.get_node(node_idx)
+            if node.node_type == 'uast_comment':
+                total_comment_loc += node.metadata.get("loc_original_code", 0)
+            elif node.node_type == 'uast_root':
+                loc_snippet = node.metadata.get("loc_snippet", 0)
+        if total_comment_loc > 0:
+            return loc_snippet / total_comment_loc
+        else:
+            return None 
+    return None

transforms/code/code_profiler/python/src/code_profiler_local_python.py

@@ -24,8 +24,8 @@
 local_conf = {
     "input_folder": input_folder,
     "output_folder": output_folder,
-    "contents": "Contents",
-    "language": "Language"
+    "contents": "contents",
+    "language": "language"
 }
 params = {
     # Data access. Only required parameters are specified

transforms/code/code_profiler/python/src/code_profiler_transform.py

@@ -40,10 +40,8 @@
 
 short_name = "CodeProfiler"
 cli_prefix = f"{short_name}_"
-language_key = "language"
-contents_key = "contents"
-language_cli_param = f"{cli_prefix}{language_key}"
-contents_cli_param = f"{cli_prefix}{contents_key}"
+language = "language"
+contents = "contents"
 
 class CodeProfilerTransform(AbstractTableTransform):
     """
@@ -57,8 +55,11 @@ def __init__(self, config: dict[str, Any]):
 
         super().__init__(config)
 
-        self.contents = self.config.get("contents")
-        self.language = self.config.get("language")
+        self.contents = self.config.get("contents", "contents")
+        self.language = self.config.get("language", "language")        
+
+        if not isinstance(self.contents, str):
+           raise ValueError(f"'contents' should be a string, got {type(self.contents).__name__}")
 
         def ensure_tree_sitter_bindings():
             # Get the directory where the script is located
@@ -148,23 +149,46 @@ def ensure_tree_sitter_bindings():
         self.ikb_file = config.get("ikb_file", "semantic-ruleset/ikb_model.csv")
         self.null_libs_file = config.get("null_libs_file", "semantic-ruleset/null_libs.csv")
 
+        src_file_dir = os.path.abspath(os.path.dirname(__file__))
+        # Check if the file exists; if not, update the default path
+        if not os.path.exists(self.ikb_file):
+            print(f"File not found at {self.ikb_file}. Updating to '../semantic-ruleset/ikb_model.csv'")
+            self.ikb_file = os.path.join(src_file_dir, "semantic-ruleset/ikb_model.csv")
+        # Raise an error if the file still doesn't exist
+        if not os.path.exists(self.ikb_file):
+            raise FileNotFoundError(f"File not found: {self.ikb_file}")
+
+        # Check if the file exists; if not, update the default path
+        if not os.path.exists(self.null_libs_file):
+            print(f"File not found at {self.null_libs_file}. Updating to '../semantic-ruleset/null_libs.csv'")
+            self.null_libs_file = os.path.join(src_file_dir, "semantic-ruleset/null_libs.csv")
+        # Raise an error if the file still doesn't exist
+        if not os.path.exists(self.null_libs_file):
+            raise FileNotFoundError(f"File not found: {self.null_libs_file}")
+
         # Higher order semantic features
-        self.metrics_list = config.get("metrics_list", ["CCR"])
+        self.metrics_list = config.get("metrics_list", ["CCR", "code_snippet_len", "avg_fn_len_in_snippet"])
 
     def transform(self, table: pa.Table, file_name: str = None) -> tuple[list[pa.Table], dict[str, Any]]:
         """
         Extracts the syntactic constructs
         """
-        print("tranforming the the input dataframe")
+        print("Transforming the the input dataframe")
 
         ts_parser = TSParser()
         uast_parser = UASTParser()
 
         def get_uast_json(code, lang):
-            if lang in self.language_map:
-                ts_parser.set_language(self.language_map[lang])
-                uast_parser.set_language(self.uast_language_map[lang])
-                ast = ts_parser.parse(bytes(code, encoding= "utf8"))
+            # Create case-insensitive mappings
+            language_map_lower = {key.lower(): value for key, value in self.language_map.items()}
+            uast_language_map_lower = {key.lower(): value for key, value in self.uast_language_map.items()}
+
+            # Check for the lowercase version of `lang`
+            lang_lower = lang.lower()
+            if lang_lower in language_map_lower:
+                ts_parser.set_language(language_map_lower[lang_lower])
+                uast_parser.set_language(uast_language_map_lower[lang_lower])
+                ast = ts_parser.parse(bytes(code, encoding="utf8"))
                 uast = uast_parser.parse(ast, code)
                 return uast.get_json()
             return None
@@ -175,8 +199,12 @@ def extract_packages_from_uast(uast_json):
 
             try:
                 uast_data = json.loads(uast_json)
-                nodes = uast_data.get("nodes", {})
-
+                if uast_data is not None:
+                    nodes = uast_data.get("nodes", {})
+                else:
+                    nodes = {}
+                    print("Warning: uast_data is None. Check the data source or initialization process.")  
+                    return              
                 # Iterate through nodes to find nodes with type 'uast_package'
                 for node_id, node_data in nodes.items():
                     if node_data.get("node_type") == "uast_package":
@@ -189,13 +217,14 @@ def extract_packages_from_uast(uast_json):
 
             return ",".join(package_list)  # Return as a comma-separated string
 
-        def get_uast_parquet():
+        def get_uast_parquet(tmp_table):
             # df = pd.read_parquet(f'{db_path}/{filename}', 'pyarrow')
             # df = df.reindex(columns=all_columns)
 
             # Extract language and content arrays from the table using PyArrow
-            lang_array = table.column(self.language)
-            content_array = table.column(self.contents)
+            print(self.language)
+            lang_array = tmp_table.column(self.language)
+            content_array = tmp_table.column(self.contents)
             # Ensure both arrays have the same length
             assert len(lang_array) == len(content_array)
 
@@ -208,68 +237,74 @@ def get_uast_parquet():
             uast_column = pa.array(uasts)
             package_list_column = pa.array(package_lists)
 
-            table_with_uast = table.append_column('UAST', uast_column)
+            tmp_table_with_uast = tmp_table.append_column('UAST', uast_column)
             # Add the uast_package column
-            table_with_package_list = table_with_uast.append_column('UAST_Package_List', package_list_column)
+            table_with_package_list = tmp_table_with_uast.append_column('UAST_Package_List', package_list_column)
             return table_with_package_list
 
-        # Custom cleanup function
-        def safe_rmtree(path):
-            if os.path.exists(path):
-                shutil.rmtree(path)
-
-        table_with_uast = get_uast_parquet()
-        # report statistics
-        stats = {"source_documents": table.num_columns, "result_documents": table_with_uast.num_columns}
+        table_with_uast = get_uast_parquet(table)
+
+        try:
+            # Use an OS command to remove the folder and its contents
+            subprocess.run(["rm", "-rf", self.bindings_dir], check=True)
+            print(f"Successfully deleted: {self.bindings_dir}")
+        except subprocess.CalledProcessError as e:
+            print(f"Error deleting {self.bindings_dir}: {e}")
 
         ## Semantic profiling
-        table = table_with_uast
-        self.logger.debug(f"Semantic profiling of one table with {len(table)} rows")
+        self.logger.debug(f"Semantic profiling of one table with {len(table_with_uast)} rows")
 
         # Load Knowledge Base
+        print(self.ikb_file)
+        print(self.null_libs_file)
         ikb = knowledge_base(self.ikb_file, self.null_libs_file)
         ikb.load_ikb_trie()
 
         # Extract concept from IKB
-        libraries = table.column('UAST_Package_List').to_pylist()
-        language = table.column('Language').to_pylist()
+        libraries = table_with_uast.column('UAST_Package_List').to_pylist()
+        language = table_with_uast.column('language').to_pylist()
         concepts = [concept_extractor(lib, lang, ikb) for lib, lang in zip(libraries, language)]
 
         # Append concepts column to table and record unknown libraries
         new_col = pa.array(concepts)
-        table = table.append_column('Concepts', new_col)
+        table_with_uast = table_with_uast.append_column('Concepts', new_col)
         ikb.write_null_files()
 
         # Higher order syntactic profiler
-        self.logger.debug(f"Transforming one table with {len(table)} rows")
+        self.logger.debug(f"Transforming one table with {len(table_with_uast)} rows")
 
         if self.metrics_list is not None:
-            for metric in self.metrics_list:
-                if metric == "CCR":
-                    self.logger.info(f"Generating {metric} values")
-                    uasts = [uast_read(uast_json) for uast_json in table['UAST'].to_pylist()]
-                    ccrs = [extract_ccr(uast) for uast in uasts]
-                    new_table = table.append_column(metric, pa.array(ccrs))
-
-        self.logger.debug(f"Transformed one table with {len(new_table)} rows")
-        metadata = {"nfiles": 1, "nrows": len(new_table)}
-
+            uasts = [uast_read(uast_json) for uast_json in table_with_uast['UAST'].to_pylist()]
+            ccrs = []
+            code_snippet_len = []    
+            avg_fn_len_in_snippet = []                                       
+
+            for uast in uasts:
+                if "CCR" in self.metrics_list:
+                    ccrs.append(extract_ccr(uast))
+                if "code_snippet_len" in self.metrics_list:
+                    code_snippet_len.append(extract_code_snippet_length(uast))
+                if "avg_fn_len_in_snippet" in self.metrics_list:
+                    avg_fn_len_in_snippet.append(extract_code_avg_fn_len_in_snippet(uast))                    
+
+            if "CCR" in self.metrics_list:
+                table_with_uast = table_with_uast.append_column("CCR", pa.array(ccrs))
+            if "code_snippet_len" in self.metrics_list:
+                table_with_uast = table_with_uast.append_column("code_snippet_len", pa.array(code_snippet_len))
+            if "avg_fn_len_in_snippet" in self.metrics_list:
+                table_with_uast = table_with_uast.append_column("avg_fn_len_in_snippet", pa.array(avg_fn_len_in_snippet))
+
+        self.logger.debug(f"Transformed one table with {len(table_with_uast)} rows")
+        metadata = {"nfiles": 1, "nrows": len(table_with_uast)}
         # Report generation
-        if 'UAST' in new_table.schema.names and 'Concepts' in new_table.schema.names:
-            generate_report(new_table,self.metrics_list)
+        if 'UAST' in table_with_uast.schema.names and 'Concepts' in table_with_uast.schema.names:
+            generate_report(table_with_uast,self.metrics_list)
 
         # Add some sample metadata.
-        self.logger.debug(f"Transformed one table with {len(table)} rows")
-        stats["nrows"] =  len(table)
-
-        try:
-            # Use an OS command to remove the folder and its contents
-            subprocess.run(["rm", "-rf", self.bindings_dir], check=True)
-            print(f"Successfully deleted: {self.bindings_dir}")
-        except subprocess.CalledProcessError as e:
-            print(f"Error deleting {self.bindings_dir}: {e}")
-
-        return [table], stats
+        self.logger.debug(f"Transformed one table with {len(table_with_uast)} rows")
+                # report statistics
+        stats = {"source_documents": table.num_columns, "result_documents": table_with_uast.num_columns}
+        return [table_with_uast], stats
 
 class CodeProfilerTransformConfiguration(TransformConfiguration):
     def __init__(self, transform_class: type[AbstractBinaryTransform] = CodeProfilerTransform):
@@ -279,15 +314,15 @@ def __init__(self, transform_class: type[AbstractBinaryTransform] = CodeProfiler
             )
     def add_input_params(self, parser: ArgumentParser) -> None:
         parser.add_argument(
-            f"--{language_cli_param}",
+            f"--{language}",
             type=str,
-            default="Language",
+            default="language",
             help="Column name that denotes the programming language",
         )
         parser.add_argument(
-            f"--{contents_cli_param}",
+            f"--{contents}",
             type=str,
-            default="Contents",
+            default="contents",
             help="Column name that contains code snippets",
         )