Merge pull request #41 from OPPIDA/feat/sarif-parser

Author: nolliv22

.pre-commit-config.yaml

@@ -27,9 +27,4 @@ repos:
     hooks:
       - id: conventional-pre-commit
         stages: [commit-msg]
-        args: []
-  
-  - repo: https://github.com/google/osv-scanner
-    rev: v2.3.1
-    hooks:
-      - id: osv-scanner
+        args: []

README.md

@@ -23,10 +23,11 @@ A framework for code security that provides abstractions for static analysis too
 **CodeSecTools** is a collection of scripts and wrappers that abstract external resources (such as SAST tools, datasets, and codebases), providing standardized interfaces to help them interact easily.
 
 <div align="center">
-  <img src="docs/assets/overview.svg" alt="CodeSecTools Overview" style="width: 75%; height: auto;" />
+  <img src="docs/assets/workflow.svg" alt="Workflow" style="width: 85%; height: auto;" />
+  <img src="docs/assets/workflow_example.svg" alt="Workflow" style="width: 85%; height: auto;" />
 </div>
 
-For step-by-step instructions on installation, configuration, and basic usage, please refer to the [quick start guide](https://oppida.github.io/CodeSecTools/home/quick_start_guide.html).
+For step-by-step instructions on installation, configuration, and basic usage, please refer to the [**quick start guide**](https://oppida.github.io/CodeSecTools/home/quick_start_guide.html).
 
 For more details on the design and integration of SAST tools and datasets in CodeSecTools, please refer to the [documentation](https://oppida.github.io/CodeSecTools). 
 
@@ -47,9 +48,9 @@ For more details on the design and integration of SAST tools and datasets in Cod
 
 |SAST Tool|Languages|Maintained|Included in Docker|Continuous Testing|Last Test Date|
 |:---:|:---:|:---:|:---:|:---:|:---:|
-|Coverity|Java|⚠️<br>(Deprioritized)|❌|❌<br>(Proprietary)|October 2025|
+|Coverity|C/C++, Java|✅|❌|❌<br>(Proprietary)|February 2026|
 |Semgrep Community Edition|C/C++, Java|✅|✅|✅|[Latest PR](https://github.com/OPPIDA/CodeSecTools/actions/workflows/ci.yaml)|
-|Snyk Code|C/C++, Java|✅|❌|❌<br>(Rate limited)|November 2025|
+|Snyk Code|C/C++, Java|✅|❌|❌<br>(Rate limited)|February 2026|
 |Bearer|Java|✅|✅|✅|[Latest PR](https://github.com/OPPIDA/CodeSecTools/actions/workflows/ci.yaml)|
 |SpotBugs|Java|✅|✅|✅|[Latest PR](https://github.com/OPPIDA/CodeSecTools/actions/workflows/ci.yaml)|
 |Cppcheck|C/C++|✅|✅|✅|[Latest PR](https://github.com/OPPIDA/CodeSecTools/actions/workflows/ci.yaml)|
@@ -97,10 +98,10 @@ Mount necessary directories if you want to include:
 - a target (`-v ./myproject:/home/codesectools/myproject`)
 - existing CodeSecTools data (`-v $HOME/.codesectools:/home/codesectools/.codesectools`) 
 
-A better way is to use the CLI:
+A simpler way is to use the CLI:
 
 ```bash
-$ cstools -d docker --help
+$ cstools docker --help
                                                                                                                                                                    
  Usage: cstools docker [OPTIONS]                                                                                                                                   
                                                                                                                                                                    

codesectools/datasets/core/dataset.py

@@ -641,7 +641,7 @@ def validate(self, analysis_results: list[AnalysisResult]) -> GitRepoDatasetData
                 "fp_cwes": fp_cwes,
                 "fn_cwes": fn_cwes,
                 "time": analysis_result.time,
-                "loc": analysis_result.loc,
+                "lines_of_codes": analysis_result.lines_of_codes,
             }
             validated_repos.append(result)
 

codesectools/sasts/all/cli.py

@@ -177,7 +177,7 @@ def list_() -> None:
                 "Dataset",
                 ", ".join(
                     f"[b]{sast.name}[/b]"
-                    for sast in all_sast.sasts
+                    for sast in all_sast.any_sasts
                     if dataset_full_name in sast.list_results(dataset=True)
                 ),
             )
@@ -187,7 +187,7 @@ def list_() -> None:
                 "Project",
                 ", ".join(
                     f"[b]{sast.name}[/b]"
-                    for sast in all_sast.sasts
+                    for sast in all_sast.any_sasts
                     if project in sast.list_results(project=True)
                 ),
             )

codesectools/sasts/all/graphics.py

@@ -15,7 +15,7 @@ class Graphics(CoreGraphics):
         project_name (str): The name of the project being visualized.
         all_sast (AllSAST): The instance managing all SAST tools.
         output_dir (Path): The directory containing the aggregated results.
-        color_mapping (dict): A dictionary mapping SAST tool names to colors.
+        sast_color (dict): A dictionary mapping SAST tool names to colors.
         sast_names (list[str]): A list of names of the SAST tools involved in the analysis.
         plot_functions (list): A list of methods responsible for generating plots.
 
@@ -26,12 +26,12 @@ def __init__(self, project_name: str) -> None:
         self.project_name = project_name
         self.all_sast = AllSAST()
         self.output_dir = self.all_sast.output_dir / project_name
-        self.color_mapping = {}
+        self.sast_color = {}
         cmap = plt.get_cmap("Set2")
         self.sast_names = []
-        for i, sast in enumerate(self.all_sast.sasts):
+        for i, sast in enumerate(self.all_sast.partial_sasts):
             if self.project_name in sast.list_results(project=True):
-                self.color_mapping[sast.name] = cmap(i)
+                self.sast_color[sast.name] = cmap(i)
                 self.sast_names.append(sast.name)
         self.plot_functions = []
 
@@ -49,11 +49,11 @@ def __init__(self, project_name: str) -> None:
         )
 
     def plot_overview(self) -> Figure:
-        """Generate an overview plot with stats by files, SAST tools, and categories."""
+        """Generate an overview plot with stats by files, SAST tools, and levels."""
         fig, (ax1, ax2, ax3) = plt.subplots(1, 3, layout="constrained")
         by_files = self.result.stats_by_files()
         by_sasts = self.result.stats_by_sasts()
-        by_categories = self.result.stats_by_categories()
+        by_levels = self.result.stats_by_levels()
 
         # Plot by files
         X_files, Y_files = [], []
@@ -64,10 +64,10 @@ def plot_overview(self) -> Figure:
             X_files.append(shorten_path(k))
             Y_files.append(v["count"])
 
-            COLORS_COUNT = {v: 0 for k, v in self.color_mapping.items()}
+            COLORS_COUNT = {v: 0 for k, v in self.sast_color.items()}
 
-            for sast in v["sasts"]:
-                color = self.color_mapping[sast]
+            for sast_name in v["sasts"]:
+                color = self.sast_color[sast_name]
                 COLORS_COUNT[color] += 1
 
             bars = []
@@ -95,41 +95,41 @@ def plot_overview(self) -> Figure:
         ax2.bar(
             X_sasts,
             Y_checkers,
-            color=[self.color_mapping[s] for s in X_sasts],
+            color=[self.sast_color[s] for s in X_sasts],
         )
         ax2.set_xticks(X_sasts, X_sasts, rotation=45, ha="right")
         ax2.set_title("Stats by SAST tools")
 
-        # Plot by categories
-        X_categories = ["HIGH", "MEDIUM", "LOW"]
-        for category in X_categories:
-            if not by_categories.get(category):
+        # Plot by levels
+        X_levels = ["error", "warning", "note", "none"]
+        for level in X_levels:
+            if not by_levels.get(level):
                 continue
 
-            sast_counts = by_categories[category]["sast_counts"]
+            sast_counts = by_levels[level]["sast_counts"]
 
             bars = []
             current_height = 0
             for sast_name, count in sorted(sast_counts.items()):
-                color = self.color_mapping[sast_name]
+                color = self.sast_color[sast_name]
                 height = count
                 if height > 0:
-                    bars.append((category, current_height + height, color))
+                    bars.append((level, current_height + height, color))
                     current_height += height
 
-            for category_name, height, color in bars[::-1]:
-                ax3.bar(category_name, height, color=color)
+            for level_name, height, color in bars[::-1]:
+                ax3.bar(level_name, height, color=color)
 
-        ax3.set_xticks(X_categories, X_categories, rotation=45, ha="right")
-        ax3.set_title("Stats by categories")
+        ax3.set_xticks(X_levels, X_levels, rotation=45, ha="right")
+        ax3.set_title("Stats by levels")
 
         fig.suptitle(
             f"Project {self.project_name}, {len(self.result.files)} files analyzed, {len(self.result.defects)} defects raised",
             fontsize=16,
         )
-        labels = list(self.color_mapping.keys())
+        labels = list(self.sast_color.keys())
         handles = [
-            plt.Rectangle((0, 0), 1, 1, color=self.color_mapping[label])
+            plt.Rectangle((0, 0), 1, 1, color=self.sast_color[label])
             for label in labels
         ]
         plt.legend(handles, labels)
@@ -160,7 +160,7 @@ def plot_top_cwes(self) -> Figure:
                 sast_counts,
                 bottom=bottoms,
                 label=sast_name,
-                color=self.color_mapping.get(sast_name),
+                color=self.sast_color.get(sast_name),
             )
             bottoms = [b + c for b, c in zip(bottoms, sast_counts, strict=False)]
 

codesectools/sasts/all/parser.py

@@ -14,7 +14,13 @@ class AllSASTAnalysisResult:
     """Represent the aggregated results from multiple SAST analyses on a single project."""
 
     def __init__(self, name: str, analysis_results: dict[str, AnalysisResult]) -> None:
-        """Initialize an AllSASTAnalysisResult instance."""
+        """Initialize an AllSASTAnalysisResult instance.
+
+        Args:
+            name: The name of the project.
+            analysis_results: A dictionary of analysis results from various SAST tools.
+
+        """
         self.name = name
         self.source_path = None
         self.analysis_results = analysis_results
@@ -34,22 +40,6 @@ def __init__(self, name: str, analysis_results: dict[str, AnalysisResult]) -> No
             self.files |= set(analysis_result.files)
             self.defects += analysis_result.defects
 
-        self.category_mapping = {}
-        for sast_name in self.sast_names:
-            sast = SASTS_ALL[sast_name]["sast"]
-            for category_name, color in sast.color_mapping.items():
-                if color.lower() == "red":
-                    self.category_mapping[(sast_name, category_name)] = "HIGH"
-                elif color.lower() == "orange":
-                    self.category_mapping[(sast_name, category_name)] = "MEDIUM"
-                elif color.lower() == "yellow":
-                    self.category_mapping[(sast_name, category_name)] = "LOW"
-
-        for defect in self.defects:
-            defect.category = self.category_mapping.get(
-                (defect.sast, defect.category), "LOW"
-            )
-
     def __repr__(self) -> str:
         """Return a developer-friendly string representation of the aggregated result."""
         return f"""{self.__class__.__name__}(
@@ -78,9 +68,9 @@ def stats_by_files(self) -> dict:
         stats = {}
         for defect in self.defects:
             if defect.filepath_str not in stats.keys():
-                stats[defect.filepath_str] = {"count": 1, "sasts": [defect.sast]}
+                stats[defect.filepath_str] = {"count": 1, "sasts": [defect.sast_name]}
             else:
-                stats[defect.filepath_str]["sasts"].append(defect.sast)
+                stats[defect.filepath_str]["sasts"].append(defect.sast_name)
                 stats[defect.filepath_str]["count"] += 1
 
         return stats
@@ -89,23 +79,23 @@ def stats_by_sasts(self) -> dict:
         """Calculate statistics on defects, grouped by SAST tool."""
         stats = {}
         for defect in self.defects:
-            if defect.sast not in stats.keys():
-                stats[defect.sast] = {"count": 1}
+            if defect.sast_name not in stats.keys():
+                stats[defect.sast_name] = {"count": 1}
             else:
-                stats[defect.sast]["count"] += 1
+                stats[defect.sast_name]["count"] += 1
 
         return stats
 
-    def stats_by_categories(self) -> dict:
-        """Calculate statistics on defects, grouped by severity category."""
+    def stats_by_levels(self) -> dict:
+        """Calculate statistics on defects, grouped by severity level."""
         stats = {}
         for defect in self.defects:
-            if defect.category not in stats.keys():
-                stats[defect.category] = {"count": 0, "sast_counts": {}}
+            if defect.level not in stats.keys():
+                stats[defect.level] = {"count": 0, "sast_counts": {}}
 
-            stats[defect.category]["count"] += 1
-            sast_counts = stats[defect.category]["sast_counts"]
-            sast_counts[defect.sast] = sast_counts.get(defect.sast, 0) + 1
+            stats[defect.level]["count"] += 1
+            sast_counts = stats[defect.level]["sast_counts"]
+            sast_counts[defect.sast_name] = sast_counts.get(defect.sast_name, 0) + 1
         return stats
 
     def stats_by_cwes(self) -> dict:
@@ -119,14 +109,14 @@ def stats_by_cwes(self) -> dict:
                 stats[defect.cwe] = {
                     "count": 1,
                     "files": [defect.filepath_str],
-                    "sast_counts": {defect.sast: 1},
+                    "sast_counts": {defect.sast_name: 1},
                 }
             else:
                 stats[defect.cwe]["count"] += 1
                 if defect.filepath_str not in stats[defect.cwe]["files"]:
                     stats[defect.cwe]["files"].append(defect.filepath_str)
-                stats[defect.cwe]["sast_counts"][defect.sast] = (
-                    stats[defect.cwe]["sast_counts"].get(defect.sast, 0) + 1
+                stats[defect.cwe]["sast_counts"][defect.sast_name] = (
+                    stats[defect.cwe]["sast_counts"].get(defect.sast_name, 0) + 1
                 )
         return stats
 
@@ -144,7 +134,7 @@ def stats_by_scores(self) -> dict:
 
             defects_same_cwe = 0
             for cwe in defects_cwes:
-                cwes_sasts = {d.sast for d in defects if d.cwe == cwe}
+                cwes_sasts = {d.sast_name for d in defects if d.cwe == cwe}
                 if set(self.sast_names) == cwes_sasts:
                     defects_same_cwe += 1
                 else:
@@ -162,7 +152,7 @@ def stats_by_scores(self) -> dict:
             defects_same_location = 0
             defects_same_location_same_cwe = 0
             for _, defects_ in defect_locations.items():
-                if set(defect.sast for defect in defects_) == set(self.sast_names):
+                if set(defect.sast_name for defect in defects_) == set(self.sast_names):
                     defects_same_location += 1
                     defects_by_cwe = {}
                     for defect in defects_:
@@ -171,14 +161,14 @@ def stats_by_scores(self) -> dict:
                         defects_by_cwe[defect.cwe].append(defect)
 
                     for _, defects_ in defects_by_cwe.items():
-                        if set(defect.sast for defect in defects_) == set(
+                        if set(defect.sast_name for defect in defects_) == set(
                             self.sast_names
                         ):
                             defects_same_location_same_cwe += 1
                         else:
                             defects_same_location_same_cwe += (
                                 len(
-                                    set(defect.sast for defect in defects_)
+                                    set(defect.sast_name for defect in defects_)
                                     & set(self.sast_names)
                                 )
                                 - 1
@@ -224,7 +214,7 @@ def prepare_report_data(self) -> dict:
                 for group in group_successive(defect.lines):
                     start, end = group[0], group[-1]
                     locations.append(
-                        (defect.sast, defect.cwe, defect.message, (start, end))
+                        (defect.sast_name, defect.cwe, defect.message, (start, end))
                     )
 
             report["files"][defect_file] = {
@@ -239,7 +229,7 @@ def prepare_report_data(self) -> dict:
             k: v
             for k, v in sorted(
                 report["files"].items(),
-                key=lambda item: (sum(v for v in item[1]["score"].values())),
+                key=lambda item: sum(v for v in item[1]["score"].values()),
                 reverse=True,
             )
         }

codesectools/sasts/all/report.py

@@ -139,7 +139,7 @@ def generate_single_defect(self, file_data: dict) -> tuple:
                         else "None"
                     )
                     rows.append(
-                        (start, shortcut, defect.sast, cwe_link, defect.message)
+                        (start, shortcut, defect.sast_name, cwe_link, defect.message)
                     )
             else:
                 cwe_link = (

codesectools/sasts/all/sast.py

@@ -19,15 +19,24 @@ class AllSAST:
     def __init__(self) -> None:
         """Initialize the AllSAST instance."""
         self.output_dir = USER_OUTPUT_DIR / self.name
-        self.sasts: list[SAST] = []
+        self.full_sasts: list[SAST] = []
+        self.partial_sasts: list[SAST] = []
+        self.any_sasts: list[SAST] = []
         for _, sast_data in SASTS_ALL.items():
             if sast_data["status"] == "full":
-                self.sasts.append(sast_data["sast"]())
+                self.full_sasts.append(sast_data["sast"]())
+                self.partial_sasts.append(sast_data["sast"]())
+                self.any_sasts.append(sast_data["sast"]())
+            elif sast_data["status"] == "partial":
+                self.partial_sasts.append(sast_data["sast"]())
+                self.any_sasts.append(sast_data["sast"]())
+            else:
+                self.any_sasts.append(sast_data["sast"]())
 
         self.sasts_by_lang = {}
         self.sasts_by_dataset = {}
 
-        for sast in self.sasts:
+        for sast in self.full_sasts:
             for lang in sast.supported_languages:
                 if self.sasts_by_lang.get(lang):
                     self.sasts_by_lang[lang].append(sast)
@@ -45,7 +54,7 @@ def list_results(
     ) -> set[str]:
         """List the names of analysis results common to all enabled SAST tools."""
         output_dirs = set()
-        for sast in self.sasts:
+        for sast in self.partial_sasts:
             if not output_dirs:
                 output_dirs = set(
                     sast.list_results(project=project, dataset=dataset, limit=limit)