update

data/generate_bpf_commits.py

@@ -29,7 +29,7 @@ def get_commit_details(commit_id):
 # Function to write commit details into a CSV
 def write_to_csv(data, csv_file):
     with open(csv_file, mode='w', newline='') as file:
-        writer = csv.writer(file)
+        writer = csv.writer(file, quoting=csv.QUOTE_ALL) 
         writer.writerow(["commit_id", "commit_hash", "author_name", "author_email", "author_date",
                          "committer_name", "committer_email", "commit_date_timestamp", "tree_hash", 
                          "parent_hashes", "commit_message", "refs"])

survey/commit_survey.yml

@@ -1,70 +1,84 @@
 title: "Commit Classification Survey"
 description: "A survey about the type, use cases and summary of commit in Linux eBPF."
 questions:
-  - id: summary
-    type: fill_in
-    question: "Please provide a summary of the commit in one short sentence not longer than 30 words. Only output one sentence."
-    required: true
+- id: summary
+  type: fill_in
+  question: "Please provide a summary of the commit in one short sentence not longer than 30 words. Only output one sentence."
+  required: true
 
-  - id: keywords
-    type: fill_in
-    question: "Please extract no more than 3 keywords from the commit. Only output 3 keywords, without any special characters."
-    required: true
+- id: keywords
+  type: fill_in
+  question: "Please extract no more than 3 keywords from the commit. Only output 3 keywords without any special characters."
+  required: true
 
-  - id: commit_classification
-    type: single_choice
-    question: "What may be the main type of the commit?"
-    choices:
-      - value: It's a bug fix.
-      - value: It's a new feature.
-      - value: It's a performance optimization.
-      - value: It's a cleanup or refactoring in the code.
-      - value: It's a documentation change or typo fix.
-      - value: It's a test case or test infrastructure change.
-      - value: It's a build system or CI/CD change.
-      - value: It's a security fix.
-      - value: It's other type of commit.
+- id: commit_classification
+  type: single_choice
+  question: "What may be the main type of the commit?"
+  choices:
+    - value: It's a bug fix.
+    - value: It's a new feature.
+    - value: It's a performance optimization.
+    - value: It's a cleanup or refactoring in the code.
+    - value: It's a documentation change or typo fix.
+    - value: It's a test case or test infrastructure change.
+    - value: It's a build system or CI/CD change.
+    - value: It's a security fix.
+    - value: It's other type of commit.
 
-  - id: commit_complexity
-    type: single_choice
-    question: "What is the estimated complexity of implementing this commit?"
-    choices:
-      - value: Simple, can be used without much configuration. For example, a simple helper function.
-      - value: Moderate, requires some setup or understanding of the system. For example, a new map type or a new link type.
-      - value: Complex, needs expert knowledge or significant changes to existing systems. Like adding a completely new subsystem support or a completely new program type don't exist before.
+- id: commit_complexity
+  type: single_choice
+  question: "What is the estimated complexity of implementing this commit?"
+  choices:
+    - value: Simple can be used without much configuration. For example a simple helper function.
+    - value: Moderate requires some setup or understanding of the system. For example a new map type or a new link type.
+    - value: Complex needs expert knowledge or significant changes to existing systems. Like adding a completely new subsystem support or a completely new program type don't exist before.
+    - value: It's a merge commit not related to any of the above.
 
-  - id: Major related component
-    type: single_choice
-    question: "What major component that the commit is related to?"
-    choices:
-      - value: The eBPF verifier
-      - value: The JIT compiler
-      - value: The helper and kfuncs
-      - value: The syscall interface
-      - value: The eBPF maps
-      - value: The libbpf library
-      - value: The bpftool utility
-      - value: The test cases and makefiles
-      - value: The attach events and bpf link. e.g. perf events, tracepoints, etc.
-      - value: The BPF Type Format (BTF)
-      - value: Other component related to eBPF but not listed above.
-      - value: It's not related to any of the above, it's not related to bpf subsystem in Linux kernel, may be wrong data.
+- id: Major related implementation component
+  type: single_choice
+  question: "What major implementation component that the commit is modified on?"
+  choices:
+    - value: The eBPF verifier
+    - value: The eBPF JIT compiler for different architectures
+    - value: The helper and kfuncs
+    - value: The syscall interface
+    - value: The eBPF maps
+    - value: The libbpf library
+    - value: The bpftool utility
+    - value: The test cases and makefiles
+    - value: The attach events e.g. perf events tracepoints network HID LSM etc.
+    - value: The BPF Type Format (BTF)
+    - value: Other component related to eBPF but not listed above.
+    - value: It's a merge commit including changes to multiple implementation components.
+    - value: It's not related to any of the above it's not related to bpf subsystem in Linux kernel may be wrong data.
 
-  - id: program_types_related
-    type: multiple_choice
-    question: "What eBPF program(s) may the commit relate to and designed for?"
-    choices:
-      - value: xdp like programs
-      - value: socket like programs
-      - value: tc/netfilter like programs
-      - value: tracepoints like programs
-      - value: kprobe/uprobe/ftrace like programs
-      - value: profile like programs
-      - value: LSM like programs
-      - value: cgroup like programs
-      - value: HID driver like programs
-      - value: scheduler like programs
-      - value: It improves the overall eBPF infrastructure (e.g., verifier, runtime, etc.).
-      - value: It's an experimental feature that doesn't fit into existing categories.
-      - value: It's not related to any of the above.
-      - value: other
+- id: Major related logic component
+  type: single_choice
+  question: "What major logic component that the commit is related to? logic component is different to implementation component."
+  choices:
+    - value: A eBPF Instruction Logic for adding fixing or updating the way eBPF instructions are interpreted validated or executed by the eBPF virtual machine in the kernel. e.g. add fix optimized eBPF instructions.
+    - value: A eBPF Program Logic related to different eBPF program types (e.g. XDP tc kprobes) and how the kernel manages attaches and runs these programs. e.g. add eBPF program type fix things related to eBPF program.
+    - value: Runtime features Logic related to eBPF helper or kfunc functions which provide access to kernel resources from eBPF programs (e.g. reading from maps manipulating packet data). e.g. helpers kfuncs etc.
+    - value: eBPF events Logic for handling events that trigger eBPF programs such as network packet reception system calls or tracing events. e.g. add new event fix things related to XDP HID perf events tracepoint etc.
+    - value: Control Plane interface Logic for userspace control. This involves adding fixing or modifying syscalls that are part of the control plane interface for eBPF allowing userspace programs to interact with eBPF features in the kernel.
+    - value: Maps Logic for how eBPF maps (data structures shared between kernel and user space) are created accessed and managed.
+    - value: It's a merge commit including changes to multiple logic components.
+
+- id: usecases_or_events
+  type: multiple_choice
+  question: "What eBPF usecases/events may the commit relate to and designed for?"
+  choices:
+    - value: xdp type programs
+    - value: socket type programs
+    - value: tc/netfilter type programs
+    - value: tracepoints type programs
+    - value: kprobe/uprobe/ftrace type programs
+    - value: profile type programs
+    - value: LSM type programs
+    - value: cgroup type programs
+    - value: HID driver type programs
+    - value: scheduler type programs
+    - value: It improves the overall eBPF infrastructure (e.g. verifier runtime etc.)
+    - value: It's an experimental feature that doesn't fit into existing categories.
+    - value: It's not related to any of the above.
+    - value: other

survey/feature_survey.yml

@@ -28,9 +28,9 @@ questions:
     type: single_choice
     question: "What is the estimated complexity of implementing this commit?"
     choices:
-      - value: Simple, can be used without much configuration. For example, a simple helper function.
-      - value: Moderate, requires some setup or understanding of the system. For example, a new map type or a new link type.
-      - value: Complex, needs expert knowledge or significant changes to existing systems. Like adding a completely new subsystem support or a completely new program type don't exist before.
+      - value: Simple and can be used without much configuration. For example, a simple helper function.
+      - value: Moderate and requires some setup or understanding of the system. For example, a new map type or a new link type.
+      - value: Complex and needs expert knowledge or significant changes to existing systems. Like adding a completely new subsystem support or a completely new program type don't exist before.
       - value: It's a merge commit, not related to any of the above.
 
   - id: program_types_related

survey/survey_struct.py

@@ -126,26 +126,28 @@ def send_openai_request(api_url, headers, payload):
     else:
         raise Exception(f"API call failed: {response.status_code} {response.text}")
 
-# Function to save the response to the CSV file, combining it with commit data
 def save_response_to_csv(content, csv_filename, commit_data):
     # Define the fieldnames (commit fields + survey response fields)
     fieldnames = list(commit_data.keys()) + list(content.keys())
 
     # Check if the file exists to determine if we need to write headers
     file_exists = os.path.isfile(csv_filename)
 
-    with open(csv_filename, mode="a", newline="") as file:
-        writer = csv.DictWriter(file, fieldnames=fieldnames)
-
-        if not file_exists:
-            # Write header if the file doesn't exist
-            writer.writeheader()
-
-        # Combine commit data with survey response content
-        combined_data = {**commit_data, **content}
-
-        # Write the row to the CSV
-        writer.writerow(combined_data)
+    try:
+        with open(csv_filename, mode="a", newline="") as file:
+            writer = csv.DictWriter(file, fieldnames=fieldnames, quoting=csv.QUOTE_ALL) 
+
+            if not file_exists:
+                # Write header if the file doesn't exist
+                writer.writeheader()
+
+            # Combine commit data with survey response content
+            combined_data = {**commit_data, **content}
+
+            # Write the row to the CSV
+            writer.writerow(combined_data)
+    except Exception as e:
+        print(f"Error writing to CSV: {e}")
 
 # Function to read commit data from the CSV file
 def read_commit_data(commit_csv_file):