OpenAirframes 1.0

src/adsb/combine_chunks_to_csv.py

@@ -27,7 +27,7 @@ from src.adsb.compress_adsb_to_aircraft_data import compress_multi_icao_df, COLU
 
 
 DEFAULT_CHUNK_DIR = os.path.join(OUTPUT_DIR, "adsb_chunks")
-FINAL_OUTPUT_DIR = "./data/planequery_aircraft"
+FINAL_OUTPUT_DIR = "./data/openairframes"
 os.makedirs(FINAL_OUTPUT_DIR, exist_ok=True)
 
 
@@ -36,8 +36,13 @@ def get_target_day() -> datetime:
     return datetime.utcnow() - timedelta(days=1)
 
 
-def process_single_chunk(chunk_path: str) -> pl.DataFrame:
-    """Load and compress a single chunk parquet file."""
+def process_single_chunk(chunk_path: str, delete_after_load: bool = False) -> pl.DataFrame:
+    """Load and compress a single chunk parquet file.
+    
+    Args:
+        chunk_path: Path to parquet file
+        delete_after_load: If True, delete the parquet file after loading to free disk space
+    """
     print(f"Processing {os.path.basename(chunk_path)}... | {get_resource_usage()}")
     
     # Load chunk - only columns we need
@@ -45,6 +50,14 @@ def process_single_chunk(chunk_path: str) -> pl.DataFrame:
     df = pl.read_parquet(chunk_path, columns=needed_columns)
     print(f"  Loaded {len(df)} rows")
     
+    # Delete file immediately after loading to free disk space
+    if delete_after_load:
+        try:
+            os.remove(chunk_path)
+            print(f"  Deleted {chunk_path} to free disk space")
+        except Exception as e:
+            print(f"  Warning: Failed to delete {chunk_path}: {e}")
+    
     # Compress to aircraft records (one per ICAO) using shared function
     compressed = compress_multi_icao_df(df, verbose=True)
     print(f"  Compressed to {len(compressed)} aircraft records")
@@ -72,12 +85,12 @@ def combine_compressed_chunks(compressed_dfs: list[pl.DataFrame]) -> pl.DataFram
 
 def download_and_merge_base_release(compressed_df: pl.DataFrame) -> pl.DataFrame:
     """Download base release and merge with new data."""
-    from src.get_latest_planequery_aircraft_release import download_latest_aircraft_adsb_csv
+    from src.get_latest_release import download_latest_aircraft_adsb_csv
     
     print("Downloading base ADS-B release...")
     try:
         base_path = download_latest_aircraft_adsb_csv(
-            output_dir="./data/planequery_aircraft_base"
+            output_dir="./data/openairframes_base"
         )
         print(f"Download returned: {base_path}")
         
@@ -156,16 +169,17 @@ def main():
     parser.add_argument("--chunks-dir", type=str, default=DEFAULT_CHUNK_DIR, help="Directory containing chunk parquet files")
     parser.add_argument("--skip-base", action="store_true", help="Skip downloading and merging base release")
     parser.add_argument("--keep-chunks", action="store_true", help="Keep chunk files after merging")
+    parser.add_argument("--stream", action="store_true", help="Delete parquet files immediately after loading to save disk space")
     args = parser.parse_args()
     
     # Determine output ID and filename based on mode
     if args.start_date and args.end_date:
         # Historical mode
         output_id = f"{args.start_date}_{args.end_date}"
-        output_filename = f"planequery_aircraft_adsb_{args.start_date}_{args.end_date}.csv"
+        output_filename = f"openairframes_adsb_{args.start_date}_{args.end_date}.csv"
         print(f"Combining chunks for date range: {args.start_date} to {args.end_date}")
     else:
-        # Daily mode
+        # Daily mode - use same date for start and end
         if args.date:
             target_day = datetime.strptime(args.date, "%Y-%m-%d")
         else:
@@ -173,7 +187,7 @@ def main():
         
         date_str = target_day.strftime("%Y-%m-%d")
         output_id = date_str
-        output_filename = f"planequery_aircraft_adsb_{date_str}.csv"
+        output_filename = f"openairframes_adsb_{date_str}_{date_str}.csv"
         print(f"Combining chunks for {date_str}")
     
     chunks_dir = args.chunks_dir
@@ -190,9 +204,10 @@ def main():
     print(f"Found {len(chunk_files)} chunk files")
     
     # Process each chunk separately to save memory
+    # With --stream, delete parquet files immediately after loading to save disk space
     compressed_chunks = []
     for chunk_path in chunk_files:
-        compressed = process_single_chunk(chunk_path)
+        compressed = process_single_chunk(chunk_path, delete_after_load=args.stream)
         compressed_chunks.append(compressed)
         gc.collect()
     

src/adsb/compress_adsb_to_aircraft_data.py

@@ -253,7 +253,7 @@ def concat_compressed_dfs(df_base, df_new):
 
 def get_latest_aircraft_adsb_csv_df():
     """Download and load the latest ADS-B CSV from GitHub releases."""
-    from get_latest_planequery_aircraft_release import download_latest_aircraft_adsb_csv
+    from get_latest_release import download_latest_aircraft_adsb_csv
     import re
     
     csv_path = download_latest_aircraft_adsb_csv()
@@ -264,8 +264,8 @@ def get_latest_aircraft_adsb_csv_df():
         if df[col].dtype == pl.Utf8:
             df = df.with_columns(pl.col(col).fill_null(""))
     
-    # Extract start date from filename pattern: planequery_aircraft_adsb_{start_date}_{end_date}.csv
-    match = re.search(r"planequery_aircraft_adsb_(\d{4}-\d{2}-\d{2})_", str(csv_path))
+    # Extract start date from filename pattern: openairframes_adsb_{start_date}_{end_date}.csv
+    match = re.search(r"openairframes_adsb_(\d{4}-\d{2}-\d{2})_", str(csv_path))
     if not match:
         raise ValueError(f"Could not extract date from filename: {csv_path.name}")
     

src/adsb/download_adsb_data_to_parquet.py

@@ -82,7 +82,8 @@ def fetch_releases(version_date: str) -> list:
     if version_date == "v2024.12.31":
         year = "2025"
     BASE_URL = f"https://api.github.com/repos/adsblol/globe_history_{year}/releases"
-    PATTERN = f"{version_date}-planes-readsb-prod-0"
+    # Match exact release name, exclude tmp releases
+    PATTERN = rf"^{re.escape(version_date)}-planes-readsb-prod-\d+$"
     releases = []
     page = 1
     
@@ -187,19 +188,23 @@ def extract_split_archive(file_paths: list, extract_dir: str) -> bool:
         cat_proc = subprocess.Popen(
             ["cat"] + file_paths,
             stdout=subprocess.PIPE,
-            stderr=subprocess.DEVNULL
+            stderr=subprocess.PIPE
         )
         tar_cmd = ["tar", "xf", "-", "-C", extract_dir, "--strip-components=1"]
-        subprocess.run(
+        result = subprocess.run(
             tar_cmd,
             stdin=cat_proc.stdout,
-            stdout=subprocess.DEVNULL,
-            stderr=subprocess.DEVNULL,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
             check=True
         )
         cat_proc.stdout.close()
+        cat_stderr = cat_proc.stderr.read().decode() if cat_proc.stderr else ""
         cat_proc.wait()
         
+        if cat_stderr:
+            print(f"cat stderr: {cat_stderr}")
+        
         print(f"Successfully extracted archive to {extract_dir}")
         
         # Delete tar files immediately after extraction
@@ -217,7 +222,10 @@ def extract_split_archive(file_paths: list, extract_dir: str) -> bool:
         
         return True
     except subprocess.CalledProcessError as e:
+        stderr_output = e.stderr.decode() if e.stderr else ""
         print(f"Failed to extract split archive: {e}")
+        if stderr_output:
+            print(f"tar stderr: {stderr_output}")
         return False
 
 

src/adsb/reducer.py

@@ -76,8 +76,8 @@ def main():
     print(f"After dedup: {df_accumulated.height} rows")
 
     # Write and upload final result
-    output_name = f"planequery_aircraft_adsb_{global_start}_{global_end}.csv.gz"
-    csv_output = Path(f"/tmp/planequery_aircraft_adsb_{global_start}_{global_end}.csv")
+    output_name = f"openairframes_adsb_{global_start}_{global_end}.csv.gz"
+    csv_output = Path(f"/tmp/openairframes_adsb_{global_start}_{global_end}.csv")
     gz_output = Path(f"/tmp/{output_name}")
     
     df_accumulated.write_csv(csv_output)

src/contributions/approve_submission.py

@@ -21,12 +21,14 @@ import urllib.request
 import urllib.error
 from datetime import datetime, timezone
 
-from .schema import extract_json_from_issue_body, extract_contributor_name_from_issue_body, parse_and_validate
+from .schema import extract_json_from_issue_body, extract_contributor_name_from_issue_body, parse_and_validate, load_schema, SCHEMAS_DIR
 from .contributor import (
     generate_contributor_uuid,
     generate_submission_filename,
     compute_content_hash,
 )
+from .update_schema import generate_updated_schema, check_for_new_tags, get_existing_tag_definitions
+from .read_community_data import build_tag_type_registry
 
 
 def github_api_request(
@@ -54,7 +56,11 @@ def github_api_request(
     
     try:
         with urllib.request.urlopen(req) as response:
-            return json.loads(response.read())
+            response_body = response.read()
+            # DELETE requests return empty body (204 No Content)
+            if not response_body:
+                return {}
+            return json.loads(response_body)
     except urllib.error.HTTPError as e:
         error_body = e.read().decode() if e.fp else ""
         print(f"GitHub API error: {e.code} {e.reason}: {error_body}", file=sys.stderr)
@@ -94,14 +100,30 @@ def create_branch(branch_name: str, sha: str) -> None:
             raise
 
 
+def get_file_sha(path: str, branch: str) -> str | None:
+    """Get the SHA of an existing file, or None if it doesn't exist."""
+    try:
+        response = github_api_request("GET", f"/contents/{path}?ref={branch}")
+        return response.get("sha")
+    except Exception:
+        return None
+
+
 def create_or_update_file(path: str, content: str, message: str, branch: str) -> None:
     """Create or update a file in the repository."""
     content_b64 = base64.b64encode(content.encode()).decode()
-    github_api_request("PUT", f"/contents/{path}", {
+    payload = {
         "message": message,
         "content": content_b64,
         "branch": branch,
-    })
+    }
+    
+    # If file exists, we need to include its SHA to update it
+    sha = get_file_sha(path, branch)
+    if sha:
+        payload["sha"] = sha
+    
+    github_api_request("PUT", f"/contents/{path}", payload)
 
 
 def create_pull_request(title: str, head: str, base: str, body: str) -> dict:
@@ -144,21 +166,19 @@ def process_submission(
         return False
     
     data, errors = parse_and_validate(json_str)
-    if errors:
-        error_list = "\n".join(f"- {e}" for e in errors)
+    if errors or data is None:
+        error_list = "\n".join(f"- {e}" for e in errors) if errors else "Unknown error"
         add_issue_comment(issue_number, f"❌ **Validation Failed**\n\n{error_list}")
         return False
     
     # Normalize to list
-    submissions = data if isinstance(data, list) else [data]
+    submissions: list[dict] = data if isinstance(data, list) else [data]
     
     # Generate contributor UUID from GitHub ID
     contributor_uuid = generate_contributor_uuid(author_id)
     
-    # Extract contributor name from issue form (or default to GitHub username)
+    # Extract contributor name from issue form (None means user opted out of attribution)
     contributor_name = extract_contributor_name_from_issue_body(issue_body)
-    if not contributor_name:
-        contributor_name = f"@{author_username}"
     
     # Add metadata to each submission
     now = datetime.now(timezone.utc)
@@ -167,14 +187,15 @@ def process_submission(
     
     for submission in submissions:
         submission["contributor_uuid"] = contributor_uuid
-        submission["contributor_name"] = contributor_name
+        if contributor_name:
+            submission["contributor_name"] = contributor_name
         submission["creation_timestamp"] = timestamp_str
     
     # Generate unique filename
     content_json = json.dumps(submissions, indent=2, sort_keys=True)
     content_hash = compute_content_hash(content_json)
     filename = generate_submission_filename(author_username, date_str, content_hash)
-    file_path = f"community/{filename}"
+    file_path = f"community/{date_str}/{filename}"
     
     # Create branch
     branch_name = f"community-submission-{issue_number}"
@@ -185,14 +206,53 @@ def process_submission(
     commit_message = f"Add community submission from @{author_username} (closes #{issue_number})"
     create_or_update_file(file_path, content_json, commit_message, branch_name)
     
+    # Update schema with any new tags (modifies v1 in place)
+    schema_updated = False
+    new_tags = []
+    try:
+        # Build tag registry from new submissions
+        tag_registry = build_tag_type_registry(submissions)
+        
+        # Get current schema and merge existing tags
+        current_schema = load_schema()
+        existing_tags = get_existing_tag_definitions(current_schema)
+        
+        # Merge existing tags into registry
+        for tag_name, tag_def in existing_tags.items():
+            if tag_name not in tag_registry:
+                tag_type = tag_def.get("type", "string")
+                tag_registry[tag_name] = tag_type
+        
+        # Check for new tags
+        new_tags = check_for_new_tags(tag_registry, current_schema)
+        
+        if new_tags:
+            # Generate updated schema
+            updated_schema = generate_updated_schema(current_schema, tag_registry)
+            schema_json = json.dumps(updated_schema, indent=2) + "\n"
+            
+            create_or_update_file(
+                "schemas/community_submission.v1.schema.json",
+                schema_json,
+                f"Update schema with new tags: {', '.join(new_tags)}",
+                branch_name
+            )
+            schema_updated = True
+    except Exception as e:
+        print(f"Warning: Could not update schema: {e}", file=sys.stderr)
+    
     # Create PR
+    schema_note = ""
+    if schema_updated:
+        schema_note = f"\n**Schema Updated:** Added new tags: `{', '.join(new_tags)}`\n"
+    
     pr_body = f"""## Community Submission
 
 Adds {len(submissions)} submission(s) from @{author_username}.
 
 **File:** `{file_path}`
 **Contributor UUID:** `{contributor_uuid}`
-
+{schema_note}
 Closes #{issue_number}
 
 ---

src/contributions/create_daily_community_release.py

@@ -17,7 +17,7 @@ import pandas as pd
 
 
 COMMUNITY_DIR = Path(__file__).parent.parent.parent / "community"
-OUT_ROOT = Path("data/planequery_aircraft")
+OUT_ROOT = Path("data/openairframes")
 
 
 def read_all_submissions(community_dir: Path) -> list[dict]:
@@ -47,7 +47,7 @@ def submissions_to_dataframe(submissions: list[dict]) -> pd.DataFrame:
     - creation_timestamp (first)
     - transponder_code_hex
     - registration_number  
-    - planequery_airframe_id
+    - openairframes_id
     - contributor_name
     - [other columns alphabetically]
     - contributor_uuid (last)
@@ -62,7 +62,7 @@ def submissions_to_dataframe(submissions: list[dict]) -> pd.DataFrame:
         "creation_timestamp",
         "transponder_code_hex",
         "registration_number",
-        "planequery_airframe_id",
+        "openairframes_id",
         "contributor_name",
         "contributor_uuid",
     ]
@@ -78,7 +78,7 @@ def submissions_to_dataframe(submissions: list[dict]) -> pd.DataFrame:
         "creation_timestamp",
         "transponder_code_hex",
         "registration_number",
-        "planequery_airframe_id",
+        "openairframes_id",
         "contributor_name",
     ]
     last_cols = ["contributor_uuid"]
@@ -108,7 +108,7 @@ def main():
             "creation_timestamp",
             "transponder_code_hex",
             "registration_number",
-            "planequery_airframe_id",
+            "openairframes_id",
             "contributor_name",
             "tags",
             "contributor_uuid",
@@ -127,7 +127,7 @@ def main():
     
     # Output
     OUT_ROOT.mkdir(parents=True, exist_ok=True)
-    output_file = OUT_ROOT / f"planequery_aircraft_community_{start_date_str}_{date_str}.csv"
+    output_file = OUT_ROOT / f"openairframes_community_{start_date_str}_{date_str}.csv"
     
     df.to_csv(output_file, index=False)
     

src/contributions/read_community_data.py

@@ -30,7 +30,8 @@ def read_all_submissions(community_dir: Path | None = None) -> list[dict]:
     
     all_submissions = []
     
-    for json_file in sorted(community_dir.glob("*.json")):
+    # Search both root directory and date subdirectories (e.g., 2026-02-12/)
+    for json_file in sorted(community_dir.glob("**/*.json")):
         try:
             with open(json_file) as f:
                 data = json.load(f)
@@ -50,6 +51,52 @@ def read_all_submissions(community_dir: Path | None = None) -> list[dict]:
     return all_submissions
 
 
+def get_python_type_name(value) -> str:
+    """Get a normalized type name for a value."""
+    if value is None:
+        return "null"
+    if isinstance(value, bool):
+        return "boolean"
+    if isinstance(value, int):
+        return "integer"
+    if isinstance(value, float):
+        return "number"
+    if isinstance(value, str):
+        return "string"
+    if isinstance(value, list):
+        return "array"
+    if isinstance(value, dict):
+        return "object"
+    return type(value).__name__
+
+
+def build_tag_type_registry(submissions: list[dict]) -> dict[str, str]:
+    """
+    Build a registry of tag names to their expected types from existing submissions.
+    
+    Args:
+        submissions: List of existing submission dictionaries
+        
+    Returns:
+        Dict mapping tag name to expected type (e.g., {"internet": "string", "year_built": "integer"})
+    """
+    tag_types = {}
+    
+    for submission in submissions:
+        tags = submission.get("tags", {})
+        if not isinstance(tags, dict):
+            continue
+        
+        for key, value in tags.items():
+            inferred_type = get_python_type_name(value)
+            
+            if key not in tag_types:
+                tag_types[key] = inferred_type
+            # If there's a conflict, keep the first type (it's already in use)
+    
+    return tag_types
+
+
 def group_by_identifier(submissions: list[dict]) -> dict[str, list[dict]]:
     """
     Group submissions by their identifier (registration, transponder, or airframe ID).
@@ -65,8 +112,8 @@ def group_by_identifier(submissions: list[dict]) -> dict[str, list[dict]]:
             key = f"reg:{submission['registration_number']}"
         elif "transponder_code_hex" in submission:
             key = f"icao:{submission['transponder_code_hex']}"
-        elif "planequery_airframe_id" in submission:
-            key = f"id:{submission['planequery_airframe_id']}"
+        elif "openairframes_id" in submission:
+            key = f"id:{submission['openairframes_id']}"
         else:
             key = "_unknown"
         

src/contributions/regenerate_pr_schema.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+"""
+Regenerate schema for a PR branch after main has been merged in.
+This script looks at the submission files in this branch and updates
+the schema if new tags were introduced.
+
+Usage: python -m src.contributions.regenerate_pr_schema
+"""
+
+import json
+import sys
+from pathlib import Path
+
+# Add parent to path for imports when running as script
+sys.path.insert(0, str(Path(__file__).parent.parent.parent))
+
+from src.contributions.read_community_data import read_all_submissions, build_tag_type_registry
+from src.contributions.update_schema import (
+    get_existing_tag_definitions,
+    check_for_new_tags,
+    generate_updated_schema,
+)
+from src.contributions.schema import load_schema, SCHEMAS_DIR
+
+
+def main():
+    """Main entry point."""
+    # Load current schema
+    current_schema = load_schema()
+    
+    # Get existing tag definitions from schema
+    existing_tags = get_existing_tag_definitions(current_schema)
+    
+    # Read all submissions (including ones from this PR branch)
+    submissions = read_all_submissions()
+    
+    if not submissions:
+        print("No submissions found")
+        return
+    
+    # Build tag registry from all submissions
+    tag_registry = build_tag_type_registry(submissions)
+    
+    # Check for new tags not in the current schema
+    new_tags = check_for_new_tags(tag_registry, current_schema)
+    
+    if new_tags:
+        print(f"Found new tags: {new_tags}")
+        print("Updating schema...")
+        
+        # Generate updated schema
+        updated_schema = generate_updated_schema(current_schema, tag_registry)
+        
+        # Write updated schema (in place)
+        schema_path = SCHEMAS_DIR / "community_submission.v1.schema.json"
+        with open(schema_path, 'w') as f:
+            json.dump(updated_schema, f, indent=2)
+            f.write("\n")
+        
+        print(f"Updated {schema_path}")
+    else:
+        print("No new tags found, schema is up to date")
+
+
+if __name__ == "__main__":
+    main()

src/contributions/schema.py

@@ -10,12 +10,59 @@ except ImportError:
     Draft202012Validator = None
 
 
-SCHEMA_PATH = Path(__file__).parent.parent.parent / "schemas" / "community_submission.v1.schema.json"
+SCHEMAS_DIR = Path(__file__).parent.parent.parent / "schemas"
+
+# For backwards compatibility
+SCHEMA_PATH = SCHEMAS_DIR / "community_submission.v1.schema.json"
 
 
-def load_schema() -> dict:
-    """Load the community submission schema."""
-    with open(SCHEMA_PATH) as f:
+def get_latest_schema_version() -> int:
+    """
+    Find the latest schema version number.
+    
+    Returns:
+        Latest version number (e.g., 1, 2, 3)
+    """
+    import re
+    pattern = re.compile(r"community_submission\.v(\d+)\.schema\.json$")
+    max_version = 0
+    
+    for path in SCHEMAS_DIR.glob("community_submission.v*.schema.json"):
+        match = pattern.search(path.name)
+        if match:
+            version = int(match.group(1))
+            max_version = max(max_version, version)
+    
+    return max_version
+
+
+def get_schema_path(version: int | None = None) -> Path:
+    """
+    Get path to a specific schema version, or latest if version is None.
+    
+    Args:
+        version: Schema version number, or None for latest
+        
+    Returns:
+        Path to schema file
+    """
+    if version is None:
+        version = get_latest_schema_version()
+    return SCHEMAS_DIR / f"community_submission.v{version}.schema.json"
+
+
+def load_schema(version: int | None = None) -> dict:
+    """
+    Load the community submission schema.
+    
+    Args:
+        version: Schema version to load. If None, loads the latest version.
+        
+    Returns:
+        Schema dict
+    """
+    schema_path = get_schema_path(version)
+    with open(schema_path) as f:
         return json.load(f)
 
 
@@ -50,11 +97,36 @@ def validate_submission(data: dict | list, schema: dict | None = None) -> list[s
     return errors
 
 
+def download_github_attachment(url: str) -> str | None:
+    """
+    Download content from a GitHub attachment URL.
+    
+    Args:
+        url: GitHub attachment URL (e.g., https://github.com/user-attachments/files/...)
+        
+    Returns:
+        File content as string, or None if download failed
+    """
+    import urllib.request
+    import urllib.error
+    
+    try:
+        req = urllib.request.Request(url, headers={"User-Agent": "OpenAirframes-Bot"})
+        with urllib.request.urlopen(req, timeout=30) as response:
+            return response.read().decode("utf-8")
+    except (urllib.error.URLError, urllib.error.HTTPError, UnicodeDecodeError) as e:
+        print(f"Failed to download attachment from {url}: {e}")
+        return None
+
+
 def extract_json_from_issue_body(body: str) -> str | None:
     """
     Extract JSON from GitHub issue body.
     
-    Looks for JSON in the 'Submission JSON' section wrapped in code blocks.
+    Looks for JSON in the 'Submission JSON' section, either:
+    - A GitHub file attachment URL (drag-and-drop .json file)
+    - Wrapped in code blocks (```json ... ``` or ``` ... ```)
+    - Or raw JSON after the header
     
     Args:
         body: The issue body text
@@ -62,13 +134,49 @@ def extract_json_from_issue_body(body: str) -> str | None:
     Returns:
         Extracted JSON string or None if not found
     """
-    # Match JSON in "### Submission JSON" section
-    pattern = r"### Submission JSON\s*\n\s*```(?:json)?\s*\n([\s\S]*?)\n\s*```"
-    match = re.search(pattern, body)
+    # Try: GitHub attachment URL in the Submission JSON section
+    # Format: [filename.json](https://github.com/user-attachments/files/...)
+    # Or just the raw URL
+    pattern_attachment = r"### Submission JSON\s*\n[\s\S]*?(https://github\.com/(?:user-attachments/files|.*?/files)/[^\s\)\]]+\.json)"
+    match = re.search(pattern_attachment, body)
+    if match:
+        url = match.group(1)
+        content = download_github_attachment(url)
+        if content:
+            return content.strip()
     
+    # Also check for GitHub user-attachments URL anywhere in submission section
+    pattern_attachment_alt = r"\[.*?\.json\]\((https://github\.com/[^\)]+)\)"
+    match = re.search(pattern_attachment_alt, body)
+    if match:
+        url = match.group(1)
+        if ".json" in url or "user-attachments" in url:
+            content = download_github_attachment(url)
+            if content:
+                return content.strip()
+    
+    # Try: JSON in code blocks after "### Submission JSON"
+    pattern_codeblock = r"### Submission JSON\s*\n\s*```(?:json)?\s*\n([\s\S]*?)\n\s*```"
+    match = re.search(pattern_codeblock, body)
     if match:
         return match.group(1).strip()
     
+    # Try: Raw JSON after "### Submission JSON" until next section or end
+    pattern_raw = r"### Submission JSON\s*\n\s*([\[{][\s\S]*?[\]}])(?=\n###|\n\n###|$)"
+    match = re.search(pattern_raw, body)
+    if match:
+        return match.group(1).strip()
+    
+    # Try: Any JSON object/array in the body (fallback)
+    pattern_any = r"([\[{][\s\S]*?[\]}])"
+    for match in re.finditer(pattern_any, body):
+        candidate = match.group(1).strip()
+        # Validate it looks like JSON
+        if candidate.startswith('{') and candidate.endswith('}'):
+            return candidate
+        if candidate.startswith('[') and candidate.endswith(']'):
+            return candidate
+    
     return None
 
 

src/contributions/update_schema.py

@@ -0,0 +1,154 @@
+#!/usr/bin/env python3
+"""
+Update the schema with tag type definitions from existing submissions.
+
+This script reads all community submissions and generates a new schema version
+that includes explicit type definitions for all known tags.
+
+When new tags are introduced, a new schema version is created (e.g., v1 -> v2 -> v3).
+
+Usage:
+    python -m src.contributions.update_schema
+    python -m src.contributions.update_schema --check  # Check if update needed
+"""
+import argparse
+import json
+import sys
+from pathlib import Path
+
+from .read_community_data import read_all_submissions, build_tag_type_registry
+from .schema import SCHEMAS_DIR, get_latest_schema_version, get_schema_path, load_schema
+
+
+def get_existing_tag_definitions(schema: dict) -> dict[str, dict]:
+    """Extract existing tag property definitions from schema."""
+    tags_props = schema.get("properties", {}).get("tags", {}).get("properties", {})
+    return tags_props
+
+
+def type_name_to_json_schema(type_name: str) -> dict:
+    """Convert a type name to a JSON Schema type definition."""
+    type_map = {
+        "string": {"type": "string"},
+        "integer": {"type": "integer"},
+        "number": {"type": "number"},
+        "boolean": {"type": "boolean"},
+        "null": {"type": "null"},
+        "array": {"type": "array", "items": {"$ref": "#/$defs/tagScalar"}},
+        "object": {"type": "object", "additionalProperties": {"$ref": "#/$defs/tagScalar"}},
+    }
+    return type_map.get(type_name, {"$ref": "#/$defs/tagValue"})
+
+
+def generate_updated_schema(base_schema: dict, tag_registry: dict[str, str]) -> dict:
+    """
+    Generate an updated schema with explicit tag definitions.
+    
+    Args:
+        base_schema: The current schema to update
+        tag_registry: Dict mapping tag name to type name
+        
+    Returns:
+        Updated schema dict
+    """
+    schema = json.loads(json.dumps(base_schema))  # Deep copy
+    
+    # Build tag properties with explicit types
+    tag_properties = {}
+    for tag_name, type_name in sorted(tag_registry.items()):
+        tag_properties[tag_name] = type_name_to_json_schema(type_name)
+    
+    # Only add/update the properties key within tags, preserve everything else
+    if "properties" in schema and "tags" in schema["properties"]:
+        schema["properties"]["tags"]["properties"] = tag_properties
+    
+    return schema
+
+
+def check_for_new_tags(tag_registry: dict[str, str], current_schema: dict) -> list[str]:
+    """
+    Check which tags in the registry are not yet defined in the schema.
+    
+    Returns:
+        List of new tag names
+    """
+    existing_tags = get_existing_tag_definitions(current_schema)
+    return [tag for tag in tag_registry if tag not in existing_tags]
+
+
+def update_schema_file(
+    tag_registry: dict[str, str],
+    check_only: bool = False
+) -> tuple[bool, list[str]]:
+    """
+    Update the v1 schema file with new tag definitions.
+    
+    Args:
+        tag_registry: Dict mapping tag name to type name
+        check_only: If True, only check if update is needed without writing
+        
+    Returns:
+        Tuple of (was_updated, list_of_new_tags)
+    """
+    current_schema = load_schema()
+    
+    # Find new tags
+    new_tags = check_for_new_tags(tag_registry, current_schema)
+    
+    if not new_tags:
+        return False, []
+    
+    if check_only:
+        return True, new_tags
+    
+    # Generate and write updated schema (in place)
+    updated_schema = generate_updated_schema(current_schema, tag_registry)
+    schema_path = get_schema_path()
+    
+    with open(schema_path, "w") as f:
+        json.dump(updated_schema, f, indent=2)
+        f.write("\n")
+    
+    return True, new_tags
+
+
+def update_schema_from_submissions(check_only: bool = False) -> tuple[bool, list[str]]:
+    """
+    Read all submissions and update the schema if needed.
+    
+    Args:
+        check_only: If True, only check if update is needed without writing
+        
+    Returns:
+        Tuple of (was_updated, list_of_new_tags)
+    """
+    submissions = read_all_submissions()
+    tag_registry = build_tag_type_registry(submissions)
+    return update_schema_file(tag_registry, check_only)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Update schema with tag definitions")
+    parser.add_argument("--check", action="store_true", help="Check if update needed without writing")
+    
+    args = parser.parse_args()
+    
+    was_updated, new_tags = update_schema_from_submissions(check_only=args.check)
+    
+    if args.check:
+        if was_updated:
+            print(f"Schema update needed. New tags: {', '.join(new_tags)}")
+            sys.exit(1)
+        else:
+            print("Schema is up to date")
+            sys.exit(0)
+    else:
+        if was_updated:
+            print(f"Updated {get_schema_path()}")
+            print(f"Added tags: {', '.join(new_tags)}")
+        else:
+            print("No update needed")
+
+
+if __name__ == "__main__":
+    main()

src/contributions/validate_submission.py

@@ -7,6 +7,7 @@ submissions when issues are opened or edited.
 
 Usage:
     python -m src.contributions.validate_submission --issue-body "..."
+    python -m src.contributions.validate_submission --issue-body-file /path/to/body.txt
     python -m src.contributions.validate_submission --file submission.json
     echo '{"registration_number": "N12345"}' | python -m src.contributions.validate_submission --stdin
     
@@ -23,6 +24,7 @@ import urllib.request
 import urllib.error
 
 from .schema import extract_json_from_issue_body, parse_and_validate, load_schema
+from .read_community_data import read_all_submissions, build_tag_type_registry, get_python_type_name
 
 
 def github_api_request(method: str, endpoint: str, data: dict | None = None) -> dict:
@@ -65,6 +67,40 @@ def remove_issue_label(issue_number: int, label: str) -> None:
         pass  # Label might not exist
 
 
+def validate_tag_consistency(data: dict | list, tag_registry: dict[str, str]) -> list[str]:
+    """
+    Check that tag types in new submissions match existing tag types.
+    
+    Args:
+        data: Single submission dict or list of submissions
+        tag_registry: Dict mapping tag name to expected type
+        
+    Returns:
+        List of error messages. Empty list means validation passed.
+    """
+    errors = []
+    submissions = data if isinstance(data, list) else [data]
+    
+    for i, submission in enumerate(submissions):
+        prefix = f"[{i}] " if len(submissions) > 1 else ""
+        tags = submission.get("tags", {})
+        
+        if not isinstance(tags, dict):
+            continue
+        
+        for key, value in tags.items():
+            actual_type = get_python_type_name(value)
+            
+            if key in tag_registry:
+                expected_type = tag_registry[key]
+                if actual_type != expected_type:
+                    errors.append(
+                        f"{prefix}tags.{key}: expected type '{expected_type}', got '{actual_type}'"
+                    )
+    
+    return errors
+
+
 def validate_and_report(json_str: str, issue_number: int | None = None) -> bool:
     """
     Validate JSON and optionally report to GitHub issue.
@@ -90,6 +126,33 @@ def validate_and_report(json_str: str, issue_number: int | None = None) -> bool:
         
         return False
     
+    # Check tag type consistency against existing submissions
+    if data is not None:
+        try:
+            existing_submissions = read_all_submissions()
+            tag_registry = build_tag_type_registry(existing_submissions)
+            tag_errors = validate_tag_consistency(data, tag_registry)
+            
+            if tag_errors:
+                error_list = "\n".join(f"- {e}" for e in tag_errors)
+                message = (
+                    f"❌ **Tag Type Mismatch**\n\n"
+                    f"Your submission uses tags with types that don't match existing submissions:\n\n"
+                    f"{error_list}\n\n"
+                    f"Please use the same type as existing tags, or use a different tag name."
+                )
+                
+                print(message, file=sys.stderr)
+                
+                if issue_number:
+                    add_issue_comment(issue_number, message)
+                    remove_issue_label(issue_number, "validated")
+                
+                return False
+        except Exception as e:
+            # Don't fail validation if we can't read existing submissions
+            print(f"Warning: Could not check tag consistency: {e}", file=sys.stderr)
+    
     count = len(data) if isinstance(data, list) else 1
     message = f"✅ **Validation Passed**\n\n{count} submission(s) validated successfully against the schema.\n\nA maintainer can approve this submission by adding the `approved` label."
     
@@ -106,6 +169,7 @@ def main():
     parser = argparse.ArgumentParser(description="Validate community submission JSON")
     source_group = parser.add_mutually_exclusive_group(required=True)
     source_group.add_argument("--issue-body", help="Issue body text containing JSON")
+    source_group.add_argument("--issue-body-file", help="File containing issue body text")
     source_group.add_argument("--file", help="JSON file to validate")
     source_group.add_argument("--stdin", action="store_true", help="Read JSON from stdin")
     
@@ -125,6 +189,20 @@ def main():
                     "Please ensure your JSON is in the 'Submission JSON' field wrapped in code blocks."
                 )
             sys.exit(1)
+    elif args.issue_body_file:
+        with open(args.issue_body_file) as f:
+            issue_body = f.read()
+        json_str = extract_json_from_issue_body(issue_body)
+        if not json_str:
+            print("❌ Could not extract JSON from issue body", file=sys.stderr)
+            print(f"Issue body:\n{issue_body}", file=sys.stderr)
+            if args.issue_number:
+                add_issue_comment(
+                    args.issue_number,
+                    "❌ **Validation Failed**\n\nCould not extract JSON from submission. "
+                    "Please ensure your JSON is in the 'Submission JSON' field."
+                )
+            sys.exit(1)
     elif args.file:
         with open(args.file) as f:
             json_str = f.read()

src/create_daily_adsb_release.py

@@ -74,10 +74,10 @@ if __name__ == '__main__':
             )
 
     # Save the result
-    OUT_ROOT = Path("data/planequery_aircraft")
+    OUT_ROOT = Path("data/openairframes")
     OUT_ROOT.mkdir(parents=True, exist_ok=True)
 
-    output_file = OUT_ROOT / f"planequery_aircraft_adsb_{start_date_str}_{date_str}.csv"
+    output_file = OUT_ROOT / f"openairframes_adsb_{start_date_str}_{date_str}.csv"
     df_combined.write_csv(output_file)
 
     print(f"Saved: {output_file}")

src/create_daily_faa_release.py

@@ -0,0 +1,49 @@
+from pathlib import Path
+from datetime import datetime, timezone, timedelta
+import argparse
+
+parser = argparse.ArgumentParser(description="Create daily FAA release")
+parser.add_argument("--date", type=str, help="Date to process (YYYY-MM-DD format, default: today)")
+args = parser.parse_args()
+
+if args.date:
+    date_str = args.date
+else:
+    date_str = datetime.now(timezone.utc).strftime("%Y-%m-%d")
+
+out_dir = Path("data/faa_releasable")
+out_dir.mkdir(parents=True, exist_ok=True)
+zip_name = f"ReleasableAircraft_{date_str}.zip"
+
+zip_path = out_dir / zip_name
+if not zip_path.exists():
+    # URL and paths
+    url = "https://registry.faa.gov/database/ReleasableAircraft.zip"
+    from urllib.request import Request, urlopen
+
+    req = Request(
+        url,
+        headers={"User-Agent": "Mozilla/5.0"},
+        method="GET",
+    )
+
+    with urlopen(req, timeout=120) as r:
+        body = r.read()
+        zip_path.write_bytes(body)
+
+OUT_ROOT = Path("data/openairframes")
+OUT_ROOT.mkdir(parents=True, exist_ok=True)
+from derive_from_faa_master_txt import convert_faa_master_txt_to_df, concat_faa_historical_df
+from get_latest_release import get_latest_aircraft_faa_csv_df
+df_new = convert_faa_master_txt_to_df(zip_path, date_str)
+
+try:
+    df_base, start_date_str = get_latest_aircraft_faa_csv_df()
+    df_base = concat_faa_historical_df(df_base, df_new)
+    assert df_base['download_date'].is_monotonic_increasing, "download_date is not monotonic increasing"
+except Exception as e:
+    print(f"No existing FAA release found, using only new data: {e}")
+    df_base = df_new
+    start_date_str = date_str
+
+df_base.to_csv(OUT_ROOT / f"openairframes_faa_{start_date_str}_{date_str}.csv", index=False)

src/create_daily_planequery_aircraft_release.py

@@ -1,33 +0,0 @@
-from pathlib import Path
-from datetime import datetime, timezone
-date_str = datetime.now(timezone.utc).strftime("%Y-%m-%d")
-
-out_dir = Path("data/faa_releasable")
-out_dir.mkdir(parents=True, exist_ok=True)
-zip_name = f"ReleasableAircraft_{date_str}.zip"
-
-zip_path = out_dir / zip_name
-if not zip_path.exists():
-    # URL and paths
-    url = "https://registry.faa.gov/database/ReleasableAircraft.zip"
-    from urllib.request import Request, urlopen
-
-    req = Request(
-        url,
-        headers={"User-Agent": "Mozilla/5.0"},
-        method="GET",
-    )
-
-    with urlopen(req, timeout=120) as r:
-        body = r.read()
-        zip_path.write_bytes(body)
-
-OUT_ROOT = Path("data/planequery_aircraft")
-OUT_ROOT.mkdir(parents=True, exist_ok=True)
-from derive_from_faa_master_txt import convert_faa_master_txt_to_df, concat_faa_historical_df
-from get_latest_planequery_aircraft_release import get_latest_aircraft_faa_csv_df
-df_new = convert_faa_master_txt_to_df(zip_path, date_str)
-df_base, start_date_str = get_latest_aircraft_faa_csv_df()
-df_base = concat_faa_historical_df(df_base, df_new)
-assert df_base['download_date'].is_monotonic_increasing, "download_date is not monotonic increasing"
-df_base.to_csv(OUT_ROOT / f"planequery_aircraft_faa_{start_date_str}_{date_str}.csv", index=False)

src/derive_from_faa_master_txt.py

@@ -29,8 +29,8 @@ def convert_faa_master_txt_to_df(zip_path: Path, date: str):
     certification = pd.json_normalize(df["certification"].where(df["certification"].notna(), {})).add_prefix("certificate_")
     df = df.drop(columns="certification").join(certification)
     
-    # Create planequery_airframe_id
-    df["planequery_airframe_id"] = (
+    # Create openairframes_id
+    df["openairframes_id"] = (
         normalize(df["aircraft_manufacturer"])
         + "|"
         + normalize(df["aircraft_model"])
@@ -38,11 +38,11 @@ def convert_faa_master_txt_to_df(zip_path: Path, date: str):
         + normalize(df["serial_number"])
     )
     
-    # Move planequery_airframe_id to come after registration_number
+    # Move openairframes_id to come after registration_number
     cols = df.columns.tolist()
-    cols.remove("planequery_airframe_id")
+    cols.remove("openairframes_id")
     reg_idx = cols.index("registration_number")
-    cols.insert(reg_idx + 1, "planequery_airframe_id")
+    cols.insert(reg_idx + 1, "openairframes_id")
     df = df[cols]
     
     # Convert all NaN to empty strings

src/get_latest_release.py

@@ -9,7 +9,7 @@ import urllib.error
 import json
 
 
-REPO = "PlaneQuery/planequery-aircraft"
+REPO = "PlaneQuery/openairframes"
 LATEST_RELEASE_URL = f"https://api.github.com/repos/{REPO}/releases/latest"
 
 
@@ -31,7 +31,7 @@ def get_latest_release_assets(repo: str = REPO, github_token: Optional[str] = No
     url = f"https://api.github.com/repos/{repo}/releases/latest"
     headers = {
         "Accept": "application/vnd.github+json",
-        "User-Agent": "planequery-aircraft-downloader/1.0",
+        "User-Agent": "openairframes-downloader/1.0",
     }
     if github_token:
         headers["Authorization"] = f"Bearer {github_token}"
@@ -80,7 +80,7 @@ def download_asset(asset: ReleaseAsset, out_path: Path, github_token: Optional[s
     out_path.parent.mkdir(parents=True, exist_ok=True)
 
     headers = {
-        "User-Agent": "planequery-aircraft-downloader/1.0",
+        "User-Agent": "openairframes-downloader/1.0",
         "Accept": "application/octet-stream",
     }
     if github_token:
@@ -109,7 +109,7 @@ def download_latest_aircraft_csv(
     repo: str = REPO,
 ) -> Path:
     """
-    Download the latest planequery_aircraft_faa_*.csv file from the latest GitHub release.
+    Download the latest openairframes_faa_*.csv file from the latest GitHub release.
 
     Args:
         output_dir: Directory to save the downloaded file (default: "downloads")
@@ -121,10 +121,10 @@ def download_latest_aircraft_csv(
     """
     assets = get_latest_release_assets(repo, github_token=github_token)
     try:
-        asset = pick_asset(assets, name_regex=r"^planequery_aircraft_faa_.*\.csv$")
+        asset = pick_asset(assets, name_regex=r"^openairframes_faa_.*\.csv$")
     except FileNotFoundError:
         # Fallback to old naming pattern
-        asset = pick_asset(assets, name_regex=r"^planequery_aircraft_\d{4}-\d{2}-\d{2}_.*\.csv$")
+        asset = pick_asset(assets, name_regex=r"^openairframes_\d{4}-\d{2}-\d{2}_.*\.csv$")
     saved_to = download_asset(asset, output_dir / asset.name, github_token=github_token)
     print(f"Downloaded: {asset.name} ({asset.size} bytes) -> {saved_to}")
     return saved_to
@@ -136,11 +136,11 @@ def get_latest_aircraft_faa_csv_df():
            'unique_regulatory_id': str, 
            'registrant_county': str})
     df = df.fillna("")
-    # Extract start date from filename pattern: planequery_aircraft_faa_{start_date}_{end_date}.csv
-    match = re.search(r"planequery_aircraft_faa_(\d{4}-\d{2}-\d{2})_", str(csv_path))
+    # Extract start date from filename pattern: openairframes_faa_{start_date}_{end_date}.csv
+    match = re.search(r"openairframes_faa_(\d{4}-\d{2}-\d{2})_", str(csv_path))
     if not match:
-        # Fallback to old naming pattern: planequery_aircraft_{start_date}_{end_date}.csv
-        match = re.search(r"planequery_aircraft_(\d{4}-\d{2}-\d{2})_", str(csv_path))
+        # Fallback to old naming pattern: openairframes_{start_date}_{end_date}.csv
+        match = re.search(r"openairframes_(\d{4}-\d{2}-\d{2})_", str(csv_path))
     if not match:
         raise ValueError(f"Could not extract date from filename: {csv_path.name}")
     
@@ -154,7 +154,7 @@ def download_latest_aircraft_adsb_csv(
     repo: str = REPO,
 ) -> Path:
     """
-    Download the latest planequery_aircraft_adsb_*.csv file from the latest GitHub release.
+    Download the latest openairframes_adsb_*.csv file from the latest GitHub release.
 
     Args:
         output_dir: Directory to save the downloaded file (default: "downloads")
@@ -165,7 +165,7 @@ def download_latest_aircraft_adsb_csv(
         Path to the downloaded file
     """
     assets = get_latest_release_assets(repo, github_token=github_token)
-    asset = pick_asset(assets, name_regex=r"^planequery_aircraft_adsb_.*\.csv$")
+    asset = pick_asset(assets, name_regex=r"^openairframes_adsb_.*\.csv$")
     saved_to = download_asset(asset, output_dir / asset.name, github_token=github_token)
     print(f"Downloaded: {asset.name} ({asset.size} bytes) -> {saved_to}")
     return saved_to
@@ -176,8 +176,8 @@ def get_latest_aircraft_adsb_csv_df():
     import pandas as pd
     df = pd.read_csv(csv_path)
     df = df.fillna("")
-    # Extract start date from filename pattern: planequery_aircraft_adsb_{start_date}_{end_date}.csv
-    match = re.search(r"planequery_aircraft_adsb_(\d{4}-\d{2}-\d{2})_", str(csv_path))
+    # Extract start date from filename pattern: openairframes_adsb_{start_date}_{end_date}.csv
+    match = re.search(r"openairframes_adsb_(\d{4}-\d{2}-\d{2})_", str(csv_path))
     if not match:
         raise ValueError(f"Could not extract date from filename: {csv_path.name}")