datatrail-cli 0.11.0__tar.gz → 0.11.1__tar.gz

{datatrail_cli-0.11.0 → datatrail_cli-0.11.1}/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## [0.11.1](https://github.com/CHIMEFRB/datatrail-cli/compare/v0.11.0...v0.11.1) (2026-07-21)
+
+
+### Bug Fixes
+
+* **unregistered:** improve way info displayed ([c5f0fca](https://github.com/CHIMEFRB/datatrail-cli/commit/c5f0fca6f6f53e5004e1f1868517100572d68d1a))
+
 ## [0.11.0](https://github.com/CHIMEFRB/datatrail-cli/compare/v0.10.3...v0.11.0) (2026-07-07)
 
 

{datatrail_cli-0.11.0 → datatrail_cli-0.11.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datatrail-cli
-Version: 0.11.0
+Version: 0.11.1
 Summary: CHIME/FRB Datatrail CLI
 Author: CHIME FRB Project Office
 Author-email: Tarik Zegmott <tarik.zegmott@mcgill.ca>
@@ -13,7 +13,7 @@ Requires-Dist: cadcutils>=1.5.1.1
 Requires-Dist: click-aliasing>=1.0.0
 Requires-Dist: click>=8.1.3
 Requires-Dist: dill>=0.3.6
-Requires-Dist: lxml>=4.9.2
+Requires-Dist: lxml>=6.1.0
 Requires-Dist: mergedeep>=1.3.4
 Requires-Dist: pyaml>=21.10.1
 Requires-Dist: requests>=2.29.0

{datatrail_cli-0.11.0 → datatrail_cli-0.11.1}/dtcli/src/functions.py

@@ -6,7 +6,7 @@ import re
 import shutil
 import subprocess
 import time
-from collections import defaultdict
+from collections import Counter
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Tuple
 
@@ -486,6 +486,15 @@ def get_unregistered_dataset(dataset: str, scope: str) -> Optional[Dict[str, Any
         return response[0]
 
 
+ATTACH_RE = re.compile(
+    r"Could not attach datasets: .+? ERROR: \"?dataset (.+?), (.+?) not found"  # noqa: E501
+)
+
+CREATE_RE = re.compile(
+    r"Could not create dataset: (.+?), scope: (.+?)\. .*UniqueViolation"  # noqa: E501
+)
+
+
 def signature(msg: str) -> str:
     """Create a signature for a reason unregistered message.
 
@@ -495,16 +504,6 @@ def signature(msg: str) -> str:
     Returns:
         str: Signature for error message.
     """
-    ATTACH_RE = re.compile(
-        r"Could not attach datasets: .+ ERROR: dataset (.+), (.+) not found"  # noqa: E501
-    )
-
-    CREATE_RE = re.compile(
-        r"Could not create dataset: (.+), scope: (.+)\. .*UniqueViolation"  # noqa: E501
-    )
-
-    POSTGRES_RE = re.compile(r".*psycopg.*")
-
     msg = msg.strip()
 
     # Attach-dataset errors
@@ -517,11 +516,12 @@ def signature(msg: str) -> str:
     m = CREATE_RE.search(msg)
     if m:
         dataset, scope = m.groups()
+        dataset = re.sub(r"\d+", "<ID>", dataset)
         return f"CREATE_DUPLICATE:{dataset}:{scope}"
 
     # PostgreSQL violation
-    m = POSTGRES_RE.search(msg)
-    if m:
+    if "psycopg" in msg:
+        msg = re.sub(r"\s+", " ", msg)
         return f"POSTGRES:{msg[:120]}"
 
     # Short status / token messages
@@ -552,11 +552,4 @@ def summarise_unregistered_datasets() -> Dict[str, int]:
         Dict[str, int]: Dictionary of error message signatures and their counts.
     """
     response = get_all_unregistered_datasets()
-    reason_groups: Dict[str, int] = defaultdict(int)
-    messages = [str(r["results"]["reason"]) for r in response]
-
-    for msg in messages:
-        sig = signature(msg)
-        reason_groups[sig] += 1
-
-    return reason_groups
+    return Counter(signature(str(r["results"]["reason"])) for r in response)

datatrail_cli-0.11.1/dtcli/unregistered.py

@@ -0,0 +1,102 @@
+"""Datatrail Unregistered datasets commands."""
+
+import logging
+from collections import defaultdict
+from typing import DefaultDict, List, Tuple
+
+import click
+from rich.console import Console
+from rich.table import Table
+from rich.text import Text
+
+from dtcli.src import functions
+from dtcli.utilities.utilities import set_log_level
+
+logger = logging.getLogger(__name__)
+
+console = Console()
+error_console = Console(stderr=True, style="bold red")
+
+CATEGORY_STYLES = {
+    "ATTACH_MISSING": "yellow",
+    "CREATE_DUPLICATE": "magenta",
+    "POSTGRES": "red",
+    "OTHER": "red",
+    "STATUS": "cyan",
+}
+
+
+@click.group(help="Commands related to unregistered datasets.")
+def unregistered():
+    """Group of commands related to unregistered datasets."""
+    pass
+
+
+@unregistered.command(help="Summarise the reasons for unregistered datasets.")
+@click.option("-v", "--verbose", count=True, help="Verbosity: v=INFO, vv=DEBUG.")
+@click.option("-q", "--quiet", is_flag=True, help="Only errors shown in logs.")
+@click.pass_context
+def summary(
+    ctx: click.Context,
+    verbose: int = 0,
+    quiet: bool = False,
+):
+    """Show a summary of the unregistered datasets.
+
+    Args:
+        ctx (click.Context): Click context.
+        verbose (int): Verbosity: v=INFO, vv=DEBUG.
+        quiet (bool): Only errors shown in logs.
+    """
+    # Set logging level.
+    set_log_level(logger, verbose, quiet)
+    logger.debug("`summary` called with:")
+    logger.debug(f"verbose: {verbose} [{type(verbose)}]")
+    logger.debug(f"quiet: {quiet} [{type(quiet)}]")
+
+    results = functions.summarise_unregistered_datasets()
+
+    if not results:
+        console.print("No unregistered datasets found.")
+        return
+
+    total = sum(results.values())
+
+    table = Table(
+        title=f"Summary of reasons — {total:,} unregistered datasets",
+        header_style="magenta",
+        title_style="bold magenta",
+        row_styles=["none", "dim"],
+    )
+    table.add_column("Category")
+    table.add_column("Detail")
+    table.add_column("Count", justify="right")
+    table.add_column("%", justify="right")
+
+    # Group signatures by their category prefix, e.g. "ATTACH_MISSING:...".
+    groups: DefaultDict[str, List[Tuple[str, int]]] = defaultdict(list)
+    for sig, count in results.items():
+        category, _, detail = sig.partition(":")
+        groups[category].append((detail, count))
+
+    ordered = sorted(
+        groups.items(),
+        key=lambda group: sum(count for _, count in group[1]),
+        reverse=True,
+    )
+    for index, (category, reasons) in enumerate(ordered):
+        if index:
+            table.add_section()
+        style = CATEGORY_STYLES.get(category, "white")
+        reasons.sort(key=lambda reason: reason[1], reverse=True)
+        for row, (detail, count) in enumerate(reasons):
+            if category in ("ATTACH_MISSING", "CREATE_DUPLICATE"):
+                detail = detail.replace(":", " → ", 1)
+            table.add_row(
+                Text(category, style=style) if row == 0 else "",
+                Text(detail) if detail else "(no reason recorded)",
+                f"{count:,}",
+                f"{count / total:.1%}",
+            )
+
+    console.print(table)