osmsg 1.2.1__tar.gz → 1.2.5__tar.gz

{osmsg-1.2.1 → osmsg-1.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: osmsg
-Version: 1.2.1
+Version: 1.2.5
 Summary: OpenStreetMap Stats Generator: Commandline
 Keywords: osm,stats,commandline,openstreetmap
 Author: Kshitij Raj Sharma
@@ -78,7 +78,9 @@ brew install osgeonepal/tap/osmsg          # macOS / Linux (Homebrew tap)
 ```
 
 On Windows, download `osmsg.exe` from the [latest release](https://github.com/osgeonepal/osmsg/releases)
-and run it directly, no Python required.
+and double-click it to open the desktop app. Pick a Quick range (last hour, day, week, month, year, or
+all time) or type your own dates, set the options, click Compute, and open the output folder. The CLI
+below is for macOS, Linux, and pip/uv users.
 
 ## Quick start
 
@@ -206,7 +208,8 @@ Same pipeline as the CLI.
 osmsg --config nepal.yaml
 ```
 
-Any flag works as a YAML key. See [docs/Manual.md](./docs/Manual.md) for the full list.
+Each option is a YAML key written with its underscore name: `output_dir`, `history_url`, `all_stats`,
+`formats`, `psql_dsn`, and so on (not the dashed flag). See [docs/Manual.md](./docs/Manual.md).
 
 ## Output formats
 
@@ -227,7 +230,7 @@ docker-compose `environment:` block all reach the same setting. CLI flag wins ov
 | `--country` | `OSMSG_COUNTRY` | unset | Geofabrik region id(s). Comma-separated when set via env. |
 | `--boundary` | `OSMSG_BOUNDARY` | unset | GeoJSON path or inline GeoJSON. |
 | `--url` | `OSMSG_URL` | `minute` | `minute`/`hour`/`day` shortcut or full URL. Comma-separated when set via env. |
-| `--workers` | `OSMSG_WORKERS` | cpu count | Parallel workers. |
+| `--workers` | `OSMSG_WORKERS` | cpu count | Parallel parse workers. |
 | `--cache-dir` | `OSMSG_CACHE_DIR` | platform cache | Where downloaded OSM files are kept across runs. |
 | `--output-dir` | `OSMSG_OUTPUT_DIR` | `.` | Where `<name>.duckdb` and exports are written. |
 | `--format` / `-f` | `OSMSG_FORMAT` | `parquet` | Repeat for multiple. Comma-separated when set via env. |
@@ -237,7 +240,7 @@ docker-compose `environment:` block all reach the same setting. CLI flag wins ov
 | `--history` / `--no-history` | `OSMSG_HISTORY` | on | Read covered months from the published dataset. |
 | `--history-url` | `OSMSG_HISTORY_URL` | `osmsg-history` | Published dataset location. |
 | `--insert` | (none) | off | Load history into the store and seed resume, then exit. No window loads all of it. |
-| `--osh-file` / `--changeset-file` | (none) | unset | Insert from local planet history + changeset files instead of the dataset. |
+| `--osh-file` / `--changeset-file` | (none) | unset | Insert from local planet history + changeset files. |
 | `--changeset-pad-hours` | `OSMSG_CHANGESET_PAD_HOURS` | `1` | See below. |
 | (auto-bootstrap on `--update`) | `OSMSG_BOOTSTRAP` | `hour` | `hour`, `day`, or `week`. Used when `--update` runs against an empty DB. |
 | (auto-bootstrap on `--update`) | `OSMSG_BOOTSTRAP_DAYS` | unset | Integer N; overrides `OSMSG_BOOTSTRAP`. |

{osmsg-1.2.1 → osmsg-1.2.5}/README.md

@@ -46,7 +46,9 @@ brew install osgeonepal/tap/osmsg          # macOS / Linux (Homebrew tap)
 ```
 
 On Windows, download `osmsg.exe` from the [latest release](https://github.com/osgeonepal/osmsg/releases)
-and run it directly, no Python required.
+and double-click it to open the desktop app. Pick a Quick range (last hour, day, week, month, year, or
+all time) or type your own dates, set the options, click Compute, and open the output folder. The CLI
+below is for macOS, Linux, and pip/uv users.
 
 ## Quick start
 
@@ -174,7 +176,8 @@ Same pipeline as the CLI.
 osmsg --config nepal.yaml
 ```
 
-Any flag works as a YAML key. See [docs/Manual.md](./docs/Manual.md) for the full list.
+Each option is a YAML key written with its underscore name: `output_dir`, `history_url`, `all_stats`,
+`formats`, `psql_dsn`, and so on (not the dashed flag). See [docs/Manual.md](./docs/Manual.md).
 
 ## Output formats
 
@@ -195,7 +198,7 @@ docker-compose `environment:` block all reach the same setting. CLI flag wins ov
 | `--country` | `OSMSG_COUNTRY` | unset | Geofabrik region id(s). Comma-separated when set via env. |
 | `--boundary` | `OSMSG_BOUNDARY` | unset | GeoJSON path or inline GeoJSON. |
 | `--url` | `OSMSG_URL` | `minute` | `minute`/`hour`/`day` shortcut or full URL. Comma-separated when set via env. |
-| `--workers` | `OSMSG_WORKERS` | cpu count | Parallel workers. |
+| `--workers` | `OSMSG_WORKERS` | cpu count | Parallel parse workers. |
 | `--cache-dir` | `OSMSG_CACHE_DIR` | platform cache | Where downloaded OSM files are kept across runs. |
 | `--output-dir` | `OSMSG_OUTPUT_DIR` | `.` | Where `<name>.duckdb` and exports are written. |
 | `--format` / `-f` | `OSMSG_FORMAT` | `parquet` | Repeat for multiple. Comma-separated when set via env. |
@@ -205,7 +208,7 @@ docker-compose `environment:` block all reach the same setting. CLI flag wins ov
 | `--history` / `--no-history` | `OSMSG_HISTORY` | on | Read covered months from the published dataset. |
 | `--history-url` | `OSMSG_HISTORY_URL` | `osmsg-history` | Published dataset location. |
 | `--insert` | (none) | off | Load history into the store and seed resume, then exit. No window loads all of it. |
-| `--osh-file` / `--changeset-file` | (none) | unset | Insert from local planet history + changeset files instead of the dataset. |
+| `--osh-file` / `--changeset-file` | (none) | unset | Insert from local planet history + changeset files. |
 | `--changeset-pad-hours` | `OSMSG_CHANGESET_PAD_HOURS` | `1` | See below. |
 | (auto-bootstrap on `--update`) | `OSMSG_BOOTSTRAP` | `hour` | `hour`, `day`, or `week`. Used when `--update` runs against an empty DB. |
 | (auto-bootstrap on `--update`) | `OSMSG_BOOTSTRAP_DAYS` | unset | Integer N; overrides `OSMSG_BOOTSTRAP`. |

osmsg-1.2.5/osmsg/__version__.py

@@ -0,0 +1 @@
+__version__ = "1.2.5"

{osmsg-1.2.1 → osmsg-1.2.5}/osmsg/_http.py

@@ -11,7 +11,7 @@ from requests.adapters import HTTPAdapter
 from urllib3.util.retry import Retry
 
 USER_AGENT = "osmsg"
-DEFAULT_TIMEOUT = (10, 60)  # (connect, read) seconds
+DEFAULT_TIMEOUT = (30, 120)  # (connect, read) seconds
 
 
 class _TimeoutSession(requests.Session):
@@ -26,10 +26,14 @@ def make_session() -> requests.Session:
     """Fresh session with the standard timeout + retry policy (use when a flow needs its own cookie jar)."""
     s = _TimeoutSession()
     retry = Retry(
-        total=5,
-        backoff_factor=0.5,
+        total=10,
+        connect=10,
+        read=10,
+        backoff_factor=1.0,
+        backoff_max=120,
         status_forcelist=(429, 500, 502, 503, 504),
         allowed_methods=frozenset({"GET", "POST", "HEAD"}),
+        respect_retry_after_header=True,
     )
     adapter = HTTPAdapter(max_retries=retry, pool_maxsize=32)
     s.mount("https://", adapter)

{osmsg-1.2.1 → osmsg-1.2.5}/osmsg/cli.py

@@ -150,7 +150,7 @@ def main(
     ] = None,
     workers: Annotated[
         int | None,
-        typer.Option(envvar="OSMSG_WORKERS", help="Parallel workers (default: cpu count)."),
+        typer.Option(envvar="OSMSG_WORKERS", help="Parallel parse workers (default: cpu count)."),
     ] = None,
     rows: Annotated[
         int | None,

osmsg-1.2.5/osmsg/gui.py

@@ -0,0 +1,272 @@
+"""Minimal tkinter desktop UI for running osmsg and saving the output."""
+
+from __future__ import annotations
+
+import datetime as dt
+import os
+import queue
+import sys
+import threading
+import webbrowser
+from pathlib import Path
+from typing import Any
+
+from .__version__ import __version__
+from .exceptions import NoDataFoundError, OsmsgError
+from .pipeline import RunConfig, run
+
+UTC = dt.UTC
+FORMATS = ["parquet", "csv", "json", "markdown"]
+ABOUT_LINKS = [
+    ("Star osmsg on GitHub", "https://github.com/osgeonepal/osmsg"),
+    ("Report a bug or request a feature", "https://github.com/osgeonepal/osmsg/issues"),
+    ("Sponsor the developer", "https://github.com/sponsors/kshitijrajsharma"),
+]
+PRESETS = ["Last hour", "Last day", "Last week", "Last month", "Last year", "All time"]
+_PRESET_DELTAS = {
+    "Last hour": dt.timedelta(hours=1),
+    "Last day": dt.timedelta(days=1),
+    "Last week": dt.timedelta(days=7),
+    "Last month": dt.timedelta(days=30),
+    "Last year": dt.timedelta(days=365),
+}
+
+
+def preset_range(name: str, now: dt.datetime | None = None) -> tuple[dt.datetime, dt.datetime]:
+    """Resolve a quick-range label to a (start, end) window."""
+    now = now or dt.datetime.now(UTC)
+    if name == "All time":
+        return dt.datetime(2005, 1, 1, tzinfo=UTC), now
+    return now - _PRESET_DELTAS[name], now
+
+
+def _fmt(when: dt.datetime) -> str:
+    return when.strftime("%Y-%m-%d %H:%M:%S")
+
+
+def _parse_date(value: str) -> dt.datetime | None:
+    value = value.strip()
+    if not value:
+        return None
+    for fmt in ("%Y-%m-%d %H:%M:%S", "%Y-%m-%d"):
+        try:
+            return dt.datetime.strptime(value, fmt).replace(tzinfo=UTC)
+        except ValueError:
+            continue
+    raise OsmsgError(f"Unrecognized date: {value!r}. Use YYYY-MM-DD.")
+
+
+def _split(value: str | None) -> list[str] | None:
+    items: list[str] = [part.strip() for part in (value or "").split(",") if part.strip()]
+    return items if items else None
+
+
+def _parse_int(value: object, field: str) -> int | None:
+    text = str(value or "").strip()
+    if not text:
+        return None
+    try:
+        number = int(text)
+    except ValueError as exc:
+        raise OsmsgError(f"{field} must be a whole number.") from exc
+    if number < 1:
+        raise OsmsgError(f"{field} must be at least 1.")
+    return number
+
+
+def build_config(form: dict[str, object], output_dir: str) -> RunConfig:
+    """Map the form fields to a RunConfig, raising OsmsgError on invalid input."""
+    formats = [name for name in FORMATS if form.get(name)]
+    if not formats:
+        raise OsmsgError("Pick at least one output format.")
+    start = _parse_date(str(form.get("start", "")))
+    if start is None:
+        raise OsmsgError("Start date is required (YYYY-MM-DD).")
+    return RunConfig(
+        name=str(form.get("name") or "stats"),
+        start_date=start,
+        end_date=_parse_date(str(form.get("end", ""))),
+        hashtags=_split(str(form.get("hashtags") or "")),
+        additional_tags=_split(str(form.get("tags") or "")),
+        tag_mode="all" if form.get("all_tags") else "none",
+        summary=bool(form.get("summary")),
+        formats=formats,
+        workers=_parse_int(form.get("workers"), "Workers"),
+        output_dir=Path(output_dir or "."),
+    )
+
+
+def _open_folder(path: Path) -> None:
+    if sys.platform == "win32":
+        os.startfile(path)  # noqa: S606
+    elif sys.platform == "darwin":
+        import subprocess
+
+        subprocess.run(["open", str(path)], check=False)
+    else:
+        import subprocess
+
+        subprocess.run(["xdg-open", str(path)], check=False)
+
+
+class _Redirector:
+    def __init__(self, sink: queue.Queue) -> None:
+        self.sink = sink
+
+    def write(self, text: str) -> None:
+        if text:
+            self.sink.put(("log", text))
+
+    def flush(self) -> None:
+        pass
+
+    def isatty(self) -> bool:
+        return False
+
+
+class App:
+    def __init__(self) -> None:
+        import tkinter as tk
+        from tkinter import filedialog, scrolledtext, ttk
+
+        self._tk = tk
+        self._ttk = ttk
+        self._filedialog = filedialog
+        self.events: queue.Queue = queue.Queue()
+        self.out_dir = str(Path.home() / "osmsg")
+
+        self.root = tk.Tk()
+        self.root.title("osmsg")
+        self.vars: dict[str, Any] = {}
+        frame = ttk.Frame(self.root, padding=12)
+        frame.grid(sticky="nsew")
+
+        rows = [
+            ("Name", "name", "stats"),
+            ("Start (YYYY-MM-DD)", "start", ""),
+            ("End (blank = now)", "end", ""),
+            ("Hashtags (comma-sep)", "hashtags", ""),
+            ("Tags (comma-sep)", "tags", ""),
+            ("Workers", "workers", str(os.cpu_count() or 4)),
+        ]
+        for i, (label, key, default) in enumerate(rows):
+            ttk.Label(frame, text=label).grid(row=i, column=0, sticky="w", pady=2)
+            var = tk.StringVar(value=default)
+            ttk.Entry(frame, textvariable=var, width=40).grid(row=i, column=1, columnspan=3, sticky="we", pady=2)
+            self.vars[key] = var
+
+        preset_frame = ttk.LabelFrame(frame, text="Quick range", padding=6)
+        preset_frame.grid(row=6, column=0, columnspan=4, sticky="we", pady=6)
+        for i, name in enumerate(PRESETS):
+            ttk.Button(preset_frame, text=name, width=11, command=lambda n=name: self._apply_preset(n)).grid(
+                row=0, column=i, padx=2
+            )
+
+        self.vars["all_tags"] = tk.BooleanVar()
+        self.vars["summary"] = tk.BooleanVar()
+        ttk.Checkbutton(frame, text="All tags", variable=self.vars["all_tags"]).grid(row=7, column=0, sticky="w")
+        ttk.Checkbutton(frame, text="Daily summary", variable=self.vars["summary"]).grid(row=7, column=1, sticky="w")
+
+        fmt_frame = ttk.LabelFrame(frame, text="Formats", padding=6)
+        fmt_frame.grid(row=8, column=0, columnspan=4, sticky="we", pady=6)
+        for i, name in enumerate(FORMATS):
+            var = tk.BooleanVar(value=name in ("parquet", "csv"))
+            ttk.Checkbutton(fmt_frame, text=name, variable=var).grid(row=0, column=i, padx=4)
+            self.vars[name] = var
+
+        self.out_label = ttk.Label(frame, text=f"Output: {self.out_dir}")
+        self.out_label.grid(row=9, column=0, columnspan=3, sticky="w")
+        ttk.Button(frame, text="Choose folder", command=self._choose_folder).grid(row=9, column=3, sticky="e")
+
+        self.run_btn = ttk.Button(frame, text="Compute", command=self._on_run)
+        self.run_btn.grid(row=10, column=0, pady=8, sticky="w")
+        self.open_btn = ttk.Button(frame, text="Open output folder", command=lambda: _open_folder(Path(self.out_dir)))
+        self.open_btn.grid(row=10, column=1, pady=8, sticky="w")
+        self.spinner = ttk.Progressbar(frame, mode="indeterminate", length=160)
+        self.spinner.grid(row=10, column=2, columnspan=2, pady=8, sticky="we")
+
+        self.log = scrolledtext.ScrolledText(frame, width=70, height=14, state="disabled")
+        self.log.grid(row=11, column=0, columnspan=4, sticky="nsew")
+
+        ttk.Button(frame, text="About", command=self._show_about).grid(row=12, column=0, pady=(6, 0), sticky="w")
+        ttk.Label(frame, text="A project of OSGeo Nepal").grid(row=12, column=1, columnspan=3, pady=(6, 0), sticky="e")
+        self.root.after(120, self._drain)
+
+    def _show_about(self) -> None:
+        tk, ttk = self._tk, self._ttk
+        win = tk.Toplevel(self.root)
+        win.title("About osmsg")
+        box = ttk.Frame(win, padding=16)
+        box.grid(sticky="nsew")
+        ttk.Label(box, text=f"osmsg {__version__}", font=("", 12, "bold")).grid(sticky="w")
+        ttk.Label(box, text="OpenStreetMap Stats Generator").grid(sticky="w")
+        ttk.Label(box, text="A project of OSGeo Nepal").grid(sticky="w", pady=(0, 10))
+        for text, url in ABOUT_LINKS:
+            link = ttk.Label(box, text=text, foreground="#1a73e8", cursor="hand2")
+            link.grid(sticky="w", pady=2)
+            link.bind("<Button-1>", lambda _event, target=url: webbrowser.open(target))
+        ttk.Button(box, text="Close", command=win.destroy).grid(sticky="e", pady=(12, 0))
+
+    def _apply_preset(self, name: str) -> None:
+        start, end = preset_range(name)
+        self.vars["start"].set(_fmt(start))
+        self.vars["end"].set(_fmt(end))
+
+    def _choose_folder(self) -> None:
+        chosen = self._filedialog.askdirectory(initialdir=self.out_dir)
+        if chosen:
+            self.out_dir = chosen
+            self.out_label.config(text=f"Output: {self.out_dir}")
+
+    def _append(self, text: str) -> None:
+        self.log.config(state="normal")
+        self.log.insert("end", text)
+        self.log.see("end")
+        self.log.config(state="disabled")
+
+    def _on_run(self) -> None:
+        try:
+            cfg = build_config({k: v.get() for k, v in self.vars.items()}, self.out_dir)
+        except OsmsgError as exc:
+            self._append(f"\n{exc}\n")
+            return
+        self.run_btn.config(state="disabled", text="Running...")
+        self.spinner.start(12)
+        self._append(f"\nComputing into {self.out_dir} ...\n")
+        threading.Thread(target=self._worker, args=(cfg,), daemon=True).start()
+
+    def _worker(self, cfg: RunConfig) -> None:
+        saved = sys.stdout, sys.stderr
+        sys.stdout = sys.stderr = _Redirector(self.events)  # type: ignore[assignment]
+        try:
+            result = run(cfg)
+            self.events.put(("done", f"Done. {result['rows']} rows. Files in {self.out_dir}"))
+        except NoDataFoundError:
+            self.events.put(("done", "No data found for that range."))
+        except OsmsgError as exc:
+            self.events.put(("done", f"Error: {exc}"))
+        except Exception as exc:
+            self.events.put(("done", f"Unexpected error: {type(exc).__name__}: {exc}"))
+        finally:
+            sys.stdout, sys.stderr = saved
+
+    def _drain(self) -> None:
+        try:
+            while True:
+                kind, payload = self.events.get_nowait()
+                if kind == "log":
+                    self._append(payload)
+                else:
+                    self._append(f"\n{payload}\n")
+                    self.spinner.stop()
+                    self.run_btn.config(state="normal", text="Compute")
+        except queue.Empty:
+            pass
+        self.root.after(120, self._drain)
+
+    def run(self) -> None:
+        self.root.mainloop()
+
+
+def launch() -> None:
+    App().run()

{osmsg-1.2.1 → osmsg-1.2.5}/osmsg/history.py

@@ -5,6 +5,7 @@ path (a glob would make DuckDB list every partition over the HF API)."""
 import datetime as dt
 import json
 import pathlib
+import time
 from dataclasses import dataclass
 
 import duckdb
@@ -16,6 +17,7 @@ UTC = dt.UTC
 SCHEMA_VERSION = 1
 DEFAULT_HISTORY_URL = "hf://datasets/kshitijrajsharma/osmsg-history"
 HISTORY_SEQ_ID = 0
+MONTH_READ_ATTEMPTS = 4
 
 
 @dataclass
@@ -185,36 +187,47 @@ def ingest_remote(
 
     info(f"history: remote ingest {start_iso} -> {end_iso} ({len(months)} month partitions) from {history_url}")
 
+    def ingest_month(month: tuple[int, int]) -> None:
+        changesets_src = _partition_list(history_url, "changesets", [month])
+        changefiles_src = _partition_list(history_url, "changefiles", [month])
+        if changesets_src is not None:
+            conn.execute(
+                f"""INSERT INTO users
+                    SELECT uid, any_value(username) FROM {changesets_src}
+                    WHERE {in_window} AND username IS NOT NULL
+                    GROUP BY uid ON CONFLICT (uid) DO NOTHING"""
+            )
+            conn.execute(
+                f"""INSERT INTO changesets
+                    SELECT changeset_id, uid, created_at, hashtags, editor,
+                           CASE WHEN min_lon IS NOT NULL
+                                THEN ST_MakeEnvelope(min_lon, min_lat, max_lon, max_lat) END
+                    FROM {changesets_src} WHERE {changeset_where}
+                    ON CONFLICT (changeset_id) DO NOTHING"""
+            )
+        if changefiles_src is not None:
+            conn.execute(
+                f"""INSERT INTO changeset_stats
+                    SELECT changeset_id, {HISTORY_SEQ_ID} AS seq_id, uid,
+                           nodes_created, nodes_modified, nodes_deleted,
+                           ways_created, ways_modified, ways_deleted,
+                           rels_created, rels_modified, rels_deleted,
+                           poi_created, poi_modified, tag_stats
+                    FROM {changefiles_src} WHERE {stats_where}
+                    ON CONFLICT (seq_id, changeset_id) DO NOTHING"""
+            )
+
     with progress_bar(len(months), unit="months", description="Reading history") as advance:
         for month in months:
-            changesets_src = _partition_list(history_url, "changesets", [month])
-            changefiles_src = _partition_list(history_url, "changefiles", [month])
-            if changesets_src is not None:
-                conn.execute(
-                    f"""INSERT INTO users
-                        SELECT uid, any_value(username) FROM {changesets_src}
-                        WHERE {in_window} AND username IS NOT NULL
-                        GROUP BY uid ON CONFLICT (uid) DO NOTHING"""
-                )
-                conn.execute(
-                    f"""INSERT INTO changesets
-                        SELECT changeset_id, uid, created_at, hashtags, editor,
-                               CASE WHEN min_lon IS NOT NULL
-                                    THEN ST_MakeEnvelope(min_lon, min_lat, max_lon, max_lat) END
-                        FROM {changesets_src} WHERE {changeset_where}
-                        ON CONFLICT (changeset_id) DO NOTHING"""
-                )
-            if changefiles_src is not None:
-                conn.execute(
-                    f"""INSERT INTO changeset_stats
-                        SELECT changeset_id, {HISTORY_SEQ_ID} AS seq_id, uid,
-                               nodes_created, nodes_modified, nodes_deleted,
-                               ways_created, ways_modified, ways_deleted,
-                               rels_created, rels_modified, rels_deleted,
-                               poi_created, poi_modified, tag_stats
-                        FROM {changefiles_src} WHERE {stats_where}
-                        ON CONFLICT (seq_id, changeset_id) DO NOTHING"""
-                )
+            for attempt in range(MONTH_READ_ATTEMPTS):
+                try:
+                    ingest_month(month)
+                    break
+                except duckdb.Error as exc:
+                    if attempt == MONTH_READ_ATTEMPTS - 1:
+                        raise
+                    warn(f"history: {month[0]}-{month[1]:02d} read failed ({type(exc).__name__}); retrying.")
+                    time.sleep(2 * (attempt + 1))
             advance()
 
     row = conn.execute(f"SELECT count(*) FROM changeset_stats WHERE seq_id = {HISTORY_SEQ_ID}").fetchone()

{osmsg-1.2.1 → osmsg-1.2.5}/osmsg/pipeline.py

@@ -14,6 +14,7 @@ from pathlib import Path
 from typing import Any
 
 import duckdb
+import requests
 from platformdirs import user_cache_dir
 from shapely.ops import unary_union
 
@@ -539,21 +540,30 @@ def _processing_config(cfg: RunConfig, *, parquet_dir: Path, geom_wkt: str | Non
     }
 
 
+_DOWNLOAD_WORKERS = 4
+
+
 def _download_all(
     urls: list[str],
     mode: str,
-    max_workers: int,
+    workers: int,
     cookie: str | None,
     cache_dir: Path,
     label: str,
     description: str = "downloading",
 ) -> None:
-    with (
-        progress_bar(len(urls), unit=label, description=description) as advance,
-        concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as pool,
-    ):
-        for _ in pool.map(lambda u: download_osm_file(u, mode=mode, cookie=cookie, cache_dir=cache_dir), urls):
-            advance()
+    try:
+        with (
+            progress_bar(len(urls), unit=label, description=description) as advance,
+            concurrent.futures.ThreadPoolExecutor(max_workers=workers) as pool,
+        ):
+            for _ in pool.map(lambda u: download_osm_file(u, mode=mode, cookie=cookie, cache_dir=cache_dir), urls):
+                advance()
+    except requests.exceptions.RequestException as exc:
+        raise OsmsgError(
+            f"Network error downloading {label} after retries ({type(exc).__name__}). "
+            "Re-run to resume: finished downloads are cached, so it continues from where it stopped."
+        ) from exc
 
 
 def _process_all(
@@ -701,10 +711,13 @@ def run(cfg: RunConfig) -> dict[str, Any]:
                         if run_live:
                             _auto_switch_replication(cfg, cfg.end_date - cfg.start_date)
                     except duckdb.Error as exc:
-                        warn(f"history: remote ingest failed ({type(exc).__name__}: {exc}); using live path.")
                         for tbl in ("changeset_stats", "changesets", "users"):
                             conn.execute(f"DELETE FROM {tbl}")
-                        run_live = True
+                        dbmod.close(conn)
+                        raise OsmsgError(
+                            f"Reading the published history failed after retries ({type(exc).__name__}). "
+                            "Re-run to try again, narrow the date range, or pass --no-history for the live path."
+                        ) from exc
 
     max_workers = cfg.workers or _cpu_count()
     info(f"Workers: {max_workers}")
@@ -727,6 +740,13 @@ def run(cfg: RunConfig) -> dict[str, Any]:
             else f"first run with {cfg.changeset_pad_hours}h backward pad"
         )
         info(f"Changesets: {len(urls)} files (seq {cs_start}-{cs_end}), {pad_note}.")
+        if len(urls) > 5000:
+            warn(
+                f"Hashtag/changeset filtering downloads the per-minute changeset stream for the live "
+                f"tail ({len(urls):,} files here). This is slow over a busy network and resumes from "
+                f"cache if interrupted; a shorter range or waiting for the dataset to cover more months "
+                f"reduces it."
+            )
 
         cs_frontier_ts = cs_repl.sequence_to_timestamp(cs_end)
 
@@ -736,7 +756,13 @@ def run(cfg: RunConfig) -> dict[str, Any]:
             cs_config["window_start_utc"] = cfg.start_date.astimezone(UTC)
 
             _download_all(
-                urls, "changeset", max_workers, None, cfg.cache_dir, "changesets", description="Downloading changesets"
+                urls,
+                "changeset",
+                _DOWNLOAD_WORKERS,
+                None,
+                cfg.cache_dir,
+                "changesets",
+                description="Downloading changesets",
             )
             _process_all(
                 urls,
@@ -799,7 +825,7 @@ def run(cfg: RunConfig) -> dict[str, Any]:
         _download_all(
             urls,
             "changefiles",
-            max_workers,
+            _DOWNLOAD_WORKERS,
             cookie,
             cfg.cache_dir,
             "changefiles",

{osmsg-1.2.1 → osmsg-1.2.5}/osmsg/replication.py

@@ -145,7 +145,7 @@ class ChangesetReplication:
     def timestamp_to_sequence(self, ts: datetime) -> int:
         cur_seq, last_run = self._state()
         wanted = int((ts - last_run).total_seconds() / 60) + cur_seq
-        return min(wanted, cur_seq)
+        return max(1, min(wanted, cur_seq))
 
     def sequence_to_timestamp(self, seq: int) -> datetime:
         txt = session.get(self.state_url(seq)).text

{osmsg-1.2.1 → osmsg-1.2.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "osmsg"
-version = "1.2.1"
+version = "1.2.5"
 description = "OpenStreetMap Stats Generator: Commandline"
 readme = "README.md"
 authors = [
@@ -41,6 +41,9 @@ repository = "https://github.com/osgeonepal/osmsg"
 [project.scripts]
 osmsg = "osmsg.cli:app"
 
+[project.gui-scripts]
+osmsg-gui = "osmsg.gui:launch"
+
 [build-system]
 requires = ["uv_build>=0.5.15,<0.9"]
 build-backend = "uv_build"

osmsg-1.2.1/osmsg/__version__.py

@@ -1 +0,0 @@
-__version__ = "1.2.1"