osmsg 1.2.2__tar.gz → 1.2.4__tar.gz

{osmsg-1.2.2 → osmsg-1.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: osmsg
-Version: 1.2.2
+Version: 1.2.4
 Summary: OpenStreetMap Stats Generator: Commandline
 Keywords: osm,stats,commandline,openstreetmap
 Author: Kshitij Raj Sharma
@@ -78,8 +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 double-click it to open the desktop app. Fill in the dates and options, click Run, and open the
-output folder. The CLI below is for macOS, Linux, and pip/uv users.
+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
 
@@ -207,7 +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
 

{osmsg-1.2.2 → osmsg-1.2.4}/README.md

@@ -46,8 +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 double-click it to open the desktop app. Fill in the dates and options, click Run, and open the
-output folder. The CLI below is for macOS, Linux, and pip/uv users.
+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
 
@@ -175,7 +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
 

osmsg-1.2.4/osmsg/__version__.py

@@ -0,0 +1 @@
+__version__ = "1.2.4"

{osmsg-1.2.2 → osmsg-1.2.4}/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-1.2.2 → osmsg-1.2.4}/osmsg/gui.py

@@ -7,14 +7,41 @@ 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:
@@ -89,6 +116,7 @@ class App:
         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")
@@ -112,31 +140,63 @@ class App:
             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=5, 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=5, column=0, sticky="w")
-        ttk.Checkbutton(frame, text="Daily summary", variable=self.vars["summary"]).grid(row=5, column=1, sticky="w")
+        ttk.Checkbutton(frame, text="All tags", variable=self.vars["all_tags"]).grid(row=6, column=0, sticky="w")
+        ttk.Checkbutton(frame, text="Daily summary", variable=self.vars["summary"]).grid(row=6, column=1, sticky="w")
 
         fmt_frame = ttk.LabelFrame(frame, text="Formats", padding=6)
-        fmt_frame.grid(row=6, column=0, columnspan=4, sticky="we", pady=6)
+        fmt_frame.grid(row=7, 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=7, column=0, columnspan=3, sticky="w")
-        ttk.Button(frame, text="Choose folder", command=self._choose_folder).grid(row=7, column=3, sticky="e")
+        self.out_label.grid(row=8, column=0, columnspan=3, sticky="w")
+        ttk.Button(frame, text="Choose folder", command=self._choose_folder).grid(row=8, column=3, sticky="e")
 
-        self.run_btn = ttk.Button(frame, text="Run", command=self._on_run)
-        self.run_btn.grid(row=8, column=0, pady=8, sticky="w")
+        self.run_btn = ttk.Button(frame, text="Compute", command=self._on_run)
+        self.run_btn.grid(row=9, 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=8, column=1, pady=8, sticky="w")
+        self.open_btn.grid(row=9, column=1, pady=8, sticky="w")
+        self.spinner = ttk.Progressbar(frame, mode="indeterminate", length=160)
+        self.spinner.grid(row=9, column=2, columnspan=2, pady=8, sticky="we")
 
         self.log = scrolledtext.ScrolledText(frame, width=70, height=14, state="disabled")
-        self.log.grid(row=9, column=0, columnspan=4, sticky="nsew")
+        self.log.grid(row=10, column=0, columnspan=4, sticky="nsew")
+
+        ttk.Button(frame, text="About", command=self._show_about).grid(row=11, column=0, pady=(6, 0), sticky="w")
+        ttk.Label(frame, text="A project of OSGeo Nepal").grid(row=11, 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:
@@ -155,8 +215,9 @@ class App:
         except OsmsgError as exc:
             self._append(f"\n{exc}\n")
             return
-        self.run_btn.config(state="disabled")
-        self._append(f"\nRunning into {self.out_dir} ...\n")
+        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:
@@ -182,7 +243,8 @@ class App:
                     self._append(payload)
                 else:
                     self._append(f"\n{payload}\n")
-                    self.run_btn.config(state="normal")
+                    self.spinner.stop()
+                    self.run_btn.config(state="normal", text="Compute")
         except queue.Empty:
             pass
         self.root.after(120, self._drain)

{osmsg-1.2.2 → osmsg-1.2.4}/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
 
@@ -539,6 +540,11 @@ def _processing_config(cfg: RunConfig, *, parquet_dir: Path, geom_wkt: str | Non
     }
 
 
+# Replication servers throttle many concurrent connections, so downloads stay polite regardless of
+# the worker count used for local parsing. Already-downloaded files are cached, so a rerun resumes.
+_DOWNLOAD_WORKERS = 4
+
+
 def _download_all(
     urls: list[str],
     mode: str,
@@ -548,12 +554,19 @@ def _download_all(
     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()
+    workers = min(max_workers, _DOWNLOAD_WORKERS)
+    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(
@@ -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)
 

{osmsg-1.2.2 → osmsg-1.2.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "osmsg"
-version = "1.2.2"
+version = "1.2.4"
 description = "OpenStreetMap Stats Generator: Commandline"
 readme = "README.md"
 authors = [

osmsg-1.2.2/osmsg/__version__.py

@@ -1 +0,0 @@
-__version__ = "1.2.2"